diff options
Diffstat (limited to 'arch/x86')
238 files changed, 7168 insertions, 4377 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dad7f85dcdea..b1d4b481fcdd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -61,6 +61,7 @@ config X86 select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT + select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 || (X86_32 && HIGHMEM) select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG @@ -125,6 +126,7 @@ config X86 select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG select DCACHE_WORD_ACCESS + select DYNAMIC_SIGFRAME select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) @@ -197,7 +199,7 @@ config X86 select HAVE_FAST_GUP select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_TRACER if X86_32 || (X86_64 && DYNAMIC_FTRACE) select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT @@ -610,9 +612,7 @@ config X86_INTEL_MID depends on X86_IO_APIC select I2C select DW_APB_TIMER - select APB_TIMER select INTEL_SCU_PCI - select MFD_INTEL_MSIC help Select to build a kernel capable of supporting Intel MID (Mobile Internet Device) platform systems which do not have the PCI legacy @@ -1001,6 +1001,17 @@ config NR_CPUS This is purely to save memory: each supported CPU adds about 8KB to the kernel image. +config SCHED_CLUSTER + bool "Cluster scheduler support" + depends on SMP + default y + help + Cluster scheduler support improves the CPU scheduler's decision + making when dealing with machines that have clusters of CPUs. + Cluster usually means a couple of CPUs which are placed closely + by sharing mid-level caches, last-level cache tags or internal + busses. + config SCHED_SMT def_bool y if SMP @@ -1256,7 +1267,8 @@ config TOSHIBA config I8K tristate "Dell i8k legacy laptop support" - select HWMON + depends on HWMON + depends on PROC_FS select SENSORS_DELL_SMM help This option enables legacy /proc/i8k userspace interface in hwmon @@ -1405,7 +1417,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 + depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6 select X86_PAE help Select this if you have a 32-bit processor and more than 4 @@ -1518,6 +1530,7 @@ config AMD_MEM_ENCRYPT select ARCH_HAS_FORCE_DMA_UNENCRYPTED select INSTRUCTION_DECODER select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS + select ARCH_HAS_CC_PLATFORM help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory @@ -1525,7 +1538,6 @@ config AMD_MEM_ENCRYPT config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT bool "Activate AMD Secure Memory Encryption (SME) by default" - default y depends on AMD_MEM_ENCRYPT help Say yes to have system memory encrypted by default if running on @@ -2389,6 +2401,22 @@ config MODIFY_LDT_SYSCALL Saying 'N' here may make sense for embedded or server kernels. +config STRICT_SIGALTSTACK_SIZE + bool "Enforce strict size checking for sigaltstack" + depends on DYNAMIC_SIGFRAME + help + For historical reasons MINSIGSTKSZ is a constant which became + already too small with AVX512 support. Add a mechanism to + enforce strict checking of the sigaltstack size against the + real size of the FPU frame. This option enables the check + by default. It can also be controlled via the kernel command + line option 'strict_sas_size' independent of this config + switch. Enabling it might break existing applications which + allocate a too small sigaltstack but 'work' because they + never get a signal delivered. + + Say 'N' unless you want to really enforce this check. + source "kernel/livepatch/Kconfig" endmenu @@ -2610,7 +2638,6 @@ config PCI_OLPC config PCI_XEN def_bool y depends on PCI && XEN - select SWIOTLB_XEN config MMCONF_FAM10H def_bool y @@ -2833,8 +2860,6 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 -source "drivers/firmware/Kconfig" - source "arch/x86/kvm/Kconfig" source "arch/x86/Kconfig.assembler" diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 814fe0d349b0..eefc434351db 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -508,3 +508,16 @@ config CPU_SUP_ZHAOXIN CPU might render the kernel unbootable. If unsure, say N. + +config CPU_SUP_VORTEX_32 + default y + bool "Support Vortex processors" if PROCESSOR_SELECT + depends on X86_32 + help + This enables detection, tunings and quirks for Vortex processors + + You need this enabled if you want your kernel to run on a + Vortex CPU. Disabling this option on other types of CPUs + makes the kernel a tiny bit smaller. + + If unsure, say N. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 7488cfbbd2f6..aab70413ae7a 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -299,7 +299,7 @@ define archhelp echo ' isoimage - Create a boot CD-ROM image (arch/x86/boot/image.iso)' echo ' bzdisk/fdimage*/hdimage/isoimage also accept:' echo ' FDARGS="..." arguments for the booted kernel' - echo ' FDINITRD=file initrd for the booted kernel' + echo ' FDINITRD=file initrd for the booted kernel' echo '' echo ' kvm_guest.config - Enable Kconfig items for running this kernel as a KVM guest' echo ' xen.config - Enable Kconfig items for running this kernel as a Xen guest' diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 67c3208b668a..411b268bc0a2 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -32,10 +32,6 @@ #include <generated/utsrelease.h> #include <asm/efi.h> -/* Macros used by the included decompressor code below. */ -#define STATIC -#include <linux/decompress/mm.h> - #define _SETUP #include <asm/setup.h> /* For COMMAND_LINE_SIZE */ #undef _SETUP diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 743f13ea25c1..a4339cb2d247 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -28,6 +28,9 @@ /* Macros used by the included decompressor code below. */ #define STATIC static +/* Define an externally visible malloc()/free(). */ +#define MALLOC_VISIBLE +#include <linux/decompress/mm.h> /* * Provide definitions of memzero and memmove as some of the decompressors will diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 31139256859f..16ed360b6692 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -14,6 +14,8 @@ #undef CONFIG_KASAN #undef CONFIG_KASAN_GENERIC +#define __NO_FORTIFY + /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 @@ -44,6 +46,8 @@ extern char _head[], _end[]; /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; +void *malloc(int size); +void free(void *where); extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 2a78746f5a4c..a1733319a22a 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "misc.h" #include <linux/efi.h> #include <asm/e820/types.h> #include <asm/processor.h> diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh index 0673fdfc1a11..c9299aeb7333 100644 --- a/arch/x86/boot/genimage.sh +++ b/arch/x86/boot/genimage.sh @@ -120,12 +120,13 @@ efiarch() { } # Get the combined sizes in bytes of the files given, counting sparse -# files as full length, and padding each file to a 4K block size +# files as full length, and padding each file to cluster size +cluster=16384 filesizes() { local t=0 local s for s in $(ls -lnL "$@" 2>/dev/null | awk '/^-/{ print $5; }'); do - t=$((t + ((s+4095)/4096)*4096)) + t=$((t + ((s+cluster-1)/cluster)*cluster)) done echo $t } @@ -230,14 +231,14 @@ genhdimage() { ptype='-T 0xef' # EFI system partition, no GPT fi sizes=$(filesizes "$FBZIMAGE" "${FDINITRDS[@]}" "$efishell") - # Allow 1% + 1 MiB for filesystem and partition table overhead, - # syslinux, and config files + # Allow 1% + 2 MiB for filesystem and partition table overhead, + # syslinux, and config files; this is probably excessive... megs=$(((sizes + sizes/100 + 2*1024*1024 - 1)/(1024*1024))) $dd if=/dev/zero of="$FIMAGE" bs=$((1024*1024)) count=$megs 2>/dev/null - mpartition -I -c -s 32 -h 64 -t $megs $ptype -b 512 -a h: + mpartition -I -c -s 32 -h 64 $ptype -b 64 -a p: $dd if="$mbr" of="$FIMAGE" bs=440 count=1 conv=notrunc 2>/dev/null - mformat -v 'LINUX_BOOT' -s 32 -h 64 -t $megs h: - syslinux --offset $((512*512)) "$FIMAGE" + mformat -v 'LINUX_BOOT' -s 32 -h 64 -c $((cluster/512)) -t $megs h: + syslinux --offset $((64*512)) "$FIMAGE" do_mcopy h: } diff --git a/arch/x86/boot/mtools.conf.in b/arch/x86/boot/mtools.conf.in index 9e2662d01364..174c60508766 100644 --- a/arch/x86/boot/mtools.conf.in +++ b/arch/x86/boot/mtools.conf.in @@ -14,7 +14,8 @@ drive v: drive w: file="@OBJ@/fdimage" cylinders=80 heads=2 sectors=36 filter -# Hard disk +# Hard disk (h: for the filesystem, p: for format - old mtools bug?) drive h: + file="@OBJ@/hdimage" offset=32768 mformat_only +drive p: file="@OBJ@/hdimage" partition=1 mformat_only - diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 0fc961bef299..e09f4672dd38 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -866,7 +866,7 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt) req = &subreq; err = skcipher_walk_virt(&walk, req, false); - if (err) + if (!walk.nbytes) return err; } else { tail = 0; diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index fa2c3f50aecb..1cc72b4804fa 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -78,7 +78,7 @@ vpxor tmp0, x, x; -.section .rodata.cst164, "aM", @progbits, 164 +.section .rodata.cst16, "aM", @progbits, 16 .align 16 /* @@ -133,6 +133,10 @@ .L0f0f0f0f: .long 0x0f0f0f0f +/* 12 bytes, only for padding */ +.Lpadding_deadbeef: + .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef + .text .align 16 @@ -367,10 +371,11 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8) * %rdx: src (1..8 blocks) * %rcx: num blocks (1..8) */ - FRAME_BEGIN - cmpq $5, %rcx; jb sm4_aesni_avx_crypt4; + + FRAME_BEGIN + vmovdqu (0 * 16)(%rdx), RA0; vmovdqu (1 * 16)(%rdx), RA1; vmovdqu (2 * 16)(%rdx), RA2; diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S index d2ffd7f76ee2..9c5d3f3ad45a 100644 --- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S @@ -93,7 +93,7 @@ vpxor tmp0, x, x; -.section .rodata.cst164, "aM", @progbits, 164 +.section .rodata.cst16, "aM", @progbits, 16 .align 16 /* @@ -148,6 +148,10 @@ .L0f0f0f0f: .long 0x0f0f0f0f +/* 12 bytes, only for padding */ +.Lpadding_deadbeef: + .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef + .text .align 16 diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 960a021d543e..7e25543693de 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -453,3 +453,4 @@ 446 i386 landlock_restrict_self sys_landlock_restrict_self 447 i386 memfd_secret sys_memfd_secret 448 i386 process_mrelease sys_process_mrelease +449 i386 futex_waitv sys_futex_waitv diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 18b5500ea8bf..fe8f8dd157b4 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -370,6 +370,7 @@ 446 common landlock_restrict_self sys_landlock_restrict_self 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..38b2c779146f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -66,6 +66,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable); +DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign); + DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); @@ -1215,6 +1217,8 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; + static_call_cond(x86_pmu_assign)(event, idx); + switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: case INTEL_PMC_IDX_FIXED_VLBR: @@ -2005,6 +2009,8 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_enable, x86_pmu.enable); static_call_update(x86_pmu_disable, x86_pmu.disable); + static_call_update(x86_pmu_assign, x86_pmu.assign); + static_call_update(x86_pmu_add, x86_pmu.add); static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); @@ -2465,6 +2471,7 @@ static int x86_pmu_event_init(struct perf_event *event) if (err) { if (event->destroy) event->destroy(event); + event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 6320d2cfd9d3..974e917e65b2 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -209,6 +209,12 @@ static void bts_update(struct bts_ctx *bts) } else { local_set(&buf->data_size, head); } + + /* + * Since BTS is coherent, just add compiler barrier to ensure + * BTS updating is ordered against bts::handle::event. + */ + barrier(); } static int diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..603964408d2d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -243,7 +243,8 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { static struct event_constraint intel_icl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ - FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* old INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ @@ -263,6 +264,7 @@ static struct event_constraint intel_icl_event_constraints[] = { INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT(0xef, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), EVENT_CONSTRAINT_END }; @@ -287,7 +289,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { static struct event_constraint intel_spr_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ - FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ @@ -2143,19 +2145,19 @@ static __initconst const u64 knl_hw_cache_extra_regs * However, there are some cases which may change PEBS status, e.g. PMI * throttle. The PEBS_ENABLE should be updated where the status changes. */ -static void __intel_pmu_disable_all(void) +static __always_inline void __intel_pmu_disable_all(bool bts) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); - if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); } -static void intel_pmu_disable_all(void) +static __always_inline void intel_pmu_disable_all(void) { - __intel_pmu_disable_all(); + __intel_pmu_disable_all(true); intel_pmu_pebs_disable_all(); intel_pmu_lbr_disable_all(); } @@ -2186,6 +2188,49 @@ static void intel_pmu_enable_all(int added) __intel_pmu_enable_all(added, false); } +static noinline int +__intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, + unsigned int cnt, unsigned long flags) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + intel_pmu_lbr_read(); + cnt = min_t(unsigned int, cnt, x86_pmu.lbr_nr); + + memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt); + intel_pmu_enable_all(0); + local_irq_restore(flags); + return cnt; +} + +static int +intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt) +{ + unsigned long flags; + + /* must not have branches... */ + local_irq_save(flags); + __intel_pmu_disable_all(false); /* we don't care about BTS */ + __intel_pmu_pebs_disable_all(); + __intel_pmu_lbr_disable(); + /* ... until here */ + return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); +} + +static int +intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned int cnt) +{ + unsigned long flags; + + /* must not have branches... */ + local_irq_save(flags); + __intel_pmu_disable_all(false); /* we don't care about BTS */ + __intel_pmu_pebs_disable_all(); + __intel_pmu_arch_lbr_disable(); + /* ... until here */ + return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); +} + /* * Workaround for: * Intel Errata AAK100 (model 26) @@ -2402,6 +2447,12 @@ static void intel_pmu_disable_event(struct perf_event *event) intel_pmu_pebs_disable(event); } +static void intel_pmu_assign_event(struct perf_event *event, int idx) +{ + if (is_pebs_pt(event)) + perf_report_aux_output_id(event, idx); +} + static void intel_pmu_del_event(struct perf_event *event) { if (needs_branch_stack(event)) @@ -2929,7 +2980,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) apic_write(APIC_LVTPC, APIC_DM_NMI); intel_bts_disable_local(); cpuc->enabled = 0; - __intel_pmu_disable_all(); + __intel_pmu_disable_all(true); handled = intel_pmu_drain_bts_buffer(); handled += intel_bts_interrupt(); status = intel_pmu_get_status(); @@ -4494,8 +4545,16 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value) return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; } +static void intel_aux_output_init(void) +{ + /* Refer also intel_pmu_aux_output_match() */ + if (x86_pmu.intel_cap.pebs_output_pt_available) + x86_pmu.assign = intel_pmu_assign_event; +} + static int intel_pmu_aux_output_match(struct perf_event *event) { + /* intel_pmu_assign_event() is needed, refer intel_aux_output_init() */ if (!x86_pmu.intel_cap.pebs_output_pt_available) return 0; @@ -6283,9 +6342,21 @@ __init int intel_pmu_init(void) x86_pmu.lbr_nr = 0; } - if (x86_pmu.lbr_nr) + if (x86_pmu.lbr_nr) { pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); + /* only support branch_stack snapshot for perfmon >= v2 */ + if (x86_pmu.disable_all == intel_pmu_disable_all) { + if (boot_cpu_has(X86_FEATURE_ARCH_LBR)) { + static_call_update(perf_snapshot_branch_stack, + intel_pmu_snapshot_arch_branch_stack); + } else { + static_call_update(perf_snapshot_branch_stack, + intel_pmu_snapshot_branch_stack); + } + } + } + intel_pmu_check_extra_regs(x86_pmu.extra_regs); /* Support full width counters using alternative MSR range */ @@ -6301,6 +6372,8 @@ __init int intel_pmu_init(void) if (is_hybrid()) intel_pmu_check_hybrid_pmus((u64)fixed_mask); + intel_aux_output_init(); + return 0; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8647713276a7..2e215369df4a 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -923,7 +923,8 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { }; struct event_constraint intel_icl_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x100000000ULL), /* old INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ @@ -943,7 +944,7 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { }; struct event_constraint intel_spr_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), @@ -1301,7 +1302,7 @@ void intel_pmu_pebs_disable_all(void) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); + __intel_pmu_pebs_disable_all(); } static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 9e6d6eaeb4cb..6b72e9b55c69 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -228,20 +228,6 @@ static void __intel_pmu_lbr_enable(bool pmi) wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN); } -static void __intel_pmu_lbr_disable(void) -{ - u64 debugctl; - - if (static_cpu_has(X86_FEATURE_ARCH_LBR)) { - wrmsrl(MSR_ARCH_LBR_CTL, 0); - return; - } - - rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); - debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); -} - void intel_pmu_lbr_reset_32(void) { int i; @@ -779,8 +765,12 @@ void intel_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (cpuc->lbr_users && !vlbr_exclude_host()) + if (cpuc->lbr_users && !vlbr_exclude_host()) { + if (static_cpu_has(X86_FEATURE_ARCH_LBR)) + return __intel_pmu_arch_lbr_disable(); + __intel_pmu_lbr_disable(); + } } void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index 7280c8a3c831..6d735611c281 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -30,7 +30,7 @@ #define uncore_discovery_invalid_unit(unit) \ - (!unit.table1 || !unit.ctl || !unit.table3 || \ + (!unit.table1 || !unit.ctl || \ unit.table1 == -1ULL || unit.ctl == -1ULL || \ unit.table3 == -1ULL) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 5ddc0f30db6f..eb2c6cea9d0d 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -452,7 +452,7 @@ #define ICX_M3UPI_PCI_PMON_BOX_CTL 0xa0 /* ICX IMC */ -#define ICX_NUMBER_IMC_CHN 2 +#define ICX_NUMBER_IMC_CHN 3 #define ICX_IMC_MEM_STRIDE 0x4 /* SPR */ @@ -5076,8 +5076,10 @@ static struct event_constraint icx_uncore_iio_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x02, 0x3), UNCORE_EVENT_CONSTRAINT(0x03, 0x3), UNCORE_EVENT_CONSTRAINT(0x83, 0x3), + UNCORE_EVENT_CONSTRAINT(0x88, 0xc), UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), UNCORE_EVENT_CONSTRAINT(0xc5, 0xc), + UNCORE_EVENT_CONSTRAINT(0xd5, 0xc), EVENT_CONSTRAINT_END }; @@ -5463,7 +5465,7 @@ static struct intel_uncore_ops icx_uncore_mmio_ops = { static struct intel_uncore_type icx_uncore_imc = { .name = "imc", .num_counters = 4, - .num_boxes = 8, + .num_boxes = 12, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, @@ -5647,6 +5649,7 @@ static struct intel_uncore_type spr_uncore_chabox = { .event_mask = SPR_CHA_PMON_EVENT_MASK, .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, .num_shared_regs = 1, + .constraints = skx_uncore_chabox_constraints, .ops = &spr_uncore_chabox_ops, .format_group = &spr_uncore_chabox_format_group, .attr_update = uncore_alias_groups, @@ -5658,6 +5661,7 @@ static struct intel_uncore_type spr_uncore_iio = { .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT, .format_group = &snr_uncore_iio_format_group, .attr_update = uncore_alias_groups, + .constraints = icx_uncore_iio_constraints, }; static struct attribute *spr_uncore_raw_formats_attr[] = { @@ -5686,9 +5690,16 @@ static struct intel_uncore_type spr_uncore_irp = { }; +static struct event_constraint spr_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + EVENT_CONSTRAINT_END +}; + static struct intel_uncore_type spr_uncore_m2pcie = { SPR_UNCORE_COMMON_FORMAT(), .name = "m2pcie", + .constraints = spr_uncore_m2pcie_constraints, }; static struct intel_uncore_type spr_uncore_pcu = { @@ -5765,6 +5776,7 @@ static struct intel_uncore_type spr_uncore_upi = { static struct intel_uncore_type spr_uncore_m3upi = { SPR_UNCORE_PCI_COMMON_FORMAT(), .name = "m3upi", + .constraints = icx_uncore_m3upi_constraints, }; static struct intel_uncore_type spr_uncore_mdf = { diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index c853b28efa33..96c775abe31f 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -68,6 +68,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_D: case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: + case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e3ac05c97b5e..5480db242083 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -14,6 +14,7 @@ #include <linux/perf_event.h> +#include <asm/fpu/xstate.h> #include <asm/intel_ds.h> #include <asm/cpu.h> @@ -726,6 +727,7 @@ struct x86_pmu { void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + void (*assign)(struct perf_event *event, int idx); void (*add)(struct perf_event *); void (*del)(struct perf_event *); void (*read)(struct perf_event *event); @@ -1240,6 +1242,25 @@ static inline bool intel_pmu_has_bts(struct perf_event *event) return intel_pmu_has_bts_period(event, hwc->sample_period); } +static __always_inline void __intel_pmu_pebs_disable_all(void) +{ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); +} + +static __always_inline void __intel_pmu_arch_lbr_disable(void) +{ + wrmsrl(MSR_ARCH_LBR_CTL, 0); +} + +static __always_inline void __intel_pmu_lbr_disable(void) +{ + u64 debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +} + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 48e2c51464e8..5d2de10809ae 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y := hv_init.o mmu.o nested.o irqdomain.o +obj-y := hv_init.o mmu.o nested.o irqdomain.o ivm.o obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o ifdef CONFIG_X86_64 diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 32a1ad356c18..db2d92fb44da 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -122,17 +122,27 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, ipi_arg->reserved = 0; ipi_arg->vp_set.valid_bank_mask = 0; - if (!cpumask_equal(mask, cpu_present_mask)) { + /* + * Use HV_GENERIC_SET_ALL and avoid converting cpumask to VP_SET + * when the IPI is sent to all currently present CPUs. + */ + if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; if (exclude_self) nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask); else nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); - } - if (nr_bank < 0) - goto ipi_mask_ex_done; - if (!nr_bank) + + /* + * 'nr_bank <= 0' means some CPUs in cpumask can't be + * represented in VP_SET. Return an error and fall back to + * native (architectural) method of sending IPIs. + */ + if (nr_bank <= 0) + goto ipi_mask_ex_done; + } else { ipi_arg->vp_set.format = HV_GENERIC_SET_ALL; + } status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank, ipi_arg, NULL); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 708a2712a516..24f4a06ac46a 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -36,12 +36,42 @@ EXPORT_SYMBOL_GPL(hv_current_partition_id); void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); +union hv_ghcb __percpu **hv_ghcb_pg; + /* Storage to save the hypercall page temporarily for hibernation */ static void *hv_hypercall_pg_saved; struct hv_vp_assist_page **hv_vp_assist_page; EXPORT_SYMBOL_GPL(hv_vp_assist_page); +static int hyperv_init_ghcb(void) +{ + u64 ghcb_gpa; + void *ghcb_va; + void **ghcb_base; + + if (!hv_isolation_type_snp()) + return 0; + + if (!hv_ghcb_pg) + return -EINVAL; + + /* + * GHCB page is allocated by paravisor. The address + * returned by MSR_AMD64_SEV_ES_GHCB is above shared + * memory boundary and map it here. + */ + rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa); + ghcb_va = memremap(ghcb_gpa, HV_HYP_PAGE_SIZE, MEMREMAP_WB); + if (!ghcb_va) + return -ENOMEM; + + ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg); + *ghcb_base = ghcb_va; + + return 0; +} + static int hv_cpu_init(unsigned int cpu) { union hv_vp_assist_msr_contents msr = { 0 }; @@ -85,7 +115,7 @@ static int hv_cpu_init(unsigned int cpu) } } - return 0; + return hyperv_init_ghcb(); } static void (*hv_reenlightenment_cb)(void); @@ -139,7 +169,6 @@ void set_hv_tscchange_cb(void (*cb)(void)) struct hv_reenlightenment_control re_ctrl = { .vector = HYPERV_REENLIGHTENMENT_VECTOR, .enabled = 1, - .target_vp = hv_vp_index[smp_processor_id()] }; struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1}; @@ -153,8 +182,12 @@ void set_hv_tscchange_cb(void (*cb)(void)) /* Make sure callback is registered before we write to MSRs */ wmb(); + re_ctrl.target_vp = hv_vp_index[get_cpu()]; + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl)); + + put_cpu(); } EXPORT_SYMBOL_GPL(set_hv_tscchange_cb); @@ -177,6 +210,14 @@ static int hv_cpu_die(unsigned int cpu) { struct hv_reenlightenment_control re_ctrl; unsigned int new_cpu; + void **ghcb_va; + + if (hv_ghcb_pg) { + ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg); + if (*ghcb_va) + memunmap(*ghcb_va); + *ghcb_va = NULL; + } hv_common_cpu_die(cpu); @@ -366,10 +407,16 @@ void __init hyperv_init(void) goto common_free; } + if (hv_isolation_type_snp()) { + hv_ghcb_pg = alloc_percpu(union hv_ghcb *); + if (!hv_ghcb_pg) + goto free_vp_assist_page; + } + cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online", hv_cpu_init, hv_cpu_die); if (cpuhp < 0) - goto free_vp_assist_page; + goto free_ghcb_page; /* * Setup the hypercall page and enable hypercalls. @@ -379,14 +426,15 @@ void __init hyperv_init(void) guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); + /* Hyper-V requires to write guest os id via ghcb in SNP IVM. */ + hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id); + hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); - if (hv_hypercall_pg == NULL) { - wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); - goto remove_cpuhp_state; - } + if (hv_hypercall_pg == NULL) + goto clean_guest_os_id; rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); hypercall_msr.enable = 1; @@ -456,8 +504,12 @@ void __init hyperv_init(void) hv_query_ext_cap(0); return; -remove_cpuhp_state: +clean_guest_os_id: + wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); + hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0); cpuhp_remove_state(cpuhp); +free_ghcb_page: + free_percpu(hv_ghcb_pg); free_vp_assist_page: kfree(hv_vp_assist_page); hv_vp_assist_page = NULL; @@ -476,6 +528,7 @@ void hyperv_cleanup(void) /* Reset our OS id */ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); + hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0); /* * Reset hypercall page reference before reset the page, @@ -546,16 +599,3 @@ bool hv_is_hyperv_initialized(void) return hypercall_msr.enable; } EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); - -enum hv_isolation_type hv_get_isolation_type(void) -{ - if (!(ms_hyperv.priv_high & HV_ISOLATION)) - return HV_ISOLATION_TYPE_NONE; - return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b); -} -EXPORT_SYMBOL_GPL(hv_get_isolation_type); - -bool hv_is_isolation_supported(void) -{ - return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE; -} diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c new file mode 100644 index 000000000000..69c7a57f3307 --- /dev/null +++ b/arch/x86/hyperv/ivm.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hyper-V Isolation VM interface with paravisor and hypervisor + * + * Author: + * Tianyu Lan <Tianyu.Lan@microsoft.com> + */ + +#include <linux/bitfield.h> +#include <linux/hyperv.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <asm/svm.h> +#include <asm/sev.h> +#include <asm/io.h> +#include <asm/mshyperv.h> +#include <asm/hypervisor.h> + +#ifdef CONFIG_AMD_MEM_ENCRYPT + +#define GHCB_USAGE_HYPERV_CALL 1 + +union hv_ghcb { + struct ghcb ghcb; + struct { + u64 hypercalldata[509]; + u64 outputgpa; + union { + union { + struct { + u32 callcode : 16; + u32 isfast : 1; + u32 reserved1 : 14; + u32 isnested : 1; + u32 countofelements : 12; + u32 reserved2 : 4; + u32 repstartindex : 12; + u32 reserved3 : 4; + }; + u64 asuint64; + } hypercallinput; + union { + struct { + u16 callstatus; + u16 reserved1; + u32 elementsprocessed : 12; + u32 reserved2 : 20; + }; + u64 asunit64; + } hypercalloutput; + }; + u64 reserved2; + } hypercall; +} __packed __aligned(HV_HYP_PAGE_SIZE); + +u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size) +{ + union hv_ghcb *hv_ghcb; + void **ghcb_base; + unsigned long flags; + u64 status; + + if (!hv_ghcb_pg) + return -EFAULT; + + WARN_ON(in_nmi()); + + local_irq_save(flags); + ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg); + hv_ghcb = (union hv_ghcb *)*ghcb_base; + if (!hv_ghcb) { + local_irq_restore(flags); + return -EFAULT; + } + + hv_ghcb->ghcb.protocol_version = GHCB_PROTOCOL_MAX; + hv_ghcb->ghcb.ghcb_usage = GHCB_USAGE_HYPERV_CALL; + + hv_ghcb->hypercall.outputgpa = (u64)output; + hv_ghcb->hypercall.hypercallinput.asuint64 = 0; + hv_ghcb->hypercall.hypercallinput.callcode = control; + + if (input_size) + memcpy(hv_ghcb->hypercall.hypercalldata, input, input_size); + + VMGEXIT(); + + hv_ghcb->ghcb.ghcb_usage = 0xffffffff; + memset(hv_ghcb->ghcb.save.valid_bitmap, 0, + sizeof(hv_ghcb->ghcb.save.valid_bitmap)); + + status = hv_ghcb->hypercall.hypercalloutput.callstatus; + + local_irq_restore(flags); + + return status; +} + +void hv_ghcb_msr_write(u64 msr, u64 value) +{ + union hv_ghcb *hv_ghcb; + void **ghcb_base; + unsigned long flags; + struct es_em_ctxt ctxt; + + if (!hv_ghcb_pg) + return; + + WARN_ON(in_nmi()); + + local_irq_save(flags); + ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg); + hv_ghcb = (union hv_ghcb *)*ghcb_base; + if (!hv_ghcb) { + local_irq_restore(flags); + return; + } + + ghcb_set_rcx(&hv_ghcb->ghcb, msr); + ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value)); + ghcb_set_rdx(&hv_ghcb->ghcb, upper_32_bits(value)); + + if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt, + SVM_EXIT_MSR, 1, 0)) + pr_warn("Fail to write msr via ghcb %llx.\n", msr); + + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(hv_ghcb_msr_write); + +void hv_ghcb_msr_read(u64 msr, u64 *value) +{ + union hv_ghcb *hv_ghcb; + void **ghcb_base; + unsigned long flags; + struct es_em_ctxt ctxt; + + /* Check size of union hv_ghcb here. */ + BUILD_BUG_ON(sizeof(union hv_ghcb) != HV_HYP_PAGE_SIZE); + + if (!hv_ghcb_pg) + return; + + WARN_ON(in_nmi()); + + local_irq_save(flags); + ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg); + hv_ghcb = (union hv_ghcb *)*ghcb_base; + if (!hv_ghcb) { + local_irq_restore(flags); + return; + } + + ghcb_set_rcx(&hv_ghcb->ghcb, msr); + if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt, + SVM_EXIT_MSR, 0, 0)) + pr_warn("Fail to read msr via ghcb %llx.\n", msr); + else + *value = (u64)lower_32_bits(hv_ghcb->ghcb.save.rax) + | ((u64)lower_32_bits(hv_ghcb->ghcb.save.rdx) << 32); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(hv_ghcb_msr_read); +#endif + +enum hv_isolation_type hv_get_isolation_type(void) +{ + if (!(ms_hyperv.priv_high & HV_ISOLATION)) + return HV_ISOLATION_TYPE_NONE; + return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b); +} +EXPORT_SYMBOL_GPL(hv_get_isolation_type); + +/* + * hv_is_isolation_supported - Check system runs in the Hyper-V + * isolation VM. + */ +bool hv_is_isolation_supported(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return false; + + if (!hypervisor_is_type(X86_HYPER_MS_HYPERV)) + return false; + + return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE; +} + +DEFINE_STATIC_KEY_FALSE(isolation_type_snp); + +/* + * hv_isolation_type_snp - Check system runs in the AMD SEV-SNP based + * isolation VM. + */ +bool hv_isolation_type_snp(void) +{ + return static_branch_unlikely(&isolation_type_snp); +} + +/* + * hv_mark_gpa_visibility - Set pages visible to host via hvcall. + * + * In Isolation VM, all guest memory is encrypted from host and guest + * needs to set memory visible to host via hvcall before sharing memory + * with host. + */ +static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], + enum hv_mem_host_visibility visibility) +{ + struct hv_gpa_range_for_visibility **input_pcpu, *input; + u16 pages_processed; + u64 hv_status; + unsigned long flags; + + /* no-op if partition isolation is not enabled */ + if (!hv_is_isolation_supported()) + return 0; + + if (count > HV_MAX_MODIFY_GPA_REP_COUNT) { + pr_err("Hyper-V: GPA count:%d exceeds supported:%lu\n", count, + HV_MAX_MODIFY_GPA_REP_COUNT); + return -EINVAL; + } + + local_irq_save(flags); + input_pcpu = (struct hv_gpa_range_for_visibility **) + this_cpu_ptr(hyperv_pcpu_input_arg); + input = *input_pcpu; + if (unlikely(!input)) { + local_irq_restore(flags); + return -EINVAL; + } + + input->partition_id = HV_PARTITION_ID_SELF; + input->host_visibility = visibility; + input->reserved0 = 0; + input->reserved1 = 0; + memcpy((void *)input->gpa_page_list, pfn, count * sizeof(*pfn)); + hv_status = hv_do_rep_hypercall( + HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY, count, + 0, input, &pages_processed); + local_irq_restore(flags); + + if (hv_result_success(hv_status)) + return 0; + else + return -EFAULT; +} + +/* + * hv_set_mem_host_visibility - Set specified memory visible to host. + * + * In Isolation VM, all guest memory is encrypted from host and guest + * needs to set memory visible to host via hvcall before sharing memory + * with host. This function works as wrap of hv_mark_gpa_visibility() + * with memory base and size. + */ +int hv_set_mem_host_visibility(unsigned long kbuffer, int pagecount, bool visible) +{ + enum hv_mem_host_visibility visibility = visible ? + VMBUS_PAGE_VISIBLE_READ_WRITE : VMBUS_PAGE_NOT_VISIBLE; + u64 *pfn_array; + int ret = 0; + int i, pfn; + + if (!hv_is_isolation_supported() || !hv_hypercall_pg) + return 0; + + pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); + if (!pfn_array) + return -ENOMEM; + + for (i = 0, pfn = 0; i < pagecount; i++) { + pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE); + pfn++; + + if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) { + ret = hv_mark_gpa_visibility(pfn, pfn_array, + visibility); + if (ret) + goto err_free_pfn_array; + pfn = 0; + } + } + + err_free_pfn_array: + kfree(pfn_array); + return ret; +} diff --git a/arch/x86/ia32/audit.c b/arch/x86/ia32/audit.c index 6efe6cb3768a..59e19549e759 100644 --- a/arch/x86/ia32/audit.c +++ b/arch/x86/ia32/audit.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/audit_arch.h> #include <asm/unistd_32.h> #include <asm/audit.h> @@ -31,15 +32,17 @@ int ia32_classify_syscall(unsigned syscall) { switch (syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: case __NR_execveat: - return 5; + return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 5e3d9b7fd5fb..c9c3859322fa 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -24,7 +24,6 @@ #include <linux/syscalls.h> #include <asm/ucontext.h> #include <linux/uaccess.h> -#include <asm/fpu/internal.h> #include <asm/fpu/signal.h> #include <asm/ptrace.h> #include <asm/ia32_unistd.h> @@ -57,8 +56,8 @@ static inline void reload_segments(struct sigcontext_32 *sc) /* * Do a signal return; undo the signal stack. */ -static int ia32_restore_sigcontext(struct pt_regs *regs, - struct sigcontext_32 __user *usc) +static bool ia32_restore_sigcontext(struct pt_regs *regs, + struct sigcontext_32 __user *usc) { struct sigcontext_32 sc; @@ -66,7 +65,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, current->restart_block.fn = do_no_restart_syscall; if (unlikely(copy_from_user(&sc, usc, sizeof(sc)))) - return -EFAULT; + return false; /* Get only the ia32 registers. */ regs->bx = sc.bx; @@ -111,7 +110,7 @@ COMPAT_SYSCALL_DEFINE0(sigreturn) set_current_blocked(&set); - if (ia32_restore_sigcontext(regs, &frame->sc)) + if (!ia32_restore_sigcontext(regs, &frame->sc)) goto badframe; return regs->ax; @@ -135,7 +134,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn) set_current_blocked(&set); - if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext)) + if (!ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; if (compat_restore_altstack(&frame->uc.uc_stack)) @@ -220,8 +219,8 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); *fpstate = (struct _fpstate_32 __user *) sp; - if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, - math_size) < 0) + if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, + math_size)) return (void __user *) -1L; sp -= frame_size; diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h index 1b07fb102c4e..07949102a08d 100644 --- a/arch/x86/include/asm/GEN-for-each-reg.h +++ b/arch/x86/include/asm/GEN-for-each-reg.h @@ -1,11 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * These are in machine order; things rely on that. + */ #ifdef CONFIG_64BIT GEN(rax) -GEN(rbx) GEN(rcx) GEN(rdx) +GEN(rbx) +GEN(rsp) +GEN(rbp) GEN(rsi) GEN(rdi) -GEN(rbp) GEN(r8) GEN(r9) GEN(r10) @@ -16,10 +21,11 @@ GEN(r14) GEN(r15) #else GEN(eax) -GEN(ebx) GEN(ecx) GEN(edx) +GEN(ebx) +GEN(esp) +GEN(ebp) GEN(esi) GEN(edi) -GEN(ebp) #endif diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index a3c2315aca12..58eee6402832 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -75,6 +75,7 @@ extern int alternatives_patched; extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); +extern void apply_retpolines(s32 *start, s32 *end); struct module; diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 4cb726c71ed8..8f80de627c60 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -17,21 +17,3 @@ extern void cmpxchg8b_emu(void); #endif -#ifdef CONFIG_RETPOLINE - -#undef GEN -#define GEN(reg) \ - extern asmlinkage void __x86_indirect_thunk_ ## reg (void); -#include <asm/GEN-for-each-reg.h> - -#undef GEN -#define GEN(reg) \ - extern asmlinkage void __x86_indirect_alt_call_ ## reg (void); -#include <asm/GEN-for-each-reg.h> - -#undef GEN -#define GEN(reg) \ - extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void); -#include <asm/GEN-for-each-reg.h> - -#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 3ad3da9a7d97..3a168483bc8e 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -6,11 +6,13 @@ # define __ASM_FORM(x, ...) x,## __VA_ARGS__ # define __ASM_FORM_RAW(x, ...) x,## __VA_ARGS__ # define __ASM_FORM_COMMA(x, ...) x,## __VA_ARGS__, +# define __ASM_REGPFX % #else #include <linux/stringify.h> # define __ASM_FORM(x, ...) " " __stringify(x,##__VA_ARGS__) " " # define __ASM_FORM_RAW(x, ...) __stringify(x,##__VA_ARGS__) # define __ASM_FORM_COMMA(x, ...) " " __stringify(x,##__VA_ARGS__) "," +# define __ASM_REGPFX %% #endif #define _ASM_BYTES(x, ...) __ASM_FORM(.byte x,##__VA_ARGS__ ;) @@ -49,6 +51,9 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +/* Adds a (%rip) suffix on 64 bits only; for immediate memory references */ +#define _ASM_RIP(x) __ASM_SEL_RAW(x, x (__ASM_REGPFX rip)) + #ifndef __x86_64__ /* 32 bit */ @@ -122,28 +127,19 @@ #ifdef __KERNEL__ +# include <asm/extable_fixup_types.h> + /* Exception table entry */ #ifdef __ASSEMBLY__ -# define _ASM_EXTABLE_HANDLE(from, to, handler) \ + +# define _ASM_EXTABLE_TYPE(from, to, type) \ .pushsection "__ex_table","a" ; \ .balign 4 ; \ .long (from) - . ; \ .long (to) - . ; \ - .long (handler) - . ; \ + .long type ; \ .popsection -# define _ASM_EXTABLE(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) - -# define _ASM_EXTABLE_UA(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess) - -# define _ASM_EXTABLE_CPY(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_copy) - -# define _ASM_EXTABLE_FAULT(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) - # ifdef CONFIG_KPROBES # define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ @@ -155,27 +151,15 @@ # endif #else /* ! __ASSEMBLY__ */ -# define _EXPAND_EXTABLE_HANDLE(x) #x -# define _ASM_EXTABLE_HANDLE(from, to, handler) \ + +# define _ASM_EXTABLE_TYPE(from, to, type) \ " .pushsection \"__ex_table\",\"a\"\n" \ " .balign 4\n" \ " .long (" #from ") - .\n" \ " .long (" #to ") - .\n" \ - " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \ + " .long " __stringify(type) " \n" \ " .popsection\n" -# define _ASM_EXTABLE(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) - -# define _ASM_EXTABLE_UA(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess) - -# define _ASM_EXTABLE_CPY(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_copy) - -# define _ASM_EXTABLE_FAULT(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) - /* For C file, we already have NOKPROBE_SYMBOL macro */ /* @@ -188,6 +172,17 @@ register unsigned long current_stack_pointer asm(_ASM_SP); #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) #endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ +#define _ASM_EXTABLE(from, to) \ + _ASM_EXTABLE_TYPE(from, to, EX_TYPE_DEFAULT) +#define _ASM_EXTABLE_UA(from, to) \ + _ASM_EXTABLE_TYPE(from, to, EX_TYPE_UACCESS) + +#define _ASM_EXTABLE_CPY(from, to) \ + _ASM_EXTABLE_TYPE(from, to, EX_TYPE_COPY) + +#define _ASM_EXTABLE_FAULT(from, to) \ + _ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT) + +#endif /* __KERNEL__ */ #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 3d52b094850a..dd5ea1bdf04c 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -10,6 +10,12 @@ #ifdef CONFIG_X86_64 +#ifdef CONFIG_AMD_MEM_ENCRYPT +#define VC_EXCEPTION_STKSZ EXCEPTION_STKSZ +#else +#define VC_EXCEPTION_STKSZ 0 +#endif + /* Macro to enforce the same ordering and stack sizes */ #define ESTACKS_MEMBERS(guardsize, optional_stack_size) \ char DF_stack_guard[guardsize]; \ @@ -28,7 +34,7 @@ /* The exception stacks' physical storage. No guard pages required */ struct exception_stacks { - ESTACKS_MEMBERS(0, 0) + ESTACKS_MEMBERS(0, VC_EXCEPTION_STKSZ) }; /* The effective cpu entry area mapping with guard pages. */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 16a51e7288d5..1261842d006c 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -173,20 +173,25 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); * means that the boot_cpu_has() variant is already fast enough for the * majority of cases and you should stick to using it as it is generally * only two instructions: a RIP-relative MOV and a TEST. + * + * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know + * that this is only used on a fallback path and will sometimes cause + * it to manifest the address of boot_cpu_data in a register, fouling + * the mainline (post-initialization) code. */ static __always_inline bool _static_cpu_has(u16 bit) { asm_volatile_goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") - ".section .altinstr_aux,\"ax\"\n" + ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" - " testb %[bitnum],%[cap_byte]\n" + " testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n" " jnz %l[t_yes]\n" " jmp %l[t_no]\n" - ".previous\n" + ".popsection\n" : : [feature] "i" (bit), [bitnum] "i" (1 << (bit & 7)), - [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + [cap_byte] "i" (&((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: return true; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index d0ce5cfd3ac1..d5b5f2ab87a0 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -277,6 +277,7 @@ #define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ #define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ #define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ +#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -298,6 +299,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 14ebd2196569..43184640b579 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -25,7 +25,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) * For !SMAP hardware we patch out CLAC on entry. */ if (boot_cpu_has(X86_FEATURE_SMAP) || - (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV))) + (IS_ENABLED(CONFIG_64BIT) && boot_cpu_has(X86_FEATURE_XENPV))) mask |= X86_EFLAGS_AC; WARN_ON_ONCE(flags & mask); diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h index 1f0cbc52937c..93f400eb728f 100644 --- a/arch/x86/include/asm/extable.h +++ b/arch/x86/include/asm/extable.h @@ -1,12 +1,18 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_EXTABLE_H #define _ASM_X86_EXTABLE_H + +#include <asm/extable_fixup_types.h> + /* - * The exception table consists of triples of addresses relative to the - * exception table entry itself. The first address is of an instruction - * that is allowed to fault, the second is the target at which the program - * should continue. The third is a handler function to deal with the fault - * caused by the instruction in the first field. + * The exception table consists of two addresses relative to the + * exception table entry itself and a type selector field. + * + * The first address is of an instruction that is allowed to fault, the + * second is the target at which the program should continue. + * + * The type entry is used by fixup_exception() to select the handler to + * deal with the fault caused by the instruction in the first field. * * All the routines below use bits of fixup code that are out of line * with the main instruction path. This means when everything is well, @@ -15,7 +21,7 @@ */ struct exception_table_entry { - int insn, fixup, handler; + int insn, fixup, type; }; struct pt_regs; @@ -25,21 +31,27 @@ struct pt_regs; do { \ (a)->fixup = (b)->fixup + (delta); \ (b)->fixup = (tmp).fixup - (delta); \ - (a)->handler = (b)->handler + (delta); \ - (b)->handler = (tmp).handler - (delta); \ + (a)->type = (b)->type; \ + (b)->type = (tmp).type; \ } while (0) -enum handler_type { - EX_HANDLER_NONE, - EX_HANDLER_FAULT, - EX_HANDLER_UACCESS, - EX_HANDLER_OTHER -}; - extern int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr); extern int fixup_bug(struct pt_regs *regs, int trapnr); -extern enum handler_type ex_get_fault_handler_type(unsigned long ip); +extern int ex_get_fixup_type(unsigned long ip); extern void early_fixup_exception(struct pt_regs *regs, int trapnr); +#ifdef CONFIG_X86_MCE +extern void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr); +#else +static inline void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) { } +#endif + +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_X86_64) +bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs); +#else +static inline bool ex_handler_bpf(const struct exception_table_entry *x, + struct pt_regs *regs) { return false; } +#endif + #endif diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h new file mode 100644 index 000000000000..409524d5d2eb --- /dev/null +++ b/arch/x86/include/asm/extable_fixup_types.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EXTABLE_FIXUP_TYPES_H +#define _ASM_X86_EXTABLE_FIXUP_TYPES_H + +#define EX_TYPE_NONE 0 +#define EX_TYPE_DEFAULT 1 +#define EX_TYPE_FAULT 2 +#define EX_TYPE_UACCESS 3 +#define EX_TYPE_COPY 4 +#define EX_TYPE_CLEAR_FS 5 +#define EX_TYPE_FPU_RESTORE 6 +#define EX_TYPE_WRMSR 7 +#define EX_TYPE_RDMSR 8 +#define EX_TYPE_BPF 9 + +#define EX_TYPE_WRMSR_IN_MCE 10 +#define EX_TYPE_RDMSR_IN_MCE 11 + +#define EX_TYPE_DEFAULT_MCE_SAFE 12 +#define EX_TYPE_FAULT_MCE_SAFE 13 + +#endif diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 23bef08a8388..6053674f9132 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -12,6 +12,8 @@ #define _ASM_X86_FPU_API_H #include <linux/bottom_half.h> +#include <asm/fpu/types.h> + /* * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods @@ -48,9 +50,9 @@ static inline void kernel_fpu_begin(void) } /* - * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. + * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate. * A context switch will (and softirq might) save CPU's FPU registers to - * fpu->state and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in + * fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in * a random state. * * local_bh_disable() protects against both preemption and soft interrupts @@ -106,6 +108,56 @@ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); */ #define PASID_DISABLED 0 -static inline void update_pasid(void) { } +/* Trap handling */ +extern int fpu__exception_code(struct fpu *fpu, int trap_nr); +extern void fpu_sync_fpstate(struct fpu *fpu); +extern void fpu_reset_from_exception_fixup(void); + +/* Boot, hotplug and resume */ +extern void fpu__init_cpu(void); +extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_check_bugs(void); +extern void fpu__resume_cpu(void); + +#ifdef CONFIG_MATH_EMULATION +extern void fpstate_init_soft(struct swregs_state *soft); +#else +static inline void fpstate_init_soft(struct swregs_state *soft) {} +#endif + +/* State tracking */ +DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +/* Process cleanup */ +#ifdef CONFIG_X86_64 +extern void fpstate_free(struct fpu *fpu); +#else +static inline void fpstate_free(struct fpu *fpu) { } +#endif + +/* fpstate-related functions which are exported to KVM */ +extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature); + +/* KVM specific functions */ +extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); +extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); +extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest); + +extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru); +extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); + +static inline void fpstate_set_confidential(struct fpu_guest *gfpu) +{ + gfpu->fpstate->is_confidential = true; +} + +static inline bool fpstate_is_confidential(struct fpu_guest *gfpu) +{ + return gfpu->fpstate->is_confidential; +} + +/* prctl */ +struct task_struct; +extern long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2); #endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 5a18694a89b2..e69de29bb2d1 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -1,540 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - * x86-64 work by Andi Kleen 2002 - */ - -#ifndef _ASM_X86_FPU_INTERNAL_H -#define _ASM_X86_FPU_INTERNAL_H - -#include <linux/compat.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/mm.h> - -#include <asm/user.h> -#include <asm/fpu/api.h> -#include <asm/fpu/xstate.h> -#include <asm/fpu/xcr.h> -#include <asm/cpufeature.h> -#include <asm/trace/fpu.h> - -/* - * High level FPU state handling functions: - */ -extern int fpu__restore_sig(void __user *buf, int ia32_frame); -extern void fpu__drop(struct fpu *fpu); -extern void fpu__clear_user_states(struct fpu *fpu); -extern int fpu__exception_code(struct fpu *fpu, int trap_nr); - -extern void fpu_sync_fpstate(struct fpu *fpu); - -/* Clone and exit operations */ -extern int fpu_clone(struct task_struct *dst); -extern void fpu_flush_thread(void); - -/* - * Boot time FPU initialization functions: - */ -extern void fpu__init_cpu(void); -extern void fpu__init_system_xstate(void); -extern void fpu__init_cpu_xstate(void); -extern void fpu__init_system(struct cpuinfo_x86 *c); -extern void fpu__init_check_bugs(void); -extern void fpu__resume_cpu(void); - -/* - * Debugging facility: - */ -#ifdef CONFIG_X86_DEBUG_FPU -# define WARN_ON_FPU(x) WARN_ON_ONCE(x) -#else -# define WARN_ON_FPU(x) ({ (void)(x); 0; }) -#endif - -/* - * FPU related CPU feature flag helper routines: - */ -static __always_inline __pure bool use_xsaveopt(void) -{ - return static_cpu_has(X86_FEATURE_XSAVEOPT); -} - -static __always_inline __pure bool use_xsave(void) -{ - return static_cpu_has(X86_FEATURE_XSAVE); -} - -static __always_inline __pure bool use_fxsr(void) -{ - return static_cpu_has(X86_FEATURE_FXSR); -} - -/* - * fpstate handling functions: - */ - -extern union fpregs_state init_fpstate; - -extern void fpstate_init(union fpregs_state *state); -#ifdef CONFIG_MATH_EMULATION -extern void fpstate_init_soft(struct swregs_state *soft); -#else -static inline void fpstate_init_soft(struct swregs_state *soft) {} -#endif -extern void save_fpregs_to_fpstate(struct fpu *fpu); - -/* Returns 0 or the negated trap number, which results in -EFAULT for #PF */ -#define user_insn(insn, output, input...) \ -({ \ - int err; \ - \ - might_fault(); \ - \ - asm volatile(ASM_STAC "\n" \ - "1: " #insn "\n" \ - "2: " ASM_CLAC "\n" \ - ".section .fixup,\"ax\"\n" \ - "3: negl %%eax\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE_FAULT(1b, 3b) \ - : [err] "=a" (err), output \ - : "0"(0), input); \ - err; \ -}) - -#define kernel_insn_err(insn, output, input...) \ -({ \ - int err; \ - asm volatile("1:" #insn "\n\t" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) - -#define kernel_insn(insn, output, input...) \ - asm volatile("1:" #insn "\n\t" \ - "2:\n" \ - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ - : output : input) - -static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx) -{ - return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); -} - -static inline int fxsave_to_user_sigframe(struct fxregs_state __user *fx) -{ - if (IS_ENABLED(CONFIG_X86_32)) - return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); - else - return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - -} - -static inline void fxrstor(struct fxregs_state *fx) -{ - if (IS_ENABLED(CONFIG_X86_32)) - kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else - kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline int fxrstor_safe(struct fxregs_state *fx) -{ - if (IS_ENABLED(CONFIG_X86_32)) - return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else - return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx) -{ - if (IS_ENABLED(CONFIG_X86_32)) - return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else - return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline void frstor(struct fregs_state *fx) -{ - kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline int frstor_safe(struct fregs_state *fx) -{ - return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline int frstor_from_user_sigframe(struct fregs_state __user *fx) -{ - return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline void fxsave(struct fxregs_state *fx) -{ - if (IS_ENABLED(CONFIG_X86_32)) - asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); - else - asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); -} - -/* These macros all use (%edi)/(%rdi) as the single memory argument. */ -#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" -#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" -#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" -#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" -#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" - -/* - * After this @err contains 0 on success or the negated trap number when - * the operation raises an exception. For faults this results in -EFAULT. - */ -#define XSTATE_OP(op, st, lmask, hmask, err) \ - asm volatile("1:" op "\n\t" \ - "xor %[err], %[err]\n" \ - "2:\n\t" \ - ".pushsection .fixup,\"ax\"\n\t" \ - "3: negl %%eax\n\t" \ - "jmp 2b\n\t" \ - ".popsection\n\t" \ - _ASM_EXTABLE_FAULT(1b, 3b) \ - : [err] "=a" (err) \ - : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ - : "memory") - -/* - * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact - * format and supervisor states in addition to modified optimization in - * XSAVEOPT. - * - * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT - * supports modified optimization which is not supported by XSAVE. - * - * We use XSAVE as a fallback. - * - * The 661 label is defined in the ALTERNATIVE* macros as the address of the - * original instruction which gets replaced. We need to use it here as the - * address of the instruction where we might get an exception at. - */ -#define XSTATE_XSAVE(st, lmask, hmask, err) \ - asm volatile(ALTERNATIVE_2(XSAVE, \ - XSAVEOPT, X86_FEATURE_XSAVEOPT, \ - XSAVES, X86_FEATURE_XSAVES) \ - "\n" \ - "xor %[err], %[err]\n" \ - "3:\n" \ - ".pushsection .fixup,\"ax\"\n" \ - "4: movl $-2, %[err]\n" \ - "jmp 3b\n" \ - ".popsection\n" \ - _ASM_EXTABLE(661b, 4b) \ - : [err] "=r" (err) \ - : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ - : "memory") - -/* - * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact - * XSAVE area format. - */ -#define XSTATE_XRESTORE(st, lmask, hmask) \ - asm volatile(ALTERNATIVE(XRSTOR, \ - XRSTORS, X86_FEATURE_XSAVES) \ - "\n" \ - "3:\n" \ - _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ - : \ - : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ - : "memory") - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline void os_xrstor_booting(struct xregs_state *xstate) -{ - u64 mask = xfeatures_mask_fpstate(); - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); - else - XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - - /* - * We should never fault when copying from a kernel buffer, and the FPU - * state we set at boot time should be valid. - */ - WARN_ON_FPU(err); -} - -/* - * Save processor xstate to xsave area. - * - * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features - * and command line options. The choice is permanent until the next reboot. - */ -static inline void os_xsave(struct xregs_state *xstate) -{ - u64 mask = xfeatures_mask_all; - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - WARN_ON_FPU(!alternatives_patched); - - XSTATE_XSAVE(xstate, lmask, hmask, err); - - /* We should never fault when copying to a kernel buffer: */ - WARN_ON_FPU(err); -} - -/* - * Restore processor xstate from xsave area. - * - * Uses XRSTORS when XSAVES is used, XRSTOR otherwise. - */ -static inline void os_xrstor(struct xregs_state *xstate, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - - XSTATE_XRESTORE(xstate, lmask, hmask); -} - -/* - * Save xstate to user space xsave area. - * - * We don't use modified optimization because xrstor/xrstors might track - * a different application. - * - * We don't use compacted format xsave area for - * backward compatibility for old applications which don't understand - * compacted format of xsave area. - */ -static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) -{ - /* - * Include the features which are not xsaved/rstored by the kernel - * internally, e.g. PKRU. That's user space ABI and also required - * to allow the signal handler to modify PKRU. - */ - u64 mask = xfeatures_mask_uabi(); - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - /* - * Clear the xsave header first, so that reserved fields are - * initialized to zero. - */ - err = __clear_user(&buf->header, sizeof(buf->header)); - if (unlikely(err)) - return -EFAULT; - - stac(); - XSTATE_OP(XSAVE, buf, lmask, hmask, err); - clac(); - - return err; -} - -/* - * Restore xstate from user space xsave area. - */ -static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask) -{ - struct xregs_state *xstate = ((__force struct xregs_state *)buf); - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - stac(); - XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - clac(); - - return err; -} - -/* - * Restore xstate from kernel space xsave area, return an error code instead of - * an exception. - */ -static inline int os_xrstor_safe(struct xregs_state *xstate, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - if (cpu_feature_enabled(X86_FEATURE_XSAVES)) - XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); - else - XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - - return err; -} - -extern void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask); - -static inline void restore_fpregs_from_fpstate(union fpregs_state *fpstate) -{ - __restore_fpregs_from_fpstate(fpstate, xfeatures_mask_fpstate()); -} - -extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); - -/* - * FPU context switch related helper methods: - */ - -DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); - -/* - * The in-register FPU state for an FPU context on a CPU is assumed to be - * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx - * matches the FPU. - * - * If the FPU register state is valid, the kernel can skip restoring the - * FPU state from memory. - * - * Any code that clobbers the FPU registers or updates the in-memory - * FPU state for a task MUST let the rest of the kernel know that the - * FPU registers are no longer valid for this task. - * - * Either one of these invalidation functions is enough. Invalidate - * a resource you control: CPU if using the CPU for something else - * (with preemption disabled), FPU for the current task, or a task that - * is prevented from running by the current task. - */ -static inline void __cpu_invalidate_fpregs_state(void) -{ - __this_cpu_write(fpu_fpregs_owner_ctx, NULL); -} - -static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) -{ - fpu->last_cpu = -1; -} - -static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) -{ - return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; -} - -/* - * These generally need preemption protection to work, - * do try to avoid using these on their own: - */ -static inline void fpregs_deactivate(struct fpu *fpu) -{ - this_cpu_write(fpu_fpregs_owner_ctx, NULL); - trace_x86_fpu_regs_deactivated(fpu); -} - -static inline void fpregs_activate(struct fpu *fpu) -{ - this_cpu_write(fpu_fpregs_owner_ctx, fpu); - trace_x86_fpu_regs_activated(fpu); -} - -/* Internal helper for switch_fpu_return() and signal frame setup */ -static inline void fpregs_restore_userregs(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - int cpu = smp_processor_id(); - - if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) - return; - - if (!fpregs_state_valid(fpu, cpu)) { - u64 mask; - - /* - * This restores _all_ xstate which has not been - * established yet. - * - * If PKRU is enabled, then the PKRU value is already - * correct because it was either set in switch_to() or in - * flush_thread(). So it is excluded because it might be - * not up to date in current->thread.fpu.xsave state. - */ - mask = xfeatures_mask_restore_user() | - xfeatures_mask_supervisor(); - __restore_fpregs_from_fpstate(&fpu->state, mask); - - fpregs_activate(fpu); - fpu->last_cpu = cpu; - } - clear_thread_flag(TIF_NEED_FPU_LOAD); -} - -/* - * FPU state switching for scheduling. - * - * This is a two-stage process: - * - * - switch_fpu_prepare() saves the old state. - * This is done within the context of the old process. - * - * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state - * will get loaded on return to userspace, or when the kernel needs it. - * - * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers - * are saved in the current thread's FPU register state. - * - * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not - * hold current()'s FPU registers. It is required to load the - * registers before returning to userland or using the content - * otherwise. - * - * The FPU context is only stored/restored for a user task and - * PF_KTHREAD is used to distinguish between kernel and user threads. - */ -static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) -{ - if (static_cpu_has(X86_FEATURE_FPU) && !(current->flags & PF_KTHREAD)) { - save_fpregs_to_fpstate(old_fpu); - /* - * The save operation preserved register state, so the - * fpu_fpregs_owner_ctx is still @old_fpu. Store the - * current CPU number in @old_fpu, so the next return - * to user space can avoid the FPU register restore - * when is returns on the same CPU and still owns the - * context. - */ - old_fpu->last_cpu = cpu; - - trace_x86_fpu_regs_deactivated(old_fpu); - } -} - -/* - * Misc helper functions: - */ - -/* - * Delay loading of the complete FPU state until the return to userland. - * PKRU is handled separately. - */ -static inline void switch_fpu_finish(struct fpu *new_fpu) -{ - if (cpu_feature_enabled(X86_FEATURE_FPU)) - set_thread_flag(TIF_NEED_FPU_LOAD); -} - -#endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h new file mode 100644 index 000000000000..99a8820e8cc4 --- /dev/null +++ b/arch/x86/include/asm/fpu/sched.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FPU_SCHED_H +#define _ASM_X86_FPU_SCHED_H + +#include <linux/sched.h> + +#include <asm/cpufeature.h> +#include <asm/fpu/types.h> + +#include <asm/trace/fpu.h> + +extern void save_fpregs_to_fpstate(struct fpu *fpu); +extern void fpu__drop(struct fpu *fpu); +extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags); +extern void fpu_flush_thread(void); + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state. + * This is done within the context of the old process. + * + * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state + * will get loaded on return to userspace, or when the kernel needs it. + * + * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers + * are saved in the current thread's FPU register state. + * + * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not + * hold current()'s FPU registers. It is required to load the + * registers before returning to userland or using the content + * otherwise. + * + * The FPU context is only stored/restored for a user task and + * PF_KTHREAD is used to distinguish between kernel and user threads. + */ +static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) +{ + if (cpu_feature_enabled(X86_FEATURE_FPU) && + !(current->flags & PF_KTHREAD)) { + save_fpregs_to_fpstate(old_fpu); + /* + * The save operation preserved register state, so the + * fpu_fpregs_owner_ctx is still @old_fpu. Store the + * current CPU number in @old_fpu, so the next return + * to user space can avoid the FPU register restore + * when is returns on the same CPU and still owns the + * context. + */ + old_fpu->last_cpu = cpu; + + trace_x86_fpu_regs_deactivated(old_fpu); + } +} + +/* + * Delay loading of the complete FPU state until the return to userland. + * PKRU is handled separately. + */ +static inline void switch_fpu_finish(void) +{ + if (cpu_feature_enabled(X86_FEATURE_FPU)) + set_thread_flag(TIF_NEED_FPU_LOAD); +} + +#endif /* _ASM_X86_FPU_SCHED_H */ diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 8b6631dffefd..22b0273a8bf1 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -5,6 +5,11 @@ #ifndef _ASM_X86_FPU_SIGNAL_H #define _ASM_X86_FPU_SIGNAL_H +#include <linux/compat.h> +#include <linux/user.h> + +#include <asm/fpu/types.h> + #ifdef CONFIG_X86_64 # include <uapi/asm/sigcontext.h> # include <asm/user32.h> @@ -31,6 +36,12 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long fpu__get_fpstate_size(void); -extern void fpu__init_prepare_fx_sw_frame(void); +extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); +extern void fpu__clear_user_states(struct fpu *fpu); +extern bool fpu__restore_sig(void __user *buf, int ia32_frame); + +extern void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask); + +extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); #endif /* _ASM_X86_FPU_SIGNAL_H */ diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index f5a38a5f3ae1..3c06c82ab355 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -120,6 +120,9 @@ enum xfeature { XFEATURE_RSRVD_COMP_13, XFEATURE_RSRVD_COMP_14, XFEATURE_LBR, + XFEATURE_RSRVD_COMP_16, + XFEATURE_XTILE_CFG, + XFEATURE_XTILE_DATA, XFEATURE_MAX, }; @@ -136,12 +139,21 @@ enum xfeature { #define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU) #define XFEATURE_MASK_PASID (1 << XFEATURE_PASID) #define XFEATURE_MASK_LBR (1 << XFEATURE_LBR) +#define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG) +#define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA) #define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE) #define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \ | XFEATURE_MASK_ZMM_Hi256 \ | XFEATURE_MASK_Hi16_ZMM) +#ifdef CONFIG_X86_64 +# define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILE_DATA \ + | XFEATURE_MASK_XTILE_CFG) +#else +# define XFEATURE_MASK_XTILE (0) +#endif + #define FIRST_EXTENDED_XFEATURE XFEATURE_YMM struct reg_128_bit { @@ -153,6 +165,9 @@ struct reg_256_bit { struct reg_512_bit { u8 regbytes[512/8]; }; +struct reg_1024_byte { + u8 regbytes[1024]; +}; /* * State component 2: @@ -255,6 +270,23 @@ struct arch_lbr_state { u64 ler_to; u64 ler_info; struct lbr_entry entries[]; +}; + +/* + * State component 17: 64-byte tile configuration register. + */ +struct xtile_cfg { + u64 tcfg[8]; +} __packed; + +/* + * State component 18: 1KB tile data register. + * Each register represents 16 64-byte rows of the matrix + * data. But the number of registers depends on the actual + * implementation. + */ +struct xtile_data { + struct reg_1024_byte tmm; } __packed; /* @@ -309,6 +341,91 @@ union fpregs_state { u8 __padding[PAGE_SIZE]; }; +struct fpstate { + /* @kernel_size: The size of the kernel register image */ + unsigned int size; + + /* @user_size: The size in non-compacted UABI format */ + unsigned int user_size; + + /* @xfeatures: xfeatures for which the storage is sized */ + u64 xfeatures; + + /* @user_xfeatures: xfeatures valid in UABI buffers */ + u64 user_xfeatures; + + /* @xfd: xfeatures disabled to trap userspace use. */ + u64 xfd; + + /* @is_valloc: Indicator for dynamically allocated state */ + unsigned int is_valloc : 1; + + /* @is_guest: Indicator for guest state (KVM) */ + unsigned int is_guest : 1; + + /* + * @is_confidential: Indicator for KVM confidential mode. + * The FPU registers are restored by the + * vmentry firmware from encrypted guest + * memory. On vmexit the FPU registers are + * saved by firmware to encrypted guest memory + * and the registers are scrubbed before + * returning to the host. So there is no + * content which is worth saving and restoring. + * The fpstate has to be there so that + * preemption and softirq FPU usage works + * without special casing. + */ + unsigned int is_confidential : 1; + + /* @in_use: State is in use */ + unsigned int in_use : 1; + + /* @regs: The register state union for all supported formats */ + union fpregs_state regs; + + /* @regs is dynamically sized! Don't add anything after @regs! */ +} __aligned(64); + +struct fpu_state_perm { + /* + * @__state_perm: + * + * This bitmap indicates the permission for state components, which + * are available to a thread group. The permission prctl() sets the + * enabled state bits in thread_group_leader()->thread.fpu. + * + * All run time operations use the per thread information in the + * currently active fpu.fpstate which contains the xfeature masks + * and sizes for kernel and user space. + * + * This master permission field is only to be used when + * task.fpu.fpstate based checks fail to validate whether the task + * is allowed to expand it's xfeatures set which requires to + * allocate a larger sized fpstate buffer. + * + * Do not access this field directly. Use the provided helper + * function. Unlocked access is possible for quick checks. + */ + u64 __state_perm; + + /* + * @__state_size: + * + * The size required for @__state_perm. Only valid to access + * with sighand locked. + */ + unsigned int __state_size; + + /* + * @__user_state_size: + * + * The size required for @__state_perm user part. Only valid to + * access with sighand locked. + */ + unsigned int __user_state_size; +}; + /* * Highest level per task FPU state data structure that * contains the FPU register state plus various FPU @@ -337,19 +454,100 @@ struct fpu { unsigned long avx512_timestamp; /* - * @state: + * @fpstate: + * + * Pointer to the active struct fpstate. Initialized to + * point at @__fpstate below. + */ + struct fpstate *fpstate; + + /* + * @__task_fpstate: + * + * Pointer to an inactive struct fpstate. Initialized to NULL. Is + * used only for KVM support to swap out the regular task fpstate. + */ + struct fpstate *__task_fpstate; + + /* + * @perm: + * + * Permission related information + */ + struct fpu_state_perm perm; + + /* + * @__fpstate: * - * In-memory copy of all FPU registers that we save/restore - * over context switches. If the task is using the FPU then - * the registers in the FPU are more recent than this state - * copy. If the task context-switches away then they get - * saved here and represent the FPU state. + * Initial in-memory storage for FPU registers which are saved in + * context switch and when the kernel uses the FPU. The registers + * are restored from this storage on return to user space if they + * are not longer containing the tasks FPU register state. */ - union fpregs_state state; + struct fpstate __fpstate; /* - * WARNING: 'state' is dynamically-sized. Do not put + * WARNING: '__fpstate' is dynamically-sized. Do not put * anything after it here. */ }; +/* + * Guest pseudo FPU container + */ +struct fpu_guest { + /* + * @fpstate: Pointer to the allocated guest fpstate + */ + struct fpstate *fpstate; +}; + +/* + * FPU state configuration data. Initialized at boot time. Read only after init. + */ +struct fpu_state_config { + /* + * @max_size: + * + * The maximum size of the register state buffer. Includes all + * supported features except independent managed features. + */ + unsigned int max_size; + + /* + * @default_size: + * + * The default size of the register state buffer. Includes all + * supported features except independent managed features and + * features which have to be requested by user space before usage. + */ + unsigned int default_size; + + /* + * @max_features: + * + * The maximum supported features bitmap. Does not include + * independent managed features. + */ + u64 max_features; + + /* + * @default_features: + * + * The default supported features bitmap. Does not include + * independent managed features and features which have to + * be requested by user space before usage. + */ + u64 default_features; + /* + * @legacy_features: + * + * Features which can be reported back to user space + * even without XSAVE support, i.e. legacy features FP + SSE + */ + u64 legacy_features; +}; + +/* FPU state configuration information */ +extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg; + #endif /* _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h index 1c7ab8d95da5..79f95d3787e2 100644 --- a/arch/x86/include/asm/fpu/xcr.h +++ b/arch/x86/include/asm/fpu/xcr.h @@ -2,17 +2,6 @@ #ifndef _ASM_X86_FPU_XCR_H #define _ASM_X86_FPU_XCR_H -/* - * MXCSR and XCR definitions: - */ - -static inline void ldmxcsr(u32 mxcsr) -{ - asm volatile("ldmxcsr %0" :: "m" (mxcsr)); -} - -extern unsigned int mxcsr_feature_mask; - #define XCR_XFEATURE_ENABLED_MASK 0x00000000 static inline u64 xgetbv(u32 index) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 109dfcc75299..0f8b90ab18c9 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -14,6 +14,8 @@ #define XSTATE_CPUID 0x0000000d +#define TILE_CPUID 0x0000001d + #define FXSAVE_SIZE 512 #define XSAVE_HDR_SIZE 64 @@ -33,7 +35,8 @@ XFEATURE_MASK_Hi16_ZMM | \ XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ - XFEATURE_MASK_BNDCSR) + XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_XTILE) /* * Features which are restored when returning to user space. @@ -43,6 +46,9 @@ #define XFEATURE_MASK_USER_RESTORE \ (XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU) +/* Features which are dynamically enabled for a process on request */ +#define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA + /* All currently supported supervisor features */ #define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID) @@ -78,78 +84,42 @@ XFEATURE_MASK_INDEPENDENT | \ XFEATURE_MASK_SUPERVISOR_UNSUPPORTED) -#ifdef CONFIG_X86_64 -#define REX_PREFIX "0x48, " -#else -#define REX_PREFIX -#endif - -extern u64 xfeatures_mask_all; - -static inline u64 xfeatures_mask_supervisor(void) -{ - return xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_SUPPORTED; -} - /* - * The xfeatures which are enabled in XCR0 and expected to be in ptrace - * buffers and signal frames. + * The feature mask required to restore FPU state: + * - All user states which are not eagerly switched in switch_to()/exec() + * - The suporvisor states */ -static inline u64 xfeatures_mask_uabi(void) -{ - return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED; -} - -/* - * The xfeatures which are restored by the kernel when returning to user - * mode. This is not necessarily the same as xfeatures_mask_uabi() as the - * kernel does not manage all XCR0 enabled features via xsave/xrstor as - * some of them have to be switched eagerly on context switch and exec(). - */ -static inline u64 xfeatures_mask_restore_user(void) -{ - return xfeatures_mask_all & XFEATURE_MASK_USER_RESTORE; -} - -/* - * Like xfeatures_mask_restore_user() but additionally restors the - * supported supervisor states. - */ -static inline u64 xfeatures_mask_fpstate(void) -{ - return xfeatures_mask_all & \ - (XFEATURE_MASK_USER_RESTORE | XFEATURE_MASK_SUPERVISOR_SUPPORTED); -} - -static inline u64 xfeatures_mask_independent(void) -{ - if (!boot_cpu_has(X86_FEATURE_ARCH_LBR)) - return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR; - - return XFEATURE_MASK_INDEPENDENT; -} +#define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \ + XFEATURE_MASK_SUPERVISOR_SUPPORTED) extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; extern void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask); -void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); int xfeature_size(int xfeature_nr); -int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); -int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); void xsaves(struct xregs_state *xsave, u64 mask); void xrstors(struct xregs_state *xsave, u64 mask); -enum xstate_copy_mode { - XSTATE_COPY_FP, - XSTATE_COPY_FX, - XSTATE_COPY_XSAVE, -}; +int xfd_enable_feature(u64 xfd_err); + +#ifdef CONFIG_X86_64 +DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); +#endif + +#ifdef CONFIG_X86_64 +DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); -struct membuf; -void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, - enum xstate_copy_mode mode); +static __always_inline __pure bool fpu_state_size_dynamic(void) +{ + return static_branch_unlikely(&__fpu_state_size_dynamic); +} +#else +static __always_inline __pure bool fpu_state_size_dynamic(void) +{ + return false; +} +#endif #endif diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 9f3130f40807..024d9797646e 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -57,6 +57,13 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) #define ftrace_instruction_pointer_set(fregs, _ip) \ do { (fregs)->regs.ip = (_ip); } while (0) + +struct ftrace_ops; +#define ftrace_graph_func ftrace_graph_func +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#else +#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR #endif #ifdef CONFIG_DYNAMIC_FTRACE @@ -65,8 +72,6 @@ struct dyn_arch_ftrace { /* No extra data needed for x86 */ }; -#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR - #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 2322d6bd5883..381e88122a5f 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -276,6 +276,23 @@ enum hv_isolation_type { #define HV_X64_MSR_TIME_REF_COUNT HV_REGISTER_TIME_REF_COUNT #define HV_X64_MSR_REFERENCE_TSC HV_REGISTER_REFERENCE_TSC +/* Hyper-V memory host visibility */ +enum hv_mem_host_visibility { + VMBUS_PAGE_NOT_VISIBLE = 0, + VMBUS_PAGE_VISIBLE_READ_ONLY = 1, + VMBUS_PAGE_VISIBLE_READ_WRITE = 3 +}; + +/* HvCallModifySparseGpaPageHostVisibility hypercall */ +#define HV_MAX_MODIFY_GPA_REP_COUNT ((PAGE_SIZE / sizeof(u64)) - 2) +struct hv_gpa_range_for_visibility { + u64 partition_id; + u32 host_visibility:2; + u32 reserved0:30; + u32 reserved1; + u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT]; +} __packed; + /* * Declare the MSR used to setup pages used to communicate with the hypervisor. */ diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 2c5f7861d373..fada857f0a1e 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -68,6 +68,6 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm); #endif -#endif /* !CONFIG_IA32_SUPPORT */ +#endif /* CONFIG_IA32_EMULATION */ #endif /* _ASM_X86_IA32_H */ diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index 91d7182ad2d6..4ec3613551e3 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -21,6 +21,7 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs); unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); int insn_get_code_seg_params(struct pt_regs *regs); +int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip); int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]); int insn_fetch_from_user_inatomic(struct pt_regs *regs, diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 841a5d104afa..5c6a4af0b911 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -391,6 +391,7 @@ extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) #define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc #endif +#ifdef CONFIG_AMD_MEM_ENCRYPT extern bool arch_memremap_can_ram_remap(resource_size_t offset, unsigned long size, unsigned long flags); @@ -398,6 +399,13 @@ extern bool arch_memremap_can_ram_remap(resource_size_t offset, extern bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size); +#else +static inline bool phys_mem_access_encrypted(unsigned long phys_addr, + unsigned long size) +{ + return true; +} +#endif /** * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 562854c60808..ae9d40f6c706 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -58,7 +58,7 @@ * the output constraints to make the compiler aware that R11 cannot be * reused after the asm() statement. * - * For builds with CONFIG_UNWIND_FRAME_POINTER ASM_CALL_CONSTRAINT is + * For builds with CONFIG_UNWINDER_FRAME_POINTER, ASM_CALL_CONSTRAINT is * required as well as this prevents certain creative GCC variants from * misplacing the ASM code. * @@ -77,11 +77,11 @@ * Function calls can clobber anything except the callee-saved * registers. Tell the compiler. */ -#define call_on_irqstack(func, asm_call, argconstr...) \ +#define call_on_stack(stack, func, asm_call, argconstr...) \ { \ register void *tos asm("r11"); \ \ - tos = ((void *)__this_cpu_read(hardirq_stack_ptr)); \ + tos = ((void *)(stack)); \ \ asm_inline volatile( \ "movq %%rsp, (%[tos]) \n" \ @@ -98,6 +98,25 @@ ); \ } +#define ASM_CALL_ARG0 \ + "call %P[__func] \n" + +#define ASM_CALL_ARG1 \ + "movq %[arg1], %%rdi \n" \ + ASM_CALL_ARG0 + +#define ASM_CALL_ARG2 \ + "movq %[arg2], %%rsi \n" \ + ASM_CALL_ARG1 + +#define ASM_CALL_ARG3 \ + "movq %[arg3], %%rdx \n" \ + ASM_CALL_ARG2 + +#define call_on_irqstack(func, asm_call, argconstr...) \ + call_on_stack(__this_cpu_read(hardirq_stack_ptr), \ + func, asm_call, argconstr) + /* Macros to assert type correctness for run_*_on_irqstack macros */ #define assert_function_type(func, proto) \ static_assert(__builtin_types_compatible_p(typeof(&func), proto)) @@ -147,8 +166,7 @@ */ #define ASM_CALL_SYSVEC \ "call irq_enter_rcu \n" \ - "movq %[arg1], %%rdi \n" \ - "call %P[__func] \n" \ + ASM_CALL_ARG1 \ "call irq_exit_rcu \n" #define SYSVEC_CONSTRAINTS , [arg1] "r" (regs) @@ -168,12 +186,10 @@ */ #define ASM_CALL_IRQ \ "call irq_enter_rcu \n" \ - "movq %[arg1], %%rdi \n" \ - "movl %[arg2], %%esi \n" \ - "call %P[__func] \n" \ + ASM_CALL_ARG2 \ "call irq_exit_rcu \n" -#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" (vector) +#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" ((unsigned long)vector) #define run_irq_on_irqstack_cond(func, regs, vector) \ { \ @@ -185,9 +201,7 @@ IRQ_CONSTRAINTS, regs, vector); \ } -#define ASM_CALL_SOFTIRQ \ - "call %P[__func] \n" - +#ifndef CONFIG_PREEMPT_RT /* * Macro to invoke __do_softirq on the irq stack. This is only called from * task context when bottom halves are about to be reenabled and soft @@ -197,10 +211,12 @@ #define do_softirq_own_stack() \ { \ __this_cpu_write(hardirq_stack_inuse, true); \ - call_on_irqstack(__do_softirq, ASM_CALL_SOFTIRQ); \ + call_on_irqstack(__do_softirq, ASM_CALL_ARG0); \ __this_cpu_write(hardirq_stack_inuse, false); \ } +#endif + #else /* CONFIG_X86_64 */ /* System vector handlers always run on the stack they interrupted. */ #define run_sysvec_on_irqstack_cond(func, regs) \ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 0a6e34b07017..11b7c06e2828 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -129,7 +129,7 @@ relocate_kernel(unsigned long indirection_page, unsigned long page_list, unsigned long start_address, unsigned int preserve_context, - unsigned int sme_active); + unsigned int host_mem_enc_active); #endif #define ARCH_HAS_KIMAGE_ARCH diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index bd7f5886a789..71ea2eab43d5 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -49,7 +49,6 @@ extern __visible kprobe_opcode_t optprobe_template_end[]; extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); -asmlinkage void kretprobe_trampoline(void); extern void arch_kprobe_override_function(struct pt_regs *regs); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8f48a7ec577..2acf37cc1991 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -50,7 +50,7 @@ * so ratio of 4 should be enough. */ #define KVM_VCPU_ID_RATIO 4 -#define KVM_MAX_VCPU_ID (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) +#define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) /* memory slots that are not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 3 @@ -407,6 +407,7 @@ struct kvm_mmu_root_info { #define KVM_HAVE_MMU_RWLOCK struct kvm_mmu_page; +struct kvm_page_fault; /* * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit, @@ -416,8 +417,7 @@ struct kvm_mmu_page; struct kvm_mmu { unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); - int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, - bool prefault); + int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, @@ -499,7 +499,6 @@ struct kvm_pmu { u64 fixed_ctr_ctrl; u64 global_ctrl; u64 global_status; - u64 global_ovf_ctrl; u64 counter_bitmask[2]; u64 global_ctrl_mask; u64 global_ovf_ctrl_mask; @@ -581,7 +580,6 @@ struct kvm_vcpu_hv { struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); - cpumask_t tlb_flush; bool enforce_cpuid; struct { u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */ @@ -691,18 +689,18 @@ struct kvm_vcpu_arch { * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The - * "guest_fpu" state here contains the guest FPU context, with the + * "guest_fpstate" state here contains the guest FPU context, with the * host PRKU bits. */ - struct fpu *user_fpu; - struct fpu *guest_fpu; + struct fpu_guest guest_fpu; u64 xcr0; u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; - void *guest_ins_data; + void *sev_pio_data; + unsigned sev_pio_count; u8 event_exit_inst_len; @@ -1073,7 +1071,7 @@ struct kvm_arch { atomic_t apic_map_dirty; /* Protects apic_access_memslot_enabled and apicv_inhibit_reasons */ - struct mutex apicv_update_lock; + struct rw_semaphore apicv_update_lock; bool apic_access_memslot_enabled; unsigned long apicv_inhibit_reasons; @@ -1087,17 +1085,23 @@ struct kvm_arch { unsigned long irq_sources_bitmap; s64 kvmclock_offset; + + /* + * This also protects nr_vcpus_matched_tsc which is read from a + * preemption-disabled region, so it must be a raw spinlock. + */ raw_spinlock_t tsc_write_lock; u64 last_tsc_nsec; u64 last_tsc_write; u32 last_tsc_khz; + u64 last_tsc_offset; u64 cur_tsc_nsec; u64 cur_tsc_write; u64 cur_tsc_offset; u64 cur_tsc_generation; int nr_vcpus_matched_tsc; - spinlock_t pvclock_gtod_sync_lock; + seqcount_raw_spinlock_t pvclock_sc; bool use_master_clock; u64 master_kernel_ns; u64 master_cycle_now; @@ -1207,10 +1211,11 @@ struct kvm_arch { #endif /* CONFIG_X86_64 */ /* - * If set, rmaps have been allocated for all memslots and should be - * allocated for any newly created or modified memslots. + * If set, at least one shadow root has been allocated. This flag + * is used as one input when determining whether certain memslot + * related allocations are necessary. */ - bool memslots_have_rmaps; + bool shadow_root_allocated; #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; @@ -1296,6 +1301,8 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) } struct kvm_x86_ops { + const char *name; + int (*hardware_enable)(void); void (*hardware_disable)(void); void (*hardware_unsetup)(void); @@ -1405,10 +1412,11 @@ struct kvm_x86_ops { void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu, u64 multiplier); /* - * Retrieve somewhat arbitrary exit information. Intended to be used - * only from within tracepoints to avoid VMREADs when tracing is off. + * Retrieve somewhat arbitrary exit information. Intended to + * be used only from within tracepoints or error paths. */ - void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, + void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *exit_int_info, u32 *exit_int_info_err_code); int (*check_intercept)(struct kvm_vcpu *vcpu, @@ -1541,6 +1549,8 @@ static inline struct kvm *kvm_arch_alloc_vm(void) { return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } + +#define __KVM_HAVE_ARCH_VM_FREE void kvm_arch_free_vm(struct kvm *kvm); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB @@ -1657,6 +1667,9 @@ extern u64 kvm_mce_cap_supported; int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); +void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, + u64 *data, u8 ndata); +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -1685,8 +1698,6 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code); -void kvm_free_guest_fpu(struct kvm_vcpu *vcpu); - void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0); void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); @@ -1715,9 +1726,6 @@ void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); -int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gfn_t gfn, void *data, int offset, int len, - u32 access); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr); @@ -1866,7 +1874,6 @@ u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); -void kvm_make_mclock_inprogress_request(struct kvm *kvm); void kvm_make_scan_ioapic_request(struct kvm *kvm); void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap); @@ -1935,6 +1942,9 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) int kvm_cpu_dirty_log_size(void); -int alloc_all_memslots_rmaps(struct kvm *kvm); +int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); + +#define KVM_CLOCK_VALID_FLAGS \ + (KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC) #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 87bd6025d91d..9d4a3b1b25b9 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -46,11 +46,15 @@ struct kvm_page_track_notifier_node { struct kvm_page_track_notifier_node *node); }; -void kvm_page_track_init(struct kvm *kvm); +int kvm_page_track_init(struct kvm *kvm); void kvm_page_track_cleanup(struct kvm *kvm); +bool kvm_page_track_write_tracking_enabled(struct kvm *kvm); +int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot); + void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); -int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, +int kvm_page_track_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, unsigned long npages); void kvm_slot_page_track_add_page(struct kvm *kvm, @@ -59,8 +63,9 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, void kvm_slot_page_track_remove_page(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, enum kvm_page_track_mode mode); -bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, - enum kvm_page_track_mode mode); +bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode); void kvm_page_track_register_notifier(struct kvm *kvm, diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index eceea9299097..6c5765192102 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -2,6 +2,20 @@ #ifndef _ASM_X86_KVM_CLOCK_H #define _ASM_X86_KVM_CLOCK_H +#include <linux/percpu.h> + extern struct clocksource kvm_clock; +DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} + #endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index da9321548f6f..8f6395d9e209 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -205,28 +205,16 @@ struct cper_ia_proc_ctx; int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); void mcheck_cpu_clear(struct cpuinfo_x86 *c); -void mcheck_vendor_init_severity(void); int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id); #else static inline int mcheck_init(void) { return 0; } static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {} -static inline void mcheck_vendor_init_severity(void) {} static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) { return -EINVAL; } #endif -#ifdef CONFIG_X86_ANCIENT_MCE -void intel_p5_mcheck_init(struct cpuinfo_x86 *c); -void winchip_mcheck_init(struct cpuinfo_x86 *c); -static inline void enable_p5_mce(void) { mce_p5_enabled = 1; } -#else -static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {} -static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {} -static inline void enable_p5_mce(void) {} -#endif - void mce_setup(struct mce *m); void mce_log(struct mce *m); DECLARE_PER_CPU(struct device *, mce_device); @@ -358,7 +346,7 @@ extern int mce_threshold_remove_device(unsigned int cpu); void mce_amd_feature_init(struct cpuinfo_x86 *c); int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr); - +enum smca_bank_types smca_get_bank_type(unsigned int bank); #else static inline int mce_threshold_create_device(unsigned int cpu) { return 0; }; diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 9c80c68d75b5..2d4f5c17d79c 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -13,6 +13,7 @@ #ifndef __ASSEMBLY__ #include <linux/init.h> +#include <linux/cc_platform.h> #include <asm/bootparam.h> @@ -50,9 +51,6 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init mem_encrypt_init(void); void __init sev_es_init_vc_handling(void); -bool sme_active(void); -bool sev_active(void); -bool sev_es_active(void); #define __bss_decrypted __section(".bss..decrypted") @@ -75,9 +73,6 @@ static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } static inline void sev_es_init_vc_handling(void) { } -static inline bool sme_active(void) { return false; } -static inline bool sev_active(void) { return false; } -static inline bool sev_es_active(void) { return false; } static inline int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } @@ -101,11 +96,6 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline bool mem_encrypt_active(void) -{ - return sme_me_mask; -} - static inline u64 sme_get_me_mask(void) { return sme_me_mask; diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index ab45a220fac4..d6bfdfb0f0af 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -130,14 +130,11 @@ static inline unsigned int x86_cpuid_family(void) extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); -extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); extern bool initrd_gone; #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void reload_early_microcode(void) { } -static inline bool -get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } #endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index adccbc209169..da3972fe5a7a 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -11,23 +11,14 @@ #include <asm/paravirt.h> #include <asm/mshyperv.h> +union hv_ghcb; + +DECLARE_STATIC_KEY_FALSE(isolation_type_snp); + typedef int (*hyperv_fill_flush_list_func)( struct hv_guest_mapping_flush_list *flush, void *data); -static inline void hv_set_register(unsigned int reg, u64 value) -{ - wrmsrl(reg, value); -} - -static inline u64 hv_get_register(unsigned int reg) -{ - u64 value; - - rdmsrl(reg, value); - return value; -} - #define hv_get_raw_timer() rdtsc_ordered() void hyperv_vector_handler(struct pt_regs *regs); @@ -39,6 +30,8 @@ extern void *hv_hypercall_pg; extern u64 hv_current_partition_id; +extern union hv_ghcb __percpu **hv_ghcb_pg; + int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages); int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id); int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags); @@ -188,6 +181,50 @@ struct irq_domain *hv_create_pci_msi_domain(void); int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector, struct hv_interrupt_entry *entry); int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); +int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible); + +#ifdef CONFIG_AMD_MEM_ENCRYPT +void hv_ghcb_msr_write(u64 msr, u64 value); +void hv_ghcb_msr_read(u64 msr, u64 *value); +#else +static inline void hv_ghcb_msr_write(u64 msr, u64 value) {} +static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {} +#endif + +extern bool hv_isolation_type_snp(void); + +static inline bool hv_is_synic_reg(unsigned int reg) +{ + if ((reg >= HV_REGISTER_SCONTROL) && + (reg <= HV_REGISTER_SINT15)) + return true; + return false; +} + +static inline u64 hv_get_register(unsigned int reg) +{ + u64 value; + + if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) + hv_ghcb_msr_read(reg, &value); + else + rdmsrl(reg, value); + return value; +} + +static inline void hv_set_register(unsigned int reg, u64 value) +{ + if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) { + hv_ghcb_msr_write(reg, value); + + /* Write proxy bit via wrmsl instruction */ + if (reg >= HV_REGISTER_SINT0 && + reg <= HV_REGISTER_SINT15) + wrmsrl(reg, value | 1 << 20); + } else { + wrmsrl(reg, value); + } +} #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} @@ -205,6 +242,13 @@ static inline int hyperv_flush_guest_mapping_range(u64 as, { return -1; } +static inline void hv_set_register(unsigned int reg, u64 value) { } +static inline u64 hv_get_register(unsigned int reg) { return 0; } +static inline int hv_set_mem_host_visibility(unsigned long addr, int numpages, + bool visible) +{ + return -1; +} #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a7c413432b33..01e2650b9585 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -625,6 +625,8 @@ #define MSR_IA32_BNDCFGS_RSVD 0x00000ffc +#define MSR_IA32_XFD 0x000001c4 +#define MSR_IA32_XFD_ERR 0x000001c5 #define MSR_IA32_XSS 0x00000da0 #define MSR_IA32_APICBASE 0x0000001b diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index a3f87f1015d3..6b52182e178a 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -92,7 +92,7 @@ static __always_inline unsigned long long __rdmsr(unsigned int msr) asm volatile("1: rdmsr\n" "2:\n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe) + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR) : EAX_EDX_RET(val, low, high) : "c" (msr)); return EAX_EDX_VAL(val, low, high); @@ -102,7 +102,7 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a"(low), "d" (high) : "memory"); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index ec2d5c8c6694..cc74dc584836 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -5,12 +5,15 @@ #include <linux/static_key.h> #include <linux/objtool.h> +#include <linux/linkage.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> +#define RETPOLINE_THUNK_SIZE 32 + /* * Fill the CPU return stack buffer. * @@ -118,6 +121,16 @@ ".popsection\n\t" #ifdef CONFIG_RETPOLINE + +typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; + +#define GEN(reg) \ + extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; +#include <asm/GEN-for-each-reg.h> +#undef GEN + +extern retpoline_thunk_t __x86_indirect_thunk_array[]; + #ifdef CONFIG_X86_64 /* @@ -303,63 +316,4 @@ static inline void mds_idle_clear_cpu_buffers(void) #endif /* __ASSEMBLY__ */ -/* - * Below is used in the eBPF JIT compiler and emits the byte sequence - * for the following assembly: - * - * With retpolines configured: - * - * callq do_rop - * spec_trap: - * pause - * lfence - * jmp spec_trap - * do_rop: - * mov %rcx,(%rsp) for x86_64 - * mov %edx,(%esp) for x86_32 - * retq - * - * Without retpolines configured: - * - * jmp *%rcx for x86_64 - * jmp *%edx for x86_32 - */ -#ifdef CONFIG_RETPOLINE -# ifdef CONFIG_X86_64 -# define RETPOLINE_RCX_BPF_JIT_SIZE 17 -# define RETPOLINE_RCX_BPF_JIT() \ -do { \ - EMIT1_off32(0xE8, 7); /* callq do_rop */ \ - /* spec_trap: */ \ - EMIT2(0xF3, 0x90); /* pause */ \ - EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ - EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ - /* do_rop: */ \ - EMIT4(0x48, 0x89, 0x0C, 0x24); /* mov %rcx,(%rsp) */ \ - EMIT1(0xC3); /* retq */ \ -} while (0) -# else /* !CONFIG_X86_64 */ -# define RETPOLINE_EDX_BPF_JIT() \ -do { \ - EMIT1_off32(0xE8, 7); /* call do_rop */ \ - /* spec_trap: */ \ - EMIT2(0xF3, 0x90); /* pause */ \ - EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ - EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ - /* do_rop: */ \ - EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */ \ - EMIT1(0xC3); /* ret */ \ -} while (0) -# endif -#else /* !CONFIG_RETPOLINE */ -# ifdef CONFIG_X86_64 -# define RETPOLINE_RCX_BPF_JIT_SIZE 2 -# define RETPOLINE_RCX_BPF_JIT() \ - EMIT2(0xFF, 0xE1); /* jmp *%rcx */ -# else /* !CONFIG_X86_64 */ -# define RETPOLINE_EDX_BPF_JIT() \ - EMIT2(0xFF, 0xE2) /* jmp *%edx */ -# endif -#endif - #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h index 94dbd51df58f..b13f8488ac85 100644 --- a/arch/x86/include/asm/page_32.h +++ b/arch/x86/include/asm/page_32.h @@ -43,7 +43,7 @@ static inline void copy_page(void *to, void *from) { memcpy(to, from, PAGE_SIZE); } -#endif /* CONFIG_X86_3DNOW */ +#endif /* CONFIG_X86_USE_3DNOW */ #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PAGE_32_H */ diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index a8d4ad856568..e9e2c3ba5923 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -15,7 +15,7 @@ #define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER) #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER) +#define EXCEPTION_STACK_ORDER (1 + KASAN_STACK_ORDER) #define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER) #define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index da3a1ac82be5..cebec95a7124 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -52,11 +52,11 @@ void __init paravirt_set_cap(void); /* The paravirtualized I/O functions */ static inline void slow_down_io(void) { - pv_ops.cpu.io_delay(); + PVOP_VCALL0(cpu.io_delay); #ifdef REALLY_SLOW_IO - pv_ops.cpu.io_delay(); - pv_ops.cpu.io_delay(); - pv_ops.cpu.io_delay(); + PVOP_VCALL0(cpu.io_delay); + PVOP_VCALL0(cpu.io_delay); + PVOP_VCALL0(cpu.io_delay); #endif } @@ -113,12 +113,12 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx, /* * These special macros can be used to get or set a debugging register */ -static inline unsigned long paravirt_get_debugreg(int reg) +static __always_inline unsigned long paravirt_get_debugreg(int reg) { return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg); } #define get_debugreg(var, reg) var = paravirt_get_debugreg(reg) -static inline void set_debugreg(unsigned long val, int reg) +static __always_inline void set_debugreg(unsigned long val, int reg) { PVOP_VCALL2(cpu.set_debugreg, reg, val); } @@ -133,14 +133,14 @@ static inline void write_cr0(unsigned long x) PVOP_VCALL1(cpu.write_cr0, x); } -static inline unsigned long read_cr2(void) +static __always_inline unsigned long read_cr2(void) { return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2, "mov %%cr2, %%rax;", ALT_NOT(X86_FEATURE_XENPV)); } -static inline void write_cr2(unsigned long x) +static __always_inline void write_cr2(unsigned long x) { PVOP_VCALL1(mmu.write_cr2, x); } @@ -653,10 +653,10 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); * functions. */ #define PV_THUNK_NAME(func) "__raw_callee_save_" #func -#define PV_CALLEE_SAVE_REGS_THUNK(func) \ +#define __PV_CALLEE_SAVE_REGS_THUNK(func, section) \ extern typeof(func) __raw_callee_save_##func; \ \ - asm(".pushsection .text;" \ + asm(".pushsection " section ", \"ax\";" \ ".globl " PV_THUNK_NAME(func) ";" \ ".type " PV_THUNK_NAME(func) ", @function;" \ PV_THUNK_NAME(func) ":" \ @@ -669,6 +669,9 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ ".popsection") +#define PV_CALLEE_SAVE_REGS_THUNK(func) \ + __PV_CALLEE_SAVE_REGS_THUNK(func, ".text") + /* Get a reference to a callee-save function */ #define PV_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { __raw_callee_save_##func }) @@ -678,23 +681,23 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); ((struct paravirt_callee_save) { func }) #ifdef CONFIG_PARAVIRT_XXL -static inline notrace unsigned long arch_local_save_flags(void) +static __always_inline unsigned long arch_local_save_flags(void) { return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;", ALT_NOT(X86_FEATURE_XENPV)); } -static inline notrace void arch_local_irq_disable(void) +static __always_inline void arch_local_irq_disable(void) { PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV)); } -static inline notrace void arch_local_irq_enable(void) +static __always_inline void arch_local_irq_enable(void) { PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV)); } -static inline notrace unsigned long arch_local_irq_save(void) +static __always_inline unsigned long arch_local_irq_save(void) { unsigned long f; diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 5c7bcaa79623..1d5f14aff5f6 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H -#define ARCH_DEFAULT_PKEY 0 - /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h index ccc539faa5bb..4cd49afa0ca4 100644 --- a/arch/x86/include/asm/pkru.h +++ b/arch/x86/include/asm/pkru.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_PKRU_H #define _ASM_X86_PKRU_H -#include <asm/fpu/xstate.h> +#include <asm/cpufeature.h> #define PKRU_AD_BIT 0x1 #define PKRU_WD_BIT 0x2 diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 9ad2acaaae9b..191878a65c61 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -164,7 +164,8 @@ enum cpuid_regs_idx { #define X86_VENDOR_NSC 8 #define X86_VENDOR_HYGON 9 #define X86_VENDOR_ZHAOXIN 10 -#define X86_VENDOR_NUM 11 +#define X86_VENDOR_VORTEX 11 +#define X86_VENDOR_NUM 12 #define X86_VENDOR_UNKNOWN 0xff @@ -461,9 +462,6 @@ DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr); #endif /* !X86_64 */ -extern unsigned int fpu_kernel_xstate_size; -extern unsigned int fpu_user_xstate_size; - struct perf_event; struct thread_struct { @@ -518,6 +516,7 @@ struct thread_struct { */ unsigned long iopl_emul; + unsigned int iopl_warn:1; unsigned int sig_on_uaccess_err:1; /* @@ -537,12 +536,12 @@ struct thread_struct { */ }; -/* Whitelist the FPU state from the task_struct for hardened usercopy. */ +extern void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size); + static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { - *offset = offsetof(struct thread_struct, fpu.state); - *size = fpu_kernel_xstate_size; + fpu_thread_struct_whitelist(offset, size); } static inline void @@ -589,7 +588,7 @@ static inline void load_sp0(unsigned long sp0) /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); /* * Generic CPUID function diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 8c5d1910a848..feed36d44d04 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -40,6 +40,6 @@ void x86_report_nx(void); extern int reboot_force; long do_arch_prctl_common(struct task_struct *task, int option, - unsigned long cpuid_enabled); + unsigned long arg2); #endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index b94f615600d5..703663175a5a 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -181,7 +181,7 @@ static inline bool any_64bit_mode(struct pt_regs *regs) #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp -static inline bool ip_within_syscall_gap(struct pt_regs *regs) +static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs) { bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 72044026eb3c..8dd8e8ec9fa5 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -339,7 +339,7 @@ static inline void __loadsegment_fs(unsigned short value) "1: movw %0, %%fs \n" "2: \n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs) + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_CLEAR_FS) : : "rm" (value) : "memory"); } diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index fa5cd05d3b5b..ec060c433589 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -53,6 +53,7 @@ static inline u64 lower_bits(u64 val, unsigned int bits) struct real_mode_header; enum stack_type; +struct ghcb; /* Early IDT entry points for #VC handler */ extern void vc_no_ghcb(void); @@ -81,6 +82,11 @@ static __always_inline void sev_es_nmi_complete(void) __sev_es_nmi_complete(); } extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); +extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, + bool set_ghcb_msr, + struct es_em_ctxt *ctxt, + u64 exit_code, u64 exit_info_1, + u64 exit_info_2); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 630ff08532be..08b0e90623ad 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -16,7 +16,9 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); /* cpus sharing the last level cache: */ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); +DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); +DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); static inline struct cpumask *cpu_llc_shared_mask(int cpu) @@ -24,6 +26,11 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu) return per_cpu(cpu_llc_shared_map, cpu); } +static inline struct cpumask *cpu_l2c_shared_mask(int cpu) +{ + return per_cpu(cpu_l2c_shared_map, cpu); +} + DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index f3fbb84ff8a7..68c257a3de0d 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -275,7 +275,7 @@ static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } __iomem *__dst = dst; - int zf; + bool zf; /* * ENQCMDS %(rdx), rax diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f248eb2ac2d4..3881b5333eb8 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -38,6 +38,16 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, struct stack_info *info); +static __always_inline +bool get_stack_guard_info(unsigned long *stack, struct stack_info *info) +{ + /* make sure it's not in the stack proper */ + if (get_stack_info_noinstr(stack, current, info)) + return false; + /* but if it is in the page below it, we hit a guard */ + return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info); +} + const char *stack_type_name(enum stack_type type); static inline bool on_stack(struct stack_info *info, void *addr, size_t len) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index cf132663c219..ebec69c35e95 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -57,6 +57,9 @@ struct thread_info { unsigned long flags; /* low level flags */ unsigned long syscall_work; /* SYSCALL_WORK_ flags */ u32 status; /* thread synchronous flags */ +#ifdef CONFIG_SMP + u32 cpu; /* current CPU */ +#endif }; #define INIT_THREAD_INFO(tsk) \ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 9239399e5491..cc164777e661 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -103,6 +103,7 @@ static inline void setup_node_to_cpumask_map(void) { } #include <asm-generic/topology.h> extern const struct cpumask *cpu_coregroup_mask(int cpu); +extern const struct cpumask *cpu_clustergroup_mask(int cpu); #define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id) #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) @@ -113,7 +114,9 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); extern unsigned int __max_die_per_package; #ifdef CONFIG_SMP +#define topology_cluster_id(cpu) (per_cpu(cpu_l2c_id, cpu)) #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) +#define topology_cluster_cpumask(cpu) (cpu_clustergroup_mask(cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 879b77792f94..4645a6334063 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -22,8 +22,8 @@ DECLARE_EVENT_CLASS(x86_fpu, __entry->fpu = fpu; __entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD); if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { - __entry->xfeatures = fpu->state.xsave.header.xfeatures; - __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; + __entry->xfeatures = fpu->fpstate->regs.xsave.header.xfeatures; + __entry->xcomp_bv = fpu->fpstate->regs.xsave.header.xcomp_bv; } ), TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx", diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 7f7200021bd1..6221be7cafc3 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -40,9 +40,9 @@ void math_emulate(struct math_emu_info *); bool fault_in_kernel_space(unsigned long address); #ifdef CONFIG_VMAP_STACK -void __noreturn handle_stack_overflow(const char *message, - struct pt_regs *regs, - unsigned long fault_address); +void __noreturn handle_stack_overflow(struct pt_regs *regs, + unsigned long fault_address, + struct stack_info *info); #endif #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 5c95d242f38d..33a68407def3 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -411,7 +411,7 @@ do { \ : [umem] "m" (__m(addr)), \ [efault] "i" (-EFAULT), "0" (err)) -#endif // CONFIG_CC_ASM_GOTO_OUTPUT +#endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 70fc159ebe69..2a1f8734416d 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -4,6 +4,7 @@ #include <linux/sched.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> @@ -15,6 +16,9 @@ struct unwind_state { unsigned long stack_mask; struct task_struct *task; int graph_idx; +#ifdef CONFIG_KRETPROBES + struct llist_node *kr_cur; +#endif bool error; #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; @@ -99,6 +103,31 @@ void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {} #endif +static inline +unsigned long unwind_recover_kretprobe(struct unwind_state *state, + unsigned long addr, unsigned long *addr_p) +{ +#ifdef CONFIG_KRETPROBES + return is_kretprobe_trampoline(addr) ? + kretprobe_find_ret_addr(state->task, addr_p, &state->kr_cur) : + addr; +#else + return addr; +#endif +} + +/* Recover the return address modified by kretprobe and ftrace_graph. */ +static inline +unsigned long unwind_recover_ret_addr(struct unwind_state *state, + unsigned long addr, unsigned long *addr_p) +{ + unsigned long ret; + + ret = ftrace_graph_ret_addr(state->task, &state->graph_idx, + addr, addr_p); + return unwind_recover_kretprobe(state, ret, addr_p); +} + /* * This disables KASAN checking when reading a value from another task's stack, * since the other task could be running on another CPU and could have poisoned diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 8e574c0afef8..8b33674288ea 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -52,6 +52,11 @@ UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC .endm +#else + +#define UNWIND_HINT_FUNC \ + UNWIND_HINT(ORC_REG_SP, 8, UNWIND_HINT_TYPE_FUNC, 0) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_UNWIND_HINTS_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 454b20815f35..4a7ff8b0db20 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -308,13 +308,13 @@ HYPERVISOR_platform_op(struct xen_platform_op *op) return _hypercall1(int, platform_op, op); } -static inline int +static __always_inline int HYPERVISOR_set_debugreg(int reg, unsigned long value) { return _hypercall2(int, set_debugreg, reg, value); } -static inline unsigned long +static __always_inline unsigned long HYPERVISOR_get_debugreg(int reg) { return _hypercall1(unsigned long, get_debugreg, reg); @@ -358,7 +358,7 @@ HYPERVISOR_event_channel_op(int cmd, void *arg) return _hypercall2(int, event_channel_op, cmd, arg); } -static inline int +static __always_inline int HYPERVISOR_xen_version(int cmd, void *arg) { return _hypercall2(int, xen_version, cmd, arg); diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 3506d8c598c1..4557f7cb0fa6 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -14,16 +14,19 @@ static inline int pci_xen_hvm_init(void) return -1; } #endif -#if defined(CONFIG_XEN_DOM0) +#ifdef CONFIG_XEN_PV_DOM0 int __init pci_xen_initial_domain(void); -int xen_find_device_domain_owner(struct pci_dev *dev); -int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); -int xen_unregister_device_domain_owner(struct pci_dev *dev); #else static inline int __init pci_xen_initial_domain(void) { return -1; } +#endif +#ifdef CONFIG_XEN_DOM0 +int xen_find_device_domain_owner(struct pci_dev *dev); +int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); +int xen_unregister_device_domain_owner(struct pci_dev *dev); +#else static inline int xen_find_device_domain_owner(struct pci_dev *dev) { return -1; diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h index 6b56d0d45d15..66b4ddde7743 100644 --- a/arch/x86/include/asm/xen/swiotlb-xen.h +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -3,14 +3,10 @@ #define _ASM_X86_SWIOTLB_XEN_H #ifdef CONFIG_SWIOTLB_XEN -extern int xen_swiotlb; extern int __init pci_xen_swiotlb_detect(void); -extern void __init pci_xen_swiotlb_init(void); extern int pci_xen_swiotlb_init_late(void); #else -#define xen_swiotlb (0) -static inline int __init pci_xen_swiotlb_detect(void) { return 0; } -static inline void __init pci_xen_swiotlb_init(void) { } +#define pci_xen_swiotlb_detect NULL static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; } #endif diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 2ef1f6513c68..5a776a08f78c 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -504,4 +504,8 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ +#define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ +#define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 5a6aac9fa41f..754a07856817 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -10,6 +10,10 @@ #define ARCH_GET_CPUID 0x1011 #define ARCH_SET_CPUID 0x1012 +#define ARCH_GET_XCOMP_SUPP 0x1021 +#define ARCH_GET_XCOMP_PERM 0x1022 +#define ARCH_REQ_XCOMP_PERM 0x1023 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 diff --git a/arch/x86/include/uapi/asm/sgx.h b/arch/x86/include/uapi/asm/sgx.h index 9690d6899ad9..f4b81587e90b 100644 --- a/arch/x86/include/uapi/asm/sgx.h +++ b/arch/x86/include/uapi/asm/sgx.h @@ -27,6 +27,8 @@ enum sgx_page_flags { _IOW(SGX_MAGIC, 0x02, struct sgx_enclave_init) #define SGX_IOC_ENCLAVE_PROVISION \ _IOW(SGX_MAGIC, 0x03, struct sgx_enclave_provision) +#define SGX_IOC_VEPC_REMOVE_ALL \ + _IO(SGX_MAGIC, 0x04) /** * struct sgx_enclave_create - parameter structure for the diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8f4e8fa6ed75..2ff3e600f426 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -21,6 +21,7 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_sev.o = -pg +CFLAGS_REMOVE_cc_platform.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -29,6 +30,7 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n KASAN_SANITIZE_sev.o := n +KASAN_SANITIZE_cc_platform.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. @@ -47,6 +49,7 @@ endif KCOV_INSTRUMENT := n CFLAGS_head$(BITS).o += -fno-stack-protector +CFLAGS_cc_platform.o += -fno-stack-protector CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace @@ -147,6 +150,9 @@ obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o + +obj-$(CONFIG_ARCH_HAS_CC_PLATFORM) += cc_platform.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 14bcd59bcdee..5b6d1a95776f 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -62,6 +62,7 @@ int acpi_fix_pin2_polarity __initdata; #ifdef CONFIG_X86_LOCAL_APIC static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; +static bool acpi_support_online_capable; #endif #ifdef CONFIG_X86_IO_APIC @@ -138,6 +139,8 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) pr_debug("Local APIC address 0x%08x\n", madt->address); } + if (madt->header.revision >= 5) + acpi_support_online_capable = true; default_acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id); @@ -239,6 +242,12 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) if (processor->id == 0xff) return 0; + /* don't register processors that can not be onlined */ + if (acpi_support_online_capable && + !(processor->lapic_flags & ACPI_MADT_ENABLED) && + !(processor->lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 7de599eba7f0..7945eae5b315 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -79,6 +79,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, */ flags->bm_control = 0; } + if (c->x86_vendor == X86_VENDOR_AMD && c->x86 >= 0x17) { + /* + * For all AMD Zen or newer CPUs that support C3, caches + * should not be flushed by software while entering C3 + * type state. Set bm->check to 1 so that kernel doesn't + * need to execute cache flush operation. + */ + flags->bm_check = 1; + /* + * In current AMD C state implementation ARB_DIS is no longer + * used. So set bm_control to zero to indicate ARB_DIS is not + * required while entering C3 type state. + */ + flags->bm_control = 0; + } } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e9da3dc71254..23fb4d51a5da 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -29,6 +29,7 @@ #include <asm/io.h> #include <asm/fixmap.h> #include <asm/paravirt.h> +#include <asm/asm-prototypes.h> int __read_mostly alternatives_patched; @@ -113,6 +114,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) } } +extern s32 __retpoline_sites[], __retpoline_sites_end[]; extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); @@ -221,7 +223,7 @@ static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off) * "noinline" to cause control flow change and thus invalidate I$ and * cause refetch after modification. */ -static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr) +static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) { struct insn insn; int i = 0; @@ -239,11 +241,11 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins * optimized. */ if (insn.length == 1 && insn.opcode.bytes[0] == 0x90) - i += optimize_nops_range(instr, a->instrlen, i); + i += optimize_nops_range(instr, len, i); else i += insn.length; - if (i >= a->instrlen) + if (i >= len) return; } } @@ -331,10 +333,185 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, text_poke_early(instr, insn_buff, insn_buff_sz); next: - optimize_nops(a, instr); + optimize_nops(instr, a->instrlen); } } +#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION) + +/* + * CALL/JMP *%\reg + */ +static int emit_indirect(int op, int reg, u8 *bytes) +{ + int i = 0; + u8 modrm; + + switch (op) { + case CALL_INSN_OPCODE: + modrm = 0x10; /* Reg = 2; CALL r/m */ + break; + + case JMP32_INSN_OPCODE: + modrm = 0x20; /* Reg = 4; JMP r/m */ + break; + + default: + WARN_ON_ONCE(1); + return -1; + } + + if (reg >= 8) { + bytes[i++] = 0x41; /* REX.B prefix */ + reg -= 8; + } + + modrm |= 0xc0; /* Mod = 3 */ + modrm += reg; + + bytes[i++] = 0xff; /* opcode */ + bytes[i++] = modrm; + + return i; +} + +/* + * Rewrite the compiler generated retpoline thunk calls. + * + * For spectre_v2=off (!X86_FEATURE_RETPOLINE), rewrite them into immediate + * indirect instructions, avoiding the extra indirection. + * + * For example, convert: + * + * CALL __x86_indirect_thunk_\reg + * + * into: + * + * CALL *%\reg + * + * It also tries to inline spectre_v2=retpoline,amd when size permits. + */ +static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) +{ + retpoline_thunk_t *target; + int reg, ret, i = 0; + u8 op, cc; + + target = addr + insn->length + insn->immediate.value; + reg = target - __x86_indirect_thunk_array; + + if (WARN_ON_ONCE(reg & ~0xf)) + return -1; + + /* If anyone ever does: CALL/JMP *%rsp, we're in deep trouble. */ + BUG_ON(reg == 4); + + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) && + !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) + return -1; + + op = insn->opcode.bytes[0]; + + /* + * Convert: + * + * Jcc.d32 __x86_indirect_thunk_\reg + * + * into: + * + * Jncc.d8 1f + * [ LFENCE ] + * JMP *%\reg + * [ NOP ] + * 1: + */ + /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */ + if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) { + cc = insn->opcode.bytes[1] & 0xf; + cc ^= 1; /* invert condition */ + + bytes[i++] = 0x70 + cc; /* Jcc.d8 */ + bytes[i++] = insn->length - 2; /* sizeof(Jcc.d8) == 2 */ + + /* Continue as if: JMP.d32 __x86_indirect_thunk_\reg */ + op = JMP32_INSN_OPCODE; + } + + /* + * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE. + */ + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + bytes[i++] = 0x0f; + bytes[i++] = 0xae; + bytes[i++] = 0xe8; /* LFENCE */ + } + + ret = emit_indirect(op, reg, bytes + i); + if (ret < 0) + return ret; + i += ret; + + for (; i < insn->length;) + bytes[i++] = BYTES_NOP1; + + return i; +} + +/* + * Generated by 'objtool --retpoline'. + */ +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + struct insn insn; + int len, ret; + u8 bytes[16]; + u8 op1, op2; + + ret = insn_decode_kernel(&insn, addr); + if (WARN_ON_ONCE(ret < 0)) + continue; + + op1 = insn.opcode.bytes[0]; + op2 = insn.opcode.bytes[1]; + + switch (op1) { + case CALL_INSN_OPCODE: + case JMP32_INSN_OPCODE: + break; + + case 0x0f: /* escape */ + if (op2 >= 0x80 && op2 <= 0x8f) + break; + fallthrough; + default: + WARN_ON_ONCE(1); + continue; + } + + DPRINTK("retpoline at: %pS (%px) len: %d to: %pS", + addr, addr, insn.length, + addr + insn.length + insn.immediate.value); + + len = patch_retpoline(addr, &insn, bytes); + if (len == insn.length) { + optimize_nops(bytes, len); + DUMP_BYTES(((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr); + text_poke_early(addr, bytes, len); + } + } +} + +#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */ + +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } + +#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */ + #ifdef CONFIG_SMP static void alternatives_smp_lock(const s32 *start, const s32 *end, u8 *text, u8 *text_end) @@ -643,6 +820,12 @@ void __init alternative_instructions(void) apply_paravirt(__parainstructions, __parainstructions_end); /* + * Rewrite the retpolines, must be done before alternatives since + * those can rewrite the retpoline thunks. + */ + apply_retpolines(__retpoline_sites, __retpoline_sites_end); + + /* * Then patch alternatives, such that those paravirt calls that are in * alternatives can be overwritten by their immediate fragments. */ diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index f4da9bb69a88..e696e22d0531 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -15,9 +15,15 @@ struct cluster_mask { struct cpumask mask; }; -static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid); +/* + * __x2apic_send_IPI_mask() possibly needs to read + * x86_cpu_to_logical_apicid for all online cpus in a sequential way. + * Using per cpu variable would cost one cache line per cpu. + */ +static u32 *x86_cpu_to_logical_apicid __read_mostly; + static DEFINE_PER_CPU(cpumask_var_t, ipi_mask); -static DEFINE_PER_CPU(struct cluster_mask *, cluster_masks); +static DEFINE_PER_CPU_READ_MOSTLY(struct cluster_mask *, cluster_masks); static struct cluster_mask *cluster_hotplug_mask; static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) @@ -27,7 +33,7 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) static void x2apic_send_IPI(int cpu, int vector) { - u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + u32 dest = x86_cpu_to_logical_apicid[cpu]; /* x2apic MSRs are special and need a special fence: */ weak_wrmsr_fence(); @@ -58,7 +64,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) dest = 0; for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask) - dest |= per_cpu(x86_cpu_to_logical_apicid, clustercpu); + dest |= x86_cpu_to_logical_apicid[clustercpu]; if (!dest) continue; @@ -94,7 +100,7 @@ static void x2apic_send_IPI_all(int vector) static u32 x2apic_calc_apicid(unsigned int cpu) { - return per_cpu(x86_cpu_to_logical_apicid, cpu); + return x86_cpu_to_logical_apicid[cpu]; } static void init_x2apic_ldr(void) @@ -103,7 +109,7 @@ static void init_x2apic_ldr(void) u32 cluster, apicid = apic_read(APIC_LDR); unsigned int cpu; - this_cpu_write(x86_cpu_to_logical_apicid, apicid); + x86_cpu_to_logical_apicid[smp_processor_id()] = apicid; if (cmsk) goto update; @@ -166,12 +172,21 @@ static int x2apic_dead_cpu(unsigned int dead_cpu) static int x2apic_cluster_probe(void) { + u32 slots; + if (!x2apic_mode) return 0; + slots = max_t(u32, L1_CACHE_BYTES/sizeof(u32), nr_cpu_ids); + x86_cpu_to_logical_apicid = kcalloc(slots, sizeof(u32), GFP_KERNEL); + if (!x86_cpu_to_logical_apicid) + return 0; + if (cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare", x2apic_prepare_cpu, x2apic_dead_cpu) < 0) { pr_err("Failed to register X2APIC_PREPARE\n"); + kfree(x86_cpu_to_logical_apicid); + x86_cpu_to_logical_apicid = NULL; return 0; } init_x2apic_ldr(); diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c index 83d9cad4e68b..44c3601cfdc4 100644 --- a/arch/x86/kernel/audit_64.c +++ b/arch/x86/kernel/audit_64.c @@ -47,14 +47,16 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_execve: case __NR_execveat: - return 5; + return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/x86/kernel/cc_platform.c b/arch/x86/kernel/cc_platform.c new file mode 100644 index 000000000000..03bb2f343ddb --- /dev/null +++ b/arch/x86/kernel/cc_platform.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Confidential Computing Platform Capability checks + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + */ + +#include <linux/export.h> +#include <linux/cc_platform.h> +#include <linux/mem_encrypt.h> + +#include <asm/processor.h> + +static bool __maybe_unused intel_cc_platform_has(enum cc_attr attr) +{ +#ifdef CONFIG_INTEL_TDX_GUEST + return false; +#else + return false; +#endif +} + +/* + * SME and SEV are very similar but they are not the same, so there are + * times that the kernel will need to distinguish between SME and SEV. The + * cc_platform_has() function is used for this. When a distinction isn't + * needed, the CC_ATTR_MEM_ENCRYPT attribute can be used. + * + * The trampoline code is a good example for this requirement. Before + * paging is activated, SME will access all memory as decrypted, but SEV + * will access all memory as encrypted. So, when APs are being brought + * up under SME the trampoline area cannot be encrypted, whereas under SEV + * the trampoline area must be encrypted. + */ +static bool amd_cc_platform_has(enum cc_attr attr) +{ +#ifdef CONFIG_AMD_MEM_ENCRYPT + switch (attr) { + case CC_ATTR_MEM_ENCRYPT: + return sme_me_mask; + + case CC_ATTR_HOST_MEM_ENCRYPT: + return sme_me_mask && !(sev_status & MSR_AMD64_SEV_ENABLED); + + case CC_ATTR_GUEST_MEM_ENCRYPT: + return sev_status & MSR_AMD64_SEV_ENABLED; + + case CC_ATTR_GUEST_STATE_ENCRYPT: + return sev_status & MSR_AMD64_SEV_ES_ENABLED; + + default: + return false; + } +#else + return false; +#endif +} + + +bool cc_platform_has(enum cc_attr attr) +{ + if (sme_me_mask) + return amd_cc_platform_has(attr); + + return false; +} +EXPORT_SYMBOL_GPL(cc_platform_has); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 637b499450d1..9661e3e802be 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -43,6 +43,7 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_CPU_SUP_ZHAOXIN) += zhaoxin.o +obj-$(CONFIG_CPU_SUP_VORTEX_32) += vortex.o obj-$(CONFIG_X86_MCE) += mce/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2131af9f2fa2..4edb6f0f628c 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -989,6 +989,8 @@ static void init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_IRPERF) && !cpu_has_amd_erratum(c, amd_erratum_1054)) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); + + check_null_seg_clears_base(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ecfca3bbcd96..1c1f218a701d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -22,7 +22,7 @@ #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/msr.h> #include <asm/vmx.h> #include <asm/paravirt.h> @@ -758,11 +758,11 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) case SPECTRE_V2_USER_CMD_FORCE: mode = SPECTRE_V2_USER_STRICT; break; + case SPECTRE_V2_USER_CMD_AUTO: case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: mode = SPECTRE_V2_USER_PRCTL; break; - case SPECTRE_V2_USER_CMD_AUTO: case SPECTRE_V2_USER_CMD_SECCOMP: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: if (IS_ENABLED(CONFIG_SECCOMP)) @@ -882,13 +882,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } - if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && - boot_cpu_data.x86_vendor != X86_VENDOR_HYGON && - boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); - return SPECTRE_V2_CMD_AUTO; - } - spec_v2_print_cond(mitigation_options[i].option, mitigation_options[i].secure); return cmd; @@ -1169,7 +1162,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) return mode; switch (cmd) { - case SPEC_STORE_BYPASS_CMD_AUTO: case SPEC_STORE_BYPASS_CMD_SECCOMP: /* * Choose prctl+seccomp as the default mode if seccomp is @@ -1183,6 +1175,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) case SPEC_STORE_BYPASS_CMD_ON: mode = SPEC_STORE_BYPASS_DISABLE; break; + case SPEC_STORE_BYPASS_CMD_AUTO: case SPEC_STORE_BYPASS_CMD_PRCTL: mode = SPEC_STORE_BYPASS_PRCTL; break; diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index b5e36bd0425b..fe98a1465be6 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -846,6 +846,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) l2 = new_l2; #ifdef CONFIG_SMP per_cpu(cpu_llc_id, cpu) = l2_id; + per_cpu(cpu_l2c_id, cpu) = l2_id; #endif } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0f8885949e8c..0083464de5e3 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -42,7 +42,7 @@ #include <asm/setup.h> #include <asm/apic.h> #include <asm/desc.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/mtrr.h> #include <asm/hwcap2.h> #include <linux/numa.h> @@ -85,6 +85,9 @@ u16 get_llc_id(unsigned int cpu) } EXPORT_SYMBOL_GPL(get_llc_id); +/* L2 cache ID of each logical CPU */ +DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id) = BAD_APICID; + /* correctly size the local cpu masks */ void __init setup_cpu_local_masks(void) { @@ -326,6 +329,7 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_SMAP cr4_set_bits(X86_CR4_SMAP); #else + clear_cpu_cap(c, X86_FEATURE_SMAP); cr4_clear_bits(X86_CR4_SMAP); #endif } @@ -1044,6 +1048,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(CENTAUR, 5, X86_MODEL_ANY, NO_SPECULATION), VULNWL(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION), VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(VORTEX, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(VORTEX, 6, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), @@ -1395,9 +1401,8 @@ void __init early_cpu_init(void) early_identify_cpu(&boot_cpu_data); } -static void detect_null_seg_behavior(struct cpuinfo_x86 *c) +static bool detect_null_seg_behavior(void) { -#ifdef CONFIG_X86_64 /* * Empirically, writing zero to a segment selector on AMD does * not clear the base, whereas writing zero to a segment @@ -1418,10 +1423,43 @@ static void detect_null_seg_behavior(struct cpuinfo_x86 *c) wrmsrl(MSR_FS_BASE, 1); loadsegment(fs, 0); rdmsrl(MSR_FS_BASE, tmp); - if (tmp != 0) - set_cpu_bug(c, X86_BUG_NULL_SEG); wrmsrl(MSR_FS_BASE, old_base); -#endif + return tmp == 0; +} + +void check_null_seg_clears_base(struct cpuinfo_x86 *c) +{ + /* BUG_NULL_SEG is only relevant with 64bit userspace */ + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Zen3 CPUs advertise Null Selector Clears Base in CPUID. */ + if (c->extended_cpuid_level >= 0x80000021 && + cpuid_eax(0x80000021) & BIT(6)) + return; + + /* + * CPUID bit above wasn't set. If this kernel is still running + * as a HV guest, then the HV has decided not to advertize + * that CPUID bit for whatever reason. For example, one + * member of the migration pool might be vulnerable. Which + * means, the bug is present: set the BUG flag and return. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) { + set_cpu_bug(c, X86_BUG_NULL_SEG); + return; + } + + /* + * Zen2 CPUs also have this behaviour, but no CPUID bit. + * 0x18 is the respective family for Hygon. + */ + if ((c->x86 == 0x17 || c->x86 == 0x18) && + detect_null_seg_behavior()) + return; + + /* All the remaining ones are affected */ + set_cpu_bug(c, X86_BUG_NULL_SEG); } static void generic_identify(struct cpuinfo_x86 *c) @@ -1457,8 +1495,6 @@ static void generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - detect_null_seg_behavior(c); - /* * ESPFIX is a strange bug. All real CPUs have it. Paravirt * systems that run Linux at CPL > 0 may or may not have the diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 95521302630d..ee6f23f7587d 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -75,6 +75,7 @@ extern int detect_extended_topology_early(struct cpuinfo_x86 *c); extern int detect_extended_topology(struct cpuinfo_x86 *c); extern int detect_ht_early(struct cpuinfo_x86 *c); extern void detect_ht(struct cpuinfo_x86 *c); +extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index defda61f372d..cb2fdd130aae 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -75,6 +75,8 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_SGX_LC, X86_FEATURE_SGX }, { X86_FEATURE_SGX1, X86_FEATURE_SGX }, { X86_FEATURE_SGX2, X86_FEATURE_SGX1 }, + { X86_FEATURE_XFD, X86_FEATURE_XSAVES }, + { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, {} }; diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 6d50136f7ab9..3fcdda4c1e11 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -335,6 +335,8 @@ static void init_hygon(struct cpuinfo_x86 *c) /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + check_null_seg_clears_base(c); } static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 08831acc1d03..fc85eb17cb6d 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -119,7 +119,7 @@ const char *smca_get_long_name(enum smca_bank_types t) } EXPORT_SYMBOL_GPL(smca_get_long_name); -static enum smca_bank_types smca_get_bank_type(unsigned int bank) +enum smca_bank_types smca_get_bank_type(unsigned int bank) { struct smca_bank *b; @@ -132,6 +132,7 @@ static enum smca_bank_types smca_get_bank_type(unsigned int bank) return b->hwid->bank_type; } +EXPORT_SYMBOL_GPL(smca_get_bank_type); static struct smca_hwid smca_hwid_mcatypes[] = { /* { bank_type, hwid_mcatype } */ @@ -526,7 +527,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high, /* Fall back to method we used for older processors: */ switch (block) { case 0: - addr = msr_ops.misc(bank); + addr = mca_msr_reg(bank, MCA_MISC); break; case 1: offset = ((low & MASK_BLKPTR_LO) >> 21); @@ -978,8 +979,8 @@ static void log_error_deferred(unsigned int bank) { bool defrd; - defrd = _log_error_bank(bank, msr_ops.status(bank), - msr_ops.addr(bank), 0); + defrd = _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), + mca_msr_reg(bank, MCA_ADDR), 0); if (!mce_flags.smca) return; @@ -1009,7 +1010,7 @@ static void amd_deferred_error_interrupt(void) static void log_error_thresholding(unsigned int bank, u64 misc) { - _log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc); + _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), mca_msr_reg(bank, MCA_ADDR), misc); } static void log_and_reset_block(struct threshold_block *block) @@ -1397,7 +1398,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, } } - err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + err = allocate_threshold_blocks(cpu, b, bank, 0, mca_msr_reg(bank, MCA_MISC)); if (err) goto out_kobj; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 193204aee880..6ed365337a3b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -121,8 +121,6 @@ mce_banks_t mce_banks_ce_disabled; static struct work_struct mce_work; static struct irq_work mce_irq_work; -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. @@ -176,53 +174,27 @@ void mce_unregister_decode_chain(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); -static inline u32 ctl_reg(int bank) -{ - return MSR_IA32_MCx_CTL(bank); -} - -static inline u32 status_reg(int bank) -{ - return MSR_IA32_MCx_STATUS(bank); -} - -static inline u32 addr_reg(int bank) -{ - return MSR_IA32_MCx_ADDR(bank); -} - -static inline u32 misc_reg(int bank) +u32 mca_msr_reg(int bank, enum mca_msr reg) { - return MSR_IA32_MCx_MISC(bank); -} - -static inline u32 smca_ctl_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_CTL(bank); -} - -static inline u32 smca_status_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_STATUS(bank); -} + if (mce_flags.smca) { + switch (reg) { + case MCA_CTL: return MSR_AMD64_SMCA_MCx_CTL(bank); + case MCA_ADDR: return MSR_AMD64_SMCA_MCx_ADDR(bank); + case MCA_MISC: return MSR_AMD64_SMCA_MCx_MISC(bank); + case MCA_STATUS: return MSR_AMD64_SMCA_MCx_STATUS(bank); + } + } -static inline u32 smca_addr_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_ADDR(bank); -} + switch (reg) { + case MCA_CTL: return MSR_IA32_MCx_CTL(bank); + case MCA_ADDR: return MSR_IA32_MCx_ADDR(bank); + case MCA_MISC: return MSR_IA32_MCx_MISC(bank); + case MCA_STATUS: return MSR_IA32_MCx_STATUS(bank); + } -static inline u32 smca_misc_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_MISC(bank); + return 0; } -struct mca_msr_regs msr_ops = { - .ctl = ctl_reg, - .status = status_reg, - .addr = addr_reg, - .misc = misc_reg -}; - static void __print_mce(struct mce *m) { pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n", @@ -362,24 +334,27 @@ static int msr_to_offset(u32 msr) if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); - if (msr == msr_ops.status(bank)) + if (msr == mca_msr_reg(bank, MCA_STATUS)) return offsetof(struct mce, status); - if (msr == msr_ops.addr(bank)) + if (msr == mca_msr_reg(bank, MCA_ADDR)) return offsetof(struct mce, addr); - if (msr == msr_ops.misc(bank)) + if (msr == mca_msr_reg(bank, MCA_MISC)) return offsetof(struct mce, misc); if (msr == MSR_IA32_MCG_STATUS) return offsetof(struct mce, mcgstatus); return -1; } -__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) { - pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", - (unsigned int)regs->cx, regs->ip, (void *)regs->ip); + if (wrmsr) { + pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, + regs->ip, (void *)regs->ip); + } else { + pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, regs->ip, (void *)regs->ip); + } show_stack_regs(regs); @@ -387,8 +362,6 @@ __visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup, while (true) cpu_relax(); - - return true; } /* MSR access wrappers used for error injection */ @@ -420,32 +393,13 @@ static noinstr u64 mce_rdmsrl(u32 msr) */ asm volatile("1: rdmsr\n" "2:\n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_fault) + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR_IN_MCE) : EAX_EDX_RET(val, low, high) : "c" (msr)); return EAX_EDX_VAL(val, low, high); } -__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) -{ - pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", - (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, - regs->ip, (void *)regs->ip); - - show_stack_regs(regs); - - panic("MCA architectural violation!\n"); - - while (true) - cpu_relax(); - - return true; -} - static noinstr void mce_wrmsrl(u32 msr, u64 v) { u32 low, high; @@ -470,7 +424,7 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v) /* See comment in mce_rdmsrl() */ asm volatile("1: wrmsr\n" "2:\n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_fault) + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE) : : "c" (msr), "a"(low), "d" (high) : "memory"); } @@ -685,10 +639,10 @@ static struct notifier_block mce_default_nb = { static void mce_read_aux(struct mce *m, int i) { if (m->status & MCI_STATUS_MISCV) - m->misc = mce_rdmsrl(msr_ops.misc(i)); + m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC)); if (m->status & MCI_STATUS_ADDRV) { - m->addr = mce_rdmsrl(msr_ops.addr(i)); + m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR)); /* * Mask the reported address by the reported granularity. @@ -758,7 +712,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) m.bank = i; barrier(); - m.status = mce_rdmsrl(msr_ops.status(i)); + m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); /* If this entry is not valid, ignore it */ if (!(m.status & MCI_STATUS_VAL)) @@ -826,7 +780,7 @@ clear_it: /* * Clear state for this bank. */ - mce_wrmsrl(msr_ops.status(i), 0); + mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); } /* @@ -841,6 +795,34 @@ clear_it: EXPORT_SYMBOL_GPL(machine_check_poll); /* + * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and + * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM + * Vol 3B Table 15-20). But this confuses both the code that determines + * whether the machine check occurred in kernel or user mode, and also + * the severity assessment code. Pretend that EIPV was set, and take the + * ip/cs values from the pt_regs that mce_gather_info() ignored earlier. + */ +static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 0) + return; + if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0) + return; + if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC| + MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV| + MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR| + MCACOD)) != + (MCI_STATUS_UC|MCI_STATUS_EN| + MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S| + MCI_STATUS_AR|MCACOD_INSTR)) + return; + + m->mcgstatus |= MCG_STATUS_EIPV; + m->ip = regs->ip; + m->cs = regs->cs; +} + +/* * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. */ @@ -851,13 +833,13 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, int i; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { - m->status = mce_rdmsrl(msr_ops.status(i)); + m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); if (!(m->status & MCI_STATUS_VAL)) continue; __set_bit(i, validp); - if (quirk_no_way_out) - quirk_no_way_out(i, m, regs); + if (mce_flags.snb_ifu_quirk) + quirk_sandybridge_ifu(i, m, regs); m->bank = i; if (mce_severity(m, regs, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { @@ -1144,7 +1126,7 @@ static void mce_clear_state(unsigned long *toclear) for (i = 0; i < this_cpu_read(mce_num_banks); i++) { if (test_bit(i, toclear)) - mce_wrmsrl(msr_ops.status(i), 0); + mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); } } @@ -1203,7 +1185,7 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin m->addr = 0; m->bank = i; - m->status = mce_rdmsrl(msr_ops.status(i)); + m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); if (!(m->status & MCI_STATUS_VAL)) continue; @@ -1272,7 +1254,7 @@ static void kill_me_maybe(struct callback_head *cb) flags |= MF_MUST_KILL; ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags); - if (!ret && !(p->mce_kflags & MCE_IN_KERNEL_COPYIN)) { + if (!ret) { set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page); sync_core(); return; @@ -1286,15 +1268,21 @@ static void kill_me_maybe(struct callback_head *cb) if (ret == -EHWPOISON) return; - if (p->mce_vaddr != (void __user *)-1l) { - force_sig_mceerr(BUS_MCEERR_AR, p->mce_vaddr, PAGE_SHIFT); - } else { - pr_err("Memory error not recovered"); - kill_me_now(cb); - } + pr_err("Memory error not recovered"); + kill_me_now(cb); +} + +static void kill_me_never(struct callback_head *cb) +{ + struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); + + p->mce_count = 0; + pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr); + if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0)) + set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page); } -static void queue_task_work(struct mce *m, char *msg, int kill_current_task) +static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *)) { int count = ++current->mce_count; @@ -1304,11 +1292,7 @@ static void queue_task_work(struct mce *m, char *msg, int kill_current_task) current->mce_kflags = m->kflags; current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); current->mce_whole_page = whole_page(m); - - if (kill_current_task) - current->mce_kill_me.func = kill_me_now; - else - current->mce_kill_me.func = kill_me_maybe; + current->mce_kill_me.func = func; } /* Ten is likely overkill. Don't expect more than two faults before task_work() */ @@ -1326,6 +1310,15 @@ static void queue_task_work(struct mce *m, char *msg, int kill_current_task) task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); } +/* Handle unconfigured int18 (should never happen) */ +static noinstr void unexpected_machine_check(struct pt_regs *regs) +{ + instrumentation_begin(); + pr_err("CPU#%d: Unexpected int18 (Machine Check)\n", + smp_processor_id()); + instrumentation_end(); +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -1346,36 +1339,43 @@ static void queue_task_work(struct mce *m, char *msg, int kill_current_task) */ noinstr void do_machine_check(struct pt_regs *regs) { + int worst = 0, order, no_way_out, kill_current_task, lmce; DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; struct mce m, *final; char *msg = NULL; - int worst = 0; + + if (unlikely(mce_flags.p5)) + return pentium_machine_check(regs); + else if (unlikely(mce_flags.winchip)) + return winchip_machine_check(regs); + else if (unlikely(!mca_cfg.initialized)) + return unexpected_machine_check(regs); /* * Establish sequential order between the CPUs entering the machine * check handler. */ - int order = -1; + order = -1; /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. */ - int no_way_out = 0; + no_way_out = 0; /* * If kill_current_task is not set, there might be a way to recover from this * error. */ - int kill_current_task = 0; + kill_current_task = 0; /* * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES * on Intel. */ - int lmce = 1; + lmce = 1; this_cpu_inc(mce_exception_count); @@ -1459,7 +1459,10 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - queue_task_work(&m, msg, kill_current_task); + if (kill_current_task) + queue_task_work(&m, msg, kill_me_now); + else + queue_task_work(&m, msg, kill_me_maybe); } else { /* @@ -1477,7 +1480,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, msg, kill_current_task); + queue_task_work(&m, msg, kill_me_never); } out: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); @@ -1687,8 +1690,8 @@ static void __mcheck_cpu_init_clear_banks(void) if (!b->init) continue; - wrmsrl(msr_ops.ctl(i), b->ctl); - wrmsrl(msr_ops.status(i), 0); + wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl); + wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); } } @@ -1714,39 +1717,11 @@ static void __mcheck_cpu_check_banks(void) if (!b->init) continue; - rdmsrl(msr_ops.ctl(i), msrval); + rdmsrl(mca_msr_reg(i, MCA_CTL), msrval); b->init = !!msrval; } } -/* - * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and - * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM - * Vol 3B Table 15-20). But this confuses both the code that determines - * whether the machine check occurred in kernel or user mode, and also - * the severity assessment code. Pretend that EIPV was set, and take the - * ip/cs values from the pt_regs that mce_gather_info() ignored earlier. - */ -static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) -{ - if (bank != 0) - return; - if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0) - return; - if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC| - MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV| - MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR| - MCACOD)) != - (MCI_STATUS_UC|MCI_STATUS_EN| - MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S| - MCI_STATUS_AR|MCACOD_INSTR)) - return; - - m->mcgstatus |= MCG_STATUS_EIPV; - m->ip = regs->ip; - m->cs = regs->cs; -} - /* Add per CPU specific workarounds here */ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { @@ -1820,7 +1795,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) cfg->bootlog = 0; if (c->x86 == 6 && c->x86_model == 45) - quirk_no_way_out = quirk_sandybridge_ifu; + mce_flags.snb_ifu_quirk = 1; } if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { @@ -1850,9 +1825,11 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: intel_p5_mcheck_init(c); + mce_flags.p5 = 1; return 1; case X86_VENDOR_CENTAUR: winchip_mcheck_init(c); + mce_flags.winchip = 1; return 1; default: return 0; @@ -1871,13 +1848,6 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); mce_flags.amd_threshold = 1; - - 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; - } } } @@ -2007,18 +1977,6 @@ bool filter_mce(struct mce *m) return false; } -/* Handle unconfigured int18 (should never happen) */ -static noinstr void unexpected_machine_check(struct pt_regs *regs) -{ - instrumentation_begin(); - pr_err("CPU#%d: Unexpected int18 (Machine Check)\n", - smp_processor_id()); - instrumentation_end(); -} - -/* Call the installed machine check handler for this CPU setup. */ -void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; - static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { irqentry_state_t irq_state; @@ -2029,31 +1987,22 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) * Only required when from kernel mode. See * mce_check_crashing_cpu() for details. */ - if (machine_check_vector == do_machine_check && - mce_check_crashing_cpu()) + if (mca_cfg.initialized && mce_check_crashing_cpu()) return; irq_state = irqentry_nmi_enter(regs); - /* - * The call targets are marked noinstr, but objtool can't figure - * that out because it's an indirect call. Annotate it. - */ - instrumentation_begin(); - machine_check_vector(regs); + do_machine_check(regs); - instrumentation_end(); irqentry_nmi_exit(regs, irq_state); } static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); - instrumentation_begin(); - machine_check_vector(regs); + do_machine_check(regs); - instrumentation_end(); irqentry_exit_to_user_mode(regs); } @@ -2120,7 +2069,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) return; } - machine_check_vector = do_machine_check; + mca_cfg.initialized = 1; __mcheck_cpu_init_early(c); __mcheck_cpu_init_generic(); @@ -2228,7 +2177,6 @@ int __init mcheck_init(void) mce_register_decode_chain(&early_nb); mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); - mcheck_vendor_init_severity(); INIT_WORK(&mce_work, mce_gen_pool_process); init_irq_work(&mce_irq_work, mce_irq_work_cb); @@ -2253,7 +2201,7 @@ static void mce_disable_error_reporting(void) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(msr_ops.ctl(i), 0); + wrmsrl(mca_msr_reg(i, MCA_CTL), 0); } return; } @@ -2605,7 +2553,7 @@ static void mce_reenable_cpu(void) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(msr_ops.ctl(i), b->ctl); + wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl); } } diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 88dcc79cfb07..acd61c41846c 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -8,9 +8,6 @@ #include <linux/device.h> #include <asm/mce.h> -/* Pointer to the installed machine check handler for this CPU setup. */ -extern void (*machine_check_vector)(struct pt_regs *); - enum severity_level { MCE_NO_SEVERITY, MCE_DEFERRED_SEVERITY, @@ -38,8 +35,7 @@ int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); struct llist_node *mce_gen_pool_prepare_records(void); -extern int (*mce_severity)(struct mce *a, struct pt_regs *regs, - int tolerant, char **msg, bool is_excp); +int mce_severity(struct mce *a, struct pt_regs *regs, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern mce_banks_t mce_banks_ce_disabled; @@ -61,7 +57,7 @@ static inline void cmci_disable_bank(int bank) { } static inline void intel_init_cmci(void) { } static inline void intel_init_lmce(void) { } static inline void intel_clear_lmce(void) { } -static inline bool intel_filter_mce(struct mce *m) { return false; }; +static inline bool intel_filter_mce(struct mce *m) { return false; } #endif void mce_timer_kick(unsigned long interval); @@ -117,23 +113,25 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif struct mca_config { - bool dont_log_ce; - bool cmci_disabled; - bool ignore_ce; - bool print_all; - __u64 lmce_disabled : 1, disabled : 1, ser : 1, recovery : 1, bios_cmci_threshold : 1, - __reserved : 59; + /* Proper #MC exception handler is set */ + initialized : 1, + __reserved : 58; + + bool dont_log_ce; + bool cmci_disabled; + bool ignore_ce; + bool print_all; - s8 bootlog; int tolerant; int monarch_timeout; int panic_timeout; u32 rip_msr; + s8 bootlog; }; extern struct mca_config mca_cfg; @@ -163,19 +161,28 @@ struct mce_vendor_flags { /* AMD-style error thresholding banks present. */ amd_threshold : 1, - __reserved_0 : 60; + /* Pentium, family 5-style MCA */ + p5 : 1, + + /* Centaur Winchip C6-style MCA */ + winchip : 1, + + /* SandyBridge IFU quirk */ + snb_ifu_quirk : 1, + + __reserved_0 : 57; }; extern struct mce_vendor_flags mce_flags; -struct mca_msr_regs { - u32 (*ctl) (int bank); - u32 (*status) (int bank); - u32 (*addr) (int bank); - u32 (*misc) (int bank); +enum mca_msr { + MCA_CTL, + MCA_STATUS, + MCA_ADDR, + MCA_MISC, }; -extern struct mca_msr_regs msr_ops; +u32 mca_msr_reg(int bank, enum mca_msr reg); /* Decide whether to add MCE record to MCE event pool or filter it out. */ extern bool filter_mce(struct mce *m); @@ -183,17 +190,21 @@ extern bool filter_mce(struct mce *m); #ifdef CONFIG_X86_MCE_AMD extern bool amd_filter_mce(struct mce *m); #else -static inline bool amd_filter_mce(struct mce *m) { return false; }; +static inline bool amd_filter_mce(struct mce *m) { return false; } #endif -__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr); - -__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr); +#ifdef CONFIG_X86_ANCIENT_MCE +void intel_p5_mcheck_init(struct cpuinfo_x86 *c); +void winchip_mcheck_init(struct cpuinfo_x86 *c); +noinstr void pentium_machine_check(struct pt_regs *regs); +noinstr void winchip_machine_check(struct pt_regs *regs); +static inline void enable_p5_mce(void) { mce_p5_enabled = 1; } +#else +static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {} +static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {} +static inline void enable_p5_mce(void) {} +static inline void pentium_machine_check(struct pt_regs *regs) {} +static inline void winchip_machine_check(struct pt_regs *regs) {} +#endif #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mce/p5.c b/arch/x86/kernel/cpu/mce/p5.c index 19e90cae8e97..2272ad53fc33 100644 --- a/arch/x86/kernel/cpu/mce/p5.c +++ b/arch/x86/kernel/cpu/mce/p5.c @@ -21,7 +21,7 @@ int mce_p5_enabled __read_mostly; /* Machine check handler for Pentium class Intel CPUs: */ -static noinstr void pentium_machine_check(struct pt_regs *regs) +noinstr void pentium_machine_check(struct pt_regs *regs) { u32 loaddr, hi, lotype; @@ -54,10 +54,6 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c) if (!cpu_has(c, X86_FEATURE_MCE)) return; - machine_check_vector = pentium_machine_check; - /* Make sure the vector pointer is visible before we enable MCEs: */ - wmb(); - /* Read registers before enabling: */ rdmsr(MSR_IA32_P5_MC_ADDR, l, h); rdmsr(MSR_IA32_P5_MC_TYPE, l, h); diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 17e631443116..bb019a594a2c 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -265,25 +265,25 @@ static bool is_copy_from_user(struct pt_regs *regs) */ static int error_context(struct mce *m, struct pt_regs *regs) { - enum handler_type t; - if ((m->cs & 3) == 3) return IN_USER; if (!mc_recoverable(m->mcgstatus)) return IN_KERNEL; - t = ex_get_fault_handler_type(m->ip); - if (t == EX_HANDLER_FAULT) { - m->kflags |= MCE_IN_KERNEL_RECOV; - return IN_KERNEL_RECOV; - } - if (t == EX_HANDLER_UACCESS && regs && is_copy_from_user(regs)) { - m->kflags |= MCE_IN_KERNEL_RECOV; + switch (ex_get_fixup_type(m->ip)) { + case EX_TYPE_UACCESS: + case EX_TYPE_COPY: + if (!regs || !is_copy_from_user(regs)) + return IN_KERNEL; m->kflags |= MCE_IN_KERNEL_COPYIN; + fallthrough; + case EX_TYPE_FAULT_MCE_SAFE: + case EX_TYPE_DEFAULT_MCE_SAFE: + m->kflags |= MCE_IN_KERNEL_RECOV; return IN_KERNEL_RECOV; + default: + return IN_KERNEL; } - - return IN_KERNEL; } static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) @@ -407,15 +407,14 @@ static int mce_severity_intel(struct mce *m, struct pt_regs *regs, } } -/* Default to mce_severity_intel */ -int (*mce_severity)(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, bool is_excp) = - mce_severity_intel; - -void __init mcheck_vendor_init_severity(void) +int mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, + bool is_excp) { if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - mce_severity = mce_severity_amd; + return mce_severity_amd(m, regs, tolerant, msg, is_excp); + else + return mce_severity_intel(m, regs, tolerant, msg, is_excp); } #ifdef CONFIG_DEBUG_FS diff --git a/arch/x86/kernel/cpu/mce/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c index 9c9f0abd2d7f..6c99f2941909 100644 --- a/arch/x86/kernel/cpu/mce/winchip.c +++ b/arch/x86/kernel/cpu/mce/winchip.c @@ -17,7 +17,7 @@ #include "internal.h" /* Machine check handler for WinChip C6: */ -static noinstr void winchip_machine_check(struct pt_regs *regs) +noinstr void winchip_machine_check(struct pt_regs *regs) { instrumentation_begin(); pr_emerg("CPU0: Machine Check Exception.\n"); @@ -30,10 +30,6 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c) { u32 lo, hi; - machine_check_vector = winchip_machine_check; - /* Make sure the vector pointer is visible before we enable MCEs: */ - wmb(); - rdmsr(MSR_IDT_FCR1, lo, hi); lo |= (1<<2); /* Enable EIERRINT (int 18 MCE) */ lo &= ~(1<<4); /* Enable MCE */ diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 3d4a48336084..8b2fcdfa6d31 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -456,17 +456,23 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) { -#ifdef CONFIG_X86_64 char fw_name[36] = "amd-ucode/microcode_amd.bin"; + struct firmware fw; + + if (IS_ENABLED(CONFIG_X86_32)) + return false; if (family >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", family); - return get_builtin_firmware(cp, fw_name); -#else + if (firmware_request_builtin(&fw, fw_name)) { + cp->size = fw.size; + cp->data = (void *)fw.data; + return true; + } + return false; -#endif } static void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index efb69be41ab1..f955d25076ba 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -140,23 +140,6 @@ static bool __init check_loader_disabled_bsp(void) return *res; } -extern struct builtin_fw __start_builtin_fw[]; -extern struct builtin_fw __end_builtin_fw[]; - -bool get_builtin_firmware(struct cpio_data *cd, const char *name) -{ - struct builtin_fw *b_fw; - - for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { - if (!strcmp(name, b_fw->name)) { - cd->size = b_fw->size; - cd->data = b_fw->data; - return true; - } - } - return false; -} - void __init load_ucode_bsp(void) { unsigned int cpuid_1_eax; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 7e8e07bddd5f..d28a9f8f3fec 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -456,6 +456,7 @@ static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int s static bool load_builtin_intel_microcode(struct cpio_data *cp) { unsigned int eax = 1, ebx, ecx = 0, edx; + struct firmware fw; char name[30]; if (IS_ENABLED(CONFIG_X86_32)) @@ -466,7 +467,13 @@ static bool load_builtin_intel_microcode(struct cpio_data *cp) sprintf(name, "intel-ucode/%02x-%02x-%02x", x86_family(eax), x86_model(eax), x86_stepping(eax)); - return get_builtin_firmware(cp, name); + if (firmware_request_builtin(&fw, name)) { + cp->size = fw.size; + cp->data = (void *)fw.data; + return true; + } + + return false; } /* diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e095c28d27ae..4794b716ec79 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -313,9 +313,14 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.priv_high & HV_ISOLATION) { ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG); ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG); + ms_hyperv.shared_gpa_boundary = + BIT_ULL(ms_hyperv.shared_gpa_boundary_bits); pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); + + if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) + static_branch_enable(&isolation_type_snp); } if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) { diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 4b8813bafffd..bb1c3f5f60c8 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -527,12 +527,14 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) rdt_domain_reconfigure_cdp(r); if (r->alloc_capable && domain_setup_ctrlval(r, d)) { - kfree(d); + kfree(hw_dom); return; } if (r->mon_capable && domain_setup_mon_state(r, d)) { - kfree(d); + kfree(hw_dom->ctrl_val); + kfree(hw_dom->mbps_val); + kfree(hw_dom); return; } diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c index 64511c4a5200..6a77a14eee38 100644 --- a/arch/x86/kernel/cpu/sgx/virt.c +++ b/arch/x86/kernel/cpu/sgx/virt.c @@ -111,10 +111,8 @@ static int sgx_vepc_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static int sgx_vepc_free_page(struct sgx_epc_page *epc_page) +static int sgx_vepc_remove_page(struct sgx_epc_page *epc_page) { - int ret; - /* * Take a previously guest-owned EPC page and return it to the * general EPC page pool. @@ -124,7 +122,12 @@ static int sgx_vepc_free_page(struct sgx_epc_page *epc_page) * case that a guest properly EREMOVE'd this page, a superfluous * EREMOVE is harmless. */ - ret = __eremove(sgx_get_epc_virt_addr(epc_page)); + return __eremove(sgx_get_epc_virt_addr(epc_page)); +} + +static int sgx_vepc_free_page(struct sgx_epc_page *epc_page) +{ + int ret = sgx_vepc_remove_page(epc_page); if (ret) { /* * Only SGX_CHILD_PRESENT is expected, which is because of @@ -144,10 +147,44 @@ static int sgx_vepc_free_page(struct sgx_epc_page *epc_page) } sgx_free_epc_page(epc_page); - return 0; } +static long sgx_vepc_remove_all(struct sgx_vepc *vepc) +{ + struct sgx_epc_page *entry; + unsigned long index; + long failures = 0; + + xa_for_each(&vepc->page_array, index, entry) { + int ret = sgx_vepc_remove_page(entry); + if (ret) { + if (ret == SGX_CHILD_PRESENT) { + /* The page is a SECS, userspace will retry. */ + failures++; + } else { + /* + * Report errors due to #GP or SGX_ENCLAVE_ACT; do not + * WARN, as userspace can induce said failures by + * calling the ioctl concurrently on multiple vEPCs or + * while one or more CPUs is running the enclave. Only + * a #PF on EREMOVE indicates a kernel/hardware issue. + */ + WARN_ON_ONCE(encls_faulted(ret) && + ENCLS_TRAPNR(ret) != X86_TRAP_GP); + return -EBUSY; + } + } + cond_resched(); + } + + /* + * Return the number of SECS pages that failed to be removed, so + * userspace knows that it has to retry. + */ + return failures; +} + static int sgx_vepc_release(struct inode *inode, struct file *file) { struct sgx_vepc *vepc = file->private_data; @@ -233,9 +270,27 @@ static int sgx_vepc_open(struct inode *inode, struct file *file) return 0; } +static long sgx_vepc_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct sgx_vepc *vepc = file->private_data; + + switch (cmd) { + case SGX_IOC_VEPC_REMOVE_ALL: + if (arg) + return -EINVAL; + return sgx_vepc_remove_all(vepc); + + default: + return -ENOTTY; + } +} + static const struct file_operations sgx_vepc_fops = { .owner = THIS_MODULE, .open = sgx_vepc_open, + .unlocked_ioctl = sgx_vepc_ioctl, + .compat_ioctl = sgx_vepc_ioctl, .release = sgx_vepc_release, .mmap = sgx_vepc_mmap, }; diff --git a/arch/x86/kernel/cpu/vortex.c b/arch/x86/kernel/cpu/vortex.c new file mode 100644 index 000000000000..e2685470ba94 --- /dev/null +++ b/arch/x86/kernel/cpu/vortex.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <asm/processor.h> +#include "cpu.h" + +/* + * No special init required for Vortex processors. + */ + +static const struct cpu_dev vortex_cpu_dev = { + .c_vendor = "Vortex", + .c_ident = { "Vortex86 SoC" }, + .legacy_models = { + { + .family = 5, + .model_names = { + [2] = "Vortex86DX", + [8] = "Vortex86MX", + }, + }, + { + .family = 6, + .model_names = { + /* + * Both the Vortex86EX and the Vortex86EX2 + * have the same family and model id. + * + * However, the -EX2 supports the product name + * CPUID call, so this name will only be used + * for the -EX, which does not. + */ + [0] = "Vortex86EX", + }, + }, + }, + .c_x86_vendor = X86_VENDOR_VORTEX, +}; + +cpu_dev_register(vortex_cpu_dev); diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index 045e82e8945b..a7f617a3981d 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -10,6 +10,7 @@ #include <linux/crash_dump.h> #include <linux/uaccess.h> #include <linux/io.h> +#include <linux/cc_platform.h> static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf, @@ -73,5 +74,6 @@ ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize, ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, sev_active()); + return read_from_oldmem(buf, count, ppos, 0, + cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 6a4cb71c2498..5cd51f25f446 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -31,11 +31,6 @@ char __initdata cmd_line[COMMAND_LINE_SIZE]; int __initdata of_ioapic; -void __init early_init_dt_scan_chosen_arch(unsigned long node) -{ - BUG(); -} - void __init early_init_dt_add_memory_arch(u64 base, u64 size) { BUG(); @@ -139,12 +134,11 @@ static void __init dtb_cpu_setup(void) { struct device_node *dn; u32 apic_id, version; - int ret; version = GET_APIC_VERSION(apic_read(APIC_LVR)); for_each_of_cpu_node(dn) { - ret = of_property_read_u32(dn, "reg", &apic_id); - if (ret < 0) { + apic_id = of_get_cpu_hwid(dn, 0); + if (apic_id == ~0U) { pr_warn("%pOF: missing local APIC ID\n", dn); continue; } diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 5601b95944fa..6c5defd6569a 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -32,9 +32,15 @@ const char *stack_type_name(enum stack_type type) { BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); + if (type == STACK_TYPE_TASK) + return "TASK"; + if (type == STACK_TYPE_IRQ) return "IRQ"; + if (type == STACK_TYPE_SOFTIRQ) + return "SOFTIRQ"; + if (type == STACK_TYPE_ENTRY) { /* * On 64-bit, we have a generic entry stack that we diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 38837dad46e6..391a4e2b8604 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -714,12 +714,6 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x3e20, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x3ec4, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x8a12, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index 2954fab15e51..794e70151203 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -2,7 +2,7 @@ /* * x86 FPU bug checks: */ -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> /* * Boot time CPU/FPU FDIV bug detection code: diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h new file mode 100644 index 000000000000..958accf2ccf0 --- /dev/null +++ b/arch/x86/kernel/fpu/context.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_KERNEL_FPU_CONTEXT_H +#define __X86_KERNEL_FPU_CONTEXT_H + +#include <asm/fpu/xstate.h> +#include <asm/trace/fpu.h> + +/* Functions related to FPU context tracking */ + +/* + * The in-register FPU state for an FPU context on a CPU is assumed to be + * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx + * matches the FPU. + * + * If the FPU register state is valid, the kernel can skip restoring the + * FPU state from memory. + * + * Any code that clobbers the FPU registers or updates the in-memory + * FPU state for a task MUST let the rest of the kernel know that the + * FPU registers are no longer valid for this task. + * + * Either one of these invalidation functions is enough. Invalidate + * a resource you control: CPU if using the CPU for something else + * (with preemption disabled), FPU for the current task, or a task that + * is prevented from running by the current task. + */ +static inline void __cpu_invalidate_fpregs_state(void) +{ + __this_cpu_write(fpu_fpregs_owner_ctx, NULL); +} + +static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) +{ + fpu->last_cpu = -1; +} + +static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) +{ + return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; +} + +static inline void fpregs_deactivate(struct fpu *fpu) +{ + __this_cpu_write(fpu_fpregs_owner_ctx, NULL); + trace_x86_fpu_regs_deactivated(fpu); +} + +static inline void fpregs_activate(struct fpu *fpu) +{ + __this_cpu_write(fpu_fpregs_owner_ctx, fpu); + trace_x86_fpu_regs_activated(fpu); +} + +/* Internal helper for switch_fpu_return() and signal frame setup */ +static inline void fpregs_restore_userregs(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + int cpu = smp_processor_id(); + + if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) + return; + + if (!fpregs_state_valid(fpu, cpu)) { + /* + * This restores _all_ xstate which has not been + * established yet. + * + * If PKRU is enabled, then the PKRU value is already + * correct because it was either set in switch_to() or in + * flush_thread(). So it is excluded because it might be + * not up to date in current->thread.fpu.xsave state. + * + * XFD state is handled in restore_fpregs_from_fpstate(). + */ + restore_fpregs_from_fpstate(fpu->fpstate, XFEATURE_MASK_FPSTATE); + + fpregs_activate(fpu); + fpu->last_cpu = cpu; + } + clear_thread_flag(TIF_NEED_FPU_LOAD); +} + +#endif diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 7ada7bd03a32..8ea306b1bf8e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -6,8 +6,9 @@ * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/fpu/regset.h> +#include <asm/fpu/sched.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/traps.h> @@ -15,15 +16,30 @@ #include <linux/hardirq.h> #include <linux/pkeys.h> +#include <linux/vmalloc.h> + +#include "context.h" +#include "internal.h" +#include "legacy.h" +#include "xstate.h" #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> +#ifdef CONFIG_X86_64 +DEFINE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); +DEFINE_PER_CPU(u64, xfd_state); +#endif + +/* The FPU state configuration data for kernel and user space */ +struct fpu_state_config fpu_kernel_cfg __ro_after_init; +struct fpu_state_config fpu_user_cfg __ro_after_init; + /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ -union fpregs_state init_fpstate __ro_after_init; +struct fpstate init_fpstate __ro_after_init; /* * Track whether the kernel is using the FPU state @@ -83,7 +99,7 @@ bool irq_fpu_usable(void) EXPORT_SYMBOL(irq_fpu_usable); /* - * Save the FPU register state in fpu->state. The register state is + * Save the FPU register state in fpu->fpstate->regs. The register state is * preserved. * * Must be called with fpregs_lock() held. @@ -99,19 +115,19 @@ EXPORT_SYMBOL(irq_fpu_usable); void save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { - os_xsave(&fpu->state.xsave); + os_xsave(fpu->fpstate); /* * AVX512 state is tracked here because its use is * known to slow the max clock speed of the core. */ - if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) + if (fpu->fpstate->regs.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; return; } if (likely(use_fxsr())) { - fxsave(&fpu->state.fxsave); + fxsave(&fpu->fpstate->regs.fxsave); return; } @@ -119,12 +135,11 @@ void save_fpregs_to_fpstate(struct fpu *fpu) * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to reload them from the memory state. */ - asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); - frstor(&fpu->state.fsave); + asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->fpstate->regs.fsave)); + frstor(&fpu->fpstate->regs.fsave); } -EXPORT_SYMBOL(save_fpregs_to_fpstate); -void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask) +void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask) { /* * AMD K7/K8 and later CPUs up to Zen don't save/restore @@ -141,15 +156,181 @@ void __restore_fpregs_from_fpstate(union fpregs_state *fpstate, u64 mask) } if (use_xsave()) { - os_xrstor(&fpstate->xsave, mask); + /* + * Dynamically enabled features are enabled in XCR0, but + * usage requires also that the corresponding bits in XFD + * are cleared. If the bits are set then using a related + * instruction will raise #NM. This allows to do the + * allocation of the larger FPU buffer lazy from #NM or if + * the task has no permission to kill it which would happen + * via #UD if the feature is disabled in XCR0. + * + * XFD state is following the same life time rules as + * XSTATE and to restore state correctly XFD has to be + * updated before XRSTORS otherwise the component would + * stay in or go into init state even if the bits are set + * in fpstate::regs::xsave::xfeatures. + */ + xfd_update_state(fpstate); + + /* + * Restoring state always needs to modify all features + * which are in @mask even if the current task cannot use + * extended features. + * + * So fpstate->xfeatures cannot be used here, because then + * a feature for which the task has no permission but was + * used by the previous task would not go into init state. + */ + mask = fpu_kernel_cfg.max_features & mask; + + os_xrstor(fpstate, mask); } else { if (use_fxsr()) - fxrstor(&fpstate->fxsave); + fxrstor(&fpstate->regs.fxsave); else - frstor(&fpstate->fsave); + frstor(&fpstate->regs.fsave); } } -EXPORT_SYMBOL_GPL(__restore_fpregs_from_fpstate); + +void fpu_reset_from_exception_fixup(void) +{ + restore_fpregs_from_fpstate(&init_fpstate, XFEATURE_MASK_FPSTATE); +} + +#if IS_ENABLED(CONFIG_KVM) +static void __fpstate_reset(struct fpstate *fpstate); + +bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) +{ + struct fpstate *fpstate; + unsigned int size; + + size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64); + fpstate = vzalloc(size); + if (!fpstate) + return false; + + __fpstate_reset(fpstate); + fpstate_init_user(fpstate); + fpstate->is_valloc = true; + fpstate->is_guest = true; + + gfpu->fpstate = fpstate; + return true; +} +EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate); + +void fpu_free_guest_fpstate(struct fpu_guest *gfpu) +{ + struct fpstate *fps = gfpu->fpstate; + + if (!fps) + return; + + if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use)) + return; + + gfpu->fpstate = NULL; + vfree(fps); +} +EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate); + +int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) +{ + struct fpstate *guest_fps = guest_fpu->fpstate; + struct fpu *fpu = ¤t->thread.fpu; + struct fpstate *cur_fps = fpu->fpstate; + + fpregs_lock(); + if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD)) + save_fpregs_to_fpstate(fpu); + + /* Swap fpstate */ + if (enter_guest) { + fpu->__task_fpstate = cur_fps; + fpu->fpstate = guest_fps; + guest_fps->in_use = true; + } else { + guest_fps->in_use = false; + fpu->fpstate = fpu->__task_fpstate; + fpu->__task_fpstate = NULL; + } + + cur_fps = fpu->fpstate; + + if (!cur_fps->is_confidential) { + /* Includes XFD update */ + restore_fpregs_from_fpstate(cur_fps, XFEATURE_MASK_FPSTATE); + } else { + /* + * XSTATE is restored by firmware from encrypted + * memory. Make sure XFD state is correct while + * running with guest fpstate + */ + xfd_update_state(cur_fps); + } + + fpregs_mark_activate(); + fpregs_unlock(); + return 0; +} +EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate); + +void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, + unsigned int size, u32 pkru) +{ + struct fpstate *kstate = gfpu->fpstate; + union fpregs_state *ustate = buf; + struct membuf mb = { .p = buf, .left = size }; + + if (cpu_feature_enabled(X86_FEATURE_XSAVE)) { + __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE); + } else { + memcpy(&ustate->fxsave, &kstate->regs.fxsave, + sizeof(ustate->fxsave)); + /* Make it restorable on a XSAVE enabled host */ + ustate->xsave.header.xfeatures = XFEATURE_MASK_FPSSE; + } +} +EXPORT_SYMBOL_GPL(fpu_copy_guest_fpstate_to_uabi); + +int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, + u64 xcr0, u32 *vpkru) +{ + struct fpstate *kstate = gfpu->fpstate; + const union fpregs_state *ustate = buf; + struct pkru_state *xpkru; + int ret; + + if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) { + if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE) + return -EINVAL; + if (ustate->fxsave.mxcsr & ~mxcsr_feature_mask) + return -EINVAL; + memcpy(&kstate->regs.fxsave, &ustate->fxsave, sizeof(ustate->fxsave)); + return 0; + } + + if (ustate->xsave.header.xfeatures & ~xcr0) + return -EINVAL; + + ret = copy_uabi_from_kernel_to_xstate(kstate, ustate); + if (ret) + return ret; + + /* Retrieve PKRU if not in init state */ + if (kstate->regs.xsave.header.xfeatures & XFEATURE_MASK_PKRU) { + xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU); + *vpkru = xpkru->pkru; + } + + /* Ensure that XCOMP_BV is set up for XSAVES */ + xstate_init_xcomp_bv(&kstate->regs.xsave, kstate->xfeatures); + return 0; +} +EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate); +#endif /* CONFIG_KVM */ void kernel_fpu_begin_mask(unsigned int kfpu_mask) { @@ -203,52 +384,88 @@ void fpu_sync_fpstate(struct fpu *fpu) fpregs_unlock(); } -static inline void fpstate_init_xstate(struct xregs_state *xsave) +static inline unsigned int init_fpstate_copy_size(void) { - /* - * XRSTORS requires these bits set in xcomp_bv, or it will - * trigger #GP: - */ - xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all; + if (!use_xsave()) + return fpu_kernel_cfg.default_size; + + /* XSAVE(S) just needs the legacy and the xstate header part */ + return sizeof(init_fpstate.regs.xsave); } -static inline void fpstate_init_fxstate(struct fxregs_state *fx) +static inline void fpstate_init_fxstate(struct fpstate *fpstate) { - fx->cwd = 0x37f; - fx->mxcsr = MXCSR_DEFAULT; + fpstate->regs.fxsave.cwd = 0x37f; + fpstate->regs.fxsave.mxcsr = MXCSR_DEFAULT; } /* * Legacy x87 fpstate state init: */ -static inline void fpstate_init_fstate(struct fregs_state *fp) +static inline void fpstate_init_fstate(struct fpstate *fpstate) { - fp->cwd = 0xffff037fu; - fp->swd = 0xffff0000u; - fp->twd = 0xffffffffu; - fp->fos = 0xffff0000u; + fpstate->regs.fsave.cwd = 0xffff037fu; + fpstate->regs.fsave.swd = 0xffff0000u; + fpstate->regs.fsave.twd = 0xffffffffu; + fpstate->regs.fsave.fos = 0xffff0000u; } -void fpstate_init(union fpregs_state *state) +/* + * Used in two places: + * 1) Early boot to setup init_fpstate for non XSAVE systems + * 2) fpu_init_fpstate_user() which is invoked from KVM + */ +void fpstate_init_user(struct fpstate *fpstate) { - if (!static_cpu_has(X86_FEATURE_FPU)) { - fpstate_init_soft(&state->soft); + if (!cpu_feature_enabled(X86_FEATURE_FPU)) { + fpstate_init_soft(&fpstate->regs.soft); return; } - memset(state, 0, fpu_kernel_xstate_size); + xstate_init_xcomp_bv(&fpstate->regs.xsave, fpstate->xfeatures); - if (static_cpu_has(X86_FEATURE_XSAVES)) - fpstate_init_xstate(&state->xsave); - if (static_cpu_has(X86_FEATURE_FXSR)) - fpstate_init_fxstate(&state->fxsave); + if (cpu_feature_enabled(X86_FEATURE_FXSR)) + fpstate_init_fxstate(fpstate); else - fpstate_init_fstate(&state->fsave); + fpstate_init_fstate(fpstate); +} + +static void __fpstate_reset(struct fpstate *fpstate) +{ + /* Initialize sizes and feature masks */ + fpstate->size = fpu_kernel_cfg.default_size; + fpstate->user_size = fpu_user_cfg.default_size; + fpstate->xfeatures = fpu_kernel_cfg.default_features; + fpstate->user_xfeatures = fpu_user_cfg.default_features; + fpstate->xfd = init_fpstate.xfd; +} + +void fpstate_reset(struct fpu *fpu) +{ + /* Set the fpstate pointer to the default fpstate */ + fpu->fpstate = &fpu->__fpstate; + __fpstate_reset(fpu->fpstate); + + /* Initialize the permission related info in fpu */ + fpu->perm.__state_perm = fpu_kernel_cfg.default_features; + fpu->perm.__state_size = fpu_kernel_cfg.default_size; + fpu->perm.__user_state_size = fpu_user_cfg.default_size; +} + +static inline void fpu_inherit_perms(struct fpu *dst_fpu) +{ + if (fpu_state_size_dynamic()) { + struct fpu *src_fpu = ¤t->group_leader->thread.fpu; + + spin_lock_irq(¤t->sighand->siglock); + /* Fork also inherits the permissions of the parent */ + dst_fpu->perm = src_fpu->perm; + spin_unlock_irq(¤t->sighand->siglock); + } } -EXPORT_SYMBOL_GPL(fpstate_init); /* Clone current's FPU state on fork */ -int fpu_clone(struct task_struct *dst) +int fpu_clone(struct task_struct *dst, unsigned long clone_flags) { struct fpu *src_fpu = ¤t->thread.fpu; struct fpu *dst_fpu = &dst->thread.fpu; @@ -256,30 +473,51 @@ int fpu_clone(struct task_struct *dst) /* The new task's FPU state cannot be valid in the hardware. */ dst_fpu->last_cpu = -1; + fpstate_reset(dst_fpu); + if (!cpu_feature_enabled(X86_FEATURE_FPU)) return 0; /* - * Don't let 'init optimized' areas of the XSAVE area - * leak into the child task: + * Enforce reload for user space tasks and prevent kernel threads + * from trying to save the FPU registers on context switch. + */ + set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); + + /* + * No FPU state inheritance for kernel threads and IO + * worker threads. + */ + if (dst->flags & (PF_KTHREAD | PF_IO_WORKER)) { + /* Clear out the minimal state */ + memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs, + init_fpstate_copy_size()); + return 0; + } + + /* + * If a new feature is added, ensure all dynamic features are + * caller-saved from here! */ - memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); + BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA); /* - * If the FPU registers are not owned by current just memcpy() the - * state. Otherwise save the FPU registers directly into the - * child's FPU context, without any memory-to-memory copying. + * Save the default portion of the current FPU state into the + * clone. Assume all dynamic features to be defined as caller- + * saved, which enables skipping both the expansion of fpstate + * and the copying of any dynamic state. + * + * Do not use memcpy() when TIF_NEED_FPU_LOAD is set because + * copying is not valid when current uses non-default states. */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) - memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); - - else - save_fpregs_to_fpstate(dst_fpu); + fpregs_restore_userregs(); + save_fpregs_to_fpstate(dst_fpu); + if (!(clone_flags & CLONE_THREAD)) + fpu_inherit_perms(dst_fpu); fpregs_unlock(); - set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); - trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); @@ -287,6 +525,16 @@ int fpu_clone(struct task_struct *dst) } /* + * Whitelist the FPU register state embedded into task_struct for hardened + * usercopy. + */ +void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size) +{ + *offset = offsetof(struct thread_struct, fpu.__fpstate.regs); + *size = fpu_kernel_cfg.default_size; +} + +/* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. @@ -319,28 +567,19 @@ void fpu__drop(struct fpu *fpu) static inline void restore_fpregs_from_init_fpstate(u64 features_mask) { if (use_xsave()) - os_xrstor(&init_fpstate.xsave, features_mask); + os_xrstor(&init_fpstate, features_mask); else if (use_fxsr()) - fxrstor(&init_fpstate.fxsave); + fxrstor(&init_fpstate.regs.fxsave); else - frstor(&init_fpstate.fsave); + frstor(&init_fpstate.regs.fsave); pkru_write_default(); } -static inline unsigned int init_fpstate_copy_size(void) -{ - if (!use_xsave()) - return fpu_kernel_xstate_size; - - /* XSAVE(S) just needs the legacy and the xstate header part */ - return sizeof(init_fpstate.xsave); -} - /* * Reset current->fpu memory state to the init values. */ -static void fpu_reset_fpstate(void) +static void fpu_reset_fpregs(void) { struct fpu *fpu = ¤t->thread.fpu; @@ -359,7 +598,7 @@ static void fpu_reset_fpstate(void) * user space as PKRU is eagerly written in switch_to() and * flush_thread(). */ - memcpy(&fpu->state, &init_fpstate, init_fpstate_copy_size()); + memcpy(&fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size()); set_thread_flag(TIF_NEED_FPU_LOAD); fpregs_unlock(); } @@ -375,7 +614,7 @@ void fpu__clear_user_states(struct fpu *fpu) fpregs_lock(); if (!cpu_feature_enabled(X86_FEATURE_FPU)) { - fpu_reset_fpstate(); + fpu_reset_fpregs(); fpregs_unlock(); return; } @@ -385,12 +624,11 @@ void fpu__clear_user_states(struct fpu *fpu) * corresponding registers. */ if (xfeatures_mask_supervisor() && - !fpregs_state_valid(fpu, smp_processor_id())) { - os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor()); - } + !fpregs_state_valid(fpu, smp_processor_id())) + os_xrstor_supervisor(fpu->fpstate); /* Reset user states in registers. */ - restore_fpregs_from_init_fpstate(xfeatures_mask_restore_user()); + restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE); /* * Now all FPU registers have their desired values. Inform the FPU @@ -405,7 +643,8 @@ void fpu__clear_user_states(struct fpu *fpu) void fpu_flush_thread(void) { - fpu_reset_fpstate(); + fpstate_reset(¤t->thread.fpu); + fpu_reset_fpregs(); } /* * Load FPU context before returning to userspace. @@ -445,7 +684,6 @@ void fpregs_mark_activate(void) fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } -EXPORT_SYMBOL_GPL(fpregs_mark_activate); /* * x87 math exception handling: @@ -468,11 +706,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { - cwd = fpu->state.fxsave.cwd; - swd = fpu->state.fxsave.swd; + cwd = fpu->fpstate->regs.fxsave.cwd; + swd = fpu->fpstate->regs.fxsave.swd; } else { - cwd = (unsigned short)fpu->state.fsave.cwd; - swd = (unsigned short)fpu->state.fsave.swd; + cwd = (unsigned short)fpu->fpstate->regs.fsave.cwd; + swd = (unsigned short)fpu->fpstate->regs.fsave.swd; } err = swd & ~cwd; @@ -486,7 +724,7 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) - mxcsr = fpu->state.fxsave.mxcsr; + mxcsr = fpu->fpstate->regs.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 64e29927cc32..621f4b6cac4a 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -2,7 +2,7 @@ /* * x86 FPU boot time init code: */ -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/tlbflush.h> #include <asm/setup.h> @@ -10,6 +10,10 @@ #include <linux/sched/task.h> #include <linux/init.h> +#include "internal.h" +#include "legacy.h" +#include "xstate.h" + /* * Initialize the registers found in all CPUs, CR0 and CR4: */ @@ -34,7 +38,7 @@ static void fpu__init_cpu_generic(void) /* Flush out any pending x87 state: */ #ifdef CONFIG_MATH_EMULATION if (!boot_cpu_has(X86_FEATURE_FPU)) - fpstate_init_soft(¤t->thread.fpu.state.soft); + fpstate_init_soft(¤t->thread.fpu.fpstate->regs.soft); else #endif asm volatile ("fninit"); @@ -121,23 +125,14 @@ static void __init fpu__init_system_mxcsr(void) static void __init fpu__init_system_generic(void) { /* - * Set up the legacy init FPU context. (xstate init might overwrite this - * with a more modern format, if the CPU supports it.) + * Set up the legacy init FPU context. Will be updated when the + * CPU supports XSAVE[S]. */ - fpstate_init(&init_fpstate); + fpstate_init_user(&init_fpstate); fpu__init_system_mxcsr(); } -/* - * Size of the FPU context state. All tasks in the system use the - * same context size, regardless of what portion they use. - * This is inherent to the XSAVE architecture which puts all state - * components into a single, continuous memory block: - */ -unsigned int fpu_kernel_xstate_size __ro_after_init; -EXPORT_SYMBOL_GPL(fpu_kernel_xstate_size); - /* Get alignment of the TYPE. */ #define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) @@ -162,13 +157,13 @@ static void __init fpu__init_task_struct_size(void) * Subtract off the static size of the register state. * It potentially has a bunch of padding. */ - task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state); + task_size -= sizeof(current->thread.fpu.__fpstate.regs); /* * Add back the dynamically-calculated register state * size. */ - task_size += fpu_kernel_xstate_size; + task_size += fpu_kernel_cfg.default_size; /* * We dynamically size 'struct fpu', so we require that @@ -177,7 +172,7 @@ static void __init fpu__init_task_struct_size(void) * you hit a compile error here, check the structure to * see if something got added to the end. */ - CHECK_MEMBER_AT_END_OF(struct fpu, state); + CHECK_MEMBER_AT_END_OF(struct fpu, __fpstate); CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); CHECK_MEMBER_AT_END_OF(struct task_struct, thread); @@ -192,37 +187,34 @@ static void __init fpu__init_task_struct_size(void) */ static void __init fpu__init_system_xstate_size_legacy(void) { - static int on_boot_cpu __initdata = 1; - - WARN_ON_FPU(!on_boot_cpu); - on_boot_cpu = 0; + unsigned int size; /* - * Note that xstate sizes might be overwritten later during - * fpu__init_system_xstate(). + * Note that the size configuration might be overwritten later + * during fpu__init_system_xstate(). */ - - if (!boot_cpu_has(X86_FEATURE_FPU)) { - fpu_kernel_xstate_size = sizeof(struct swregs_state); + if (!cpu_feature_enabled(X86_FEATURE_FPU)) { + size = sizeof(struct swregs_state); + } else if (cpu_feature_enabled(X86_FEATURE_FXSR)) { + size = sizeof(struct fxregs_state); + fpu_user_cfg.legacy_features = XFEATURE_MASK_FPSSE; } else { - if (boot_cpu_has(X86_FEATURE_FXSR)) - fpu_kernel_xstate_size = - sizeof(struct fxregs_state); - else - fpu_kernel_xstate_size = - sizeof(struct fregs_state); + size = sizeof(struct fregs_state); + fpu_user_cfg.legacy_features = XFEATURE_MASK_FP; } - fpu_user_xstate_size = fpu_kernel_xstate_size; + fpu_kernel_cfg.max_size = size; + fpu_kernel_cfg.default_size = size; + fpu_user_cfg.max_size = size; + fpu_user_cfg.default_size = size; + fpstate_reset(¤t->thread.fpu); } -/* Legacy code to initialize eager fpu mode. */ -static void __init fpu__init_system_ctx_switch(void) +static void __init fpu__init_init_fpstate(void) { - static bool on_boot_cpu __initdata = 1; - - WARN_ON_FPU(!on_boot_cpu); - on_boot_cpu = 0; + /* Bring init_fpstate size and features up to date */ + init_fpstate.size = fpu_kernel_cfg.max_size; + init_fpstate.xfeatures = fpu_kernel_cfg.max_features; } /* @@ -231,6 +223,7 @@ static void __init fpu__init_system_ctx_switch(void) */ void __init fpu__init_system(struct cpuinfo_x86 *c) { + fpstate_reset(¤t->thread.fpu); fpu__init_system_early_generic(c); /* @@ -241,8 +234,7 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) fpu__init_system_generic(); fpu__init_system_xstate_size_legacy(); - fpu__init_system_xstate(); + fpu__init_system_xstate(fpu_kernel_cfg.max_size); fpu__init_task_struct_size(); - - fpu__init_system_ctx_switch(); + fpu__init_init_fpstate(); } diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h new file mode 100644 index 000000000000..dbdb31f55fc7 --- /dev/null +++ b/arch/x86/kernel/fpu/internal.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_KERNEL_FPU_INTERNAL_H +#define __X86_KERNEL_FPU_INTERNAL_H + +extern struct fpstate init_fpstate; + +/* CPU feature check wrappers */ +static __always_inline __pure bool use_xsave(void) +{ + return cpu_feature_enabled(X86_FEATURE_XSAVE); +} + +static __always_inline __pure bool use_fxsr(void) +{ + return cpu_feature_enabled(X86_FEATURE_FXSR); +} + +#ifdef CONFIG_X86_DEBUG_FPU +# define WARN_ON_FPU(x) WARN_ON_ONCE(x) +#else +# define WARN_ON_FPU(x) ({ (void)(x); 0; }) +#endif + +/* Used in init.c */ +extern void fpstate_init_user(struct fpstate *fpstate); +extern void fpstate_reset(struct fpu *fpu); + +#endif diff --git a/arch/x86/kernel/fpu/legacy.h b/arch/x86/kernel/fpu/legacy.h new file mode 100644 index 000000000000..17c26b164c63 --- /dev/null +++ b/arch/x86/kernel/fpu/legacy.h @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_KERNEL_FPU_LEGACY_H +#define __X86_KERNEL_FPU_LEGACY_H + +#include <asm/fpu/types.h> + +extern unsigned int mxcsr_feature_mask; + +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + +/* + * Returns 0 on success or the trap number when the operation raises an + * exception. + */ +#define user_insn(insn, output, input...) \ +({ \ + int err; \ + \ + might_fault(); \ + \ + asm volatile(ASM_STAC "\n" \ + "1: " #insn "\n" \ + "2: " ASM_CLAC "\n" \ + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ + : [err] "=a" (err), output \ + : "0"(0), input); \ + err; \ +}) + +#define kernel_insn_err(insn, output, input...) \ +({ \ + int err; \ + asm volatile("1:" #insn "\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +#define kernel_insn(insn, output, input...) \ + asm volatile("1:" #insn "\n\t" \ + "2:\n" \ + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FPU_RESTORE) \ + : output : input) + +static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx) +{ + return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); +} + +static inline int fxsave_to_user_sigframe(struct fxregs_state __user *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); + else + return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); + +} + +static inline void fxrstor(struct fxregs_state *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline int fxrstor_safe(struct fxregs_state *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else + return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else + return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline void frstor(struct fregs_state *fx) +{ + kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline int frstor_safe(struct fregs_state *fx) +{ + return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline int frstor_from_user_sigframe(struct fregs_state __user *fx) +{ + return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline void fxsave(struct fxregs_state *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); + else + asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); +} + +#endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 66ed317ebc0d..437d7c930c0b 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -5,10 +5,14 @@ #include <linux/sched/task_stack.h> #include <linux/vmalloc.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/fpu/signal.h> #include <asm/fpu/regset.h> -#include <asm/fpu/xstate.h> + +#include "context.h" +#include "internal.h" +#include "legacy.h" +#include "xstate.h" /* * The xstateregs_active() routine is the same as the regset_fpregs_active() routine, @@ -74,8 +78,8 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, sync_fpstate(fpu); if (!use_xsave()) { - return membuf_write(&to, &fpu->state.fxsave, - sizeof(fpu->state.fxsave)); + return membuf_write(&to, &fpu->fpstate->regs.fxsave, + sizeof(fpu->fpstate->regs.fxsave)); } copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_FX); @@ -110,15 +114,15 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, fpu_force_restore(fpu); /* Copy the state */ - memcpy(&fpu->state.fxsave, &newstate, sizeof(newstate)); + memcpy(&fpu->fpstate->regs.fxsave, &newstate, sizeof(newstate)); /* Clear xmm8..15 */ - BUILD_BUG_ON(sizeof(fpu->state.fxsave.xmm_space) != 16 * 16); - memset(&fpu->state.fxsave.xmm_space[8], 0, 8 * 16); + BUILD_BUG_ON(sizeof(fpu->__fpstate.regs.fxsave.xmm_space) != 16 * 16); + memset(&fpu->fpstate->regs.fxsave.xmm_space[8], 0, 8 * 16); /* Mark FP and SSE as in use when XSAVE is enabled */ if (use_xsave()) - fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; + fpu->fpstate->regs.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; return 0; } @@ -149,7 +153,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, /* * A whole standard-format XSAVE buffer is needed: */ - if (pos != 0 || count != fpu_user_xstate_size) + if (pos != 0 || count != fpu_user_cfg.max_size) return -EFAULT; if (!kbuf) { @@ -164,7 +168,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, } fpu_force_restore(fpu); - ret = copy_uabi_from_kernel_to_xstate(&fpu->state.xsave, kbuf ?: tmpbuf); + ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf); out: vfree(tmpbuf); @@ -283,7 +287,7 @@ static void __convert_from_fxsr(struct user_i387_ia32_struct *env, void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { - __convert_from_fxsr(env, tsk, &tsk->thread.fpu.state.fxsave); + __convert_from_fxsr(env, tsk, &tsk->thread.fpu.fpstate->regs.fxsave); } void convert_to_fxsr(struct fxregs_state *fxsave, @@ -326,7 +330,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, return fpregs_soft_get(target, regset, to); if (!cpu_feature_enabled(X86_FEATURE_FXSR)) { - return membuf_write(&to, &fpu->state.fsave, + return membuf_write(&to, &fpu->fpstate->regs.fsave, sizeof(struct fregs_state)); } @@ -337,7 +341,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, copy_xstate_to_uabi_buf(mb, target, XSTATE_COPY_FP); fx = &fxsave; } else { - fx = &fpu->state.fxsave; + fx = &fpu->fpstate->regs.fxsave; } __convert_from_fxsr(&env, target, fx); @@ -366,16 +370,16 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, fpu_force_restore(fpu); if (cpu_feature_enabled(X86_FEATURE_FXSR)) - convert_to_fxsr(&fpu->state.fxsave, &env); + convert_to_fxsr(&fpu->fpstate->regs.fxsave, &env); else - memcpy(&fpu->state.fsave, &env, sizeof(env)); + memcpy(&fpu->fpstate->regs.fsave, &env, sizeof(env)); /* * Update the header bit in the xsave header, indicating the * presence of FP. */ if (cpu_feature_enabled(X86_FEATURE_XSAVE)) - fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP; + fpu->fpstate->regs.xsave.header.xfeatures |= XFEATURE_MASK_FP; return 0; } diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 445c57c9c539..d5958278eba6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -7,23 +7,25 @@ #include <linux/cpu.h> #include <linux/pagemap.h> -#include <asm/fpu/internal.h> #include <asm/fpu/signal.h> #include <asm/fpu/regset.h> #include <asm/fpu/xstate.h> #include <asm/sigframe.h> +#include <asm/trapnr.h> #include <asm/trace/fpu.h> -static struct _fpx_sw_bytes fx_sw_reserved __ro_after_init; -static struct _fpx_sw_bytes fx_sw_reserved_ia32 __ro_after_init; +#include "context.h" +#include "internal.h" +#include "legacy.h" +#include "xstate.h" /* * Check for the presence of extended state information in the * user fpstate pointer in the sigcontext. */ -static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf, - struct _fpx_sw_bytes *fx_sw) +static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf, + struct _fpx_sw_bytes *fx_sw) { int min_xstate_size = sizeof(struct fxregs_state) + sizeof(struct xstate_header); @@ -31,12 +33,12 @@ static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf, unsigned int magic2; if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw))) - return -EFAULT; + return false; /* Check for the first magic field and other error scenarios. */ if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || fx_sw->xstate_size < min_xstate_size || - fx_sw->xstate_size > fpu_user_xstate_size || + fx_sw->xstate_size > current->thread.fpu.fpstate->user_size || fx_sw->xstate_size > fx_sw->extended_size) goto setfx; @@ -47,10 +49,10 @@ static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf, * in the memory layout. */ if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))) - return -EFAULT; + return false; if (likely(magic2 == FP_XSTATE_MAGIC2)) - return 0; + return true; setfx: trace_x86_fpu_xstate_check_failed(¤t->thread.fpu); @@ -58,22 +60,22 @@ setfx: fx_sw->magic1 = 0; fx_sw->xstate_size = sizeof(struct fxregs_state); fx_sw->xfeatures = XFEATURE_MASK_FPSSE; - return 0; + return true; } /* * Signal frame handlers. */ -static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) +static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf) { if (use_fxsr()) { - struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct xregs_state *xsave = &tsk->thread.fpu.fpstate->regs.xsave; struct user_i387_ia32_struct env; struct _fpstate_32 __user *fp = buf; fpregs_lock(); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - fxsave(&tsk->thread.fpu.state.fxsave); + fxsave(&tsk->thread.fpu.fpstate->regs.fxsave); fpregs_unlock(); convert_from_fxsr(&env, tsk); @@ -81,33 +83,54 @@ static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) if (__copy_to_user(buf, &env, sizeof(env)) || __put_user(xsave->i387.swd, &fp->status) || __put_user(X86_FXSR_MAGIC, &fp->magic)) - return -1; + return false; } else { struct fregs_state __user *fp = buf; u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) - return -1; + return false; } - return 0; + return true; +} + +/* + * Prepare the SW reserved portion of the fxsave memory layout, indicating + * the presence of the extended state information in the memory layout + * pointed to by the fpstate pointer in the sigcontext. + * This is saved when ever the FP and extended state context is + * saved on the user stack during the signal handler delivery to the user. + */ +static inline void save_sw_bytes(struct _fpx_sw_bytes *sw_bytes, bool ia32_frame, + struct fpstate *fpstate) +{ + sw_bytes->magic1 = FP_XSTATE_MAGIC1; + sw_bytes->extended_size = fpstate->user_size + FP_XSTATE_MAGIC2_SIZE; + sw_bytes->xfeatures = fpstate->user_xfeatures; + sw_bytes->xstate_size = fpstate->user_size; + + if (ia32_frame) + sw_bytes->extended_size += sizeof(struct fregs_state); } -static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, + struct fpstate *fpstate) { struct xregs_state __user *x = buf; - struct _fpx_sw_bytes *sw_bytes; + struct _fpx_sw_bytes sw_bytes; u32 xfeatures; int err; /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ - sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; - err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); + save_sw_bytes(&sw_bytes, ia32_frame, fpstate); + err = __copy_to_user(&x->i387.sw_reserved, &sw_bytes, sizeof(sw_bytes)); if (!use_xsave()) - return err; + return !err; err |= __put_user(FP_XSTATE_MAGIC2, - (__u32 __user *)(buf + fpu_user_xstate_size)); + (__u32 __user *)(buf + fpstate->user_size)); /* * Read the xfeatures which we copied (directly from the cpu or @@ -130,23 +153,17 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame) err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures); - return err; + return !err; } static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) { - int err; - if (use_xsave()) - err = xsave_to_user_sigframe(buf); - else if (use_fxsr()) - err = fxsave_to_user_sigframe((struct fxregs_state __user *) buf); + return xsave_to_user_sigframe(buf); + if (use_fxsr()) + return fxsave_to_user_sigframe((struct fxregs_state __user *) buf); else - err = fnsave_to_user_sigframe((struct fregs_state __user *) buf); - - if (unlikely(err) && __clear_user(buf, fpu_user_xstate_size)) - err = -EFAULT; - return err; + return fnsave_to_user_sigframe((struct fregs_state __user *) buf); } /* @@ -159,10 +176,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) * buf == buf_fx for 64-bit frames and 32-bit fsave frame. * buf != buf_fx for 32-bit frames with fxstate. * - * Try to save it directly to the user frame with disabled page fault handler. - * If this fails then do the slow path where the FPU state is first saved to - * task's fpu->state and then copy it to the user frame pointed to by the - * aligned pointer 'buf_fx'. + * Save it directly to the user frame with disabled page fault handler. If + * that faults, try to clear the frame which handles the page fault. * * If this is a 32-bit frame with fxstate, put a fsave header before * the aligned state at 'buf_fx'. @@ -170,10 +185,11 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) * For [f]xsave state, update the SW reserved fields in the [f]xsave frame * indicating the absence/presence of the extended state to the user. */ -int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) { struct task_struct *tsk = current; - int ia32_fxstate = (buf != buf_fx); + struct fpstate *fpstate = tsk->thread.fpu.fpstate; + bool ia32_fxstate = (buf != buf_fx); int ret; ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) || @@ -181,13 +197,25 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) if (!static_cpu_has(X86_FEATURE_FPU)) { struct user_i387_ia32_struct fp; + fpregs_soft_get(current, NULL, (struct membuf){.p = &fp, .left = sizeof(fp)}); - return copy_to_user(buf, &fp, sizeof(fp)) ? -EFAULT : 0; + return !copy_to_user(buf, &fp, sizeof(fp)); } if (!access_ok(buf, size)) - return -EACCES; + return false; + + if (use_xsave()) { + struct xregs_state __user *xbuf = buf_fx; + + /* + * Clear the xsave header first, so that reserved fields are + * initialized to zero. + */ + if (__clear_user(&xbuf->header, sizeof(xbuf->header))) + return false; + } retry: /* * Load the FPU registers if they are not valid for the current task. @@ -205,26 +233,26 @@ retry: fpregs_unlock(); if (ret) { - if (!fault_in_pages_writeable(buf_fx, fpu_user_xstate_size)) + if (!__clear_user(buf_fx, fpstate->user_size)) goto retry; - return -EFAULT; + return false; } /* Save the fsave header for the 32-bit frames. */ - if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) - return -1; + if ((ia32_fxstate || !use_fxsr()) && !save_fsave_header(tsk, buf)) + return false; - if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) - return -1; + if (use_fxsr() && !save_xstate_epilog(buf_fx, ia32_fxstate, fpstate)) + return false; - return 0; + return true; } -static int __restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only) +static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, + u64 xrestore, bool fx_only) { if (use_xsave()) { - u64 init_bv = xfeatures_mask_uabi() & ~xrestore; + u64 init_bv = ufeatures & ~xrestore; int ret; if (likely(!fx_only)) @@ -233,7 +261,7 @@ static int __restore_fpregs_from_user(void __user *buf, u64 xrestore, ret = fxrstor_from_user_sigframe(buf); if (!ret && unlikely(init_bv)) - os_xrstor(&init_fpstate.xsave, init_bv); + os_xrstor(&init_fpstate, init_bv); return ret; } else if (use_fxsr()) { return fxrstor_from_user_sigframe(buf); @@ -246,16 +274,19 @@ static int __restore_fpregs_from_user(void __user *buf, u64 xrestore, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static int restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, + bool fx_only, unsigned int size) { struct fpu *fpu = ¤t->thread.fpu; int ret; retry: fpregs_lock(); + /* Ensure that XFD is up to date */ + xfd_update_state(fpu->fpstate); pagefault_disable(); - ret = __restore_fpregs_from_user(buf, xrestore, fx_only); + ret = __restore_fpregs_from_user(buf, fpu->fpstate->user_xfeatures, + xrestore, fx_only); pagefault_enable(); if (unlikely(ret)) { @@ -275,13 +306,12 @@ retry: fpregs_unlock(); /* Try to handle #PF, but anything else is fatal. */ - if (ret != -EFAULT) - return -EINVAL; + if (ret != X86_TRAP_PF) + return false; - ret = fault_in_pages_readable(buf, size); - if (!ret) + if (!fault_in_readable(buf, size)) goto retry; - return ret; + return false; } /* @@ -294,45 +324,40 @@ retry: * been restored from a user buffer directly. */ if (test_thread_flag(TIF_NEED_FPU_LOAD) && xfeatures_mask_supervisor()) - os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor()); + os_xrstor_supervisor(fpu->fpstate); fpregs_mark_activate(); fpregs_unlock(); - return 0; + return true; } -static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, - bool ia32_fxstate) +static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, + bool ia32_fxstate) { - int state_size = fpu_kernel_xstate_size; struct task_struct *tsk = current; struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; + bool success, fx_only = false; + union fpregs_state *fpregs; + unsigned int state_size; u64 user_xfeatures = 0; - bool fx_only = false; - int ret; if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; - ret = check_xstate_in_sigframe(buf_fx, &fx_sw_user); - if (unlikely(ret)) - return ret; + if (!check_xstate_in_sigframe(buf_fx, &fx_sw_user)) + return false; fx_only = !fx_sw_user.magic1; state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; + state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { - /* - * Attempt to restore the FPU registers directly from user - * memory. For that to succeed, the user access cannot cause page - * faults. If it does, fall back to the slow path below, going - * through the kernel buffer with the enabled pagefault handler. - */ + /* Restore the FPU registers directly from user memory. */ return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, state_size); } @@ -342,9 +367,8 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, * to be ignored for histerical raisins. The legacy state is folded * in once the larger state has been copied. */ - ret = __copy_from_user(&env, buf, sizeof(env)); - if (ret) - return ret; + if (__copy_from_user(&env, buf, sizeof(env))) + return false; /* * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is @@ -363,33 +387,38 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, * the right place in memory. It's ia32 mode. Shrug. */ if (xfeatures_mask_supervisor()) - os_xsave(&fpu->state.xsave); + os_xsave(fpu->fpstate); set_thread_flag(TIF_NEED_FPU_LOAD); } __fpu_invalidate_fpregs_state(fpu); __cpu_invalidate_fpregs_state(); fpregs_unlock(); + fpregs = &fpu->fpstate->regs; if (use_xsave() && !fx_only) { - ret = copy_sigframe_from_user_to_xstate(&fpu->state.xsave, buf_fx); - if (ret) - return ret; + if (copy_sigframe_from_user_to_xstate(fpu->fpstate, buf_fx)) + return false; } else { - if (__copy_from_user(&fpu->state.fxsave, buf_fx, - sizeof(fpu->state.fxsave))) - return -EFAULT; - - /* Reject invalid MXCSR values. */ - if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask) - return -EINVAL; + if (__copy_from_user(&fpregs->fxsave, buf_fx, + sizeof(fpregs->fxsave))) + return false; + + if (IS_ENABLED(CONFIG_X86_64)) { + /* Reject invalid MXCSR values. */ + if (fpregs->fxsave.mxcsr & ~mxcsr_feature_mask) + return false; + } else { + /* Mask invalid bits out for historical reasons (broken hardware). */ + fpregs->fxsave.mxcsr &= mxcsr_feature_mask; + } /* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */ if (use_xsave()) - fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; + fpregs->xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; } /* Fold the legacy FP storage */ - convert_to_fxsr(&fpu->state.fxsave, &env); + convert_to_fxsr(&fpregs->fxsave, &env); fpregs_lock(); if (use_xsave()) { @@ -404,40 +433,45 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, */ u64 mask = user_xfeatures | xfeatures_mask_supervisor(); - fpu->state.xsave.header.xfeatures &= mask; - ret = os_xrstor_safe(&fpu->state.xsave, xfeatures_mask_all); + fpregs->xsave.header.xfeatures &= mask; + success = !os_xrstor_safe(fpu->fpstate, + fpu_kernel_cfg.max_features); } else { - ret = fxrstor_safe(&fpu->state.fxsave); + success = !fxrstor_safe(&fpregs->fxsave); } - if (likely(!ret)) + if (likely(success)) fpregs_mark_activate(); fpregs_unlock(); - return ret; + return success; } -static inline int xstate_sigframe_size(void) + +static inline unsigned int xstate_sigframe_size(struct fpstate *fpstate) { - return use_xsave() ? fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE : - fpu_user_xstate_size; + unsigned int size = fpstate->user_size; + + return use_xsave() ? size + FP_XSTATE_MAGIC2_SIZE : size; } /* * Restore FPU state from a sigframe: */ -int fpu__restore_sig(void __user *buf, int ia32_frame) +bool fpu__restore_sig(void __user *buf, int ia32_frame) { - unsigned int size = xstate_sigframe_size(); struct fpu *fpu = ¤t->thread.fpu; void __user *buf_fx = buf; bool ia32_fxstate = false; - int ret; + bool success = false; + unsigned int size; if (unlikely(!buf)) { fpu__clear_user_states(fpu); - return 0; + return true; } + size = xstate_sigframe_size(fpu->fpstate); + ia32_frame &= (IS_ENABLED(CONFIG_X86_32) || IS_ENABLED(CONFIG_IA32_EMULATION)); @@ -451,30 +485,28 @@ int fpu__restore_sig(void __user *buf, int ia32_frame) ia32_fxstate = true; } - if (!access_ok(buf, size)) { - ret = -EACCES; + if (!access_ok(buf, size)) goto out; - } if (!IS_ENABLED(CONFIG_X86_64) && !cpu_feature_enabled(X86_FEATURE_FPU)) { - ret = fpregs_soft_set(current, NULL, 0, - sizeof(struct user_i387_ia32_struct), - NULL, buf); + success = !fpregs_soft_set(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), + NULL, buf); } else { - ret = __fpu_restore_sig(buf, buf_fx, ia32_fxstate); + success = __fpu_restore_sig(buf, buf_fx, ia32_fxstate); } out: - if (unlikely(ret)) + if (unlikely(!success)) fpu__clear_user_states(fpu); - return ret; + return success; } unsigned long fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, unsigned long *size) { - unsigned long frame_size = xstate_sigframe_size(); + unsigned long frame_size = xstate_sigframe_size(current->thread.fpu.fpstate); *buf_fx = sp = round_down(sp - frame_size, 64); if (ia32_frame && use_fxsr()) { @@ -487,9 +519,12 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, return sp; } -unsigned long fpu__get_fpstate_size(void) +unsigned long __init fpu__get_fpstate_size(void) { - unsigned long ret = xstate_sigframe_size(); + unsigned long ret = fpu_user_cfg.max_size; + + if (use_xsave()) + ret += FP_XSTATE_MAGIC2_SIZE; /* * This space is needed on (most) 32-bit kernels, or when a 32-bit @@ -505,28 +540,3 @@ unsigned long fpu__get_fpstate_size(void) return ret; } -/* - * Prepare the SW reserved portion of the fxsave memory layout, indicating - * the presence of the extended state information in the memory layout - * pointed by the fpstate pointer in the sigcontext. - * This will be saved when ever the FP and extended state context is - * saved on the user stack during the signal handler delivery to the user. - */ -void fpu__init_prepare_fx_sw_frame(void) -{ - int size = fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE; - - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = size; - fx_sw_reserved.xfeatures = xfeatures_mask_uabi(); - fx_sw_reserved.xstate_size = fpu_user_xstate_size; - - if (IS_ENABLED(CONFIG_IA32_EMULATION) || - IS_ENABLED(CONFIG_X86_32)) { - int fsave_header_size = sizeof(struct fregs_state); - - fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size = size + fsave_header_size; - } -} - diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c8def1b7f8fb..d28829403ed0 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -4,21 +4,33 @@ * * Author: Suresh Siddha <suresh.b.siddha@intel.com> */ +#include <linux/bitops.h> #include <linux/compat.h> #include <linux/cpu.h> #include <linux/mman.h> +#include <linux/nospec.h> #include <linux/pkeys.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> +#include <linux/vmalloc.h> #include <asm/fpu/api.h> -#include <asm/fpu/internal.h> -#include <asm/fpu/signal.h> #include <asm/fpu/regset.h> -#include <asm/fpu/xstate.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/xcr.h> #include <asm/tlbflush.h> -#include <asm/cpufeature.h> +#include <asm/prctl.h> +#include <asm/elf.h> + +#include "context.h" +#include "internal.h" +#include "legacy.h" +#include "xstate.h" + +#define for_each_extended_xfeature(bit, mask) \ + (bit) = FIRST_EXTENDED_XFEATURE; \ + for_each_set_bit_from(bit, (unsigned long *)&(mask), 8 * sizeof(mask)) /* * Although we spell it out in here, the Processor Trace @@ -39,29 +51,32 @@ static const char *xfeature_names[] = "Protection Keys User registers", "PASID state", "unknown xstate feature" , + "unknown xstate feature" , + "unknown xstate feature" , + "unknown xstate feature" , + "unknown xstate feature" , + "unknown xstate feature" , + "AMX Tile config" , + "AMX Tile data" , + "unknown xstate feature" , }; -static short xsave_cpuid_features[] __initdata = { - X86_FEATURE_FPU, - X86_FEATURE_XMM, - X86_FEATURE_AVX, - X86_FEATURE_MPX, - X86_FEATURE_MPX, - X86_FEATURE_AVX512F, - X86_FEATURE_AVX512F, - X86_FEATURE_AVX512F, - X86_FEATURE_INTEL_PT, - X86_FEATURE_PKU, - X86_FEATURE_ENQCMD, +static unsigned short xsave_cpuid_features[] __initdata = { + [XFEATURE_FP] = X86_FEATURE_FPU, + [XFEATURE_SSE] = X86_FEATURE_XMM, + [XFEATURE_YMM] = X86_FEATURE_AVX, + [XFEATURE_BNDREGS] = X86_FEATURE_MPX, + [XFEATURE_BNDCSR] = X86_FEATURE_MPX, + [XFEATURE_OPMASK] = X86_FEATURE_AVX512F, + [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F, + [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F, + [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT, + [XFEATURE_PKRU] = X86_FEATURE_PKU, + [XFEATURE_PASID] = X86_FEATURE_ENQCMD, + [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE, + [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE, }; -/* - * This represents the full set of bits that should ever be set in a kernel - * XSAVE buffer, both supervisor and user xstates. - */ -u64 xfeatures_mask_all __ro_after_init; -EXPORT_SYMBOL_GPL(xfeatures_mask_all); - static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init = @@ -72,20 +87,13 @@ static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] __ro_after_init { [ 0 ... XFEATURE_MAX - 1] = -1}; /* - * The XSAVE area of kernel can be in standard or compacted format; - * it is always in standard format for user mode. This is the user - * mode standard format size used for signal and ptrace frames. - */ -unsigned int fpu_user_xstate_size __ro_after_init; - -/* * Return whether the system supports a given xfeature. * * Also return the name of the (most advanced) feature that the caller requested: */ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) { - u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all; + u64 xfeatures_missing = xfeatures_needed & ~fpu_kernel_cfg.max_features; if (unlikely(feature_name)) { long xfeature_idx, max_idx; @@ -135,17 +143,26 @@ static bool xfeature_is_supervisor(int xfeature_nr) */ void fpu__init_cpu_xstate(void) { - if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all) + if (!boot_cpu_has(X86_FEATURE_XSAVE) || !fpu_kernel_cfg.max_features) return; cr4_set_bits(X86_CR4_OSXSAVE); /* + * Must happen after CR4 setup and before xsetbv() to allow KVM + * lazy passthrough. Write independent of the dynamic state static + * key as that does not work on the boot CPU. This also ensures + * that any stale state is wiped out from XFD. + */ + if (cpu_feature_enabled(X86_FEATURE_XFD)) + wrmsrl(MSR_IA32_XFD, init_fpstate.xfd); + + /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user * states can be set here. */ - xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_uabi()); + xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * MSR_IA32_XSS sets supervisor states managed by XSAVES. @@ -158,7 +175,7 @@ void fpu__init_cpu_xstate(void) static bool xfeature_enabled(enum xfeature xfeature) { - return xfeatures_mask_all & BIT_ULL(xfeature); + return fpu_kernel_cfg.max_features & BIT_ULL(xfeature); } /* @@ -184,10 +201,7 @@ static void __init setup_xstate_features(void) xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); - for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (!xfeature_enabled(i)) - continue; - + for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); xstate_sizes[i] = eax; @@ -236,6 +250,8 @@ static void __init print_xstate_features(void) print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); print_xstate_feature(XFEATURE_MASK_PKRU); print_xstate_feature(XFEATURE_MASK_PASID); + print_xstate_feature(XFEATURE_MASK_XTILE_CFG); + print_xstate_feature(XFEATURE_MASK_XTILE_DATA); } /* @@ -291,20 +307,15 @@ static void __init setup_xstate_comp_offsets(void) xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state, xmm_space); - if (!boot_cpu_has(X86_FEATURE_XSAVES)) { - for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (xfeature_enabled(i)) - xstate_comp_offsets[i] = xstate_offsets[i]; - } + if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) { + for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) + xstate_comp_offsets[i] = xstate_offsets[i]; return; } next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE; - for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (!xfeature_enabled(i)) - continue; - + for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { if (xfeature_is_aligned(i)) next_offset = ALIGN(next_offset, 64); @@ -328,8 +339,8 @@ static void __init setup_supervisor_only_offsets(void) next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE; - for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (!xfeature_enabled(i) || !xfeature_is_supervisor(i)) + for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { + if (!xfeature_is_supervisor(i)) continue; if (xfeature_is_aligned(i)) @@ -347,15 +358,36 @@ static void __init print_xstate_offset_size(void) { int i; - for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (!xfeature_enabled(i)) - continue; + for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", i, xstate_comp_offsets[i], i, xstate_sizes[i]); } } /* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static __init void os_xrstor_booting(struct xregs_state *xstate) +{ + u64 mask = fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSTATE; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err; + + if (cpu_feature_enabled(X86_FEATURE_XSAVES)) + XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); + else + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); + + /* + * We should never fault when copying from a kernel buffer, and the FPU + * state we set at boot time should be valid. + */ + WARN_ON_FPU(err); +} + +/* * All supported features have either init state all zeros or are * handled in setup_init_fpu() individually. This is an explicit * feature list and does not use XFEATURE_MASK*SUPPORTED to catch @@ -372,36 +404,30 @@ static void __init print_xstate_offset_size(void) XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ - XFEATURE_MASK_PASID) + XFEATURE_MASK_PASID | \ + XFEATURE_MASK_XTILE) /* * setup the xstate image representing the init state */ static void __init setup_init_fpu_buf(void) { - static int on_boot_cpu __initdata = 1; - BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED) != XFEATURES_INIT_FPSTATE_HANDLED); - WARN_ON_FPU(!on_boot_cpu); - on_boot_cpu = 0; - if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; setup_xstate_features(); print_xstate_features(); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | - xfeatures_mask_all; + xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features); /* * Init all the features state with header.xfeatures being 0x0 */ - os_xrstor_booting(&init_fpstate.xsave); + os_xrstor_booting(&init_fpstate.regs.xsave); /* * All components are now in init state. Read the state back so @@ -419,7 +445,7 @@ static void __init setup_init_fpu_buf(void) * state is all zeroes or if not to add the necessary handling * here. */ - fxsave(&init_fpstate.fxsave); + fxsave(&init_fpstate.regs.fxsave); } static int xfeature_uncompacted_offset(int xfeature_nr) @@ -451,10 +477,11 @@ int xfeature_size(int xfeature_nr) } /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ -static int validate_user_xstate_header(const struct xstate_header *hdr) +static int validate_user_xstate_header(const struct xstate_header *hdr, + struct fpstate *fpstate) { /* No unknown or supervisor features may be set */ - if (hdr->xfeatures & ~xfeatures_mask_uabi()) + if (hdr->xfeatures & ~fpstate->user_xfeatures) return -EINVAL; /* Userspace must use the uncompacted format */ @@ -474,7 +501,7 @@ static int validate_user_xstate_header(const struct xstate_header *hdr) return 0; } -static void __xstate_dump_leaves(void) +static void __init __xstate_dump_leaves(void) { int i; u32 eax, ebx, ecx, edx; @@ -509,12 +536,73 @@ static void __xstate_dump_leaves(void) } \ } while (0) +/** + * check_xtile_data_against_struct - Check tile data state size. + * + * Calculate the state size by multiplying the single tile size which is + * recorded in a C struct, and the number of tiles that the CPU informs. + * Compare the provided size with the calculation. + * + * @size: The tile data state size + * + * Returns: 0 on success, -EINVAL on mismatch. + */ +static int __init check_xtile_data_against_struct(int size) +{ + u32 max_palid, palid, state_size; + u32 eax, ebx, ecx, edx; + u16 max_tile; + + /* + * Check the maximum palette id: + * eax: the highest numbered palette subleaf. + */ + cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx); + + /* + * Cross-check each tile size and find the maximum number of + * supported tiles. + */ + for (palid = 1, max_tile = 0; palid <= max_palid; palid++) { + u16 tile_size, max; + + /* + * Check the tile size info: + * eax[31:16]: bytes per title + * ebx[31:16]: the max names (or max number of tiles) + */ + cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx); + tile_size = eax >> 16; + max = ebx >> 16; + + if (tile_size != sizeof(struct xtile_data)) { + pr_err("%s: struct is %zu bytes, cpu xtile %d bytes\n", + __stringify(XFEATURE_XTILE_DATA), + sizeof(struct xtile_data), tile_size); + __xstate_dump_leaves(); + return -EINVAL; + } + + if (max > max_tile) + max_tile = max; + } + + state_size = sizeof(struct xtile_data) * max_tile; + if (size != state_size) { + pr_err("%s: calculated size is %u bytes, cpu state %d bytes\n", + __stringify(XFEATURE_XTILE_DATA), state_size, size); + __xstate_dump_leaves(); + return -EINVAL; + } + return 0; +} + /* * We have a C struct for each 'xstate'. We need to ensure * that our software representation matches what the CPU * tells us about the state's size. */ -static void check_xstate_against_struct(int nr) +static bool __init check_xstate_against_struct(int nr) { /* * Ask the CPU for the size of the state. @@ -532,6 +620,11 @@ static void check_xstate_against_struct(int nr) XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state); XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state); + XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg); + + /* The tile data size varies between implementations. */ + if (nr == XFEATURE_XTILE_DATA) + check_xtile_data_against_struct(sz); /* * Make *SURE* to add any feature numbers in below if @@ -541,10 +634,39 @@ static void check_xstate_against_struct(int nr) if ((nr < XFEATURE_YMM) || (nr >= XFEATURE_MAX) || (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) || - ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) { + ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) { WARN_ONCE(1, "no structure for xstate: %d\n", nr); XSTATE_WARN_ON(1); + return false; + } + return true; +} + +static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) +{ + unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + int i; + + for_each_extended_xfeature(i, xfeatures) { + /* Align from the end of the previous feature */ + if (xfeature_is_aligned(i)) + size = ALIGN(size, 64); + /* + * In compacted format the enabled features are packed, + * i.e. disabled features do not occupy space. + * + * In non-compacted format the offsets are fixed and + * disabled states still occupy space in the memory buffer. + */ + if (!compacted) + size = xfeature_uncompacted_offset(i); + /* + * Add the feature size even for non-compacted format + * to make the end result correct + */ + size += xfeature_size(i); } + return size; } /* @@ -556,44 +678,29 @@ static void check_xstate_against_struct(int nr) * covered by these checks. Only the size of the buffer for task->fpu * is checked here. */ -static void do_extra_xstate_size_checks(void) +static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) { - int paranoid_xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; int i; - for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (!xfeature_enabled(i)) - continue; - - check_xstate_against_struct(i); + for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { + if (!check_xstate_against_struct(i)) + return false; /* * Supervisor state components can be managed only by * XSAVES. */ - if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) - XSTATE_WARN_ON(xfeature_is_supervisor(i)); - - /* Align from the end of the previous feature */ - if (xfeature_is_aligned(i)) - paranoid_xstate_size = ALIGN(paranoid_xstate_size, 64); - /* - * The offset of a given state in the non-compacted - * format is given to us in a CPUID leaf. We check - * them for being ordered (increasing offsets) in - * setup_xstate_features(). XSAVES uses compacted format. - */ - if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) - paranoid_xstate_size = xfeature_uncompacted_offset(i); - /* - * The compacted-format offset always depends on where - * the previous state ended. - */ - paranoid_xstate_size += xfeature_size(i); + if (!compacted && xfeature_is_supervisor(i)) { + XSTATE_WARN_ON(1); + return false; + } } - XSTATE_WARN_ON(paranoid_xstate_size != fpu_kernel_xstate_size); + size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted); + XSTATE_WARN_ON(size != kernel_size); + return size == kernel_size; } - /* * Get total size of enabled xstates in XCR0 | IA32_XSS. * @@ -644,7 +751,7 @@ static unsigned int __init get_xsaves_size_no_independent(void) return size; } -static unsigned int __init get_xsave_size(void) +static unsigned int __init get_xsave_size_user(void) { unsigned int eax, ebx, ecx, edx; /* @@ -662,44 +769,54 @@ static unsigned int __init get_xsave_size(void) * Will the runtime-enumerated 'xstate_size' fit in the init * task's statically-allocated buffer? */ -static bool is_supported_xstate_size(unsigned int test_xstate_size) +static bool __init is_supported_xstate_size(unsigned int test_xstate_size) { - if (test_xstate_size <= sizeof(union fpregs_state)) + if (test_xstate_size <= sizeof(init_fpstate.regs)) return true; pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n", - sizeof(union fpregs_state), test_xstate_size); + sizeof(init_fpstate.regs), test_xstate_size); return false; } static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ - unsigned int possible_xstate_size; - unsigned int xsave_size; + unsigned int user_size, kernel_size, kernel_default_size; + bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); - xsave_size = get_xsave_size(); + /* Uncompacted user space size */ + user_size = get_xsave_size_user(); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - possible_xstate_size = get_xsaves_size_no_independent(); + /* + * XSAVES kernel size includes supervisor states and + * uses compacted format when available. + * + * XSAVE does not support supervisor states so + * kernel and user size is identical. + */ + if (compacted) + kernel_size = get_xsaves_size_no_independent(); else - possible_xstate_size = xsave_size; + kernel_size = user_size; + + kernel_default_size = + xstate_calculate_size(fpu_kernel_cfg.default_features, compacted); - /* Ensure we have the space to store all enabled: */ - if (!is_supported_xstate_size(possible_xstate_size)) + /* Ensure we have the space to store all default enabled features. */ + if (!is_supported_xstate_size(kernel_default_size)) return -EINVAL; - /* - * The size is OK, we are definitely going to use xsave, - * make it known to the world that we need more space. - */ - fpu_kernel_xstate_size = possible_xstate_size; - do_extra_xstate_size_checks(); + if (!paranoid_xstate_size_valid(kernel_size)) + return -EINVAL; + + fpu_kernel_cfg.max_size = kernel_size; + fpu_user_cfg.max_size = user_size; + + fpu_kernel_cfg.default_size = kernel_default_size; + fpu_user_cfg.default_size = + xstate_calculate_size(fpu_user_cfg.default_features, false); - /* - * User space is always in standard format. - */ - fpu_user_xstate_size = xsave_size; return 0; } @@ -707,28 +824,38 @@ static int __init init_xstate_size(void) * We enabled the XSAVE hardware, but something went wrong and * we can not use it. Disable it. */ -static void fpu__init_disable_system_xstate(void) +static void __init fpu__init_disable_system_xstate(unsigned int legacy_size) { - xfeatures_mask_all = 0; + fpu_kernel_cfg.max_features = 0; cr4_clear_bits(X86_CR4_OSXSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVE); + + /* Restore the legacy size.*/ + fpu_kernel_cfg.max_size = legacy_size; + fpu_kernel_cfg.default_size = legacy_size; + fpu_user_cfg.max_size = legacy_size; + fpu_user_cfg.default_size = legacy_size; + + /* + * Prevent enabling the static branch which enables writes to the + * XFD MSR. + */ + init_fpstate.xfd = 0; + + fpstate_reset(¤t->thread.fpu); } /* * Enable and initialize the xsave feature. * Called once per system bootup. */ -void __init fpu__init_system_xstate(void) +void __init fpu__init_system_xstate(unsigned int legacy_size) { unsigned int eax, ebx, ecx, edx; - static int on_boot_cpu __initdata = 1; u64 xfeatures; int err; int i; - WARN_ON_FPU(!on_boot_cpu); - on_boot_cpu = 0; - if (!boot_cpu_has(X86_FEATURE_FPU)) { pr_info("x86/fpu: No FPU detected\n"); return; @@ -749,22 +876,22 @@ void __init fpu__init_system_xstate(void) * Find user xstates supported by the processor. */ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xfeatures_mask_all = eax + ((u64)edx << 32); + fpu_kernel_cfg.max_features = eax + ((u64)edx << 32); /* * Find supervisor xstates supported by the processor. */ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); - xfeatures_mask_all |= ecx + ((u64)edx << 32); + fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32); - if ((xfeatures_mask_uabi() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { + if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { /* * This indicates that something really unexpected happened * with the enumeration. Disable XSAVE and try to continue * booting without it. This is too early to BUG(). */ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", - xfeatures_mask_all); + fpu_kernel_cfg.max_features); goto out_disable; } @@ -772,15 +899,39 @@ void __init fpu__init_system_xstate(void) * Clear XSAVE features that are disabled in the normal CPUID. */ for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { - if (!boot_cpu_has(xsave_cpuid_features[i])) - xfeatures_mask_all &= ~BIT_ULL(i); + unsigned short cid = xsave_cpuid_features[i]; + + /* Careful: X86_FEATURE_FPU is 0! */ + if ((i != XFEATURE_FP && !cid) || !boot_cpu_has(cid)) + fpu_kernel_cfg.max_features &= ~BIT_ULL(i); } - xfeatures_mask_all &= XFEATURE_MASK_USER_SUPPORTED | + if (!cpu_feature_enabled(X86_FEATURE_XFD)) + fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC; + + fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED; + fpu_user_cfg.max_features = fpu_kernel_cfg.max_features; + fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; + + /* Clean out dynamic features from default */ + fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features; + fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; + + fpu_user_cfg.default_features = fpu_user_cfg.max_features; + fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; + /* Store it for paranoia check at the end */ - xfeatures = xfeatures_mask_all; + xfeatures = fpu_kernel_cfg.max_features; + + /* + * Initialize the default XFD state in initfp_state and enable the + * dynamic sizing mechanism if dynamic states are available. The + * static key cannot be enabled here because this runs before + * jump_label_init(). This is delayed to an initcall. + */ + init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC; /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); @@ -788,13 +939,16 @@ void __init fpu__init_system_xstate(void) if (err) goto out_disable; + /* Reset the state for the current task */ + fpstate_reset(¤t->thread.fpu); + /* * Update info used for ptrace frames; use standard-format size and no * supervisor xstates: */ - update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_uabi()); + update_regset_xstate_info(fpu_user_cfg.max_size, + fpu_user_cfg.max_features); - fpu__init_prepare_fx_sw_frame(); setup_init_fpu_buf(); setup_xstate_comp_offsets(); setup_supervisor_only_offsets(); @@ -803,22 +957,22 @@ void __init fpu__init_system_xstate(void) * Paranoia check whether something in the setup modified the * xfeatures mask. */ - if (xfeatures != xfeatures_mask_all) { + if (xfeatures != fpu_kernel_cfg.max_features) { pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n", - xfeatures, xfeatures_mask_all); + xfeatures, fpu_kernel_cfg.max_features); goto out_disable; } print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", - xfeatures_mask_all, - fpu_kernel_xstate_size, + fpu_kernel_cfg.max_features, + fpu_kernel_cfg.max_size, boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard"); return; out_disable: /* something went wrong, try to boot without any XSAVE support */ - fpu__init_disable_system_xstate(); + fpu__init_disable_system_xstate(legacy_size); } /* @@ -830,7 +984,7 @@ void fpu__resume_cpu(void) * Restore XCR0 on xsave capable CPUs: */ if (cpu_feature_enabled(X86_FEATURE_XSAVE)) - xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_uabi()); + xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * Restore IA32_XSS. The same CPUID bit enumerates support @@ -840,6 +994,9 @@ void fpu__resume_cpu(void) wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } + + if (fpu_state_size_dynamic()) + wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd); } /* @@ -886,7 +1043,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) * We should not ever be requesting features that we * have not enabled. */ - WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)), + WARN_ONCE(!(fpu_kernel_cfg.max_features & BIT_ULL(xfeature_nr)), "get of unsupported state"); /* * This assumes the last 'xsave*' instruction to @@ -904,7 +1061,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) return __raw_xsave_addr(xsave, xfeature_nr); } -EXPORT_SYMBOL_GPL(get_xsave_addr); #ifdef CONFIG_ARCH_HAS_PKEYS @@ -961,9 +1117,10 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, } /** - * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer + * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor - * @tsk: The task from which to copy the saved xstate + * @fpstate: The fpstate buffer from which to copy + * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming @@ -972,14 +1129,15 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * * It supports partial copy but @to.pos always starts from zero. */ -void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, - enum xstate_copy_mode copy_mode) +void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, + u32 pkru_val, enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); - struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; - struct xregs_state *xinit = &init_fpstate.xsave; + struct xregs_state *xinit = &init_fpstate.regs.xsave; + struct xregs_state *xsave = &fpstate->regs.xsave; struct xstate_header header; unsigned int zerofrom; + u64 mask; int i; memset(&header, 0, sizeof(header)); @@ -996,7 +1154,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, break; case XSTATE_COPY_XSAVE: - header.xfeatures &= xfeatures_mask_uabi(); + header.xfeatures &= fpstate->user_xfeatures; break; } @@ -1033,17 +1191,15 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, zerofrom = offsetof(struct xregs_state, extended_state_area); - for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - /* - * The ptrace buffer is in non-compacted XSAVE format. - * In non-compacted format disabled features still occupy - * state space, but there is no state to copy from in the - * compacted init_fpstate. The gap tracking will zero this - * later. - */ - if (!(xfeatures_mask_uabi() & BIT_ULL(i))) - continue; + /* + * The ptrace buffer is in non-compacted XSAVE format. In + * non-compacted format disabled features still occupy state space, + * but there is no state to copy from in the compacted + * init_fpstate. The gap tracking will zero these states. + */ + mask = fpstate->user_xfeatures; + for_each_extended_xfeature(i, mask) { /* * If there was a feature or alignment gap, zero the space * in the destination buffer. @@ -1055,10 +1211,9 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, struct pkru_state pkru = {0}; /* * PKRU is not necessarily up to date in the - * thread's XSAVE buffer. Fill this part from the - * per-thread storage. + * XSAVE buffer. Use the provided value. */ - pkru.pkru = tsk->thread.pkru; + pkru.pkru = pkru_val; membuf_write(&to, &pkru, sizeof(pkru)); } else { copy_feature(header.xfeatures & BIT_ULL(i), &to, @@ -1078,6 +1233,25 @@ out: membuf_zero(&to, to.left); } +/** + * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer + * @to: membuf descriptor + * @tsk: The task from which to copy the saved xstate + * @copy_mode: The requested copy mode + * + * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming + * format, i.e. from the kernel internal hardware dependent storage format + * to the requested @mode. UABI XSTATE is always uncompacted! + * + * It supports partial copy but @to.pos always starts from zero. + */ +void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, + enum xstate_copy_mode copy_mode) +{ + __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate, + tsk->thread.pkru, copy_mode); +} + static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size, const void *kbuf, const void __user *ubuf) { @@ -1091,9 +1265,10 @@ static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size, } -static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf, +static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, const void __user *ubuf) { + struct xregs_state *xsave = &fpstate->regs.xsave; unsigned int offset, size; struct xstate_header hdr; u64 mask; @@ -1103,7 +1278,7 @@ static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf, if (copy_from_buffer(&hdr, offset, sizeof(hdr), kbuf, ubuf)) return -EFAULT; - if (validate_user_xstate_header(&hdr)) + if (validate_user_xstate_header(&hdr, fpstate)) return -EINVAL; /* Validate MXCSR when any of the related features is in use */ @@ -1156,12 +1331,11 @@ static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf, /* * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S] - * format and copy to the target thread. This is called from - * xstateregs_set(). + * format and copy to the target thread. Used by ptrace and KVM. */ -int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) +int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf) { - return copy_uabi_to_xstate(xsave, kbuf, NULL); + return copy_uabi_to_xstate(fpstate, kbuf, NULL); } /* @@ -1169,26 +1343,20 @@ int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) * XSAVE[S] format and copy to the target thread. This is called from the * sigreturn() and rt_sigreturn() system calls. */ -int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave, +int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate, const void __user *ubuf) { - return copy_uabi_to_xstate(xsave, NULL, ubuf); + return copy_uabi_to_xstate(fpstate, NULL, ubuf); } -static bool validate_xsaves_xrstors(u64 mask) +static bool validate_independent_components(u64 mask) { u64 xchk; if (WARN_ON_FPU(!cpu_feature_enabled(X86_FEATURE_XSAVES))) return false; - /* - * Validate that this is either a task->fpstate related component - * subset or an independent one. - */ - if (mask & xfeatures_mask_independent()) - xchk = ~xfeatures_mask_independent(); - else - xchk = ~xfeatures_mask_all; + + xchk = ~xfeatures_mask_independent(); if (WARN_ON_ONCE(!mask || mask & xchk)) return false; @@ -1206,14 +1374,13 @@ static bool validate_xsaves_xrstors(u64 mask) * buffer should be zeroed otherwise a consecutive XRSTORS from that buffer * can #GP. * - * The feature mask must either be a subset of the independent features or - * a subset of the task->fpstate related features. + * The feature mask must be a subset of the independent features. */ void xsaves(struct xregs_state *xstate, u64 mask) { int err; - if (!validate_xsaves_xrstors(mask)) + if (!validate_independent_components(mask)) return; XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err); @@ -1231,20 +1398,379 @@ void xsaves(struct xregs_state *xstate, u64 mask) * Proper usage is to restore the state which was saved with * xsaves() into @xstate. * - * The feature mask must either be a subset of the independent features or - * a subset of the task->fpstate related features. + * The feature mask must be a subset of the independent features. */ void xrstors(struct xregs_state *xstate, u64 mask) { int err; - if (!validate_xsaves_xrstors(mask)) + if (!validate_independent_components(mask)) return; XSTATE_OP(XRSTORS, xstate, (u32)mask, (u32)(mask >> 32), err); WARN_ON_ONCE(err); } +#if IS_ENABLED(CONFIG_KVM) +void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature) +{ + void *addr = get_xsave_addr(&fps->regs.xsave, xfeature); + + if (addr) + memset(addr, 0, xstate_sizes[xfeature]); +} +EXPORT_SYMBOL_GPL(fpstate_clear_xstate_component); +#endif + +#ifdef CONFIG_X86_64 + +#ifdef CONFIG_X86_DEBUG_FPU +/* + * Ensure that a subsequent XSAVE* or XRSTOR* instruction with RFBM=@mask + * can safely operate on the @fpstate buffer. + */ +static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor) +{ + u64 xfd = __this_cpu_read(xfd_state); + + if (fpstate->xfd == xfd) + return true; + + /* + * The XFD MSR does not match fpstate->xfd. That's invalid when + * the passed in fpstate is current's fpstate. + */ + if (fpstate->xfd == current->thread.fpu.fpstate->xfd) + return false; + + /* + * XRSTOR(S) from init_fpstate are always correct as it will just + * bring all components into init state and not read from the + * buffer. XSAVE(S) raises #PF after init. + */ + if (fpstate == &init_fpstate) + return rstor; + + /* + * XSAVE(S): clone(), fpu_swap_kvm_fpu() + * XRSTORS(S): fpu_swap_kvm_fpu() + */ + + /* + * No XSAVE/XRSTOR instructions (except XSAVE itself) touch + * the buffer area for XFD-disabled state components. + */ + mask &= ~xfd; + + /* + * Remove features which are valid in fpstate. They + * have space allocated in fpstate. + */ + mask &= ~fpstate->xfeatures; + + /* + * Any remaining state components in 'mask' might be written + * by XSAVE/XRSTOR. Fail validation it found. + */ + return !mask; +} + +void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) +{ + WARN_ON_ONCE(!xstate_op_valid(fpstate, mask, rstor)); +} +#endif /* CONFIG_X86_DEBUG_FPU */ + +static int __init xfd_update_static_branch(void) +{ + /* + * If init_fpstate.xfd has bits set then dynamic features are + * available and the dynamic sizing must be enabled. + */ + if (init_fpstate.xfd) + static_branch_enable(&__fpu_state_size_dynamic); + return 0; +} +arch_initcall(xfd_update_static_branch) + +void fpstate_free(struct fpu *fpu) +{ + if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate) + vfree(fpu->fpstate); +} + +/** + * fpu_install_fpstate - Update the active fpstate in the FPU + * + * @fpu: A struct fpu * pointer + * @newfps: A struct fpstate * pointer + * + * Returns: A null pointer if the last active fpstate is the embedded + * one or the new fpstate is already installed; + * otherwise, a pointer to the old fpstate which has to + * be freed by the caller. + */ +static struct fpstate *fpu_install_fpstate(struct fpu *fpu, + struct fpstate *newfps) +{ + struct fpstate *oldfps = fpu->fpstate; + + if (fpu->fpstate == newfps) + return NULL; + + fpu->fpstate = newfps; + return oldfps != &fpu->__fpstate ? oldfps : NULL; +} + +/** + * fpstate_realloc - Reallocate struct fpstate for the requested new features + * + * @xfeatures: A bitmap of xstate features which extend the enabled features + * of that task + * @ksize: The required size for the kernel buffer + * @usize: The required size for user space buffers + * + * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer + * terminates quickly, vfree()-induced IPIs may be a concern, but tasks + * with large states are likely to live longer. + * + * Returns: 0 on success, -ENOMEM on allocation error. + */ +static int fpstate_realloc(u64 xfeatures, unsigned int ksize, + unsigned int usize) +{ + struct fpu *fpu = ¤t->thread.fpu; + struct fpstate *curfps, *newfps = NULL; + unsigned int fpsize; + + curfps = fpu->fpstate; + fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64); + + newfps = vzalloc(fpsize); + if (!newfps) + return -ENOMEM; + newfps->size = ksize; + newfps->user_size = usize; + newfps->is_valloc = true; + + fpregs_lock(); + /* + * Ensure that the current state is in the registers before + * swapping fpstate as that might invalidate it due to layout + * changes. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + fpregs_restore_userregs(); + + newfps->xfeatures = curfps->xfeatures | xfeatures; + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; + newfps->xfd = curfps->xfd & ~xfeatures; + + curfps = fpu_install_fpstate(fpu, newfps); + + /* Do the final updates within the locked region */ + xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures); + xfd_update_state(newfps); + + fpregs_unlock(); + + vfree(curfps); + return 0; +} + +static int validate_sigaltstack(unsigned int usize) +{ + struct task_struct *thread, *leader = current->group_leader; + unsigned long framesize = get_sigframe_size(); + + lockdep_assert_held(¤t->sighand->siglock); + + /* get_sigframe_size() is based on fpu_user_cfg.max_size */ + framesize -= fpu_user_cfg.max_size; + framesize += usize; + for_each_thread(leader, thread) { + if (thread->sas_ss_size && thread->sas_ss_size < framesize) + return -ENOSPC; + } + return 0; +} + +static int __xstate_request_perm(u64 permitted, u64 requested) +{ + /* + * This deliberately does not exclude !XSAVES as we still might + * decide to optionally context switch XCR0 or talk the silicon + * vendors into extending XFD for the pre AMX states, especially + * AVX512. + */ + bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + struct fpu *fpu = ¤t->group_leader->thread.fpu; + unsigned int ksize, usize; + u64 mask; + int ret; + + /* Check whether fully enabled */ + if ((permitted & requested) == requested) + return 0; + + /* Calculate the resulting kernel state size */ + mask = permitted | requested; + ksize = xstate_calculate_size(mask, compacted); + + /* Calculate the resulting user state size */ + mask &= XFEATURE_MASK_USER_SUPPORTED; + usize = xstate_calculate_size(mask, false); + + ret = validate_sigaltstack(usize); + if (ret) + return ret; + + /* Pairs with the READ_ONCE() in xstate_get_group_perm() */ + WRITE_ONCE(fpu->perm.__state_perm, requested); + /* Protected by sighand lock */ + fpu->perm.__state_size = ksize; + fpu->perm.__user_state_size = usize; + return ret; +} + +/* + * Permissions array to map facilities with more than one component + */ +static const u64 xstate_prctl_req[XFEATURE_MAX] = { + [XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA, +}; + +static int xstate_request_perm(unsigned long idx) +{ + u64 permitted, requested; + int ret; + + if (idx >= XFEATURE_MAX) + return -EINVAL; + + /* + * Look up the facility mask which can require more than + * one xstate component. + */ + idx = array_index_nospec(idx, ARRAY_SIZE(xstate_prctl_req)); + requested = xstate_prctl_req[idx]; + if (!requested) + return -EOPNOTSUPP; + + if ((fpu_user_cfg.max_features & requested) != requested) + return -EOPNOTSUPP; + + /* Lockless quick check */ + permitted = xstate_get_host_group_perm(); + if ((permitted & requested) == requested) + return 0; + + /* Protect against concurrent modifications */ + spin_lock_irq(¤t->sighand->siglock); + permitted = xstate_get_host_group_perm(); + ret = __xstate_request_perm(permitted, requested); + spin_unlock_irq(¤t->sighand->siglock); + return ret; +} + +int xfd_enable_feature(u64 xfd_err) +{ + u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC; + unsigned int ksize, usize; + struct fpu *fpu; + + if (!xfd_event) { + pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err); + return 0; + } + + /* Protect against concurrent modifications */ + spin_lock_irq(¤t->sighand->siglock); + + /* If not permitted let it die */ + if ((xstate_get_host_group_perm() & xfd_event) != xfd_event) { + spin_unlock_irq(¤t->sighand->siglock); + return -EPERM; + } + + fpu = ¤t->group_leader->thread.fpu; + ksize = fpu->perm.__state_size; + usize = fpu->perm.__user_state_size; + /* + * The feature is permitted. State size is sufficient. Dropping + * the lock is safe here even if more features are added from + * another task, the retrieved buffer sizes are valid for the + * currently requested feature(s). + */ + spin_unlock_irq(¤t->sighand->siglock); + + /* + * Try to allocate a new fpstate. If that fails there is no way + * out. + */ + if (fpstate_realloc(xfd_event, ksize, usize)) + return -EFAULT; + return 0; +} +#else /* CONFIG_X86_64 */ +static inline int xstate_request_perm(unsigned long idx) +{ + return -EPERM; +} +#endif /* !CONFIG_X86_64 */ + +/** + * fpu_xstate_prctl - xstate permission operations + * @tsk: Redundant pointer to current + * @option: A subfunction of arch_prctl() + * @arg2: option argument + * Return: 0 if successful; otherwise, an error code + * + * Option arguments: + * + * ARCH_GET_XCOMP_SUPP: Pointer to user space u64 to store the info + * ARCH_GET_XCOMP_PERM: Pointer to user space u64 to store the info + * ARCH_REQ_XCOMP_PERM: Facility number requested + * + * For facilities which require more than one XSTATE component, the request + * must be the highest state component number related to that facility, + * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and + * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18). + */ +long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2) +{ + u64 __user *uptr = (u64 __user *)arg2; + u64 permitted, supported; + unsigned long idx = arg2; + + if (tsk != current) + return -EPERM; + + switch (option) { + case ARCH_GET_XCOMP_SUPP: + supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features; + return put_user(supported, uptr); + + case ARCH_GET_XCOMP_PERM: + /* + * Lockless snapshot as it can also change right after the + * dropping the lock. + */ + permitted = xstate_get_host_group_perm(); + permitted &= XFEATURE_MASK_USER_SUPPORTED; + return put_user(permitted, uptr); + + case ARCH_REQ_XCOMP_PERM: + if (!IS_ENABLED(CONFIG_X86_64)) + return -EOPNOTSUPP; + + return xstate_request_perm(idx); + + default: + return -EINVAL; + } +} + #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h new file mode 100644 index 000000000000..e18210dff88c --- /dev/null +++ b/arch/x86/kernel/fpu/xstate.h @@ -0,0 +1,278 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_KERNEL_FPU_XSTATE_H +#define __X86_KERNEL_FPU_XSTATE_H + +#include <asm/cpufeature.h> +#include <asm/fpu/xstate.h> + +#ifdef CONFIG_X86_64 +DECLARE_PER_CPU(u64, xfd_state); +#endif + +static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) +{ + /* + * XRSTORS requires these bits set in xcomp_bv, or it will + * trigger #GP: + */ + if (cpu_feature_enabled(X86_FEATURE_XSAVES)) + xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT; +} + +static inline u64 xstate_get_host_group_perm(void) +{ + /* Pairs with WRITE_ONCE() in xstate_request_perm() */ + return READ_ONCE(current->group_leader->thread.fpu.perm.__state_perm); +} + +enum xstate_copy_mode { + XSTATE_COPY_FP, + XSTATE_COPY_FX, + XSTATE_COPY_XSAVE, +}; + +struct membuf; +extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, + u32 pkru_val, enum xstate_copy_mode copy_mode); +extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, + enum xstate_copy_mode mode); +extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf); +extern int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate, const void __user *ubuf); + + +extern void fpu__init_cpu_xstate(void); +extern void fpu__init_system_xstate(unsigned int legacy_size); + +extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); + +static inline u64 xfeatures_mask_supervisor(void) +{ + return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED; +} + +static inline u64 xfeatures_mask_independent(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) + return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR; + + return XFEATURE_MASK_INDEPENDENT; +} + +/* XSAVE/XRSTOR wrapper functions */ + +#ifdef CONFIG_X86_64 +#define REX_PREFIX "0x48, " +#else +#define REX_PREFIX +#endif + +/* These macros all use (%edi)/(%rdi) as the single memory argument. */ +#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" +#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" +#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" +#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" + +/* + * After this @err contains 0 on success or the trap number when the + * operation raises an exception. + */ +#define XSTATE_OP(op, st, lmask, hmask, err) \ + asm volatile("1:" op "\n\t" \ + "xor %[err], %[err]\n" \ + "2:\n\t" \ + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ + : [err] "=a" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact + * format and supervisor states in addition to modified optimization in + * XSAVEOPT. + * + * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT + * supports modified optimization which is not supported by XSAVE. + * + * We use XSAVE as a fallback. + * + * The 661 label is defined in the ALTERNATIVE* macros as the address of the + * original instruction which gets replaced. We need to use it here as the + * address of the instruction where we might get an exception at. + */ +#define XSTATE_XSAVE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE_2(XSAVE, \ + XSAVEOPT, X86_FEATURE_XSAVEOPT, \ + XSAVES, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact + * XSAVE area format. + */ +#define XSTATE_XRESTORE(st, lmask, hmask) \ + asm volatile(ALTERNATIVE(XRSTOR, \ + XRSTORS, X86_FEATURE_XSAVES) \ + "\n" \ + "3:\n" \ + _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE) \ + : \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +#if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU) +extern void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor); +#else +static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { } +#endif + +#ifdef CONFIG_X86_64 +static inline void xfd_update_state(struct fpstate *fpstate) +{ + if (fpu_state_size_dynamic()) { + u64 xfd = fpstate->xfd; + + if (__this_cpu_read(xfd_state) != xfd) { + wrmsrl(MSR_IA32_XFD, xfd); + __this_cpu_write(xfd_state, xfd); + } + } +} +#else +static inline void xfd_update_state(struct fpstate *fpstate) { } +#endif + +/* + * Save processor xstate to xsave area. + * + * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features + * and command line options. The choice is permanent until the next reboot. + */ +static inline void os_xsave(struct fpstate *fpstate) +{ + u64 mask = fpstate->xfeatures; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err; + + WARN_ON_FPU(!alternatives_patched); + xfd_validate_state(fpstate, mask, false); + + XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err); + + /* We should never fault when copying to a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Restore processor xstate from xsave area. + * + * Uses XRSTORS when XSAVES is used, XRSTOR otherwise. + */ +static inline void os_xrstor(struct fpstate *fpstate, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + + xfd_validate_state(fpstate, mask, true); + XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); +} + +/* Restore of supervisor state. Does not require XFD */ +static inline void os_xrstor_supervisor(struct fpstate *fpstate) +{ + u64 mask = xfeatures_mask_supervisor(); + u32 lmask = mask; + u32 hmask = mask >> 32; + + XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); +} + +/* + * Save xstate to user space xsave area. + * + * We don't use modified optimization because xrstor/xrstors might track + * a different application. + * + * We don't use compacted format xsave area for backward compatibility for + * old applications which don't understand the compacted format of the + * xsave area. + * + * The caller has to zero buf::header before calling this because XSAVE* + * does not touch the reserved fields in the header. + */ +static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) +{ + /* + * Include the features which are not xsaved/rstored by the kernel + * internally, e.g. PKRU. That's user space ABI and also required + * to allow the signal handler to modify PKRU. + */ + struct fpstate *fpstate = current->thread.fpu.fpstate; + u64 mask = fpstate->user_xfeatures; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err; + + xfd_validate_state(fpstate, mask, false); + + stac(); + XSTATE_OP(XSAVE, buf, lmask, hmask, err); + clac(); + + return err; +} + +/* + * Restore xstate from user space xsave area. + */ +static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask) +{ + struct xregs_state *xstate = ((__force struct xregs_state *)buf); + u32 lmask = mask; + u32 hmask = mask >> 32; + int err; + + xfd_validate_state(current->thread.fpu.fpstate, mask, true); + + stac(); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); + clac(); + + return err; +} + +/* + * Restore xstate from kernel space xsave area, return an error code instead of + * an exception. + */ +static inline int os_xrstor_safe(struct fpstate *fpstate, u64 mask) +{ + struct xregs_state *xstate = &fpstate->regs.xsave; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err; + + /* Ensure that XFD is up to date */ + xfd_update_state(fpstate); + + if (cpu_feature_enabled(X86_FEATURE_XSAVES)) + XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); + else + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); + + return err; +} + + +#endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1b3ce3b4a2a2..c39f906cdc4e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -252,11 +252,6 @@ void arch_ftrace_update_code(int command) ftrace_modify_all_code(command); } -int __init ftrace_dyn_arch_init(void) -{ - return 0; -} - /* Currently only x86_64 supports dynamic trampolines */ #ifdef CONFIG_X86_64 @@ -527,7 +522,7 @@ static void *addr_from_call(void *ptr) return ptr + CALL_INSN_SIZE + call.disp; } -void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, unsigned long frame_pointer); /* @@ -541,7 +536,8 @@ static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec) void *ptr; if (ops && ops->trampoline) { -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) && \ + defined(CONFIG_FUNCTION_GRAPH_TRACER) /* * We only know about function graph tracer setting as static * trampoline. @@ -589,8 +585,9 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_FUNCTION_GRAPH_TRACER #ifdef CONFIG_DYNAMIC_FTRACE -extern void ftrace_graph_call(void); +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +extern void ftrace_graph_call(void); static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr); @@ -618,19 +615,28 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_mod_jmp(ip, &ftrace_stub); } +#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ +int ftrace_enable_ftrace_graph_caller(void) +{ + return 0; +} +int ftrace_disable_ftrace_graph_caller(void) +{ + return 0; +} +#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* !CONFIG_DYNAMIC_FTRACE */ /* * Hook the return address and push it in the stack of return addrs * in current thread info. */ -void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, unsigned long frame_pointer) { unsigned long return_hooker = (unsigned long)&return_to_handler; - unsigned long old; - int faulted; + int bit; /* * When resuming from suspend-to-ram, this function can be indirectly @@ -650,37 +656,25 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; - /* - * Protect against fault, even if it shouldn't - * happen. This tool is too much intrusive to - * ignore such a protection. - */ - asm volatile( - "1: " _ASM_MOV " (%[parent]), %[old]\n" - "2: " _ASM_MOV " %[return_hooker], (%[parent])\n" - " movl $0, %[faulted]\n" - "3:\n" - - ".section .fixup, \"ax\"\n" - "4: movl $1, %[faulted]\n" - " jmp 3b\n" - ".previous\n" - - _ASM_EXTABLE(1b, 4b) - _ASM_EXTABLE(2b, 4b) - - : [old] "=&r" (old), [faulted] "=r" (faulted) - : [parent] "r" (parent), [return_hooker] "r" (return_hooker) - : "memory" - ); - - if (unlikely(faulted)) { - ftrace_graph_stop(); - WARN_ON(1); + bit = ftrace_test_recursion_trylock(ip, *parent); + if (bit < 0) return; - } - if (function_graph_enter(old, self_addr, frame_pointer, parent)) - *parent = old; + if (!function_graph_enter(*parent, ip, frame_pointer, parent)) + *parent = return_hooker; + + ftrace_test_recursion_unlock(bit); } + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + struct pt_regs *regs = &fregs->regs; + unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs); + + prepare_ftrace_return(ip, (unsigned long *)stack, 0); +} +#endif + #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 7c273846c687..7a879901f103 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -174,11 +174,6 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) SYM_FUNC_END(ftrace_caller); SYM_FUNC_START(ftrace_epilogue) -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) - jmp ftrace_stub -#endif - /* * This is weak to keep gas from relaxing the jumps. * It is also used to copy the retq for trampolines. @@ -251,7 +246,6 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) * If ORIG_RAX is anything but zero, make this a call to that. * See arch_ftrace_set_direct_caller(). */ - movq ORIG_RAX(%rsp), %rax testq %rax, %rax SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL) jnz 1f @@ -289,15 +283,6 @@ SYM_FUNC_START(__fentry__) cmpq $ftrace_stub, ftrace_trace_function jnz trace -fgraph_trace: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpq $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpq $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif - SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) retq @@ -315,25 +300,12 @@ trace: CALL_NOSPEC r8 restore_mcount_regs - jmp fgraph_trace + jmp ftrace_stub SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_FUNC_START(ftrace_graph_caller) - /* Saves rbp into %rdx and fills first parameter */ - save_mcount_regs - - leaq MCOUNT_REG_SIZE+8(%rsp), %rsi - movq $0, %rdx /* No framepointers needed */ - call prepare_ftrace_return - - restore_mcount_regs - - retq -SYM_FUNC_END(ftrace_graph_caller) - SYM_FUNC_START(return_to_handler) subq $24, %rsp diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index de01903c3735..fc5371a7e9d1 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -19,7 +19,7 @@ #include <linux/start_kernel.h> #include <linux/io.h> #include <linux/memblock.h> -#include <linux/mem_encrypt.h> +#include <linux/cc_platform.h> #include <linux/pgtable.h> #include <asm/processor.h> @@ -284,8 +284,13 @@ unsigned long __head __startup_64(unsigned long physaddr, * The bss section will be memset to zero later in the initialization so * there is no need to zero it after changing the memory encryption * attribute. + * + * This is early code, use an open coded check for SME instead of + * using cc_platform_has(). This eliminates worries about removing + * instrumentation or checking boot_cpu_data in the cc_platform_has() + * function. */ - if (mem_encrypt_active()) { + if (sme_get_me_mask()) { vaddr = (unsigned long)__start_bss_decrypted; vaddr_end = (unsigned long)__end_bss_decrypted; for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 42fc41dd0e1f..882213df3713 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -10,6 +10,7 @@ #include <asm/irq_remapping.h> #include <asm/hpet.h> #include <asm/time.h> +#include <asm/mwait.h> #undef pr_fmt #define pr_fmt(fmt) "hpet: " fmt @@ -916,6 +917,83 @@ static bool __init hpet_counting(void) return false; } +static bool __init mwait_pc10_supported(void) +{ + unsigned int eax, ebx, ecx, mwait_substates; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + if (!cpu_feature_enabled(X86_FEATURE_MWAIT)) + return false; + + if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) + return false; + + cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates); + + return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) && + (ecx & CPUID5_ECX_INTERRUPT_BREAK) && + (mwait_substates & (0xF << 28)); +} + +/* + * Check whether the system supports PC10. If so force disable HPET as that + * stops counting in PC10. This check is overbroad as it does not take any + * of the following into account: + * + * - ACPI tables + * - Enablement of intel_idle + * - Command line arguments which limit intel_idle C-state support + * + * That's perfectly fine. HPET is a piece of hardware designed by committee + * and the only reasons why it is still in use on modern systems is the + * fact that it is impossible to reliably query TSC and CPU frequency via + * CPUID or firmware. + * + * If HPET is functional it is useful for calibrating TSC, but this can be + * done via PMTIMER as well which seems to be the last remaining timer on + * X86/INTEL platforms that has not been completely wreckaged by feature + * creep. + * + * In theory HPET support should be removed altogether, but there are older + * systems out there which depend on it because TSC and APIC timer are + * dysfunctional in deeper C-states. + * + * It's only 20 years now that hardware people have been asked to provide + * reliable and discoverable facilities which can be used for timekeeping + * and per CPU timer interrupts. + * + * The probability that this problem is going to be solved in the + * forseeable future is close to zero, so the kernel has to be cluttered + * with heuristics to keep up with the ever growing amount of hardware and + * firmware trainwrecks. Hopefully some day hardware people will understand + * that the approach of "This can be fixed in software" is not sustainable. + * Hope dies last... + */ +static bool __init hpet_is_pc10_damaged(void) +{ + unsigned long long pcfg; + + /* Check whether PC10 substates are supported */ + if (!mwait_pc10_supported()) + return false; + + /* Check whether PC10 is enabled in PKG C-state limit */ + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg); + if ((pcfg & 0xF) < 8) + return false; + + if (hpet_force_user) { + pr_warn("HPET force enabled via command line, but dysfunctional in PC10.\n"); + return false; + } + + pr_info("HPET dysfunctional in PC10. Force disabled.\n"); + boot_hpet_disable = true; + return true; +} + /** * hpet_enable - Try to setup the HPET timer. Returns 1 on success. */ @@ -929,6 +1007,9 @@ int __init hpet_enable(void) if (!is_hpet_capable()) return 0; + if (hpet_is_pc10_damaged()) + return 0; + hpet_set_mapping(); if (!hpet_virt_address) return 0; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index e28f6a5d14f1..766ffe3ba313 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -291,8 +291,10 @@ void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)) { if (handler) kvm_posted_intr_wakeup_handler = handler; - else + else { kvm_posted_intr_wakeup_handler = dummy_handler; + synchronize_rcu(); + } } EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 044902d5a3c4..e5dd6da78713 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -132,6 +132,7 @@ int irq_init_percpu_irqstack(unsigned int cpu) return 0; } +#ifndef CONFIG_PREEMPT_RT void do_softirq_own_stack(void) { struct irq_stack *irqstk; @@ -148,6 +149,7 @@ void do_softirq_own_stack(void) call_on_stack(__do_softirq, isp); } +#endif void __handle_irq(struct irq_desc *desc, struct pt_regs *regs) { diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index 8ef35063964b..760e1f293093 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -7,9 +7,11 @@ /* * unsigned long native_save_fl(void) */ +.pushsection .noinstr.text, "ax" SYM_FUNC_START(native_save_fl) pushf pop %_ASM_AX ret SYM_FUNC_END(native_save_fl) +.popsection EXPORT_SYMBOL(native_save_fl) diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 1afbdd1dd777..9ff480e94511 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -198,7 +198,7 @@ void sched_set_itmt_core_prio(int prio, int core_cpu) * of the priority chain and only used when * all other high priority cpus are out of capacity. */ - smt_prio = prio * smp_num_siblings / i; + smt_prio = prio * smp_num_siblings / (i * i); per_cpu(sched_core_priority, cpu) = smt_prio; i++; } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index b6e046e4b289..fce99e249d61 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -809,7 +809,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) ri->fp = sara; /* Replace the return addr with trampoline addr */ - *sara = (unsigned long) &kretprobe_trampoline; + *sara = (unsigned long) &__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -1019,52 +1019,91 @@ NOKPROBE_SYMBOL(kprobe_int3_handler); */ asm( ".text\n" - ".global kretprobe_trampoline\n" - ".type kretprobe_trampoline, @function\n" - "kretprobe_trampoline:\n" - /* We don't bother saving the ss register */ + ".global __kretprobe_trampoline\n" + ".type __kretprobe_trampoline, @function\n" + "__kretprobe_trampoline:\n" #ifdef CONFIG_X86_64 + /* Push a fake return address to tell the unwinder it's a kretprobe. */ + " pushq $__kretprobe_trampoline\n" + UNWIND_HINT_FUNC + /* Save the 'sp - 8', this will be fixed later. */ " pushq %rsp\n" " pushfq\n" SAVE_REGS_STRING " movq %rsp, %rdi\n" " call trampoline_handler\n" - /* Replace saved sp with true return address. */ - " movq %rax, 19*8(%rsp)\n" RESTORE_REGS_STRING + /* In trampoline_handler(), 'regs->flags' is copied to 'regs->sp'. */ + " addq $8, %rsp\n" " popfq\n" #else + /* Push a fake return address to tell the unwinder it's a kretprobe. */ + " pushl $__kretprobe_trampoline\n" + UNWIND_HINT_FUNC + /* Save the 'sp - 4', this will be fixed later. */ " pushl %esp\n" " pushfl\n" SAVE_REGS_STRING " movl %esp, %eax\n" " call trampoline_handler\n" - /* Replace saved sp with true return address. */ - " movl %eax, 15*4(%esp)\n" RESTORE_REGS_STRING + /* In trampoline_handler(), 'regs->flags' is copied to 'regs->sp'. */ + " addl $4, %esp\n" " popfl\n" #endif " ret\n" - ".size kretprobe_trampoline, .-kretprobe_trampoline\n" + ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n" ); -NOKPROBE_SYMBOL(kretprobe_trampoline); -STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +NOKPROBE_SYMBOL(__kretprobe_trampoline); +/* + * __kretprobe_trampoline() skips updating frame pointer. The frame pointer + * saved in trampoline_handler() points to the real caller function's + * frame pointer. Thus the __kretprobe_trampoline() doesn't have a + * standard stack frame with CONFIG_FRAME_POINTER=y. + * Let's mark it non-standard function. Anyway, FP unwinder can correctly + * unwind without the hint. + */ +STACK_FRAME_NON_STANDARD_FP(__kretprobe_trampoline); + +/* This is called from kretprobe_trampoline_handler(). */ +void arch_kretprobe_fixup_return(struct pt_regs *regs, + kprobe_opcode_t *correct_ret_addr) +{ + unsigned long *frame_pointer = ®s->sp + 1; + /* Replace fake return address with real one. */ + *frame_pointer = (unsigned long)correct_ret_addr; +} /* - * Called from kretprobe_trampoline + * Called from __kretprobe_trampoline */ -__used __visible void *trampoline_handler(struct pt_regs *regs) +__used __visible void trampoline_handler(struct pt_regs *regs) { + unsigned long *frame_pointer; + /* fixup registers */ regs->cs = __KERNEL_CS; #ifdef CONFIG_X86_32 regs->gs = 0; #endif - regs->ip = (unsigned long)&kretprobe_trampoline; + regs->ip = (unsigned long)&__kretprobe_trampoline; regs->orig_ax = ~0UL; + regs->sp += sizeof(long); + frame_pointer = ®s->sp + 1; - return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, ®s->sp); + /* + * The return address at 'frame_pointer' is recovered by the + * arch_kretprobe_fixup_return() which called from the + * kretprobe_trampoline_handler(). + */ + kretprobe_trampoline_handler(regs, frame_pointer); + + /* + * Copy FLAGS to 'pt_regs::sp' so that __kretprobe_trapmoline() + * can do RET right after POPF. + */ + regs->sp = regs->flags; } NOKPROBE_SYMBOL(trampoline_handler); diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 596de2f6d3a5..dd2ec14adb77 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -25,7 +25,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -59,7 +58,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, __this_cpu_write(current_kprobe, NULL); } out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 71425ebba98a..b4a54a52aa59 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -367,10 +367,10 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op) /* Check the addr is within the optimized instructions. */ int arch_within_optimized_kprobe(struct optimized_kprobe *op, - unsigned long addr) + kprobe_opcode_t *addr) { - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + op->optinsn.size > addr); + return (op->kp.addr <= addr && + op->kp.addr + op->optinsn.size > addr); } /* Free optimized instruction slot */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b656456c3a94..8863d1941f1b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -27,6 +27,7 @@ #include <linux/nmi.h> #include <linux/swait.h> #include <linux/syscore_ops.h> +#include <linux/cc_platform.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -418,7 +419,7 @@ static void __init sev_map_percpu_data(void) { int cpu; - if (!sev_active()) + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; for_each_possible_cpu(cpu) { diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index ad273e5861c1..462dd8e9b03d 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -16,9 +16,9 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/set_memory.h> +#include <linux/cc_platform.h> #include <asm/hypervisor.h> -#include <asm/mem_encrypt.h> #include <asm/x86_init.h> #include <asm/kvmclock.h> @@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); static struct pvclock_vsyscall_time_info hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); static struct pvclock_wall_clock wall_clock __bss_decrypted; -static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static struct pvclock_vsyscall_time_info *hvclock_mem; - -static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) -{ - return &this_cpu_read(hv_clock_per_cpu)->pvti; -} - -static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) -{ - return this_cpu_read(hv_clock_per_cpu); -} +DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu); /* * The wallclock is the time of day when we booted. Since then, some time may @@ -232,7 +223,7 @@ static void __init kvmclock_init_mem(void) * hvclock is shared between the guest and the hypervisor, must * be mapped decrypted. */ - if (sev_active()) { + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { r = set_memory_decrypted((unsigned long) hvclock_mem, 1UL << order); if (r) { diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 131f30fdcfbd..f5da4a18070a 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -17,6 +17,7 @@ #include <linux/suspend.h> #include <linux/vmalloc.h> #include <linux/efi.h> +#include <linux/cc_platform.h> #include <asm/init.h> #include <asm/tlbflush.h> @@ -166,7 +167,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) } pte = pte_offset_kernel(pmd, vaddr); - if (sev_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) prot = PAGE_KERNEL_EXEC; set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot)); @@ -206,7 +207,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) level4p = (pgd_t *)__va(start_pgtable); clear_page(level4p); - if (sev_active()) { + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { info.page_flag |= _PAGE_ENC; info.kernpg_flag |= _PAGE_ENC; } @@ -358,7 +359,7 @@ void machine_kexec(struct kimage *image) (unsigned long)page_list, image->start, image->preserve_context, - sme_active()); + cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -569,12 +570,12 @@ void arch_kexec_unprotect_crashkres(void) */ int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) { - if (sev_active()) + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) return 0; /* - * If SME is active we need to be sure that kexec pages are - * not encrypted because when we boot to the new kernel the + * If host memory encryption is active we need to be sure that kexec + * pages are not encrypted because when we boot to the new kernel the * pages won't be accessed encrypted (initially). */ return set_memory_decrypted((unsigned long)vaddr, pages); @@ -582,12 +583,12 @@ int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { - if (sev_active()) + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) return; /* - * If SME is active we need to reset the pages back to being - * an encrypted mapping before freeing them. + * If host memory encryption is active we need to reset the pages back + * to being an encrypted mapping before freeing them. */ set_memory_encrypted((unsigned long)vaddr, pages); } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 5e9a34b5bd74..169fb6f4cd2e 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -251,7 +251,8 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, - *para = NULL, *orc = NULL, *orc_ip = NULL; + *para = NULL, *orc = NULL, *orc_ip = NULL, + *retpolines = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { @@ -267,8 +268,14 @@ int module_finalize(const Elf_Ehdr *hdr, orc = s; if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) orc_ip = s; + if (!strcmp(".retpoline_sites", secstrings + s->sh_name)) + retpolines = s; } + if (retpolines) { + void *rseg = (void *)retpolines->sh_addr; + apply_retpolines(rseg, rseg + retpolines->sh_size); + } if (alt) { /* patch .altinstructions */ void *aseg = (void *)alt->sh_addr; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 04cafc057bed..ebc45360ffd4 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -218,6 +218,36 @@ void paravirt_end_context_switch(struct task_struct *next) if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES)) arch_enter_lazy_mmu_mode(); } + +static noinstr unsigned long pv_native_read_cr2(void) +{ + return native_read_cr2(); +} + +static noinstr void pv_native_write_cr2(unsigned long val) +{ + native_write_cr2(val); +} + +static noinstr unsigned long pv_native_get_debugreg(int regno) +{ + return native_get_debugreg(regno); +} + +static noinstr void pv_native_set_debugreg(int regno, unsigned long val) +{ + native_set_debugreg(regno, val); +} + +static noinstr void pv_native_irq_enable(void) +{ + native_irq_enable(); +} + +static noinstr void pv_native_irq_disable(void) +{ + native_irq_disable(); +} #endif enum paravirt_lazy_mode paravirt_get_lazy_mode(void) @@ -244,8 +274,8 @@ struct paravirt_patch_template pv_ops = { #ifdef CONFIG_PARAVIRT_XXL .cpu.cpuid = native_cpuid, - .cpu.get_debugreg = native_get_debugreg, - .cpu.set_debugreg = native_set_debugreg, + .cpu.get_debugreg = pv_native_get_debugreg, + .cpu.set_debugreg = pv_native_set_debugreg, .cpu.read_cr0 = native_read_cr0, .cpu.write_cr0 = native_write_cr0, .cpu.write_cr4 = native_write_cr4, @@ -281,8 +311,8 @@ struct paravirt_patch_template pv_ops = { /* Irq ops. */ .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), - .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), - .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), + .irq.irq_disable = __PV_IS_CALLEE_SAVE(pv_native_irq_disable), + .irq.irq_enable = __PV_IS_CALLEE_SAVE(pv_native_irq_enable), .irq.safe_halt = native_safe_halt, .irq.halt = native_halt, #endif /* CONFIG_PARAVIRT_XXL */ @@ -298,8 +328,8 @@ struct paravirt_patch_template pv_ops = { .mmu.exit_mmap = paravirt_nop, #ifdef CONFIG_PARAVIRT_XXL - .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(native_read_cr2), - .mmu.write_cr2 = native_write_cr2, + .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2), + .mmu.write_cr2 = pv_native_write_cr2, .mmu.read_cr3 = __native_read_cr3, .mmu.write_cr3 = native_write_cr3, @@ -371,9 +401,6 @@ struct paravirt_patch_template pv_ops = { }; #ifdef CONFIG_PARAVIRT_XXL -/* At this point, native_get/set_debugreg has real function entries */ -NOKPROBE_SYMBOL(native_get_debugreg); -NOKPROBE_SYMBOL(native_set_debugreg); NOKPROBE_SYMBOL(native_load_idt); void (*paravirt_iret)(void) = native_iret; diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index c2cfa5e7c152..814ab46a0dad 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -6,7 +6,7 @@ #include <linux/swiotlb.h> #include <linux/memblock.h> #include <linux/dma-direct.h> -#include <linux/mem_encrypt.h> +#include <linux/cc_platform.h> #include <asm/iommu.h> #include <asm/swiotlb.h> @@ -45,11 +45,10 @@ int __init pci_swiotlb_detect_4gb(void) swiotlb = 1; /* - * If SME is active then swiotlb will be set to 1 so that bounce - * buffers are allocated and used for devices that do not support - * the addressing range required for the encryption mask. + * Set swiotlb to 1 so that bounce buffers are allocated and used for + * devices that can't support DMA to encrypted memory. */ - if (sme_active()) + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) swiotlb = 1; return swiotlb; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 1d9463e3096b..e9ee8b526319 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -30,7 +30,9 @@ #include <asm/apic.h> #include <linux/uaccess.h> #include <asm/mwait.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> +#include <asm/fpu/sched.h> +#include <asm/fpu/xstate.h> #include <asm/debugreg.h> #include <asm/nmi.h> #include <asm/tlbflush.h> @@ -43,6 +45,7 @@ #include <asm/io_bitmap.h> #include <asm/proto.h> #include <asm/frame.h> +#include <asm/unwind.h> #include "process.h" @@ -87,9 +90,20 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) #ifdef CONFIG_VM86 dst->thread.vm86 = NULL; #endif - return fpu_clone(dst); + /* Drop the copied pointer to current's fpstate */ + dst->thread.fpu.fpstate = NULL; + + return 0; } +#ifdef CONFIG_X86_64 +void arch_release_task_struct(struct task_struct *tsk) +{ + if (fpu_state_size_dynamic()) + fpstate_free(&tsk->thread.fpu); +} +#endif + /* * Free thread data structures etc.. */ @@ -132,6 +146,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; + p->thread.iopl_warn = 0; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); #ifdef CONFIG_X86_64 @@ -154,6 +169,8 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, frame->flags = X86_EFLAGS_FIXED; #endif + fpu_clone(p, clone_flags); + /* Kernel thread ? */ if (unlikely(p->flags & PF_KTHREAD)) { p->thread.pkru = pkru_get_init_value(); @@ -942,70 +959,36 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) * because the task might wake up and we might look at a stack * changing under us. */ -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { - unsigned long start, bottom, top, sp, fp, ip, ret = 0; - int count = 0; - - if (p == current || task_is_running(p)) - return 0; - - if (!try_get_task_stack(p)) - return 0; - - start = (unsigned long)task_stack_page(p); - if (!start) - goto out; + struct unwind_state state; + unsigned long addr = 0; - /* - * Layout of the stack page: - * - * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long) - * PADDING - * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING - * stack - * ----------- bottom = start - * - * The tasks stack pointer points at the location where the - * framepointer is stored. The data on the stack is: - * ... IP FP ... IP FP - * - * We need to read FP and IP, so we need to adjust the upper - * bound by another unsigned long. - */ - top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; - top -= 2 * sizeof(unsigned long); - bottom = start; - - sp = READ_ONCE(p->thread.sp); - if (sp < bottom || sp > top) - goto out; - - fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp); - do { - if (fp < bottom || fp > top) - goto out; - ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); - if (!in_sched_functions(ip)) { - ret = ip; - goto out; - } - fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); - } while (count++ < 16 && !task_is_running(p)); + for (unwind_start(&state, p, NULL, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr) + break; + if (in_sched_functions(addr)) + continue; + break; + } -out: - put_task_stack(p); - return ret; + return addr; } long do_arch_prctl_common(struct task_struct *task, int option, - unsigned long cpuid_enabled) + unsigned long arg2) { switch (option) { case ARCH_GET_CPUID: return get_cpuid_mode(); case ARCH_SET_CPUID: - return set_cpuid_mode(task, cpuid_enabled); + return set_cpuid_mode(task, arg2); + case ARCH_GET_XCOMP_SUPP: + case ARCH_GET_XCOMP_PERM: + case ARCH_REQ_XCOMP_PERM: + return fpu_xstate_prctl(task, option, arg2); } return -EINVAL; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 4f2f54e1281c..26edb1cd07a4 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -41,7 +41,7 @@ #include <asm/ldt.h> #include <asm/processor.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/sched.h> #include <asm/desc.h> #include <linux/err.h> @@ -160,7 +160,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct thread_struct *prev = &prev_p->thread, *next = &next_p->thread; struct fpu *prev_fpu = &prev->fpu; - struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ @@ -213,7 +212,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) this_cpu_write(current_task, next_p); - switch_fpu_finish(next_fpu); + switch_fpu_finish(); /* Load the Intel cache allocation PQR MSR. */ resctrl_sched_in(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ec0d836a13b1..3402edec236c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -42,7 +42,7 @@ #include <asm/processor.h> #include <asm/pkru.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/sched.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> @@ -559,7 +559,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; struct fpu *prev_fpu = &prev->fpu; - struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && @@ -620,7 +619,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) this_cpu_write(current_task, next_p); this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); - switch_fpu_finish(next_fpu); + switch_fpu_finish(); /* Reload sp0. */ update_task_stack(next_p); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 4c208ea3bd9f..6d2244c94799 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -29,9 +29,9 @@ #include <linux/uaccess.h> #include <asm/processor.h> -#include <asm/fpu/internal.h> #include <asm/fpu/signal.h> #include <asm/fpu/regset.h> +#include <asm/fpu/xstate.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index c53271aebb64..c8fe74a28143 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -47,7 +47,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) * %rsi page_list * %rdx start address * %rcx preserve_context - * %r8 sme_active + * %r8 host_mem_enc_active */ /* Save the CPU context, used for jumping back */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 79f164141116..40ed44ead063 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -830,6 +830,20 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); + /* + * Do some memory reservations *before* memory is added to memblock, so + * memblock allocations won't overwrite it. + * + * After this point, everything still needed from the boot loader or + * firmware or kernel text should be early reserved or marked not RAM in + * e820. All other memory is free game. + * + * This call needs to happen before e820__memory_setup() which calls the + * xen_memory_setup() on Xen dom0 which relies on the fact that those + * early reservations have happened already. + */ + early_reserve_memory(); + iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; e820__memory_setup(); parse_setup_data(); @@ -876,18 +890,6 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); - /* - * Do some memory reservations *before* memory is added to - * memblock, so memblock allocations won't overwrite it. - * Do it after early param, so we could get (unlikely) panic from - * serial. - * - * After this point everything still needed from the boot loader or - * firmware or kernel text should be early reserved or marked not - * RAM in e820. All other memory is free game. - */ - early_reserve_memory(); - #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 9f90f460a28c..787dc5f568b5 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -64,7 +64,7 @@ static bool sev_es_negotiate_protocol(void) static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb) { ghcb->save.sw_exit_code = 0; - memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); + __builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } static bool vc_decoding_needed(unsigned long exit_code) @@ -94,25 +94,15 @@ static void vc_finish_insn(struct es_em_ctxt *ctxt) ctxt->regs->ip += ctxt->insn.length; } -static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, - struct es_em_ctxt *ctxt, - u64 exit_code, u64 exit_info_1, - u64 exit_info_2) +static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { - enum es_result ret; - - /* Fill in protocol and format specifiers */ - ghcb->protocol_version = GHCB_PROTOCOL_MAX; - ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; - - ghcb_set_sw_exit_code(ghcb, exit_code); - ghcb_set_sw_exit_info_1(ghcb, exit_info_1); - ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + u32 ret; - sev_es_wr_ghcb_msr(__pa(ghcb)); - VMGEXIT(); + ret = ghcb->save.sw_exit_info_1 & GENMASK_ULL(31, 0); + if (!ret) + return ES_OK; - if ((ghcb->save.sw_exit_info_1 & 0xffffffff) == 1) { + if (ret == 1) { u64 info = ghcb->save.sw_exit_info_2; unsigned long v; @@ -124,17 +114,40 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, ((v == X86_TRAP_GP) || (v == X86_TRAP_UD)) && ((info & SVM_EVTINJ_TYPE_MASK) == SVM_EVTINJ_TYPE_EXEPT)) { ctxt->fi.vector = v; + if (info & SVM_EVTINJ_VALID_ERR) ctxt->fi.error_code = info >> 32; - ret = ES_EXCEPTION; - } else { - ret = ES_VMM_ERROR; + + return ES_EXCEPTION; } - } else { - ret = ES_OK; } - return ret; + return ES_VMM_ERROR; +} + +enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, + struct es_em_ctxt *ctxt, u64 exit_code, + u64 exit_info_1, u64 exit_info_2) +{ + /* Fill in protocol and format specifiers */ + ghcb->protocol_version = GHCB_PROTOCOL_MAX; + ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; + + ghcb_set_sw_exit_code(ghcb, exit_code); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + /* + * Hyper-V unenlightened guests use a paravisor for communicating and + * GHCB pages are being allocated and set up by that paravisor. Linux + * should not change the GHCB page's physical address. + */ + if (set_ghcb_msr) + sev_es_wr_ghcb_msr(__pa(ghcb)); + + VMGEXIT(); + + return verify_exception_info(ghcb, ctxt); } /* @@ -411,7 +424,7 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) */ sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer); ghcb_set_sw_scratch(ghcb, sw_scratch); - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_IOIO, exit_info_1, exit_info_2); if (ret != ES_OK) return ret; @@ -453,7 +466,8 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) ghcb_set_rax(ghcb, rax); - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0); + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, + SVM_EXIT_IOIO, exit_info_1, 0); if (ret != ES_OK) return ret; @@ -484,7 +498,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb, /* xgetbv will cause #GP - use reset value for xcr0 */ ghcb_set_xcr0(ghcb, 1); - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_CPUID, 0, 0); if (ret != ES_OK) return ret; @@ -509,7 +523,7 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); enum es_result ret; - ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, 0, 0); if (ret != ES_OK) return ret; diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index a6895e440bc3..74f0ec955384 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -11,7 +11,7 @@ #include <linux/sched/debug.h> /* For show_regs() */ #include <linux/percpu-defs.h> -#include <linux/mem_encrypt.h> +#include <linux/cc_platform.h> #include <linux/printk.h> #include <linux/mm_types.h> #include <linux/set_memory.h> @@ -23,7 +23,7 @@ #include <asm/stacktrace.h> #include <asm/sev.h> #include <asm/insn-eval.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/xcr.h> #include <asm/processor.h> #include <asm/realmode.h> #include <asm/traps.h> @@ -46,16 +46,6 @@ static struct ghcb __initdata *boot_ghcb; struct sev_es_runtime_data { struct ghcb ghcb_page; - /* Physical storage for the per-CPU IST stack of the #VC handler */ - char ist_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); - - /* - * Physical storage for the per-CPU fall-back stack of the #VC handler. - * The fall-back stack is used when it is not safe to switch back to the - * interrupted stack in the #VC entry code. - */ - char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); - /* * Reserve one page per CPU as backup storage for the unencrypted GHCB. * It is needed when an NMI happens while the #VC handler uses the real @@ -99,27 +89,6 @@ DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); /* Needed in vc_early_forward_exception */ void do_early_exception(struct pt_regs *regs, int trapnr); -static void __init setup_vc_stacks(int cpu) -{ - struct sev_es_runtime_data *data; - struct cpu_entry_area *cea; - unsigned long vaddr; - phys_addr_t pa; - - data = per_cpu(runtime_data, cpu); - cea = get_cpu_entry_area(cpu); - - /* Map #VC IST stack */ - vaddr = CEA_ESTACK_BOT(&cea->estacks, VC); - pa = __pa(data->ist_stack); - cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); - - /* Map VC fall-back stack */ - vaddr = CEA_ESTACK_BOT(&cea->estacks, VC2); - pa = __pa(data->fallback_stack); - cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); -} - static __always_inline bool on_vc_stack(struct pt_regs *regs) { unsigned long sp = regs->sp; @@ -615,7 +584,7 @@ int __init sev_es_efi_map_ghcbs(pgd_t *pgd) int cpu; u64 pfn; - if (!sev_es_active()) + if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) return 0; pflags = _PAGE_NX | _PAGE_RW; @@ -648,7 +617,8 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) ghcb_set_rdx(ghcb, regs->dx); } - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0); + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_MSR, + exit_info_1, 0); if ((ret == ES_OK) && (!exit_info_1)) { regs->ax = ghcb->save.rax; @@ -774,7 +744,7 @@ void __init sev_es_init_vc_handling(void) BUILD_BUG_ON(offsetof(struct sev_es_runtime_data, ghcb_page) % PAGE_SIZE); - if (!sev_es_active()) + if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) return; if (!sev_es_check_cpu_features()) @@ -787,7 +757,6 @@ void __init sev_es_init_vc_handling(void) for_each_possible_cpu(cpu) { alloc_runtime_data(cpu); init_ghcb(cpu); - setup_vc_stacks(cpu); } sev_es_setup_play_dead(); @@ -867,7 +836,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer)); - return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2); + return sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, exit_info_1, exit_info_2); } static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb, @@ -1117,7 +1086,7 @@ static enum es_result vc_handle_dr7_write(struct ghcb *ghcb, /* Using a value of 0 for ExitInfo1 means RAX holds the value */ ghcb_set_rax(ghcb, val); - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WRITE_DR7, 0, 0); if (ret != ES_OK) return ret; @@ -1147,7 +1116,7 @@ static enum es_result vc_handle_dr7_read(struct ghcb *ghcb, static enum es_result vc_handle_wbinvd(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { - return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); + return sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WBINVD, 0, 0); } static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) @@ -1156,7 +1125,7 @@ static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt ghcb_set_rcx(ghcb, ctxt->regs->cx); - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_RDPMC, 0, 0); if (ret != ES_OK) return ret; @@ -1197,7 +1166,7 @@ static enum es_result vc_handle_vmmcall(struct ghcb *ghcb, if (x86_platform.hyper.sev_es_hcall_prepare) x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs); - ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0); + ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_VMMCALL, 0, 0); if (ret != ES_OK) return ret; @@ -1319,13 +1288,26 @@ static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt) } } -static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs) +static __always_inline bool is_vc2_stack(unsigned long sp) { - unsigned long sp = (unsigned long)regs; - return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2)); } +static __always_inline bool vc_from_invalid_context(struct pt_regs *regs) +{ + unsigned long sp, prev_sp; + + sp = (unsigned long)regs; + prev_sp = regs->sp; + + /* + * If the code was already executing on the VC2 stack when the #VC + * happened, let it proceed to the normal handling routine. This way the + * code executing on the VC2 stack can cause #VC exceptions to get handled. + */ + return is_vc2_stack(sp) && !is_vc2_stack(prev_sp); +} + static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code) { struct ghcb_state state; @@ -1406,7 +1388,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication) * But keep this here in case the noinstr annotations are violated due * to bug elsewhere. */ - if (unlikely(on_vc_fallback_stack(regs))) { + if (unlikely(vc_from_invalid_context(regs))) { instrumentation_begin(); panic("Can't handle #VC exception from unsupported context\n"); instrumentation_end(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index f4d21e470083..ec71e06ae364 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/errno.h> #include <linux/wait.h> #include <linux/tracehook.h> @@ -30,8 +31,8 @@ #include <asm/processor.h> #include <asm/ucontext.h> -#include <asm/fpu/internal.h> #include <asm/fpu/signal.h> +#include <asm/fpu/xstate.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> @@ -41,6 +42,7 @@ #include <linux/compat.h> #include <asm/proto.h> #include <asm/ia32_unistd.h> +#include <asm/fpu/xstate.h> #endif /* CONFIG_X86_64 */ #include <asm/syscall.h> @@ -79,9 +81,9 @@ static void force_valid_ss(struct pt_regs *regs) # define CONTEXT_COPY_SIZE sizeof(struct sigcontext) #endif -static int restore_sigcontext(struct pt_regs *regs, - struct sigcontext __user *usc, - unsigned long uc_flags) +static bool restore_sigcontext(struct pt_regs *regs, + struct sigcontext __user *usc, + unsigned long uc_flags) { struct sigcontext sc; @@ -89,7 +91,7 @@ static int restore_sigcontext(struct pt_regs *regs, current->restart_block.fn = do_no_restart_syscall; if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE)) - return -EFAULT; + return false; #ifdef CONFIG_X86_32 set_user_gs(regs, sc.gs); @@ -244,7 +246,6 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, unsigned long math_size = 0; unsigned long sp = regs->sp; unsigned long buf_fx = 0; - int ret; /* redzone */ if (IS_ENABLED(CONFIG_X86_64)) @@ -292,8 +293,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, } /* save i387 and extended state */ - ret = copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size); - if (ret < 0) + if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size)) return (void __user *)-1L; return (void __user *)sp; @@ -643,7 +643,7 @@ SYSCALL_DEFINE0(sigreturn) * x86_32 has no uc_flags bits relevant to restore_sigcontext. * Save a few cycles by skipping the __get_user. */ - if (restore_sigcontext(regs, &frame->sc, 0)) + if (!restore_sigcontext(regs, &frame->sc, 0)) goto badframe; return regs->ax; @@ -671,7 +671,7 @@ SYSCALL_DEFINE0(rt_sigreturn) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; if (restore_altstack(&frame->uc.uc_stack)) @@ -721,12 +721,15 @@ badframe: /* max_frame_size tells userspace the worst case signal stack size. */ static unsigned long __ro_after_init max_frame_size; +static unsigned int __ro_after_init fpu_default_state_size; void __init init_sigframe_size(void) { + fpu_default_state_size = fpu__get_fpstate_size(); + max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING; - max_frame_size += fpu__get_fpstate_size() + MAX_XSAVE_PADDING; + max_frame_size += fpu_default_state_size + MAX_XSAVE_PADDING; /* Userspace expects an aligned size. */ max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); @@ -910,6 +913,62 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) force_sig(SIGSEGV); } +#ifdef CONFIG_DYNAMIC_SIGFRAME +#ifdef CONFIG_STRICT_SIGALTSTACK_SIZE +static bool strict_sigaltstack_size __ro_after_init = true; +#else +static bool strict_sigaltstack_size __ro_after_init = false; +#endif + +static int __init strict_sas_size(char *arg) +{ + return kstrtobool(arg, &strict_sigaltstack_size); +} +__setup("strict_sas_size", strict_sas_size); + +/* + * MINSIGSTKSZ is 2048 and can't be changed despite the fact that AVX512 + * exceeds that size already. As such programs might never use the + * sigaltstack they just continued to work. While always checking against + * the real size would be correct, this might be considered a regression. + * + * Therefore avoid the sanity check, unless enforced by kernel + * configuration or command line option. + * + * When dynamic FPU features are supported, the check is also enforced when + * the task has permissions to use dynamic features. Tasks which have no + * permission are checked against the size of the non-dynamic feature set + * if strict checking is enabled. This avoids forcing all tasks on the + * system to allocate large sigaltstacks even if they are never going + * to use a dynamic feature. As this is serialized via sighand::siglock + * any permission request for a dynamic feature either happened already + * or will see the newly install sigaltstack size in the permission checks. + */ +bool sigaltstack_size_valid(size_t ss_size) +{ + unsigned long fsize = max_frame_size - fpu_default_state_size; + u64 mask; + + lockdep_assert_held(¤t->sighand->siglock); + + if (!fpu_state_size_dynamic() && !strict_sigaltstack_size) + return true; + + fsize += current->group_leader->thread.fpu.perm.__user_state_size; + if (likely(ss_size > fsize)) + return true; + + if (strict_sigaltstack_size) + return ss_size > fsize; + + mask = current->group_leader->thread.fpu.perm.__state_perm; + if (mask & XFEATURE_MASK_USER_DYNAMIC) + return ss_size > fsize; + + return true; +} +#endif /* CONFIG_DYNAMIC_SIGFRAME */ + #ifdef CONFIG_X86_X32_ABI COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) { @@ -929,7 +988,7 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; if (compat_restore_altstack(&frame->uc.uc_stack)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 85f6e242b6b4..8241927addff 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -70,7 +70,7 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -101,6 +101,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map); DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); +DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); + /* Per CPU bogomips and other parameters */ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); @@ -464,6 +466,21 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } +static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + /* If the arch didn't set up l2c_id, fall back to SMT */ + if (per_cpu(cpu_l2c_id, cpu1) == BAD_APICID) + return match_smt(c, o); + + /* Do not match if L2 cache id does not match: */ + if (per_cpu(cpu_l2c_id, cpu1) != per_cpu(cpu_l2c_id, cpu2)) + return false; + + return topology_sane(c, o, "l2c"); +} + /* * Unlike the other levels, we do not enforce keeping a * multicore group inside a NUMA node. If this happens, we will @@ -523,7 +540,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) } -#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC) +#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC) static inline int x86_sched_itmt_flags(void) { return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0; @@ -541,12 +558,21 @@ static int x86_smt_flags(void) return cpu_smt_flags() | x86_sched_itmt_flags(); } #endif +#ifdef CONFIG_SCHED_CLUSTER +static int x86_cluster_flags(void) +{ + return cpu_cluster_flags() | x86_sched_itmt_flags(); +} +#endif #endif static struct sched_domain_topology_level x86_numa_in_package_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, #endif +#ifdef CONFIG_SCHED_CLUSTER + { cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) }, +#endif #ifdef CONFIG_SCHED_MC { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, #endif @@ -557,6 +583,9 @@ static struct sched_domain_topology_level x86_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, #endif +#ifdef CONFIG_SCHED_CLUSTER + { cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) }, +#endif #ifdef CONFIG_SCHED_MC { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, #endif @@ -584,6 +613,7 @@ void set_cpu_sibling_map(int cpu) if (!has_mp) { cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); + cpumask_set_cpu(cpu, cpu_l2c_shared_mask(cpu)); cpumask_set_cpu(cpu, topology_core_cpumask(cpu)); cpumask_set_cpu(cpu, topology_die_cpumask(cpu)); c->booted_cores = 1; @@ -602,6 +632,9 @@ void set_cpu_sibling_map(int cpu) if ((i == cpu) || (has_mp && match_llc(c, o))) link_mask(cpu_llc_shared_mask, cpu, i); + if ((i == cpu) || (has_mp && match_l2c(c, o))) + link_mask(cpu_l2c_shared_mask, cpu, i); + if ((i == cpu) || (has_mp && match_die(c, o))) link_mask(topology_die_cpumask, cpu, i); } @@ -652,6 +685,11 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return cpu_llc_shared_mask(cpu); } +const struct cpumask *cpu_clustergroup_mask(int cpu) +{ + return cpu_l2c_shared_mask(cpu); +} + static void impress_friends(void) { int cpu; @@ -1335,6 +1373,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL); zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL); } /* @@ -1564,7 +1603,10 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + for_each_cpu(sibling, cpu_l2c_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_l2c_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); + cpumask_clear(cpu_l2c_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); cpumask_clear(topology_die_cpumask(cpu)); @@ -2166,7 +2208,7 @@ DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; void arch_scale_freq_tick(void) { - u64 freq_scale = SCHED_CAPACITY_SCALE; + u64 freq_scale; u64 aperf, mperf; u64 acnt, mcnt; diff --git a/arch/x86/kernel/trace.c b/arch/x86/kernel/trace.c index 6b73b6f92ad3..8322e8352777 100644 --- a/arch/x86/kernel/trace.c +++ b/arch/x86/kernel/trace.c @@ -231,4 +231,4 @@ void osnoise_arch_unregister(void) unregister_trace_local_timer_exit(trace_intel_irq_exit, "local_timer"); unregister_trace_local_timer_entry(trace_intel_irq_entry, NULL); } -#endif /* CONFIG_OSNOISE_TRAECR && CONFIG_X86_LOCAL_APIC */ +#endif /* CONFIG_OSNOISE_TRACER && CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a58800973aed..c9d566dcf89a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -48,7 +48,7 @@ #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/cpu.h> #include <asm/cpu_entry_area.h> #include <asm/mce.h> @@ -313,17 +313,19 @@ out: } #ifdef CONFIG_VMAP_STACK -__visible void __noreturn handle_stack_overflow(const char *message, - struct pt_regs *regs, - unsigned long fault_address) +__visible void __noreturn handle_stack_overflow(struct pt_regs *regs, + unsigned long fault_address, + struct stack_info *info) { - printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n", - (void *)fault_address, current->stack, - (char *)current->stack + THREAD_SIZE - 1); - die(message, regs, 0); + const char *name = stack_type_name(info->type); + + printk(KERN_EMERG "BUG: %s stack guard page was hit at %p (stack is %p..%p)\n", + name, (void *)fault_address, info->begin, info->end); + + die("stack guard page", regs, 0); /* Be absolutely certain we don't return. */ - panic("%s", message); + panic("%s stack guard hit", name); } #endif @@ -353,6 +355,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault) #ifdef CONFIG_VMAP_STACK unsigned long address = read_cr2(); + struct stack_info info; #endif #ifdef CONFIG_X86_ESPFIX64 @@ -455,10 +458,8 @@ DEFINE_IDTENTRY_DF(exc_double_fault) * stack even if the actual trigger for the double fault was * something else. */ - if ((unsigned long)task_stack_page(tsk) - 1 - address < PAGE_SIZE) { - handle_stack_overflow("kernel stack overflow (double-fault)", - regs, address); - } + if (get_stack_guard_info((void *)address, &info)) + handle_stack_overflow(regs, address, &info); #endif pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); @@ -528,6 +529,36 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, #define GPFSTR "general protection fault" +static bool fixup_iopl_exception(struct pt_regs *regs) +{ + struct thread_struct *t = ¤t->thread; + unsigned char byte; + unsigned long ip; + + if (!IS_ENABLED(CONFIG_X86_IOPL_IOPERM) || t->iopl_emul != 3) + return false; + + if (insn_get_effective_ip(regs, &ip)) + return false; + + if (get_user(byte, (const char __user *)ip)) + return false; + + if (byte != 0xfa && byte != 0xfb) + return false; + + if (!t->iopl_warn && printk_ratelimit()) { + pr_err("%s[%d] attempts to use CLI/STI, pretending it's a NOP, ip:%lx", + current->comm, task_pid_nr(current), ip); + print_vma_addr(KERN_CONT " in ", ip); + pr_cont("\n"); + t->iopl_warn = 1; + } + + regs->ip += 1; + return true; +} + DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) { char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; @@ -553,6 +584,9 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) tsk = current; if (user_mode(regs)) { + if (fixup_iopl_exception(regs)) + goto exit; + tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; @@ -709,7 +743,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r stack = (unsigned long *)sp; if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY || - info.type >= STACK_TYPE_EXCEPTION_LAST) + info.type > STACK_TYPE_EXCEPTION_LAST) sp = __this_cpu_ist_top_va(VC2); sync: @@ -1108,10 +1142,48 @@ DEFINE_IDTENTRY(exc_spurious_interrupt_bug) */ } +static bool handle_xfd_event(struct pt_regs *regs) +{ + u64 xfd_err; + int err; + + if (!IS_ENABLED(CONFIG_X86_64) || !cpu_feature_enabled(X86_FEATURE_XFD)) + return false; + + rdmsrl(MSR_IA32_XFD_ERR, xfd_err); + if (!xfd_err) + return false; + + wrmsrl(MSR_IA32_XFD_ERR, 0); + + /* Die if that happens in kernel space */ + if (WARN_ON(!user_mode(regs))) + return false; + + local_irq_enable(); + + err = xfd_enable_feature(xfd_err); + + switch (err) { + case -EPERM: + force_sig_fault(SIGILL, ILL_ILLOPC, error_get_trap_addr(regs)); + break; + case -EFAULT: + force_sig(SIGSEGV); + break; + } + + local_irq_disable(); + return true; +} + DEFINE_IDTENTRY(exc_device_not_available) { unsigned long cr0 = read_cr0(); + if (handle_xfd_event(regs)) + return; + #ifdef CONFIG_MATH_EMULATION if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) { struct math_emu_info info = { }; diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index 576b47e7523d..5a4b21389b1d 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -92,8 +92,8 @@ static const char * const umip_insns[5] = { #define umip_pr_err(regs, fmt, ...) \ umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__) -#define umip_pr_warn(regs, fmt, ...) \ - umip_printk(regs, KERN_WARNING, fmt, ##__VA_ARGS__) +#define umip_pr_debug(regs, fmt, ...) \ + umip_printk(regs, KERN_DEBUG, fmt, ##__VA_ARGS__) /** * umip_printk() - Print a rate-limited message @@ -361,10 +361,10 @@ bool fixup_umip_exception(struct pt_regs *regs) if (umip_inst < 0) return false; - umip_pr_warn(regs, "%s instruction cannot be used by applications.\n", + umip_pr_debug(regs, "%s instruction cannot be used by applications.\n", umip_insns[umip_inst]); - umip_pr_warn(regs, "For now, expensive software emulation returns the result.\n"); + umip_pr_debug(regs, "For now, expensive software emulation returns the result.\n"); if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size, user_64bit_mode(regs))) diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index d7c44b257f7f..8e1c50c86e5d 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -240,8 +240,7 @@ static bool update_stack_state(struct unwind_state *state, 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); + state->ip = unwind_recover_ret_addr(state, addr, addr_p); } /* Save the original stack pointer for unwind_dump(): */ diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index c49f10ffd8cd..884d68a6e714 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -15,8 +15,7 @@ unsigned long unwind_get_return_address(struct unwind_state *state) addr = READ_ONCE_NOCHECK(*state->sp); - return ftrace_graph_ret_addr(state->task, &state->graph_idx, - addr, state->sp); + return unwind_recover_ret_addr(state, addr, state->sp); } EXPORT_SYMBOL_GPL(unwind_get_return_address); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index a1202536fc57..e6f7592790af 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -534,9 +534,8 @@ bool unwind_next_frame(struct unwind_state *state) if (!deref_stack_reg(state, ip_p, &state->ip)) goto err; - state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - state->ip, (void *)ip_p); - + state->ip = unwind_recover_ret_addr(state, state->ip, + (unsigned long *)ip_p); state->sp = sp; state->regs = NULL; state->prev_regs = NULL; @@ -549,7 +548,18 @@ bool unwind_next_frame(struct unwind_state *state) (void *)orig_ip); goto err; } - + /* + * There is a small chance to interrupt at the entry of + * __kretprobe_trampoline() where the ORC info doesn't exist. + * That point is right after the RET to __kretprobe_trampoline() + * which was modified return address. + * At that point, the @addr_p of the unwind_recover_kretprobe() + * (this has to point the address of the stack entry storing + * the modified return address) must be "SP - (a stack entry)" + * because SP is incremented by the RET. + */ + state->ip = unwind_recover_kretprobe(state, state->ip, + (unsigned long *)(state->sp - sizeof(long))); state->regs = (struct pt_regs *)sp; state->prev_regs = NULL; state->full_regs = true; @@ -562,6 +572,9 @@ bool unwind_next_frame(struct unwind_state *state) (void *)orig_ip); goto err; } + /* See UNWIND_HINT_TYPE_REGS case comment. */ + state->ip = unwind_recover_kretprobe(state, state->ip, + (unsigned long *)(state->sp - sizeof(long))); if (state->full_regs) state->prev_regs = state->regs; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index efd9e9ea17f2..3d6dc12d198f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -272,6 +272,20 @@ SECTIONS __parainstructions_end = .; } +#ifdef CONFIG_RETPOLINE + /* + * List of instructions that call/jmp/jcc to retpoline thunks + * __x86_indirect_thunk_*(). These instructions can be patched along + * with alternatives, after which the section can be freed. + */ + . = ALIGN(8); + .retpoline_sites : AT(ADDR(.retpoline_sites) - LOAD_OFFSET) { + __retpoline_sites = .; + *(.retpoline_sites) + __retpoline_sites_end = .; + } +#endif + /* * struct alt_inst entries. From the header (alternative.h): * "Alternative instructions for different CPU types or capabilities" diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ac69894eab88..619186138176 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -129,4 +129,7 @@ config KVM_MMU_AUDIT This option adds a R/W kVM module parameter 'mmu_audit', which allows auditing of KVM MMU events at runtime. +config KVM_EXTERNAL_WRITE_TRACKING + bool + endif # VIRTUALIZATION diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index fe03bd978761..2d70edb0f323 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -53,9 +53,16 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } +/* + * This one is tied to SSB in the user API, and not + * visible in /proc/cpuinfo. + */ +#define KVM_X86_FEATURE_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ + #define F feature_bit #define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0) + static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( struct kvm_cpuid_entry2 *entries, int nent, u32 function, u32 index) { @@ -65,8 +72,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( for (i = 0; i < nent; i++) { e = &entries[i]; - if (e->function == function && (e->index == index || - !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + if (e->function == function && + (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)) return e; } @@ -500,7 +507,8 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_0008_EBX, F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | - F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) + F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | + __feature_bit(KVM_X86_FEATURE_PSFD) ); /* diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2837110e66ed..28b1a4e57827 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -435,7 +435,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); __FOP_RET(#op) asm(".pushsection .fixup, \"ax\"\n" - ".global kvm_fastop_exception \n" "kvm_fastop_exception: xor %esi, %esi; ret\n" ".popsection"); @@ -4206,7 +4205,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt) u64 cr4 = ctxt->ops->get_cr(ctxt, 4); if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt)) - return emulate_ud(ctxt); + return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } @@ -4223,6 +4222,11 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt) if (enable_vmware_backdoor && is_vmware_backdoor_pmc(rcx)) return X86EMUL_CONTINUE; + /* + * If CR4.PCE is set, the SDM requires CPL=0 or CR0.PE=0. The CR0.PE + * check however is unnecessary because CPL is always 0 outside + * protected mode. + */ if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) || ctxt->ops->check_pmc(ctxt, rcx)) return emulate_gp(ctxt, 0); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 232a86a6faaf..4f15c0165c05 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -112,7 +112,7 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, if (!!auto_eoi_old == !!auto_eoi_new) return; - mutex_lock(&vcpu->kvm->arch.apicv_update_lock); + down_write(&vcpu->kvm->arch.apicv_update_lock); if (auto_eoi_new) hv->synic_auto_eoi_used++; @@ -123,7 +123,7 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, !hv->synic_auto_eoi_used, APICV_INHIBIT_REASON_HYPERV); - mutex_unlock(&vcpu->kvm->arch.apicv_update_lock); + up_write(&vcpu->kvm->arch.apicv_update_lock); } static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, @@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_init(&hv_vcpu->stimer[i], i); - hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); + hv_vcpu->vp_index = vcpu->vcpu_idx; return 0; } @@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); - int vcpu_idx = kvm_vcpu_get_idx(vcpu); u32 new_vp_index = (u32)data; if (!host || new_vp_index >= KVM_MAX_VCPUS) @@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) * VP index is changing, adjust num_mismatched_vp_indexes if * it now matches or no longer matches vcpu_idx. */ - if (hv_vcpu->vp_index == vcpu_idx) + if (hv_vcpu->vp_index == vcpu->vcpu_idx) atomic_inc(&hv->num_mismatched_vp_indexes); - else if (new_vp_index == vcpu_idx) + else if (new_vp_index == vcpu->vcpu_idx) atomic_dec(&hv->num_mismatched_vp_indexes); hv_vcpu->vp_index = new_vp_index; @@ -1755,7 +1754,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool int i; gpa_t gpa; struct kvm *kvm = vcpu->kvm; - struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct hv_tlb_flush_ex flush_ex; struct hv_tlb_flush flush; u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; @@ -1837,18 +1835,19 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool } } - cpumask_clear(&hv_vcpu->tlb_flush); - - vcpu_mask = all_cpus ? NULL : - sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, - vp_bitmap, vcpu_bitmap); - /* * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ - kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, - NULL, vcpu_mask, &hv_vcpu->tlb_flush); + if (all_cpus) { + kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH_GUEST); + } else { + vcpu_mask = sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, + vp_bitmap, vcpu_bitmap); + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, + vcpu_mask); + } ret_success: /* We always do full TLB flush, set 'Reps completed' = 'Rep Count' */ diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 730da8537d05..ed1c4e546d04 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu); + return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx; } int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index ff005fe738a4..816a82515dcd 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_IDS); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); @@ -319,8 +319,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) unsigned index; bool mask_before, mask_after; union kvm_ioapic_redirect_entry *e; - unsigned long vcpu_bitmap; int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; + DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS); switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -384,9 +384,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) irq.shorthand = APIC_DEST_NOSHORT; irq.dest_id = e->fields.dest_id; irq.msi_redir_hint = false; - bitmap_zero(&vcpu_bitmap, 16); + bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); if (old_dest_mode != e->fields.dest_mode || old_dest_id != e->fields.dest_id) { /* @@ -399,10 +399,10 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) kvm_lapic_irq_dest_mode( !!e->fields.dest_mode); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); } kvm_make_scan_ioapic_request_mask(ioapic->kvm, - &vcpu_bitmap); + vcpu_bitmap); } else { kvm_make_scan_ioapic_request(ioapic->kvm); } diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index bbd4a5d18b5d..e66e620c3bed 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -39,13 +39,13 @@ struct kvm_vcpu; struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1); + DECLARE_BITMAP(map, KVM_MAX_VCPU_IDS); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID + 1]; + u8 vectors[KVM_MAX_VCPU_IDS]; }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 76fb00921203..d6ac32f3f650 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2321,13 +2321,14 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_apicv); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic = vcpu->arch.apic; + u64 msr_val; int i; if (!init_event) { - vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; + msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) - vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; + msr_val |= MSR_IA32_APICBASE_BSP; + kvm_lapic_set_base(vcpu, msr_val); } if (!apic) @@ -2336,11 +2337,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - if (!init_event) { - apic->base_address = APIC_DEFAULT_PHYS_BASE; - + /* The xAPIC ID is set at RESET even if the APIC was already enabled. */ + if (!init_event) kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); - } kvm_apic_set_version(apic->vcpu); for (i = 0; i < KVM_APIC_LVT_NUM; i++) @@ -2481,6 +2480,11 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) lapic_timer_advance_dynamic = false; } + /* + * Stuff the APIC ENABLE bit in lieu of temporarily incrementing + * apic_hw_disabled; the full RESET value is set by kvm_lapic_reset(). + */ + vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_iodevice_init(&apic->dev, &apic_mmio_ops); @@ -2942,5 +2946,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu) void kvm_lapic_exit(void) { static_key_deferred_flush(&apic_hw_disabled); + WARN_ON(static_branch_unlikely(&apic_hw_disabled.key)); static_key_deferred_flush(&apic_sw_disabled); + WARN_ON(static_branch_unlikely(&apic_sw_disabled.key)); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e9688a9f7b57..9ae6168d381e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -44,9 +44,8 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 -#define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | \ - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE | \ - X86_CR4_LA57) +#define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PSE | X86_CR4_PAE | X86_CR4_LA57 | \ + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE) #define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP) @@ -80,6 +79,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); +void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu); static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { @@ -114,17 +114,91 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) vcpu->arch.mmu->shadow_root_level); } -int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - bool prefault); +struct kvm_page_fault { + /* arguments to kvm_mmu_do_page_fault. */ + const gpa_t addr; + const u32 error_code; + const bool prefetch; + + /* Derived from error_code. */ + const bool exec; + const bool write; + const bool present; + const bool rsvd; + const bool user; + + /* Derived from mmu and global state. */ + const bool is_tdp; + const bool nx_huge_page_workaround_enabled; + + /* + * Whether a >4KB mapping can be created or is forbidden due to NX + * hugepages. + */ + bool huge_page_disallowed; + + /* + * Maximum page size that can be created for this fault; input to + * FNAME(fetch), __direct_map and kvm_tdp_mmu_map. + */ + u8 max_level; + + /* + * Page size that can be created based on the max_level and the + * page size used by the host mapping. + */ + u8 req_level; + + /* + * Page size that will be created based on the req_level and + * huge_page_disallowed. + */ + u8 goal_level; + + /* Shifted addr, or result of guest page table walk if addr is a gva. */ + gfn_t gfn; + + /* The memslot containing gfn. May be NULL. */ + struct kvm_memory_slot *slot; + + /* Outputs of kvm_faultin_pfn. */ + kvm_pfn_t pfn; + hva_t hva; + bool map_writable; +}; + +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); + +extern int nx_huge_pages; +static inline bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - u32 err, bool prefault) + u32 err, bool prefetch) { + struct kvm_page_fault fault = { + .addr = cr2_or_gpa, + .error_code = err, + .exec = err & PFERR_FETCH_MASK, + .write = err & PFERR_WRITE_MASK, + .present = err & PFERR_PRESENT_MASK, + .rsvd = err & PFERR_RSVD_MASK, + .user = err & PFERR_USER_MASK, + .prefetch = prefetch, + .is_tdp = likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault), + .nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(), + + .max_level = KVM_MAX_HUGEPAGE_LEVEL, + .req_level = PG_LEVEL_4K, + .goal_level = PG_LEVEL_4K, + }; #ifdef CONFIG_RETPOLINE - if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault)) - return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault); + if (fault.is_tdp) + return kvm_tdp_page_fault(vcpu, &fault); #endif - return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault); + return vcpu->arch.mmu->page_fault(vcpu, &fault); } /* @@ -230,14 +304,26 @@ int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); -static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) +static inline bool kvm_shadow_root_allocated(struct kvm *kvm) { /* - * Read memslot_have_rmaps before rmap pointers. Hence, threads reading - * memslots_have_rmaps in any lock context are guaranteed to see the - * pointers. Pairs with smp_store_release in alloc_all_memslots_rmaps. + * Read shadow_root_allocated before related pointers. Hence, threads + * reading shadow_root_allocated in any lock context are guaranteed to + * see the pointers. Pairs with smp_store_release in + * mmu_first_shadow_root_alloc. */ - return smp_load_acquire(&kvm->arch.memslots_have_rmaps); + return smp_load_acquire(&kvm->arch.shadow_root_allocated); +} + +#ifdef CONFIG_X86_64 +static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } +#else +static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } +#endif + +static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) +{ + return !is_tdp_mmu_enabled(kvm) || kvm_shadow_root_allocated(kvm); } static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2d7e61122af8..323b5057d08f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -58,6 +58,7 @@ extern bool itlb_multihit_kvm_mitigation; int __read_mostly nx_huge_pages = -1; +static uint __read_mostly nx_huge_pages_recovery_period_ms; #ifdef CONFIG_PREEMPT_RT /* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ static uint __read_mostly nx_huge_pages_recovery_ratio = 0; @@ -66,23 +67,26 @@ static uint __read_mostly nx_huge_pages_recovery_ratio = 60; #endif static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); -static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp); static const struct kernel_param_ops nx_huge_pages_ops = { .set = set_nx_huge_pages, .get = param_get_bool, }; -static const struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { - .set = set_nx_huge_pages_recovery_ratio, +static const struct kernel_param_ops nx_huge_pages_recovery_param_ops = { + .set = set_nx_huge_pages_recovery_param, .get = param_get_uint, }; module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); __MODULE_PARM_TYPE(nx_huge_pages, "bool"); -module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_param_ops, &nx_huge_pages_recovery_ratio, 0644); __MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); +module_param_cb(nx_huge_pages_recovery_period_ms, &nx_huge_pages_recovery_param_ops, + &nx_huge_pages_recovery_period_ms, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_period_ms, "uint"); static bool __read_mostly force_flush_and_sync_on_reuse; module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644); @@ -1071,20 +1075,6 @@ static bool rmap_can_add(struct kvm_vcpu *vcpu) return kvm_mmu_memory_cache_nr_free_objects(mc); } -static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) -{ - struct kvm_memory_slot *slot; - struct kvm_mmu_page *sp; - struct kvm_rmap_head *rmap_head; - - sp = sptep_to_sp(spte); - kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); - return pte_list_add(vcpu, spte, rmap_head); -} - - static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_memslots *slots; @@ -1097,9 +1087,9 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); /* - * Unlike rmap_add and rmap_recycle, rmap_remove does not run in the - * context of a vCPU so have to determine which memslots to use based - * on context information in sp->role. + * Unlike rmap_add, rmap_remove does not run in the context of a vCPU + * so we have to determine which memslots to use based on context + * information in sp->role. */ slots = kvm_memslots_for_spte_role(kvm, sp->role); @@ -1639,19 +1629,23 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, #define RMAP_RECYCLE_THRESHOLD 1000 -static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) +static void rmap_add(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, + u64 *spte, gfn_t gfn) { - struct kvm_memory_slot *slot; - struct kvm_rmap_head *rmap_head; struct kvm_mmu_page *sp; + struct kvm_rmap_head *rmap_head; + int rmap_count; sp = sptep_to_sp(spte); - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); + rmap_count = pte_list_add(vcpu, spte, rmap_head); - kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, __pte(0)); - kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(sp->role.level)); + if (rmap_count > RMAP_RECYCLE_THRESHOLD) { + kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, __pte(0)); + kvm_flush_remote_tlbs_with_address( + vcpu->kvm, sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level)); + } } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1795,7 +1789,7 @@ static void mark_unsync(u64 *spte) static int nonpaging_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - return 0; + return -1; } #define KVM_PAGE_ARRAY_NR 16 @@ -1909,12 +1903,14 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - if (vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { + int ret = vcpu->arch.mmu->sync_page(vcpu, sp); + + if (ret < 0) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return false; } - return true; + return !!ret; } static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, @@ -1931,17 +1927,6 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, return true; } -static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu, - struct list_head *invalid_list, - bool remote_flush, bool local_flush) -{ - if (kvm_mmu_remote_flush_or_zap(vcpu->kvm, invalid_list, remote_flush)) - return; - - if (local_flush) - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); -} - #ifdef CONFIG_KVM_MMU_AUDIT #include "mmu_audit.c" #else @@ -2027,8 +2012,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) } while (!sp->unsync_children); } -static void mmu_sync_children(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *parent) +static int mmu_sync_children(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *parent, bool can_yield) { int i; struct kvm_mmu_page *sp; @@ -2044,7 +2029,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, protected |= rmap_write_protect(vcpu, sp->gfn); if (protected) { - kvm_flush_remote_tlbs(vcpu->kvm); + kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, true); flush = false; } @@ -2054,13 +2039,19 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, mmu_pages_clear_parents(&parents); } if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { - kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush); + if (!can_yield) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + return -EINTR; + } + cond_resched_rwlock_write(&vcpu->kvm->mmu_lock); flush = false; } } - kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush); + return 0; } static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) @@ -2143,12 +2134,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, break; WARN_ON(!list_empty(&invalid_list)); - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + kvm_flush_remote_tlbs(vcpu->kvm); } - if (sp->unsync_children) - kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - __clear_sp_write_flooding_count(sp); trace_get_page: @@ -2226,7 +2214,7 @@ static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator, u64 spte) { - if (is_last_spte(spte, iterator->level)) { + if (!is_shadow_present_pte(spte) || is_last_spte(spte, iterator->level)) { iterator->level = 0; return; } @@ -2588,7 +2576,8 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must * be write-protected. */ -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) +int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, + gfn_t gfn, bool can_unsync, bool prefetch) { struct kvm_mmu_page *sp; bool locked = false; @@ -2598,7 +2587,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) * track machinery is used to write-protect upper-level shadow pages, * i.e. this guards the role.level == 4K assertion below! */ - if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(vcpu, slot, gfn, KVM_PAGE_TRACK_WRITE)) return -EPERM; /* @@ -2614,6 +2603,9 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) if (sp->unsync) continue; + if (prefetch) + return -EEXIST; + /* * TDP MMU page faults require an additional spinlock as they * run with mmu_lock held for read, not write, and the unsync @@ -2677,48 +2669,30 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) * (sp->unsync = true) * * The write barrier below ensures that 1.1 happens before 1.2 and thus - * the situation in 2.4 does not arise. The implicit barrier in 2.2 - * pairs with this write barrier. + * the situation in 2.4 does not arise. It pairs with the read barrier + * in is_unsync_root(), placed between 2.1's load of SPTE.W and 2.3. */ smp_wmb(); return 0; } -static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned int pte_access, int level, - gfn_t gfn, kvm_pfn_t pfn, bool speculative, - bool can_unsync, bool host_writable) -{ - u64 spte; - struct kvm_mmu_page *sp; - int ret; - - sp = sptep_to_sp(sptep); - - ret = make_spte(vcpu, pte_access, level, gfn, pfn, *sptep, speculative, - can_unsync, host_writable, sp_ad_disabled(sp), &spte); - - if (spte & PT_WRITABLE_MASK) - kvm_vcpu_mark_page_dirty(vcpu, gfn); - - if (*sptep == spte) - ret |= SET_SPTE_SPURIOUS; - else if (mmu_spte_update(sptep, spte)) - ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; - return ret; -} - -static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned int pte_access, bool write_fault, int level, - gfn_t gfn, kvm_pfn_t pfn, bool speculative, - bool host_writable) +static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, + u64 *sptep, unsigned int pte_access, gfn_t gfn, + kvm_pfn_t pfn, struct kvm_page_fault *fault) { + struct kvm_mmu_page *sp = sptep_to_sp(sptep); + int level = sp->role.level; int was_rmapped = 0; - int rmap_count; - int set_spte_ret; int ret = RET_PF_FIXED; bool flush = false; + bool wrprot; + u64 spte; + + /* Prefetching always gets a writable pfn. */ + bool host_writable = !fault || fault->map_writable; + bool prefetch = !fault || fault->prefetch; + bool write_fault = fault && fault->write; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); @@ -2749,52 +2723,36 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, was_rmapped = 1; } - set_spte_ret = set_spte(vcpu, sptep, pte_access, level, gfn, pfn, - speculative, true, host_writable); - if (set_spte_ret & SET_SPTE_WRITE_PROTECTED_PT) { + wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch, + true, host_writable, &spte); + + if (*sptep == spte) { + ret = RET_PF_SPURIOUS; + } else { + trace_kvm_mmu_set_spte(level, gfn, sptep); + flush |= mmu_spte_update(sptep, spte); + } + + if (wrprot) { if (write_fault) ret = RET_PF_EMULATE; - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH || flush) + if (flush) kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, KVM_PAGES_PER_HPAGE(level)); - /* - * The fault is fully spurious if and only if the new SPTE and old SPTE - * are identical, and emulation is not required. - */ - if ((set_spte_ret & SET_SPTE_SPURIOUS) && ret == RET_PF_FIXED) { - WARN_ON_ONCE(!was_rmapped); - return RET_PF_SPURIOUS; - } - pgprintk("%s: setting spte %llx\n", __func__, *sptep); - trace_kvm_mmu_set_spte(level, gfn, sptep); if (!was_rmapped) { + WARN_ON_ONCE(ret == RET_PF_SPURIOUS); kvm_update_page_stats(vcpu->kvm, level, 1); - rmap_count = rmap_add(vcpu, sptep, gfn); - if (rmap_count > RMAP_RECYCLE_THRESHOLD) - rmap_recycle(vcpu, sptep, gfn); + rmap_add(vcpu, slot, sptep, gfn); } return ret; } -static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, - bool no_dirty_log) -{ - struct kvm_memory_slot *slot; - - slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log); - if (!slot) - return KVM_PFN_ERR_FAULT; - - return gfn_to_pfn_memslot_atomic(slot, gfn); -} - static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *start, u64 *end) @@ -2815,8 +2773,8 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, return -1; for (i = 0; i < ret; i++, gfn++, start++) { - mmu_set_spte(vcpu, start, access, false, sp->role.level, gfn, - page_to_pfn(pages[i]), true, true); + mmu_set_spte(vcpu, slot, start, access, gfn, + page_to_pfn(pages[i]), NULL); put_page(pages[i]); } @@ -2839,11 +2797,13 @@ static void __direct_pte_prefetch(struct kvm_vcpu *vcpu, if (!start) continue; if (direct_pte_prefetch_many(vcpu, sp, start, spte) < 0) - break; + return; start = NULL; } else if (!start) start = spte; } + if (start) + direct_pte_prefetch_many(vcpu, sp, start, spte); } static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) @@ -2921,52 +2881,46 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } -int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, - int max_level, kvm_pfn_t *pfnp, - bool huge_page_disallowed, int *req_level) +void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_memory_slot *slot; - kvm_pfn_t pfn = *pfnp; + struct kvm_memory_slot *slot = fault->slot; kvm_pfn_t mask; - int level; - *req_level = PG_LEVEL_4K; + fault->huge_page_disallowed = fault->exec && fault->nx_huge_page_workaround_enabled; - if (unlikely(max_level == PG_LEVEL_4K)) - return PG_LEVEL_4K; + if (unlikely(fault->max_level == PG_LEVEL_4K)) + return; - if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn)) - return PG_LEVEL_4K; + if (is_error_noslot_pfn(fault->pfn) || kvm_is_reserved_pfn(fault->pfn)) + return; - slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, true); - if (!slot) - return PG_LEVEL_4K; + if (kvm_slot_dirty_track_enabled(slot)) + return; /* * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - *req_level = level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, gfn, pfn, max_level); - if (level == PG_LEVEL_4K || huge_page_disallowed) - return PG_LEVEL_4K; + fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->pfn, + fault->max_level); + if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) + return; /* * mmu_notifier_retry() was successful and mmu_lock is held, so * the pmd can't be split from under us. */ - mask = KVM_PAGES_PER_HPAGE(level) - 1; - VM_BUG_ON((gfn & mask) != (pfn & mask)); - *pfnp = pfn & ~mask; - - return level; + fault->goal_level = fault->req_level; + mask = KVM_PAGES_PER_HPAGE(fault->goal_level) - 1; + VM_BUG_ON((fault->gfn & mask) != (fault->pfn & mask)); + fault->pfn &= ~mask; } -void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level, - kvm_pfn_t *pfnp, int *goal_levelp) +void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level) { - int level = *goal_levelp; - - if (cur_level == level && level > PG_LEVEL_4K && + if (cur_level > PG_LEVEL_4K && + cur_level == fault->goal_level && is_shadow_present_pte(spte) && !is_large_pte(spte)) { /* @@ -2976,42 +2930,33 @@ void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level, * patching back for them into pfn the next 9 bits of * the address. */ - u64 page_mask = KVM_PAGES_PER_HPAGE(level) - - KVM_PAGES_PER_HPAGE(level - 1); - *pfnp |= gfn & page_mask; - (*goal_levelp)--; + u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) - + KVM_PAGES_PER_HPAGE(cur_level - 1); + fault->pfn |= fault->gfn & page_mask; + fault->goal_level--; } } -static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - int map_writable, int max_level, kvm_pfn_t pfn, - bool prefault, bool is_tdp) +static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(); - bool write = error_code & PFERR_WRITE_MASK; - bool exec = error_code & PFERR_FETCH_MASK; - bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled; struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int level, req_level, ret; - gfn_t gfn = gpa >> PAGE_SHIFT; - gfn_t base_gfn = gfn; + int ret; + gfn_t base_gfn = fault->gfn; - level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, - huge_page_disallowed, &req_level); + kvm_mmu_hugepage_adjust(vcpu, fault); - trace_kvm_mmu_spte_requested(gpa, level, pfn); - for_each_shadow_entry(vcpu, gpa, it) { + trace_kvm_mmu_spte_requested(fault); + for_each_shadow_entry(vcpu, fault->addr, it) { /* * We cannot overwrite existing page tables with an NX * large page, as the leaf could be executable. */ - if (nx_huge_page_workaround_enabled) - disallowed_hugepage_adjust(*it.sptep, gfn, it.level, - &pfn, &level); + if (fault->nx_huge_page_workaround_enabled) + disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); - if (it.level == level) + base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == fault->goal_level) break; drop_large_spte(vcpu, it.sptep); @@ -3022,14 +2967,16 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, it.level - 1, true, ACC_ALL); link_shadow_page(vcpu, it.sptep, sp); - if (is_tdp && huge_page_disallowed && - req_level >= it.level) + if (fault->is_tdp && fault->huge_page_disallowed && + fault->req_level >= it.level) account_huge_nx_page(vcpu->kvm, sp); } - ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL, - write, level, base_gfn, pfn, prefault, - map_writable); + if (WARN_ON_ONCE(it.level != fault->goal_level)) + return -EFAULT; + + ret = mmu_set_spte(vcpu, fault->slot, it.sptep, ACC_ALL, + base_gfn, fault->pfn, fault); if (ret == RET_PF_SPURIOUS) return ret; @@ -3061,18 +3008,19 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return -EFAULT; } -static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - kvm_pfn_t pfn, unsigned int access, - int *ret_val) +static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, + unsigned int access, int *ret_val) { /* The pfn is invalid, report the error! */ - if (unlikely(is_error_pfn(pfn))) { - *ret_val = kvm_handle_bad_page(vcpu, gfn, pfn); + if (unlikely(is_error_pfn(fault->pfn))) { + *ret_val = kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn); return true; } - if (unlikely(is_noslot_pfn(pfn))) { - vcpu_cache_mmio_info(vcpu, gva, gfn, + if (unlikely(!fault->slot)) { + gva_t gva = fault->is_tdp ? 0 : fault->addr; + + vcpu_cache_mmio_info(vcpu, gva, fault->gfn, access & shadow_mmio_access_mask); /* * If MMIO caching is disabled, emulate immediately without @@ -3088,18 +3036,17 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, return false; } -static bool page_fault_can_be_fast(u32 error_code) +static bool page_fault_can_be_fast(struct kvm_page_fault *fault) { /* * Do not fix the mmio spte with invalid generation number which * need to be updated by slow page fault path. */ - if (unlikely(error_code & PFERR_RSVD_MASK)) + if (fault->rsvd) return false; /* See if the page fault is due to an NX violation */ - if (unlikely(((error_code & (PFERR_FETCH_MASK | PFERR_PRESENT_MASK)) - == (PFERR_FETCH_MASK | PFERR_PRESENT_MASK)))) + if (unlikely(fault->exec && fault->present)) return false; /* @@ -3116,9 +3063,7 @@ static bool page_fault_can_be_fast(u32 error_code) * accesses to a present page. */ - return shadow_acc_track_mask != 0 || - ((error_code & (PFERR_WRITE_MASK | PFERR_PRESENT_MASK)) - == (PFERR_WRITE_MASK | PFERR_PRESENT_MASK)); + return shadow_acc_track_mask != 0 || (fault->write && fault->present); } /* @@ -3126,13 +3071,9 @@ static bool page_fault_can_be_fast(u32 error_code) * someone else modified the SPTE from its original value. */ static bool -fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, +fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, u64 *sptep, u64 old_spte, u64 new_spte) { - gfn_t gfn; - - WARN_ON(!sp->role.direct); - /* * Theoretically we could also set dirty bit (and flush TLB) here in * order to eliminate unnecessary PML logging. See comments in @@ -3148,24 +3089,18 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (cmpxchg64(sptep, old_spte, new_spte) != old_spte) return false; - if (is_writable_pte(new_spte) && !is_writable_pte(old_spte)) { - /* - * The gfn of direct spte is stable since it is - * calculated by sp->gfn. - */ - gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); - kvm_vcpu_mark_page_dirty(vcpu, gfn); - } + if (is_writable_pte(new_spte) && !is_writable_pte(old_spte)) + mark_page_dirty_in_slot(vcpu->kvm, fault->slot, fault->gfn); return true; } -static bool is_access_allowed(u32 fault_err_code, u64 spte) +static bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) { - if (fault_err_code & PFERR_FETCH_MASK) + if (fault->exec) return is_executable_pte(spte); - if (fault_err_code & PFERR_WRITE_MASK) + if (fault->write) return is_writable_pte(spte); /* Fault was on Read access */ @@ -3190,9 +3125,6 @@ static u64 *fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gpa_t gpa, u64 *spte) for_each_shadow_entry_lockless(vcpu, gpa, iterator, old_spte) { sptep = iterator.sptep; *spte = old_spte; - - if (!is_shadow_present_pte(old_spte)) - break; } return sptep; @@ -3201,7 +3133,7 @@ static u64 *fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gpa_t gpa, u64 *spte) /* * Returns one of RET_PF_INVALID, RET_PF_FIXED or RET_PF_SPURIOUS. */ -static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) +static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp; int ret = RET_PF_INVALID; @@ -3209,7 +3141,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) u64 *sptep = NULL; uint retry_count = 0; - if (!page_fault_can_be_fast(error_code)) + if (!page_fault_can_be_fast(fault)) return ret; walk_shadow_page_lockless_begin(vcpu); @@ -3218,9 +3150,9 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) u64 new_spte; if (is_tdp_mmu(vcpu->arch.mmu)) - sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, gpa, &spte); + sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte); else - sptep = fast_pf_get_last_sptep(vcpu, gpa, &spte); + sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); if (!is_shadow_present_pte(spte)) break; @@ -3239,7 +3171,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) * Need not check the access of upper level table entries since * they are always ACC_ALL. */ - if (is_access_allowed(error_code, spte)) { + if (is_access_allowed(fault, spte)) { ret = RET_PF_SPURIOUS; break; } @@ -3254,7 +3186,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) * be removed in the fast path only if the SPTE was * write-protected for dirty-logging or access tracking. */ - if ((error_code & PFERR_WRITE_MASK) && + if (fault->write && spte_can_locklessly_be_made_writable(spte)) { new_spte |= PT_WRITABLE_MASK; @@ -3275,7 +3207,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) /* Verify that the fault can be handled in the fast path */ if (new_spte == spte || - !is_access_allowed(error_code, new_spte)) + !is_access_allowed(fault, new_spte)) break; /* @@ -3283,7 +3215,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) * since the gfn is not stable for indirect shadow page. See * Documentation/virt/kvm/locking.rst to get more detail. */ - if (fast_pf_fix_direct_spte(vcpu, sp, sptep, spte, new_spte)) { + if (fast_pf_fix_direct_spte(vcpu, fault, sptep, spte, new_spte)) { ret = RET_PF_FIXED; break; } @@ -3296,7 +3228,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code) } while (true); - trace_fast_page_fault(vcpu, gpa, error_code, sptep, spte, ret); + trace_fast_page_fault(vcpu, fault, sptep, spte, ret); walk_shadow_page_lockless_end(vcpu); return ret; @@ -3469,6 +3401,67 @@ out_unlock: return r; } +static int mmu_first_shadow_root_alloc(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; + int r = 0, i; + + /* + * Check if this is the first shadow root being allocated before + * taking the lock. + */ + if (kvm_shadow_root_allocated(kvm)) + return 0; + + mutex_lock(&kvm->slots_arch_lock); + + /* Recheck, under the lock, whether this is the first shadow root. */ + if (kvm_shadow_root_allocated(kvm)) + goto out_unlock; + + /* + * Check if anything actually needs to be allocated, e.g. all metadata + * will be allocated upfront if TDP is disabled. + */ + if (kvm_memslots_have_rmaps(kvm) && + kvm_page_track_write_tracking_enabled(kvm)) + goto out_success; + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(slot, slots) { + /* + * Both of these functions are no-ops if the target is + * already allocated, so unconditionally calling both + * is safe. Intentionally do NOT free allocations on + * failure to avoid having to track which allocations + * were made now versus when the memslot was created. + * The metadata is guaranteed to be freed when the slot + * is freed, and will be kept/used if userspace retries + * KVM_RUN instead of killing the VM. + */ + r = memslot_rmap_alloc(slot, slot->npages); + if (r) + goto out_unlock; + r = kvm_page_track_write_tracking_alloc(slot); + if (r) + goto out_unlock; + } + } + + /* + * Ensure that shadow_root_allocated becomes true strictly after + * all the related pointers are set. + */ +out_success: + smp_store_release(&kvm->arch.shadow_root_allocated, true); + +out_unlock: + mutex_unlock(&kvm->slots_arch_lock); + return r; +} + static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -3499,7 +3492,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } } - r = alloc_all_memslots_rmaps(vcpu->kvm); + r = mmu_first_shadow_root_alloc(vcpu->kvm); if (r) return r; @@ -3650,6 +3643,33 @@ err_pml4: #endif } +static bool is_unsync_root(hpa_t root) +{ + struct kvm_mmu_page *sp; + + if (!VALID_PAGE(root)) + return false; + + /* + * The read barrier orders the CPU's read of SPTE.W during the page table + * walk before the reads of sp->unsync/sp->unsync_children here. + * + * Even if another CPU was marking the SP as unsync-ed simultaneously, + * any guest page table changes are not guaranteed to be visible anyway + * until this VCPU issues a TLB flush strictly after those changes are + * made. We only need to ensure that the other CPU sets these flags + * before any actual changes to the page tables are made. The comments + * in mmu_try_to_unsync_pages() describe what could go wrong if this + * requirement isn't satisfied. + */ + smp_rmb(); + sp = to_shadow_page(root); + if (sp->unsync || sp->unsync_children) + return true; + + return false; +} + void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) { int i; @@ -3667,24 +3687,13 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) hpa_t root = vcpu->arch.mmu->root_hpa; sp = to_shadow_page(root); - /* - * Even if another CPU was marking the SP as unsync-ed - * simultaneously, any guest page table changes are not - * guaranteed to be visible anyway until this VCPU issues a TLB - * flush strictly after those changes are made. We only need to - * ensure that the other CPU sets these flags before any actual - * changes to the page tables are made. The comments in - * mmu_try_to_unsync_pages() describe what could go wrong if - * this requirement isn't satisfied. - */ - if (!smp_load_acquire(&sp->unsync) && - !smp_load_acquire(&sp->unsync_children)) + if (!is_unsync_root(root)) return; write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); write_unlock(&vcpu->kvm->mmu_lock); @@ -3700,7 +3709,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) if (IS_VALID_PAE_ROOT(root)) { root &= PT64_BASE_ADDR_MASK; sp = to_shadow_page(root); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); } } @@ -3708,6 +3717,19 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) write_unlock(&vcpu->kvm->mmu_lock); } +void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu) +{ + unsigned long roots_to_free = 0; + int i; + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (is_unsync_root(vcpu->arch.mmu->prev_roots[i].hpa)) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + + /* sync prev_roots by simply freeing them */ + kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); +} + static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -3760,9 +3782,6 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level spte = mmu_spte_get_lockless(iterator.sptep); sptes[leaf] = spte; - - if (!is_shadow_present_pte(spte)) - break; } return leaf; @@ -3853,20 +3872,19 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) } static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, - u32 error_code, gfn_t gfn) + struct kvm_page_fault *fault) { - if (unlikely(error_code & PFERR_RSVD_MASK)) + if (unlikely(fault->rsvd)) return false; - if (!(error_code & PFERR_PRESENT_MASK) || - !(error_code & PFERR_WRITE_MASK)) + if (!fault->present || !fault->write) return false; /* * guest is writing the page which is write tracked which can * not be fixed by page fault handler. */ - if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE)) + if (kvm_slot_page_track_is_active(vcpu, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE)) return true; return false; @@ -3878,11 +3896,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) u64 spte; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { + for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) clear_sp_write_flooding_count(iterator.sptep); - if (!is_shadow_present_pte(spte)) - break; - } walk_shadow_page_lockless_end(vcpu); } @@ -3900,11 +3915,9 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } -static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva, - bool write, bool *writable, int *r) +static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, int *r) { - struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + struct kvm_memory_slot *slot = fault->slot; bool async; /* @@ -3918,8 +3931,9 @@ static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, if (!kvm_is_visible_memslot(slot)) { /* Don't expose private memslots to L2. */ if (is_guest_mode(vcpu)) { - *pfn = KVM_PFN_NOSLOT; - *writable = false; + fault->slot = NULL; + fault->pfn = KVM_PFN_NOSLOT; + fault->map_writable = false; return false; } /* @@ -3936,46 +3950,46 @@ static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, } async = false; - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, - write, writable, hva); + fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async, + fault->write, &fault->map_writable, + &fault->hva); if (!async) return false; /* *pfn has correct page already */ - if (!prefault && kvm_can_do_async_pf(vcpu)) { - trace_kvm_try_async_get_page(cr2_or_gpa, gfn); - if (kvm_find_async_pf_gfn(vcpu, gfn)) { - trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); + if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) { + trace_kvm_try_async_get_page(fault->addr, fault->gfn); + if (kvm_find_async_pf_gfn(vcpu, fault->gfn)) { + trace_kvm_async_pf_doublefault(fault->addr, fault->gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); goto out_retry; - } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) + } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) goto out_retry; } - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, - write, writable, hva); + fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL, + fault->write, &fault->map_writable, + &fault->hva); + return false; out_retry: *r = RET_PF_RETRY; return true; } -static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - bool prefault, int max_level, bool is_tdp) +static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); - bool write = error_code & PFERR_WRITE_MASK; - bool map_writable; - gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; - kvm_pfn_t pfn; - hva_t hva; int r; - if (page_fault_handle_page_track(vcpu, error_code, gfn)) + fault->gfn = fault->addr >> PAGE_SHIFT; + fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn); + + if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_EMULATE; - r = fast_page_fault(vcpu, gpa, error_code); + r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) return r; @@ -3986,11 +4000,10 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (kvm_faultin_pfn(vcpu, prefault, gfn, gpa, &pfn, &hva, - write, &map_writable, &r)) + if (kvm_faultin_pfn(vcpu, fault, &r)) return r; - if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) + if (handle_abnormal_pfn(vcpu, fault, ACC_ALL, &r)) return r; r = RET_PF_RETRY; @@ -4000,36 +4013,34 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, else write_lock(&vcpu->kvm->mmu_lock); - if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) + if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) goto out_unlock; r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; if (is_tdp_mmu_fault) - r = kvm_tdp_mmu_map(vcpu, gpa, error_code, map_writable, max_level, - pfn, prefault); + r = kvm_tdp_mmu_map(vcpu, fault); else - r = __direct_map(vcpu, gpa, error_code, map_writable, max_level, pfn, - prefault, is_tdp); + r = __direct_map(vcpu, fault); out_unlock: if (is_tdp_mmu_fault) read_unlock(&vcpu->kvm->mmu_lock); else write_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); + kvm_release_pfn_clean(fault->pfn); return r; } -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, - u32 error_code, bool prefault) +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) { - pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code); + pgprintk("%s: gva %lx error %x\n", __func__, fault->addr, fault->error_code); /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ - return direct_page_fault(vcpu, gpa & PAGE_MASK, error_code, prefault, - PG_LEVEL_2M, false); + fault->max_level = PG_LEVEL_2M; + return direct_page_fault(vcpu, fault); } int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, @@ -4065,23 +4076,19 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); -int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - bool prefault) +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - int max_level; - - for (max_level = KVM_MAX_HUGEPAGE_LEVEL; - max_level > PG_LEVEL_4K; - max_level--) { - int page_num = KVM_PAGES_PER_HPAGE(max_level); - gfn_t base = (gpa >> PAGE_SHIFT) & ~(page_num - 1); + while (fault->max_level > PG_LEVEL_4K) { + int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); + gfn_t base = (fault->addr >> PAGE_SHIFT) & ~(page_num - 1); if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) break; + + --fault->max_level; } - return direct_page_fault(vcpu, gpa, error_code, prefault, - max_level, true); + return direct_page_fault(vcpu, fault); } static void nonpaging_init_context(struct kvm_mmu *context) @@ -4202,7 +4209,7 @@ static unsigned long get_cr3(struct kvm_vcpu *vcpu) } static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - unsigned int access, int *nr_present) + unsigned int access) { if (unlikely(is_mmio_spte(*sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { @@ -4210,7 +4217,6 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, return true; } - (*nr_present)++; mark_mmio_spte(vcpu, sptep, gfn, access); return true; } @@ -4593,10 +4599,10 @@ static void update_pkru_bitmask(struct kvm_mmu *mmu) unsigned bit; bool wp; - if (!is_cr4_pke(mmu)) { - mmu->pkru_mask = 0; + mmu->pkru_mask = 0; + + if (!is_cr4_pke(mmu)) return; - } wp = is_cr0_wp(mmu); @@ -5209,7 +5215,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, LIST_HEAD(invalid_list); u64 entry, gentry, *spte; int npte; - bool remote_flush, local_flush; + bool flush = false; /* * If we don't have indirect shadow pages, it means no page is @@ -5218,8 +5224,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) return; - remote_flush = local_flush = false; - pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); /* @@ -5248,18 +5252,17 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (!spte) continue; - local_flush = true; while (npte--) { entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL); if (gentry && sp->role.level != PG_LEVEL_4K) ++vcpu->kvm->stat.mmu_pde_zapped; if (need_remote_flush(entry, *spte)) - remote_flush = true; + flush = true; ++spte; } } - kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush); + kvm_mmu_remote_flush_or_zap(vcpu->kvm, &invalid_list, flush); kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); write_unlock(&vcpu->kvm->mmu_lock); } @@ -5470,8 +5473,8 @@ slot_handle_level(struct kvm *kvm, const struct kvm_memory_slot *memslot, } static __always_inline bool -slot_handle_leaf(struct kvm *kvm, const struct kvm_memory_slot *memslot, - slot_level_handler fn, bool flush_on_yield) +slot_handle_level_4k(struct kvm *kvm, const struct kvm_memory_slot *memslot, + slot_level_handler fn, bool flush_on_yield) { return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); @@ -5691,13 +5694,7 @@ void kvm_mmu_init_vm(struct kvm *kvm) spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - if (!kvm_mmu_init_tdp_mmu(kvm)) - /* - * No smp_load/store wrappers needed here as we are in - * VM init and there cannot be any memslots / other threads - * accessing this struct kvm yet. - */ - kvm->arch.memslots_have_rmaps = true; + kvm_mmu_init_tdp_mmu(kvm); node->track_write = kvm_mmu_pte_write; node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; @@ -5713,55 +5710,58 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) kvm_mmu_uninit_tdp_mmu(kvm); } +static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) +{ + const struct kvm_memory_slot *memslot; + struct kvm_memslots *slots; + bool flush = false; + gfn_t start, end; + int i; + + if (!kvm_memslots_have_rmaps(kvm)) + return flush; + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + start = max(gfn_start, memslot->base_gfn); + end = min(gfn_end, memslot->base_gfn + memslot->npages); + if (start >= end) + continue; + + flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + start, end - 1, true, flush); + } + } + + return flush; +} + /* * Invalidate (zap) SPTEs that cover GFNs from gfn_start and up to gfn_end * (not including it) */ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { - struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; + bool flush; int i; - bool flush = false; write_lock(&kvm->mmu_lock); kvm_inc_notifier_count(kvm, gfn_start, gfn_end); - if (kvm_memslots_have_rmaps(kvm)) { - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { - gfn_t start, end; - - start = max(gfn_start, memslot->base_gfn); - end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) - continue; - - flush = slot_handle_level_range(kvm, - (const struct kvm_memory_slot *) memslot, - kvm_zap_rmapp, PG_LEVEL_4K, - KVM_MAX_HUGEPAGE_LEVEL, start, - end - 1, true, flush); - } - } - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end - gfn_start); - } + flush = __kvm_zap_rmaps(kvm, gfn_start, gfn_end); if (is_tdp_mmu_enabled(kvm)) { for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start, gfn_end, flush); - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end - gfn_start); } if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); + kvm_flush_remote_tlbs_with_address(kvm, gfn_start, + gfn_end - gfn_start); kvm_dec_notifier_count(kvm, gfn_start, gfn_end); @@ -5857,7 +5857,12 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); - flush = slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true); + /* + * Zap only 4k SPTEs since the legacy MMU only supports dirty + * logging at a 4k granularity and never creates collapsible + * 2m SPTEs during dirty logging. + */ + flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true); if (flush) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); write_unlock(&kvm->mmu_lock); @@ -5894,8 +5899,11 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); - flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, - false); + /* + * Clear dirty bits only on 4k SPTEs since the legacy MMU only + * support dirty logging at a 4k granularity. + */ + flush = slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false); write_unlock(&kvm->mmu_lock); } @@ -6173,18 +6181,24 @@ void kvm_mmu_module_exit(void) mmu_audit_disable(); } -static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp) { - unsigned int old_val; + bool was_recovery_enabled, is_recovery_enabled; + uint old_period, new_period; int err; - old_val = nx_huge_pages_recovery_ratio; + was_recovery_enabled = nx_huge_pages_recovery_ratio; + old_period = nx_huge_pages_recovery_period_ms; + err = param_set_uint(val, kp); if (err) return err; - if (READ_ONCE(nx_huge_pages) && - !old_val && nx_huge_pages_recovery_ratio) { + is_recovery_enabled = nx_huge_pages_recovery_ratio; + new_period = nx_huge_pages_recovery_period_ms; + + if (READ_ONCE(nx_huge_pages) && is_recovery_enabled && + (!was_recovery_enabled || old_period > new_period)) { struct kvm *kvm; mutex_lock(&kvm_lock); @@ -6247,8 +6261,17 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) static long get_nx_lpage_recovery_timeout(u64 start_time) { - return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) - ? start_time + 60 * HZ - get_jiffies_64() + uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + uint period = READ_ONCE(nx_huge_pages_recovery_period_ms); + + if (!period && ratio) { + /* Make sure the period is not less than one second. */ + ratio = min(ratio, 3600u); + period = 60 * 60 * 1000 / ratio; + } + + return READ_ONCE(nx_huge_pages) && ratio + ? start_time + msecs_to_jiffies(period) - get_jiffies_64() : MAX_SCHEDULE_TIMEOUT; } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index bf2bdbf333c2..52c6527b1a06 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -118,13 +118,8 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) kvm_x86_ops.cpu_dirty_log_size; } -extern int nx_huge_pages; -static inline bool is_nx_huge_page_enabled(void) -{ - return READ_ONCE(nx_huge_pages); -} - -int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync); +int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, + gfn_t gfn, bool can_unsync, bool prefetch); void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); @@ -155,19 +150,11 @@ enum { RET_PF_SPURIOUS, }; -/* Bits which may be returned by set_spte() */ -#define SET_SPTE_WRITE_PROTECTED_PT BIT(0) -#define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) -#define SET_SPTE_SPURIOUS BIT(2) - int kvm_mmu_max_mapping_level(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t pfn, int max_level); -int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, - int max_level, kvm_pfn_t *pfnp, - bool huge_page_disallowed, int *req_level); -void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level, - kvm_pfn_t *pfnp, int *goal_levelp); +void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); +void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level); void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index 2924a4081a19..b8151bbca36a 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -252,9 +252,9 @@ TRACE_EVENT( TRACE_EVENT( fast_page_fault, - TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code, + TP_PROTO(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, u64 *sptep, u64 old_spte, int ret), - TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, ret), + TP_ARGS(vcpu, fault, sptep, old_spte, ret), TP_STRUCT__entry( __field(int, vcpu_id) @@ -268,8 +268,8 @@ TRACE_EVENT( TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->cr2_or_gpa = cr2_or_gpa; - __entry->error_code = error_code; + __entry->cr2_or_gpa = fault->addr; + __entry->error_code = fault->error_code; __entry->sptep = sptep; __entry->old_spte = old_spte; __entry->new_spte = *sptep; @@ -367,8 +367,8 @@ TRACE_EVENT( TRACE_EVENT( kvm_mmu_spte_requested, - TP_PROTO(gpa_t addr, int level, kvm_pfn_t pfn), - TP_ARGS(addr, level, pfn), + TP_PROTO(struct kvm_page_fault *fault), + TP_ARGS(fault), TP_STRUCT__entry( __field(u64, gfn) @@ -377,9 +377,9 @@ TRACE_EVENT( ), TP_fast_assign( - __entry->gfn = addr >> PAGE_SHIFT; - __entry->pfn = pfn | (__entry->gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); - __entry->level = level; + __entry->gfn = fault->gfn; + __entry->pfn = fault->pfn | (fault->gfn & (KVM_PAGES_PER_HPAGE(fault->goal_level) - 1)); + __entry->level = fault->goal_level; ), TP_printk("gfn %llx pfn %llx level %d", diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 269f11f92fd0..cc4eb5b7fb76 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -19,6 +19,12 @@ #include "mmu.h" #include "mmu_internal.h" +bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_KVM_EXTERNAL_WRITE_TRACKING) || + !tdp_enabled || kvm_shadow_root_allocated(kvm); +} + void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { int i; @@ -29,12 +35,17 @@ void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) } } -int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, +int kvm_page_track_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, unsigned long npages) { - int i; + int i; for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { + if (i == KVM_PAGE_TRACK_WRITE && + !kvm_page_track_write_tracking_enabled(kvm)) + continue; + slot->arch.gfn_track[i] = kvcalloc(npages, sizeof(*slot->arch.gfn_track[i]), GFP_KERNEL_ACCOUNT); @@ -57,6 +68,21 @@ static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode) return true; } +int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot) +{ + unsigned short *gfn_track; + + if (slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE]) + return 0; + + gfn_track = kvcalloc(slot->npages, sizeof(*gfn_track), GFP_KERNEL_ACCOUNT); + if (gfn_track == NULL) + return -ENOMEM; + + slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE] = gfn_track; + return 0; +} + static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, enum kvm_page_track_mode mode, short count) { @@ -92,6 +118,10 @@ void kvm_slot_page_track_add_page(struct kvm *kvm, if (WARN_ON(!page_track_mode_is_valid(mode))) return; + if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && + !kvm_page_track_write_tracking_enabled(kvm))) + return; + update_gfn_track(slot, gfn, mode, 1); /* @@ -126,6 +156,10 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm, if (WARN_ON(!page_track_mode_is_valid(mode))) return; + if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE && + !kvm_page_track_write_tracking_enabled(kvm))) + return; + update_gfn_track(slot, gfn, mode, -1); /* @@ -139,19 +173,22 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); /* * check if the corresponding access on the specified guest page is tracked. */ -bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, - enum kvm_page_track_mode mode) +bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode) { - struct kvm_memory_slot *slot; int index; if (WARN_ON(!page_track_mode_is_valid(mode))) return false; - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); if (!slot) return false; + if (mode == KVM_PAGE_TRACK_WRITE && + !kvm_page_track_write_tracking_enabled(vcpu->kvm)) + return false; + index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); return !!READ_ONCE(slot->arch.gfn_track[mode][index]); } @@ -164,13 +201,13 @@ void kvm_page_track_cleanup(struct kvm *kvm) cleanup_srcu_struct(&head->track_srcu); } -void kvm_page_track_init(struct kvm *kvm) +int kvm_page_track_init(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; head = &kvm->arch.track_notifier_head; - init_srcu_struct(&head->track_srcu); INIT_HLIST_HEAD(&head->track_notifier_list); + return init_srcu_struct(&head->track_srcu); } /* diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 7d03e9b7ccfa..f87d36898c44 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -561,6 +561,7 @@ static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, pt_element_t gpte, bool no_dirty_log) { + struct kvm_memory_slot *slot; unsigned pte_access; gfn_t gfn; kvm_pfn_t pfn; @@ -573,30 +574,21 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, gfn = gpte_to_gfn(gpte); pte_access = sp->role.access & FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); - pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn, + + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log && (pte_access & ACC_WRITE_MASK)); - if (is_error_pfn(pfn)) + if (!slot) return false; - /* - * we call mmu_set_spte() with host_writable = true because - * pte_prefetch_gfn_to_pfn always gets a writable pfn. - */ - mmu_set_spte(vcpu, spte, pte_access, false, PG_LEVEL_4K, gfn, pfn, - true, true); + pfn = gfn_to_pfn_memslot_atomic(slot, gfn); + if (is_error_pfn(pfn)) + return false; + mmu_set_spte(vcpu, slot, spte, pte_access, gfn, pfn, NULL); kvm_release_pfn_clean(pfn); return true; } -static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte) -{ - pt_element_t gpte = *(const pt_element_t *)pte; - - FNAME(prefetch_gpte)(vcpu, sp, spte, gpte, false); -} - static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu, struct guest_walker *gw, int level) { @@ -663,21 +655,16 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If the guest tries to write a write-protected page, we need to * emulate this operation, return 1 to indicate this case. */ -static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, - struct guest_walker *gw, u32 error_code, - int max_level, kvm_pfn_t pfn, bool map_writable, - bool prefault) +static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, + struct guest_walker *gw) { - bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(); - bool write_fault = error_code & PFERR_WRITE_MASK; - bool exec = error_code & PFERR_FETCH_MASK; - bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled; struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned int direct_access, access; - int top_level, level, req_level, ret; - gfn_t base_gfn = gw->gfn; + int top_level, ret; + gfn_t base_gfn = fault->gfn; + WARN_ON_ONCE(gw->gfn != base_gfn); direct_access = gw->pte_access; top_level = vcpu->arch.mmu->root_level; @@ -695,7 +682,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) goto out_gpte_changed; - for (shadow_walk_init(&it, vcpu, addr); + for (shadow_walk_init(&it, vcpu, fault->addr); shadow_walk_okay(&it) && it.level > gw->level; shadow_walk_next(&it)) { gfn_t table_gfn; @@ -707,8 +694,27 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; access = gw->pt_access[it.level - 2]; - sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, - false, access); + sp = kvm_mmu_get_page(vcpu, table_gfn, fault->addr, + it.level-1, false, access); + /* + * We must synchronize the pagetable before linking it + * because the guest doesn't need to flush tlb when + * the gpte is changed from non-present to present. + * Otherwise, the guest may use the wrong mapping. + * + * For PG_LEVEL_4K, kvm_mmu_get_page() has already + * synchronized it transiently via kvm_sync_page(). + * + * For higher level pagetable, we synchronize it via + * the slower mmu_sync_children(). If it needs to + * break, some progress has been made; return + * RET_PF_RETRY and retry on the next #PF. + * KVM_REQ_MMU_SYNC is not necessary but it + * expedites the process. + */ + if (sp->unsync_children && + mmu_sync_children(vcpu, sp, false)) + return RET_PF_RETRY; } /* @@ -722,10 +728,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, link_shadow_page(vcpu, it.sptep, sp); } - level = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn, - huge_page_disallowed, &req_level); + kvm_mmu_hugepage_adjust(vcpu, fault); - trace_kvm_mmu_spte_requested(addr, gw->level, pfn); + trace_kvm_mmu_spte_requested(fault); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); @@ -734,12 +739,11 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, * We cannot overwrite existing page tables with an NX * large page, as the leaf could be executable. */ - if (nx_huge_page_workaround_enabled) - disallowed_hugepage_adjust(*it.sptep, gw->gfn, it.level, - &pfn, &level); + if (fault->nx_huge_page_workaround_enabled) + disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); - if (it.level == level) + base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == fault->goal_level) break; validate_direct_spte(vcpu, it.sptep, direct_access); @@ -747,16 +751,20 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, drop_large_spte(vcpu, it.sptep); if (!is_shadow_present_pte(*it.sptep)) { - sp = kvm_mmu_get_page(vcpu, base_gfn, addr, + sp = kvm_mmu_get_page(vcpu, base_gfn, fault->addr, it.level - 1, true, direct_access); link_shadow_page(vcpu, it.sptep, sp); - if (huge_page_disallowed && req_level >= it.level) + if (fault->huge_page_disallowed && + fault->req_level >= it.level) account_huge_nx_page(vcpu->kvm, sp); } } - ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, - it.level, base_gfn, pfn, prefault, map_writable); + if (WARN_ON_ONCE(it.level != fault->goal_level)) + return -EFAULT; + + ret = mmu_set_spte(vcpu, fault->slot, it.sptep, gw->pte_access, + base_gfn, fault->pfn, fault); if (ret == RET_PF_SPURIOUS) return ret; @@ -822,45 +830,40 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, * Returns: 1 if we need to emulate the instruction, 0 otherwise, or * a negative value on error. */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, - bool prefault) +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - bool write_fault = error_code & PFERR_WRITE_MASK; - bool user_fault = error_code & PFERR_USER_MASK; struct guest_walker walker; int r; - kvm_pfn_t pfn; - hva_t hva; unsigned long mmu_seq; - bool map_writable, is_self_change_mapping; - int max_level; + bool is_self_change_mapping; - pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); + pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); + WARN_ON_ONCE(fault->is_tdp); /* + * Look up the guest pte for the faulting address. * If PFEC.RSVD is set, this is a shadow page fault. * The bit needs to be cleared before walking guest page tables. */ - error_code &= ~PFERR_RSVD_MASK; - - /* - * Look up the guest pte for the faulting address. - */ - r = FNAME(walk_addr)(&walker, vcpu, addr, error_code); + r = FNAME(walk_addr)(&walker, vcpu, fault->addr, + fault->error_code & ~PFERR_RSVD_MASK); /* * The page is not mapped by the guest. Let the guest handle it. */ if (!r) { pgprintk("%s: guest page fault\n", __func__); - if (!prefault) + if (!fault->prefetch) kvm_inject_emulated_page_fault(vcpu, &walker.fault); return RET_PF_RETRY; } - if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) { - shadow_page_table_clear_flood(vcpu, addr); + fault->gfn = walker.gfn; + fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn); + + if (page_fault_handle_page_track(vcpu, fault)) { + shadow_page_table_clear_flood(vcpu, fault->addr); return RET_PF_EMULATE; } @@ -871,29 +874,28 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, vcpu->arch.write_fault_to_shadow_pgtable = false; is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, - &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); + &walker, fault->user, &vcpu->arch.write_fault_to_shadow_pgtable); if (is_self_change_mapping) - max_level = PG_LEVEL_4K; + fault->max_level = PG_LEVEL_4K; else - max_level = walker.level; + fault->max_level = walker.level; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (kvm_faultin_pfn(vcpu, prefault, walker.gfn, addr, &pfn, &hva, - write_fault, &map_writable, &r)) + if (kvm_faultin_pfn(vcpu, fault, &r)) return r; - if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r)) + if (handle_abnormal_pfn(vcpu, fault, walker.pte_access, &r)) return r; /* * Do not change pte_access if the pfn is a mmio page, otherwise * we will cache the incorrect access into mmio spte. */ - if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) && - !is_cr0_wp(vcpu->arch.mmu) && !user_fault && !is_noslot_pfn(pfn)) { + if (fault->write && !(walker.pte_access & ACC_WRITE_MASK) && + !is_cr0_wp(vcpu->arch.mmu) && !fault->user && fault->slot) { walker.pte_access |= ACC_WRITE_MASK; walker.pte_access &= ~ACC_USER_MASK; @@ -909,20 +911,19 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) + if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; - r = FNAME(fetch)(vcpu, addr, &walker, error_code, max_level, pfn, - map_writable, prefault); + r = FNAME(fetch)(vcpu, fault, &walker); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: write_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); + kvm_release_pfn_clean(fault->pfn); return r; } @@ -988,10 +989,10 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) sizeof(pt_element_t))) break; - FNAME(update_pte)(vcpu, sp, sptep, &gpte); + FNAME(prefetch_gpte)(vcpu, sp, sptep, gpte, false); } - if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) + if (!sp->unsync_children) break; } write_unlock(&vcpu->kvm->mmu_lock); @@ -1048,21 +1049,18 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, * - The spte has a reference to the struct page, so the pfn for a given gfn * can't change unless all sptes pointing to it are nuked first. * - * Note: - * We should flush all tlbs if spte is dropped even though guest is - * responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page - * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't - * used by guest then tlbs are not flushed, so guest is allowed to access the - * freed pages. - * And we increase kvm->tlbs_dirty to delay tlbs flush in this case. + * Returns + * < 0: the sp should be zapped + * 0: the sp is synced and no tlb flushing is required + * > 0: the sp is synced and tlb flushing is required */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { union kvm_mmu_page_role mmu_role = vcpu->arch.mmu->mmu_role.base; - int i, nr_present = 0; + int i; bool host_writable; gpa_t first_pte_gpa; - int set_spte_ret = 0; + bool flush = false; /* * Ignore various flags when verifying that it's safe to sync a shadow @@ -1087,11 +1085,13 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) */ if (WARN_ON_ONCE(sp->role.direct || (sp->role.word ^ mmu_role.word) & ~sync_role_ign.word)) - return 0; + return -1; first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { + u64 *sptep, spte; + struct kvm_memory_slot *slot; unsigned pte_access; pt_element_t gpte; gpa_t pte_gpa; @@ -1104,16 +1104,10 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, sizeof(pt_element_t))) - return 0; + return -1; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - /* - * Update spte before increasing tlbs_dirty to make - * sure no tlb flush is lost after spte is zapped; see - * the comments in kvm_flush_remote_tlbs(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + flush = true; continue; } @@ -1122,35 +1116,27 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_access &= FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); - if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access, - &nr_present)) + if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access)) continue; if (gfn != sp->gfns[i]) { drop_spte(vcpu->kvm, &sp->spt[i]); - /* - * The same as above where we are doing - * prefetch_invalid_gpte(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + flush = true; continue; } - nr_present++; - - host_writable = sp->spt[i] & shadow_host_writable_mask; + sptep = &sp->spt[i]; + spte = *sptep; + host_writable = spte & shadow_host_writable_mask; + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + make_spte(vcpu, sp, slot, pte_access, gfn, + spte_to_pfn(spte), spte, true, false, + host_writable, &spte); - set_spte_ret |= set_spte(vcpu, &sp->spt[i], - pte_access, PG_LEVEL_4K, - gfn, spte_to_pfn(sp->spt[i]), - true, false, host_writable); + flush |= mmu_spte_update(sptep, spte); } - if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH) - kvm_flush_remote_tlbs(vcpu->kvm); - - return nr_present; + return flush; } #undef pt_element_t diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 3e97cdb13eb7..0c76c45fdb68 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -89,15 +89,17 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) E820_TYPE_RAM); } -int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, - gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool speculative, - bool can_unsync, bool host_writable, bool ad_disabled, - u64 *new_spte) +bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct kvm_memory_slot *slot, + unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, + u64 old_spte, bool prefetch, bool can_unsync, + bool host_writable, u64 *new_spte) { + int level = sp->role.level; u64 spte = SPTE_MMU_PRESENT_MASK; - int ret = 0; + bool wrprot = false; - if (ad_disabled) + if (sp->role.ad_disabled) spte |= SPTE_TDP_AD_DISABLED_MASK; else if (kvm_vcpu_ad_need_write_protect(vcpu)) spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; @@ -109,7 +111,7 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, * read access. See FNAME(gpte_access) in paging_tmpl.h. */ spte |= shadow_present_mask; - if (!speculative) + if (!prefetch) spte |= spte_shadow_accessed_mask(spte); if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) && @@ -150,7 +152,7 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, * is responsibility of kvm_mmu_get_page / kvm_mmu_sync_roots. * Same reasoning can be applied to dirty page accounting. */ - if (!can_unsync && is_writable_pte(old_spte)) + if (is_writable_pte(old_spte)) goto out; /* @@ -159,10 +161,10 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, * e.g. it's write-tracked (upper-level SPs) or has one or more * shadow pages and unsync'ing pages is not allowed. */ - if (mmu_try_to_unsync_pages(vcpu, gfn, can_unsync)) { + if (mmu_try_to_unsync_pages(vcpu, slot, gfn, can_unsync, prefetch)) { pgprintk("%s: found shadow page for %llx, marking ro\n", __func__, gfn); - ret |= SET_SPTE_WRITE_PROTECTED_PT; + wrprot = true; pte_access &= ~ACC_WRITE_MASK; spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask); } @@ -171,16 +173,22 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, if (pte_access & ACC_WRITE_MASK) spte |= spte_shadow_dirty_mask(spte); - if (speculative) +out: + if (prefetch) spte = mark_spte_for_access_track(spte); -out: WARN_ONCE(is_rsvd_spte(&vcpu->arch.mmu->shadow_zero_check, spte, level), "spte = 0x%llx, level = %d, rsvd bits = 0x%llx", spte, level, get_rsvd_bits(&vcpu->arch.mmu->shadow_zero_check, spte, level)); + if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) { + /* Enforced by kvm_mmu_hugepage_adjust. */ + WARN_ON(level > PG_LEVEL_4K); + mark_page_dirty_in_slot(vcpu->kvm, slot, gfn); + } + *new_spte = spte; - return ret; + return wrprot; } u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled) diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index eb7b227fc6cf..cc432f9a966b 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -310,12 +310,7 @@ static inline bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, u64 spte, int level) { - /* - * Use a bitwise-OR instead of a logical-OR to aggregate the reserved - * bits and EPT's invalid memtype/XWR checks to avoid an extra Jcc - * (this is extremely unlikely to be short-circuited as true). - */ - return __is_bad_mt_xwr(rsvd_check, spte) | + return __is_bad_mt_xwr(rsvd_check, spte) || __is_rsvd_bits_set(rsvd_check, spte, level); } @@ -334,15 +329,11 @@ static inline u64 get_mmio_spte_generation(u64 spte) return gen; } -/* Bits which may be returned by set_spte() */ -#define SET_SPTE_WRITE_PROTECTED_PT BIT(0) -#define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) -#define SET_SPTE_SPURIOUS BIT(2) - -int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level, - gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool speculative, - bool can_unsync, bool host_writable, bool ad_disabled, - u64 *new_spte); +bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct kvm_memory_slot *slot, + unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, + u64 old_spte, bool prefetch, bool can_unsync, + bool host_writable, u64 *new_spte); u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled); u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access); u64 mark_spte_for_access_track(u64 spte); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 64ccfc1fa553..7c5dd83e52de 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -167,6 +167,7 @@ static union kvm_mmu_page_role page_role_for_level(struct kvm_vcpu *vcpu, role.direct = true; role.gpte_is_8_bytes = true; role.access = ACC_ALL; + role.ad_disabled = !shadow_accessed_mask; return role; } @@ -489,8 +490,8 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, } /* - * tdp_mmu_set_spte_atomic_no_dirty_log - Set a TDP MMU SPTE atomically - * and handle the associated bookkeeping, but do not mark the page dirty + * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically + * and handle the associated bookkeeping. Do not mark the page dirty * in KVM's dirty bitmaps. * * @kvm: kvm instance @@ -499,9 +500,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * Returns: true if the SPTE was set, false if it was not. If false is returned, * this function will have no side-effects. */ -static inline bool tdp_mmu_set_spte_atomic_no_dirty_log(struct kvm *kvm, - struct tdp_iter *iter, - u64 new_spte) +static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter, + u64 new_spte) { lockdep_assert_held_read(&kvm->mmu_lock); @@ -527,43 +528,6 @@ static inline bool tdp_mmu_set_spte_atomic_no_dirty_log(struct kvm *kvm, return true; } -/* - * tdp_mmu_map_set_spte_atomic - Set a leaf TDP MMU SPTE atomically to resolve a - * TDP page fault. - * - * @vcpu: The vcpu instance that took the TDP page fault. - * @iter: a tdp_iter instance currently on the SPTE that should be set - * @new_spte: The value the SPTE should be set to - * - * Returns: true if the SPTE was set, false if it was not. If false is returned, - * this function will have no side-effects. - */ -static inline bool tdp_mmu_map_set_spte_atomic(struct kvm_vcpu *vcpu, - struct tdp_iter *iter, - u64 new_spte) -{ - struct kvm *kvm = vcpu->kvm; - - if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, iter, new_spte)) - return false; - - /* - * Use kvm_vcpu_gfn_to_memslot() instead of going through - * handle_changed_spte_dirty_log() to leverage vcpu->last_used_slot. - */ - if (is_writable_pte(new_spte)) { - struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, iter->gfn); - - if (slot && kvm_slot_dirty_track_enabled(slot)) { - /* Enforced by kvm_mmu_hugepage_adjust. */ - WARN_ON_ONCE(iter->level > PG_LEVEL_4K); - mark_page_dirty_in_slot(kvm, slot, iter->gfn); - } - } - - return true; -} - static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm, struct tdp_iter *iter) { @@ -573,7 +537,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm, * immediately installing a present entry in its place * before the TLBs are flushed. */ - if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, iter, REMOVED_SPTE)) + if (!tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE)) return false; kvm_flush_remote_tlbs_with_address(kvm, iter->gfn, @@ -929,26 +893,26 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) * Installs a last-level SPTE to handle a TDP page fault. * (NPT/EPT violation/misconfiguration) */ -static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, - int map_writable, - struct tdp_iter *iter, - kvm_pfn_t pfn, bool prefault) +static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, + struct tdp_iter *iter) { + struct kvm_mmu_page *sp = sptep_to_sp(iter->sptep); u64 new_spte; int ret = RET_PF_FIXED; - int make_spte_ret = 0; + bool wrprot = false; - if (unlikely(is_noslot_pfn(pfn))) + WARN_ON(sp->role.level != fault->goal_level); + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else - make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn, - pfn, iter->old_spte, prefault, true, - map_writable, !shadow_accessed_mask, - &new_spte); + wrprot = make_spte(vcpu, sp, fault->slot, ACC_ALL, iter->gfn, + fault->pfn, iter->old_spte, fault->prefetch, true, + fault->map_writable, &new_spte); if (new_spte == iter->old_spte) ret = RET_PF_SPURIOUS; - else if (!tdp_mmu_map_set_spte_atomic(vcpu, iter, new_spte)) + else if (!tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte)) return RET_PF_RETRY; /* @@ -956,10 +920,9 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, * protected, emulation is needed. If the emulation was skipped, * the vCPU would have the same fault again. */ - if (make_spte_ret & SET_SPTE_WRITE_PROTECTED_PT) { - if (write) + if (wrprot) { + if (fault->write) ret = RET_PF_EMULATE; - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */ @@ -986,37 +949,26 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, * Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing * page tables and SPTEs to translate the faulting guest physical address. */ -int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - int map_writable, int max_level, kvm_pfn_t pfn, - bool prefault) +int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(); - bool write = error_code & PFERR_WRITE_MASK; - bool exec = error_code & PFERR_FETCH_MASK; - bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled; struct kvm_mmu *mmu = vcpu->arch.mmu; struct tdp_iter iter; struct kvm_mmu_page *sp; u64 *child_pt; u64 new_spte; int ret; - gfn_t gfn = gpa >> PAGE_SHIFT; - int level; - int req_level; - level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, - huge_page_disallowed, &req_level); + kvm_mmu_hugepage_adjust(vcpu, fault); - trace_kvm_mmu_spte_requested(gpa, level, pfn); + trace_kvm_mmu_spte_requested(fault); rcu_read_lock(); - tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { - if (nx_huge_page_workaround_enabled) - disallowed_hugepage_adjust(iter.old_spte, gfn, - iter.level, &pfn, &level); + tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) { + if (fault->nx_huge_page_workaround_enabled) + disallowed_hugepage_adjust(fault, iter.old_spte, iter.level); - if (iter.level == level) + if (iter.level == fault->goal_level) break; /* @@ -1052,10 +1004,10 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, new_spte = make_nonleaf_spte(child_pt, !shadow_accessed_mask); - if (tdp_mmu_set_spte_atomic_no_dirty_log(vcpu->kvm, &iter, new_spte)) { + if (tdp_mmu_set_spte_atomic(vcpu->kvm, &iter, new_spte)) { tdp_mmu_link_page(vcpu->kvm, sp, - huge_page_disallowed && - req_level >= iter.level); + fault->huge_page_disallowed && + fault->req_level >= iter.level); trace_kvm_mmu_get_page(sp, true); } else { @@ -1065,13 +1017,12 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, } } - if (iter.level != level) { + if (iter.level != fault->goal_level) { rcu_read_unlock(); return RET_PF_RETRY; } - ret = tdp_mmu_map_handle_target_level(vcpu, write, map_writable, &iter, - pfn, prefault); + ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter); rcu_read_unlock(); return ret; @@ -1241,8 +1192,7 @@ retry: new_spte = iter.old_spte & ~PT_WRITABLE_MASK; - if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, &iter, - new_spte)) { + if (!tdp_mmu_set_spte_atomic(kvm, &iter, new_spte)) { /* * The iter must explicitly re-read the SPTE because * the atomic cmpxchg failed. @@ -1310,8 +1260,7 @@ retry: continue; } - if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, &iter, - new_spte)) { + if (!tdp_mmu_set_spte_atomic(kvm, &iter, new_spte)) { /* * The iter must explicitly re-read the SPTE because * the atomic cmpxchg failed. diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 358f447d4012..476b133544dd 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -48,9 +48,7 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm); -int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - int map_writable, int max_level, kvm_pfn_t pfn, - bool prefault); +int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush); @@ -92,7 +90,6 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, #ifdef CONFIG_X86_64 bool kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } static inline bool is_tdp_mmu(struct kvm_mmu *mmu) @@ -114,7 +111,6 @@ static inline bool is_tdp_mmu(struct kvm_mmu *mmu) #else static inline bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return false; } static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; } #endif diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 2545d0c61985..f8b7bc04b3e7 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -238,6 +238,18 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size) kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1); } +static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) +{ + /* Nested FLUSHBYASID is not supported yet. */ + switch(tlb_ctl) { + case TLB_CONTROL_DO_NOTHING: + case TLB_CONTROL_FLUSH_ALL_ASID: + return true; + default: + return false; + } +} + static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, struct vmcb_control_area *control) { @@ -257,6 +269,9 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu, IOPM_SIZE))) return false; + if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) + return false; + return true; } @@ -538,22 +553,27 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) if (nested_npt_enabled(svm)) nested_svm_init_mmu_context(vcpu); - svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset = - vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + vcpu->arch.l1_tsc_offset, + svm->nested.ctl.tsc_offset, + svm->tsc_ratio_msr); + + svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset; + + if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { + WARN_ON(!svm->tsc_scaling_enabled); + nested_svm_update_tsc_ratio_msr(vcpu); + } svm->vmcb->control.int_ctl = (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits); - svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; svm->vmcb->control.int_state = svm->nested.ctl.int_state; svm->vmcb->control.event_inj = svm->nested.ctl.event_inj; svm->vmcb->control.event_inj_err = svm->nested.ctl.event_inj_err; - svm->vmcb->control.pause_filter_count = svm->nested.ctl.pause_filter_count; - svm->vmcb->control.pause_filter_thresh = svm->nested.ctl.pause_filter_thresh; - nested_svm_transition_tlb_flush(vcpu); /* Enter Guest-Mode */ @@ -579,7 +599,7 @@ static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, - struct vmcb *vmcb12) + struct vmcb *vmcb12, bool from_vmrun) { struct vcpu_svm *svm = to_svm(vcpu); int ret; @@ -609,13 +629,16 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, - nested_npt_enabled(svm), true); + nested_npt_enabled(svm), from_vmrun); if (ret) return ret; if (!npt_enabled) vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested; + if (!from_vmrun) + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + svm_set_gif(svm, true); return 0; @@ -681,7 +704,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) svm->nested.nested_run_pending = 1; - if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12)) + if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true)) goto out_exit_err; if (nested_svm_vmrun_msrpm(svm)) @@ -808,11 +831,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->control.event_inj = svm->nested.ctl.event_inj; vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; - vmcb12->control.pause_filter_count = - svm->vmcb->control.pause_filter_count; - vmcb12->control.pause_filter_thresh = - svm->vmcb->control.pause_filter_thresh; - nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); svm_switch_vmcb(svm, &svm->vmcb01); @@ -830,6 +848,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } + if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { + WARN_ON(!svm->tsc_scaling_enabled); + vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; + svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); + } + svm->nested.ctl.nested_cr3 = 0; /* @@ -1217,6 +1241,16 @@ int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_CONTINUE; } +void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->arch.tsc_scaling_ratio = + kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio, + svm->tsc_ratio_msr); + svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio); +} + static int svm_get_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, u32 user_data_size) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 75e0b21ad07c..1964b9a174be 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -17,10 +17,10 @@ #include <linux/misc_cgroup.h> #include <linux/processor.h> #include <linux/trace_events.h> -#include <asm/fpu/internal.h> #include <asm/pkru.h> #include <asm/trapnr.h> +#include <asm/fpu/xcr.h> #include "x86.h" #include "svm.h" @@ -595,43 +595,55 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) return 0; } -static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) +static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, + int *error) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct sev_data_launch_update_vmsa vmsa; + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + /* Perform some pre-encryption checks against the VMSA */ + ret = sev_es_sync_vmsa(svm); + if (ret) + return ret; + + /* + * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of + * the VMSA memory content (i.e it will write the same memory region + * with the guest's key), so invalidate it first. + */ + clflush_cache_range(svm->vmsa, PAGE_SIZE); + + vmsa.reserved = 0; + vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; + vmsa.address = __sme_pa(svm->vmsa); + vmsa.len = PAGE_SIZE; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); + if (ret) + return ret; + + vcpu->arch.guest_state_protected = true; + return 0; +} + +static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ struct kvm_vcpu *vcpu; int i, ret; if (!sev_es_guest(kvm)) return -ENOTTY; - vmsa.reserved = 0; - kvm_for_each_vcpu(i, vcpu, kvm) { - struct vcpu_svm *svm = to_svm(vcpu); - - /* Perform some pre-encryption checks against the VMSA */ - ret = sev_es_sync_vmsa(svm); + ret = mutex_lock_killable(&vcpu->mutex); if (ret) return ret; - /* - * The LAUNCH_UPDATE_VMSA command will perform in-place - * encryption of the VMSA memory content (i.e it will write - * the same memory region with the guest's key), so invalidate - * it first. - */ - clflush_cache_range(svm->vmsa, PAGE_SIZE); + ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error); - vmsa.handle = sev->handle; - vmsa.address = __sme_pa(svm->vmsa); - vmsa.len = PAGE_SIZE; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, - &argp->error); + mutex_unlock(&vcpu->mutex); if (ret) return ret; - - svm->vcpu.arch.guest_state_protected = true; } return 0; @@ -1397,8 +1409,10 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start.handle, error); - if (ret) + if (ret) { + sev_decommission(start.handle); goto e_free_session; + } params.handle = start.handle; if (copy_to_user((void __user *)(uintptr_t)argp->data, @@ -1464,12 +1478,19 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, - PAGE_SIZE, &n, 0); + PAGE_SIZE, &n, 1); if (IS_ERR(guest_page)) { ret = PTR_ERR(guest_page); goto e_free_trans; } + /* + * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP + * encrypts the written data with the guest's key, and the cache may + * contain dirty, unencrypted data. + */ + sev_clflush_pages(guest_page, n); + /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; data.guest_address |= sev_me_mask; @@ -1501,6 +1522,20 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); } +static bool cmd_allowed_from_miror(u32 cmd_id) +{ + /* + * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES + * active mirror VMs. Also allow the debugging and status commands. + */ + if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA || + cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT || + cmd_id == KVM_SEV_DBG_ENCRYPT) + return true; + + return false; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1517,8 +1552,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) mutex_lock(&kvm->lock); - /* enc_context_owner handles all memory enc operations */ - if (is_mirroring_enc_context(kvm)) { + /* Only the enc_context_owner handles some memory enc operations. */ + if (is_mirroring_enc_context(kvm) && + !cmd_allowed_from_miror(sev_cmd.id)) { r = -EINVAL; goto out; } @@ -1715,8 +1751,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info *mirror_sev; - unsigned int asid; + struct kvm_sev_info source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); @@ -1739,7 +1774,8 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) goto e_source_unlock; } - asid = to_kvm_svm(source_kvm)->sev_info.asid; + memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, + sizeof(source_sev)); /* * The mirror kvm holds an enc_context_owner ref so its asid can't @@ -1759,8 +1795,16 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; - mirror_sev->asid = asid; mirror_sev->active = true; + mirror_sev->asid = source_sev.asid; + mirror_sev->fd = source_sev.fd; + mirror_sev->es_active = source_sev.es_active; + mirror_sev->handle = source_sev.handle; + /* + * Do not copy ap_jump_table. Since the mirror does not share the same + * KVM contexts as the original, and they may have different + * memory-views. + */ mutex_unlock(&kvm->lock); return 0; @@ -2547,11 +2591,20 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) { - if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2)) + int count; + int bytes; + + if (svm->vmcb->control.exit_info_2 > INT_MAX) + return -EINVAL; + + count = svm->vmcb->control.exit_info_2; + if (unlikely(check_mul_overflow(count, size, &bytes))) + return -EINVAL; + + if (!setup_vmgexit_scratch(svm, in, bytes)) return -EINVAL; - return kvm_sev_es_string_io(&svm->vcpu, size, port, - svm->ghcb_sa, svm->ghcb_sa_len, in); + return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in); } void sev_es_init_vmcb(struct vcpu_svm *svm) @@ -2599,11 +2652,11 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); } -void sev_es_create_vcpu(struct vcpu_svm *svm) +void sev_es_vcpu_reset(struct vcpu_svm *svm) { /* - * Set the GHCB MSR value as per the GHCB specification when creating - * a vCPU for an SEV-ES guest. + * Set the GHCB MSR value as per the GHCB specification when emulating + * vCPU RESET for an SEV-ES guest. */ set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, GHCB_VERSION_MIN, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 05e8d4d27969..b36ca4e476c2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -25,6 +25,7 @@ #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/rwsem.h> +#include <linux/cc_platform.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -36,6 +37,7 @@ #include <asm/spec-ctrl.h> #include <asm/cpu_device_id.h> #include <asm/traps.h> +#include <asm/fpu/api.h> #include <asm/virtext.h> #include "trace.h" @@ -186,6 +188,13 @@ module_param(vls, int, 0444); static int vgif = true; module_param(vgif, int, 0444); +/* enable/disable LBR virtualization */ +static int lbrv = true; +module_param(lbrv, int, 0444); + +static int tsc_scaling = true; +module_param(tsc_scaling, int, 0444); + /* * enable / disable AVIC. Because the defaults differ for APICv * support between VMX and SVM we cannot use module_param_named. @@ -455,7 +464,7 @@ static int has_svm(void) return 0; } - if (sev_active()) { + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { pr_info("KVM is unsupported when running as an SEV guest\n"); return 0; } @@ -466,7 +475,7 @@ static int has_svm(void) static void svm_hardware_disable(void) { /* Make sure we clean up behind us */ - if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) + if (tsc_scaling) wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); cpu_svm_disable(); @@ -509,6 +518,10 @@ static int svm_hardware_enable(void) wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area)); if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + /* + * Set the default value, even if we don't use TSC scaling + * to avoid having stale value in the msr + */ wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); __this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT); } @@ -929,6 +942,9 @@ static __init void svm_set_cpu_caps(void) if (npt_enabled) kvm_cpu_cap_set(X86_FEATURE_NPT); + if (tsc_scaling) + kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR); + /* Nested VM can receive #VMEXIT instead of triggering #GP */ kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK); } @@ -976,10 +992,15 @@ static __init int svm_hardware_setup(void) if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) kvm_enable_efer_bits(EFER_FFXSR); - if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - kvm_has_tsc_control = true; - kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX; - kvm_tsc_scaling_ratio_frac_bits = 32; + if (tsc_scaling) { + if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { + tsc_scaling = false; + } else { + pr_info("TSC scaling supported\n"); + kvm_has_tsc_control = true; + kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX; + kvm_tsc_scaling_ratio_frac_bits = 32; + } } tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); @@ -1059,6 +1080,13 @@ static __init int svm_hardware_setup(void) pr_info("Virtual GIF supported\n"); } + if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } + svm_set_cpu_caps(); /* @@ -1109,7 +1137,9 @@ static u64 svm_get_l2_tsc_offset(struct kvm_vcpu *vcpu) static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) { - return kvm_default_tsc_scaling_ratio; + struct vcpu_svm *svm = to_svm(vcpu); + + return svm->tsc_ratio_msr; } static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) @@ -1121,7 +1151,7 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) { wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); } @@ -1150,6 +1180,38 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, } } +static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (guest_cpuid_is_intel(vcpu)) { + /* + * We must intercept SYSENTER_EIP and SYSENTER_ESP + * accesses because the processor only stores 32 bits. + * For the same reason we cannot use virtual VMLOAD/VMSAVE. + */ + svm_set_intercept(svm, INTERCEPT_VMLOAD); + svm_set_intercept(svm, INTERCEPT_VMSAVE); + svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0); + } else { + /* + * If hardware supports Virtual VMLOAD VMSAVE then enable it + * in VMCB and clear intercepts to avoid #VMEXIT. + */ + if (vls) { + svm_clr_intercept(svm, INTERCEPT_VMLOAD); + svm_clr_intercept(svm, INTERCEPT_VMSAVE); + svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + } + /* No need to intercept these MSRs */ + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 1, 1); + } +} + static void init_vmcb(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1296,11 +1358,25 @@ static void init_vmcb(struct kvm_vcpu *vcpu) } svm_hv_init_vmcb(svm->vmcb); + init_vmcb_after_set_cpuid(vcpu); vmcb_mark_all_dirty(svm->vmcb); enable_gif(svm); +} + +static void __svm_vcpu_reset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + svm_vcpu_init_msrpm(vcpu, svm->msrpm); + + svm_init_osvw(vcpu); + vcpu->arch.microcode_version = 0x01000065; + svm->tsc_ratio_msr = kvm_default_tsc_scaling_ratio; + + if (sev_es_guest(vcpu->kvm)) + sev_es_vcpu_reset(svm); } static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -1311,6 +1387,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) svm->virt_spec_ctrl = 0; init_vmcb(vcpu); + + if (!init_event) + __svm_vcpu_reset(vcpu); } void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb) @@ -1346,10 +1425,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) /* * SEV-ES guests maintain an encrypted version of their FPU * state which is restored and saved on VMRUN and VMEXIT. - * Free the fpu structure to prevent KVM from attempting to - * access the FPU state. + * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't + * do xsave/xrstor on it. */ - kvm_free_guest_fpu(vcpu); + fpstate_set_confidential(&vcpu->arch.guest_fpu); } err = avic_init_vcpu(svm); @@ -1370,24 +1449,13 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->vmcb01.ptr = page_address(vmcb01_page); svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT); + svm_switch_vmcb(svm, &svm->vmcb01); if (vmsa_page) svm->vmsa = page_address(vmsa_page); svm->guest_state_loaded = false; - svm_switch_vmcb(svm, &svm->vmcb01); - init_vmcb(vcpu); - - svm_vcpu_init_msrpm(vcpu, svm->msrpm); - - svm_init_osvw(vcpu); - vcpu->arch.microcode_version = 0x01000065; - - if (sev_es_guest(vcpu->kvm)) - /* Perform SEV-ES specific VMCB creation updates */ - sev_es_create_vcpu(svm); - return 0; error_free_vmsa_page: @@ -1447,7 +1515,7 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) vmsave(__sme_page_pa(sd->save_area)); } - if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + if (tsc_scaling) { u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) { __this_cpu_write(current_tsc_ratio, tsc_ratio); @@ -1566,6 +1634,8 @@ static void svm_clear_vintr(struct vcpu_svm *svm) svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & V_IRQ_INJECTION_BITS_MASK; + + svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; } vmcb_mark_dirty(svm->vmcb, VMCB_INTR); @@ -2222,6 +2292,10 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (error_code) goto reinject; + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + /* Decode the instruction for usage later */ if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) goto reinject; @@ -2651,6 +2725,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) struct vcpu_svm *svm = to_svm(vcpu); switch (msr_info->index) { + case MSR_AMD64_TSC_RATIO: + if (!msr_info->host_initiated && !svm->tsc_scaling_enabled) + return 1; + msr_info->data = svm->tsc_ratio_msr; + break; case MSR_STAR: msr_info->data = svm->vmcb01.ptr->save.star; break; @@ -2800,6 +2879,19 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u32 ecx = msr->index; u64 data = msr->data; switch (ecx) { + case MSR_AMD64_TSC_RATIO: + if (!msr->host_initiated && !svm->tsc_scaling_enabled) + return 1; + + if (data & TSC_RATIO_RSVD) + return 1; + + svm->tsc_ratio_msr = data; + + if (svm->tsc_scaling_enabled && is_guest_mode(vcpu)) + nested_svm_update_tsc_ratio_msr(vcpu); + + break; case MSR_IA32_CR_PAT: if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) return 1; @@ -2912,7 +3004,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->tsc_aux = data; break; case MSR_IA32_DEBUGCTLMSR: - if (!boot_cpu_has(X86_FEATURE_LBRV)) { + if (!lbrv) { vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", __func__, data); break; @@ -3272,11 +3364,13 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) return svm_exit_handlers[exit_code](vcpu); } -static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, +static void svm_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + *reason = control->exit_code; *info1 = control->exit_info_1; *info2 = control->exit_info_2; *intr_info = control->exit_int_info; @@ -3293,7 +3387,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + trace_kvm_exit(vcpu, KVM_ISA_SVM); /* SEV-ES guests must use the CR write traps to track CR registers. */ if (!sev_es_guest(vcpu->kvm)) { @@ -3306,7 +3400,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (is_guest_mode(vcpu)) { int vmexit; - trace_kvm_nested_vmexit(exit_code, vcpu, KVM_ISA_SVM); + trace_kvm_nested_vmexit(vcpu, KVM_ISA_SVM); vmexit = nested_svm_exit_special(svm); @@ -3774,8 +3868,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) pre_svm_run(vcpu); - WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu)); - sync_lapic_to_cr8(vcpu); if (unlikely(svm->asid != svm->vmcb->control.asid)) { @@ -3995,6 +4087,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && guest_cpuid_has(vcpu, X86_FEATURE_NRIPS); + svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR); + svm_recalc_instruction_intercepts(vcpu, svm); /* For sev guests, the memory encryption bit is not reserved in CR3. */ @@ -4021,33 +4115,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_NESTED); } - - if (guest_cpuid_is_intel(vcpu)) { - /* - * We must intercept SYSENTER_EIP and SYSENTER_ESP - * accesses because the processor only stores 32 bits. - * For the same reason we cannot use virtual VMLOAD/VMSAVE. - */ - svm_set_intercept(svm, INTERCEPT_VMLOAD); - svm_set_intercept(svm, INTERCEPT_VMSAVE); - svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0); - } else { - /* - * If hardware supports Virtual VMLOAD VMSAVE then enable it - * in VMCB and clear intercepts to avoid #VMEXIT. - */ - if (vls) { - svm_clr_intercept(svm, INTERCEPT_VMLOAD); - svm_clr_intercept(svm, INTERCEPT_VMSAVE); - svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - } - /* No need to intercept these MSRs */ - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 1, 1); - } + init_vmcb_after_set_cpuid(vcpu); } static bool svm_has_wbinvd_exit(void) @@ -4285,43 +4353,44 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) struct kvm_host_map map_save; int ret; - if (is_guest_mode(vcpu)) { - /* FED8h - SVM Guest */ - put_smstate(u64, smstate, 0x7ed8, 1); - /* FEE0h - SVM Guest VMCB Physical Address */ - put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); + if (!is_guest_mode(vcpu)) + return 0; - svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + /* FED8h - SVM Guest */ + put_smstate(u64, smstate, 0x7ed8, 1); + /* FEE0h - SVM Guest VMCB Physical Address */ + put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); - ret = nested_svm_vmexit(svm); - if (ret) - return ret; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; - /* - * KVM uses VMCB01 to store L1 host state while L2 runs but - * VMCB01 is going to be used during SMM and thus the state will - * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save - * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the - * format of the area is identical to guest save area offsetted - * by 0x400 (matches the offset of 'struct vmcb_save_area' - * within 'struct vmcb'). Note: HSAVE area may also be used by - * L1 hypervisor to save additional host context (e.g. KVM does - * that, see svm_prepare_guest_switch()) which must be - * preserved. - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + ret = nested_svm_vmexit(svm); + if (ret) + return ret; - BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_guest_switch()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; - svm_copy_vmrun_state(map_save.hva + 0x400, - &svm->vmcb01.ptr->save); + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); - kvm_vcpu_unmap(vcpu, &map_save, true); - } + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); return 0; } @@ -4329,50 +4398,54 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map, map_save; - int ret = 0; + u64 saved_efer, vmcb12_gpa; + struct vmcb *vmcb12; + int ret; - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { - u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); - u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); - u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); - struct vmcb *vmcb12; + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 0; - if (guest) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - return 1; + /* Non-zero if SMI arrived while vCPU was in guest mode. */ + if (!GET_SMSTATE(u64, smstate, 0x7ed8)) + return 0; - if (!(saved_efer & EFER_SVME)) - return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; - if (kvm_vcpu_map(vcpu, - gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) - return 1; + saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); + if (!(saved_efer & EFER_SVME)) + return 1; - if (svm_allocate_nested(svm)) - return 1; + vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) + return 1; - vmcb12 = map.hva; + ret = 1; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL) + goto unmap_map; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + if (svm_allocate_nested(svm)) + goto unmap_save; - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); - kvm_vcpu_unmap(vcpu, &map, true); + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ - /* - * Restore L1 host state from L1 HSAVE area as VMCB01 was - * used during SMM (see svm_enter_smm()) - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400); - svm_copy_vmrun_state(&svm->vmcb01.ptr->save, - map_save.hva + 0x400); + /* + * Enter the nested guest now + */ - kvm_vcpu_unmap(vcpu, &map_save, true); - } - } + vmcb12 = map.hva; + nested_load_control_from_vmcb12(svm, &vmcb12->control); + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); +unmap_save: + kvm_vcpu_unmap(vcpu, &map_save, true); +unmap_map: + kvm_vcpu_unmap(vcpu, &map, true); return ret; } @@ -4509,6 +4582,8 @@ static int svm_vm_init(struct kvm *kvm) } static struct kvm_x86_ops svm_x86_ops __initdata = { + .name = "kvm_amd", + .hardware_unsetup = svm_hardware_teardown, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 524d943f3efc..5e9510d4574e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -140,6 +140,8 @@ struct vcpu_svm { u64 next_rip; u64 spec_ctrl; + + u64 tsc_ratio_msr; /* * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be * translated into the appropriate L2_CFG bits on the host to @@ -160,7 +162,8 @@ struct vcpu_svm { unsigned long int3_rip; /* cached guest cpuid flags for faster access */ - bool nrips_enabled : 1; + bool nrips_enabled : 1; + bool tsc_scaling_enabled : 1; u32 ldr_reg; u32 dfr_reg; @@ -191,7 +194,7 @@ struct vcpu_svm { /* SEV-ES scratch area support */ void *ghcb_sa; - u64 ghcb_sa_len; + u32 ghcb_sa_len; bool ghcb_sa_sync; bool ghcb_sa_free; @@ -218,12 +221,12 @@ DECLARE_PER_CPU(struct svm_cpu_data *, svm_data); void recalc_intercepts(struct vcpu_svm *svm); -static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) +static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) { return container_of(kvm, struct kvm_svm, kvm); } -static inline bool sev_guest(struct kvm *kvm) +static __always_inline bool sev_guest(struct kvm *kvm) { #ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -234,7 +237,7 @@ static inline bool sev_guest(struct kvm *kvm) #endif } -static inline bool sev_es_guest(struct kvm *kvm) +static __always_inline bool sev_es_guest(struct kvm *kvm) { #ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -271,7 +274,7 @@ static inline bool vmcb_is_dirty(struct vmcb *vmcb, int bit) return !test_bit(bit, (unsigned long *)&vmcb->control.clean); } -static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) +static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_svm, vcpu); } @@ -459,7 +462,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } -int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12); +int enter_svm_guest_mode(struct kvm_vcpu *vcpu, + u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); @@ -482,6 +486,8 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); int nested_svm_exit_special(struct vcpu_svm *svm); +void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); +void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier); void nested_load_control_from_vmcb12(struct vcpu_svm *svm, struct vmcb_control_area *control); void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); @@ -561,7 +567,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); void sev_es_init_vmcb(struct vcpu_svm *svm); -void sev_es_create_vcpu(struct vcpu_svm *svm); +void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu); void sev_es_unmap_ghcb(struct vcpu_svm *svm); diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 22e2b019de37..9430d6437c9f 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -56,12 +56,12 @@ static inline void invlpga(unsigned long addr, u32 asid) * VMSAVE, VMLOAD, etc... is still controlled by the effective address size, * hence 'unsigned long' instead of 'hpa_t'. */ -static inline void vmsave(unsigned long pa) +static __always_inline void vmsave(unsigned long pa) { svm_asm1(vmsave, "a" (pa), "memory"); } -static inline void vmload(unsigned long pa) +static __always_inline void vmload(unsigned long pa) { svm_asm1(vmload, "a" (pa), "memory"); } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 03ebe368333e..953b0fcb21ee 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -288,8 +288,8 @@ TRACE_EVENT(kvm_apic, #define TRACE_EVENT_KVM_EXIT(name) \ TRACE_EVENT(name, \ - TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu, u32 isa), \ - TP_ARGS(exit_reason, vcpu, isa), \ + TP_PROTO(struct kvm_vcpu *vcpu, u32 isa), \ + TP_ARGS(vcpu, isa), \ \ TP_STRUCT__entry( \ __field( unsigned int, exit_reason ) \ @@ -303,11 +303,12 @@ TRACE_EVENT(name, \ ), \ \ TP_fast_assign( \ - __entry->exit_reason = exit_reason; \ __entry->guest_rip = kvm_rip_read(vcpu); \ __entry->isa = isa; \ __entry->vcpu_id = vcpu->vcpu_id; \ - static_call(kvm_x86_get_exit_info)(vcpu, &__entry->info1, \ + static_call(kvm_x86_get_exit_info)(vcpu, \ + &__entry->exit_reason, \ + &__entry->info1, \ &__entry->info2, \ &__entry->intr_info, \ &__entry->error_code); \ diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 0dab1b7b529f..ba6f99f584ac 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -353,14 +353,20 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; + break; + case MSR_IA32_VMX_PINBASED_CTLS: + ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; + break; + case MSR_IA32_VMX_VMFUNC: + ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC; break; } diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 152ab0aa82cf..16731d2cf231 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -93,7 +93,7 @@ static __always_inline int get_evmcs_offset(unsigned long field, return evmcs_field->offset; } -static inline void evmcs_write64(unsigned long field, u64 value) +static __always_inline void evmcs_write64(unsigned long field, u64 value) { u16 clean_field; int offset = get_evmcs_offset(field, &clean_field); @@ -183,7 +183,7 @@ static inline void evmcs_load(u64 phys_addr) __init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ -static inline void evmcs_write64(unsigned long field, u64 value) {} +static __always_inline void evmcs_write64(unsigned long field, u64 value) {} static inline void evmcs_write32(unsigned long field, u32 value) {} static inline void evmcs_write16(unsigned long field, u16 value) {} static inline u64 evmcs_read64(unsigned long field) { return 0; } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ccb03d69546c..b4ee5e9f9e20 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -191,7 +191,7 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) * failValid writes the error number to the current VMCS, which * can't be done if there isn't a current VMCS. */ - if (vmx->nested.current_vmptr == -1ull && + if (vmx->nested.current_vmptr == INVALID_GPA && !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) return nested_vmx_failInvalid(vcpu); @@ -218,7 +218,7 @@ static inline u64 vmx_control_msr(u32 low, u32 high) static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); vmx->nested.need_vmcs12_to_shadow_sync = false; } @@ -290,9 +290,10 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; + vmx->nested.vmxon_ptr = INVALID_GPA; free_vpid(vmx->nested.vpid02); vmx->nested.posted_intr_nv = -1; - vmx->nested.current_vmptr = -1ull; + vmx->nested.current_vmptr = INVALID_GPA; if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); @@ -709,7 +710,7 @@ static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *shadow; if (!nested_cpu_has_shadow_vmcs(vmcs12) || - vmcs12->vmcs_link_pointer == -1ull) + vmcs12->vmcs_link_pointer == INVALID_GPA) return; shadow = get_shadow_vmcs12(vcpu); @@ -727,7 +728,7 @@ static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); if (!nested_cpu_has_shadow_vmcs(vmcs12) || - vmcs12->vmcs_link_pointer == -1ull) + vmcs12->vmcs_link_pointer == INVALID_GPA) return; kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer, @@ -1994,7 +1995,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( } if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { - vmx->nested.current_vmptr = -1ull; + vmx->nested.current_vmptr = INVALID_GPA; nested_release_evmcs(vcpu); @@ -2178,7 +2179,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) } if (cpu_has_vmx_encls_vmexit()) - vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); + vmcs_write64(ENCLS_EXITING_BITMAP, INVALID_GPA); /* * Set the MSR load/store lists to match L0's settings. Only the @@ -2197,7 +2198,7 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, { prepare_vmcs02_constant_state(vmx); - vmcs_write64(VMCS_LINK_POINTER, -1ull); + vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) @@ -2583,8 +2584,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Guest state is invalid and unrestricted guest is disabled, * which means L1 attempted VMEntry to L2 with invalid state. * Fail the VMEntry. + * + * However when force loading the guest state (SMM exit or + * loading nested state after migration, it is possible to + * have invalid guest state now, which will be later fixed by + * restoring L2 register state */ - if (CC(!vmx_guest_state_valid(vcpu))) { + if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -2944,7 +2950,7 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, struct vmcs12 *shadow; struct kvm_host_map map; - if (vmcs12->vmcs_link_pointer == -1ull) + if (vmcs12->vmcs_link_pointer == INVALID_GPA) return 0; if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))) @@ -3211,7 +3217,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR to * force VM-Entry to fail. */ - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, INVALID_GPA); } } @@ -3522,7 +3528,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && - vmx->nested.current_vmptr == -1ull)) + vmx->nested.current_vmptr == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); vmcs12 = get_vmcs12(vcpu); @@ -4351,6 +4357,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); + + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) @@ -4899,14 +4907,7 @@ out_vmcs02: return -ENOMEM; } -/* - * Emulate the VMXON instruction. - * Currently, we just remember that VMX is active, and do not save or even - * inspect the argument to VMXON (the so-called "VMXON pointer") because we - * do not currently need to store anything in that guest-allocated memory - * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their - * argument is different from the VMXON pointer (which the spec says they do). - */ +/* Emulate the VMXON instruction. */ static int handle_vmon(struct kvm_vcpu *vcpu) { int ret; @@ -4975,7 +4976,7 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vmx->nested.current_vmptr == -1ull) + if (vmx->nested.current_vmptr == INVALID_GPA) return; copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); @@ -4995,7 +4996,7 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu) kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL); - vmx->nested.current_vmptr = -1ull; + vmx->nested.current_vmptr = INVALID_GPA; } /* Emulate the VMXOFF instruction */ @@ -5090,12 +5091,12 @@ static int handle_vmread(struct kvm_vcpu *vcpu) return 1; /* - * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMREAD sets the ALU flags for VMfailInvalid. */ - if (vmx->nested.current_vmptr == -1ull || + if (vmx->nested.current_vmptr == INVALID_GPA || (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) + get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); /* Decode instruction info and find the field to read */ @@ -5182,12 +5183,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return 1; /* - * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMWRITE sets the ALU flags for VMfailInvalid. */ - if (vmx->nested.current_vmptr == -1ull || + if (vmx->nested.current_vmptr == INVALID_GPA || (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) + get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); if (instr_info & BIT(10)) @@ -5630,7 +5631,7 @@ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, gpa_t bitmap, last_bitmap; u8 b; - last_bitmap = (gpa_t)-1; + last_bitmap = INVALID_GPA; b = -1; while (size > 0) { @@ -5903,6 +5904,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ return true; + case EXIT_REASON_BUS_LOCK: + /* + * At present, bus lock VM exit is never exposed to L1. + * Handle L2's bus locks in L0 directly. + */ + return true; default: break; } @@ -6059,7 +6066,7 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) goto reflect_vmexit; } - trace_kvm_nested_vmexit(exit_reason.full, vcpu, KVM_ISA_VMX); + trace_kvm_nested_vmexit(vcpu, KVM_ISA_VMX); /* If L0 (KVM) wants the exit, it trumps L1's desires. */ if (nested_vmx_l0_wants_exit(vcpu, exit_reason)) @@ -6100,8 +6107,8 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, .format = KVM_STATE_NESTED_FORMAT_VMX, .size = sizeof(kvm_state), .hdr.vmx.flags = 0, - .hdr.vmx.vmxon_pa = -1ull, - .hdr.vmx.vmcs12_pa = -1ull, + .hdr.vmx.vmxon_pa = INVALID_GPA, + .hdr.vmx.vmcs12_pa = INVALID_GPA, .hdr.vmx.preemption_timer_deadline = 0, }; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = @@ -6127,7 +6134,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && nested_cpu_has_shadow_vmcs(vmcs12) && - vmcs12->vmcs_link_pointer != -1ull) + vmcs12->vmcs_link_pointer != INVALID_GPA) kvm_state.size += sizeof(user_vmx_nested_state->shadow_vmcs12); } @@ -6203,7 +6210,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, return -EFAULT; if (nested_cpu_has_shadow_vmcs(vmcs12) && - vmcs12->vmcs_link_pointer != -1ull) { + vmcs12->vmcs_link_pointer != INVALID_GPA) { if (copy_to_user(user_vmx_nested_state->shadow_vmcs12, get_shadow_vmcs12(vcpu), VMCS12_SIZE)) return -EFAULT; @@ -6238,11 +6245,11 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (kvm_state->format != KVM_STATE_NESTED_FORMAT_VMX) return -EINVAL; - if (kvm_state->hdr.vmx.vmxon_pa == -1ull) { + if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA) { if (kvm_state->hdr.vmx.smm.flags) return -EINVAL; - if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) + if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA) return -EINVAL; /* @@ -6296,7 +6303,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx_leave_nested(vcpu); - if (kvm_state->hdr.vmx.vmxon_pa == -1ull) + if (kvm_state->hdr.vmx.vmxon_pa == INVALID_GPA) return 0; vmx->nested.vmxon_ptr = kvm_state->hdr.vmx.vmxon_pa; @@ -6309,13 +6316,13 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, /* See vmx_has_valid_vmcs12. */ if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) || (kvm_state->flags & KVM_STATE_NESTED_EVMCS) || - (kvm_state->hdr.vmx.vmcs12_pa != -1ull)) + (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA)) return -EINVAL; else return 0; } - if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) { + if (kvm_state->hdr.vmx.vmcs12_pa != INVALID_GPA) { if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa || !page_address_valid(vcpu, kvm_state->hdr.vmx.vmcs12_pa)) return -EINVAL; @@ -6360,7 +6367,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && - vmcs12->vmcs_link_pointer != -1ull) { + vmcs12->vmcs_link_pointer != INVALID_GPA) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); if (kvm_state->size < diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 10cc4f65c4ef..b8e0d21b7c8a 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -365,7 +365,7 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = pmu->global_ctrl; return 0; case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - msr_info->data = pmu->global_ovf_ctrl; + msr_info->data = 0; return 0; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || @@ -423,7 +423,6 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & pmu->global_ovf_ctrl_mask)) { if (!msr_info->host_initiated) pmu->global_status &= ~data; - pmu->global_ovf_ctrl = data; return 0; } break; @@ -588,8 +587,7 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) pmc->counter = 0; } - pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = - pmu->global_ovf_ctrl = 0; + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; intel_pmu_release_guest_lbr_event(vcpu); } diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 6693ebdc0770..35e7ec91ae86 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -53,11 +53,9 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, static void sgx_handle_emulation_failure(struct kvm_vcpu *vcpu, u64 addr, unsigned int size) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = addr; - vcpu->run->internal.data[1] = size; + uint64_t data[2] = { addr, size }; + + __kvm_prepare_emulation_failure_exit(vcpu, data, ARRAY_SIZE(data)); } static int sgx_read_hva(struct kvm_vcpu *vcpu, unsigned long hva, void *data, @@ -112,9 +110,7 @@ static int sgx_inject_fault(struct kvm_vcpu *vcpu, gva_t gva, int trapnr) * but the error code isn't (yet) plumbed through the ENCLS helpers. */ if (trapnr == PF_VECTOR && !boot_cpu_has(X86_FEATURE_SGX2)) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } @@ -155,9 +151,7 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, sgx_12_0 = kvm_find_cpuid_entry(vcpu, 0x12, 0); sgx_12_1 = kvm_find_cpuid_entry(vcpu, 0x12, 1); if (!sgx_12_0 || !sgx_12_1) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0c2c0d5ae873..76861b66bbcf 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -35,7 +35,7 @@ #include <asm/cpu_device_id.h> #include <asm/debugreg.h> #include <asm/desc.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> @@ -1059,8 +1059,8 @@ static void pt_guest_enter(struct vcpu_vmx *vmx) rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { wrmsrl(MSR_IA32_RTIT_CTL, 0); - pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range); - pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range); + pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); + pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); } } @@ -1070,12 +1070,16 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) return; if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { - pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range); - pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range); + pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); + pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); } - /* Reload host state (IA32_RTIT_CTL will be cleared on VM exit). */ - wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); + /* + * KVM requires VM_EXIT_CLEAR_IA32_RTIT_CTL to expose PT to the guest, + * i.e. RTIT_CTL is always cleared on VM-Exit. Restore it if necessary. + */ + if (vmx->pt_desc.host.ctl) + wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, @@ -1323,7 +1327,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) vmx_prepare_switch_to_host(to_vmx(vcpu)); } -static bool emulation_required(struct kvm_vcpu *vcpu) +bool vmx_emulation_required(struct kvm_vcpu *vcpu) { return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu); } @@ -1367,7 +1371,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) @@ -1456,16 +1460,16 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) * cause a #GP fault. */ value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 1)) || (value > 2)) + if ((value && (vmx->pt_desc.num_address_ranges < 1)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 2)) || (value > 2)) + if ((value && (vmx->pt_desc.num_address_ranges < 2)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 3)) || (value > 2)) + if ((value && (vmx->pt_desc.num_address_ranges < 3)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 4)) || (value > 2)) + if ((value && (vmx->pt_desc.num_address_ranges < 4)) || (value > 2)) return 1; return 0; @@ -1837,10 +1841,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &msr_info->data)) return 1; /* - * Enlightened VMCS v1 doesn't have certain fields, but buggy - * Hyper-V versions are still trying to use corresponding - * features when they are exposed. Filter out the essential - * minimum. + * Enlightened VMCS v1 doesn't have certain VMCS fields but + * instead of just ignoring the features, different Hyper-V + * versions are either trying to use them and fail or do some + * sanity checking and refuse to boot. Filter all unsupported + * features out. */ if (!msr_info->host_initiated && vmx->nested.enlightened_vmcs_enabled) @@ -1885,8 +1890,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (!vmx_pt_mode_is_host_guest() || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) + (index >= 2 * vmx->pt_desc.num_address_ranges)) return 1; if (index % 2) msr_info->data = vmx->pt_desc.guest.addr_b[index / 2]; @@ -2201,8 +2205,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!pt_can_write_msr(vmx)) return 1; index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges)) + if (index >= 2 * vmx->pt_desc.num_address_ranges) return 1; if (is_noncanonical_address(data, vcpu)) return 1; @@ -3077,7 +3080,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } static int vmx_get_max_tdp_level(void) @@ -3330,7 +3333,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int { __vmx_set_segment(vcpu, var, seg); - to_vmx(vcpu)->emulation_required = emulation_required(vcpu); + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -3878,7 +3881,7 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_BASE, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_MASK, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_CR3_MATCH, MSR_TYPE_RW, flag); - for (i = 0; i < vmx->pt_desc.addr_range; i++) { + for (i = 0; i < vmx->pt_desc.num_address_ranges; i++) { vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag); } @@ -4327,10 +4330,6 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) #define VMX_XSS_EXIT_BITMAP 0 -/* - * Noting that the initialization of Guest-state Area of VMCS is in - * vmx_vcpu_reset(). - */ static void init_vmcs(struct vcpu_vmx *vmx) { if (nested) @@ -4339,7 +4338,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); - vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ + vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); /* 22.3.1.5 */ /* Control */ pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); @@ -4435,10 +4434,40 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmx_setup_uret_msrs(vmx); } +static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + init_vmcs(vmx); + + if (nested) + memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs)); + + vcpu_setup_sgx_lepubkeyhash(vcpu); + + vmx->nested.posted_intr_nv = -1; + vmx->nested.vmxon_ptr = INVALID_GPA; + vmx->nested.current_vmptr = INVALID_GPA; + vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; + + vcpu->arch.microcode_version = 0x100000000ULL; + vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; + + /* + * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR + * or POSTED_INTR_WAKEUP_VECTOR. + */ + vmx->pi_desc.nv = POSTED_INTR_VECTOR; + vmx->pi_desc.sn = 1; +} + static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (!init_event) + __vmx_vcpu_reset(vcpu); + vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; @@ -4448,6 +4477,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_set_cr8(vcpu, 0); vmx_segment_cache_clear(vmx); + kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); @@ -5378,10 +5408,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vmx->emulation_required && !vmx->rmode.vm86_active && vcpu->arch.exception.pending) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } @@ -5561,9 +5588,13 @@ static int handle_encls(struct kvm_vcpu *vcpu) static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) { - vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; - vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; - return 0; + /* + * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK + * VM-Exits. Unconditionally set the flag here and leave the handling to + * vmx_handle_exit(). + */ + to_vmx(vcpu)->exit_reason.bus_lock_detected = true; + return 1; } /* @@ -5628,11 +5659,13 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); -static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, +static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + *reason = vmx->exit_reason.full; *info1 = vmx_get_exit_qual(vcpu); if (!(vmx->exit_reason.failed_vmentry)) { *info2 = vmx->idt_vectoring_info; @@ -6050,9 +6083,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) int ret = __vmx_handle_exit(vcpu, exit_fastpath); /* - * Even when current exit reason is handled by KVM internally, we - * still need to exit to user space when bus lock detected to inform - * that there is a bus lock in guest. + * Exit to user space when bus lock detected to inform that there is + * a bus lock in guest. */ if (to_vmx(vcpu)->exit_reason.bus_lock_detected) { if (ret > 0) @@ -6301,18 +6333,13 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) /* * If we are running L2 and L1 has a new pending interrupt - * which can be injected, we should re-evaluate - * what should be done with this new L1 interrupt. - * If L1 intercepts external-interrupts, we should - * exit from L2 to L1. Otherwise, interrupt should be - * delivered directly to L2. + * which can be injected, this may cause a vmexit or it may + * be injected into L2. Either way, this interrupt will be + * processed via KVM_REQ_EVENT, not RVI, because we do not use + * virtual interrupt delivery to inject L1 interrupts into L2. */ - if (is_guest_mode(vcpu) && max_irr_updated) { - if (nested_exit_on_intr(vcpu)) - kvm_vcpu_exiting_guest_mode(vcpu); - else - kvm_make_request(KVM_REQ_EVENT, vcpu); - } + if (is_guest_mode(vcpu) && max_irr_updated) + kvm_make_request(KVM_REQ_EVENT, vcpu); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); } @@ -6407,6 +6434,7 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: return nested; case MSR_AMD64_VIRT_SPEC_CTRL: + case MSR_AMD64_TSC_RATIO: /* This is AMD only. */ return false; default: @@ -6621,10 +6649,24 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->entry_time = ktime_get(); - /* Don't enter VMX if guest state is invalid, let the exit handler - start emulation until we arrive back to a valid state */ - if (vmx->emulation_required) + /* + * Don't enter VMX if guest state is invalid, let the exit handler + * start emulation until we arrive back to a valid state. Synthesize a + * consistency check VM-Exit due to invalid guest state and bail. + */ + if (unlikely(vmx->emulation_required)) { + + /* We don't emulate invalid state of a nested guest */ + vmx->fail = is_guest_mode(vcpu); + + vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; + vmx->exit_reason.failed_vmentry = 1; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + vmx->exit_qualification = ENTRY_FAIL_DEFAULT; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + vmx->exit_intr_info = 0; return EXIT_FASTPATH_NONE; + } trace_kvm_entry(vcpu); @@ -6769,7 +6811,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) if (likely(!vmx->exit_reason.failed_vmentry)) vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - trace_kvm_exit(vmx->exit_reason.full, vcpu, KVM_ISA_VMX); + trace_kvm_exit(vcpu, KVM_ISA_VMX); if (unlikely(vmx->exit_reason.failed_vmentry)) return EXIT_FASTPATH_NONE; @@ -6800,7 +6842,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; - int i, cpu, err; + int i, err; BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); vmx = to_vmx(vcpu); @@ -6821,10 +6863,8 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) goto free_vpid; } - for (i = 0; i < kvm_nr_uret_msrs; ++i) { - vmx->guest_uret_msrs[i].data = 0; + for (i = 0; i < kvm_nr_uret_msrs; ++i) vmx->guest_uret_msrs[i].mask = -1ull; - } if (boot_cpu_has(X86_FEATURE_RTM)) { /* * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. @@ -6833,7 +6873,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) - vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); @@ -6861,12 +6901,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) } vmx->loaded_vmcs = &vmx->vmcs01; - cpu = get_cpu(); - vmx_vcpu_load(vcpu, cpu); - vcpu->cpu = cpu; - init_vmcs(vmx); - vmx_vcpu_put(vcpu); - put_cpu(); + if (cpu_need_virtualize_apic_accesses(vcpu)) { err = alloc_apic_access_page(vcpu->kvm); if (err) @@ -6879,27 +6914,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) goto free_vmcs; } - if (nested) - memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs)); - else - memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); - - vcpu_setup_sgx_lepubkeyhash(vcpu); - - vmx->nested.posted_intr_nv = -1; - vmx->nested.current_vmptr = -1ull; - vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; - - vcpu->arch.microcode_version = 0x100000000ULL; - vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; - - /* - * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR - * or POSTED_INTR_WAKEUP_VECTOR. - */ - vmx->pi_desc.nv = POSTED_INTR_VECTOR; - vmx->pi_desc.sn = 1; - return 0; free_vmcs: @@ -7114,12 +7128,13 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) } /* Get the number of configurable Address Ranges for filtering */ - vmx->pt_desc.addr_range = intel_pt_validate_cap(vmx->pt_desc.caps, + vmx->pt_desc.num_address_ranges = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_num_address_ranges); /* Initialize and clear the no dependency bits */ vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS | - RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC); + RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC | + RTIT_CTL_BRANCH_EN); /* * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise @@ -7137,12 +7152,11 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ); /* - * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn BranchEn and - * MTCFreq can be set + * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn and MTCFreq can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc)) vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN | - RTIT_CTL_BRANCH_EN | RTIT_CTL_MTC_RANGE); + RTIT_CTL_MTC_RANGE); /* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite)) @@ -7162,7 +7176,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; /* unmask address range configure area */ - for (i = 0; i < vmx->pt_desc.addr_range; i++) + for (i = 0; i < vmx->pt_desc.num_address_ranges; i++) vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); } @@ -7538,6 +7552,8 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu) static void hardware_unsetup(void) { + kvm_set_posted_intr_wakeup_handler(NULL); + if (nested) nested_vmx_hardware_unsetup(); @@ -7553,6 +7569,8 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit) } static struct kvm_x86_ops vmx_x86_ops __initdata = { + .name = "kvm_intel", + .hardware_unsetup = hardware_unsetup, .hardware_enable = hardware_enable, @@ -7866,8 +7884,6 @@ static __init int hardware_setup(void) vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } - kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); - kvm_mce_cap_supported |= MCG_LMCE_P; if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) @@ -7891,6 +7907,9 @@ static __init int hardware_setup(void) r = alloc_kvm_area(); if (r) nested_vmx_hardware_unsetup(); + + kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); + return r; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4858c5fd95f2..e7db42e3b0ce 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -62,7 +62,7 @@ struct pt_ctx { struct pt_desc { u64 ctl_bitmask; - u32 addr_range; + u32 num_address_ranges; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; struct pt_ctx host; struct pt_ctx guest; @@ -248,12 +248,8 @@ struct vcpu_vmx { * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to * be loaded into hardware if those conditions aren't met. - * nr_active_uret_msrs tracks the number of MSRs that need to be loaded - * into hardware when running the guest. guest_uret_msrs[] is resorted - * whenever the number of "active" uret MSRs is modified. */ struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; - int nr_active_uret_msrs; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; @@ -359,6 +355,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); +bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 28ef14155726..c1c4e2b05a63 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -68,7 +68,9 @@ #include <asm/mce.h> #include <asm/pkru.h> #include <linux/kernel_stat.h> -#include <asm/fpu/internal.h> /* Ugh! */ +#include <asm/fpu/api.h> +#include <asm/fpu/xcr.h> +#include <asm/fpu/xstate.h> #include <asm/pvclock.h> #include <asm/div64.h> #include <asm/irq_remapping.h> @@ -293,8 +295,6 @@ u64 __read_mostly host_xcr0; u64 __read_mostly supported_xcr0; EXPORT_SYMBOL_GPL(supported_xcr0); -static struct kmem_cache *x86_fpu_cache; - static struct kmem_cache *x86_emulator_cache; /* @@ -790,30 +790,6 @@ bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) } EXPORT_SYMBOL_GPL(kvm_require_dr); -/* - * This function will be used to read from the physical memory of the currently - * running guest. The difference to kvm_vcpu_read_guest_page is that this function - * can read from guest physical or from the guest's guest physical memory. - */ -int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gfn_t ngfn, void *data, int offset, int len, - u32 access) -{ - struct x86_exception exception; - gfn_t real_gfn; - gpa_t ngpa; - - ngpa = gfn_to_gpa(ngfn); - real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception); - if (real_gfn == UNMAPPED_GVA) - return -EFAULT; - - real_gfn = gpa_to_gfn(real_gfn); - - return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len); -} -EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); - static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); @@ -825,34 +801,38 @@ static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) { gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; - unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2; + gpa_t real_gpa; int i; int ret; u64 pdpte[ARRAY_SIZE(mmu->pdptrs)]; - ret = kvm_read_guest_page_mmu(vcpu, mmu, pdpt_gfn, pdpte, - offset * sizeof(u64), sizeof(pdpte), - PFERR_USER_MASK|PFERR_WRITE_MASK); - if (ret < 0) { - ret = 0; - goto out; - } + /* + * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated + * to an L1 GPA. + */ + real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(pdpt_gfn), + PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); + if (real_gpa == UNMAPPED_GVA) + return 0; + + /* Note the offset, PDPTRs are 32 byte aligned when using PAE paging. */ + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(real_gpa), pdpte, + cr3 & GENMASK(11, 5), sizeof(pdpte)); + if (ret < 0) + return 0; + for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && (pdpte[i] & pdptr_rsvd_bits(vcpu))) { - ret = 0; - goto out; + return 0; } } - ret = 1; memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); vcpu->arch.pdptrs_from_userspace = false; -out: - - return ret; + return 1; } EXPORT_SYMBOL_GPL(load_pdptrs); @@ -993,7 +973,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) /* * Do not allow the guest to set bits that we do not support * saving. However, xcr0 bit 0 is always set, even if the - * emulated CPU does not support XSAVE (see fx_init). + * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) @@ -1042,9 +1022,28 @@ EXPORT_SYMBOL_GPL(kvm_is_valid_cr4); void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) { - if (((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) || - (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) + /* + * If any role bit is changed, the MMU needs to be reset. + * + * If CR4.PCIDE is changed 1 -> 0, the guest TLB must be flushed. + * If CR4.PCIDE is changed 0 -> 1, there is no need to flush the TLB + * according to the SDM; however, stale prev_roots could be reused + * incorrectly in the future after a MOV to CR3 with NOFLUSH=1, so we + * free them all. KVM_REQ_MMU_RELOAD is fit for the both cases; it + * is slow, but changing CR4.PCIDE is a rare case. + * + * If CR4.PGE is changed, the guest TLB must be flushed. + * + * Note: resetting MMU is a superset of KVM_REQ_MMU_RELOAD and + * KVM_REQ_MMU_RELOAD is a superset of KVM_REQ_TLB_FLUSH_GUEST, hence + * the usage of "else if". + */ + if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) kvm_mmu_reset_context(vcpu); + else if ((cr4 ^ old_cr4) & X86_CR4_PCIDE) + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + else if ((cr4 ^ old_cr4) & X86_CR4_PGE) + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } EXPORT_SYMBOL_GPL(kvm_post_set_cr4); @@ -1092,6 +1091,18 @@ static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) int i; /* + * MOV CR3 and INVPCID are usually not intercepted when using TDP, but + * this is reachable when running EPT=1 and unrestricted_guest=0, and + * also via the emulator. KVM's TDP page tables are not in the scope of + * the invalidation, but the guest's TLB entries need to be flushed as + * the CPU may have cached entries in its TLB for the target PCID. + */ + if (unlikely(tdp_enabled)) { + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + return; + } + + /* * If neither the current CR3 nor any of the prev_roots use the given * PCID, then nothing needs to be done here because a resync will * happen anyway before switching to any other CR3. @@ -1101,6 +1112,14 @@ static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } + /* + * If PCID is disabled, there is no need to free prev_roots even if the + * PCIDs for them are also 0, because MOV to CR3 always flushes the TLB + * with PCIDE=0. + */ + if (!kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + return; + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); @@ -1332,6 +1351,13 @@ static const u32 msrs_to_save_all[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; @@ -1374,6 +1400,7 @@ static const u32 emulated_msrs_all[] = { MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, MSR_AMD64_VIRT_SPEC_CTRL, + MSR_AMD64_TSC_RATIO, MSR_IA32_POWER_CTL, MSR_IA32_UCODE_REV, @@ -2447,13 +2474,64 @@ static inline bool kvm_check_tsc_unstable(void) return check_tsc_unstable(); } +/* + * Infers attempts to synchronize the guest's tsc from host writes. Sets the + * offset for the vcpu and tracks the TSC matching generation that the vcpu + * participates in. + */ +static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, + u64 ns, bool matched) +{ + struct kvm *kvm = vcpu->kvm; + + lockdep_assert_held(&kvm->arch.tsc_write_lock); + + /* + * We also track th most recent recorded KHZ, write and time to + * allow the matching interval to be extended at each write. + */ + kvm->arch.last_tsc_nsec = ns; + kvm->arch.last_tsc_write = tsc; + kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; + kvm->arch.last_tsc_offset = offset; + + vcpu->arch.last_guest_tsc = tsc; + + kvm_vcpu_write_tsc_offset(vcpu, offset); + + if (!matched) { + /* + * We split periods of matched TSC writes into generations. + * For each generation, we track the original measured + * nanosecond time, offset, and write, so if TSCs are in + * sync, we can match exact offset, and if not, we can match + * exact software computation in compute_guest_tsc() + * + * These values are tracked in kvm->arch.cur_xxx variables. + */ + kvm->arch.cur_tsc_generation++; + kvm->arch.cur_tsc_nsec = ns; + kvm->arch.cur_tsc_write = tsc; + kvm->arch.cur_tsc_offset = offset; + kvm->arch.nr_vcpus_matched_tsc = 0; + } else if (vcpu->arch.this_tsc_generation != kvm->arch.cur_tsc_generation) { + kvm->arch.nr_vcpus_matched_tsc++; + } + + /* Keep track of which generation this VCPU has synchronized to */ + vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; + vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; + vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; + + kvm_track_tsc_matching(vcpu); +} + static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) { struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; - bool matched; - bool already_matched; + bool matched = false; bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); @@ -2499,51 +2577,10 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) offset = kvm_compute_l1_tsc_offset(vcpu, data); } matched = true; - already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation); - } else { - /* - * We split periods of matched TSC writes into generations. - * For each generation, we track the original measured - * nanosecond time, offset, and write, so if TSCs are in - * sync, we can match exact offset, and if not, we can match - * exact software computation in compute_guest_tsc() - * - * These values are tracked in kvm->arch.cur_xxx variables. - */ - kvm->arch.cur_tsc_generation++; - kvm->arch.cur_tsc_nsec = ns; - kvm->arch.cur_tsc_write = data; - kvm->arch.cur_tsc_offset = offset; - matched = false; } - /* - * We also track th most recent recorded KHZ, write and time to - * allow the matching interval to be extended at each write. - */ - kvm->arch.last_tsc_nsec = ns; - kvm->arch.last_tsc_write = data; - kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; - - vcpu->arch.last_guest_tsc = data; - - /* Keep track of which generation this VCPU has synchronized to */ - vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; - vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; - vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; - - kvm_vcpu_write_tsc_offset(vcpu, offset); + __kvm_synchronize_tsc(vcpu, offset, data, ns, matched); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - - spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); - if (!matched) { - kvm->arch.nr_vcpus_matched_tsc = 0; - } else if (!already_matched) { - kvm->arch.nr_vcpus_matched_tsc++; - } - - kvm_track_tsc_matching(vcpu); - spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, @@ -2731,6 +2768,7 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) int vclock_mode; bool host_tsc_clocksource, vcpus_matched; + lockdep_assert_held(&kvm->arch.tsc_write_lock); vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&kvm->online_vcpus)); @@ -2755,68 +2793,101 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) #endif } -void kvm_make_mclock_inprogress_request(struct kvm *kvm) +static void kvm_make_mclock_inprogress_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); } -static void kvm_gen_update_masterclock(struct kvm *kvm) +static void __kvm_start_pvclock_update(struct kvm *kvm) { -#ifdef CONFIG_X86_64 - int i; - struct kvm_vcpu *vcpu; - struct kvm_arch *ka = &kvm->arch; - unsigned long flags; - - kvm_hv_invalidate_tsc_page(kvm); + raw_spin_lock_irq(&kvm->arch.tsc_write_lock); + write_seqcount_begin(&kvm->arch.pvclock_sc); +} +static void kvm_start_pvclock_update(struct kvm *kvm) +{ kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); - pvclock_update_vm_gtod_copy(kvm); - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + __kvm_start_pvclock_update(kvm); +} + +static void kvm_end_pvclock_update(struct kvm *kvm) +{ + struct kvm_arch *ka = &kvm->arch; + struct kvm_vcpu *vcpu; + int i; + write_seqcount_end(&ka->pvclock_sc); + raw_spin_unlock_irq(&ka->tsc_write_lock); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); -#endif } -u64 get_kvmclock_ns(struct kvm *kvm) +static void kvm_update_masterclock(struct kvm *kvm) +{ + kvm_hv_invalidate_tsc_page(kvm); + kvm_start_pvclock_update(kvm); + pvclock_update_vm_gtod_copy(kvm); + kvm_end_pvclock_update(kvm); +} + +/* Called within read_seqcount_begin/retry for kvm->pvclock_sc. */ +static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; - unsigned long flags; - u64 ret; - - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); - if (!ka->use_master_clock) { - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); - return get_kvmclock_base_ns() + ka->kvmclock_offset; - } - - hv_clock.tsc_timestamp = ka->master_cycle_now; - hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); - if (__this_cpu_read(cpu_tsc_khz)) { + data->flags = 0; + if (ka->use_master_clock && __this_cpu_read(cpu_tsc_khz)) { +#ifdef CONFIG_X86_64 + struct timespec64 ts; + + if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) { + data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec; + data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC; + } else +#endif + data->host_tsc = rdtsc(); + + data->flags |= KVM_CLOCK_TSC_STABLE; + hv_clock.tsc_timestamp = ka->master_cycle_now; + hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); - ret = __pvclock_read_cycles(&hv_clock, rdtsc()); - } else - ret = get_kvmclock_base_ns() + ka->kvmclock_offset; + data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); + } else { + data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset; + } put_cpu(); +} - return ret; +static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) +{ + struct kvm_arch *ka = &kvm->arch; + unsigned seq; + + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + __get_kvmclock(kvm, data); + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); +} + +u64 get_kvmclock_ns(struct kvm *kvm) +{ + struct kvm_clock_data data; + + get_kvmclock(kvm, &data); + return data.clock; } static void kvm_setup_pvclock_page(struct kvm_vcpu *v, @@ -2881,6 +2952,7 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v, static int kvm_guest_time_update(struct kvm_vcpu *v) { unsigned long flags, tgt_tsc_khz; + unsigned seq; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; @@ -2895,13 +2967,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); - use_master_clock = ka->use_master_clock; - if (use_master_clock) { - host_tsc = ka->master_cycle_now; - kernel_ns = ka->master_kernel_ns; - } - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + use_master_clock = ka->use_master_clock; + if (use_master_clock) { + host_tsc = ka->master_cycle_now; + kernel_ns = ka->master_kernel_ns; + } + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); @@ -2969,7 +3042,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (v == kvm_get_vcpu(v->kvm, 0)) + if (!v->vcpu_idx) kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -3172,15 +3245,14 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) ++vcpu->stat.tlb_flush; if (!tdp_enabled) { - /* + /* * A TLB flush on behalf of the guest is equivalent to * INVPCID(all), toggling CR4.PGE, etc., which requires - * a forced sync of the shadow page tables. Unload the - * entire MMU here and the subsequent load will sync the - * shadow page tables, and also flush the TLB. + * a forced sync of the shadow page tables. Ensure all the + * roots are synced and the guest TLB in hardware is clean. */ - kvm_mmu_unload(vcpu); - return; + kvm_mmu_sync_roots(vcpu); + kvm_mmu_sync_prev_roots(vcpu); } static_call(kvm_x86_tlb_flush_guest)(vcpu); @@ -4021,6 +4093,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: + case KVM_CAP_VCPU_ATTRIBUTES: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4041,7 +4114,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_SYNC_X86_VALID_FIELDS; break; case KVM_CAP_ADJUST_CLOCK: - r = KVM_CLOCK_TSC_STABLE; + r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE | @@ -4070,7 +4143,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; break; case KVM_CAP_MAX_VCPU_ID: - r = KVM_MAX_VCPU_ID; + r = KVM_MAX_VCPU_IDS; break; case KVM_CAP_PV_MMU: /* obsolete */ r = 0; @@ -4693,144 +4766,27 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return 0; } -#define XSTATE_COMPACTION_ENABLED (1ULL << 63) - -static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) -{ - struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave; - u64 xstate_bv = xsave->header.xfeatures; - u64 valid; - - /* - * Copy legacy XSAVE area, to avoid complications with CPUID - * leaves 0 and 1 in the loop below. - */ - memcpy(dest, xsave, XSAVE_HDR_OFFSET); - - /* Set XSTATE_BV */ - xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; - *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; - - /* - * Copy each region from the possibly compacted offset to the - * non-compacted offset. - */ - valid = xstate_bv & ~XFEATURE_MASK_FPSSE; - while (valid) { - u32 size, offset, ecx, edx; - u64 xfeature_mask = valid & -valid; - int xfeature_nr = fls64(xfeature_mask) - 1; - void *src; - - cpuid_count(XSTATE_CPUID, xfeature_nr, - &size, &offset, &ecx, &edx); - - if (xfeature_nr == XFEATURE_PKRU) { - memcpy(dest + offset, &vcpu->arch.pkru, - sizeof(vcpu->arch.pkru)); - } else { - src = get_xsave_addr(xsave, xfeature_nr); - if (src) - memcpy(dest + offset, src, size); - } - - valid -= xfeature_mask; - } -} - -static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) -{ - struct xregs_state *xsave = &vcpu->arch.guest_fpu->state.xsave; - u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET); - u64 valid; - - /* - * Copy legacy XSAVE area, to avoid complications with CPUID - * leaves 0 and 1 in the loop below. - */ - memcpy(xsave, src, XSAVE_HDR_OFFSET); - - /* Set XSTATE_BV and possibly XCOMP_BV. */ - xsave->header.xfeatures = xstate_bv; - if (boot_cpu_has(X86_FEATURE_XSAVES)) - xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; - - /* - * Copy each region from the non-compacted offset to the - * possibly compacted offset. - */ - valid = xstate_bv & ~XFEATURE_MASK_FPSSE; - while (valid) { - u32 size, offset, ecx, edx; - u64 xfeature_mask = valid & -valid; - int xfeature_nr = fls64(xfeature_mask) - 1; - - cpuid_count(XSTATE_CPUID, xfeature_nr, - &size, &offset, &ecx, &edx); - - if (xfeature_nr == XFEATURE_PKRU) { - memcpy(&vcpu->arch.pkru, src + offset, - sizeof(vcpu->arch.pkru)); - } else { - void *dest = get_xsave_addr(xsave, xfeature_nr); - - if (dest) - memcpy(dest, src + offset, size); - } - - valid -= xfeature_mask; - } -} - static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - if (!vcpu->arch.guest_fpu) + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return; - if (boot_cpu_has(X86_FEATURE_XSAVE)) { - memset(guest_xsave, 0, sizeof(struct kvm_xsave)); - fill_xsave((u8 *) guest_xsave->region, vcpu); - } else { - memcpy(guest_xsave->region, - &vcpu->arch.guest_fpu->state.fxsave, - sizeof(struct fxregs_state)); - *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = - XFEATURE_MASK_FPSSE; - } + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, + guest_xsave->region, + sizeof(guest_xsave->region), + vcpu->arch.pkru); } -#define XSAVE_MXCSR_OFFSET 24 - static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - u64 xstate_bv; - u32 mxcsr; - - if (!vcpu->arch.guest_fpu) + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return 0; - xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; - mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; - - if (boot_cpu_has(X86_FEATURE_XSAVE)) { - /* - * Here we allow setting states that are not present in - * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility - * with old userspace. - */ - if (xstate_bv & ~supported_xcr0 || mxcsr & ~mxcsr_feature_mask) - return -EINVAL; - load_xsave(vcpu, (u8 *)guest_xsave->region); - } else { - if (xstate_bv & ~XFEATURE_MASK_FPSSE || - mxcsr & ~mxcsr_feature_mask) - return -EINVAL; - memcpy(&vcpu->arch.guest_fpu->state.fxsave, - guest_xsave->region, sizeof(struct fxregs_state)); - } - return 0; + return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, + guest_xsave->region, + supported_xcr0, &vcpu->arch.pkru); } static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, @@ -4885,6 +4841,115 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) return 0; } +static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + int r; + + switch (attr->attr) { + case KVM_VCPU_TSC_OFFSET: + r = 0; + break; + default: + r = -ENXIO; + } + + return r; +} + +static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + int r; + + if ((u64)(unsigned long)uaddr != attr->addr) + return -EFAULT; + + switch (attr->attr) { + case KVM_VCPU_TSC_OFFSET: + r = -EFAULT; + if (put_user(vcpu->arch.l1_tsc_offset, uaddr)) + break; + r = 0; + break; + default: + r = -ENXIO; + } + + return r; +} + +static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + struct kvm *kvm = vcpu->kvm; + int r; + + if ((u64)(unsigned long)uaddr != attr->addr) + return -EFAULT; + + switch (attr->attr) { + case KVM_VCPU_TSC_OFFSET: { + u64 offset, tsc, ns; + unsigned long flags; + bool matched; + + r = -EFAULT; + if (get_user(offset, uaddr)) + break; + + raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); + + matched = (vcpu->arch.virtual_tsc_khz && + kvm->arch.last_tsc_khz == vcpu->arch.virtual_tsc_khz && + kvm->arch.last_tsc_offset == offset); + + tsc = kvm_scale_tsc(vcpu, rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; + ns = get_kvmclock_base_ns(); + + __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + + r = 0; + break; + } + default: + r = -ENXIO; + } + + return r; +} + +static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, + unsigned int ioctl, + void __user *argp) +{ + struct kvm_device_attr attr; + int r; + + if (copy_from_user(&attr, argp, sizeof(attr))) + return -EFAULT; + + if (attr.group != KVM_VCPU_TSC_CTRL) + return -ENXIO; + + switch (ioctl) { + case KVM_HAS_DEVICE_ATTR: + r = kvm_arch_tsc_has_attr(vcpu, &attr); + break; + case KVM_GET_DEVICE_ATTR: + r = kvm_arch_tsc_get_attr(vcpu, &attr); + break; + case KVM_SET_DEVICE_ATTR: + r = kvm_arch_tsc_set_attr(vcpu, &attr); + break; + } + + return r; +} + static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { @@ -5339,6 +5404,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = __set_sregs2(vcpu, u.sregs2); break; } + case KVM_HAS_DEVICE_ATTR: + case KVM_GET_DEVICE_ATTR: + case KVM_SET_DEVICE_ATTR: + r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp); + break; default: r = -EINVAL; } @@ -5822,6 +5892,63 @@ int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ +static int kvm_vm_ioctl_get_clock(struct kvm *kvm, void __user *argp) +{ + struct kvm_clock_data data = { 0 }; + + get_kvmclock(kvm, &data); + if (copy_to_user(argp, &data, sizeof(data))) + return -EFAULT; + + return 0; +} + +static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) +{ + struct kvm_arch *ka = &kvm->arch; + struct kvm_clock_data data; + u64 now_raw_ns; + + if (copy_from_user(&data, argp, sizeof(data))) + return -EFAULT; + + /* + * Only KVM_CLOCK_REALTIME is used, but allow passing the + * result of KVM_GET_CLOCK back to KVM_SET_CLOCK. + */ + if (data.flags & ~KVM_CLOCK_VALID_FLAGS) + return -EINVAL; + + kvm_hv_invalidate_tsc_page(kvm); + kvm_start_pvclock_update(kvm); + pvclock_update_vm_gtod_copy(kvm); + + /* + * This pairs with kvm_guest_time_update(): when masterclock is + * in use, we use master_kernel_ns + kvmclock_offset to set + * unsigned 'system_time' so if we use get_kvmclock_ns() (which + * is slightly ahead) here we risk going negative on unsigned + * 'system_time' when 'data.clock' is very small. + */ + if (data.flags & KVM_CLOCK_REALTIME) { + u64 now_real_ns = ktime_get_real_ns(); + + /* + * Avoid stepping the kvmclock backwards. + */ + if (now_real_ns > data.realtime) + data.clock += now_real_ns - data.realtime; + } + + if (ka->use_master_clock) + now_raw_ns = ka->master_kernel_ns; + else + now_raw_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = data.clock - now_raw_ns; + kvm_end_pvclock_update(kvm); + return 0; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -6065,60 +6192,12 @@ set_pit2_out: break; } #endif - case KVM_SET_CLOCK: { - struct kvm_arch *ka = &kvm->arch; - struct kvm_clock_data user_ns; - u64 now_ns; - - r = -EFAULT; - if (copy_from_user(&user_ns, argp, sizeof(user_ns))) - goto out; - - r = -EINVAL; - if (user_ns.flags) - goto out; - - r = 0; - /* - * TODO: userspace has to take care of races with VCPU_RUN, so - * kvm_gen_update_masterclock() can be cut down to locked - * pvclock_update_vm_gtod_copy(). - */ - kvm_gen_update_masterclock(kvm); - - /* - * This pairs with kvm_guest_time_update(): when masterclock is - * in use, we use master_kernel_ns + kvmclock_offset to set - * unsigned 'system_time' so if we use get_kvmclock_ns() (which - * is slightly ahead) here we risk going negative on unsigned - * 'system_time' when 'user_ns.clock' is very small. - */ - spin_lock_irq(&ka->pvclock_gtod_sync_lock); - if (kvm->arch.use_master_clock) - now_ns = ka->master_kernel_ns; - else - now_ns = get_kvmclock_base_ns(); - ka->kvmclock_offset = user_ns.clock - now_ns; - spin_unlock_irq(&ka->pvclock_gtod_sync_lock); - - kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); + case KVM_SET_CLOCK: + r = kvm_vm_ioctl_set_clock(kvm, argp); break; - } - case KVM_GET_CLOCK: { - struct kvm_clock_data user_ns; - u64 now_ns; - - now_ns = get_kvmclock_ns(kvm); - user_ns.clock = now_ns; - user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0; - memset(&user_ns.pad, 0, sizeof(user_ns.pad)); - - r = -EFAULT; - if (copy_to_user(argp, &user_ns, sizeof(user_ns))) - goto out; - r = 0; + case KVM_GET_CLOCK: + r = kvm_vm_ioctl_get_clock(kvm, argp); break; - } case KVM_MEMORY_ENCRYPT_OP: { r = -ENOTTY; if (kvm_x86_ops.mem_enc_op) @@ -6899,7 +6978,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) } static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, + unsigned short port, unsigned int count, bool in) { vcpu->arch.pio.port = port; @@ -6907,10 +6986,8 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - vcpu->arch.pio.count = 0; + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) return 1; - } vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; @@ -6922,26 +6999,39 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, return 0; } -static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, - unsigned short port, void *val, unsigned int count) +static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, unsigned int count) { - int ret; + WARN_ON(vcpu->arch.pio.count); + memset(vcpu->arch.pio_data, 0, size * count); + return emulator_pio_in_out(vcpu, size, port, count, true); +} - if (vcpu->arch.pio.count) - goto data_avail; +static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val) +{ + int size = vcpu->arch.pio.size; + unsigned count = vcpu->arch.pio.count; + memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data); + vcpu->arch.pio.count = 0; +} - memset(vcpu->arch.pio_data, 0, size * count); +static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, unsigned int count) +{ + if (vcpu->arch.pio.count) { + /* Complete previous iteration. */ + } else { + int r = __emulator_pio_in(vcpu, size, port, count); + if (!r) + return r; - ret = emulator_pio_in_out(vcpu, size, port, val, count, true); - if (ret) { -data_avail: - memcpy(val, vcpu->arch.pio_data, size * count); - trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); - vcpu->arch.pio.count = 0; - return 1; + /* Results already available, fall through. */ } - return 0; + WARN_ON(count != vcpu->arch.pio.count); + complete_emulator_pio_in(vcpu, val); + return 1; } static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, @@ -6956,9 +7046,15 @@ static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port, const void *val, unsigned int count) { + int ret; + memcpy(vcpu->arch.pio_data, val, size * count); trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); - return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); + ret = emulator_pio_in_out(vcpu, size, port, count, false); + if (ret) + vcpu->arch.pio.count = 0; + + return ret; } static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, @@ -7468,29 +7564,78 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); -static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata, u8 *insn_bytes, u8 insn_size) { - struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; - u32 insn_size = ctxt->fetch.end - ctxt->fetch.data; struct kvm_run *run = vcpu->run; + u64 info[5]; + u8 info_start; + + /* + * Zero the whole array used to retrieve the exit info, as casting to + * u32 for select entries will leave some chunks uninitialized. + */ + memset(&info, 0, sizeof(info)); + + static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1], + &info[2], (u32 *)&info[3], + (u32 *)&info[4]); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; - run->emulation_failure.ndata = 0; + + /* + * There's currently space for 13 entries, but 5 are used for the exit + * reason and info. Restrict to 4 to reduce the maintenance burden + * when expanding kvm_run.emulation_failure in the future. + */ + if (WARN_ON_ONCE(ndata > 4)) + ndata = 4; + + /* Always include the flags as a 'data' entry. */ + info_start = 1; run->emulation_failure.flags = 0; if (insn_size) { - run->emulation_failure.ndata = 3; + BUILD_BUG_ON((sizeof(run->emulation_failure.insn_size) + + sizeof(run->emulation_failure.insn_bytes) != 16)); + info_start += 2; run->emulation_failure.flags |= KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; run->emulation_failure.insn_size = insn_size; memset(run->emulation_failure.insn_bytes, 0x90, sizeof(run->emulation_failure.insn_bytes)); - memcpy(run->emulation_failure.insn_bytes, - ctxt->fetch.data, insn_size); + memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size); } + + memcpy(&run->internal.data[info_start], info, sizeof(info)); + memcpy(&run->internal.data[info_start + ARRAY_SIZE(info)], data, + ndata * sizeof(data[0])); + + run->emulation_failure.ndata = info_start + ARRAY_SIZE(info) + ndata; } +static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + + prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data, + ctxt->fetch.end - ctxt->fetch.data); +} + +void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata) +{ + prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0); +} +EXPORT_SYMBOL_GPL(__kvm_prepare_emulation_failure_exit); + +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + __kvm_prepare_emulation_failure_exit(vcpu, NULL, 0); +} +EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit); + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; @@ -7505,16 +7650,14 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) if (kvm->arch.exit_on_emulation_error || (emulation_type & EMULTYPE_SKIP)) { - prepare_emulation_failure_exit(vcpu); + prepare_emulation_ctxt_failure_exit(vcpu); return 0; } kvm_queue_exception(vcpu, UD_VECTOR); if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + prepare_emulation_ctxt_failure_exit(vcpu); return 0; } @@ -7658,6 +7801,13 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) /* Process a latched INIT or SMI, if any. */ kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, + * on SMM exit we still need to reload them from + * guest memory + */ + vcpu->arch.pdptrs_from_userspace = false; } kvm_mmu_reset_context(vcpu); @@ -8107,14 +8257,13 @@ static void tsc_khz_changed(void *data) static void kvm_hyperv_tsc_notifier(void) { struct kvm *kvm; - struct kvm_vcpu *vcpu; int cpu; - unsigned long flags; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ hyperv_stop_tsc_emulation(); /* TSC frequency always matches when on Hyper-V */ @@ -8123,18 +8272,11 @@ static void kvm_hyperv_tsc_notifier(void) kvm_max_guest_tsc_khz = tsc_khz; list_for_each_entry(kvm, &vm_list, vm_list) { - struct kvm_arch *ka = &kvm->arch; - - spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); + __kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); - spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); - - kvm_for_each_vcpu(cpu, vcpu, kvm) - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - - kvm_for_each_vcpu(cpu, vcpu, kvm) - kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); + kvm_end_pvclock_update(kvm); } + mutex_unlock(&kvm_lock); } #endif @@ -8375,18 +8517,20 @@ int kvm_arch_init(void *opaque) int r; if (kvm_x86_ops.hardware_enable) { - printk(KERN_ERR "kvm: already loaded the other module\n"); + pr_err("kvm: already loaded vendor module '%s'\n", kvm_x86_ops.name); r = -EEXIST; goto out; } if (!ops->cpu_has_kvm_support()) { - pr_err_ratelimited("kvm: no hardware support\n"); + pr_err_ratelimited("kvm: no hardware support for '%s'\n", + ops->runtime_ops->name); r = -EOPNOTSUPP; goto out; } if (ops->disabled_by_bios()) { - pr_err_ratelimited("kvm: disabled by bios\n"); + pr_err_ratelimited("kvm: support for '%s' disabled by bios\n", + ops->runtime_ops->name); r = -EOPNOTSUPP; goto out; } @@ -8403,18 +8547,11 @@ int kvm_arch_init(void *opaque) } r = -ENOMEM; - x86_fpu_cache = kmem_cache_create("x86_fpu", sizeof(struct fpu), - __alignof__(struct fpu), SLAB_ACCOUNT, - NULL); - if (!x86_fpu_cache) { - printk(KERN_ERR "kvm: failed to allocate cache for x86 fpu\n"); - goto out; - } x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { pr_err("kvm: failed to allocate cache for x86 emulator\n"); - goto out_free_x86_fpu_cache; + goto out; } user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); @@ -8452,8 +8589,6 @@ out_free_percpu: free_percpu(user_return_msrs); out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); -out_free_x86_fpu_cache: - kmem_cache_destroy(x86_fpu_cache); out: return r; } @@ -8480,7 +8615,6 @@ void kvm_arch_exit(void) kvm_mmu_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); - kmem_cache_destroy(x86_fpu_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); @@ -8581,7 +8715,7 @@ EXPORT_SYMBOL_GPL(kvm_apicv_activated); static void kvm_apicv_init(struct kvm *kvm) { - mutex_init(&kvm->arch.apicv_update_lock); + init_rwsem(&kvm->arch.apicv_update_lock); if (enable_apicv) clear_bit(APICV_INHIBIT_REASON_DISABLE, @@ -8769,9 +8903,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); + + /* + * The call to kvm_ready_for_interrupt_injection() may end up in + * kvm_xen_has_interrupt() which may require the srcu lock to be + * held, to protect against changes in the vcpu_info address. + */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -9228,14 +9370,7 @@ static void process_smi(struct kvm_vcpu *vcpu) void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap) { - cpumask_var_t cpus; - - zalloc_cpumask_var(&cpus, GFP_ATOMIC); - - kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, - NULL, vcpu_bitmap, cpus); - - free_cpumask_var(cpus); + kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, vcpu_bitmap); } void kvm_make_scan_ioapic_request(struct kvm *kvm) @@ -9250,7 +9385,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; - mutex_lock(&vcpu->kvm->arch.apicv_update_lock); + down_read(&vcpu->kvm->arch.apicv_update_lock); activate = kvm_apicv_activated(vcpu->kvm); if (vcpu->arch.apicv_active == activate) @@ -9270,7 +9405,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); out: - mutex_unlock(&vcpu->kvm->arch.apicv_update_lock); + up_read(&vcpu->kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -9278,6 +9413,8 @@ void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) { unsigned long old, new; + lockdep_assert_held_write(&kvm->arch.apicv_update_lock); + if (!kvm_x86_ops.check_apicv_inhibit_reasons || !static_call(kvm_x86_check_apicv_inhibit_reasons)(bit)) return; @@ -9291,6 +9428,18 @@ void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) if (!!old != !!new) { trace_kvm_apicv_update_request(activate, bit); + /* + * Kick all vCPUs before setting apicv_inhibit_reasons to avoid + * false positives in the sanity check WARN in svm_vcpu_run(). + * This task will wait for all vCPUs to ack the kick IRQ before + * updating apicv_inhibit_reasons, and all other vCPUs will + * block on acquiring apicv_update_lock so that vCPUs can't + * redo svm_vcpu_run() without seeing the new inhibit state. + * + * Note, holding apicv_update_lock and taking it in the read + * side (handling the request) also prevents other vCPUs from + * servicing the request with a stale apicv_inhibit_reasons. + */ kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); kvm->arch.apicv_inhibit_reasons = new; if (new) { @@ -9304,9 +9453,9 @@ EXPORT_SYMBOL_GPL(__kvm_request_apicv_update); void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) { - mutex_lock(&kvm->arch.apicv_update_lock); + down_write(&kvm->arch.apicv_update_lock); __kvm_request_apicv_update(kvm, activate, bit); - mutex_unlock(&kvm->arch.apicv_update_lock); + up_write(&kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_GPL(kvm_request_apicv_update); @@ -9418,7 +9567,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) __kvm_migrate_timers(vcpu); if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) - kvm_gen_update_masterclock(vcpu->kvm); + kvm_update_masterclock(vcpu->kvm); if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu)) kvm_gen_kvmclock_update(vcpu); if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { @@ -9625,18 +9774,26 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } for (;;) { + /* + * Assert that vCPU vs. VM APICv state is consistent. An APICv + * update must kick and wait for all vCPUs before toggling the + * per-VM state, and responsing vCPUs must wait for the update + * to complete before servicing KVM_REQ_APICV_UPDATE. + */ + WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu)); + exit_fastpath = static_call(kvm_x86_run)(vcpu); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; - if (unlikely(kvm_vcpu_exit_request(vcpu))) { + if (vcpu->arch.apicv_active) + static_call(kvm_x86_sync_pir_to_irr)(vcpu); + + if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; break; } - - if (vcpu->arch.apicv_active) - static_call(kvm_x86_sync_pir_to_irr)(vcpu); - } + } /* * Do this here before restoring debug registers on the host. And @@ -9899,58 +10056,21 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } -static void kvm_save_current_fpu(struct fpu *fpu) -{ - /* - * If the target FPU state is not resident in the CPU registers, just - * memcpy() from current, else save CPU state directly to the target. - */ - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - memcpy(&fpu->state, ¤t->thread.fpu.state, - fpu_kernel_xstate_size); - else - save_fpregs_to_fpstate(fpu); -} - /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { - fpregs_lock(); - - kvm_save_current_fpu(vcpu->arch.user_fpu); - /* - * Guests with protected state can't have it set by the hypervisor, - * so skip trying to set it. + * Exclude PKRU from restore as restored separately in + * kvm_x86_ops.run(). */ - if (vcpu->arch.guest_fpu) - /* PKRU is separately restored in kvm_x86_ops.run. */ - __restore_fpregs_from_fpstate(&vcpu->arch.guest_fpu->state, - ~XFEATURE_MASK_PKRU); - - fpregs_mark_activate(); - fpregs_unlock(); - + fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true); trace_kvm_fpu(1); } /* When vcpu_run ends, restore user space FPU context. */ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - fpregs_lock(); - - /* - * Guests with protected state can't have it read by the hypervisor, - * so skip trying to save it. - */ - if (vcpu->arch.guest_fpu) - kvm_save_current_fpu(vcpu->arch.guest_fpu); - - restore_fpregs_from_fpstate(&vcpu->arch.user_fpu->state); - - fpregs_mark_activate(); - fpregs_unlock(); - + fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false); ++vcpu->stat.fpu_reload; trace_kvm_fpu(0); } @@ -10531,12 +10651,12 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; - if (!vcpu->arch.guest_fpu) + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return 0; vcpu_load(vcpu); - fxsave = &vcpu->arch.guest_fpu->state.fxsave; + fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; fpu->fsw = fxsave->swd; @@ -10554,12 +10674,12 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; - if (!vcpu->arch.guest_fpu) + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return 0; vcpu_load(vcpu); - fxsave = &vcpu->arch.guest_fpu->state.fxsave; + fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -10610,33 +10730,6 @@ static int sync_regs(struct kvm_vcpu *vcpu) return 0; } -static void fx_init(struct kvm_vcpu *vcpu) -{ - if (!vcpu->arch.guest_fpu) - return; - - fpstate_init(&vcpu->arch.guest_fpu->state); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv = - host_xcr0 | XSTATE_COMPACTION_ENABLED; - - /* - * Ensure guest xcr0 is valid for loading - */ - vcpu->arch.xcr0 = XFEATURE_MASK_FP; - - vcpu->arch.cr0 |= X86_CR0_ET; -} - -void kvm_free_guest_fpu(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.guest_fpu) { - kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); - vcpu->arch.guest_fpu = NULL; - } -} -EXPORT_SYMBOL_GPL(kvm_free_guest_fpu); - int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) @@ -10652,6 +10745,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) int r; vcpu->arch.last_vmentry_cpu = -1; + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -10691,20 +10786,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (!alloc_emulate_ctxt(vcpu)) goto free_wbinvd_dirty_mask; - vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vcpu->arch.user_fpu) { - pr_err("kvm: failed to allocate userspace's fpu\n"); - goto free_emulate_ctxt; - } - - vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vcpu->arch.guest_fpu) { + if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) { pr_err("kvm: failed to allocate vcpu's fpu\n"); - goto free_user_fpu; + goto free_emulate_ctxt; } - fx_init(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); @@ -10736,9 +10821,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) return 0; free_guest_fpu: - kvm_free_guest_fpu(vcpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); + fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); free_emulate_ctxt: kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_wbinvd_dirty_mask: @@ -10787,8 +10870,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); - kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); - kvm_free_guest_fpu(vcpu); + fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); kvm_hv_vcpu_uninit(vcpu); kvm_pmu_destroy(vcpu); @@ -10805,9 +10887,19 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + struct kvm_cpuid_entry2 *cpuid_0x1; unsigned long old_cr0 = kvm_read_cr0(vcpu); unsigned long new_cr0; - u32 eax, dummy; + + /* + * Several of the "set" flows, e.g. ->set_cr0(), read other registers + * to handle side effects. RESET emulation hits those flows and relies + * on emulated/virtualized registers, including those that are loaded + * into hardware, to be zeroed at vCPU creation. Use CRs as a sentinel + * to detect improper or missing initialization. + */ + WARN_ON_ONCE(!init_event && + (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); kvm_lapic_reset(vcpu, init_event); @@ -10840,8 +10932,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - if (vcpu->arch.guest_fpu && kvm_mpx_supported()) { - void *mpx_state_buffer; + if (vcpu->arch.guest_fpu.fpstate && kvm_mpx_supported()) { + struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; /* * To avoid have the INIT path from kvm_apic_has_events() that be @@ -10849,14 +10941,10 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) */ if (init_event) kvm_put_guest_fpu(vcpu); - mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave, - XFEATURE_BNDREGS); - if (mpx_state_buffer) - memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state)); - mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu->state.xsave, - XFEATURE_BNDCSR); - if (mpx_state_buffer) - memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr)); + + fpstate_clear_xstate_component(fpstate, XFEATURE_BNDREGS); + fpstate_clear_xstate_component(fpstate, XFEATURE_BNDCSR); + if (init_event) kvm_load_guest_fpu(vcpu); } @@ -10870,21 +10958,19 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.xcr0 = XFEATURE_MASK_FP; } + /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); - vcpu->arch.regs_avail = ~0; - vcpu->arch.regs_dirty = ~0; + kvm_register_mark_dirty(vcpu, VCPU_REGS_RSP); /* * Fall back to KVM's default Family/Model/Stepping of 0x600 (P6/Athlon) * if no CPUID match is found. Note, it's impossible to get a match at * RESET since KVM emulates RESET before exposing the vCPU to userspace, - * i.e. it'simpossible for kvm_cpuid() to find a valid entry on RESET. - * But, go through the motions in case that's ever remedied. + * i.e. it's impossible for kvm_find_cpuid_entry() to find a valid entry + * on RESET. But, go through the motions in case that's ever remedied. */ - eax = 1; - if (!kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true)) - eax = 0x600; - kvm_rdx_write(vcpu, eax); + cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1, 0); + kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); vcpu->arch.ia32_xss = 0; @@ -10893,6 +10979,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); + vcpu->arch.cr3 = 0; + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + /* * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions * of Intel's SDM list CD/NW as being set on INIT, but they contradict @@ -11133,15 +11222,22 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_free_vm(struct kvm *kvm) { kfree(to_kvm_hv(kvm)->hv_pa_pg); - vfree(kvm); + __kvm_arch_free_vm(kvm); } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { + int ret; + unsigned long flags; + if (type) return -EINVAL; + ret = kvm_page_track_init(kvm); + if (ret) + return ret; + INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); @@ -11157,10 +11253,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); - spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); - + seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock); kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); + + raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); pvclock_update_vm_gtod_copy(kvm); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); kvm->arch.guest_can_read_msr_platform_info = true; @@ -11174,7 +11272,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); - kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); kvm_xen_init_vm(kvm); @@ -11358,8 +11455,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) kvm_page_track_free_memslot(slot); } -static int memslot_rmap_alloc(struct kvm_memory_slot *slot, - unsigned long npages) +int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) { const int sz = sizeof(*slot->arch.rmap[0]); int i; @@ -11368,7 +11464,8 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot, int level = i + 1; int lpages = __kvm_mmu_slot_lpages(slot, npages, level); - WARN_ON(slot->arch.rmap[i]); + if (slot->arch.rmap[i]) + continue; slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) { @@ -11380,50 +11477,6 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot, return 0; } -int alloc_all_memslots_rmaps(struct kvm *kvm) -{ - struct kvm_memslots *slots; - struct kvm_memory_slot *slot; - int r, i; - - /* - * Check if memslots alreday have rmaps early before acquiring - * the slots_arch_lock below. - */ - if (kvm_memslots_have_rmaps(kvm)) - return 0; - - mutex_lock(&kvm->slots_arch_lock); - - /* - * Read memslots_have_rmaps again, under the slots arch lock, - * before allocating the rmaps - */ - if (kvm_memslots_have_rmaps(kvm)) { - mutex_unlock(&kvm->slots_arch_lock); - return 0; - } - - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { - r = memslot_rmap_alloc(slot, slot->npages); - if (r) { - mutex_unlock(&kvm->slots_arch_lock); - return r; - } - } - } - - /* - * Ensure that memslots_have_rmaps becomes true strictly after - * all the rmap pointers are set. - */ - smp_store_release(&kvm->arch.memslots_have_rmaps, true); - mutex_unlock(&kvm->slots_arch_lock); - return 0; -} - static int kvm_alloc_memslot_metadata(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages) @@ -11474,7 +11527,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, } } - if (kvm_page_track_create_memslot(slot, npages)) + if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; return 0; @@ -12072,6 +12125,15 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, return static_call(kvm_x86_update_pi_irte)(kvm, host_irq, guest_irq, set); } +bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) +{ + if (new->type != KVM_IRQ_ROUTING_MSI) + return true; + + return !!memcmp(&old->msi, &new->msi, sizeof(new->msi)); +} + bool kvm_vector_hashing_enabled(void) { return vector_hashing; @@ -12153,9 +12215,7 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, * doesn't seem to be a real use-case behind such requests, just return * KVM_EXIT_INTERNAL_ERROR for now. */ - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } @@ -12343,44 +12403,81 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes, } EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read); -static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port); + +static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu) { - memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data, - vcpu->arch.pio.count * vcpu->arch.pio.size); - vcpu->arch.pio.count = 0; + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + vcpu->arch.pio.count = 0; + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_outs(vcpu, size, port); return 1; } static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, - unsigned int port, void *data, unsigned int count) + unsigned int port) { - int ret; - - ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port, - data, count); - if (ret) - return ret; + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count); + + /* memcpy done already by emulator_pio_out. */ + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; + if (!ret) + break; - vcpu->arch.pio.count = 0; + /* Emulation done by the kernel. */ + if (!vcpu->arch.sev_pio_count) + return 1; + } + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs; return 0; } static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, - unsigned int port, void *data, unsigned int count) + unsigned int port); + +static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu) { - int ret; + unsigned count = vcpu->arch.pio.count; + complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data); + vcpu->arch.sev_pio_count -= count; + vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size; +} - ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port, - data, count); - if (ret) { - vcpu->arch.pio.count = 0; - } else { - vcpu->arch.guest_ins_data = data; - vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; +static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) +{ + int size = vcpu->arch.pio.size; + int port = vcpu->arch.pio.port; + + advance_sev_es_emulated_ins(vcpu); + if (vcpu->arch.sev_pio_count) + return kvm_sev_es_ins(vcpu, size, port); + return 1; +} + +static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, + unsigned int port) +{ + for (;;) { + unsigned int count = + min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); + if (!__emulator_pio_in(vcpu, size, port, count)) + break; + + /* Emulation done by the kernel. */ + advance_sev_es_emulated_ins(vcpu); + if (!vcpu->arch.sev_pio_count) + return 1; } + vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; return 0; } @@ -12388,8 +12485,10 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port, void *data, unsigned int count, int in) { - return in ? kvm_sev_es_ins(vcpu, size, port, data, count) - : kvm_sev_es_outs(vcpu, size, port, data, count); + vcpu->arch.sev_pio_data = data; + vcpu->arch.sev_pio_count = count; + return in ? kvm_sev_es_ins(vcpu, size, port) + : kvm_sev_es_outs(vcpu, size, port); } EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7d66d63dc55a..ea264c4502e4 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -343,8 +343,6 @@ extern bool enable_vmware_backdoor; extern int pi_inject_timer; -extern struct static_key kvm_no_apic_vcpu; - extern bool report_ignored_msrs; static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 9ea9c3dabe37..8f62baebd028 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -190,6 +190,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) int __kvm_xen_has_interrupt(struct kvm_vcpu *v) { + int err; u8 rc = 0; /* @@ -216,13 +217,29 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) if (likely(slots->generation == ghc->generation && !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { /* Fast path */ - __get_user(rc, (u8 __user *)ghc->hva + offset); - } else { - /* Slow path */ - kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, - sizeof(rc)); + pagefault_disable(); + err = __get_user(rc, (u8 __user *)ghc->hva + offset); + pagefault_enable(); + if (!err) + return rc; } + /* Slow path */ + + /* + * This function gets called from kvm_vcpu_block() after setting the + * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately + * from a HLT. So we really mustn't sleep. If the page ended up absent + * at that point, just return 1 in order to trigger an immediate wake, + * and we'll end up getting called again from a context where we *can* + * fault in the page and wait for it. + */ + if (in_atomic() || !task_is_running(current)) + return 1; + + kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, + sizeof(rc)); + return rc; } diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S index e5f77e293034..7334055157ba 100644 --- a/arch/x86/lib/copy_mc_64.S +++ b/arch/x86/lib/copy_mc_64.S @@ -107,9 +107,9 @@ SYM_FUNC_END(copy_mc_fragile) .previous - _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) - _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) - _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) + _ASM_EXTABLE_TYPE(.L_read_leading_bytes, .E_leading_bytes, EX_TYPE_DEFAULT_MCE_SAFE) + _ASM_EXTABLE_TYPE(.L_read_words, .E_read_words, EX_TYPE_DEFAULT_MCE_SAFE) + _ASM_EXTABLE_TYPE(.L_read_trailing_bytes, .E_trailing_bytes, EX_TYPE_DEFAULT_MCE_SAFE) _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) _ASM_EXTABLE(.L_write_words, .E_write_words) _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) @@ -149,5 +149,5 @@ SYM_FUNC_END(copy_mc_enhanced_fast_string) .previous - _ASM_EXTABLE_FAULT(.L_copy, .E_copy) + _ASM_EXTABLE_TYPE(.L_copy, .E_copy, EX_TYPE_DEFAULT_MCE_SAFE) #endif /* !CONFIG_UML */ diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 57b79c577496..2797e630b9b1 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -234,24 +234,11 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string) */ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) movl %edx,%ecx - cmp $X86_TRAP_MC,%eax /* check if X86_TRAP_MC */ - je 3f 1: rep movsb 2: mov %ecx,%eax ASM_CLAC ret - /* - * Return zero to pretend that this copy succeeded. This - * is counter-intuitive, but needed to prevent the code - * in lib/iov_iter.c from retrying and running back into - * the poison cache line again. The machine check handler - * will ensure that a SIGBUS is sent to the task. - */ -3: xorl %eax,%eax - ASM_CLAC - ret - _ASM_EXTABLE_CPY(1b, 2b) SYM_CODE_END(.Lcopy_user_handle_tail) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index a1d24fdc07cf..eb3ccffb9b9d 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1417,7 +1417,7 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) } } -static int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip) +int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip) { unsigned long seg_base = 0; diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 058f19b20465..55e371cc69fd 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -13,6 +13,7 @@ #endif #include <asm/inat.h> /*__ignore_sync_check__ */ #include <asm/insn.h> /* __ignore_sync_check__ */ +#include <asm/unaligned.h> /* __ignore_sync_check__ */ #include <linux/errno.h> #include <linux/kconfig.h> @@ -37,10 +38,10 @@ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) + ({ t r = get_unaligned((t *)(insn)->next_byte); (insn)->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); }) + ({ t r = get_unaligned((t *)(insn)->next_byte + n); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index a53665116458..2b3eb8c948a3 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -56,11 +56,14 @@ unsigned long kaslr_get_random_long(const char *purpose) unsigned long raw, random = get_boot_seed(); bool use_i8254 = true; - debug_putstr(purpose); - debug_putstr(" KASLR using"); + if (purpose) { + debug_putstr(purpose); + debug_putstr(" KASLR using"); + } if (has_cpuflag(X86_FEATURE_RDRAND)) { - debug_putstr(" RDRAND"); + if (purpose) + debug_putstr(" RDRAND"); if (rdrand_long(&raw)) { random ^= raw; use_i8254 = false; @@ -68,7 +71,8 @@ unsigned long kaslr_get_random_long(const char *purpose) } if (has_cpuflag(X86_FEATURE_TSC)) { - debug_putstr(" RDTSC"); + if (purpose) + debug_putstr(" RDTSC"); raw = rdtsc(); random ^= raw; @@ -76,7 +80,8 @@ unsigned long kaslr_get_random_long(const char *purpose) } if (use_i8254) { - debug_putstr(" i8254"); + if (purpose) + debug_putstr(" i8254"); random ^= i8254(); } @@ -86,7 +91,8 @@ unsigned long kaslr_get_random_long(const char *purpose) : "a" (random), "rm" (mix_const)); random += raw; - debug_putstr("...\n"); + if (purpose) + debug_putstr("...\n"); return random; } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index ec9922cba30a..cf0b39f97adc 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -28,46 +28,14 @@ .macro THUNK reg - .align 32 - -SYM_FUNC_START(__x86_indirect_thunk_\reg) + .align RETPOLINE_THUNK_SIZE +SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_EMPTY ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD -SYM_FUNC_END(__x86_indirect_thunk_\reg) - -.endm - -/* - * This generates .altinstr_replacement symbols for use by objtool. They, - * however, must not actually live in .altinstr_replacement since that will be - * discarded after init, but module alternatives will also reference these - * symbols. - * - * Their names matches the "__x86_indirect_" prefix to mark them as retpolines. - */ -.macro ALT_THUNK reg - - .align 1 - -SYM_FUNC_START_NOALIGN(__x86_indirect_alt_call_\reg) - ANNOTATE_RETPOLINE_SAFE -1: call *%\reg -2: .skip 5-(2b-1b), 0x90 -SYM_FUNC_END(__x86_indirect_alt_call_\reg) - -STACK_FRAME_NON_STANDARD(__x86_indirect_alt_call_\reg) - -SYM_FUNC_START_NOALIGN(__x86_indirect_alt_jmp_\reg) - ANNOTATE_RETPOLINE_SAFE -1: jmp *%\reg -2: .skip 5-(2b-1b), 0x90 -SYM_FUNC_END(__x86_indirect_alt_jmp_\reg) - -STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg) - .endm /* @@ -85,22 +53,16 @@ STACK_FRAME_NON_STANDARD(__x86_indirect_alt_jmp_\reg) #define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) #define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) -#undef GEN + .align RETPOLINE_THUNK_SIZE +SYM_CODE_START(__x86_indirect_thunk_array) + #define GEN(reg) THUNK reg #include <asm/GEN-for-each-reg.h> - #undef GEN -#define GEN(reg) EXPORT_THUNK(reg) -#include <asm/GEN-for-each-reg.h> -#undef GEN -#define GEN(reg) ALT_THUNK reg -#include <asm/GEN-for-each-reg.h> + .align RETPOLINE_THUNK_SIZE +SYM_CODE_END(__x86_indirect_thunk_array) -#undef GEN -#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_call_ ## reg) +#define GEN(reg) EXPORT_THUNK(reg) #include <asm/GEN-for-each-reg.h> - #undef GEN -#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_jmp_ ## reg) -#include <asm/GEN-for-each-reg.h> diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c index d15fdae9656e..53b3f202267c 100644 --- a/arch/x86/lib/string_32.c +++ b/arch/x86/lib/string_32.c @@ -11,6 +11,7 @@ * strings. */ +#define __NO_FORTIFY #include <linux/string.h> #include <linux/export.h> diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index 034748459482..d62662bdd460 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -53,7 +53,7 @@ void fpstate_init_soft(struct swregs_state *soft) void finit(void) { - fpstate_init_soft(¤t->thread.fpu.state.soft); + fpstate_init_soft(¤t->thread.fpu.fpstate->regs.soft); } /* diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 8679a9d6c47f..7fe56c594aa6 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -31,7 +31,7 @@ #include <linux/uaccess.h> #include <asm/traps.h> #include <asm/user.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include "fpu_system.h" #include "fpu_emu.h" @@ -640,7 +640,7 @@ int fpregs_soft_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct swregs_state *s387 = &target->thread.fpu.state.soft; + struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft; void *space = s387->st_space; int ret; int offset, other, i, tags, regnr, tag, newtop; @@ -691,7 +691,7 @@ int fpregs_soft_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { - struct swregs_state *s387 = &target->thread.fpu.state.soft; + struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft; const void *space = s387->st_space; int offset = (S387->ftop & 7) * 10, other = 80 - offset; diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 9b41391867dc..eec3e4805c75 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -73,7 +73,7 @@ static inline bool seg_writable(struct desc_struct *d) return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE; } -#define I387 (¤t->thread.fpu.state) +#define I387 (¤t->thread.fpu.fpstate->regs) #define FPU_info (I387->soft.info) #define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs)) diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index f5e1e60c9095..6c2f1b76a0b6 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -110,6 +110,13 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu) cea_map_stack(NMI); cea_map_stack(DB); cea_map_stack(MCE); + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) { + cea_map_stack(VC); + cea_map_stack(VC2); + } + } } #else static inline void percpu_setup_exception_stacks(unsigned int cpu) diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index e1664e9f969c..5cd2a88930a9 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -4,46 +4,30 @@ #include <linux/sched/debug.h> #include <xen/xen.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> -typedef bool (*ex_handler_t)(const struct exception_table_entry *, - struct pt_regs *, int, unsigned long, - unsigned long); - static inline unsigned long ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } -static inline ex_handler_t -ex_fixup_handler(const struct exception_table_entry *x) -{ - return (ex_handler_t)((unsigned long)&x->handler + x->handler); -} -__visible bool ex_handler_default(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_default(const struct exception_table_entry *fixup, + struct pt_regs *regs) { regs->ip = ex_fixup_addr(fixup); return true; } -EXPORT_SYMBOL(ex_handler_default); -__visible bool ex_handler_fault(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) { - regs->ip = ex_fixup_addr(fixup); regs->ax = trapnr; - return true; + return ex_handler_default(fixup, regs); } -EXPORT_SYMBOL_GPL(ex_handler_fault); /* * Handler for when we fail to restore a task's FPU state. We should never get @@ -55,65 +39,47 @@ EXPORT_SYMBOL_GPL(ex_handler_fault); * of vulnerability by restoring from the initial state (essentially, zeroing * out all the FPU registers) if we can't restore from the task's FPU state. */ -__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_fprestore(const struct exception_table_entry *fixup, + struct pt_regs *regs) { regs->ip = ex_fixup_addr(fixup); WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); - __restore_fpregs_from_fpstate(&init_fpstate, xfeatures_mask_fpstate()); + fpu_reset_from_exception_fixup(); return true; } -EXPORT_SYMBOL_GPL(ex_handler_fprestore); -__visible bool ex_handler_uaccess(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_uaccess(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) { WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?"); - regs->ip = ex_fixup_addr(fixup); - return true; + return ex_handler_default(fixup, regs); } -EXPORT_SYMBOL(ex_handler_uaccess); -__visible bool ex_handler_copy(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_copy(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) { WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?"); - regs->ip = ex_fixup_addr(fixup); - regs->ax = trapnr; - return true; + return ex_handler_fault(fixup, regs, trapnr); } -EXPORT_SYMBOL(ex_handler_copy); -__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, + struct pt_regs *regs) { if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, regs->ip, (void *)regs->ip)) show_stack_regs(regs); /* Pretend that the read succeeded and returned 0. */ - regs->ip = ex_fixup_addr(fixup); regs->ax = 0; regs->dx = 0; - return true; + return ex_handler_default(fixup, regs); } -EXPORT_SYMBOL(ex_handler_rdmsr_unsafe); -__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup, + struct pt_regs *regs) { if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, (unsigned int)regs->dx, @@ -121,45 +87,29 @@ __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup show_stack_regs(regs); /* Pretend that the write succeeded. */ - regs->ip = ex_fixup_addr(fixup); - return true; + return ex_handler_default(fixup, regs); } -EXPORT_SYMBOL(ex_handler_wrmsr_unsafe); -__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) +static bool ex_handler_clear_fs(const struct exception_table_entry *fixup, + struct pt_regs *regs) { if (static_cpu_has(X86_BUG_NULL_SEG)) asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); asm volatile ("mov %0, %%fs" : : "rm" (0)); - return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr); + return ex_handler_default(fixup, regs); } -EXPORT_SYMBOL(ex_handler_clear_fs); -enum handler_type ex_get_fault_handler_type(unsigned long ip) +int ex_get_fixup_type(unsigned long ip) { - const struct exception_table_entry *e; - ex_handler_t handler; + const struct exception_table_entry *e = search_exception_tables(ip); - e = search_exception_tables(ip); - if (!e) - return EX_HANDLER_NONE; - handler = ex_fixup_handler(e); - if (handler == ex_handler_fault) - return EX_HANDLER_FAULT; - else if (handler == ex_handler_uaccess || handler == ex_handler_copy) - return EX_HANDLER_UACCESS; - else - return EX_HANDLER_OTHER; + return e ? e->type : EX_TYPE_NONE; } int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { const struct exception_table_entry *e; - ex_handler_t handler; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { @@ -179,8 +129,35 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, if (!e) return 0; - handler = ex_fixup_handler(e); - return handler(e, regs, trapnr, error_code, fault_addr); + switch (e->type) { + case EX_TYPE_DEFAULT: + case EX_TYPE_DEFAULT_MCE_SAFE: + return ex_handler_default(e, regs); + case EX_TYPE_FAULT: + case EX_TYPE_FAULT_MCE_SAFE: + return ex_handler_fault(e, regs, trapnr); + case EX_TYPE_UACCESS: + return ex_handler_uaccess(e, regs, trapnr); + case EX_TYPE_COPY: + return ex_handler_copy(e, regs, trapnr); + case EX_TYPE_CLEAR_FS: + return ex_handler_clear_fs(e, regs); + case EX_TYPE_FPU_RESTORE: + return ex_handler_fprestore(e, regs); + case EX_TYPE_RDMSR: + return ex_handler_rdmsr_unsafe(e, regs); + case EX_TYPE_WRMSR: + return ex_handler_wrmsr_unsafe(e, regs); + case EX_TYPE_BPF: + return ex_handler_bpf(e, regs); + case EX_TYPE_RDMSR_IN_MCE: + ex_handler_msr_mce(regs, false); + break; + case EX_TYPE_WRMSR_IN_MCE: + ex_handler_msr_mce(regs, true); + break; + } + BUG(); } extern unsigned int early_recursion_flag; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b2eefdefc108..4bfed53e210e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -32,6 +32,7 @@ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #include <asm/vdso.h> /* fixup_vdso_exception() */ +#include <asm/irq_stack.h> #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -631,6 +632,9 @@ static noinline void page_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { +#ifdef CONFIG_VMAP_STACK + struct stack_info info; +#endif unsigned long flags; int sig; @@ -649,9 +653,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && - (((unsigned long)current->stack - 1 - address < PAGE_SIZE) || - address - ((unsigned long)current->stack + THREAD_SIZE) < PAGE_SIZE)) { - unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *); + get_stack_guard_info((void *)address, &info)) { /* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but @@ -662,13 +664,11 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, * and then double-fault, though, because we're likely to * break the console driver and lose most of the stack dump. */ - asm volatile ("movq %[stack], %%rsp\n\t" - "call handle_stack_overflow\n\t" - "1: jmp 1b" - : ASM_CALL_CONSTRAINT - : "D" ("kernel stack overflow (page fault)"), - "S" (regs), "d" (address), - [stack] "rm" (stack)); + call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*), + handle_stack_overflow, + ASM_CALL_ARG3, + , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info)); + unreachable(); } #endif @@ -710,7 +710,8 @@ oops: static noinline void kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, - unsigned long address, int signal, int si_code) + unsigned long address, int signal, int si_code, + u32 pkey) { WARN_ON_ONCE(user_mode(regs)); @@ -735,8 +736,12 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, set_signal_archinfo(address, error_code); - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); + if (si_code == SEGV_PKUERR) { + force_sig_pkuerr((void __user *)address, pkey); + } else { + /* XXX: hwpoison faults will set the wrong code. */ + force_sig_fault(signal, si_code, (void __user *)address); + } } /* @@ -798,7 +803,8 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, pkey, si_code); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGSEGV, si_code, pkey); return; } @@ -930,7 +936,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } @@ -1396,7 +1403,8 @@ good_area: */ if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, - SIGBUS, BUS_ADRERR); + SIGBUS, BUS_ADRERR, + ARCH_DEFAULT_PKEY); return; } @@ -1416,7 +1424,8 @@ good_area: return; if (fatal_signal_pending(current) && !user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, 0, 0); + kernelmode_fixup_or_oops(regs, error_code, address, + 0, 0, ARCH_DEFAULT_PKEY); return; } @@ -1424,7 +1433,8 @@ good_area: /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, - SIGSEGV, SEGV_MAPERR); + SIGSEGV, SEGV_MAPERR, + ARCH_DEFAULT_PKEY); return; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 60ade7dd71bd..026031b3b782 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -14,7 +14,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mmiotrace.h> -#include <linux/mem_encrypt.h> +#include <linux/cc_platform.h> #include <linux/efi.h> #include <linux/pgtable.h> @@ -92,7 +92,7 @@ static unsigned int __ioremap_check_ram(struct resource *res) */ static unsigned int __ioremap_check_encrypted(struct resource *res) { - if (!sev_active()) + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return 0; switch (res->desc) { @@ -112,7 +112,7 @@ static unsigned int __ioremap_check_encrypted(struct resource *res) */ static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc) { - if (!sev_active()) + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; if (!IS_ENABLED(CONFIG_EFI)) @@ -508,6 +508,7 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) memunmap((void *)((unsigned long)addr & PAGE_MASK)); } +#ifdef CONFIG_AMD_MEM_ENCRYPT /* * Examine the physical address to determine if it is an area of memory * that should be mapped decrypted. If the memory is not part of the @@ -555,7 +556,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, case E820_TYPE_NVS: case E820_TYPE_UNUSABLE: /* For SEV, these areas are encrypted */ - if (sev_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) break; fallthrough; @@ -693,7 +694,7 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, unsigned long flags) { - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return true; if (flags & MEMREMAP_ENC) @@ -702,7 +703,7 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, if (flags & MEMREMAP_DEC) return false; - if (sme_active()) { + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { if (memremap_is_setup_data(phys_addr, size) || memremap_is_efi_data(phys_addr, size)) return false; @@ -723,12 +724,12 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, { bool encrypted_prot; - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return prot; encrypted_prot = true; - if (sme_active()) { + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { if (early_memremap_is_setup_data(phys_addr, size) || memremap_is_efi_data(phys_addr, size)) encrypted_prot = false; @@ -746,7 +747,6 @@ bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size) return arch_memremap_can_ram_remap(phys_addr, size, 0); } -#ifdef CONFIG_AMD_MEM_ENCRYPT /* Remap memory with encryption */ void __init *early_memremap_encrypted(resource_size_t phys_addr, unsigned long size) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index ff08dc463634..23d54b810f08 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -20,6 +20,7 @@ #include <linux/bitops.h> #include <linux/dma-mapping.h> #include <linux/virtio_config.h> +#include <linux/cc_platform.h> #include <asm/tlbflush.h> #include <asm/fixmap.h> @@ -143,7 +144,7 @@ void __init sme_unmap_bootdata(char *real_mode_data) struct boot_params *boot_data; unsigned long cmdline_paddr; - if (!sme_active()) + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) return; /* Get the command line address before unmapping the real_mode_data */ @@ -163,7 +164,7 @@ void __init sme_map_bootdata(char *real_mode_data) struct boot_params *boot_data; unsigned long cmdline_paddr; - if (!sme_active()) + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) return; __sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true); @@ -193,7 +194,7 @@ void __init sme_early_init(void) for (i = 0; i < ARRAY_SIZE(protection_map); i++) protection_map[i] = pgprot_encrypted(protection_map[i]); - if (sev_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) swiotlb_force = SWIOTLB_FORCE; } @@ -202,7 +203,7 @@ void __init sev_setup_arch(void) phys_addr_t total_mem = memblock_phys_mem_size(); unsigned long size; - if (!sev_active()) + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; /* @@ -360,42 +361,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) return early_set_memory_enc_dec(vaddr, size, true); } -/* - * SME and SEV are very similar but they are not the same, so there are - * times that the kernel will need to distinguish between SME and SEV. The - * sme_active() and sev_active() functions are used for this. When a - * distinction isn't needed, the mem_encrypt_active() function can be used. - * - * The trampoline code is a good example for this requirement. Before - * paging is activated, SME will access all memory as decrypted, but SEV - * will access all memory as encrypted. So, when APs are being brought - * up under SME the trampoline area cannot be encrypted, whereas under SEV - * the trampoline area must be encrypted. - */ -bool sev_active(void) -{ - return sev_status & MSR_AMD64_SEV_ENABLED; -} - -bool sme_active(void) -{ - return sme_me_mask && !sev_active(); -} -EXPORT_SYMBOL_GPL(sev_active); - -/* Needs to be called from non-instrumentable code */ -bool noinstr sev_es_active(void) -{ - return sev_status & MSR_AMD64_SEV_ES_ENABLED; -} - /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { /* * For SEV, all DMA must be to unencrypted addresses. */ - if (sev_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return true; /* @@ -403,7 +375,7 @@ bool force_dma_unencrypted(struct device *dev) * device does not support DMA to addresses that include the * encryption mask. */ - if (sme_active()) { + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask)); u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); @@ -428,7 +400,7 @@ void __init mem_encrypt_free_decrypted_mem(void) * The unused memory range was mapped decrypted, change the encryption * attribute from decrypted to encrypted before freeing it. */ - if (mem_encrypt_active()) { + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { r = set_memory_encrypted(vaddr, npages); if (r) { pr_warn("failed to free unused decrypted pages\n"); @@ -444,7 +416,7 @@ static void print_mem_encrypt_feature_info(void) pr_info("AMD Memory Encryption Features active:"); /* Secure Memory Encryption */ - if (sme_active()) { + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { /* * SME is mutually exclusive with any of the SEV * features below. @@ -454,11 +426,11 @@ static void print_mem_encrypt_feature_info(void) } /* Secure Encrypted Virtualization */ - if (sev_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) pr_cont(" SEV"); /* Encrypted Register State */ - if (sev_es_active()) + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) pr_cont(" SEV-ES"); pr_cont("\n"); @@ -477,7 +449,8 @@ void __init mem_encrypt_init(void) * With SEV, we need to unroll the rep string I/O instructions, * but SEV-ES supports them through the #VC handler. */ - if (sev_active() && !sev_es_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && + !cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) static_branch_enable(&sev_enable_key); print_mem_encrypt_feature_info(); @@ -485,6 +458,6 @@ void __init mem_encrypt_init(void) int arch_has_restricted_virtio_memory_access(void) { - return sev_active(); + return cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT); } EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access); diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 470b20208430..3f0abb403340 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -27,9 +27,19 @@ #undef CONFIG_PARAVIRT_XXL #undef CONFIG_PARAVIRT_SPINLOCKS +/* + * This code runs before CPU feature bits are set. By default, the + * pgtable_l5_enabled() function uses bit X86_FEATURE_LA57 to determine if + * 5-level paging is active, so that won't work here. USE_EARLY_PGTABLE_L5 + * is provided to handle this situation and, instead, use a variable that + * has been set by the early boot code. + */ +#define USE_EARLY_PGTABLE_L5 + #include <linux/kernel.h> #include <linux/mm.h> #include <linux/mem_encrypt.h> +#include <linux/cc_platform.h> #include <asm/setup.h> #include <asm/sections.h> @@ -287,7 +297,13 @@ void __init sme_encrypt_kernel(struct boot_params *bp) unsigned long pgtable_area_len; unsigned long decrypted_base; - if (!sme_active()) + /* + * This is early code, use an open coded check for SME instead of + * using cc_platform_has(). This eliminates worries about removing + * instrumentation or checking boot_cpu_data in the cc_platform_has() + * function. + */ + if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED) return; /* diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index ad8a5c586a35..934dc5b2df36 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -18,6 +18,7 @@ #include <linux/libnvdimm.h> #include <linux/vmstat.h> #include <linux/kernel.h> +#include <linux/cc_platform.h> #include <asm/e820/api.h> #include <asm/processor.h> @@ -29,6 +30,8 @@ #include <asm/proto.h> #include <asm/memtype.h> #include <asm/set_memory.h> +#include <asm/hyperv-tlfs.h> +#include <asm/mshyperv.h> #include "../mm_internal.h" @@ -1980,15 +1983,15 @@ int set_memory_global(unsigned long addr, int numpages) __pgprot(_PAGE_GLOBAL), 0); } -static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) +/* + * __set_memory_enc_pgtable() is used for the hypervisors that get + * informed about "encryption" status via page tables. + */ +static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) { struct cpa_data cpa; int ret; - /* Nothing to do if memory encryption is not active */ - if (!mem_encrypt_active()) - return 0; - /* Should not be working on unaligned addresses */ if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr)) addr &= PAGE_MASK; @@ -2023,6 +2026,17 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) return ret; } +static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) +{ + if (hv_is_isolation_supported()) + return hv_set_mem_host_visibility(addr, numpages, !enc); + + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) + return __set_memory_enc_pgtable(addr, numpages, enc); + + return 0; +} + int set_memory_encrypted(unsigned long addr, int numpages) { return __set_memory_enc_dec(addr, numpages, true); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0fe6aacef3db..726700fabca6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -15,7 +15,6 @@ #include <asm/set_memory.h> #include <asm/nospec-branch.h> #include <asm/text-patching.h> -#include <asm/asm-prototypes.h> static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -225,6 +224,14 @@ static void jit_fill_hole(void *area, unsigned int size) struct jit_context { int cleanup_addr; /* Epilogue code offset */ + + /* + * Program specific offsets of labels in the code; these rely on the + * JIT doing at least 2 passes, recording the position on the first + * pass, only to generate the correct offset on the second pass. + */ + int tail_call_direct_label; + int tail_call_indirect_label; }; /* Maximum number of bytes emitted while JITing one eBPF insn */ @@ -380,20 +387,23 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true); } -static int get_pop_bytes(bool *callee_regs_used) +#define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8) + +static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { - int bytes = 0; + u8 *prog = *pprog; - if (callee_regs_used[3]) - bytes += 2; - if (callee_regs_used[2]) - bytes += 2; - if (callee_regs_used[1]) - bytes += 2; - if (callee_regs_used[0]) - bytes += 1; +#ifdef CONFIG_RETPOLINE + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + EMIT_LFENCE(); + EMIT2(0xFF, 0xE0 + reg); + } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); + } else +#endif + EMIT2(0xFF, 0xE0 + reg); - return bytes; + *pprog = prog; } /* @@ -411,29 +421,12 @@ static int get_pop_bytes(bool *callee_regs_used) * out: */ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, - u32 stack_depth) + u32 stack_depth, u8 *ip, + struct jit_context *ctx) { int tcc_off = -4 - round_up(stack_depth, 8); - u8 *prog = *pprog; - int pop_bytes = 0; - int off1 = 42; - int off2 = 31; - int off3 = 9; - - /* count the additional bytes used for popping callee regs from stack - * that need to be taken into account for each of the offsets that - * are used for bailing out of the tail call - */ - pop_bytes = get_pop_bytes(callee_regs_used); - off1 += pop_bytes; - off2 += pop_bytes; - off3 += pop_bytes; - - if (stack_depth) { - off1 += 7; - off2 += 7; - off3 += 7; - } + u8 *prog = *pprog, *start = *pprog; + int offset; /* * rdi - pointer to ctx @@ -448,8 +441,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, EMIT2(0x89, 0xD2); /* mov edx, edx */ EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); -#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */ - EMIT2(X86_JBE, OFFSET1); /* jbe out */ + + offset = ctx->tail_call_indirect_label - (prog + 2 - start); + EMIT2(X86_JBE, offset); /* jbe out */ /* * if (tail_call_cnt > MAX_TAIL_CALL_CNT) @@ -457,8 +451,9 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE) - EMIT2(X86_JA, OFFSET2); /* ja out */ + + offset = ctx->tail_call_indirect_label - (prog + 2 - start); + EMIT2(X86_JA, offset); /* ja out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ @@ -471,12 +466,11 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, * goto out; */ EMIT3(0x48, 0x85, 0xC9); /* test rcx,rcx */ -#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE) - EMIT2(X86_JE, OFFSET3); /* je out */ - *pprog = prog; - pop_callee_regs(pprog, callee_regs_used); - prog = *pprog; + offset = ctx->tail_call_indirect_label - (prog + 2 - start); + EMIT2(X86_JE, offset); /* je out */ + + pop_callee_regs(&prog, callee_regs_used); EMIT1(0x58); /* pop rax */ if (stack_depth) @@ -493,41 +487,21 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, * rdi == ctx (1st arg) * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET */ - RETPOLINE_RCX_BPF_JIT(); + emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start)); /* out: */ + ctx->tail_call_indirect_label = prog - start; *pprog = prog; } static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, - u8 **pprog, int addr, u8 *image, - bool *callee_regs_used, u32 stack_depth) + u8 **pprog, u8 *ip, + bool *callee_regs_used, u32 stack_depth, + struct jit_context *ctx) { int tcc_off = -4 - round_up(stack_depth, 8); - u8 *prog = *pprog; - int pop_bytes = 0; - int off1 = 20; - int poke_off; - - /* count the additional bytes used for popping callee regs to stack - * that need to be taken into account for jump offset that is used for - * bailing out from of the tail call when limit is reached - */ - pop_bytes = get_pop_bytes(callee_regs_used); - off1 += pop_bytes; - - /* - * total bytes for: - * - nop5/ jmpq $off - * - pop callee regs - * - sub rsp, $val if depth > 0 - * - pop rax - */ - poke_off = X86_PATCH_SIZE + pop_bytes + 1; - if (stack_depth) { - poke_off += 7; - off1 += 7; - } + u8 *prog = *pprog, *start = *pprog; + int offset; /* * if (tail_call_cnt > MAX_TAIL_CALL_CNT) @@ -535,28 +509,30 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ - EMIT2(X86_JA, off1); /* ja out */ + + offset = ctx->tail_call_direct_label - (prog + 2 - start); + EMIT2(X86_JA, offset); /* ja out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ - poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE); + poke->tailcall_bypass = ip + (prog - start); poke->adj_off = X86_TAIL_CALL_OFFSET; - poke->tailcall_target = image + (addr - X86_PATCH_SIZE); + poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE; poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE; emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE, poke->tailcall_bypass); - *pprog = prog; - pop_callee_regs(pprog, callee_regs_used); - prog = *pprog; + pop_callee_regs(&prog, callee_regs_used); EMIT1(0x58); /* pop rax */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8)); memcpy(prog, x86_nops[5], X86_PATCH_SIZE); prog += X86_PATCH_SIZE; + /* out: */ + ctx->tail_call_direct_label = prog - start; *pprog = prog; } @@ -721,6 +697,20 @@ static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64) *pprog = prog; } +/* + * Similar version of maybe_emit_mod() for a single register + */ +static void maybe_emit_1mod(u8 **pprog, u32 reg, bool is64) +{ + u8 *prog = *pprog; + + if (is64) + EMIT1(add_1mod(0x48, reg)); + else if (is_ereg(reg)) + EMIT1(add_1mod(0x40, reg)); + *pprog = prog; +} + /* LDX: dst_reg = *(u8*)(src_reg + off) */ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { @@ -827,9 +817,7 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, return 0; } -static bool ex_handler_bpf(const struct exception_table_entry *x, - struct pt_regs *regs, int trapnr, - unsigned long error_code, unsigned long fault_addr) +bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs) { u32 reg = x->fixup >> 8; @@ -951,10 +939,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, /* neg dst */ case BPF_ALU | BPF_NEG: case BPF_ALU64 | BPF_NEG: - if (BPF_CLASS(insn->code) == BPF_ALU64) - EMIT1(add_1mod(0x48, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); + maybe_emit_1mod(&prog, dst_reg, + BPF_CLASS(insn->code) == BPF_ALU64); EMIT2(0xF7, add_1reg(0xD8, dst_reg)); break; @@ -968,10 +954,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: - if (BPF_CLASS(insn->code) == BPF_ALU64) - EMIT1(add_1mod(0x48, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); + maybe_emit_1mod(&prog, dst_reg, + BPF_CLASS(insn->code) == BPF_ALU64); /* * b3 holds 'normal' opcode, b2 short form only valid @@ -1028,19 +1012,30 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU64 | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_K: - case BPF_ALU64 | BPF_DIV | BPF_K: - EMIT1(0x50); /* push rax */ - EMIT1(0x52); /* push rdx */ + case BPF_ALU64 | BPF_DIV | BPF_K: { + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; - if (BPF_SRC(insn->code) == BPF_X) - /* mov r11, src_reg */ - EMIT_mov(AUX_REG, src_reg); - else + if (dst_reg != BPF_REG_0) + EMIT1(0x50); /* push rax */ + if (dst_reg != BPF_REG_3) + EMIT1(0x52); /* push rdx */ + + if (BPF_SRC(insn->code) == BPF_X) { + if (src_reg == BPF_REG_0 || + src_reg == BPF_REG_3) { + /* mov r11, src_reg */ + EMIT_mov(AUX_REG, src_reg); + src_reg = AUX_REG; + } + } else { /* mov r11, imm32 */ EMIT3_off32(0x49, 0xC7, 0xC3, imm32); + src_reg = AUX_REG; + } - /* mov rax, dst_reg */ - EMIT_mov(BPF_REG_0, dst_reg); + if (dst_reg != BPF_REG_0) + /* mov rax, dst_reg */ + emit_mov_reg(&prog, is64, BPF_REG_0, dst_reg); /* * xor edx, edx @@ -1048,63 +1043,51 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, */ EMIT2(0x31, 0xd2); - if (BPF_CLASS(insn->code) == BPF_ALU64) - /* div r11 */ - EMIT3(0x49, 0xF7, 0xF3); - else - /* div r11d */ - EMIT3(0x41, 0xF7, 0xF3); - - if (BPF_OP(insn->code) == BPF_MOD) - /* mov r11, rdx */ - EMIT3(0x49, 0x89, 0xD3); - else - /* mov r11, rax */ - EMIT3(0x49, 0x89, 0xC3); + /* div src_reg */ + maybe_emit_1mod(&prog, src_reg, is64); + EMIT2(0xF7, add_1reg(0xF0, src_reg)); - EMIT1(0x5A); /* pop rdx */ - EMIT1(0x58); /* pop rax */ + if (BPF_OP(insn->code) == BPF_MOD && + dst_reg != BPF_REG_3) + /* mov dst_reg, rdx */ + emit_mov_reg(&prog, is64, dst_reg, BPF_REG_3); + else if (BPF_OP(insn->code) == BPF_DIV && + dst_reg != BPF_REG_0) + /* mov dst_reg, rax */ + emit_mov_reg(&prog, is64, dst_reg, BPF_REG_0); - /* mov dst_reg, r11 */ - EMIT_mov(dst_reg, AUX_REG); + if (dst_reg != BPF_REG_3) + EMIT1(0x5A); /* pop rdx */ + if (dst_reg != BPF_REG_0) + EMIT1(0x58); /* pop rax */ break; + } case BPF_ALU | BPF_MUL | BPF_K: - case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU64 | BPF_MUL | BPF_K: - case BPF_ALU64 | BPF_MUL | BPF_X: - { - bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; - - if (dst_reg != BPF_REG_0) - EMIT1(0x50); /* push rax */ - if (dst_reg != BPF_REG_3) - EMIT1(0x52); /* push rdx */ - - /* mov r11, dst_reg */ - EMIT_mov(AUX_REG, dst_reg); + maybe_emit_mod(&prog, dst_reg, dst_reg, + BPF_CLASS(insn->code) == BPF_ALU64); - if (BPF_SRC(insn->code) == BPF_X) - emit_mov_reg(&prog, is64, BPF_REG_0, src_reg); + if (is_imm8(imm32)) + /* imul dst_reg, dst_reg, imm8 */ + EMIT3(0x6B, add_2reg(0xC0, dst_reg, dst_reg), + imm32); else - emit_mov_imm32(&prog, is64, BPF_REG_0, imm32); + /* imul dst_reg, dst_reg, imm32 */ + EMIT2_off32(0x69, + add_2reg(0xC0, dst_reg, dst_reg), + imm32); + break; - if (is64) - EMIT1(add_1mod(0x48, AUX_REG)); - else if (is_ereg(AUX_REG)) - EMIT1(add_1mod(0x40, AUX_REG)); - /* mul(q) r11 */ - EMIT2(0xF7, add_1reg(0xE0, AUX_REG)); + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_X: + maybe_emit_mod(&prog, src_reg, dst_reg, + BPF_CLASS(insn->code) == BPF_ALU64); - if (dst_reg != BPF_REG_3) - EMIT1(0x5A); /* pop rdx */ - if (dst_reg != BPF_REG_0) { - /* mov dst_reg, rax */ - EMIT_mov(dst_reg, BPF_REG_0); - EMIT1(0x58); /* pop rax */ - } + /* imul dst_reg, src_reg */ + EMIT3(0x0F, 0xAF, add_2reg(0xC0, src_reg, dst_reg)); break; - } + /* Shifts */ case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: @@ -1112,10 +1095,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU64 | BPF_LSH | BPF_K: case BPF_ALU64 | BPF_RSH | BPF_K: case BPF_ALU64 | BPF_ARSH | BPF_K: - if (BPF_CLASS(insn->code) == BPF_ALU64) - EMIT1(add_1mod(0x48, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); + maybe_emit_1mod(&prog, dst_reg, + BPF_CLASS(insn->code) == BPF_ALU64); b3 = simple_alu_opcodes[BPF_OP(insn->code)]; if (imm32 == 1) @@ -1146,10 +1127,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } /* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */ - if (BPF_CLASS(insn->code) == BPF_ALU64) - EMIT1(add_1mod(0x48, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); + maybe_emit_1mod(&prog, dst_reg, + BPF_CLASS(insn->code) == BPF_ALU64); b3 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(0xD3, add_1reg(b3, dst_reg)); @@ -1222,8 +1201,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, /* speculation barrier */ case BPF_ST | BPF_NOSPEC: if (boot_cpu_has(X86_FEATURE_XMM2)) - /* Emit 'lfence' */ - EMIT3(0x0F, 0xAE, 0xE8); + EMIT_LFENCE(); break; /* ST: *(u8*)(dst_reg + off) = imm */ @@ -1313,12 +1291,7 @@ st: if (is_imm8(insn->off)) } ex->insn = delta; - delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler; - if (!is_simm32(delta)) { - pr_err("extable->handler doesn't fit into 32-bit\n"); - return -EFAULT; - } - ex->handler = delta; + ex->type = EX_TYPE_BPF; if (dst_reg > BPF_REG_9) { pr_err("verifier error\n"); @@ -1341,9 +1314,10 @@ st: if (is_imm8(insn->off)) if (insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH)) { - u8 *branch_target; bool is64 = BPF_SIZE(insn->code) == BPF_DW; u32 real_src_reg = src_reg; + u32 real_dst_reg = dst_reg; + u8 *branch_target; /* * Can't be implemented with a single x86 insn. @@ -1354,11 +1328,13 @@ st: if (is_imm8(insn->off)) emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0); if (src_reg == BPF_REG_0) real_src_reg = BPF_REG_AX; + if (dst_reg == BPF_REG_0) + real_dst_reg = BPF_REG_AX; branch_target = prog; /* Load old value */ emit_ldx(&prog, BPF_SIZE(insn->code), - BPF_REG_0, dst_reg, insn->off); + BPF_REG_0, real_dst_reg, insn->off); /* * Perform the (commutative) operation locally, * put the result in the AUX_REG. @@ -1369,7 +1345,8 @@ st: if (is_imm8(insn->off)) add_2reg(0xC0, AUX_REG, real_src_reg)); /* Attempt to swap in new value */ err = emit_atomic(&prog, BPF_CMPXCHG, - dst_reg, AUX_REG, insn->off, + real_dst_reg, AUX_REG, + insn->off, BPF_SIZE(insn->code)); if (WARN_ON(err)) return err; @@ -1383,11 +1360,10 @@ st: if (is_imm8(insn->off)) /* Restore R0 after clobbering RAX */ emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX); break; - } err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, - insn->off, BPF_SIZE(insn->code)); + insn->off, BPF_SIZE(insn->code)); if (err) return err; break; @@ -1409,13 +1385,16 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_TAIL_CALL: if (imm32) emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1], - &prog, addrs[i], image, + &prog, image + addrs[i - 1], callee_regs_used, - bpf_prog->aux->stack_depth); + bpf_prog->aux->stack_depth, + ctx); else emit_bpf_tail_call_indirect(&prog, callee_regs_used, - bpf_prog->aux->stack_depth); + bpf_prog->aux->stack_depth, + image + addrs[i - 1], + ctx); break; /* cond jump */ @@ -1456,10 +1435,8 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: /* test dst_reg, imm32 */ - if (BPF_CLASS(insn->code) == BPF_JMP) - EMIT1(add_1mod(0x48, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); + maybe_emit_1mod(&prog, dst_reg, + BPF_CLASS(insn->code) == BPF_JMP); EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32); goto emit_cond_jmp; @@ -1492,10 +1469,8 @@ st: if (is_imm8(insn->off)) } /* cmp dst_reg, imm8/32 */ - if (BPF_CLASS(insn->code) == BPF_JMP) - EMIT1(add_1mod(0x48, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); + maybe_emit_1mod(&prog, dst_reg, + BPF_CLASS(insn->code) == BPF_JMP); if (is_imm8(imm32)) EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32); @@ -1744,7 +1719,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, - struct bpf_prog *p, int stack_size, bool mod_ret) + struct bpf_prog *p, int stack_size, bool save_ret) { u8 *prog = *pprog; u8 *jmp_insn; @@ -1777,11 +1752,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (emit_call(&prog, p->bpf_func, prog)) return -EINVAL; - /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + /* + * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return * of the previous call which is then passed on the stack to * the next BPF program. + * + * BPF_TRAMP_FENTRY trampoline may need to return the return + * value of BPF_PROG_TYPE_STRUCT_OPS prog. */ - if (mod_ret) + if (save_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); /* replace 2 nops with JE insn, since jmp target is known */ @@ -1828,13 +1807,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) } static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, - struct bpf_tramp_progs *tp, int stack_size) + struct bpf_tramp_progs *tp, int stack_size, + bool save_ret) { int i; u8 *prog = *pprog; for (i = 0; i < tp->nr_progs; i++) { - if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, + save_ret)) return -EINVAL; } *pprog = prog; @@ -1877,6 +1858,23 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, return 0; } +static bool is_valid_bpf_tramp_flags(unsigned int flags) +{ + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return false; + + /* + * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, + * and it must be used alone. + */ + if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) && + (flags & ~BPF_TRAMP_F_RET_FENTRY_RET)) + return false; + + return true; +} + /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -1949,17 +1947,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; u8 **branches = NULL; u8 *prog; + bool save_ret; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ if (nr_args > 6) return -ENOTSUPP; - if ((flags & BPF_TRAMP_F_RESTORE_REGS) && - (flags & BPF_TRAMP_F_SKIP_FRAME)) + if (!is_valid_bpf_tramp_flags(flags)) return -EINVAL; - if (flags & BPF_TRAMP_F_CALL_ORIG) - stack_size += 8; /* room for return value of orig_call */ + /* room for return value of orig_call or fentry prog */ + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) + stack_size += 8; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2005,7 +2005,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fentry->nr_progs) - if (invoke_bpf(m, &prog, fentry, stack_size)) + if (invoke_bpf(m, &prog, fentry, stack_size, + flags & BPF_TRAMP_F_RET_FENTRY_RET)) return -EINVAL; if (fmod_ret->nr_progs) { @@ -2052,7 +2053,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fexit->nr_progs) - if (invoke_bpf(m, &prog, fexit, stack_size)) { + if (invoke_bpf(m, &prog, fexit, stack_size, false)) { ret = -EINVAL; goto cleanup; } @@ -2072,9 +2073,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - /* restore original return value back into RAX */ - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); } + /* restore return value of orig_call or fentry prog back into RAX */ + if (save_ret) + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); EMIT1(0x5B); /* pop rbx */ EMIT1(0xC9); /* leave */ @@ -2094,24 +2096,6 @@ cleanup: return ret; } -static int emit_fallback_jump(u8 **pprog) -{ - u8 *prog = *pprog; - int err = 0; - -#ifdef CONFIG_RETPOLINE - /* Note that this assumes the the compiler uses external - * thunks for indirect calls. Both clang and GCC use the same - * naming convention for external thunks. - */ - err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog); -#else - EMIT2(0xFF, 0xE2); /* jmp rdx */ -#endif - *pprog = prog; - return err; -} - static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) { u8 *jg_reloc, *prog = *pprog; @@ -2133,9 +2117,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) if (err) return err; - err = emit_fallback_jump(&prog); /* jmp thunk/indirect */ - if (err) - return err; + emit_indirect_jump(&prog, 2 /* rdx */, prog); *pprog = prog; return 0; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 3bfda5f502cb..da9b7cfa4632 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -15,6 +15,7 @@ #include <asm/cacheflush.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> +#include <asm/asm-prototypes.h> #include <linux/bpf.h> /* @@ -1267,6 +1268,21 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) *pprog = prog; } +static int emit_jmp_edx(u8 **pprog, u8 *ip) +{ + u8 *prog = *pprog; + int cnt = 0; + +#ifdef CONFIG_RETPOLINE + EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5)); +#else + EMIT2(0xFF, 0xE2); +#endif + *pprog = prog; + + return cnt; +} + /* * Generate the following code: * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... @@ -1280,7 +1296,7 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) * goto *(prog->bpf_func + prologue_size); * out: */ -static void emit_bpf_tail_call(u8 **pprog) +static void emit_bpf_tail_call(u8 **pprog, u8 *ip) { u8 *prog = *pprog; int cnt = 0; @@ -1362,7 +1378,7 @@ static void emit_bpf_tail_call(u8 **pprog) * eax == ctx (1st arg) * edx == prog->bpf_func + prologue_size */ - RETPOLINE_EDX_BPF_JIT(); + cnt += emit_jmp_edx(&prog, ip + cnt); if (jmp_label1 == -1) jmp_label1 = cnt; @@ -2122,7 +2138,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; } case BPF_JMP | BPF_TAIL_CALL: - emit_bpf_tail_call(&prog); + emit_bpf_tail_call(&prog, image + addrs[i - 1]); break; /* cond jump */ diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 3d41a09c2c14..5debe4ac6f81 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -113,7 +113,7 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, false /* no mapping of GSI to PIRQ */); } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 static int xen_register_gsi(u32 gsi, int triggering, int polarity) { int rc, irq; @@ -261,7 +261,7 @@ error: return irq; } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 static bool __read_mostly pci_seg_supported = true; static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) @@ -375,10 +375,10 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev) WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret); } } -#else /* CONFIG_XEN_DOM0 */ +#else /* CONFIG_XEN_PV_DOM0 */ #define xen_initdom_setup_msi_irqs NULL #define xen_initdom_restore_msi_irqs NULL -#endif /* !CONFIG_XEN_DOM0 */ +#endif /* !CONFIG_XEN_PV_DOM0 */ static void xen_teardown_msi_irqs(struct pci_dev *dev) { @@ -555,7 +555,7 @@ int __init pci_xen_hvm_init(void) return 0; } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 int __init pci_xen_initial_domain(void) { int irq; @@ -583,6 +583,9 @@ int __init pci_xen_initial_domain(void) } return 0; } +#endif + +#ifdef CONFIG_XEN_DOM0 struct xen_device_domain_owner { domid_t domain; @@ -656,4 +659,4 @@ int xen_unregister_device_domain_owner(struct pci_dev *dev) return 0; } EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner); -#endif +#endif /* CONFIG_XEN_DOM0 */ diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 7515e78ef898..1f3675453a57 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -33,7 +33,7 @@ #include <linux/reboot.h> #include <linux/slab.h> #include <linux/ucs2_string.h> -#include <linux/mem_encrypt.h> +#include <linux/cc_platform.h> #include <linux/sched/task.h> #include <asm/setup.h> @@ -284,7 +284,8 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; - if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && + md->type != EFI_MEMORY_MAPPED_IO) flags |= _PAGE_ENC; pfn = md->phys_addr >> PAGE_SHIFT; @@ -390,7 +391,7 @@ static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *m if (!(md->attribute & EFI_MEMORY_RO)) pf |= _PAGE_RW; - if (sev_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) pf |= _PAGE_ENC; return efi_update_mappings(md, pf); @@ -438,7 +439,7 @@ void __init efi_runtime_update_mappings(void) (md->type != EFI_RUNTIME_SERVICES_CODE)) pf |= _PAGE_RW; - if (sev_active()) + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) pf |= _PAGE_ENC; efi_update_mappings(md, pf); diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index ee2beda590d0..1d4a00e767ec 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -274,7 +274,7 @@ static struct olpc_ec_driver ec_xo1_driver = { static struct olpc_ec_driver ec_xo1_5_driver = { .ec_cmd = olpc_xo1_ec_cmd, -#ifdef CONFIG_OLPC_XO1_5_SCI +#ifdef CONFIG_OLPC_XO15_SCI /* * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is * compiled in diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 9ac7457f52a3..ed0442e35434 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -16,15 +16,15 @@ /* * PVH variables. * - * pvh_bootparams and pvh_start_info need to live in the data segment since + * pvh_bootparams and pvh_start_info need to live in a data segment since * they are used after startup_{32|64}, which clear .bss, are invoked. */ -struct boot_params pvh_bootparams __section(".data"); -struct hvm_start_info pvh_start_info __section(".data"); +struct boot_params __initdata pvh_bootparams; +struct hvm_start_info __initdata pvh_start_info; -unsigned int pvh_start_info_sz = sizeof(pvh_start_info); +const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info); -static u64 pvh_get_root_pointer(void) +static u64 __init pvh_get_root_pointer(void) { return pvh_start_info.rsdp_paddr; } @@ -107,7 +107,7 @@ void __init __weak xen_pvh_init(struct boot_params *boot_params) BUG(); } -static void hypervisor_specific_init(bool xen_guest) +static void __init hypervisor_specific_init(bool xen_guest) { if (xen_guest) xen_pvh_init(&pvh_bootparams); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 6665f8802098..9f2b251e83c5 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -20,7 +20,7 @@ #include <asm/page.h> #include <asm/mce.h> #include <asm/suspend.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 31b5856010cb..4a3da7592b99 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -2,7 +2,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/memblock.h> -#include <linux/mem_encrypt.h> +#include <linux/cc_platform.h> #include <linux/pgtable.h> #include <asm/set_memory.h> @@ -44,10 +44,10 @@ void __init reserve_real_mode(void) static void sme_sev_setup_real_mode(struct trampoline_header *th) { #ifdef CONFIG_AMD_MEM_ENCRYPT - if (sme_active()) + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) th->flags |= TH_FLAGS_SME_ACTIVE; - if (sev_es_active()) { + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) { /* * Skip the call to verify_cpu() in secondary_startup_64 as it * will cause #VC exceptions when the AP can't handle them yet. @@ -81,7 +81,7 @@ static void __init setup_real_mode(void) * decrypted memory in order to bring up other processors * successfully. This is not needed for SEV. */ - if (sme_active()) + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) set_memory_decrypted((unsigned long)base, size >> PAGE_SHIFT); memcpy(base, real_mode_blob, size); diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 27c82207d387..c736cf2ac76b 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -14,6 +14,10 @@ static Elf_Ehdr ehdr; static unsigned long shnum; static unsigned int shstrndx; +static unsigned int shsymtabndx; +static unsigned int shxsymtabndx; + +static int sym_index(Elf_Sym *sym); struct relocs { uint32_t *offset; @@ -35,6 +39,7 @@ struct section { Elf_Shdr shdr; struct section *link; Elf_Sym *symtab; + Elf32_Word *xsymtab; Elf_Rel *reltab; char *strtab; }; @@ -63,7 +68,9 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "(__parainstructions|__alt_instructions)(_end)?|" "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|" "__(start|end)_pci_.*|" +#if CONFIG_FW_LOADER_BUILTIN "__(start|end)_builtin_fw|" +#endif "__(start|stop)___ksymtab(_gpl)?|" "__(start|stop)___kcrctab(_gpl)?|" "__(start|stop)___param|" @@ -268,7 +275,7 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym) name = sym_strtab + sym->st_name; } else { - name = sec_name(sym->st_shndx); + name = sec_name(sym_index(sym)); } return name; } @@ -338,6 +345,23 @@ static uint64_t elf64_to_cpu(uint64_t val) #define elf_xword_to_cpu(x) elf32_to_cpu(x) #endif +static int sym_index(Elf_Sym *sym) +{ + Elf_Sym *symtab = secs[shsymtabndx].symtab; + Elf32_Word *xsymtab = secs[shxsymtabndx].xsymtab; + unsigned long offset; + int index; + + if (sym->st_shndx != SHN_XINDEX) + return sym->st_shndx; + + /* calculate offset of sym from head of table. */ + offset = (unsigned long)sym - (unsigned long)symtab; + index = offset / sizeof(*sym); + + return elf32_to_cpu(xsymtab[index]); +} + static void read_ehdr(FILE *fp) { if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) { @@ -471,31 +495,60 @@ static void read_strtabs(FILE *fp) static void read_symtabs(FILE *fp) { int i,j; + for (i = 0; i < shnum; i++) { struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_SYMTAB) { + int num_syms; + + switch (sec->shdr.sh_type) { + case SHT_SYMTAB_SHNDX: + sec->xsymtab = malloc(sec->shdr.sh_size); + if (!sec->xsymtab) { + die("malloc of %" FMT " bytes for xsymtab failed\n", + sec->shdr.sh_size); + } + if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { + die("Seek to %" FMT " failed: %s\n", + sec->shdr.sh_offset, strerror(errno)); + } + if (fread(sec->xsymtab, 1, sec->shdr.sh_size, fp) + != sec->shdr.sh_size) { + die("Cannot read extended symbol table: %s\n", + strerror(errno)); + } + shxsymtabndx = i; + continue; + + case SHT_SYMTAB: + num_syms = sec->shdr.sh_size / sizeof(Elf_Sym); + + sec->symtab = malloc(sec->shdr.sh_size); + if (!sec->symtab) { + die("malloc of %" FMT " bytes for symtab failed\n", + sec->shdr.sh_size); + } + if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { + die("Seek to %" FMT " failed: %s\n", + sec->shdr.sh_offset, strerror(errno)); + } + if (fread(sec->symtab, 1, sec->shdr.sh_size, fp) + != sec->shdr.sh_size) { + die("Cannot read symbol table: %s\n", + strerror(errno)); + } + for (j = 0; j < num_syms; j++) { + Elf_Sym *sym = &sec->symtab[j]; + + sym->st_name = elf_word_to_cpu(sym->st_name); + sym->st_value = elf_addr_to_cpu(sym->st_value); + sym->st_size = elf_xword_to_cpu(sym->st_size); + sym->st_shndx = elf_half_to_cpu(sym->st_shndx); + } + shsymtabndx = i; + continue; + + default: continue; - } - sec->symtab = malloc(sec->shdr.sh_size); - if (!sec->symtab) { - die("malloc of %" FMT " bytes for symtab failed\n", - sec->shdr.sh_size); - } - if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) { - die("Seek to %" FMT " failed: %s\n", - sec->shdr.sh_offset, strerror(errno)); - } - if (fread(sec->symtab, 1, sec->shdr.sh_size, fp) - != sec->shdr.sh_size) { - die("Cannot read symbol table: %s\n", - strerror(errno)); - } - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) { - Elf_Sym *sym = &sec->symtab[j]; - sym->st_name = elf_word_to_cpu(sym->st_name); - sym->st_value = elf_addr_to_cpu(sym->st_value); - sym->st_size = elf_xword_to_cpu(sym->st_size); - sym->st_shndx = elf_half_to_cpu(sym->st_shndx); } } } @@ -762,7 +815,9 @@ static void percpu_init(void) */ static int is_percpu_sym(ElfW(Sym) *sym, const char *symname) { - return (sym->st_shndx == per_cpu_shndx) && + int shndx = sym_index(sym); + + return (shndx == per_cpu_shndx) && strcmp(symname, "__init_begin") && strcmp(symname, "__per_cpu_load") && strncmp(symname, "init_per_cpu_", 13); @@ -1095,7 +1150,7 @@ static int do_reloc_info(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, sec_name(sec->shdr.sh_info), rel_type(ELF_R_TYPE(rel->r_info)), symname, - sec_name(sym->st_shndx)); + sec_name(sym_index(sym))); return 0; } diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index afc1da68b06d..6bcd3d8ca6ac 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -43,13 +43,9 @@ config XEN_PV_SMP def_bool y depends on XEN_PV && SMP -config XEN_DOM0 - bool "Xen PV Dom0 support" - default y - depends on XEN_PV && PCI_XEN && SWIOTLB_XEN - depends on X86_IO_APIC && ACPI && PCI - help - Support running as a Xen PV Dom0 guest. +config XEN_PV_DOM0 + def_bool y + depends on XEN_PV && XEN_DOM0 config XEN_PVHVM def_bool y @@ -86,3 +82,12 @@ config XEN_PVH def_bool n help Support for running as a Xen PVH guest. + +config XEN_DOM0 + bool "Xen Dom0 support" + default XEN_PV + depends on (XEN_PV && SWIOTLB_XEN) || (XEN_PVH && X86_64) + depends on X86_IO_APIC && ACPI && PCI + select X86_X2APIC if XEN_PVH && X86_64 + help + Support running as a Xen Dom0 guest. diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 40b5779fce21..4953260e281c 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -45,7 +45,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += vga.o +obj-$(CONFIG_XEN_PV_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c79bd0af2e8c..95d970359e17 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -3,6 +3,7 @@ #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG #include <linux/memblock.h> #endif +#include <linux/console.h> #include <linux/cpu.h> #include <linux/kexec.h> #include <linux/slab.h> @@ -10,12 +11,15 @@ #include <xen/xen.h> #include <xen/features.h> +#include <xen/interface/sched.h> +#include <xen/interface/version.h> #include <xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> #include <asm/cpu.h> #include <asm/e820/api.h> +#include <asm/setup.h> #include "xen-ops.h" #include "smp.h" @@ -52,9 +56,6 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); -enum xen_domain_type xen_domain_type = XEN_NATIVE; -EXPORT_SYMBOL_GPL(xen_domain_type); - unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; EXPORT_SYMBOL(machine_to_phys_mapping); unsigned long machine_to_phys_nr; @@ -69,10 +70,12 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* - * NB: needs to live in .data because it's used by xen_prepare_pvh which runs - * before clearing the bss. + * NB: These need to live in .data or alike because they're used by + * xen_prepare_pvh() which runs before clearing the bss. */ -uint32_t xen_start_flags __section(".data") = 0; +enum xen_domain_type __ro_after_init xen_domain_type = XEN_NATIVE; +EXPORT_SYMBOL_GPL(xen_domain_type); +uint32_t __ro_after_init xen_start_flags; EXPORT_SYMBOL(xen_start_flags); /* @@ -258,6 +261,45 @@ int xen_vcpu_setup(int cpu) return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0); } +void __init xen_banner(void) +{ + unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); + struct xen_extraversion extra; + + HYPERVISOR_xen_version(XENVER_extraversion, &extra); + + pr_info("Booting kernel on %s\n", pv_info.name); + pr_info("Xen version: %u.%u%s%s\n", + version >> 16, version & 0xffff, extra.extraversion, + xen_feature(XENFEAT_mmu_pt_update_preserve_ad) + ? " (preserve-AD)" : ""); +} + +/* Check if running on Xen version (major, minor) or later */ +bool xen_running_on_version_or_later(unsigned int major, unsigned int minor) +{ + unsigned int version; + + if (!xen_domain()) + return false; + + version = HYPERVISOR_xen_version(XENVER_version, NULL); + if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || + ((version >> 16) > major)) + return true; + return false; +} + +void __init xen_add_preferred_consoles(void) +{ + add_preferred_console("xenboot", 0, NULL); + if (!boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); + add_preferred_console("hvc", 0, NULL); + if (boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); +} + void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 349f780a1567..4f63117f09bb 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -28,7 +28,6 @@ #include <linux/mm.h> #include <linux/page-flags.h> #include <linux/highmem.h> -#include <linux/console.h> #include <linux/pci.h> #include <linux/gfp.h> #include <linux/edd.h> @@ -109,17 +108,6 @@ struct tls_descs { */ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); -static void __init xen_banner(void) -{ - unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); - struct xen_extraversion extra; - HYPERVISOR_xen_version(XENVER_extraversion, &extra); - - pr_info("Booting paravirtualized kernel on %s\n", pv_info.name); - pr_info("Xen version: %d.%d%s (preserve-AD)\n", - version >> 16, version & 0xffff, extra.extraversion); -} - static void __init xen_pv_init_platform(void) { populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); @@ -142,22 +130,6 @@ static void __init xen_pv_guest_late_init(void) #endif } -/* Check if running on Xen version (major, minor) or later */ -bool -xen_running_on_version_or_later(unsigned int major, unsigned int minor) -{ - unsigned int version; - - if (!xen_domain()) - return false; - - version = HYPERVISOR_xen_version(XENVER_version, NULL); - if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || - ((version >> 16) > major)) - return true; - return false; -} - static __read_mostly unsigned int cpuid_leaf5_ecx_val; static __read_mostly unsigned int cpuid_leaf5_edx_val; @@ -311,12 +283,12 @@ static void __init xen_init_capabilities(void) } } -static void xen_set_debugreg(int reg, unsigned long val) +static noinstr void xen_set_debugreg(int reg, unsigned long val) { HYPERVISOR_set_debugreg(reg, val); } -static unsigned long xen_get_debugreg(int reg) +static noinstr unsigned long xen_get_debugreg(int reg) { return HYPERVISOR_get_debugreg(reg); } @@ -755,8 +727,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) preempt_enable(); } -static void xen_convert_trap_info(const struct desc_ptr *desc, - struct trap_info *traps) +static unsigned xen_convert_trap_info(const struct desc_ptr *desc, + struct trap_info *traps, bool full) { unsigned in, out, count; @@ -766,17 +738,18 @@ static void xen_convert_trap_info(const struct desc_ptr *desc, for (in = out = 0; in < count; in++) { gate_desc *entry = (gate_desc *)(desc->address) + in; - if (cvt_gate_to_trap(in, entry, &traps[out])) + if (cvt_gate_to_trap(in, entry, &traps[out]) || full) out++; } - traps[out].address = 0; + + return out; } void xen_copy_trap_info(struct trap_info *traps) { const struct desc_ptr *desc = this_cpu_ptr(&idt_desc); - xen_convert_trap_info(desc, traps); + xen_convert_trap_info(desc, traps, true); } /* Load a new IDT into Xen. In principle this can be per-CPU, so we @@ -786,6 +759,7 @@ static void xen_load_idt(const struct desc_ptr *desc) { static DEFINE_SPINLOCK(lock); static struct trap_info traps[257]; + unsigned out; trace_xen_cpu_load_idt(desc); @@ -793,7 +767,8 @@ static void xen_load_idt(const struct desc_ptr *desc) memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); - xen_convert_trap_info(desc, traps); + out = xen_convert_trap_info(desc, traps, false); + memset(&traps[out], 0, sizeof(traps[0])); xen_mc_flush(); if (HYPERVISOR_set_trap_table(traps)) @@ -1050,52 +1025,54 @@ static const struct pv_info xen_info __initconst = { .name = "Xen", }; -static const struct pv_cpu_ops xen_cpu_ops __initconst = { - .cpuid = xen_cpuid, +static const typeof(pv_ops) xen_cpu_ops __initconst = { + .cpu = { + .cpuid = xen_cpuid, - .set_debugreg = xen_set_debugreg, - .get_debugreg = xen_get_debugreg, + .set_debugreg = xen_set_debugreg, + .get_debugreg = xen_get_debugreg, - .read_cr0 = xen_read_cr0, - .write_cr0 = xen_write_cr0, + .read_cr0 = xen_read_cr0, + .write_cr0 = xen_write_cr0, - .write_cr4 = xen_write_cr4, + .write_cr4 = xen_write_cr4, - .wbinvd = native_wbinvd, + .wbinvd = native_wbinvd, - .read_msr = xen_read_msr, - .write_msr = xen_write_msr, + .read_msr = xen_read_msr, + .write_msr = xen_write_msr, - .read_msr_safe = xen_read_msr_safe, - .write_msr_safe = xen_write_msr_safe, + .read_msr_safe = xen_read_msr_safe, + .write_msr_safe = xen_write_msr_safe, - .read_pmc = xen_read_pmc, + .read_pmc = xen_read_pmc, - .load_tr_desc = paravirt_nop, - .set_ldt = xen_set_ldt, - .load_gdt = xen_load_gdt, - .load_idt = xen_load_idt, - .load_tls = xen_load_tls, - .load_gs_index = xen_load_gs_index, + .load_tr_desc = paravirt_nop, + .set_ldt = xen_set_ldt, + .load_gdt = xen_load_gdt, + .load_idt = xen_load_idt, + .load_tls = xen_load_tls, + .load_gs_index = xen_load_gs_index, - .alloc_ldt = xen_alloc_ldt, - .free_ldt = xen_free_ldt, + .alloc_ldt = xen_alloc_ldt, + .free_ldt = xen_free_ldt, - .store_tr = xen_store_tr, + .store_tr = xen_store_tr, - .write_ldt_entry = xen_write_ldt_entry, - .write_gdt_entry = xen_write_gdt_entry, - .write_idt_entry = xen_write_idt_entry, - .load_sp0 = xen_load_sp0, + .write_ldt_entry = xen_write_ldt_entry, + .write_gdt_entry = xen_write_gdt_entry, + .write_idt_entry = xen_write_idt_entry, + .load_sp0 = xen_load_sp0, #ifdef CONFIG_X86_IOPL_IOPERM - .invalidate_io_bitmap = xen_invalidate_io_bitmap, - .update_io_bitmap = xen_update_io_bitmap, + .invalidate_io_bitmap = xen_invalidate_io_bitmap, + .update_io_bitmap = xen_update_io_bitmap, #endif - .io_delay = xen_io_delay, + .io_delay = xen_io_delay, - .start_context_switch = paravirt_start_context_switch, - .end_context_switch = xen_end_context_switch, + .start_context_switch = paravirt_start_context_switch, + .end_context_switch = xen_end_context_switch, + }, }; static void xen_restart(char *msg) @@ -1236,7 +1213,7 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; - pv_ops.cpu = xen_cpu_ops; + pv_ops.cpu = xen_cpu_ops.cpu; paravirt_iret = xen_iret; xen_init_irq_ops(); @@ -1361,7 +1338,6 @@ asmlinkage __visible void __init xen_start_kernel(void) boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN; if (!xen_initial_domain()) { - add_preferred_console("xenboot", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; x86_platform.set_legacy_features = @@ -1406,11 +1382,7 @@ asmlinkage __visible void __init xen_start_kernel(void) #endif } - if (!boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); - add_preferred_console("hvc", 0, NULL); - if (boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); + xen_add_preferred_consoles(); #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 0d5e34b9e6f9..bcae606bbc5c 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> +#include <linux/export.h> #include <xen/hvc-console.h> @@ -18,10 +19,11 @@ /* * PVH variables. * - * The variable xen_pvh needs to live in the data segment since it is used + * The variable xen_pvh needs to live in a data segment since it is used * after startup_{32|64} is invoked, which will clear the .bss segment. */ -bool xen_pvh __section(".data") = 0; +bool __ro_after_init xen_pvh; +EXPORT_SYMBOL_GPL(xen_pvh); void __init xen_pvh_init(struct boot_params *boot_params) { @@ -36,6 +38,10 @@ void __init xen_pvh_init(struct boot_params *boot_params) pfn = __pa(hypercall_page); wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + if (xen_initial_domain()) + x86_init.oem.arch_setup = xen_add_preferred_consoles; + x86_init.oem.banner = xen_banner; + xen_efi_init(boot_params); } diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index dfa091d79c2e..4fe387e520af 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -19,12 +19,12 @@ * callback mask. We do this in a very simple manner, by making a call * down into Xen. The pending flag will be checked by Xen on return. */ -void xen_force_evtchn_callback(void) +noinstr void xen_force_evtchn_callback(void) { (void)HYPERVISOR_xen_version(0, NULL); } -asmlinkage __visible unsigned long xen_save_fl(void) +asmlinkage __visible noinstr unsigned long xen_save_fl(void) { struct vcpu_info *vcpu; unsigned long flags; @@ -40,9 +40,9 @@ asmlinkage __visible unsigned long xen_save_fl(void) */ return (-flags) & X86_EFLAGS_IF; } -PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl); +__PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl, ".noinstr.text"); -asmlinkage __visible void xen_irq_disable(void) +asmlinkage __visible noinstr void xen_irq_disable(void) { /* There's a one instruction preempt window here. We need to make sure we're don't switch CPUs between getting the vcpu @@ -51,9 +51,9 @@ asmlinkage __visible void xen_irq_disable(void) this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1; preempt_enable_no_resched(); } -PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable); +__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable, ".noinstr.text"); -asmlinkage __visible void xen_irq_enable(void) +asmlinkage __visible noinstr void xen_irq_enable(void) { struct vcpu_info *vcpu; @@ -76,7 +76,7 @@ asmlinkage __visible void xen_irq_enable(void) preempt_enable(); } -PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable); +__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable, ".noinstr.text"); static void xen_safe_halt(void) { @@ -94,17 +94,20 @@ static void xen_halt(void) xen_safe_halt(); } -static const struct pv_irq_ops xen_irq_ops __initconst = { - .save_fl = PV_CALLEE_SAVE(xen_save_fl), - .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), - .irq_enable = PV_CALLEE_SAVE(xen_irq_enable), +static const typeof(pv_ops) xen_irq_ops __initconst = { + .irq = { - .safe_halt = xen_safe_halt, - .halt = xen_halt, + .save_fl = PV_CALLEE_SAVE(xen_save_fl), + .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), + .irq_enable = PV_CALLEE_SAVE(xen_irq_enable), + + .safe_halt = xen_safe_halt, + .halt = xen_halt, + }, }; void __init xen_init_irq_ops(void) { - pv_ops.irq = xen_irq_ops; + pv_ops.irq = xen_irq_ops.irq; x86_init.irqs.intr_init = xen_init_IRQ; } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 8d751939c6f3..1ce436eeda15 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1204,7 +1204,8 @@ static void __init xen_pagetable_init(void) xen_remap_memory(); xen_setup_mfn_list_list(); } -static void xen_write_cr2(unsigned long cr2) + +static noinstr void xen_write_cr2(unsigned long cr2) { this_cpu_read(xen_vcpu)->arch.cr2 = cr2; } @@ -2078,67 +2079,69 @@ static void xen_leave_lazy_mmu(void) preempt_enable(); } -static const struct pv_mmu_ops xen_mmu_ops __initconst = { - .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2), - .write_cr2 = xen_write_cr2, +static const typeof(pv_ops) xen_mmu_ops __initconst = { + .mmu = { + .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2), + .write_cr2 = xen_write_cr2, - .read_cr3 = xen_read_cr3, - .write_cr3 = xen_write_cr3_init, + .read_cr3 = xen_read_cr3, + .write_cr3 = xen_write_cr3_init, - .flush_tlb_user = xen_flush_tlb, - .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_one_user = xen_flush_tlb_one_user, - .flush_tlb_multi = xen_flush_tlb_multi, - .tlb_remove_table = tlb_remove_table, + .flush_tlb_user = xen_flush_tlb, + .flush_tlb_kernel = xen_flush_tlb, + .flush_tlb_one_user = xen_flush_tlb_one_user, + .flush_tlb_multi = xen_flush_tlb_multi, + .tlb_remove_table = tlb_remove_table, - .pgd_alloc = xen_pgd_alloc, - .pgd_free = xen_pgd_free, + .pgd_alloc = xen_pgd_alloc, + .pgd_free = xen_pgd_free, - .alloc_pte = xen_alloc_pte_init, - .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pmd_init, - .release_pmd = xen_release_pmd_init, + .alloc_pte = xen_alloc_pte_init, + .release_pte = xen_release_pte_init, + .alloc_pmd = xen_alloc_pmd_init, + .release_pmd = xen_release_pmd_init, - .set_pte = xen_set_pte_init, - .set_pmd = xen_set_pmd_hyper, + .set_pte = xen_set_pte_init, + .set_pmd = xen_set_pmd_hyper, - .ptep_modify_prot_start = xen_ptep_modify_prot_start, - .ptep_modify_prot_commit = xen_ptep_modify_prot_commit, + .ptep_modify_prot_start = xen_ptep_modify_prot_start, + .ptep_modify_prot_commit = xen_ptep_modify_prot_commit, - .pte_val = PV_CALLEE_SAVE(xen_pte_val), - .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), + .pte_val = PV_CALLEE_SAVE(xen_pte_val), + .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), - .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), - .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), + .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), + .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), - .set_pud = xen_set_pud_hyper, + .set_pud = xen_set_pud_hyper, - .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), - .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), + .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), + .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), - .pud_val = PV_CALLEE_SAVE(xen_pud_val), - .make_pud = PV_CALLEE_SAVE(xen_make_pud), - .set_p4d = xen_set_p4d_hyper, + .pud_val = PV_CALLEE_SAVE(xen_pud_val), + .make_pud = PV_CALLEE_SAVE(xen_make_pud), + .set_p4d = xen_set_p4d_hyper, - .alloc_pud = xen_alloc_pmd_init, - .release_pud = xen_release_pmd_init, + .alloc_pud = xen_alloc_pmd_init, + .release_pud = xen_release_pmd_init, #if CONFIG_PGTABLE_LEVELS >= 5 - .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), - .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), + .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), + .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), #endif - .activate_mm = xen_activate_mm, - .dup_mmap = xen_dup_mmap, - .exit_mmap = xen_exit_mmap, + .activate_mm = xen_activate_mm, + .dup_mmap = xen_dup_mmap, + .exit_mmap = xen_exit_mmap, - .lazy_mode = { - .enter = paravirt_enter_lazy_mmu, - .leave = xen_leave_lazy_mmu, - .flush = paravirt_flush_lazy_mmu, - }, + .lazy_mode = { + .enter = paravirt_enter_lazy_mmu, + .leave = xen_leave_lazy_mmu, + .flush = paravirt_flush_lazy_mmu, + }, - .set_fixmap = xen_set_fixmap, + .set_fixmap = xen_set_fixmap, + }, }; void __init xen_init_mmu_ops(void) @@ -2146,7 +2149,7 @@ void __init xen_init_mmu_ops(void) x86_init.paging.pagetable_init = xen_pagetable_init; x86_init.hyper.init_after_bootmem = xen_after_bootmem; - pv_ops.mmu = xen_mmu_ops; + pv_ops.mmu = xen_mmu_ops.mmu; memset(dummy_mapping, 0xff, PAGE_SIZE); } @@ -2398,7 +2401,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages) + unsigned int domid, bool no_translate) { int err = 0; struct remap_data rmd; diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 54f9aa7e8457..46df59aeaa06 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -18,7 +18,7 @@ #endif #include <linux/export.h> -int xen_swiotlb __read_mostly; +static int xen_swiotlb __read_mostly; /* * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary @@ -56,7 +56,7 @@ int __init pci_xen_swiotlb_detect(void) return xen_swiotlb; } -void __init pci_xen_swiotlb_init(void) +static void __init pci_xen_swiotlb_init(void) { if (xen_swiotlb) { xen_swiotlb_init_early(); diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 96afadf9878e..7ed56c6075b0 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -290,8 +290,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) gdt = get_cpu_gdt_rw(cpu); - memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); - /* * Bring up the CPU in cpu_bringup_and_idle() with the stack * pointing just below where pt_regs would be if it were a normal @@ -308,8 +306,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) xen_copy_trap_info(ctxt->trap_ctxt); - ctxt->ldt_ents = 0; - BUG_ON((unsigned long)gdt & ~PAGE_MASK); gdt_mfn = arbitrary_virt_to_mfn(gdt); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1e626444712b..220dd9678494 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -21,6 +21,45 @@ #include <linux/init.h> #include <linux/linkage.h> +.pushsection .noinstr.text, "ax" +/* + * Disabling events is simply a matter of making the event mask + * non-zero. + */ +SYM_FUNC_START(xen_irq_disable_direct) + movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + ret +SYM_FUNC_END(xen_irq_disable_direct) + +/* + * Force an event check by making a hypercall, but preserve regs + * before making the call. + */ +SYM_FUNC_START(check_events) + FRAME_BEGIN + push %rax + push %rcx + push %rdx + push %rsi + push %rdi + push %r8 + push %r9 + push %r10 + push %r11 + call xen_force_evtchn_callback + pop %r11 + pop %r10 + pop %r9 + pop %r8 + pop %rdi + pop %rsi + pop %rdx + pop %rcx + pop %rax + FRAME_END + ret +SYM_FUNC_END(check_events) + /* * Enable events. This clears the event mask and tests the pending * event status with one and operation. If there are pending events, @@ -47,16 +86,6 @@ SYM_FUNC_START(xen_irq_enable_direct) ret SYM_FUNC_END(xen_irq_enable_direct) - -/* - * Disabling events is simply a matter of making the event mask - * non-zero. - */ -SYM_FUNC_START(xen_irq_disable_direct) - movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask - ret -SYM_FUNC_END(xen_irq_disable_direct) - /* * (xen_)save_fl is used to get the current interrupt enable status. * Callers expect the status to be in X86_EFLAGS_IF, and other bits @@ -73,35 +102,6 @@ SYM_FUNC_START(xen_save_fl_direct) ret SYM_FUNC_END(xen_save_fl_direct) -/* - * Force an event check by making a hypercall, but preserve regs - * before making the call. - */ -SYM_FUNC_START(check_events) - FRAME_BEGIN - push %rax - push %rcx - push %rdx - push %rsi - push %rdi - push %r8 - push %r9 - push %r10 - push %r11 - call xen_force_evtchn_callback - pop %r11 - pop %r10 - pop %r9 - pop %r8 - pop %rdi - pop %rsi - pop %rdx - pop %rcx - pop %rax - FRAME_END - ret -SYM_FUNC_END(check_events) - SYM_FUNC_START(xen_read_cr2) FRAME_BEGIN _ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX @@ -116,6 +116,7 @@ SYM_FUNC_START(xen_read_cr2_direct) FRAME_END ret SYM_FUNC_END(xen_read_cr2_direct); +.popsection .macro xen_pv_trap name SYM_CODE_START(xen_\name) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index cb6538ae2fe0..9e27b86a0c31 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -20,6 +20,23 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> +.pushsection .noinstr.text, "ax" + .balign PAGE_SIZE +SYM_CODE_START(hypercall_page) + .rept (PAGE_SIZE / 32) + UNWIND_HINT_FUNC + .skip 31, 0x90 + ret + .endr + +#define HYPERCALL(n) \ + .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ + .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 +#include <asm/xen-hypercalls.h> +#undef HYPERCALL +SYM_CODE_END(hypercall_page) +.popsection + #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -64,23 +81,6 @@ SYM_CODE_END(asm_cpu_bringup_and_idle) #endif #endif -.pushsection .text - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - .skip 31, 0x90 - ret - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include <asm/xen-hypercalls.h> -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 8d7ec49a35fb..8bc8b72a205d 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -51,6 +51,7 @@ void __init xen_remap_memory(void); phys_addr_t __init xen_find_free_area(phys_addr_t size); char * __init xen_memory_setup(void); void __init xen_arch_setup(void); +void xen_banner(void); void xen_enable_sysenter(void); void xen_enable_syscall(void); void xen_vcpu_restore(void); @@ -109,7 +110,7 @@ static inline void xen_uninit_lock_cpu(int cpu) struct dom0_vga_console_info; -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, @@ -118,6 +119,8 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, } #endif +void xen_add_preferred_consoles(void); + void __init xen_init_apic(void); #ifdef CONFIG_XEN_EFI |