summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/boot.c26
-rw-r--r--arch/x86/kernel/cpu/amd.c19
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c2
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c4
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c46
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h18
-rw-r--r--arch/x86/kernel/ftrace.c2
-rw-r--r--arch/x86/kernel/hw_breakpoint.c45
-rw-r--r--arch/x86/kernel/irq.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c20
-rw-r--r--arch/x86/kernel/tls.c25
-rw-r--r--arch/x86/kernel/tsc.c2
15 files changed, 140 insertions, 82 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index add9b3a4ba13..a18fff361c7f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -611,20 +611,20 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
{
- int irq;
-
- if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
- *irqp = gsi;
- } else {
- mutex_lock(&acpi_ioapic_lock);
- irq = mp_map_gsi_to_irq(gsi,
- IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
- mutex_unlock(&acpi_ioapic_lock);
- if (irq < 0)
- return -1;
- *irqp = irq;
+ int rc, irq, trigger, polarity;
+
+ rc = acpi_get_override_irq(gsi, &trigger, &polarity);
+ if (rc == 0) {
+ trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+ polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+ irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+ if (irq >= 0) {
+ *irqp = irq;
+ return 0;
+ }
}
- return 0;
+
+ return -1;
}
EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 15c5df92f74e..a220239cea65 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -869,3 +869,22 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
return false;
}
+
+void set_dr_addr_mask(unsigned long mask, int dr)
+{
+ if (!cpu_has_bpext)
+ return;
+
+ switch (dr) {
+ case 0:
+ wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
+ break;
+ case 1:
+ case 2:
+ case 3:
+ wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
+ break;
+ default:
+ break;
+ }
+}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 15c29096136b..36a83617eb21 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -552,7 +552,7 @@ static int __init microcode_init(void)
int error;
if (paravirt_enabled() || dis_ucode_ldr)
- return 0;
+ return -EINVAL;
if (c->x86_vendor == X86_VENDOR_INTEL)
microcode_ops = init_intel_microcode();
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a450373e8e91..939155ffdece 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -107,6 +107,7 @@ static struct clocksource hyperv_cs = {
.rating = 400, /* use this when running on Hyperv*/
.read = read_hv_clock,
.mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
static void __init ms_hyperv_init_platform(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 944bf019b74f..498b6d967138 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
break;
case 55: /* 22nm Atom "Silvermont" */
+ case 76: /* 14nm Atom "Airmont" */
case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3c895d480cd7..073983398364 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -568,8 +568,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
};
struct event_constraint intel_slm_pebs_event_constraints[] = {
- /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1),
/* Allow all events as PEBS with no flags */
INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
EVENT_CONSTRAINT_END
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 673f930c700f..c4bb8b8e5017 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -103,6 +103,13 @@ static struct kobj_attribute format_attr_##_var = \
#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
+#define RAPL_EVENT_ATTR_STR(_name, v, str) \
+static struct perf_pmu_events_attr event_attr_##v = { \
+ .attr = __ATTR(_name, 0444, rapl_sysfs_show, NULL), \
+ .id = 0, \
+ .event_str = str, \
+};
+
struct rapl_pmu {
spinlock_t lock;
int hw_unit; /* 1/2^hw_unit Joule */
@@ -135,7 +142,7 @@ static inline u64 rapl_scale(u64 v)
* or use ldexp(count, -32).
* Watts = Joules/Time delta
*/
- return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
+ return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
}
static u64 rapl_event_update(struct perf_event *event)
@@ -379,23 +386,36 @@ static struct attribute_group rapl_pmu_attr_group = {
.attrs = rapl_pmu_attrs,
};
-EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
-EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
-EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
-EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04");
+static ssize_t rapl_sysfs_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr = \
+ container_of(attr, struct perf_pmu_events_attr, attr);
+
+ if (pmu_attr->event_str)
+ return sprintf(page, "%s", pmu_attr->event_str);
+
+ return 0;
+}
+
+RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
+RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
+RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04");
-EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
-EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
-EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
-EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules");
/*
* we compute in 0.23 nJ increments regardless of MSR
*/
-EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
static struct attribute *rapl_events_srv_attr[] = {
EVENT_PTR(rapl_cores),
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 10b8d3eaaf15..c635b8b49e93 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -840,7 +840,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
box->phys_id = phys_id;
box->pci_dev = pdev;
box->pmu = pmu;
- uncore_box_init(box);
pci_set_drvdata(pdev, box);
raw_spin_lock(&uncore_box_lock);
@@ -1004,10 +1003,8 @@ static int uncore_cpu_starting(int cpu)
pmu = &type->pmus[j];
box = *per_cpu_ptr(pmu->box, cpu);
/* called by uncore_cpu_init? */
- if (box && box->phys_id >= 0) {
- uncore_box_init(box);
+ if (box && box->phys_id >= 0)
continue;
- }
for_each_online_cpu(k) {
exist = *per_cpu_ptr(pmu->box, k);
@@ -1023,10 +1020,8 @@ static int uncore_cpu_starting(int cpu)
}
}
- if (box) {
+ if (box)
box->phys_id = phys_id;
- uncore_box_init(box);
- }
}
}
return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 863d9b02563e..6c8c1e7e69d8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -257,6 +257,14 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
return box->pmu->type->num_counters;
}
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+ if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+ if (box->pmu->type->ops->init_box)
+ box->pmu->type->ops->init_box(box);
+ }
+}
+
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
@@ -265,6 +273,8 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
static inline void uncore_enable_box(struct intel_uncore_box *box)
{
+ uncore_box_init(box);
+
if (box->pmu->type->ops->enable_box)
box->pmu->type->ops->enable_box(box);
}
@@ -287,14 +297,6 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
return box->pmu->type->ops->read_counter(box, event);
}
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
- if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
- if (box->pmu->type->ops->init_box)
- box->pmu->type->ops->init_box(box);
- }
-}
-
static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
return (box->phys_id < 0);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 2142376dc8c6..8b7b0a51e742 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size)
}
static inline void tramp_free(void *tramp)
{
- module_free(NULL, tramp);
+ module_memfree(tramp);
}
#else
/* Trampolines can only be created if modules are supported */
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 3d5fb509bdeb..7114ba220fd4 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -126,6 +126,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
*dr7 |= encode_dr7(i, info->len, info->type);
set_debugreg(*dr7, 7);
+ if (info->mask)
+ set_dr_addr_mask(info->mask, i);
return 0;
}
@@ -161,29 +163,8 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
*dr7 &= ~__encode_dr7(i, info->len, info->type);
set_debugreg(*dr7, 7);
-}
-
-static int get_hbp_len(u8 hbp_len)
-{
- unsigned int len_in_bytes = 0;
-
- switch (hbp_len) {
- case X86_BREAKPOINT_LEN_1:
- len_in_bytes = 1;
- break;
- case X86_BREAKPOINT_LEN_2:
- len_in_bytes = 2;
- break;
- case X86_BREAKPOINT_LEN_4:
- len_in_bytes = 4;
- break;
-#ifdef CONFIG_X86_64
- case X86_BREAKPOINT_LEN_8:
- len_in_bytes = 8;
- break;
-#endif
- }
- return len_in_bytes;
+ if (info->mask)
+ set_dr_addr_mask(0, i);
}
/*
@@ -196,7 +177,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
va = info->address;
- len = get_hbp_len(info->len);
+ len = bp->attr.bp_len;
return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
}
@@ -277,6 +258,8 @@ static int arch_build_bp_info(struct perf_event *bp)
}
/* Len */
+ info->mask = 0;
+
switch (bp->attr.bp_len) {
case HW_BREAKPOINT_LEN_1:
info->len = X86_BREAKPOINT_LEN_1;
@@ -293,11 +276,17 @@ static int arch_build_bp_info(struct perf_event *bp)
break;
#endif
default:
- return -EINVAL;
+ if (!is_power_of_2(bp->attr.bp_len))
+ return -EINVAL;
+ if (!cpu_has_bpext)
+ return -EOPNOTSUPP;
+ info->mask = bp->attr.bp_len - 1;
+ info->len = X86_BREAKPOINT_LEN_1;
}
return 0;
}
+
/*
* Validate the arch-specific HW Breakpoint register settings
*/
@@ -312,11 +301,11 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
if (ret)
return ret;
- ret = -EINVAL;
-
switch (info->len) {
case X86_BREAKPOINT_LEN_1:
align = 0;
+ if (info->mask)
+ align = info->mask;
break;
case X86_BREAKPOINT_LEN_2:
align = 1;
@@ -330,7 +319,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
break;
#endif
default:
- return ret;
+ WARN_ON_ONCE(1);
}
/*
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 6307a0f0cf17..705ef8d48e2d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -127,7 +127,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_puts(p, " Machine check polls\n");
#endif
#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
- seq_printf(p, "%*s: ", prec, "THR");
+ seq_printf(p, "%*s: ", prec, "HYP");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
seq_puts(p, " Hypervisor callback interrupts\n");
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index f7e3cd50ece0..98f654d466e5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1020,6 +1020,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
regs->flags &= ~X86_EFLAGS_IF;
trace_hardirqs_off();
regs->ip = (unsigned long)(jp->entry);
+
+ /*
+ * jprobes use jprobe_return() which skips the normal return
+ * path of the function, and this messes up the accounting of the
+ * function graph tracer to get messed up.
+ *
+ * Pause function graph tracing while performing the jprobe function.
+ */
+ pause_graph_tracing();
return 1;
}
NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -1048,24 +1057,25 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
u8 *addr = (u8 *) (regs->ip - 1);
struct jprobe *jp = container_of(p, struct jprobe, kp);
+ void *saved_sp = kcb->jprobe_saved_sp;
if ((addr > (u8 *) jprobe_return) &&
(addr < (u8 *) jprobe_return_end)) {
- if (stack_addr(regs) != kcb->jprobe_saved_sp) {
+ if (stack_addr(regs) != saved_sp) {
struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
printk(KERN_ERR
"current sp %p does not match saved sp %p\n",
- stack_addr(regs), kcb->jprobe_saved_sp);
+ stack_addr(regs), saved_sp);
printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
show_regs(saved_regs);
printk(KERN_ERR "Current registers\n");
show_regs(regs);
BUG();
}
+ /* It's OK to start function graph tracing again */
+ unpause_graph_tracing();
*regs = kcb->jprobe_saved_regs;
- memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
- kcb->jprobes_stack,
- MIN_STACK_SIZE(kcb->jprobe_saved_sp));
+ memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
preempt_enable_no_resched();
return 1;
}
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 4e942f31b1a7..7fc5e843f247 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -29,7 +29,28 @@ static int get_free_idx(void)
static bool tls_desc_okay(const struct user_desc *info)
{
- if (LDT_empty(info))
+ /*
+ * For historical reasons (i.e. no one ever documented how any
+ * of the segmentation APIs work), user programs can and do
+ * assume that a struct user_desc that's all zeros except for
+ * entry_number means "no segment at all". This never actually
+ * worked. In fact, up to Linux 3.19, a struct user_desc like
+ * this would create a 16-bit read-write segment with base and
+ * limit both equal to zero.
+ *
+ * That was close enough to "no segment at all" until we
+ * hardened this function to disallow 16-bit TLS segments. Fix
+ * it up by interpreting these zeroed segments the way that they
+ * were almost certainly intended to be interpreted.
+ *
+ * The correct way to ask for "no segment at all" is to specify
+ * a user_desc that satisfies LDT_empty. To keep everything
+ * working, we accept both.
+ *
+ * Note that there's a similar kludge in modify_ldt -- look at
+ * the distinction between modes 1 and 0x11.
+ */
+ if (LDT_empty(info) || LDT_zero(info))
return true;
/*
@@ -71,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx,
cpu = get_cpu();
while (n-- > 0) {
- if (LDT_empty(info))
+ if (LDT_empty(info) || LDT_zero(info))
desc->a = desc->b = 0;
else
fill_ldt(desc, info);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b7e50bba3bbb..505449700e0c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -617,7 +617,7 @@ static unsigned long quick_pit_calibrate(void)
goto success;
}
}
- pr_err("Fast TSC calibration failed\n");
+ pr_info("Fast TSC calibration failed\n");
return 0;
success:
generated by cgit (git 2.34.1) at 2025-04-19 07:53:52 +0000