summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/cpu/bugs.c147
-rw-r--r--arch/x86/kernel/cpu/common.c134
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c44
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c3
-rw-r--r--arch/x86/kernel/fpu/core.c6
-rw-r--r--arch/x86/kernel/ftrace.c32
-rw-r--r--arch/x86/kernel/irq_64.c19
-rw-r--r--arch/x86/kernel/kprobes/core.c22
-rw-r--r--arch/x86/kernel/nmi.c4
-rw-r--r--arch/x86/kernel/process_32.c7
-rw-r--r--arch/x86/kernel/process_64.c8
-rw-r--r--arch/x86/kernel/reboot.c21
-rw-r--r--arch/x86/kernel/signal.c29
-rw-r--r--arch/x86/kernel/tsc.c2
14 files changed, 373 insertions, 105 deletions
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5567705e0601..2769e0f5c686 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -26,6 +26,7 @@
#include <asm/vmx.h>
#include <asm/paravirt.h>
#include <asm/alternative.h>
+#include <asm/hypervisor.h>
#include <asm/pgtable.h>
#include <asm/set_memory.h>
#include <asm/intel-family.h>
@@ -34,6 +35,7 @@
static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
static void __init l1tf_select_mitigation(void);
+static void __init mds_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
u64 x86_spec_ctrl_base;
@@ -60,6 +62,13 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
/* Control unconditional IBPB in switch_mm() */
DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
+/* Control MDS CPU buffer clear before returning to user space */
+DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+EXPORT_SYMBOL_GPL(mds_user_clear);
+/* Control MDS CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+EXPORT_SYMBOL_GPL(mds_idle_clear);
+
void __init check_bugs(void)
{
identify_boot_cpu();
@@ -98,6 +107,10 @@ void __init check_bugs(void)
l1tf_select_mitigation();
+ mds_select_mitigation();
+
+ arch_smt_update();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -204,6 +217,61 @@ static void x86_amd_ssb_disable(void)
}
#undef pr_fmt
+#define pr_fmt(fmt) "MDS: " fmt
+
+/* Default mitigation for MDS-affected CPUs */
+static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL;
+static bool mds_nosmt __ro_after_init = false;
+
+static const char * const mds_strings[] = {
+ [MDS_MITIGATION_OFF] = "Vulnerable",
+ [MDS_MITIGATION_FULL] = "Mitigation: Clear CPU buffers",
+ [MDS_MITIGATION_VMWERV] = "Vulnerable: Clear CPU buffers attempted, no microcode",
+};
+
+static void __init mds_select_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
+ mds_mitigation = MDS_MITIGATION_OFF;
+ return;
+ }
+
+ if (mds_mitigation == MDS_MITIGATION_FULL) {
+ if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+ mds_mitigation = MDS_MITIGATION_VMWERV;
+
+ static_branch_enable(&mds_user_clear);
+
+ if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
+ (mds_nosmt || cpu_mitigations_auto_nosmt()))
+ cpu_smt_disable(false);
+ }
+
+ pr_info("%s\n", mds_strings[mds_mitigation]);
+}
+
+static int __init mds_cmdline(char *str)
+{
+ if (!boot_cpu_has_bug(X86_BUG_MDS))
+ return 0;
+
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ mds_mitigation = MDS_MITIGATION_OFF;
+ else if (!strcmp(str, "full"))
+ mds_mitigation = MDS_MITIGATION_FULL;
+ else if (!strcmp(str, "full,nosmt")) {
+ mds_mitigation = MDS_MITIGATION_FULL;
+ mds_nosmt = true;
+ }
+
+ return 0;
+}
+early_param("mds", mds_cmdline);
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
@@ -427,7 +495,8 @@ 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));
@@ -559,9 +628,6 @@ specv2_set_mode:
/* Set up IBPB and STIBP depending on the general spectre V2 command */
spectre_v2_user_select_mitigation(cmd);
-
- /* Enable STIBP if appropriate */
- arch_smt_update();
}
static void update_stibp_msr(void * __unused)
@@ -595,6 +661,31 @@ static void update_indir_branch_cond(void)
static_branch_disable(&switch_to_cond_stibp);
}
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+/* Update the static key controlling the MDS CPU buffer clear in idle */
+static void update_mds_branch_idle(void)
+{
+ /*
+ * Enable the idle clearing if SMT is active on CPUs which are
+ * affected only by MSBDS and not any other MDS variant.
+ *
+ * The other variants cannot be mitigated when SMT is enabled, so
+ * clearing the buffers on idle just to prevent the Store Buffer
+ * repartitioning leak would be a window dressing exercise.
+ */
+ if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
+ return;
+
+ if (sched_smt_active())
+ static_branch_enable(&mds_idle_clear);
+ else
+ static_branch_disable(&mds_idle_clear);
+}
+
+#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+
void arch_smt_update(void)
{
/* Enhanced IBRS implies STIBP. No update required. */
@@ -615,6 +706,17 @@ void arch_smt_update(void)
break;
}
+ switch (mds_mitigation) {
+ case MDS_MITIGATION_FULL:
+ case MDS_MITIGATION_VMWERV:
+ if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
+ pr_warn_once(MDS_MSG_SMT);
+ update_mds_branch_idle();
+ break;
+ case MDS_MITIGATION_OFF:
+ break;
+ }
+
mutex_unlock(&spec_ctrl_mutex);
}
@@ -656,7 +758,8 @@ 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",
@@ -977,6 +1080,11 @@ 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) {
@@ -1005,7 +1113,7 @@ static void __init l1tf_select_mitigation(void)
pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
half_pa);
pr_info("However, doing so will make a part of your RAM unusable.\n");
- pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
+ pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html might help you decide.\n");
return;
}
@@ -1038,6 +1146,7 @@ static int __init l1tf_cmdline(char *str)
early_param("l1tf", l1tf_cmdline);
#undef pr_fmt
+#define pr_fmt(fmt) fmt
#ifdef CONFIG_SYSFS
@@ -1076,6 +1185,23 @@ static ssize_t l1tf_show_state(char *buf)
}
#endif
+static ssize_t mds_show_state(char *buf)
+{
+ if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+ return sprintf(buf, "%s; SMT Host state unknown\n",
+ mds_strings[mds_mitigation]);
+ }
+
+ if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) {
+ return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+ (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" :
+ sched_smt_active() ? "mitigated" : "disabled"));
+ }
+
+ return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+ sched_smt_active() ? "vulnerable" : "disabled");
+}
+
static char *stibp_state(void)
{
if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1137,6 +1263,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
return l1tf_show_state(buf);
break;
+
+ case X86_BUG_MDS:
+ return mds_show_state(buf);
+
default:
break;
}
@@ -1168,4 +1298,9 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b
{
return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
}
+
+ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
+}
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 51e49f6fe8e1..ebe547b1ffce 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -899,85 +899,95 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
c->x86_cache_bits = c->x86_phys_bits;
}
-static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_CENTAUR, 5 },
- { X86_VENDOR_INTEL, 5 },
- { X86_VENDOR_NSC, 5 },
- { X86_VENDOR_ANY, 4 },
+#define NO_SPECULATION BIT(0)
+#define NO_MELTDOWN BIT(1)
+#define NO_SSB BIT(2)
+#define NO_L1TF BIT(3)
+#define NO_MDS BIT(4)
+#define MSBDS_ONLY BIT(5)
+
+#define VULNWL(_vendor, _family, _model, _whitelist) \
+ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
+
+#define VULNWL_INTEL(model, whitelist) \
+ VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
+
+#define VULNWL_AMD(family, whitelist) \
+ VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
+
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+ VULNWL(ANY, 4, X86_MODEL_ANY, NO_SPECULATION),
+ VULNWL(CENTAUR, 5, X86_MODEL_ANY, NO_SPECULATION),
+ VULNWL(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION),
+ VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION),
+
+ /* Intel Family 6 */
+ VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION),
+
+ VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY),
+
+ VULNWL_INTEL(CORE_YONAH, NO_SSB),
+
+ VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY),
+
+ VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF),
+ VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF),
+ VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF),
+
+ /* AMD Family 0xf - 0x12 */
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+
+ /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
{}
};
-static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
- { X86_VENDOR_AMD },
- {}
-};
-
-static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
- { X86_VENDOR_CENTAUR, 5, },
- { X86_VENDOR_INTEL, 5, },
- { X86_VENDOR_NSC, 5, },
- { X86_VENDOR_AMD, 0x12, },
- { X86_VENDOR_AMD, 0x11, },
- { X86_VENDOR_AMD, 0x10, },
- { X86_VENDOR_AMD, 0xf, },
- { X86_VENDOR_ANY, 4, },
- {}
-};
+static bool __init cpu_matches(unsigned long which)
+{
+ const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
-static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
- /* in addition to cpu_no_speculation */
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
- {}
-};
+ return m && !!(m->driver_data & which);
+}
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = 0;
+ if (cpu_matches(NO_SPECULATION))
+ return;
+
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+
if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
- if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
- !(ia32_cap & ARCH_CAP_SSB_NO) &&
+ if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
- if (x86_match_cpu(cpu_no_speculation))
- return;
-
- setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
- setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
-
if (ia32_cap & ARCH_CAP_IBRS_ALL)
setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
- if (x86_match_cpu(cpu_no_meltdown))
+ if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+ setup_force_cpu_bug(X86_BUG_MDS);
+ if (cpu_matches(MSBDS_ONLY))
+ setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
+ }
+
+ if (cpu_matches(NO_MELTDOWN))
return;
/* Rogue Data Cache Load? No! */
@@ -986,7 +996,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
- if (x86_match_cpu(cpu_no_l1tf))
+ if (cpu_matches(NO_L1TF))
return;
setup_force_cpu_bug(X86_BUG_L1TF);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 54874e2b1d32..4f3be91f0b0b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -701,19 +701,49 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
barrier();
m.status = mce_rdmsrl(msr_ops.status(i));
+
+ /* If this entry is not valid, ignore it */
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.
- *
- * TBD do the same check for MCI_STATUS_EN here?
+ * If we are logging everything (at CPU online) or this
+ * is a corrected error, then we must log it.
*/
- if (!(flags & MCP_UC) &&
- (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
- continue;
+ if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
+ goto log_it;
+
+ /*
+ * Newer Intel systems that support software error
+ * recovery need to make additional checks. Other
+ * CPUs should skip over uncorrected errors, but log
+ * everything else.
+ */
+ if (!mca_cfg.ser) {
+ if (m.status & MCI_STATUS_UC)
+ continue;
+ goto log_it;
+ }
+
+ /* Log "not enabled" (speculative) errors */
+ if (!(m.status & MCI_STATUS_EN))
+ goto log_it;
+
+ /*
+ * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+ * UC == 1 && PCC == 0 && S == 0
+ */
+ if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
+ goto log_it;
+
+ /*
+ * Skip anything else. Presumption is that our read of this
+ * bank is racing with a machine check. Leave the log alone
+ * for do_machine_check() to deal with it.
+ */
+ continue;
+log_it:
error_seen = true;
mce_read_aux(&m, i);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 387a8f44fba1..b6b44017cf16 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -418,8 +418,9 @@ static int do_microcode_update(const void __user *buf, size_t size)
if (ustate == UCODE_ERROR) {
error = -1;
break;
- } else if (ustate == UCODE_OK)
+ } else if (ustate == UCODE_NEW) {
apply_microcode_on_target(cpu);
+ }
}
return error;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2ea85b32421a..2e5003fef51a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -93,7 +93,7 @@ bool irq_fpu_usable(void)
}
EXPORT_SYMBOL(irq_fpu_usable);
-void __kernel_fpu_begin(void)
+static void __kernel_fpu_begin(void)
{
struct fpu *fpu = &current->thread.fpu;
@@ -111,9 +111,8 @@ void __kernel_fpu_begin(void)
__cpu_invalidate_fpregs_state();
}
}
-EXPORT_SYMBOL(__kernel_fpu_begin);
-void __kernel_fpu_end(void)
+static void __kernel_fpu_end(void)
{
struct fpu *fpu = &current->thread.fpu;
@@ -122,7 +121,6 @@ void __kernel_fpu_end(void)
kernel_fpu_enable();
}
-EXPORT_SYMBOL(__kernel_fpu_end);
void kernel_fpu_begin(void)
{
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 7acb87cb2da8..c020ba4b7eb6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -30,6 +30,7 @@
#include <asm/sections.h>
#include <asm/ftrace.h>
#include <asm/nops.h>
+#include <asm/text-patching.h>
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -229,6 +230,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
}
static unsigned long ftrace_update_func;
+static unsigned long ftrace_update_func_call;
static int update_ftrace_func(unsigned long ip, void *new)
{
@@ -257,6 +259,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
unsigned char *new;
int ret;
+ ftrace_update_func_call = (unsigned long)func;
+
new = ftrace_call_replace(ip, (unsigned long)func);
ret = update_ftrace_func(ip, new);
@@ -292,13 +296,28 @@ int ftrace_int3_handler(struct pt_regs *regs)
if (WARN_ON_ONCE(!regs))
return 0;
- ip = regs->ip - 1;
- if (!ftrace_location(ip) && !is_ftrace_caller(ip))
- return 0;
+ ip = regs->ip - INT3_INSN_SIZE;
- regs->ip += MCOUNT_INSN_SIZE - 1;
+#ifdef CONFIG_X86_64
+ if (ftrace_location(ip)) {
+ int3_emulate_call(regs, (unsigned long)ftrace_regs_caller);
+ return 1;
+ } else if (is_ftrace_caller(ip)) {
+ if (!ftrace_update_func_call) {
+ int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
+ return 1;
+ }
+ int3_emulate_call(regs, ftrace_update_func_call);
+ return 1;
+ }
+#else
+ if (ftrace_location(ip) || is_ftrace_caller(ip)) {
+ int3_emulate_jmp(regs, ip + CALL_INSN_SIZE);
+ return 1;
+ }
+#endif
- return 1;
+ return 0;
}
static int ftrace_write(unsigned long ip, const char *val, int size)
@@ -869,6 +888,8 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
func = ftrace_ops_get_func(ops);
+ ftrace_update_func_call = (unsigned long)func;
+
/* Do a safe modify in case the trampoline is executing */
new = ftrace_call_replace(ip, (unsigned long)func);
ret = update_ftrace_func(ip, new);
@@ -965,6 +986,7 @@ static int ftrace_mod_jmp(unsigned long ip, void *func)
{
unsigned char *new;
+ ftrace_update_func_call = 0UL;
new = ftrace_jmp_replace(ip, (unsigned long)func);
return update_ftrace_func(ip, new);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 0469cd078db1..b50ac9c7397b 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,9 +26,18 @@ int sysctl_panic_on_stackoverflow;
/*
* Probabilistic stack overflow check:
*
- * Only check the stack in process context, because everything else
- * runs on the big interrupt stacks. Checking reliably is too expensive,
- * so we just check from interrupts.
+ * Regular device interrupts can enter on the following stacks:
+ *
+ * - User stack
+ *
+ * - Kernel task stack
+ *
+ * - Interrupt stack if a device driver reenables interrupts
+ * which should only happen in really old drivers.
+ *
+ * - Debug IST stack
+ *
+ * All other contexts are invalid.
*/
static inline void stack_overflow_check(struct pt_regs *regs)
{
@@ -53,8 +62,8 @@ static inline void stack_overflow_check(struct pt_regs *regs)
return;
oist = this_cpu_ptr(&orig_ist);
- estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
- estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
+ estack_bottom = (u64)oist->ist[DEBUG_STACK];
+ estack_top = estack_bottom - DEBUG_STKSZ + STACK_TOP_MARGIN;
if (regs->sp >= estack_top && regs->sp <= estack_bottom)
return;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 56cf6c263254..9d7bb8de2917 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -744,11 +744,16 @@ asm(
NOKPROBE_SYMBOL(kretprobe_trampoline);
STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
+static struct kprobe kretprobe_kprobe = {
+ .addr = (void *)kretprobe_trampoline,
+};
+
/*
* Called from kretprobe_trampoline
*/
__visible __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;
@@ -758,6 +763,17 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
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 */
@@ -833,10 +849,9 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
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);
@@ -852,6 +867,9 @@ __visible __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/nmi.c b/arch/x86/kernel/nmi.c
index 35aafc95e4b8..d796a7f6a74a 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -34,6 +34,7 @@
#include <asm/x86_init.h>
#include <asm/reboot.h>
#include <asm/cache.h>
+#include <asm/nospec-branch.h>
#define CREATE_TRACE_POINTS
#include <trace/events/nmi.h>
@@ -533,6 +534,9 @@ nmi_restart:
write_cr2(this_cpu_read(nmi_cr2));
if (this_cpu_dec_return(nmi_state))
goto nmi_restart;
+
+ if (user_mode(regs))
+ mds_user_clear_cpu_buffers();
}
NOKPROBE_SYMBOL(do_nmi);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c2df91eab573..df6bb5f8ab2a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -132,6 +132,13 @@ 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 ec63d6be5e02..d1dfd1397b46 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -278,6 +278,14 @@ 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;
+
+ /*
+ * 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/reboot.c b/arch/x86/kernel/reboot.c
index 2126b9d27c34..c663d5fcff2e 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();
@@ -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/signal.c b/arch/x86/kernel/signal.c
index 4cdc0b27ec82..01741834fd6a 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -131,16 +131,6 @@ 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 */
@@ -149,6 +139,15 @@ 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();
@@ -460,6 +459,7 @@ 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);
@@ -472,9 +472,11 @@ 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);
@@ -540,6 +542,7 @@ 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;
@@ -554,9 +557,11 @@ 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);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 36d02484e384..5d681fe6d352 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -620,7 +620,7 @@ unsigned long native_calibrate_tsc(void)
case INTEL_FAM6_KABYLAKE_DESKTOP:
crystal_khz = 24000; /* 24.0 MHz */
break;
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
crystal_khz = 25000; /* 25.0 MHz */
break;
case INTEL_FAM6_ATOM_GOLDMONT:
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-04 16:43:46 +0000