summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/cstate.c12
-rw-r--r--arch/x86/kernel/apic/apic.c57
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c5
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c6
-rw-r--r--arch/x86/kernel/cpu/bugs.c17
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/cpu/hygon.c5
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c2
-rw-r--r--arch/x86/kernel/cpu/proc.c10
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c4
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c176
-rw-r--r--arch/x86/kernel/crash.c3
-rw-r--r--arch/x86/kernel/kprobes/core.c49
-rw-r--r--arch/x86/kernel/ldt.c14
-rw-r--r--arch/x86/kernel/paravirt.c2
-rw-r--r--arch/x86/kernel/perf_regs.c27
-rw-r--r--arch/x86/kernel/process.c12
-rw-r--r--arch/x86/kernel/process_32.c7
-rw-r--r--arch/x86/kernel/process_64.c1
-rw-r--r--arch/x86/kernel/reboot.c23
-rw-r--r--arch/x86/kernel/setup.c6
-rw-r--r--arch/x86/kernel/signal.c34
-rw-r--r--arch/x86/kernel/stacktrace.c128
-rw-r--r--arch/x86/kernel/vm86_32.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S2
27 files changed, 337 insertions, 275 deletions
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 158ad1483c43..cb6e076a6d39 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -51,6 +51,18 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
if (c->x86_vendor == X86_VENDOR_INTEL &&
(c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f)))
flags->bm_control = 0;
+ /*
+ * For all recent Centaur CPUs, the ucode will make sure that each
+ * core can keep cache coherence with each other while entering C3
+ * type state. So, set bm_check to 1 to indicate that the kernel
+ * doesn't need to execute a cache flush operation (WBINVD) when
+ * entering C3 type state.
+ */
+ if (c->x86_vendor == X86_VENDOR_CENTAUR) {
+ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f &&
+ c->x86_stepping >= 0x0e))
+ flags->bm_check = 1;
+ }
}
EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b7bcdd781651..ab6af775f06c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -802,6 +802,24 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
return 0;
}
+static int __init lapic_init_clockevent(void)
+{
+ if (!lapic_timer_frequency)
+ return -1;
+
+ /* Calculate the scaled math multiplication factor */
+ lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+ TICK_NSEC, lapic_clockevent.shift);
+ lapic_clockevent.max_delta_ns =
+ clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
+ lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ticks = 0xF;
+
+ return 0;
+}
+
static int __init calibrate_APIC_clock(void)
{
struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
@@ -810,25 +828,21 @@ static int __init calibrate_APIC_clock(void)
long delta, deltatsc;
int pm_referenced = 0;
- /**
- * check if lapic timer has already been calibrated by platform
- * specific routine, such as tsc calibration code. if so, we just fill
+ if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ return 0;
+
+ /*
+ * Check if lapic timer has already been calibrated by platform
+ * specific routine, such as tsc calibration code. If so just fill
* in the clockevent structure and return.
*/
-
- if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
- return 0;
- } else if (lapic_timer_frequency) {
+ if (!lapic_init_clockevent()) {
apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
- lapic_timer_frequency);
- lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
- TICK_NSEC, lapic_clockevent.shift);
- lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
- lapic_clockevent.max_delta_ticks = 0x7FFFFF;
- lapic_clockevent.min_delta_ns =
- clockevent_delta2ns(0xF, &lapic_clockevent);
- lapic_clockevent.min_delta_ticks = 0xF;
+ lapic_timer_frequency);
+ /*
+ * Direct calibration methods must have an always running
+ * local APIC timer, no need for broadcast timer.
+ */
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
return 0;
}
@@ -869,17 +883,8 @@ static int __init calibrate_APIC_clock(void)
pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
&delta, &deltatsc);
- /* Calculate the scaled math multiplication factor */
- lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
- lapic_clockevent.shift);
- lapic_clockevent.max_delta_ns =
- clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
- lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
- lapic_clockevent.min_delta_ns =
- clockevent_delta2ns(0xF, &lapic_clockevent);
- lapic_clockevent.min_delta_ticks = 0xF;
-
lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+ lapic_init_clockevent();
apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 78778b54f904..a5464b8b6c46 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -175,7 +175,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
this_cpu_write(cpu_llc_id, node);
/* Account for nodes per socket in multi-core-module processors */
- if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
+ if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
rdmsrl(MSR_FAM10H_NODE_ID, val);
nodes = ((val >> 3) & 7) + 1;
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 01004bfb1a1b..fb6a64bd765f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -82,11 +82,14 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
* performance at the same time..
*/
+#ifdef CONFIG_X86_32
extern __visible void vide(void);
-__asm__(".globl vide\n"
+__asm__(".text\n"
+ ".globl vide\n"
".type vide, @function\n"
".align 4\n"
"vide: ret\n");
+#endif
static void init_amd_k5(struct cpuinfo_x86 *c)
{
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 804c49493938..64d5aec24203 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -83,7 +83,7 @@ unsigned int aperfmperf_get_khz(int cpu)
if (!cpu_khz)
return 0;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
@@ -99,7 +99,7 @@ void arch_freq_prepare_all(void)
if (!cpu_khz)
return;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return;
for_each_online_cpu(cpu)
@@ -115,7 +115,7 @@ unsigned int arch_freq_get_on_cpu(int cpu)
if (!cpu_khz)
return 0;
- if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+ if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
return 0;
if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2da82eff0eb4..29630393f300 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -275,7 +275,7 @@ static const struct {
const char *option;
enum spectre_v2_user_cmd cmd;
bool secure;
-} v2_user_options[] __initdata = {
+} v2_user_options[] __initconst = {
{ "auto", SPECTRE_V2_USER_CMD_AUTO, false },
{ "off", SPECTRE_V2_USER_CMD_NONE, false },
{ "on", SPECTRE_V2_USER_CMD_FORCE, true },
@@ -419,7 +419,7 @@ static const struct {
const char *option;
enum spectre_v2_mitigation_cmd cmd;
bool secure;
-} mitigation_options[] __initdata = {
+} mitigation_options[] __initconst = {
{ "off", SPECTRE_V2_CMD_NONE, false },
{ "on", SPECTRE_V2_CMD_FORCE, true },
{ "retpoline", SPECTRE_V2_CMD_RETPOLINE, false },
@@ -440,7 +440,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
char arg[20];
int ret, i;
- if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+ if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") ||
+ cpu_mitigations_off())
return SPECTRE_V2_CMD_NONE;
ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
@@ -658,7 +659,7 @@ static const char * const ssb_strings[] = {
static const struct {
const char *option;
enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[] __initdata = {
+} ssb_mitigation_options[] __initconst = {
{ "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
{ "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */
{ "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
@@ -672,7 +673,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
char arg[20];
int ret, i;
- if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+ if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") ||
+ cpu_mitigations_off()) {
return SPEC_STORE_BYPASS_CMD_NONE;
} else {
ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
@@ -1008,6 +1010,11 @@ static void __init l1tf_select_mitigation(void)
if (!boot_cpu_has_bug(X86_BUG_L1TF))
return;
+ if (cpu_mitigations_off())
+ l1tf_mitigation = L1TF_MITIGATION_OFF;
+ else if (cpu_mitigations_auto_nosmt())
+ l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+
override_cache_bits(&boot_cpu_data);
switch (l1tf_mitigation) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 801c6f040faa..37f7d438a6ef 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1637,7 +1637,7 @@ static void setup_getcpu(int cpu)
unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
struct desc_struct d = { };
- if (static_cpu_has(X86_FEATURE_RDTSCP))
+ if (boot_cpu_has(X86_FEATURE_RDTSCP))
write_rdtscp_aux(cpudata);
/* Store CPU and node number in limit. */
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index cf25405444ab..415621ddb8a2 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -19,6 +19,8 @@
#include "cpu.h"
+#define APICID_SOCKET_ID_BIT 6
+
/*
* nodes_per_socket: Stores the number of nodes per socket.
* Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
@@ -87,6 +89,9 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
if (!err)
c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+ /* Socket ID is ApicId[6] for these processors. */
+ c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+
cacheinfo_hygon_init_llc_id(c, cpu, node_id);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fc3c07fe7df5..3142fd7a9b32 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -611,8 +611,8 @@ static void init_intel_energy_perf(struct cpuinfo_x86 *c)
if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
return;
- pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
- pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
+ pr_info_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+ pr_info_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
}
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 8492ef7d9015..3da9a8823e47 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -528,7 +528,7 @@ static void do_inject(void)
* only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for
* Fam10h and later BKDGs.
*/
- if (static_cpu_has(X86_FEATURE_AMD_DCM) &&
+ if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
b == 4 &&
boot_cpu_data.x86 < 0x17) {
toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 2c8522a39ed5..cb2e49810d68 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -35,11 +35,11 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
"fpu_exception\t: %s\n"
"cpuid level\t: %d\n"
"wp\t\t: yes\n",
- static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
- static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
- static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
- static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
- static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
+ boot_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
+ boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+ boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
c->cpuid_level);
}
#else
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 2dbd990a2eb7..89320c0396b1 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -342,10 +342,10 @@ int update_domains(struct rdt_resource *r, int closid)
if (cpumask_empty(cpu_mask) || mba_sc)
goto done;
cpu = get_cpu();
- /* Update CBM on this cpu if it's in cpu_mask. */
+ /* Update resource control msr on this CPU if it's in cpu_mask. */
if (cpumask_test_cpu(cpu, cpu_mask))
rdt_ctrl_update(&msr_param);
- /* Update CBM on other cpus. */
+ /* Update resource control msr on other CPUs. */
smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
put_cpu();
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 54b9eef3eea9..333c177a2471 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2516,103 +2516,131 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
bitmap_clear(val, zero_bit, cbm_len - zero_bit);
}
-/**
- * rdtgroup_init_alloc - Initialize the new RDT group's allocations
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations. That is, all shareable and unused bits.
+/*
+ * Initialize cache resources per RDT domain
*
- * All-zero CBM is invalid. If there are no more shareable bits available
- * on any domain then the entire allocation will fail.
+ * Set the RDT domain up to start off with all usable allocations. That is,
+ * all shareable and unused bits. All-zero CBM is invalid.
*/
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
+ u32 closid)
{
struct rdt_resource *r_cdp = NULL;
struct rdt_domain *d_cdp = NULL;
u32 used_b = 0, unused_b = 0;
- u32 closid = rdtgrp->closid;
- struct rdt_resource *r;
unsigned long tmp_cbm;
enum rdtgrp_mode mode;
- struct rdt_domain *d;
u32 peer_ctl, *ctrl;
- int i, ret;
+ int i;
- for_each_alloc_enabled_rdt_resource(r) {
- /*
- * Only initialize default allocations for CBM cache
- * resources
- */
- if (r->rid == RDT_RESOURCE_MBA)
- continue;
- list_for_each_entry(d, &r->domains, list) {
- rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
- d->have_new_ctrl = false;
- d->new_ctrl = r->cache.shareable_bits;
- used_b = r->cache.shareable_bits;
- ctrl = d->ctrl_val;
- for (i = 0; i < closids_supported(); i++, ctrl++) {
- if (closid_allocated(i) && i != closid) {
- mode = rdtgroup_mode_by_closid(i);
- if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
- break;
- /*
- * If CDP is active include peer
- * domain's usage to ensure there
- * is no overlap with an exclusive
- * group.
- */
- if (d_cdp)
- peer_ctl = d_cdp->ctrl_val[i];
- else
- peer_ctl = 0;
- used_b |= *ctrl | peer_ctl;
- if (mode == RDT_MODE_SHAREABLE)
- d->new_ctrl |= *ctrl | peer_ctl;
- }
- }
- if (d->plr && d->plr->cbm > 0)
- used_b |= d->plr->cbm;
- unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
- unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
- d->new_ctrl |= unused_b;
- /*
- * Force the initial CBM to be valid, user can
- * modify the CBM based on system availability.
- */
- cbm_ensure_valid(&d->new_ctrl, r);
+ rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
+ d->have_new_ctrl = false;
+ d->new_ctrl = r->cache.shareable_bits;
+ used_b = r->cache.shareable_bits;
+ ctrl = d->ctrl_val;
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
+ if (closid_allocated(i) && i != closid) {
+ mode = rdtgroup_mode_by_closid(i);
+ if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+ break;
/*
- * Assign the u32 CBM to an unsigned long to ensure
- * that bitmap_weight() does not access out-of-bound
- * memory.
+ * If CDP is active include peer domain's
+ * usage to ensure there is no overlap
+ * with an exclusive group.
*/
- tmp_cbm = d->new_ctrl;
- if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
- r->cache.min_cbm_bits) {
- rdt_last_cmd_printf("No space on %s:%d\n",
- r->name, d->id);
- return -ENOSPC;
- }
- d->have_new_ctrl = true;
+ if (d_cdp)
+ peer_ctl = d_cdp->ctrl_val[i];
+ else
+ peer_ctl = 0;
+ used_b |= *ctrl | peer_ctl;
+ if (mode == RDT_MODE_SHAREABLE)
+ d->new_ctrl |= *ctrl | peer_ctl;
}
}
+ if (d->plr && d->plr->cbm > 0)
+ used_b |= d->plr->cbm;
+ unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+ unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+ d->new_ctrl |= unused_b;
+ /*
+ * Force the initial CBM to be valid, user can
+ * modify the CBM based on system availability.
+ */
+ cbm_ensure_valid(&d->new_ctrl, r);
+ /*
+ * Assign the u32 CBM to an unsigned long to ensure that
+ * bitmap_weight() does not access out-of-bound memory.
+ */
+ tmp_cbm = d->new_ctrl;
+ if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
+ rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id);
+ return -ENOSPC;
+ }
+ d->have_new_ctrl = true;
+
+ return 0;
+}
+
+/*
+ * Initialize cache resources with default values.
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations.
+ *
+ * If there are no more shareable bits available on any domain then
+ * the entire allocation will fail.
+ */
+static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid)
+{
+ struct rdt_domain *d;
+ int ret;
+
+ list_for_each_entry(d, &r->domains, list) {
+ ret = __init_one_rdt_domain(d, r, closid);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+/* Initialize MBA resource with default values. */
+static void rdtgroup_init_mba(struct rdt_resource *r)
+{
+ struct rdt_domain *d;
+
+ list_for_each_entry(d, &r->domains, list) {
+ d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+ d->have_new_ctrl = true;
+ }
+}
+
+/* Initialize the RDT group's allocations. */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+ struct rdt_resource *r;
+ int ret;
for_each_alloc_enabled_rdt_resource(r) {
- /*
- * Only initialize default allocations for CBM cache
- * resources
- */
- if (r->rid == RDT_RESOURCE_MBA)
- continue;
+ if (r->rid == RDT_RESOURCE_MBA) {
+ rdtgroup_init_mba(r);
+ } else {
+ ret = rdtgroup_init_cat(r, rdtgrp->closid);
+ if (ret < 0)
+ return ret;
+ }
+
ret = update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("Failed to initialize allocations\n");
return ret;
}
- rdtgrp->mode = RDT_MODE_SHAREABLE;
+
}
+ rdtgrp->mode = RDT_MODE_SHAREABLE;
+
return 0;
}
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 17ffc869cab8..a96ca8584803 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -204,8 +204,7 @@ static struct crash_mem *fill_up_crash_elf_data(void)
* another range split. So add extra two slots here.
*/
nr_ranges += 2;
- cmem = vzalloc(sizeof(struct crash_mem) +
- sizeof(struct crash_mem_range) * nr_ranges);
+ cmem = vzalloc(struct_size(cmem, ranges, nr_ranges));
if (!cmem)
return NULL;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a034cb808e7e..122548ad5c2e 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
unsigned long *sara = stack_addr(regs);
ri->ret_addr = (kprobe_opcode_t *) *sara;
+ ri->fp = sara;
/* Replace the return addr with trampoline addr */
*sara = (unsigned long) &kretprobe_trampoline;
@@ -715,6 +716,7 @@ NOKPROBE_SYMBOL(kprobe_int3_handler);
* calls trampoline_handler() runs, which calls the kretprobe's handler.
*/
asm(
+ ".text\n"
".global kretprobe_trampoline\n"
".type kretprobe_trampoline, @function\n"
"kretprobe_trampoline:\n"
@@ -748,26 +750,48 @@ asm(
NOKPROBE_SYMBOL(kretprobe_trampoline);
STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
+static struct kprobe kretprobe_kprobe = {
+ .addr = (void *)kretprobe_trampoline,
+};
+
/*
* Called from kretprobe_trampoline
*/
static __used void *trampoline_handler(struct pt_regs *regs)
{
+ struct kprobe_ctlblk *kcb;
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
kprobe_opcode_t *correct_ret_addr = NULL;
+ void *frame_pointer;
+ bool skipped = false;
+
+ preempt_disable();
+
+ /*
+ * Set a dummy kprobe for avoiding kretprobe recursion.
+ * Since kretprobe never run in kprobe handler, kprobe must not
+ * be running at this point.
+ */
+ kcb = get_kprobe_ctlblk();
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/* fixup registers */
#ifdef CONFIG_X86_64
regs->cs = __KERNEL_CS;
+ /* On x86-64, we use pt_regs->sp for return address holder. */
+ frame_pointer = &regs->sp;
#else
regs->cs = __KERNEL_CS | get_kernel_rpl();
regs->gs = 0;
+ /* On x86-32, we use pt_regs->flags for return address holder. */
+ frame_pointer = &regs->flags;
#endif
regs->ip = trampoline_address;
regs->orig_ax = ~0UL;
@@ -789,8 +813,25 @@ static __used void *trampoline_handler(struct pt_regs *regs)
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ /*
+ * Return probes must be pushed on this hash list correct
+ * order (same as return order) so that it can be poped
+ * correctly. However, if we find it is pushed it incorrect
+ * order, this means we find a function which should not be
+ * probed, because the wrong order entry is pushed on the
+ * path of processing other kretprobe itself.
+ */
+ if (ri->fp != frame_pointer) {
+ if (!skipped)
+ pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+ skipped = true;
+ continue;
+ }
orig_ret_address = (unsigned long)ri->ret_addr;
+ if (skipped)
+ pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+ ri->rp->kp.addr);
if (orig_ret_address != trampoline_address)
/*
@@ -808,14 +849,15 @@ static __used void *trampoline_handler(struct pt_regs *regs)
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
+ if (ri->fp != frame_pointer)
+ continue;
orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
- get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
- __this_cpu_write(current_kprobe, NULL);
+ __this_cpu_write(current_kprobe, &kretprobe_kprobe);
}
recycle_rp_inst(ri, &empty_rp);
@@ -831,6 +873,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
kretprobe_hash_unlock(current, &flags);
+ __this_cpu_write(current_kprobe, NULL);
+ preempt_enable();
+
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 6135ae8ce036..b2463fcb20a8 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -113,7 +113,7 @@ static void do_sanity_check(struct mm_struct *mm,
* tables.
*/
WARN_ON(!had_kernel_mapping);
- if (static_cpu_has(X86_FEATURE_PTI))
+ if (boot_cpu_has(X86_FEATURE_PTI))
WARN_ON(!had_user_mapping);
} else {
/*
@@ -121,7 +121,7 @@ static void do_sanity_check(struct mm_struct *mm,
* Sync the pgd to the usermode tables.
*/
WARN_ON(had_kernel_mapping);
- if (static_cpu_has(X86_FEATURE_PTI))
+ if (boot_cpu_has(X86_FEATURE_PTI))
WARN_ON(had_user_mapping);
}
}
@@ -156,7 +156,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
- if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
set_pmd(u_pmd, *k_pmd);
}
@@ -181,7 +181,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
{
pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
- if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
set_pgd(kernel_to_user_pgdp(pgd), *pgd);
}
@@ -208,7 +208,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
spinlock_t *ptl;
int i, nr_pages;
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return 0;
/*
@@ -271,7 +271,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
return;
/* LDT map/unmap is only required for PTI */
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
@@ -311,7 +311,7 @@ static void free_ldt_pgtables(struct mm_struct *mm)
unsigned long start = LDT_BASE_ADDR;
unsigned long end = LDT_END_ADDR;
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
tlb_gather_mmu(&tlb, mm, start, end);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c0e0101133f3..7bbaa6baf37f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -121,7 +121,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
void __init native_pv_lock_init(void)
{
- if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
static_branch_disable(&virt_spin_lock_key);
}
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index c06c4c16c6b6..07c30ee17425 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
u64 perf_reg_value(struct pt_regs *regs, int idx)
{
+ struct x86_perf_regs *perf_regs;
+
+ if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ if (!perf_regs->xmm_regs)
+ return 0;
+ return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+ }
+
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
return 0;
return regs_get_register(regs, pt_regs_offset[idx]);
}
-#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
-
#ifdef CONFIG_X86_32
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
+
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
@@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
- return -EINVAL;
-
- if (mask & REG_NOSUPPORT)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 58ac7be52c7a..d1d312d012a6 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -236,7 +236,7 @@ static int get_cpuid_mode(void)
static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
{
- if (!static_cpu_has(X86_FEATURE_CPUID_FAULT))
+ if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
return -ENODEV;
if (cpuid_enabled)
@@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
u64 msr = x86_spec_ctrl_base;
bool updmsr = false;
+ lockdep_assert_irqs_disabled();
+
/*
* If TIF_SSBD is different, select the proper mitigation
* method. Note that if SSBD mitigation is disabled or permanentely
@@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
void speculation_ctrl_update(unsigned long tif)
{
+ unsigned long flags;
+
/* Forced update. Make sure all relevant TIF flags are different */
- preempt_disable();
+ local_irq_save(flags);
__speculation_ctrl_update(~tif, tif);
- preempt_enable();
+ local_irq_restore(flags);
}
/* Called from seccomp/prctl update */
@@ -666,7 +670,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
if (c->x86_vendor != X86_VENDOR_INTEL)
return 0;
- if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR))
+ if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_cpu_has_bug(X86_BUG_MONITOR))
return 0;
return 1;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e471d8e6f0b2..70933193878c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
struct task_struct *tsk;
int err;
+ /*
+ * For a new task use the RESET flags value since there is no before.
+ * All the status flags are zero; DF and all the system flags must also
+ * be 0, specifically IF must be 0 because we context switch to the new
+ * task with interrupts disabled.
+ */
+ frame->flags = X86_EFLAGS_FIXED;
frame->bp = 0;
frame->ret_addr = (unsigned long) ret_from_fork;
p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6a62f4af9fcf..844a28b29967 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -392,6 +392,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
childregs = task_pt_regs(p);
fork_frame = container_of(childregs, struct fork_frame, regs);
frame = &fork_frame->frame;
+
frame->bp = 0;
frame->ret_addr = (unsigned long) ret_from_fork;
p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 725624b6c0c0..09d6bded3c1e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
return 0;
}
+/*
+ * Some machines don't handle the default ACPI reboot method and
+ * require the EFI reboot method:
+ */
+static int __init set_efi_reboot(const struct dmi_system_id *d)
+{
+ if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) {
+ reboot_type = BOOT_EFI;
+ pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident);
+ }
+ return 0;
+}
+
void __noreturn machine_real_restart(unsigned int type)
{
local_irq_disable();
@@ -108,7 +121,7 @@ void __noreturn machine_real_restart(unsigned int type)
write_cr3(real_mode_header->trampoline_pgd);
/* Exiting long mode will fail if CR4.PCIDE is set. */
- if (static_cpu_has(X86_FEATURE_PCID))
+ if (boot_cpu_has(X86_FEATURE_PCID))
cr4_clear_bits(X86_CR4_PCIDE);
#endif
@@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
},
},
+ { /* Handle reboot issue on Acer TravelMate X514-51T */
+ .callback = set_efi_reboot,
+ .ident = "Acer TravelMate X514-51T",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"),
+ },
+ },
/* Apple */
{ /* Handle problems with rebooting on Apple MacBook5 */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3d872a527cd9..3773905cd2c1 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1005,13 +1005,11 @@ void __init setup_arch(char **cmdline_p)
if (efi_enabled(EFI_BOOT))
efi_init();
- dmi_scan_machine();
- dmi_memdev_walk();
- dmi_set_dump_stack_arch_desc();
+ dmi_setup();
/*
* VMware detection requires dmi to be available, so this
- * needs to be done after dmi_scan_machine(), for the boot CPU.
+ * needs to be done after dmi_setup(), for the boot CPU.
*/
init_hypervisor_platform();
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 08dfd4c1a4f9..dff90fb6a9af 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -132,16 +132,6 @@ static int restore_sigcontext(struct pt_regs *regs,
COPY_SEG_CPL3(cs);
COPY_SEG_CPL3(ss);
-#ifdef CONFIG_X86_64
- /*
- * Fix up SS if needed for the benefit of old DOSEMU and
- * CRIU.
- */
- if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
- user_64bit_mode(regs)))
- force_valid_ss(regs);
-#endif
-
get_user_ex(tmpflags, &sc->flags);
regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
regs->orig_ax = -1; /* disable syscall checks */
@@ -150,6 +140,15 @@ static int restore_sigcontext(struct pt_regs *regs,
buf = (void __user *)buf_val;
} get_user_catch(err);
+#ifdef CONFIG_X86_64
+ /*
+ * Fix up SS if needed for the benefit of old DOSEMU and
+ * CRIU.
+ */
+ if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs)))
+ force_valid_ss(regs);
+#endif
+
err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32));
force_iret();
@@ -461,6 +460,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
{
struct rt_sigframe __user *frame;
void __user *fp = NULL;
+ unsigned long uc_flags;
int err = 0;
frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
@@ -473,9 +473,11 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
return -EFAULT;
}
+ uc_flags = frame_uc_flags(regs);
+
put_user_try {
/* Create the ucontext. */
- put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+ put_user_ex(uc_flags, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
save_altstack_ex(&frame->uc.uc_stack, regs->sp);
@@ -541,6 +543,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
{
#ifdef CONFIG_X86_X32_ABI
struct rt_sigframe_x32 __user *frame;
+ unsigned long uc_flags;
void __user *restorer;
int err = 0;
void __user *fpstate = NULL;
@@ -555,9 +558,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
return -EFAULT;
}
+ uc_flags = frame_uc_flags(regs);
+
put_user_try {
/* Create the ucontext. */
- put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+ put_user_ex(uc_flags, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
put_user_ex(0, &frame->uc.uc__pad0);
@@ -688,10 +693,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
sigset_t *set = sigmask_to_save();
compat_sigset_t *cset = (compat_sigset_t *) set;
- /*
- * Increment event counter and perform fixup for the pre-signal
- * frame.
- */
+ /* Perform fixup for the pre-signal frame. */
rseq_signal_deliver(ksig, regs);
/* Set up the stack frame */
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 5c2d71a1dc06..2abf27d7df6b 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -12,78 +12,31 @@
#include <asm/stacktrace.h>
#include <asm/unwind.h>
-static int save_stack_address(struct stack_trace *trace, unsigned long addr,
- bool nosched)
-{
- if (nosched && in_sched_functions(addr))
- return 0;
-
- if (trace->skip > 0) {
- trace->skip--;
- return 0;
- }
-
- if (trace->nr_entries >= trace->max_entries)
- return -1;
-
- trace->entries[trace->nr_entries++] = addr;
- return 0;
-}
-
-static void noinline __save_stack_trace(struct stack_trace *trace,
- struct task_struct *task, struct pt_regs *regs,
- bool nosched)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+ struct task_struct *task, struct pt_regs *regs)
{
struct unwind_state state;
unsigned long addr;
- if (regs)
- save_stack_address(trace, regs->ip, nosched);
+ if (regs && !consume_entry(cookie, regs->ip, false))
+ return;
for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
- if (!addr || save_stack_address(trace, addr, nosched))
+ if (!addr || !consume_entry(cookie, addr, false))
break;
}
-
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
}
/*
- * Save stack-backtrace addresses into a stack_trace buffer.
+ * This function returns an error if it detects any unreliable features of the
+ * stack. Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
*/
-void save_stack_trace(struct stack_trace *trace)
-{
- trace->skip++;
- __save_stack_trace(trace, current, NULL, false);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
-
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
- __save_stack_trace(trace, current, regs, false);
-}
-
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
- if (!try_get_task_stack(tsk))
- return;
-
- if (tsk == current)
- trace->skip++;
- __save_stack_trace(trace, tsk, NULL, true);
-
- put_task_stack(tsk);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
-
-#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
-
-static int __always_inline
-__save_stack_trace_reliable(struct stack_trace *trace,
- struct task_struct *task)
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task)
{
struct unwind_state state;
struct pt_regs *regs;
@@ -97,7 +50,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
if (regs) {
/* Success path for user tasks */
if (user_mode(regs))
- goto success;
+ return 0;
/*
* Kernel mode registers on the stack indicate an
@@ -120,7 +73,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
if (!addr)
return -EINVAL;
- if (save_stack_address(trace, addr, false))
+ if (!consume_entry(cookie, addr, false))
return -EINVAL;
}
@@ -132,39 +85,9 @@ __save_stack_trace_reliable(struct stack_trace *trace,
if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
return -EINVAL;
-success:
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
-
return 0;
}
-/*
- * This function returns an error if it detects any unreliable features of the
- * stack. Otherwise it guarantees that the stack trace is reliable.
- *
- * If the task is not 'current', the caller *must* ensure the task is inactive.
- */
-int save_stack_trace_tsk_reliable(struct task_struct *tsk,
- struct stack_trace *trace)
-{
- int ret;
-
- /*
- * If the task doesn't have a stack (e.g., a zombie), the stack is
- * "reliably" empty.
- */
- if (!try_get_task_stack(tsk))
- return 0;
-
- ret = __save_stack_trace_reliable(trace, tsk);
-
- put_task_stack(tsk);
-
- return ret;
-}
-#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
-
/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
struct stack_frame_user {
@@ -189,15 +112,15 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
return ret;
}
-static inline void __save_stack_trace_user(struct stack_trace *trace)
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+ const struct pt_regs *regs)
{
- const struct pt_regs *regs = task_pt_regs(current);
const void __user *fp = (const void __user *)regs->bp;
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = regs->ip;
+ if (!consume_entry(cookie, regs->ip, false))
+ return;
- while (trace->nr_entries < trace->max_entries) {
+ while (1) {
struct stack_frame_user frame;
frame.next_fp = NULL;
@@ -207,8 +130,8 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
if ((unsigned long)fp < regs->sp)
break;
if (frame.ret_addr) {
- trace->entries[trace->nr_entries++] =
- frame.ret_addr;
+ if (!consume_entry(cookie, frame.ret_addr, false))
+ return;
}
if (fp == frame.next_fp)
break;
@@ -216,14 +139,3 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
}
}
-void save_stack_trace_user(struct stack_trace *trace)
-{
- /*
- * Trace user stack if we are not a kernel thread
- */
- if (current->mm) {
- __save_stack_trace_user(trace);
- }
- if (trace->nr_entries < trace->max_entries)
- trace->entries[trace->nr_entries++] = ULONG_MAX;
-}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index a092b6b40c6b..6a38717d179c 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -369,7 +369,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
preempt_disable();
tsk->thread.sp0 += 16;
- if (static_cpu_has(X86_FEATURE_SEP)) {
+ if (boot_cpu_has(X86_FEATURE_SEP)) {
tsk->thread.sysenter_cs = 0;
refresh_sysenter_cs(&tsk->thread);
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a5af9a7c4be4..4d1517022a14 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -362,7 +362,7 @@ SECTIONS
.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
__bss_start = .;
*(.bss..page_aligned)
- *(.bss)
+ *(BSS_MAIN)
BSS_DECRYPTED
. = ALIGN(PAGE_SIZE);
__bss_stop = .;