summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig23
-rw-r--r--arch/x86/boot/compressed/Makefile5
-rw-r--r--arch/x86/boot/compressed/eboot.c65
-rw-r--r--arch/x86/boot/cpu.c6
-rw-r--r--arch/x86/events/amd/core.c8
-rw-r--r--arch/x86/events/core.c20
-rw-r--r--arch/x86/events/intel/core.c2
-rw-r--r--arch/x86/events/intel/cstate.c1
-rw-r--r--arch/x86/events/intel/ds.c35
-rw-r--r--arch/x86/events/intel/uncore.c8
-rw-r--r--arch/x86/events/intel/uncore_snb.c44
-rw-r--r--arch/x86/events/perf_event.h4
-rw-r--r--arch/x86/include/asm/amd_nb.h23
-rw-r--r--arch/x86/include/asm/apic.h3
-rw-r--r--arch/x86/include/asm/compat.h4
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/efi.h16
-rw-r--r--arch/x86/include/asm/intel-mid.h1
-rw-r--r--arch/x86/include/asm/mce.h23
-rw-r--r--arch/x86/include/asm/msr-index.h4
-rw-r--r--arch/x86/include/asm/msr.h46
-rw-r--r--arch/x86/include/asm/mutex.h5
-rw-r--r--arch/x86/include/asm/mutex_32.h110
-rw-r--r--arch/x86/include/asm/mutex_64.h127
-rw-r--r--arch/x86/include/asm/paravirt.h5
-rw-r--r--arch/x86/include/asm/paravirt_types.h16
-rw-r--r--arch/x86/include/asm/preempt.h8
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/qspinlock.h6
-rw-r--r--arch/x86/include/asm/topology.h32
-rw-r--r--arch/x86/include/asm/uaccess.h13
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h1
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h4
-rw-r--r--arch/x86/include/uapi/asm/mce.h1
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--arch/x86/kernel/acpi/boot.c2
-rw-r--r--arch/x86/kernel/amd_nb.c164
-rw-r--r--arch/x86/kernel/apic/apic.c1
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c4
-rw-r--r--arch/x86/kernel/apm_32.c4
-rw-r--r--arch/x86/kernel/cpu/amd.c6
-rw-r--r--arch/x86/kernel/cpu/common.c32
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c72
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c272
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c41
-rw-r--r--arch/x86/kernel/dumpstack.c2
-rw-r--r--arch/x86/kernel/fpu/core.c16
-rw-r--r--arch/x86/kernel/head_32.S9
-rw-r--r--arch/x86/kernel/itmt.c215
-rw-r--r--arch/x86/kernel/kvm.c17
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c14
-rw-r--r--arch/x86/kernel/paravirt_patch_32.c12
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c12
-rw-r--r--arch/x86/kernel/smp.c2
-rw-r--r--arch/x86/kernel/smpboot.c47
-rw-r--r--arch/x86/kernel/sysfb_simplefb.c39
-rw-r--r--arch/x86/kernel/unwind_guess.c13
-rw-r--r--arch/x86/kvm/emulate.c36
-rw-r--r--arch/x86/kvm/ioapic.c2
-rw-r--r--arch/x86/kvm/ioapic.h4
-rw-r--r--arch/x86/kvm/irq_comm.c71
-rw-r--r--arch/x86/kvm/lapic.c2
-rw-r--r--arch/x86/kvm/x86.c63
-rw-r--r--arch/x86/lib/msr.c4
-rw-r--r--arch/x86/mm/extable.c7
-rw-r--r--arch/x86/mm/pat.c7
-rw-r--r--arch/x86/net/bpf_jit_comp.c2
-rw-r--r--arch/x86/platform/efi/efi.c2
-rw-r--r--arch/x86/platform/efi/efi_64.c80
-rw-r--r--arch/x86/platform/intel-mid/device_libs/Makefile2
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c (renamed from arch/x86/platform/intel-mid/device_libs/platform_wdt.c)34
-rw-r--r--arch/x86/platform/intel-mid/pwr.c19
-rw-r--r--arch/x86/platform/olpc/olpc-xo15-sci.c2
-rw-r--r--arch/x86/purgatory/Makefile1
-rw-r--r--arch/x86/ras/mce_amd_inj.c2
-rw-r--r--arch/x86/tools/relocs.h2
-rw-r--r--arch/x86/um/asm/processor.h1
-rw-r--r--arch/x86/xen/spinlock.c2
79 files changed, 1441 insertions, 575 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bada636d1065..a8cd4227869f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -939,6 +939,27 @@ config SCHED_MC
making when dealing with multi-core CPU chips at a cost of slightly
increased overhead in some places. If unsure say N here.
+config SCHED_MC_PRIO
+ bool "CPU core priorities scheduler support"
+ depends on SCHED_MC && CPU_SUP_INTEL
+ select X86_INTEL_PSTATE
+ select CPU_FREQ
+ default y
+ ---help---
+ Intel Turbo Boost Max Technology 3.0 enabled CPUs have a
+ core ordering determined at manufacturing time, which allows
+ certain cores to reach higher turbo frequencies (when running
+ single threaded workloads) than others.
+
+ Enabling this kernel feature teaches the scheduler about
+ the TBM3 (aka ITMT) priority order of the CPU cores and adjusts the
+ scheduler's CPU selection logic accordingly, so that higher
+ overall system performance can be achieved.
+
+ This feature will have no effect on CPUs without this feature.
+
+ If unsure say Y here.
+
source "kernel/Kconfig.preempt"
config UP_LATE_INIT
@@ -1025,7 +1046,7 @@ config X86_MCE_INTEL
config X86_MCE_AMD
def_bool y
prompt "AMD MCE features"
- depends on X86_MCE && X86_LOCAL_APIC
+ depends on X86_MCE && X86_LOCAL_APIC && AMD_NB
---help---
Additional support for AMD specific MCE features such as
the DRAM Error Threshold.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 536ccfcc01c6..34d9e15857c3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -40,8 +40,8 @@ GCOV_PROFILE := n
UBSAN_SANITIZE :=n
LDFLAGS := -m elf_$(UTS_MACHINE)
-ifeq ($(CONFIG_RELOCATABLE),y)
-# If kernel is relocatable, build compressed kernel as PIE.
+# Compressed kernel should be built as PIE since it may be loaded at any
+# address by the bootloader.
ifeq ($(CONFIG_X86_32),y)
LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
else
@@ -51,7 +51,6 @@ else
LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
&& echo "-z noreloc-overflow -pie --no-dynamic-linker")
endif
-endif
LDFLAGS_vmlinux := -T
hostprogs-y := mkpiggy
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index cc69e37548db..ff01c8fc76f7 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -537,6 +537,69 @@ free_handle:
efi_call_early(free_pool, pci_handle);
}
+static void retrieve_apple_device_properties(struct boot_params *boot_params)
+{
+ efi_guid_t guid = APPLE_PROPERTIES_PROTOCOL_GUID;
+ struct setup_data *data, *new;
+ efi_status_t status;
+ u32 size = 0;
+ void *p;
+
+ status = efi_call_early(locate_protocol, &guid, NULL, &p);
+ if (status != EFI_SUCCESS)
+ return;
+
+ if (efi_table_attr(apple_properties_protocol, version, p) != 0x10000) {
+ efi_printk(sys_table, "Unsupported properties proto version\n");
+ return;
+ }
+
+ efi_call_proto(apple_properties_protocol, get_all, p, NULL, &size);
+ if (!size)
+ return;
+
+ do {
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ size + sizeof(struct setup_data), &new);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table,
+ "Failed to alloc mem for properties\n");
+ return;
+ }
+
+ status = efi_call_proto(apple_properties_protocol, get_all, p,
+ new->data, &size);
+
+ if (status == EFI_BUFFER_TOO_SMALL)
+ efi_call_early(free_pool, new);
+ } while (status == EFI_BUFFER_TOO_SMALL);
+
+ new->type = SETUP_APPLE_PROPERTIES;
+ new->len = size;
+ new->next = 0;
+
+ data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
+ if (!data)
+ boot_params->hdr.setup_data = (unsigned long)new;
+ else {
+ while (data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
+ data->next = (unsigned long)new;
+ }
+}
+
+static void setup_quirks(struct boot_params *boot_params)
+{
+ efi_char16_t const apple[] = { 'A', 'p', 'p', 'l', 'e', 0 };
+ efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long)
+ efi_table_attr(efi_system_table, fw_vendor, sys_table);
+
+ if (!memcmp(fw_vendor, apple, sizeof(apple))) {
+ if (IS_ENABLED(CONFIG_APPLE_PROPERTIES))
+ retrieve_apple_device_properties(boot_params);
+ }
+}
+
static efi_status_t
setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
{
@@ -1098,6 +1161,8 @@ struct boot_params *efi_main(struct efi_config *c,
setup_efi_pci(boot_params);
+ setup_quirks(boot_params);
+
status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
sizeof(*gdt), (void **)&gdt);
if (status != EFI_SUCCESS) {
diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 26240dde081e..4224ede43b4e 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -87,6 +87,12 @@ int validate_cpu(void)
return -1;
}
+ if (CONFIG_X86_MINIMUM_CPU_FAMILY <= 4 && !IS_ENABLED(CONFIG_M486) &&
+ !has_eflag(X86_EFLAGS_ID)) {
+ printf("This kernel requires a CPU with the CPUID instruction. Build with CONFIG_M486=y to run on this CPU.\n");
+ return -1;
+ }
+
if (err_flags) {
puts("This kernel requires the following features "
"not present on the CPU:\n");
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index f5f4b3fbbbc2..afb222b63cae 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -662,7 +662,13 @@ static int __init amd_core_pmu_init(void)
pr_cont("Fam15h ");
x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
break;
-
+ case 0x17:
+ pr_cont("Fam17h ");
+ /*
+ * In family 17h, there are no event constraints in the PMC hardware.
+ * We fallback to using default amd_get_event_constraints.
+ */
+ break;
default:
pr_err("core perfctr but no constraints; unknown hardware!\n");
return -ENODEV;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d31735f37ed7..7fe88bb57e36 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -69,7 +69,7 @@ u64 x86_perf_event_update(struct perf_event *event)
int shift = 64 - x86_pmu.cntval_bits;
u64 prev_raw_count, new_raw_count;
int idx = hwc->idx;
- s64 delta;
+ u64 delta;
if (idx == INTEL_PMC_IDX_FIXED_BTS)
return 0;
@@ -365,7 +365,11 @@ int x86_add_exclusive(unsigned int what)
{
int i;
- if (x86_pmu.lbr_pt_coexist)
+ /*
+ * When lbr_pt_coexist we allow PT to coexist with either LBR or BTS.
+ * LBR and BTS are still mutually exclusive.
+ */
+ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
return 0;
if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
@@ -388,7 +392,7 @@ fail_unlock:
void x86_del_exclusive(unsigned int what)
{
- if (x86_pmu.lbr_pt_coexist)
+ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt)
return;
atomic_dec(&x86_pmu.lbr_exclusive[what]);
@@ -2352,7 +2356,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
frame.next_frame = 0;
frame.return_address = 0;
- if (!access_ok(VERIFY_READ, fp, 8))
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
@@ -2362,9 +2366,6 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
if (bytes != 0)
break;
- if (!valid_user_frame(fp, sizeof(frame)))
- break;
-
perf_callchain_store(entry, cs_base + frame.return_address);
fp = compat_ptr(ss_base + frame.next_frame);
}
@@ -2413,7 +2414,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
frame.next_frame = NULL;
frame.return_address = 0;
- if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
@@ -2423,9 +2424,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
if (bytes != 0)
break;
- if (!valid_user_frame(fp, sizeof(frame)))
- break;
-
perf_callchain_store(entry, frame.return_address);
fp = (void __user *)frame.next_frame;
}
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a74a2dbc0180..cb8522290e6a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4034,7 +4034,7 @@ __init int intel_pmu_init(void)
/* Support full width counters using alternative MSR range */
if (x86_pmu.intel_cap.full_width_write) {
- x86_pmu.max_period = x86_pmu.cntval_mask;
+ x86_pmu.max_period = x86_pmu.cntval_mask >> 1;
x86_pmu.perfctr = MSR_IA32_PMC0;
pr_cont("full-width counters, ");
}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4f5ac726335f..da51e5a3e2ff 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -540,6 +540,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 0319311dbdbb..be202390bbd3 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1108,20 +1108,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
}
/*
- * We use the interrupt regs as a base because the PEBS record
- * does not contain a full regs set, specifically it seems to
- * lack segment descriptors, which get used by things like
- * user_mode().
+ * We use the interrupt regs as a base because the PEBS record does not
+ * contain a full regs set, specifically it seems to lack segment
+ * descriptors, which get used by things like user_mode().
*
- * In the simple case fix up only the IP and BP,SP regs, for
- * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
- * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+ * In the simple case fix up only the IP for PERF_SAMPLE_IP.
+ *
+ * We must however always use BP,SP from iregs for the unwinder to stay
+ * sane; the record BP,SP can point into thin air when the record is
+ * from a previous PMI context or an (I)RET happend between the record
+ * and PMI.
*/
*regs = *iregs;
regs->flags = pebs->flags;
set_linear_ip(regs, pebs->ip);
- regs->bp = pebs->bp;
- regs->sp = pebs->sp;
if (sample_type & PERF_SAMPLE_REGS_INTR) {
regs->ax = pebs->ax;
@@ -1130,10 +1130,21 @@ static void setup_pebs_sample_data(struct perf_event *event,
regs->dx = pebs->dx;
regs->si = pebs->si;
regs->di = pebs->di;
- regs->bp = pebs->bp;
- regs->sp = pebs->sp;
- regs->flags = pebs->flags;
+ /*
+ * Per the above; only set BP,SP if we don't need callchains.
+ *
+ * XXX: does this make sense?
+ */
+ if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+ regs->bp = pebs->bp;
+ regs->sp = pebs->sp;
+ }
+
+ /*
+ * Preserve PERF_EFLAGS_VM from set_linear_ip().
+ */
+ regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
#ifndef CONFIG_X86_32
regs->r8 = pebs->r8;
regs->r9 = pebs->r9;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index efca2685d876..dbaaf7dc8373 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -319,9 +319,9 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
*/
static int uncore_pmu_event_init(struct perf_event *event);
-static bool is_uncore_event(struct perf_event *event)
+static bool is_box_event(struct intel_uncore_box *box, struct perf_event *event)
{
- return event->pmu->event_init == uncore_pmu_event_init;
+ return &box->pmu->pmu == event->pmu;
}
static int
@@ -340,7 +340,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
n = box->n_events;
- if (is_uncore_event(leader)) {
+ if (is_box_event(box, leader)) {
box->event_list[n] = leader;
n++;
}
@@ -349,7 +349,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
return n;
list_for_each_entry(event, &leader->sibling_list, group_entry) {
- if (!is_uncore_event(event) ||
+ if (!is_box_event(box, event) ||
event->state <= PERF_EVENT_STATE_OFF)
continue;
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 5f845eef9a4d..a3dcc12bef4a 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -8,8 +8,12 @@
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -486,24 +490,12 @@ static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
snb_uncore_imc_event_start(event, 0);
- box->n_events++;
-
return 0;
}
static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- int i;
-
snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-
- for (i = 0; i < box->n_events; i++) {
- if (event == box->event_list[i]) {
- --box->n_events;
- break;
- }
- }
}
int snb_pci2phy_map_init(int devid)
@@ -616,13 +608,29 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
static const struct pci_device_id skl_uncore_pci_ids[] = {
{ /* IMC */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
{ /* end: all zeroes */ },
};
@@ -666,8 +674,12 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */
IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */
- IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */
+ IMC_DEV(SKL_Y_IMC, &skl_uncore_pci_driver), /* 6th Gen Core Y */
IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver), /* 6th Gen Core U */
+ IMC_DEV(SKL_HD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Dual Core */
+ IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */
+ IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */
+ IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */
{ /* end marker */ }
};
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 5874d8de1f8d..bcbb1d2ae10b 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -113,7 +113,7 @@ struct debug_store {
* Per register state.
*/
struct er_account {
- raw_spinlock_t lock; /* per-core: protect structure */
+ raw_spinlock_t lock; /* per-core: protect structure */
u64 config; /* extra MSR config */
u64 reg; /* extra MSR number */
atomic_t ref; /* reference count */
@@ -604,7 +604,7 @@ struct x86_pmu {
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
const int *lbr_sel_map; /* lbr_select mappings */
bool lbr_double_abort; /* duplicated lbr aborts */
- bool lbr_pt_coexist; /* LBR may coexist with PT */
+ bool lbr_pt_coexist; /* (LBR|BTS) may coexist with PT */
/*
* Intel PT/LBR/BTS are exclusive
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 5e828da2e18f..00c88a01301d 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -21,6 +21,10 @@ extern int amd_numa_init(void);
extern int amd_get_subcaches(int);
extern int amd_set_subcaches(int, unsigned long);
+extern int amd_smn_read(u16 node, u32 address, u32 *value);
+extern int amd_smn_write(u16 node, u32 address, u32 value);
+extern int amd_df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo);
+
struct amd_l3_cache {
unsigned indices;
u8 subcaches[4];
@@ -55,6 +59,7 @@ struct threshold_bank {
};
struct amd_northbridge {
+ struct pci_dev *root;
struct pci_dev *misc;
struct pci_dev *link;
struct amd_l3_cache l3_cache;
@@ -66,7 +71,6 @@ struct amd_northbridge_info {
u64 flags;
struct amd_northbridge *nb;
};
-extern struct amd_northbridge_info amd_northbridges;
#define AMD_NB_GART BIT(0)
#define AMD_NB_L3_INDEX_DISABLE BIT(1)
@@ -74,20 +78,9 @@ extern struct amd_northbridge_info amd_northbridges;
#ifdef CONFIG_AMD_NB
-static inline u16 amd_nb_num(void)
-{
- return amd_northbridges.num;
-}
-
-static inline bool amd_nb_has_feature(unsigned feature)
-{
- return ((amd_northbridges.flags & feature) == feature);
-}
-
-static inline struct amd_northbridge *node_to_amd_nb(int node)
-{
- return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL;
-}
+u16 amd_nb_num(void);
+bool amd_nb_has_feature(unsigned int feature);
+struct amd_northbridge *node_to_amd_nb(int node);
static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev)
{
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f5aaf6c83222..a5a0bcfde76a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -196,7 +196,7 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
{
- wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+ wrmsr_notrace(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
}
static inline u32 native_apic_msr_read(u32 reg)
@@ -332,6 +332,7 @@ struct apic {
* on write for EOI.
*/
void (*eoi_write)(u32 reg, u32 v);
+ void (*native_eoi_write)(u32 reg, u32 v);
u64 (*icr_read)(void);
void (*icr_write)(u32 low, u32 high);
void (*wait_icr_idle)(void);
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 03d269bed941..24118c0b4640 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -272,7 +272,6 @@ struct compat_shmid64_ds {
/*
* The type of struct elf_prstatus.pr_reg in compatible core dumps.
*/
-#ifdef CONFIG_X86_X32_ABI
typedef struct user_regs_struct compat_elf_gregset_t;
/* Full regset -- prstatus on x32, otherwise on ia32 */
@@ -281,10 +280,9 @@ typedef struct user_regs_struct compat_elf_gregset_t;
do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \
while (0)
+#ifdef CONFIG_X86_X32_ABI
#define COMPAT_USE_64BIT_TIME \
(!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
-#else
-typedef struct user_regs_struct32 compat_elf_gregset_t;
#endif
/*
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index eac7572bf8bb..4dba597c5807 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -193,6 +193,7 @@
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 389d700b961e..e99675b9c861 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -210,12 +210,18 @@ static inline bool efi_is_64bit(void)
return __efi_early()->is64;
}
+#define efi_table_attr(table, attr, instance) \
+ (efi_is_64bit() ? \
+ ((table##_64_t *)(unsigned long)instance)->attr : \
+ ((table##_32_t *)(unsigned long)instance)->attr)
+
+#define efi_call_proto(protocol, f, instance, ...) \
+ __efi_early()->call(efi_table_attr(protocol, f, instance), \
+ instance, ##__VA_ARGS__)
+
#define efi_call_early(f, ...) \
- __efi_early()->call(efi_is_64bit() ? \
- ((efi_boot_services_64_t *)(unsigned long) \
- __efi_early()->boot_services)->f : \
- ((efi_boot_services_32_t *)(unsigned long) \
- __efi_early()->boot_services)->f, __VA_ARGS__)
+ __efi_early()->call(efi_table_attr(efi_boot_services, f, \
+ __efi_early()->boot_services), __VA_ARGS__)
#define __efi_call_early(f, ...) \
__efi_early()->call((unsigned long)f, __VA_ARGS__);
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 5b6753d1f7f4..49da9f497b90 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -17,6 +17,7 @@
extern int intel_mid_pci_init(void);
extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state);
+extern pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev);
extern void intel_mid_pwr_power_off(void);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 9bd7ff5ffbcc..caab413c91ad 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -252,8 +252,10 @@ static inline void cmci_recheck(void) {}
#ifdef CONFIG_X86_MCE_AMD
void mce_amd_feature_init(struct cpuinfo_x86 *c);
+int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
#else
static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
+static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
#endif
int mce_available(struct cpuinfo_x86 *c);
@@ -356,28 +358,23 @@ enum smca_bank_types {
N_SMCA_BANK_TYPES
};
-struct smca_bank_name {
- const char *name; /* Short name for sysfs */
- const char *long_name; /* Long name for pretty-printing */
-};
-
-extern struct smca_bank_name smca_bank_names[N_SMCA_BANK_TYPES];
-
-#define HWID_MCATYPE(hwid, mcatype) ((hwid << 16) | mcatype)
+#define HWID_MCATYPE(hwid, mcatype) (((hwid) << 16) | (mcatype))
-struct smca_hwid_mcatype {
+struct smca_hwid {
unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */
u32 hwid_mcatype; /* (hwid,mcatype) tuple */
u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */
};
-struct smca_bank_info {
- struct smca_hwid_mcatype *type;
- u32 type_instance;
+struct smca_bank {
+ struct smca_hwid *hwid;
+ /* Instance ID */
+ u32 id;
};
-extern struct smca_bank_info smca_banks[MAX_NR_BANKS];
+extern struct smca_bank smca_banks[MAX_NR_BANKS];
+extern const char *smca_get_long_name(enum smca_bank_types t);
#endif
#endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 78f3760ca1f2..710273c617b8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -37,6 +37,10 @@
#define EFER_FFXSR (1<<_EFER_FFXSR)
/* Intel MSRs. Some also available on other CPUs */
+
+#define MSR_PPIN_CTL 0x0000004e
+#define MSR_PPIN 0x0000004f
+
#define MSR_IA32_PERFCTR0 0x000000c1
#define MSR_IA32_PERFCTR1 0x000000c2
#define MSR_FSB_FREQ 0x000000cd
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index b5fee97813cd..db0b90c3b03e 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -70,14 +70,14 @@ extern struct tracepoint __tracepoint_read_msr;
extern struct tracepoint __tracepoint_write_msr;
extern struct tracepoint __tracepoint_rdpmc;
#define msr_tracepoint_active(t) static_key_false(&(t).key)
-extern void do_trace_write_msr(unsigned msr, u64 val, int failed);
-extern void do_trace_read_msr(unsigned msr, u64 val, int failed);
-extern void do_trace_rdpmc(unsigned msr, u64 val, int failed);
+extern void do_trace_write_msr(unsigned int msr, u64 val, int failed);
+extern void do_trace_read_msr(unsigned int msr, u64 val, int failed);
+extern void do_trace_rdpmc(unsigned int msr, u64 val, int failed);
#else
#define msr_tracepoint_active(t) false
-static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {}
-static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {}
-static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {}
+static inline void do_trace_write_msr(unsigned int msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
#endif
static inline unsigned long long native_read_msr(unsigned int msr)
@@ -115,22 +115,36 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
}
/* Can be uninlined because referenced by paravirt */
-notrace static inline void native_write_msr(unsigned int msr,
- unsigned low, unsigned high)
+static inline void notrace
+__native_write_msr_notrace(unsigned int msr, u32 low, u32 high)
{
asm volatile("1: wrmsr\n"
"2:\n"
_ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
: : "c" (msr), "a"(low), "d" (high) : "memory");
+}
+
+/* Can be uninlined because referenced by paravirt */
+static inline void notrace
+native_write_msr(unsigned int msr, u32 low, u32 high)
+{
+ __native_write_msr_notrace(msr, low, high);
if (msr_tracepoint_active(__tracepoint_write_msr))
do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
}
+static inline void
+wrmsr_notrace(unsigned int msr, u32 low, u32 high)
+{
+ __native_write_msr_notrace(msr, low, high);
+}
+
/* Can be uninlined because referenced by paravirt */
-notrace static inline int native_write_msr_safe(unsigned int msr,
- unsigned low, unsigned high)
+static inline int notrace
+native_write_msr_safe(unsigned int msr, u32 low, u32 high)
{
int err;
+
asm volatile("2: wrmsr ; xor %[err],%[err]\n"
"1:\n\t"
".section .fixup,\"ax\"\n\t"
@@ -223,7 +237,7 @@ do { \
(void)((high) = (u32)(__val >> 32)); \
} while (0)
-static inline void wrmsr(unsigned msr, unsigned low, unsigned high)
+static inline void wrmsr(unsigned int msr, u32 low, u32 high)
{
native_write_msr(msr, low, high);
}
@@ -231,13 +245,13 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high)
#define rdmsrl(msr, val) \
((val) = native_read_msr((msr)))
-static inline void wrmsrl(unsigned msr, u64 val)
+static inline void wrmsrl(unsigned int msr, u64 val)
{
native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
}
/* wrmsr with exception handling */
-static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
+static inline int wrmsr_safe(unsigned int msr, u32 low, u32 high)
{
return native_write_msr_safe(msr, low, high);
}
@@ -252,7 +266,7 @@ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
__err; \
})
-static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
+static inline int rdmsrl_safe(unsigned int msr, unsigned long long *p)
{
int err;
@@ -325,12 +339,12 @@ static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
struct msr *msrs)
{
- rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h));
+ rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h));
}
static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no,
struct msr *msrs)
{
- wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h);
+ wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h);
}
static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
u32 *l, u32 *h)
diff --git a/arch/x86/include/asm/mutex.h b/arch/x86/include/asm/mutex.h
deleted file mode 100644
index 7d3a48275394..000000000000
--- a/arch/x86/include/asm/mutex.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include <asm/mutex_32.h>
-#else
-# include <asm/mutex_64.h>
-#endif
diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h
deleted file mode 100644
index e9355a84fc67..000000000000
--- a/arch/x86/include/asm/mutex_32.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef _ASM_X86_MUTEX_32_H
-#define _ASM_X86_MUTEX_32_H
-
-#include <asm/alternative.h>
-
-/**
- * __mutex_fastpath_lock - try to take the lock by moving the count
- * from 1 to a 0 value
- * @count: pointer of type atomic_t
- * @fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fn> if it
- * wasn't 1 originally. This function MUST leave the value lower than 1
- * even when the "1" assertion wasn't true.
- */
-#define __mutex_fastpath_lock(count, fail_fn) \
-do { \
- unsigned int dummy; \
- \
- typecheck(atomic_t *, count); \
- typecheck_fn(void (*)(atomic_t *), fail_fn); \
- \
- asm volatile(LOCK_PREFIX " decl (%%eax)\n" \
- " jns 1f \n" \
- " call " #fail_fn "\n" \
- "1:\n" \
- : "=a" (dummy) \
- : "a" (count) \
- : "memory", "ecx", "edx"); \
-} while (0)
-
-
-/**
- * __mutex_fastpath_lock_retval - try to take the lock by moving the count
- * from 1 to a 0 value
- * @count: pointer of type atomic_t
- *
- * Change the count from 1 to a value lower than 1. This function returns 0
- * if the fastpath succeeds, or -1 otherwise.
- */
-static inline int __mutex_fastpath_lock_retval(atomic_t *count)
-{
- if (unlikely(atomic_dec_return(count) < 0))
- return -1;
- else
- return 0;
-}
-
-/**
- * __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
- * @count: pointer of type atomic_t
- * @fail_fn: function to call if the original value was not 0
- *
- * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
- * In the failure case, this function is allowed to either set the value
- * to 1, or to set it to a value lower than 1.
- *
- * If the implementation sets it to a value of lower than 1, the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-#define __mutex_fastpath_unlock(count, fail_fn) \
-do { \
- unsigned int dummy; \
- \
- typecheck(atomic_t *, count); \
- typecheck_fn(void (*)(atomic_t *), fail_fn); \
- \
- asm volatile(LOCK_PREFIX " incl (%%eax)\n" \
- " jg 1f\n" \
- " call " #fail_fn "\n" \
- "1:\n" \
- : "=a" (dummy) \
- : "a" (count) \
- : "memory", "ecx", "edx"); \
-} while (0)
-
-#define __mutex_slowpath_needs_to_unlock() 1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- * @count: pointer of type atomic_t
- * @fail_fn: fallback function
- *
- * Change the count from 1 to a value lower than 1, and return 0 (failure)
- * if it wasn't 1 originally, or return 1 (success) otherwise. This function
- * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
- * Additionally, if the value was < 0 originally, this function must not leave
- * it to 0 on failure.
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
- int (*fail_fn)(atomic_t *))
-{
- /* cmpxchg because it never induces a false contention state. */
- if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
- return 1;
-
- return 0;
-}
-
-#endif /* _ASM_X86_MUTEX_32_H */
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
deleted file mode 100644
index d9850758464e..000000000000
--- a/arch/x86/include/asm/mutex_64.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef _ASM_X86_MUTEX_64_H
-#define _ASM_X86_MUTEX_64_H
-
-/**
- * __mutex_fastpath_lock - decrement and call function if negative
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is negative
- *
- * Atomically decrements @v and calls <fail_fn> if the result is negative.
- */
-#ifdef CC_HAVE_ASM_GOTO
-static inline void __mutex_fastpath_lock(atomic_t *v,
- void (*fail_fn)(atomic_t *))
-{
- asm_volatile_goto(LOCK_PREFIX " decl %0\n"
- " jns %l[exit]\n"
- : : "m" (v->counter)
- : "memory", "cc"
- : exit);
- fail_fn(v);
-exit:
- return;
-}
-#else
-#define __mutex_fastpath_lock(v, fail_fn) \
-do { \
- unsigned long dummy; \
- \
- typecheck(atomic_t *, v); \
- typecheck_fn(void (*)(atomic_t *), fail_fn); \
- \
- asm volatile(LOCK_PREFIX " decl (%%rdi)\n" \
- " jns 1f \n" \
- " call " #fail_fn "\n" \
- "1:" \
- : "=D" (dummy) \
- : "D" (v) \
- : "rax", "rsi", "rdx", "rcx", \
- "r8", "r9", "r10", "r11", "memory"); \
-} while (0)
-#endif
-
-/**
- * __mutex_fastpath_lock_retval - try to take the lock by moving the count
- * from 1 to a 0 value
- * @count: pointer of type atomic_t
- *
- * Change the count from 1 to a value lower than 1. This function returns 0
- * if the fastpath succeeds, or -1 otherwise.
- */
-static inline int __mutex_fastpath_lock_retval(atomic_t *count)
-{
- if (unlikely(atomic_dec_return(count) < 0))
- return -1;
- else
- return 0;
-}
-
-/**
- * __mutex_fastpath_unlock - increment and call function if nonpositive
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is nonpositive
- *
- * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
- */
-#ifdef CC_HAVE_ASM_GOTO
-static inline void __mutex_fastpath_unlock(atomic_t *v,
- void (*fail_fn)(atomic_t *))
-{
- asm_volatile_goto(LOCK_PREFIX " incl %0\n"
- " jg %l[exit]\n"
- : : "m" (v->counter)
- : "memory", "cc"
- : exit);
- fail_fn(v);
-exit:
- return;
-}
-#else
-#define __mutex_fastpath_unlock(v, fail_fn) \
-do { \
- unsigned long dummy; \
- \
- typecheck(atomic_t *, v); \
- typecheck_fn(void (*)(atomic_t *), fail_fn); \
- \
- asm volatile(LOCK_PREFIX " incl (%%rdi)\n" \
- " jg 1f\n" \
- " call " #fail_fn "\n" \
- "1:" \
- : "=D" (dummy) \
- : "D" (v) \
- : "rax", "rsi", "rdx", "rcx", \
- "r8", "r9", "r10", "r11", "memory"); \
-} while (0)
-#endif
-
-#define __mutex_slowpath_needs_to_unlock() 1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- * @count: pointer of type atomic_t
- * @fail_fn: fallback function
- *
- * Change the count from 1 to 0 and return 1 (success), or return 0 (failure)
- * if it wasn't 1 originally. [the fallback function is never used on
- * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.]
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
- int (*fail_fn)(atomic_t *))
-{
- if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
- return 1;
-
- return 0;
-}
-
-#endif /* _ASM_X86_MUTEX_64_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ce932812f142..6108b1fada2b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -678,6 +678,11 @@ static __always_inline void pv_kick(int cpu)
PVOP_VCALL1(pv_lock_ops.kick, cpu);
}
+static __always_inline bool pv_vcpu_is_preempted(int cpu)
+{
+ return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu);
+}
+
#endif /* SMP && PARAVIRT_SPINLOCKS */
#ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0f400c0e4979..3f2bc0f0d3e8 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -310,6 +310,8 @@ struct pv_lock_ops {
void (*wait)(u8 *ptr, u8 val);
void (*kick)(int cpu);
+
+ struct paravirt_callee_save vcpu_is_preempted;
};
/* This contains all the paravirt structures: we get a convenient
@@ -508,6 +510,18 @@ int paravirt_disable_iospace(void);
#define PVOP_TEST_NULL(op) ((void)op)
#endif
+#define PVOP_RETMASK(rettype) \
+ ({ unsigned long __mask = ~0UL; \
+ switch (sizeof(rettype)) { \
+ case 1: __mask = 0xffUL; break; \
+ case 2: __mask = 0xffffUL; break; \
+ case 4: __mask = 0xffffffffUL; break; \
+ default: break; \
+ } \
+ __mask; \
+ })
+
+
#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \
pre, post, ...) \
({ \
@@ -535,7 +549,7 @@ int paravirt_disable_iospace(void);
paravirt_clobber(clbr), \
##__VA_ARGS__ \
: "memory", "cc" extra_clbr); \
- __ret = (rettype)__eax; \
+ __ret = (rettype)(__eax & PVOP_RETMASK(rettype)); \
} \
__ret; \
})
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 17f218645701..ec1f3c651150 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -24,7 +24,13 @@ static __always_inline int preempt_count(void)
static __always_inline void preempt_count_set(int pc)
{
- raw_cpu_write_4(__preempt_count, pc);
+ int old, new;
+
+ do {
+ old = raw_cpu_read_4(__preempt_count);
+ new = (old & PREEMPT_NEED_RESCHED) |
+ (pc & ~PREEMPT_NEED_RESCHED);
+ } while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old);
}
/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index e7f8c62701d4..1f6a92903b09 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -602,8 +602,6 @@ static __always_inline void cpu_relax(void)
rep_nop();
}
-#define cpu_relax_lowlatency() cpu_relax()
-
/* Stop speculative execution and prefetching of modified code. */
static inline void sync_core(void)
{
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index eaba08076030..c343ab52579f 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -32,6 +32,12 @@ static inline void queued_spin_unlock(struct qspinlock *lock)
{
pv_queued_spin_unlock(lock);
}
+
+#define vcpu_is_preempted vcpu_is_preempted
+static inline bool vcpu_is_preempted(int cpu)
+{
+ return pv_vcpu_is_preempted(cpu);
+}
#else
static inline void queued_spin_unlock(struct qspinlock *lock)
{
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index cf75871d2f81..6358a85e2270 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -146,4 +146,36 @@ struct pci_bus;
int x86_pci_root_bus_node(int bus);
void x86_pci_root_bus_resources(int bus, struct list_head *resources);
+extern bool x86_topology_update;
+
+#ifdef CONFIG_SCHED_MC_PRIO
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority);
+extern unsigned int __read_mostly sysctl_sched_itmt_enabled;
+
+/* Interface to set priority of a cpu */
+void sched_set_itmt_core_prio(int prio, int core_cpu);
+
+/* Interface to notify scheduler that system supports ITMT */
+int sched_set_itmt_support(void);
+
+/* Interface to notify scheduler that system revokes ITMT support */
+void sched_clear_itmt_support(void);
+
+#else /* CONFIG_SCHED_MC_PRIO */
+
+#define sysctl_sched_itmt_enabled 0
+static inline void sched_set_itmt_core_prio(int prio, int core_cpu)
+{
+}
+static inline int sched_set_itmt_support(void)
+{
+ return 0;
+}
+static inline void sched_clear_itmt_support(void)
+{
+}
+#endif /* CONFIG_SCHED_MC_PRIO */
+
#endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index faf3687f1035..ea148313570f 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -68,6 +68,12 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
__chk_range_not_ok((unsigned long __force)(addr), size, limit); \
})
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+# define WARN_ON_IN_IRQ() WARN_ON_ONCE(!in_task())
+#else
+# define WARN_ON_IN_IRQ()
+#endif
+
/**
* access_ok: - Checks if a user space pointer is valid
* @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that
@@ -88,8 +94,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
* checks that the pointer is in the user space range - after calling
* this function, memory access functions may still return -EFAULT.
*/
-#define access_ok(type, addr, size) \
- likely(!__range_not_ok(addr, size, user_addr_max()))
+#define access_ok(type, addr, size) \
+({ \
+ WARN_ON_IN_IRQ(); \
+ likely(!__range_not_ok(addr, size, user_addr_max())); \
+})
/*
* These are the main single-value transfer routines. They automatically
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index c18ce67495fa..b10bf319ed20 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -7,6 +7,7 @@
#define SETUP_DTB 2
#define SETUP_PCI 3
#define SETUP_EFI 4
+#define SETUP_APPLE_PROPERTIES 5
/* ram_size flags */
#define RAMDISK_IMAGE_START_MASK 0x07FF
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 94dc8ca434e0..1421a6585126 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -45,7 +45,9 @@ struct kvm_steal_time {
__u64 steal;
__u32 version;
__u32 flags;
- __u32 pad[12];
+ __u8 preempted;
+ __u8 u8_pad[3];
+ __u32 pad[11];
};
#define KVM_STEAL_ALIGNMENT_BITS 5
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 69a6e07e3149..eb6247a7009b 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -28,6 +28,7 @@ struct mce {
__u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */
__u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */
__u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */
+ __u64 ppin; /* Protected Processor Inventory Number */
};
#define MCE_GET_RECORD_LEN _IOR('M', 1, int)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 79076d75bdbf..05110c1097ae 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -123,6 +123,7 @@ obj-$(CONFIG_EFI) += sysfb_efi.o
obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
obj-$(CONFIG_TRACING) += tracepoint.o
+obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o
ifdef CONFIG_FRAME_POINTER
obj-y += unwind_frame.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 931ced8ca345..4764fa56924d 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -76,6 +76,7 @@ int acpi_fix_pin2_polarity __initdata;
static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
#endif
+#ifdef CONFIG_X86_IO_APIC
/*
* Locks related to IOAPIC hotplug
* Hotplug side:
@@ -88,6 +89,7 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
* ->ioapic_lock
*/
static DEFINE_MUTEX(acpi_ioapic_lock);
+#endif
/* --------------------------------------------------------------------------
Boot-time Configuration
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 4fdf6230d93c..458da8509b75 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -13,8 +13,20 @@
#include <linux/spinlock.h>
#include <asm/amd_nb.h>
+#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450
+#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463
+#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
+
+/* Protect the PCI config register pairs used for SMN and DF indirect access. */
+static DEFINE_MUTEX(smn_mutex);
+
static u32 *flush_words;
+static const struct pci_device_id amd_root_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
+ {}
+};
+
const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
@@ -24,9 +36,10 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
{}
};
-EXPORT_SYMBOL(amd_nb_misc_ids);
+EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
@@ -34,6 +47,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
{}
};
@@ -44,8 +58,25 @@ const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
{ }
};
-struct amd_northbridge_info amd_northbridges;
-EXPORT_SYMBOL(amd_northbridges);
+static struct amd_northbridge_info amd_northbridges;
+
+u16 amd_nb_num(void)
+{
+ return amd_northbridges.num;
+}
+EXPORT_SYMBOL_GPL(amd_nb_num);
+
+bool amd_nb_has_feature(unsigned int feature)
+{
+ return ((amd_northbridges.flags & feature) == feature);
+}
+EXPORT_SYMBOL_GPL(amd_nb_has_feature);
+
+struct amd_northbridge *node_to_amd_nb(int node)
+{
+ return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL;
+}
+EXPORT_SYMBOL_GPL(node_to_amd_nb);
static struct pci_dev *next_northbridge(struct pci_dev *dev,
const struct pci_device_id *ids)
@@ -58,13 +89,106 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev,
return dev;
}
+static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write)
+{
+ struct pci_dev *root;
+ int err = -ENODEV;
+
+ if (node >= amd_northbridges.num)
+ goto out;
+
+ root = node_to_amd_nb(node)->root;
+ if (!root)
+ goto out;
+
+ mutex_lock(&smn_mutex);
+
+ err = pci_write_config_dword(root, 0x60, address);
+ if (err) {
+ pr_warn("Error programming SMN address 0x%x.\n", address);
+ goto out_unlock;
+ }
+
+ err = (write ? pci_write_config_dword(root, 0x64, *value)
+ : pci_read_config_dword(root, 0x64, value));
+ if (err)
+ pr_warn("Error %s SMN address 0x%x.\n",
+ (write ? "writing to" : "reading from"), address);
+
+out_unlock:
+ mutex_unlock(&smn_mutex);
+
+out:
+ return err;
+}
+
+int amd_smn_read(u16 node, u32 address, u32 *value)
+{
+ return __amd_smn_rw(node, address, value, false);
+}
+EXPORT_SYMBOL_GPL(amd_smn_read);
+
+int amd_smn_write(u16 node, u32 address, u32 value)
+{
+ return __amd_smn_rw(node, address, &value, true);
+}
+EXPORT_SYMBOL_GPL(amd_smn_write);
+
+/*
+ * Data Fabric Indirect Access uses FICAA/FICAD.
+ *
+ * Fabric Indirect Configuration Access Address (FICAA): Constructed based
+ * on the device's Instance Id and the PCI function and register offset of
+ * the desired register.
+ *
+ * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO
+ * and FICAD HI registers but so far we only need the LO register.
+ */
+int amd_df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
+{
+ struct pci_dev *F4;
+ u32 ficaa;
+ int err = -ENODEV;
+
+ if (node >= amd_northbridges.num)
+ goto out;
+
+ F4 = node_to_amd_nb(node)->link;
+ if (!F4)
+ goto out;
+
+ ficaa = 1;
+ ficaa |= reg & 0x3FC;
+ ficaa |= (func & 0x7) << 11;
+ ficaa |= instance_id << 16;
+
+ mutex_lock(&smn_mutex);
+
+ err = pci_write_config_dword(F4, 0x5C, ficaa);
+ if (err) {
+ pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa);
+ goto out_unlock;
+ }
+
+ err = pci_read_config_dword(F4, 0x98, lo);
+ if (err)
+ pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa);
+
+out_unlock:
+ mutex_unlock(&smn_mutex);
+
+out:
+ return err;
+}
+EXPORT_SYMBOL_GPL(amd_df_indirect_read);
+
int amd_cache_northbridges(void)
{
u16 i = 0;
struct amd_northbridge *nb;
- struct pci_dev *misc, *link;
+ struct pci_dev *root, *misc, *link;
- if (amd_nb_num())
+ if (amd_northbridges.num)
return 0;
misc = NULL;
@@ -74,15 +198,17 @@ int amd_cache_northbridges(void)
if (!i)
return -ENODEV;
- nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
+ nb = kcalloc(i, sizeof(struct amd_northbridge), GFP_KERNEL);
if (!nb)
return -ENOMEM;
amd_northbridges.nb = nb;
amd_northbridges.num = i;
- link = misc = NULL;
- for (i = 0; i != amd_nb_num(); i++) {
+ link = misc = root = NULL;
+ for (i = 0; i != amd_northbridges.num; i++) {
+ node_to_amd_nb(i)->root = root =
+ next_northbridge(root, amd_root_ids);
node_to_amd_nb(i)->misc = misc =
next_northbridge(misc, amd_nb_misc_ids);
node_to_amd_nb(i)->link = link =
@@ -139,13 +265,13 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
{
u32 address;
u64 base, msr;
- unsigned segn_busn_bits;
+ unsigned int segn_busn_bits;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
return NULL;
/* assume all cpus from fam10h have mmconfig */
- if (boot_cpu_data.x86 < 0x10)
+ if (boot_cpu_data.x86 < 0x10)
return NULL;
address = MSR_FAM10H_MMIO_CONF_BASE;
@@ -226,14 +352,14 @@ static void amd_cache_gart(void)
if (!amd_nb_has_feature(AMD_NB_GART))
return;
- flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
+ flush_words = kmalloc_array(amd_northbridges.num, sizeof(u32), GFP_KERNEL);
if (!flush_words) {
amd_northbridges.flags &= ~AMD_NB_GART;
pr_notice("Cannot initialize GART flush words, GART support disabled\n");
return;
}
- for (i = 0; i != amd_nb_num(); i++)
+ for (i = 0; i != amd_northbridges.num; i++)
pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c, &flush_words[i]);
}
@@ -246,18 +372,20 @@ void amd_flush_garts(void)
if (!amd_nb_has_feature(AMD_NB_GART))
return;
- /* Avoid races between AGP and IOMMU. In theory it's not needed
- but I'm not sure if the hardware won't lose flush requests
- when another is pending. This whole thing is so expensive anyways
- that it doesn't matter to serialize more. -AK */
+ /*
+ * Avoid races between AGP and IOMMU. In theory it's not needed
+ * but I'm not sure if the hardware won't lose flush requests
+ * when another is pending. This whole thing is so expensive anyways
+ * that it doesn't matter to serialize more. -AK
+ */
spin_lock_irqsave(&gart_lock, flags);
flushed = 0;
- for (i = 0; i < amd_nb_num(); i++) {
+ for (i = 0; i < amd_northbridges.num; i++) {
pci_write_config_dword(node_to_amd_nb(i)->misc, 0x9c,
flush_words[i] | 1);
flushed++;
}
- for (i = 0; i < amd_nb_num(); i++) {
+ for (i = 0; i < amd_northbridges.num; i++) {
u32 w;
/* Make sure the hardware actually executed the flush*/
for (;;) {
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 88c657b057e2..2686894350a4 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2263,6 +2263,7 @@ void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v))
for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) {
/* Should happen once for each apic */
WARN_ON((*drv)->eoi_write == eoi_write);
+ (*drv)->native_eoi_write = (*drv)->eoi_write;
(*drv)->eoi_write = eoi_write;
}
}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index aeef53ce93e1..35690a168cf7 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -815,9 +815,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
l = li;
}
addr1 = (base << shift) +
- f * (unsigned long)(1 << m_io);
+ f * (1ULL << m_io);
addr2 = (base << shift) +
- (l + 1) * (unsigned long)(1 << m_io);
+ (l + 1) * (1ULL << m_io);
pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n",
id, fi, li, lnasid, addr1, addr2);
if (max_io < l)
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 51287cd90bf6..643818a7688b 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -906,14 +906,14 @@ static int apm_cpu_idle(struct cpuidle_device *dev,
static int use_apm_idle; /* = 0 */
static unsigned int last_jiffies; /* = 0 */
static unsigned int last_stime; /* = 0 */
- cputime_t stime;
+ cputime_t stime, utime;
int apm_idle_done = 0;
unsigned int jiffies_since_last_check = jiffies - last_jiffies;
unsigned int bucket;
recalc:
- task_cputime(current, NULL, &stime);
+ task_cputime(current, &utime, &stime);
if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
use_apm_idle = 0;
} else if (jiffies_since_last_check > idle_period) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index b81fe2d63e15..1e81a37c034e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -347,7 +347,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
- unsigned int socket_id, core_complex_id;
bits = c->x86_coreid_bits;
/* Low order bits define the core id (index of core in socket) */
@@ -365,10 +364,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
return;
- socket_id = (c->apicid >> bits) - 1;
- core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3;
-
- per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
#endif
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bd910a7dd0a..cc9e980c68ec 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -979,6 +979,35 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c)
}
/*
+ * The physical to logical package id mapping is initialized from the
+ * acpi/mptables information. Make sure that CPUID actually agrees with
+ * that.
+ */
+static void sanitize_package_id(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ unsigned int pkg, apicid, cpu = smp_processor_id();
+
+ apicid = apic->cpu_present_to_apicid(cpu);
+ pkg = apicid >> boot_cpu_data.x86_coreid_bits;
+
+ if (apicid != c->initial_apicid) {
+ pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n",
+ cpu, apicid, c->initial_apicid);
+ c->initial_apicid = apicid;
+ }
+ if (pkg != c->phys_proc_id) {
+ pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n",
+ cpu, pkg, c->phys_proc_id);
+ c->phys_proc_id = pkg;
+ }
+ c->logical_proc_id = topology_phys_to_logical_pkg(pkg);
+#else
+ c->logical_proc_id = 0;
+#endif
+}
+
+/*
* This does the hard work of actually picking apart the CPU stuff...
*/
static void identify_cpu(struct cpuinfo_x86 *c)
@@ -1103,8 +1132,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
#ifdef CONFIG_NUMA
numa_add_cpu(smp_processor_id());
#endif
- /* The boot/hotplug time assigment got cleared, restore it */
- c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id);
+ sanitize_package_id(c);
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 631356c8cca4..c7efbcfbeda6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -311,7 +311,7 @@ static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_e
*msg = s->msg;
s->covered = 1;
if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) {
- if (panic_on_oops || tolerant < 1)
+ if (tolerant < 1)
return MCE_PANIC_SEVERITY;
}
return s->sev;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a7fdf453d895..a3cb27af4f9b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -43,6 +43,7 @@
#include <linux/export.h>
#include <linux/jump_label.h>
+#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/traps.h>
#include <asm/tlbflush.h>
@@ -135,6 +136,9 @@ void mce_setup(struct mce *m)
m->socketid = cpu_data(m->extcpu).phys_proc_id;
m->apicid = cpu_data(m->extcpu).initial_apicid;
rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
+
+ if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
+ rdmsrl(MSR_PPIN, m->ppin);
}
DEFINE_PER_CPU(struct mce, injectm);
@@ -207,8 +211,12 @@ EXPORT_SYMBOL_GPL(mce_inject_log);
static struct notifier_block mce_srao_nb;
+static atomic_t num_notifiers;
+
void mce_register_decode_chain(struct notifier_block *nb)
{
+ atomic_inc(&num_notifiers);
+
/* Ensure SRAO notifier has the highest priority in the decode chain. */
if (nb != &mce_srao_nb && nb->priority == INT_MAX)
nb->priority -= 1;
@@ -219,6 +227,8 @@ EXPORT_SYMBOL_GPL(mce_register_decode_chain);
void mce_unregister_decode_chain(struct notifier_block *nb)
{
+ atomic_dec(&num_notifiers);
+
atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
@@ -270,17 +280,17 @@ struct mca_msr_regs msr_ops = {
.misc = misc_reg
};
-static void print_mce(struct mce *m)
+static void __print_mce(struct mce *m)
{
- int ret = 0;
-
- pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
- m->extcpu, m->mcgstatus, m->bank, m->status);
+ pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
+ m->extcpu,
+ (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""),
+ m->mcgstatus, m->bank, m->status);
if (m->ip) {
pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ",
!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
- m->cs, m->ip);
+ m->cs, m->ip);
if (m->cs == __KERNEL_CS)
print_symbol("{%s}", m->ip);
@@ -308,6 +318,13 @@ static void print_mce(struct mce *m)
pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
cpu_data(m->extcpu).microcode);
+}
+
+static void print_mce(struct mce *m)
+{
+ int ret = 0;
+
+ __print_mce(m);
/*
* Print out human-readable details about the MCE error,
@@ -569,6 +586,32 @@ static struct notifier_block mce_srao_nb = {
.priority = INT_MAX,
};
+static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct mce *m = (struct mce *)data;
+
+ if (!m)
+ return NOTIFY_DONE;
+
+ /*
+ * Run the default notifier if we have only the SRAO
+ * notifier and us registered.
+ */
+ if (atomic_read(&num_notifiers) > 2)
+ return NOTIFY_DONE;
+
+ __print_mce(m);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block mce_default_nb = {
+ .notifier_call = mce_default_notifier,
+ /* lowest prio, we want it to run last. */
+ .priority = 0,
+};
+
/*
* Read ADDR and MISC registers.
*/
@@ -667,6 +710,15 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
mce_gather_info(&m, NULL);
+ /*
+ * m.tsc was set in mce_setup(). Clear it if not requested.
+ *
+ * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid
+ * that dance.
+ */
+ if (!(flags & MCP_TIMESTAMP))
+ m.tsc = 0;
+
for (i = 0; i < mca_cfg.banks; i++) {
if (!mce_banks[i].ctl || !test_bit(i, *b))
continue;
@@ -674,14 +726,12 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
m.misc = 0;
m.addr = 0;
m.bank = i;
- m.tsc = 0;
barrier();
m.status = mce_rdmsrl(msr_ops.status(i));
if (!(m.status & MCI_STATUS_VAL))
continue;
-
/*
* Uncorrected or signalled events are handled by the exception
* handler when it is enabled, so don't process those here.
@@ -696,9 +746,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
mce_read_aux(&m, i);
- if (!(flags & MCP_TIMESTAMP))
- m.tsc = 0;
-
severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
@@ -1355,7 +1402,7 @@ static void mce_timer_fn(unsigned long data)
iv = __this_cpu_read(mce_next_interval);
if (mce_available(this_cpu_ptr(&cpu_info))) {
- machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_poll_banks));
+ machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
if (mce_intel_cmci_poll()) {
iv = mce_adjust_timer(iv);
@@ -2138,6 +2185,7 @@ int __init mcheck_init(void)
{
mcheck_intel_therm_init();
mce_register_decode_chain(&mce_srao_nb);
+ mce_register_decode_chain(&mce_default_nb);
mcheck_vendor_init_severity();
INIT_WORK(&mce_work, mce_process_work);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 9b5403462936..1a0b0a0e5e2b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -69,7 +69,12 @@ static const char * const smca_umc_block_names[] = {
"misc_umc"
};
-struct smca_bank_name smca_bank_names[] = {
+struct smca_bank_name {
+ const char *name; /* Short name for sysfs */
+ const char *long_name; /* Long name for pretty-printing */
+};
+
+static struct smca_bank_name smca_names[] = {
[SMCA_LS] = { "load_store", "Load Store Unit" },
[SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" },
[SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" },
@@ -84,9 +89,25 @@ struct smca_bank_name smca_bank_names[] = {
[SMCA_PSP] = { "psp", "Platform Security Processor" },
[SMCA_SMU] = { "smu", "System Management Unit" },
};
-EXPORT_SYMBOL_GPL(smca_bank_names);
-static struct smca_hwid_mcatype smca_hwid_mcatypes[] = {
+const char *smca_get_name(enum smca_bank_types t)
+{
+ if (t >= N_SMCA_BANK_TYPES)
+ return NULL;
+
+ return smca_names[t].name;
+}
+
+const char *smca_get_long_name(enum smca_bank_types t)
+{
+ if (t >= N_SMCA_BANK_TYPES)
+ return NULL;
+
+ return smca_names[t].long_name;
+}
+EXPORT_SYMBOL_GPL(smca_get_long_name);
+
+static struct smca_hwid smca_hwid_mcatypes[] = {
/* { bank_type, hwid_mcatype, xec_bitmap } */
/* ZN Core (HWID=0xB0) MCA types */
@@ -116,7 +137,7 @@ static struct smca_hwid_mcatype smca_hwid_mcatypes[] = {
{ SMCA_SMU, HWID_MCATYPE(0x01, 0x0), 0x1 },
};
-struct smca_bank_info smca_banks[MAX_NR_BANKS];
+struct smca_bank smca_banks[MAX_NR_BANKS];
EXPORT_SYMBOL_GPL(smca_banks);
/*
@@ -142,35 +163,34 @@ static void default_deferred_error_interrupt(void)
}
void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
-/*
- * CPU Initialization
- */
-
static void get_smca_bank_info(unsigned int bank)
{
unsigned int i, hwid_mcatype, cpu = smp_processor_id();
- struct smca_hwid_mcatype *type;
- u32 high, instanceId;
- u16 hwid, mcatype;
+ struct smca_hwid *s_hwid;
+ u32 high, instance_id;
/* Collect bank_info using CPU 0 for now. */
if (cpu)
return;
- if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instanceId, &high)) {
+ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instance_id, &high)) {
pr_warn("Failed to read MCA_IPID for bank %d\n", bank);
return;
}
- hwid = high & MCI_IPID_HWID;
- mcatype = (high & MCI_IPID_MCATYPE) >> 16;
- hwid_mcatype = HWID_MCATYPE(hwid, mcatype);
+ hwid_mcatype = HWID_MCATYPE(high & MCI_IPID_HWID,
+ (high & MCI_IPID_MCATYPE) >> 16);
for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) {
- type = &smca_hwid_mcatypes[i];
- if (hwid_mcatype == type->hwid_mcatype) {
- smca_banks[bank].type = type;
- smca_banks[bank].type_instance = instanceId;
+ s_hwid = &smca_hwid_mcatypes[i];
+ if (hwid_mcatype == s_hwid->hwid_mcatype) {
+
+ WARN(smca_banks[bank].hwid,
+ "Bank %s already initialized!\n",
+ smca_get_name(s_hwid->bank_type));
+
+ smca_banks[bank].hwid = s_hwid;
+ smca_banks[bank].id = instance_id;
break;
}
}
@@ -533,6 +553,206 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
deferred_error_interrupt_enable(c);
}
+int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
+{
+ u64 dram_base_addr, dram_limit_addr, dram_hole_base;
+ /* We start from the normalized address */
+ u64 ret_addr = norm_addr;
+
+ u32 tmp;
+
+ u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask;
+ u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets;
+ u8 intlv_addr_sel, intlv_addr_bit;
+ u8 num_intlv_bits, hashed_bit;
+ u8 lgcy_mmio_hole_en, base = 0;
+ u8 cs_mask, cs_id = 0;
+ bool hash_enabled = false;
+
+ /* Read D18F0x1B4 (DramOffset), check if base 1 is used. */
+ if (amd_df_indirect_read(nid, 0, 0x1B4, umc, &tmp))
+ goto out_err;
+
+ /* Remove HiAddrOffset from normalized address, if enabled: */
+ if (tmp & BIT(0)) {
+ u64 hi_addr_offset = (tmp & GENMASK_ULL(31, 20)) << 8;
+
+ if (norm_addr >= hi_addr_offset) {
+ ret_addr -= hi_addr_offset;
+ base = 1;
+ }
+ }
+
+ /* Read D18F0x110 (DramBaseAddress). */
+ if (amd_df_indirect_read(nid, 0, 0x110 + (8 * base), umc, &tmp))
+ goto out_err;
+
+ /* Check if address range is valid. */
+ if (!(tmp & BIT(0))) {
+ pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n",
+ __func__, tmp);
+ goto out_err;
+ }
+
+ lgcy_mmio_hole_en = tmp & BIT(1);
+ intlv_num_chan = (tmp >> 4) & 0xF;
+ intlv_addr_sel = (tmp >> 8) & 0x7;
+ dram_base_addr = (tmp & GENMASK_ULL(31, 12)) << 16;
+
+ /* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */
+ if (intlv_addr_sel > 3) {
+ pr_err("%s: Invalid interleave address select %d.\n",
+ __func__, intlv_addr_sel);
+ goto out_err;
+ }
+
+ /* Read D18F0x114 (DramLimitAddress). */
+ if (amd_df_indirect_read(nid, 0, 0x114 + (8 * base), umc, &tmp))
+ goto out_err;
+
+ intlv_num_sockets = (tmp >> 8) & 0x1;
+ intlv_num_dies = (tmp >> 10) & 0x3;
+ dram_limit_addr = ((tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0);
+
+ intlv_addr_bit = intlv_addr_sel + 8;
+
+ /* Re-use intlv_num_chan by setting it equal to log2(#channels) */
+ switch (intlv_num_chan) {
+ case 0: intlv_num_chan = 0; break;
+ case 1: intlv_num_chan = 1; break;
+ case 3: intlv_num_chan = 2; break;
+ case 5: intlv_num_chan = 3; break;
+ case 7: intlv_num_chan = 4; break;
+
+ case 8: intlv_num_chan = 1;
+ hash_enabled = true;
+ break;
+ default:
+ pr_err("%s: Invalid number of interleaved channels %d.\n",
+ __func__, intlv_num_chan);
+ goto out_err;
+ }
+
+ num_intlv_bits = intlv_num_chan;
+
+ if (intlv_num_dies > 2) {
+ pr_err("%s: Invalid number of interleaved nodes/dies %d.\n",
+ __func__, intlv_num_dies);
+ goto out_err;
+ }
+
+ num_intlv_bits += intlv_num_dies;
+
+ /* Add a bit if sockets are interleaved. */
+ num_intlv_bits += intlv_num_sockets;
+
+ /* Assert num_intlv_bits <= 4 */
+ if (num_intlv_bits > 4) {
+ pr_err("%s: Invalid interleave bits %d.\n",
+ __func__, num_intlv_bits);
+ goto out_err;
+ }
+
+ if (num_intlv_bits > 0) {
+ u64 temp_addr_x, temp_addr_i, temp_addr_y;
+ u8 die_id_bit, sock_id_bit, cs_fabric_id;
+
+ /*
+ * Read FabricBlockInstanceInformation3_CS[BlockFabricID].
+ * This is the fabric id for this coherent slave. Use
+ * umc/channel# as instance id of the coherent slave
+ * for FICAA.
+ */
+ if (amd_df_indirect_read(nid, 0, 0x50, umc, &tmp))
+ goto out_err;
+
+ cs_fabric_id = (tmp >> 8) & 0xFF;
+ die_id_bit = 0;
+
+ /* If interleaved over more than 1 channel: */
+ if (intlv_num_chan) {
+ die_id_bit = intlv_num_chan;
+ cs_mask = (1 << die_id_bit) - 1;
+ cs_id = cs_fabric_id & cs_mask;
+ }
+
+ sock_id_bit = die_id_bit;
+
+ /* Read D18F1x208 (SystemFabricIdMask). */
+ if (intlv_num_dies || intlv_num_sockets)
+ if (amd_df_indirect_read(nid, 1, 0x208, umc, &tmp))
+ goto out_err;
+
+ /* If interleaved over more than 1 die. */
+ if (intlv_num_dies) {
+ sock_id_bit = die_id_bit + intlv_num_dies;
+ die_id_shift = (tmp >> 24) & 0xF;
+ die_id_mask = (tmp >> 8) & 0xFF;
+
+ cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit;
+ }
+
+ /* If interleaved over more than 1 socket. */
+ if (intlv_num_sockets) {
+ socket_id_shift = (tmp >> 28) & 0xF;
+ socket_id_mask = (tmp >> 16) & 0xFF;
+
+ cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit;
+ }
+
+ /*
+ * The pre-interleaved address consists of XXXXXXIIIYYYYY
+ * where III is the ID for this CS, and XXXXXXYYYYY are the
+ * address bits from the post-interleaved address.
+ * "num_intlv_bits" has been calculated to tell us how many "I"
+ * bits there are. "intlv_addr_bit" tells us how many "Y" bits
+ * there are (where "I" starts).
+ */
+ temp_addr_y = ret_addr & GENMASK_ULL(intlv_addr_bit-1, 0);
+ temp_addr_i = (cs_id << intlv_addr_bit);
+ temp_addr_x = (ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits;
+ ret_addr = temp_addr_x | temp_addr_i | temp_addr_y;
+ }
+
+ /* Add dram base address */
+ ret_addr += dram_base_addr;
+
+ /* If legacy MMIO hole enabled */
+ if (lgcy_mmio_hole_en) {
+ if (amd_df_indirect_read(nid, 0, 0x104, umc, &tmp))
+ goto out_err;
+
+ dram_hole_base = tmp & GENMASK(31, 24);
+ if (ret_addr >= dram_hole_base)
+ ret_addr += (BIT_ULL(32) - dram_hole_base);
+ }
+
+ if (hash_enabled) {
+ /* Save some parentheses and grab ls-bit at the end. */
+ hashed_bit = (ret_addr >> 12) ^
+ (ret_addr >> 18) ^
+ (ret_addr >> 21) ^
+ (ret_addr >> 30) ^
+ cs_id;
+
+ hashed_bit &= BIT(0);
+
+ if (hashed_bit != ((ret_addr >> intlv_addr_bit) & BIT(0)))
+ ret_addr ^= BIT(intlv_addr_bit);
+ }
+
+ /* Is calculated system address is above DRAM limit address? */
+ if (ret_addr > dram_limit_addr)
+ goto out_err;
+
+ *sys_addr = ret_addr;
+ return 0;
+
+out_err:
+ return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr);
+
static void
__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
{
@@ -645,6 +865,7 @@ static void amd_threshold_interrupt(void)
{
u32 low = 0, high = 0, address = 0;
unsigned int bank, block, cpu = smp_processor_id();
+ struct thresh_restart tr;
/* assume first bank caused it */
for (bank = 0; bank < mca_cfg.banks; ++bank) {
@@ -681,6 +902,11 @@ static void amd_threshold_interrupt(void)
log:
__log_error(bank, false, true, ((u64)high << 32) | low);
+
+ /* Reset threshold block after logging error. */
+ memset(&tr, 0, sizeof(tr));
+ tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block];
+ threshold_restart_bank(&tr);
}
/*
@@ -826,10 +1052,10 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
return th_names[bank];
}
- if (!smca_banks[bank].type)
+ if (!smca_banks[bank].hwid)
return NULL;
- bank_type = smca_banks[bank].type->bank_type;
+ bank_type = smca_banks[bank].hwid->bank_type;
if (b && bank_type == SMCA_UMC) {
if (b->block < ARRAY_SIZE(smca_umc_block_names))
@@ -838,8 +1064,8 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
}
snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
- "%s_%x", smca_bank_names[bank_type].name,
- smca_banks[bank].type_instance);
+ "%s_%x", smca_get_name(bank_type),
+ smca_banks[bank].id);
return buf_mcatype;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 1defb8ea882c..190b3e6cef4d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -11,6 +11,8 @@
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <asm/apic.h>
+#include <asm/cpufeature.h>
+#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/mce.h>
@@ -130,7 +132,7 @@ bool mce_intel_cmci_poll(void)
* Reset the counter if we've logged an error in the last poll
* during the storm.
*/
- if (machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)))
+ if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned)))
this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL);
else
this_cpu_dec(cmci_backoff_cnt);
@@ -342,7 +344,7 @@ void cmci_recheck(void)
return;
local_irq_save(flags);
- machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
+ machine_check_poll(0, this_cpu_ptr(&mce_banks_owned));
local_irq_restore(flags);
}
@@ -464,11 +466,46 @@ static void intel_clear_lmce(void)
wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
}
+static void intel_ppin_init(struct cpuinfo_x86 *c)
+{
+ unsigned long long val;
+
+ /*
+ * Even if testing the presence of the MSR would be enough, we don't
+ * want to risk the situation where other models reuse this MSR for
+ * other purposes.
+ */
+ switch (c->x86_model) {
+ case INTEL_FAM6_IVYBRIDGE_X:
+ case INTEL_FAM6_HASWELL_X:
+ case INTEL_FAM6_BROADWELL_XEON_D:
+ case INTEL_FAM6_BROADWELL_X:
+ case INTEL_FAM6_SKYLAKE_X:
+ if (rdmsrl_safe(MSR_PPIN_CTL, &val))
+ return;
+
+ if ((val & 3UL) == 1UL) {
+ /* PPIN available but disabled: */
+ return;
+ }
+
+ /* If PPIN is disabled, but not locked, try to enable: */
+ if (!(val & 3UL)) {
+ wrmsrl_safe(MSR_PPIN_CTL, val | 2UL);
+ rdmsrl_safe(MSR_PPIN_CTL, &val);
+ }
+
+ if ((val & 3UL) == 2UL)
+ set_cpu_cap(c, X86_FEATURE_INTEL_PPIN);
+ }
+}
+
void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
intel_init_thermal(c);
intel_init_cmci();
intel_init_lmce();
+ intel_ppin_init(c);
}
void mce_intel_feature_clear(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 0e5c9d0f6c28..0cfd01d2754c 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -105,7 +105,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
for (; stack < stack_info.end; stack++) {
unsigned long real_addr;
int reliable = 0;
- unsigned long addr = *stack;
+ unsigned long addr = READ_ONCE_NOCHECK(*stack);
unsigned long *ret_addr_p =
unwind_get_return_address_ptr(&state);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 47004010ad5d..ebb4e95fbd74 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -521,14 +521,14 @@ void fpu__clear(struct fpu *fpu)
{
WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
- if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
- /* FPU state will be reallocated lazily at the first use. */
- fpu__drop(fpu);
- } else {
- if (!fpu->fpstate_active) {
- fpu__activate_curr(fpu);
- user_fpu_begin();
- }
+ fpu__drop(fpu);
+
+ /*
+ * Make sure fpstate is cleared and initialized.
+ */
+ if (static_cpu_has(X86_FEATURE_FPU)) {
+ fpu__activate_curr(fpu);
+ user_fpu_begin();
copy_init_fpstate_to_fpregs();
}
}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index df541ac2071e..4e8577d03372 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -669,14 +669,17 @@ __PAGE_ALIGNED_BSS
initial_pg_pmd:
.fill 1024*KPMDS,4,0
#else
-ENTRY(initial_page_table)
+.globl initial_page_table
+initial_page_table:
.fill 1024,4,0
#endif
initial_pg_fixmap:
.fill 1024,4,0
-ENTRY(empty_zero_page)
+.globl empty_zero_page
+empty_zero_page:
.fill 4096,1,0
-ENTRY(swapper_pg_dir)
+.globl swapper_pg_dir
+swapper_pg_dir:
.fill 1024,4,0
EXPORT_SYMBOL(empty_zero_page)
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
new file mode 100644
index 000000000000..cb9c1ed1d391
--- /dev/null
+++ b/arch/x86/kernel/itmt.c
@@ -0,0 +1,215 @@
+/*
+ * itmt.c: Support Intel Turbo Boost Max Technology 3.0
+ *
+ * (C) Copyright 2016 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * On platforms supporting Intel Turbo Boost Max Technology 3.0, (ITMT),
+ * the maximum turbo frequencies of some cores in a CPU package may be
+ * higher than for the other cores in the same package. In that case,
+ * better performance can be achieved by making the scheduler prefer
+ * to run tasks on the CPUs with higher max turbo frequencies.
+ *
+ * This file provides functions and data structures for enabling the
+ * scheduler to favor scheduling on cores can be boosted to a higher
+ * frequency under ITMT.
+ */
+
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/cpuset.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/sysctl.h>
+#include <linux/nodemask.h>
+
+static DEFINE_MUTEX(itmt_update_mutex);
+DEFINE_PER_CPU_READ_MOSTLY(int, sched_core_priority);
+
+/* Boolean to track if system has ITMT capabilities */
+static bool __read_mostly sched_itmt_capable;
+
+/*
+ * Boolean to control whether we want to move processes to cpu capable
+ * of higher turbo frequency for cpus supporting Intel Turbo Boost Max
+ * Technology 3.0.
+ *
+ * It can be set via /proc/sys/kernel/sched_itmt_enabled
+ */
+unsigned int __read_mostly sysctl_sched_itmt_enabled;
+
+static int sched_itmt_update_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ unsigned int old_sysctl;
+ int ret;
+
+ mutex_lock(&itmt_update_mutex);
+
+ if (!sched_itmt_capable) {
+ mutex_unlock(&itmt_update_mutex);
+ return -EINVAL;
+ }
+
+ old_sysctl = sysctl_sched_itmt_enabled;
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+ if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) {
+ x86_topology_update = true;
+ rebuild_sched_domains();
+ }
+
+ mutex_unlock(&itmt_update_mutex);
+
+ return ret;
+}
+
+static unsigned int zero;
+static unsigned int one = 1;
+static struct ctl_table itmt_kern_table[] = {
+ {
+ .procname = "sched_itmt_enabled",
+ .data = &sysctl_sched_itmt_enabled,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sched_itmt_update_handler,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {}
+};
+
+static struct ctl_table itmt_root_table[] = {
+ {
+ .procname = "kernel",
+ .mode = 0555,
+ .child = itmt_kern_table,
+ },
+ {}
+};
+
+static struct ctl_table_header *itmt_sysctl_header;
+
+/**
+ * sched_set_itmt_support() - Indicate platform supports ITMT
+ *
+ * This function is used by the OS to indicate to scheduler that the platform
+ * is capable of supporting the ITMT feature.
+ *
+ * The current scheme has the pstate driver detects if the system
+ * is ITMT capable and call sched_set_itmt_support.
+ *
+ * This must be done only after sched_set_itmt_core_prio
+ * has been called to set the cpus' priorities.
+ * It must not be called with cpu hot plug lock
+ * held as we need to acquire the lock to rebuild sched domains
+ * later.
+ *
+ * Return: 0 on success
+ */
+int sched_set_itmt_support(void)
+{
+ mutex_lock(&itmt_update_mutex);
+
+ if (sched_itmt_capable) {
+ mutex_unlock(&itmt_update_mutex);
+ return 0;
+ }
+
+ itmt_sysctl_header = register_sysctl_table(itmt_root_table);
+ if (!itmt_sysctl_header) {
+ mutex_unlock(&itmt_update_mutex);
+ return -ENOMEM;
+ }
+
+ sched_itmt_capable = true;
+
+ sysctl_sched_itmt_enabled = 1;
+
+ if (sysctl_sched_itmt_enabled) {
+ x86_topology_update = true;
+ rebuild_sched_domains();
+ }
+
+ mutex_unlock(&itmt_update_mutex);
+
+ return 0;
+}
+
+/**
+ * sched_clear_itmt_support() - Revoke platform's support of ITMT
+ *
+ * This function is used by the OS to indicate that it has
+ * revoked the platform's support of ITMT feature.
+ *
+ * It must not be called with cpu hot plug lock
+ * held as we need to acquire the lock to rebuild sched domains
+ * later.
+ */
+void sched_clear_itmt_support(void)
+{
+ mutex_lock(&itmt_update_mutex);
+
+ if (!sched_itmt_capable) {
+ mutex_unlock(&itmt_update_mutex);
+ return;
+ }
+ sched_itmt_capable = false;
+
+ if (itmt_sysctl_header) {
+ unregister_sysctl_table(itmt_sysctl_header);
+ itmt_sysctl_header = NULL;
+ }
+
+ if (sysctl_sched_itmt_enabled) {
+ /* disable sched_itmt if we are no longer ITMT capable */
+ sysctl_sched_itmt_enabled = 0;
+ x86_topology_update = true;
+ rebuild_sched_domains();
+ }
+
+ mutex_unlock(&itmt_update_mutex);
+}
+
+int arch_asym_cpu_priority(int cpu)
+{
+ return per_cpu(sched_core_priority, cpu);
+}
+
+/**
+ * sched_set_itmt_core_prio() - Set CPU priority based on ITMT
+ * @prio: Priority of cpu core
+ * @core_cpu: The cpu number associated with the core
+ *
+ * The pstate driver will find out the max boost frequency
+ * and call this function to set a priority proportional
+ * to the max boost frequency. CPU with higher boost
+ * frequency will receive higher priority.
+ *
+ * No need to rebuild sched domain after updating
+ * the CPU priorities. The sched domains have no
+ * dependency on CPU priorities.
+ */
+void sched_set_itmt_core_prio(int prio, int core_cpu)
+{
+ int cpu, i = 1;
+
+ for_each_cpu(cpu, topology_sibling_cpumask(core_cpu)) {
+ int smt_prio;
+
+ /*
+ * Ensure that the siblings are moved to the end
+ * of the priority chain and only used when
+ * all other high priority cpus are out of capacity.
+ */
+ smt_prio = prio * smp_num_siblings / i;
+ per_cpu(sched_core_priority, cpu) = smt_prio;
+ i++;
+ }
+}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index edbbfc854e39..fb5afc6356b2 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -308,7 +308,7 @@ static void kvm_register_steal_time(void)
static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED;
-static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
+static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val)
{
/**
* This relies on __test_and_clear_bit to modify the memory
@@ -319,7 +319,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
*/
if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi)))
return;
- apic_write(APIC_EOI, APIC_EOI_ACK);
+ apic->native_eoi_write(APIC_EOI, APIC_EOI_ACK);
}
static void kvm_guest_cpu_init(void)
@@ -592,6 +592,14 @@ out:
local_irq_restore(flags);
}
+__visible bool __kvm_vcpu_is_preempted(int cpu)
+{
+ struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+ return !!src->preempted;
+}
+PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
@@ -608,6 +616,11 @@ void __init kvm_spinlock_init(void)
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = kvm_wait;
pv_lock_ops.kick = kvm_kick_cpu;
+
+ if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ pv_lock_ops.vcpu_is_preempted =
+ PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
+ }
}
static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 2c55a003b793..6d4bf812af45 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -12,7 +12,6 @@ __visible void __native_queued_spin_unlock(struct qspinlock *lock)
{
native_queued_spin_unlock(lock);
}
-
PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
bool pv_is_native_spin_unlock(void)
@@ -21,12 +20,25 @@ bool pv_is_native_spin_unlock(void)
__raw_callee_save___native_queued_spin_unlock;
}
+__visible bool __native_vcpu_is_preempted(int cpu)
+{
+ return false;
+}
+PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted);
+
+bool pv_is_native_vcpu_is_preempted(void)
+{
+ return pv_lock_ops.vcpu_is_preempted.func ==
+ __raw_callee_save___native_vcpu_is_preempted;
+}
+
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
.wait = paravirt_nop,
.kick = paravirt_nop,
+ .vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted),
#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 920c6ae08592..33cdec221f3d 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,7 @@ DEF_NATIVE(pv_cpu_ops, clts, "clts");
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -27,6 +28,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
}
extern bool pv_is_native_spin_unlock(void);
+extern bool pv_is_native_vcpu_is_preempted(void);
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
@@ -56,9 +58,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
end = end_pv_lock_ops_queued_spin_unlock;
goto patch_site;
}
+ goto patch_default;
+
+ case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+ if (pv_is_native_vcpu_is_preempted()) {
+ start = start_pv_lock_ops_vcpu_is_preempted;
+ end = end_pv_lock_ops_vcpu_is_preempted;
+ goto patch_site;
+ }
+ goto patch_default;
#endif
default:
+patch_default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index bb3840cedb4f..b0fceff502b3 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -36,6 +37,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
}
extern bool pv_is_native_spin_unlock(void);
+extern bool pv_is_native_vcpu_is_preempted(void);
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
@@ -68,9 +70,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
end = end_pv_lock_ops_queued_spin_unlock;
goto patch_site;
}
+ goto patch_default;
+
+ case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+ if (pv_is_native_vcpu_is_preempted()) {
+ start = start_pv_lock_ops_vcpu_is_preempted;
+ end = end_pv_lock_ops_vcpu_is_preempted;
+ goto patch_site;
+ }
+ goto patch_default;
#endif
default:
+patch_default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index c00cb64bc0a1..68f8cc222f25 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -261,10 +261,8 @@ static inline void __smp_reschedule_interrupt(void)
__visible void smp_reschedule_interrupt(struct pt_regs *regs)
{
- irq_enter();
ack_APIC_irq();
__smp_reschedule_interrupt();
- irq_exit();
/*
* KVM uses this interrupt to force a cpu out of guest mode
*/
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 95d6fc549ad5..8add3a5b8635 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -109,6 +109,17 @@ static bool logical_packages_frozen __read_mostly;
/* Maximum number of SMT threads on any online core */
int __max_smt_threads __read_mostly;
+/* Flag to indicate if a complete sched domain rebuild is required */
+bool x86_topology_update;
+
+int arch_update_cpu_topology(void)
+{
+ int retval = x86_topology_update;
+
+ x86_topology_update = false;
+ return retval;
+}
+
static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
{
unsigned long flags;
@@ -471,22 +482,42 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
return false;
}
+#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
+static inline int x86_sched_itmt_flags(void)
+{
+ return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
+}
+
+#ifdef CONFIG_SCHED_MC
+static int x86_core_flags(void)
+{
+ return cpu_core_flags() | x86_sched_itmt_flags();
+}
+#endif
+#ifdef CONFIG_SCHED_SMT
+static int x86_smt_flags(void)
+{
+ return cpu_smt_flags() | x86_sched_itmt_flags();
+}
+#endif
+#endif
+
static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+ { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
#endif
#ifdef CONFIG_SCHED_MC
- { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+ { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
#endif
{ NULL, },
};
static struct sched_domain_topology_level x86_topology[] = {
#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+ { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
#endif
#ifdef CONFIG_SCHED_MC
- { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+ { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
#endif
{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
{ NULL, },
@@ -821,14 +852,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
return (send_status | accept_status);
}
-void smp_announce(void)
-{
- int num_nodes = num_online_nodes();
-
- printk(KERN_INFO "x86: Booted up %d node%s, %d CPUs\n",
- num_nodes, (num_nodes > 1 ? "s" : ""), num_online_cpus());
-}
-
/* reduce the number of lines printed when booting a large cpu count system */
static void announce_cpu(int cpu, int apicid)
{
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
index 764a29f84de7..85195d447a92 100644
--- a/arch/x86/kernel/sysfb_simplefb.c
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -66,13 +66,36 @@ __init int create_simplefb(const struct screen_info *si,
{
struct platform_device *pd;
struct resource res;
- unsigned long len;
+ u64 base, size;
+ u32 length;
- /* don't use lfb_size as it may contain the whole VMEM instead of only
- * the part that is occupied by the framebuffer */
- len = mode->height * mode->stride;
- len = PAGE_ALIGN(len);
- if (len > (u64)si->lfb_size << 16) {
+ /*
+ * If the 64BIT_BASE capability is set, ext_lfb_base will contain the
+ * upper half of the base address. Assemble the address, then make sure
+ * it is valid and we can actually access it.
+ */
+ base = si->lfb_base;
+ if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+ base |= (u64)si->ext_lfb_base << 32;
+ if (!base || (u64)(resource_size_t)base != base) {
+ printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Don't use lfb_size as IORESOURCE size, since it may contain the
+ * entire VMEM, and thus require huge mappings. Use just the part we
+ * need, that is, the part where the framebuffer is located. But verify
+ * that it does not exceed the advertised VMEM.
+ * Note that in case of VBE, the lfb_size is shifted by 16 bits for
+ * historical reasons.
+ */
+ size = si->lfb_size;
+ if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
+ size <<= 16;
+ length = mode->height * mode->stride;
+ length = PAGE_ALIGN(length);
+ if (length > size) {
printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
return -EINVAL;
}
@@ -81,8 +104,8 @@ __init int create_simplefb(const struct screen_info *si,
memset(&res, 0, sizeof(res));
res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
res.name = simplefb_resname;
- res.start = si->lfb_base;
- res.end = si->lfb_base + len - 1;
+ res.start = base;
+ res.end = res.start + length - 1;
if (res.end <= res.start)
return -EINVAL;
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 2d721e533cf4..22881ddcbb9f 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -7,11 +7,15 @@
unsigned long unwind_get_return_address(struct unwind_state *state)
{
+ unsigned long addr;
+
if (unwind_done(state))
return 0;
+ addr = READ_ONCE_NOCHECK(*state->sp);
+
return ftrace_graph_ret_addr(state->task, &state->graph_idx,
- *state->sp, state->sp);
+ addr, state->sp);
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
@@ -23,9 +27,12 @@ bool unwind_next_frame(struct unwind_state *state)
return false;
do {
- for (state->sp++; state->sp < info->end; state->sp++)
- if (__kernel_text_address(*state->sp))
+ for (state->sp++; state->sp < info->end; state->sp++) {
+ unsigned long addr = READ_ONCE_NOCHECK(*state->sp);
+
+ if (__kernel_text_address(addr))
return true;
+ }
state->sp = info->next_sp;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index cbd7b92585bb..a3ce9d260d68 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2105,16 +2105,10 @@ static int em_iret(struct x86_emulate_ctxt *ctxt)
static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
- unsigned short sel, old_sel;
- struct desc_struct old_desc, new_desc;
- const struct x86_emulate_ops *ops = ctxt->ops;
+ unsigned short sel;
+ struct desc_struct new_desc;
u8 cpl = ctxt->ops->cpl(ctxt);
- /* Assignment of RIP may only fail in 64-bit mode */
- if (ctxt->mode == X86EMUL_MODE_PROT64)
- ops->get_segment(ctxt, &old_sel, &old_desc, NULL,
- VCPU_SREG_CS);
-
memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl,
@@ -2124,12 +2118,10 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
return rc;
rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
- if (rc != X86EMUL_CONTINUE) {
- WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
- /* assigning eip failed; restore the old cs */
- ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS);
- return rc;
- }
+ /* Error handling is not implemented. */
+ if (rc != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
return rc;
}
@@ -2189,14 +2181,8 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned long eip, cs;
- u16 old_cs;
int cpl = ctxt->ops->cpl(ctxt);
- struct desc_struct old_desc, new_desc;
- const struct x86_emulate_ops *ops = ctxt->ops;
-
- if (ctxt->mode == X86EMUL_MODE_PROT64)
- ops->get_segment(ctxt, &old_cs, &old_desc, NULL,
- VCPU_SREG_CS);
+ struct desc_struct new_desc;
rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
@@ -2213,10 +2199,10 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
rc = assign_eip_far(ctxt, eip, &new_desc);
- if (rc != X86EMUL_CONTINUE) {
- WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
- ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
- }
+ /* Error handling is not implemented. */
+ if (rc != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
return rc;
}
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 1a22de70f7f7..6e219e5c07d2 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -94,7 +94,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
{
ioapic->rtc_status.pending_eoi = 0;
- bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPUS);
+ bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
}
static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 7d2692a49657..1cc6e54436db 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -42,13 +42,13 @@ struct kvm_vcpu;
struct dest_map {
/* vcpu bitmap where IRQ has been sent */
- DECLARE_BITMAP(map, KVM_MAX_VCPUS);
+ DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
/*
* Vector sent to a given vcpu, only valid when
* the vcpu's bit in map is set
*/
- u8 vectors[KVM_MAX_VCPUS];
+ u8 vectors[KVM_MAX_VCPU_ID];
};
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 25810b144b58..6c0191615f23 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -41,6 +41,15 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
bool line_status)
{
struct kvm_pic *pic = pic_irqchip(kvm);
+
+ /*
+ * XXX: rejecting pic routes when pic isn't in use would be better,
+ * but the default routing table is installed while kvm->arch.vpic is
+ * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE.
+ */
+ if (!pic)
+ return -1;
+
return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
}
@@ -49,6 +58,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
bool line_status)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+ if (!ioapic)
+ return -1;
+
return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
line_status);
}
@@ -156,6 +169,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
}
+static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ if (!level)
+ return -1;
+
+ return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
+}
+
int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
bool line_status)
@@ -163,18 +186,26 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
struct kvm_lapic_irq irq;
int r;
- if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
- return -EWOULDBLOCK;
+ switch (e->type) {
+ case KVM_IRQ_ROUTING_HV_SINT:
+ return kvm_hv_set_sint(e, kvm, irq_source_id, level,
+ line_status);
- if (kvm_msi_route_invalid(kvm, e))
- return -EINVAL;
+ case KVM_IRQ_ROUTING_MSI:
+ if (kvm_msi_route_invalid(kvm, e))
+ return -EINVAL;
- kvm_set_msi_irq(kvm, e, &irq);
+ kvm_set_msi_irq(kvm, e, &irq);
- if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
- return r;
- else
- return -EWOULDBLOCK;
+ if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+ return r;
+ break;
+
+ default:
+ break;
+ }
+
+ return -EWOULDBLOCK;
}
int kvm_request_irq_source_id(struct kvm *kvm)
@@ -254,16 +285,6 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
srcu_read_unlock(&kvm->irq_srcu, idx);
}
-static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- if (!level)
- return -1;
-
- return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
-}
-
int kvm_set_routing_entry(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
@@ -423,18 +444,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
srcu_read_unlock(&kvm->irq_srcu, idx);
}
-int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm,
- int irq_source_id, int level, bool line_status)
-{
- switch (irq->type) {
- case KVM_IRQ_ROUTING_HV_SINT:
- return kvm_hv_set_sint(irq, kvm, irq_source_id, level,
- line_status);
- default:
- return -EWOULDBLOCK;
- }
-}
-
void kvm_arch_irq_routing_update(struct kvm *kvm)
{
kvm_hv_irq_routing_update(kvm);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 23b99f305382..6f69340f9fa3 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -138,7 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
*mask = dest_id & 0xff;
return true;
case KVM_APIC_MODE_XAPIC_CLUSTER:
- *cluster = map->xapic_cluster_map[dest_id >> 4];
+ *cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf];
*mask = dest_id & 0xf;
return true;
default:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3017de0431bd..59c2d6f1b131 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -210,7 +210,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
struct kvm_shared_msrs *locals
= container_of(urn, struct kvm_shared_msrs, urn);
struct kvm_shared_msr_values *values;
+ unsigned long flags;
+ /*
+ * Disabling irqs at this point since the following code could be
+ * interrupted and executed through kvm_arch_hardware_disable()
+ */
+ local_irq_save(flags);
+ if (locals->registered) {
+ locals->registered = false;
+ user_return_notifier_unregister(urn);
+ }
+ local_irq_restore(flags);
for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
values = &locals->values[slot];
if (values->host != values->curr) {
@@ -218,8 +229,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
values->curr = values->host;
}
}
- locals->registered = false;
- user_return_notifier_unregister(urn);
}
static void shared_msr_update(unsigned slot, u32 msr)
@@ -1724,18 +1733,23 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
static u64 __get_kvmclock_ns(struct kvm *kvm)
{
- struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
struct kvm_arch *ka = &kvm->arch;
- s64 ns;
+ struct pvclock_vcpu_time_info hv_clock;
- if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
- u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
- ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
- } else {
- ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+ spin_lock(&ka->pvclock_gtod_sync_lock);
+ if (!ka->use_master_clock) {
+ spin_unlock(&ka->pvclock_gtod_sync_lock);
+ return ktime_get_boot_ns() + ka->kvmclock_offset;
}
- return ns;
+ hv_clock.tsc_timestamp = ka->master_cycle_now;
+ hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
+ spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+ kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+ &hv_clock.tsc_shift,
+ &hv_clock.tsc_to_system_mul);
+ return __pvclock_read_cycles(&hv_clock, rdtsc());
}
u64 get_kvmclock_ns(struct kvm *kvm)
@@ -2057,6 +2071,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
+ vcpu->arch.st.steal.preempted = 0;
+
if (vcpu->arch.st.steal.version & 1)
vcpu->arch.st.steal.version += 1; /* first time write, random junk */
@@ -2596,7 +2612,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_PIT_STATE2:
case KVM_CAP_SET_IDENTITY_MAP_ADDR:
case KVM_CAP_XEN_HVM:
- case KVM_CAP_ADJUST_CLOCK:
case KVM_CAP_VCPU_EVENTS:
case KVM_CAP_HYPERV:
case KVM_CAP_HYPERV_VAPIC:
@@ -2623,6 +2638,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
#endif
r = 1;
break;
+ case KVM_CAP_ADJUST_CLOCK:
+ r = KVM_CLOCK_TSC_STABLE;
+ break;
case KVM_CAP_X86_SMM:
/* SMBASE is usually relocated above 1M on modern chipsets,
* and SMM handlers might indeed rely on 4G segment limits,
@@ -2810,8 +2828,22 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
}
+static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
+ return;
+
+ vcpu->arch.st.steal.preempted = 1;
+
+ kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
+ &vcpu->arch.st.steal.preempted,
+ offsetof(struct kvm_steal_time, preempted),
+ sizeof(vcpu->arch.st.steal.preempted));
+}
+
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ kvm_steal_time_set_preempted(vcpu);
kvm_x86_ops->vcpu_put(vcpu);
kvm_put_guest_fpu(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
@@ -3415,6 +3447,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
};
case KVM_SET_VAPIC_ADDR: {
struct kvm_vapic_addr va;
+ int idx;
r = -EINVAL;
if (!lapic_in_kernel(vcpu))
@@ -3422,7 +3455,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EFAULT;
if (copy_from_user(&va, argp, sizeof va))
goto out;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
}
case KVM_X86_SETUP_MCE: {
@@ -4103,9 +4138,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
struct kvm_clock_data user_ns;
u64 now_ns;
- now_ns = get_kvmclock_ns(kvm);
+ local_irq_disable();
+ now_ns = __get_kvmclock_ns(kvm);
user_ns.clock = now_ns;
- user_ns.flags = 0;
+ user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0;
+ local_irq_enable();
memset(&user_ns.pad, 0, sizeof(user_ns.pad));
r = -EFAULT;
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index d1dee753b949..07764255b611 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -113,14 +113,14 @@ int msr_clear_bit(u32 msr, u8 bit)
}
#ifdef CONFIG_TRACEPOINTS
-void do_trace_write_msr(unsigned msr, u64 val, int failed)
+void do_trace_write_msr(unsigned int msr, u64 val, int failed)
{
trace_write_msr(msr, val, failed);
}
EXPORT_SYMBOL(do_trace_write_msr);
EXPORT_TRACEPOINT_SYMBOL(write_msr);
-void do_trace_read_msr(unsigned msr, u64 val, int failed)
+void do_trace_read_msr(unsigned int msr, u64 val, int failed)
{
trace_read_msr(msr, val, failed);
}
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 79ae939970d3..fcd06f7526de 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -135,7 +135,12 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
if (early_recursion_flag > 2)
goto halt_loop;
- if (regs->cs != __KERNEL_CS)
+ /*
+ * Old CPUs leave the high bits of CS on the stack
+ * undefined. I'm not sure which CPUs do this, but at least
+ * the 486 DX works this way.
+ */
+ if ((regs->cs & 0xFFFF) != __KERNEL_CS)
goto fail;
/*
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 83e701f160a9..efc32bc6862b 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -986,20 +986,17 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
return 0;
}
-int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
- pfn_t pfn)
+void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
{
enum page_cache_mode pcm;
if (!pat_enabled())
- return 0;
+ return;
/* Set prot based on lookup */
pcm = lookup_memtype(pfn_t_to_phys(pfn));
*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
cachemode2protval(pcm));
-
- return 0;
}
/*
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index fe04a04dab8e..e76d1af60f7a 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -853,7 +853,7 @@ xadd: if (is_imm8(insn->off))
func = (u8 *) __bpf_call_base + imm32;
jmp_offset = func - (image + addrs[i]);
if (seen_ld_abs) {
- reload_skb_data = bpf_helper_changes_skb_data(func);
+ reload_skb_data = bpf_helper_changes_pkt_data(func);
if (reload_skb_data) {
EMIT1(0x57); /* push %rdi */
jmp_offset += 22; /* pop, mov, sub, mov */
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index bf99aa7005eb..936a488d6cf6 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -861,7 +861,7 @@ static void __init __efi_enter_virtual_mode(void)
int count = 0, pg_shift = 0;
void *new_memmap = NULL;
efi_status_t status;
- phys_addr_t pa;
+ unsigned long pa;
efi.systab = NULL;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 58b0f801f66f..319148bd4b05 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -31,6 +31,7 @@
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/slab.h>
+#include <linux/ucs2_string.h>
#include <asm/setup.h>
#include <asm/page.h>
@@ -211,6 +212,35 @@ void efi_sync_low_kernel_mappings(void)
memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
}
+/*
+ * Wrapper for slow_virt_to_phys() that handles NULL addresses.
+ */
+static inline phys_addr_t
+virt_to_phys_or_null_size(void *va, unsigned long size)
+{
+ bool bad_size;
+
+ if (!va)
+ return 0;
+
+ if (virt_addr_valid(va))
+ return virt_to_phys(va);
+
+ /*
+ * A fully aligned variable on the stack is guaranteed not to
+ * cross a page bounary. Try to catch strings on the stack by
+ * checking that 'size' is a power of two.
+ */
+ bad_size = size > PAGE_SIZE || !is_power_of_2(size);
+
+ WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size);
+
+ return slow_virt_to_phys(va);
+}
+
+#define virt_to_phys_or_null(addr) \
+ virt_to_phys_or_null_size((addr), sizeof(*(addr)))
+
int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
unsigned long pfn, text;
@@ -494,8 +524,8 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
spin_lock(&rtc_lock);
- phys_tm = virt_to_phys(tm);
- phys_tc = virt_to_phys(tc);
+ phys_tm = virt_to_phys_or_null(tm);
+ phys_tc = virt_to_phys_or_null(tc);
status = efi_thunk(get_time, phys_tm, phys_tc);
@@ -511,7 +541,7 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm)
spin_lock(&rtc_lock);
- phys_tm = virt_to_phys(tm);
+ phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(set_time, phys_tm);
@@ -529,9 +559,9 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
spin_lock(&rtc_lock);
- phys_enabled = virt_to_phys(enabled);
- phys_pending = virt_to_phys(pending);
- phys_tm = virt_to_phys(tm);
+ phys_enabled = virt_to_phys_or_null(enabled);
+ phys_pending = virt_to_phys_or_null(pending);
+ phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(get_wakeup_time, phys_enabled,
phys_pending, phys_tm);
@@ -549,7 +579,7 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
spin_lock(&rtc_lock);
- phys_tm = virt_to_phys(tm);
+ phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(set_wakeup_time, enabled, phys_tm);
@@ -558,6 +588,10 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
return status;
}
+static unsigned long efi_name_size(efi_char16_t *name)
+{
+ return ucs2_strsize(name, EFI_VAR_NAME_LEN) + 1;
+}
static efi_status_t
efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
@@ -567,11 +601,11 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
u32 phys_name, phys_vendor, phys_attr;
u32 phys_data_size, phys_data;
- phys_data_size = virt_to_phys(data_size);
- phys_vendor = virt_to_phys(vendor);
- phys_name = virt_to_phys(name);
- phys_attr = virt_to_phys(attr);
- phys_data = virt_to_phys(data);
+ phys_data_size = virt_to_phys_or_null(data_size);
+ phys_vendor = virt_to_phys_or_null(vendor);
+ phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+ phys_attr = virt_to_phys_or_null(attr);
+ phys_data = virt_to_phys_or_null_size(data, *data_size);
status = efi_thunk(get_variable, phys_name, phys_vendor,
phys_attr, phys_data_size, phys_data);
@@ -586,9 +620,9 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
u32 phys_name, phys_vendor, phys_data;
efi_status_t status;
- phys_name = virt_to_phys(name);
- phys_vendor = virt_to_phys(vendor);
- phys_data = virt_to_phys(data);
+ phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+ phys_vendor = virt_to_phys_or_null(vendor);
+ phys_data = virt_to_phys_or_null_size(data, data_size);
/* If data_size is > sizeof(u32) we've got problems */
status = efi_thunk(set_variable, phys_name, phys_vendor,
@@ -605,9 +639,9 @@ efi_thunk_get_next_variable(unsigned long *name_size,
efi_status_t status;
u32 phys_name_size, phys_name, phys_vendor;
- phys_name_size = virt_to_phys(name_size);
- phys_vendor = virt_to_phys(vendor);
- phys_name = virt_to_phys(name);
+ phys_name_size = virt_to_phys_or_null(name_size);
+ phys_vendor = virt_to_phys_or_null(vendor);
+ phys_name = virt_to_phys_or_null_size(name, *name_size);
status = efi_thunk(get_next_variable, phys_name_size,
phys_name, phys_vendor);
@@ -621,7 +655,7 @@ efi_thunk_get_next_high_mono_count(u32 *count)
efi_status_t status;
u32 phys_count;
- phys_count = virt_to_phys(count);
+ phys_count = virt_to_phys_or_null(count);
status = efi_thunk(get_next_high_mono_count, phys_count);
return status;
@@ -633,7 +667,7 @@ efi_thunk_reset_system(int reset_type, efi_status_t status,
{
u32 phys_data;
- phys_data = virt_to_phys(data);
+ phys_data = virt_to_phys_or_null_size(data, data_size);
efi_thunk(reset_system, reset_type, status, data_size, phys_data);
}
@@ -661,9 +695,9 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
return EFI_UNSUPPORTED;
- phys_storage = virt_to_phys(storage_space);
- phys_remaining = virt_to_phys(remaining_space);
- phys_max = virt_to_phys(max_variable_size);
+ phys_storage = virt_to_phys_or_null(storage_space);
+ phys_remaining = virt_to_phys_or_null(remaining_space);
+ phys_max = virt_to_phys_or_null(max_variable_size);
status = efi_thunk(query_variable_info, attr, phys_storage,
phys_remaining, phys_max);
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index 429d08be7848..dd6cfa4ad3ac 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -28,4 +28,4 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
# MISC Devices
obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
-obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_wdt.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index de734134bc8d..3f1f1c77d090 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -1,5 +1,5 @@
/*
- * platform_wdt.c: Watchdog platform library file
+ * Intel Merrifield watchdog platform device library file
*
* (C) Copyright 2014 Intel Corporation
* Author: David Cohen <david.a.cohen@linux.intel.com>
@@ -14,7 +14,9 @@
#include <linux/interrupt.h>
#include <linux/platform_device.h>
#include <linux/platform_data/intel-mid_wdt.h>
+
#include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
#include <asm/io_apic.h>
#define TANGIER_EXT_TIMER0_MSI 15
@@ -50,14 +52,34 @@ static struct intel_mid_wdt_pdata tangier_pdata = {
.probe = tangier_probe,
};
-static int __init register_mid_wdt(void)
+static int wdt_scu_status_change(struct notifier_block *nb,
+ unsigned long code, void *data)
{
- if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) {
- wdt_dev.dev.platform_data = &tangier_pdata;
- return platform_device_register(&wdt_dev);
+ if (code == SCU_DOWN) {
+ platform_device_unregister(&wdt_dev);
+ return 0;
}
- return -ENODEV;
+ return platform_device_register(&wdt_dev);
}
+static struct notifier_block wdt_scu_notifier = {
+ .notifier_call = wdt_scu_status_change,
+};
+
+static int __init register_mid_wdt(void)
+{
+ if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+ return -ENODEV;
+
+ wdt_dev.dev.platform_data = &tangier_pdata;
+
+ /*
+ * We need to be sure that the SCU IPC is ready before watchdog device
+ * can be registered:
+ */
+ intel_scu_notifier_add(&wdt_scu_notifier);
+
+ return 0;
+}
rootfs_initcall(register_mid_wdt);
diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c
index 5d3b45ad1c03..67375dda451c 100644
--- a/arch/x86/platform/intel-mid/pwr.c
+++ b/arch/x86/platform/intel-mid/pwr.c
@@ -272,6 +272,25 @@ int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state)
}
EXPORT_SYMBOL_GPL(intel_mid_pci_set_power_state);
+pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev)
+{
+ struct mid_pwr *pwr = midpwr;
+ int id, reg, bit;
+ u32 power;
+
+ if (!pwr || !pwr->available)
+ return PCI_UNKNOWN;
+
+ id = intel_mid_pwr_get_lss_id(pdev);
+ if (id < 0)
+ return PCI_UNKNOWN;
+
+ reg = (id * LSS_PWS_BITS) / 32;
+ bit = (id * LSS_PWS_BITS) % 32;
+ power = mid_pwr_get_state(pwr, reg);
+ return (__force pci_power_t)((power >> bit) & 3);
+}
+
void intel_mid_pwr_power_off(void)
{
struct mid_pwr *pwr = midpwr;
diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c
index 55130846ac87..c0533fbc39e3 100644
--- a/arch/x86/platform/olpc/olpc-xo15-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo15-sci.c
@@ -196,6 +196,7 @@ static int xo15_sci_remove(struct acpi_device *device)
return 0;
}
+#ifdef CONFIG_PM_SLEEP
static int xo15_sci_resume(struct device *dev)
{
/* Enable all EC events */
@@ -207,6 +208,7 @@ static int xo15_sci_resume(struct device *dev)
return 0;
}
+#endif
static SIMPLE_DEV_PM_OPS(xo15_sci_pm, NULL, xo15_sci_resume);
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index ac58c1616408..555b9fa0ad43 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -16,6 +16,7 @@ KCOV_INSTRUMENT := n
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
KBUILD_CFLAGS += -m$(BITS)
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
$(call if_changed,ld)
diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 1ac76479c266..8730c2882fff 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -275,6 +275,8 @@ static void do_inject(void)
unsigned int cpu = i_mce.extcpu;
u8 b = i_mce.bank;
+ rdtscll(i_mce.tsc);
+
if (i_mce.misc)
i_mce.status |= MCI_STATUS_MISCV;
diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h
index f59590645b68..1d23bf953a4a 100644
--- a/arch/x86/tools/relocs.h
+++ b/arch/x86/tools/relocs.h
@@ -16,7 +16,7 @@
#include <regex.h>
#include <tools/le_byteshift.h>
-void die(char *fmt, ...);
+void die(char *fmt, ...) __attribute__((noreturn));
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 233ee09c1ce8..c77db2288982 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -26,7 +26,6 @@ static inline void rep_nop(void)
}
#define cpu_relax() rep_nop()
-#define cpu_relax_lowlatency() cpu_relax()
#define task_pt_regs(t) (&(t)->thread.regs)
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 3d6e0064cbfc..e8a9ea7d7a21 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -114,6 +114,7 @@ void xen_uninit_lock_cpu(int cpu)
per_cpu(irq_name, cpu) = NULL;
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
/*
* Our init of PV spinlocks is split in two init functions due to us
@@ -137,6 +138,7 @@ void __init xen_init_spinlocks(void)
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = xen_qlock_wait;
pv_lock_ops.kick = xen_qlock_kick;
+ pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
}
/*