summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/Makefile2
-rw-r--r--arch/x86/boot/compressed/mem.c5
-rw-r--r--arch/x86/boot/compressed/sev.c67
-rw-r--r--arch/x86/boot/compressed/sev.h2
-rw-r--r--arch/x86/events/core.c2
-rw-r--r--arch/x86/events/intel/core.c24
-rw-r--r--arch/x86/events/intel/ds.c8
-rw-r--r--arch/x86/events/intel/uncore_snbep.c107
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h6
-rw-r--r--arch/x86/include/asm/pgalloc.h19
-rw-r--r--arch/x86/kernel/cpu/amd.c19
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c9
-rw-r--r--arch/x86/kernel/e820.c8
-rw-r--r--arch/x86/kernel/i8253.c3
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kvm/svm/avic.c68
-rw-r--r--arch/x86/kvm/trace.h13
-rw-r--r--arch/x86/kvm/vmx/posted_intr.c28
-rw-r--r--arch/x86/kvm/x86.c28
-rw-r--r--arch/x86/lib/x86-opcode-map.txt4
-rw-r--r--arch/x86/mm/pgtable.c4
-rw-r--r--arch/x86/platform/efi/efi_64.c4
-rw-r--r--arch/x86/xen/enlighten.c7
-rw-r--r--arch/x86/xen/multicalls.c26
-rw-r--r--arch/x86/xen/smp_pv.c1
-rw-r--r--arch/x86/xen/xen-ops.h3
27 files changed, 205 insertions, 268 deletions
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 81f55da81967..640fcac3af74 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -59,7 +59,7 @@ KBUILD_CFLAGS += $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
$(obj)/bzImage: asflags-y := $(SVGA_MODE)
quiet_cmd_image = BUILD $@
- cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@
+ cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
$(call if_changed,image)
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c
index dbba332e4a12..f676156d9f3d 100644
--- a/arch/x86/boot/compressed/mem.c
+++ b/arch/x86/boot/compressed/mem.c
@@ -34,11 +34,14 @@ static bool early_is_tdx_guest(void)
void arch_accept_memory(phys_addr_t start, phys_addr_t end)
{
+ static bool sevsnp;
+
/* Platform-specific memory-acceptance call goes here */
if (early_is_tdx_guest()) {
if (!tdx_accept_memory(start, end))
panic("TDX: Failed to accept memory\n");
- } else if (sev_snp_enabled()) {
+ } else if (sevsnp || (sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) {
+ sevsnp = true;
snp_accept_memory(start, end);
} else {
error("Cannot accept memory: unknown platform\n");
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index bb55934c1cee..89ba168f4f0f 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -164,10 +164,7 @@ bool sev_snp_enabled(void)
static void __page_state_change(unsigned long paddr, enum psc_op op)
{
- u64 val;
-
- if (!sev_snp_enabled())
- return;
+ u64 val, msr;
/*
* If private -> shared then invalidate the page before requesting the
@@ -176,6 +173,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
if (op == SNP_PAGE_STATE_SHARED)
pvalidate_4k_page(paddr, paddr, false);
+ /* Save the current GHCB MSR value */
+ msr = sev_es_rd_ghcb_msr();
+
/* Issue VMGEXIT to change the page state in RMP table. */
sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
VMGEXIT();
@@ -185,6 +185,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val))
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+ /* Restore the GHCB MSR value */
+ sev_es_wr_ghcb_msr(msr);
+
/*
* Now that page state is changed in the RMP table, validate it so that it is
* consistent with the RMP entry.
@@ -195,11 +198,17 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
void snp_set_page_private(unsigned long paddr)
{
+ if (!sev_snp_enabled())
+ return;
+
__page_state_change(paddr, SNP_PAGE_STATE_PRIVATE);
}
void snp_set_page_shared(unsigned long paddr)
{
+ if (!sev_snp_enabled())
+ return;
+
__page_state_change(paddr, SNP_PAGE_STATE_SHARED);
}
@@ -223,56 +232,10 @@ static bool early_setup_ghcb(void)
return true;
}
-static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc,
- phys_addr_t pa, phys_addr_t pa_end)
-{
- struct psc_hdr *hdr;
- struct psc_entry *e;
- unsigned int i;
-
- hdr = &desc->hdr;
- memset(hdr, 0, sizeof(*hdr));
-
- e = desc->entries;
-
- i = 0;
- while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) {
- hdr->end_entry = i;
-
- e->gfn = pa >> PAGE_SHIFT;
- e->operation = SNP_PAGE_STATE_PRIVATE;
- if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) {
- e->pagesize = RMP_PG_SIZE_2M;
- pa += PMD_SIZE;
- } else {
- e->pagesize = RMP_PG_SIZE_4K;
- pa += PAGE_SIZE;
- }
-
- e++;
- i++;
- }
-
- if (vmgexit_psc(boot_ghcb, desc))
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
- pvalidate_pages(desc);
-
- return pa;
-}
-
void snp_accept_memory(phys_addr_t start, phys_addr_t end)
{
- struct snp_psc_desc desc = {};
- unsigned int i;
- phys_addr_t pa;
-
- if (!boot_ghcb && !early_setup_ghcb())
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-
- pa = start;
- while (pa < end)
- pa = __snp_accept_memory(&desc, pa, end);
+ for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE)
+ __page_state_change(pa, SNP_PAGE_STATE_PRIVATE);
}
void sev_es_shutdown_ghcb(void)
diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h
index fc725a981b09..4e463f33186d 100644
--- a/arch/x86/boot/compressed/sev.h
+++ b/arch/x86/boot/compressed/sev.h
@@ -12,11 +12,13 @@
bool sev_snp_enabled(void);
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
+u64 sev_get_status(void);
#else
static inline bool sev_snp_enabled(void) { return false; }
static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
+static inline u64 sev_get_status(void) { return 0; }
#endif
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6866cc5acb0b..3a4f031d2f44 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -629,7 +629,7 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.type == event->pmu->type)
event->hw.config |= x86_pmu_get_event_config(event);
- if (!event->attr.freq && x86_pmu.limit_period) {
+ if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
s64 left = event->attr.sample_period;
x86_pmu.limit_period(event, &left);
if (left > event->attr.sample_period)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 09d2d66c9f21..00dfe487bd00 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3049,7 +3049,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int bit;
int handled = 0;
- u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
inc_irq_stat(apic_perf_irqs);
@@ -3093,7 +3092,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
handled++;
x86_pmu_handle_guest_pebs(regs, &data);
static_call(x86_pmu_drain_pebs)(regs, &data);
- status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
/*
* PMI throttle may be triggered, which stops the PEBS event.
@@ -3104,6 +3102,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
*/
if (pebs_enabled != cpuc->pebs_enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+ /*
+ * Above PEBS handler (PEBS counters snapshotting) has updated fixed
+ * counter 3 and perf metrics counts if they are in counter group,
+ * unnecessary to update again.
+ */
+ if (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS] &&
+ is_pebs_counter_event_group(cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS]))
+ status &= ~GLOBAL_STATUS_PERF_METRICS_OVF_BIT;
}
/*
@@ -3123,6 +3130,8 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
static_call(intel_pmu_update_topdown_event)(NULL, NULL);
}
+ status &= hybrid(cpuc->pmu, intel_ctrl);
+
/*
* Checkpointed counters can lead to 'spurious' PMIs because the
* rollback caused by the PMI will have cleared the overflow status
@@ -7305,8 +7314,17 @@ __init int intel_pmu_init(void)
name = "meteorlake_hybrid";
break;
+ case INTEL_PANTHERLAKE_L:
+ pr_cont("Pantherlake Hybrid events, ");
+ name = "pantherlake_hybrid";
+ goto lnl_common;
+
case INTEL_LUNARLAKE_M:
case INTEL_ARROWLAKE:
+ pr_cont("Lunarlake Hybrid events, ");
+ name = "lunarlake_hybrid";
+
+ lnl_common:
intel_pmu_init_hybrid(hybrid_big_small);
x86_pmu.pebs_latency_data = lnl_latency_data;
@@ -7328,8 +7346,6 @@ __init int intel_pmu_init(void)
intel_pmu_init_skt(&pmu->pmu);
intel_pmu_pebs_data_source_lnl();
- pr_cont("Lunarlake Hybrid events, ");
- name = "lunarlake_hybrid";
break;
case INTEL_ARROWLAKE_H:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1f7e1a692a7a..18c3ab579b8b 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1399,8 +1399,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
* + precise_ip < 2 for the non event IP
* + For RTM TSX weight we need GPRs for the abort code.
*/
- gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
- (attr->sample_regs_intr & PEBS_GP_REGS);
+ gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GP_REGS)) ||
+ ((sample_type & PERF_SAMPLE_REGS_USER) &&
+ (attr->sample_regs_user & PEBS_GP_REGS));
tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
((attr->config & INTEL_ARCH_EVENT_MASK) ==
@@ -2123,7 +2125,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
regs->flags &= ~PERF_EFLAGS_EXACT;
}
- if (sample_type & PERF_SAMPLE_REGS_INTR)
+ if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
adaptive_pebs_save_regs(regs, gprs);
}
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 60973c209c0e..76d96df1475a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -4891,28 +4891,28 @@ static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
/* Free-Running IIO BANDWIDTH IN Counters */
INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.0517578125e-5"),
INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
{ /* end: all zeroes */ },
};
@@ -5485,37 +5485,6 @@ static struct freerunning_counters icx_iio_freerunning[] = {
[ICX_IIO_MSR_BW_IN] = { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets },
};
-static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = {
- /* Free-Running IIO CLOCKS Counter */
- INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
- /* Free-Running IIO BANDWIDTH IN Counters */
- INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
- { /* end: all zeroes */ },
-};
-
static struct intel_uncore_type icx_uncore_iio_free_running = {
.name = "iio_free_running",
.num_counters = 9,
@@ -5523,7 +5492,7 @@ static struct intel_uncore_type icx_uncore_iio_free_running = {
.num_freerunning_types = ICX_IIO_FREERUNNING_TYPE_MAX,
.freerunning = icx_iio_freerunning,
.ops = &skx_uncore_iio_freerunning_ops,
- .event_descs = icx_uncore_iio_freerunning_events,
+ .event_descs = snr_uncore_iio_freerunning_events,
.format_group = &skx_uncore_iio_freerunning_format_group,
};
@@ -6320,69 +6289,13 @@ static struct freerunning_counters spr_iio_freerunning[] = {
[SPR_IIO_MSR_BW_OUT] = { 0x3808, 0x1, 0x10, 8, 48 },
};
-static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = {
- /* Free-Running IIO CLOCKS Counter */
- INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
- /* Free-Running IIO BANDWIDTH IN Counters */
- INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
- /* Free-Running IIO BANDWIDTH OUT Counters */
- INTEL_UNCORE_EVENT_DESC(bw_out_port0, "event=0xff,umask=0x30"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port1, "event=0xff,umask=0x31"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port2, "event=0xff,umask=0x32"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port3, "event=0xff,umask=0x33"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port4, "event=0xff,umask=0x34"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port5, "event=0xff,umask=0x35"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port6, "event=0xff,umask=0x36"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit, "MiB"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port7, "event=0xff,umask=0x37"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale, "3.814697266e-6"),
- INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit, "MiB"),
- { /* end: all zeroes */ },
-};
-
static struct intel_uncore_type spr_uncore_iio_free_running = {
.name = "iio_free_running",
.num_counters = 17,
.num_freerunning_types = SPR_IIO_FREERUNNING_TYPE_MAX,
.freerunning = spr_iio_freerunning,
.ops = &skx_uncore_iio_freerunning_ops,
- .event_descs = spr_uncore_iio_freerunning_events,
+ .event_descs = snr_uncore_iio_freerunning_events,
.format_group = &skx_uncore_iio_freerunning_format_group,
};
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 3a97a7eefb51..be10c188614f 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -126,6 +126,8 @@
#define INTEL_GRANITERAPIDS_X IFM(6, 0xAD) /* Redwood Cove */
#define INTEL_GRANITERAPIDS_D IFM(6, 0xAE)
+#define INTEL_BARTLETTLAKE IFM(6, 0xD7) /* Raptor Cove */
+
/* "Hybrid" Processors (P-Core/E-Core) */
#define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3bdae454a959..7bc174a1f1cb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,6 +35,7 @@
#include <asm/mtrr.h>
#include <asm/msr-index.h>
#include <asm/asm.h>
+#include <asm/irq_remapping.h>
#include <asm/kvm_page_track.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/reboot.h>
@@ -2423,4 +2424,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
*/
#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1)
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index a33147520044..c88691b15f3c 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,8 @@
#include <linux/mm.h> /* for struct page */
#include <linux/pagemap.h>
+#include <asm/cpufeature.h>
+
#define __HAVE_ARCH_PTE_ALLOC_ONE
#define __HAVE_ARCH_PGD_FREE
#include <asm-generic/pgalloc.h>
@@ -29,16 +31,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
static inline void paravirt_release_p4d(unsigned long pfn) {}
#endif
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
- * Instead of one PGD, we acquire two PGDs. Being order-1, it is
- * both 8k in size and 8k-aligned. That lets us just flip bit 12
- * in a pointer to swap between the two 4k halves.
+ * In case of Page Table Isolation active, we acquire two PGDs instead of one.
+ * Being order-1, it is both 8k in size and 8k-aligned. That lets us just
+ * flip bit 12 in a pointer to swap between the two 4k halves.
*/
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+static inline unsigned int pgd_allocation_order(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_PTI))
+ return 1;
+ return 0;
+}
/*
* Allocate and free page tables.
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a839ff506f45..2b36379ff675 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -869,6 +869,16 @@ static void init_amd_zen1(struct cpuinfo_x86 *c)
pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
setup_force_cpu_bug(X86_BUG_DIV0);
+
+ /*
+ * Turn off the Instructions Retired free counter on machines that are
+ * susceptible to erratum #1054 "Instructions Retired Performance
+ * Counter May Be Inaccurate".
+ */
+ if (c->x86_model < 0x30) {
+ msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
+ clear_cpu_cap(c, X86_FEATURE_IRPERF);
+ }
}
static bool cpu_has_zenbleed_microcode(void)
@@ -1052,13 +1062,8 @@ static void init_amd(struct cpuinfo_x86 *c)
if (!cpu_feature_enabled(X86_FEATURE_XENPV))
set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
- /*
- * Turn on the Instructions Retired free counter on machines not
- * susceptible to erratum #1054 "Instructions Retired Performance
- * Counter May Be Inaccurate".
- */
- if (cpu_has(c, X86_FEATURE_IRPERF) &&
- (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f))
+ /* Enable the Instructions Retired free counter */
+ if (cpu_has(c, X86_FEATURE_IRPERF))
msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
check_null_seg_clears_base(c);
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index b61028cf5c8a..4a10d35e70aa 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -199,6 +199,12 @@ static bool need_sha_check(u32 cur_rev)
case 0xa70c0: return cur_rev <= 0xa70C009; break;
case 0xaa001: return cur_rev <= 0xaa00116; break;
case 0xaa002: return cur_rev <= 0xaa00218; break;
+ case 0xb0021: return cur_rev <= 0xb002146; break;
+ case 0xb1010: return cur_rev <= 0xb101046; break;
+ case 0xb2040: return cur_rev <= 0xb204031; break;
+ case 0xb4040: return cur_rev <= 0xb404031; break;
+ case 0xb6000: return cur_rev <= 0xb600031; break;
+ case 0xb7000: return cur_rev <= 0xb700031; break;
default: break;
}
@@ -214,8 +220,7 @@ static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsi
struct sha256_state s;
int i;
- if (x86_family(bsp_cpuid_1_eax) < 0x17 ||
- x86_family(bsp_cpuid_1_eax) > 0x19)
+ if (x86_family(bsp_cpuid_1_eax) < 0x17)
return true;
if (!need_sha_check(cur_rev))
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 9d8dd8deb2a7..9920122018a0 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1299,6 +1299,14 @@ void __init e820__memblock_setup(void)
memblock_add(entry->addr, entry->size);
}
+ /*
+ * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
+ * to even less without it.
+ * Discard memory after max_pfn - the actual limit detected at runtime.
+ */
+ if (IS_ENABLED(CONFIG_X86_32))
+ memblock_remove(PFN_PHYS(max_pfn), -1);
+
/* Throw away partial pages: */
memblock_trim_memory(PAGE_SIZE);
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 80e262bb627f..cb9852ad6098 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -46,7 +46,8 @@ bool __init pit_timer_init(void)
* VMMs otherwise steal CPU time just to pointlessly waggle
* the (masked) IRQ.
*/
- clockevent_i8253_disable();
+ scoped_guard(irq)
+ clockevent_i8253_disable();
return false;
}
clockevent_i8253_init(true);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 80265162aeff..1f325304c4a8 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -42,7 +42,7 @@ static void load_segments(void)
static void machine_kexec_free_page_tables(struct kimage *image)
{
- free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)image->arch.pgd, pgd_allocation_order());
image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
@@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image)
static int machine_kexec_alloc_page_tables(struct kimage *image)
{
image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- PGD_ALLOCATION_ORDER);
+ pgd_allocation_order());
#ifdef CONFIG_X86_PAE
image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 65fd245a9953..7338879d1c0c 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -796,12 +796,15 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
struct amd_svm_iommu_ir *ir;
u64 entry;
+ if (WARN_ON_ONCE(!pi->ir_data))
+ return -EINVAL;
+
/**
* In some cases, the existing irte is updated and re-set,
* so we need to check here if it's already been * added
* to the ir_list.
*/
- if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+ if (pi->prev_ga_tag) {
struct kvm *kvm = svm->vcpu.kvm;
u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
@@ -820,7 +823,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
* Allocating new amd_iommu_pi_data, which will get
* add to the per-vcpu ir_list.
*/
- ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+ ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
if (!ir) {
ret = -ENOMEM;
goto out;
@@ -896,10 +899,10 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
int idx, ret = 0;
- if (!kvm_arch_has_assigned_device(kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
return 0;
pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
@@ -933,6 +936,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_vcpu_apicv_active(&svm->vcpu)) {
struct amd_iommu_pi_data pi;
+ enable_remapped_mode = false;
+
/* Try to enable guest_mode in IRTE */
pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
AVIC_HPA_MASK);
@@ -951,33 +956,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
*/
if (!ret && pi.is_guest_mode)
svm_ir_list_add(svm, &pi);
- } else {
- /* Use legacy mode in IRTE */
- struct amd_iommu_pi_data pi;
-
- /**
- * Here, pi is used to:
- * - Tell IOMMU to use legacy mode for this interrupt.
- * - Retrieve ga_tag of prior interrupt remapping data.
- */
- pi.prev_ga_tag = 0;
- pi.is_guest_mode = false;
- ret = irq_set_vcpu_affinity(host_irq, &pi);
-
- /**
- * Check if the posted interrupt was previously
- * setup with the guest_mode by checking if the ga_tag
- * was cached. If so, we need to clean up the per-vcpu
- * ir_list.
- */
- if (!ret && pi.prev_ga_tag) {
- int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
- struct kvm_vcpu *vcpu;
-
- vcpu = kvm_get_vcpu_by_id(kvm, id);
- if (vcpu)
- svm_ir_list_del(to_svm(vcpu), &pi);
- }
}
if (!ret && svm) {
@@ -993,6 +971,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
ret = 0;
+ if (enable_remapped_mode) {
+ /* Use legacy mode in IRTE */
+ struct amd_iommu_pi_data pi;
+
+ /**
+ * Here, pi is used to:
+ * - Tell IOMMU to use legacy mode for this interrupt.
+ * - Retrieve ga_tag of prior interrupt remapping data.
+ */
+ pi.prev_ga_tag = 0;
+ pi.is_guest_mode = false;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Check if the posted interrupt was previously
+ * setup with the guest_mode by checking if the ga_tag
+ * was cached. If so, we need to clean up the per-vcpu
+ * ir_list.
+ */
+ if (!ret && pi.prev_ga_tag) {
+ int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kvm_get_vcpu_by_id(kvm, id);
+ if (vcpu)
+ svm_ir_list_del(to_svm(vcpu), &pi);
+ }
+ }
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ccda95e53f62..ba736cbb0587 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -11,6 +11,13 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
+#ifdef CREATE_TRACE_POINTS
+#define tracing_kvm_rip_read(vcpu) ({ \
+ typeof(vcpu) __vcpu = vcpu; \
+ __vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu); \
+ })
+#endif
+
/*
* Tracepoint for guest mode entry.
*/
@@ -28,7 +35,7 @@ TRACE_EVENT(kvm_entry,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->rip = kvm_rip_read(vcpu);
+ __entry->rip = tracing_kvm_rip_read(vcpu);
__entry->immediate_exit = force_immediate_exit;
kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info,
@@ -319,7 +326,7 @@ TRACE_EVENT(name, \
), \
\
TP_fast_assign( \
- __entry->guest_rip = kvm_rip_read(vcpu); \
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu); \
__entry->isa = isa; \
__entry->vcpu_id = vcpu->vcpu_id; \
__entry->requests = READ_ONCE(vcpu->requests); \
@@ -423,7 +430,7 @@ TRACE_EVENT(kvm_page_fault,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->guest_rip = kvm_rip_read(vcpu);
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu);
__entry->fault_address = fault_address;
__entry->error_code = error_code;
),
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 51116fe69a50..d70e5b90087d 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -297,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
@@ -335,21 +336,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_set_msi_irq(kvm, e, &irq);
if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
- !kvm_irq_is_postable(&irq)) {
- /*
- * Make sure the IRTE is in remapped mode if
- * we don't handle it in posted mode.
- */
- ret = irq_set_vcpu_affinity(host_irq, NULL);
- if (ret < 0) {
- printk(KERN_INFO
- "failed to back to remapped mode, irq: %u\n",
- host_irq);
- goto out;
- }
-
+ !kvm_irq_is_postable(&irq))
continue;
- }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
@@ -357,11 +345,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
- if (set)
- ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else
- ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (!set)
+ continue;
+ enable_remapped_mode = false;
+
+ ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
__func__);
@@ -369,6 +358,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
}
+ if (enable_remapped_mode)
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+
ret = 0;
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3712dde0bf9d..df5b99ea1f18 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11098,7 +11098,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
/*
* Profile KVM exit RIPs:
*/
- if (unlikely(prof_on == KVM_PROFILING)) {
+ if (unlikely(prof_on == KVM_PROFILING &&
+ !vcpu->arch.guest_state_protected)) {
unsigned long rip = kvm_rip_read(vcpu);
profile_hit(KVM_PROFILING, (void *)rip);
}
@@ -13556,25 +13557,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
}
EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
-bool kvm_arch_has_irq_bypass(void)
-{
- return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
int ret;
- irqfd->producer = prod;
kvm_arch_start_assignment(irqfd->kvm);
+
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = prod;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 1);
if (ret)
kvm_arch_end_assignment(irqfd->kvm);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
return ret;
}
@@ -13584,9 +13587,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
int ret;
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
WARN_ON(irqfd->producer != prod);
- irqfd->producer = NULL;
/*
* When producer of consumer is unregistered, we change back to
@@ -13594,12 +13597,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
* when the irq is masked/disabled or the consumer side (KVM
* int this case doesn't want to receive the interrupts.
*/
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = NULL;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 0);
if (ret)
printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
" fails: %d\n", irqfd->consumer.token, ret);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
kvm_arch_end_assignment(irqfd->kvm);
}
@@ -13612,7 +13621,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
struct kvm_kernel_irq_routing_entry *new)
{
- if (new->type != KVM_IRQ_ROUTING_MSI)
+ if (old->type != KVM_IRQ_ROUTING_MSI ||
+ new->type != KVM_IRQ_ROUTING_MSI)
return true;
return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..f5dd84eb55dc 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@ AVXcode: 4
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a05fcddfc811..f7ae44d3dd9e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -360,7 +360,7 @@ static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
* We allocate one page for pgd.
*/
if (!SHARED_KERNEL_PMD)
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
/*
* Now PAE kernel is not running as a Xen domain. We can allocate
@@ -380,7 +380,7 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
{
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
}
static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac57259a432b..a4b4ebd41b8f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void)
gfp_t gfp_mask;
gfp_mask = GFP_KERNEL | __GFP_ZERO;
- efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
+ efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
if (!efi_pgd)
goto fail;
@@ -96,7 +96,7 @@ free_p4d:
if (pgtable_l5_enabled())
free_page((unsigned long)pgd_page_vaddr(*pgd));
free_pgd:
- free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)efi_pgd, pgd_allocation_order());
fail:
return -ENOMEM;
}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1b7710bd0d05..53282dc7d5ac 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -103,10 +103,6 @@ noinstr void *__xen_hypercall_setfunc(void)
void (*func)(void);
/*
- * Xen is supported only on CPUs with CPUID, so testing for
- * X86_FEATURE_CPUID is a test for early_cpu_init() having been
- * run.
- *
* Note that __xen_hypercall_setfunc() is noinstr only due to a nasty
* dependency chain: it is being called via the xen_hypercall static
* call when running as a PVH or HVM guest. Hypercalls need to be
@@ -118,8 +114,7 @@ noinstr void *__xen_hypercall_setfunc(void)
*/
instrumentation_begin();
- if (!boot_cpu_has(X86_FEATURE_CPUID))
- xen_get_vendor();
+ xen_get_vendor();
if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 10c660fae8b3..7237d56a9d3f 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,14 +54,20 @@ struct mc_debug_data {
static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
static struct mc_debug_data mc_debug_data_early __initdata;
-static DEFINE_PER_CPU(struct mc_debug_data *, mc_debug_data) =
- &mc_debug_data_early;
static struct mc_debug_data __percpu *mc_debug_data_ptr;
DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
static struct static_key mc_debug __ro_after_init;
static bool mc_debug_enabled __initdata;
+static struct mc_debug_data * __ref get_mc_debug(void)
+{
+ if (!mc_debug_data_ptr)
+ return &mc_debug_data_early;
+
+ return this_cpu_ptr(mc_debug_data_ptr);
+}
+
static int __init xen_parse_mc_debug(char *arg)
{
mc_debug_enabled = true;
@@ -71,20 +77,16 @@ static int __init xen_parse_mc_debug(char *arg)
}
early_param("xen_mc_debug", xen_parse_mc_debug);
-void mc_percpu_init(unsigned int cpu)
-{
- per_cpu(mc_debug_data, cpu) = per_cpu_ptr(mc_debug_data_ptr, cpu);
-}
-
static int __init mc_debug_enable(void)
{
unsigned long flags;
+ struct mc_debug_data __percpu *mcdb;
if (!mc_debug_enabled)
return 0;
- mc_debug_data_ptr = alloc_percpu(struct mc_debug_data);
- if (!mc_debug_data_ptr) {
+ mcdb = alloc_percpu(struct mc_debug_data);
+ if (!mcdb) {
pr_err("xen_mc_debug inactive\n");
static_key_slow_dec(&mc_debug);
return -ENOMEM;
@@ -93,7 +95,7 @@ static int __init mc_debug_enable(void)
/* Be careful when switching to percpu debug data. */
local_irq_save(flags);
xen_mc_flush();
- mc_percpu_init(0);
+ mc_debug_data_ptr = mcdb;
local_irq_restore(flags);
pr_info("xen_mc_debug active\n");
@@ -155,7 +157,7 @@ void xen_mc_flush(void)
trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
if (static_key_false(&mc_debug)) {
- mcdb = __this_cpu_read(mc_debug_data);
+ mcdb = get_mc_debug();
memcpy(mcdb->entries, b->entries,
b->mcidx * sizeof(struct multicall_entry));
}
@@ -235,7 +237,7 @@ struct multicall_space __xen_mc_entry(size_t args)
ret.mc = &b->entries[b->mcidx];
if (static_key_false(&mc_debug)) {
- struct mc_debug_data *mcdb = __this_cpu_read(mc_debug_data);
+ struct mc_debug_data *mcdb = get_mc_debug();
mcdb->caller[b->mcidx] = __builtin_return_address(0);
mcdb->argsz[b->mcidx] = args;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 688ff59318ae..9bb8ff8bff30 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -305,7 +305,6 @@ static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
return rc;
xen_pmu_init(cpu);
- mc_percpu_init(cpu);
/*
* Why is this a BUG? If the hypercall fails then everything can be
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 63c13a2ccf55..25e318ef27d6 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -261,9 +261,6 @@ void xen_mc_callback(void (*fn)(void *), void *data);
*/
struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
-/* Do percpu data initialization for multicalls. */
-void mc_percpu_init(unsigned int cpu);
-
extern bool is_xen_pmu;
irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);