summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/Makefile14
-rw-r--r--arch/x86/boot/compressed/misc.h12
-rw-r--r--arch/x86/boot/compressed/sev.c8
-rw-r--r--arch/x86/configs/xen.config1
-rw-r--r--arch/x86/crypto/blowfish-x86_64-asm_64.S5
-rw-r--r--arch/x86/entry/entry_64_compat.S2
-rw-r--r--arch/x86/entry/vdso/Makefile3
-rw-r--r--arch/x86/events/intel/core.c47
-rw-r--r--arch/x86/events/intel/ds.c22
-rw-r--r--arch/x86/events/intel/lbr.c8
-rw-r--r--arch/x86/events/intel/uncore_snb.c18
-rw-r--r--arch/x86/events/perf_event.h2
-rw-r--r--arch/x86/include/asm/acrn.h14
-rw-r--r--arch/x86/include/asm/bitops.h21
-rw-r--r--arch/x86/include/asm/cfi.h22
-rw-r--r--arch/x86/include/asm/cpufeature.h15
-rw-r--r--arch/x86/include/asm/cpufeatures.h5
-rw-r--r--arch/x86/include/asm/extable_fixup_types.h2
-rw-r--r--arch/x86/include/asm/ibt.h11
-rw-r--r--arch/x86/include/asm/intel-family.h5
-rw-r--r--arch/x86/include/asm/irq_stack.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h3
-rw-r--r--arch/x86/include/asm/linkage.h12
-rw-r--r--arch/x86/include/asm/mc146818rtc.h2
-rw-r--r--arch/x86/include/asm/mce.h1
-rw-r--r--arch/x86/include/asm/nospec-branch.h92
-rw-r--r--arch/x86/include/asm/paravirt_types.h27
-rw-r--r--arch/x86/include/asm/rmwcc.h6
-rw-r--r--arch/x86/include/asm/sev.h2
-rw-r--r--arch/x86/include/asm/smp.h25
-rw-r--r--arch/x86/include/asm/word-at-a-time.h46
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/alternative.c45
-rw-r--r--arch/x86/kernel/cfi.c86
-rw-r--r--arch/x86/kernel/cpu/acrn.c3
-rw-r--r--arch/x86/kernel/cpu/bugs.c14
-rw-r--r--arch/x86/kernel/cpu/common.c42
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.c26
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.h2
-rw-r--r--arch/x86/kernel/cpu/sgx/main.c15
-rw-r--r--arch/x86/kernel/irq_32.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c2
-rw-r--r--arch/x86/kernel/rtc.c63
-rw-r--r--arch/x86/kernel/sev.c18
-rw-r--r--arch/x86/kernel/traps.c4
-rw-r--r--arch/x86/kernel/unwind_orc.c15
-rw-r--r--arch/x86/kernel/x86_init.c2
-rw-r--r--arch/x86/kvm/cpuid.c13
-rw-r--r--arch/x86/kvm/emulate.c31
-rw-r--r--arch/x86/kvm/mmu/mmu.c76
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h4
-rw-r--r--arch/x86/kvm/mmu/spte.h14
-rw-r--r--arch/x86/kvm/vmx/vmx.c3
-rw-r--r--arch/x86/kvm/x86.c102
-rw-r--r--arch/x86/lib/memcpy_64.S3
-rw-r--r--arch/x86/lib/usercopy.c2
-rw-r--r--arch/x86/mm/Makefile3
-rw-r--r--arch/x86/mm/extable.c55
-rw-r--r--arch/x86/mm/init_64.c2
-rw-r--r--arch/x86/mm/pat/memtype.c10
-rw-r--r--arch/x86/purgatory/Makefile4
-rw-r--r--arch/x86/tools/relocs.c1
-rw-r--r--arch/x86/um/shared/sysdep/syscalls_32.h5
-rw-r--r--arch/x86/um/tls_32.c6
-rw-r--r--arch/x86/um/vdso/Makefile2
-rw-r--r--arch/x86/xen/enlighten_pv.c3
67 files changed, 745 insertions, 393 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f9920f1341c8..cabd6e13f549 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -107,6 +107,8 @@ config X86
select ARCH_SUPPORTS_PAGE_TABLE_CHECK if X86_64
select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096
+ select ARCH_SUPPORTS_CFI_CLANG if X86_64
+ select ARCH_USES_CFI_TRAPS if X86_64 && CFI_CLANG
select ARCH_SUPPORTS_LTO_CLANG
select ARCH_SUPPORTS_LTO_CLANG_THIN
select ARCH_USE_BUILTIN_BSWAP
@@ -257,6 +259,7 @@ config X86
select HAVE_STATIC_CALL_INLINE if HAVE_OBJTOOL
select HAVE_PREEMPT_DYNAMIC_CALL
select HAVE_RSEQ
+ select HAVE_RUST if X86_64
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UACCESS_VALIDATION if HAVE_OBJTOOL
select HAVE_UNSTABLE_SCHED_CLOCK
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 7854685c5f25..2d7e640674c6 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -68,6 +68,7 @@ export BITS
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
#
KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
+KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
ifeq ($(CONFIG_X86_KERNEL_IBT),y)
#
@@ -155,8 +156,17 @@ else
cflags-$(CONFIG_GENERIC_CPU) += -mtune=generic
KBUILD_CFLAGS += $(cflags-y)
+ rustflags-$(CONFIG_MK8) += -Ctarget-cpu=k8
+ rustflags-$(CONFIG_MPSC) += -Ctarget-cpu=nocona
+ rustflags-$(CONFIG_MCORE2) += -Ctarget-cpu=core2
+ rustflags-$(CONFIG_MATOM) += -Ctarget-cpu=atom
+ rustflags-$(CONFIG_GENERIC_CPU) += -Ztune-cpu=generic
+ KBUILD_RUSTFLAGS += $(rustflags-y)
+
KBUILD_CFLAGS += -mno-red-zone
KBUILD_CFLAGS += -mcmodel=kernel
+ KBUILD_RUSTFLAGS += -Cno-redzone=y
+ KBUILD_RUSTFLAGS += -Ccode-model=kernel
endif
#
@@ -286,10 +296,6 @@ vdso_install:
archprepare: checkbin
checkbin:
-ifndef CONFIG_CC_HAS_ASM_GOTO
- @echo Compiler lacks asm-goto support.
- @exit 1
-endif
ifdef CONFIG_RETPOLINE
ifeq ($(RETPOLINE_CFLAGS),)
@echo "You are building kernel with non-retpoline compiler." >&2
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 4910bf230d7b..62208ec04ca4 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -132,7 +132,17 @@ void snp_set_page_private(unsigned long paddr);
void snp_set_page_shared(unsigned long paddr);
void sev_prep_identity_maps(unsigned long top_level_pgt);
#else
-static inline void sev_enable(struct boot_params *bp) { }
+static inline void sev_enable(struct boot_params *bp)
+{
+ /*
+ * bp->cc_blob_address should only be set by boot/compressed kernel.
+ * Initialize it to 0 unconditionally (thus here in this stub too) to
+ * ensure that uninitialized values from buggy bootloaders aren't
+ * propagated.
+ */
+ if (bp)
+ bp->cc_blob_address = 0;
+}
static inline void sev_es_shutdown_ghcb(void) { }
static inline bool sev_es_check_ghcb_fault(unsigned long address)
{
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 52f989f6acc2..c93930d5ccbd 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -277,6 +277,14 @@ void sev_enable(struct boot_params *bp)
bool snp;
/*
+ * bp->cc_blob_address should only be set by boot/compressed kernel.
+ * Initialize it to 0 to ensure that uninitialized values from
+ * buggy bootloaders aren't propagated.
+ */
+ if (bp)
+ bp->cc_blob_address = 0;
+
+ /*
* Setup/preliminary detection of SNP. This will be sanity-checked
* against CPUID/MSR values later.
*/
diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config
index d9fc7139fd46..581296255b39 100644
--- a/arch/x86/configs/xen.config
+++ b/arch/x86/configs/xen.config
@@ -14,7 +14,6 @@ CONFIG_CPU_FREQ=y
# x86 xen specific config options
CONFIG_XEN_PVH=y
-CONFIG_XEN_MAX_DOMAIN_MEMORY=500
CONFIG_XEN_SAVE_RESTORE=y
# CONFIG_XEN_DEBUG_FS is not set
CONFIG_XEN_MCE_LOG=y
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 802d71582689..4a43e072d2d1 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
.file "blowfish-x86_64-asm.S"
.text
@@ -141,7 +142,7 @@ SYM_FUNC_START(__blowfish_enc_blk)
RET;
SYM_FUNC_END(__blowfish_enc_blk)
-SYM_FUNC_START(blowfish_dec_blk)
+SYM_TYPED_FUNC_START(blowfish_dec_blk)
/* input:
* %rdi: ctx
* %rsi: dst
@@ -332,7 +333,7 @@ SYM_FUNC_START(__blowfish_enc_blk_4way)
RET;
SYM_FUNC_END(__blowfish_enc_blk_4way)
-SYM_FUNC_START(blowfish_dec_blk_4way)
+SYM_TYPED_FUNC_START(blowfish_dec_blk_4way)
/* input:
* %rdi: ctx
* %rsi: dst
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 682338e7e2a3..4dd19819053a 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -311,7 +311,7 @@ SYM_CODE_START(entry_INT80_compat)
* Interrupts are off on entry.
*/
ASM_CLAC /* Do this early to minimize exposure */
- SWAPGS
+ ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
/*
* User tracing code (ptrace or signal handlers) might assume that
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 12f6c4d714cd..381d3333b996 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),)
endif
endif
-$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
$(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO
#
@@ -153,6 +153,7 @@ KBUILD_CFLAGS_32 := $(filter-out $(RANDSTRUCT_CFLAGS),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_CFI),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
KBUILD_CFLAGS_32 += -fno-stack-protector
KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2db93498ff71..c20d8cd47c48 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
+EVENT_ATTR_STR(mem-loads, mem_ld_grt, "event=0xd0,umask=0x5,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_grt, "event=0xd0,umask=0x6");
+
+static struct attribute *grt_mem_attrs[] = {
+ EVENT_PTR(mem_ld_grt),
+ EVENT_PTR(mem_st_grt),
+ NULL
+};
+
static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
@@ -4052,8 +4061,9 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
/* Disable guest PEBS if host PEBS is enabled. */
arr[pebs_enable].guest = 0;
} else {
- /* Disable guest PEBS for cross-mapped PEBS counters. */
+ /* Disable guest PEBS thoroughly for cross-mapped PEBS counters. */
arr[pebs_enable].guest &= ~kvm_pmu->host_cross_mapped_mask;
+ arr[global_ctrl].guest &= ~kvm_pmu->host_cross_mapped_mask;
/* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */
arr[global_ctrl].guest |= arr[pebs_enable].guest;
}
@@ -5974,6 +5984,36 @@ __init int intel_pmu_init(void)
name = "Tremont";
break;
+ case INTEL_FAM6_ALDERLAKE_N:
+ x86_pmu.mid_ack = true;
+ memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+ x86_pmu.event_constraints = intel_slm_event_constraints;
+ x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_grt_extra_regs;
+
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.pebs_block = true;
+ x86_pmu.lbr_pt_coexist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+ intel_pmu_pebs_data_source_grt();
+ x86_pmu.pebs_latency_data = adl_latency_data_small;
+ x86_pmu.get_event_constraints = tnt_get_event_constraints;
+ x86_pmu.limit_period = spr_limit_period;
+ td_attr = tnt_events_attrs;
+ mem_attr = grt_mem_attrs;
+ extra_attr = nhm_format_attr;
+ pr_cont("Gracemont events, ");
+ name = "gracemont";
+ break;
+
case INTEL_FAM6_WESTMERE:
case INTEL_FAM6_WESTMERE_EP:
case INTEL_FAM6_WESTMERE_EX:
@@ -6291,10 +6331,8 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_aliases = NULL;
x86_pmu.pebs_prec_dist = true;
x86_pmu.pebs_block = true;
- x86_pmu.pebs_capable = ~0ULL;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
@@ -6318,7 +6356,6 @@ __init int intel_pmu_init(void)
case INTEL_FAM6_ALDERLAKE:
case INTEL_FAM6_ALDERLAKE_L:
- case INTEL_FAM6_ALDERLAKE_N:
case INTEL_FAM6_RAPTORLAKE:
case INTEL_FAM6_RAPTORLAKE_P:
/*
@@ -6337,10 +6374,8 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_aliases = NULL;
x86_pmu.pebs_prec_dist = true;
x86_pmu.pebs_block = true;
- x86_pmu.pebs_capable = ~0ULL;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
x86_pmu.lbr_pt_coexist = true;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ba60427caa6d..ac973c6f82ad 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem)
__intel_pmu_pebs_data_source_skl(pmem, pebs_data_source);
}
-static void __init intel_pmu_pebs_data_source_grt(u64 *data_source)
+static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source)
{
data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
}
+void __init intel_pmu_pebs_data_source_grt(void)
+{
+ __intel_pmu_pebs_data_source_grt(pebs_data_source);
+}
+
void __init intel_pmu_pebs_data_source_adl(void)
{
u64 *data_source;
@@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void)
data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
- intel_pmu_pebs_data_source_grt(data_source);
+ __intel_pmu_pebs_data_source_grt(data_source);
}
static u64 precise_store_data(u64 status)
@@ -291,6 +296,7 @@ static u64 load_latency_data(struct perf_event *event, u64 status)
static u64 store_latency_data(struct perf_event *event, u64 status)
{
union intel_x86_pebs_dse dse;
+ union perf_mem_data_src src;
u64 val;
dse.val = status;
@@ -304,7 +310,14 @@ static u64 store_latency_data(struct perf_event *event, u64 status)
val |= P(BLK, NA);
- return val;
+ /*
+ * the pebs_data_source table is only for loads
+ * so override the mem_op to say STORE instead
+ */
+ src.val = val;
+ src.mem_op = P(OP,STORE);
+
+ return src.val;
}
struct pebs_record_core {
@@ -822,7 +835,7 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
struct event_constraint intel_grt_pebs_event_constraints[] = {
/* Allow all events as PEBS with no flags */
- INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0xf),
+ INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3),
INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf),
EVENT_CONSTRAINT_END
};
@@ -2262,6 +2275,7 @@ void __init intel_ds_init(void)
PERF_SAMPLE_BRANCH_STACK |
PERF_SAMPLE_TIME;
x86_pmu.flags |= PMU_FL_PEBS_ALL;
+ x86_pmu.pebs_capable = ~0ULL;
pebs_qual = "-baseline";
x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
} else {
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4f70fb6c2c1e..47fca6a7a8bc 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1097,6 +1097,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
reg->config = mask;
+
+ /*
+ * The Arch LBR HW can retrieve the common branch types
+ * from the LBR_INFO. It doesn't require the high overhead
+ * SW disassemble.
+ * Enable the branch type by default for the Arch LBR.
+ */
+ reg->reg |= X86_BR_TYPE_SAVE;
return 0;
}
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index ce440011cc4e..1ef4f7861e2e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -841,6 +841,22 @@ int snb_pci2phy_map_init(int devid)
return 0;
}
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ /*
+ * SNB IMC counters are 32-bit and are laid out back to back
+ * in MMIO space. Therefore we must use a 32-bit accessor function
+ * using readq() from uncore_mmio_read_counter() causes problems
+ * because it is reading 64-bit at a time. This is okay for the
+ * uncore_perf_event_update() function because it drops the upper
+ * 32-bits but not okay for plain uncore_read_counter() as invoked
+ * in uncore_pmu_event_start().
+ */
+ return (u64)readl(box->io_addr + hwc->event_base);
+}
+
static struct pmu snb_uncore_imc_pmu = {
.task_ctx_nr = perf_invalid_context,
.event_init = snb_uncore_imc_event_init,
@@ -860,7 +876,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
.disable_event = snb_uncore_imc_disable_event,
.enable_event = snb_uncore_imc_enable_event,
.hw_config = snb_uncore_imc_hw_config,
- .read_counter = uncore_mmio_read_counter,
+ .read_counter = snb_uncore_imc_read_counter,
};
static struct intel_uncore_type snb_uncore_imc = {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba3d24a6a4ec..266143abcbd8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1516,6 +1516,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem);
void intel_pmu_pebs_data_source_adl(void);
+void intel_pmu_pebs_data_source_grt(void);
+
int intel_pmu_setup_lbr_filter(struct perf_event *event);
void intel_pt_interrupt(void);
diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h
index e003a01b7c67..1dd14381bcb6 100644
--- a/arch/x86/include/asm/acrn.h
+++ b/arch/x86/include/asm/acrn.h
@@ -10,6 +10,15 @@
/* Bit 0 indicates whether guest VM is privileged */
#define ACRN_FEATURE_PRIVILEGED_VM BIT(0)
+/*
+ * Timing Information.
+ * This leaf returns the current TSC frequency in kHz.
+ *
+ * EAX: (Virtual) TSC frequency in kHz.
+ * EBX, ECX, EDX: RESERVED (reserved fields are set to zero).
+ */
+#define ACRN_CPUID_TIMING_INFO 0x40000010
+
void acrn_setup_intr_handler(void (*handler)(void));
void acrn_remove_intr_handler(void);
@@ -21,6 +30,11 @@ static inline u32 acrn_cpuid_base(void)
return 0;
}
+static inline unsigned long acrn_get_tsc_khz(void)
+{
+ return cpuid_eax(ACRN_CPUID_TIMING_INFO);
+}
+
/*
* Hypercalls for ACRN
*
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 973c6bd17f98..0fe9de58af31 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l
(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
}
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+ bool oldbit;
+
+ asm volatile("testb %2,%1"
+ CC_SET(nz)
+ : CC_OUT(nz) (oldbit)
+ : "m" (((unsigned char *)addr)[nr >> 3]),
+ "i" (1 << (nr & 7))
+ :"memory");
+
+ return oldbit;
+}
+
static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
{
bool oldbit;
@@ -226,6 +240,13 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
variable_test_bit(nr, addr);
}
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+ return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+ variable_test_bit(nr, addr);
+}
+
/**
* __ffs - find first set bit in word
* @word: The word to search
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
new file mode 100644
index 000000000000..58dacd90daef
--- /dev/null
+++ b/arch/x86/include/asm/cfi.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CFI_H
+#define _ASM_X86_CFI_H
+
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2022 Google LLC
+ */
+
+#include <linux/cfi.h>
+
+#ifdef CONFIG_CFI_CLANG
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
+#else
+static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+ return BUG_TRAP_TYPE_NONE;
+}
+#endif /* CONFIG_CFI_CLANG */
+
+#endif /* _ASM_X86_CFI_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ea34cc31b047..1a85e1fb0922 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -155,20 +155,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
-#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO)
-
-/*
- * Workaround for the sake of BPF compilation which utilizes kernel
- * headers, but clang does not support ASM GOTO and fails the build.
- */
-#ifndef __BPF_TRACING__
-#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
-#endif
-
-#define static_cpu_has(bit) boot_cpu_has(bit)
-
-#else
-
/*
* Static testing of CPU features. Used the same as boot_cpu_has(). It
* statically patches the target code for additional performance. Use
@@ -208,7 +194,6 @@ t_no:
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
-#endif
#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 235dc85c91c3..ef4775c6db01 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -457,7 +457,8 @@
#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */
-#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 503622627400..991e31cfde94 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -64,4 +64,6 @@
#define EX_TYPE_UCOPY_LEN4 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
#define EX_TYPE_UCOPY_LEN8 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
+#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */
+
#endif
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 689880eca9ba..9b08082a5d9f 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -31,6 +31,16 @@
#define __noendbr __attribute__((nocf_check))
+/*
+ * Create a dummy function pointer reference to prevent objtool from marking
+ * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by
+ * apply_ibt_endbr()).
+ */
+#define IBT_NOSEAL(fname) \
+ ".pushsection .discard.ibt_endbr_noseal\n\t" \
+ _ASM_PTR fname "\n\t" \
+ ".popsection\n\t"
+
static inline __attribute_const__ u32 gen_endbr(void)
{
u32 endbr;
@@ -84,6 +94,7 @@ extern __noendbr void ibt_restore(u64 save);
#ifndef __ASSEMBLY__
#define ASM_ENDBR
+#define IBT_NOSEAL(name)
#define __noendbr
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index def6ca121111..5d75fe229342 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -27,6 +27,7 @@
* _X - regular server parts
* _D - micro server parts
* _N,_P - other mobile parts
+ * _S - other client parts
*
* Historical OPTDIFFs:
*
@@ -112,6 +113,10 @@
#define INTEL_FAM6_RAPTORLAKE 0xB7
#define INTEL_FAM6_RAPTORLAKE_P 0xBA
+#define INTEL_FAM6_RAPTORLAKE_S 0xBF
+
+#define INTEL_FAM6_METEORLAKE 0xAC
+#define INTEL_FAM6_METEORLAKE_L 0xAA
/* "Small Core" Processors (Atom) */
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 63f818aedf77..147cb8fdda92 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -203,7 +203,7 @@
IRQ_CONSTRAINTS, regs, vector); \
}
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
/*
* 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
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5ffa578cafe1..aa381ab69a19 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -53,7 +53,7 @@
#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
+#define KVM_INTERNAL_MEM_SLOTS 3
#define KVM_HALT_POLL_NS_DEFAULT 200000
@@ -729,6 +729,7 @@ struct kvm_vcpu_arch {
struct fpu_guest guest_fpu;
u64 xcr0;
+ u64 guest_supported_xcr0;
struct kvm_pio_request pio;
void *pio_data;
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 73ca20049835..f484d656d34e 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -43,6 +43,18 @@
#endif /* __ASSEMBLY__ */
+#define __CFI_TYPE(name) \
+ SYM_START(__cfi_##name, SYM_L_LOCAL, SYM_A_NONE) \
+ .fill 11, 1, 0x90 ASM_NL \
+ .byte 0xb8 ASM_NL \
+ .long __kcfi_typeid_##name ASM_NL \
+ SYM_FUNC_END(__cfi_##name)
+
+/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
+#define SYM_TYPED_FUNC_START(name) \
+ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \
+ ENDBR
+
/* SYM_FUNC_START -- use for global functions */
#define SYM_FUNC_START(name) \
SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 97198001e567..6115bb3d5795 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -95,7 +95,7 @@ static inline unsigned char current_lock_cmos_reg(void)
unsigned char rtc_cmos_read(unsigned char addr);
void rtc_cmos_write(unsigned char val, unsigned char addr);
-extern int mach_set_rtc_mmss(const struct timespec64 *now);
+extern int mach_set_cmos_time(const struct timespec64 *now);
extern void mach_get_cmos_time(struct timespec64 *now);
#define RTC_IRQ 8
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index cc73061e7255..6e986088817d 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -42,6 +42,7 @@
#define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */
#define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38)
#define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT)
+#define MCI_STATUS_MSCOD(m) (((m) >> 16) & 0xffff)
/* AMD-specific bits */
#define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index e64fd20778b6..c936ce9f0c47 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -35,33 +35,56 @@
#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
/*
+ * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN.
+ */
+#define __FILL_RETURN_SLOT \
+ ANNOTATE_INTRA_FUNCTION_CALL; \
+ call 772f; \
+ int3; \
+772:
+
+/*
+ * Stuff the entire RSB.
+ *
* Google experimented with loop-unrolling and this turned out to be
* the optimal version - two calls, each with their own speculation
* trap should their return address end up getting used, in a loop.
*/
-#define __FILL_RETURN_BUFFER(reg, nr, sp) \
- mov $(nr/2), reg; \
-771: \
- ANNOTATE_INTRA_FUNCTION_CALL; \
- call 772f; \
-773: /* speculation trap */ \
- UNWIND_HINT_EMPTY; \
- pause; \
- lfence; \
- jmp 773b; \
-772: \
- ANNOTATE_INTRA_FUNCTION_CALL; \
- call 774f; \
-775: /* speculation trap */ \
- UNWIND_HINT_EMPTY; \
- pause; \
- lfence; \
- jmp 775b; \
-774: \
- add $(BITS_PER_LONG/8) * 2, sp; \
- dec reg; \
- jnz 771b; \
- /* barrier for jnz misprediction */ \
+#ifdef CONFIG_X86_64
+#define __FILL_RETURN_BUFFER(reg, nr) \
+ mov $(nr/2), reg; \
+771: \
+ __FILL_RETURN_SLOT \
+ __FILL_RETURN_SLOT \
+ add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \
+ dec reg; \
+ jnz 771b; \
+ /* barrier for jnz misprediction */ \
+ lfence;
+#else
+/*
+ * i386 doesn't unconditionally have LFENCE, as such it can't
+ * do a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr) \
+ .rept nr; \
+ __FILL_RETURN_SLOT; \
+ .endr; \
+ add $(BITS_PER_LONG/8) * nr, %_ASM_SP;
+#endif
+
+/*
+ * Stuff a single RSB slot.
+ *
+ * To mitigate Post-Barrier RSB speculation, one CALL instruction must be
+ * forced to retire before letting a RET instruction execute.
+ *
+ * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed
+ * before this point.
+ */
+#define __FILL_ONE_RETURN \
+ __FILL_RETURN_SLOT \
+ add $(BITS_PER_LONG/8), %_ASM_SP; \
lfence;
#ifdef __ASSEMBLY__
@@ -132,28 +155,15 @@
#endif
.endm
-.macro ISSUE_UNBALANCED_RET_GUARD
- ANNOTATE_INTRA_FUNCTION_CALL
- call .Lunbalanced_ret_guard_\@
- int3
-.Lunbalanced_ret_guard_\@:
- add $(BITS_PER_LONG/8), %_ASM_SP
- lfence
-.endm
-
/*
* A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
* monstrosity above, manually.
*/
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2
-.ifb \ftr2
- ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
-.else
- ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2
-.endif
- __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
-.Lunbalanced_\@:
- ISSUE_UNBALANCED_RET_GUARD
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS)
+ ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \
+ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \
+ __stringify(__FILL_ONE_RETURN), \ftr2
+
.Lskip_rsb_\@:
.endm
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 89df6c6617f5..b1ab5d94881b 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -328,7 +328,7 @@ int paravirt_disable_iospace(void);
* Unfortunately, this is a relatively slow operation for modern CPUs,
* because it cannot necessarily determine what the destination
* address is. In this case, the address is a runtime constant, so at
- * the very least we can patch the call to e a simple direct call, or
+ * the very least we can patch the call to a simple direct call, or,
* ideally, patch an inline implementation into the callsite. (Direct
* calls are essentially free, because the call and return addresses
* are completely predictable.)
@@ -339,10 +339,10 @@ int paravirt_disable_iospace(void);
* on the stack. All caller-save registers (eax,edx,ecx) are expected
* to be modified (either clobbered or used for return values).
* X86_64, on the other hand, already specifies a register-based calling
- * conventions, returning at %rax, with parameters going on %rdi, %rsi,
+ * conventions, returning at %rax, with parameters going in %rdi, %rsi,
* %rdx, and %rcx. Note that for this reason, x86_64 does not need any
* special handling for dealing with 4 arguments, unlike i386.
- * However, x86_64 also have to clobber all caller saved registers, which
+ * However, x86_64 also has to clobber all caller saved registers, which
* unfortunately, are quite a bit (r8 - r11)
*
* The call instruction itself is marked by placing its start address
@@ -360,22 +360,22 @@ int paravirt_disable_iospace(void);
* There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
* It could be extended to more arguments, but there would be little
* to be gained from that. For each number of arguments, there are
- * the two VCALL and CALL variants for void and non-void functions.
+ * two VCALL and CALL variants for void and non-void functions.
*
* When there is a return value, the invoker of the macro must specify
* the return type. The macro then uses sizeof() on that type to
- * determine whether its a 32 or 64 bit value, and places the return
+ * determine whether it's a 32 or 64 bit value and places the return
* in the right register(s) (just %eax for 32-bit, and %edx:%eax for
- * 64-bit). For x86_64 machines, it just returns at %rax regardless of
+ * 64-bit). For x86_64 machines, it just returns in %rax regardless of
* the return value size.
*
- * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
+ * 64-bit arguments are passed as a pair of adjacent 32-bit arguments;
* i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments
* in low,high order
*
* Small structures are passed and returned in registers. The macro
* calling convention can't directly deal with this, so the wrapper
- * functions must do this.
+ * functions must do it.
*
* These PVOP_* macros are only defined within this header. This
* means that all uses must be wrapped in inline functions. This also
@@ -414,8 +414,17 @@ int paravirt_disable_iospace(void);
"=c" (__ecx)
#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax)
-/* void functions are still allowed [re]ax for scratch */
+/*
+ * void functions are still allowed [re]ax for scratch.
+ *
+ * The ZERO_CALL_USED REGS feature may end up zeroing out callee-saved
+ * registers. Make sure we model this with the appropriate clobbers.
+ */
+#ifdef CONFIG_ZERO_CALL_USED_REGS
+#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), PVOP_VCALL_CLOBBERS
+#else
#define PVOP_VCALLEE_CLOBBERS "=a" (__eax)
+#endif
#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS
#define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11"
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 8a9eba191516..7fa611216417 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -11,7 +11,7 @@
#define __CLOBBERS_MEM(clb...) "memory", ## clb
-#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO)
+#ifndef __GCC_ASM_FLAG_OUTPUTS__
/* Use asm goto */
@@ -27,7 +27,7 @@ cc_label: c = true; \
c; \
})
-#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
/* Use flags output or a set instruction */
@@ -40,7 +40,7 @@ cc_label: c = true; \
c; \
})
-#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
#define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \
__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 4a23e52fe0ee..ebc271bb6d8e 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -195,7 +195,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
void snp_set_wakeup_secondary_cpu(void);
bool snp_init(struct boot_params *bp);
-void snp_abort(void);
+void __init __noreturn snp_abort(void);
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 81a0211a372d..a73bced40e24 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -21,16 +21,6 @@ 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)
-{
- 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);
@@ -172,6 +162,16 @@ extern int safe_smp_processor_id(void);
# define safe_smp_processor_id() smp_processor_id()
#endif
+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);
+}
+
#else /* !CONFIG_SMP */
#define wbinvd_on_cpu(cpu) wbinvd()
static inline int wbinvd_on_all_cpus(void)
@@ -179,6 +179,11 @@ static inline int wbinvd_on_all_cpus(void)
wbinvd();
return 0;
}
+
+static inline struct cpumask *cpu_llc_shared_mask(int cpu)
+{
+ return (struct cpumask *)cpumask_of(0);
+}
#endif /* CONFIG_SMP */
extern unsigned disabled_cpus;
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 8338b0432b50..46b4f1f7f354 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -77,58 +77,18 @@ static inline unsigned long find_zero(unsigned long mask)
* and the next page not being mapped, take the exception and
* return zeroes in the non-existing part.
*/
-#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
-
static inline unsigned long load_unaligned_zeropad(const void *addr)
{
- unsigned long offset, data;
unsigned long ret;
- asm_volatile_goto(
+ asm volatile(
"1: mov %[mem], %[ret]\n"
-
- _ASM_EXTABLE(1b, %l[do_exception])
-
- : [ret] "=r" (ret)
- : [mem] "m" (*(unsigned long *)addr)
- : : do_exception);
-
- return ret;
-
-do_exception:
- offset = (unsigned long)addr & (sizeof(long) - 1);
- addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
- data = *(unsigned long *)addr;
- ret = data >> offset * 8;
-
- return ret;
-}
-
-#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
-static inline unsigned long load_unaligned_zeropad(const void *addr)
-{
- unsigned long offset, data;
- unsigned long ret, err = 0;
-
- asm( "1: mov %[mem], %[ret]\n"
"2:\n"
-
- _ASM_EXTABLE_FAULT(1b, 2b)
-
- : [ret] "=&r" (ret), "+a" (err)
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD)
+ : [ret] "=r" (ret)
: [mem] "m" (*(unsigned long *)addr));
- if (unlikely(err)) {
- offset = (unsigned long)addr & (sizeof(long) - 1);
- addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
- data = *(unsigned long *)addr;
- ret = data >> offset * 8;
- }
-
return ret;
}
-#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a20a5ebfacd7..1286a73ebdbc 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -139,6 +139,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o
+obj-$(CONFIG_CFI_CLANG) += cfi.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 62f6b8b7c4a5..4f3204364caa 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1319,22 +1319,23 @@ struct bp_patching_desc {
atomic_t refs;
};
-static struct bp_patching_desc *bp_desc;
+static struct bp_patching_desc bp_desc;
static __always_inline
-struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
+struct bp_patching_desc *try_get_desc(void)
{
- /* rcu_dereference */
- struct bp_patching_desc *desc = __READ_ONCE(*descp);
+ struct bp_patching_desc *desc = &bp_desc;
- if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
+ if (!arch_atomic_inc_not_zero(&desc->refs))
return NULL;
return desc;
}
-static __always_inline void put_desc(struct bp_patching_desc *desc)
+static __always_inline void put_desc(void)
{
+ struct bp_patching_desc *desc = &bp_desc;
+
smp_mb__before_atomic();
arch_atomic_dec(&desc->refs);
}
@@ -1367,15 +1368,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
/*
* Having observed our INT3 instruction, we now must observe
- * bp_desc:
+ * bp_desc with non-zero refcount:
*
- * bp_desc = desc INT3
+ * bp_desc.refs = 1 INT3
* WMB RMB
- * write INT3 if (desc)
+ * write INT3 if (bp_desc.refs != 0)
*/
smp_rmb();
- desc = try_get_desc(&bp_desc);
+ desc = try_get_desc();
if (!desc)
return 0;
@@ -1429,7 +1430,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
ret = 1;
out_put:
- put_desc(desc);
+ put_desc();
return ret;
}
@@ -1460,18 +1461,20 @@ static int tp_vec_nr;
*/
static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
{
- struct bp_patching_desc desc = {
- .vec = tp,
- .nr_entries = nr_entries,
- .refs = ATOMIC_INIT(1),
- };
unsigned char int3 = INT3_INSN_OPCODE;
unsigned int i;
int do_sync;
lockdep_assert_held(&text_mutex);
- smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */
+ bp_desc.vec = tp;
+ bp_desc.nr_entries = nr_entries;
+
+ /*
+ * Corresponds to the implicit memory barrier in try_get_desc() to
+ * ensure reading a non-zero refcount provides up to date bp_desc data.
+ */
+ atomic_set_release(&bp_desc.refs, 1);
/*
* Corresponding read barrier in int3 notifier for making sure the
@@ -1559,12 +1562,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
text_poke_sync();
/*
- * Remove and synchronize_rcu(), except we have a very primitive
- * refcount based completion.
+ * Remove and wait for refs to be zero.
*/
- WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
- if (!atomic_dec_and_test(&desc.refs))
- atomic_cond_read_acquire(&desc.refs, !VAL);
+ if (!atomic_dec_and_test(&bp_desc.refs))
+ atomic_cond_read_acquire(&bp_desc.refs, !VAL);
}
static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
new file mode 100644
index 000000000000..8674a5c0c031
--- /dev/null
+++ b/arch/x86/kernel/cfi.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2022 Google LLC
+ */
+#include <asm/cfi.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+#include <linux/string.h>
+
+/*
+ * Returns the target address and the expected type when regs->ip points
+ * to a compiler-generated CFI trap.
+ */
+static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
+ u32 *type)
+{
+ char buffer[MAX_INSN_SIZE];
+ struct insn insn;
+ int offset = 0;
+
+ *target = *type = 0;
+
+ /*
+ * The compiler generates the following instruction sequence
+ * for indirect call checks:
+ *
+ *   movl -<id>, %r10d ; 6 bytes
+ * addl -4(%reg), %r10d ; 4 bytes
+ * je .Ltmp1 ; 2 bytes
+ * ud2 ; <- regs->ip
+ * .Ltmp1:
+ *
+ * We can decode the expected type and the target address from the
+ * movl/addl instructions.
+ */
+ if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 12, MAX_INSN_SIZE))
+ return false;
+ if (insn_decode_kernel(&insn, &buffer[offset]))
+ return false;
+ if (insn.opcode.value != 0xBA)
+ return false;
+
+ *type = -(u32)insn.immediate.value;
+
+ if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 6, MAX_INSN_SIZE))
+ return false;
+ if (insn_decode_kernel(&insn, &buffer[offset]))
+ return false;
+ if (insn.opcode.value != 0x3)
+ return false;
+
+ /* Read the target address from the register. */
+ offset = insn_get_modrm_rm_off(&insn, regs);
+ if (offset < 0)
+ return false;
+
+ *target = *(unsigned long *)((void *)regs + offset);
+
+ return true;
+}
+
+/*
+ * Checks if a ud2 trap is because of a CFI failure, and handles the trap
+ * if needed. Returns a bug_trap_type value similarly to report_bug.
+ */
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+ unsigned long target;
+ u32 type;
+
+ if (!is_cfi_trap(regs->ip))
+ return BUG_TRAP_TYPE_NONE;
+
+ if (!decode_cfi_insn(regs, &target, &type))
+ return report_cfi_failure_noaddr(regs, regs->ip);
+
+ return report_cfi_failure(regs, regs->ip, &target, type);
+}
+
+/*
+ * Ensure that __kcfi_typeid_ symbols are emitted for functions that may
+ * not be indirectly called with all configurations.
+ */
+__ADDRESSABLE(__memcpy)
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 23f5f27b5a02..485441b7f030 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -28,6 +28,9 @@ static void __init acrn_init_platform(void)
{
/* Setup the IDT for ACRN hypervisor callback */
alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback);
+
+ x86_platform.calibrate_tsc = acrn_get_tsc_khz;
+ x86_platform.calibrate_cpu = acrn_get_tsc_khz;
}
static bool acrn_x2apic_available(void)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 510d85261132..da7c361f47e0 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -433,7 +433,8 @@ static void __init mmio_select_mitigation(void)
u64 ia32_cap;
if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
- cpu_mitigations_off()) {
+ boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
+ cpu_mitigations_off()) {
mmio_mitigation = MMIO_MITIGATION_OFF;
return;
}
@@ -538,6 +539,8 @@ out:
pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
+ else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+ pr_info("MMIO Stale Data: Unknown: No mitigations\n");
}
static void __init md_clear_select_mitigation(void)
@@ -2275,6 +2278,9 @@ static ssize_t tsx_async_abort_show_state(char *buf)
static ssize_t mmio_stale_data_show_state(char *buf)
{
+ if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+ return sysfs_emit(buf, "Unknown: No mitigations\n");
+
if (mmio_mitigation == MMIO_MITIGATION_OFF)
return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
@@ -2421,6 +2427,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
return srbds_show_state(buf);
case X86_BUG_MMIO_STALE_DATA:
+ case X86_BUG_MMIO_UNKNOWN:
return mmio_stale_data_show_state(buf);
case X86_BUG_RETBLEED:
@@ -2480,7 +2487,10 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
{
- return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+ if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+ return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN);
+ else
+ return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
}
ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 64a73f415f03..3e508f239098 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1135,7 +1135,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#define NO_SWAPGS BIT(6)
#define NO_ITLB_MULTIHIT BIT(7)
#define NO_SPECTRE_V2 BIT(8)
-#define NO_EIBRS_PBRSB BIT(9)
+#define NO_MMIO BIT(9)
+#define NO_EIBRS_PBRSB BIT(10)
#define VULNWL(vendor, family, model, whitelist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1158,6 +1159,11 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL(VORTEX, 6, X86_MODEL_ANY, NO_SPECULATION),
/* Intel Family 6 */
+ VULNWL_INTEL(TIGERLAKE, NO_MMIO),
+ VULNWL_INTEL(TIGERLAKE_L, NO_MMIO),
+ VULNWL_INTEL(ALDERLAKE, NO_MMIO),
+ VULNWL_INTEL(ALDERLAKE_L, NO_MMIO),
+
VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
@@ -1176,9 +1182,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
+ VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
/*
* Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1193,18 +1199,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
/* AMD Family 0xf - 0x12 */
- VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
- VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
/* Zhaoxin Family 7 */
- VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS),
- VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS),
+ VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+ VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
{}
};
@@ -1358,10 +1364,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
* Affected CPU list is generally enough to enumerate the vulnerability,
* but for virtualization case check for ARCH_CAP MSR bits also, VMM may
* not want the guest to enumerate the bug.
+ *
+ * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
+ * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
*/
- if (cpu_matches(cpu_vuln_blacklist, MMIO) &&
- !arch_cap_mmio_immune(ia32_cap))
- setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+ if (!arch_cap_mmio_immune(ia32_cap)) {
+ if (cpu_matches(cpu_vuln_blacklist, MMIO))
+ setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+ else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
+ setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
+ }
if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 24c1bb8eb196..9f13d724172e 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -12,6 +12,9 @@
#include "encls.h"
#include "sgx.h"
+static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+ struct sgx_backing *backing);
+
#define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd))
/*
* 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to
@@ -344,8 +347,11 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
}
va_page = sgx_encl_grow(encl, false);
- if (IS_ERR(va_page))
+ if (IS_ERR(va_page)) {
+ if (PTR_ERR(va_page) == -EBUSY)
+ vmret = VM_FAULT_NOPAGE;
goto err_out_epc;
+ }
if (va_page)
list_add(&va_page->list, &encl->va_pages);
@@ -914,7 +920,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
}
/**
- * sgx_encl_get_backing() - Pin the backing storage
+ * __sgx_encl_get_backing() - Pin the backing storage
* @encl: an enclave pointer
* @page_index: enclave page index
* @backing: data for accessing backing storage for the page
@@ -926,7 +932,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
* 0 on success,
* -errno otherwise.
*/
-static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+static int __sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
struct sgx_backing *backing)
{
pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index);
@@ -1001,7 +1007,7 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
}
/**
- * sgx_encl_alloc_backing() - allocate a new backing storage page
+ * sgx_encl_alloc_backing() - create a new backing storage page
* @encl: an enclave pointer
* @page_index: enclave page index
* @backing: data for accessing backing storage for the page
@@ -1009,7 +1015,9 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
* When called from ksgxd, sets the active memcg from one of the
* mms in the enclave's mm_list prior to any backing page allocation,
* in order to ensure that shmem page allocations are charged to the
- * enclave.
+ * enclave. Create a backing page for loading data back into an EPC page with
+ * ELDU. This function takes a reference on a new backing page which
+ * must be dropped with a corresponding call to sgx_encl_put_backing().
*
* Return:
* 0 on success,
@@ -1022,7 +1030,7 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
struct mem_cgroup *memcg = set_active_memcg(encl_memcg);
int ret;
- ret = sgx_encl_get_backing(encl, page_index, backing);
+ ret = __sgx_encl_get_backing(encl, page_index, backing);
set_active_memcg(memcg);
mem_cgroup_put(encl_memcg);
@@ -1040,15 +1048,17 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
* It is the caller's responsibility to ensure that it is appropriate to use
* sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is
* not used correctly, this will cause an allocation which is not accounted for.
+ * This function takes a reference on an existing backing page which must be
+ * dropped with a corresponding call to sgx_encl_put_backing().
*
* Return:
* 0 on success,
* -errno otherwise.
*/
-int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
struct sgx_backing *backing)
{
- return sgx_encl_get_backing(encl, page_index, backing);
+ return __sgx_encl_get_backing(encl, page_index, backing);
}
/**
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index a65a952116fd..f94ff14c9486 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -107,8 +107,6 @@ bool current_is_ksgxd(void);
void sgx_encl_release(struct kref *ref);
int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl);
-int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
- struct sgx_backing *backing);
int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
struct sgx_backing *backing);
void sgx_encl_put_backing(struct sgx_backing *backing);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 515e2a5f25bb..0aad028f04d4 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -49,9 +49,13 @@ static LIST_HEAD(sgx_dirty_page_list);
* Reset post-kexec EPC pages to the uninitialized state. The pages are removed
* from the input list, and made available for the page allocator. SECS pages
* prepending their children in the input list are left intact.
+ *
+ * Return 0 when sanitization was successful or kthread was stopped, and the
+ * number of unsanitized pages otherwise.
*/
-static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
+static unsigned long __sgx_sanitize_pages(struct list_head *dirty_page_list)
{
+ unsigned long left_dirty = 0;
struct sgx_epc_page *page;
LIST_HEAD(dirty);
int ret;
@@ -59,7 +63,7 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
/* dirty_page_list is thread-local, no need for a lock: */
while (!list_empty(dirty_page_list)) {
if (kthread_should_stop())
- return;
+ return 0;
page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);
@@ -92,12 +96,14 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
} else {
/* The page is not yet clean - move to the dirty list. */
list_move_tail(&page->list, &dirty);
+ left_dirty++;
}
cond_resched();
}
list_splice(&dirty, dirty_page_list);
+ return left_dirty;
}
static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
@@ -395,10 +401,7 @@ static int ksgxd(void *p)
* required for SECS pages, whose child pages blocked EREMOVE.
*/
__sgx_sanitize_pages(&sgx_dirty_page_list);
- __sgx_sanitize_pages(&sgx_dirty_page_list);
-
- /* sanity check: */
- WARN_ON(!list_empty(&sgx_dirty_page_list));
+ WARN_ON(__sgx_sanitize_pages(&sgx_dirty_page_list));
while (!kthread_should_stop()) {
if (try_to_freeze())
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index e5dd6da78713..01833ebf5e8e 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -132,7 +132,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
return 0;
}
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
void do_softirq_own_stack(void)
{
struct irq_stack *irqstk;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 74167dc5f55e..4c3c27b6aea3 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -505,7 +505,7 @@ static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
if (p->ainsn.jcc.type >= 0xe)
- match = match && (regs->flags & X86_EFLAGS_ZF);
+ match = match || (regs->flags & X86_EFLAGS_ZF);
}
__kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
}
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 586f718b8e95..349046434513 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -4,11 +4,8 @@
*/
#include <linux/platform_device.h>
#include <linux/mc146818rtc.h>
-#include <linux/acpi.h>
-#include <linux/bcd.h>
#include <linux/export.h>
#include <linux/pnp.h>
-#include <linux/of.h>
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
@@ -20,26 +17,23 @@
/*
* This is a special lock that is owned by the CPU and holds the index
* register we are working with. It is required for NMI access to the
- * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details.
+ * CMOS/RTC registers. See arch/x86/include/asm/mc146818rtc.h for details.
*/
volatile unsigned long cmos_lock;
EXPORT_SYMBOL(cmos_lock);
#endif /* CONFIG_X86_32 */
-/* For two digit years assume time is always after that */
-#define CMOS_YEARS_OFFS 2000
-
DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL(rtc_lock);
/*
- * In order to set the CMOS clock precisely, set_rtc_mmss has to be
+ * In order to set the CMOS clock precisely, mach_set_cmos_time has to be
* called 500 ms after the second nowtime has started, because when
* nowtime is written into the registers of the CMOS clock, it will
* jump to the next second precisely 500 ms later. Check the Motorola
* MC146818A or Dallas DS12887 data sheet for details.
*/
-int mach_set_rtc_mmss(const struct timespec64 *now)
+int mach_set_cmos_time(const struct timespec64 *now)
{
unsigned long long nowtime = now->tv_sec;
struct rtc_time tm;
@@ -62,8 +56,7 @@ int mach_set_rtc_mmss(const struct timespec64 *now)
void mach_get_cmos_time(struct timespec64 *now)
{
- unsigned int status, year, mon, day, hour, min, sec, century = 0;
- unsigned long flags;
+ struct rtc_time tm;
/*
* If pm_trace abused the RTC as storage, set the timespec to 0,
@@ -74,51 +67,13 @@ void mach_get_cmos_time(struct timespec64 *now)
return;
}
- spin_lock_irqsave(&rtc_lock, flags);
-
- /*
- * If UIP is clear, then we have >= 244 microseconds before
- * RTC registers will be updated. Spec sheet says that this
- * is the reliable way to read RTC - registers. If UIP is set
- * then the register access might be invalid.
- */
- while ((CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP))
- cpu_relax();
-
- sec = CMOS_READ(RTC_SECONDS);
- min = CMOS_READ(RTC_MINUTES);
- hour = CMOS_READ(RTC_HOURS);
- day = CMOS_READ(RTC_DAY_OF_MONTH);
- mon = CMOS_READ(RTC_MONTH);
- year = CMOS_READ(RTC_YEAR);
-
-#ifdef CONFIG_ACPI
- if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
- acpi_gbl_FADT.century)
- century = CMOS_READ(acpi_gbl_FADT.century);
-#endif
-
- status = CMOS_READ(RTC_CONTROL);
- WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
-
- spin_unlock_irqrestore(&rtc_lock, flags);
-
- if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
- sec = bcd2bin(sec);
- min = bcd2bin(min);
- hour = bcd2bin(hour);
- day = bcd2bin(day);
- mon = bcd2bin(mon);
- year = bcd2bin(year);
+ if (mc146818_get_time(&tm)) {
+ pr_err("Unable to read current time from RTC\n");
+ now->tv_sec = now->tv_nsec = 0;
+ return;
}
- if (century) {
- century = bcd2bin(century);
- year += century * 100;
- } else
- year += CMOS_YEARS_OFFS;
-
- now->tv_sec = mktime64(year, mon, day, hour, min, sec);
+ now->tv_sec = rtc_tm_to_time64(&tm);
now->tv_nsec = 0;
}
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 63dc626627a0..a428c62330d3 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -701,7 +701,13 @@ e_term:
void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
unsigned int npages)
{
- if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ /*
+ * This can be invoked in early boot while running identity mapped, so
+ * use an open coded check for SNP instead of using cc_platform_has().
+ * This eliminates worries about jump tables or checking boot_cpu_data
+ * in the cc_platform_has() function.
+ */
+ if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
return;
/*
@@ -717,7 +723,13 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd
void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
unsigned int npages)
{
- if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ /*
+ * This can be invoked in early boot while running identity mapped, so
+ * use an open coded check for SNP instead of using cc_platform_has().
+ * This eliminates worries about jump tables or checking boot_cpu_data
+ * in the cc_platform_has() function.
+ */
+ if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
return;
/* Invalidate the memory pages before they are marked shared in the RMP table. */
@@ -2100,7 +2112,7 @@ bool __init snp_init(struct boot_params *bp)
return true;
}
-void __init snp_abort(void)
+void __init __noreturn snp_abort(void)
{
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d62b2cb85cea..178015a820f0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -63,6 +63,7 @@
#include <asm/insn-eval.h>
#include <asm/vdso.h>
#include <asm/tdx.h>
+#include <asm/cfi.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -313,7 +314,8 @@ static noinstr bool handle_bug(struct pt_regs *regs)
*/
if (regs->flags & X86_EFLAGS_IF)
raw_local_irq_enable();
- if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+ if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
+ handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
regs->ip += LEN_UD2;
handled = true;
}
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 38185aedf7d1..0ea57da92940 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -93,22 +93,27 @@ static struct orc_entry *orc_find(unsigned long ip);
static struct orc_entry *orc_ftrace_find(unsigned long ip)
{
struct ftrace_ops *ops;
- unsigned long caller;
+ unsigned long tramp_addr, offset;
ops = ftrace_ops_trampoline(ip);
if (!ops)
return NULL;
+ /* Set tramp_addr to the start of the code copied by the trampoline */
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
- caller = (unsigned long)ftrace_regs_call;
+ tramp_addr = (unsigned long)ftrace_regs_caller;
else
- caller = (unsigned long)ftrace_call;
+ tramp_addr = (unsigned long)ftrace_caller;
+
+ /* Now place tramp_addr to the location within the trampoline ip is at */
+ offset = ip - ops->trampoline;
+ tramp_addr += offset;
/* Prevent unlikely recursion */
- if (ip == caller)
+ if (ip == tramp_addr)
return NULL;
- return orc_find(caller);
+ return orc_find(tramp_addr);
}
#else
static struct orc_entry *orc_ftrace_find(unsigned long ip)
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e84ee5cdbd8c..57353519bc11 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -138,7 +138,7 @@ struct x86_platform_ops x86_platform __ro_after_init = {
.calibrate_cpu = native_calibrate_cpu_early,
.calibrate_tsc = native_calibrate_tsc,
.get_wallclock = mach_get_cmos_time,
- .set_wallclock = mach_set_rtc_mmss,
+ .set_wallclock = mach_set_cmos_time,
.iommu_shutdown = iommu_shutdown_noop,
.is_untracked_pat_range = is_ISA_range,
.nmi_init = default_nmi_init,
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 75dcf7a72605..2796dde06302 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -315,7 +315,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
struct kvm_cpuid_entry2 *best;
- u64 guest_supported_xcr0;
best = kvm_find_cpuid_entry(vcpu, 1);
if (best && apic) {
@@ -327,10 +326,16 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
kvm_apic_set_version(vcpu);
}
- guest_supported_xcr0 =
+ vcpu->arch.guest_supported_xcr0 =
cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
- vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0;
+ /*
+ * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
+ * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
+ * supported by the host.
+ */
+ vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 |
+ XFEATURE_MASK_FPSSE;
kvm_update_pv_runtime(vcpu);
@@ -897,8 +902,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->edx = 0;
}
break;
- case 9:
- break;
case 0xa: { /* Architectural Performance Monitoring */
union cpuid10_eax eax;
union cpuid10_edx edx;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b4eeb7c75dfa..aacb28c83e43 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -326,7 +326,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
".align " __stringify(FASTOP_SIZE) " \n\t" \
".type " name ", @function \n\t" \
name ":\n\t" \
- ASM_ENDBR
+ ASM_ENDBR \
+ IBT_NOSEAL(name)
#define FOP_FUNC(name) \
__FOP_FUNC(#name)
@@ -446,27 +447,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
FOP_END
/* Special case for SETcc - 1 instruction per cc */
-
-/*
- * Depending on .config the SETcc functions look like:
- *
- * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT]
- * SETcc %al [3 bytes]
- * RET | JMP __x86_return_thunk [1,5 bytes; CONFIG_RETHUNK]
- * INT3 [1 byte; CONFIG_SLS]
- */
-#define SETCC_ALIGN 16
-
#define FOP_SETCC(op) \
- ".align " __stringify(SETCC_ALIGN) " \n\t" \
- ".type " #op ", @function \n\t" \
- #op ": \n\t" \
- ASM_ENDBR \
+ FOP_FUNC(op) \
#op " %al \n\t" \
- __FOP_RET(#op) \
- ".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t"
+ FOP_RET(op)
-__FOP_START(setcc, SETCC_ALIGN)
+FOP_START(setcc)
FOP_SETCC(seto)
FOP_SETCC(setno)
FOP_SETCC(setc)
@@ -493,7 +479,7 @@ FOP_END;
/*
* XXX: inoutclob user must know where the argument is being expanded.
- * Relying on CONFIG_CC_HAS_ASM_GOTO would allow us to remove _fault.
+ * Using asm goto would allow us to remove _fault.
*/
#define asm_safe(insn, inoutclob...) \
({ \
@@ -1079,7 +1065,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
{
u8 rc;
- void (*fop)(void) = (void *)em_setcc + SETCC_ALIGN * (condition & 0xf);
+ void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf);
flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
asm("push %[flags]; popf; " CALL_NOSPEC
@@ -4146,6 +4132,9 @@ static int em_xsetbv(struct x86_emulate_ctxt *ctxt)
{
u32 eax, ecx, edx;
+ if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSXSAVE))
+ return emulate_ud(ctxt);
+
eax = reg_read(ctxt, VCPU_REGS_RAX);
edx = reg_read(ctxt, VCPU_REGS_RDX);
ecx = reg_read(ctxt, VCPU_REGS_RCX);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index eccddb136954..3552e6af3684 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1596,6 +1596,8 @@ static void __rmap_add(struct kvm *kvm,
rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
rmap_count = pte_list_add(cache, spte, rmap_head);
+ if (rmap_count > kvm->stat.max_mmu_rmap_size)
+ kvm->stat.max_mmu_rmap_size = rmap_count;
if (rmap_count > RMAP_RECYCLE_THRESHOLD) {
kvm_zap_all_rmap_sptes(kvm, rmap_head);
kvm_flush_remote_tlbs_with_address(
@@ -2914,7 +2916,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
* If addresses are being invalidated, skip prefetching to avoid
* accidentally prefetching those addresses.
*/
- if (unlikely(vcpu->kvm->mmu_notifier_count))
+ if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
return;
__direct_pte_prefetch(vcpu, sp, sptep);
@@ -2928,7 +2930,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
*
* There are several ways to safely use this helper:
*
- * - Check mmu_notifier_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
* consuming it. In this case, mmu_lock doesn't need to be held during the
* lookup, but it does need to be held while checking the MMU notifier.
*
@@ -3056,7 +3058,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
return;
/*
- * mmu_notifier_retry() was successful and mmu_lock is held, so
+ * mmu_invalidate_retry() was successful and mmu_lock is held, so
* the pmd can't be split from under us.
*/
fault->goal_level = fault->req_level;
@@ -4203,7 +4205,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
return true;
return fault->slot &&
- mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+ mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
}
static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -4227,7 +4229,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
if (r)
return r;
- mmu_seq = vcpu->kvm->mmu_notifier_seq;
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
r = kvm_faultin_pfn(vcpu, fault);
@@ -5361,19 +5363,6 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
}
-static bool need_remote_flush(u64 old, u64 new)
-{
- if (!is_shadow_present_pte(old))
- return false;
- if (!is_shadow_present_pte(new))
- return true;
- if ((old ^ new) & SPTE_BASE_ADDR_MASK)
- return true;
- old ^= shadow_nx_mask;
- new ^= shadow_nx_mask;
- return (old & ~new & SPTE_PERM_MASK) != 0;
-}
-
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
int *bytes)
{
@@ -5519,7 +5508,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
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))
+ if (is_shadow_present_pte(entry))
flush = true;
++spte;
}
@@ -6055,7 +6044,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
write_lock(&kvm->mmu_lock);
- kvm_inc_notifier_count(kvm, gfn_start, gfn_end);
+ kvm_mmu_invalidate_begin(kvm, gfn_start, gfn_end);
flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
@@ -6069,7 +6058,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
gfn_end - gfn_start);
- kvm_dec_notifier_count(kvm, gfn_start, gfn_end);
+ kvm_mmu_invalidate_end(kvm, gfn_start, gfn_end);
write_unlock(&kvm->mmu_lock);
}
@@ -6085,47 +6074,18 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
const struct kvm_memory_slot *memslot,
int start_level)
{
- bool flush = false;
-
if (kvm_memslots_have_rmaps(kvm)) {
write_lock(&kvm->mmu_lock);
- flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect,
- start_level, KVM_MAX_HUGEPAGE_LEVEL,
- false);
+ slot_handle_level(kvm, memslot, slot_rmap_write_protect,
+ start_level, KVM_MAX_HUGEPAGE_LEVEL, false);
write_unlock(&kvm->mmu_lock);
}
if (is_tdp_mmu_enabled(kvm)) {
read_lock(&kvm->mmu_lock);
- flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level);
+ kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level);
read_unlock(&kvm->mmu_lock);
}
-
- /*
- * Flush TLBs if any SPTEs had to be write-protected to ensure that
- * guest writes are reflected in the dirty bitmap before the memslot
- * update completes, i.e. before enabling dirty logging is visible to
- * userspace.
- *
- * Perform the TLB flush outside the mmu_lock to reduce the amount of
- * time the lock is held. However, this does mean that another CPU can
- * now grab mmu_lock and encounter a write-protected SPTE while CPUs
- * still have a writable mapping for the associated GFN in their TLB.
- *
- * This is safe but requires KVM to be careful when making decisions
- * based on the write-protection status of an SPTE. Specifically, KVM
- * also write-protects SPTEs to monitor changes to guest page tables
- * during shadow paging, and must guarantee no CPUs can write to those
- * page before the lock is dropped. As mentioned in the previous
- * paragraph, a write-protected SPTE is no guarantee that CPU cannot
- * perform writes. So to determine if a TLB flush is truly required, KVM
- * will clear a separate software-only bit (MMU-writable) and skip the
- * flush if-and-only-if this bit was already clear.
- *
- * See is_writable_pte() for more details.
- */
- if (flush)
- kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
}
static inline bool need_topup(struct kvm_mmu_memory_cache *cache, int min)
@@ -6493,32 +6453,30 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
const struct kvm_memory_slot *memslot)
{
- bool flush = false;
-
if (kvm_memslots_have_rmaps(kvm)) {
write_lock(&kvm->mmu_lock);
/*
* 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);
+ slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false);
write_unlock(&kvm->mmu_lock);
}
if (is_tdp_mmu_enabled(kvm)) {
read_lock(&kvm->mmu_lock);
- flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
+ kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
read_unlock(&kvm->mmu_lock);
}
/*
+ * The caller will flush the TLBs after this function returns.
+ *
* It's also safe to flush TLBs out of mmu lock here as currently this
* function is only used for dirty logging, in which case flushing TLB
* out of mmu lock also guarantees no dirty pages will be lost in
* dirty_bitmap.
*/
- if (flush)
- kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
}
void kvm_mmu_zap_all(struct kvm *kvm)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index f5958071220c..39e0205e7300 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -589,7 +589,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
* If addresses are being invalidated, skip prefetching to avoid
* accidentally prefetching those addresses.
*/
- if (unlikely(vcpu->kvm->mmu_notifier_count))
+ if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
return;
if (sp->role.direct)
@@ -838,7 +838,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
else
fault->max_level = walker.level;
- mmu_seq = vcpu->kvm->mmu_notifier_seq;
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
r = kvm_faultin_pfn(vcpu, fault);
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index f3744eea45f5..7670c13ce251 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -343,7 +343,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
}
/*
- * An shadow-present leaf SPTE may be non-writable for 3 possible reasons:
+ * A shadow-present leaf SPTE may be non-writable for 4 possible reasons:
*
* 1. To intercept writes for dirty logging. KVM write-protects huge pages
* so that they can be split be split down into the dirty logging
@@ -361,8 +361,13 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
* read-only memslot or guest memory backed by a read-only VMA. Writes to
* such pages are disallowed entirely.
*
- * To keep track of why a given SPTE is write-protected, KVM uses 2
- * software-only bits in the SPTE:
+ * 4. To emulate the Accessed bit for SPTEs without A/D bits. Note, in this
+ * case, the SPTE is access-protected, not just write-protected!
+ *
+ * For cases #1 and #4, KVM can safely make such SPTEs writable without taking
+ * mmu_lock as capturing the Accessed/Dirty state doesn't require taking it.
+ * To differentiate #1 and #4 from #2 and #3, KVM uses two software-only bits
+ * in the SPTE:
*
* shadow_mmu_writable_mask, aka MMU-writable -
* Cleared on SPTEs that KVM is currently write-protecting for shadow paging
@@ -391,7 +396,8 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
* shadow page tables between vCPUs. Write-protecting an SPTE for dirty logging
* (which does not clear the MMU-writable bit), does not flush TLBs before
* dropping the lock, as it only needs to synchronize guest writes with the
- * dirty bitmap.
+ * dirty bitmap. Similarly, making the SPTE inaccessible (and non-writable) for
+ * access-tracking via the clear_young() MMU notifier also does not flush TLBs.
*
* So, there is the problem: clearing the MMU-writable bit can encounter a
* write-protected SPTE while CPUs still have writable mappings for that SPTE
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d7f8331d6f7e..c9b49a09e6b5 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -843,8 +843,7 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr)
if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS))
return true;
- return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap,
- MSR_IA32_SPEC_CTRL);
+ return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr);
}
unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 205ebdc2b11b..b0c47b41c264 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1011,15 +1011,10 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
-static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu)
-{
- return vcpu->arch.guest_fpu.fpstate->user_xfeatures;
-}
-
#ifdef CONFIG_X86_64
static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu)
{
- return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC;
+ return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC;
}
#endif
@@ -1042,7 +1037,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
* saving. However, xcr0 bit 0 is always set, even if the
* emulated CPU does not support XSAVE (see kvm_vcpu_reset()).
*/
- valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP;
+ valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
if (xcr0 & ~valid_bits)
return 1;
@@ -1070,6 +1065,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu)
{
+ /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */
if (static_call(kvm_x86_get_cpl)(vcpu) != 0 ||
__kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) {
kvm_inject_gp(vcpu, 0);
@@ -1557,12 +1553,32 @@ static const u32 msr_based_features_all[] = {
static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
static unsigned int num_msr_based_features;
+/*
+ * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM
+ * does not yet virtualize. These include:
+ * 10 - MISC_PACKAGE_CTRLS
+ * 11 - ENERGY_FILTERING_CTL
+ * 12 - DOITM
+ * 18 - FB_CLEAR_CTRL
+ * 21 - XAPIC_DISABLE_STATUS
+ * 23 - OVERCLOCKING_STATUS
+ */
+
+#define KVM_SUPPORTED_ARCH_CAP \
+ (ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \
+ ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
+ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
+ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
+ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO)
+
static u64 kvm_get_arch_capabilities(void)
{
u64 data = 0;
- if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+ if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
+ data &= KVM_SUPPORTED_ARCH_CAP;
+ }
/*
* If nx_huge_pages is enabled, KVM's shadow paging will ensure that
@@ -1610,9 +1626,6 @@ static u64 kvm_get_arch_capabilities(void)
*/
}
- /* Guests don't need to know "Fill buffer clear control" exists */
- data &= ~ARCH_CAP_FB_CLEAR_CTRL;
-
return data;
}
@@ -10652,7 +10665,8 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu)
case KVM_MP_STATE_INIT_RECEIVED:
break;
default:
- return -EINTR;
+ WARN_ON_ONCE(1);
+ break;
}
return 1;
}
@@ -11093,9 +11107,22 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
vcpu_load(vcpu);
- if (!lapic_in_kernel(vcpu) &&
- mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
+ switch (mp_state->mp_state) {
+ case KVM_MP_STATE_UNINITIALIZED:
+ case KVM_MP_STATE_HALTED:
+ case KVM_MP_STATE_AP_RESET_HOLD:
+ case KVM_MP_STATE_INIT_RECEIVED:
+ case KVM_MP_STATE_SIPI_RECEIVED:
+ if (!lapic_in_kernel(vcpu))
+ goto out;
+ break;
+
+ case KVM_MP_STATE_RUNNABLE:
+ break;
+
+ default:
goto out;
+ }
/*
* KVM_MP_STATE_INIT_RECEIVED means the processor is in
@@ -11563,7 +11590,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64),
GFP_KERNEL_ACCOUNT);
if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks)
- goto fail_free_pio_data;
+ goto fail_free_mce_banks;
vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;
if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask,
@@ -11617,7 +11644,6 @@ free_wbinvd_dirty_mask:
fail_free_mce_banks:
kfree(vcpu->arch.mce_banks);
kfree(vcpu->arch.mci_ctl2_banks);
-fail_free_pio_data:
free_page((unsigned long)vcpu->arch.pio_data);
fail_free_lapic:
kvm_free_lapic(vcpu);
@@ -12473,6 +12499,50 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
} else {
kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K);
}
+
+ /*
+ * Unconditionally flush the TLBs after enabling dirty logging.
+ * A flush is almost always going to be necessary (see below),
+ * and unconditionally flushing allows the helpers to omit
+ * the subtly complex checks when removing write access.
+ *
+ * Do the flush outside of mmu_lock to reduce the amount of
+ * time mmu_lock is held. Flushing after dropping mmu_lock is
+ * safe as KVM only needs to guarantee the slot is fully
+ * write-protected before returning to userspace, i.e. before
+ * userspace can consume the dirty status.
+ *
+ * Flushing outside of mmu_lock requires KVM to be careful when
+ * making decisions based on writable status of an SPTE, e.g. a
+ * !writable SPTE doesn't guarantee a CPU can't perform writes.
+ *
+ * Specifically, KVM also write-protects guest page tables to
+ * monitor changes when using shadow paging, and must guarantee
+ * no CPUs can write to those page before mmu_lock is dropped.
+ * Because CPUs may have stale TLB entries at this point, a
+ * !writable SPTE doesn't guarantee CPUs can't perform writes.
+ *
+ * KVM also allows making SPTES writable outside of mmu_lock,
+ * e.g. to allow dirty logging without taking mmu_lock.
+ *
+ * To handle these scenarios, KVM uses a separate software-only
+ * bit (MMU-writable) to track if a SPTE is !writable due to
+ * a guest page table being write-protected (KVM clears the
+ * MMU-writable flag when write-protecting for shadow paging).
+ *
+ * The use of MMU-writable is also the primary motivation for
+ * the unconditional flush. Because KVM must guarantee that a
+ * CPU doesn't contain stale, writable TLB entries for a
+ * !MMU-writable SPTE, KVM must flush if it encounters any
+ * MMU-writable SPTE regardless of whether the actual hardware
+ * writable bit was set. I.e. KVM is almost guaranteed to need
+ * to flush, while unconditionally flushing allows the "remove
+ * write access" helpers to ignore MMU-writable entirely.
+ *
+ * See is_writable_pte() for more details (the case involving
+ * access-tracked SPTEs is particularly relevant).
+ */
+ kvm_arch_flush_remote_tlbs_memslot(kvm, new);
}
}
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index d0d7b9bc6cad..dd8cd8831251 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -2,6 +2,7 @@
/* Copyright 2002 Andi Kleen */
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -27,7 +28,7 @@
* Output:
* rax original destination
*/
-SYM_FUNC_START(__memcpy)
+SYM_TYPED_FUNC_START(__memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ad0139d25401..f1bb18617156 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -44,7 +44,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
* called from other contexts.
*/
pagefault_disable();
- ret = __copy_from_user_inatomic(to, from, n);
+ ret = raw_copy_from_user(to, from, n);
pagefault_enable();
return ret;
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index f8220fd2c169..829c1409ffbd 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -4,10 +4,12 @@ KCOV_INSTRUMENT_tlb.o := n
KCOV_INSTRUMENT_mem_encrypt.o := n
KCOV_INSTRUMENT_mem_encrypt_amd.o := n
KCOV_INSTRUMENT_mem_encrypt_identity.o := n
+KCOV_INSTRUMENT_pgprot.o := n
KASAN_SANITIZE_mem_encrypt.o := n
KASAN_SANITIZE_mem_encrypt_amd.o := n
KASAN_SANITIZE_mem_encrypt_identity.o := n
+KASAN_SANITIZE_pgprot.o := n
# Disable KCSAN entirely, because otherwise we get warnings that some functions
# reference __initdata sections.
@@ -17,6 +19,7 @@ ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_mem_encrypt.o = -pg
CFLAGS_REMOVE_mem_encrypt_amd.o = -pg
CFLAGS_REMOVE_mem_encrypt_identity.o = -pg
+CFLAGS_REMOVE_pgprot.o = -pg
endif
obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 331310c29349..60814e110a54 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -41,6 +41,59 @@ static bool ex_handler_default(const struct exception_table_entry *e,
return true;
}
+/*
+ * This is the *very* rare case where we do a "load_unaligned_zeropad()"
+ * and it's a page crosser into a non-existent page.
+ *
+ * This happens when we optimistically load a pathname a word-at-a-time
+ * and the name is less than the full word and the next page is not
+ * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC.
+ *
+ * NOTE! The faulting address is always a 'mov mem,reg' type instruction
+ * of size 'long', and the exception fixup must always point to right
+ * after the instruction.
+ */
+static bool ex_handler_zeropad(const struct exception_table_entry *e,
+ struct pt_regs *regs,
+ unsigned long fault_addr)
+{
+ struct insn insn;
+ const unsigned long mask = sizeof(long) - 1;
+ unsigned long offset, addr, next_ip, len;
+ unsigned long *reg;
+
+ next_ip = ex_fixup_addr(e);
+ len = next_ip - regs->ip;
+ if (len > MAX_INSN_SIZE)
+ return false;
+
+ if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN))
+ return false;
+ if (insn.length != len)
+ return false;
+
+ if (insn.opcode.bytes[0] != 0x8b)
+ return false;
+ if (insn.opnd_bytes != sizeof(long))
+ return false;
+
+ addr = (unsigned long) insn_get_addr_ref(&insn, regs);
+ if (addr == ~0ul)
+ return false;
+
+ offset = addr & mask;
+ addr = addr & ~mask;
+ if (fault_addr != addr + sizeof(long))
+ return false;
+
+ reg = insn_get_modrm_reg_ptr(&insn, regs);
+ if (!reg)
+ return false;
+
+ *reg = *(unsigned long *)addr >> (offset * 8);
+ return ex_handler_default(e, regs);
+}
+
static bool ex_handler_fault(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
@@ -217,6 +270,8 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
return ex_handler_sgx(e, regs, trapnr);
case EX_TYPE_UCOPY_LEN:
return ex_handler_ucopy_len(e, regs, trapnr, reg, imm);
+ case EX_TYPE_ZEROPAD:
+ return ex_handler_zeropad(e, regs, fault_addr);
}
BUG();
}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 39c5246964a9..0fe690ebc269 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -645,7 +645,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
pages++;
spin_lock(&init_mm.page_table_lock);
- prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE);
+ prot = __pgprot(pgprot_val(prot) | _PAGE_PSE);
set_pte_init((pte_t *)pud,
pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index d5ef64ddd35e..66a209f7eb86 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -62,6 +62,7 @@
static bool __read_mostly pat_bp_initialized;
static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);
+static bool __initdata pat_force_disabled = !IS_ENABLED(CONFIG_X86_PAT);
static bool __read_mostly pat_bp_enabled;
static bool __read_mostly pat_cm_initialized;
@@ -86,6 +87,7 @@ void pat_disable(const char *msg_reason)
static int __init nopat(char *str)
{
pat_disable("PAT support disabled via boot option.");
+ pat_force_disabled = true;
return 0;
}
early_param("nopat", nopat);
@@ -272,7 +274,7 @@ static void pat_ap_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
}
-void init_cache_modes(void)
+void __init init_cache_modes(void)
{
u64 pat = 0;
@@ -313,6 +315,12 @@ void init_cache_modes(void)
*/
pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+ } else if (!pat_force_disabled && cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) {
+ /*
+ * Clearly PAT is enabled underneath. Allow pat_enabled() to
+ * reflect this.
+ */
+ pat_bp_enabled = true;
}
__init_cache_modes(pat);
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 31c634a22818..58a200dc762d 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -55,6 +55,10 @@ ifdef CONFIG_RETPOLINE
PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS)
endif
+ifdef CONFIG_CFI_CLANG
+PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI)
+endif
+
CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE)
CFLAGS_purgatory.o += $(PURGATORY_CFLAGS)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e2c5b296120d..2925074b9a58 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -56,6 +56,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
"^(xen_irq_disable_direct_reloc$|"
"xen_save_fl_direct_reloc$|"
"VDSO|"
+ "__kcfi_typeid_|"
"__crc_)",
/*
diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h
index 68fd2cf526fd..f6e9f84397e7 100644
--- a/arch/x86/um/shared/sysdep/syscalls_32.h
+++ b/arch/x86/um/shared/sysdep/syscalls_32.h
@@ -6,10 +6,9 @@
#include <asm/unistd.h>
#include <sysdep/ptrace.h>
-typedef long syscall_handler_t(struct pt_regs);
+typedef long syscall_handler_t(struct syscall_args);
extern syscall_handler_t *sys_call_table[];
#define EXECUTE_SYSCALL(syscall, regs) \
- ((long (*)(struct syscall_args)) \
- (*sys_call_table[syscall]))(SYSCALL_ARGS(&regs->regs))
+ ((*sys_call_table[syscall]))(SYSCALL_ARGS(&regs->regs))
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index ac8eee093f9c..66162eafd8e8 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -65,9 +65,6 @@ static int get_free_idx(struct task_struct* task)
struct thread_struct *t = &task->thread;
int idx;
- if (!t->arch.tls_array)
- return GDT_ENTRY_TLS_MIN;
-
for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
if (!t->arch.tls_array[idx].present)
return idx + GDT_ENTRY_TLS_MIN;
@@ -240,9 +237,6 @@ static int get_tls_entry(struct task_struct *task, struct user_desc *info,
{
struct thread_struct *t = &task->thread;
- if (!t->arch.tls_array)
- goto clear;
-
if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
return -EINVAL;
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 8c0396fd0e6f..6fbe97c52c99 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -65,7 +65,7 @@ quiet_cmd_vdso = VDSO $@
-Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
-VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv
+VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack
GCOV_PROFILE := n
#
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 0ed2e487a693..9b1a58dda935 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -765,6 +765,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
{
static DEFINE_SPINLOCK(lock);
static struct trap_info traps[257];
+ static const struct trap_info zero = { };
unsigned out;
trace_xen_cpu_load_idt(desc);
@@ -774,7 +775,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
out = xen_convert_trap_info(desc, traps, false);
- memset(&traps[out], 0, sizeof(traps[0]));
+ traps[out] = zero;
xen_mc_flush();
if (HYPERVISOR_set_trap_table(traps))