summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile6
-rw-r--r--arch/x86/kernel/acpi/cppc.c2
-rw-r--r--arch/x86/kernel/acpi/cstate.c4
-rw-r--r--arch/x86/kernel/alternative.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c10
-rw-r--r--arch/x86/kernel/cpu/feat_ctl.c2
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c103
-rw-r--r--arch/x86/kernel/devicetree.c26
-rw-r--r--arch/x86/kernel/idt.c2
-rw-r--r--arch/x86/kernel/irq.c4
-rw-r--r--arch/x86/kernel/kexec-bzimage64.c4
-rw-r--r--arch/x86/kernel/kprobes/common.h2
-rw-r--r--arch/x86/kernel/kprobes/core.c98
-rw-r--r--arch/x86/kernel/kvm.c4
-rw-r--r--arch/x86/kernel/machine_kexec_64.c3
-rw-r--r--arch/x86/kernel/reboot.c4
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/smp.c2
-rw-r--r--arch/x86/kernel/vmcore_info_32.c (renamed from arch/x86/kernel/crash_core_32.c)2
-rw-r--r--arch/x86/kernel/vmcore_info_64.c (renamed from arch/x86/kernel/crash_core_64.c)2
20 files changed, 168 insertions, 116 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d0c744cb2a0e..74077694da7d 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -100,11 +100,11 @@ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
obj-$(CONFIG_X86_TSC) += trace_clock.o
obj-$(CONFIG_TRACING) += trace.o
obj-$(CONFIG_RETHOOK) += rethook.o
-obj-$(CONFIG_CRASH_CORE) += crash_core_$(BITS).o
+obj-$(CONFIG_VMCORE_INFO) += vmcore_info_$(BITS).o
obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o
-obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o
+obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o
obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o
-obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
+obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o crash.o
obj-y += kprobes/
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_X86_32) += doublefault_32.o
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index 8d8752b44f11..ff8f25faca3d 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -20,7 +20,7 @@ bool cpc_supported_by_cpu(void)
(boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f)))
return true;
else if (boot_cpu_data.x86 == 0x17 &&
- boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f)
+ boot_cpu_data.x86_model >= 0x30 && boot_cpu_data.x86_model <= 0x7f)
return true;
return boot_cpu_has(X86_FEATURE_CPPC);
}
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 401808b47af3..f3ffd0a3a012 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -131,8 +131,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
/* Check whether this particular cx_type (in CST) is supported or not */
- cstate_type = ((cx->address >> MWAIT_SUBSTATE_SIZE) &
- MWAIT_CSTATE_MASK) + 1;
+ cstate_type = (((cx->address >> MWAIT_SUBSTATE_SIZE) &
+ MWAIT_CSTATE_MASK) + 1) & MWAIT_CSTATE_MASK;
edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE);
num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ff6e32ec8259..45a280f2161c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1804,7 +1804,7 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
* restoring the previous mm.
*/
if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
- leave_mm(smp_processor_id());
+ leave_mm();
temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
switch_mm_irqs_off(NULL, mm, current);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3282a747b645..6d8677e80ddb 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -864,11 +864,11 @@ static bool cpu_has_zenbleed_microcode(void)
u32 good_rev = 0;
switch (boot_cpu_data.x86_model) {
- case 0x30 ... 0x3f: good_rev = 0x0830107a; break;
- case 0x60 ... 0x67: good_rev = 0x0860010b; break;
- case 0x68 ... 0x6f: good_rev = 0x08608105; break;
- case 0x70 ... 0x7f: good_rev = 0x08701032; break;
- case 0xa0 ... 0xaf: good_rev = 0x08a00008; break;
+ case 0x30 ... 0x3f: good_rev = 0x0830107b; break;
+ case 0x60 ... 0x67: good_rev = 0x0860010c; break;
+ case 0x68 ... 0x6f: good_rev = 0x08608107; break;
+ case 0x70 ... 0x7f: good_rev = 0x08701033; break;
+ case 0xa0 ... 0xaf: good_rev = 0x08a00009; break;
default:
return false;
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 03851240c3e3..1640ae76548f 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -72,6 +72,8 @@ static void init_vmx_capabilities(struct cpuinfo_x86 *c)
c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_AD);
if (ept & VMX_EPT_1GB_PAGE_BIT)
c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_1GB);
+ if (ept & VMX_EPT_PAGE_WALK_5_BIT)
+ c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_5LEVEL);
/* Synthetic APIC features that are aggregates of multiple features. */
if ((c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) &&
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 45e0e70e238c..e0fd57a8ba84 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -45,70 +45,70 @@ bool hyperv_paravisor_present __ro_after_init;
EXPORT_SYMBOL_GPL(hyperv_paravisor_present);
#if IS_ENABLED(CONFIG_HYPERV)
-static inline unsigned int hv_get_nested_reg(unsigned int reg)
+static inline unsigned int hv_get_nested_msr(unsigned int reg)
{
- if (hv_is_sint_reg(reg))
- return reg - HV_REGISTER_SINT0 + HV_REGISTER_NESTED_SINT0;
+ if (hv_is_sint_msr(reg))
+ return reg - HV_X64_MSR_SINT0 + HV_X64_MSR_NESTED_SINT0;
switch (reg) {
- case HV_REGISTER_SIMP:
- return HV_REGISTER_NESTED_SIMP;
- case HV_REGISTER_SIEFP:
- return HV_REGISTER_NESTED_SIEFP;
- case HV_REGISTER_SVERSION:
- return HV_REGISTER_NESTED_SVERSION;
- case HV_REGISTER_SCONTROL:
- return HV_REGISTER_NESTED_SCONTROL;
- case HV_REGISTER_EOM:
- return HV_REGISTER_NESTED_EOM;
+ case HV_X64_MSR_SIMP:
+ return HV_X64_MSR_NESTED_SIMP;
+ case HV_X64_MSR_SIEFP:
+ return HV_X64_MSR_NESTED_SIEFP;
+ case HV_X64_MSR_SVERSION:
+ return HV_X64_MSR_NESTED_SVERSION;
+ case HV_X64_MSR_SCONTROL:
+ return HV_X64_MSR_NESTED_SCONTROL;
+ case HV_X64_MSR_EOM:
+ return HV_X64_MSR_NESTED_EOM;
default:
return reg;
}
}
-u64 hv_get_non_nested_register(unsigned int reg)
+u64 hv_get_non_nested_msr(unsigned int reg)
{
u64 value;
- if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present)
+ if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present)
hv_ivm_msr_read(reg, &value);
else
rdmsrl(reg, value);
return value;
}
-EXPORT_SYMBOL_GPL(hv_get_non_nested_register);
+EXPORT_SYMBOL_GPL(hv_get_non_nested_msr);
-void hv_set_non_nested_register(unsigned int reg, u64 value)
+void hv_set_non_nested_msr(unsigned int reg, u64 value)
{
- if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) {
+ if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) {
hv_ivm_msr_write(reg, value);
/* Write proxy bit via wrmsl instruction */
- if (hv_is_sint_reg(reg))
+ if (hv_is_sint_msr(reg))
wrmsrl(reg, value | 1 << 20);
} else {
wrmsrl(reg, value);
}
}
-EXPORT_SYMBOL_GPL(hv_set_non_nested_register);
+EXPORT_SYMBOL_GPL(hv_set_non_nested_msr);
-u64 hv_get_register(unsigned int reg)
+u64 hv_get_msr(unsigned int reg)
{
if (hv_nested)
- reg = hv_get_nested_reg(reg);
+ reg = hv_get_nested_msr(reg);
- return hv_get_non_nested_register(reg);
+ return hv_get_non_nested_msr(reg);
}
-EXPORT_SYMBOL_GPL(hv_get_register);
+EXPORT_SYMBOL_GPL(hv_get_msr);
-void hv_set_register(unsigned int reg, u64 value)
+void hv_set_msr(unsigned int reg, u64 value)
{
if (hv_nested)
- reg = hv_get_nested_reg(reg);
+ reg = hv_get_nested_msr(reg);
- hv_set_non_nested_register(reg, value);
+ hv_set_non_nested_msr(reg, value);
}
-EXPORT_SYMBOL_GPL(hv_set_register);
+EXPORT_SYMBOL_GPL(hv_set_msr);
static void (*vmbus_handler)(void);
static void (*hv_stimer0_handler)(void);
@@ -209,7 +209,9 @@ static void hv_machine_shutdown(void)
if (kexec_in_progress)
hyperv_cleanup();
}
+#endif /* CONFIG_KEXEC_CORE */
+#ifdef CONFIG_CRASH_DUMP
static void hv_machine_crash_shutdown(struct pt_regs *regs)
{
if (hv_crash_handler)
@@ -221,7 +223,7 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
/* Disable the hypercall page when there is only 1 active CPU. */
hyperv_cleanup();
}
-#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_CRASH_DUMP */
#endif /* CONFIG_HYPERV */
static uint32_t __init ms_hyperv_platform(void)
@@ -350,13 +352,24 @@ static void __init reduced_hw_init(void)
x86_init.irqs.pre_vector_init = x86_init_noop;
}
+int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
+{
+ unsigned int hv_max_functions;
+
+ hv_max_functions = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS);
+ if (hv_max_functions < HYPERV_CPUID_VERSION) {
+ pr_err("%s: Could not detect Hyper-V version\n", __func__);
+ return -ENODEV;
+ }
+
+ cpuid(HYPERV_CPUID_VERSION, &info->eax, &info->ebx, &info->ecx, &info->edx);
+
+ return 0;
+}
+
static void __init ms_hyperv_init_platform(void)
{
int hv_max_functions_eax;
- int hv_host_info_eax;
- int hv_host_info_ebx;
- int hv_host_info_ecx;
- int hv_host_info_edx;
#ifdef CONFIG_PARAVIRT
pv_info.name = "Hyper-V";
@@ -407,21 +420,6 @@ static void __init ms_hyperv_init_platform(void)
pr_info("Hyper-V: running on a nested hypervisor\n");
}
- /*
- * Extract host information.
- */
- if (hv_max_functions_eax >= HYPERV_CPUID_VERSION) {
- hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION);
- hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION);
- hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION);
- hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION);
-
- pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n",
- hv_host_info_ebx >> 16, hv_host_info_ebx & 0xFFFF,
- hv_host_info_eax, hv_host_info_edx & 0xFFFFFF,
- hv_host_info_ecx, hv_host_info_edx >> 24);
- }
-
if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
x86_platform.calibrate_tsc = hv_get_tsc_khz;
@@ -454,7 +452,7 @@ static void __init ms_hyperv_init_platform(void)
/* To be supported: more work is required. */
ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE;
- /* HV_REGISTER_CRASH_CTL is unsupported. */
+ /* HV_MSR_CRASH_CTL is unsupported. */
ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
/* Don't trust Hyper-V's TLB-flushing hypercalls. */
@@ -495,10 +493,14 @@ static void __init ms_hyperv_init_platform(void)
no_timer_check = 1;
#endif
-#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
+#if IS_ENABLED(CONFIG_HYPERV)
+#if defined(CONFIG_KEXEC_CORE)
machine_ops.shutdown = hv_machine_shutdown;
+#endif
+#if defined(CONFIG_CRASH_DUMP)
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
#endif
+#endif
if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
/*
* Writing to synthetic MSR 0x40000118 updates/changes the
@@ -642,6 +644,7 @@ const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
.init.x2apic_available = ms_hyperv_x2apic_available,
.init.msi_ext_dest_id = ms_hyperv_msi_ext_dest_id,
.init.init_platform = ms_hyperv_init_platform,
+ .init.guest_late_init = ms_hyperv_late_init,
#ifdef CONFIG_AMD_MEM_ENCRYPT
.runtime.sev_es_hcall_prepare = hv_sev_es_hcall_prepare,
.runtime.sev_es_hcall_finish = hv_sev_es_hcall_finish,
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 4aeafe63521b..003e0298f46a 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -283,22 +283,24 @@ void __init x86_flattree_get_config(void)
u32 size, map_len;
void *dt;
- if (!initial_dtb)
- return;
-
- map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
+ if (initial_dtb) {
+ map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
+
+ dt = early_memremap(initial_dtb, map_len);
+ size = fdt_totalsize(dt);
+ if (map_len < size) {
+ early_memunmap(dt, map_len);
+ dt = early_memremap(initial_dtb, size);
+ map_len = size;
+ }
- dt = early_memremap(initial_dtb, map_len);
- size = fdt_totalsize(dt);
- if (map_len < size) {
- early_memunmap(dt, map_len);
- dt = early_memremap(initial_dtb, size);
- map_len = size;
+ early_init_dt_verify(dt);
}
- early_init_dt_verify(dt);
unflatten_and_copy_device_tree();
- early_memunmap(dt, map_len);
+
+ if (initial_dtb)
+ early_memunmap(dt, map_len);
}
#endif
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 0cd53fa8c65d..fc37c8d83daf 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -153,7 +153,7 @@ static const __initconst struct idt_data apic_idts[] = {
#ifdef CONFIG_X86_LOCAL_APIC
INTG(LOCAL_TIMER_VECTOR, asm_sysvec_apic_timer_interrupt),
INTG(X86_PLATFORM_IPI_VECTOR, asm_sysvec_x86_platform_ipi),
-# ifdef CONFIG_HAVE_KVM
+# if IS_ENABLED(CONFIG_KVM)
INTG(POSTED_INTR_VECTOR, asm_sysvec_kvm_posted_intr_ipi),
INTG(POSTED_INTR_WAKEUP_VECTOR, asm_sysvec_kvm_posted_intr_wakeup_ipi),
INTG(POSTED_INTR_NESTED_VECTOR, asm_sysvec_kvm_posted_intr_nested_ipi),
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 11761c124545..35fde0107901 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -164,7 +164,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
-#ifdef CONFIG_HAVE_KVM
+#if IS_ENABLED(CONFIG_KVM)
seq_printf(p, "%*s: ", prec, "PIN");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
@@ -290,7 +290,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_x86_platform_ipi)
}
#endif
-#ifdef CONFIG_HAVE_KVM
+#if IS_ENABLED(CONFIG_KVM)
static void dummy_handler(void) {}
static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index cde167b0ea92..68530fad05f7 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -263,11 +263,13 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
memset(&params->hd0_info, 0, sizeof(params->hd0_info));
memset(&params->hd1_info, 0, sizeof(params->hd1_info));
+#ifdef CONFIG_CRASH_DUMP
if (image->type == KEXEC_TYPE_CRASH) {
ret = crash_setup_memmap_entries(image, params);
if (ret)
return ret;
} else
+#endif
setup_e820_entries(params);
nr_e820_entries = params->e820_entries;
@@ -433,12 +435,14 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
return ERR_PTR(-EINVAL);
}
+#ifdef CONFIG_CRASH_DUMP
/* Allocate and load backup region */
if (image->type == KEXEC_TYPE_CRASH) {
ret = crash_load_segments(image);
if (ret)
return ERR_PTR(ret);
}
+#endif
/*
* Load purgatory. For 64bit entry point, purgatory code can be
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c993521d4933..e772276f5aa9 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -78,7 +78,7 @@
#endif
/* Ensure if the instruction can be boostable */
-extern int can_boost(struct insn *insn, void *orig_addr);
+extern bool can_boost(struct insn *insn, void *orig_addr);
/* Recover instruction if given address is probed */
extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a0ce46c0a2d8..091b3ab76a18 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -137,14 +137,14 @@ NOKPROBE_SYMBOL(synthesize_relcall);
* Returns non-zero if INSN is boostable.
* RIP relative instructions are adjusted at copying time in 64 bits mode
*/
-int can_boost(struct insn *insn, void *addr)
+bool can_boost(struct insn *insn, void *addr)
{
kprobe_opcode_t opcode;
insn_byte_t prefix;
int i;
if (search_exception_tables((unsigned long)addr))
- return 0; /* Page fault may occur on this address. */
+ return false; /* Page fault may occur on this address. */
/* 2nd-byte opcode */
if (insn->opcode.nbytes == 2)
@@ -152,7 +152,7 @@ int can_boost(struct insn *insn, void *addr)
(unsigned long *)twobyte_is_boostable);
if (insn->opcode.nbytes != 1)
- return 0;
+ return false;
for_each_insn_prefix(insn, i, prefix) {
insn_attr_t attr;
@@ -160,7 +160,7 @@ int can_boost(struct insn *insn, void *addr)
attr = inat_get_opcode_attribute(prefix);
/* Can't boost Address-size override prefix and CS override prefix */
if (prefix == 0x2e || inat_is_address_size_prefix(attr))
- return 0;
+ return false;
}
opcode = insn->opcode.bytes[0];
@@ -169,24 +169,35 @@ int can_boost(struct insn *insn, void *addr)
case 0x62: /* bound */
case 0x70 ... 0x7f: /* Conditional jumps */
case 0x9a: /* Call far */
- case 0xc0 ... 0xc1: /* Grp2 */
case 0xcc ... 0xce: /* software exceptions */
- case 0xd0 ... 0xd3: /* Grp2 */
case 0xd6: /* (UD) */
case 0xd8 ... 0xdf: /* ESC */
case 0xe0 ... 0xe3: /* LOOP*, JCXZ */
case 0xe8 ... 0xe9: /* near Call, JMP */
case 0xeb: /* Short JMP */
case 0xf0 ... 0xf4: /* LOCK/REP, HLT */
+ /* ... are not boostable */
+ return false;
+ case 0xc0 ... 0xc1: /* Grp2 */
+ case 0xd0 ... 0xd3: /* Grp2 */
+ /*
+ * AMD uses nnn == 110 as SHL/SAL, but Intel makes it reserved.
+ */
+ return X86_MODRM_REG(insn->modrm.bytes[0]) != 0b110;
case 0xf6 ... 0xf7: /* Grp3 */
+ /* AMD uses nnn == 001 as TEST, but Intel makes it reserved. */
+ return X86_MODRM_REG(insn->modrm.bytes[0]) != 0b001;
case 0xfe: /* Grp4 */
- /* ... are not boostable */
- return 0;
+ /* Only INC and DEC are boostable */
+ return X86_MODRM_REG(insn->modrm.bytes[0]) == 0b000 ||
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 0b001;
case 0xff: /* Grp5 */
- /* Only indirect jmp is boostable */
- return X86_MODRM_REG(insn->modrm.bytes[0]) == 4;
+ /* Only INC, DEC, and indirect JMP are boostable */
+ return X86_MODRM_REG(insn->modrm.bytes[0]) == 0b000 ||
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 0b001 ||
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 0b100;
default:
- return 1;
+ return true;
}
}
@@ -252,21 +263,40 @@ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long add
return __recover_probed_insn(buf, addr);
}
-/* Check if paddr is at an instruction boundary */
-static int can_probe(unsigned long paddr)
+/* Check if insn is INT or UD */
+static inline bool is_exception_insn(struct insn *insn)
+{
+ /* UD uses 0f escape */
+ if (insn->opcode.bytes[0] == 0x0f) {
+ /* UD0 / UD1 / UD2 */
+ return insn->opcode.bytes[1] == 0xff ||
+ insn->opcode.bytes[1] == 0xb9 ||
+ insn->opcode.bytes[1] == 0x0b;
+ }
+
+ /* INT3 / INT n / INTO / INT1 */
+ return insn->opcode.bytes[0] == 0xcc ||
+ insn->opcode.bytes[0] == 0xcd ||
+ insn->opcode.bytes[0] == 0xce ||
+ insn->opcode.bytes[0] == 0xf1;
+}
+
+/*
+ * Check if paddr is at an instruction boundary and that instruction can
+ * be probed
+ */
+static bool can_probe(unsigned long paddr)
{
unsigned long addr, __addr, offset = 0;
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
- return 0;
+ return false;
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr) {
- int ret;
-
/*
* Check if the instruction has been modified by another
* kprobe, in which case we replace the breakpoint by the
@@ -277,11 +307,10 @@ static int can_probe(unsigned long paddr)
*/
__addr = recover_probed_instruction(buf, addr);
if (!__addr)
- return 0;
+ return false;
- ret = insn_decode_kernel(&insn, (void *)__addr);
- if (ret < 0)
- return 0;
+ if (insn_decode_kernel(&insn, (void *)__addr) < 0)
+ return false;
#ifdef CONFIG_KGDB
/*
@@ -290,10 +319,26 @@ static int can_probe(unsigned long paddr)
*/
if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
kgdb_has_hit_break(addr))
- return 0;
+ return false;
#endif
addr += insn.length;
}
+
+ /* Check if paddr is at an instruction boundary */
+ if (addr != paddr)
+ return false;
+
+ __addr = recover_probed_instruction(buf, addr);
+ if (!__addr)
+ return false;
+
+ if (insn_decode_kernel(&insn, (void *)__addr) < 0)
+ return false;
+
+ /* INT and UD are special and should not be kprobed */
+ if (is_exception_insn(&insn))
+ return false;
+
if (IS_ENABLED(CONFIG_CFI_CLANG)) {
/*
* The compiler generates the following instruction sequence
@@ -308,13 +353,6 @@ static int can_probe(unsigned long paddr)
* Also, these movl and addl are used for showing expected
* type. So those must not be touched.
*/
- __addr = recover_probed_instruction(buf, addr);
- if (!__addr)
- return 0;
-
- if (insn_decode_kernel(&insn, (void *)__addr) < 0)
- return 0;
-
if (insn.opcode.value == 0xBA)
offset = 12;
else if (insn.opcode.value == 0x3)
@@ -324,11 +362,11 @@ static int can_probe(unsigned long paddr)
/* This movl/addl is used for decoding CFI. */
if (is_cfi_trap(addr + offset))
- return 0;
+ return false;
}
out:
- return (addr == paddr);
+ return true;
}
/* If x86 supports IBT (ENDBR) it must be skipped. */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 101a7c1bf200..4cadfd606e8e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -770,7 +770,7 @@ static struct notifier_block kvm_pv_reboot_nb = {
* won't be valid. In cases like kexec, in which you install a new kernel, this
* means a random memory location will be kept being written.
*/
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
static void kvm_crash_shutdown(struct pt_regs *regs)
{
kvm_guest_cpu_offline(true);
@@ -853,7 +853,7 @@ static void __init kvm_guest_init(void)
kvm_guest_cpu_init();
#endif
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
machine_ops.crash_shutdown = kvm_crash_shutdown;
#endif
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index bc0a5348b4a6..b180d8e497c3 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -508,6 +508,8 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
}
#endif /* CONFIG_KEXEC_FILE */
+#ifdef CONFIG_CRASH_DUMP
+
static int
kexec_mark_range(unsigned long start, unsigned long end, bool protect)
{
@@ -552,6 +554,7 @@ void arch_kexec_unprotect_crashkres(void)
{
kexec_mark_crashkres(false);
}
+#endif
/*
* During a traditional boot under SME, SME will encrypt the kernel,
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 830425e6d38e..f3130f762784 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -796,7 +796,7 @@ struct machine_ops machine_ops __ro_after_init = {
.emergency_restart = native_machine_emergency_restart,
.restart = native_machine_restart,
.halt = native_machine_halt,
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
.crash_shutdown = native_machine_crash_shutdown,
#endif
};
@@ -826,7 +826,7 @@ void machine_halt(void)
machine_ops.halt();
}
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
void machine_crash_shutdown(struct pt_regs *regs)
{
machine_ops.crash_shutdown(regs);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 46d5a8c520ad..3e1e96efadfe 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -471,7 +471,7 @@ static void __init arch_reserve_crashkernel(void)
bool high = false;
int ret;
- if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+ if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
return;
ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 2908e063d7d8..18266cc3d98c 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -286,7 +286,7 @@ struct smp_ops smp_ops = {
.smp_cpus_done = native_smp_cpus_done,
.stop_other_cpus = native_stop_other_cpus,
-#if defined(CONFIG_KEXEC_CORE)
+#if defined(CONFIG_CRASH_DUMP)
.crash_stop_other_cpus = kdump_nmi_shootdown_cpus,
#endif
.smp_send_reschedule = native_smp_send_reschedule,
diff --git a/arch/x86/kernel/crash_core_32.c b/arch/x86/kernel/vmcore_info_32.c
index 8a89c109e20a..5995a749288a 100644
--- a/arch/x86/kernel/crash_core_32.c
+++ b/arch/x86/kernel/vmcore_info_32.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
#include <linux/pgtable.h>
#include <asm/setup.h>
diff --git a/arch/x86/kernel/crash_core_64.c b/arch/x86/kernel/vmcore_info_64.c
index 7d255f882afe..0dec7d868754 100644
--- a/arch/x86/kernel/crash_core_64.c
+++ b/arch/x86/kernel/vmcore_info_64.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
#include <linux/pgtable.h>
#include <asm/setup.h>