summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include/asm')
-rw-r--r--arch/x86/include/asm/Kbuild1
-rw-r--r--arch/x86/include/asm/acpi.h14
-rw-r--r--arch/x86/include/asm/alternative.h34
-rw-r--r--arch/x86/include/asm/amd_nb.h2
-rw-r--r--arch/x86/include/asm/apic.h46
-rw-r--r--arch/x86/include/asm/apicdef.h276
-rw-r--r--arch/x86/include/asm/barrier.h18
-rw-r--r--arch/x86/include/asm/bitops.h11
-rw-r--r--arch/x86/include/asm/boot.h47
-rw-r--r--arch/x86/include/asm/cacheinfo.h3
-rw-r--r--arch/x86/include/asm/cfi.h126
-rw-r--r--arch/x86/include/asm/cmpxchg.h6
-rw-r--r--arch/x86/include/asm/coco.h5
-rw-r--r--arch/x86/include/asm/cpu.h26
-rw-r--r--arch/x86/include/asm/cpufeature.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h16
-rw-r--r--arch/x86/include/asm/crash_core.h42
-rw-r--r--arch/x86/include/asm/current.h1
-rw-r--r--arch/x86/include/asm/debugreg.h1
-rw-r--r--arch/x86/include/asm/desc_defs.h78
-rw-r--r--arch/x86/include/asm/efi.h32
-rw-r--r--arch/x86/include/asm/elf.h3
-rw-r--r--arch/x86/include/asm/extable_fixup_types.h2
-rw-r--r--arch/x86/include/asm/fb.h10
-rw-r--r--arch/x86/include/asm/fpu/api.h3
-rw-r--r--arch/x86/include/asm/fpu/types.h4
-rw-r--r--arch/x86/include/asm/hw_irq.h6
-rw-r--r--arch/x86/include/asm/i8259.h2
-rw-r--r--arch/x86/include/asm/ia32.h34
-rw-r--r--arch/x86/include/asm/idtentry.h4
-rw-r--r--arch/x86/include/asm/init.h2
-rw-r--r--arch/x86/include/asm/intel-family.h4
-rw-r--r--arch/x86/include/asm/io.h8
-rw-r--r--arch/x86/include/asm/iosf_mbi.h2
-rw-r--r--arch/x86/include/asm/irq_work.h1
-rw-r--r--arch/x86/include/asm/jump_label.h6
-rw-r--r--arch/x86/include/asm/kexec.h2
-rw-r--r--arch/x86/include/asm/kmsan.h17
-rw-r--r--arch/x86/include/asm/kprobes.h2
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h6
-rw-r--r--arch/x86/include/asm/kvm-x86-pmu-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h151
-rw-r--r--arch/x86/include/asm/kvm_page_track.h67
-rw-r--r--arch/x86/include/asm/linkage.h15
-rw-r--r--arch/x86/include/asm/local.h33
-rw-r--r--arch/x86/include/asm/mce.h6
-rw-r--r--arch/x86/include/asm/mem_encrypt.h4
-rw-r--r--arch/x86/include/asm/microcode.h21
-rw-r--r--arch/x86/include/asm/mman.h15
-rw-r--r--arch/x86/include/asm/mmu_context.h3
-rw-r--r--arch/x86/include/asm/mpspec.h2
-rw-r--r--arch/x86/include/asm/mshyperv.h6
-rw-r--r--arch/x86/include/asm/msr-index.h31
-rw-r--r--arch/x86/include/asm/mwait.h20
-rw-r--r--arch/x86/include/asm/nospec-branch.h75
-rw-r--r--arch/x86/include/asm/numa.h7
-rw-r--r--arch/x86/include/asm/paravirt.h83
-rw-r--r--arch/x86/include/asm/paravirt_types.h103
-rw-r--r--arch/x86/include/asm/percpu.h2
-rw-r--r--arch/x86/include/asm/perf_event.h13
-rw-r--r--arch/x86/include/asm/pgtable.h23
-rw-r--r--arch/x86/include/asm/pgtable_64.h2
-rw-r--r--arch/x86/include/asm/preempt.h1
-rw-r--r--arch/x86/include/asm/processor.h83
-rw-r--r--arch/x86/include/asm/prom.h5
-rw-r--r--arch/x86/include/asm/proto.h7
-rw-r--r--arch/x86/include/asm/qspinlock_paravirt.h4
-rw-r--r--arch/x86/include/asm/reboot.h7
-rw-r--r--arch/x86/include/asm/rmwcc.h2
-rw-r--r--arch/x86/include/asm/setup.h3
-rw-r--r--arch/x86/include/asm/shared/tdx.h96
-rw-r--r--arch/x86/include/asm/smp.h5
-rw-r--r--arch/x86/include/asm/sparsemem.h2
-rw-r--r--arch/x86/include/asm/spec-ctrl.h11
-rw-r--r--arch/x86/include/asm/special_insns.h2
-rw-r--r--arch/x86/include/asm/svm.h12
-rw-r--r--arch/x86/include/asm/syscall.h6
-rw-r--r--arch/x86/include/asm/syscall_wrapper.h59
-rw-r--r--arch/x86/include/asm/tdx.h51
-rw-r--r--arch/x86/include/asm/text-patching.h16
-rw-r--r--arch/x86/include/asm/topology.h12
-rw-r--r--arch/x86/include/asm/traps.h1
-rw-r--r--arch/x86/include/asm/uaccess.h12
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h2
-rw-r--r--arch/x86/include/asm/vdso/gettimeofday.h4
-rw-r--r--arch/x86/include/asm/virtext.h154
-rw-r--r--arch/x86/include/asm/vmx.h2
-rw-r--r--arch/x86/include/asm/x86_init.h2
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h46
-rw-r--r--arch/x86/include/asm/xen/interface_64.h2
90 files changed, 1140 insertions, 1058 deletions
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4f1ce5fc4e19..a192bdea69e2 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -10,5 +10,4 @@ generated-y += unistd_64_x32.h
generated-y += xen-hypercalls.h
generic-y += early_ioremap.h
-generic-y += export.h
generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
#include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
if (!cpu_has(c, X86_FEATURE_MWAIT) ||
boot_option_idle_override == IDLE_NOMWAIT)
*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+ if (xen_initial_domain()) {
+ /*
+ * When Linux is running as Xen dom0, the hypervisor is the
+ * entity in charge of the processor power management, and so
+ * Xen needs to check the OS capabilities reported in the
+ * processor capabilities buffer matches what the hypervisor
+ * driver supports.
+ */
+ xen_sanitize_proc_cap_bits(cap);
+ }
}
static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 9c4da699e11a..fcd20c6dc7f9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -10,6 +10,9 @@
#define ALT_FLAG_NOT (1 << 0)
#define ALT_NOT(feature) ((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature))
+#define ALT_FLAG_DIRECT_CALL (1 << 1)
+#define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature))
+#define ALT_CALL_ALWAYS ALT_DIRECT_CALL(X86_FEATURE_ALWAYS)
#ifndef __ASSEMBLY__
@@ -58,7 +61,7 @@
#define ANNOTATE_IGNORE_ALTERNATIVE \
"999:\n\t" \
".pushsection .discard.ignore_alts\n\t" \
- ".long 999b - .\n\t" \
+ ".long 999b\n\t" \
".popsection\n\t"
/*
@@ -86,6 +89,8 @@ struct alt_instr {
u8 replacementlen; /* length of new instruction */
} __packed;
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+
/*
* Debug flag that can be tested to see whether alternative
* instructions were patched in already:
@@ -101,11 +106,10 @@ extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
s32 *start_cfi, s32 *end_cfi);
struct module;
-struct paravirt_patch_site;
struct callthunk_sites {
s32 *call_start, *call_end;
- struct paravirt_patch_site *pv_start, *pv_end;
+ struct alt_instr *alt_start, *alt_end;
};
#ifdef CONFIG_CALL_THUNKS
@@ -150,6 +154,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
}
#endif /* CONFIG_SMP */
+#define ALT_CALL_INSTR "call BUG_func"
+
#define b_replacement(num) "664"#num
#define e_replacement(num) "665"#num
@@ -330,6 +336,22 @@ static inline int alternatives_text_reserved(void *start, void *end)
*/
#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+/* Macro for creating assembler functions avoiding any C magic. */
+#define DEFINE_ASM_FUNC(func, instr, sec) \
+ asm (".pushsection " #sec ", \"ax\"\n" \
+ ".global " #func "\n\t" \
+ ".type " #func ", @function\n\t" \
+ ASM_FUNC_ALIGN "\n" \
+ #func ":\n\t" \
+ ASM_ENDBR \
+ instr "\n\t" \
+ ASM_RET \
+ ".size " #func ", . - " #func "\n\t" \
+ ".popsection")
+
+void BUG_func(void);
+void nop_func(void);
+
#else /* __ASSEMBLY__ */
#ifdef CONFIG_SMP
@@ -352,7 +374,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
.macro ANNOTATE_IGNORE_ALTERNATIVE
.Lannotate_\@:
.pushsection .discard.ignore_alts
- .long .Lannotate_\@ - .
+ .long .Lannotate_\@
.popsection
.endm
@@ -370,6 +392,10 @@ static inline int alternatives_text_reserved(void *start, void *end)
.byte \alt_len
.endm
+.macro ALT_CALL_INSTR
+ call BUG_func
+.endm
+
/*
* Define an alternative between two instructions. If @feature is
* present, early code in apply_alternatives() replaces @oldinstr with
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index ed0eaf65c437..5c37944c8a5e 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -104,7 +104,7 @@ static inline bool amd_gart_present(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
return false;
- /* GART present only on Fam15h, upto model 0fh */
+ /* GART present only on Fam15h, up to model 0fh */
if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
(boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
return true;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 5af4ec1a0f71..9d159b771dc8 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -54,7 +54,7 @@ extern int local_apic_timer_c2_ok;
extern bool apic_is_disabled;
extern unsigned int lapic_timer_period;
-extern int cpuid_to_apicid[];
+extern u32 cpuid_to_apicid[];
extern enum apic_intr_mode_id apic_intr_mode;
enum apic_intr_mode_id {
@@ -272,11 +272,10 @@ struct apic {
void (*send_IPI_all)(int vector);
void (*send_IPI_self)(int vector);
- enum apic_delivery_modes delivery_mode;
-
u32 disable_esr : 1,
dest_mode_logical : 1,
- x2apic_set_max_apicid : 1;
+ x2apic_set_max_apicid : 1,
+ nmi_to_offline_cpu : 1;
u32 (*calc_dest_apicid)(unsigned int cpu);
@@ -292,19 +291,19 @@ struct apic {
int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
bool (*apic_id_registered)(void);
- bool (*check_apicid_used)(physid_mask_t *map, int apicid);
+ bool (*check_apicid_used)(physid_mask_t *map, u32 apicid);
void (*init_apic_ldr)(void);
void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
- int (*cpu_present_to_apicid)(int mps_cpu);
- int (*phys_pkg_id)(int cpuid_apic, int index_msb);
+ u32 (*cpu_present_to_apicid)(int mps_cpu);
+ u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
- u32 (*get_apic_id)(unsigned long x);
- u32 (*set_apic_id)(unsigned int id);
+ u32 (*get_apic_id)(u32 id);
+ u32 (*set_apic_id)(u32 apicid);
/* wakeup_secondary_cpu */
- int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
/* wakeup secondary CPU using 64-bit wakeup point */
- int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
char *name;
};
@@ -322,8 +321,8 @@ struct apic_override {
void (*send_IPI_self)(int vector);
u64 (*icr_read)(void);
void (*icr_write)(u32 low, u32 high);
- int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
- int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
};
/*
@@ -493,16 +492,6 @@ static inline bool lapic_vector_set_in_irr(unsigned int vector)
return !!(irr & (1U << (vector % 32)));
}
-static inline unsigned default_get_apic_id(unsigned long x)
-{
- unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-
- if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
- return (x >> 24) & 0xFF;
- else
- return (x >> 24) & 0x0F;
-}
-
/*
* Warm reset vector position:
*/
@@ -517,9 +506,9 @@ extern void generic_bigsmp_probe(void);
extern struct apic apic_noop;
-static inline unsigned int read_apic_id(void)
+static inline u32 read_apic_id(void)
{
- unsigned int reg = apic_read(APIC_ID);
+ u32 reg = apic_read(APIC_ID);
return apic->get_apic_id(reg);
}
@@ -538,13 +527,14 @@ extern int default_apic_id_valid(u32 apicid);
extern u32 apic_default_calc_apicid(unsigned int cpu);
extern u32 apic_flat_calc_apicid(unsigned int cpu);
-extern bool default_check_apicid_used(physid_mask_t *map, int apicid);
extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
-extern int default_cpu_present_to_apicid(int mps_cpu);
+extern u32 default_cpu_present_to_apicid(int mps_cpu);
+
+void apic_send_nmi_to_offline_cpu(unsigned int cpu);
#else /* CONFIG_X86_LOCAL_APIC */
-static inline unsigned int read_apic_id(void) { return 0; }
+static inline u32 read_apic_id(void) { return 0; }
#endif /* !CONFIG_X86_LOCAL_APIC */
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 4b125e5b3187..094106b6a538 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -20,6 +20,13 @@
*/
#define IO_APIC_SLOT_SIZE 1024
+#define APIC_DELIVERY_MODE_FIXED 0
+#define APIC_DELIVERY_MODE_LOWESTPRIO 1
+#define APIC_DELIVERY_MODE_SMI 2
+#define APIC_DELIVERY_MODE_NMI 4
+#define APIC_DELIVERY_MODE_INIT 5
+#define APIC_DELIVERY_MODE_EXTINT 7
+
#define APIC_ID 0x20
#define APIC_LVR 0x30
@@ -165,279 +172,10 @@
#define APIC_CPUID(apicid) ((apicid) & XAPIC_DEST_CPUS_MASK)
#define NUM_APIC_CLUSTERS ((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT)
-#ifndef __ASSEMBLY__
-/*
- * the local APIC register structure, memory mapped. Not terribly well
- * tested, but we might eventually use this one in the future - the
- * problem why we cannot use it right now is the P5 APIC, it has an
- * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
- */
-#define u32 unsigned int
-
-struct local_apic {
-
-/*000*/ struct { u32 __reserved[4]; } __reserved_01;
-
-/*010*/ struct { u32 __reserved[4]; } __reserved_02;
-
-/*020*/ struct { /* APIC ID Register */
- u32 __reserved_1 : 24,
- phys_apic_id : 4,
- __reserved_2 : 4;
- u32 __reserved[3];
- } id;
-
-/*030*/ const
- struct { /* APIC Version Register */
- u32 version : 8,
- __reserved_1 : 8,
- max_lvt : 8,
- __reserved_2 : 8;
- u32 __reserved[3];
- } version;
-
-/*040*/ struct { u32 __reserved[4]; } __reserved_03;
-
-/*050*/ struct { u32 __reserved[4]; } __reserved_04;
-
-/*060*/ struct { u32 __reserved[4]; } __reserved_05;
-
-/*070*/ struct { u32 __reserved[4]; } __reserved_06;
-
-/*080*/ struct { /* Task Priority Register */
- u32 priority : 8,
- __reserved_1 : 24;
- u32 __reserved_2[3];
- } tpr;
-
-/*090*/ const
- struct { /* Arbitration Priority Register */
- u32 priority : 8,
- __reserved_1 : 24;
- u32 __reserved_2[3];
- } apr;
-
-/*0A0*/ const
- struct { /* Processor Priority Register */
- u32 priority : 8,
- __reserved_1 : 24;
- u32 __reserved_2[3];
- } ppr;
-
-/*0B0*/ struct { /* End Of Interrupt Register */
- u32 eoi;
- u32 __reserved[3];
- } eoi;
-
-/*0C0*/ struct { u32 __reserved[4]; } __reserved_07;
-
-/*0D0*/ struct { /* Logical Destination Register */
- u32 __reserved_1 : 24,
- logical_dest : 8;
- u32 __reserved_2[3];
- } ldr;
-
-/*0E0*/ struct { /* Destination Format Register */
- u32 __reserved_1 : 28,
- model : 4;
- u32 __reserved_2[3];
- } dfr;
-
-/*0F0*/ struct { /* Spurious Interrupt Vector Register */
- u32 spurious_vector : 8,
- apic_enabled : 1,
- focus_cpu : 1,
- __reserved_2 : 22;
- u32 __reserved_3[3];
- } svr;
-
-/*100*/ struct { /* In Service Register */
-/*170*/ u32 bitfield;
- u32 __reserved[3];
- } isr [8];
-
-/*180*/ struct { /* Trigger Mode Register */
-/*1F0*/ u32 bitfield;
- u32 __reserved[3];
- } tmr [8];
-
-/*200*/ struct { /* Interrupt Request Register */
-/*270*/ u32 bitfield;
- u32 __reserved[3];
- } irr [8];
-
-/*280*/ union { /* Error Status Register */
- struct {
- u32 send_cs_error : 1,
- receive_cs_error : 1,
- send_accept_error : 1,
- receive_accept_error : 1,
- __reserved_1 : 1,
- send_illegal_vector : 1,
- receive_illegal_vector : 1,
- illegal_register_address : 1,
- __reserved_2 : 24;
- u32 __reserved_3[3];
- } error_bits;
- struct {
- u32 errors;
- u32 __reserved_3[3];
- } all_errors;
- } esr;
-
-/*290*/ struct { u32 __reserved[4]; } __reserved_08;
-
-/*2A0*/ struct { u32 __reserved[4]; } __reserved_09;
-
-/*2B0*/ struct { u32 __reserved[4]; } __reserved_10;
-
-/*2C0*/ struct { u32 __reserved[4]; } __reserved_11;
-
-/*2D0*/ struct { u32 __reserved[4]; } __reserved_12;
-
-/*2E0*/ struct { u32 __reserved[4]; } __reserved_13;
-
-/*2F0*/ struct { u32 __reserved[4]; } __reserved_14;
-
-/*300*/ struct { /* Interrupt Command Register 1 */
- u32 vector : 8,
- delivery_mode : 3,
- destination_mode : 1,
- delivery_status : 1,
- __reserved_1 : 1,
- level : 1,
- trigger : 1,
- __reserved_2 : 2,
- shorthand : 2,
- __reserved_3 : 12;
- u32 __reserved_4[3];
- } icr1;
-
-/*310*/ struct { /* Interrupt Command Register 2 */
- union {
- u32 __reserved_1 : 24,
- phys_dest : 4,
- __reserved_2 : 4;
- u32 __reserved_3 : 24,
- logical_dest : 8;
- } dest;
- u32 __reserved_4[3];
- } icr2;
-
-/*320*/ struct { /* LVT - Timer */
- u32 vector : 8,
- __reserved_1 : 4,
- delivery_status : 1,
- __reserved_2 : 3,
- mask : 1,
- timer_mode : 1,
- __reserved_3 : 14;
- u32 __reserved_4[3];
- } lvt_timer;
-
-/*330*/ struct { /* LVT - Thermal Sensor */
- u32 vector : 8,
- delivery_mode : 3,
- __reserved_1 : 1,
- delivery_status : 1,
- __reserved_2 : 3,
- mask : 1,
- __reserved_3 : 15;
- u32 __reserved_4[3];
- } lvt_thermal;
-
-/*340*/ struct { /* LVT - Performance Counter */
- u32 vector : 8,
- delivery_mode : 3,
- __reserved_1 : 1,
- delivery_status : 1,
- __reserved_2 : 3,
- mask : 1,
- __reserved_3 : 15;
- u32 __reserved_4[3];
- } lvt_pc;
-
-/*350*/ struct { /* LVT - LINT0 */
- u32 vector : 8,
- delivery_mode : 3,
- __reserved_1 : 1,
- delivery_status : 1,
- polarity : 1,
- remote_irr : 1,
- trigger : 1,
- mask : 1,
- __reserved_2 : 15;
- u32 __reserved_3[3];
- } lvt_lint0;
-
-/*360*/ struct { /* LVT - LINT1 */
- u32 vector : 8,
- delivery_mode : 3,
- __reserved_1 : 1,
- delivery_status : 1,
- polarity : 1,
- remote_irr : 1,
- trigger : 1,
- mask : 1,
- __reserved_2 : 15;
- u32 __reserved_3[3];
- } lvt_lint1;
-
-/*370*/ struct { /* LVT - Error */
- u32 vector : 8,
- __reserved_1 : 4,
- delivery_status : 1,
- __reserved_2 : 3,
- mask : 1,
- __reserved_3 : 15;
- u32 __reserved_4[3];
- } lvt_error;
-
-/*380*/ struct { /* Timer Initial Count Register */
- u32 initial_count;
- u32 __reserved_2[3];
- } timer_icr;
-
-/*390*/ const
- struct { /* Timer Current Count Register */
- u32 curr_count;
- u32 __reserved_2[3];
- } timer_ccr;
-
-/*3A0*/ struct { u32 __reserved[4]; } __reserved_16;
-
-/*3B0*/ struct { u32 __reserved[4]; } __reserved_17;
-
-/*3C0*/ struct { u32 __reserved[4]; } __reserved_18;
-
-/*3D0*/ struct { u32 __reserved[4]; } __reserved_19;
-
-/*3E0*/ struct { /* Timer Divide Configuration Register */
- u32 divisor : 4,
- __reserved_1 : 28;
- u32 __reserved_2[3];
- } timer_dcr;
-
-/*3F0*/ struct { u32 __reserved[4]; } __reserved_20;
-
-} __attribute__ ((packed));
-
-#undef u32
-
#ifdef CONFIG_X86_32
#define BAD_APICID 0xFFu
#else
#define BAD_APICID 0xFFFFu
#endif
-enum apic_delivery_modes {
- APIC_DELIVERY_MODE_FIXED = 0,
- APIC_DELIVERY_MODE_LOWESTPRIO = 1,
- APIC_DELIVERY_MODE_SMI = 2,
- APIC_DELIVERY_MODE_NMI = 4,
- APIC_DELIVERY_MODE_INIT = 5,
- APIC_DELIVERY_MODE_EXTINT = 7,
-};
-
-#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_APICDEF_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 35389b2af88e..0216f63a366b 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -81,22 +81,4 @@ do { \
#include <asm-generic/barrier.h>
-/*
- * Make previous memory operations globally visible before
- * a WRMSR.
- *
- * MFENCE makes writes visible, but only affects load/store
- * instructions. WRMSR is unfortunately not a load/store
- * instruction and is unaffected by MFENCE. The LFENCE ensures
- * that the WRMSR is not reordered.
- *
- * Most WRMSRs are full serializing instructions themselves and
- * do not require this barrier. This is only required for the
- * IA32_TSC_DEADLINE and X2APIC MSRs.
- */
-static inline void weak_wrmsr_fence(void)
-{
- asm volatile("mfence; lfence" : : : "memory");
-}
-
#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 50e5ebf9d0a0..990eb686ca67 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -94,18 +94,17 @@ arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
-static __always_inline bool
-arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+ volatile unsigned long *addr)
{
bool negative;
- asm volatile(LOCK_PREFIX "andb %2,%1"
+ asm volatile(LOCK_PREFIX "xorb %2,%1"
CC_SET(s)
: CC_OUT(s) (negative), WBYTE_ADDR(addr)
- : "ir" ((char) ~(1 << nr)) : "memory");
+ : "iq" ((char)mask) : "memory");
return negative;
}
-#define arch_clear_bit_unlock_is_negative_byte \
- arch_clear_bit_unlock_is_negative_byte
+#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte
static __always_inline void
arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 4ae14339cb8c..a38cc0afc90a 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -40,23 +40,40 @@
#ifdef CONFIG_X86_64
# define BOOT_STACK_SIZE 0x4000
+/*
+ * Used by decompressor's startup_32() to allocate page tables for identity
+ * mapping of the 4G of RAM in 4-level paging mode:
+ * - 1 level4 table;
+ * - 1 level3 table;
+ * - 4 level2 table that maps everything with 2M pages;
+ *
+ * The additional level5 table needed for 5-level paging is allocated from
+ * trampoline_32bit memory.
+ */
# define BOOT_INIT_PGT_SIZE (6*4096)
-# ifdef CONFIG_RANDOMIZE_BASE
+
/*
- * Assuming all cross the 512GB boundary:
- * 1 page for level4
- * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
- * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
- * Total is 19 pages.
+ * Total number of page tables kernel_add_identity_map() can allocate,
+ * including page tables consumed by startup_32().
+ *
+ * Worst-case scenario:
+ * - 5-level paging needs 1 level5 table;
+ * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel,
+ * assuming all of them cross 256T boundary:
+ * + 4*2 level4 table;
+ * + 4*2 level3 table;
+ * + 4*2 level2 table;
+ * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM):
+ * + 1 level4 table;
+ * + 1 level3 table;
+ * + 1 level2 table;
+ * Total: 28 tables
+ *
+ * Add 4 spare table in case decompressor touches anything beyond what is
+ * accounted above. Warn if it happens.
*/
-# ifdef CONFIG_X86_VERBOSE_BOOTUP
-# define BOOT_PGT_SIZE (19*4096)
-# else /* !CONFIG_X86_VERBOSE_BOOTUP */
-# define BOOT_PGT_SIZE (17*4096)
-# endif
-# else /* !CONFIG_RANDOMIZE_BASE */
-# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE
-# endif
+# define BOOT_PGT_SIZE_WARN (28*4096)
+# define BOOT_PGT_SIZE (32*4096)
#else /* !CONFIG_X86_64 */
# define BOOT_STACK_SIZE 0x1000
@@ -68,6 +85,8 @@ extern const unsigned long kernel_total_size;
unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
void (*error)(char *x));
+
+extern struct boot_params *boot_params_ptr;
#endif
#endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
index ce9685fc78d8..5aa061199866 100644
--- a/arch/x86/include/asm/cacheinfo.h
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -7,9 +7,6 @@ extern unsigned int memory_caching_control;
#define CACHE_MTRR 0x01
#define CACHE_PAT 0x02
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu);
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu);
-
void cache_disable(void);
void cache_enable(void);
void set_cache_aps_delayed_init(bool val);
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 58dacd90daef..7cd752557905 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -7,16 +7,140 @@
*
* Copyright (C) 2022 Google LLC
*/
+#include <linux/bug.h>
+#include <asm/ibt.h>
-#include <linux/cfi.h>
+/*
+ * An overview of the various calling conventions...
+ *
+ * Traditional:
+ *
+ * foo:
+ * ... code here ...
+ * ret
+ *
+ * direct caller:
+ * call foo
+ *
+ * indirect caller:
+ * lea foo(%rip), %r11
+ * ...
+ * call *%r11
+ *
+ *
+ * IBT:
+ *
+ * foo:
+ * endbr64
+ * ... code here ...
+ * ret
+ *
+ * direct caller:
+ * call foo / call foo+4
+ *
+ * indirect caller:
+ * lea foo(%rip), %r11
+ * ...
+ * call *%r11
+ *
+ *
+ * kCFI:
+ *
+ * __cfi_foo:
+ * movl $0x12345678, %eax
+ * # 11 nops when CONFIG_CALL_PADDING
+ * foo:
+ * endbr64 # when IBT
+ * ... code here ...
+ * ret
+ *
+ * direct call:
+ * call foo # / call foo+4 when IBT
+ *
+ * indirect call:
+ * lea foo(%rip), %r11
+ * ...
+ * movl $(-0x12345678), %r10d
+ * addl -4(%r11), %r10d # -15 when CONFIG_CALL_PADDING
+ * jz 1f
+ * ud2
+ * 1:call *%r11
+ *
+ *
+ * FineIBT (builds as kCFI + CALL_PADDING + IBT + RETPOLINE and runtime patches into):
+ *
+ * __cfi_foo:
+ * endbr64
+ * subl 0x12345678, %r10d
+ * jz foo
+ * ud2
+ * nop
+ * foo:
+ * osp nop3 # was endbr64
+ * ... code here ...
+ * ret
+ *
+ * direct caller:
+ * call foo / call foo+4
+ *
+ * indirect caller:
+ * lea foo(%rip), %r11
+ * ...
+ * movl $0x12345678, %r10d
+ * subl $16, %r11
+ * nop4
+ * call *%r11
+ *
+ */
+enum cfi_mode {
+ CFI_DEFAULT, /* FineIBT if hardware has IBT, otherwise kCFI */
+ CFI_OFF, /* Taditional / IBT depending on .config */
+ CFI_KCFI, /* Optionally CALL_PADDING, IBT, RETPOLINE */
+ CFI_FINEIBT, /* see arch/x86/kernel/alternative.c */
+};
+
+extern enum cfi_mode cfi_mode;
+
+struct pt_regs;
#ifdef CONFIG_CFI_CLANG
enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
+#define __bpfcall
+extern u32 cfi_bpf_hash;
+extern u32 cfi_bpf_subprog_hash;
+
+static inline int cfi_get_offset(void)
+{
+ switch (cfi_mode) {
+ case CFI_FINEIBT:
+ return 16;
+ case CFI_KCFI:
+ if (IS_ENABLED(CONFIG_CALL_PADDING))
+ return 16;
+ return 5;
+ default:
+ return 0;
+ }
+}
+#define cfi_get_offset cfi_get_offset
+
+extern u32 cfi_get_func_hash(void *func);
+
#else
static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
{
return BUG_TRAP_TYPE_NONE;
}
+#define cfi_bpf_hash 0U
+#define cfi_bpf_subprog_hash 0U
+static inline u32 cfi_get_func_hash(void *func)
+{
+ return 0;
+}
#endif /* CONFIG_CFI_CLANG */
+#if HAS_KERNEL_IBT == 1
+#define CFI_NOSEAL(x) asm(IBT_NOSEAL(__stringify(x)))
+#endif
+
#endif /* _ASM_X86_CFI_H */
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index d53636506134..5612648b0202 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -221,12 +221,18 @@ extern void __add_wrong_size(void)
#define __try_cmpxchg(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
+#define __sync_try_cmpxchg(ptr, pold, new, size) \
+ __raw_try_cmpxchg((ptr), (pold), (new), (size), "lock; ")
+
#define __try_cmpxchg_local(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), "")
#define arch_try_cmpxchg(ptr, pold, new) \
__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+#define arch_sync_try_cmpxchg(ptr, pold, new) \
+ __sync_try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+
#define arch_try_cmpxchg_local(ptr, pold, new) \
__try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr)))
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 6ae2d16a7613..76c310b19b11 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -10,13 +10,14 @@ enum cc_vendor {
CC_VENDOR_INTEL,
};
-extern enum cc_vendor cc_vendor;
-
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+extern enum cc_vendor cc_vendor;
void cc_set_mask(u64 mask);
u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
#else
+#define cc_vendor (CC_VENDOR_NONE)
+
static inline u64 cc_mkenc(u64 val)
{
return val;
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 3a233ebff712..f8f9a9b79395 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -23,13 +23,7 @@ static inline void prefill_possible_map(void) {}
#endif /* CONFIG_SMP */
-struct x86_cpu {
- struct cpu cpu;
-};
-
#ifdef CONFIG_HOTPLUG_CPU
-extern int arch_register_cpu(int num);
-extern void arch_unregister_cpu(int);
extern void soft_restart_cpu(void);
#endif
@@ -73,26 +67,12 @@ static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
extern __noendbr void cet_disable(void);
-struct ucode_cpu_info;
-
-int intel_cpu_collect_info(struct ucode_cpu_info *uci);
-
-static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1,
- unsigned int s2, unsigned int p2)
-{
- if (s1 != s2)
- return false;
-
- /* Processor flags are either both 0 ... */
- if (!p1 && !p2)
- return true;
+struct cpu_signature;
- /* ... or they intersect. */
- return p1 & p2;
-}
+void intel_collect_cpu_info(struct cpu_signature *sig);
extern u64 x86_read_arch_cap_msr(void);
-int intel_find_matching_signature(void *mc, unsigned int csig, int cpf);
+bool intel_find_matching_signature(void *mc, struct cpu_signature *sig);
int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type);
extern struct cpumask cpus_stop_mask;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a26bebbdff87..a1273698fc43 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto(
+ asm goto(
ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
".pushsection .altinstr_aux,\"ax\"\n"
"6:\n"
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 2061ed1c398f..fdf723b6f6d0 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -81,10 +81,8 @@
#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-
-/* CPU types for specific tunings: */
#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */
-/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */
+#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */
#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */
#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */
#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
@@ -198,6 +196,7 @@
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -218,7 +217,7 @@
#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */
#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN (7*32+28) /* "" CPU based on Zen microarchitecture */
+#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */
#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */
#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */
#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -308,10 +307,14 @@
#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */
#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */
#define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */
-
#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */
#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */
#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
@@ -439,9 +442,11 @@
#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */
#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */
+#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */
/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */
+#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */
#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */
@@ -493,6 +498,7 @@
#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
/* BUG word 2 */
#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
diff --git a/arch/x86/include/asm/crash_core.h b/arch/x86/include/asm/crash_core.h
new file mode 100644
index 000000000000..76af98f4e801
--- /dev/null
+++ b/arch/x86/include/asm/crash_core.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_CRASH_CORE_H
+#define _X86_CRASH_CORE_H
+
+/* 16M alignment for crash kernel regions */
+#define CRASH_ALIGN SZ_16M
+
+/*
+ * Keep the crash kernel below this limit.
+ *
+ * Earlier 32-bits kernels would limit the kernel to the low 512 MB range
+ * due to mapping restrictions.
+ *
+ * 64-bit kdump kernels need to be restricted to be under 64 TB, which is
+ * the upper limit of system RAM in 4-level paging mode. Since the kdump
+ * jump could be from 5-level paging to 4-level paging, the jump will fail if
+ * the kernel is put above 64 TB, and during the 1st kernel bootup there's
+ * no good way to detect the paging mode of the target kernel which will be
+ * loaded for dumping.
+ */
+extern unsigned long swiotlb_size_or_default(void);
+
+#ifdef CONFIG_X86_32
+# define CRASH_ADDR_LOW_MAX SZ_512M
+# define CRASH_ADDR_HIGH_MAX SZ_512M
+#else
+# define CRASH_ADDR_LOW_MAX SZ_4G
+# define CRASH_ADDR_HIGH_MAX SZ_64T
+#endif
+
+# define DEFAULT_CRASH_KERNEL_LOW_SIZE crash_low_size_default()
+
+static inline unsigned long crash_low_size_default(void)
+{
+#ifdef CONFIG_X86_64
+ return max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20);
+#else
+ return 0;
+#endif
+}
+
+#endif /* _X86_CRASH_CORE_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index c8c5674d69f6..fb7702d4170c 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -2,6 +2,7 @@
#ifndef _ASM_X86_CURRENT_H
#define _ASM_X86_CURRENT_H
+#include <linux/build_bug.h>
#include <linux/compiler.h>
#ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 66eb5e1ac4fb..0cec92c430cc 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -5,6 +5,7 @@
#include <linux/bug.h>
#include <linux/percpu.h>
#include <uapi/asm/debugreg.h>
+#include <asm/cpufeature.h>
DECLARE_PER_CPU(unsigned long, cpu_dr7);
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index f7e7099af595..d440a65af8f3 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -8,6 +8,56 @@
* archs.
*/
+/*
+ * Low-level interface mapping flags/field names to bits
+ */
+
+/* Flags for _DESC_S (non-system) descriptors */
+#define _DESC_ACCESSED 0x0001
+#define _DESC_DATA_WRITABLE 0x0002
+#define _DESC_CODE_READABLE 0x0002
+#define _DESC_DATA_EXPAND_DOWN 0x0004
+#define _DESC_CODE_CONFORMING 0x0004
+#define _DESC_CODE_EXECUTABLE 0x0008
+
+/* Common flags */
+#define _DESC_S 0x0010
+#define _DESC_DPL(dpl) ((dpl) << 5)
+#define _DESC_PRESENT 0x0080
+
+#define _DESC_LONG_CODE 0x2000
+#define _DESC_DB 0x4000
+#define _DESC_GRANULARITY_4K 0x8000
+
+/* System descriptors have a numeric "type" field instead of flags */
+#define _DESC_SYSTEM(code) (code)
+
+/*
+ * High-level interface mapping intended usage to low-level combinations
+ * of flags
+ */
+
+#define _DESC_DATA (_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \
+ _DESC_DATA_WRITABLE)
+#define _DESC_CODE (_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \
+ _DESC_CODE_READABLE | _DESC_CODE_EXECUTABLE)
+
+#define DESC_DATA16 (_DESC_DATA)
+#define DESC_CODE16 (_DESC_CODE)
+
+#define DESC_DATA32 (_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB)
+#define DESC_DATA32_BIOS (_DESC_DATA | _DESC_DB)
+
+#define DESC_CODE32 (_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_DB)
+#define DESC_CODE32_BIOS (_DESC_CODE | _DESC_DB)
+
+#define DESC_TSS32 (_DESC_SYSTEM(9) | _DESC_PRESENT)
+
+#define DESC_DATA64 (_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB)
+#define DESC_CODE64 (_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_LONG_CODE)
+
+#define DESC_USER (_DESC_DPL(3))
+
#ifndef __ASSEMBLY__
#include <linux/types.h>
@@ -22,19 +72,19 @@ struct desc_struct {
#define GDT_ENTRY_INIT(flags, base, limit) \
{ \
- .limit0 = (u16) (limit), \
- .limit1 = ((limit) >> 16) & 0x0F, \
- .base0 = (u16) (base), \
- .base1 = ((base) >> 16) & 0xFF, \
- .base2 = ((base) >> 24) & 0xFF, \
- .type = (flags & 0x0f), \
- .s = (flags >> 4) & 0x01, \
- .dpl = (flags >> 5) & 0x03, \
- .p = (flags >> 7) & 0x01, \
- .avl = (flags >> 12) & 0x01, \
- .l = (flags >> 13) & 0x01, \
- .d = (flags >> 14) & 0x01, \
- .g = (flags >> 15) & 0x01, \
+ .limit0 = ((limit) >> 0) & 0xFFFF, \
+ .limit1 = ((limit) >> 16) & 0x000F, \
+ .base0 = ((base) >> 0) & 0xFFFF, \
+ .base1 = ((base) >> 16) & 0x00FF, \
+ .base2 = ((base) >> 24) & 0x00FF, \
+ .type = ((flags) >> 0) & 0x000F, \
+ .s = ((flags) >> 4) & 0x0001, \
+ .dpl = ((flags) >> 5) & 0x0003, \
+ .p = ((flags) >> 7) & 0x0001, \
+ .avl = ((flags) >> 12) & 0x0001, \
+ .l = ((flags) >> 13) & 0x0001, \
+ .d = ((flags) >> 14) & 0x0001, \
+ .g = ((flags) >> 15) & 0x0001, \
}
enum {
@@ -94,6 +144,7 @@ struct gate_struct {
typedef struct gate_struct gate_desc;
+#ifndef _SETUP
static inline unsigned long gate_offset(const gate_desc *g)
{
#ifdef CONFIG_X86_64
@@ -108,6 +159,7 @@ static inline unsigned long gate_segment(const gate_desc *g)
{
return g->segment;
}
+#endif
struct desc_ptr {
unsigned short size;
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index b0994ae3bc23..c4555b269a1b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -91,19 +91,6 @@ static inline void efi_fpu_end(void)
#ifdef CONFIG_X86_32
#define EFI_X86_KERNEL_ALLOC_LIMIT (SZ_512M - 1)
-
-#define arch_efi_call_virt_setup() \
-({ \
- efi_fpu_begin(); \
- firmware_restrict_branch_speculation_start(); \
-})
-
-#define arch_efi_call_virt_teardown() \
-({ \
- firmware_restrict_branch_speculation_end(); \
- efi_fpu_end(); \
-})
-
#else /* !CONFIG_X86_32 */
#define EFI_X86_KERNEL_ALLOC_LIMIT EFI_ALLOC_LIMIT
@@ -116,14 +103,6 @@ extern bool efi_disable_ibt_for_runtime;
__efi_call(__VA_ARGS__); \
})
-#define arch_efi_call_virt_setup() \
-({ \
- efi_sync_low_kernel_mappings(); \
- efi_fpu_begin(); \
- firmware_restrict_branch_speculation_start(); \
- efi_enter_mm(); \
-})
-
#undef arch_efi_call_virt
#define arch_efi_call_virt(p, f, args...) ({ \
u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime); \
@@ -132,13 +111,6 @@ extern bool efi_disable_ibt_for_runtime;
ret; \
})
-#define arch_efi_call_virt_teardown() \
-({ \
- efi_leave_mm(); \
- firmware_restrict_branch_speculation_end(); \
- efi_fpu_end(); \
-})
-
#ifdef CONFIG_KASAN
/*
* CONFIG_KASAN may redefine memset to __memset. __memset function is present
@@ -168,8 +140,8 @@ extern void efi_delete_dummy_variable(void);
extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
extern void efi_free_boot_services(void);
-void efi_enter_mm(void);
-void efi_leave_mm(void);
+void arch_efi_call_virt_setup(void);
+void arch_efi_call_virt_teardown(void);
/* kexec external ABI */
struct efi_setup_data {
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 18fd06f7936a..1e16bd5ac781 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -7,6 +7,7 @@
*/
#include <linux/thread_info.h>
+#include <asm/ia32.h>
#include <asm/ptrace.h>
#include <asm/user.h>
#include <asm/auxvec.h>
@@ -149,7 +150,7 @@ do { \
((x)->e_machine == EM_X86_64)
#define compat_elf_check_arch(x) \
- (elf_check_arch_ia32(x) || \
+ ((elf_check_arch_ia32(x) && ia32_enabled_verbose()) || \
(IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
static inline void elf_common_init(struct thread_struct *t,
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 991e31cfde94..fe6312045042 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -4,7 +4,7 @@
/*
* Our IMM is signed, as such it must live at the top end of the word. Also,
- * since C99 hex constants are of ambigious type, force cast the mask to 'int'
+ * since C99 hex constants are of ambiguous type, force cast the mask to 'int'
* so that FIELD_GET() will DTRT and sign extend the value when it extracts it.
*/
#define EX_DATA_TYPE_MASK ((int)0x000000FF)
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
index 23873da8fb77..c3b9582de7ef 100644
--- a/arch/x86/include/asm/fb.h
+++ b/arch/x86/include/asm/fb.h
@@ -2,12 +2,14 @@
#ifndef _ASM_X86_FB_H
#define _ASM_X86_FB_H
+#include <asm/page.h>
+
struct fb_info;
-struct file;
-struct vm_area_struct;
-void fb_pgprotect(struct file *file, struct vm_area_struct *vma, unsigned long off);
-#define fb_pgprotect fb_pgprotect
+pgprot_t pgprot_framebuffer(pgprot_t prot,
+ unsigned long vm_start, unsigned long vm_end,
+ unsigned long offset);
+#define pgprot_framebuffer pgprot_framebuffer
int fb_is_primary_device(struct fb_info *info);
#define fb_is_primary_device fb_is_primary_device
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 31089b851c4f..a2be3aefff9f 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -157,7 +157,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) {
static inline void fpu_sync_guest_vmexit_xfd_state(void) { }
#endif
-extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru);
+extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+ unsigned int size, u64 xfeatures, u32 pkru);
extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru);
static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index eb810074f1e7..ace9aa3b78a3 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -5,6 +5,8 @@
#ifndef _ASM_X86_FPU_H
#define _ASM_X86_FPU_H
+#include <asm/page_types.h>
+
/*
* The legacy x87 FPU state format, as saved by FSAVE and
* restored by the FRSTOR instructions:
@@ -415,7 +417,7 @@ struct fpu_state_perm {
*
* This master permission field is only to be used when
* task.fpu.fpstate based checks fail to validate whether the task
- * is allowed to expand it's xfeatures set which requires to
+ * is allowed to expand its xfeatures set which requires to
* allocate a larger sized fpstate buffer.
*
* Do not access this field directly. Use the provided helper
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 551829884734..b02c3cd3c0f6 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -28,7 +28,7 @@
#include <asm/irq.h>
#include <asm/sections.h>
-#ifdef CONFIG_X86_LOCAL_APIC
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
struct irq_data;
struct pci_dev;
struct msi_desc;
@@ -105,10 +105,10 @@ static inline void irq_complete_move(struct irq_cfg *c) { }
#endif
extern void apic_ack_edge(struct irq_data *data);
-#else /* CONFIG_X86_LOCAL_APIC */
+#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */
static inline void lock_vector_lock(void) {}
static inline void unlock_vector_lock(void) {}
-#endif /* CONFIG_X86_LOCAL_APIC */
+#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */
/* Statistics */
extern atomic_t irq_err_count;
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 637fa1df3512..c715097e92fd 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -69,6 +69,8 @@ struct legacy_pic {
void (*make_irq)(unsigned int irq);
};
+void legacy_pic_pcat_compat(void);
+
extern struct legacy_pic *legacy_pic;
extern struct legacy_pic null_legacy_pic;
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index fada857f0a1e..c7ef6ea2fa99 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -2,7 +2,6 @@
#ifndef _ASM_X86_IA32_H
#define _ASM_X86_IA32_H
-
#ifdef CONFIG_IA32_EMULATION
#include <linux/compat.h>
@@ -68,6 +67,37 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm);
#endif
-#endif /* CONFIG_IA32_EMULATION */
+extern bool __ia32_enabled;
+
+static inline bool ia32_enabled(void)
+{
+ return __ia32_enabled;
+}
+
+static inline void ia32_disable(void)
+{
+ __ia32_enabled = false;
+}
+
+#else /* !CONFIG_IA32_EMULATION */
+
+static inline bool ia32_enabled(void)
+{
+ return IS_ENABLED(CONFIG_X86_32);
+}
+
+static inline void ia32_disable(void) {}
+
+#endif
+
+static inline bool ia32_enabled_verbose(void)
+{
+ bool enabled = ia32_enabled();
+
+ if (IS_ENABLED(CONFIG_IA32_EMULATION) && !enabled)
+ pr_notice_once("32-bit emulation disabled. You can reenable with ia32_emulation=on\n");
+
+ return enabled;
+}
#endif /* _ASM_X86_IA32_H */
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 05fd175cec7d..13639e57e1f8 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -569,6 +569,10 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_UD, exc_invalid_op);
DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3);
DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault);
+#if defined(CONFIG_IA32_EMULATION)
+DECLARE_IDTENTRY_RAW(IA32_SYSCALL_VECTOR, int80_emulation);
+#endif
+
#ifdef CONFIG_X86_MCE
#ifdef CONFIG_X86_64
DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check);
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 5f1d3c421f68..cc9ccf61b6bd 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_INIT_H
#define _ASM_X86_INIT_H
+#define __head __section(".head.text")
+
struct x86_mapping_info {
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
void *context; /* context for alloc_pgt_page */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 5fcd85fd64fd..b65e9c46b922 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -27,6 +27,7 @@
* _X - regular server parts
* _D - micro server parts
* _N,_P - other mobile parts
+ * _H - premium mobile parts
* _S - other client parts
*
* Historical OPTDIFFs:
@@ -124,6 +125,7 @@
#define INTEL_FAM6_METEORLAKE 0xAC
#define INTEL_FAM6_METEORLAKE_L 0xAA
+#define INTEL_FAM6_ARROWLAKE_H 0xC5
#define INTEL_FAM6_ARROWLAKE 0xC6
#define INTEL_FAM6_LUNARLAKE_M 0xBD
@@ -160,6 +162,8 @@
#define INTEL_FAM6_ATOM_CRESTMONT_X 0xAF /* Sierra Forest */
#define INTEL_FAM6_ATOM_CRESTMONT 0xB6 /* Grand Ridge */
+#define INTEL_FAM6_ATOM_DARKMONT_X 0xDD /* Clearwater Forest */
+
/* Xeon Phi */
#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 76238842406a..3814a9263d64 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -242,7 +242,7 @@ static inline void slow_down_io(void)
#endif
-#define BUILDIO(bwl, bw, type) \
+#define BUILDIO(bwl, type) \
static inline void out##bwl##_p(type value, u16 port) \
{ \
out##bwl(value, port); \
@@ -288,9 +288,9 @@ static inline void ins##bwl(u16 port, void *addr, unsigned long count) \
} \
}
-BUILDIO(b, b, u8)
-BUILDIO(w, w, u16)
-BUILDIO(l, , u32)
+BUILDIO(b, u8)
+BUILDIO(w, u16)
+BUILDIO(l, u32)
#undef BUILDIO
#define inb_p inb_p
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index a1911fea8739..af7541c11821 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -111,7 +111,7 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask);
* This function will block all kernel access to the PMIC I2C bus, so that the
* P-Unit can safely access the PMIC over the shared I2C bus.
*
- * Note on these systems the i2c-bus driver will request a sempahore from the
+ * Note on these systems the i2c-bus driver will request a semaphore from the
* P-Unit for exclusive access to the PMIC bus when i2c drivers are accessing
* it, but this does not appear to be sufficient, we still need to avoid making
* certain P-Unit requests during the access window to avoid problems.
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index 800ffce0db29..6b4d36c95165 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -9,7 +9,6 @@ static inline bool arch_irq_work_has_interrupt(void)
{
return boot_cpu_has(X86_FEATURE_APIC);
}
-extern void arch_irq_work_raise(void);
#else
static inline bool arch_irq_work_has_interrupt(void)
{
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 071572e23d3a..cbbef32517f0 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -24,7 +24,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
"jmp %l[l_yes] # objtool NOPs this \n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (2 | branch) : : l_yes);
@@ -38,7 +38,7 @@ l_yes:
static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
".byte " __stringify(BYTES_NOP5) "\n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (branch) : : l_yes);
@@ -52,7 +52,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
"jmp %l[l_yes]\n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (branch) : : l_yes);
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 3be6a98751f0..c9f6a6c5de3c 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -205,8 +205,6 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image);
#endif
#endif
-typedef void crash_vmclear_fn(void);
-extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
extern void kdump_nmi_shootdown_cpus(void);
#ifdef CONFIG_CRASH_HOTPLUG
diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h
index 8fa6ac0e2d76..d91b37f5b4bb 100644
--- a/arch/x86/include/asm/kmsan.h
+++ b/arch/x86/include/asm/kmsan.h
@@ -64,6 +64,7 @@ static inline bool kmsan_virt_addr_valid(void *addr)
{
unsigned long x = (unsigned long)addr;
unsigned long y = x - __START_KERNEL_map;
+ bool ret;
/* use the carry flag to determine if x was < __START_KERNEL_map */
if (unlikely(x > y)) {
@@ -79,7 +80,21 @@ static inline bool kmsan_virt_addr_valid(void *addr)
return false;
}
- return pfn_valid(x >> PAGE_SHIFT);
+ /*
+ * pfn_valid() relies on RCU, and may call into the scheduler on exiting
+ * the critical section. However, this would result in recursion with
+ * KMSAN. Therefore, disable preemption here, and re-enable preemption
+ * below while suppressing reschedules to avoid recursion.
+ *
+ * Note, this sacrifices occasionally breaking scheduling guarantees.
+ * Although, a kernel compiled with KMSAN has already given up on any
+ * performance guarantees due to being heavily instrumented.
+ */
+ preempt_disable();
+ ret = pfn_valid(x >> PAGE_SHIFT);
+ preempt_enable_no_resched();
+
+ return ret;
}
#endif /* !MODULE */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index a2e9317aad49..5939694dfb28 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -113,8 +113,6 @@ struct kprobe_ctlblk {
};
extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
-extern int kprobe_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data);
extern int kprobe_int3_handler(struct pt_regs *regs);
#else
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index e3054e3e46d5..378ed944b849 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -55,8 +55,10 @@ KVM_X86_OP(set_rflags)
KVM_X86_OP(get_if_flag)
KVM_X86_OP(flush_tlb_all)
KVM_X86_OP(flush_tlb_current)
+#if IS_ENABLED(CONFIG_HYPERV)
KVM_X86_OP_OPTIONAL(flush_remote_tlbs)
KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range)
+#endif
KVM_X86_OP(flush_tlb_gva)
KVM_X86_OP(flush_tlb_guest)
KVM_X86_OP(vcpu_pre_run)
@@ -108,6 +110,7 @@ KVM_X86_OP_OPTIONAL(vcpu_blocking)
KVM_X86_OP_OPTIONAL(vcpu_unblocking)
KVM_X86_OP_OPTIONAL(pi_update_irte)
KVM_X86_OP_OPTIONAL(pi_start_assignment)
+KVM_X86_OP_OPTIONAL(apicv_pre_state_restore)
KVM_X86_OP_OPTIONAL(apicv_post_state_restore)
KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt)
KVM_X86_OP_OPTIONAL(set_hv_timer)
@@ -126,7 +129,7 @@ KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from)
KVM_X86_OP_OPTIONAL(vm_move_enc_context_from)
KVM_X86_OP_OPTIONAL(guest_memory_reclaimed)
KVM_X86_OP(get_msr_feature)
-KVM_X86_OP(can_emulate_instruction)
+KVM_X86_OP(check_emulate_instruction)
KVM_X86_OP(apic_init_signal_blocked)
KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush)
KVM_X86_OP_OPTIONAL(migrate_timers)
@@ -134,6 +137,7 @@ KVM_X86_OP(msr_filter_changed)
KVM_X86_OP(complete_emulated_msr)
KVM_X86_OP(vcpu_deliver_sipi_vector)
KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
+KVM_X86_OP_OPTIONAL(get_untagged_addr)
#undef KVM_X86_OP
#undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index 6c98f4bb4228..058bc636356a 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -22,7 +22,7 @@ KVM_X86_PMU_OP(get_msr)
KVM_X86_PMU_OP(set_msr)
KVM_X86_PMU_OP(refresh)
KVM_X86_PMU_OP(init)
-KVM_X86_PMU_OP(reset)
+KVM_X86_PMU_OP_OPTIONAL(reset)
KVM_X86_PMU_OP_OPTIONAL(deliver_pmi)
KVM_X86_PMU_OP_OPTIONAL(cleanup)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3bc146dfd38d..d271ba20a0b2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -39,7 +39,15 @@
#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
+/*
+ * CONFIG_KVM_MAX_NR_VCPUS is defined iff CONFIG_KVM!=n, provide a dummy max if
+ * KVM is disabled (arbitrarily use the default from CONFIG_KVM_MAX_NR_VCPUS).
+ */
+#ifdef CONFIG_KVM_MAX_NR_VCPUS
+#define KVM_MAX_VCPUS CONFIG_KVM_MAX_NR_VCPUS
+#else
#define KVM_MAX_VCPUS 1024
+#endif
/*
* In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs
@@ -125,7 +133,8 @@
| X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
| X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
| X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
- | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
+ | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \
+ | X86_CR4_LAM_SUP))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
@@ -288,13 +297,13 @@ struct kvm_kernel_irq_routing_entry;
* kvm_mmu_page_role tracks the properties of a shadow page (where shadow page
* also includes TDP pages) to determine whether or not a page can be used in
* the given MMU context. This is a subset of the overall kvm_cpu_role to
- * minimize the size of kvm_memory_slot.arch.gfn_track, i.e. allows allocating
- * 2 bytes per gfn instead of 4 bytes per gfn.
+ * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows
+ * allocating 2 bytes per gfn instead of 4 bytes per gfn.
*
* Upper-level shadow pages having gptes are tracked for write-protection via
- * gfn_track. As above, gfn_track is a 16 bit counter, so KVM must not create
- * more than 2^16-1 upper-level shadow pages at a single gfn, otherwise
- * gfn_track will overflow and explosions will ensure.
+ * gfn_write_track. As above, gfn_write_track is a 16 bit counter, so KVM must
+ * not create more than 2^16-1 upper-level shadow pages at a single gfn,
+ * otherwise gfn_write_track will overflow and explosions will ensue.
*
* A unique shadow page (SP) for a gfn is created if and only if an existing SP
* cannot be reused. The ability to reuse a SP is tracked by its role, which
@@ -492,8 +501,23 @@ struct kvm_pmc {
u8 idx;
bool is_paused;
bool intr;
+ /*
+ * Base value of the PMC counter, relative to the *consumed* count in
+ * the associated perf_event. This value includes counter updates from
+ * the perf_event and emulated_count since the last time the counter
+ * was reprogrammed, but it is *not* the current value as seen by the
+ * guest or userspace.
+ *
+ * The count is relative to the associated perf_event so that KVM
+ * doesn't need to reprogram the perf_event every time the guest writes
+ * to the counter.
+ */
u64 counter;
- u64 prev_counter;
+ /*
+ * PMC events triggered by KVM emulation that haven't been fully
+ * processed, i.e. haven't undergone overflow detection.
+ */
+ u64 emulated_counter;
u64 eventsel;
struct perf_event *perf_event;
struct kvm_vcpu *vcpu;
@@ -528,7 +552,6 @@ struct kvm_pmu {
u64 raw_event_mask;
struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
- struct irq_work irq_work;
/*
* Overlay the bitmap with a 64-bit atomic so that all bits can be
@@ -680,6 +703,7 @@ struct kvm_hypervisor_cpuid {
u32 limit;
};
+#ifdef CONFIG_KVM_XEN
/* Xen HVM per vcpu emulation context */
struct kvm_vcpu_xen {
u64 hypercall_rip;
@@ -702,6 +726,7 @@ struct kvm_vcpu_xen {
struct timer_list poll_timer;
struct kvm_hypervisor_cpuid cpuid;
};
+#endif
struct kvm_queued_exception {
bool pending;
@@ -746,7 +771,6 @@ struct kvm_vcpu_arch {
u64 smi_count;
bool at_instruction_boundary;
bool tpr_access_reporting;
- bool xsaves_enabled;
bool xfd_no_write_intercept;
u64 ia32_xss;
u64 microcode_version;
@@ -831,6 +855,25 @@ struct kvm_vcpu_arch {
struct kvm_cpuid_entry2 *cpuid_entries;
struct kvm_hypervisor_cpuid kvm_cpuid;
+ /*
+ * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly
+ * when "struct kvm_vcpu_arch" is no longer defined in an
+ * arch/x86/include/asm header. The max is mostly arbitrary, i.e.
+ * can be increased as necessary.
+ */
+#define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG
+
+ /*
+ * Track whether or not the guest is allowed to use features that are
+ * governed by KVM, where "governed" means KVM needs to manage state
+ * and/or explicitly enable the feature in hardware. Typically, but
+ * not always, governed features can be used by the guest if and only
+ * if both KVM and userspace want to expose the feature to the guest.
+ */
+ struct {
+ DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES);
+ } governed_features;
+
u64 reserved_gpa_bits;
int maxphyaddr;
@@ -910,10 +953,13 @@ struct kvm_vcpu_arch {
/* used for guest single stepping over the given code position */
unsigned long singlestep_rip;
+#ifdef CONFIG_KVM_HYPERV
bool hyperv_enabled;
struct kvm_vcpu_hv *hyperv;
+#endif
+#ifdef CONFIG_KVM_XEN
struct kvm_vcpu_xen xen;
-
+#endif
cpumask_var_t wbinvd_dirty_mask;
unsigned long last_retry_eip;
@@ -1005,7 +1051,7 @@ struct kvm_lpage_info {
struct kvm_arch_memory_slot {
struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
- unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
+ unsigned short *gfn_write_track;
};
/*
@@ -1067,6 +1113,7 @@ enum hv_tsc_page_status {
HV_TSC_PAGE_BROKEN,
};
+#ifdef CONFIG_KVM_HYPERV
/* Hyper-V emulation context */
struct kvm_hv {
struct mutex hv_lock;
@@ -1097,9 +1144,11 @@ struct kvm_hv {
*/
unsigned int synic_auto_eoi_used;
- struct hv_partition_assist_pg *hv_pa_pg;
struct kvm_hv_syndbg hv_syndbg;
+
+ bool xsaves_xsavec_checked;
};
+#endif
struct msr_bitmap_range {
u32 flags;
@@ -1108,6 +1157,7 @@ struct msr_bitmap_range {
unsigned long *bitmap;
};
+#ifdef CONFIG_KVM_XEN
/* Xen emulation context */
struct kvm_xen {
struct mutex xen_lock;
@@ -1119,6 +1169,7 @@ struct kvm_xen {
struct idr evtchn_ports;
unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
};
+#endif
enum kvm_irqchip_mode {
KVM_IRQCHIP_NONE,
@@ -1227,6 +1278,7 @@ enum kvm_apicv_inhibit {
};
struct kvm_arch {
+ unsigned long vm_type;
unsigned long n_used_mmu_pages;
unsigned long n_requested_mmu_pages;
unsigned long n_max_mmu_pages;
@@ -1247,8 +1299,9 @@ struct kvm_arch {
* create an NX huge page (without hanging the guest).
*/
struct list_head possible_nx_huge_pages;
- struct kvm_page_track_notifier_node mmu_sp_tracker;
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
struct kvm_page_track_notifier_head track_notifier_head;
+#endif
/*
* Protects marking pages unsync during page faults, as TDP MMU page
* faults only take mmu_lock for read. For simplicity, the unsync
@@ -1257,7 +1310,6 @@ struct kvm_arch {
*/
spinlock_t mmu_unsync_pages_lock;
- struct list_head assigned_dev_head;
struct iommu_domain *iommu_domain;
bool iommu_noncoherent;
#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
@@ -1305,6 +1357,7 @@ struct kvm_arch {
int nr_vcpus_matched_tsc;
u32 default_tsc_khz;
+ bool user_set_tsc;
seqcount_raw_spinlock_t pvclock_sc;
bool use_master_clock;
@@ -1318,8 +1371,13 @@ struct kvm_arch {
/* reads protected by irq_srcu, writes by irq_lock */
struct hlist_head mask_notifier_list;
+#ifdef CONFIG_KVM_HYPERV
struct kvm_hv hyperv;
+#endif
+
+#ifdef CONFIG_KVM_XEN
struct kvm_xen xen;
+#endif
bool backwards_tsc_observed;
bool boot_vcpu_runs_old_kvmclock;
@@ -1377,9 +1435,8 @@ struct kvm_arch {
* the MMU lock in read mode + RCU or
* the MMU lock in write mode
*
- * For writes, this list is protected by:
- * the MMU lock in read mode + the tdp_mmu_pages_lock or
- * the MMU lock in write mode
+ * For writes, this list is protected by tdp_mmu_pages_lock; see
+ * below for the details.
*
* Roots will remain in the list until their tdp_mmu_root_count
* drops to zero, at which point the thread that decremented the
@@ -1396,11 +1453,12 @@ struct kvm_arch {
* - possible_nx_huge_pages;
* - the possible_nx_huge_page_link field of kvm_mmu_page structs used
* by the TDP MMU
- * It is acceptable, but not necessary, to acquire this lock when
- * the thread holds the MMU lock in write mode.
+ * Because the lock is only taken within the MMU lock, strictly
+ * speaking it is redundant to acquire this lock when the thread
+ * holds the MMU lock in write mode. However it often simplifies
+ * the code to do so.
*/
spinlock_t tdp_mmu_pages_lock;
- struct workqueue_struct *tdp_mmu_zap_wq;
#endif /* CONFIG_X86_64 */
/*
@@ -1413,6 +1471,7 @@ struct kvm_arch {
#if IS_ENABLED(CONFIG_HYPERV)
hpa_t hv_root_tdp;
spinlock_t hv_root_tdp_lock;
+ struct hv_partition_assist_pg *hv_pa_pg;
#endif
/*
* VM-scope maximum vCPU ID. Used to determine the size of structures
@@ -1585,9 +1644,11 @@ struct kvm_x86_ops {
void (*flush_tlb_all)(struct kvm_vcpu *vcpu);
void (*flush_tlb_current)(struct kvm_vcpu *vcpu);
+#if IS_ENABLED(CONFIG_HYPERV)
int (*flush_remote_tlbs)(struct kvm *kvm);
int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn,
gfn_t nr_pages);
+#endif
/*
* Flush any TLB entries associated with the given GVA.
@@ -1624,7 +1685,7 @@ struct kvm_x86_ops {
/* Whether or not a virtual NMI is pending in hardware. */
bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu);
/*
- * Attempt to pend a virtual NMI in harware. Returns %true on success
+ * Attempt to pend a virtual NMI in hardware. Returns %true on success
* to allow using static_call_ret0 as the fallback.
*/
bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu);
@@ -1655,8 +1716,8 @@ struct kvm_x86_ops {
u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu);
u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu);
- void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
- void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu, u64 multiplier);
+ void (*write_tsc_offset)(struct kvm_vcpu *vcpu);
+ void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu);
/*
* Retrieve somewhat arbitrary exit information. Intended to
@@ -1674,7 +1735,7 @@ struct kvm_x86_ops {
void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
- void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
+ void (*sched_in)(struct kvm_vcpu *vcpu, int cpu);
/*
* Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A zero
@@ -1691,6 +1752,7 @@ struct kvm_x86_ops {
int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
void (*pi_start_assignment)(struct kvm *kvm);
+ void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu);
void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
@@ -1716,8 +1778,8 @@ struct kvm_x86_ops {
int (*get_msr_feature)(struct kvm_msr_entry *entry);
- bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type,
- void *insn, int insn_len);
+ int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type,
+ void *insn, int insn_len);
bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu);
@@ -1732,6 +1794,8 @@ struct kvm_x86_ops {
* Returns vCPU specific APICv inhibit reasons
*/
unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
+
+ gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
};
struct kvm_x86_nested_ops {
@@ -1795,8 +1859,9 @@ static inline struct kvm *kvm_arch_alloc_vm(void)
#define __KVM_HAVE_ARCH_VM_FREE
void kvm_arch_free_vm(struct kvm *kvm);
-#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
-static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
+#if IS_ENABLED(CONFIG_HYPERV)
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
{
if (kvm_x86_ops.flush_remote_tlbs &&
!static_call(kvm_x86_flush_remote_tlbs)(kvm))
@@ -1805,6 +1870,17 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
return -ENOTSUPP;
}
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
+ u64 nr_pages)
+{
+ if (!kvm_x86_ops.flush_remote_tlbs_range)
+ return -EOPNOTSUPP;
+
+ return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+}
+#endif /* CONFIG_HYPERV */
+
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
@@ -1814,9 +1890,12 @@ void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-int kvm_mmu_init_vm(struct kvm *kvm);
+void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
+void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
+ struct kvm_memory_slot *slot);
+
void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
@@ -1833,7 +1912,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
-void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
@@ -2056,6 +2134,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
int tdp_max_root_level, int tdp_huge_page_level);
+#ifdef CONFIG_KVM_PRIVATE_MEM
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#else
+#define kvm_arch_has_private_mem(kvm) false
+#endif
+
static inline u16 kvm_read_ldt(void)
{
u16 ldt;
@@ -2103,16 +2187,15 @@ enum {
#define HF_SMM_MASK (1 << 1)
#define HF_SMM_INSIDE_NMI_MASK (1 << 2)
-# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
-# define KVM_ADDRESS_SPACE_NUM 2
+# define KVM_MAX_NR_ADDRESS_SPACES 2
+/* SMM is currently unsupported for guests with private memory. */
+# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2)
# define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
#else
# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
#endif
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_cpu_has_extint(struct kvm_vcpu *v);
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index eb186bc57f6a..3d040741044b 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -2,11 +2,9 @@
#ifndef _ASM_X86_KVM_PAGE_TRACK_H
#define _ASM_X86_KVM_PAGE_TRACK_H
-enum kvm_page_track_mode {
- KVM_PAGE_TRACK_WRITE,
- KVM_PAGE_TRACK_MAX,
-};
+#include <linux/kvm_types.h>
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
/*
* The notifier represented by @kvm_page_track_notifier_node is linked into
* the head which will be notified when guest is triggering the track event.
@@ -26,54 +24,39 @@ struct kvm_page_track_notifier_node {
* It is called when guest is writing the write-tracked page
* and write emulation is finished at that time.
*
- * @vcpu: the vcpu where the write access happened.
* @gpa: the physical address written by guest.
* @new: the data was written to the address.
* @bytes: the written length.
* @node: this node
*/
- void (*track_write)(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
- int bytes, struct kvm_page_track_notifier_node *node);
+ void (*track_write)(gpa_t gpa, const u8 *new, int bytes,
+ struct kvm_page_track_notifier_node *node);
+
/*
- * It is called when memory slot is being moved or removed
- * users can drop write-protection for the pages in that memory slot
+ * Invoked when a memory region is removed from the guest. Or in KVM
+ * terms, when a memslot is deleted.
*
- * @kvm: the kvm where memory slot being moved or removed
- * @slot: the memory slot being moved or removed
- * @node: this node
+ * @gfn: base gfn of the region being removed
+ * @nr_pages: number of pages in the to-be-removed region
+ * @node: this node
*/
- void (*track_flush_slot)(struct kvm *kvm, struct kvm_memory_slot *slot,
- struct kvm_page_track_notifier_node *node);
+ void (*track_remove_region)(gfn_t gfn, unsigned long nr_pages,
+ struct kvm_page_track_notifier_node *node);
};
-int kvm_page_track_init(struct kvm *kvm);
-void kvm_page_track_cleanup(struct kvm *kvm);
+int kvm_page_track_register_notifier(struct kvm *kvm,
+ struct kvm_page_track_notifier_node *n);
+void kvm_page_track_unregister_notifier(struct kvm *kvm,
+ struct kvm_page_track_notifier_node *n);
-bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
-int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
-
-void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
-int kvm_page_track_create_memslot(struct kvm *kvm,
- struct kvm_memory_slot *slot,
- unsigned long npages);
-
-void kvm_slot_page_track_add_page(struct kvm *kvm,
- struct kvm_memory_slot *slot, gfn_t gfn,
- enum kvm_page_track_mode mode);
-void kvm_slot_page_track_remove_page(struct kvm *kvm,
- struct kvm_memory_slot *slot, gfn_t gfn,
- enum kvm_page_track_mode mode);
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
- const struct kvm_memory_slot *slot,
- gfn_t gfn, enum kvm_page_track_mode mode);
+int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn);
+int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn);
+#else
+/*
+ * Allow defining a node in a structure even if page tracking is disabled, e.g.
+ * to play nice with testing headers via direct inclusion from the command line.
+ */
+struct kvm_page_track_notifier_node {};
+#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */
-void
-kvm_page_track_register_notifier(struct kvm *kvm,
- struct kvm_page_track_notifier_node *n);
-void
-kvm_page_track_unregister_notifier(struct kvm *kvm,
- struct kvm_page_track_notifier_node *n);
-void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
- int bytes);
-void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
#endif
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 97a3de7892d3..571fe4d2d232 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,6 +8,14 @@
#undef notrace
#define notrace __attribute__((no_instrument_function))
+#ifdef CONFIG_64BIT
+/*
+ * The generic version tends to create spurious ENDBR instructions under
+ * certain conditions.
+ */
+#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; })
+#endif
+
#ifdef CONFIG_X86_32
#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
#endif /* CONFIG_X86_32 */
@@ -97,6 +105,13 @@
CFI_POST_PADDING \
SYM_FUNC_END(__cfi_##name)
+/* UML needs to be able to override memcpy() and friends for KASAN. */
+#ifdef CONFIG_UML
+# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS_WEAK
+#else
+# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
#define SYM_TYPED_FUNC_START(name) \
SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 635132a12778..73dba8b94443 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -135,28 +135,27 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
/**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
* @l: pointer of type local_t
* @a: the amount to add to l...
* @u: ...unless l is equal to u.
*
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-#define local_add_unless(l, a, u) \
-({ \
- long c, old; \
- c = local_read((l)); \
- for (;;) { \
- if (unlikely(c == (u))) \
- break; \
- old = local_cmpxchg((l), c, c + (a)); \
- if (likely(old == c)) \
- break; \
- c = old; \
- } \
- c != (u); \
-})
+static __always_inline bool
+local_add_unless(local_t *l, long a, long u)
+{
+ long c = local_read(l);
+
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!local_try_cmpxchg(l, &c, c + a));
+
+ return true;
+}
+
#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
/* On x86_32, these are no better than the atomic variants.
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 180b1cbfcc4e..de3118305838 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -245,7 +245,7 @@ static inline void cmci_recheck(void) {}
int mce_available(struct cpuinfo_x86 *c);
bool mce_is_memory_error(struct mce *m);
bool mce_is_correctable(struct mce *m);
-int mce_usable_address(struct mce *m);
+bool mce_usable_address(struct mce *m);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
@@ -311,6 +311,7 @@ enum smca_bank_types {
SMCA_PIE, /* Power, Interrupts, etc. */
SMCA_UMC, /* Unified Memory Controller */
SMCA_UMC_V2,
+ SMCA_MA_LLC, /* Memory Attached Last Level Cache */
SMCA_PB, /* Parameter Block */
SMCA_PSP, /* Platform Security Processor */
SMCA_PSP_V2,
@@ -326,6 +327,8 @@ enum smca_bank_types {
SMCA_SHUB, /* System HUB Unit */
SMCA_SATA, /* SATA Unit */
SMCA_USB, /* USB Unit */
+ SMCA_USR_DP, /* Ultra Short Reach Data Plane Controller */
+ SMCA_USR_CP, /* Ultra Short Reach Control Plane Controller */
SMCA_GMI_PCS, /* GMI PCS Unit */
SMCA_XGMI_PHY, /* xGMI PHY Unit */
SMCA_WAFL_PHY, /* WAFL PHY Unit */
@@ -333,7 +336,6 @@ enum smca_bank_types {
N_SMCA_BANK_TYPES
};
-extern const char *smca_get_long_name(enum smca_bank_types t);
extern bool amd_mce_is_memory_error(struct mce *m);
extern int mce_threshold_create_device(unsigned int cpu);
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 473b16d73b47..359ada486fa9 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -19,8 +19,10 @@
#ifdef CONFIG_X86_MEM_ENCRYPT
void __init mem_encrypt_init(void);
+void __init mem_encrypt_setup_arch(void);
#else
static inline void mem_encrypt_init(void) { }
+static inline void __init mem_encrypt_setup_arch(void) { }
#endif
#ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -43,7 +45,6 @@ void __init sme_map_bootdata(char *real_mode_data);
void __init sme_unmap_bootdata(char *real_mode_data);
void __init sme_early_init(void);
-void __init sev_setup_arch(void);
void __init sme_encrypt_kernel(struct boot_params *bp);
void __init sme_enable(struct boot_params *bp);
@@ -73,7 +74,6 @@ static inline void __init sme_map_bootdata(char *real_mode_data) { }
static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
static inline void __init sme_early_init(void) { }
-static inline void __init sev_setup_arch(void) { }
static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
static inline void __init sme_enable(struct boot_params *bp) { }
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index bbbe9d744977..695e569159c1 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -23,6 +23,8 @@ static inline void load_ucode_ap(void) { }
static inline void microcode_bsp_resume(void) { }
#endif
+extern unsigned long initrd_start_early;
+
#ifdef CONFIG_CPU_SUP_INTEL
/* Intel specific microcode defines. Public for IFS */
struct microcode_header_intel {
@@ -36,7 +38,8 @@ struct microcode_header_intel {
unsigned int datasize;
unsigned int totalsize;
unsigned int metasize;
- unsigned int reserved[2];
+ unsigned int min_req_ver;
+ unsigned int reserved;
};
struct microcode_intel {
@@ -68,11 +71,19 @@ static inline u32 intel_get_microcode_revision(void)
return rev;
}
+#endif /* !CONFIG_CPU_SUP_INTEL */
-void show_ucode_info_early(void);
+bool microcode_nmi_handler(void);
+void microcode_offline_nmi_handler(void);
-#else /* CONFIG_CPU_SUP_INTEL */
-static inline void show_ucode_info_early(void) { }
-#endif /* !CONFIG_CPU_SUP_INTEL */
+#ifdef CONFIG_MICROCODE_LATE_LOADING
+DECLARE_STATIC_KEY_FALSE(microcode_nmi_handler_enable);
+static __always_inline bool microcode_nmi_handler_enabled(void)
+{
+ return static_branch_unlikely(&microcode_nmi_handler_enable);
+}
+#else
+static __always_inline bool microcode_nmi_handler_enabled(void) { return false; }
+#endif
#endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
new file mode 100644
index 000000000000..12b820259b9f
--- /dev/null
+++ b/arch/x86/include/asm/mman.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#define arch_calc_vm_prot_bits(prot, key) ( \
+ ((key) & 0x1 ? VM_PKEY_BIT0 : 0) | \
+ ((key) & 0x2 ? VM_PKEY_BIT1 : 0) | \
+ ((key) & 0x4 ? VM_PKEY_BIT2 : 0) | \
+ ((key) & 0x8 ? VM_PKEY_BIT3 : 0))
+#endif
+
+#include <uapi/asm/mman.h>
+
+#endif /* __ASM_MMAN_H__ */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 416901d406f8..8dac45a2c7fc 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -186,8 +186,7 @@ do { \
#else
#define deactivate_mm(tsk, mm) \
do { \
- if (!tsk->vfork_done) \
- shstk_free(tsk); \
+ shstk_free(tsk); \
load_gs_index(0); \
loadsegment(fs, 0); \
} while (0)
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index f46df8349e86..4b0f98a8d338 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -37,7 +37,7 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES];
extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
-extern unsigned int boot_cpu_physical_apicid;
+extern u32 boot_cpu_physical_apicid;
extern u8 boot_cpu_apic_version;
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 033b53f993c6..ce4ce8720d55 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -276,11 +276,11 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
#ifdef CONFIG_AMD_MEM_ENCRYPT
bool hv_ghcb_negotiate_protocol(void);
void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason);
-int hv_snp_boot_ap(int cpu, unsigned long start_ip);
+int hv_snp_boot_ap(u32 cpu, unsigned long start_ip);
#else
static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
-static inline int hv_snp_boot_ap(int cpu, unsigned long start_ip) { return 0; }
+static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; }
#endif
#if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST)
@@ -340,8 +340,10 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; }
#ifdef CONFIG_HYPERV_VTL_MODE
void __init hv_vtl_init_platform(void);
+int __init hv_vtl_early_init(void);
#else
static inline void __init hv_vtl_init_platform(void) {}
+static inline int __init hv_vtl_early_init(void) { return 0; }
#endif
#include <asm-generic/mshyperv.h>
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1d111350197f..f1bd7b91b3c6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -222,6 +222,7 @@
#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
#define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4
#define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
+#define MSR_INTEGRITY_CAPS_SAF_GEN_MASK GENMASK_ULL(10, 9)
#define MSR_LBR_NHM_FROM 0x00000680
#define MSR_LBR_NHM_TO 0x000006c0
@@ -236,6 +237,11 @@
#define LBR_INFO_CYCLES 0xffff
#define LBR_INFO_BR_TYPE_OFFSET 56
#define LBR_INFO_BR_TYPE (0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET 32
+#define LBR_INFO_BR_CNTR_NUM 4
+#define LBR_INFO_BR_CNTR_BITS 2
+#define LBR_INFO_BR_CNTR_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
#define MSR_ARCH_LBR_CTL 0x000014ce
#define ARCH_LBR_CTL_LBREN BIT(0)
@@ -535,6 +541,9 @@
#define MSR_RELOAD_PMC0 0x000014c1
#define MSR_RELOAD_FIXED_CTR0 0x00001309
+/* KeyID partitioning between MKTME and TDX */
+#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087
+
/*
* AMD64 MSRs. Not complete. See the architecture manual for a more
* complete list.
@@ -553,6 +562,7 @@
#define MSR_AMD64_CPUID_FN_1 0xc0011004
#define MSR_AMD64_LS_CFG 0xc0011020
#define MSR_AMD64_DC_CFG 0xc0011022
+#define MSR_AMD64_TW_CFG 0xc0011023
#define MSR_AMD64_DE_CFG 0xc0011029
#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1
@@ -637,12 +647,21 @@
/* AMD Last Branch Record MSRs */
#define MSR_AMD64_LBR_SELECT 0xc000010e
+/* Zen4 */
+#define MSR_ZEN4_BP_CFG 0xc001102e
+#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
+
+/* Fam 19h MSRs */
+#define MSR_F19H_UMC_PERF_CTL 0xc0010800
+#define MSR_F19H_UMC_PERF_CTR 0xc0010801
+
+/* Zen 2 */
+#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1)
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
-#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3
-#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1)
-
/* Fam 16h MSRs */
#define MSR_F16H_L2I_PERF_CTL 0xc0010230
#define MSR_F16H_L2I_PERF_CTR 0xc0010231
@@ -1112,12 +1131,16 @@
#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14)
#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
-/* AMD-V MSRs */
+/* AMD-V MSRs */
#define MSR_VM_CR 0xc0010114
#define MSR_VM_IGNNE 0xc0010115
#define MSR_VM_HSAVE_PA 0xc0010117
+#define SVM_VM_CR_VALID_MASK 0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
+
/* Hardware Feedback Interface */
#define MSR_IA32_HW_FEEDBACK_PTR 0x17d0
#define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 778df05f8539..920426d691ce 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -87,6 +87,15 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
:: "a" (eax), "b" (ebx), "c" (ecx));
}
+/*
+ * Re-enable interrupts right upon calling mwait in such a way that
+ * no interrupt can fire _before_ the execution of mwait, ie: no
+ * instruction must be placed between "sti" and "mwait".
+ *
+ * This is necessary because if an interrupt queues a timer before
+ * executing mwait, it would otherwise go unnoticed and the next tick
+ * would not be reprogrammed accordingly before mwait ever wakes up.
+ */
static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
{
mds_idle_clear_cpu_buffers();
@@ -115,8 +124,15 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo
}
__monitor((void *)&current_thread_info()->flags, 0, 0);
- if (!need_resched())
- __mwait(eax, ecx);
+
+ if (!need_resched()) {
+ if (ecx & 1) {
+ __mwait(eax, ecx);
+ } else {
+ __sti_mwait(eax, ecx);
+ raw_local_irq_disable();
+ }
+ }
}
current_clr_polling();
}
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 65fbf6b853af..691ff1ef701b 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -49,7 +49,7 @@
* but there is still a cushion vs. the RSB depth. The algorithm does not
* claim to be perfect and it can be speculated around by the CPU, but it
* is considered that it obfuscates the problem enough to make exploitation
- * extremly difficult.
+ * extremely difficult.
*/
#define RET_DEPTH_SHIFT 5
#define RSB_RET_STUFF_LOOPS 16
@@ -187,7 +187,7 @@
.macro ANNOTATE_RETPOLINE_SAFE
.Lhere_\@:
.pushsection .discard.retpoline_safe
- .long .Lhere_\@ - .
+ .long .Lhere_\@
.popsection
.endm
@@ -199,7 +199,7 @@
/*
* Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should
- * eventually turn into it's own annotation.
+ * eventually turn into its own annotation.
*/
.macro VALIDATE_UNRET_END
#if defined(CONFIG_NOINSTR_VALIDATION) && \
@@ -262,7 +262,7 @@
.Lskip_rsb_\@:
.endm
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
#define CALL_UNTRAIN_RET "call entry_untrain_ret"
#else
#define CALL_UNTRAIN_RET ""
@@ -279,38 +279,24 @@
* As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
* where we have a stack but before any RET instruction.
*/
-.macro UNTRAIN_RET
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
+.macro __UNTRAIN_RET ibpb_feature, call_depth_insns
+#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY)
VALIDATE_UNRET_END
ALTERNATIVE_3 "", \
CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+ "call entry_ibpb", \ibpb_feature, \
+ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
.endm
-.macro UNTRAIN_RET_VM
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
-#endif
-.endm
+#define UNTRAIN_RET \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH)
-.macro UNTRAIN_RET_FROM_CALL
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH
-#endif
-.endm
+#define UNTRAIN_RET_VM \
+ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH)
+
+#define UNTRAIN_RET_FROM_CALL \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL)
.macro CALL_DEPTH_ACCOUNT
@@ -325,7 +311,7 @@
#define ANNOTATE_RETPOLINE_SAFE \
"999:\n\t" \
".pushsection .discard.retpoline_safe\n\t" \
- ".long 999b - .\n\t" \
+ ".long 999b\n\t" \
".popsection\n\t"
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
@@ -339,13 +325,23 @@ extern void __x86_return_thunk(void);
static inline void __x86_return_thunk(void) {}
#endif
+#ifdef CONFIG_CPU_UNRET_ENTRY
extern void retbleed_return_thunk(void);
+#else
+static inline void retbleed_return_thunk(void) {}
+#endif
+
+#ifdef CONFIG_CPU_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
+#else
+static inline void srso_return_thunk(void) {}
+static inline void srso_alias_return_thunk(void) {}
+#endif
-extern void retbleed_untrain_ret(void);
-extern void srso_untrain_ret(void);
-extern void srso_alias_untrain_ret(void);
+extern void retbleed_return_thunk(void);
+extern void srso_return_thunk(void);
+extern void srso_alias_return_thunk(void);
extern void entry_untrain_ret(void);
extern void entry_ibpb(void);
@@ -353,12 +349,7 @@ extern void entry_ibpb(void);
extern void (*x86_return_thunk)(void);
#ifdef CONFIG_CALL_DEPTH_TRACKING
-extern void __x86_return_skl(void);
-
-static inline void x86_set_skl_return_thunk(void)
-{
- x86_return_thunk = &__x86_return_skl;
-}
+extern void call_depth_return_thunk(void);
#define CALL_DEPTH_ACCOUNT \
ALTERNATIVE("", \
@@ -371,12 +362,12 @@ DECLARE_PER_CPU(u64, __x86_ret_count);
DECLARE_PER_CPU(u64, __x86_stuffs_count);
DECLARE_PER_CPU(u64, __x86_ctxsw_count);
#endif
-#else
-static inline void x86_set_skl_return_thunk(void) {}
+#else /* !CONFIG_CALL_DEPTH_TRACKING */
+static inline void call_depth_return_thunk(void) {}
#define CALL_DEPTH_ACCOUNT ""
-#endif
+#endif /* CONFIG_CALL_DEPTH_TRACKING */
#ifdef CONFIG_RETPOLINE
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index e3bae2b60a0d..ef2844d69173 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -12,13 +12,6 @@
#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-/*
- * Too small node sizes may confuse the VM badly. Usually they
- * result from BIOS bugs. So dont recognize nodes as standalone
- * NUMA entities that have less than this amount of RAM listed:
- */
-#define NODE_MIN_SIZE (4*1024*1024)
-
extern int numa_off;
/*
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6c8ff12140ae..d4eb9e1d61b8 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -6,6 +6,10 @@
#include <asm/paravirt_types.h>
+#ifndef __ASSEMBLY__
+struct mm_struct;
+#endif
+
#ifdef CONFIG_PARAVIRT
#include <asm/pgtable_types.h>
#include <asm/asm.h>
@@ -142,8 +146,7 @@ static inline void write_cr0(unsigned long x)
static __always_inline unsigned long read_cr2(void)
{
return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
- "mov %%cr2, %%rax;",
- ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%cr2, %%rax;", ALT_NOT_XEN);
}
static __always_inline void write_cr2(unsigned long x)
@@ -154,13 +157,12 @@ static __always_inline void write_cr2(unsigned long x)
static inline unsigned long __read_cr3(void)
{
return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
- "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%cr3, %%rax;", ALT_NOT_XEN);
}
static inline void write_cr3(unsigned long x)
{
- PVOP_ALT_VCALL1(mmu.write_cr3, x,
- "mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
+ PVOP_ALT_VCALL1(mmu.write_cr3, x, "mov %%rdi, %%cr3", ALT_NOT_XEN);
}
static inline void __write_cr4(unsigned long x)
@@ -182,7 +184,7 @@ extern noinstr void pv_native_wbinvd(void);
static __always_inline void wbinvd(void)
{
- PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
+ PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN);
}
static inline u64 paravirt_read_msr(unsigned msr)
@@ -390,27 +392,25 @@ static inline void paravirt_release_p4d(unsigned long pfn)
static inline pte_t __pte(pteval_t val)
{
return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
- "mov %%rdi, %%rax",
- ALT_NOT(X86_FEATURE_XENPV)) };
+ "mov %%rdi, %%rax", ALT_NOT_XEN) };
}
static inline pteval_t pte_val(pte_t pte)
{
return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
- "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%rdi, %%rax", ALT_NOT_XEN);
}
static inline pgd_t __pgd(pgdval_t val)
{
return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
- "mov %%rdi, %%rax",
- ALT_NOT(X86_FEATURE_XENPV)) };
+ "mov %%rdi, %%rax", ALT_NOT_XEN) };
}
static inline pgdval_t pgd_val(pgd_t pgd)
{
return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
- "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%rdi, %%rax", ALT_NOT_XEN);
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -444,14 +444,13 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
static inline pmd_t __pmd(pmdval_t val)
{
return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
- "mov %%rdi, %%rax",
- ALT_NOT(X86_FEATURE_XENPV)) };
+ "mov %%rdi, %%rax", ALT_NOT_XEN) };
}
static inline pmdval_t pmd_val(pmd_t pmd)
{
return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
- "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%rdi, %%rax", ALT_NOT_XEN);
}
static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -464,7 +463,7 @@ static inline pud_t __pud(pudval_t val)
pudval_t ret;
ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
- "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%rdi, %%rax", ALT_NOT_XEN);
return (pud_t) { ret };
}
@@ -472,7 +471,7 @@ static inline pud_t __pud(pudval_t val)
static inline pudval_t pud_val(pud_t pud)
{
return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
- "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%rdi, %%rax", ALT_NOT_XEN);
}
static inline void pud_clear(pud_t *pudp)
@@ -492,8 +491,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
static inline p4d_t __p4d(p4dval_t val)
{
p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
- "mov %%rdi, %%rax",
- ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%rdi, %%rax", ALT_NOT_XEN);
return (p4d_t) { ret };
}
@@ -501,7 +499,7 @@ static inline p4d_t __p4d(p4dval_t val)
static inline p4dval_t p4d_val(p4d_t p4d)
{
return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
- "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
+ "mov %%rdi, %%rax", ALT_NOT_XEN);
}
static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
@@ -687,17 +685,17 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
static __always_inline unsigned long arch_local_save_flags(void)
{
return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
- ALT_NOT(X86_FEATURE_XENPV));
+ ALT_NOT_XEN);
}
static __always_inline void arch_local_irq_disable(void)
{
- PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
+ PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT_XEN);
}
static __always_inline void arch_local_irq_enable(void)
{
- PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
+ PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT_XEN);
}
static __always_inline unsigned long arch_local_irq_save(void)
@@ -726,52 +724,25 @@ static __always_inline unsigned long arch_local_irq_save(void)
#undef PVOP_VCALL4
#undef PVOP_CALL4
-#define DEFINE_PARAVIRT_ASM(func, instr, sec) \
- asm (".pushsection " #sec ", \"ax\"\n" \
- ".global " #func "\n\t" \
- ".type " #func ", @function\n\t" \
- ASM_FUNC_ALIGN "\n" \
- #func ":\n\t" \
- ASM_ENDBR \
- instr "\n\t" \
- ASM_RET \
- ".size " #func ", . - " #func "\n\t" \
- ".popsection")
-
extern void default_banner(void);
void native_pv_lock_init(void) __init;
#else /* __ASSEMBLY__ */
-#define _PVSITE(ptype, ops, word, algn) \
-771:; \
- ops; \
-772:; \
- .pushsection .parainstructions,"a"; \
- .align algn; \
- word 771b; \
- .byte ptype; \
- .byte 772b-771b; \
- _ASM_ALIGN; \
- .popsection
-
-
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT_XXL
+#ifdef CONFIG_DEBUG_ENTRY
-#define PARA_PATCH(off) ((off) / 8)
-#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
-#ifdef CONFIG_DEBUG_ENTRY
.macro PARA_IRQ_save_fl
- PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),
- ANNOTATE_RETPOLINE_SAFE;
- call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);)
+ ANNOTATE_RETPOLINE_SAFE;
+ call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);
.endm
-#define SAVE_FLAGS ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \
- ALT_NOT(X86_FEATURE_XENPV)
+#define SAVE_FLAGS ALTERNATIVE_2 "PARA_IRQ_save_fl;", \
+ "ALT_CALL_INSTR;", ALT_CALL_ALWAYS, \
+ "pushf; pop %rax;", ALT_NOT_XEN
#endif
#endif /* CONFIG_PARAVIRT_XXL */
#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 4acbcddddc29..8d4fbe1be489 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -2,25 +2,10 @@
#ifndef _ASM_X86_PARAVIRT_TYPES_H
#define _ASM_X86_PARAVIRT_TYPES_H
-#ifndef __ASSEMBLY__
-/* These all sit in the .parainstructions section to tell us what to patch. */
-struct paravirt_patch_site {
- u8 *instr; /* original instructions */
- u8 type; /* type of this instruction */
- u8 len; /* length of original instruction */
-};
-
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
- PARAVIRT_LAZY_NONE,
- PARAVIRT_LAZY_MMU,
- PARAVIRT_LAZY_CPU,
-};
-#endif
-
#ifdef CONFIG_PARAVIRT
#ifndef __ASSEMBLY__
+#include <linux/types.h>
#include <asm/desc_defs.h>
#include <asm/pgtable_types.h>
@@ -257,43 +242,11 @@ struct paravirt_patch_template {
extern struct pv_info pv_info;
extern struct paravirt_patch_template pv_ops;
-#define PARAVIRT_PATCH(x) \
- (offsetof(struct paravirt_patch_template, x) / sizeof(void *))
-
-#define paravirt_type(op) \
- [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \
- [paravirt_opptr] "m" (pv_ops.op)
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type) \
- "771:\n\t" insn_string "\n" "772:\n" \
- ".pushsection .parainstructions,\"a\"\n" \
- _ASM_ALIGN "\n" \
- _ASM_PTR " 771b\n" \
- " .byte " type "\n" \
- " .byte 772b-771b\n" \
- _ASM_ALIGN "\n" \
- ".popsection\n"
-
-/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string) \
- _paravirt_alt(insn_string, "%c[paravirt_typenum]")
-
-/* Simple instruction patching code. */
-#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
-
-unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
+#define paravirt_ptr(op) [paravirt_opptr] "m" (pv_ops.op)
int paravirt_disable_iospace(void);
-/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
+/* This generates an indirect call based on the operation type number. */
#define PARAVIRT_CALL \
ANNOTATE_RETPOLINE_SAFE \
"call *%[paravirt_opptr];"
@@ -326,12 +279,6 @@ int paravirt_disable_iospace(void);
* However, x86_64 also has to clobber all caller saved registers, which
* unfortunately, are quite a bit (r8 - r11)
*
- * The call instruction itself is marked by placing its start address
- * and size into the .parainstructions section, so that
- * apply_paravirt() in arch/i386/kernel/alternative.c can do the
- * appropriate patching under the control of the backend pv_init_ops
- * implementation.
- *
* Unfortunately there's no way to get gcc to generate the args setup
* for the call, and then allow the call itself to be generated by an
* inline asm. Because of this, we must do the complete arg setup and
@@ -430,14 +377,27 @@ int paravirt_disable_iospace(void);
__mask & __eax; \
})
-
+/*
+ * Use alternative patching for paravirt calls:
+ * - For replacing an indirect call with a direct one, use the "normal"
+ * ALTERNATIVE() macro with the indirect call as the initial code sequence,
+ * which will be replaced with the related direct call by using the
+ * ALT_FLAG_DIRECT_CALL special case and the "always on" feature.
+ * - In case the replacement is either a direct call or a short code sequence
+ * depending on a feature bit, the ALTERNATIVE_2() macro is being used.
+ * The indirect call is the initial code sequence again, while the special
+ * code sequence is selected with the specified feature bit. In case the
+ * feature is not active, the direct call is used as above via the
+ * ALT_FLAG_DIRECT_CALL special case and the "always on" feature.
+ */
#define ____PVOP_CALL(ret, op, call_clbr, extra_clbr, ...) \
({ \
PVOP_CALL_ARGS; \
PVOP_TEST_NULL(op); \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
+ asm volatile(ALTERNATIVE(PARAVIRT_CALL, ALT_CALL_INSTR, \
+ ALT_CALL_ALWAYS) \
: call_clbr, ASM_CALL_CONSTRAINT \
- : paravirt_type(op), \
+ : paravirt_ptr(op), \
##__VA_ARGS__ \
: "memory", "cc" extra_clbr); \
ret; \
@@ -448,10 +408,11 @@ int paravirt_disable_iospace(void);
({ \
PVOP_CALL_ARGS; \
PVOP_TEST_NULL(op); \
- asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL), \
- alt, cond) \
+ asm volatile(ALTERNATIVE_2(PARAVIRT_CALL, \
+ ALT_CALL_INSTR, ALT_CALL_ALWAYS, \
+ alt, cond) \
: call_clbr, ASM_CALL_CONSTRAINT \
- : paravirt_type(op), \
+ : paravirt_ptr(op), \
##__VA_ARGS__ \
: "memory", "cc" extra_clbr); \
ret; \
@@ -549,16 +510,6 @@ int paravirt_disable_iospace(void);
__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_start_context_switch(struct task_struct *prev);
-void paravirt_end_context_switch(struct task_struct *next);
-
-void paravirt_enter_lazy_mmu(void);
-void paravirt_leave_lazy_mmu(void);
-void paravirt_flush_lazy_mmu(void);
-
-void _paravirt_nop(void);
-void paravirt_BUG(void);
unsigned long paravirt_ret0(void);
#ifdef CONFIG_PARAVIRT_XXL
u64 _paravirt_ident_64(u64);
@@ -568,11 +519,11 @@ void pv_native_irq_enable(void);
unsigned long pv_native_read_cr2(void);
#endif
-#define paravirt_nop ((void *)_paravirt_nop)
-
-extern struct paravirt_patch_site __parainstructions[],
- __parainstructions_end[];
+#define paravirt_nop ((void *)nop_func)
#endif /* __ASSEMBLY__ */
+
+#define ALT_NOT_XEN ALT_NOT(X86_FEATURE_XENPV)
+
#endif /* CONFIG_PARAVIRT */
#endif /* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e56a37886143..44958ebaf626 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -29,8 +29,8 @@
#else /* ...!ASSEMBLY */
#include <linux/build_bug.h>
-#include <linux/kernel.h>
#include <linux/stringify.h>
+#include <asm/asm.h>
#ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 85a9fd5a3ec3..3736b8a46c04 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -31,6 +31,7 @@
#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23)
#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
+#define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35)
#define INTEL_FIXED_BITS_MASK 0xFULL
#define INTEL_FIXED_BITS_STRIDE 4
@@ -112,6 +113,13 @@
(AMD64_PERFMON_V2_EVENTSEL_EVENT_NB | \
AMD64_PERFMON_V2_EVENTSEL_UMASK_NB)
+#define AMD64_PERFMON_V2_ENABLE_UMC BIT_ULL(31)
+#define AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC GENMASK_ULL(7, 0)
+#define AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC GENMASK_ULL(9, 8)
+#define AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC \
+ (AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC | \
+ AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC)
+
#define AMD64_NUM_COUNTERS 4
#define AMD64_NUM_COUNTERS_CORE 6
#define AMD64_NUM_COUNTERS_NB 4
@@ -216,6 +224,9 @@ union cpuid28_ecx {
unsigned int lbr_timed_lbr:1;
/* Branch Type Field Supported */
unsigned int lbr_br_type:1;
+ unsigned int reserved:13;
+ /* Branch counters (Event Logging) Supported */
+ unsigned int lbr_counters:4;
} split;
unsigned int full;
};
@@ -232,6 +243,8 @@ union cpuid_0x80000022_ebx {
unsigned int lbr_v2_stack_sz:6;
/* Number of Data Fabric Counters */
unsigned int num_df_pmc:6;
+ /* Number of Unified Memory Controller Counters */
+ unsigned int num_umc_pmc:6;
} split;
unsigned int full;
};
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index d6ad98ca1288..9d077bca6a10 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -141,6 +141,7 @@ static inline int pte_young(pte_t pte)
return pte_flags(pte) & _PAGE_ACCESSED;
}
+#define pmd_dirty pmd_dirty
static inline bool pmd_dirty(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_DIRTY_BITS;
@@ -955,6 +956,14 @@ static inline int pte_same(pte_t a, pte_t b)
return a.pte == b.pte;
}
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+ if (__pte_needs_invert(pte_val(pte)))
+ return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
+ return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#define pte_next_pfn pte_next_pfn
+
static inline int pte_present(pte_t a)
{
return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
@@ -1671,12 +1680,6 @@ static inline bool arch_has_pfn_modify_check(void)
return boot_cpu_has_bug(X86_BUG_L1TF);
}
-#define arch_has_hw_pte_young arch_has_hw_pte_young
-static inline bool arch_has_hw_pte_young(void)
-{
- return true;
-}
-
#define arch_check_zapped_pte arch_check_zapped_pte
void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte);
@@ -1708,6 +1711,14 @@ static inline bool pud_user_accessible_page(pud_t pud)
}
#endif
+#ifdef CONFIG_X86_SGX
+int arch_memory_failure(unsigned long pfn, int flags);
+#define arch_memory_failure arch_memory_failure
+
+bool arch_is_platform_page(u64 paddr);
+#define arch_is_platform_page arch_is_platform_page
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index a629b1b9f65a..24af25b1551a 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -203,7 +203,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
* F (2) in swp entry is used to record when a pagetable is
* writeprotected by userfaultfd WP support.
*
- * E (3) in swp entry is used to rememeber PG_anon_exclusive.
+ * E (3) in swp entry is used to remember PG_anon_exclusive.
*
* Bit 7 in swp entry should be 0 because pmd_present checks not only P,
* but also L and G.
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 4b2a35d8d56a..919909d8cb77 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -6,7 +6,6 @@
#include <asm/percpu.h>
#include <asm/current.h>
-#include <linux/thread_info.h>
#include <linux/static_call_types.h>
/* We use the MSB mostly because its available */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a94a857152c4..1188e8bf76a2 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -75,11 +75,36 @@ extern u16 __read_mostly tlb_lld_4m[NR_INFO];
extern u16 __read_mostly tlb_lld_1g[NR_INFO];
/*
- * CPU type and hardware bug flags. Kept separately for each CPU.
- * Members of this structure are referenced in head_32.S, so think twice
- * before touching them. [mj]
+ * CPU type and hardware bug flags. Kept separately for each CPU.
*/
+struct cpuinfo_topology {
+ // Real APIC ID read from the local APIC
+ u32 apicid;
+ // The initial APIC ID provided by CPUID
+ u32 initial_apicid;
+
+ // Physical package ID
+ u32 pkg_id;
+
+ // Physical die ID on AMD, Relative on Intel
+ u32 die_id;
+
+ // Compute unit ID - AMD specific
+ u32 cu_id;
+
+ // Core ID relative to the package
+ u32 core_id;
+
+ // Logical ID mappings
+ u32 logical_pkg_id;
+ u32 logical_die_id;
+
+ // Cache level topology IDs
+ u32 llc_id;
+ u32 l2c_id;
+};
+
struct cpuinfo_x86 {
__u8 x86; /* CPU family */
__u8 x86_vendor; /* CPU vendor */
@@ -96,7 +121,6 @@ struct cpuinfo_x86 {
__u8 x86_phys_bits;
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
- __u8 cu_id;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
@@ -112,6 +136,7 @@ struct cpuinfo_x86 {
};
char x86_vendor_id[16];
char x86_model_id[64];
+ struct cpuinfo_topology topo;
/* in KB - valid for CPUS which support this call: */
unsigned int x86_cache_size;
int x86_cache_alignment; /* In bytes */
@@ -125,19 +150,9 @@ struct cpuinfo_x86 {
u64 ppin;
/* cpuid returned max cores value: */
u16 x86_max_cores;
- u16 apicid;
- u16 initial_apicid;
u16 x86_clflush_size;
/* number of cores as seen by the OS: */
u16 booted_cores;
- /* Physical processor id: */
- u16 phys_proc_id;
- /* Logical processor id: */
- u16 logical_proc_id;
- /* Core id: */
- u16 cpu_core_id;
- u16 cpu_die_id;
- u16 logical_die_id;
/* Index into per_cpu list: */
u16 cpu_index;
/* Is SMT active on this core? */
@@ -399,7 +414,7 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu)
return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
}
-extern asmlinkage void ignore_sysret(void);
+extern asmlinkage void entry_SYSCALL32_ignore(void);
/* Save actual FS/GS selectors and bases to current->thread */
void current_save_fsgs(void);
@@ -681,18 +696,24 @@ extern int set_tsc_mode(unsigned int val);
DECLARE_PER_CPU(u64, msr_misc_features_shadow);
-extern u16 get_llc_id(unsigned int cpu);
+static inline u32 per_cpu_llc_id(unsigned int cpu)
+{
+ return per_cpu(cpu_info.topo.llc_id, cpu);
+}
+
+static inline u32 per_cpu_l2c_id(unsigned int cpu)
+{
+ return per_cpu(cpu_info.topo.l2c_id, cpu);
+}
#ifdef CONFIG_CPU_SUP_AMD
extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
-extern bool cpu_has_ibpb_brtype_microcode(void);
extern void amd_clear_divider(void);
extern void amd_check_microcode(void);
#else
static inline u32 amd_get_nodes_per_socket(void) { return 0; }
static inline u32 amd_get_highest_perf(void) { return 0; }
-static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; }
static inline void amd_clear_divider(void) { }
static inline void amd_check_microcode(void) { }
#endif
@@ -729,14 +750,24 @@ enum mds_mitigations {
MDS_MITIGATION_VMWERV,
};
-#ifdef CONFIG_X86_SGX
-int arch_memory_failure(unsigned long pfn, int flags);
-#define arch_memory_failure arch_memory_failure
-
-bool arch_is_platform_page(u64 paddr);
-#define arch_is_platform_page arch_is_platform_page
-#endif
-
extern bool gds_ucode_mitigated(void);
+/*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions. WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE. The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier. This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+static inline void weak_wrmsr_fence(void)
+{
+ alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE));
+}
+
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index b716d291d0d4..65dee2420624 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -31,6 +31,11 @@ static inline void x86_dtb_init(void) { }
#define of_ioapic 0
#endif
+#ifdef CONFIG_OF_EARLY_FLATTREE
+void x86_flattree_get_config(void);
+#else
+static inline void x86_flattree_get_config(void) { }
+#endif
extern char cmd_line[COMMAND_LINE_SIZE];
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 12ef86b19910..484f4f0131a5 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -32,10 +32,9 @@ void entry_SYSCALL_compat(void);
void entry_SYSCALL_compat_safe_stack(void);
void entry_SYSRETL_compat_unsafe_stack(void);
void entry_SYSRETL_compat_end(void);
-void entry_INT80_compat(void);
-#ifdef CONFIG_XEN_PV
-void xen_entry_INT80_compat(void);
-#endif
+#else /* !CONFIG_IA32_EMULATION */
+#define entry_SYSCALL_compat NULL
+#define entry_SYSENTER_compat NULL
#endif
void x86_configure_nx(void);
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 85b6e3609cb9..ef9697f20129 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -56,8 +56,8 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
"pop %rdx\n\t" \
FRAME_END
-DEFINE_PARAVIRT_ASM(__raw_callee_save___pv_queued_spin_unlock,
- PV_UNLOCK_ASM, .spinlock.text);
+DEFINE_ASM_FUNC(__raw_callee_save___pv_queued_spin_unlock,
+ PV_UNLOCK_ASM, .spinlock.text);
#else /* CONFIG_64BIT */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 9177b4354c3f..6536873f8fc0 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,7 +25,14 @@ void __noreturn machine_real_restart(unsigned int type);
#define MRR_BIOS 0
#define MRR_APM 1
+#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
+typedef void (cpu_emergency_virt_cb)(void);
+void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback);
+void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback);
void cpu_emergency_disable_virtualization(void);
+#else
+static inline void cpu_emergency_disable_virtualization(void) {}
+#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */
typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
void nmi_shootdown_cpus(nmi_shootdown_cb callback);
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4b081e0d3306..363266cbcada 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -13,7 +13,7 @@
#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \
({ \
bool c = false; \
- asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \
+ asm goto (fullop "; j" #cc " %l[cc_label]" \
: : [var] "m" (_var), ## __VA_ARGS__ \
: clobbers : cc_label); \
if (0) { \
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index f3495623ac99..5c83729c8e71 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -31,8 +31,6 @@
#include <asm/bootparam.h>
#include <asm/x86_init.h>
-extern u64 relocated_ramdisk;
-
/* Interrupt control for vSMPowered x86_64 systems */
#ifdef CONFIG_X86_64
void vsmp_init(void);
@@ -126,6 +124,7 @@ void clear_bss(void);
#ifdef __i386__
asmlinkage void __init __noreturn i386_start_kernel(void);
+void __init mk_early_pgtbl_32(void);
#else
asmlinkage void __init __noreturn x86_64_start_kernel(char *real_mode);
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index 7513b3bb69b7..fdfd41511b02 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -11,45 +11,91 @@
#define TDX_IDENT "IntelTDX "
/* TDX module Call Leaf IDs */
-#define TDX_GET_INFO 1
-#define TDX_GET_VEINFO 3
-#define TDX_GET_REPORT 4
-#define TDX_ACCEPT_PAGE 6
-#define TDX_WR 8
+#define TDG_VP_VMCALL 0
+#define TDG_VP_INFO 1
+#define TDG_VP_VEINFO_GET 3
+#define TDG_MR_REPORT 4
+#define TDG_MEM_PAGE_ACCEPT 6
+#define TDG_VM_WR 8
/* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */
#define TDCS_NOTIFY_ENABLES 0x9100000000000010
/* TDX hypercall Leaf IDs */
#define TDVMCALL_MAP_GPA 0x10001
+#define TDVMCALL_GET_QUOTE 0x10002
#define TDVMCALL_REPORT_FATAL_ERROR 0x10003
+#define TDVMCALL_STATUS_RETRY 1
+
+/*
+ * Bitmasks of exposed registers (with VMM).
+ */
+#define TDX_RDX BIT(2)
+#define TDX_RBX BIT(3)
+#define TDX_RSI BIT(6)
+#define TDX_RDI BIT(7)
+#define TDX_R8 BIT(8)
+#define TDX_R9 BIT(9)
+#define TDX_R10 BIT(10)
+#define TDX_R11 BIT(11)
+#define TDX_R12 BIT(12)
+#define TDX_R13 BIT(13)
+#define TDX_R14 BIT(14)
+#define TDX_R15 BIT(15)
+
+/*
+ * These registers are clobbered to hold arguments for each
+ * TDVMCALL. They are safe to expose to the VMM.
+ * Each bit in this mask represents a register ID. Bit field
+ * details can be found in TDX GHCI specification, section
+ * titled "TDCALL [TDG.VP.VMCALL] leaf".
+ */
+#define TDVMCALL_EXPOSE_REGS_MASK \
+ (TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \
+ TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15)
+
+/* TDX supported page sizes from the TDX module ABI. */
+#define TDX_PS_4K 0
+#define TDX_PS_2M 1
+#define TDX_PS_1G 2
+#define TDX_PS_NR (TDX_PS_1G + 1)
+
#ifndef __ASSEMBLY__
+#include <linux/compiler_attributes.h>
+
/*
- * Used in __tdx_hypercall() to pass down and get back registers' values of
- * the TDCALL instruction when requesting services from the VMM.
- *
- * This is a software only structure and not part of the TDX module/VMM ABI.
+ * Used in __tdcall*() to gather the input/output registers' values of the
+ * TDCALL instruction when requesting services from the TDX module. This is a
+ * software only structure and not part of the TDX module/VMM ABI
*/
-struct tdx_hypercall_args {
+struct tdx_module_args {
+ /* callee-clobbered */
+ u64 rcx;
+ u64 rdx;
u64 r8;
u64 r9;
+ /* extra callee-clobbered */
u64 r10;
u64 r11;
+ /* callee-saved + rdi/rsi */
u64 r12;
u64 r13;
u64 r14;
u64 r15;
+ u64 rbx;
u64 rdi;
u64 rsi;
- u64 rbx;
- u64 rdx;
};
+/* Used to communicate with the TDX module */
+u64 __tdcall(u64 fn, struct tdx_module_args *args);
+u64 __tdcall_ret(u64 fn, struct tdx_module_args *args);
+u64 __tdcall_saved_ret(u64 fn, struct tdx_module_args *args);
+
/* Used to request services from the VMM */
-u64 __tdx_hypercall(struct tdx_hypercall_args *args);
-u64 __tdx_hypercall_ret(struct tdx_hypercall_args *args);
+u64 __tdx_hypercall(struct tdx_module_args *args);
/*
* Wrapper for standard use of __tdx_hypercall with no output aside from
@@ -57,7 +103,7 @@ u64 __tdx_hypercall_ret(struct tdx_hypercall_args *args);
*/
static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15)
{
- struct tdx_hypercall_args args = {
+ struct tdx_module_args args = {
.r10 = TDX_HYPERCALL_STANDARD,
.r11 = fn,
.r12 = r12,
@@ -71,25 +117,7 @@ static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15)
/* Called from __tdx_hypercall() for unrecoverable failure */
-void __tdx_hypercall_failed(void);
-
-/*
- * Used in __tdx_module_call() to gather the output registers' values of the
- * TDCALL instruction when requesting services from the TDX module. This is a
- * software only structure and not part of the TDX module/VMM ABI
- */
-struct tdx_module_output {
- u64 rcx;
- u64 rdx;
- u64 r8;
- u64 r9;
- u64 r10;
- u64 r11;
-};
-
-/* Used to communicate with the TDX module */
-u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
- struct tdx_module_output *out);
+void __noreturn __tdx_hypercall_failed(void);
bool tdx_accept_memory(phys_addr_t start, phys_addr_t end);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ad98dd1d9cfb..4fab2ed454f3 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -17,10 +17,8 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
/* cpus sharing the last level cache: */
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
-DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
-DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
-DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid);
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
struct task_struct;
@@ -129,7 +127,6 @@ void native_smp_send_reschedule(int cpu);
void native_send_call_func_ipi(const struct cpumask *mask);
void native_send_call_func_single_ipi(int cpu);
-bool smp_park_other_cpus_in_init(void);
void smp_store_cpu_info(int id);
asmlinkage __visible void smp_reboot_interrupt(void);
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 64df897c0ee3..1be13b2dfe8b 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -37,6 +37,8 @@ extern int phys_to_target_node(phys_addr_t start);
#define phys_to_target_node phys_to_target_node
extern int memory_add_physaddr_to_nid(u64 start);
#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+extern int numa_fill_memblks(u64 start, u64 end);
+#define numa_fill_memblks numa_fill_memblks
#endif
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index cb0386fc4dc3..c648502e4535 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -4,6 +4,7 @@
#include <linux/thread_info.h>
#include <asm/nospec-branch.h>
+#include <asm/msr.h>
/*
* On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
@@ -76,6 +77,16 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
}
+/*
+ * This can be used in noinstr functions & should only be called in bare
+ * metal context.
+ */
+static __always_inline void __update_spec_ctrl(u64 val)
+{
+ __this_cpu_write(x86_spec_ctrl_current, val);
+ native_wrmsrl(MSR_IA32_SPEC_CTRL, val);
+}
+
#ifdef CONFIG_SMP
extern void speculative_store_bypass_ht_init(void);
#else
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d6cd9344f6c7..48f8dd47cf68 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p)
#ifdef CONFIG_X86_USER_SHADOW_STACK
static inline int write_user_shstk_64(u64 __user *addr, u64 val)
{
- asm_volatile_goto("1: wrussq %[val], (%[addr])\n"
+ asm goto("1: wrussq %[val], (%[addr])\n"
_ASM_EXTABLE(1b, %l[fail])
:: [addr] "r" (addr), [val] "r" (val)
:: fail);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index e7c7379d6ac7..87a7b917d30e 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -229,10 +229,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
-#define SVM_VM_CR_VALID_MASK 0x001fULL
-#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
-#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
-
#define SVM_NESTED_CTL_NP_ENABLE BIT(0)
#define SVM_NESTED_CTL_SEV_ENABLE BIT(1)
#define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2)
@@ -268,6 +264,7 @@ enum avic_ipi_failure_cause {
AVIC_IPI_FAILURE_TARGET_NOT_RUNNING,
AVIC_IPI_FAILURE_INVALID_TARGET,
AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
+ AVIC_IPI_FAILURE_INVALID_IPI_VECTOR,
};
#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0)
@@ -288,6 +285,7 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF)
+#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5)
struct vmcb_seg {
u16 selector;
@@ -345,7 +343,7 @@ struct vmcb_save_area {
u64 last_excp_from;
u64 last_excp_to;
u8 reserved_0x298[72];
- u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */
+ u64 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */
} __packed;
/* Save area definition for SEV-ES and SEV-SNP guests */
@@ -512,7 +510,7 @@ struct ghcb {
} __packed;
-#define EXPECTED_VMCB_SAVE_AREA_SIZE 740
+#define EXPECTED_VMCB_SAVE_AREA_SIZE 744
#define EXPECTED_GHCB_SAVE_AREA_SIZE 1032
#define EXPECTED_SEV_ES_SAVE_AREA_SIZE 1648
#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024
@@ -570,8 +568,6 @@ struct vmcb {
#define SVM_CPUID_FUNC 0x8000000a
-#define SVM_VM_CR_SVM_DISABLE 4
-
#define SVM_SELECTOR_S_SHIFT 4
#define SVM_SELECTOR_DPL_SHIFT 5
#define SVM_SELECTOR_P_SHIFT 7
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 4fb36fba4b5a..f44e2f9ab65d 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -126,12 +126,12 @@ static inline int syscall_get_arch(struct task_struct *task)
? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
}
-void do_syscall_64(struct pt_regs *regs, int nr);
+bool do_syscall_64(struct pt_regs *regs, int nr);
#endif /* CONFIG_X86_32 */
void do_int80_syscall_32(struct pt_regs *regs);
-long do_fast_syscall_32(struct pt_regs *regs);
-long do_SYSENTER_32(struct pt_regs *regs);
+bool do_fast_syscall_32(struct pt_regs *regs);
+bool do_SYSENTER_32(struct pt_regs *regs);
#endif /* _ASM_X86_SYSCALL_H */
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index fd2669b1cb2d..7e88705e907f 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
,,regs->di,,regs->si,,regs->dx \
,,regs->r10,,regs->r8,,regs->r9) \
+
+/* SYSCALL_PT_ARGS is Adapted from s390x */
+#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6) \
+ SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp))
+#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5) \
+ SYSCALL_PT_ARG4(m, t1, t2, t3, t4), m(t5, (regs->di))
+#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4) \
+ SYSCALL_PT_ARG3(m, t1, t2, t3), m(t4, (regs->si))
+#define SYSCALL_PT_ARG3(m, t1, t2, t3) \
+ SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx))
+#define SYSCALL_PT_ARG2(m, t1, t2) \
+ SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx))
+#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx))
+#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__)
+
+#define __SC_COMPAT_CAST(t, a) \
+ (__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U))) \
+ (unsigned int)a
+
/* Mapping of registers to parameters for syscalls on i386 */
#define SC_IA32_REGS_TO_ARGS(x, ...) \
- __MAP(x,__SC_ARGS \
- ,,(unsigned int)regs->bx,,(unsigned int)regs->cx \
- ,,(unsigned int)regs->dx,,(unsigned int)regs->si \
- ,,(unsigned int)regs->di,,(unsigned int)regs->bp)
+ SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST, \
+ __MAP(x, __SC_TYPE, __VA_ARGS__)) \
#define __SYS_STUB0(abi, name) \
long __##abi##_##name(const struct pt_regs *regs); \
@@ -86,9 +103,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
return sys_ni_syscall(); \
}
-#define __SYS_NI(abi, name) \
- SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers);
-
#ifdef CONFIG_X86_64
#define __X64_SYS_STUB0(name) \
__SYS_STUB0(x64, sys_##name)
@@ -100,13 +114,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
#define __X64_COND_SYSCALL(name) \
__COND_SYSCALL(x64, sys_##name)
-#define __X64_SYS_NI(name) \
- __SYS_NI(x64, sys_##name)
#else /* CONFIG_X86_64 */
#define __X64_SYS_STUB0(name)
#define __X64_SYS_STUBx(x, name, ...)
#define __X64_COND_SYSCALL(name)
-#define __X64_SYS_NI(name)
#endif /* CONFIG_X86_64 */
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
@@ -120,13 +131,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
#define __IA32_COND_SYSCALL(name) \
__COND_SYSCALL(ia32, sys_##name)
-#define __IA32_SYS_NI(name) \
- __SYS_NI(ia32, sys_##name)
#else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
#define __IA32_SYS_STUB0(name)
#define __IA32_SYS_STUBx(x, name, ...)
#define __IA32_COND_SYSCALL(name)
-#define __IA32_SYS_NI(name)
#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
#ifdef CONFIG_IA32_EMULATION
@@ -135,8 +143,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
* additional wrappers (aptly named __ia32_sys_xyzzy) which decode the
* ia32 regs in the proper order for shared or "common" syscalls. As some
* syscalls may not be implemented, we need to expand COND_SYSCALL in
- * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
- * case as well.
+ * kernel/sys_ni.c to cover this case as well.
*/
#define __IA32_COMPAT_SYS_STUB0(name) \
__SYS_STUB0(ia32, compat_sys_##name)
@@ -148,14 +155,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
#define __IA32_COMPAT_COND_SYSCALL(name) \
__COND_SYSCALL(ia32, compat_sys_##name)
-#define __IA32_COMPAT_SYS_NI(name) \
- __SYS_NI(ia32, compat_sys_##name)
-
#else /* CONFIG_IA32_EMULATION */
#define __IA32_COMPAT_SYS_STUB0(name)
#define __IA32_COMPAT_SYS_STUBx(x, name, ...)
#define __IA32_COMPAT_COND_SYSCALL(name)
-#define __IA32_COMPAT_SYS_NI(name)
#endif /* CONFIG_IA32_EMULATION */
@@ -175,13 +178,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
#define __X32_COMPAT_COND_SYSCALL(name) \
__COND_SYSCALL(x64, compat_sys_##name)
-#define __X32_COMPAT_SYS_NI(name) \
- __SYS_NI(x64, compat_sys_##name)
#else /* CONFIG_X86_X32_ABI */
#define __X32_COMPAT_SYS_STUB0(name)
#define __X32_COMPAT_SYS_STUBx(x, name, ...)
#define __X32_COMPAT_COND_SYSCALL(name)
-#define __X32_COMPAT_SYS_NI(name)
#endif /* CONFIG_X86_X32_ABI */
@@ -212,17 +212,12 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
/*
* As some compat syscalls may not be implemented, we need to expand
- * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
- * kernel/time/posix-stubs.c to cover this case as well.
+ * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well.
*/
#define COND_SYSCALL_COMPAT(name) \
__IA32_COMPAT_COND_SYSCALL(name) \
__X32_COMPAT_COND_SYSCALL(name)
-#define COMPAT_SYS_NI(name) \
- __IA32_COMPAT_SYS_NI(name) \
- __X32_COMPAT_SYS_NI(name)
-
#endif /* CONFIG_COMPAT */
#define __SYSCALL_DEFINEx(x, name, ...) \
@@ -243,8 +238,8 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
* As the generic SYSCALL_DEFINE0() macro does not decode any parameters for
* obvious reasons, and passing struct pt_regs *regs to it in %rdi does not
* hurt, we only need to re-define it here to keep the naming congruent to
- * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI()
- * macros to work correctly.
+ * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() macro
+ * to work correctly.
*/
#define SYSCALL_DEFINE0(sname) \
SYSCALL_METADATA(_##sname, 0); \
@@ -257,10 +252,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
__X64_COND_SYSCALL(name) \
__IA32_COND_SYSCALL(name)
-#define SYS_NI(name) \
- __X64_SYS_NI(name) \
- __IA32_SYS_NI(name)
-
/*
* For VSYSCALLS, we need to declare these three syscalls with the new
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 603e6d1e9d4a..eba178996d84 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -8,6 +8,7 @@
#include <asm/errno.h>
#include <asm/ptrace.h>
+#include <asm/trapnr.h>
#include <asm/shared/tdx.h>
/*
@@ -20,8 +21,19 @@
#define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40))
#define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000))
+#define TDX_SEAMCALL_GP (TDX_SW_ERROR | X86_TRAP_GP)
+#define TDX_SEAMCALL_UD (TDX_SW_ERROR | X86_TRAP_UD)
+
+/*
+ * TDX module SEAMCALL leaf function error codes
+ */
+#define TDX_SUCCESS 0ULL
+#define TDX_RND_NO_ENTROPY 0x8000020300000000ULL
+
#ifndef __ASSEMBLY__
+#include <uapi/asm/mce.h>
+
/*
* Used by the #VE exception handler to gather the #VE exception
* info from the TDX module. This is a software only structure
@@ -52,6 +64,8 @@ bool tdx_early_handle_ve(struct pt_regs *regs);
int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport);
+u64 tdx_hcall_get_quote(u8 *buf, size_t size);
+
#else
static inline void tdx_early_init(void) { };
@@ -72,5 +86,42 @@ static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1,
return -ENODEV;
}
#endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */
+
+#ifdef CONFIG_INTEL_TDX_HOST
+u64 __seamcall(u64 fn, struct tdx_module_args *args);
+u64 __seamcall_ret(u64 fn, struct tdx_module_args *args);
+u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args);
+void tdx_init(void);
+
+#include <asm/archrandom.h>
+
+typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
+
+static inline u64 sc_retry(sc_func_t func, u64 fn,
+ struct tdx_module_args *args)
+{
+ int retry = RDRAND_RETRY_LOOPS;
+ u64 ret;
+
+ do {
+ ret = func(fn, args);
+ } while (ret == TDX_RND_NO_ENTROPY && --retry);
+
+ return ret;
+}
+
+#define seamcall(_fn, _args) sc_retry(__seamcall, (_fn), (_args))
+#define seamcall_ret(_fn, _args) sc_retry(__seamcall_ret, (_fn), (_args))
+#define seamcall_saved_ret(_fn, _args) sc_retry(__seamcall_saved_ret, (_fn), (_args))
+int tdx_cpu_enable(void);
+int tdx_enable(void);
+const char *tdx_dump_mce_info(struct mce *m);
+#else
+static inline void tdx_init(void) { }
+static inline int tdx_cpu_enable(void) { return -ENODEV; }
+static inline int tdx_enable(void) { return -ENODEV; }
+static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
+#endif /* CONFIG_INTEL_TDX_HOST */
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_TDX_H */
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index fb338f00d383..345aafbc1964 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -6,20 +6,6 @@
#include <linux/stddef.h>
#include <asm/ptrace.h>
-struct paravirt_patch_site;
-#ifdef CONFIG_PARAVIRT
-void apply_paravirt(struct paravirt_patch_site *start,
- struct paravirt_patch_site *end);
-#else
-static inline void apply_paravirt(struct paravirt_patch_site *start,
- struct paravirt_patch_site *end)
-{}
-#define __parainstructions NULL
-#define __parainstructions_end NULL
-#endif
-
-extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
-
/*
* Currently, the max observed size in the kernel code is
* JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
@@ -29,6 +15,8 @@ extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_
extern void text_poke_early(void *addr, const void *opcode, size_t len);
+extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
+
/*
* Clear and restore the kernel write-protection flag on the local CPU.
* Allows the kernel to edit read-only pages.
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 3235ba1e5b06..5f87f6b9b09e 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -105,17 +105,17 @@ static inline void setup_node_to_cpumask_map(void) { }
extern const struct cpumask *cpu_coregroup_mask(int cpu);
extern const struct cpumask *cpu_clustergroup_mask(int cpu);
-#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id)
-#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
-#define topology_logical_die_id(cpu) (cpu_data(cpu).logical_die_id)
-#define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id)
-#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
+#define topology_logical_package_id(cpu) (cpu_data(cpu).topo.logical_pkg_id)
+#define topology_physical_package_id(cpu) (cpu_data(cpu).topo.pkg_id)
+#define topology_logical_die_id(cpu) (cpu_data(cpu).topo.logical_die_id)
+#define topology_die_id(cpu) (cpu_data(cpu).topo.die_id)
+#define topology_core_id(cpu) (cpu_data(cpu).topo.core_id)
#define topology_ppin(cpu) (cpu_data(cpu).ppin)
extern unsigned int __max_die_per_package;
#ifdef CONFIG_SMP
-#define topology_cluster_id(cpu) (per_cpu(cpu_l2c_id, cpu))
+#define topology_cluster_id(cpu) (cpu_data(cpu).topo.l2c_id)
#define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu))
#define topology_cluster_cpumask(cpu) (cpu_clustergroup_mask(cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index b1c9cea6ba88..1f1deaecd364 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -14,7 +14,6 @@
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
asmlinkage __visible notrace
struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
-void __init trap_init(void);
asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
#endif
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8bae40a66282..237dc8cdd12b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -133,7 +133,7 @@ extern int __get_user_bad(void);
#ifdef CONFIG_X86_32
#define __put_user_goto_u64(x, addr, label) \
- asm_volatile_goto("\n" \
+ asm goto("\n" \
"1: movl %%eax,0(%1)\n" \
"2: movl %%edx,4(%1)\n" \
_ASM_EXTABLE_UA(1b, %l2) \
@@ -295,7 +295,7 @@ do { \
} while (0)
#define __get_user_asm(x, addr, itype, ltype, label) \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: mov"itype" %[umem],%[output]\n" \
_ASM_EXTABLE_UA(1b, %l2) \
: [output] ltype(x) \
@@ -375,7 +375,7 @@ do { \
__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \
__typeof__(*(_ptr)) __old = *_old; \
__typeof__(*(_ptr)) __new = (_new); \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
_ASM_EXTABLE_UA(1b, %l[label]) \
: CC_OUT(z) (success), \
@@ -394,7 +394,7 @@ do { \
__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \
__typeof__(*(_ptr)) __old = *_old; \
__typeof__(*(_ptr)) __new = (_new); \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \
_ASM_EXTABLE_UA(1b, %l[label]) \
: CC_OUT(z) (success), \
@@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; };
* aliasing issues.
*/
#define __put_user_goto(x, addr, itype, ltype, label) \
- asm_volatile_goto("\n" \
+ asm goto("\n" \
"1: mov"itype" %0,%1\n" \
_ASM_EXTABLE_UA(1b, %l2) \
: : ltype(x), "m" (__m(addr)) \
@@ -496,7 +496,7 @@ copy_mc_to_kernel(void *to, const void *from, unsigned len);
#define copy_mc_to_kernel copy_mc_to_kernel
unsigned long __must_check
-copy_mc_to_user(void *to, const void *from, unsigned len);
+copy_mc_to_user(void __user *to, const void *from, unsigned len);
#endif
/*
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 5fa76c2ced51..ea877fd83114 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -653,7 +653,7 @@ static inline int uv_blade_to_node(int blade)
return uv_socket_to_node(blade);
}
-/* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
+/* Blade number of current cpu. Numbered 0 .. <#blades -1> */
static inline int uv_numa_blade_id(void)
{
return uv_hub_info->numa_blade_id;
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index c81858d903dc..8e048ca980df 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -321,7 +321,7 @@ static __always_inline
u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
{
/*
- * Due to the MSB/Sign-bit being used as invald marker (see
+ * Due to the MSB/Sign-bit being used as invalid marker (see
* arch_vdso_cycles_valid() above), the effective mask is S64_MAX.
*/
u64 delta = (cycles - last) & S64_MAX;
@@ -337,8 +337,6 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
}
#define vdso_calc_delta vdso_calc_delta
-int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
-
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
deleted file mode 100644
index 3b12e6b99412..000000000000
--- a/arch/x86/include/asm/virtext.h
+++ /dev/null
@@ -1,154 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/* CPU virtualization extensions handling
- *
- * This should carry the code for handling CPU virtualization extensions
- * that needs to live in the kernel core.
- *
- * Author: Eduardo Habkost <ehabkost@redhat.com>
- *
- * Copyright (C) 2008, Red Hat Inc.
- *
- * Contains code from KVM, Copyright (C) 2006 Qumranet, Inc.
- */
-#ifndef _ASM_X86_VIRTEX_H
-#define _ASM_X86_VIRTEX_H
-
-#include <asm/processor.h>
-
-#include <asm/vmx.h>
-#include <asm/svm.h>
-#include <asm/tlbflush.h>
-
-/*
- * VMX functions:
- */
-
-static inline int cpu_has_vmx(void)
-{
- unsigned long ecx = cpuid_ecx(1);
- return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
-}
-
-
-/**
- * cpu_vmxoff() - Disable VMX on the current CPU
- *
- * Disable VMX and clear CR4.VMXE (even if VMXOFF faults)
- *
- * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to
- * atomically track post-VMXON state, e.g. this may be called in NMI context.
- * Eat all faults as all other faults on VMXOFF faults are mode related, i.e.
- * faults are guaranteed to be due to the !post-VMXON check unless the CPU is
- * magically in RM, VM86, compat mode, or at CPL>0.
- */
-static inline int cpu_vmxoff(void)
-{
- asm_volatile_goto("1: vmxoff\n\t"
- _ASM_EXTABLE(1b, %l[fault])
- ::: "cc", "memory" : fault);
-
- cr4_clear_bits(X86_CR4_VMXE);
- return 0;
-
-fault:
- cr4_clear_bits(X86_CR4_VMXE);
- return -EIO;
-}
-
-static inline int cpu_vmx_enabled(void)
-{
- return __read_cr4() & X86_CR4_VMXE;
-}
-
-/** Disable VMX if it is enabled on the current CPU
- *
- * You shouldn't call this if cpu_has_vmx() returns 0.
- */
-static inline void __cpu_emergency_vmxoff(void)
-{
- if (cpu_vmx_enabled())
- cpu_vmxoff();
-}
-
-/** Disable VMX if it is supported and enabled on the current CPU
- */
-static inline void cpu_emergency_vmxoff(void)
-{
- if (cpu_has_vmx())
- __cpu_emergency_vmxoff();
-}
-
-
-
-
-/*
- * SVM functions:
- */
-
-/** Check if the CPU has SVM support
- *
- * You can use the 'msg' arg to get a message describing the problem,
- * if the function returns zero. Simply pass NULL if you are not interested
- * on the messages; gcc should take care of not generating code for
- * the messages on this case.
- */
-static inline int cpu_has_svm(const char **msg)
-{
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
- boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) {
- if (msg)
- *msg = "not amd or hygon";
- return 0;
- }
-
- if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) {
- if (msg)
- *msg = "can't execute cpuid_8000000a";
- return 0;
- }
-
- if (!boot_cpu_has(X86_FEATURE_SVM)) {
- if (msg)
- *msg = "svm not available";
- return 0;
- }
- return 1;
-}
-
-
-/** Disable SVM on the current CPU
- *
- * You should call this only if cpu_has_svm() returned true.
- */
-static inline void cpu_svm_disable(void)
-{
- uint64_t efer;
-
- wrmsrl(MSR_VM_HSAVE_PA, 0);
- rdmsrl(MSR_EFER, efer);
- if (efer & EFER_SVME) {
- /*
- * Force GIF=1 prior to disabling SVM to ensure INIT and NMI
- * aren't blocked, e.g. if a fatal error occurred between CLGI
- * and STGI. Note, STGI may #UD if SVM is disabled from NMI
- * context between reading EFER and executing STGI. In that
- * case, GIF must already be set, otherwise the NMI would have
- * been blocked, so just eat the fault.
- */
- asm_volatile_goto("1: stgi\n\t"
- _ASM_EXTABLE(1b, %l[fault])
- ::: "memory" : fault);
-fault:
- wrmsrl(MSR_EFER, efer & ~EFER_SVME);
- }
-}
-
-/** Makes sure SVM is disabled, if it is supported on the CPU
- */
-static inline void cpu_emergency_svm_disable(void)
-{
- if (cpu_has_svm(NULL))
- cpu_svm_disable();
-}
-
-#endif /* _ASM_X86_VIRTEX_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 0d02c4aafa6f..0e73616b82f3 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -71,7 +71,7 @@
#define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING)
#define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING)
#define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX)
-#define SECONDARY_EXEC_XSAVES VMCS_CONTROL_BIT(XSAVES)
+#define SECONDARY_EXEC_ENABLE_XSAVES VMCS_CONTROL_BIT(XSAVES)
#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
#define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA)
#define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 5240d88db52a..c878616a18b8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -177,7 +177,7 @@ struct x86_init_ops {
* struct x86_cpuinit_ops - platform specific cpu hotplug setups
* @setup_percpu_clockev: set up the per cpu clock event device
* @early_percpu_clock_init: early init of the per cpu clock event device
- * @fixup_cpu_id: fixup function for cpuinfo_x86::phys_proc_id
+ * @fixup_cpu_id: fixup function for cpuinfo_x86::topo.pkg_id
* @parallel_bringup: Parallel bringup control
*/
struct x86_cpuinit_ops {
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 5fc35f889cd1..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -36,6 +36,7 @@
extern struct shared_info *HYPERVISOR_shared_info;
extern struct start_info *xen_start_info;
+#include <asm/bug.h>
#include <asm/processor.h>
#define XEN_SIGNATURE "XenVMMXenVMM"
@@ -63,4 +64,49 @@ void __init xen_pvh_init(struct boot_params *boot_params);
void __init mem_map_via_hcall(struct boot_params *boot_params_p);
#endif
+/* Lazy mode for batching updates / context switch */
+enum xen_lazy_mode {
+ XEN_LAZY_NONE,
+ XEN_LAZY_MMU,
+ XEN_LAZY_CPU,
+};
+
+DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode);
+DECLARE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+static inline void enter_lazy(enum xen_lazy_mode mode)
+{
+ enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode);
+
+ if (mode == old_mode) {
+ this_cpu_inc(xen_lazy_nesting);
+ return;
+ }
+
+ BUG_ON(old_mode != XEN_LAZY_NONE);
+
+ this_cpu_write(xen_lazy_mode, mode);
+}
+
+static inline void leave_lazy(enum xen_lazy_mode mode)
+{
+ BUG_ON(this_cpu_read(xen_lazy_mode) != mode);
+
+ if (this_cpu_read(xen_lazy_nesting) == 0)
+ this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE);
+ else
+ this_cpu_dec(xen_lazy_nesting);
+}
+
+enum xen_lazy_mode xen_get_lazy_mode(void);
+
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+ BUG();
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index c599ec269a25..c10f279aae93 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -61,7 +61,7 @@
* RING1 -> RING3 kernel mode.
* RING2 -> RING3 kernel mode.
* RING3 -> RING3 user mode.
- * However RING0 indicates that the guest kernel should return to iteself
+ * However RING0 indicates that the guest kernel should return to itself
* directly with
* orb $3,1*8(%rsp)
* iretq