summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/boot.c3
-rw-r--r--arch/x86/kernel/alternative.c14
-rw-r--r--arch/x86/kernel/apm_32.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c66
-rw-r--r--arch/x86/kernel/cpu/bugs.c96
-rw-r--r--arch/x86/kernel/cpu/common.c25
-rw-r--r--arch/x86/kernel/cpu/intel.c27
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c3
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c2
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c6
-rw-r--r--arch/x86/kernel/cpu/scattered.c1
-rw-r--r--arch/x86/kernel/devicetree.c6
-rw-r--r--arch/x86/kernel/dumpstack.c2
-rw-r--r--arch/x86/kernel/early-quirks.c87
-rw-r--r--arch/x86/kernel/irq.c9
-rw-r--r--arch/x86/kernel/kvm.c49
-rw-r--r--arch/x86/kernel/process_64.c4
-rw-r--r--arch/x86/kernel/ptrace.c2
-rw-r--r--arch/x86/kernel/relocate_kernel_64.S8
-rw-r--r--arch/x86/kernel/signal.c2
20 files changed, 269 insertions, 144 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ec3a286163c3..2aa92094b59d 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -36,6 +36,7 @@
#include <linux/ioport.h>
#include <linux/pci.h>
#include <linux/efi-bgrt.h>
+#include <linux/serial_core.h>
#include <asm/e820/api.h>
#include <asm/irqdomain.h>
@@ -1625,6 +1626,8 @@ int __init acpi_boot_init(void)
if (!acpi_noirq)
x86_init.pci.init = pci_acpi_init;
+ /* Do not enable ACPI SPCR console by default */
+ acpi_parse_spcr(earlycon_acpi_spcr_enable, false);
return 0;
}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 30571fdaaf6f..a481763a3776 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(char *str)
}
__setup("noreplace-smp", setup_noreplace_smp);
-#ifdef CONFIG_PARAVIRT
-static int __initdata_or_module noreplace_paravirt = 0;
-
-static int __init setup_noreplace_paravirt(char *str)
-{
- noreplace_paravirt = 1;
- return 1;
-}
-__setup("noreplace-paravirt", setup_noreplace_paravirt);
-#endif
-
#define DPRINTK(fmt, args...) \
do { \
if (debug_alternative) \
@@ -599,9 +588,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
struct paravirt_patch_site *p;
char insnbuf[MAX_PATCH_LEN];
- if (noreplace_paravirt)
- return;
-
for (p = start; p < end; p++) {
unsigned int used;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index ab1865342002..dc0ca8e29c75 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -2389,6 +2389,7 @@ static int __init apm_init(void)
if (HZ != 100)
idle_period = (idle_period * HZ) / 100;
if (idle_threshold < 100) {
+ cpuidle_poll_state_init(&apm_idle_driver);
if (!cpuidle_register_driver(&apm_idle_driver))
if (cpuidle_register_device(&apm_cpuidle_device))
cpuidle_unregister_driver(&apm_idle_driver);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ea831c858195..5bddbdcbc4a3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -556,6 +556,51 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
}
}
+static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
+{
+ u64 msr;
+
+ /*
+ * BIOS support is required for SME and SEV.
+ * For SME: If BIOS has enabled SME then adjust x86_phys_bits by
+ * the SME physical address space reduction value.
+ * If BIOS has not enabled SME then don't advertise the
+ * SME feature (set in scattered.c).
+ * For SEV: If BIOS has not enabled SEV then don't advertise the
+ * SEV feature (set in scattered.c).
+ *
+ * In all cases, since support for SME and SEV requires long mode,
+ * don't advertise the feature under CONFIG_X86_32.
+ */
+ if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
+ /* Check if memory encryption is enabled */
+ rdmsrl(MSR_K8_SYSCFG, msr);
+ if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+ goto clear_all;
+
+ /*
+ * Always adjust physical address bits. Even though this
+ * will be a value above 32-bits this is still done for
+ * CONFIG_X86_32 so that accurate values are reported.
+ */
+ c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f;
+
+ if (IS_ENABLED(CONFIG_X86_32))
+ goto clear_all;
+
+ rdmsrl(MSR_K7_HWCR, msr);
+ if (!(msr & MSR_K7_HWCR_SMMLOCK))
+ goto clear_sev;
+
+ return;
+
+clear_all:
+ clear_cpu_cap(c, X86_FEATURE_SME);
+clear_sev:
+ clear_cpu_cap(c, X86_FEATURE_SEV);
+ }
+}
+
static void early_init_amd(struct cpuinfo_x86 *c)
{
u32 dummy;
@@ -627,26 +672,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (cpu_has_amd_erratum(c, amd_erratum_400))
set_cpu_bug(c, X86_BUG_AMD_E400);
- /*
- * BIOS support is required for SME. If BIOS has enabled SME then
- * adjust x86_phys_bits by the SME physical address space reduction
- * value. If BIOS has not enabled SME then don't advertise the
- * feature (set in scattered.c). Also, since the SME support requires
- * long mode, don't advertise the feature under CONFIG_X86_32.
- */
- if (cpu_has(c, X86_FEATURE_SME)) {
- u64 msr;
-
- /* Check if SME is enabled */
- rdmsrl(MSR_K8_SYSCFG, msr);
- if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) {
- c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f;
- if (IS_ENABLED(CONFIG_X86_32))
- clear_cpu_cap(c, X86_FEATURE_SME);
- } else {
- clear_cpu_cap(c, X86_FEATURE_SME);
- }
- }
+ early_detect_mem_encrypt(c);
}
static void init_amd_k8(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 3bfb2b23d79c..71949bf2de5a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -103,7 +103,7 @@ bool retpoline_module_ok(bool has_retpoline)
if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline)
return true;
- pr_err("System may be vunerable to spectre v2\n");
+ pr_err("System may be vulnerable to spectre v2\n");
spectre_v2_bad_module = true;
return false;
}
@@ -119,13 +119,13 @@ static inline const char *spectre_v2_module_string(void) { return ""; }
static void __init spec2_print_if_insecure(const char *reason)
{
if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
- pr_info("%s\n", reason);
+ pr_info("%s selected on command line.\n", reason);
}
static void __init spec2_print_if_secure(const char *reason)
{
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
- pr_info("%s\n", reason);
+ pr_info("%s selected on command line.\n", reason);
}
static inline bool retp_compiler(void)
@@ -140,42 +140,68 @@ static inline bool match_option(const char *arg, int arglen, const char *opt)
return len == arglen && !strncmp(arg, opt, len);
}
+static const struct {
+ const char *option;
+ enum spectre_v2_mitigation_cmd cmd;
+ bool secure;
+} mitigation_options[] = {
+ { "off", SPECTRE_V2_CMD_NONE, false },
+ { "on", SPECTRE_V2_CMD_FORCE, true },
+ { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false },
+ { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false },
+ { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
+ { "auto", SPECTRE_V2_CMD_AUTO, false },
+};
+
static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
{
char arg[20];
- int ret;
-
- ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
- sizeof(arg));
- if (ret > 0) {
- if (match_option(arg, ret, "off")) {
- goto disable;
- } else if (match_option(arg, ret, "on")) {
- spec2_print_if_secure("force enabled on command line.");
- return SPECTRE_V2_CMD_FORCE;
- } else if (match_option(arg, ret, "retpoline")) {
- spec2_print_if_insecure("retpoline selected on command line.");
- return SPECTRE_V2_CMD_RETPOLINE;
- } else if (match_option(arg, ret, "retpoline,amd")) {
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
- pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
- return SPECTRE_V2_CMD_AUTO;
- }
- spec2_print_if_insecure("AMD retpoline selected on command line.");
- return SPECTRE_V2_CMD_RETPOLINE_AMD;
- } else if (match_option(arg, ret, "retpoline,generic")) {
- spec2_print_if_insecure("generic retpoline selected on command line.");
- return SPECTRE_V2_CMD_RETPOLINE_GENERIC;
- } else if (match_option(arg, ret, "auto")) {
+ int ret, i;
+ enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO;
+
+ if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+ return SPECTRE_V2_CMD_NONE;
+ else {
+ ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
+ sizeof(arg));
+ if (ret < 0)
return SPECTRE_V2_CMD_AUTO;
+
+ for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) {
+ if (!match_option(arg, ret, mitigation_options[i].option))
+ continue;
+ cmd = mitigation_options[i].cmd;
+ break;
}
+
+ if (i >= ARRAY_SIZE(mitigation_options)) {
+ pr_err("unknown option (%s). Switching to AUTO select\n",
+ mitigation_options[i].option);
+ return SPECTRE_V2_CMD_AUTO;
+ }
+ }
+
+ if ((cmd == SPECTRE_V2_CMD_RETPOLINE ||
+ cmd == SPECTRE_V2_CMD_RETPOLINE_AMD ||
+ cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) &&
+ !IS_ENABLED(CONFIG_RETPOLINE)) {
+ pr_err("%s selected but not compiled in. Switching to AUTO select\n",
+ mitigation_options[i].option);
+ return SPECTRE_V2_CMD_AUTO;
}
- if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+ if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+ pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
return SPECTRE_V2_CMD_AUTO;
-disable:
- spec2_print_if_insecure("disabled on command line.");
- return SPECTRE_V2_CMD_NONE;
+ }
+
+ if (mitigation_options[i].secure)
+ spec2_print_if_secure(mitigation_options[i].option);
+ else
+ spec2_print_if_insecure(mitigation_options[i].option);
+
+ return cmd;
}
/* Check for Skylake-like CPUs (for RSB handling) */
@@ -213,10 +239,10 @@ static void __init spectre_v2_select_mitigation(void)
return;
case SPECTRE_V2_CMD_FORCE:
- /* FALLTRHU */
case SPECTRE_V2_CMD_AUTO:
- goto retpoline_auto;
-
+ if (IS_ENABLED(CONFIG_RETPOLINE))
+ goto retpoline_auto;
+ break;
case SPECTRE_V2_CMD_RETPOLINE_AMD:
if (IS_ENABLED(CONFIG_RETPOLINE))
goto retpoline_amd;
@@ -297,7 +323,7 @@ ssize_t cpu_show_spectre_v1(struct device *dev,
{
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
return sprintf(buf, "Not affected\n");
- return sprintf(buf, "Vulnerable\n");
+ return sprintf(buf, "Mitigation: __user pointer sanitization\n");
}
ssize_t cpu_show_spectre_v2(struct device *dev,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c7c996a692fd..d63f4b5706e4 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -750,6 +750,26 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
}
}
+static void init_speculation_control(struct cpuinfo_x86 *c)
+{
+ /*
+ * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
+ * and they also have a different bit for STIBP support. Also,
+ * a hypervisor might have set the individual AMD bits even on
+ * Intel CPUs, for finer-grained selection of what's available.
+ *
+ * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
+ * features, which are visible in /proc/cpuinfo and used by the
+ * kernel. So set those accordingly from the Intel bits.
+ */
+ if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
+ set_cpu_cap(c, X86_FEATURE_IBRS);
+ set_cpu_cap(c, X86_FEATURE_IBPB);
+ }
+ if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
+ set_cpu_cap(c, X86_FEATURE_STIBP);
+}
+
void get_cpu_cap(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
@@ -844,6 +864,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
init_scattered_cpuid_features(c);
+ init_speculation_control(c);
/*
* Clear/Set all flags overridden by options, after probe.
@@ -879,7 +900,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#endif
}
-static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
+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 },
@@ -892,7 +913,7 @@ static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
{}
};
-static const __initdata struct x86_cpu_id cpu_no_meltdown[] = {
+static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
{ X86_VENDOR_AMD },
{}
};
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 6936d14d4c77..319bf989fad1 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -175,28 +175,17 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64))
c->microcode = intel_get_microcode_revision();
- /*
- * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
- * and they also have a different bit for STIBP support. Also,
- * a hypervisor might have set the individual AMD bits even on
- * Intel CPUs, for finer-grained selection of what's available.
- */
- if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
- set_cpu_cap(c, X86_FEATURE_IBRS);
- set_cpu_cap(c, X86_FEATURE_IBPB);
- }
- if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
- set_cpu_cap(c, X86_FEATURE_STIBP);
-
/* Now if any of them are set, check the blacklist and clear the lot */
- if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
+ if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) ||
+ cpu_has(c, X86_FEATURE_INTEL_STIBP) ||
+ cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) {
pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n");
- clear_cpu_cap(c, X86_FEATURE_IBRS);
- clear_cpu_cap(c, X86_FEATURE_IBPB);
- clear_cpu_cap(c, X86_FEATURE_STIBP);
- clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
- clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP);
+ setup_clear_cpu_cap(X86_FEATURE_IBRS);
+ setup_clear_cpu_cap(X86_FEATURE_IBPB);
+ setup_clear_cpu_cap(X86_FEATURE_STIBP);
+ setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
+ setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ba1f9555fbc5..3a8e88a611eb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -14,7 +14,6 @@
#include <linux/capability.h>
#include <linux/miscdevice.h>
#include <linux/ratelimit.h>
-#include <linux/kallsyms.h>
#include <linux/rcupdate.h>
#include <linux/kobject.h>
#include <linux/uaccess.h>
@@ -235,7 +234,7 @@ static void __print_mce(struct mce *m)
m->cs, m->ip);
if (m->cs == __KERNEL_CS)
- print_symbol("{%s}", m->ip);
+ pr_cont("{%pS}", (void *)m->ip);
pr_cont("\n");
}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index e4fc595cd6ea..319dd65f98a2 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -560,7 +560,7 @@ static ssize_t pf_show(struct device *dev,
return sprintf(buf, "0x%x\n", uci->cpu_sig.pf);
}
-static DEVICE_ATTR(reload, 0200, NULL, reload_store);
+static DEVICE_ATTR_WO(reload);
static DEVICE_ATTR(version, 0400, version_show, NULL);
static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 85eb5fc180c8..9340f41ce8d3 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -251,6 +251,12 @@ static void __init ms_hyperv_init_platform(void)
hyperv_setup_mmu_ops();
/* Setup the IDT for hypervisor callback */
alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
+ /* Setup the IDT for reenlightenment notifications */
+ if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT)
+ alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
+ hyperv_reenlightenment_vector);
+
#endif
}
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 4075d2be5357..772c219b6889 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -30,6 +30,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
{ X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 },
+ { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 },
{ 0, 0, 0, 0, 0 }
};
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 76e07698e6d1..25de5f6ca997 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,7 +2,6 @@
/*
* Architecture specific OF callbacks.
*/
-#include <linux/bootmem.h>
#include <linux/export.h>
#include <linux/io.h>
#include <linux/interrupt.h>
@@ -39,11 +38,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
BUG();
}
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
- return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
-}
-
void __init add_dtb(u64 data)
{
initial_dtb = data + offsetof(struct setup_data, data);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index afbecff161d1..a2d8a3908670 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -109,7 +109,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
struct stack_info stack_info = {0};
unsigned long visit_mask = 0;
int graph_idx = 0;
- bool partial;
+ bool partial = false;
printk("%sCall Trace:\n", log_lvl);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 1e82f787c160..bae0d32e327b 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -243,7 +243,7 @@ static void __init intel_remapping_check(int num, int slot, int func)
#define KB(x) ((x) * 1024UL)
#define MB(x) (KB (KB (x)))
-static size_t __init i830_tseg_size(void)
+static resource_size_t __init i830_tseg_size(void)
{
u8 esmramc = read_pci_config_byte(0, 0, 0, I830_ESMRAMC);
@@ -256,7 +256,7 @@ static size_t __init i830_tseg_size(void)
return KB(512);
}
-static size_t __init i845_tseg_size(void)
+static resource_size_t __init i845_tseg_size(void)
{
u8 esmramc = read_pci_config_byte(0, 0, 0, I845_ESMRAMC);
u8 tseg_size = esmramc & I845_TSEG_SIZE_MASK;
@@ -273,7 +273,7 @@ static size_t __init i845_tseg_size(void)
return 0;
}
-static size_t __init i85x_tseg_size(void)
+static resource_size_t __init i85x_tseg_size(void)
{
u8 esmramc = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC);
@@ -283,12 +283,12 @@ static size_t __init i85x_tseg_size(void)
return MB(1);
}
-static size_t __init i830_mem_size(void)
+static resource_size_t __init i830_mem_size(void)
{
return read_pci_config_byte(0, 0, 0, I830_DRB3) * MB(32);
}
-static size_t __init i85x_mem_size(void)
+static resource_size_t __init i85x_mem_size(void)
{
return read_pci_config_byte(0, 0, 1, I85X_DRB3) * MB(32);
}
@@ -297,36 +297,36 @@ static size_t __init i85x_mem_size(void)
* On 830/845/85x the stolen memory base isn't available in any
* register. We need to calculate it as TOM-TSEG_SIZE-stolen_size.
*/
-static phys_addr_t __init i830_stolen_base(int num, int slot, int func,
- size_t stolen_size)
+static resource_size_t __init i830_stolen_base(int num, int slot, int func,
+ resource_size_t stolen_size)
{
- return (phys_addr_t)i830_mem_size() - i830_tseg_size() - stolen_size;
+ return i830_mem_size() - i830_tseg_size() - stolen_size;
}
-static phys_addr_t __init i845_stolen_base(int num, int slot, int func,
- size_t stolen_size)
+static resource_size_t __init i845_stolen_base(int num, int slot, int func,
+ resource_size_t stolen_size)
{
- return (phys_addr_t)i830_mem_size() - i845_tseg_size() - stolen_size;
+ return i830_mem_size() - i845_tseg_size() - stolen_size;
}
-static phys_addr_t __init i85x_stolen_base(int num, int slot, int func,
- size_t stolen_size)
+static resource_size_t __init i85x_stolen_base(int num, int slot, int func,
+ resource_size_t stolen_size)
{
- return (phys_addr_t)i85x_mem_size() - i85x_tseg_size() - stolen_size;
+ return i85x_mem_size() - i85x_tseg_size() - stolen_size;
}
-static phys_addr_t __init i865_stolen_base(int num, int slot, int func,
- size_t stolen_size)
+static resource_size_t __init i865_stolen_base(int num, int slot, int func,
+ resource_size_t stolen_size)
{
u16 toud = 0;
toud = read_pci_config_16(0, 0, 0, I865_TOUD);
- return (phys_addr_t)(toud << 16) + i845_tseg_size();
+ return toud * KB(64) + i845_tseg_size();
}
-static phys_addr_t __init gen3_stolen_base(int num, int slot, int func,
- size_t stolen_size)
+static resource_size_t __init gen3_stolen_base(int num, int slot, int func,
+ resource_size_t stolen_size)
{
u32 bsm;
@@ -337,10 +337,10 @@ static phys_addr_t __init gen3_stolen_base(int num, int slot, int func,
*/
bsm = read_pci_config(num, slot, func, INTEL_BSM);
- return (phys_addr_t)bsm & INTEL_BSM_MASK;
+ return bsm & INTEL_BSM_MASK;
}
-static size_t __init i830_stolen_size(int num, int slot, int func)
+static resource_size_t __init i830_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
u16 gms;
@@ -361,7 +361,7 @@ static size_t __init i830_stolen_size(int num, int slot, int func)
return 0;
}
-static size_t __init gen3_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen3_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
u16 gms;
@@ -390,7 +390,7 @@ static size_t __init gen3_stolen_size(int num, int slot, int func)
return 0;
}
-static size_t __init gen6_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen6_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
u16 gms;
@@ -398,10 +398,10 @@ static size_t __init gen6_stolen_size(int num, int slot, int func)
gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
gms = (gmch_ctrl >> SNB_GMCH_GMS_SHIFT) & SNB_GMCH_GMS_MASK;
- return (size_t)gms * MB(32);
+ return gms * MB(32);
}
-static size_t __init gen8_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen8_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
u16 gms;
@@ -409,10 +409,10 @@ static size_t __init gen8_stolen_size(int num, int slot, int func)
gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
gms = (gmch_ctrl >> BDW_GMCH_GMS_SHIFT) & BDW_GMCH_GMS_MASK;
- return (size_t)gms * MB(32);
+ return gms * MB(32);
}
-static size_t __init chv_stolen_size(int num, int slot, int func)
+static resource_size_t __init chv_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
u16 gms;
@@ -426,14 +426,14 @@ static size_t __init chv_stolen_size(int num, int slot, int func)
* 0x17 to 0x1d: 4MB increments start at 36MB
*/
if (gms < 0x11)
- return (size_t)gms * MB(32);
+ return gms * MB(32);
else if (gms < 0x17)
- return (size_t)(gms - 0x11 + 2) * MB(4);
+ return (gms - 0x11) * MB(4) + MB(8);
else
- return (size_t)(gms - 0x17 + 9) * MB(4);
+ return (gms - 0x17) * MB(4) + MB(36);
}
-static size_t __init gen9_stolen_size(int num, int slot, int func)
+static resource_size_t __init gen9_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
u16 gms;
@@ -444,14 +444,15 @@ static size_t __init gen9_stolen_size(int num, int slot, int func)
/* 0x0 to 0xef: 32MB increments starting at 0MB */
/* 0xf0 to 0xfe: 4MB increments starting at 4MB */
if (gms < 0xf0)
- return (size_t)gms * MB(32);
+ return gms * MB(32);
else
- return (size_t)(gms - 0xf0 + 1) * MB(4);
+ return (gms - 0xf0) * MB(4) + MB(4);
}
struct intel_early_ops {
- size_t (*stolen_size)(int num, int slot, int func);
- phys_addr_t (*stolen_base)(int num, int slot, int func, size_t size);
+ resource_size_t (*stolen_size)(int num, int slot, int func);
+ resource_size_t (*stolen_base)(int num, int slot, int func,
+ resource_size_t size);
};
static const struct intel_early_ops i830_early_ops __initconst = {
@@ -527,16 +528,20 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
INTEL_SKL_IDS(&gen9_early_ops),
INTEL_BXT_IDS(&gen9_early_ops),
INTEL_KBL_IDS(&gen9_early_ops),
+ INTEL_CFL_IDS(&gen9_early_ops),
INTEL_GLK_IDS(&gen9_early_ops),
INTEL_CNL_IDS(&gen9_early_ops),
};
+struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0);
+EXPORT_SYMBOL(intel_graphics_stolen_res);
+
static void __init
intel_graphics_stolen(int num, int slot, int func,
const struct intel_early_ops *early_ops)
{
- phys_addr_t base, end;
- size_t size;
+ resource_size_t base, size;
+ resource_size_t end;
size = early_ops->stolen_size(num, slot, func);
base = early_ops->stolen_base(num, slot, func, size);
@@ -545,8 +550,12 @@ intel_graphics_stolen(int num, int slot, int func,
return;
end = base + size - 1;
- printk(KERN_INFO "Reserving Intel graphics memory at %pa-%pa\n",
- &base, &end);
+
+ intel_graphics_stolen_res.start = base;
+ intel_graphics_stolen_res.end = end;
+
+ printk(KERN_INFO "Reserving Intel graphics memory at %pR\n",
+ &intel_graphics_stolen_res);
/* Mark this space as reserved */
e820__range_add(base, size, E820_TYPE_RESERVED);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 68e1867cca80..45fb4d2565f8 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -142,6 +142,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_puts(p, " Hypervisor callback interrupts\n");
}
#endif
+#if IS_ENABLED(CONFIG_HYPERV)
+ if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) {
+ seq_printf(p, "%*s: ", prec, "HRE");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->irq_hv_reenlightenment_count);
+ seq_puts(p, " Hyper-V reenlightenment interrupts\n");
+ }
+#endif
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b40ffbf156c1..4e37d1a851a6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -498,6 +498,34 @@ static void __init kvm_apf_trap_init(void)
update_intr_gate(X86_TRAP_PF, async_page_fault);
}
+static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
+
+static void kvm_flush_tlb_others(const struct cpumask *cpumask,
+ const struct flush_tlb_info *info)
+{
+ u8 state;
+ int cpu;
+ struct kvm_steal_time *src;
+ struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+
+ cpumask_copy(flushmask, cpumask);
+ /*
+ * We have to call flush only on online vCPUs. And
+ * queue flush_on_enter for pre-empted vCPUs
+ */
+ for_each_cpu(cpu, flushmask) {
+ src = &per_cpu(steal_time, cpu);
+ state = READ_ONCE(src->preempted);
+ if ((state & KVM_VCPU_PREEMPTED)) {
+ if (try_cmpxchg(&src->preempted, &state,
+ state | KVM_VCPU_FLUSH_TLB))
+ __cpumask_clear_cpu(cpu, flushmask);
+ }
+ }
+
+ native_flush_tlb_others(flushmask, info);
+}
+
static void __init kvm_guest_init(void)
{
int i;
@@ -517,6 +545,9 @@ static void __init kvm_guest_init(void)
pv_time_ops.steal_clock = kvm_steal_clock;
}
+ if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+ pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
+
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apic_set_eoi_write(kvm_guest_apic_eoi_write);
@@ -598,6 +629,22 @@ static __init int activate_jump_labels(void)
}
arch_initcall(activate_jump_labels);
+static __init int kvm_setup_pv_tlb_flush(void)
+{
+ int cpu;
+
+ if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+ for_each_possible_cpu(cpu) {
+ zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+ }
+ pr_info("KVM setup pv remote TLB flush\n");
+ }
+
+ return 0;
+}
+arch_initcall(kvm_setup_pv_tlb_flush);
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
@@ -643,7 +690,7 @@ __visible bool __kvm_vcpu_is_preempted(long cpu)
{
struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
- return !!src->preempted;
+ return !!(src->preempted & KVM_VCPU_PREEMPTED);
}
PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c75466232016..9eb448c7859d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -557,7 +557,7 @@ static void __set_personality_x32(void)
* Pretend to come from a x32 execve.
*/
task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT;
- current->thread.status &= ~TS_COMPAT;
+ current_thread_info()->status &= ~TS_COMPAT;
#endif
}
@@ -571,7 +571,7 @@ static void __set_personality_ia32(void)
current->personality |= force_personality32;
/* Prepare the first "return" to user space */
task_pt_regs(current)->orig_ax = __NR_ia32_execve;
- current->thread.status |= TS_COMPAT;
+ current_thread_info()->status |= TS_COMPAT;
#endif
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index f37d18124648..ed5c4cdf0a34 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -935,7 +935,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value)
*/
regs->orig_ax = value;
if (syscall_get_nr(child, regs) >= 0)
- child->thread.status |= TS_I386_REGS_POKED;
+ child->thread_info.status |= TS_I386_REGS_POKED;
break;
case offsetof(struct user32, regs.eflags):
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 307d3bac5f04..11eda21eb697 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -68,6 +68,9 @@ relocate_kernel:
movq %cr4, %rax
movq %rax, CR4(%r11)
+ /* Save CR4. Required to enable the right paging mode later. */
+ movq %rax, %r13
+
/* zero out flags, and disable interrupts */
pushq $0
popfq
@@ -126,8 +129,13 @@ identity_mapped:
/*
* Set cr4 to a known state:
* - physical address extension enabled
+ * - 5-level paging, if it was enabled before
*/
movl $X86_CR4_PAE, %eax
+ testq $X86_CR4_LA57, %r13
+ jz 1f
+ orl $X86_CR4_LA57, %eax
+1:
movq %rax, %cr4
jmp 1f
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b9e00e8f1c9b..4cdc0b27ec82 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -787,7 +787,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
* than the tracee.
*/
#ifdef CONFIG_IA32_EMULATION
- if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
+ if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
return __NR_ia32_restart_syscall;
#endif
#ifdef CONFIG_X86_X32_ABI
generated by cgit (git 2.34.1) at 2024-06-08 09:25:35 +0000