summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig39
-rw-r--r--arch/x86/Kconfig.assembler2
-rw-r--r--arch/x86/boot/compressed/kaslr.c43
-rw-r--r--arch/x86/boot/compressed/misc.c5
-rw-r--r--arch/x86/boot/compressed/sev.c86
-rw-r--r--arch/x86/boot/cpucheck.c2
-rw-r--r--arch/x86/boot/main.c42
-rw-r--r--arch/x86/coco/Makefile1
-rw-r--r--arch/x86/coco/core.c1
-rw-r--r--arch/x86/coco/sev/Makefile15
-rw-r--r--arch/x86/coco/sev/core.c (renamed from arch/x86/kernel/sev.c)449
-rw-r--r--arch/x86/coco/sev/shared.c (renamed from arch/x86/kernel/sev-shared.c)460
-rw-r--r--arch/x86/coco/tdx/tdx.c121
-rw-r--r--arch/x86/crypto/Kconfig1
-rw-r--r--arch/x86/crypto/Makefile8
-rw-r--r--arch/x86/crypto/aes-gcm-aesni-x86_64.S1128
-rw-r--r--arch/x86/crypto/aes-gcm-avx10-x86_64.S1222
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S1503
-rw-r--r--arch/x86/crypto/aesni-intel_avx-x86_64.S2804
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c1269
-rw-r--r--arch/x86/crypto/crc32-pclmul_glue.c1
-rw-r--r--arch/x86/crypto/curve25519-x86_64.c1
-rw-r--r--arch/x86/crypto/poly1305_glue.c4
-rw-r--r--arch/x86/crypto/twofish_glue_3way.c9
-rw-r--r--arch/x86/entry/entry_64_compat.S14
-rw-r--r--arch/x86/entry/syscall_32.c10
-rw-r--r--arch/x86/entry/syscall_64.c9
-rw-r--r--arch/x86/entry/syscall_x32.c7
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl7
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl8
-rw-r--r--arch/x86/events/amd/core.c28
-rw-r--r--arch/x86/events/amd/uncore.c36
-rw-r--r--arch/x86/events/core.c113
-rw-r--r--arch/x86/events/intel/core.c638
-rw-r--r--arch/x86/events/intel/cstate.c39
-rw-r--r--arch/x86/events/intel/ds.c180
-rw-r--r--arch/x86/events/intel/knc.c2
-rw-r--r--arch/x86/events/intel/p4.c10
-rw-r--r--arch/x86/events/intel/p6.c2
-rw-r--r--arch/x86/events/intel/pt.c4
-rw-r--r--arch/x86/events/intel/pt.h4
-rw-r--r--arch/x86/events/intel/uncore.c97
-rw-r--r--arch/x86/events/intel/uncore.h8
-rw-r--r--arch/x86/events/intel/uncore_discovery.c306
-rw-r--r--arch/x86/events/intel/uncore_discovery.h22
-rw-r--r--arch/x86/events/intel/uncore_snbep.c134
-rw-r--r--arch/x86/events/perf_event.h98
-rw-r--r--arch/x86/events/rapl.c90
-rw-r--r--arch/x86/events/zhaoxin/core.c12
-rw-r--r--arch/x86/hyperv/ivm.c22
-rw-r--r--arch/x86/include/asm/acpi.h7
-rw-r--r--arch/x86/include/asm/alternative.h241
-rw-r--r--arch/x86/include/asm/amd_nb.h4
-rw-r--r--arch/x86/include/asm/cfi.h2
-rw-r--r--arch/x86/include/asm/cpu_device_id.h8
-rw-r--r--arch/x86/include/asm/cpufeatures.h803
-rw-r--r--arch/x86/include/asm/efi.h22
-rw-r--r--arch/x86/include/asm/ftrace.h2
-rw-r--r--arch/x86/include/asm/init.h3
-rw-r--r--arch/x86/include/asm/intel_ds.h1
-rw-r--r--arch/x86/include/asm/intel_pconfig.h65
-rw-r--r--arch/x86/include/asm/irqflags.h20
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h8
-rw-r--r--arch/x86/include/asm/kvm-x86-pmu-ops.h3
-rw-r--r--arch/x86/include/asm/kvm_host.h90
-rw-r--r--arch/x86/include/asm/mce.h3
-rw-r--r--arch/x86/include/asm/msr-index.h11
-rw-r--r--arch/x86/include/asm/page_64.h2
-rw-r--r--arch/x86/include/asm/percpu.h533
-rw-r--r--arch/x86/include/asm/perf_event.h8
-rw-r--r--arch/x86/include/asm/pgtable.h5
-rw-r--r--arch/x86/include/asm/pgtable_types.h1
-rw-r--r--arch/x86/include/asm/processor.h12
-rw-r--r--arch/x86/include/asm/runtime-const.h61
-rw-r--r--arch/x86/include/asm/set_memory.h3
-rw-r--r--arch/x86/include/asm/setup.h8
-rw-r--r--arch/x86/include/asm/sev-common.h43
-rw-r--r--arch/x86/include/asm/sev.h186
-rw-r--r--arch/x86/include/asm/shstk.h4
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/svm.h9
-rw-r--r--arch/x86/include/asm/tsc.h3
-rw-r--r--arch/x86/include/asm/unistd.h1
-rw-r--r--arch/x86/include/asm/vdso/gettimeofday.h5
-rw-r--r--arch/x86/include/asm/vdso/vsyscall.h1
-rw-r--r--arch/x86/include/asm/vgtod.h5
-rw-r--r--arch/x86/include/asm/vmware.h336
-rw-r--r--arch/x86/include/asm/vmxfeatures.h110
-rw-r--r--arch/x86/include/asm/word-at-a-time.h57
-rw-r--r--arch/x86/include/asm/x86_init.h14
-rw-r--r--arch/x86/include/uapi/asm/kvm.h49
-rw-r--r--arch/x86/include/uapi/asm/svm.h1
-rw-r--r--arch/x86/kernel/Makefile6
-rw-r--r--arch/x86/kernel/acpi/Makefile1
-rw-r--r--arch/x86/kernel/acpi/boot.c86
-rw-r--r--arch/x86/kernel/acpi/madt_playdead.S28
-rw-r--r--arch/x86/kernel/acpi/madt_wakeup.c292
-rw-r--r--arch/x86/kernel/alternative.c30
-rw-r--r--arch/x86/kernel/amd_nb.c44
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/amd.c11
-rw-r--r--arch/x86/kernel/cpu/bugs.c16
-rw-r--r--arch/x86/kernel/cpu/intel.c188
-rw-r--r--arch/x86/kernel/cpu/intel_pconfig.c84
-rw-r--r--arch/x86/kernel/cpu/mce/core.c7
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c9
-rw-r--r--arch/x86/kernel/cpu/mkcapflags.sh3
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c312
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c89
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h108
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c250
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c42
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c288
-rw-r--r--arch/x86/kernel/cpu/scattered.c1
-rw-r--r--arch/x86/kernel/cpu/vmware.c225
-rw-r--r--arch/x86/kernel/crash.c12
-rw-r--r--arch/x86/kernel/devicetree.c2
-rw-r--r--arch/x86/kernel/e820.c9
-rw-r--r--arch/x86/kernel/early-quirks.c85
-rw-r--r--arch/x86/kernel/fpu/xstate.h14
-rw-r--r--arch/x86/kernel/process.c7
-rw-r--r--arch/x86/kernel/reboot.c18
-rw-r--r--arch/x86/kernel/relocate_kernel_64.S27
-rw-r--r--arch/x86/kernel/setup.c3
-rw-r--r--arch/x86/kernel/shstk.c16
-rw-r--r--arch/x86/kernel/tsc.c92
-rw-r--r--arch/x86/kernel/uprobes.c124
-rw-r--r--arch/x86/kernel/vmlinux.lds.S3
-rw-r--r--arch/x86/kernel/x86_init.c8
-rw-r--r--arch/x86/kvm/Kconfig4
-rw-r--r--arch/x86/kvm/cpuid.c14
-rw-r--r--arch/x86/kvm/cpuid.h18
-rw-r--r--arch/x86/kvm/emulate.c73
-rw-r--r--arch/x86/kvm/hyperv.c9
-rw-r--r--arch/x86/kvm/irq.c2
-rw-r--r--arch/x86/kvm/irq.h1
-rw-r--r--arch/x86/kvm/irq_comm.c7
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h10
-rw-r--r--arch/x86/kvm/kvm_emulate.h1
-rw-r--r--arch/x86/kvm/lapic.c48
-rw-r--r--arch/x86/kvm/lapic.h5
-rw-r--r--arch/x86/kvm/mmu.h42
-rw-r--r--arch/x86/kvm/mmu/mmu.c206
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h26
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h3
-rw-r--r--arch/x86/kvm/mmu/spte.c46
-rw-r--r--arch/x86/kvm/mmu/spte.h10
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c136
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h2
-rw-r--r--arch/x86/kvm/mtrr.c644
-rw-r--r--arch/x86/kvm/pmu.c73
-rw-r--r--arch/x86/kvm/pmu.h10
-rw-r--r--arch/x86/kvm/smm.c44
-rw-r--r--arch/x86/kvm/svm/nested.c2
-rw-r--r--arch/x86/kvm/svm/pmu.c11
-rw-r--r--arch/x86/kvm/svm/sev.c1564
-rw-r--r--arch/x86/kvm/svm/svm.c78
-rw-r--r--arch/x86/kvm/svm/svm.h70
-rw-r--r--arch/x86/kvm/trace.h55
-rw-r--r--arch/x86/kvm/vmx/main.c5
-rw-r--r--arch/x86/kvm/vmx/nested.c55
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c52
-rw-r--r--arch/x86/kvm/vmx/posted_intr.h10
-rw-r--r--arch/x86/kvm/vmx/vmcs12.h14
-rw-r--r--arch/x86/kvm/vmx/vmx.c205
-rw-r--r--arch/x86/kvm/vmx/vmx.h3
-rw-r--r--arch/x86/kvm/vmx/x86_ops.h4
-rw-r--r--arch/x86/kvm/x86.c567
-rw-r--r--arch/x86/kvm/x86.h25
-rw-r--r--arch/x86/kvm/xen.c6
-rw-r--r--arch/x86/lib/cmdline.c8
-rw-r--r--arch/x86/lib/getuser.S69
-rw-r--r--arch/x86/lib/iomem.c5
-rw-r--r--arch/x86/mm/ident_map.c73
-rw-r--r--arch/x86/mm/init_64.c30
-rw-r--r--arch/x86/mm/mem_encrypt_amd.c16
-rw-r--r--arch/x86/mm/pat/set_memory.c79
-rw-r--r--arch/x86/net/bpf_jit_comp.c15
-rw-r--r--arch/x86/pci/intel_mid_pci.c8
-rw-r--r--arch/x86/pci/xen.c4
-rw-r--r--arch/x86/platform/atom/punit_atom_debug.c11
-rw-r--r--arch/x86/platform/efi/Makefile1
-rw-r--r--arch/x86/platform/efi/efi.c2
-rw-r--r--arch/x86/platform/efi/fake_mem.c197
-rw-r--r--arch/x86/platform/efi/memmap.c1
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c6
-rw-r--r--arch/x86/platform/intel/iosf_mbi.c4
-rw-r--r--arch/x86/um/sys_call_table_32.c10
-rw-r--r--arch/x86/um/sys_call_table_64.c11
-rw-r--r--arch/x86/virt/svm/sev.c44
-rw-r--r--arch/x86/virt/vmx/tdx/tdx.c8
-rw-r--r--arch/x86/xen/apic.c2
-rw-r--r--arch/x86/xen/debugfs.c2
-rw-r--r--arch/x86/xen/debugfs.h7
-rw-r--r--arch/x86/xen/enlighten.c2
-rw-r--r--arch/x86/xen/enlighten_hvm.c2
-rw-r--r--arch/x86/xen/enlighten_pv.c4
-rw-r--r--arch/x86/xen/mmu.c3
-rw-r--r--arch/x86/xen/mmu.h28
-rw-r--r--arch/x86/xen/mmu_hvm.c2
-rw-r--r--arch/x86/xen/mmu_pv.c15
-rw-r--r--arch/x86/xen/multicalls.c128
-rw-r--r--arch/x86/xen/multicalls.h69
-rw-r--r--arch/x86/xen/p2m.c6
-rw-r--r--arch/x86/xen/pmu.c1
-rw-r--r--arch/x86/xen/pmu.h22
-rw-r--r--arch/x86/xen/setup.c1
-rw-r--r--arch/x86/xen/smp.c1
-rw-r--r--arch/x86/xen/smp.h51
-rw-r--r--arch/x86/xen/smp_hvm.c2
-rw-r--r--arch/x86/xen/smp_pv.c3
-rw-r--r--arch/x86/xen/spinlock.c20
-rw-r--r--arch/x86/xen/suspend.c2
-rw-r--r--arch/x86/xen/time.c2
-rw-r--r--arch/x86/xen/xen-ops.h148
215 files changed, 11986 insertions, 9708 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d7122a1883e..cbe5fac4b9dd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1118,6 +1118,13 @@ config X86_LOCAL_APIC
depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
select IRQ_DOMAIN_HIERARCHY
+config ACPI_MADT_WAKEUP
+ def_bool y
+ depends on X86_64
+ depends on ACPI
+ depends on SMP
+ depends on X86_LOCAL_APIC
+
config X86_IO_APIC
def_bool y
depends on X86_LOCAL_APIC || X86_UP_IOAPIC
@@ -2038,26 +2045,6 @@ config EFI_MIXED
If unsure, say N.
-config EFI_FAKE_MEMMAP
- bool "Enable EFI fake memory map"
- depends on EFI
- help
- Saying Y here will enable "efi_fake_mem" boot option. By specifying
- this parameter, you can add arbitrary attribute to specific memory
- range by updating original (firmware provided) EFI memmap. This is
- useful for debugging of EFI memmap related feature, e.g., Address
- Range Mirroring feature.
-
-config EFI_MAX_FAKE_MEM
- int "maximum allowable number of ranges in efi_fake_mem boot option"
- depends on EFI_FAKE_MEMMAP
- range 1 128
- default 8
- help
- Maximum allowable number of ranges in efi_fake_mem boot option.
- Ranges can be set up to this value using comma-separated list.
- The default value is 8.
-
config EFI_RUNTIME_MAP
bool "Export EFI runtime maps to sysfs" if EXPERT
depends on EFI
@@ -2427,12 +2414,22 @@ config STRICT_SIGALTSTACK_SIZE
Say 'N' unless you want to really enforce this check.
+config CFI_AUTO_DEFAULT
+ bool "Attempt to use FineIBT by default at boot time"
+ depends on FINEIBT
+ default y
+ help
+ Attempt to use FineIBT by default at boot time. If enabled,
+ this is the same as booting with "cfi=auto". If disabled,
+ this is the same as booting with "cfi=kcfi".
+
source "kernel/livepatch/Kconfig"
endmenu
config CC_HAS_NAMED_AS
- def_bool CC_IS_GCC && GCC_VERSION >= 90100
+ def_bool $(success,echo 'int __seg_fs fs; int __seg_gs gs;' | $(CC) -x c - -S -o /dev/null)
+ depends on CC_IS_GCC
config CC_HAS_NAMED_AS_FIXED_SANITIZERS
def_bool CC_IS_GCC && GCC_VERSION >= 130300
diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 59aedf32c4ea..6d20a6ce0507 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -36,6 +36,6 @@ config AS_VPCLMULQDQ
Supported by binutils >= 2.30 and LLVM integrated assembler
config AS_WRUSS
- def_bool $(as-instr,wrussq %rax$(comma)(%rbx))
+ def_bool $(as-instr64,wrussq %rax$(comma)(%rbx))
help
Supported by binutils >= 2.31 and LLVM integrated assembler
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index dec961c6d16a..f4d82379bf44 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -119,13 +119,8 @@ char *skip_spaces(const char *str)
#include "../../../../lib/ctype.c"
#include "../../../../lib/cmdline.c"
-enum parse_mode {
- PARSE_MEMMAP,
- PARSE_EFI,
-};
-
static int
-parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode)
+parse_memmap(char *p, u64 *start, u64 *size)
{
char *oldp;
@@ -148,29 +143,11 @@ parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode)
*start = memparse(p + 1, &p);
return 0;
case '@':
- if (mode == PARSE_MEMMAP) {
- /*
- * memmap=nn@ss specifies usable region, should
- * be skipped
- */
- *size = 0;
- } else {
- u64 flags;
-
- /*
- * efi_fake_mem=nn@ss:attr the attr specifies
- * flags that might imply a soft-reservation.
- */
- *start = memparse(p + 1, &p);
- if (p && *p == ':') {
- p++;
- if (kstrtoull(p, 0, &flags) < 0)
- *size = 0;
- else if (flags & EFI_MEMORY_SP)
- return 0;
- }
- *size = 0;
- }
+ /*
+ * memmap=nn@ss specifies usable region, should
+ * be skipped
+ */
+ *size = 0;
fallthrough;
default:
/*
@@ -185,7 +162,7 @@ parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode)
return -EINVAL;
}
-static void mem_avoid_memmap(enum parse_mode mode, char *str)
+static void mem_avoid_memmap(char *str)
{
static int i;
@@ -200,7 +177,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str)
if (k)
*k++ = 0;
- rc = parse_memmap(str, &start, &size, mode);
+ rc = parse_memmap(str, &start, &size);
if (rc < 0)
break;
str = k;
@@ -281,7 +258,7 @@ static void handle_mem_options(void)
break;
if (!strcmp(param, "memmap")) {
- mem_avoid_memmap(PARSE_MEMMAP, val);
+ mem_avoid_memmap(val);
} else if (IS_ENABLED(CONFIG_X86_64) && strstr(param, "hugepages")) {
parse_gb_huge_pages(param, val);
} else if (!strcmp(param, "mem")) {
@@ -295,8 +272,6 @@ static void handle_mem_options(void)
if (mem_size < mem_limit)
mem_limit = mem_size;
- } else if (!strcmp(param, "efi_fake_mem")) {
- mem_avoid_memmap(PARSE_EFI, val);
}
}
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b70e4a21c15f..944454306ef4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -531,8 +531,3 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
return output + entry_offset;
}
-
-void __fortify_panic(const u8 reason, size_t avail, size_t size)
-{
- error("detected buffer overflow");
-}
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 0457a9d7e515..cd44e120fe53 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -127,7 +127,35 @@ static bool fault_in_kernel_space(unsigned long address)
#include "../../lib/insn.c"
/* Include code for early handlers */
-#include "../../kernel/sev-shared.c"
+#include "../../coco/sev/shared.c"
+
+static struct svsm_ca *svsm_get_caa(void)
+{
+ return boot_svsm_caa;
+}
+
+static u64 svsm_get_caa_pa(void)
+{
+ return boot_svsm_caa_pa;
+}
+
+static int svsm_perform_call_protocol(struct svsm_call *call)
+{
+ struct ghcb *ghcb;
+ int ret;
+
+ if (boot_ghcb)
+ ghcb = boot_ghcb;
+ else
+ ghcb = NULL;
+
+ do {
+ ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
+ : svsm_perform_msr_protocol(call);
+ } while (ret == -EAGAIN);
+
+ return ret;
+}
bool sev_snp_enabled(void)
{
@@ -145,8 +173,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
* If private -> shared then invalidate the page before requesting the
* state change in the RMP table.
*/
- if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0))
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+ if (op == SNP_PAGE_STATE_SHARED)
+ pvalidate_4k_page(paddr, paddr, false);
/* Issue VMGEXIT to change the page state in RMP table. */
sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
@@ -161,8 +189,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
* Now that page state is changed in the RMP table, validate it so that it is
* consistent with the RMP entry.
*/
- if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1))
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+ if (op == SNP_PAGE_STATE_PRIVATE)
+ pvalidate_4k_page(paddr, paddr, true);
}
void snp_set_page_private(unsigned long paddr)
@@ -256,6 +284,16 @@ void sev_es_shutdown_ghcb(void)
error("SEV-ES CPU Features missing.");
/*
+ * This denotes whether to use the GHCB MSR protocol or the GHCB
+ * shared page to perform a GHCB request. Since the GHCB page is
+ * being changed to encrypted, it can't be used to perform GHCB
+ * requests. Clear the boot_ghcb variable so that the GHCB MSR
+ * protocol is used to change the GHCB page over to an encrypted
+ * page.
+ */
+ boot_ghcb = NULL;
+
+ /*
* GHCB Page must be flushed from the cache and mapped encrypted again.
* Otherwise the running kernel will see strange cache effects when
* trying to use that page.
@@ -463,6 +501,13 @@ static bool early_snp_init(struct boot_params *bp)
setup_cpuid_table(cc_info);
/*
+ * Record the SVSM Calling Area (CA) address if the guest is not
+ * running at VMPL0. The CA will be used to communicate with the
+ * SVSM and request its services.
+ */
+ svsm_setup_ca(cc_info);
+
+ /*
* Pass run-time kernel a pointer to CC info via boot_params so EFI
* config table doesn't need to be searched again during early startup
* phase.
@@ -565,22 +610,31 @@ void sev_enable(struct boot_params *bp)
* features.
*/
if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
- if (!(get_hv_features() & GHCB_HV_FT_SNP))
+ u64 hv_features;
+ int ret;
+
+ hv_features = get_hv_features();
+ if (!(hv_features & GHCB_HV_FT_SNP))
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
/*
- * Enforce running at VMPL0.
- *
- * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically
- * higher) privilege level. Here, clear the VMPL1 permission mask of the
- * GHCB page. If the guest is not running at VMPL0, this will fail.
+ * Enforce running at VMPL0 or with an SVSM.
*
- * If the guest is running at VMPL0, it will succeed. Even if that operation
- * modifies permission bits, it is still ok to do so currently because Linux
- * SNP guests running at VMPL0 only run at VMPL0, so VMPL1 or higher
- * permission mask changes are a don't-care.
+ * Use RMPADJUST (see the rmpadjust() function for a description of
+ * what the instruction does) to update the VMPL1 permissions of a
+ * page. If the guest is running at VMPL0, this will succeed. If the
+ * guest is running at any other VMPL, this will fail. Linux SNP guests
+ * only ever run at a single VMPL level so permission mask changes of a
+ * lesser-privileged VMPL are a don't-care.
+ */
+ ret = rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1);
+
+ /*
+ * Running at VMPL0 is not required if an SVSM is present and the hypervisor
+ * supports the required SVSM GHCB events.
*/
- if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1))
+ if (ret &&
+ !(snp_vmpl && (hv_features & GHCB_HV_FT_SNP_MULTI_VMPL)))
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
}
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index fed8d13ce252..0aae4d4ed615 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -203,7 +203,7 @@ int check_knl_erratum(void)
*/
if (!is_intel() ||
cpu.family != 6 ||
- cpu.model != INTEL_FAM6_XEON_PHI_KNL)
+ cpu.model != 0x57 /*INTEL_XEON_PHI_KNL*/)
return 0;
/*
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index 9049f390d834..9d0fea18d3c8 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -27,34 +27,32 @@ char *heap_end = _end; /* Default end of heap = no heap */
* screws up the old-style command line protocol, adjust by
* filling in the new-style command line pointer instead.
*/
-
static void copy_boot_params(void)
{
struct old_cmdline {
u16 cl_magic;
u16 cl_offset;
};
- const struct old_cmdline * const oldcmd =
- absolute_pointer(OLD_CL_ADDRESS);
+ const struct old_cmdline * const oldcmd = absolute_pointer(OLD_CL_ADDRESS);
BUILD_BUG_ON(sizeof(boot_params) != 4096);
memcpy(&boot_params.hdr, &hdr, sizeof(hdr));
- if (!boot_params.hdr.cmd_line_ptr &&
- oldcmd->cl_magic == OLD_CL_MAGIC) {
- /* Old-style command line protocol. */
+ if (!boot_params.hdr.cmd_line_ptr && oldcmd->cl_magic == OLD_CL_MAGIC) {
+ /* Old-style command line protocol */
u16 cmdline_seg;
- /* Figure out if the command line falls in the region
- of memory that an old kernel would have copied up
- to 0x90000... */
+ /*
+ * Figure out if the command line falls in the region
+ * of memory that an old kernel would have copied up
+ * to 0x90000...
+ */
if (oldcmd->cl_offset < boot_params.hdr.setup_move_size)
cmdline_seg = ds();
else
cmdline_seg = 0x9000;
- boot_params.hdr.cmd_line_ptr =
- (cmdline_seg << 4) + oldcmd->cl_offset;
+ boot_params.hdr.cmd_line_ptr = (cmdline_seg << 4) + oldcmd->cl_offset;
}
}
@@ -66,6 +64,7 @@ static void copy_boot_params(void)
static void keyboard_init(void)
{
struct biosregs ireg, oreg;
+
initregs(&ireg);
ireg.ah = 0x02; /* Get keyboard status */
@@ -83,8 +82,10 @@ static void query_ist(void)
{
struct biosregs ireg, oreg;
- /* Some older BIOSes apparently crash on this call, so filter
- it from machines too old to have SpeedStep at all. */
+ /*
+ * Some older BIOSes apparently crash on this call, so filter
+ * it from machines too old to have SpeedStep at all.
+ */
if (cpu.level < 6)
return;
@@ -119,17 +120,13 @@ static void init_heap(void)
char *stack_end;
if (boot_params.hdr.loadflags & CAN_USE_HEAP) {
- asm("leal %n1(%%esp),%0"
- : "=r" (stack_end) : "i" (STACK_SIZE));
-
- heap_end = (char *)
- ((size_t)boot_params.hdr.heap_end_ptr + 0x200);
+ stack_end = (char *) (current_stack_pointer - STACK_SIZE);
+ heap_end = (char *) ((size_t)boot_params.hdr.heap_end_ptr + 0x200);
if (heap_end > stack_end)
heap_end = stack_end;
} else {
/* Boot protocol 2.00 only, no heap available */
- puts("WARNING: Ancient bootloader, some functionality "
- "may be limited!\n");
+ puts("WARNING: Ancient bootloader, some functionality may be limited!\n");
}
}
@@ -150,12 +147,11 @@ void main(void)
/* Make sure we have all the proper CPU support */
if (validate_cpu()) {
- puts("Unable to boot - please use a kernel appropriate "
- "for your CPU.\n");
+ puts("Unable to boot - please use a kernel appropriate for your CPU.\n");
die();
}
- /* Tell the BIOS what CPU mode we intend to run in. */
+ /* Tell the BIOS what CPU mode we intend to run in */
set_bios_mode();
/* Detect memory layout */
diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile
index c816acf78b6a..eabdc7486538 100644
--- a/arch/x86/coco/Makefile
+++ b/arch/x86/coco/Makefile
@@ -6,3 +6,4 @@ CFLAGS_core.o += -fno-stack-protector
obj-y += core.o
obj-$(CONFIG_INTEL_TDX_GUEST) += tdx/
+obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev/
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index b31ef2424d19..0f81f70aca82 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -29,7 +29,6 @@ static bool noinstr intel_cc_platform_has(enum cc_attr attr)
{
switch (attr) {
case CC_ATTR_GUEST_UNROLL_STRING_IO:
- case CC_ATTR_HOTPLUG_DISABLED:
case CC_ATTR_GUEST_MEM_ENCRYPT:
case CC_ATTR_MEM_ENCRYPT:
return true;
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
new file mode 100644
index 000000000000..4e375e7305ac
--- /dev/null
+++ b/arch/x86/coco/sev/Makefile
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y += core.o
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_core.o = -pg
+endif
+
+KASAN_SANITIZE_core.o := n
+KMSAN_SANITIZE_core.o := n
+KCOV_INSTRUMENT_core.o := n
+
+# With some compiler versions the generated code results in boot hangs, caused
+# by several compilation units. To be safe, disable all instrumentation.
+KCSAN_SANITIZE := n
diff --git a/arch/x86/kernel/sev.c b/arch/x86/coco/sev/core.c
index 3342ed58e168..082d61d85dfc 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/coco/sev/core.c
@@ -133,16 +133,20 @@ struct ghcb_state {
struct ghcb *ghcb;
};
+/* For early boot SVSM communication */
+static struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
+
static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
+static DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
+static DEFINE_PER_CPU(u64, svsm_caa_pa);
struct sev_config {
__u64 debug : 1,
/*
- * A flag used by __set_pages_state() that indicates when the
- * per-CPU GHCB has been created and registered and thus can be
- * used by the BSP instead of the early boot GHCB.
+ * Indicates when the per-CPU GHCB has been created and registered
+ * and thus can be used by the BSP instead of the early boot GHCB.
*
* For APs, the per-CPU GHCB is created before they are started
* and registered upon startup, so this flag can be used globally
@@ -150,6 +154,15 @@ struct sev_config {
*/
ghcbs_initialized : 1,
+ /*
+ * Indicates when the per-CPU SVSM CA is to be used instead of the
+ * boot SVSM CA.
+ *
+ * For APs, the per-CPU SVSM CA is created as part of the AP
+ * bringup, so this flag can be used globally for the BSP and APs.
+ */
+ use_cas : 1,
+
__reserved : 62;
};
@@ -572,8 +585,61 @@ fault:
return ES_EXCEPTION;
}
+static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
+{
+ long error_code = ctxt->fi.error_code;
+ int trapnr = ctxt->fi.vector;
+
+ ctxt->regs->orig_ax = ctxt->fi.error_code;
+
+ switch (trapnr) {
+ case X86_TRAP_GP:
+ exc_general_protection(ctxt->regs, error_code);
+ break;
+ case X86_TRAP_UD:
+ exc_invalid_op(ctxt->regs);
+ break;
+ case X86_TRAP_PF:
+ write_cr2(ctxt->fi.cr2);
+ exc_page_fault(ctxt->regs, error_code);
+ break;
+ case X86_TRAP_AC:
+ exc_alignment_check(ctxt->regs, error_code);
+ break;
+ default:
+ pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
+ BUG();
+ }
+}
+
/* Include code shared with pre-decompression boot stage */
-#include "sev-shared.c"
+#include "shared.c"
+
+static inline struct svsm_ca *svsm_get_caa(void)
+{
+ /*
+ * Use rIP-relative references when called early in the boot. If
+ * ->use_cas is set, then it is late in the boot and no need
+ * to worry about rIP-relative references.
+ */
+ if (RIP_REL_REF(sev_cfg).use_cas)
+ return this_cpu_read(svsm_caa);
+ else
+ return RIP_REL_REF(boot_svsm_caa);
+}
+
+static u64 svsm_get_caa_pa(void)
+{
+ /*
+ * Use rIP-relative references when called early in the boot. If
+ * ->use_cas is set, then it is late in the boot and no need
+ * to worry about rIP-relative references.
+ */
+ if (RIP_REL_REF(sev_cfg).use_cas)
+ return this_cpu_read(svsm_caa_pa);
+ else
+ return RIP_REL_REF(boot_svsm_caa_pa);
+}
static noinstr void __sev_put_ghcb(struct ghcb_state *state)
{
@@ -600,6 +666,44 @@ static noinstr void __sev_put_ghcb(struct ghcb_state *state)
}
}
+static int svsm_perform_call_protocol(struct svsm_call *call)
+{
+ struct ghcb_state state;
+ unsigned long flags;
+ struct ghcb *ghcb;
+ int ret;
+
+ /*
+ * This can be called very early in the boot, use native functions in
+ * order to avoid paravirt issues.
+ */
+ flags = native_local_irq_save();
+
+ /*
+ * Use rip-relative references when called early in the boot. If
+ * ghcbs_initialized is set, then it is late in the boot and no need
+ * to worry about rip-relative references in called functions.
+ */
+ if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
+ ghcb = __sev_get_ghcb(&state);
+ else if (RIP_REL_REF(boot_ghcb))
+ ghcb = RIP_REL_REF(boot_ghcb);
+ else
+ ghcb = NULL;
+
+ do {
+ ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
+ : svsm_perform_msr_protocol(call);
+ } while (ret == -EAGAIN);
+
+ if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
+ __sev_put_ghcb(&state);
+
+ native_local_irq_restore(flags);
+
+ return ret;
+}
+
void noinstr __sev_es_nmi_complete(void)
{
struct ghcb_state state;
@@ -709,7 +813,6 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr,
{
unsigned long paddr_end;
u64 val;
- int ret;
vaddr = vaddr & PAGE_MASK;
@@ -717,12 +820,9 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr,
paddr_end = paddr + (npages << PAGE_SHIFT);
while (paddr < paddr_end) {
- if (op == SNP_PAGE_STATE_SHARED) {
- /* Page validation must be rescinded before changing to shared */
- ret = pvalidate(vaddr, RMP_PG_SIZE_4K, false);
- if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret))
- goto e_term;
- }
+ /* Page validation must be rescinded before changing to shared */
+ if (op == SNP_PAGE_STATE_SHARED)
+ pvalidate_4k_page(vaddr, paddr, false);
/*
* Use the MSR protocol because this function can be called before
@@ -744,12 +844,9 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr,
paddr, GHCB_MSR_PSC_RESP_VAL(val)))
goto e_term;
- if (op == SNP_PAGE_STATE_PRIVATE) {
- /* Page validation must be performed after changing to private */
- ret = pvalidate(vaddr, RMP_PG_SIZE_4K, true);
- if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret))
- goto e_term;
- }
+ /* Page validation must be performed after changing to private */
+ if (op == SNP_PAGE_STATE_PRIVATE)
+ pvalidate_4k_page(vaddr, paddr, true);
vaddr += PAGE_SIZE;
paddr += PAGE_SIZE;
@@ -913,22 +1010,49 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end)
set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
}
-static int snp_set_vmsa(void *va, bool vmsa)
+static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
{
- u64 attrs;
+ int ret;
- /*
- * Running at VMPL0 allows the kernel to change the VMSA bit for a page
- * using the RMPADJUST instruction. However, for the instruction to
- * succeed it must target the permissions of a lesser privileged
- * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST
- * instruction in the AMD64 APM Volume 3).
- */
- attrs = 1;
- if (vmsa)
- attrs |= RMPADJUST_VMSA_PAGE_BIT;
+ if (snp_vmpl) {
+ struct svsm_call call = {};
+ unsigned long flags;
+
+ local_irq_save(flags);
- return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+ call.caa = this_cpu_read(svsm_caa);
+ call.rcx = __pa(va);
+
+ if (make_vmsa) {
+ /* Protocol 0, Call ID 2 */
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
+ call.rdx = __pa(caa);
+ call.r8 = apic_id;
+ } else {
+ /* Protocol 0, Call ID 3 */
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
+ }
+
+ ret = svsm_perform_call_protocol(&call);
+
+ local_irq_restore(flags);
+ } else {
+ /*
+ * If the kernel runs at VMPL0, it can change the VMSA
+ * bit for a page using the RMPADJUST instruction.
+ * However, for the instruction to succeed it must
+ * target the permissions of a lesser privileged (higher
+ * numbered) VMPL level, so use VMPL1.
+ */
+ u64 attrs = 1;
+
+ if (make_vmsa)
+ attrs |= RMPADJUST_VMSA_PAGE_BIT;
+
+ ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+ }
+
+ return ret;
}
#define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
@@ -962,11 +1086,11 @@ static void *snp_alloc_vmsa_page(int cpu)
return page_address(p + 1);
}
-static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
+static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
{
int err;
- err = snp_set_vmsa(vmsa, false);
+ err = snp_set_vmsa(vmsa, NULL, apic_id, false);
if (err)
pr_err("clear VMSA page failed (%u), leaking page\n", err);
else
@@ -977,6 +1101,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
{
struct sev_es_save_area *cur_vmsa, *vmsa;
struct ghcb_state state;
+ struct svsm_ca *caa;
unsigned long flags;
struct ghcb *ghcb;
u8 sipi_vector;
@@ -1023,6 +1148,9 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
if (!vmsa)
return -ENOMEM;
+ /* If an SVSM is present, the SVSM per-CPU CAA will be !NULL */
+ caa = per_cpu(svsm_caa, cpu);
+
/* CR4 should maintain the MCE value */
cr4 = native_read_cr4() & X86_CR4_MCE;
@@ -1070,11 +1198,11 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
* VMPL level
* SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits)
*/
- vmsa->vmpl = 0;
+ vmsa->vmpl = snp_vmpl;
vmsa->sev_features = sev_status >> 2;
/* Switch the page over to a VMSA page now that it is initialized */
- ret = snp_set_vmsa(vmsa, true);
+ ret = snp_set_vmsa(vmsa, caa, apic_id, true);
if (ret) {
pr_err("set VMSA page failed (%u)\n", ret);
free_page((unsigned long)vmsa);
@@ -1090,7 +1218,10 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
vc_ghcb_invalidate(ghcb);
ghcb_set_rax(ghcb, vmsa->sev_features);
ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
- ghcb_set_sw_exit_info_1(ghcb, ((u64)apic_id << 32) | SVM_VMGEXIT_AP_CREATE);
+ ghcb_set_sw_exit_info_1(ghcb,
+ ((u64)apic_id << 32) |
+ ((u64)snp_vmpl << 16) |
+ SVM_VMGEXIT_AP_CREATE);
ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
sev_es_wr_ghcb_msr(__pa(ghcb));
@@ -1108,13 +1239,13 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
/* Perform cleanup if there was an error */
if (ret) {
- snp_cleanup_vmsa(vmsa);
+ snp_cleanup_vmsa(vmsa, apic_id);
vmsa = NULL;
}
/* Free up any previous VMSA page */
if (cur_vmsa)
- snp_cleanup_vmsa(cur_vmsa);
+ snp_cleanup_vmsa(cur_vmsa, apic_id);
/* Record the current VMSA page */
per_cpu(sev_vmsa, cpu) = vmsa;
@@ -1209,6 +1340,17 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
/* Is it a WRMSR? */
exit_info_1 = (ctxt->insn.opcode.bytes[1] == 0x30) ? 1 : 0;
+ if (regs->cx == MSR_SVSM_CAA) {
+ /* Writes to the SVSM CAA msr are ignored */
+ if (exit_info_1)
+ return ES_OK;
+
+ regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
+ regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
+
+ return ES_OK;
+ }
+
ghcb_set_rcx(ghcb, regs->cx);
if (exit_info_1) {
ghcb_set_rax(ghcb, regs->ax);
@@ -1346,6 +1488,18 @@ static void __init alloc_runtime_data(int cpu)
panic("Can't allocate SEV-ES runtime data");
per_cpu(runtime_data, cpu) = data;
+
+ if (snp_vmpl) {
+ struct svsm_ca *caa;
+
+ /* Allocate the SVSM CA page if an SVSM is present */
+ caa = memblock_alloc(sizeof(*caa), PAGE_SIZE);
+ if (!caa)
+ panic("Can't allocate SVSM CA page\n");
+
+ per_cpu(svsm_caa, cpu) = caa;
+ per_cpu(svsm_caa_pa, cpu) = __pa(caa);
+ }
}
static void __init init_ghcb(int cpu)
@@ -1395,6 +1549,32 @@ void __init sev_es_init_vc_handling(void)
init_ghcb(cpu);
}
+ /* If running under an SVSM, switch to the per-cpu CA */
+ if (snp_vmpl) {
+ struct svsm_call call = {};
+ unsigned long flags;
+ int ret;
+
+ local_irq_save(flags);
+
+ /*
+ * SVSM_CORE_REMAP_CA call:
+ * RAX = 0 (Protocol=0, CallID=0)
+ * RCX = New CA GPA
+ */
+ call.caa = svsm_get_caa();
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
+ call.rcx = this_cpu_read(svsm_caa_pa);
+ ret = svsm_perform_call_protocol(&call);
+ if (ret)
+ panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n",
+ ret, call.rax_out);
+
+ sev_cfg.use_cas = true;
+
+ local_irq_restore(flags);
+ }
+
sev_es_setup_play_dead();
/* Secondary CPUs use the runtime #VC handler */
@@ -1819,33 +1999,6 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
return result;
}
-static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
-{
- long error_code = ctxt->fi.error_code;
- int trapnr = ctxt->fi.vector;
-
- ctxt->regs->orig_ax = ctxt->fi.error_code;
-
- switch (trapnr) {
- case X86_TRAP_GP:
- exc_general_protection(ctxt->regs, error_code);
- break;
- case X86_TRAP_UD:
- exc_invalid_op(ctxt->regs);
- break;
- case X86_TRAP_PF:
- write_cr2(ctxt->fi.cr2);
- exc_page_fault(ctxt->regs, error_code);
- break;
- case X86_TRAP_AC:
- exc_alignment_check(ctxt->regs, error_code);
- break;
- default:
- pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
- BUG();
- }
-}
-
static __always_inline bool is_vc2_stack(unsigned long sp)
{
return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
@@ -2095,6 +2248,47 @@ found_cc_info:
return cc_info;
}
+static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
+{
+ struct svsm_call call = {};
+ int ret;
+ u64 pa;
+
+ /*
+ * Record the SVSM Calling Area address (CAA) if the guest is not
+ * running at VMPL0. The CA will be used to communicate with the
+ * SVSM to perform the SVSM services.
+ */
+ if (!svsm_setup_ca(cc_info))
+ return;
+
+ /*
+ * It is very early in the boot and the kernel is running identity
+ * mapped but without having adjusted the pagetables to where the
+ * kernel was loaded (physbase), so the get the CA address using
+ * RIP-relative addressing.
+ */
+ pa = (u64)&RIP_REL_REF(boot_svsm_ca_page);
+
+ /*
+ * Switch over to the boot SVSM CA while the current CA is still
+ * addressable. There is no GHCB at this point so use the MSR protocol.
+ *
+ * SVSM_CORE_REMAP_CA call:
+ * RAX = 0 (Protocol=0, CallID=0)
+ * RCX = New CA GPA
+ */
+ call.caa = svsm_get_caa();
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
+ call.rcx = pa;
+ ret = svsm_perform_call_protocol(&call);
+ if (ret)
+ panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n", ret, call.rax_out);
+
+ RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa;
+ RIP_REL_REF(boot_svsm_caa_pa) = pa;
+}
+
bool __head snp_init(struct boot_params *bp)
{
struct cc_blob_sev_info *cc_info;
@@ -2108,6 +2302,8 @@ bool __head snp_init(struct boot_params *bp)
setup_cpuid_table(cc_info);
+ svsm_setup(cc_info);
+
/*
* The CC blob will be used later to access the secrets page. Cache
* it here like the boot kernel does.
@@ -2156,23 +2352,27 @@ static void dump_cpuid_table(void)
* expected, but that initialization happens too early in boot to print any
* sort of indicator, and there's not really any other good place to do it,
* so do it here.
+ *
+ * If running as an SNP guest, report the current VM privilege level (VMPL).
*/
-static int __init report_cpuid_table(void)
+static int __init report_snp_info(void)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
- if (!cpuid_table->count)
- return 0;
+ if (cpuid_table->count) {
+ pr_info("Using SNP CPUID table, %d entries present.\n",
+ cpuid_table->count);
- pr_info("Using SNP CPUID table, %d entries present.\n",
- cpuid_table->count);
+ if (sev_cfg.debug)
+ dump_cpuid_table();
+ }
- if (sev_cfg.debug)
- dump_cpuid_table();
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ pr_info("SNP running at VMPL%u.\n", snp_vmpl);
return 0;
}
-arch_initcall(report_cpuid_table);
+arch_initcall(report_snp_info);
static int __init init_sev_config(char *str)
{
@@ -2191,6 +2391,56 @@ static int __init init_sev_config(char *str)
}
__setup("sev=", init_sev_config);
+static void update_attest_input(struct svsm_call *call, struct svsm_attest_call *input)
+{
+ /* If (new) lengths have been returned, propagate them up */
+ if (call->rcx_out != call->rcx)
+ input->manifest_buf.len = call->rcx_out;
+
+ if (call->rdx_out != call->rdx)
+ input->certificates_buf.len = call->rdx_out;
+
+ if (call->r8_out != call->r8)
+ input->report_buf.len = call->r8_out;
+}
+
+int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call,
+ struct svsm_attest_call *input)
+{
+ struct svsm_attest_call *ac;
+ unsigned long flags;
+ u64 attest_call_pa;
+ int ret;
+
+ if (!snp_vmpl)
+ return -EINVAL;
+
+ local_irq_save(flags);
+
+ call->caa = svsm_get_caa();
+
+ ac = (struct svsm_attest_call *)call->caa->svsm_buffer;
+ attest_call_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+ *ac = *input;
+
+ /*
+ * Set input registers for the request and set RDX and R8 to known
+ * values in order to detect length values being returned in them.
+ */
+ call->rax = call_id;
+ call->rcx = attest_call_pa;
+ call->rdx = -1;
+ call->r8 = -1;
+ ret = svsm_perform_call_protocol(call);
+ update_attest_input(call, input);
+
+ local_irq_restore(flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req);
+
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio)
{
struct ghcb_state state;
@@ -2299,3 +2549,58 @@ void sev_show_status(void)
}
pr_cont("\n");
}
+
+void __init snp_update_svsm_ca(void)
+{
+ if (!snp_vmpl)
+ return;
+
+ /* Update the CAA to a proper kernel address */
+ boot_svsm_caa = &boot_svsm_ca_page;
+}
+
+#ifdef CONFIG_SYSFS
+static ssize_t vmpl_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", snp_vmpl);
+}
+
+static struct kobj_attribute vmpl_attr = __ATTR_RO(vmpl);
+
+static struct attribute *vmpl_attrs[] = {
+ &vmpl_attr.attr,
+ NULL
+};
+
+static struct attribute_group sev_attr_group = {
+ .attrs = vmpl_attrs,
+};
+
+static int __init sev_sysfs_init(void)
+{
+ struct kobject *sev_kobj;
+ struct device *dev_root;
+ int ret;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return -ENODEV;
+
+ dev_root = bus_get_dev_root(&cpu_subsys);
+ if (!dev_root)
+ return -ENODEV;
+
+ sev_kobj = kobject_create_and_add("sev", &dev_root->kobj);
+ put_device(dev_root);
+
+ if (!sev_kobj)
+ return -ENOMEM;
+
+ ret = sysfs_create_group(sev_kobj, &sev_attr_group);
+ if (ret)
+ kobject_put(sev_kobj);
+
+ return ret;
+}
+arch_initcall(sev_sysfs_init);
+#endif // CONFIG_SYSFS
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/coco/sev/shared.c
index b4f8fa0f722c..71de53194089 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/coco/sev/shared.c
@@ -21,8 +21,30 @@
#define WARN(condition, format...) (!!(condition))
#define sev_printk(fmt, ...)
#define sev_printk_rtl(fmt, ...)
+#undef vc_forward_exception
+#define vc_forward_exception(c) panic("SNP: Hypervisor requested exception\n")
#endif
+/*
+ * SVSM related information:
+ * When running under an SVSM, the VMPL that Linux is executing at must be
+ * non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
+ *
+ * During boot, the page tables are set up as identity mapped and later
+ * changed to use kernel virtual addresses. Maintain separate virtual and
+ * physical addresses for the CAA to allow SVSM functions to be used during
+ * early boot, both with identity mapped virtual addresses and proper kernel
+ * virtual addresses.
+ */
+u8 snp_vmpl __ro_after_init;
+EXPORT_SYMBOL_GPL(snp_vmpl);
+static struct svsm_ca *boot_svsm_caa __ro_after_init;
+static u64 boot_svsm_caa_pa __ro_after_init;
+
+static struct svsm_ca *svsm_get_caa(void);
+static u64 svsm_get_caa_pa(void);
+static int svsm_perform_call_protocol(struct svsm_call *call);
+
/* I/O parameters for CPUID-related helpers */
struct cpuid_leaf {
u32 fn;
@@ -229,6 +251,126 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt
return ES_VMM_ERROR;
}
+static inline int svsm_process_result_codes(struct svsm_call *call)
+{
+ switch (call->rax_out) {
+ case SVSM_SUCCESS:
+ return 0;
+ case SVSM_ERR_INCOMPLETE:
+ case SVSM_ERR_BUSY:
+ return -EAGAIN;
+ default:
+ return -EINVAL;
+ }
+}
+
+/*
+ * Issue a VMGEXIT to call the SVSM:
+ * - Load the SVSM register state (RAX, RCX, RDX, R8 and R9)
+ * - Set the CA call pending field to 1
+ * - Issue VMGEXIT
+ * - Save the SVSM return register state (RAX, RCX, RDX, R8 and R9)
+ * - Perform atomic exchange of the CA call pending field
+ *
+ * - See the "Secure VM Service Module for SEV-SNP Guests" specification for
+ * details on the calling convention.
+ * - The calling convention loosely follows the Microsoft X64 calling
+ * convention by putting arguments in RCX, RDX, R8 and R9.
+ * - RAX specifies the SVSM protocol/callid as input and the return code
+ * as output.
+ */
+static __always_inline void svsm_issue_call(struct svsm_call *call, u8 *pending)
+{
+ register unsigned long rax asm("rax") = call->rax;
+ register unsigned long rcx asm("rcx") = call->rcx;
+ register unsigned long rdx asm("rdx") = call->rdx;
+ register unsigned long r8 asm("r8") = call->r8;
+ register unsigned long r9 asm("r9") = call->r9;
+
+ call->caa->call_pending = 1;
+
+ asm volatile("rep; vmmcall\n\t"
+ : "+r" (rax), "+r" (rcx), "+r" (rdx), "+r" (r8), "+r" (r9)
+ : : "memory");
+
+ *pending = xchg(&call->caa->call_pending, *pending);
+
+ call->rax_out = rax;
+ call->rcx_out = rcx;
+ call->rdx_out = rdx;
+ call->r8_out = r8;
+ call->r9_out = r9;
+}
+
+static int svsm_perform_msr_protocol(struct svsm_call *call)
+{
+ u8 pending = 0;
+ u64 val, resp;
+
+ /*
+ * When using the MSR protocol, be sure to save and restore
+ * the current MSR value.
+ */
+ val = sev_es_rd_ghcb_msr();
+
+ sev_es_wr_ghcb_msr(GHCB_MSR_VMPL_REQ_LEVEL(0));
+
+ svsm_issue_call(call, &pending);
+
+ resp = sev_es_rd_ghcb_msr();
+
+ sev_es_wr_ghcb_msr(val);
+
+ if (pending)
+ return -EINVAL;
+
+ if (GHCB_RESP_CODE(resp) != GHCB_MSR_VMPL_RESP)
+ return -EINVAL;
+
+ if (GHCB_MSR_VMPL_RESP_VAL(resp))
+ return -EINVAL;
+
+ return svsm_process_result_codes(call);
+}
+
+static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
+{
+ struct es_em_ctxt ctxt;
+ u8 pending = 0;
+
+ vc_ghcb_invalidate(ghcb);
+
+ /*
+ * Fill in protocol and format specifiers. This can be called very early
+ * in the boot, so use rip-relative references as needed.
+ */
+ ghcb->protocol_version = RIP_REL_REF(ghcb_version);
+ ghcb->ghcb_usage = GHCB_DEFAULT_USAGE;
+
+ ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_SNP_RUN_VMPL);
+ ghcb_set_sw_exit_info_1(ghcb, 0);
+ ghcb_set_sw_exit_info_2(ghcb, 0);
+
+ sev_es_wr_ghcb_msr(__pa(ghcb));
+
+ svsm_issue_call(call, &pending);
+
+ if (pending)
+ return -EINVAL;
+
+ switch (verify_exception_info(ghcb, &ctxt)) {
+ case ES_OK:
+ break;
+ case ES_EXCEPTION:
+ vc_forward_exception(&ctxt);
+ fallthrough;
+ default:
+ return -EINVAL;
+ }
+
+ return svsm_process_result_codes(call);
+}
+
static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
struct es_em_ctxt *ctxt,
u64 exit_code, u64 exit_info_1,
@@ -1079,38 +1221,268 @@ static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
}
}
-static void pvalidate_pages(struct snp_psc_desc *desc)
+static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
+ int ret, u64 svsm_ret)
+{
+ WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
+ pfn, action, page_size, ret, svsm_ret);
+
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+}
+
+static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
+{
+ unsigned int page_size;
+ bool action;
+ u64 pfn;
+
+ pfn = pc->entry[pc->cur_index].pfn;
+ action = pc->entry[pc->cur_index].action;
+ page_size = pc->entry[pc->cur_index].page_size;
+
+ __pval_terminate(pfn, action, page_size, ret, svsm_ret);
+}
+
+static void svsm_pval_4k_page(unsigned long paddr, bool validate)
+{
+ struct svsm_pvalidate_call *pc;
+ struct svsm_call call = {};
+ unsigned long flags;
+ u64 pc_pa;
+ int ret;
+
+ /*
+ * This can be called very early in the boot, use native functions in
+ * order to avoid paravirt issues.
+ */
+ flags = native_local_irq_save();
+
+ call.caa = svsm_get_caa();
+
+ pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+ pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+ pc->num_entries = 1;
+ pc->cur_index = 0;
+ pc->entry[0].page_size = RMP_PG_SIZE_4K;
+ pc->entry[0].action = validate;
+ pc->entry[0].ignore_cf = 0;
+ pc->entry[0].pfn = paddr >> PAGE_SHIFT;
+
+ /* Protocol 0, Call ID 1 */
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+ call.rcx = pc_pa;
+
+ ret = svsm_perform_call_protocol(&call);
+ if (ret)
+ svsm_pval_terminate(pc, ret, call.rax_out);
+
+ native_local_irq_restore(flags);
+}
+
+static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool validate)
+{
+ int ret;
+
+ /*
+ * This can be called very early during boot, so use rIP-relative
+ * references as needed.
+ */
+ if (RIP_REL_REF(snp_vmpl)) {
+ svsm_pval_4k_page(paddr, validate);
+ } else {
+ ret = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+ if (ret)
+ __pval_terminate(PHYS_PFN(paddr), validate, RMP_PG_SIZE_4K, ret, 0);
+ }
+}
+
+static void pval_pages(struct snp_psc_desc *desc)
{
struct psc_entry *e;
unsigned long vaddr;
unsigned int size;
unsigned int i;
bool validate;
+ u64 pfn;
int rc;
for (i = 0; i <= desc->hdr.end_entry; i++) {
e = &desc->entries[i];
- vaddr = (unsigned long)pfn_to_kaddr(e->gfn);
+ pfn = e->gfn;
+ vaddr = (unsigned long)pfn_to_kaddr(pfn);
size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
validate = e->operation == SNP_PAGE_STATE_PRIVATE;
rc = pvalidate(vaddr, size, validate);
+ if (!rc)
+ continue;
+
if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
unsigned long vaddr_end = vaddr + PMD_SIZE;
- for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) {
+ for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
if (rc)
- break;
+ __pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
}
+ } else {
+ __pval_terminate(pfn, validate, size, rc, 0);
}
+ }
+}
+
+static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
+ struct svsm_pvalidate_call *pc)
+{
+ struct svsm_pvalidate_entry *pe;
+
+ /* Nothing in the CA yet */
+ pc->num_entries = 0;
+ pc->cur_index = 0;
+
+ pe = &pc->entry[0];
+
+ while (pfn < pfn_end) {
+ pe->page_size = RMP_PG_SIZE_4K;
+ pe->action = action;
+ pe->ignore_cf = 0;
+ pe->pfn = pfn;
+
+ pe++;
+ pfn++;
+
+ pc->num_entries++;
+ if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+ break;
+ }
+
+ return pfn;
+}
+
+static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
+ struct svsm_pvalidate_call *pc)
+{
+ struct svsm_pvalidate_entry *pe;
+ struct psc_entry *e;
+
+ /* Nothing in the CA yet */
+ pc->num_entries = 0;
+ pc->cur_index = 0;
+
+ pe = &pc->entry[0];
+ e = &desc->entries[desc_entry];
+
+ while (desc_entry <= desc->hdr.end_entry) {
+ pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+ pe->action = e->operation == SNP_PAGE_STATE_PRIVATE;
+ pe->ignore_cf = 0;
+ pe->pfn = e->gfn;
+
+ pe++;
+ e++;
+
+ desc_entry++;
+ pc->num_entries++;
+ if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+ break;
+ }
+
+ return desc_entry;
+}
+
+static void svsm_pval_pages(struct snp_psc_desc *desc)
+{
+ struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
+ unsigned int i, pv_4k_count = 0;
+ struct svsm_pvalidate_call *pc;
+ struct svsm_call call = {};
+ unsigned long flags;
+ bool action;
+ u64 pc_pa;
+ int ret;
+
+ /*
+ * This can be called very early in the boot, use native functions in
+ * order to avoid paravirt issues.
+ */
+ flags = native_local_irq_save();
+
+ /*
+ * The SVSM calling area (CA) can support processing 510 entries at a
+ * time. Loop through the Page State Change descriptor until the CA is
+ * full or the last entry in the descriptor is reached, at which time
+ * the SVSM is invoked. This repeats until all entries in the descriptor
+ * are processed.
+ */
+ call.caa = svsm_get_caa();
+
+ pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+ pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+ /* Protocol 0, Call ID 1 */
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+ call.rcx = pc_pa;
+
+ for (i = 0; i <= desc->hdr.end_entry;) {
+ i = svsm_build_ca_from_psc_desc(desc, i, pc);
+
+ do {
+ ret = svsm_perform_call_protocol(&call);
+ if (!ret)
+ continue;
+
+ /*
+ * Check if the entry failed because of an RMP mismatch (a
+ * PVALIDATE at 2M was requested, but the page is mapped in
+ * the RMP as 4K).
+ */
- if (rc) {
- WARN(1, "Failed to validate address 0x%lx ret %d", vaddr, rc);
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+ if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
+ pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
+ /* Save this entry for post-processing at 4K */
+ pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
+
+ /* Skip to the next one unless at the end of the list */
+ pc->cur_index++;
+ if (pc->cur_index < pc->num_entries)
+ ret = -EAGAIN;
+ else
+ ret = 0;
+ }
+ } while (ret == -EAGAIN);
+
+ if (ret)
+ svsm_pval_terminate(pc, ret, call.rax_out);
+ }
+
+ /* Process any entries that failed to be validated at 2M and validate them at 4K */
+ for (i = 0; i < pv_4k_count; i++) {
+ u64 pfn, pfn_end;
+
+ action = pv_4k[i].action;
+ pfn = pv_4k[i].pfn;
+ pfn_end = pfn + 512;
+
+ while (pfn < pfn_end) {
+ pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
+
+ ret = svsm_perform_call_protocol(&call);
+ if (ret)
+ svsm_pval_terminate(pc, ret, call.rax_out);
}
}
+
+ native_local_irq_restore(flags);
+}
+
+static void pvalidate_pages(struct snp_psc_desc *desc)
+{
+ if (snp_vmpl)
+ svsm_pval_pages(desc);
+ else
+ pval_pages(desc);
}
static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
@@ -1269,3 +1641,77 @@ static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
return ES_UNSUPPORTED;
}
+
+/*
+ * Maintain the GPA of the SVSM Calling Area (CA) in order to utilize the SVSM
+ * services needed when not running in VMPL0.
+ */
+static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
+{
+ struct snp_secrets_page *secrets_page;
+ struct snp_cpuid_table *cpuid_table;
+ unsigned int i;
+ u64 caa;
+
+ BUILD_BUG_ON(sizeof(*secrets_page) != PAGE_SIZE);
+
+ /*
+ * Check if running at VMPL0.
+ *
+ * Use RMPADJUST (see the rmpadjust() function for a description of what
+ * the instruction does) to update the VMPL1 permissions of a page. If
+ * the guest is running at VMPL0, this will succeed and implies there is
+ * no SVSM. If the guest is running at any other VMPL, this will fail.
+ * Linux SNP guests only ever run at a single VMPL level so permission mask
+ * changes of a lesser-privileged VMPL are a don't-care.
+ *
+ * Use a rip-relative reference to obtain the proper address, since this
+ * routine is running identity mapped when called, both by the decompressor
+ * code and the early kernel code.
+ */
+ if (!rmpadjust((unsigned long)&RIP_REL_REF(boot_ghcb_page), RMP_PG_SIZE_4K, 1))
+ return false;
+
+ /*
+ * Not running at VMPL0, ensure everything has been properly supplied
+ * for running under an SVSM.
+ */
+ if (!cc_info || !cc_info->secrets_phys || cc_info->secrets_len != PAGE_SIZE)
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECRETS_PAGE);
+
+ secrets_page = (struct snp_secrets_page *)cc_info->secrets_phys;
+ if (!secrets_page->svsm_size)
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NO_SVSM);
+
+ if (!secrets_page->svsm_guest_vmpl)
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_VMPL0);
+
+ RIP_REL_REF(snp_vmpl) = secrets_page->svsm_guest_vmpl;
+
+ caa = secrets_page->svsm_caa;
+
+ /*
+ * An open-coded PAGE_ALIGNED() in order to avoid including
+ * kernel-proper headers into the decompressor.
+ */
+ if (caa & (PAGE_SIZE - 1))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CAA);
+
+ /*
+ * The CA is identity mapped when this routine is called, both by the
+ * decompressor code and the early kernel code.
+ */
+ RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)caa;
+ RIP_REL_REF(boot_svsm_caa_pa) = caa;
+
+ /* Advertise the SVSM presence via CPUID. */
+ cpuid_table = (struct snp_cpuid_table *)snp_cpuid_get_table();
+ for (i = 0; i < cpuid_table->count; i++) {
+ struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
+
+ if (fn->eax_in == 0x8000001f)
+ fn->eax |= BIT(28);
+ }
+
+ return true;
+}
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index c1cb90369915..078e2bac2553 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -7,6 +7,7 @@
#include <linux/cpufeature.h>
#include <linux/export.h>
#include <linux/io.h>
+#include <linux/kexec.h>
#include <asm/coco.h>
#include <asm/tdx.h>
#include <asm/vmx.h>
@@ -14,6 +15,7 @@
#include <asm/insn.h>
#include <asm/insn-eval.h>
#include <asm/pgtable.h>
+#include <asm/set_memory.h>
/* MMIO direction */
#define EPT_READ 0
@@ -38,6 +40,8 @@
#define TDREPORT_SUBTYPE_0 0
+static atomic_long_t nr_shared;
+
/* Called from __tdx_hypercall() for unrecoverable failure */
noinstr void __noreturn __tdx_hypercall_failed(void)
{
@@ -798,28 +802,124 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
return true;
}
-static bool tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
- bool enc)
+static int tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
+ bool enc)
{
/*
* Only handle shared->private conversion here.
* See the comment in tdx_early_init().
*/
- if (enc)
- return tdx_enc_status_changed(vaddr, numpages, enc);
- return true;
+ if (enc && !tdx_enc_status_changed(vaddr, numpages, enc))
+ return -EIO;
+
+ return 0;
}
-static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
+static int tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
bool enc)
{
/*
* Only handle private->shared conversion here.
* See the comment in tdx_early_init().
*/
- if (!enc)
- return tdx_enc_status_changed(vaddr, numpages, enc);
- return true;
+ if (!enc && !tdx_enc_status_changed(vaddr, numpages, enc))
+ return -EIO;
+
+ if (enc)
+ atomic_long_sub(numpages, &nr_shared);
+ else
+ atomic_long_add(numpages, &nr_shared);
+
+ return 0;
+}
+
+/* Stop new private<->shared conversions */
+static void tdx_kexec_begin(void)
+{
+ if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+ return;
+
+ /*
+ * Crash kernel reaches here with interrupts disabled: can't wait for
+ * conversions to finish.
+ *
+ * If race happened, just report and proceed.
+ */
+ if (!set_memory_enc_stop_conversion())
+ pr_warn("Failed to stop shared<->private conversions\n");
+}
+
+/* Walk direct mapping and convert all shared memory back to private */
+static void tdx_kexec_finish(void)
+{
+ unsigned long addr, end;
+ long found = 0, shared;
+
+ if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+ return;
+
+ lockdep_assert_irqs_disabled();
+
+ addr = PAGE_OFFSET;
+ end = PAGE_OFFSET + get_max_mapped();
+
+ while (addr < end) {
+ unsigned long size;
+ unsigned int level;
+ pte_t *pte;
+
+ pte = lookup_address(addr, &level);
+ size = page_level_size(level);
+
+ if (pte && pte_decrypted(*pte)) {
+ int pages = size / PAGE_SIZE;
+
+ /*
+ * Touching memory with shared bit set triggers implicit
+ * conversion to shared.
+ *
+ * Make sure nobody touches the shared range from
+ * now on.
+ */
+ set_pte(pte, __pte(0));
+
+ /*
+ * Memory encryption state persists across kexec.
+ * If tdx_enc_status_changed() fails in the first
+ * kernel, it leaves memory in an unknown state.
+ *
+ * If that memory remains shared, accessing it in the
+ * *next* kernel through a private mapping will result
+ * in an unrecoverable guest shutdown.
+ *
+ * The kdump kernel boot is not impacted as it uses
+ * a pre-reserved memory range that is always private.
+ * However, gathering crash information could lead to
+ * a crash if it accesses unconverted memory through
+ * a private mapping which is possible when accessing
+ * that memory through /proc/vmcore, for example.
+ *
+ * In all cases, print error info in order to leave
+ * enough bread crumbs for debugging.
+ */
+ if (!tdx_enc_status_changed(addr, pages, true)) {
+ pr_err("Failed to unshare range %#lx-%#lx\n",
+ addr, addr + size);
+ }
+
+ found += pages;
+ }
+
+ addr += size;
+ }
+
+ __flush_tlb_all();
+
+ shared = atomic_long_read(&nr_shared);
+ if (shared != found) {
+ pr_err("shared page accounting is off\n");
+ pr_err("nr_shared = %ld, nr_found = %ld\n", shared, found);
+ }
}
void __init tdx_early_init(void)
@@ -881,6 +981,9 @@ void __init tdx_early_init(void)
x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required;
x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required;
+ x86_platform.guest.enc_kexec_begin = tdx_kexec_begin;
+ x86_platform.guest.enc_kexec_finish = tdx_kexec_finish;
+
/*
* TDX intercepts the RDMSR to read the X2APIC ID in the parallel
* bringup low level code. That raises #VE which cannot be handled
diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig
index c9e59589a1ce..24875e6295f2 100644
--- a/arch/x86/crypto/Kconfig
+++ b/arch/x86/crypto/Kconfig
@@ -18,6 +18,7 @@ config CRYPTO_AES_NI_INTEL
depends on X86
select CRYPTO_AEAD
select CRYPTO_LIB_AES
+ select CRYPTO_LIB_GF128MUL
select CRYPTO_ALGAPI
select CRYPTO_SKCIPHER
select CRYPTO_SIMD
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 9c5ce5613738..53b4a277809e 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -48,8 +48,12 @@ chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
-aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o \
- aes_ctrby8_avx-x86_64.o aes-xts-avx-x86_64.o
+aesni-intel-$(CONFIG_64BIT) += aes_ctrby8_avx-x86_64.o \
+ aes-gcm-aesni-x86_64.o \
+ aes-xts-avx-x86_64.o
+ifeq ($(CONFIG_AS_VAES)$(CONFIG_AS_VPCLMULQDQ),yy)
+aesni-intel-$(CONFIG_64BIT) += aes-gcm-avx10-x86_64.o
+endif
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o
diff --git a/arch/x86/crypto/aes-gcm-aesni-x86_64.S b/arch/x86/crypto/aes-gcm-aesni-x86_64.S
new file mode 100644
index 000000000000..45940e2883a0
--- /dev/null
+++ b/arch/x86/crypto/aes-gcm-aesni-x86_64.S
@@ -0,0 +1,1128 @@
+/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */
+//
+// AES-NI optimized AES-GCM for x86_64
+//
+// Copyright 2024 Google LLC
+//
+// Author: Eric Biggers <ebiggers@google.com>
+//
+//------------------------------------------------------------------------------
+//
+// This file is dual-licensed, meaning that you can use it under your choice of
+// either of the following two licenses:
+//
+// Licensed under the Apache License 2.0 (the "License"). You may obtain a copy
+// of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+//
+// or
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+// 1. Redistributions of source code must retain the above copyright notice,
+// this list of conditions and the following disclaimer.
+//
+// 2. Redistributions in binary form must reproduce the above copyright
+// notice, this list of conditions and the following disclaimer in the
+// documentation and/or other materials provided with the distribution.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+// ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+// LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+// CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+// SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+// CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+// ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+// POSSIBILITY OF SUCH DAMAGE.
+//
+//------------------------------------------------------------------------------
+//
+// This file implements AES-GCM (Galois/Counter Mode) for x86_64 CPUs that
+// support the original set of AES instructions, i.e. AES-NI. Two
+// implementations are provided, one that uses AVX and one that doesn't. They
+// are very similar, being generated by the same macros. The only difference is
+// that the AVX implementation takes advantage of VEX-coded instructions in some
+// places to avoid some 'movdqu' and 'movdqa' instructions. The AVX
+// implementation does *not* use 256-bit vectors, as AES is not supported on
+// 256-bit vectors until the VAES feature (which this file doesn't target).
+//
+// The specific CPU feature prerequisites are AES-NI and PCLMULQDQ, plus SSE4.1
+// for the *_aesni functions or AVX for the *_aesni_avx ones. (But it seems
+// there are no CPUs that support AES-NI without also PCLMULQDQ and SSE4.1.)
+//
+// The design generally follows that of aes-gcm-avx10-x86_64.S, and that file is
+// more thoroughly commented. This file has the following notable changes:
+//
+// - The vector length is fixed at 128-bit, i.e. xmm registers. This means
+// there is only one AES block (and GHASH block) per register.
+//
+// - Without AVX512 / AVX10, only 16 SIMD registers are available instead of
+// 32. We work around this by being much more careful about using
+// registers, relying heavily on loads to load values as they are needed.
+//
+// - Masking is not available either. We work around this by implementing
+// partial block loads and stores using overlapping scalar loads and stores
+// combined with shifts and SSE4.1 insertion and extraction instructions.
+//
+// - The main loop is organized differently due to the different design
+// constraints. First, with just one AES block per SIMD register, on some
+// CPUs 4 registers don't saturate the 'aesenc' throughput. We therefore
+// do an 8-register wide loop. Considering that and the fact that we have
+// just 16 SIMD registers to work with, it's not feasible to cache AES
+// round keys and GHASH key powers in registers across loop iterations.
+// That's not ideal, but also not actually that bad, since loads can run in
+// parallel with other instructions. Significantly, this also makes it
+// possible to roll up the inner loops, relying on hardware loop unrolling
+// instead of software loop unrolling, greatly reducing code size.
+//
+// - We implement the GHASH multiplications in the main loop using Karatsuba
+// multiplication instead of schoolbook multiplication. This saves one
+// pclmulqdq instruction per block, at the cost of one 64-bit load, one
+// pshufd, and 0.25 pxors per block. (This is without the three-argument
+// XOR support that would be provided by AVX512 / AVX10, which would be
+// more beneficial to schoolbook than Karatsuba.)
+//
+// As a rough approximation, we can assume that Karatsuba multiplication is
+// faster than schoolbook multiplication in this context if one pshufd and
+// 0.25 pxors are cheaper than a pclmulqdq. (We assume that the 64-bit
+// load is "free" due to running in parallel with arithmetic instructions.)
+// This is true on AMD CPUs, including all that support pclmulqdq up to at
+// least Zen 3. It's also true on older Intel CPUs: Westmere through
+// Haswell on the Core side, and Silvermont through Goldmont Plus on the
+// low-power side. On some of these CPUs, pclmulqdq is quite slow, and the
+// benefit of Karatsuba should be substantial. On newer Intel CPUs,
+// schoolbook multiplication should be faster, but only marginally.
+//
+// Not all these CPUs were available to be tested. However, benchmarks on
+// available CPUs suggest that this approximation is plausible. Switching
+// to Karatsuba showed negligible change (< 1%) on Intel Broadwell,
+// Skylake, and Cascade Lake, but it improved AMD Zen 1-3 by 6-7%.
+// Considering that and the fact that Karatsuba should be even more
+// beneficial on older Intel CPUs, it seems like the right choice here.
+//
+// An additional 0.25 pclmulqdq per block (2 per 8 blocks) could be
+// saved by using a multiplication-less reduction method. We don't do that
+// because it would require a large number of shift and xor instructions,
+// making it less worthwhile and likely harmful on newer CPUs.
+//
+// It does make sense to sometimes use a different reduction optimization
+// that saves a pclmulqdq, though: precompute the hash key times x^64, and
+// multiply the low half of the data block by the hash key with the extra
+// factor of x^64. This eliminates one step of the reduction. However,
+// this is incompatible with Karatsuba multiplication. Therefore, for
+// multi-block processing we use Karatsuba multiplication with a regular
+// reduction. For single-block processing, we use the x^64 optimization.
+
+#include <linux/linkage.h>
+
+.section .rodata
+.p2align 4
+.Lbswap_mask:
+ .octa 0x000102030405060708090a0b0c0d0e0f
+.Lgfpoly:
+ .quad 0xc200000000000000
+.Lone:
+ .quad 1
+.Lgfpoly_and_internal_carrybit:
+ .octa 0xc2000000000000010000000000000001
+ // Loading 16 bytes from '.Lzeropad_mask + 16 - len' produces a mask of
+ // 'len' 0xff bytes and the rest zeroes.
+.Lzeropad_mask:
+ .octa 0xffffffffffffffffffffffffffffffff
+ .octa 0
+
+// Offsets in struct aes_gcm_key_aesni
+#define OFFSETOF_AESKEYLEN 480
+#define OFFSETOF_H_POWERS 496
+#define OFFSETOF_H_POWERS_XORED 624
+#define OFFSETOF_H_TIMES_X64 688
+
+.text
+
+// Do a vpclmulqdq, or fall back to a movdqa and a pclmulqdq. The fallback
+// assumes that all operands are distinct and that any mem operand is aligned.
+.macro _vpclmulqdq imm, src1, src2, dst
+.if USE_AVX
+ vpclmulqdq \imm, \src1, \src2, \dst
+.else
+ movdqa \src2, \dst
+ pclmulqdq \imm, \src1, \dst
+.endif
+.endm
+
+// Do a vpshufb, or fall back to a movdqa and a pshufb. The fallback assumes
+// that all operands are distinct and that any mem operand is aligned.
+.macro _vpshufb src1, src2, dst
+.if USE_AVX
+ vpshufb \src1, \src2, \dst
+.else
+ movdqa \src2, \dst
+ pshufb \src1, \dst
+.endif
+.endm
+
+// Do a vpand, or fall back to a movdqu and a pand. The fallback assumes that
+// all operands are distinct.
+.macro _vpand src1, src2, dst
+.if USE_AVX
+ vpand \src1, \src2, \dst
+.else
+ movdqu \src1, \dst
+ pand \src2, \dst
+.endif
+.endm
+
+// XOR the unaligned memory operand \mem into the xmm register \reg. \tmp must
+// be a temporary xmm register.
+.macro _xor_mem_to_reg mem, reg, tmp
+.if USE_AVX
+ vpxor \mem, \reg, \reg
+.else
+ movdqu \mem, \tmp
+ pxor \tmp, \reg
+.endif
+.endm
+
+// Test the unaligned memory operand \mem against the xmm register \reg. \tmp
+// must be a temporary xmm register.
+.macro _test_mem mem, reg, tmp
+.if USE_AVX
+ vptest \mem, \reg
+.else
+ movdqu \mem, \tmp
+ ptest \tmp, \reg
+.endif
+.endm
+
+// Load 1 <= %ecx <= 15 bytes from the pointer \src into the xmm register \dst
+// and zeroize any remaining bytes. Clobbers %rax, %rcx, and \tmp{64,32}.
+.macro _load_partial_block src, dst, tmp64, tmp32
+ sub $8, %ecx // LEN - 8
+ jle .Lle8\@
+
+ // Load 9 <= LEN <= 15 bytes.
+ movq (\src), \dst // Load first 8 bytes
+ mov (\src, %rcx), %rax // Load last 8 bytes
+ neg %ecx
+ shl $3, %ecx
+ shr %cl, %rax // Discard overlapping bytes
+ pinsrq $1, %rax, \dst
+ jmp .Ldone\@
+
+.Lle8\@:
+ add $4, %ecx // LEN - 4
+ jl .Llt4\@
+
+ // Load 4 <= LEN <= 8 bytes.
+ mov (\src), %eax // Load first 4 bytes
+ mov (\src, %rcx), \tmp32 // Load last 4 bytes
+ jmp .Lcombine\@
+
+.Llt4\@:
+ // Load 1 <= LEN <= 3 bytes.
+ add $2, %ecx // LEN - 2
+ movzbl (\src), %eax // Load first byte
+ jl .Lmovq\@
+ movzwl (\src, %rcx), \tmp32 // Load last 2 bytes
+.Lcombine\@:
+ shl $3, %ecx
+ shl %cl, \tmp64
+ or \tmp64, %rax // Combine the two parts
+.Lmovq\@:
+ movq %rax, \dst
+.Ldone\@:
+.endm
+
+// Store 1 <= %ecx <= 15 bytes from the xmm register \src to the pointer \dst.
+// Clobbers %rax, %rcx, and %rsi.
+.macro _store_partial_block src, dst
+ sub $8, %ecx // LEN - 8
+ jl .Llt8\@
+
+ // Store 8 <= LEN <= 15 bytes.
+ pextrq $1, \src, %rax
+ mov %ecx, %esi
+ shl $3, %ecx
+ ror %cl, %rax
+ mov %rax, (\dst, %rsi) // Store last LEN - 8 bytes
+ movq \src, (\dst) // Store first 8 bytes
+ jmp .Ldone\@
+
+.Llt8\@:
+ add $4, %ecx // LEN - 4
+ jl .Llt4\@
+
+ // Store 4 <= LEN <= 7 bytes.
+ pextrd $1, \src, %eax
+ mov %ecx, %esi
+ shl $3, %ecx
+ ror %cl, %eax
+ mov %eax, (\dst, %rsi) // Store last LEN - 4 bytes
+ movd \src, (\dst) // Store first 4 bytes
+ jmp .Ldone\@
+
+.Llt4\@:
+ // Store 1 <= LEN <= 3 bytes.
+ pextrb $0, \src, 0(\dst)
+ cmp $-2, %ecx // LEN - 4 == -2, i.e. LEN == 2?
+ jl .Ldone\@
+ pextrb $1, \src, 1(\dst)
+ je .Ldone\@
+ pextrb $2, \src, 2(\dst)
+.Ldone\@:
+.endm
+
+// Do one step of GHASH-multiplying \a by \b and storing the reduced product in
+// \b. To complete all steps, this must be invoked with \i=0 through \i=9.
+// \a_times_x64 must contain \a * x^64 in reduced form, \gfpoly must contain the
+// .Lgfpoly constant, and \t0-\t1 must be temporary registers.
+.macro _ghash_mul_step i, a, a_times_x64, b, gfpoly, t0, t1
+
+ // MI = (a_L * b_H) + ((a*x^64)_L * b_L)
+.if \i == 0
+ _vpclmulqdq $0x01, \a, \b, \t0
+.elseif \i == 1
+ _vpclmulqdq $0x00, \a_times_x64, \b, \t1
+.elseif \i == 2
+ pxor \t1, \t0
+
+ // HI = (a_H * b_H) + ((a*x^64)_H * b_L)
+.elseif \i == 3
+ _vpclmulqdq $0x11, \a, \b, \t1
+.elseif \i == 4
+ pclmulqdq $0x10, \a_times_x64, \b
+.elseif \i == 5
+ pxor \t1, \b
+.elseif \i == 6
+
+ // Fold MI into HI.
+ pshufd $0x4e, \t0, \t1 // Swap halves of MI
+.elseif \i == 7
+ pclmulqdq $0x00, \gfpoly, \t0 // MI_L*(x^63 + x^62 + x^57)
+.elseif \i == 8
+ pxor \t1, \b
+.elseif \i == 9
+ pxor \t0, \b
+.endif
+.endm
+
+// GHASH-multiply \a by \b and store the reduced product in \b.
+// See _ghash_mul_step for details.
+.macro _ghash_mul a, a_times_x64, b, gfpoly, t0, t1
+.irp i, 0,1,2,3,4,5,6,7,8,9
+ _ghash_mul_step \i, \a, \a_times_x64, \b, \gfpoly, \t0, \t1
+.endr
+.endm
+
+// GHASH-multiply \a by \b and add the unreduced product to \lo, \mi, and \hi.
+// This does Karatsuba multiplication and must be paired with _ghash_reduce. On
+// the first call, \lo, \mi, and \hi must be zero. \a_xored must contain the
+// two halves of \a XOR'd together, i.e. a_L + a_H. \b is clobbered.
+.macro _ghash_mul_noreduce a, a_xored, b, lo, mi, hi, t0
+
+ // LO += a_L * b_L
+ _vpclmulqdq $0x00, \a, \b, \t0
+ pxor \t0, \lo
+
+ // b_L + b_H
+ pshufd $0x4e, \b, \t0
+ pxor \b, \t0
+
+ // HI += a_H * b_H
+ pclmulqdq $0x11, \a, \b
+ pxor \b, \hi
+
+ // MI += (a_L + a_H) * (b_L + b_H)
+ pclmulqdq $0x00, \a_xored, \t0
+ pxor \t0, \mi
+.endm
+
+// Reduce the product from \lo, \mi, and \hi, and store the result in \dst.
+// This assumes that _ghash_mul_noreduce was used.
+.macro _ghash_reduce lo, mi, hi, dst, t0
+
+ movq .Lgfpoly(%rip), \t0
+
+ // MI += LO + HI (needed because we used Karatsuba multiplication)
+ pxor \lo, \mi
+ pxor \hi, \mi
+
+ // Fold LO into MI.
+ pshufd $0x4e, \lo, \dst
+ pclmulqdq $0x00, \t0, \lo
+ pxor \dst, \mi
+ pxor \lo, \mi
+
+ // Fold MI into HI.
+ pshufd $0x4e, \mi, \dst
+ pclmulqdq $0x00, \t0, \mi
+ pxor \hi, \dst
+ pxor \mi, \dst
+.endm
+
+// Do the first step of the GHASH update of a set of 8 ciphertext blocks.
+//
+// The whole GHASH update does:
+//
+// GHASH_ACC = (blk0+GHASH_ACC)*H^8 + blk1*H^7 + blk2*H^6 + blk3*H^5 +
+// blk4*H^4 + blk5*H^3 + blk6*H^2 + blk7*H^1
+//
+// This macro just does the first step: it does the unreduced multiplication
+// (blk0+GHASH_ACC)*H^8 and starts gathering the unreduced product in the xmm
+// registers LO, MI, and GHASH_ACC a.k.a. HI. It also zero-initializes the
+// inner block counter in %rax, which is a value that counts up by 8 for each
+// block in the set of 8 and is used later to index by 8*blknum and 16*blknum.
+//
+// To reduce the number of pclmulqdq instructions required, both this macro and
+// _ghash_update_continue_8x use Karatsuba multiplication instead of schoolbook
+// multiplication. See the file comment for more details about this choice.
+//
+// Both macros expect the ciphertext blocks blk[0-7] to be available at DST if
+// encrypting, or SRC if decrypting. They also expect the precomputed hash key
+// powers H^i and their XOR'd-together halves to be available in the struct
+// pointed to by KEY. Both macros clobber TMP[0-2].
+.macro _ghash_update_begin_8x enc
+
+ // Initialize the inner block counter.
+ xor %eax, %eax
+
+ // Load the highest hash key power, H^8.
+ movdqa OFFSETOF_H_POWERS(KEY), TMP0
+
+ // Load the first ciphertext block and byte-reflect it.
+.if \enc
+ movdqu (DST), TMP1
+.else
+ movdqu (SRC), TMP1
+.endif
+ pshufb BSWAP_MASK, TMP1
+
+ // Add the GHASH accumulator to the ciphertext block to get the block
+ // 'b' that needs to be multiplied with the hash key power 'a'.
+ pxor TMP1, GHASH_ACC
+
+ // b_L + b_H
+ pshufd $0x4e, GHASH_ACC, MI
+ pxor GHASH_ACC, MI
+
+ // LO = a_L * b_L
+ _vpclmulqdq $0x00, TMP0, GHASH_ACC, LO
+
+ // HI = a_H * b_H
+ pclmulqdq $0x11, TMP0, GHASH_ACC
+
+ // MI = (a_L + a_H) * (b_L + b_H)
+ pclmulqdq $0x00, OFFSETOF_H_POWERS_XORED(KEY), MI
+.endm
+
+// Continue the GHASH update of 8 ciphertext blocks as described above by doing
+// an unreduced multiplication of the next ciphertext block by the next lowest
+// key power and accumulating the result into LO, MI, and GHASH_ACC a.k.a. HI.
+.macro _ghash_update_continue_8x enc
+ add $8, %eax
+
+ // Load the next lowest key power.
+ movdqa OFFSETOF_H_POWERS(KEY,%rax,2), TMP0
+
+ // Load the next ciphertext block and byte-reflect it.
+.if \enc
+ movdqu (DST,%rax,2), TMP1
+.else
+ movdqu (SRC,%rax,2), TMP1
+.endif
+ pshufb BSWAP_MASK, TMP1
+
+ // LO += a_L * b_L
+ _vpclmulqdq $0x00, TMP0, TMP1, TMP2
+ pxor TMP2, LO
+
+ // b_L + b_H
+ pshufd $0x4e, TMP1, TMP2
+ pxor TMP1, TMP2
+
+ // HI += a_H * b_H
+ pclmulqdq $0x11, TMP0, TMP1
+ pxor TMP1, GHASH_ACC
+
+ // MI += (a_L + a_H) * (b_L + b_H)
+ movq OFFSETOF_H_POWERS_XORED(KEY,%rax), TMP1
+ pclmulqdq $0x00, TMP1, TMP2
+ pxor TMP2, MI
+.endm
+
+// Reduce LO, MI, and GHASH_ACC a.k.a. HI into GHASH_ACC. This is similar to
+// _ghash_reduce, but it's hardcoded to use the registers of the main loop and
+// it uses the same register for HI and the destination. It's also divided into
+// two steps. TMP1 must be preserved across steps.
+//
+// One pshufd could be saved by shuffling MI and XOR'ing LO into it, instead of
+// shuffling LO, XOR'ing LO into MI, and shuffling MI. However, this would
+// increase the critical path length, and it seems to slightly hurt performance.
+.macro _ghash_update_end_8x_step i
+.if \i == 0
+ movq .Lgfpoly(%rip), TMP1
+ pxor LO, MI
+ pxor GHASH_ACC, MI
+ pshufd $0x4e, LO, TMP2
+ pclmulqdq $0x00, TMP1, LO
+ pxor TMP2, MI
+ pxor LO, MI
+.elseif \i == 1
+ pshufd $0x4e, MI, TMP2
+ pclmulqdq $0x00, TMP1, MI
+ pxor TMP2, GHASH_ACC
+ pxor MI, GHASH_ACC
+.endif
+.endm
+
+// void aes_gcm_precompute_##suffix(struct aes_gcm_key_aesni *key);
+//
+// Given the expanded AES key, derive the GHASH subkey and initialize the GHASH
+// related fields in the key struct.
+.macro _aes_gcm_precompute
+
+ // Function arguments
+ .set KEY, %rdi
+
+ // Additional local variables.
+ // %xmm0-%xmm1 and %rax are used as temporaries.
+ .set RNDKEYLAST_PTR, %rsi
+ .set H_CUR, %xmm2
+ .set H_POW1, %xmm3 // H^1
+ .set H_POW1_X64, %xmm4 // H^1 * x^64
+ .set GFPOLY, %xmm5
+
+ // Encrypt an all-zeroes block to get the raw hash subkey.
+ movl OFFSETOF_AESKEYLEN(KEY), %eax
+ lea 6*16(KEY,%rax,4), RNDKEYLAST_PTR
+ movdqa (KEY), H_POW1 // Zero-th round key XOR all-zeroes block
+ lea 16(KEY), %rax
+1:
+ aesenc (%rax), H_POW1
+ add $16, %rax
+ cmp %rax, RNDKEYLAST_PTR
+ jne 1b
+ aesenclast (RNDKEYLAST_PTR), H_POW1
+
+ // Preprocess the raw hash subkey as needed to operate on GHASH's
+ // bit-reflected values directly: reflect its bytes, then multiply it by
+ // x^-1 (using the backwards interpretation of polynomial coefficients
+ // from the GCM spec) or equivalently x^1 (using the alternative,
+ // natural interpretation of polynomial coefficients).
+ pshufb .Lbswap_mask(%rip), H_POW1
+ movdqa H_POW1, %xmm0
+ pshufd $0xd3, %xmm0, %xmm0
+ psrad $31, %xmm0
+ paddq H_POW1, H_POW1
+ pand .Lgfpoly_and_internal_carrybit(%rip), %xmm0
+ pxor %xmm0, H_POW1
+
+ // Store H^1.
+ movdqa H_POW1, OFFSETOF_H_POWERS+7*16(KEY)
+
+ // Compute and store H^1 * x^64.
+ movq .Lgfpoly(%rip), GFPOLY
+ pshufd $0x4e, H_POW1, %xmm0
+ _vpclmulqdq $0x00, H_POW1, GFPOLY, H_POW1_X64
+ pxor %xmm0, H_POW1_X64
+ movdqa H_POW1_X64, OFFSETOF_H_TIMES_X64(KEY)
+
+ // Compute and store the halves of H^1 XOR'd together.
+ pxor H_POW1, %xmm0
+ movq %xmm0, OFFSETOF_H_POWERS_XORED+7*8(KEY)
+
+ // Compute and store the remaining key powers H^2 through H^8.
+ movdqa H_POW1, H_CUR
+ mov $6*8, %eax
+.Lprecompute_next\@:
+ // Compute H^i = H^{i-1} * H^1.
+ _ghash_mul H_POW1, H_POW1_X64, H_CUR, GFPOLY, %xmm0, %xmm1
+ // Store H^i.
+ movdqa H_CUR, OFFSETOF_H_POWERS(KEY,%rax,2)
+ // Compute and store the halves of H^i XOR'd together.
+ pshufd $0x4e, H_CUR, %xmm0
+ pxor H_CUR, %xmm0
+ movq %xmm0, OFFSETOF_H_POWERS_XORED(KEY,%rax)
+ sub $8, %eax
+ jge .Lprecompute_next\@
+
+ RET
+.endm
+
+// void aes_gcm_aad_update_aesni(const struct aes_gcm_key_aesni *key,
+// u8 ghash_acc[16], const u8 *aad, int aadlen);
+//
+// This function processes the AAD (Additional Authenticated Data) in GCM.
+// Using the key |key|, it updates the GHASH accumulator |ghash_acc| with the
+// data given by |aad| and |aadlen|. On the first call, |ghash_acc| must be all
+// zeroes. |aadlen| must be a multiple of 16, except on the last call where it
+// can be any length. The caller must do any buffering needed to ensure this.
+.macro _aes_gcm_aad_update
+
+ // Function arguments
+ .set KEY, %rdi
+ .set GHASH_ACC_PTR, %rsi
+ .set AAD, %rdx
+ .set AADLEN, %ecx
+ // Note: _load_partial_block relies on AADLEN being in %ecx.
+
+ // Additional local variables.
+ // %rax, %r10, and %xmm0-%xmm1 are used as temporary registers.
+ .set BSWAP_MASK, %xmm2
+ .set GHASH_ACC, %xmm3
+ .set H_POW1, %xmm4 // H^1
+ .set H_POW1_X64, %xmm5 // H^1 * x^64
+ .set GFPOLY, %xmm6
+
+ movdqa .Lbswap_mask(%rip), BSWAP_MASK
+ movdqu (GHASH_ACC_PTR), GHASH_ACC
+ movdqa OFFSETOF_H_POWERS+7*16(KEY), H_POW1
+ movdqa OFFSETOF_H_TIMES_X64(KEY), H_POW1_X64
+ movq .Lgfpoly(%rip), GFPOLY
+
+ // Process the AAD one full block at a time.
+ sub $16, AADLEN
+ jl .Laad_loop_1x_done\@
+.Laad_loop_1x\@:
+ movdqu (AAD), %xmm0
+ pshufb BSWAP_MASK, %xmm0
+ pxor %xmm0, GHASH_ACC
+ _ghash_mul H_POW1, H_POW1_X64, GHASH_ACC, GFPOLY, %xmm0, %xmm1
+ add $16, AAD
+ sub $16, AADLEN
+ jge .Laad_loop_1x\@
+.Laad_loop_1x_done\@:
+ // Check whether there is a partial block at the end.
+ add $16, AADLEN
+ jz .Laad_done\@
+
+ // Process a partial block of length 1 <= AADLEN <= 15.
+ // _load_partial_block assumes that %ecx contains AADLEN.
+ _load_partial_block AAD, %xmm0, %r10, %r10d
+ pshufb BSWAP_MASK, %xmm0
+ pxor %xmm0, GHASH_ACC
+ _ghash_mul H_POW1, H_POW1_X64, GHASH_ACC, GFPOLY, %xmm0, %xmm1
+
+.Laad_done\@:
+ movdqu GHASH_ACC, (GHASH_ACC_PTR)
+ RET
+.endm
+
+// Increment LE_CTR eight times to generate eight little-endian counter blocks,
+// swap each to big-endian, and store them in AESDATA[0-7]. Also XOR them with
+// the zero-th AES round key. Clobbers TMP0 and TMP1.
+.macro _ctr_begin_8x
+ movq .Lone(%rip), TMP0
+ movdqa (KEY), TMP1 // zero-th round key
+.irp i, 0,1,2,3,4,5,6,7
+ _vpshufb BSWAP_MASK, LE_CTR, AESDATA\i
+ pxor TMP1, AESDATA\i
+ paddd TMP0, LE_CTR
+.endr
+.endm
+
+// Do a non-last round of AES on AESDATA[0-7] using \round_key.
+.macro _aesenc_8x round_key
+.irp i, 0,1,2,3,4,5,6,7
+ aesenc \round_key, AESDATA\i
+.endr
+.endm
+
+// Do the last round of AES on AESDATA[0-7] using \round_key.
+.macro _aesenclast_8x round_key
+.irp i, 0,1,2,3,4,5,6,7
+ aesenclast \round_key, AESDATA\i
+.endr
+.endm
+
+// XOR eight blocks from SRC with the keystream blocks in AESDATA[0-7], and
+// store the result to DST. Clobbers TMP0.
+.macro _xor_data_8x
+.irp i, 0,1,2,3,4,5,6,7
+ _xor_mem_to_reg \i*16(SRC), AESDATA\i, tmp=TMP0
+.endr
+.irp i, 0,1,2,3,4,5,6,7
+ movdqu AESDATA\i, \i*16(DST)
+.endr
+.endm
+
+// void aes_gcm_{enc,dec}_update_##suffix(const struct aes_gcm_key_aesni *key,
+// const u32 le_ctr[4], u8 ghash_acc[16],
+// const u8 *src, u8 *dst, int datalen);
+//
+// This macro generates a GCM encryption or decryption update function with the
+// above prototype (with \enc selecting which one).
+//
+// This function computes the next portion of the CTR keystream, XOR's it with
+// |datalen| bytes from |src|, and writes the resulting encrypted or decrypted
+// data to |dst|. It also updates the GHASH accumulator |ghash_acc| using the
+// next |datalen| ciphertext bytes.
+//
+// |datalen| must be a multiple of 16, except on the last call where it can be
+// any length. The caller must do any buffering needed to ensure this. Both
+// in-place and out-of-place en/decryption are supported.
+//
+// |le_ctr| must give the current counter in little-endian format. For a new
+// message, the low word of the counter must be 2. This function loads the
+// counter from |le_ctr| and increments the loaded counter as needed, but it
+// does *not* store the updated counter back to |le_ctr|. The caller must
+// update |le_ctr| if any more data segments follow. Internally, only the low
+// 32-bit word of the counter is incremented, following the GCM standard.
+.macro _aes_gcm_update enc
+
+ // Function arguments
+ .set KEY, %rdi
+ .set LE_CTR_PTR, %rsi // Note: overlaps with usage as temp reg
+ .set GHASH_ACC_PTR, %rdx
+ .set SRC, %rcx
+ .set DST, %r8
+ .set DATALEN, %r9d
+ .set DATALEN64, %r9 // Zero-extend DATALEN before using!
+ // Note: the code setting up for _load_partial_block assumes that SRC is
+ // in %rcx (and that DATALEN is *not* in %rcx).
+
+ // Additional local variables
+
+ // %rax and %rsi are used as temporary registers. Note: %rsi overlaps
+ // with LE_CTR_PTR, which is used only at the beginning.
+
+ .set AESKEYLEN, %r10d // AES key length in bytes
+ .set AESKEYLEN64, %r10
+ .set RNDKEYLAST_PTR, %r11 // Pointer to last AES round key
+
+ // Put the most frequently used values in %xmm0-%xmm7 to reduce code
+ // size. (%xmm0-%xmm7 take fewer bytes to encode than %xmm8-%xmm15.)
+ .set TMP0, %xmm0
+ .set TMP1, %xmm1
+ .set TMP2, %xmm2
+ .set LO, %xmm3 // Low part of unreduced product
+ .set MI, %xmm4 // Middle part of unreduced product
+ .set GHASH_ACC, %xmm5 // GHASH accumulator; in main loop also
+ // the high part of unreduced product
+ .set BSWAP_MASK, %xmm6 // Shuffle mask for reflecting bytes
+ .set LE_CTR, %xmm7 // Little-endian counter value
+ .set AESDATA0, %xmm8
+ .set AESDATA1, %xmm9
+ .set AESDATA2, %xmm10
+ .set AESDATA3, %xmm11
+ .set AESDATA4, %xmm12
+ .set AESDATA5, %xmm13
+ .set AESDATA6, %xmm14
+ .set AESDATA7, %xmm15
+
+ movdqa .Lbswap_mask(%rip), BSWAP_MASK
+ movdqu (GHASH_ACC_PTR), GHASH_ACC
+ movdqu (LE_CTR_PTR), LE_CTR
+
+ movl OFFSETOF_AESKEYLEN(KEY), AESKEYLEN
+ lea 6*16(KEY,AESKEYLEN64,4), RNDKEYLAST_PTR
+
+ // If there are at least 8*16 bytes of data, then continue into the main
+ // loop, which processes 8*16 bytes of data per iteration.
+ //
+ // The main loop interleaves AES and GHASH to improve performance on
+ // CPUs that can execute these instructions in parallel. When
+ // decrypting, the GHASH input (the ciphertext) is immediately
+ // available. When encrypting, we instead encrypt a set of 8 blocks
+ // first and then GHASH those blocks while encrypting the next set of 8,
+ // repeat that as needed, and finally GHASH the last set of 8 blocks.
+ //
+ // Code size optimization: Prefer adding or subtracting -8*16 over 8*16,
+ // as this makes the immediate fit in a signed byte, saving 3 bytes.
+ add $-8*16, DATALEN
+ jl .Lcrypt_loop_8x_done\@
+.if \enc
+ // Encrypt the first 8 plaintext blocks.
+ _ctr_begin_8x
+ lea 16(KEY), %rsi
+ .p2align 4
+1:
+ movdqa (%rsi), TMP0
+ _aesenc_8x TMP0
+ add $16, %rsi
+ cmp %rsi, RNDKEYLAST_PTR
+ jne 1b
+ movdqa (%rsi), TMP0
+ _aesenclast_8x TMP0
+ _xor_data_8x
+ // Don't increment DST until the ciphertext blocks have been hashed.
+ sub $-8*16, SRC
+ add $-8*16, DATALEN
+ jl .Lghash_last_ciphertext_8x\@
+.endif
+
+ .p2align 4
+.Lcrypt_loop_8x\@:
+
+ // Generate the next set of 8 counter blocks and start encrypting them.
+ _ctr_begin_8x
+ lea 16(KEY), %rsi
+
+ // Do a round of AES, and start the GHASH update of 8 ciphertext blocks
+ // by doing the unreduced multiplication for the first ciphertext block.
+ movdqa (%rsi), TMP0
+ add $16, %rsi
+ _aesenc_8x TMP0
+ _ghash_update_begin_8x \enc
+
+ // Do 7 more rounds of AES, and continue the GHASH update by doing the
+ // unreduced multiplication for the remaining ciphertext blocks.
+ .p2align 4
+1:
+ movdqa (%rsi), TMP0
+ add $16, %rsi
+ _aesenc_8x TMP0
+ _ghash_update_continue_8x \enc
+ cmp $7*8, %eax
+ jne 1b
+
+ // Do the remaining AES rounds.
+ .p2align 4
+1:
+ movdqa (%rsi), TMP0
+ add $16, %rsi
+ _aesenc_8x TMP0
+ cmp %rsi, RNDKEYLAST_PTR
+ jne 1b
+
+ // Do the GHASH reduction and the last round of AES.
+ movdqa (RNDKEYLAST_PTR), TMP0
+ _ghash_update_end_8x_step 0
+ _aesenclast_8x TMP0
+ _ghash_update_end_8x_step 1
+
+ // XOR the data with the AES-CTR keystream blocks.
+.if \enc
+ sub $-8*16, DST
+.endif
+ _xor_data_8x
+ sub $-8*16, SRC
+.if !\enc
+ sub $-8*16, DST
+.endif
+ add $-8*16, DATALEN
+ jge .Lcrypt_loop_8x\@
+
+.if \enc
+.Lghash_last_ciphertext_8x\@:
+ // Update GHASH with the last set of 8 ciphertext blocks.
+ _ghash_update_begin_8x \enc
+ .p2align 4
+1:
+ _ghash_update_continue_8x \enc
+ cmp $7*8, %eax
+ jne 1b
+ _ghash_update_end_8x_step 0
+ _ghash_update_end_8x_step 1
+ sub $-8*16, DST
+.endif
+
+.Lcrypt_loop_8x_done\@:
+
+ sub $-8*16, DATALEN
+ jz .Ldone\@
+
+ // Handle the remainder of length 1 <= DATALEN < 8*16 bytes. We keep
+ // things simple and keep the code size down by just going one block at
+ // a time, again taking advantage of hardware loop unrolling. Since
+ // there are enough key powers available for all remaining data, we do
+ // the GHASH multiplications unreduced, and only reduce at the very end.
+
+ .set HI, TMP2
+ .set H_POW, AESDATA0
+ .set H_POW_XORED, AESDATA1
+ .set ONE, AESDATA2
+
+ movq .Lone(%rip), ONE
+
+ // Start collecting the unreduced GHASH intermediate value LO, MI, HI.
+ pxor LO, LO
+ pxor MI, MI
+ pxor HI, HI
+
+ // Set up a block counter %rax to contain 8*(8-n), where n is the number
+ // of blocks that remain, counting any partial block. This will be used
+ // to access the key powers H^n through H^1.
+ mov DATALEN, %eax
+ neg %eax
+ and $~15, %eax
+ sar $1, %eax
+ add $64, %eax
+
+ sub $16, DATALEN
+ jl .Lcrypt_loop_1x_done\@
+
+ // Process the data one full block at a time.
+.Lcrypt_loop_1x\@:
+
+ // Encrypt the next counter block.
+ _vpshufb BSWAP_MASK, LE_CTR, TMP0
+ paddd ONE, LE_CTR
+ pxor (KEY), TMP0
+ lea -6*16(RNDKEYLAST_PTR), %rsi // Reduce code size
+ cmp $24, AESKEYLEN
+ jl 128f // AES-128?
+ je 192f // AES-192?
+ // AES-256
+ aesenc -7*16(%rsi), TMP0
+ aesenc -6*16(%rsi), TMP0
+192:
+ aesenc -5*16(%rsi), TMP0
+ aesenc -4*16(%rsi), TMP0
+128:
+.irp i, -3,-2,-1,0,1,2,3,4,5
+ aesenc \i*16(%rsi), TMP0
+.endr
+ aesenclast (RNDKEYLAST_PTR), TMP0
+
+ // Load the next key power H^i.
+ movdqa OFFSETOF_H_POWERS(KEY,%rax,2), H_POW
+ movq OFFSETOF_H_POWERS_XORED(KEY,%rax), H_POW_XORED
+
+ // XOR the keystream block that was just generated in TMP0 with the next
+ // source data block and store the resulting en/decrypted data to DST.
+.if \enc
+ _xor_mem_to_reg (SRC), TMP0, tmp=TMP1
+ movdqu TMP0, (DST)
+.else
+ movdqu (SRC), TMP1
+ pxor TMP1, TMP0
+ movdqu TMP0, (DST)
+.endif
+
+ // Update GHASH with the ciphertext block.
+.if \enc
+ pshufb BSWAP_MASK, TMP0
+ pxor TMP0, GHASH_ACC
+.else
+ pshufb BSWAP_MASK, TMP1
+ pxor TMP1, GHASH_ACC
+.endif
+ _ghash_mul_noreduce H_POW, H_POW_XORED, GHASH_ACC, LO, MI, HI, TMP0
+ pxor GHASH_ACC, GHASH_ACC
+
+ add $8, %eax
+ add $16, SRC
+ add $16, DST
+ sub $16, DATALEN
+ jge .Lcrypt_loop_1x\@
+.Lcrypt_loop_1x_done\@:
+ // Check whether there is a partial block at the end.
+ add $16, DATALEN
+ jz .Lghash_reduce\@
+
+ // Process a partial block of length 1 <= DATALEN <= 15.
+
+ // Encrypt a counter block for the last time.
+ pshufb BSWAP_MASK, LE_CTR
+ pxor (KEY), LE_CTR
+ lea 16(KEY), %rsi
+1:
+ aesenc (%rsi), LE_CTR
+ add $16, %rsi
+ cmp %rsi, RNDKEYLAST_PTR
+ jne 1b
+ aesenclast (RNDKEYLAST_PTR), LE_CTR
+
+ // Load the lowest key power, H^1.
+ movdqa OFFSETOF_H_POWERS(KEY,%rax,2), H_POW
+ movq OFFSETOF_H_POWERS_XORED(KEY,%rax), H_POW_XORED
+
+ // Load and zero-pad 1 <= DATALEN <= 15 bytes of data from SRC. SRC is
+ // in %rcx, but _load_partial_block needs DATALEN in %rcx instead.
+ // RNDKEYLAST_PTR is no longer needed, so reuse it for SRC.
+ mov SRC, RNDKEYLAST_PTR
+ mov DATALEN, %ecx
+ _load_partial_block RNDKEYLAST_PTR, TMP0, %rsi, %esi
+
+ // XOR the keystream block that was just generated in LE_CTR with the
+ // source data block and store the resulting en/decrypted data to DST.
+ pxor TMP0, LE_CTR
+ mov DATALEN, %ecx
+ _store_partial_block LE_CTR, DST
+
+ // If encrypting, zero-pad the final ciphertext block for GHASH. (If
+ // decrypting, this was already done by _load_partial_block.)
+.if \enc
+ lea .Lzeropad_mask+16(%rip), %rax
+ sub DATALEN64, %rax
+ _vpand (%rax), LE_CTR, TMP0
+.endif
+
+ // Update GHASH with the final ciphertext block.
+ pshufb BSWAP_MASK, TMP0
+ pxor TMP0, GHASH_ACC
+ _ghash_mul_noreduce H_POW, H_POW_XORED, GHASH_ACC, LO, MI, HI, TMP0
+
+.Lghash_reduce\@:
+ // Finally, do the GHASH reduction.
+ _ghash_reduce LO, MI, HI, GHASH_ACC, TMP0
+
+.Ldone\@:
+ // Store the updated GHASH accumulator back to memory.
+ movdqu GHASH_ACC, (GHASH_ACC_PTR)
+
+ RET
+.endm
+
+// void aes_gcm_enc_final_##suffix(const struct aes_gcm_key_aesni *key,
+// const u32 le_ctr[4], u8 ghash_acc[16],
+// u64 total_aadlen, u64 total_datalen);
+// bool aes_gcm_dec_final_##suffix(const struct aes_gcm_key_aesni *key,
+// const u32 le_ctr[4], const u8 ghash_acc[16],
+// u64 total_aadlen, u64 total_datalen,
+// const u8 tag[16], int taglen);
+//
+// This macro generates one of the above two functions (with \enc selecting
+// which one). Both functions finish computing the GCM authentication tag by
+// updating GHASH with the lengths block and encrypting the GHASH accumulator.
+// |total_aadlen| and |total_datalen| must be the total length of the additional
+// authenticated data and the en/decrypted data in bytes, respectively.
+//
+// The encryption function then stores the full-length (16-byte) computed
+// authentication tag to |ghash_acc|. The decryption function instead loads the
+// expected authentication tag (the one that was transmitted) from the 16-byte
+// buffer |tag|, compares the first 4 <= |taglen| <= 16 bytes of it to the
+// computed tag in constant time, and returns true if and only if they match.
+.macro _aes_gcm_final enc
+
+ // Function arguments
+ .set KEY, %rdi
+ .set LE_CTR_PTR, %rsi
+ .set GHASH_ACC_PTR, %rdx
+ .set TOTAL_AADLEN, %rcx
+ .set TOTAL_DATALEN, %r8
+ .set TAG, %r9
+ .set TAGLEN, %r10d // Originally at 8(%rsp)
+ .set TAGLEN64, %r10
+
+ // Additional local variables.
+ // %rax and %xmm0-%xmm2 are used as temporary registers.
+ .set AESKEYLEN, %r11d
+ .set AESKEYLEN64, %r11
+ .set BSWAP_MASK, %xmm3
+ .set GHASH_ACC, %xmm4
+ .set H_POW1, %xmm5 // H^1
+ .set H_POW1_X64, %xmm6 // H^1 * x^64
+ .set GFPOLY, %xmm7
+
+ movdqa .Lbswap_mask(%rip), BSWAP_MASK
+ movl OFFSETOF_AESKEYLEN(KEY), AESKEYLEN
+
+ // Set up a counter block with 1 in the low 32-bit word. This is the
+ // counter that produces the ciphertext needed to encrypt the auth tag.
+ movdqu (LE_CTR_PTR), %xmm0
+ mov $1, %eax
+ pinsrd $0, %eax, %xmm0
+
+ // Build the lengths block and XOR it into the GHASH accumulator.
+ movq TOTAL_DATALEN, GHASH_ACC
+ pinsrq $1, TOTAL_AADLEN, GHASH_ACC
+ psllq $3, GHASH_ACC // Bytes to bits
+ _xor_mem_to_reg (GHASH_ACC_PTR), GHASH_ACC, %xmm1
+
+ movdqa OFFSETOF_H_POWERS+7*16(KEY), H_POW1
+ movdqa OFFSETOF_H_TIMES_X64(KEY), H_POW1_X64
+ movq .Lgfpoly(%rip), GFPOLY
+
+ // Make %rax point to the 6th from last AES round key. (Using signed
+ // byte offsets -7*16 through 6*16 decreases code size.)
+ lea (KEY,AESKEYLEN64,4), %rax
+
+ // AES-encrypt the counter block and also multiply GHASH_ACC by H^1.
+ // Interleave the AES and GHASH instructions to improve performance.
+ pshufb BSWAP_MASK, %xmm0
+ pxor (KEY), %xmm0
+ cmp $24, AESKEYLEN
+ jl 128f // AES-128?
+ je 192f // AES-192?
+ // AES-256
+ aesenc -7*16(%rax), %xmm0
+ aesenc -6*16(%rax), %xmm0
+192:
+ aesenc -5*16(%rax), %xmm0
+ aesenc -4*16(%rax), %xmm0
+128:
+.irp i, 0,1,2,3,4,5,6,7,8
+ aesenc (\i-3)*16(%rax), %xmm0
+ _ghash_mul_step \i, H_POW1, H_POW1_X64, GHASH_ACC, GFPOLY, %xmm1, %xmm2
+.endr
+ aesenclast 6*16(%rax), %xmm0
+ _ghash_mul_step 9, H_POW1, H_POW1_X64, GHASH_ACC, GFPOLY, %xmm1, %xmm2
+
+ // Undo the byte reflection of the GHASH accumulator.
+ pshufb BSWAP_MASK, GHASH_ACC
+
+ // Encrypt the GHASH accumulator.
+ pxor %xmm0, GHASH_ACC
+
+.if \enc
+ // Return the computed auth tag.
+ movdqu GHASH_ACC, (GHASH_ACC_PTR)
+.else
+ .set ZEROPAD_MASK_PTR, TOTAL_AADLEN // Reusing TOTAL_AADLEN!
+
+ // Verify the auth tag in constant time by XOR'ing the transmitted and
+ // computed auth tags together and using the ptest instruction to check
+ // whether the first TAGLEN bytes of the result are zero.
+ _xor_mem_to_reg (TAG), GHASH_ACC, tmp=%xmm0
+ movl 8(%rsp), TAGLEN
+ lea .Lzeropad_mask+16(%rip), ZEROPAD_MASK_PTR
+ sub TAGLEN64, ZEROPAD_MASK_PTR
+ xor %eax, %eax
+ _test_mem (ZEROPAD_MASK_PTR), GHASH_ACC, tmp=%xmm0
+ sete %al
+.endif
+ RET
+.endm
+
+.set USE_AVX, 0
+SYM_FUNC_START(aes_gcm_precompute_aesni)
+ _aes_gcm_precompute
+SYM_FUNC_END(aes_gcm_precompute_aesni)
+SYM_FUNC_START(aes_gcm_aad_update_aesni)
+ _aes_gcm_aad_update
+SYM_FUNC_END(aes_gcm_aad_update_aesni)
+SYM_FUNC_START(aes_gcm_enc_update_aesni)
+ _aes_gcm_update 1
+SYM_FUNC_END(aes_gcm_enc_update_aesni)
+SYM_FUNC_START(aes_gcm_dec_update_aesni)
+ _aes_gcm_update 0
+SYM_FUNC_END(aes_gcm_dec_update_aesni)
+SYM_FUNC_START(aes_gcm_enc_final_aesni)
+ _aes_gcm_final 1
+SYM_FUNC_END(aes_gcm_enc_final_aesni)
+SYM_FUNC_START(aes_gcm_dec_final_aesni)
+ _aes_gcm_final 0
+SYM_FUNC_END(aes_gcm_dec_final_aesni)
+
+.set USE_AVX, 1
+SYM_FUNC_START(aes_gcm_precompute_aesni_avx)
+ _aes_gcm_precompute
+SYM_FUNC_END(aes_gcm_precompute_aesni_avx)
+SYM_FUNC_START(aes_gcm_aad_update_aesni_avx)
+ _aes_gcm_aad_update
+SYM_FUNC_END(aes_gcm_aad_update_aesni_avx)
+SYM_FUNC_START(aes_gcm_enc_update_aesni_avx)
+ _aes_gcm_update 1
+SYM_FUNC_END(aes_gcm_enc_update_aesni_avx)
+SYM_FUNC_START(aes_gcm_dec_update_aesni_avx)
+ _aes_gcm_update 0
+SYM_FUNC_END(aes_gcm_dec_update_aesni_avx)
+SYM_FUNC_START(aes_gcm_enc_final_aesni_avx)
+ _aes_gcm_final 1
+SYM_FUNC_END(aes_gcm_enc_final_aesni_avx)
+SYM_FUNC_START(aes_gcm_dec_final_aesni_avx)
+ _aes_gcm_final 0
+SYM_FUNC_END(aes_gcm_dec_final_aesni_avx)
diff --git a/arch/x86/crypto/aes-gcm-avx10-x86_64.S b/arch/x86/crypto/aes-gcm-avx10-x86_64.S
new file mode 100644
index 000000000000..97e0ee515fc5
--- /dev/null
+++ b/arch/x86/crypto/aes-gcm-avx10-x86_64.S
@@ -0,0 +1,1222 @@
+/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */
+//
+// VAES and VPCLMULQDQ optimized AES-GCM for x86_64
+//
+// Copyright 2024 Google LLC
+//
+// Author: Eric Biggers <ebiggers@google.com>
+//
+//------------------------------------------------------------------------------
+//
+// This file is dual-licensed, meaning that you can use it under your choice of
+// either of the following two licenses:
+//
+// Licensed under the Apache License 2.0 (the "License"). You may obtain a copy
+// of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+//
+// or
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+// 1. Redistributions of source code must retain the above copyright notice,
+// this list of conditions and the following disclaimer.
+//
+// 2. Redistributions in binary form must reproduce the above copyright
+// notice, this list of conditions and the following disclaimer in the
+// documentation and/or other materials provided with the distribution.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+// ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+// LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+// CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+// SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+// CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+// ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+// POSSIBILITY OF SUCH DAMAGE.
+//
+//------------------------------------------------------------------------------
+//
+// This file implements AES-GCM (Galois/Counter Mode) for x86_64 CPUs that
+// support VAES (vector AES), VPCLMULQDQ (vector carryless multiplication), and
+// either AVX512 or AVX10. Some of the functions, notably the encryption and
+// decryption update functions which are the most performance-critical, are
+// provided in two variants generated from a macro: one using 256-bit vectors
+// (suffix: vaes_avx10_256) and one using 512-bit vectors (vaes_avx10_512). The
+// other, "shared" functions (vaes_avx10) use at most 256-bit vectors.
+//
+// The functions that use 512-bit vectors are intended for CPUs that support
+// 512-bit vectors *and* where using them doesn't cause significant
+// downclocking. They require the following CPU features:
+//
+// VAES && VPCLMULQDQ && BMI2 && ((AVX512BW && AVX512VL) || AVX10/512)
+//
+// The other functions require the following CPU features:
+//
+// VAES && VPCLMULQDQ && BMI2 && ((AVX512BW && AVX512VL) || AVX10/256)
+//
+// All functions use the "System V" ABI. The Windows ABI is not supported.
+//
+// Note that we use "avx10" in the names of the functions as a shorthand to
+// really mean "AVX10 or a certain set of AVX512 features". Due to Intel's
+// introduction of AVX512 and then its replacement by AVX10, there doesn't seem
+// to be a simple way to name things that makes sense on all CPUs.
+//
+// Note that the macros that support both 256-bit and 512-bit vectors could
+// fairly easily be changed to support 128-bit too. However, this would *not*
+// be sufficient to allow the code to run on CPUs without AVX512 or AVX10,
+// because the code heavily uses several features of these extensions other than
+// the vector length: the increase in the number of SIMD registers from 16 to
+// 32, masking support, and new instructions such as vpternlogd (which can do a
+// three-argument XOR). These features are very useful for AES-GCM.
+
+#include <linux/linkage.h>
+
+.section .rodata
+.p2align 6
+
+ // A shuffle mask that reflects the bytes of 16-byte blocks
+.Lbswap_mask:
+ .octa 0x000102030405060708090a0b0c0d0e0f
+
+ // This is the GHASH reducing polynomial without its constant term, i.e.
+ // x^128 + x^7 + x^2 + x, represented using the backwards mapping
+ // between bits and polynomial coefficients.
+ //
+ // Alternatively, it can be interpreted as the naturally-ordered
+ // representation of the polynomial x^127 + x^126 + x^121 + 1, i.e. the
+ // "reversed" GHASH reducing polynomial without its x^128 term.
+.Lgfpoly:
+ .octa 0xc2000000000000000000000000000001
+
+ // Same as above, but with the (1 << 64) bit set.
+.Lgfpoly_and_internal_carrybit:
+ .octa 0xc2000000000000010000000000000001
+
+ // The below constants are used for incrementing the counter blocks.
+ // ctr_pattern points to the four 128-bit values [0, 1, 2, 3].
+ // inc_2blocks and inc_4blocks point to the single 128-bit values 2 and
+ // 4. Note that the same '2' is reused in ctr_pattern and inc_2blocks.
+.Lctr_pattern:
+ .octa 0
+ .octa 1
+.Linc_2blocks:
+ .octa 2
+ .octa 3
+.Linc_4blocks:
+ .octa 4
+
+// Number of powers of the hash key stored in the key struct. The powers are
+// stored from highest (H^NUM_H_POWERS) to lowest (H^1).
+#define NUM_H_POWERS 16
+
+// Offset to AES key length (in bytes) in the key struct
+#define OFFSETOF_AESKEYLEN 480
+
+// Offset to start of hash key powers array in the key struct
+#define OFFSETOF_H_POWERS 512
+
+// Offset to end of hash key powers array in the key struct.
+//
+// This is immediately followed by three zeroized padding blocks, which are
+// included so that partial vectors can be handled more easily. E.g. if VL=64
+// and two blocks remain, we load the 4 values [H^2, H^1, 0, 0]. The most
+// padding blocks needed is 3, which occurs if [H^1, 0, 0, 0] is loaded.
+#define OFFSETOFEND_H_POWERS (OFFSETOF_H_POWERS + (NUM_H_POWERS * 16))
+
+.text
+
+// Set the vector length in bytes. This sets the VL variable and defines
+// register aliases V0-V31 that map to the ymm or zmm registers.
+.macro _set_veclen vl
+ .set VL, \vl
+.irp i, 0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
+ 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+.if VL == 32
+ .set V\i, %ymm\i
+.elseif VL == 64
+ .set V\i, %zmm\i
+.else
+ .error "Unsupported vector length"
+.endif
+.endr
+.endm
+
+// The _ghash_mul_step macro does one step of GHASH multiplication of the
+// 128-bit lanes of \a by the corresponding 128-bit lanes of \b and storing the
+// reduced products in \dst. \t0, \t1, and \t2 are temporary registers of the
+// same size as \a and \b. To complete all steps, this must invoked with \i=0
+// through \i=9. The division into steps allows users of this macro to
+// optionally interleave the computation with other instructions. Users of this
+// macro must preserve the parameter registers across steps.
+//
+// The multiplications are done in GHASH's representation of the finite field
+// GF(2^128). Elements of GF(2^128) are represented as binary polynomials
+// (i.e. polynomials whose coefficients are bits) modulo a reducing polynomial
+// G. The GCM specification uses G = x^128 + x^7 + x^2 + x + 1. Addition is
+// just XOR, while multiplication is more complex and has two parts: (a) do
+// carryless multiplication of two 128-bit input polynomials to get a 256-bit
+// intermediate product polynomial, and (b) reduce the intermediate product to
+// 128 bits by adding multiples of G that cancel out terms in it. (Adding
+// multiples of G doesn't change which field element the polynomial represents.)
+//
+// Unfortunately, the GCM specification maps bits to/from polynomial
+// coefficients backwards from the natural order. In each byte it specifies the
+// highest bit to be the lowest order polynomial coefficient, *not* the highest!
+// This makes it nontrivial to work with the GHASH polynomials. We could
+// reflect the bits, but x86 doesn't have an instruction that does that.
+//
+// Instead, we operate on the values without bit-reflecting them. This *mostly*
+// just works, since XOR and carryless multiplication are symmetric with respect
+// to bit order, but it has some consequences. First, due to GHASH's byte
+// order, by skipping bit reflection, *byte* reflection becomes necessary to
+// give the polynomial terms a consistent order. E.g., considering an N-bit
+// value interpreted using the G = x^128 + x^7 + x^2 + x + 1 convention, bits 0
+// through N-1 of the byte-reflected value represent the coefficients of x^(N-1)
+// through x^0, whereas bits 0 through N-1 of the non-byte-reflected value
+// represent x^7...x^0, x^15...x^8, ..., x^(N-1)...x^(N-8) which can't be worked
+// with. Fortunately, x86's vpshufb instruction can do byte reflection.
+//
+// Second, forgoing the bit reflection causes an extra multiple of x (still
+// using the G = x^128 + x^7 + x^2 + x + 1 convention) to be introduced by each
+// multiplication. This is because an M-bit by N-bit carryless multiplication
+// really produces a (M+N-1)-bit product, but in practice it's zero-extended to
+// M+N bits. In the G = x^128 + x^7 + x^2 + x + 1 convention, which maps bits
+// to polynomial coefficients backwards, this zero-extension actually changes
+// the product by introducing an extra factor of x. Therefore, users of this
+// macro must ensure that one of the inputs has an extra factor of x^-1, i.e.
+// the multiplicative inverse of x, to cancel out the extra x.
+//
+// Third, the backwards coefficients convention is just confusing to work with,
+// since it makes "low" and "high" in the polynomial math mean the opposite of
+// their normal meaning in computer programming. This can be solved by using an
+// alternative interpretation: the polynomial coefficients are understood to be
+// in the natural order, and the multiplication is actually \a * \b * x^-128 mod
+// x^128 + x^127 + x^126 + x^121 + 1. This doesn't change the inputs, outputs,
+// or the implementation at all; it just changes the mathematical interpretation
+// of what each instruction is doing. Starting from here, we'll use this
+// alternative interpretation, as it's easier to understand the code that way.
+//
+// Moving onto the implementation, the vpclmulqdq instruction does 64 x 64 =>
+// 128-bit carryless multiplication, so we break the 128 x 128 multiplication
+// into parts as follows (the _L and _H suffixes denote low and high 64 bits):
+//
+// LO = a_L * b_L
+// MI = (a_L * b_H) + (a_H * b_L)
+// HI = a_H * b_H
+//
+// The 256-bit product is x^128*HI + x^64*MI + LO. LO, MI, and HI are 128-bit.
+// Note that MI "overlaps" with LO and HI. We don't consolidate MI into LO and
+// HI right away, since the way the reduction works makes that unnecessary.
+//
+// For the reduction, we cancel out the low 128 bits by adding multiples of G =
+// x^128 + x^127 + x^126 + x^121 + 1. This is done by two iterations, each of
+// which cancels out the next lowest 64 bits. Consider a value x^64*A + B,
+// where A and B are 128-bit. Adding B_L*G to that value gives:
+//
+// x^64*A + B + B_L*G
+// = x^64*A + x^64*B_H + B_L + B_L*(x^128 + x^127 + x^126 + x^121 + 1)
+// = x^64*A + x^64*B_H + B_L + x^128*B_L + x^64*B_L*(x^63 + x^62 + x^57) + B_L
+// = x^64*A + x^64*B_H + x^128*B_L + x^64*B_L*(x^63 + x^62 + x^57) + B_L + B_L
+// = x^64*(A + B_H + x^64*B_L + B_L*(x^63 + x^62 + x^57))
+//
+// So: if we sum A, B with its halves swapped, and the low half of B times x^63
+// + x^62 + x^57, we get a 128-bit value C where x^64*C is congruent to the
+// original value x^64*A + B. I.e., the low 64 bits got canceled out.
+//
+// We just need to apply this twice: first to fold LO into MI, and second to
+// fold the updated MI into HI.
+//
+// The needed three-argument XORs are done using the vpternlogd instruction with
+// immediate 0x96, since this is faster than two vpxord instructions.
+//
+// A potential optimization, assuming that b is fixed per-key (if a is fixed
+// per-key it would work the other way around), is to use one iteration of the
+// reduction described above to precompute a value c such that x^64*c = b mod G,
+// and then multiply a_L by c (and implicitly by x^64) instead of by b:
+//
+// MI = (a_L * c_L) + (a_H * b_L)
+// HI = (a_L * c_H) + (a_H * b_H)
+//
+// This would eliminate the LO part of the intermediate product, which would
+// eliminate the need to fold LO into MI. This would save two instructions,
+// including a vpclmulqdq. However, we currently don't use this optimization
+// because it would require twice as many per-key precomputed values.
+//
+// Using Karatsuba multiplication instead of "schoolbook" multiplication
+// similarly would save a vpclmulqdq but does not seem to be worth it.
+.macro _ghash_mul_step i, a, b, dst, gfpoly, t0, t1, t2
+.if \i == 0
+ vpclmulqdq $0x00, \a, \b, \t0 // LO = a_L * b_L
+ vpclmulqdq $0x01, \a, \b, \t1 // MI_0 = a_L * b_H
+.elseif \i == 1
+ vpclmulqdq $0x10, \a, \b, \t2 // MI_1 = a_H * b_L
+.elseif \i == 2
+ vpxord \t2, \t1, \t1 // MI = MI_0 + MI_1
+.elseif \i == 3
+ vpclmulqdq $0x01, \t0, \gfpoly, \t2 // LO_L*(x^63 + x^62 + x^57)
+.elseif \i == 4
+ vpshufd $0x4e, \t0, \t0 // Swap halves of LO
+.elseif \i == 5
+ vpternlogd $0x96, \t2, \t0, \t1 // Fold LO into MI
+.elseif \i == 6
+ vpclmulqdq $0x11, \a, \b, \dst // HI = a_H * b_H
+.elseif \i == 7
+ vpclmulqdq $0x01, \t1, \gfpoly, \t0 // MI_L*(x^63 + x^62 + x^57)
+.elseif \i == 8
+ vpshufd $0x4e, \t1, \t1 // Swap halves of MI
+.elseif \i == 9
+ vpternlogd $0x96, \t0, \t1, \dst // Fold MI into HI
+.endif
+.endm
+
+// GHASH-multiply the 128-bit lanes of \a by the 128-bit lanes of \b and store
+// the reduced products in \dst. See _ghash_mul_step for full explanation.
+.macro _ghash_mul a, b, dst, gfpoly, t0, t1, t2
+.irp i, 0,1,2,3,4,5,6,7,8,9
+ _ghash_mul_step \i, \a, \b, \dst, \gfpoly, \t0, \t1, \t2
+.endr
+.endm
+
+// GHASH-multiply the 128-bit lanes of \a by the 128-bit lanes of \b and add the
+// *unreduced* products to \lo, \mi, and \hi.
+.macro _ghash_mul_noreduce a, b, lo, mi, hi, t0, t1, t2, t3
+ vpclmulqdq $0x00, \a, \b, \t0 // a_L * b_L
+ vpclmulqdq $0x01, \a, \b, \t1 // a_L * b_H
+ vpclmulqdq $0x10, \a, \b, \t2 // a_H * b_L
+ vpclmulqdq $0x11, \a, \b, \t3 // a_H * b_H
+ vpxord \t0, \lo, \lo
+ vpternlogd $0x96, \t2, \t1, \mi
+ vpxord \t3, \hi, \hi
+.endm
+
+// Reduce the unreduced products from \lo, \mi, and \hi and store the 128-bit
+// reduced products in \hi. See _ghash_mul_step for explanation of reduction.
+.macro _ghash_reduce lo, mi, hi, gfpoly, t0
+ vpclmulqdq $0x01, \lo, \gfpoly, \t0
+ vpshufd $0x4e, \lo, \lo
+ vpternlogd $0x96, \t0, \lo, \mi
+ vpclmulqdq $0x01, \mi, \gfpoly, \t0
+ vpshufd $0x4e, \mi, \mi
+ vpternlogd $0x96, \t0, \mi, \hi
+.endm
+
+// void aes_gcm_precompute_##suffix(struct aes_gcm_key_avx10 *key);
+//
+// Given the expanded AES key |key->aes_key|, this function derives the GHASH
+// subkey and initializes |key->ghash_key_powers| with powers of it.
+//
+// The number of key powers initialized is NUM_H_POWERS, and they are stored in
+// the order H^NUM_H_POWERS to H^1. The zeroized padding blocks after the key
+// powers themselves are also initialized.
+//
+// This macro supports both VL=32 and VL=64. _set_veclen must have been invoked
+// with the desired length. In the VL=32 case, the function computes twice as
+// many key powers than are actually used by the VL=32 GCM update functions.
+// This is done to keep the key format the same regardless of vector length.
+.macro _aes_gcm_precompute
+
+ // Function arguments
+ .set KEY, %rdi
+
+ // Additional local variables. V0-V2 and %rax are used as temporaries.
+ .set POWERS_PTR, %rsi
+ .set RNDKEYLAST_PTR, %rdx
+ .set H_CUR, V3
+ .set H_CUR_YMM, %ymm3
+ .set H_CUR_XMM, %xmm3
+ .set H_INC, V4
+ .set H_INC_YMM, %ymm4
+ .set H_INC_XMM, %xmm4
+ .set GFPOLY, V5
+ .set GFPOLY_YMM, %ymm5
+ .set GFPOLY_XMM, %xmm5
+
+ // Get pointer to lowest set of key powers (located at end of array).
+ lea OFFSETOFEND_H_POWERS-VL(KEY), POWERS_PTR
+
+ // Encrypt an all-zeroes block to get the raw hash subkey.
+ movl OFFSETOF_AESKEYLEN(KEY), %eax
+ lea 6*16(KEY,%rax,4), RNDKEYLAST_PTR
+ vmovdqu (KEY), %xmm0 // Zero-th round key XOR all-zeroes block
+ add $16, KEY
+1:
+ vaesenc (KEY), %xmm0, %xmm0
+ add $16, KEY
+ cmp KEY, RNDKEYLAST_PTR
+ jne 1b
+ vaesenclast (RNDKEYLAST_PTR), %xmm0, %xmm0
+
+ // Reflect the bytes of the raw hash subkey.
+ vpshufb .Lbswap_mask(%rip), %xmm0, H_CUR_XMM
+
+ // Zeroize the padding blocks.
+ vpxor %xmm0, %xmm0, %xmm0
+ vmovdqu %ymm0, VL(POWERS_PTR)
+ vmovdqu %xmm0, VL+2*16(POWERS_PTR)
+
+ // Finish preprocessing the first key power, H^1. Since this GHASH
+ // implementation operates directly on values with the backwards bit
+ // order specified by the GCM standard, it's necessary to preprocess the
+ // raw key as follows. First, reflect its bytes. Second, multiply it
+ // by x^-1 mod x^128 + x^7 + x^2 + x + 1 (if using the backwards
+ // interpretation of polynomial coefficients), which can also be
+ // interpreted as multiplication by x mod x^128 + x^127 + x^126 + x^121
+ // + 1 using the alternative, natural interpretation of polynomial
+ // coefficients. For details, see the comment above _ghash_mul_step.
+ //
+ // Either way, for the multiplication the concrete operation performed
+ // is a left shift of the 128-bit value by 1 bit, then an XOR with (0xc2
+ // << 120) | 1 if a 1 bit was carried out. However, there's no 128-bit
+ // wide shift instruction, so instead double each of the two 64-bit
+ // halves and incorporate the internal carry bit into the value XOR'd.
+ vpshufd $0xd3, H_CUR_XMM, %xmm0
+ vpsrad $31, %xmm0, %xmm0
+ vpaddq H_CUR_XMM, H_CUR_XMM, H_CUR_XMM
+ vpand .Lgfpoly_and_internal_carrybit(%rip), %xmm0, %xmm0
+ vpxor %xmm0, H_CUR_XMM, H_CUR_XMM
+
+ // Load the gfpoly constant.
+ vbroadcasti32x4 .Lgfpoly(%rip), GFPOLY
+
+ // Square H^1 to get H^2.
+ //
+ // Note that as with H^1, all higher key powers also need an extra
+ // factor of x^-1 (or x using the natural interpretation). Nothing
+ // special needs to be done to make this happen, though: H^1 * H^1 would
+ // end up with two factors of x^-1, but the multiplication consumes one.
+ // So the product H^2 ends up with the desired one factor of x^-1.
+ _ghash_mul H_CUR_XMM, H_CUR_XMM, H_INC_XMM, GFPOLY_XMM, \
+ %xmm0, %xmm1, %xmm2
+
+ // Create H_CUR_YMM = [H^2, H^1] and H_INC_YMM = [H^2, H^2].
+ vinserti128 $1, H_CUR_XMM, H_INC_YMM, H_CUR_YMM
+ vinserti128 $1, H_INC_XMM, H_INC_YMM, H_INC_YMM
+
+.if VL == 64
+ // Create H_CUR = [H^4, H^3, H^2, H^1] and H_INC = [H^4, H^4, H^4, H^4].
+ _ghash_mul H_INC_YMM, H_CUR_YMM, H_INC_YMM, GFPOLY_YMM, \
+ %ymm0, %ymm1, %ymm2
+ vinserti64x4 $1, H_CUR_YMM, H_INC, H_CUR
+ vshufi64x2 $0, H_INC, H_INC, H_INC
+.endif
+
+ // Store the lowest set of key powers.
+ vmovdqu8 H_CUR, (POWERS_PTR)
+
+ // Compute and store the remaining key powers. With VL=32, repeatedly
+ // multiply [H^(i+1), H^i] by [H^2, H^2] to get [H^(i+3), H^(i+2)].
+ // With VL=64, repeatedly multiply [H^(i+3), H^(i+2), H^(i+1), H^i] by
+ // [H^4, H^4, H^4, H^4] to get [H^(i+7), H^(i+6), H^(i+5), H^(i+4)].
+ mov $(NUM_H_POWERS*16/VL) - 1, %eax
+.Lprecompute_next\@:
+ sub $VL, POWERS_PTR
+ _ghash_mul H_INC, H_CUR, H_CUR, GFPOLY, V0, V1, V2
+ vmovdqu8 H_CUR, (POWERS_PTR)
+ dec %eax
+ jnz .Lprecompute_next\@
+
+ vzeroupper // This is needed after using ymm or zmm registers.
+ RET
+.endm
+
+// XOR together the 128-bit lanes of \src (whose low lane is \src_xmm) and store
+// the result in \dst_xmm. This implicitly zeroizes the other lanes of dst.
+.macro _horizontal_xor src, src_xmm, dst_xmm, t0_xmm, t1_xmm, t2_xmm
+ vextracti32x4 $1, \src, \t0_xmm
+.if VL == 32
+ vpxord \t0_xmm, \src_xmm, \dst_xmm
+.elseif VL == 64
+ vextracti32x4 $2, \src, \t1_xmm
+ vextracti32x4 $3, \src, \t2_xmm
+ vpxord \t0_xmm, \src_xmm, \dst_xmm
+ vpternlogd $0x96, \t1_xmm, \t2_xmm, \dst_xmm
+.else
+ .error "Unsupported vector length"
+.endif
+.endm
+
+// Do one step of the GHASH update of the data blocks given in the vector
+// registers GHASHDATA[0-3]. \i specifies the step to do, 0 through 9. The
+// division into steps allows users of this macro to optionally interleave the
+// computation with other instructions. This macro uses the vector register
+// GHASH_ACC as input/output; GHASHDATA[0-3] as inputs that are clobbered;
+// H_POW[4-1], GFPOLY, and BSWAP_MASK as inputs that aren't clobbered; and
+// GHASHTMP[0-2] as temporaries. This macro handles the byte-reflection of the
+// data blocks. The parameter registers must be preserved across steps.
+//
+// The GHASH update does: GHASH_ACC = H_POW4*(GHASHDATA0 + GHASH_ACC) +
+// H_POW3*GHASHDATA1 + H_POW2*GHASHDATA2 + H_POW1*GHASHDATA3, where the
+// operations are vectorized operations on vectors of 16-byte blocks. E.g.,
+// with VL=32 there are 2 blocks per vector and the vectorized terms correspond
+// to the following non-vectorized terms:
+//
+// H_POW4*(GHASHDATA0 + GHASH_ACC) => H^8*(blk0 + GHASH_ACC_XMM) and H^7*(blk1 + 0)
+// H_POW3*GHASHDATA1 => H^6*blk2 and H^5*blk3
+// H_POW2*GHASHDATA2 => H^4*blk4 and H^3*blk5
+// H_POW1*GHASHDATA3 => H^2*blk6 and H^1*blk7
+//
+// With VL=64, we use 4 blocks/vector, H^16 through H^1, and blk0 through blk15.
+//
+// More concretely, this code does:
+// - Do vectorized "schoolbook" multiplications to compute the intermediate
+// 256-bit product of each block and its corresponding hash key power.
+// There are 4*VL/16 of these intermediate products.
+// - Sum (XOR) the intermediate 256-bit products across vectors. This leaves
+// VL/16 256-bit intermediate values.
+// - Do a vectorized reduction of these 256-bit intermediate values to
+// 128-bits each. This leaves VL/16 128-bit intermediate values.
+// - Sum (XOR) these values and store the 128-bit result in GHASH_ACC_XMM.
+//
+// See _ghash_mul_step for the full explanation of the operations performed for
+// each individual finite field multiplication and reduction.
+.macro _ghash_step_4x i
+.if \i == 0
+ vpshufb BSWAP_MASK, GHASHDATA0, GHASHDATA0
+ vpxord GHASH_ACC, GHASHDATA0, GHASHDATA0
+ vpshufb BSWAP_MASK, GHASHDATA1, GHASHDATA1
+ vpshufb BSWAP_MASK, GHASHDATA2, GHASHDATA2
+.elseif \i == 1
+ vpshufb BSWAP_MASK, GHASHDATA3, GHASHDATA3
+ vpclmulqdq $0x00, H_POW4, GHASHDATA0, GHASH_ACC // LO_0
+ vpclmulqdq $0x00, H_POW3, GHASHDATA1, GHASHTMP0 // LO_1
+ vpclmulqdq $0x00, H_POW2, GHASHDATA2, GHASHTMP1 // LO_2
+.elseif \i == 2
+ vpxord GHASHTMP0, GHASH_ACC, GHASH_ACC // sum(LO_{1,0})
+ vpclmulqdq $0x00, H_POW1, GHASHDATA3, GHASHTMP2 // LO_3
+ vpternlogd $0x96, GHASHTMP2, GHASHTMP1, GHASH_ACC // LO = sum(LO_{3,2,1,0})
+ vpclmulqdq $0x01, H_POW4, GHASHDATA0, GHASHTMP0 // MI_0
+.elseif \i == 3
+ vpclmulqdq $0x01, H_POW3, GHASHDATA1, GHASHTMP1 // MI_1
+ vpclmulqdq $0x01, H_POW2, GHASHDATA2, GHASHTMP2 // MI_2
+ vpternlogd $0x96, GHASHTMP2, GHASHTMP1, GHASHTMP0 // sum(MI_{2,1,0})
+ vpclmulqdq $0x01, H_POW1, GHASHDATA3, GHASHTMP1 // MI_3
+.elseif \i == 4
+ vpclmulqdq $0x10, H_POW4, GHASHDATA0, GHASHTMP2 // MI_4
+ vpternlogd $0x96, GHASHTMP2, GHASHTMP1, GHASHTMP0 // sum(MI_{4,3,2,1,0})
+ vpclmulqdq $0x10, H_POW3, GHASHDATA1, GHASHTMP1 // MI_5
+ vpclmulqdq $0x10, H_POW2, GHASHDATA2, GHASHTMP2 // MI_6
+.elseif \i == 5
+ vpternlogd $0x96, GHASHTMP2, GHASHTMP1, GHASHTMP0 // sum(MI_{6,5,4,3,2,1,0})
+ vpclmulqdq $0x01, GHASH_ACC, GFPOLY, GHASHTMP2 // LO_L*(x^63 + x^62 + x^57)
+ vpclmulqdq $0x10, H_POW1, GHASHDATA3, GHASHTMP1 // MI_7
+ vpxord GHASHTMP1, GHASHTMP0, GHASHTMP0 // MI = sum(MI_{7,6,5,4,3,2,1,0})
+.elseif \i == 6
+ vpshufd $0x4e, GHASH_ACC, GHASH_ACC // Swap halves of LO
+ vpclmulqdq $0x11, H_POW4, GHASHDATA0, GHASHDATA0 // HI_0
+ vpclmulqdq $0x11, H_POW3, GHASHDATA1, GHASHDATA1 // HI_1
+ vpclmulqdq $0x11, H_POW2, GHASHDATA2, GHASHDATA2 // HI_2
+.elseif \i == 7
+ vpternlogd $0x96, GHASHTMP2, GHASH_ACC, GHASHTMP0 // Fold LO into MI
+ vpclmulqdq $0x11, H_POW1, GHASHDATA3, GHASHDATA3 // HI_3
+ vpternlogd $0x96, GHASHDATA2, GHASHDATA1, GHASHDATA0 // sum(HI_{2,1,0})
+ vpclmulqdq $0x01, GHASHTMP0, GFPOLY, GHASHTMP1 // MI_L*(x^63 + x^62 + x^57)
+.elseif \i == 8
+ vpxord GHASHDATA3, GHASHDATA0, GHASH_ACC // HI = sum(HI_{3,2,1,0})
+ vpshufd $0x4e, GHASHTMP0, GHASHTMP0 // Swap halves of MI
+ vpternlogd $0x96, GHASHTMP1, GHASHTMP0, GHASH_ACC // Fold MI into HI
+.elseif \i == 9
+ _horizontal_xor GHASH_ACC, GHASH_ACC_XMM, GHASH_ACC_XMM, \
+ GHASHDATA0_XMM, GHASHDATA1_XMM, GHASHDATA2_XMM
+.endif
+.endm
+
+// Do one non-last round of AES encryption on the counter blocks in V0-V3 using
+// the round key that has been broadcast to all 128-bit lanes of \round_key.
+.macro _vaesenc_4x round_key
+ vaesenc \round_key, V0, V0
+ vaesenc \round_key, V1, V1
+ vaesenc \round_key, V2, V2
+ vaesenc \round_key, V3, V3
+.endm
+
+// Start the AES encryption of four vectors of counter blocks.
+.macro _ctr_begin_4x
+
+ // Increment LE_CTR four times to generate four vectors of little-endian
+ // counter blocks, swap each to big-endian, and store them in V0-V3.
+ vpshufb BSWAP_MASK, LE_CTR, V0
+ vpaddd LE_CTR_INC, LE_CTR, LE_CTR
+ vpshufb BSWAP_MASK, LE_CTR, V1
+ vpaddd LE_CTR_INC, LE_CTR, LE_CTR
+ vpshufb BSWAP_MASK, LE_CTR, V2
+ vpaddd LE_CTR_INC, LE_CTR, LE_CTR
+ vpshufb BSWAP_MASK, LE_CTR, V3
+ vpaddd LE_CTR_INC, LE_CTR, LE_CTR
+
+ // AES "round zero": XOR in the zero-th round key.
+ vpxord RNDKEY0, V0, V0
+ vpxord RNDKEY0, V1, V1
+ vpxord RNDKEY0, V2, V2
+ vpxord RNDKEY0, V3, V3
+.endm
+
+// void aes_gcm_{enc,dec}_update_##suffix(const struct aes_gcm_key_avx10 *key,
+// const u32 le_ctr[4], u8 ghash_acc[16],
+// const u8 *src, u8 *dst, int datalen);
+//
+// This macro generates a GCM encryption or decryption update function with the
+// above prototype (with \enc selecting which one). This macro supports both
+// VL=32 and VL=64. _set_veclen must have been invoked with the desired length.
+//
+// This function computes the next portion of the CTR keystream, XOR's it with
+// |datalen| bytes from |src|, and writes the resulting encrypted or decrypted
+// data to |dst|. It also updates the GHASH accumulator |ghash_acc| using the
+// next |datalen| ciphertext bytes.
+//
+// |datalen| must be a multiple of 16, except on the last call where it can be
+// any length. The caller must do any buffering needed to ensure this. Both
+// in-place and out-of-place en/decryption are supported.
+//
+// |le_ctr| must give the current counter in little-endian format. For a new
+// message, the low word of the counter must be 2. This function loads the
+// counter from |le_ctr| and increments the loaded counter as needed, but it
+// does *not* store the updated counter back to |le_ctr|. The caller must
+// update |le_ctr| if any more data segments follow. Internally, only the low
+// 32-bit word of the counter is incremented, following the GCM standard.
+.macro _aes_gcm_update enc
+
+ // Function arguments
+ .set KEY, %rdi
+ .set LE_CTR_PTR, %rsi
+ .set GHASH_ACC_PTR, %rdx
+ .set SRC, %rcx
+ .set DST, %r8
+ .set DATALEN, %r9d
+ .set DATALEN64, %r9 // Zero-extend DATALEN before using!
+
+ // Additional local variables
+
+ // %rax and %k1 are used as temporary registers. LE_CTR_PTR is also
+ // available as a temporary register after the counter is loaded.
+
+ // AES key length in bytes
+ .set AESKEYLEN, %r10d
+ .set AESKEYLEN64, %r10
+
+ // Pointer to the last AES round key for the chosen AES variant
+ .set RNDKEYLAST_PTR, %r11
+
+ // In the main loop, V0-V3 are used as AES input and output. Elsewhere
+ // they are used as temporary registers.
+
+ // GHASHDATA[0-3] hold the ciphertext blocks and GHASH input data.
+ .set GHASHDATA0, V4
+ .set GHASHDATA0_XMM, %xmm4
+ .set GHASHDATA1, V5
+ .set GHASHDATA1_XMM, %xmm5
+ .set GHASHDATA2, V6
+ .set GHASHDATA2_XMM, %xmm6
+ .set GHASHDATA3, V7
+
+ // BSWAP_MASK is the shuffle mask for byte-reflecting 128-bit values
+ // using vpshufb, copied to all 128-bit lanes.
+ .set BSWAP_MASK, V8
+
+ // RNDKEY temporarily holds the next AES round key.
+ .set RNDKEY, V9
+
+ // GHASH_ACC is the accumulator variable for GHASH. When fully reduced,
+ // only the lowest 128-bit lane can be nonzero. When not fully reduced,
+ // more than one lane may be used, and they need to be XOR'd together.
+ .set GHASH_ACC, V10
+ .set GHASH_ACC_XMM, %xmm10
+
+ // LE_CTR_INC is the vector of 32-bit words that need to be added to a
+ // vector of little-endian counter blocks to advance it forwards.
+ .set LE_CTR_INC, V11
+
+ // LE_CTR contains the next set of little-endian counter blocks.
+ .set LE_CTR, V12
+
+ // RNDKEY0, RNDKEYLAST, and RNDKEY_M[9-5] contain cached AES round keys,
+ // copied to all 128-bit lanes. RNDKEY0 is the zero-th round key,
+ // RNDKEYLAST the last, and RNDKEY_M\i the one \i-th from the last.
+ .set RNDKEY0, V13
+ .set RNDKEYLAST, V14
+ .set RNDKEY_M9, V15
+ .set RNDKEY_M8, V16
+ .set RNDKEY_M7, V17
+ .set RNDKEY_M6, V18
+ .set RNDKEY_M5, V19
+
+ // RNDKEYLAST[0-3] temporarily store the last AES round key XOR'd with
+ // the corresponding block of source data. This is useful because
+ // vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a), and key ^ b can
+ // be computed in parallel with the AES rounds.
+ .set RNDKEYLAST0, V20
+ .set RNDKEYLAST1, V21
+ .set RNDKEYLAST2, V22
+ .set RNDKEYLAST3, V23
+
+ // GHASHTMP[0-2] are temporary variables used by _ghash_step_4x. These
+ // cannot coincide with anything used for AES encryption, since for
+ // performance reasons GHASH and AES encryption are interleaved.
+ .set GHASHTMP0, V24
+ .set GHASHTMP1, V25
+ .set GHASHTMP2, V26
+
+ // H_POW[4-1] contain the powers of the hash key H^(4*VL/16)...H^1. The
+ // descending numbering reflects the order of the key powers.
+ .set H_POW4, V27
+ .set H_POW3, V28
+ .set H_POW2, V29
+ .set H_POW1, V30
+
+ // GFPOLY contains the .Lgfpoly constant, copied to all 128-bit lanes.
+ .set GFPOLY, V31
+
+ // Load some constants.
+ vbroadcasti32x4 .Lbswap_mask(%rip), BSWAP_MASK
+ vbroadcasti32x4 .Lgfpoly(%rip), GFPOLY
+
+ // Load the GHASH accumulator and the starting counter.
+ vmovdqu (GHASH_ACC_PTR), GHASH_ACC_XMM
+ vbroadcasti32x4 (LE_CTR_PTR), LE_CTR
+
+ // Load the AES key length in bytes.
+ movl OFFSETOF_AESKEYLEN(KEY), AESKEYLEN
+
+ // Make RNDKEYLAST_PTR point to the last AES round key. This is the
+ // round key with index 10, 12, or 14 for AES-128, AES-192, or AES-256
+ // respectively. Then load the zero-th and last round keys.
+ lea 6*16(KEY,AESKEYLEN64,4), RNDKEYLAST_PTR
+ vbroadcasti32x4 (KEY), RNDKEY0
+ vbroadcasti32x4 (RNDKEYLAST_PTR), RNDKEYLAST
+
+ // Finish initializing LE_CTR by adding [0, 1, ...] to its low words.
+ vpaddd .Lctr_pattern(%rip), LE_CTR, LE_CTR
+
+ // Initialize LE_CTR_INC to contain VL/16 in all 128-bit lanes.
+.if VL == 32
+ vbroadcasti32x4 .Linc_2blocks(%rip), LE_CTR_INC
+.elseif VL == 64
+ vbroadcasti32x4 .Linc_4blocks(%rip), LE_CTR_INC
+.else
+ .error "Unsupported vector length"
+.endif
+
+ // If there are at least 4*VL bytes of data, then continue into the loop
+ // that processes 4*VL bytes of data at a time. Otherwise skip it.
+ //
+ // Pre-subtracting 4*VL from DATALEN saves an instruction from the main
+ // loop and also ensures that at least one write always occurs to
+ // DATALEN, zero-extending it and allowing DATALEN64 to be used later.
+ sub $4*VL, DATALEN
+ jl .Lcrypt_loop_4x_done\@
+
+ // Load powers of the hash key.
+ vmovdqu8 OFFSETOFEND_H_POWERS-4*VL(KEY), H_POW4
+ vmovdqu8 OFFSETOFEND_H_POWERS-3*VL(KEY), H_POW3
+ vmovdqu8 OFFSETOFEND_H_POWERS-2*VL(KEY), H_POW2
+ vmovdqu8 OFFSETOFEND_H_POWERS-1*VL(KEY), H_POW1
+
+ // Main loop: en/decrypt and hash 4 vectors at a time.
+ //
+ // When possible, interleave the AES encryption of the counter blocks
+ // with the GHASH update of the ciphertext blocks. This improves
+ // performance on many CPUs because the execution ports used by the VAES
+ // instructions often differ from those used by vpclmulqdq and other
+ // instructions used in GHASH. For example, many Intel CPUs dispatch
+ // vaesenc to ports 0 and 1 and vpclmulqdq to port 5.
+ //
+ // The interleaving is easiest to do during decryption, since during
+ // decryption the ciphertext blocks are immediately available. For
+ // encryption, instead encrypt the first set of blocks, then hash those
+ // blocks while encrypting the next set of blocks, repeat that as
+ // needed, and finally hash the last set of blocks.
+
+.if \enc
+ // Encrypt the first 4 vectors of plaintext blocks. Leave the resulting
+ // ciphertext in GHASHDATA[0-3] for GHASH.
+ _ctr_begin_4x
+ lea 16(KEY), %rax
+1:
+ vbroadcasti32x4 (%rax), RNDKEY
+ _vaesenc_4x RNDKEY
+ add $16, %rax
+ cmp %rax, RNDKEYLAST_PTR
+ jne 1b
+ vpxord 0*VL(SRC), RNDKEYLAST, RNDKEYLAST0
+ vpxord 1*VL(SRC), RNDKEYLAST, RNDKEYLAST1
+ vpxord 2*VL(SRC), RNDKEYLAST, RNDKEYLAST2
+ vpxord 3*VL(SRC), RNDKEYLAST, RNDKEYLAST3
+ vaesenclast RNDKEYLAST0, V0, GHASHDATA0
+ vaesenclast RNDKEYLAST1, V1, GHASHDATA1
+ vaesenclast RNDKEYLAST2, V2, GHASHDATA2
+ vaesenclast RNDKEYLAST3, V3, GHASHDATA3
+ vmovdqu8 GHASHDATA0, 0*VL(DST)
+ vmovdqu8 GHASHDATA1, 1*VL(DST)
+ vmovdqu8 GHASHDATA2, 2*VL(DST)
+ vmovdqu8 GHASHDATA3, 3*VL(DST)
+ add $4*VL, SRC
+ add $4*VL, DST
+ sub $4*VL, DATALEN
+ jl .Lghash_last_ciphertext_4x\@
+.endif
+
+ // Cache as many additional AES round keys as possible.
+.irp i, 9,8,7,6,5
+ vbroadcasti32x4 -\i*16(RNDKEYLAST_PTR), RNDKEY_M\i
+.endr
+
+.Lcrypt_loop_4x\@:
+
+ // If decrypting, load more ciphertext blocks into GHASHDATA[0-3]. If
+ // encrypting, GHASHDATA[0-3] already contain the previous ciphertext.
+.if !\enc
+ vmovdqu8 0*VL(SRC), GHASHDATA0
+ vmovdqu8 1*VL(SRC), GHASHDATA1
+ vmovdqu8 2*VL(SRC), GHASHDATA2
+ vmovdqu8 3*VL(SRC), GHASHDATA3
+.endif
+
+ // Start the AES encryption of the counter blocks.
+ _ctr_begin_4x
+ cmp $24, AESKEYLEN
+ jl 128f // AES-128?
+ je 192f // AES-192?
+ // AES-256
+ vbroadcasti32x4 -13*16(RNDKEYLAST_PTR), RNDKEY
+ _vaesenc_4x RNDKEY
+ vbroadcasti32x4 -12*16(RNDKEYLAST_PTR), RNDKEY
+ _vaesenc_4x RNDKEY
+192:
+ vbroadcasti32x4 -11*16(RNDKEYLAST_PTR), RNDKEY
+ _vaesenc_4x RNDKEY
+ vbroadcasti32x4 -10*16(RNDKEYLAST_PTR), RNDKEY
+ _vaesenc_4x RNDKEY
+128:
+
+ // XOR the source data with the last round key, saving the result in
+ // RNDKEYLAST[0-3]. This reduces latency by taking advantage of the
+ // property vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a).
+.if \enc
+ vpxord 0*VL(SRC), RNDKEYLAST, RNDKEYLAST0
+ vpxord 1*VL(SRC), RNDKEYLAST, RNDKEYLAST1
+ vpxord 2*VL(SRC), RNDKEYLAST, RNDKEYLAST2
+ vpxord 3*VL(SRC), RNDKEYLAST, RNDKEYLAST3
+.else
+ vpxord GHASHDATA0, RNDKEYLAST, RNDKEYLAST0
+ vpxord GHASHDATA1, RNDKEYLAST, RNDKEYLAST1
+ vpxord GHASHDATA2, RNDKEYLAST, RNDKEYLAST2
+ vpxord GHASHDATA3, RNDKEYLAST, RNDKEYLAST3
+.endif
+
+ // Finish the AES encryption of the counter blocks in V0-V3, interleaved
+ // with the GHASH update of the ciphertext blocks in GHASHDATA[0-3].
+.irp i, 9,8,7,6,5
+ _vaesenc_4x RNDKEY_M\i
+ _ghash_step_4x (9 - \i)
+.endr
+.irp i, 4,3,2,1
+ vbroadcasti32x4 -\i*16(RNDKEYLAST_PTR), RNDKEY
+ _vaesenc_4x RNDKEY
+ _ghash_step_4x (9 - \i)
+.endr
+ _ghash_step_4x 9
+
+ // Do the last AES round. This handles the XOR with the source data
+ // too, as per the optimization described above.
+ vaesenclast RNDKEYLAST0, V0, GHASHDATA0
+ vaesenclast RNDKEYLAST1, V1, GHASHDATA1
+ vaesenclast RNDKEYLAST2, V2, GHASHDATA2
+ vaesenclast RNDKEYLAST3, V3, GHASHDATA3
+
+ // Store the en/decrypted data to DST.
+ vmovdqu8 GHASHDATA0, 0*VL(DST)
+ vmovdqu8 GHASHDATA1, 1*VL(DST)
+ vmovdqu8 GHASHDATA2, 2*VL(DST)
+ vmovdqu8 GHASHDATA3, 3*VL(DST)
+
+ add $4*VL, SRC
+ add $4*VL, DST
+ sub $4*VL, DATALEN
+ jge .Lcrypt_loop_4x\@
+
+.if \enc
+.Lghash_last_ciphertext_4x\@:
+ // Update GHASH with the last set of ciphertext blocks.
+.irp i, 0,1,2,3,4,5,6,7,8,9
+ _ghash_step_4x \i
+.endr
+.endif
+
+.Lcrypt_loop_4x_done\@:
+
+ // Undo the extra subtraction by 4*VL and check whether data remains.
+ add $4*VL, DATALEN
+ jz .Ldone\@
+
+ // The data length isn't a multiple of 4*VL. Process the remaining data
+ // of length 1 <= DATALEN < 4*VL, up to one vector (VL bytes) at a time.
+ // Going one vector at a time may seem inefficient compared to having
+ // separate code paths for each possible number of vectors remaining.
+ // However, using a loop keeps the code size down, and it performs
+ // surprising well; modern CPUs will start executing the next iteration
+ // before the previous one finishes and also predict the number of loop
+ // iterations. For a similar reason, we roll up the AES rounds.
+ //
+ // On the last iteration, the remaining length may be less than VL.
+ // Handle this using masking.
+ //
+ // Since there are enough key powers available for all remaining data,
+ // there is no need to do a GHASH reduction after each iteration.
+ // Instead, multiply each remaining block by its own key power, and only
+ // do a GHASH reduction at the very end.
+
+ // Make POWERS_PTR point to the key powers [H^N, H^(N-1), ...] where N
+ // is the number of blocks that remain.
+ .set POWERS_PTR, LE_CTR_PTR // LE_CTR_PTR is free to be reused.
+ mov DATALEN, %eax
+ neg %rax
+ and $~15, %rax // -round_up(DATALEN, 16)
+ lea OFFSETOFEND_H_POWERS(KEY,%rax), POWERS_PTR
+
+ // Start collecting the unreduced GHASH intermediate value LO, MI, HI.
+ .set LO, GHASHDATA0
+ .set LO_XMM, GHASHDATA0_XMM
+ .set MI, GHASHDATA1
+ .set MI_XMM, GHASHDATA1_XMM
+ .set HI, GHASHDATA2
+ .set HI_XMM, GHASHDATA2_XMM
+ vpxor LO_XMM, LO_XMM, LO_XMM
+ vpxor MI_XMM, MI_XMM, MI_XMM
+ vpxor HI_XMM, HI_XMM, HI_XMM
+
+.Lcrypt_loop_1x\@:
+
+ // Select the appropriate mask for this iteration: all 1's if
+ // DATALEN >= VL, otherwise DATALEN 1's. Do this branchlessly using the
+ // bzhi instruction from BMI2. (This relies on DATALEN <= 255.)
+.if VL < 64
+ mov $-1, %eax
+ bzhi DATALEN, %eax, %eax
+ kmovd %eax, %k1
+.else
+ mov $-1, %rax
+ bzhi DATALEN64, %rax, %rax
+ kmovq %rax, %k1
+.endif
+
+ // Encrypt a vector of counter blocks. This does not need to be masked.
+ vpshufb BSWAP_MASK, LE_CTR, V0
+ vpaddd LE_CTR_INC, LE_CTR, LE_CTR
+ vpxord RNDKEY0, V0, V0
+ lea 16(KEY), %rax
+1:
+ vbroadcasti32x4 (%rax), RNDKEY
+ vaesenc RNDKEY, V0, V0
+ add $16, %rax
+ cmp %rax, RNDKEYLAST_PTR
+ jne 1b
+ vaesenclast RNDKEYLAST, V0, V0
+
+ // XOR the data with the appropriate number of keystream bytes.
+ vmovdqu8 (SRC), V1{%k1}{z}
+ vpxord V1, V0, V0
+ vmovdqu8 V0, (DST){%k1}
+
+ // Update GHASH with the ciphertext block(s), without reducing.
+ //
+ // In the case of DATALEN < VL, the ciphertext is zero-padded to VL.
+ // (If decrypting, it's done by the above masked load. If encrypting,
+ // it's done by the below masked register-to-register move.) Note that
+ // if DATALEN <= VL - 16, there will be additional padding beyond the
+ // padding of the last block specified by GHASH itself; i.e., there may
+ // be whole block(s) that get processed by the GHASH multiplication and
+ // reduction instructions but should not actually be included in the
+ // GHASH. However, any such blocks are all-zeroes, and the values that
+ // they're multiplied with are also all-zeroes. Therefore they just add
+ // 0 * 0 = 0 to the final GHASH result, which makes no difference.
+ vmovdqu8 (POWERS_PTR), H_POW1
+.if \enc
+ vmovdqu8 V0, V1{%k1}{z}
+.endif
+ vpshufb BSWAP_MASK, V1, V0
+ vpxord GHASH_ACC, V0, V0
+ _ghash_mul_noreduce H_POW1, V0, LO, MI, HI, GHASHDATA3, V1, V2, V3
+ vpxor GHASH_ACC_XMM, GHASH_ACC_XMM, GHASH_ACC_XMM
+
+ add $VL, POWERS_PTR
+ add $VL, SRC
+ add $VL, DST
+ sub $VL, DATALEN
+ jg .Lcrypt_loop_1x\@
+
+ // Finally, do the GHASH reduction.
+ _ghash_reduce LO, MI, HI, GFPOLY, V0
+ _horizontal_xor HI, HI_XMM, GHASH_ACC_XMM, %xmm0, %xmm1, %xmm2
+
+.Ldone\@:
+ // Store the updated GHASH accumulator back to memory.
+ vmovdqu GHASH_ACC_XMM, (GHASH_ACC_PTR)
+
+ vzeroupper // This is needed after using ymm or zmm registers.
+ RET
+.endm
+
+// void aes_gcm_enc_final_vaes_avx10(const struct aes_gcm_key_avx10 *key,
+// const u32 le_ctr[4], u8 ghash_acc[16],
+// u64 total_aadlen, u64 total_datalen);
+// bool aes_gcm_dec_final_vaes_avx10(const struct aes_gcm_key_avx10 *key,
+// const u32 le_ctr[4],
+// const u8 ghash_acc[16],
+// u64 total_aadlen, u64 total_datalen,
+// const u8 tag[16], int taglen);
+//
+// This macro generates one of the above two functions (with \enc selecting
+// which one). Both functions finish computing the GCM authentication tag by
+// updating GHASH with the lengths block and encrypting the GHASH accumulator.
+// |total_aadlen| and |total_datalen| must be the total length of the additional
+// authenticated data and the en/decrypted data in bytes, respectively.
+//
+// The encryption function then stores the full-length (16-byte) computed
+// authentication tag to |ghash_acc|. The decryption function instead loads the
+// expected authentication tag (the one that was transmitted) from the 16-byte
+// buffer |tag|, compares the first 4 <= |taglen| <= 16 bytes of it to the
+// computed tag in constant time, and returns true if and only if they match.
+.macro _aes_gcm_final enc
+
+ // Function arguments
+ .set KEY, %rdi
+ .set LE_CTR_PTR, %rsi
+ .set GHASH_ACC_PTR, %rdx
+ .set TOTAL_AADLEN, %rcx
+ .set TOTAL_DATALEN, %r8
+ .set TAG, %r9
+ .set TAGLEN, %r10d // Originally at 8(%rsp)
+
+ // Additional local variables.
+ // %rax, %xmm0-%xmm3, and %k1 are used as temporary registers.
+ .set AESKEYLEN, %r11d
+ .set AESKEYLEN64, %r11
+ .set GFPOLY, %xmm4
+ .set BSWAP_MASK, %xmm5
+ .set LE_CTR, %xmm6
+ .set GHASH_ACC, %xmm7
+ .set H_POW1, %xmm8
+
+ // Load some constants.
+ vmovdqa .Lgfpoly(%rip), GFPOLY
+ vmovdqa .Lbswap_mask(%rip), BSWAP_MASK
+
+ // Load the AES key length in bytes.
+ movl OFFSETOF_AESKEYLEN(KEY), AESKEYLEN
+
+ // Set up a counter block with 1 in the low 32-bit word. This is the
+ // counter that produces the ciphertext needed to encrypt the auth tag.
+ // GFPOLY has 1 in the low word, so grab the 1 from there using a blend.
+ vpblendd $0xe, (LE_CTR_PTR), GFPOLY, LE_CTR
+
+ // Build the lengths block and XOR it with the GHASH accumulator.
+ // Although the lengths block is defined as the AAD length followed by
+ // the en/decrypted data length, both in big-endian byte order, a byte
+ // reflection of the full block is needed because of the way we compute
+ // GHASH (see _ghash_mul_step). By using little-endian values in the
+ // opposite order, we avoid having to reflect any bytes here.
+ vmovq TOTAL_DATALEN, %xmm0
+ vpinsrq $1, TOTAL_AADLEN, %xmm0, %xmm0
+ vpsllq $3, %xmm0, %xmm0 // Bytes to bits
+ vpxor (GHASH_ACC_PTR), %xmm0, GHASH_ACC
+
+ // Load the first hash key power (H^1), which is stored last.
+ vmovdqu8 OFFSETOFEND_H_POWERS-16(KEY), H_POW1
+
+.if !\enc
+ // Prepare a mask of TAGLEN one bits.
+ movl 8(%rsp), TAGLEN
+ mov $-1, %eax
+ bzhi TAGLEN, %eax, %eax
+ kmovd %eax, %k1
+.endif
+
+ // Make %rax point to the last AES round key for the chosen AES variant.
+ lea 6*16(KEY,AESKEYLEN64,4), %rax
+
+ // Start the AES encryption of the counter block by swapping the counter
+ // block to big-endian and XOR-ing it with the zero-th AES round key.
+ vpshufb BSWAP_MASK, LE_CTR, %xmm0
+ vpxor (KEY), %xmm0, %xmm0
+
+ // Complete the AES encryption and multiply GHASH_ACC by H^1.
+ // Interleave the AES and GHASH instructions to improve performance.
+ cmp $24, AESKEYLEN
+ jl 128f // AES-128?
+ je 192f // AES-192?
+ // AES-256
+ vaesenc -13*16(%rax), %xmm0, %xmm0
+ vaesenc -12*16(%rax), %xmm0, %xmm0
+192:
+ vaesenc -11*16(%rax), %xmm0, %xmm0
+ vaesenc -10*16(%rax), %xmm0, %xmm0
+128:
+.irp i, 0,1,2,3,4,5,6,7,8
+ _ghash_mul_step \i, H_POW1, GHASH_ACC, GHASH_ACC, GFPOLY, \
+ %xmm1, %xmm2, %xmm3
+ vaesenc (\i-9)*16(%rax), %xmm0, %xmm0
+.endr
+ _ghash_mul_step 9, H_POW1, GHASH_ACC, GHASH_ACC, GFPOLY, \
+ %xmm1, %xmm2, %xmm3
+
+ // Undo the byte reflection of the GHASH accumulator.
+ vpshufb BSWAP_MASK, GHASH_ACC, GHASH_ACC
+
+ // Do the last AES round and XOR the resulting keystream block with the
+ // GHASH accumulator to produce the full computed authentication tag.
+ //
+ // Reduce latency by taking advantage of the property vaesenclast(key,
+ // a) ^ b == vaesenclast(key ^ b, a). I.e., XOR GHASH_ACC into the last
+ // round key, instead of XOR'ing the final AES output with GHASH_ACC.
+ //
+ // enc_final then returns the computed auth tag, while dec_final
+ // compares it with the transmitted one and returns a bool. To compare
+ // the tags, dec_final XORs them together and uses vptest to check
+ // whether the result is all-zeroes. This should be constant-time.
+ // dec_final applies the vaesenclast optimization to this additional
+ // value XOR'd too, using vpternlogd to XOR the last round key, GHASH
+ // accumulator, and transmitted auth tag together in one instruction.
+.if \enc
+ vpxor (%rax), GHASH_ACC, %xmm1
+ vaesenclast %xmm1, %xmm0, GHASH_ACC
+ vmovdqu GHASH_ACC, (GHASH_ACC_PTR)
+.else
+ vmovdqu (TAG), %xmm1
+ vpternlogd $0x96, (%rax), GHASH_ACC, %xmm1
+ vaesenclast %xmm1, %xmm0, %xmm0
+ xor %eax, %eax
+ vmovdqu8 %xmm0, %xmm0{%k1}{z} // Truncate to TAGLEN bytes
+ vptest %xmm0, %xmm0
+ sete %al
+.endif
+ // No need for vzeroupper here, since only used xmm registers were used.
+ RET
+.endm
+
+_set_veclen 32
+SYM_FUNC_START(aes_gcm_precompute_vaes_avx10_256)
+ _aes_gcm_precompute
+SYM_FUNC_END(aes_gcm_precompute_vaes_avx10_256)
+SYM_FUNC_START(aes_gcm_enc_update_vaes_avx10_256)
+ _aes_gcm_update 1
+SYM_FUNC_END(aes_gcm_enc_update_vaes_avx10_256)
+SYM_FUNC_START(aes_gcm_dec_update_vaes_avx10_256)
+ _aes_gcm_update 0
+SYM_FUNC_END(aes_gcm_dec_update_vaes_avx10_256)
+
+_set_veclen 64
+SYM_FUNC_START(aes_gcm_precompute_vaes_avx10_512)
+ _aes_gcm_precompute
+SYM_FUNC_END(aes_gcm_precompute_vaes_avx10_512)
+SYM_FUNC_START(aes_gcm_enc_update_vaes_avx10_512)
+ _aes_gcm_update 1
+SYM_FUNC_END(aes_gcm_enc_update_vaes_avx10_512)
+SYM_FUNC_START(aes_gcm_dec_update_vaes_avx10_512)
+ _aes_gcm_update 0
+SYM_FUNC_END(aes_gcm_dec_update_vaes_avx10_512)
+
+// void aes_gcm_aad_update_vaes_avx10(const struct aes_gcm_key_avx10 *key,
+// u8 ghash_acc[16],
+// const u8 *aad, int aadlen);
+//
+// This function processes the AAD (Additional Authenticated Data) in GCM.
+// Using the key |key|, it updates the GHASH accumulator |ghash_acc| with the
+// data given by |aad| and |aadlen|. |key->ghash_key_powers| must have been
+// initialized. On the first call, |ghash_acc| must be all zeroes. |aadlen|
+// must be a multiple of 16, except on the last call where it can be any length.
+// The caller must do any buffering needed to ensure this.
+//
+// AES-GCM is almost always used with small amounts of AAD, less than 32 bytes.
+// Therefore, for AAD processing we currently only provide this implementation
+// which uses 256-bit vectors (ymm registers) and only has a 1x-wide loop. This
+// keeps the code size down, and it enables some micro-optimizations, e.g. using
+// VEX-coded instructions instead of EVEX-coded to save some instruction bytes.
+// To optimize for large amounts of AAD, we could implement a 4x-wide loop and
+// provide a version using 512-bit vectors, but that doesn't seem to be useful.
+SYM_FUNC_START(aes_gcm_aad_update_vaes_avx10)
+
+ // Function arguments
+ .set KEY, %rdi
+ .set GHASH_ACC_PTR, %rsi
+ .set AAD, %rdx
+ .set AADLEN, %ecx
+ .set AADLEN64, %rcx // Zero-extend AADLEN before using!
+
+ // Additional local variables.
+ // %rax, %ymm0-%ymm3, and %k1 are used as temporary registers.
+ .set BSWAP_MASK, %ymm4
+ .set GFPOLY, %ymm5
+ .set GHASH_ACC, %ymm6
+ .set GHASH_ACC_XMM, %xmm6
+ .set H_POW1, %ymm7
+
+ // Load some constants.
+ vbroadcasti128 .Lbswap_mask(%rip), BSWAP_MASK
+ vbroadcasti128 .Lgfpoly(%rip), GFPOLY
+
+ // Load the GHASH accumulator.
+ vmovdqu (GHASH_ACC_PTR), GHASH_ACC_XMM
+
+ // Update GHASH with 32 bytes of AAD at a time.
+ //
+ // Pre-subtracting 32 from AADLEN saves an instruction from the loop and
+ // also ensures that at least one write always occurs to AADLEN,
+ // zero-extending it and allowing AADLEN64 to be used later.
+ sub $32, AADLEN
+ jl .Laad_loop_1x_done
+ vmovdqu8 OFFSETOFEND_H_POWERS-32(KEY), H_POW1 // [H^2, H^1]
+.Laad_loop_1x:
+ vmovdqu (AAD), %ymm0
+ vpshufb BSWAP_MASK, %ymm0, %ymm0
+ vpxor %ymm0, GHASH_ACC, GHASH_ACC
+ _ghash_mul H_POW1, GHASH_ACC, GHASH_ACC, GFPOLY, \
+ %ymm0, %ymm1, %ymm2
+ vextracti128 $1, GHASH_ACC, %xmm0
+ vpxor %xmm0, GHASH_ACC_XMM, GHASH_ACC_XMM
+ add $32, AAD
+ sub $32, AADLEN
+ jge .Laad_loop_1x
+.Laad_loop_1x_done:
+ add $32, AADLEN
+ jz .Laad_done
+
+ // Update GHASH with the remaining 1 <= AADLEN < 32 bytes of AAD.
+ mov $-1, %eax
+ bzhi AADLEN, %eax, %eax
+ kmovd %eax, %k1
+ vmovdqu8 (AAD), %ymm0{%k1}{z}
+ neg AADLEN64
+ and $~15, AADLEN64 // -round_up(AADLEN, 16)
+ vmovdqu8 OFFSETOFEND_H_POWERS(KEY,AADLEN64), H_POW1
+ vpshufb BSWAP_MASK, %ymm0, %ymm0
+ vpxor %ymm0, GHASH_ACC, GHASH_ACC
+ _ghash_mul H_POW1, GHASH_ACC, GHASH_ACC, GFPOLY, \
+ %ymm0, %ymm1, %ymm2
+ vextracti128 $1, GHASH_ACC, %xmm0
+ vpxor %xmm0, GHASH_ACC_XMM, GHASH_ACC_XMM
+
+.Laad_done:
+ // Store the updated GHASH accumulator back to memory.
+ vmovdqu GHASH_ACC_XMM, (GHASH_ACC_PTR)
+
+ vzeroupper // This is needed after using ymm or zmm registers.
+ RET
+SYM_FUNC_END(aes_gcm_aad_update_vaes_avx10)
+
+SYM_FUNC_START(aes_gcm_enc_final_vaes_avx10)
+ _aes_gcm_final 1
+SYM_FUNC_END(aes_gcm_enc_final_vaes_avx10)
+SYM_FUNC_START(aes_gcm_dec_final_vaes_avx10)
+ _aes_gcm_final 0
+SYM_FUNC_END(aes_gcm_dec_final_vaes_avx10)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 39066b57a70e..eb153eff9331 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -10,16 +10,7 @@
* Vinodh Gopal <vinodh.gopal@intel.com>
* Kahraman Akdemir
*
- * Added RFC4106 AES-GCM support for 128-bit keys under the AEAD
- * interface for 64-bit kernels.
- * Authors: Erdinc Ozturk (erdinc.ozturk@intel.com)
- * Aidan O'Mahony (aidan.o.mahony@intel.com)
- * Adrian Hoban <adrian.hoban@intel.com>
- * James Guilford (james.guilford@intel.com)
- * Gabriele Paoloni <gabriele.paoloni@intel.com>
- * Tadeusz Struk (tadeusz.struk@intel.com)
- * Wajdi Feghali (wajdi.k.feghali@intel.com)
- * Copyright (c) 2010, Intel Corporation.
+ * Copyright (c) 2010, Intel Corporation.
*
* Ported x86_64 version to x86:
* Author: Mathias Krause <minipli@googlemail.com>
@@ -27,95 +18,6 @@
#include <linux/linkage.h>
#include <asm/frame.h>
-#include <asm/nospec-branch.h>
-
-/*
- * The following macros are used to move an (un)aligned 16 byte value to/from
- * an XMM register. This can done for either FP or integer values, for FP use
- * movaps (move aligned packed single) or integer use movdqa (move double quad
- * aligned). It doesn't make a performance difference which instruction is used
- * since Nehalem (original Core i7) was released. However, the movaps is a byte
- * shorter, so that is the one we'll use for now. (same for unaligned).
- */
-#define MOVADQ movaps
-#define MOVUDQ movups
-
-#ifdef __x86_64__
-
-# constants in mergeable sections, linker can reorder and merge
-.section .rodata.cst16.POLY, "aM", @progbits, 16
-.align 16
-POLY: .octa 0xC2000000000000000000000000000001
-.section .rodata.cst16.TWOONE, "aM", @progbits, 16
-.align 16
-TWOONE: .octa 0x00000001000000000000000000000001
-
-.section .rodata.cst16.SHUF_MASK, "aM", @progbits, 16
-.align 16
-SHUF_MASK: .octa 0x000102030405060708090A0B0C0D0E0F
-.section .rodata.cst16.MASK1, "aM", @progbits, 16
-.align 16
-MASK1: .octa 0x0000000000000000ffffffffffffffff
-.section .rodata.cst16.MASK2, "aM", @progbits, 16
-.align 16
-MASK2: .octa 0xffffffffffffffff0000000000000000
-.section .rodata.cst16.ONE, "aM", @progbits, 16
-.align 16
-ONE: .octa 0x00000000000000000000000000000001
-.section .rodata.cst16.F_MIN_MASK, "aM", @progbits, 16
-.align 16
-F_MIN_MASK: .octa 0xf1f2f3f4f5f6f7f8f9fafbfcfdfeff0
-.section .rodata.cst16.dec, "aM", @progbits, 16
-.align 16
-dec: .octa 0x1
-.section .rodata.cst16.enc, "aM", @progbits, 16
-.align 16
-enc: .octa 0x2
-
-# order of these constants should not change.
-# more specifically, ALL_F should follow SHIFT_MASK,
-# and zero should follow ALL_F
-.section .rodata, "a", @progbits
-.align 16
-SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100
-ALL_F: .octa 0xffffffffffffffffffffffffffffffff
- .octa 0x00000000000000000000000000000000
-
-.text
-
-#define AadHash 16*0
-#define AadLen 16*1
-#define InLen (16*1)+8
-#define PBlockEncKey 16*2
-#define OrigIV 16*3
-#define CurCount 16*4
-#define PBlockLen 16*5
-#define HashKey 16*6 // store HashKey <<1 mod poly here
-#define HashKey_2 16*7 // store HashKey^2 <<1 mod poly here
-#define HashKey_3 16*8 // store HashKey^3 <<1 mod poly here
-#define HashKey_4 16*9 // store HashKey^4 <<1 mod poly here
-#define HashKey_k 16*10 // store XOR of High 64 bits and Low 64
- // bits of HashKey <<1 mod poly here
- //(for Karatsuba purposes)
-#define HashKey_2_k 16*11 // store XOR of High 64 bits and Low 64
- // bits of HashKey^2 <<1 mod poly here
- // (for Karatsuba purposes)
-#define HashKey_3_k 16*12 // store XOR of High 64 bits and Low 64
- // bits of HashKey^3 <<1 mod poly here
- // (for Karatsuba purposes)
-#define HashKey_4_k 16*13 // store XOR of High 64 bits and Low 64
- // bits of HashKey^4 <<1 mod poly here
- // (for Karatsuba purposes)
-
-#define arg1 rdi
-#define arg2 rsi
-#define arg3 rdx
-#define arg4 rcx
-#define arg5 r8
-#define arg6 r9
-#define keysize 2*15*16(%arg1)
-#endif
-
#define STATE1 %xmm0
#define STATE2 %xmm4
@@ -162,1409 +64,6 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff
#define TKEYP T1
#endif
-.macro FUNC_SAVE
- push %r12
- push %r13
- push %r14
-#
-# states of %xmm registers %xmm6:%xmm15 not saved
-# all %xmm registers are clobbered
-#
-.endm
-
-
-.macro FUNC_RESTORE
- pop %r14
- pop %r13
- pop %r12
-.endm
-
-# Precompute hashkeys.
-# Input: Hash subkey.
-# Output: HashKeys stored in gcm_context_data. Only needs to be called
-# once per key.
-# clobbers r12, and tmp xmm registers.
-.macro PRECOMPUTE SUBKEY TMP1 TMP2 TMP3 TMP4 TMP5 TMP6 TMP7
- mov \SUBKEY, %r12
- movdqu (%r12), \TMP3
- movdqa SHUF_MASK(%rip), \TMP2
- pshufb \TMP2, \TMP3
-
- # precompute HashKey<<1 mod poly from the HashKey (required for GHASH)
-
- movdqa \TMP3, \TMP2
- psllq $1, \TMP3
- psrlq $63, \TMP2
- movdqa \TMP2, \TMP1
- pslldq $8, \TMP2
- psrldq $8, \TMP1
- por \TMP2, \TMP3
-
- # reduce HashKey<<1
-
- pshufd $0x24, \TMP1, \TMP2
- pcmpeqd TWOONE(%rip), \TMP2
- pand POLY(%rip), \TMP2
- pxor \TMP2, \TMP3
- movdqu \TMP3, HashKey(%arg2)
-
- movdqa \TMP3, \TMP5
- pshufd $78, \TMP3, \TMP1
- pxor \TMP3, \TMP1
- movdqu \TMP1, HashKey_k(%arg2)
-
- GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^2<<1 (mod poly)
- movdqu \TMP5, HashKey_2(%arg2)
-# HashKey_2 = HashKey^2<<1 (mod poly)
- pshufd $78, \TMP5, \TMP1
- pxor \TMP5, \TMP1
- movdqu \TMP1, HashKey_2_k(%arg2)
-
- GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^3<<1 (mod poly)
- movdqu \TMP5, HashKey_3(%arg2)
- pshufd $78, \TMP5, \TMP1
- pxor \TMP5, \TMP1
- movdqu \TMP1, HashKey_3_k(%arg2)
-
- GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
-# TMP5 = HashKey^3<<1 (mod poly)
- movdqu \TMP5, HashKey_4(%arg2)
- pshufd $78, \TMP5, \TMP1
- pxor \TMP5, \TMP1
- movdqu \TMP1, HashKey_4_k(%arg2)
-.endm
-
-# GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding.
-# Clobbers rax, r10-r13 and xmm0-xmm6, %xmm13
-.macro GCM_INIT Iv SUBKEY AAD AADLEN
- mov \AADLEN, %r11
- mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
- xor %r11d, %r11d
- mov %r11, InLen(%arg2) # ctx_data.in_length = 0
- mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
- mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
- mov \Iv, %rax
- movdqu (%rax), %xmm0
- movdqu %xmm0, OrigIV(%arg2) # ctx_data.orig_IV = iv
-
- movdqa SHUF_MASK(%rip), %xmm2
- pshufb %xmm2, %xmm0
- movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
-
- PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7
- movdqu HashKey(%arg2), %xmm13
-
- CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
- %xmm4, %xmm5, %xmm6
-.endm
-
-# GCM_ENC_DEC Encodes/Decodes given data. Assumes that the passed gcm_context
-# struct has been initialized by GCM_INIT.
-# Requires the input data be at least 1 byte long because of READ_PARTIAL_BLOCK
-# Clobbers rax, r10-r13, and xmm0-xmm15
-.macro GCM_ENC_DEC operation
- movdqu AadHash(%arg2), %xmm8
- movdqu HashKey(%arg2), %xmm13
- add %arg5, InLen(%arg2)
-
- xor %r11d, %r11d # initialise the data pointer offset as zero
- PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation
-
- sub %r11, %arg5 # sub partial block data used
- mov %arg5, %r13 # save the number of bytes
-
- and $-16, %r13 # %r13 = %r13 - (%r13 mod 16)
- mov %r13, %r12
- # Encrypt/Decrypt first few blocks
-
- and $(3<<4), %r12
- jz .L_initial_num_blocks_is_0_\@
- cmp $(2<<4), %r12
- jb .L_initial_num_blocks_is_1_\@
- je .L_initial_num_blocks_is_2_\@
-.L_initial_num_blocks_is_3_\@:
- INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, \operation
- sub $48, %r13
- jmp .L_initial_blocks_\@
-.L_initial_num_blocks_is_2_\@:
- INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, \operation
- sub $32, %r13
- jmp .L_initial_blocks_\@
-.L_initial_num_blocks_is_1_\@:
- INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, \operation
- sub $16, %r13
- jmp .L_initial_blocks_\@
-.L_initial_num_blocks_is_0_\@:
- INITIAL_BLOCKS_ENC_DEC %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
-%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, \operation
-.L_initial_blocks_\@:
-
- # Main loop - Encrypt/Decrypt remaining blocks
-
- test %r13, %r13
- je .L_zero_cipher_left_\@
- sub $64, %r13
- je .L_four_cipher_left_\@
-.L_crypt_by_4_\@:
- GHASH_4_ENCRYPT_4_PARALLEL_\operation %xmm9, %xmm10, %xmm11, %xmm12, \
- %xmm13, %xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, \
- %xmm7, %xmm8, enc
- add $64, %r11
- sub $64, %r13
- jne .L_crypt_by_4_\@
-.L_four_cipher_left_\@:
- GHASH_LAST_4 %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \
-%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8
-.L_zero_cipher_left_\@:
- movdqu %xmm8, AadHash(%arg2)
- movdqu %xmm0, CurCount(%arg2)
-
- mov %arg5, %r13
- and $15, %r13 # %r13 = arg5 (mod 16)
- je .L_multiple_of_16_bytes_\@
-
- mov %r13, PBlockLen(%arg2)
-
- # Handle the last <16 Byte block separately
- paddd ONE(%rip), %xmm0 # INCR CNT to get Yn
- movdqu %xmm0, CurCount(%arg2)
- movdqa SHUF_MASK(%rip), %xmm10
- pshufb %xmm10, %xmm0
-
- ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # Encrypt(K, Yn)
- movdqu %xmm0, PBlockEncKey(%arg2)
-
- cmp $16, %arg5
- jge .L_large_enough_update_\@
-
- lea (%arg4,%r11,1), %r10
- mov %r13, %r12
- READ_PARTIAL_BLOCK %r10 %r12 %xmm2 %xmm1
- jmp .L_data_read_\@
-
-.L_large_enough_update_\@:
- sub $16, %r11
- add %r13, %r11
-
- # receive the last <16 Byte block
- movdqu (%arg4, %r11, 1), %xmm1
-
- sub %r13, %r11
- add $16, %r11
-
- lea SHIFT_MASK+16(%rip), %r12
- # adjust the shuffle mask pointer to be able to shift 16-r13 bytes
- # (r13 is the number of bytes in plaintext mod 16)
- sub %r13, %r12
- # get the appropriate shuffle mask
- movdqu (%r12), %xmm2
- # shift right 16-r13 bytes
- pshufb %xmm2, %xmm1
-
-.L_data_read_\@:
- lea ALL_F+16(%rip), %r12
- sub %r13, %r12
-
-.ifc \operation, dec
- movdqa %xmm1, %xmm2
-.endif
- pxor %xmm1, %xmm0 # XOR Encrypt(K, Yn)
- movdqu (%r12), %xmm1
- # get the appropriate mask to mask out top 16-r13 bytes of xmm0
- pand %xmm1, %xmm0 # mask out top 16-r13 bytes of xmm0
-.ifc \operation, dec
- pand %xmm1, %xmm2
- movdqa SHUF_MASK(%rip), %xmm10
- pshufb %xmm10 ,%xmm2
-
- pxor %xmm2, %xmm8
-.else
- movdqa SHUF_MASK(%rip), %xmm10
- pshufb %xmm10,%xmm0
-
- pxor %xmm0, %xmm8
-.endif
-
- movdqu %xmm8, AadHash(%arg2)
-.ifc \operation, enc
- # GHASH computation for the last <16 byte block
- movdqa SHUF_MASK(%rip), %xmm10
- # shuffle xmm0 back to output as ciphertext
- pshufb %xmm10, %xmm0
-.endif
-
- # Output %r13 bytes
- movq %xmm0, %rax
- cmp $8, %r13
- jle .L_less_than_8_bytes_left_\@
- mov %rax, (%arg3 , %r11, 1)
- add $8, %r11
- psrldq $8, %xmm0
- movq %xmm0, %rax
- sub $8, %r13
-.L_less_than_8_bytes_left_\@:
- mov %al, (%arg3, %r11, 1)
- add $1, %r11
- shr $8, %rax
- sub $1, %r13
- jne .L_less_than_8_bytes_left_\@
-.L_multiple_of_16_bytes_\@:
-.endm
-
-# GCM_COMPLETE Finishes update of tag of last partial block
-# Output: Authorization Tag (AUTH_TAG)
-# Clobbers rax, r10-r12, and xmm0, xmm1, xmm5-xmm15
-.macro GCM_COMPLETE AUTHTAG AUTHTAGLEN
- movdqu AadHash(%arg2), %xmm8
- movdqu HashKey(%arg2), %xmm13
-
- mov PBlockLen(%arg2), %r12
-
- test %r12, %r12
- je .L_partial_done\@
-
- GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
-
-.L_partial_done\@:
- mov AadLen(%arg2), %r12 # %r13 = aadLen (number of bytes)
- shl $3, %r12 # convert into number of bits
- movd %r12d, %xmm15 # len(A) in %xmm15
- mov InLen(%arg2), %r12
- shl $3, %r12 # len(C) in bits (*128)
- movq %r12, %xmm1
-
- pslldq $8, %xmm15 # %xmm15 = len(A)||0x0000000000000000
- pxor %xmm1, %xmm15 # %xmm15 = len(A)||len(C)
- pxor %xmm15, %xmm8
- GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
- # final GHASH computation
- movdqa SHUF_MASK(%rip), %xmm10
- pshufb %xmm10, %xmm8
-
- movdqu OrigIV(%arg2), %xmm0 # %xmm0 = Y0
- ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # E(K, Y0)
- pxor %xmm8, %xmm0
-.L_return_T_\@:
- mov \AUTHTAG, %r10 # %r10 = authTag
- mov \AUTHTAGLEN, %r11 # %r11 = auth_tag_len
- cmp $16, %r11
- je .L_T_16_\@
- cmp $8, %r11
- jl .L_T_4_\@
-.L_T_8_\@:
- movq %xmm0, %rax
- mov %rax, (%r10)
- add $8, %r10
- sub $8, %r11
- psrldq $8, %xmm0
- test %r11, %r11
- je .L_return_T_done_\@
-.L_T_4_\@:
- movd %xmm0, %eax
- mov %eax, (%r10)
- add $4, %r10
- sub $4, %r11
- psrldq $4, %xmm0
- test %r11, %r11
- je .L_return_T_done_\@
-.L_T_123_\@:
- movd %xmm0, %eax
- cmp $2, %r11
- jl .L_T_1_\@
- mov %ax, (%r10)
- cmp $2, %r11
- je .L_return_T_done_\@
- add $2, %r10
- sar $16, %eax
-.L_T_1_\@:
- mov %al, (%r10)
- jmp .L_return_T_done_\@
-.L_T_16_\@:
- movdqu %xmm0, (%r10)
-.L_return_T_done_\@:
-.endm
-
-#ifdef __x86_64__
-/* GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
-*
-*
-* Input: A and B (128-bits each, bit-reflected)
-* Output: C = A*B*x mod poly, (i.e. >>1 )
-* To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
-* GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
-*
-*/
-.macro GHASH_MUL GH HK TMP1 TMP2 TMP3 TMP4 TMP5
- movdqa \GH, \TMP1
- pshufd $78, \GH, \TMP2
- pshufd $78, \HK, \TMP3
- pxor \GH, \TMP2 # TMP2 = a1+a0
- pxor \HK, \TMP3 # TMP3 = b1+b0
- pclmulqdq $0x11, \HK, \TMP1 # TMP1 = a1*b1
- pclmulqdq $0x00, \HK, \GH # GH = a0*b0
- pclmulqdq $0x00, \TMP3, \TMP2 # TMP2 = (a0+a1)*(b1+b0)
- pxor \GH, \TMP2
- pxor \TMP1, \TMP2 # TMP2 = (a0*b0)+(a1*b0)
- movdqa \TMP2, \TMP3
- pslldq $8, \TMP3 # left shift TMP3 2 DWs
- psrldq $8, \TMP2 # right shift TMP2 2 DWs
- pxor \TMP3, \GH
- pxor \TMP2, \TMP1 # TMP2:GH holds the result of GH*HK
-
- # first phase of the reduction
-
- movdqa \GH, \TMP2
- movdqa \GH, \TMP3
- movdqa \GH, \TMP4 # copy GH into TMP2,TMP3 and TMP4
- # in in order to perform
- # independent shifts
- pslld $31, \TMP2 # packed right shift <<31
- pslld $30, \TMP3 # packed right shift <<30
- pslld $25, \TMP4 # packed right shift <<25
- pxor \TMP3, \TMP2 # xor the shifted versions
- pxor \TMP4, \TMP2
- movdqa \TMP2, \TMP5
- psrldq $4, \TMP5 # right shift TMP5 1 DW
- pslldq $12, \TMP2 # left shift TMP2 3 DWs
- pxor \TMP2, \GH
-
- # second phase of the reduction
-
- movdqa \GH,\TMP2 # copy GH into TMP2,TMP3 and TMP4
- # in in order to perform
- # independent shifts
- movdqa \GH,\TMP3
- movdqa \GH,\TMP4
- psrld $1,\TMP2 # packed left shift >>1
- psrld $2,\TMP3 # packed left shift >>2
- psrld $7,\TMP4 # packed left shift >>7
- pxor \TMP3,\TMP2 # xor the shifted versions
- pxor \TMP4,\TMP2
- pxor \TMP5, \TMP2
- pxor \TMP2, \GH
- pxor \TMP1, \GH # result is in TMP1
-.endm
-
-# Reads DLEN bytes starting at DPTR and stores in XMMDst
-# where 0 < DLEN < 16
-# Clobbers %rax, DLEN and XMM1
-.macro READ_PARTIAL_BLOCK DPTR DLEN XMM1 XMMDst
- cmp $8, \DLEN
- jl .L_read_lt8_\@
- mov (\DPTR), %rax
- movq %rax, \XMMDst
- sub $8, \DLEN
- jz .L_done_read_partial_block_\@
- xor %eax, %eax
-.L_read_next_byte_\@:
- shl $8, %rax
- mov 7(\DPTR, \DLEN, 1), %al
- dec \DLEN
- jnz .L_read_next_byte_\@
- movq %rax, \XMM1
- pslldq $8, \XMM1
- por \XMM1, \XMMDst
- jmp .L_done_read_partial_block_\@
-.L_read_lt8_\@:
- xor %eax, %eax
-.L_read_next_byte_lt8_\@:
- shl $8, %rax
- mov -1(\DPTR, \DLEN, 1), %al
- dec \DLEN
- jnz .L_read_next_byte_lt8_\@
- movq %rax, \XMMDst
-.L_done_read_partial_block_\@:
-.endm
-
-# CALC_AAD_HASH: Calculates the hash of the data which will not be encrypted.
-# clobbers r10-11, xmm14
-.macro CALC_AAD_HASH HASHKEY AAD AADLEN TMP1 TMP2 TMP3 TMP4 TMP5 \
- TMP6 TMP7
- MOVADQ SHUF_MASK(%rip), %xmm14
- mov \AAD, %r10 # %r10 = AAD
- mov \AADLEN, %r11 # %r11 = aadLen
- pxor \TMP7, \TMP7
- pxor \TMP6, \TMP6
-
- cmp $16, %r11
- jl .L_get_AAD_rest\@
-.L_get_AAD_blocks\@:
- movdqu (%r10), \TMP7
- pshufb %xmm14, \TMP7 # byte-reflect the AAD data
- pxor \TMP7, \TMP6
- GHASH_MUL \TMP6, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5
- add $16, %r10
- sub $16, %r11
- cmp $16, %r11
- jge .L_get_AAD_blocks\@
-
- movdqu \TMP6, \TMP7
-
- /* read the last <16B of AAD */
-.L_get_AAD_rest\@:
- test %r11, %r11
- je .L_get_AAD_done\@
-
- READ_PARTIAL_BLOCK %r10, %r11, \TMP1, \TMP7
- pshufb %xmm14, \TMP7 # byte-reflect the AAD data
- pxor \TMP6, \TMP7
- GHASH_MUL \TMP7, \HASHKEY, \TMP1, \TMP2, \TMP3, \TMP4, \TMP5
- movdqu \TMP7, \TMP6
-
-.L_get_AAD_done\@:
- movdqu \TMP6, AadHash(%arg2)
-.endm
-
-# PARTIAL_BLOCK: Handles encryption/decryption and the tag partial blocks
-# between update calls.
-# Requires the input data be at least 1 byte long due to READ_PARTIAL_BLOCK
-# Outputs encrypted bytes, and updates hash and partial info in gcm_data_context
-# Clobbers rax, r10, r12, r13, xmm0-6, xmm9-13
-.macro PARTIAL_BLOCK CYPH_PLAIN_OUT PLAIN_CYPH_IN PLAIN_CYPH_LEN DATA_OFFSET \
- AAD_HASH operation
- mov PBlockLen(%arg2), %r13
- test %r13, %r13
- je .L_partial_block_done_\@ # Leave Macro if no partial blocks
- # Read in input data without over reading
- cmp $16, \PLAIN_CYPH_LEN
- jl .L_fewer_than_16_bytes_\@
- movups (\PLAIN_CYPH_IN), %xmm1 # If more than 16 bytes, just fill xmm
- jmp .L_data_read_\@
-
-.L_fewer_than_16_bytes_\@:
- lea (\PLAIN_CYPH_IN, \DATA_OFFSET, 1), %r10
- mov \PLAIN_CYPH_LEN, %r12
- READ_PARTIAL_BLOCK %r10 %r12 %xmm0 %xmm1
-
- mov PBlockLen(%arg2), %r13
-
-.L_data_read_\@: # Finished reading in data
-
- movdqu PBlockEncKey(%arg2), %xmm9
- movdqu HashKey(%arg2), %xmm13
-
- lea SHIFT_MASK(%rip), %r12
-
- # adjust the shuffle mask pointer to be able to shift r13 bytes
- # r16-r13 is the number of bytes in plaintext mod 16)
- add %r13, %r12
- movdqu (%r12), %xmm2 # get the appropriate shuffle mask
- pshufb %xmm2, %xmm9 # shift right r13 bytes
-
-.ifc \operation, dec
- movdqa %xmm1, %xmm3
- pxor %xmm1, %xmm9 # Ciphertext XOR E(K, Yn)
-
- mov \PLAIN_CYPH_LEN, %r10
- add %r13, %r10
- # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
- sub $16, %r10
- # Determine if partial block is not being filled and
- # shift mask accordingly
- jge .L_no_extra_mask_1_\@
- sub %r10, %r12
-.L_no_extra_mask_1_\@:
-
- movdqu ALL_F-SHIFT_MASK(%r12), %xmm1
- # get the appropriate mask to mask out bottom r13 bytes of xmm9
- pand %xmm1, %xmm9 # mask out bottom r13 bytes of xmm9
-
- pand %xmm1, %xmm3
- movdqa SHUF_MASK(%rip), %xmm10
- pshufb %xmm10, %xmm3
- pshufb %xmm2, %xmm3
- pxor %xmm3, \AAD_HASH
-
- test %r10, %r10
- jl .L_partial_incomplete_1_\@
-
- # GHASH computation for the last <16 Byte block
- GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %eax, %eax
-
- mov %rax, PBlockLen(%arg2)
- jmp .L_dec_done_\@
-.L_partial_incomplete_1_\@:
- add \PLAIN_CYPH_LEN, PBlockLen(%arg2)
-.L_dec_done_\@:
- movdqu \AAD_HASH, AadHash(%arg2)
-.else
- pxor %xmm1, %xmm9 # Plaintext XOR E(K, Yn)
-
- mov \PLAIN_CYPH_LEN, %r10
- add %r13, %r10
- # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
- sub $16, %r10
- # Determine if partial block is not being filled and
- # shift mask accordingly
- jge .L_no_extra_mask_2_\@
- sub %r10, %r12
-.L_no_extra_mask_2_\@:
-
- movdqu ALL_F-SHIFT_MASK(%r12), %xmm1
- # get the appropriate mask to mask out bottom r13 bytes of xmm9
- pand %xmm1, %xmm9
-
- movdqa SHUF_MASK(%rip), %xmm1
- pshufb %xmm1, %xmm9
- pshufb %xmm2, %xmm9
- pxor %xmm9, \AAD_HASH
-
- test %r10, %r10
- jl .L_partial_incomplete_2_\@
-
- # GHASH computation for the last <16 Byte block
- GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %eax, %eax
-
- mov %rax, PBlockLen(%arg2)
- jmp .L_encode_done_\@
-.L_partial_incomplete_2_\@:
- add \PLAIN_CYPH_LEN, PBlockLen(%arg2)
-.L_encode_done_\@:
- movdqu \AAD_HASH, AadHash(%arg2)
-
- movdqa SHUF_MASK(%rip), %xmm10
- # shuffle xmm9 back to output as ciphertext
- pshufb %xmm10, %xmm9
- pshufb %xmm2, %xmm9
-.endif
- # output encrypted Bytes
- test %r10, %r10
- jl .L_partial_fill_\@
- mov %r13, %r12
- mov $16, %r13
- # Set r13 to be the number of bytes to write out
- sub %r12, %r13
- jmp .L_count_set_\@
-.L_partial_fill_\@:
- mov \PLAIN_CYPH_LEN, %r13
-.L_count_set_\@:
- movdqa %xmm9, %xmm0
- movq %xmm0, %rax
- cmp $8, %r13
- jle .L_less_than_8_bytes_left_\@
-
- mov %rax, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
- add $8, \DATA_OFFSET
- psrldq $8, %xmm0
- movq %xmm0, %rax
- sub $8, %r13
-.L_less_than_8_bytes_left_\@:
- movb %al, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
- add $1, \DATA_OFFSET
- shr $8, %rax
- sub $1, %r13
- jne .L_less_than_8_bytes_left_\@
-.L_partial_block_done_\@:
-.endm # PARTIAL_BLOCK
-
-/*
-* if a = number of total plaintext bytes
-* b = floor(a/16)
-* num_initial_blocks = b mod 4
-* encrypt the initial num_initial_blocks blocks and apply ghash on
-* the ciphertext
-* %r10, %r11, %r12, %rax, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers
-* are clobbered
-* arg1, %arg2, %arg3 are used as a pointer only, not modified
-*/
-
-
-.macro INITIAL_BLOCKS_ENC_DEC TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \
- XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
- MOVADQ SHUF_MASK(%rip), %xmm14
-
- movdqu AadHash(%arg2), %xmm\i # XMM0 = Y0
-
- # start AES for num_initial_blocks blocks
-
- movdqu CurCount(%arg2), \XMM0 # XMM0 = Y0
-
-.if (\i == 5) || (\i == 6) || (\i == 7)
-
- MOVADQ ONE(%RIP),\TMP1
- MOVADQ 0(%arg1),\TMP2
-.irpc index, \i_seq
- paddd \TMP1, \XMM0 # INCR Y0
-.ifc \operation, dec
- movdqa \XMM0, %xmm\index
-.else
- MOVADQ \XMM0, %xmm\index
-.endif
- pshufb %xmm14, %xmm\index # perform a 16 byte swap
- pxor \TMP2, %xmm\index
-.endr
- lea 0x10(%arg1),%r10
- mov keysize,%eax
- shr $2,%eax # 128->4, 192->6, 256->8
- add $5,%eax # 128->9, 192->11, 256->13
-
-.Laes_loop_initial_\@:
- MOVADQ (%r10),\TMP1
-.irpc index, \i_seq
- aesenc \TMP1, %xmm\index
-.endr
- add $16,%r10
- sub $1,%eax
- jnz .Laes_loop_initial_\@
-
- MOVADQ (%r10), \TMP1
-.irpc index, \i_seq
- aesenclast \TMP1, %xmm\index # Last Round
-.endr
-.irpc index, \i_seq
- movdqu (%arg4 , %r11, 1), \TMP1
- pxor \TMP1, %xmm\index
- movdqu %xmm\index, (%arg3 , %r11, 1)
- # write back plaintext/ciphertext for num_initial_blocks
- add $16, %r11
-
-.ifc \operation, dec
- movdqa \TMP1, %xmm\index
-.endif
- pshufb %xmm14, %xmm\index
-
- # prepare plaintext/ciphertext for GHASH computation
-.endr
-.endif
-
- # apply GHASH on num_initial_blocks blocks
-
-.if \i == 5
- pxor %xmm5, %xmm6
- GHASH_MUL %xmm6, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
- pxor %xmm6, %xmm7
- GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
- pxor %xmm7, %xmm8
- GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-.elseif \i == 6
- pxor %xmm6, %xmm7
- GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
- pxor %xmm7, %xmm8
- GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-.elseif \i == 7
- pxor %xmm7, %xmm8
- GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
-.endif
- cmp $64, %r13
- jl .L_initial_blocks_done\@
- # no need for precomputed values
-/*
-*
-* Precomputations for HashKey parallel with encryption of first 4 blocks.
-* Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
-*/
- MOVADQ ONE(%RIP),\TMP1
- paddd \TMP1, \XMM0 # INCR Y0
- MOVADQ \XMM0, \XMM1
- pshufb %xmm14, \XMM1 # perform a 16 byte swap
-
- paddd \TMP1, \XMM0 # INCR Y0
- MOVADQ \XMM0, \XMM2
- pshufb %xmm14, \XMM2 # perform a 16 byte swap
-
- paddd \TMP1, \XMM0 # INCR Y0
- MOVADQ \XMM0, \XMM3
- pshufb %xmm14, \XMM3 # perform a 16 byte swap
-
- paddd \TMP1, \XMM0 # INCR Y0
- MOVADQ \XMM0, \XMM4
- pshufb %xmm14, \XMM4 # perform a 16 byte swap
-
- MOVADQ 0(%arg1),\TMP1
- pxor \TMP1, \XMM1
- pxor \TMP1, \XMM2
- pxor \TMP1, \XMM3
- pxor \TMP1, \XMM4
-.irpc index, 1234 # do 4 rounds
- movaps 0x10*\index(%arg1), \TMP1
- aesenc \TMP1, \XMM1
- aesenc \TMP1, \XMM2
- aesenc \TMP1, \XMM3
- aesenc \TMP1, \XMM4
-.endr
-.irpc index, 56789 # do next 5 rounds
- movaps 0x10*\index(%arg1), \TMP1
- aesenc \TMP1, \XMM1
- aesenc \TMP1, \XMM2
- aesenc \TMP1, \XMM3
- aesenc \TMP1, \XMM4
-.endr
- lea 0xa0(%arg1),%r10
- mov keysize,%eax
- shr $2,%eax # 128->4, 192->6, 256->8
- sub $4,%eax # 128->0, 192->2, 256->4
- jz .Laes_loop_pre_done\@
-
-.Laes_loop_pre_\@:
- MOVADQ (%r10),\TMP2
-.irpc index, 1234
- aesenc \TMP2, %xmm\index
-.endr
- add $16,%r10
- sub $1,%eax
- jnz .Laes_loop_pre_\@
-
-.Laes_loop_pre_done\@:
- MOVADQ (%r10), \TMP2
- aesenclast \TMP2, \XMM1
- aesenclast \TMP2, \XMM2
- aesenclast \TMP2, \XMM3
- aesenclast \TMP2, \XMM4
- movdqu 16*0(%arg4 , %r11 , 1), \TMP1
- pxor \TMP1, \XMM1
-.ifc \operation, dec
- movdqu \XMM1, 16*0(%arg3 , %r11 , 1)
- movdqa \TMP1, \XMM1
-.endif
- movdqu 16*1(%arg4 , %r11 , 1), \TMP1
- pxor \TMP1, \XMM2
-.ifc \operation, dec
- movdqu \XMM2, 16*1(%arg3 , %r11 , 1)
- movdqa \TMP1, \XMM2
-.endif
- movdqu 16*2(%arg4 , %r11 , 1), \TMP1
- pxor \TMP1, \XMM3
-.ifc \operation, dec
- movdqu \XMM3, 16*2(%arg3 , %r11 , 1)
- movdqa \TMP1, \XMM3
-.endif
- movdqu 16*3(%arg4 , %r11 , 1), \TMP1
- pxor \TMP1, \XMM4
-.ifc \operation, dec
- movdqu \XMM4, 16*3(%arg3 , %r11 , 1)
- movdqa \TMP1, \XMM4
-.else
- movdqu \XMM1, 16*0(%arg3 , %r11 , 1)
- movdqu \XMM2, 16*1(%arg3 , %r11 , 1)
- movdqu \XMM3, 16*2(%arg3 , %r11 , 1)
- movdqu \XMM4, 16*3(%arg3 , %r11 , 1)
-.endif
-
- add $64, %r11
- pshufb %xmm14, \XMM1 # perform a 16 byte swap
- pxor \XMMDst, \XMM1
-# combine GHASHed value with the corresponding ciphertext
- pshufb %xmm14, \XMM2 # perform a 16 byte swap
- pshufb %xmm14, \XMM3 # perform a 16 byte swap
- pshufb %xmm14, \XMM4 # perform a 16 byte swap
-
-.L_initial_blocks_done\@:
-
-.endm
-
-/*
-* encrypt 4 blocks at a time
-* ghash the 4 previously encrypted ciphertext blocks
-* arg1, %arg3, %arg4 are used as pointers only, not modified
-* %r11 is the data offset value
-*/
-.macro GHASH_4_ENCRYPT_4_PARALLEL_enc TMP1 TMP2 TMP3 TMP4 TMP5 \
-TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
-
- movdqa \XMM1, \XMM5
- movdqa \XMM2, \XMM6
- movdqa \XMM3, \XMM7
- movdqa \XMM4, \XMM8
-
- movdqa SHUF_MASK(%rip), %xmm15
- # multiply TMP5 * HashKey using karatsuba
-
- movdqa \XMM5, \TMP4
- pshufd $78, \XMM5, \TMP6
- pxor \XMM5, \TMP6
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqu HashKey_4(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP4 # TMP4 = a1*b1
- movdqa \XMM0, \XMM1
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa \XMM0, \XMM2
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa \XMM0, \XMM3
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa \XMM0, \XMM4
- pshufb %xmm15, \XMM1 # perform a 16 byte swap
- pclmulqdq $0x00, \TMP5, \XMM5 # XMM5 = a0*b0
- pshufb %xmm15, \XMM2 # perform a 16 byte swap
- pshufb %xmm15, \XMM3 # perform a 16 byte swap
- pshufb %xmm15, \XMM4 # perform a 16 byte swap
-
- pxor (%arg1), \XMM1
- pxor (%arg1), \XMM2
- pxor (%arg1), \XMM3
- pxor (%arg1), \XMM4
- movdqu HashKey_4_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0)
- movaps 0x10(%arg1), \TMP1
- aesenc \TMP1, \XMM1 # Round 1
- aesenc \TMP1, \XMM2
- aesenc \TMP1, \XMM3
- aesenc \TMP1, \XMM4
- movaps 0x20(%arg1), \TMP1
- aesenc \TMP1, \XMM1 # Round 2
- aesenc \TMP1, \XMM2
- aesenc \TMP1, \XMM3
- aesenc \TMP1, \XMM4
- movdqa \XMM6, \TMP1
- pshufd $78, \XMM6, \TMP2
- pxor \XMM6, \TMP2
- movdqu HashKey_3(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1 * b1
- movaps 0x30(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 3
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pclmulqdq $0x00, \TMP5, \XMM6 # XMM6 = a0*b0
- movaps 0x40(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 4
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- movdqu HashKey_3_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- movaps 0x50(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 5
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pxor \TMP1, \TMP4
-# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
- pxor \XMM6, \XMM5
- pxor \TMP2, \TMP6
- movdqa \XMM7, \TMP1
- pshufd $78, \XMM7, \TMP2
- pxor \XMM7, \TMP2
- movdqu HashKey_2(%arg2), \TMP5
-
- # Multiply TMP5 * HashKey using karatsuba
-
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1*b1
- movaps 0x60(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 6
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pclmulqdq $0x00, \TMP5, \XMM7 # XMM7 = a0*b0
- movaps 0x70(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 7
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- movdqu HashKey_2_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- movaps 0x80(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 8
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pxor \TMP1, \TMP4
-# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
- pxor \XMM7, \XMM5
- pxor \TMP2, \TMP6
-
- # Multiply XMM8 * HashKey
- # XMM8 and TMP5 hold the values for the two operands
-
- movdqa \XMM8, \TMP1
- pshufd $78, \XMM8, \TMP2
- pxor \XMM8, \TMP2
- movdqu HashKey(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1*b1
- movaps 0x90(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 9
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pclmulqdq $0x00, \TMP5, \XMM8 # XMM8 = a0*b0
- lea 0xa0(%arg1),%r10
- mov keysize,%eax
- shr $2,%eax # 128->4, 192->6, 256->8
- sub $4,%eax # 128->0, 192->2, 256->4
- jz .Laes_loop_par_enc_done\@
-
-.Laes_loop_par_enc\@:
- MOVADQ (%r10),\TMP3
-.irpc index, 1234
- aesenc \TMP3, %xmm\index
-.endr
- add $16,%r10
- sub $1,%eax
- jnz .Laes_loop_par_enc\@
-
-.Laes_loop_par_enc_done\@:
- MOVADQ (%r10), \TMP3
- aesenclast \TMP3, \XMM1 # Round 10
- aesenclast \TMP3, \XMM2
- aesenclast \TMP3, \XMM3
- aesenclast \TMP3, \XMM4
- movdqu HashKey_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- movdqu (%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK
- movdqu 16(%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM2 # Ciphertext/Plaintext XOR EK
- movdqu 32(%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM3 # Ciphertext/Plaintext XOR EK
- movdqu 48(%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM4 # Ciphertext/Plaintext XOR EK
- movdqu \XMM1, (%arg3,%r11,1) # Write to the ciphertext buffer
- movdqu \XMM2, 16(%arg3,%r11,1) # Write to the ciphertext buffer
- movdqu \XMM3, 32(%arg3,%r11,1) # Write to the ciphertext buffer
- movdqu \XMM4, 48(%arg3,%r11,1) # Write to the ciphertext buffer
- pshufb %xmm15, \XMM1 # perform a 16 byte swap
- pshufb %xmm15, \XMM2 # perform a 16 byte swap
- pshufb %xmm15, \XMM3 # perform a 16 byte swap
- pshufb %xmm15, \XMM4 # perform a 16 byte swap
-
- pxor \TMP4, \TMP1
- pxor \XMM8, \XMM5
- pxor \TMP6, \TMP2
- pxor \TMP1, \TMP2
- pxor \XMM5, \TMP2
- movdqa \TMP2, \TMP3
- pslldq $8, \TMP3 # left shift TMP3 2 DWs
- psrldq $8, \TMP2 # right shift TMP2 2 DWs
- pxor \TMP3, \XMM5
- pxor \TMP2, \TMP1 # accumulate the results in TMP1:XMM5
-
- # first phase of reduction
-
- movdqa \XMM5, \TMP2
- movdqa \XMM5, \TMP3
- movdqa \XMM5, \TMP4
-# move XMM5 into TMP2, TMP3, TMP4 in order to perform shifts independently
- pslld $31, \TMP2 # packed right shift << 31
- pslld $30, \TMP3 # packed right shift << 30
- pslld $25, \TMP4 # packed right shift << 25
- pxor \TMP3, \TMP2 # xor the shifted versions
- pxor \TMP4, \TMP2
- movdqa \TMP2, \TMP5
- psrldq $4, \TMP5 # right shift T5 1 DW
- pslldq $12, \TMP2 # left shift T2 3 DWs
- pxor \TMP2, \XMM5
-
- # second phase of reduction
-
- movdqa \XMM5,\TMP2 # make 3 copies of XMM5 into TMP2, TMP3, TMP4
- movdqa \XMM5,\TMP3
- movdqa \XMM5,\TMP4
- psrld $1, \TMP2 # packed left shift >>1
- psrld $2, \TMP3 # packed left shift >>2
- psrld $7, \TMP4 # packed left shift >>7
- pxor \TMP3,\TMP2 # xor the shifted versions
- pxor \TMP4,\TMP2
- pxor \TMP5, \TMP2
- pxor \TMP2, \XMM5
- pxor \TMP1, \XMM5 # result is in TMP1
-
- pxor \XMM5, \XMM1
-.endm
-
-/*
-* decrypt 4 blocks at a time
-* ghash the 4 previously decrypted ciphertext blocks
-* arg1, %arg3, %arg4 are used as pointers only, not modified
-* %r11 is the data offset value
-*/
-.macro GHASH_4_ENCRYPT_4_PARALLEL_dec TMP1 TMP2 TMP3 TMP4 TMP5 \
-TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
-
- movdqa \XMM1, \XMM5
- movdqa \XMM2, \XMM6
- movdqa \XMM3, \XMM7
- movdqa \XMM4, \XMM8
-
- movdqa SHUF_MASK(%rip), %xmm15
- # multiply TMP5 * HashKey using karatsuba
-
- movdqa \XMM5, \TMP4
- pshufd $78, \XMM5, \TMP6
- pxor \XMM5, \TMP6
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqu HashKey_4(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP4 # TMP4 = a1*b1
- movdqa \XMM0, \XMM1
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa \XMM0, \XMM2
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa \XMM0, \XMM3
- paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa \XMM0, \XMM4
- pshufb %xmm15, \XMM1 # perform a 16 byte swap
- pclmulqdq $0x00, \TMP5, \XMM5 # XMM5 = a0*b0
- pshufb %xmm15, \XMM2 # perform a 16 byte swap
- pshufb %xmm15, \XMM3 # perform a 16 byte swap
- pshufb %xmm15, \XMM4 # perform a 16 byte swap
-
- pxor (%arg1), \XMM1
- pxor (%arg1), \XMM2
- pxor (%arg1), \XMM3
- pxor (%arg1), \XMM4
- movdqu HashKey_4_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0)
- movaps 0x10(%arg1), \TMP1
- aesenc \TMP1, \XMM1 # Round 1
- aesenc \TMP1, \XMM2
- aesenc \TMP1, \XMM3
- aesenc \TMP1, \XMM4
- movaps 0x20(%arg1), \TMP1
- aesenc \TMP1, \XMM1 # Round 2
- aesenc \TMP1, \XMM2
- aesenc \TMP1, \XMM3
- aesenc \TMP1, \XMM4
- movdqa \XMM6, \TMP1
- pshufd $78, \XMM6, \TMP2
- pxor \XMM6, \TMP2
- movdqu HashKey_3(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1 * b1
- movaps 0x30(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 3
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pclmulqdq $0x00, \TMP5, \XMM6 # XMM6 = a0*b0
- movaps 0x40(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 4
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- movdqu HashKey_3_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- movaps 0x50(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 5
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pxor \TMP1, \TMP4
-# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
- pxor \XMM6, \XMM5
- pxor \TMP2, \TMP6
- movdqa \XMM7, \TMP1
- pshufd $78, \XMM7, \TMP2
- pxor \XMM7, \TMP2
- movdqu HashKey_2(%arg2), \TMP5
-
- # Multiply TMP5 * HashKey using karatsuba
-
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1*b1
- movaps 0x60(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 6
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pclmulqdq $0x00, \TMP5, \XMM7 # XMM7 = a0*b0
- movaps 0x70(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 7
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- movdqu HashKey_2_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- movaps 0x80(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 8
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pxor \TMP1, \TMP4
-# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
- pxor \XMM7, \XMM5
- pxor \TMP2, \TMP6
-
- # Multiply XMM8 * HashKey
- # XMM8 and TMP5 hold the values for the two operands
-
- movdqa \XMM8, \TMP1
- pshufd $78, \XMM8, \TMP2
- pxor \XMM8, \TMP2
- movdqu HashKey(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1*b1
- movaps 0x90(%arg1), \TMP3
- aesenc \TMP3, \XMM1 # Round 9
- aesenc \TMP3, \XMM2
- aesenc \TMP3, \XMM3
- aesenc \TMP3, \XMM4
- pclmulqdq $0x00, \TMP5, \XMM8 # XMM8 = a0*b0
- lea 0xa0(%arg1),%r10
- mov keysize,%eax
- shr $2,%eax # 128->4, 192->6, 256->8
- sub $4,%eax # 128->0, 192->2, 256->4
- jz .Laes_loop_par_dec_done\@
-
-.Laes_loop_par_dec\@:
- MOVADQ (%r10),\TMP3
-.irpc index, 1234
- aesenc \TMP3, %xmm\index
-.endr
- add $16,%r10
- sub $1,%eax
- jnz .Laes_loop_par_dec\@
-
-.Laes_loop_par_dec_done\@:
- MOVADQ (%r10), \TMP3
- aesenclast \TMP3, \XMM1 # last round
- aesenclast \TMP3, \XMM2
- aesenclast \TMP3, \XMM3
- aesenclast \TMP3, \XMM4
- movdqu HashKey_k(%arg2), \TMP5
- pclmulqdq $0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- movdqu (%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK
- movdqu \XMM1, (%arg3,%r11,1) # Write to plaintext buffer
- movdqa \TMP3, \XMM1
- movdqu 16(%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM2 # Ciphertext/Plaintext XOR EK
- movdqu \XMM2, 16(%arg3,%r11,1) # Write to plaintext buffer
- movdqa \TMP3, \XMM2
- movdqu 32(%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM3 # Ciphertext/Plaintext XOR EK
- movdqu \XMM3, 32(%arg3,%r11,1) # Write to plaintext buffer
- movdqa \TMP3, \XMM3
- movdqu 48(%arg4,%r11,1), \TMP3
- pxor \TMP3, \XMM4 # Ciphertext/Plaintext XOR EK
- movdqu \XMM4, 48(%arg3,%r11,1) # Write to plaintext buffer
- movdqa \TMP3, \XMM4
- pshufb %xmm15, \XMM1 # perform a 16 byte swap
- pshufb %xmm15, \XMM2 # perform a 16 byte swap
- pshufb %xmm15, \XMM3 # perform a 16 byte swap
- pshufb %xmm15, \XMM4 # perform a 16 byte swap
-
- pxor \TMP4, \TMP1
- pxor \XMM8, \XMM5
- pxor \TMP6, \TMP2
- pxor \TMP1, \TMP2
- pxor \XMM5, \TMP2
- movdqa \TMP2, \TMP3
- pslldq $8, \TMP3 # left shift TMP3 2 DWs
- psrldq $8, \TMP2 # right shift TMP2 2 DWs
- pxor \TMP3, \XMM5
- pxor \TMP2, \TMP1 # accumulate the results in TMP1:XMM5
-
- # first phase of reduction
-
- movdqa \XMM5, \TMP2
- movdqa \XMM5, \TMP3
- movdqa \XMM5, \TMP4
-# move XMM5 into TMP2, TMP3, TMP4 in order to perform shifts independently
- pslld $31, \TMP2 # packed right shift << 31
- pslld $30, \TMP3 # packed right shift << 30
- pslld $25, \TMP4 # packed right shift << 25
- pxor \TMP3, \TMP2 # xor the shifted versions
- pxor \TMP4, \TMP2
- movdqa \TMP2, \TMP5
- psrldq $4, \TMP5 # right shift T5 1 DW
- pslldq $12, \TMP2 # left shift T2 3 DWs
- pxor \TMP2, \XMM5
-
- # second phase of reduction
-
- movdqa \XMM5,\TMP2 # make 3 copies of XMM5 into TMP2, TMP3, TMP4
- movdqa \XMM5,\TMP3
- movdqa \XMM5,\TMP4
- psrld $1, \TMP2 # packed left shift >>1
- psrld $2, \TMP3 # packed left shift >>2
- psrld $7, \TMP4 # packed left shift >>7
- pxor \TMP3,\TMP2 # xor the shifted versions
- pxor \TMP4,\TMP2
- pxor \TMP5, \TMP2
- pxor \TMP2, \XMM5
- pxor \TMP1, \XMM5 # result is in TMP1
-
- pxor \XMM5, \XMM1
-.endm
-
-/* GHASH the last 4 ciphertext blocks. */
-.macro GHASH_LAST_4 TMP1 TMP2 TMP3 TMP4 TMP5 TMP6 \
-TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
-
- # Multiply TMP6 * HashKey (using Karatsuba)
-
- movdqa \XMM1, \TMP6
- pshufd $78, \XMM1, \TMP2
- pxor \XMM1, \TMP2
- movdqu HashKey_4(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP6 # TMP6 = a1*b1
- pclmulqdq $0x00, \TMP5, \XMM1 # XMM1 = a0*b0
- movdqu HashKey_4_k(%arg2), \TMP4
- pclmulqdq $0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- movdqa \XMM1, \XMMDst
- movdqa \TMP2, \XMM1 # result in TMP6, XMMDst, XMM1
-
- # Multiply TMP1 * HashKey (using Karatsuba)
-
- movdqa \XMM2, \TMP1
- pshufd $78, \XMM2, \TMP2
- pxor \XMM2, \TMP2
- movdqu HashKey_3(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1*b1
- pclmulqdq $0x00, \TMP5, \XMM2 # XMM2 = a0*b0
- movdqu HashKey_3_k(%arg2), \TMP4
- pclmulqdq $0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- pxor \TMP1, \TMP6
- pxor \XMM2, \XMMDst
- pxor \TMP2, \XMM1
-# results accumulated in TMP6, XMMDst, XMM1
-
- # Multiply TMP1 * HashKey (using Karatsuba)
-
- movdqa \XMM3, \TMP1
- pshufd $78, \XMM3, \TMP2
- pxor \XMM3, \TMP2
- movdqu HashKey_2(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1*b1
- pclmulqdq $0x00, \TMP5, \XMM3 # XMM3 = a0*b0
- movdqu HashKey_2_k(%arg2), \TMP4
- pclmulqdq $0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- pxor \TMP1, \TMP6
- pxor \XMM3, \XMMDst
- pxor \TMP2, \XMM1 # results accumulated in TMP6, XMMDst, XMM1
-
- # Multiply TMP1 * HashKey (using Karatsuba)
- movdqa \XMM4, \TMP1
- pshufd $78, \XMM4, \TMP2
- pxor \XMM4, \TMP2
- movdqu HashKey(%arg2), \TMP5
- pclmulqdq $0x11, \TMP5, \TMP1 # TMP1 = a1*b1
- pclmulqdq $0x00, \TMP5, \XMM4 # XMM4 = a0*b0
- movdqu HashKey_k(%arg2), \TMP4
- pclmulqdq $0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
- pxor \TMP1, \TMP6
- pxor \XMM4, \XMMDst
- pxor \XMM1, \TMP2
- pxor \TMP6, \TMP2
- pxor \XMMDst, \TMP2
- # middle section of the temp results combined as in karatsuba algorithm
- movdqa \TMP2, \TMP4
- pslldq $8, \TMP4 # left shift TMP4 2 DWs
- psrldq $8, \TMP2 # right shift TMP2 2 DWs
- pxor \TMP4, \XMMDst
- pxor \TMP2, \TMP6
-# TMP6:XMMDst holds the result of the accumulated carry-less multiplications
- # first phase of the reduction
- movdqa \XMMDst, \TMP2
- movdqa \XMMDst, \TMP3
- movdqa \XMMDst, \TMP4
-# move XMMDst into TMP2, TMP3, TMP4 in order to perform 3 shifts independently
- pslld $31, \TMP2 # packed right shifting << 31
- pslld $30, \TMP3 # packed right shifting << 30
- pslld $25, \TMP4 # packed right shifting << 25
- pxor \TMP3, \TMP2 # xor the shifted versions
- pxor \TMP4, \TMP2
- movdqa \TMP2, \TMP7
- psrldq $4, \TMP7 # right shift TMP7 1 DW
- pslldq $12, \TMP2 # left shift TMP2 3 DWs
- pxor \TMP2, \XMMDst
-
- # second phase of the reduction
- movdqa \XMMDst, \TMP2
- # make 3 copies of XMMDst for doing 3 shift operations
- movdqa \XMMDst, \TMP3
- movdqa \XMMDst, \TMP4
- psrld $1, \TMP2 # packed left shift >> 1
- psrld $2, \TMP3 # packed left shift >> 2
- psrld $7, \TMP4 # packed left shift >> 7
- pxor \TMP3, \TMP2 # xor the shifted versions
- pxor \TMP4, \TMP2
- pxor \TMP7, \TMP2
- pxor \TMP2, \XMMDst
- pxor \TMP6, \XMMDst # reduced result is in XMMDst
-.endm
-
-
-/* Encryption of a single block
-* uses eax & r10
-*/
-
-.macro ENCRYPT_SINGLE_BLOCK XMM0 TMP1
-
- pxor (%arg1), \XMM0
- mov keysize,%eax
- shr $2,%eax # 128->4, 192->6, 256->8
- add $5,%eax # 128->9, 192->11, 256->13
- lea 16(%arg1), %r10 # get first expanded key address
-
-_esb_loop_\@:
- MOVADQ (%r10),\TMP1
- aesenc \TMP1,\XMM0
- add $16,%r10
- sub $1,%eax
- jnz _esb_loop_\@
-
- MOVADQ (%r10),\TMP1
- aesenclast \TMP1,\XMM0
-.endm
-
-/*****************************************************************************
-* void aesni_gcm_init(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary.
-* struct gcm_context_data *data,
-* // context data
-* u8 *iv, // Pre-counter block j0: 4 byte salt (from Security Association)
-* // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload)
-* // concatenated with 0x00000001. 16-byte aligned pointer.
-* u8 *hash_subkey, // H, the Hash sub key input. Data starts on a 16-byte boundary.
-* const u8 *aad, // Additional Authentication Data (AAD)
-* u64 aad_len) // Length of AAD in bytes.
-*/
-SYM_FUNC_START(aesni_gcm_init)
- FUNC_SAVE
- GCM_INIT %arg3, %arg4,%arg5, %arg6
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_init)
-
-/*****************************************************************************
-* void aesni_gcm_enc_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary.
-* struct gcm_context_data *data,
-* // context data
-* u8 *out, // Ciphertext output. Encrypt in-place is allowed.
-* const u8 *in, // Plaintext input
-* u64 plaintext_len, // Length of data in bytes for encryption.
-*/
-SYM_FUNC_START(aesni_gcm_enc_update)
- FUNC_SAVE
- GCM_ENC_DEC enc
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_enc_update)
-
-/*****************************************************************************
-* void aesni_gcm_dec_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary.
-* struct gcm_context_data *data,
-* // context data
-* u8 *out, // Ciphertext output. Encrypt in-place is allowed.
-* const u8 *in, // Plaintext input
-* u64 plaintext_len, // Length of data in bytes for encryption.
-*/
-SYM_FUNC_START(aesni_gcm_dec_update)
- FUNC_SAVE
- GCM_ENC_DEC dec
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_dec_update)
-
-/*****************************************************************************
-* void aesni_gcm_finalize(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary.
-* struct gcm_context_data *data,
-* // context data
-* u8 *auth_tag, // Authenticated Tag output.
-* u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16 (most likely),
-* // 12 or 8.
-*/
-SYM_FUNC_START(aesni_gcm_finalize)
- FUNC_SAVE
- GCM_COMPLETE %arg3 %arg4
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_finalize)
-
-#endif
-
SYM_FUNC_START_LOCAL(_key_expansion_256a)
pshufd $0b11111111, %xmm1, %xmm1
shufps $0b00010000, %xmm0, %xmm4
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
deleted file mode 100644
index 8c9749ed0651..000000000000
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ /dev/null
@@ -1,2804 +0,0 @@
-########################################################################
-# Copyright (c) 2013, Intel Corporation
-#
-# This software is available to you under a choice of one of two
-# licenses. You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions are
-# met:
-#
-# * Redistributions of source code must retain the above copyright
-# notice, this list of conditions and the following disclaimer.
-#
-# * Redistributions in binary form must reproduce the above copyright
-# notice, this list of conditions and the following disclaimer in the
-# documentation and/or other materials provided with the
-# distribution.
-#
-# * Neither the name of the Intel Corporation nor the names of its
-# contributors may be used to endorse or promote products derived from
-# this software without specific prior written permission.
-#
-#
-# THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
-# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
-# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES# LOSS OF USE, DATA, OR
-# PROFITS# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
-# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
-# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-########################################################################
-##
-## Authors:
-## Erdinc Ozturk <erdinc.ozturk@intel.com>
-## Vinodh Gopal <vinodh.gopal@intel.com>
-## James Guilford <james.guilford@intel.com>
-## Tim Chen <tim.c.chen@linux.intel.com>
-##
-## References:
-## This code was derived and highly optimized from the code described in paper:
-## Vinodh Gopal et. al. Optimized Galois-Counter-Mode Implementation
-## on Intel Architecture Processors. August, 2010
-## The details of the implementation is explained in:
-## Erdinc Ozturk et. al. Enabling High-Performance Galois-Counter-Mode
-## on Intel Architecture Processors. October, 2012.
-##
-## Assumptions:
-##
-##
-##
-## iv:
-## 0 1 2 3
-## 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | Salt (From the SA) |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | Initialization Vector |
-## | (This is the sequence number from IPSec header) |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | 0x1 |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-##
-##
-##
-## AAD:
-## AAD padded to 128 bits with 0
-## for example, assume AAD is a u32 vector
-##
-## if AAD is 8 bytes:
-## AAD[3] = {A0, A1}#
-## padded AAD in xmm register = {A1 A0 0 0}
-##
-## 0 1 2 3
-## 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | SPI (A1) |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | 32-bit Sequence Number (A0) |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | 0x0 |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-##
-## AAD Format with 32-bit Sequence Number
-##
-## if AAD is 12 bytes:
-## AAD[3] = {A0, A1, A2}#
-## padded AAD in xmm register = {A2 A1 A0 0}
-##
-## 0 1 2 3
-## 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | SPI (A2) |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | 64-bit Extended Sequence Number {A1,A0} |
-## | |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-## | 0x0 |
-## +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-##
-## AAD Format with 64-bit Extended Sequence Number
-##
-##
-## aadLen:
-## from the definition of the spec, aadLen can only be 8 or 12 bytes.
-## The code additionally supports aadLen of length 16 bytes.
-##
-## TLen:
-## from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
-##
-## poly = x^128 + x^127 + x^126 + x^121 + 1
-## throughout the code, one tab and two tab indentations are used. one tab is
-## for GHASH part, two tabs is for AES part.
-##
-
-#include <linux/linkage.h>
-
-# constants in mergeable sections, linker can reorder and merge
-.section .rodata.cst16.POLY, "aM", @progbits, 16
-.align 16
-POLY: .octa 0xC2000000000000000000000000000001
-
-.section .rodata.cst16.POLY2, "aM", @progbits, 16
-.align 16
-POLY2: .octa 0xC20000000000000000000001C2000000
-
-.section .rodata.cst16.TWOONE, "aM", @progbits, 16
-.align 16
-TWOONE: .octa 0x00000001000000000000000000000001
-
-.section .rodata.cst16.SHUF_MASK, "aM", @progbits, 16
-.align 16
-SHUF_MASK: .octa 0x000102030405060708090A0B0C0D0E0F
-
-.section .rodata.cst16.ONE, "aM", @progbits, 16
-.align 16
-ONE: .octa 0x00000000000000000000000000000001
-
-.section .rodata.cst16.ONEf, "aM", @progbits, 16
-.align 16
-ONEf: .octa 0x01000000000000000000000000000000
-
-# order of these constants should not change.
-# more specifically, ALL_F should follow SHIFT_MASK, and zero should follow ALL_F
-.section .rodata, "a", @progbits
-.align 16
-SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100
-ALL_F: .octa 0xffffffffffffffffffffffffffffffff
- .octa 0x00000000000000000000000000000000
-
-.text
-
-
-#define AadHash 16*0
-#define AadLen 16*1
-#define InLen (16*1)+8
-#define PBlockEncKey 16*2
-#define OrigIV 16*3
-#define CurCount 16*4
-#define PBlockLen 16*5
-
-HashKey = 16*6 # store HashKey <<1 mod poly here
-HashKey_2 = 16*7 # store HashKey^2 <<1 mod poly here
-HashKey_3 = 16*8 # store HashKey^3 <<1 mod poly here
-HashKey_4 = 16*9 # store HashKey^4 <<1 mod poly here
-HashKey_5 = 16*10 # store HashKey^5 <<1 mod poly here
-HashKey_6 = 16*11 # store HashKey^6 <<1 mod poly here
-HashKey_7 = 16*12 # store HashKey^7 <<1 mod poly here
-HashKey_8 = 16*13 # store HashKey^8 <<1 mod poly here
-HashKey_k = 16*14 # store XOR of HashKey <<1 mod poly here (for Karatsuba purposes)
-HashKey_2_k = 16*15 # store XOR of HashKey^2 <<1 mod poly here (for Karatsuba purposes)
-HashKey_3_k = 16*16 # store XOR of HashKey^3 <<1 mod poly here (for Karatsuba purposes)
-HashKey_4_k = 16*17 # store XOR of HashKey^4 <<1 mod poly here (for Karatsuba purposes)
-HashKey_5_k = 16*18 # store XOR of HashKey^5 <<1 mod poly here (for Karatsuba purposes)
-HashKey_6_k = 16*19 # store XOR of HashKey^6 <<1 mod poly here (for Karatsuba purposes)
-HashKey_7_k = 16*20 # store XOR of HashKey^7 <<1 mod poly here (for Karatsuba purposes)
-HashKey_8_k = 16*21 # store XOR of HashKey^8 <<1 mod poly here (for Karatsuba purposes)
-
-#define arg1 %rdi
-#define arg2 %rsi
-#define arg3 %rdx
-#define arg4 %rcx
-#define arg5 %r8
-#define arg6 %r9
-#define keysize 2*15*16(arg1)
-
-i = 0
-j = 0
-
-out_order = 0
-in_order = 1
-DEC = 0
-ENC = 1
-
-.macro define_reg r n
-reg_\r = %xmm\n
-.endm
-
-.macro setreg
-.altmacro
-define_reg i %i
-define_reg j %j
-.noaltmacro
-.endm
-
-TMP1 = 16*0 # Temporary storage for AAD
-TMP2 = 16*1 # Temporary storage for AES State 2 (State 1 is stored in an XMM register)
-TMP3 = 16*2 # Temporary storage for AES State 3
-TMP4 = 16*3 # Temporary storage for AES State 4
-TMP5 = 16*4 # Temporary storage for AES State 5
-TMP6 = 16*5 # Temporary storage for AES State 6
-TMP7 = 16*6 # Temporary storage for AES State 7
-TMP8 = 16*7 # Temporary storage for AES State 8
-
-VARIABLE_OFFSET = 16*8
-
-################################
-# Utility Macros
-################################
-
-.macro FUNC_SAVE
- push %r12
- push %r13
- push %r15
-
- push %rbp
- mov %rsp, %rbp
-
- sub $VARIABLE_OFFSET, %rsp
- and $~63, %rsp # align rsp to 64 bytes
-.endm
-
-.macro FUNC_RESTORE
- mov %rbp, %rsp
- pop %rbp
-
- pop %r15
- pop %r13
- pop %r12
-.endm
-
-# Encryption of a single block
-.macro ENCRYPT_SINGLE_BLOCK REP XMM0
- vpxor (arg1), \XMM0, \XMM0
- i = 1
- setreg
-.rep \REP
- vaesenc 16*i(arg1), \XMM0, \XMM0
- i = (i+1)
- setreg
-.endr
- vaesenclast 16*i(arg1), \XMM0, \XMM0
-.endm
-
-# combined for GCM encrypt and decrypt functions
-# clobbering all xmm registers
-# clobbering r10, r11, r12, r13, r15, rax
-.macro GCM_ENC_DEC INITIAL_BLOCKS GHASH_8_ENCRYPT_8_PARALLEL GHASH_LAST_8 GHASH_MUL ENC_DEC REP
- vmovdqu AadHash(arg2), %xmm8
- vmovdqu HashKey(arg2), %xmm13 # xmm13 = HashKey
- add arg5, InLen(arg2)
-
- # initialize the data pointer offset as zero
- xor %r11d, %r11d
-
- PARTIAL_BLOCK \GHASH_MUL, arg3, arg4, arg5, %r11, %xmm8, \ENC_DEC
- sub %r11, arg5
-
- mov arg5, %r13 # save the number of bytes of plaintext/ciphertext
- and $-16, %r13 # r13 = r13 - (r13 mod 16)
-
- mov %r13, %r12
- shr $4, %r12
- and $7, %r12
- jz .L_initial_num_blocks_is_0\@
-
- cmp $7, %r12
- je .L_initial_num_blocks_is_7\@
- cmp $6, %r12
- je .L_initial_num_blocks_is_6\@
- cmp $5, %r12
- je .L_initial_num_blocks_is_5\@
- cmp $4, %r12
- je .L_initial_num_blocks_is_4\@
- cmp $3, %r12
- je .L_initial_num_blocks_is_3\@
- cmp $2, %r12
- je .L_initial_num_blocks_is_2\@
-
- jmp .L_initial_num_blocks_is_1\@
-
-.L_initial_num_blocks_is_7\@:
- \INITIAL_BLOCKS \REP, 7, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*7, %r13
- jmp .L_initial_blocks_encrypted\@
-
-.L_initial_num_blocks_is_6\@:
- \INITIAL_BLOCKS \REP, 6, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*6, %r13
- jmp .L_initial_blocks_encrypted\@
-
-.L_initial_num_blocks_is_5\@:
- \INITIAL_BLOCKS \REP, 5, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*5, %r13
- jmp .L_initial_blocks_encrypted\@
-
-.L_initial_num_blocks_is_4\@:
- \INITIAL_BLOCKS \REP, 4, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*4, %r13
- jmp .L_initial_blocks_encrypted\@
-
-.L_initial_num_blocks_is_3\@:
- \INITIAL_BLOCKS \REP, 3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*3, %r13
- jmp .L_initial_blocks_encrypted\@
-
-.L_initial_num_blocks_is_2\@:
- \INITIAL_BLOCKS \REP, 2, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*2, %r13
- jmp .L_initial_blocks_encrypted\@
-
-.L_initial_num_blocks_is_1\@:
- \INITIAL_BLOCKS \REP, 1, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
- sub $16*1, %r13
- jmp .L_initial_blocks_encrypted\@
-
-.L_initial_num_blocks_is_0\@:
- \INITIAL_BLOCKS \REP, 0, %xmm12, %xmm13, %xmm14, %xmm15, %xmm11, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm10, %xmm0, \ENC_DEC
-
-
-.L_initial_blocks_encrypted\@:
- test %r13, %r13
- je .L_zero_cipher_left\@
-
- sub $128, %r13
- je .L_eight_cipher_left\@
-
-
-
-
- vmovd %xmm9, %r15d
- and $255, %r15d
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
-
-
-.L_encrypt_by_8_new\@:
- cmp $(255-8), %r15d
- jg .L_encrypt_by_8\@
-
-
-
- add $8, %r15b
- \GHASH_8_ENCRYPT_8_PARALLEL \REP, %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, out_order, \ENC_DEC
- add $128, %r11
- sub $128, %r13
- jne .L_encrypt_by_8_new\@
-
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- jmp .L_eight_cipher_left\@
-
-.L_encrypt_by_8\@:
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- add $8, %r15b
- \GHASH_8_ENCRYPT_8_PARALLEL \REP, %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm9, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm15, in_order, \ENC_DEC
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- add $128, %r11
- sub $128, %r13
- jne .L_encrypt_by_8_new\@
-
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
-
-
-
-
-.L_eight_cipher_left\@:
- \GHASH_LAST_8 %xmm0, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8
-
-
-.L_zero_cipher_left\@:
- vmovdqu %xmm14, AadHash(arg2)
- vmovdqu %xmm9, CurCount(arg2)
-
- # check for 0 length
- mov arg5, %r13
- and $15, %r13 # r13 = (arg5 mod 16)
-
- je .L_multiple_of_16_bytes\@
-
- # handle the last <16 Byte block separately
-
- mov %r13, PBlockLen(arg2)
-
- vpaddd ONE(%rip), %xmm9, %xmm9 # INCR CNT to get Yn
- vmovdqu %xmm9, CurCount(arg2)
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
-
- ENCRYPT_SINGLE_BLOCK \REP, %xmm9 # E(K, Yn)
- vmovdqu %xmm9, PBlockEncKey(arg2)
-
- cmp $16, arg5
- jge .L_large_enough_update\@
-
- lea (arg4,%r11,1), %r10
- mov %r13, %r12
-
- READ_PARTIAL_BLOCK %r10 %r12 %xmm1
-
- lea SHIFT_MASK+16(%rip), %r12
- sub %r13, %r12 # adjust the shuffle mask pointer to be
- # able to shift 16-r13 bytes (r13 is the
- # number of bytes in plaintext mod 16)
-
- jmp .L_final_ghash_mul\@
-
-.L_large_enough_update\@:
- sub $16, %r11
- add %r13, %r11
-
- # receive the last <16 Byte block
- vmovdqu (arg4, %r11, 1), %xmm1
-
- sub %r13, %r11
- add $16, %r11
-
- lea SHIFT_MASK+16(%rip), %r12
- # adjust the shuffle mask pointer to be able to shift 16-r13 bytes
- # (r13 is the number of bytes in plaintext mod 16)
- sub %r13, %r12
- # get the appropriate shuffle mask
- vmovdqu (%r12), %xmm2
- # shift right 16-r13 bytes
- vpshufb %xmm2, %xmm1, %xmm1
-
-.L_final_ghash_mul\@:
- .if \ENC_DEC == DEC
- vmovdqa %xmm1, %xmm2
- vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
- # mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm2, %xmm2
- vpshufb SHUF_MASK(%rip), %xmm2, %xmm2
- vpxor %xmm2, %xmm14, %xmm14
-
- vmovdqu %xmm14, AadHash(arg2)
- .else
- vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1 # get the appropriate mask to
- # mask out top 16-r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9 # mask out top 16-r13 bytes of xmm9
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9
- vpxor %xmm9, %xmm14, %xmm14
-
- vmovdqu %xmm14, AadHash(arg2)
- vpshufb SHUF_MASK(%rip), %xmm9, %xmm9 # shuffle xmm9 back to output as ciphertext
- .endif
-
-
- #############################
- # output r13 Bytes
- vmovq %xmm9, %rax
- cmp $8, %r13
- jle .L_less_than_8_bytes_left\@
-
- mov %rax, (arg3 , %r11)
- add $8, %r11
- vpsrldq $8, %xmm9, %xmm9
- vmovq %xmm9, %rax
- sub $8, %r13
-
-.L_less_than_8_bytes_left\@:
- movb %al, (arg3 , %r11)
- add $1, %r11
- shr $8, %rax
- sub $1, %r13
- jne .L_less_than_8_bytes_left\@
- #############################
-
-.L_multiple_of_16_bytes\@:
-.endm
-
-
-# GCM_COMPLETE Finishes update of tag of last partial block
-# Output: Authorization Tag (AUTH_TAG)
-# Clobbers rax, r10-r12, and xmm0, xmm1, xmm5-xmm15
-.macro GCM_COMPLETE GHASH_MUL REP AUTH_TAG AUTH_TAG_LEN
- vmovdqu AadHash(arg2), %xmm14
- vmovdqu HashKey(arg2), %xmm13
-
- mov PBlockLen(arg2), %r12
- test %r12, %r12
- je .L_partial_done\@
-
- #GHASH computation for the last <16 Byte block
- \GHASH_MUL %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
-
-.L_partial_done\@:
- mov AadLen(arg2), %r12 # r12 = aadLen (number of bytes)
- shl $3, %r12 # convert into number of bits
- vmovd %r12d, %xmm15 # len(A) in xmm15
-
- mov InLen(arg2), %r12
- shl $3, %r12 # len(C) in bits (*128)
- vmovq %r12, %xmm1
- vpslldq $8, %xmm15, %xmm15 # xmm15 = len(A)|| 0x0000000000000000
- vpxor %xmm1, %xmm15, %xmm15 # xmm15 = len(A)||len(C)
-
- vpxor %xmm15, %xmm14, %xmm14
- \GHASH_MUL %xmm14, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6 # final GHASH computation
- vpshufb SHUF_MASK(%rip), %xmm14, %xmm14 # perform a 16Byte swap
-
- vmovdqu OrigIV(arg2), %xmm9
-
- ENCRYPT_SINGLE_BLOCK \REP, %xmm9 # E(K, Y0)
-
- vpxor %xmm14, %xmm9, %xmm9
-
-
-
-.L_return_T\@:
- mov \AUTH_TAG, %r10 # r10 = authTag
- mov \AUTH_TAG_LEN, %r11 # r11 = auth_tag_len
-
- cmp $16, %r11
- je .L_T_16\@
-
- cmp $8, %r11
- jl .L_T_4\@
-
-.L_T_8\@:
- vmovq %xmm9, %rax
- mov %rax, (%r10)
- add $8, %r10
- sub $8, %r11
- vpsrldq $8, %xmm9, %xmm9
- test %r11, %r11
- je .L_return_T_done\@
-.L_T_4\@:
- vmovd %xmm9, %eax
- mov %eax, (%r10)
- add $4, %r10
- sub $4, %r11
- vpsrldq $4, %xmm9, %xmm9
- test %r11, %r11
- je .L_return_T_done\@
-.L_T_123\@:
- vmovd %xmm9, %eax
- cmp $2, %r11
- jl .L_T_1\@
- mov %ax, (%r10)
- cmp $2, %r11
- je .L_return_T_done\@
- add $2, %r10
- sar $16, %eax
-.L_T_1\@:
- mov %al, (%r10)
- jmp .L_return_T_done\@
-
-.L_T_16\@:
- vmovdqu %xmm9, (%r10)
-
-.L_return_T_done\@:
-.endm
-
-.macro CALC_AAD_HASH GHASH_MUL AAD AADLEN T1 T2 T3 T4 T5 T6 T7 T8
-
- mov \AAD, %r10 # r10 = AAD
- mov \AADLEN, %r12 # r12 = aadLen
-
-
- mov %r12, %r11
-
- vpxor \T8, \T8, \T8
- vpxor \T7, \T7, \T7
- cmp $16, %r11
- jl .L_get_AAD_rest8\@
-.L_get_AAD_blocks\@:
- vmovdqu (%r10), \T7
- vpshufb SHUF_MASK(%rip), \T7, \T7
- vpxor \T7, \T8, \T8
- \GHASH_MUL \T8, \T2, \T1, \T3, \T4, \T5, \T6
- add $16, %r10
- sub $16, %r12
- sub $16, %r11
- cmp $16, %r11
- jge .L_get_AAD_blocks\@
- vmovdqu \T8, \T7
- test %r11, %r11
- je .L_get_AAD_done\@
-
- vpxor \T7, \T7, \T7
-
- /* read the last <16B of AAD. since we have at least 4B of
- data right after the AAD (the ICV, and maybe some CT), we can
- read 4B/8B blocks safely, and then get rid of the extra stuff */
-.L_get_AAD_rest8\@:
- cmp $4, %r11
- jle .L_get_AAD_rest4\@
- movq (%r10), \T1
- add $8, %r10
- sub $8, %r11
- vpslldq $8, \T1, \T1
- vpsrldq $8, \T7, \T7
- vpxor \T1, \T7, \T7
- jmp .L_get_AAD_rest8\@
-.L_get_AAD_rest4\@:
- test %r11, %r11
- jle .L_get_AAD_rest0\@
- mov (%r10), %eax
- movq %rax, \T1
- add $4, %r10
- sub $4, %r11
- vpslldq $12, \T1, \T1
- vpsrldq $4, \T7, \T7
- vpxor \T1, \T7, \T7
-.L_get_AAD_rest0\@:
- /* finalize: shift out the extra bytes we read, and align
- left. since pslldq can only shift by an immediate, we use
- vpshufb and a pair of shuffle masks */
- leaq ALL_F(%rip), %r11
- subq %r12, %r11
- vmovdqu 16(%r11), \T1
- andq $~3, %r11
- vpshufb (%r11), \T7, \T7
- vpand \T1, \T7, \T7
-.L_get_AAD_rest_final\@:
- vpshufb SHUF_MASK(%rip), \T7, \T7
- vpxor \T8, \T7, \T7
- \GHASH_MUL \T7, \T2, \T1, \T3, \T4, \T5, \T6
-
-.L_get_AAD_done\@:
- vmovdqu \T7, AadHash(arg2)
-.endm
-
-.macro INIT GHASH_MUL PRECOMPUTE
- mov arg6, %r11
- mov %r11, AadLen(arg2) # ctx_data.aad_length = aad_length
- xor %r11d, %r11d
- mov %r11, InLen(arg2) # ctx_data.in_length = 0
-
- mov %r11, PBlockLen(arg2) # ctx_data.partial_block_length = 0
- mov %r11, PBlockEncKey(arg2) # ctx_data.partial_block_enc_key = 0
- mov arg3, %rax
- movdqu (%rax), %xmm0
- movdqu %xmm0, OrigIV(arg2) # ctx_data.orig_IV = iv
-
- vpshufb SHUF_MASK(%rip), %xmm0, %xmm0
- movdqu %xmm0, CurCount(arg2) # ctx_data.current_counter = iv
-
- vmovdqu (arg4), %xmm6 # xmm6 = HashKey
-
- vpshufb SHUF_MASK(%rip), %xmm6, %xmm6
- ############### PRECOMPUTATION of HashKey<<1 mod poly from the HashKey
- vmovdqa %xmm6, %xmm2
- vpsllq $1, %xmm6, %xmm6
- vpsrlq $63, %xmm2, %xmm2
- vmovdqa %xmm2, %xmm1
- vpslldq $8, %xmm2, %xmm2
- vpsrldq $8, %xmm1, %xmm1
- vpor %xmm2, %xmm6, %xmm6
- #reduction
- vpshufd $0b00100100, %xmm1, %xmm2
- vpcmpeqd TWOONE(%rip), %xmm2, %xmm2
- vpand POLY(%rip), %xmm2, %xmm2
- vpxor %xmm2, %xmm6, %xmm6 # xmm6 holds the HashKey<<1 mod poly
- #######################################################################
- vmovdqu %xmm6, HashKey(arg2) # store HashKey<<1 mod poly
-
- CALC_AAD_HASH \GHASH_MUL, arg5, arg6, %xmm2, %xmm6, %xmm3, %xmm4, %xmm5, %xmm7, %xmm1, %xmm0
-
- \PRECOMPUTE %xmm6, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5
-.endm
-
-
-# Reads DLEN bytes starting at DPTR and stores in XMMDst
-# where 0 < DLEN < 16
-# Clobbers %rax, DLEN
-.macro READ_PARTIAL_BLOCK DPTR DLEN XMMDst
- vpxor \XMMDst, \XMMDst, \XMMDst
-
- cmp $8, \DLEN
- jl .L_read_lt8_\@
- mov (\DPTR), %rax
- vpinsrq $0, %rax, \XMMDst, \XMMDst
- sub $8, \DLEN
- jz .L_done_read_partial_block_\@
- xor %eax, %eax
-.L_read_next_byte_\@:
- shl $8, %rax
- mov 7(\DPTR, \DLEN, 1), %al
- dec \DLEN
- jnz .L_read_next_byte_\@
- vpinsrq $1, %rax, \XMMDst, \XMMDst
- jmp .L_done_read_partial_block_\@
-.L_read_lt8_\@:
- xor %eax, %eax
-.L_read_next_byte_lt8_\@:
- shl $8, %rax
- mov -1(\DPTR, \DLEN, 1), %al
- dec \DLEN
- jnz .L_read_next_byte_lt8_\@
- vpinsrq $0, %rax, \XMMDst, \XMMDst
-.L_done_read_partial_block_\@:
-.endm
-
-# PARTIAL_BLOCK: Handles encryption/decryption and the tag partial blocks
-# between update calls.
-# Requires the input data be at least 1 byte long due to READ_PARTIAL_BLOCK
-# Outputs encrypted bytes, and updates hash and partial info in gcm_data_context
-# Clobbers rax, r10, r12, r13, xmm0-6, xmm9-13
-.macro PARTIAL_BLOCK GHASH_MUL CYPH_PLAIN_OUT PLAIN_CYPH_IN PLAIN_CYPH_LEN DATA_OFFSET \
- AAD_HASH ENC_DEC
- mov PBlockLen(arg2), %r13
- test %r13, %r13
- je .L_partial_block_done_\@ # Leave Macro if no partial blocks
- # Read in input data without over reading
- cmp $16, \PLAIN_CYPH_LEN
- jl .L_fewer_than_16_bytes_\@
- vmovdqu (\PLAIN_CYPH_IN), %xmm1 # If more than 16 bytes, just fill xmm
- jmp .L_data_read_\@
-
-.L_fewer_than_16_bytes_\@:
- lea (\PLAIN_CYPH_IN, \DATA_OFFSET, 1), %r10
- mov \PLAIN_CYPH_LEN, %r12
- READ_PARTIAL_BLOCK %r10 %r12 %xmm1
-
- mov PBlockLen(arg2), %r13
-
-.L_data_read_\@: # Finished reading in data
-
- vmovdqu PBlockEncKey(arg2), %xmm9
- vmovdqu HashKey(arg2), %xmm13
-
- lea SHIFT_MASK(%rip), %r12
-
- # adjust the shuffle mask pointer to be able to shift r13 bytes
- # r16-r13 is the number of bytes in plaintext mod 16)
- add %r13, %r12
- vmovdqu (%r12), %xmm2 # get the appropriate shuffle mask
- vpshufb %xmm2, %xmm9, %xmm9 # shift right r13 bytes
-
-.if \ENC_DEC == DEC
- vmovdqa %xmm1, %xmm3
- pxor %xmm1, %xmm9 # Ciphertext XOR E(K, Yn)
-
- mov \PLAIN_CYPH_LEN, %r10
- add %r13, %r10
- # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
- sub $16, %r10
- # Determine if partial block is not being filled and
- # shift mask accordingly
- jge .L_no_extra_mask_1_\@
- sub %r10, %r12
-.L_no_extra_mask_1_\@:
-
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1
- # get the appropriate mask to mask out bottom r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9 # mask out bottom r13 bytes of xmm9
-
- vpand %xmm1, %xmm3, %xmm3
- vmovdqa SHUF_MASK(%rip), %xmm10
- vpshufb %xmm10, %xmm3, %xmm3
- vpshufb %xmm2, %xmm3, %xmm3
- vpxor %xmm3, \AAD_HASH, \AAD_HASH
-
- test %r10, %r10
- jl .L_partial_incomplete_1_\@
-
- # GHASH computation for the last <16 Byte block
- \GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %eax,%eax
-
- mov %rax, PBlockLen(arg2)
- jmp .L_dec_done_\@
-.L_partial_incomplete_1_\@:
- add \PLAIN_CYPH_LEN, PBlockLen(arg2)
-.L_dec_done_\@:
- vmovdqu \AAD_HASH, AadHash(arg2)
-.else
- vpxor %xmm1, %xmm9, %xmm9 # Plaintext XOR E(K, Yn)
-
- mov \PLAIN_CYPH_LEN, %r10
- add %r13, %r10
- # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling
- sub $16, %r10
- # Determine if partial block is not being filled and
- # shift mask accordingly
- jge .L_no_extra_mask_2_\@
- sub %r10, %r12
-.L_no_extra_mask_2_\@:
-
- vmovdqu ALL_F-SHIFT_MASK(%r12), %xmm1
- # get the appropriate mask to mask out bottom r13 bytes of xmm9
- vpand %xmm1, %xmm9, %xmm9
-
- vmovdqa SHUF_MASK(%rip), %xmm1
- vpshufb %xmm1, %xmm9, %xmm9
- vpshufb %xmm2, %xmm9, %xmm9
- vpxor %xmm9, \AAD_HASH, \AAD_HASH
-
- test %r10, %r10
- jl .L_partial_incomplete_2_\@
-
- # GHASH computation for the last <16 Byte block
- \GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
- xor %eax,%eax
-
- mov %rax, PBlockLen(arg2)
- jmp .L_encode_done_\@
-.L_partial_incomplete_2_\@:
- add \PLAIN_CYPH_LEN, PBlockLen(arg2)
-.L_encode_done_\@:
- vmovdqu \AAD_HASH, AadHash(arg2)
-
- vmovdqa SHUF_MASK(%rip), %xmm10
- # shuffle xmm9 back to output as ciphertext
- vpshufb %xmm10, %xmm9, %xmm9
- vpshufb %xmm2, %xmm9, %xmm9
-.endif
- # output encrypted Bytes
- test %r10, %r10
- jl .L_partial_fill_\@
- mov %r13, %r12
- mov $16, %r13
- # Set r13 to be the number of bytes to write out
- sub %r12, %r13
- jmp .L_count_set_\@
-.L_partial_fill_\@:
- mov \PLAIN_CYPH_LEN, %r13
-.L_count_set_\@:
- vmovdqa %xmm9, %xmm0
- vmovq %xmm0, %rax
- cmp $8, %r13
- jle .L_less_than_8_bytes_left_\@
-
- mov %rax, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
- add $8, \DATA_OFFSET
- psrldq $8, %xmm0
- vmovq %xmm0, %rax
- sub $8, %r13
-.L_less_than_8_bytes_left_\@:
- movb %al, (\CYPH_PLAIN_OUT, \DATA_OFFSET, 1)
- add $1, \DATA_OFFSET
- shr $8, %rax
- sub $1, %r13
- jne .L_less_than_8_bytes_left_\@
-.L_partial_block_done_\@:
-.endm # PARTIAL_BLOCK
-
-###############################################################################
-# GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
-# Input: A and B (128-bits each, bit-reflected)
-# Output: C = A*B*x mod poly, (i.e. >>1 )
-# To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
-# GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
-###############################################################################
-.macro GHASH_MUL_AVX GH HK T1 T2 T3 T4 T5
-
- vpshufd $0b01001110, \GH, \T2
- vpshufd $0b01001110, \HK, \T3
- vpxor \GH , \T2, \T2 # T2 = (a1+a0)
- vpxor \HK , \T3, \T3 # T3 = (b1+b0)
-
- vpclmulqdq $0x11, \HK, \GH, \T1 # T1 = a1*b1
- vpclmulqdq $0x00, \HK, \GH, \GH # GH = a0*b0
- vpclmulqdq $0x00, \T3, \T2, \T2 # T2 = (a1+a0)*(b1+b0)
- vpxor \GH, \T2,\T2
- vpxor \T1, \T2,\T2 # T2 = a0*b1+a1*b0
-
- vpslldq $8, \T2,\T3 # shift-L T3 2 DWs
- vpsrldq $8, \T2,\T2 # shift-R T2 2 DWs
- vpxor \T3, \GH, \GH
- vpxor \T2, \T1, \T1 # <T1:GH> = GH x HK
-
- #first phase of the reduction
- vpslld $31, \GH, \T2 # packed right shifting << 31
- vpslld $30, \GH, \T3 # packed right shifting shift << 30
- vpslld $25, \GH, \T4 # packed right shifting shift << 25
-
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
-
- vpsrldq $4, \T2, \T5 # shift-R T5 1 DW
-
- vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
- vpxor \T2, \GH, \GH # first phase of the reduction complete
-
- #second phase of the reduction
-
- vpsrld $1,\GH, \T2 # packed left shifting >> 1
- vpsrld $2,\GH, \T3 # packed left shifting >> 2
- vpsrld $7,\GH, \T4 # packed left shifting >> 7
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
-
- vpxor \T5, \T2, \T2
- vpxor \T2, \GH, \GH
- vpxor \T1, \GH, \GH # the result is in GH
-
-
-.endm
-
-.macro PRECOMPUTE_AVX HK T1 T2 T3 T4 T5 T6
-
- # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
- vmovdqa \HK, \T5
-
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_k(arg2)
-
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
- vmovdqu \T5, HashKey_2(arg2) # [HashKey_2] = HashKey^2<<1 mod poly
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_2_k(arg2)
-
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
- vmovdqu \T5, HashKey_3(arg2)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_3_k(arg2)
-
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
- vmovdqu \T5, HashKey_4(arg2)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_4_k(arg2)
-
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
- vmovdqu \T5, HashKey_5(arg2)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_5_k(arg2)
-
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
- vmovdqu \T5, HashKey_6(arg2)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_6_k(arg2)
-
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
- vmovdqu \T5, HashKey_7(arg2)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_7_k(arg2)
-
- GHASH_MUL_AVX \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
- vmovdqu \T5, HashKey_8(arg2)
- vpshufd $0b01001110, \T5, \T1
- vpxor \T5, \T1, \T1
- vmovdqu \T1, HashKey_8_k(arg2)
-
-.endm
-
-## if a = number of total plaintext bytes
-## b = floor(a/16)
-## num_initial_blocks = b mod 4#
-## encrypt the initial num_initial_blocks blocks and apply ghash on the ciphertext
-## r10, r11, r12, rax are clobbered
-## arg1, arg2, arg3, arg4 are used as pointers only, not modified
-
-.macro INITIAL_BLOCKS_AVX REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC
- i = (8-\num_initial_blocks)
- setreg
- vmovdqu AadHash(arg2), reg_i
-
- # start AES for num_initial_blocks blocks
- vmovdqu CurCount(arg2), \CTR
-
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, reg_i
- vpshufb SHUF_MASK(%rip), reg_i, reg_i # perform a 16Byte swap
- i = (i+1)
- setreg
-.endr
-
- vmovdqa (arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vpxor \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
-
- j = 1
- setreg
-.rep \REP
- vmovdqa 16*j(arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vaesenc \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
-
- j = (j+1)
- setreg
-.endr
-
- vmovdqa 16*j(arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vaesenclast \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
-
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vmovdqu (arg4, %r11), \T1
- vpxor \T1, reg_i, reg_i
- vmovdqu reg_i, (arg3 , %r11) # write back ciphertext for num_initial_blocks blocks
- add $16, %r11
-.if \ENC_DEC == DEC
- vmovdqa \T1, reg_i
-.endif
- vpshufb SHUF_MASK(%rip), reg_i, reg_i # prepare ciphertext for GHASH computations
- i = (i+1)
- setreg
-.endr
-
-
- i = (8-\num_initial_blocks)
- j = (9-\num_initial_blocks)
- setreg
-
-.rep \num_initial_blocks
- vpxor reg_i, reg_j, reg_j
- GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
- i = (i+1)
- j = (j+1)
- setreg
-.endr
- # XMM8 has the combined result here
-
- vmovdqa \XMM8, TMP1(%rsp)
- vmovdqa \XMM8, \T3
-
- cmp $128, %r13
- jl .L_initial_blocks_done\@ # no need for precomputed constants
-
-###############################################################################
-# Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM1
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM2
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM3
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM4
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM5
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM6
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM7
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM8
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-
- vmovdqa (arg1), \T_key
- vpxor \T_key, \XMM1, \XMM1
- vpxor \T_key, \XMM2, \XMM2
- vpxor \T_key, \XMM3, \XMM3
- vpxor \T_key, \XMM4, \XMM4
- vpxor \T_key, \XMM5, \XMM5
- vpxor \T_key, \XMM6, \XMM6
- vpxor \T_key, \XMM7, \XMM7
- vpxor \T_key, \XMM8, \XMM8
-
- i = 1
- setreg
-.rep \REP # do REP rounds
- vmovdqa 16*i(arg1), \T_key
- vaesenc \T_key, \XMM1, \XMM1
- vaesenc \T_key, \XMM2, \XMM2
- vaesenc \T_key, \XMM3, \XMM3
- vaesenc \T_key, \XMM4, \XMM4
- vaesenc \T_key, \XMM5, \XMM5
- vaesenc \T_key, \XMM6, \XMM6
- vaesenc \T_key, \XMM7, \XMM7
- vaesenc \T_key, \XMM8, \XMM8
- i = (i+1)
- setreg
-.endr
-
- vmovdqa 16*i(arg1), \T_key
- vaesenclast \T_key, \XMM1, \XMM1
- vaesenclast \T_key, \XMM2, \XMM2
- vaesenclast \T_key, \XMM3, \XMM3
- vaesenclast \T_key, \XMM4, \XMM4
- vaesenclast \T_key, \XMM5, \XMM5
- vaesenclast \T_key, \XMM6, \XMM6
- vaesenclast \T_key, \XMM7, \XMM7
- vaesenclast \T_key, \XMM8, \XMM8
-
- vmovdqu (arg4, %r11), \T1
- vpxor \T1, \XMM1, \XMM1
- vmovdqu \XMM1, (arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM1
- .endif
-
- vmovdqu 16*1(arg4, %r11), \T1
- vpxor \T1, \XMM2, \XMM2
- vmovdqu \XMM2, 16*1(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM2
- .endif
-
- vmovdqu 16*2(arg4, %r11), \T1
- vpxor \T1, \XMM3, \XMM3
- vmovdqu \XMM3, 16*2(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM3
- .endif
-
- vmovdqu 16*3(arg4, %r11), \T1
- vpxor \T1, \XMM4, \XMM4
- vmovdqu \XMM4, 16*3(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM4
- .endif
-
- vmovdqu 16*4(arg4, %r11), \T1
- vpxor \T1, \XMM5, \XMM5
- vmovdqu \XMM5, 16*4(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM5
- .endif
-
- vmovdqu 16*5(arg4, %r11), \T1
- vpxor \T1, \XMM6, \XMM6
- vmovdqu \XMM6, 16*5(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM6
- .endif
-
- vmovdqu 16*6(arg4, %r11), \T1
- vpxor \T1, \XMM7, \XMM7
- vmovdqu \XMM7, 16*6(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM7
- .endif
-
- vmovdqu 16*7(arg4, %r11), \T1
- vpxor \T1, \XMM8, \XMM8
- vmovdqu \XMM8, 16*7(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM8
- .endif
-
- add $128, %r11
-
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpxor TMP1(%rsp), \XMM1, \XMM1 # combine GHASHed value with the corresponding ciphertext
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-
-###############################################################################
-
-.L_initial_blocks_done\@:
-
-.endm
-
-# encrypt 8 blocks at a time
-# ghash the 8 previously encrypted ciphertext blocks
-# arg1, arg2, arg3, arg4 are used as pointers only, not modified
-# r11 is the data offset value
-.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
-
- vmovdqa \XMM1, \T2
- vmovdqa \XMM2, TMP2(%rsp)
- vmovdqa \XMM3, TMP3(%rsp)
- vmovdqa \XMM4, TMP4(%rsp)
- vmovdqa \XMM5, TMP5(%rsp)
- vmovdqa \XMM6, TMP6(%rsp)
- vmovdqa \XMM7, TMP7(%rsp)
- vmovdqa \XMM8, TMP8(%rsp)
-
-.if \loop_idx == in_order
- vpaddd ONE(%rip), \CTR, \XMM1 # INCR CNT
- vpaddd ONE(%rip), \XMM1, \XMM2
- vpaddd ONE(%rip), \XMM2, \XMM3
- vpaddd ONE(%rip), \XMM3, \XMM4
- vpaddd ONE(%rip), \XMM4, \XMM5
- vpaddd ONE(%rip), \XMM5, \XMM6
- vpaddd ONE(%rip), \XMM6, \XMM7
- vpaddd ONE(%rip), \XMM7, \XMM8
- vmovdqa \XMM8, \CTR
-
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-.else
- vpaddd ONEf(%rip), \CTR, \XMM1 # INCR CNT
- vpaddd ONEf(%rip), \XMM1, \XMM2
- vpaddd ONEf(%rip), \XMM2, \XMM3
- vpaddd ONEf(%rip), \XMM3, \XMM4
- vpaddd ONEf(%rip), \XMM4, \XMM5
- vpaddd ONEf(%rip), \XMM5, \XMM6
- vpaddd ONEf(%rip), \XMM6, \XMM7
- vpaddd ONEf(%rip), \XMM7, \XMM8
- vmovdqa \XMM8, \CTR
-.endif
-
-
- #######################################################################
-
- vmovdqu (arg1), \T1
- vpxor \T1, \XMM1, \XMM1
- vpxor \T1, \XMM2, \XMM2
- vpxor \T1, \XMM3, \XMM3
- vpxor \T1, \XMM4, \XMM4
- vpxor \T1, \XMM5, \XMM5
- vpxor \T1, \XMM6, \XMM6
- vpxor \T1, \XMM7, \XMM7
- vpxor \T1, \XMM8, \XMM8
-
- #######################################################################
-
-
-
-
-
- vmovdqu 16*1(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqu 16*2(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
-
- #######################################################################
-
- vmovdqu HashKey_8(arg2), \T5
- vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
- vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
-
- vpshufd $0b01001110, \T2, \T6
- vpxor \T2, \T6, \T6
-
- vmovdqu HashKey_8_k(arg2), \T5
- vpclmulqdq $0x00, \T5, \T6, \T6
-
- vmovdqu 16*3(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP2(%rsp), \T1
- vmovdqu HashKey_7(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqu HashKey_7_k(arg2), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*4(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- #######################################################################
-
- vmovdqa TMP3(%rsp), \T1
- vmovdqu HashKey_6(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqu HashKey_6_k(arg2), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*5(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP4(%rsp), \T1
- vmovdqu HashKey_5(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqu HashKey_5_k(arg2), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*6(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
-
- vmovdqa TMP5(%rsp), \T1
- vmovdqu HashKey_4(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqu HashKey_4_k(arg2), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*7(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP6(%rsp), \T1
- vmovdqu HashKey_3(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqu HashKey_3_k(arg2), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
-
- vmovdqu 16*8(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP7(%rsp), \T1
- vmovdqu HashKey_2(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqu HashKey_2_k(arg2), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- #######################################################################
-
- vmovdqu 16*9(arg1), \T5
- vaesenc \T5, \XMM1, \XMM1
- vaesenc \T5, \XMM2, \XMM2
- vaesenc \T5, \XMM3, \XMM3
- vaesenc \T5, \XMM4, \XMM4
- vaesenc \T5, \XMM5, \XMM5
- vaesenc \T5, \XMM6, \XMM6
- vaesenc \T5, \XMM7, \XMM7
- vaesenc \T5, \XMM8, \XMM8
-
- vmovdqa TMP8(%rsp), \T1
- vmovdqu HashKey(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpshufd $0b01001110, \T1, \T3
- vpxor \T1, \T3, \T3
- vmovdqu HashKey_k(arg2), \T5
- vpclmulqdq $0x10, \T5, \T3, \T3
- vpxor \T3, \T6, \T6
-
- vpxor \T4, \T6, \T6
- vpxor \T7, \T6, \T6
-
- vmovdqu 16*10(arg1), \T5
-
- i = 11
- setreg
-.rep (\REP-9)
-
- vaesenc \T5, \XMM1, \XMM1
- vaesenc \T5, \XMM2, \XMM2
- vaesenc \T5, \XMM3, \XMM3
- vaesenc \T5, \XMM4, \XMM4
- vaesenc \T5, \XMM5, \XMM5
- vaesenc \T5, \XMM6, \XMM6
- vaesenc \T5, \XMM7, \XMM7
- vaesenc \T5, \XMM8, \XMM8
-
- vmovdqu 16*i(arg1), \T5
- i = i + 1
- setreg
-.endr
-
- i = 0
- j = 1
- setreg
-.rep 8
- vpxor 16*i(arg4, %r11), \T5, \T2
- .if \ENC_DEC == ENC
- vaesenclast \T2, reg_j, reg_j
- .else
- vaesenclast \T2, reg_j, \T3
- vmovdqu 16*i(arg4, %r11), reg_j
- vmovdqu \T3, 16*i(arg3, %r11)
- .endif
- i = (i+1)
- j = (j+1)
- setreg
-.endr
- #######################################################################
-
-
- vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
- vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
- vpxor \T3, \T7, \T7
- vpxor \T4, \T6, \T6 # accumulate the results in T6:T7
-
-
-
- #######################################################################
- #first phase of the reduction
- #######################################################################
- vpslld $31, \T7, \T2 # packed right shifting << 31
- vpslld $30, \T7, \T3 # packed right shifting shift << 30
- vpslld $25, \T7, \T4 # packed right shifting shift << 25
-
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
-
- vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
-
- vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
- #######################################################################
- .if \ENC_DEC == ENC
- vmovdqu \XMM1, 16*0(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM2, 16*1(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM3, 16*2(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM4, 16*3(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM5, 16*4(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM6, 16*5(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM7, 16*6(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM8, 16*7(arg3,%r11) # Write to the Ciphertext buffer
- .endif
-
- #######################################################################
- #second phase of the reduction
- vpsrld $1, \T7, \T2 # packed left shifting >> 1
- vpsrld $2, \T7, \T3 # packed left shifting >> 2
- vpsrld $7, \T7, \T4 # packed left shifting >> 7
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
-
- vpxor \T1, \T2, \T2
- vpxor \T2, \T7, \T7
- vpxor \T7, \T6, \T6 # the result is in T6
- #######################################################################
-
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-
-
- vpxor \T6, \XMM1, \XMM1
-
-
-
-.endm
-
-
-# GHASH the last 4 ciphertext blocks.
-.macro GHASH_LAST_8_AVX T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
-
- ## Karatsuba Method
-
-
- vpshufd $0b01001110, \XMM1, \T2
- vpxor \XMM1, \T2, \T2
- vmovdqu HashKey_8(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM1, \T6
- vpclmulqdq $0x00, \T5, \XMM1, \T7
-
- vmovdqu HashKey_8_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \XMM1
-
- ######################
-
- vpshufd $0b01001110, \XMM2, \T2
- vpxor \XMM2, \T2, \T2
- vmovdqu HashKey_7(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM2, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM2, \T4
- vpxor \T4, \T7, \T7
-
- vmovdqu HashKey_7_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vpshufd $0b01001110, \XMM3, \T2
- vpxor \XMM3, \T2, \T2
- vmovdqu HashKey_6(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM3, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM3, \T4
- vpxor \T4, \T7, \T7
-
- vmovdqu HashKey_6_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vpshufd $0b01001110, \XMM4, \T2
- vpxor \XMM4, \T2, \T2
- vmovdqu HashKey_5(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM4, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM4, \T4
- vpxor \T4, \T7, \T7
-
- vmovdqu HashKey_5_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vpshufd $0b01001110, \XMM5, \T2
- vpxor \XMM5, \T2, \T2
- vmovdqu HashKey_4(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM5, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM5, \T4
- vpxor \T4, \T7, \T7
-
- vmovdqu HashKey_4_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vpshufd $0b01001110, \XMM6, \T2
- vpxor \XMM6, \T2, \T2
- vmovdqu HashKey_3(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM6, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM6, \T4
- vpxor \T4, \T7, \T7
-
- vmovdqu HashKey_3_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vpshufd $0b01001110, \XMM7, \T2
- vpxor \XMM7, \T2, \T2
- vmovdqu HashKey_2(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM7, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM7, \T4
- vpxor \T4, \T7, \T7
-
- vmovdqu HashKey_2_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vpshufd $0b01001110, \XMM8, \T2
- vpxor \XMM8, \T2, \T2
- vmovdqu HashKey(arg2), \T5
- vpclmulqdq $0x11, \T5, \XMM8, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM8, \T4
- vpxor \T4, \T7, \T7
-
- vmovdqu HashKey_k(arg2), \T3
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
- vpxor \T6, \XMM1, \XMM1
- vpxor \T7, \XMM1, \T2
-
-
-
-
- vpslldq $8, \T2, \T4
- vpsrldq $8, \T2, \T2
-
- vpxor \T4, \T7, \T7
- vpxor \T2, \T6, \T6 # <T6:T7> holds the result of
- # the accumulated carry-less multiplications
-
- #######################################################################
- #first phase of the reduction
- vpslld $31, \T7, \T2 # packed right shifting << 31
- vpslld $30, \T7, \T3 # packed right shifting shift << 30
- vpslld $25, \T7, \T4 # packed right shifting shift << 25
-
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
-
- vpsrldq $4, \T2, \T1 # shift-R T1 1 DW
-
- vpslldq $12, \T2, \T2 # shift-L T2 3 DWs
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
- #######################################################################
-
-
- #second phase of the reduction
- vpsrld $1, \T7, \T2 # packed left shifting >> 1
- vpsrld $2, \T7, \T3 # packed left shifting >> 2
- vpsrld $7, \T7, \T4 # packed left shifting >> 7
- vpxor \T3, \T2, \T2 # xor the shifted versions
- vpxor \T4, \T2, \T2
-
- vpxor \T1, \T2, \T2
- vpxor \T2, \T7, \T7
- vpxor \T7, \T6, \T6 # the result is in T6
-
-.endm
-
-#############################################################
-#void aesni_gcm_precomp_avx_gen2
-# (gcm_data *my_ctx_data,
-# gcm_context_data *data,
-# u8 *hash_subkey# /* H, the Hash sub key input. Data starts on a 16-byte boundary. */
-# u8 *iv, /* Pre-counter block j0: 4 byte salt
-# (from Security Association) concatenated with 8 byte
-# Initialisation Vector (from IPSec ESP Payload)
-# concatenated with 0x00000001. 16-byte aligned pointer. */
-# const u8 *aad, /* Additional Authentication Data (AAD)*/
-# u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
-#############################################################
-SYM_FUNC_START(aesni_gcm_init_avx_gen2)
- FUNC_SAVE
- INIT GHASH_MUL_AVX, PRECOMPUTE_AVX
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_init_avx_gen2)
-
-###############################################################################
-#void aesni_gcm_enc_update_avx_gen2(
-# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
-# gcm_context_data *data,
-# u8 *out, /* Ciphertext output. Encrypt in-place is allowed. */
-# const u8 *in, /* Plaintext input */
-# u64 plaintext_len) /* Length of data in Bytes for encryption. */
-###############################################################################
-SYM_FUNC_START(aesni_gcm_enc_update_avx_gen2)
- FUNC_SAVE
- mov keysize, %eax
- cmp $32, %eax
- je key_256_enc_update
- cmp $16, %eax
- je key_128_enc_update
- # must be 192
- GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 11
- FUNC_RESTORE
- RET
-key_128_enc_update:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 9
- FUNC_RESTORE
- RET
-key_256_enc_update:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_enc_update_avx_gen2)
-
-###############################################################################
-#void aesni_gcm_dec_update_avx_gen2(
-# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
-# gcm_context_data *data,
-# u8 *out, /* Plaintext output. Decrypt in-place is allowed. */
-# const u8 *in, /* Ciphertext input */
-# u64 plaintext_len) /* Length of data in Bytes for encryption. */
-###############################################################################
-SYM_FUNC_START(aesni_gcm_dec_update_avx_gen2)
- FUNC_SAVE
- mov keysize,%eax
- cmp $32, %eax
- je key_256_dec_update
- cmp $16, %eax
- je key_128_dec_update
- # must be 192
- GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 11
- FUNC_RESTORE
- RET
-key_128_dec_update:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 9
- FUNC_RESTORE
- RET
-key_256_dec_update:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_dec_update_avx_gen2)
-
-###############################################################################
-#void aesni_gcm_finalize_avx_gen2(
-# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
-# gcm_context_data *data,
-# u8 *auth_tag, /* Authenticated Tag output. */
-# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
-# Valid values are 16 (most likely), 12 or 8. */
-###############################################################################
-SYM_FUNC_START(aesni_gcm_finalize_avx_gen2)
- FUNC_SAVE
- mov keysize,%eax
- cmp $32, %eax
- je key_256_finalize
- cmp $16, %eax
- je key_128_finalize
- # must be 192
- GCM_COMPLETE GHASH_MUL_AVX, 11, arg3, arg4
- FUNC_RESTORE
- RET
-key_128_finalize:
- GCM_COMPLETE GHASH_MUL_AVX, 9, arg3, arg4
- FUNC_RESTORE
- RET
-key_256_finalize:
- GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_finalize_avx_gen2)
-
-###############################################################################
-# GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
-# Input: A and B (128-bits each, bit-reflected)
-# Output: C = A*B*x mod poly, (i.e. >>1 )
-# To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
-# GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
-###############################################################################
-.macro GHASH_MUL_AVX2 GH HK T1 T2 T3 T4 T5
-
- vpclmulqdq $0x11,\HK,\GH,\T1 # T1 = a1*b1
- vpclmulqdq $0x00,\HK,\GH,\T2 # T2 = a0*b0
- vpclmulqdq $0x01,\HK,\GH,\T3 # T3 = a1*b0
- vpclmulqdq $0x10,\HK,\GH,\GH # GH = a0*b1
- vpxor \T3, \GH, \GH
-
-
- vpsrldq $8 , \GH, \T3 # shift-R GH 2 DWs
- vpslldq $8 , \GH, \GH # shift-L GH 2 DWs
-
- vpxor \T3, \T1, \T1
- vpxor \T2, \GH, \GH
-
- #######################################################################
- #first phase of the reduction
- vmovdqa POLY2(%rip), \T3
-
- vpclmulqdq $0x01, \GH, \T3, \T2
- vpslldq $8, \T2, \T2 # shift-L T2 2 DWs
-
- vpxor \T2, \GH, \GH # first phase of the reduction complete
- #######################################################################
- #second phase of the reduction
- vpclmulqdq $0x00, \GH, \T3, \T2
- vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
-
- vpclmulqdq $0x10, \GH, \T3, \GH
- vpslldq $4, \GH, \GH # shift-L GH 1 DW (Shift-L 1-DW to obtain result with no shifts)
-
- vpxor \T2, \GH, \GH # second phase of the reduction complete
- #######################################################################
- vpxor \T1, \GH, \GH # the result is in GH
-
-
-.endm
-
-.macro PRECOMPUTE_AVX2 HK T1 T2 T3 T4 T5 T6
-
- # Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
- vmovdqa \HK, \T5
- GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^2<<1 mod poly
- vmovdqu \T5, HashKey_2(arg2) # [HashKey_2] = HashKey^2<<1 mod poly
-
- GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^3<<1 mod poly
- vmovdqu \T5, HashKey_3(arg2)
-
- GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^4<<1 mod poly
- vmovdqu \T5, HashKey_4(arg2)
-
- GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^5<<1 mod poly
- vmovdqu \T5, HashKey_5(arg2)
-
- GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^6<<1 mod poly
- vmovdqu \T5, HashKey_6(arg2)
-
- GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^7<<1 mod poly
- vmovdqu \T5, HashKey_7(arg2)
-
- GHASH_MUL_AVX2 \T5, \HK, \T1, \T3, \T4, \T6, \T2 # T5 = HashKey^8<<1 mod poly
- vmovdqu \T5, HashKey_8(arg2)
-
-.endm
-
-## if a = number of total plaintext bytes
-## b = floor(a/16)
-## num_initial_blocks = b mod 4#
-## encrypt the initial num_initial_blocks blocks and apply ghash on the ciphertext
-## r10, r11, r12, rax are clobbered
-## arg1, arg2, arg3, arg4 are used as pointers only, not modified
-
-.macro INITIAL_BLOCKS_AVX2 REP num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER
- i = (8-\num_initial_blocks)
- setreg
- vmovdqu AadHash(arg2), reg_i
-
- # start AES for num_initial_blocks blocks
- vmovdqu CurCount(arg2), \CTR
-
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, reg_i
- vpshufb SHUF_MASK(%rip), reg_i, reg_i # perform a 16Byte swap
- i = (i+1)
- setreg
-.endr
-
- vmovdqa (arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vpxor \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
-
- j = 1
- setreg
-.rep \REP
- vmovdqa 16*j(arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vaesenc \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
-
- j = (j+1)
- setreg
-.endr
-
-
- vmovdqa 16*j(arg1), \T_key
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vaesenclast \T_key, reg_i, reg_i
- i = (i+1)
- setreg
-.endr
-
- i = (9-\num_initial_blocks)
- setreg
-.rep \num_initial_blocks
- vmovdqu (arg4, %r11), \T1
- vpxor \T1, reg_i, reg_i
- vmovdqu reg_i, (arg3 , %r11) # write back ciphertext for
- # num_initial_blocks blocks
- add $16, %r11
-.if \ENC_DEC == DEC
- vmovdqa \T1, reg_i
-.endif
- vpshufb SHUF_MASK(%rip), reg_i, reg_i # prepare ciphertext for GHASH computations
- i = (i+1)
- setreg
-.endr
-
-
- i = (8-\num_initial_blocks)
- j = (9-\num_initial_blocks)
- setreg
-
-.rep \num_initial_blocks
- vpxor reg_i, reg_j, reg_j
- GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 # apply GHASH on num_initial_blocks blocks
- i = (i+1)
- j = (j+1)
- setreg
-.endr
- # XMM8 has the combined result here
-
- vmovdqa \XMM8, TMP1(%rsp)
- vmovdqa \XMM8, \T3
-
- cmp $128, %r13
- jl .L_initial_blocks_done\@ # no need for precomputed constants
-
-###############################################################################
-# Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM1
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM2
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM3
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM4
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM5
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM6
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM7
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
-
- vpaddd ONE(%rip), \CTR, \CTR # INCR Y0
- vmovdqa \CTR, \XMM8
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-
- vmovdqa (arg1), \T_key
- vpxor \T_key, \XMM1, \XMM1
- vpxor \T_key, \XMM2, \XMM2
- vpxor \T_key, \XMM3, \XMM3
- vpxor \T_key, \XMM4, \XMM4
- vpxor \T_key, \XMM5, \XMM5
- vpxor \T_key, \XMM6, \XMM6
- vpxor \T_key, \XMM7, \XMM7
- vpxor \T_key, \XMM8, \XMM8
-
- i = 1
- setreg
-.rep \REP # do REP rounds
- vmovdqa 16*i(arg1), \T_key
- vaesenc \T_key, \XMM1, \XMM1
- vaesenc \T_key, \XMM2, \XMM2
- vaesenc \T_key, \XMM3, \XMM3
- vaesenc \T_key, \XMM4, \XMM4
- vaesenc \T_key, \XMM5, \XMM5
- vaesenc \T_key, \XMM6, \XMM6
- vaesenc \T_key, \XMM7, \XMM7
- vaesenc \T_key, \XMM8, \XMM8
- i = (i+1)
- setreg
-.endr
-
-
- vmovdqa 16*i(arg1), \T_key
- vaesenclast \T_key, \XMM1, \XMM1
- vaesenclast \T_key, \XMM2, \XMM2
- vaesenclast \T_key, \XMM3, \XMM3
- vaesenclast \T_key, \XMM4, \XMM4
- vaesenclast \T_key, \XMM5, \XMM5
- vaesenclast \T_key, \XMM6, \XMM6
- vaesenclast \T_key, \XMM7, \XMM7
- vaesenclast \T_key, \XMM8, \XMM8
-
- vmovdqu (arg4, %r11), \T1
- vpxor \T1, \XMM1, \XMM1
- vmovdqu \XMM1, (arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM1
- .endif
-
- vmovdqu 16*1(arg4, %r11), \T1
- vpxor \T1, \XMM2, \XMM2
- vmovdqu \XMM2, 16*1(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM2
- .endif
-
- vmovdqu 16*2(arg4, %r11), \T1
- vpxor \T1, \XMM3, \XMM3
- vmovdqu \XMM3, 16*2(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM3
- .endif
-
- vmovdqu 16*3(arg4, %r11), \T1
- vpxor \T1, \XMM4, \XMM4
- vmovdqu \XMM4, 16*3(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM4
- .endif
-
- vmovdqu 16*4(arg4, %r11), \T1
- vpxor \T1, \XMM5, \XMM5
- vmovdqu \XMM5, 16*4(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM5
- .endif
-
- vmovdqu 16*5(arg4, %r11), \T1
- vpxor \T1, \XMM6, \XMM6
- vmovdqu \XMM6, 16*5(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM6
- .endif
-
- vmovdqu 16*6(arg4, %r11), \T1
- vpxor \T1, \XMM7, \XMM7
- vmovdqu \XMM7, 16*6(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM7
- .endif
-
- vmovdqu 16*7(arg4, %r11), \T1
- vpxor \T1, \XMM8, \XMM8
- vmovdqu \XMM8, 16*7(arg3 , %r11)
- .if \ENC_DEC == DEC
- vmovdqa \T1, \XMM8
- .endif
-
- add $128, %r11
-
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpxor TMP1(%rsp), \XMM1, \XMM1 # combine GHASHed value with
- # the corresponding ciphertext
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-
-###############################################################################
-
-.L_initial_blocks_done\@:
-
-
-.endm
-
-
-
-# encrypt 8 blocks at a time
-# ghash the 8 previously encrypted ciphertext blocks
-# arg1, arg2, arg3, arg4 are used as pointers only, not modified
-# r11 is the data offset value
-.macro GHASH_8_ENCRYPT_8_PARALLEL_AVX2 REP T1 T2 T3 T4 T5 T6 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T7 loop_idx ENC_DEC
-
- vmovdqa \XMM1, \T2
- vmovdqa \XMM2, TMP2(%rsp)
- vmovdqa \XMM3, TMP3(%rsp)
- vmovdqa \XMM4, TMP4(%rsp)
- vmovdqa \XMM5, TMP5(%rsp)
- vmovdqa \XMM6, TMP6(%rsp)
- vmovdqa \XMM7, TMP7(%rsp)
- vmovdqa \XMM8, TMP8(%rsp)
-
-.if \loop_idx == in_order
- vpaddd ONE(%rip), \CTR, \XMM1 # INCR CNT
- vpaddd ONE(%rip), \XMM1, \XMM2
- vpaddd ONE(%rip), \XMM2, \XMM3
- vpaddd ONE(%rip), \XMM3, \XMM4
- vpaddd ONE(%rip), \XMM4, \XMM5
- vpaddd ONE(%rip), \XMM5, \XMM6
- vpaddd ONE(%rip), \XMM6, \XMM7
- vpaddd ONE(%rip), \XMM7, \XMM8
- vmovdqa \XMM8, \CTR
-
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-.else
- vpaddd ONEf(%rip), \CTR, \XMM1 # INCR CNT
- vpaddd ONEf(%rip), \XMM1, \XMM2
- vpaddd ONEf(%rip), \XMM2, \XMM3
- vpaddd ONEf(%rip), \XMM3, \XMM4
- vpaddd ONEf(%rip), \XMM4, \XMM5
- vpaddd ONEf(%rip), \XMM5, \XMM6
- vpaddd ONEf(%rip), \XMM6, \XMM7
- vpaddd ONEf(%rip), \XMM7, \XMM8
- vmovdqa \XMM8, \CTR
-.endif
-
-
- #######################################################################
-
- vmovdqu (arg1), \T1
- vpxor \T1, \XMM1, \XMM1
- vpxor \T1, \XMM2, \XMM2
- vpxor \T1, \XMM3, \XMM3
- vpxor \T1, \XMM4, \XMM4
- vpxor \T1, \XMM5, \XMM5
- vpxor \T1, \XMM6, \XMM6
- vpxor \T1, \XMM7, \XMM7
- vpxor \T1, \XMM8, \XMM8
-
- #######################################################################
-
-
-
-
-
- vmovdqu 16*1(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqu 16*2(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
-
- #######################################################################
-
- vmovdqu HashKey_8(arg2), \T5
- vpclmulqdq $0x11, \T5, \T2, \T4 # T4 = a1*b1
- vpclmulqdq $0x00, \T5, \T2, \T7 # T7 = a0*b0
- vpclmulqdq $0x01, \T5, \T2, \T6 # T6 = a1*b0
- vpclmulqdq $0x10, \T5, \T2, \T5 # T5 = a0*b1
- vpxor \T5, \T6, \T6
-
- vmovdqu 16*3(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP2(%rsp), \T1
- vmovdqu HashKey_7(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*4(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- #######################################################################
-
- vmovdqa TMP3(%rsp), \T1
- vmovdqu HashKey_6(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*5(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP4(%rsp), \T1
- vmovdqu HashKey_5(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*6(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
-
- vmovdqa TMP5(%rsp), \T1
- vmovdqu HashKey_4(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*7(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP6(%rsp), \T1
- vmovdqu HashKey_3(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vmovdqu 16*8(arg1), \T1
- vaesenc \T1, \XMM1, \XMM1
- vaesenc \T1, \XMM2, \XMM2
- vaesenc \T1, \XMM3, \XMM3
- vaesenc \T1, \XMM4, \XMM4
- vaesenc \T1, \XMM5, \XMM5
- vaesenc \T1, \XMM6, \XMM6
- vaesenc \T1, \XMM7, \XMM7
- vaesenc \T1, \XMM8, \XMM8
-
- vmovdqa TMP7(%rsp), \T1
- vmovdqu HashKey_2(arg2), \T5
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T4
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
-
- #######################################################################
-
- vmovdqu 16*9(arg1), \T5
- vaesenc \T5, \XMM1, \XMM1
- vaesenc \T5, \XMM2, \XMM2
- vaesenc \T5, \XMM3, \XMM3
- vaesenc \T5, \XMM4, \XMM4
- vaesenc \T5, \XMM5, \XMM5
- vaesenc \T5, \XMM6, \XMM6
- vaesenc \T5, \XMM7, \XMM7
- vaesenc \T5, \XMM8, \XMM8
-
- vmovdqa TMP8(%rsp), \T1
- vmovdqu HashKey(arg2), \T5
-
- vpclmulqdq $0x00, \T5, \T1, \T3
- vpxor \T3, \T7, \T7
-
- vpclmulqdq $0x01, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x10, \T5, \T1, \T3
- vpxor \T3, \T6, \T6
-
- vpclmulqdq $0x11, \T5, \T1, \T3
- vpxor \T3, \T4, \T1
-
-
- vmovdqu 16*10(arg1), \T5
-
- i = 11
- setreg
-.rep (\REP-9)
- vaesenc \T5, \XMM1, \XMM1
- vaesenc \T5, \XMM2, \XMM2
- vaesenc \T5, \XMM3, \XMM3
- vaesenc \T5, \XMM4, \XMM4
- vaesenc \T5, \XMM5, \XMM5
- vaesenc \T5, \XMM6, \XMM6
- vaesenc \T5, \XMM7, \XMM7
- vaesenc \T5, \XMM8, \XMM8
-
- vmovdqu 16*i(arg1), \T5
- i = i + 1
- setreg
-.endr
-
- i = 0
- j = 1
- setreg
-.rep 8
- vpxor 16*i(arg4, %r11), \T5, \T2
- .if \ENC_DEC == ENC
- vaesenclast \T2, reg_j, reg_j
- .else
- vaesenclast \T2, reg_j, \T3
- vmovdqu 16*i(arg4, %r11), reg_j
- vmovdqu \T3, 16*i(arg3, %r11)
- .endif
- i = (i+1)
- j = (j+1)
- setreg
-.endr
- #######################################################################
-
-
- vpslldq $8, \T6, \T3 # shift-L T3 2 DWs
- vpsrldq $8, \T6, \T6 # shift-R T2 2 DWs
- vpxor \T3, \T7, \T7
- vpxor \T6, \T1, \T1 # accumulate the results in T1:T7
-
-
-
- #######################################################################
- #first phase of the reduction
- vmovdqa POLY2(%rip), \T3
-
- vpclmulqdq $0x01, \T7, \T3, \T2
- vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
-
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
- #######################################################################
- .if \ENC_DEC == ENC
- vmovdqu \XMM1, 16*0(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM2, 16*1(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM3, 16*2(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM4, 16*3(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM5, 16*4(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM6, 16*5(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM7, 16*6(arg3,%r11) # Write to the Ciphertext buffer
- vmovdqu \XMM8, 16*7(arg3,%r11) # Write to the Ciphertext buffer
- .endif
-
- #######################################################################
- #second phase of the reduction
- vpclmulqdq $0x00, \T7, \T3, \T2
- vpsrldq $4, \T2, \T2 # shift-R xmm2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
-
- vpclmulqdq $0x10, \T7, \T3, \T4
- vpslldq $4, \T4, \T4 # shift-L xmm0 1 DW (Shift-L 1-DW to obtain result with no shifts)
-
- vpxor \T2, \T4, \T4 # second phase of the reduction complete
- #######################################################################
- vpxor \T4, \T1, \T1 # the result is in T1
-
- vpshufb SHUF_MASK(%rip), \XMM1, \XMM1 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM2, \XMM2 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM3, \XMM3 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM4, \XMM4 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM5, \XMM5 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM6, \XMM6 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM7, \XMM7 # perform a 16Byte swap
- vpshufb SHUF_MASK(%rip), \XMM8, \XMM8 # perform a 16Byte swap
-
-
- vpxor \T1, \XMM1, \XMM1
-
-
-
-.endm
-
-
-# GHASH the last 4 ciphertext blocks.
-.macro GHASH_LAST_8_AVX2 T1 T2 T3 T4 T5 T6 T7 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8
-
- ## Karatsuba Method
-
- vmovdqu HashKey_8(arg2), \T5
-
- vpshufd $0b01001110, \XMM1, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM1, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM1, \T6
- vpclmulqdq $0x00, \T5, \XMM1, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \XMM1
-
- ######################
-
- vmovdqu HashKey_7(arg2), \T5
- vpshufd $0b01001110, \XMM2, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM2, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM2, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM2, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqu HashKey_6(arg2), \T5
- vpshufd $0b01001110, \XMM3, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM3, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM3, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM3, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqu HashKey_5(arg2), \T5
- vpshufd $0b01001110, \XMM4, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM4, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM4, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM4, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqu HashKey_4(arg2), \T5
- vpshufd $0b01001110, \XMM5, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM5, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM5, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM5, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqu HashKey_3(arg2), \T5
- vpshufd $0b01001110, \XMM6, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM6, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM6, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM6, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqu HashKey_2(arg2), \T5
- vpshufd $0b01001110, \XMM7, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM7, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM7, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM7, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
-
- ######################
-
- vmovdqu HashKey(arg2), \T5
- vpshufd $0b01001110, \XMM8, \T2
- vpshufd $0b01001110, \T5, \T3
- vpxor \XMM8, \T2, \T2
- vpxor \T5, \T3, \T3
-
- vpclmulqdq $0x11, \T5, \XMM8, \T4
- vpxor \T4, \T6, \T6
-
- vpclmulqdq $0x00, \T5, \XMM8, \T4
- vpxor \T4, \T7, \T7
-
- vpclmulqdq $0x00, \T3, \T2, \T2
-
- vpxor \T2, \XMM1, \XMM1
- vpxor \T6, \XMM1, \XMM1
- vpxor \T7, \XMM1, \T2
-
-
-
-
- vpslldq $8, \T2, \T4
- vpsrldq $8, \T2, \T2
-
- vpxor \T4, \T7, \T7
- vpxor \T2, \T6, \T6 # <T6:T7> holds the result of the
- # accumulated carry-less multiplications
-
- #######################################################################
- #first phase of the reduction
- vmovdqa POLY2(%rip), \T3
-
- vpclmulqdq $0x01, \T7, \T3, \T2
- vpslldq $8, \T2, \T2 # shift-L xmm2 2 DWs
-
- vpxor \T2, \T7, \T7 # first phase of the reduction complete
- #######################################################################
-
-
- #second phase of the reduction
- vpclmulqdq $0x00, \T7, \T3, \T2
- vpsrldq $4, \T2, \T2 # shift-R T2 1 DW (Shift-R only 1-DW to obtain 2-DWs shift-R)
-
- vpclmulqdq $0x10, \T7, \T3, \T4
- vpslldq $4, \T4, \T4 # shift-L T4 1 DW (Shift-L 1-DW to obtain result with no shifts)
-
- vpxor \T2, \T4, \T4 # second phase of the reduction complete
- #######################################################################
- vpxor \T4, \T6, \T6 # the result is in T6
-.endm
-
-
-
-#############################################################
-#void aesni_gcm_init_avx_gen4
-# (gcm_data *my_ctx_data,
-# gcm_context_data *data,
-# u8 *iv, /* Pre-counter block j0: 4 byte salt
-# (from Security Association) concatenated with 8 byte
-# Initialisation Vector (from IPSec ESP Payload)
-# concatenated with 0x00000001. 16-byte aligned pointer. */
-# u8 *hash_subkey# /* H, the Hash sub key input. Data starts on a 16-byte boundary. */
-# const u8 *aad, /* Additional Authentication Data (AAD)*/
-# u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
-#############################################################
-SYM_FUNC_START(aesni_gcm_init_avx_gen4)
- FUNC_SAVE
- INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_init_avx_gen4)
-
-###############################################################################
-#void aesni_gcm_enc_avx_gen4(
-# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
-# gcm_context_data *data,
-# u8 *out, /* Ciphertext output. Encrypt in-place is allowed. */
-# const u8 *in, /* Plaintext input */
-# u64 plaintext_len) /* Length of data in Bytes for encryption. */
-###############################################################################
-SYM_FUNC_START(aesni_gcm_enc_update_avx_gen4)
- FUNC_SAVE
- mov keysize,%eax
- cmp $32, %eax
- je key_256_enc_update4
- cmp $16, %eax
- je key_128_enc_update4
- # must be 192
- GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 11
- FUNC_RESTORE
- RET
-key_128_enc_update4:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 9
- FUNC_RESTORE
- RET
-key_256_enc_update4:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_enc_update_avx_gen4)
-
-###############################################################################
-#void aesni_gcm_dec_update_avx_gen4(
-# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
-# gcm_context_data *data,
-# u8 *out, /* Plaintext output. Decrypt in-place is allowed. */
-# const u8 *in, /* Ciphertext input */
-# u64 plaintext_len) /* Length of data in Bytes for encryption. */
-###############################################################################
-SYM_FUNC_START(aesni_gcm_dec_update_avx_gen4)
- FUNC_SAVE
- mov keysize,%eax
- cmp $32, %eax
- je key_256_dec_update4
- cmp $16, %eax
- je key_128_dec_update4
- # must be 192
- GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 11
- FUNC_RESTORE
- RET
-key_128_dec_update4:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 9
- FUNC_RESTORE
- RET
-key_256_dec_update4:
- GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_dec_update_avx_gen4)
-
-###############################################################################
-#void aesni_gcm_finalize_avx_gen4(
-# gcm_data *my_ctx_data, /* aligned to 16 Bytes */
-# gcm_context_data *data,
-# u8 *auth_tag, /* Authenticated Tag output. */
-# u64 auth_tag_len)# /* Authenticated Tag Length in bytes.
-# Valid values are 16 (most likely), 12 or 8. */
-###############################################################################
-SYM_FUNC_START(aesni_gcm_finalize_avx_gen4)
- FUNC_SAVE
- mov keysize,%eax
- cmp $32, %eax
- je key_256_finalize4
- cmp $16, %eax
- je key_128_finalize4
- # must be 192
- GCM_COMPLETE GHASH_MUL_AVX2, 11, arg3, arg4
- FUNC_RESTORE
- RET
-key_128_finalize4:
- GCM_COMPLETE GHASH_MUL_AVX2, 9, arg3, arg4
- FUNC_RESTORE
- RET
-key_256_finalize4:
- GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_finalize_avx_gen4)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index ef031655b2d3..cd37de5ec404 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
- * Support for Intel AES-NI instructions. This file contains glue
- * code, the real AES implementation is in intel-aes_asm.S.
+ * Support for AES-NI and VAES instructions. This file contains glue code.
+ * The real AES implementations are in aesni-intel_asm.S and other .S files.
*
* Copyright (C) 2008, Intel Corp.
* Author: Huang Ying <ying.huang@intel.com>
@@ -13,6 +13,8 @@
* Tadeusz Struk (tadeusz.struk@intel.com)
* Aidan O'Mahony (aidan.o.mahony@intel.com)
* Copyright (c) 2010, Intel Corporation.
+ *
+ * Copyright 2024 Google LLC
*/
#include <linux/hardirq.h>
@@ -44,41 +46,11 @@
#define CRYPTO_AES_CTX_SIZE (sizeof(struct crypto_aes_ctx) + AESNI_ALIGN_EXTRA)
#define XTS_AES_CTX_SIZE (sizeof(struct aesni_xts_ctx) + AESNI_ALIGN_EXTRA)
-/* This data is stored at the end of the crypto_tfm struct.
- * It's a type of per "session" data storage location.
- * This needs to be 16 byte aligned.
- */
-struct aesni_rfc4106_gcm_ctx {
- u8 hash_subkey[16] AESNI_ALIGN_ATTR;
- struct crypto_aes_ctx aes_key_expanded AESNI_ALIGN_ATTR;
- u8 nonce[4];
-};
-
-struct generic_gcmaes_ctx {
- u8 hash_subkey[16] AESNI_ALIGN_ATTR;
- struct crypto_aes_ctx aes_key_expanded AESNI_ALIGN_ATTR;
-};
-
struct aesni_xts_ctx {
struct crypto_aes_ctx tweak_ctx AESNI_ALIGN_ATTR;
struct crypto_aes_ctx crypt_ctx AESNI_ALIGN_ATTR;
};
-#define GCM_BLOCK_LEN 16
-
-struct gcm_context_data {
- /* init, update and finalize context data */
- u8 aad_hash[GCM_BLOCK_LEN];
- u64 aad_length;
- u64 in_length;
- u8 partial_block_enc_key[GCM_BLOCK_LEN];
- u8 orig_IV[GCM_BLOCK_LEN];
- u8 current_counter[GCM_BLOCK_LEN];
- u64 partial_block_len;
- u64 unused;
- u8 hash_keys[GCM_BLOCK_LEN * 16];
-};
-
static inline void *aes_align_addr(void *addr)
{
if (crypto_tfm_ctx_alignment() >= AESNI_ALIGN)
@@ -103,9 +75,6 @@ asmlinkage void aesni_cts_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv);
-#define AVX_GEN2_OPTSIZE 640
-#define AVX_GEN4_OPTSIZE 4096
-
asmlinkage void aesni_xts_enc(const struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv);
@@ -118,23 +87,6 @@ asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv);
DEFINE_STATIC_CALL(aesni_ctr_enc_tfm, aesni_ctr_enc);
-/* Scatter / Gather routines, with args similar to above */
-asmlinkage void aesni_gcm_init(void *ctx,
- struct gcm_context_data *gdata,
- u8 *iv,
- u8 *hash_subkey, const u8 *aad,
- unsigned long aad_len);
-asmlinkage void aesni_gcm_enc_update(void *ctx,
- struct gcm_context_data *gdata, u8 *out,
- const u8 *in, unsigned long plaintext_len);
-asmlinkage void aesni_gcm_dec_update(void *ctx,
- struct gcm_context_data *gdata, u8 *out,
- const u8 *in,
- unsigned long ciphertext_len);
-asmlinkage void aesni_gcm_finalize(void *ctx,
- struct gcm_context_data *gdata,
- u8 *auth_tag, unsigned long auth_tag_len);
-
asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
void *keys, u8 *out, unsigned int num_bytes);
asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv,
@@ -154,67 +106,6 @@ asmlinkage void aes_xctr_enc_192_avx_by8(const u8 *in, const u8 *iv,
asmlinkage void aes_xctr_enc_256_avx_by8(const u8 *in, const u8 *iv,
const void *keys, u8 *out, unsigned int num_bytes,
unsigned int byte_ctr);
-
-/*
- * asmlinkage void aesni_gcm_init_avx_gen2()
- * gcm_data *my_ctx_data, context data
- * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
- */
-asmlinkage void aesni_gcm_init_avx_gen2(void *my_ctx_data,
- struct gcm_context_data *gdata,
- u8 *iv,
- u8 *hash_subkey,
- const u8 *aad,
- unsigned long aad_len);
-
-asmlinkage void aesni_gcm_enc_update_avx_gen2(void *ctx,
- struct gcm_context_data *gdata, u8 *out,
- const u8 *in, unsigned long plaintext_len);
-asmlinkage void aesni_gcm_dec_update_avx_gen2(void *ctx,
- struct gcm_context_data *gdata, u8 *out,
- const u8 *in,
- unsigned long ciphertext_len);
-asmlinkage void aesni_gcm_finalize_avx_gen2(void *ctx,
- struct gcm_context_data *gdata,
- u8 *auth_tag, unsigned long auth_tag_len);
-
-/*
- * asmlinkage void aesni_gcm_init_avx_gen4()
- * gcm_data *my_ctx_data, context data
- * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
- */
-asmlinkage void aesni_gcm_init_avx_gen4(void *my_ctx_data,
- struct gcm_context_data *gdata,
- u8 *iv,
- u8 *hash_subkey,
- const u8 *aad,
- unsigned long aad_len);
-
-asmlinkage void aesni_gcm_enc_update_avx_gen4(void *ctx,
- struct gcm_context_data *gdata, u8 *out,
- const u8 *in, unsigned long plaintext_len);
-asmlinkage void aesni_gcm_dec_update_avx_gen4(void *ctx,
- struct gcm_context_data *gdata, u8 *out,
- const u8 *in,
- unsigned long ciphertext_len);
-asmlinkage void aesni_gcm_finalize_avx_gen4(void *ctx,
- struct gcm_context_data *gdata,
- u8 *auth_tag, unsigned long auth_tag_len);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx2);
-
-static inline struct
-aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
-{
- return aes_align_addr(crypto_aead_ctx(tfm));
-}
-
-static inline struct
-generic_gcmaes_ctx *generic_gcmaes_ctx_get(struct crypto_aead *tfm)
-{
- return aes_align_addr(crypto_aead_ctx(tfm));
-}
#endif
static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx)
@@ -588,280 +479,6 @@ static int xctr_crypt(struct skcipher_request *req)
}
return err;
}
-
-static int aes_gcm_derive_hash_subkey(const struct crypto_aes_ctx *aes_key,
- u8 hash_subkey[AES_BLOCK_SIZE])
-{
- static const u8 zeroes[AES_BLOCK_SIZE];
-
- aes_encrypt(aes_key, hash_subkey, zeroes);
- return 0;
-}
-
-static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
- unsigned int key_len)
-{
- struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead);
-
- if (key_len < 4)
- return -EINVAL;
-
- /*Account for 4 byte nonce at the end.*/
- key_len -= 4;
-
- memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce));
-
- return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?:
- aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded,
- ctx->hash_subkey);
-}
-
-/* This is the Integrity Check Value (aka the authentication tag) length and can
- * be 8, 12 or 16 bytes long. */
-static int common_rfc4106_set_authsize(struct crypto_aead *aead,
- unsigned int authsize)
-{
- switch (authsize) {
- case 8:
- case 12:
- case 16:
- break;
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
- unsigned int authsize)
-{
- switch (authsize) {
- case 4:
- case 8:
- case 12:
- case 13:
- case 14:
- case 15:
- case 16:
- break;
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
- unsigned int assoclen, u8 *hash_subkey,
- u8 *iv, void *aes_ctx, u8 *auth_tag,
- unsigned long auth_tag_len)
-{
- u8 databuf[sizeof(struct gcm_context_data) + (AESNI_ALIGN - 8)] __aligned(8);
- struct gcm_context_data *data = PTR_ALIGN((void *)databuf, AESNI_ALIGN);
- unsigned long left = req->cryptlen;
- struct scatter_walk assoc_sg_walk;
- struct skcipher_walk walk;
- bool do_avx, do_avx2;
- u8 *assocmem = NULL;
- u8 *assoc;
- int err;
-
- if (!enc)
- left -= auth_tag_len;
-
- do_avx = (left >= AVX_GEN2_OPTSIZE);
- do_avx2 = (left >= AVX_GEN4_OPTSIZE);
-
- /* Linearize assoc, if not already linear */
- if (req->src->length >= assoclen && req->src->length) {
- scatterwalk_start(&assoc_sg_walk, req->src);
- assoc = scatterwalk_map(&assoc_sg_walk);
- } else {
- gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
- GFP_KERNEL : GFP_ATOMIC;
-
- /* assoc can be any length, so must be on heap */
- assocmem = kmalloc(assoclen, flags);
- if (unlikely(!assocmem))
- return -ENOMEM;
- assoc = assocmem;
-
- scatterwalk_map_and_copy(assoc, req->src, 0, assoclen, 0);
- }
-
- kernel_fpu_begin();
- if (static_branch_likely(&gcm_use_avx2) && do_avx2)
- aesni_gcm_init_avx_gen4(aes_ctx, data, iv, hash_subkey, assoc,
- assoclen);
- else if (static_branch_likely(&gcm_use_avx) && do_avx)
- aesni_gcm_init_avx_gen2(aes_ctx, data, iv, hash_subkey, assoc,
- assoclen);
- else
- aesni_gcm_init(aes_ctx, data, iv, hash_subkey, assoc, assoclen);
- kernel_fpu_end();
-
- if (!assocmem)
- scatterwalk_unmap(assoc);
- else
- kfree(assocmem);
-
- err = enc ? skcipher_walk_aead_encrypt(&walk, req, false)
- : skcipher_walk_aead_decrypt(&walk, req, false);
-
- while (walk.nbytes > 0) {
- kernel_fpu_begin();
- if (static_branch_likely(&gcm_use_avx2) && do_avx2) {
- if (enc)
- aesni_gcm_enc_update_avx_gen4(aes_ctx, data,
- walk.dst.virt.addr,
- walk.src.virt.addr,
- walk.nbytes);
- else
- aesni_gcm_dec_update_avx_gen4(aes_ctx, data,
- walk.dst.virt.addr,
- walk.src.virt.addr,
- walk.nbytes);
- } else if (static_branch_likely(&gcm_use_avx) && do_avx) {
- if (enc)
- aesni_gcm_enc_update_avx_gen2(aes_ctx, data,
- walk.dst.virt.addr,
- walk.src.virt.addr,
- walk.nbytes);
- else
- aesni_gcm_dec_update_avx_gen2(aes_ctx, data,
- walk.dst.virt.addr,
- walk.src.virt.addr,
- walk.nbytes);
- } else if (enc) {
- aesni_gcm_enc_update(aes_ctx, data, walk.dst.virt.addr,
- walk.src.virt.addr, walk.nbytes);
- } else {
- aesni_gcm_dec_update(aes_ctx, data, walk.dst.virt.addr,
- walk.src.virt.addr, walk.nbytes);
- }
- kernel_fpu_end();
-
- err = skcipher_walk_done(&walk, 0);
- }
-
- if (err)
- return err;
-
- kernel_fpu_begin();
- if (static_branch_likely(&gcm_use_avx2) && do_avx2)
- aesni_gcm_finalize_avx_gen4(aes_ctx, data, auth_tag,
- auth_tag_len);
- else if (static_branch_likely(&gcm_use_avx) && do_avx)
- aesni_gcm_finalize_avx_gen2(aes_ctx, data, auth_tag,
- auth_tag_len);
- else
- aesni_gcm_finalize(aes_ctx, data, auth_tag, auth_tag_len);
- kernel_fpu_end();
-
- return 0;
-}
-
-static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen,
- u8 *hash_subkey, u8 *iv, void *aes_ctx)
-{
- struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- unsigned long auth_tag_len = crypto_aead_authsize(tfm);
- u8 auth_tag[16];
- int err;
-
- err = gcmaes_crypt_by_sg(true, req, assoclen, hash_subkey, iv, aes_ctx,
- auth_tag, auth_tag_len);
- if (err)
- return err;
-
- scatterwalk_map_and_copy(auth_tag, req->dst,
- req->assoclen + req->cryptlen,
- auth_tag_len, 1);
- return 0;
-}
-
-static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen,
- u8 *hash_subkey, u8 *iv, void *aes_ctx)
-{
- struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- unsigned long auth_tag_len = crypto_aead_authsize(tfm);
- u8 auth_tag_msg[16];
- u8 auth_tag[16];
- int err;
-
- err = gcmaes_crypt_by_sg(false, req, assoclen, hash_subkey, iv, aes_ctx,
- auth_tag, auth_tag_len);
- if (err)
- return err;
-
- /* Copy out original auth_tag */
- scatterwalk_map_and_copy(auth_tag_msg, req->src,
- req->assoclen + req->cryptlen - auth_tag_len,
- auth_tag_len, 0);
-
- /* Compare generated tag with passed in tag. */
- if (crypto_memneq(auth_tag_msg, auth_tag, auth_tag_len)) {
- memzero_explicit(auth_tag, sizeof(auth_tag));
- return -EBADMSG;
- }
- return 0;
-}
-
-static int helper_rfc4106_encrypt(struct aead_request *req)
-{
- struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
- void *aes_ctx = &(ctx->aes_key_expanded);
- u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
- u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
- unsigned int i;
- __be32 counter = cpu_to_be32(1);
-
- /* Assuming we are supporting rfc4106 64-bit extended */
- /* sequence numbers We need to have the AAD length equal */
- /* to 16 or 20 bytes */
- if (unlikely(req->assoclen != 16 && req->assoclen != 20))
- return -EINVAL;
-
- /* IV below built */
- for (i = 0; i < 4; i++)
- *(iv+i) = ctx->nonce[i];
- for (i = 0; i < 8; i++)
- *(iv+4+i) = req->iv[i];
- *((__be32 *)(iv+12)) = counter;
-
- return gcmaes_encrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
- aes_ctx);
-}
-
-static int helper_rfc4106_decrypt(struct aead_request *req)
-{
- __be32 counter = cpu_to_be32(1);
- struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
- void *aes_ctx = &(ctx->aes_key_expanded);
- u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
- u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
- unsigned int i;
-
- if (unlikely(req->assoclen != 16 && req->assoclen != 20))
- return -EINVAL;
-
- /* Assuming we are supporting rfc4106 64-bit extended */
- /* sequence numbers We need to have the AAD length */
- /* equal to 16 or 20 bytes */
-
- /* IV below built */
- for (i = 0; i < 4; i++)
- *(iv+i) = ctx->nonce[i];
- for (i = 0; i < 8; i++)
- *(iv+4+i) = req->iv[i];
- *((__be32 *)(iv+12)) = counter;
-
- return gcmaes_decrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
- aes_ctx);
-}
#endif
static int xts_setkey_aesni(struct crypto_skcipher *tfm, const u8 *key,
@@ -1216,11 +833,717 @@ DEFINE_XTS_ALG(vaes_avx10_256, "xts-aes-vaes-avx10_256", 700);
DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800);
#endif
+/* The common part of the x86_64 AES-GCM key struct */
+struct aes_gcm_key {
+ /* Expanded AES key and the AES key length in bytes */
+ struct crypto_aes_ctx aes_key;
+
+ /* RFC4106 nonce (used only by the rfc4106 algorithms) */
+ u32 rfc4106_nonce;
+};
+
+/* Key struct used by the AES-NI implementations of AES-GCM */
+struct aes_gcm_key_aesni {
+ /*
+ * Common part of the key. The assembly code requires 16-byte alignment
+ * for the round keys; we get this by them being located at the start of
+ * the struct and the whole struct being 16-byte aligned.
+ */
+ struct aes_gcm_key base;
+
+ /*
+ * Powers of the hash key H^8 through H^1. These are 128-bit values.
+ * They all have an extra factor of x^-1 and are byte-reversed. 16-byte
+ * alignment is required by the assembly code.
+ */
+ u64 h_powers[8][2] __aligned(16);
+
+ /*
+ * h_powers_xored[i] contains the two 64-bit halves of h_powers[i] XOR'd
+ * together. It's used for Karatsuba multiplication. 16-byte alignment
+ * is required by the assembly code.
+ */
+ u64 h_powers_xored[8] __aligned(16);
+
+ /*
+ * H^1 times x^64 (and also the usual extra factor of x^-1). 16-byte
+ * alignment is required by the assembly code.
+ */
+ u64 h_times_x64[2] __aligned(16);
+};
+#define AES_GCM_KEY_AESNI(key) \
+ container_of((key), struct aes_gcm_key_aesni, base)
+#define AES_GCM_KEY_AESNI_SIZE \
+ (sizeof(struct aes_gcm_key_aesni) + (15 & ~(CRYPTO_MINALIGN - 1)))
+
+/* Key struct used by the VAES + AVX10 implementations of AES-GCM */
+struct aes_gcm_key_avx10 {
+ /*
+ * Common part of the key. The assembly code prefers 16-byte alignment
+ * for the round keys; we get this by them being located at the start of
+ * the struct and the whole struct being 64-byte aligned.
+ */
+ struct aes_gcm_key base;
+
+ /*
+ * Powers of the hash key H^16 through H^1. These are 128-bit values.
+ * They all have an extra factor of x^-1 and are byte-reversed. This
+ * array is aligned to a 64-byte boundary to make it naturally aligned
+ * for 512-bit loads, which can improve performance. (The assembly code
+ * doesn't *need* the alignment; this is just an optimization.)
+ */
+ u64 h_powers[16][2] __aligned(64);
+
+ /* Three padding blocks required by the assembly code */
+ u64 padding[3][2];
+};
+#define AES_GCM_KEY_AVX10(key) \
+ container_of((key), struct aes_gcm_key_avx10, base)
+#define AES_GCM_KEY_AVX10_SIZE \
+ (sizeof(struct aes_gcm_key_avx10) + (63 & ~(CRYPTO_MINALIGN - 1)))
+
+/*
+ * These flags are passed to the AES-GCM helper functions to specify the
+ * specific version of AES-GCM (RFC4106 or not), whether it's encryption or
+ * decryption, and which assembly functions should be called. Assembly
+ * functions are selected using flags instead of function pointers to avoid
+ * indirect calls (which are very expensive on x86) regardless of inlining.
+ */
+#define FLAG_RFC4106 BIT(0)
+#define FLAG_ENC BIT(1)
+#define FLAG_AVX BIT(2)
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+# define FLAG_AVX10_256 BIT(3)
+# define FLAG_AVX10_512 BIT(4)
+#else
+ /*
+ * This should cause all calls to the AVX10 assembly functions to be
+ * optimized out, avoiding the need to ifdef each call individually.
+ */
+# define FLAG_AVX10_256 0
+# define FLAG_AVX10_512 0
+#endif
+
+static inline struct aes_gcm_key *
+aes_gcm_key_get(struct crypto_aead *tfm, int flags)
+{
+ if (flags & (FLAG_AVX10_256 | FLAG_AVX10_512))
+ return PTR_ALIGN(crypto_aead_ctx(tfm), 64);
+ else
+ return PTR_ALIGN(crypto_aead_ctx(tfm), 16);
+}
+
+asmlinkage void
+aes_gcm_precompute_aesni(struct aes_gcm_key_aesni *key);
+asmlinkage void
+aes_gcm_precompute_aesni_avx(struct aes_gcm_key_aesni *key);
+asmlinkage void
+aes_gcm_precompute_vaes_avx10_256(struct aes_gcm_key_avx10 *key);
+asmlinkage void
+aes_gcm_precompute_vaes_avx10_512(struct aes_gcm_key_avx10 *key);
+
+static void aes_gcm_precompute(struct aes_gcm_key *key, int flags)
+{
+ /*
+ * To make things a bit easier on the assembly side, the AVX10
+ * implementations use the same key format. Therefore, a single
+ * function using 256-bit vectors would suffice here. However, it's
+ * straightforward to provide a 512-bit one because of how the assembly
+ * code is structured, and it works nicely because the total size of the
+ * key powers is a multiple of 512 bits. So we take advantage of that.
+ *
+ * A similar situation applies to the AES-NI implementations.
+ */
+ if (flags & FLAG_AVX10_512)
+ aes_gcm_precompute_vaes_avx10_512(AES_GCM_KEY_AVX10(key));
+ else if (flags & FLAG_AVX10_256)
+ aes_gcm_precompute_vaes_avx10_256(AES_GCM_KEY_AVX10(key));
+ else if (flags & FLAG_AVX)
+ aes_gcm_precompute_aesni_avx(AES_GCM_KEY_AESNI(key));
+ else
+ aes_gcm_precompute_aesni(AES_GCM_KEY_AESNI(key));
+}
+
+asmlinkage void
+aes_gcm_aad_update_aesni(const struct aes_gcm_key_aesni *key,
+ u8 ghash_acc[16], const u8 *aad, int aadlen);
+asmlinkage void
+aes_gcm_aad_update_aesni_avx(const struct aes_gcm_key_aesni *key,
+ u8 ghash_acc[16], const u8 *aad, int aadlen);
+asmlinkage void
+aes_gcm_aad_update_vaes_avx10(const struct aes_gcm_key_avx10 *key,
+ u8 ghash_acc[16], const u8 *aad, int aadlen);
+
+static void aes_gcm_aad_update(const struct aes_gcm_key *key, u8 ghash_acc[16],
+ const u8 *aad, int aadlen, int flags)
+{
+ if (flags & (FLAG_AVX10_256 | FLAG_AVX10_512))
+ aes_gcm_aad_update_vaes_avx10(AES_GCM_KEY_AVX10(key), ghash_acc,
+ aad, aadlen);
+ else if (flags & FLAG_AVX)
+ aes_gcm_aad_update_aesni_avx(AES_GCM_KEY_AESNI(key), ghash_acc,
+ aad, aadlen);
+ else
+ aes_gcm_aad_update_aesni(AES_GCM_KEY_AESNI(key), ghash_acc,
+ aad, aadlen);
+}
+
+asmlinkage void
+aes_gcm_enc_update_aesni(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+asmlinkage void
+aes_gcm_enc_update_aesni_avx(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+asmlinkage void
+aes_gcm_enc_update_vaes_avx10_256(const struct aes_gcm_key_avx10 *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+asmlinkage void
+aes_gcm_enc_update_vaes_avx10_512(const struct aes_gcm_key_avx10 *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+
+asmlinkage void
+aes_gcm_dec_update_aesni(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+asmlinkage void
+aes_gcm_dec_update_aesni_avx(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+asmlinkage void
+aes_gcm_dec_update_vaes_avx10_256(const struct aes_gcm_key_avx10 *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+asmlinkage void
+aes_gcm_dec_update_vaes_avx10_512(const struct aes_gcm_key_avx10 *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen);
+
+/* __always_inline to optimize out the branches based on @flags */
+static __always_inline void
+aes_gcm_update(const struct aes_gcm_key *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ const u8 *src, u8 *dst, int datalen, int flags)
+{
+ if (flags & FLAG_ENC) {
+ if (flags & FLAG_AVX10_512)
+ aes_gcm_enc_update_vaes_avx10_512(AES_GCM_KEY_AVX10(key),
+ le_ctr, ghash_acc,
+ src, dst, datalen);
+ else if (flags & FLAG_AVX10_256)
+ aes_gcm_enc_update_vaes_avx10_256(AES_GCM_KEY_AVX10(key),
+ le_ctr, ghash_acc,
+ src, dst, datalen);
+ else if (flags & FLAG_AVX)
+ aes_gcm_enc_update_aesni_avx(AES_GCM_KEY_AESNI(key),
+ le_ctr, ghash_acc,
+ src, dst, datalen);
+ else
+ aes_gcm_enc_update_aesni(AES_GCM_KEY_AESNI(key), le_ctr,
+ ghash_acc, src, dst, datalen);
+ } else {
+ if (flags & FLAG_AVX10_512)
+ aes_gcm_dec_update_vaes_avx10_512(AES_GCM_KEY_AVX10(key),
+ le_ctr, ghash_acc,
+ src, dst, datalen);
+ else if (flags & FLAG_AVX10_256)
+ aes_gcm_dec_update_vaes_avx10_256(AES_GCM_KEY_AVX10(key),
+ le_ctr, ghash_acc,
+ src, dst, datalen);
+ else if (flags & FLAG_AVX)
+ aes_gcm_dec_update_aesni_avx(AES_GCM_KEY_AESNI(key),
+ le_ctr, ghash_acc,
+ src, dst, datalen);
+ else
+ aes_gcm_dec_update_aesni(AES_GCM_KEY_AESNI(key),
+ le_ctr, ghash_acc,
+ src, dst, datalen);
+ }
+}
+
+asmlinkage void
+aes_gcm_enc_final_aesni(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ u64 total_aadlen, u64 total_datalen);
+asmlinkage void
+aes_gcm_enc_final_aesni_avx(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ u64 total_aadlen, u64 total_datalen);
+asmlinkage void
+aes_gcm_enc_final_vaes_avx10(const struct aes_gcm_key_avx10 *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ u64 total_aadlen, u64 total_datalen);
+
+/* __always_inline to optimize out the branches based on @flags */
+static __always_inline void
+aes_gcm_enc_final(const struct aes_gcm_key *key,
+ const u32 le_ctr[4], u8 ghash_acc[16],
+ u64 total_aadlen, u64 total_datalen, int flags)
+{
+ if (flags & (FLAG_AVX10_256 | FLAG_AVX10_512))
+ aes_gcm_enc_final_vaes_avx10(AES_GCM_KEY_AVX10(key),
+ le_ctr, ghash_acc,
+ total_aadlen, total_datalen);
+ else if (flags & FLAG_AVX)
+ aes_gcm_enc_final_aesni_avx(AES_GCM_KEY_AESNI(key),
+ le_ctr, ghash_acc,
+ total_aadlen, total_datalen);
+ else
+ aes_gcm_enc_final_aesni(AES_GCM_KEY_AESNI(key),
+ le_ctr, ghash_acc,
+ total_aadlen, total_datalen);
+}
+
+asmlinkage bool __must_check
+aes_gcm_dec_final_aesni(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], const u8 ghash_acc[16],
+ u64 total_aadlen, u64 total_datalen,
+ const u8 tag[16], int taglen);
+asmlinkage bool __must_check
+aes_gcm_dec_final_aesni_avx(const struct aes_gcm_key_aesni *key,
+ const u32 le_ctr[4], const u8 ghash_acc[16],
+ u64 total_aadlen, u64 total_datalen,
+ const u8 tag[16], int taglen);
+asmlinkage bool __must_check
+aes_gcm_dec_final_vaes_avx10(const struct aes_gcm_key_avx10 *key,
+ const u32 le_ctr[4], const u8 ghash_acc[16],
+ u64 total_aadlen, u64 total_datalen,
+ const u8 tag[16], int taglen);
+
+/* __always_inline to optimize out the branches based on @flags */
+static __always_inline bool __must_check
+aes_gcm_dec_final(const struct aes_gcm_key *key, const u32 le_ctr[4],
+ u8 ghash_acc[16], u64 total_aadlen, u64 total_datalen,
+ u8 tag[16], int taglen, int flags)
+{
+ if (flags & (FLAG_AVX10_256 | FLAG_AVX10_512))
+ return aes_gcm_dec_final_vaes_avx10(AES_GCM_KEY_AVX10(key),
+ le_ctr, ghash_acc,
+ total_aadlen, total_datalen,
+ tag, taglen);
+ else if (flags & FLAG_AVX)
+ return aes_gcm_dec_final_aesni_avx(AES_GCM_KEY_AESNI(key),
+ le_ctr, ghash_acc,
+ total_aadlen, total_datalen,
+ tag, taglen);
+ else
+ return aes_gcm_dec_final_aesni(AES_GCM_KEY_AESNI(key),
+ le_ctr, ghash_acc,
+ total_aadlen, total_datalen,
+ tag, taglen);
+}
+
+/*
+ * This is the Integrity Check Value (aka the authentication tag) length and can
+ * be 8, 12 or 16 bytes long.
+ */
+static int common_rfc4106_set_authsize(struct crypto_aead *aead,
+ unsigned int authsize)
+{
+ switch (authsize) {
+ case 8:
+ case 12:
+ case 16:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
+ unsigned int authsize)
+{
+ switch (authsize) {
+ case 4:
+ case 8:
+ case 12:
+ case 13:
+ case 14:
+ case 15:
+ case 16:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/*
+ * This is the setkey function for the x86_64 implementations of AES-GCM. It
+ * saves the RFC4106 nonce if applicable, expands the AES key, and precomputes
+ * powers of the hash key.
+ *
+ * To comply with the crypto_aead API, this has to be usable in no-SIMD context.
+ * For that reason, this function includes a portable C implementation of the
+ * needed logic. However, the portable C implementation is very slow, taking
+ * about the same time as encrypting 37 KB of data. To be ready for users that
+ * may set a key even somewhat frequently, we therefore also include a SIMD
+ * assembly implementation, expanding the AES key using AES-NI and precomputing
+ * the hash key powers using PCLMULQDQ or VPCLMULQDQ.
+ */
+static int gcm_setkey(struct crypto_aead *tfm, const u8 *raw_key,
+ unsigned int keylen, int flags)
+{
+ struct aes_gcm_key *key = aes_gcm_key_get(tfm, flags);
+ int err;
+
+ if (flags & FLAG_RFC4106) {
+ if (keylen < 4)
+ return -EINVAL;
+ keylen -= 4;
+ key->rfc4106_nonce = get_unaligned_be32(raw_key + keylen);
+ }
+
+ /* The assembly code assumes the following offsets. */
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_aesni, base.aes_key.key_enc) != 0);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_aesni, base.aes_key.key_length) != 480);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_aesni, h_powers) != 496);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_aesni, h_powers_xored) != 624);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_aesni, h_times_x64) != 688);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_avx10, base.aes_key.key_enc) != 0);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_avx10, base.aes_key.key_length) != 480);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_avx10, h_powers) != 512);
+ BUILD_BUG_ON(offsetof(struct aes_gcm_key_avx10, padding) != 768);
+
+ if (likely(crypto_simd_usable())) {
+ err = aes_check_keylen(keylen);
+ if (err)
+ return err;
+ kernel_fpu_begin();
+ aesni_set_key(&key->aes_key, raw_key, keylen);
+ aes_gcm_precompute(key, flags);
+ kernel_fpu_end();
+ } else {
+ static const u8 x_to_the_minus1[16] __aligned(__alignof__(be128)) = {
+ [0] = 0xc2, [15] = 1
+ };
+ static const u8 x_to_the_63[16] __aligned(__alignof__(be128)) = {
+ [7] = 1,
+ };
+ be128 h1 = {};
+ be128 h;
+ int i;
+
+ err = aes_expandkey(&key->aes_key, raw_key, keylen);
+ if (err)
+ return err;
+
+ /* Encrypt the all-zeroes block to get the hash key H^1 */
+ aes_encrypt(&key->aes_key, (u8 *)&h1, (u8 *)&h1);
+
+ /* Compute H^1 * x^-1 */
+ h = h1;
+ gf128mul_lle(&h, (const be128 *)x_to_the_minus1);
+
+ /* Compute the needed key powers */
+ if (flags & (FLAG_AVX10_256 | FLAG_AVX10_512)) {
+ struct aes_gcm_key_avx10 *k = AES_GCM_KEY_AVX10(key);
+
+ for (i = ARRAY_SIZE(k->h_powers) - 1; i >= 0; i--) {
+ k->h_powers[i][0] = be64_to_cpu(h.b);
+ k->h_powers[i][1] = be64_to_cpu(h.a);
+ gf128mul_lle(&h, &h1);
+ }
+ memset(k->padding, 0, sizeof(k->padding));
+ } else {
+ struct aes_gcm_key_aesni *k = AES_GCM_KEY_AESNI(key);
+
+ for (i = ARRAY_SIZE(k->h_powers) - 1; i >= 0; i--) {
+ k->h_powers[i][0] = be64_to_cpu(h.b);
+ k->h_powers[i][1] = be64_to_cpu(h.a);
+ k->h_powers_xored[i] = k->h_powers[i][0] ^
+ k->h_powers[i][1];
+ gf128mul_lle(&h, &h1);
+ }
+ gf128mul_lle(&h1, (const be128 *)x_to_the_63);
+ k->h_times_x64[0] = be64_to_cpu(h1.b);
+ k->h_times_x64[1] = be64_to_cpu(h1.a);
+ }
+ }
+ return 0;
+}
+
+/*
+ * Initialize @ghash_acc, then pass all @assoclen bytes of associated data
+ * (a.k.a. additional authenticated data) from @sg_src through the GHASH update
+ * assembly function. kernel_fpu_begin() must have already been called.
+ */
+static void gcm_process_assoc(const struct aes_gcm_key *key, u8 ghash_acc[16],
+ struct scatterlist *sg_src, unsigned int assoclen,
+ int flags)
+{
+ struct scatter_walk walk;
+ /*
+ * The assembly function requires that the length of any non-last
+ * segment of associated data be a multiple of 16 bytes, so this
+ * function does the buffering needed to achieve that.
+ */
+ unsigned int pos = 0;
+ u8 buf[16];
+
+ memset(ghash_acc, 0, 16);
+ scatterwalk_start(&walk, sg_src);
+
+ while (assoclen) {
+ unsigned int len_this_page = scatterwalk_clamp(&walk, assoclen);
+ void *mapped = scatterwalk_map(&walk);
+ const void *src = mapped;
+ unsigned int len;
+
+ assoclen -= len_this_page;
+ scatterwalk_advance(&walk, len_this_page);
+ if (unlikely(pos)) {
+ len = min(len_this_page, 16 - pos);
+ memcpy(&buf[pos], src, len);
+ pos += len;
+ src += len;
+ len_this_page -= len;
+ if (pos < 16)
+ goto next;
+ aes_gcm_aad_update(key, ghash_acc, buf, 16, flags);
+ pos = 0;
+ }
+ len = len_this_page;
+ if (unlikely(assoclen)) /* Not the last segment yet? */
+ len = round_down(len, 16);
+ aes_gcm_aad_update(key, ghash_acc, src, len, flags);
+ src += len;
+ len_this_page -= len;
+ if (unlikely(len_this_page)) {
+ memcpy(buf, src, len_this_page);
+ pos = len_this_page;
+ }
+next:
+ scatterwalk_unmap(mapped);
+ scatterwalk_pagedone(&walk, 0, assoclen);
+ if (need_resched()) {
+ kernel_fpu_end();
+ kernel_fpu_begin();
+ }
+ }
+ if (unlikely(pos))
+ aes_gcm_aad_update(key, ghash_acc, buf, pos, flags);
+}
+
+
+/* __always_inline to optimize out the branches based on @flags */
+static __always_inline int
+gcm_crypt(struct aead_request *req, int flags)
+{
+ struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+ const struct aes_gcm_key *key = aes_gcm_key_get(tfm, flags);
+ unsigned int assoclen = req->assoclen;
+ struct skcipher_walk walk;
+ unsigned int nbytes;
+ u8 ghash_acc[16]; /* GHASH accumulator */
+ u32 le_ctr[4]; /* Counter in little-endian format */
+ int taglen;
+ int err;
+
+ /* Initialize the counter and determine the associated data length. */
+ le_ctr[0] = 2;
+ if (flags & FLAG_RFC4106) {
+ if (unlikely(assoclen != 16 && assoclen != 20))
+ return -EINVAL;
+ assoclen -= 8;
+ le_ctr[1] = get_unaligned_be32(req->iv + 4);
+ le_ctr[2] = get_unaligned_be32(req->iv + 0);
+ le_ctr[3] = key->rfc4106_nonce; /* already byte-swapped */
+ } else {
+ le_ctr[1] = get_unaligned_be32(req->iv + 8);
+ le_ctr[2] = get_unaligned_be32(req->iv + 4);
+ le_ctr[3] = get_unaligned_be32(req->iv + 0);
+ }
+
+ /* Begin walking through the plaintext or ciphertext. */
+ if (flags & FLAG_ENC)
+ err = skcipher_walk_aead_encrypt(&walk, req, false);
+ else
+ err = skcipher_walk_aead_decrypt(&walk, req, false);
+
+ /*
+ * Since the AES-GCM assembly code requires that at least three assembly
+ * functions be called to process any message (this is needed to support
+ * incremental updates cleanly), to reduce overhead we try to do all
+ * three calls in the same kernel FPU section if possible. We close the
+ * section and start a new one if there are multiple data segments or if
+ * rescheduling is needed while processing the associated data.
+ */
+ kernel_fpu_begin();
+
+ /* Pass the associated data through GHASH. */
+ gcm_process_assoc(key, ghash_acc, req->src, assoclen, flags);
+
+ /* En/decrypt the data and pass the ciphertext through GHASH. */
+ while ((nbytes = walk.nbytes) != 0) {
+ if (unlikely(nbytes < walk.total)) {
+ /*
+ * Non-last segment. In this case, the assembly
+ * function requires that the length be a multiple of 16
+ * (AES_BLOCK_SIZE) bytes. The needed buffering of up
+ * to 16 bytes is handled by the skcipher_walk. Here we
+ * just need to round down to a multiple of 16.
+ */
+ nbytes = round_down(nbytes, AES_BLOCK_SIZE);
+ aes_gcm_update(key, le_ctr, ghash_acc,
+ walk.src.virt.addr, walk.dst.virt.addr,
+ nbytes, flags);
+ le_ctr[0] += nbytes / AES_BLOCK_SIZE;
+ kernel_fpu_end();
+ err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+ kernel_fpu_begin();
+ } else {
+ /* Last segment: process all remaining data. */
+ aes_gcm_update(key, le_ctr, ghash_acc,
+ walk.src.virt.addr, walk.dst.virt.addr,
+ nbytes, flags);
+ err = skcipher_walk_done(&walk, 0);
+ /*
+ * The low word of the counter isn't used by the
+ * finalize, so there's no need to increment it here.
+ */
+ }
+ }
+ if (err)
+ goto out;
+
+ /* Finalize */
+ taglen = crypto_aead_authsize(tfm);
+ if (flags & FLAG_ENC) {
+ /* Finish computing the auth tag. */
+ aes_gcm_enc_final(key, le_ctr, ghash_acc, assoclen,
+ req->cryptlen, flags);
+
+ /* Store the computed auth tag in the dst scatterlist. */
+ scatterwalk_map_and_copy(ghash_acc, req->dst, req->assoclen +
+ req->cryptlen, taglen, 1);
+ } else {
+ unsigned int datalen = req->cryptlen - taglen;
+ u8 tag[16];
+
+ /* Get the transmitted auth tag from the src scatterlist. */
+ scatterwalk_map_and_copy(tag, req->src, req->assoclen + datalen,
+ taglen, 0);
+ /*
+ * Finish computing the auth tag and compare it to the
+ * transmitted one. The assembly function does the actual tag
+ * comparison. Here, just check the boolean result.
+ */
+ if (!aes_gcm_dec_final(key, le_ctr, ghash_acc, assoclen,
+ datalen, tag, taglen, flags))
+ err = -EBADMSG;
+ }
+out:
+ kernel_fpu_end();
+ return err;
+}
+
+#define DEFINE_GCM_ALGS(suffix, flags, generic_driver_name, rfc_driver_name, \
+ ctxsize, priority) \
+ \
+static int gcm_setkey_##suffix(struct crypto_aead *tfm, const u8 *raw_key, \
+ unsigned int keylen) \
+{ \
+ return gcm_setkey(tfm, raw_key, keylen, (flags)); \
+} \
+ \
+static int gcm_encrypt_##suffix(struct aead_request *req) \
+{ \
+ return gcm_crypt(req, (flags) | FLAG_ENC); \
+} \
+ \
+static int gcm_decrypt_##suffix(struct aead_request *req) \
+{ \
+ return gcm_crypt(req, (flags)); \
+} \
+ \
+static int rfc4106_setkey_##suffix(struct crypto_aead *tfm, const u8 *raw_key, \
+ unsigned int keylen) \
+{ \
+ return gcm_setkey(tfm, raw_key, keylen, (flags) | FLAG_RFC4106); \
+} \
+ \
+static int rfc4106_encrypt_##suffix(struct aead_request *req) \
+{ \
+ return gcm_crypt(req, (flags) | FLAG_RFC4106 | FLAG_ENC); \
+} \
+ \
+static int rfc4106_decrypt_##suffix(struct aead_request *req) \
+{ \
+ return gcm_crypt(req, (flags) | FLAG_RFC4106); \
+} \
+ \
+static struct aead_alg aes_gcm_algs_##suffix[] = { { \
+ .setkey = gcm_setkey_##suffix, \
+ .setauthsize = generic_gcmaes_set_authsize, \
+ .encrypt = gcm_encrypt_##suffix, \
+ .decrypt = gcm_decrypt_##suffix, \
+ .ivsize = GCM_AES_IV_SIZE, \
+ .chunksize = AES_BLOCK_SIZE, \
+ .maxauthsize = 16, \
+ .base = { \
+ .cra_name = "__gcm(aes)", \
+ .cra_driver_name = "__" generic_driver_name, \
+ .cra_priority = (priority), \
+ .cra_flags = CRYPTO_ALG_INTERNAL, \
+ .cra_blocksize = 1, \
+ .cra_ctxsize = (ctxsize), \
+ .cra_module = THIS_MODULE, \
+ }, \
+}, { \
+ .setkey = rfc4106_setkey_##suffix, \
+ .setauthsize = common_rfc4106_set_authsize, \
+ .encrypt = rfc4106_encrypt_##suffix, \
+ .decrypt = rfc4106_decrypt_##suffix, \
+ .ivsize = GCM_RFC4106_IV_SIZE, \
+ .chunksize = AES_BLOCK_SIZE, \
+ .maxauthsize = 16, \
+ .base = { \
+ .cra_name = "__rfc4106(gcm(aes))", \
+ .cra_driver_name = "__" rfc_driver_name, \
+ .cra_priority = (priority), \
+ .cra_flags = CRYPTO_ALG_INTERNAL, \
+ .cra_blocksize = 1, \
+ .cra_ctxsize = (ctxsize), \
+ .cra_module = THIS_MODULE, \
+ }, \
+} }; \
+ \
+static struct simd_aead_alg *aes_gcm_simdalgs_##suffix[2] \
+
+/* aes_gcm_algs_aesni */
+DEFINE_GCM_ALGS(aesni, /* no flags */ 0,
+ "generic-gcm-aesni", "rfc4106-gcm-aesni",
+ AES_GCM_KEY_AESNI_SIZE, 400);
+
+/* aes_gcm_algs_aesni_avx */
+DEFINE_GCM_ALGS(aesni_avx, FLAG_AVX,
+ "generic-gcm-aesni-avx", "rfc4106-gcm-aesni-avx",
+ AES_GCM_KEY_AESNI_SIZE, 500);
+
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+/* aes_gcm_algs_vaes_avx10_256 */
+DEFINE_GCM_ALGS(vaes_avx10_256, FLAG_AVX10_256,
+ "generic-gcm-vaes-avx10_256", "rfc4106-gcm-vaes-avx10_256",
+ AES_GCM_KEY_AVX10_SIZE, 700);
+
+/* aes_gcm_algs_vaes_avx10_512 */
+DEFINE_GCM_ALGS(vaes_avx10_512, FLAG_AVX10_512,
+ "generic-gcm-vaes-avx10_512", "rfc4106-gcm-vaes-avx10_512",
+ AES_GCM_KEY_AVX10_SIZE, 800);
+#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
+
/*
* This is a list of CPU models that are known to suffer from downclocking when
- * zmm registers (512-bit vectors) are used. On these CPUs, the AES-XTS
- * implementation with zmm registers won't be used by default. An
- * implementation with ymm registers (256-bit vectors) will be used instead.
+ * zmm registers (512-bit vectors) are used. On these CPUs, the AES mode
+ * implementations with zmm registers won't be used by default. Implementations
+ * with ymm registers (256-bit vectors) will be used by default instead.
*/
static const struct x86_cpu_id zmm_exclusion_list[] = {
X86_MATCH_VFM(INTEL_SKYLAKE_X, 0),
@@ -1236,7 +1559,7 @@ static const struct x86_cpu_id zmm_exclusion_list[] = {
{},
};
-static int __init register_xts_algs(void)
+static int __init register_avx_algs(void)
{
int err;
@@ -1246,6 +1569,11 @@ static int __init register_xts_algs(void)
&aes_xts_simdalg_aesni_avx);
if (err)
return err;
+ err = simd_register_aeads_compat(aes_gcm_algs_aesni_avx,
+ ARRAY_SIZE(aes_gcm_algs_aesni_avx),
+ aes_gcm_simdalgs_aesni_avx);
+ if (err)
+ return err;
#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
if (!boot_cpu_has(X86_FEATURE_AVX2) ||
!boot_cpu_has(X86_FEATURE_VAES) ||
@@ -1269,23 +1597,42 @@ static int __init register_xts_algs(void)
&aes_xts_simdalg_vaes_avx10_256);
if (err)
return err;
+ err = simd_register_aeads_compat(aes_gcm_algs_vaes_avx10_256,
+ ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256),
+ aes_gcm_simdalgs_vaes_avx10_256);
+ if (err)
+ return err;
+
+ if (x86_match_cpu(zmm_exclusion_list)) {
+ int i;
- if (x86_match_cpu(zmm_exclusion_list))
aes_xts_alg_vaes_avx10_512.base.cra_priority = 1;
+ for (i = 0; i < ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512); i++)
+ aes_gcm_algs_vaes_avx10_512[i].base.cra_priority = 1;
+ }
err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_512, 1,
&aes_xts_simdalg_vaes_avx10_512);
if (err)
return err;
+ err = simd_register_aeads_compat(aes_gcm_algs_vaes_avx10_512,
+ ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512),
+ aes_gcm_simdalgs_vaes_avx10_512);
+ if (err)
+ return err;
#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
return 0;
}
-static void unregister_xts_algs(void)
+static void unregister_avx_algs(void)
{
if (aes_xts_simdalg_aesni_avx)
simd_unregister_skciphers(&aes_xts_alg_aesni_avx, 1,
&aes_xts_simdalg_aesni_avx);
+ if (aes_gcm_simdalgs_aesni_avx[0])
+ simd_unregister_aeads(aes_gcm_algs_aesni_avx,
+ ARRAY_SIZE(aes_gcm_algs_aesni_avx),
+ aes_gcm_simdalgs_aesni_avx);
#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
if (aes_xts_simdalg_vaes_avx2)
simd_unregister_skciphers(&aes_xts_alg_vaes_avx2, 1,
@@ -1293,106 +1640,33 @@ static void unregister_xts_algs(void)
if (aes_xts_simdalg_vaes_avx10_256)
simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_256, 1,
&aes_xts_simdalg_vaes_avx10_256);
+ if (aes_gcm_simdalgs_vaes_avx10_256[0])
+ simd_unregister_aeads(aes_gcm_algs_vaes_avx10_256,
+ ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256),
+ aes_gcm_simdalgs_vaes_avx10_256);
if (aes_xts_simdalg_vaes_avx10_512)
simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_512, 1,
&aes_xts_simdalg_vaes_avx10_512);
+ if (aes_gcm_simdalgs_vaes_avx10_512[0])
+ simd_unregister_aeads(aes_gcm_algs_vaes_avx10_512,
+ ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512),
+ aes_gcm_simdalgs_vaes_avx10_512);
#endif
}
#else /* CONFIG_X86_64 */
-static int __init register_xts_algs(void)
+static struct aead_alg aes_gcm_algs_aesni[0];
+static struct simd_aead_alg *aes_gcm_simdalgs_aesni[0];
+
+static int __init register_avx_algs(void)
{
return 0;
}
-static void unregister_xts_algs(void)
+static void unregister_avx_algs(void)
{
}
#endif /* !CONFIG_X86_64 */
-#ifdef CONFIG_X86_64
-static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
- unsigned int key_len)
-{
- struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead);
-
- return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?:
- aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded,
- ctx->hash_subkey);
-}
-
-static int generic_gcmaes_encrypt(struct aead_request *req)
-{
- struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
- void *aes_ctx = &(ctx->aes_key_expanded);
- u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
- u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
- __be32 counter = cpu_to_be32(1);
-
- memcpy(iv, req->iv, 12);
- *((__be32 *)(iv+12)) = counter;
-
- return gcmaes_encrypt(req, req->assoclen, ctx->hash_subkey, iv,
- aes_ctx);
-}
-
-static int generic_gcmaes_decrypt(struct aead_request *req)
-{
- __be32 counter = cpu_to_be32(1);
- struct crypto_aead *tfm = crypto_aead_reqtfm(req);
- struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
- void *aes_ctx = &(ctx->aes_key_expanded);
- u8 ivbuf[16 + (AESNI_ALIGN - 8)] __aligned(8);
- u8 *iv = PTR_ALIGN(&ivbuf[0], AESNI_ALIGN);
-
- memcpy(iv, req->iv, 12);
- *((__be32 *)(iv+12)) = counter;
-
- return gcmaes_decrypt(req, req->assoclen, ctx->hash_subkey, iv,
- aes_ctx);
-}
-
-static struct aead_alg aesni_aeads[] = { {
- .setkey = common_rfc4106_set_key,
- .setauthsize = common_rfc4106_set_authsize,
- .encrypt = helper_rfc4106_encrypt,
- .decrypt = helper_rfc4106_decrypt,
- .ivsize = GCM_RFC4106_IV_SIZE,
- .maxauthsize = 16,
- .base = {
- .cra_name = "__rfc4106(gcm(aes))",
- .cra_driver_name = "__rfc4106-gcm-aesni",
- .cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
- .cra_blocksize = 1,
- .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx),
- .cra_alignmask = 0,
- .cra_module = THIS_MODULE,
- },
-}, {
- .setkey = generic_gcmaes_set_key,
- .setauthsize = generic_gcmaes_set_authsize,
- .encrypt = generic_gcmaes_encrypt,
- .decrypt = generic_gcmaes_decrypt,
- .ivsize = GCM_AES_IV_SIZE,
- .maxauthsize = 16,
- .base = {
- .cra_name = "__gcm(aes)",
- .cra_driver_name = "__generic-gcm-aesni",
- .cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
- .cra_blocksize = 1,
- .cra_ctxsize = sizeof(struct generic_gcmaes_ctx),
- .cra_alignmask = 0,
- .cra_module = THIS_MODULE,
- },
-} };
-#else
-static struct aead_alg aesni_aeads[0];
-#endif
-
-static struct simd_aead_alg *aesni_simd_aeads[ARRAY_SIZE(aesni_aeads)];
-
static const struct x86_cpu_id aesni_cpu_id[] = {
X86_MATCH_FEATURE(X86_FEATURE_AES, NULL),
{}
@@ -1406,17 +1680,6 @@ static int __init aesni_init(void)
if (!x86_match_cpu(aesni_cpu_id))
return -ENODEV;
#ifdef CONFIG_X86_64
- if (boot_cpu_has(X86_FEATURE_AVX2)) {
- pr_info("AVX2 version of gcm_enc/dec engaged.\n");
- static_branch_enable(&gcm_use_avx);
- static_branch_enable(&gcm_use_avx2);
- } else
- if (boot_cpu_has(X86_FEATURE_AVX)) {
- pr_info("AVX version of gcm_enc/dec engaged.\n");
- static_branch_enable(&gcm_use_avx);
- } else {
- pr_info("SSE version of gcm_enc/dec engaged.\n");
- }
if (boot_cpu_has(X86_FEATURE_AVX)) {
/* optimize performance of ctr mode encryption transform */
static_call_update(aesni_ctr_enc_tfm, aesni_ctr_enc_avx_tfm);
@@ -1434,8 +1697,9 @@ static int __init aesni_init(void)
if (err)
goto unregister_cipher;
- err = simd_register_aeads_compat(aesni_aeads, ARRAY_SIZE(aesni_aeads),
- aesni_simd_aeads);
+ err = simd_register_aeads_compat(aes_gcm_algs_aesni,
+ ARRAY_SIZE(aes_gcm_algs_aesni),
+ aes_gcm_simdalgs_aesni);
if (err)
goto unregister_skciphers;
@@ -1447,22 +1711,22 @@ static int __init aesni_init(void)
goto unregister_aeads;
#endif /* CONFIG_X86_64 */
- err = register_xts_algs();
+ err = register_avx_algs();
if (err)
- goto unregister_xts;
+ goto unregister_avx;
return 0;
-unregister_xts:
- unregister_xts_algs();
+unregister_avx:
+ unregister_avx_algs();
#ifdef CONFIG_X86_64
if (aesni_simd_xctr)
simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
unregister_aeads:
#endif /* CONFIG_X86_64 */
- simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads),
- aesni_simd_aeads);
-
+ simd_unregister_aeads(aes_gcm_algs_aesni,
+ ARRAY_SIZE(aes_gcm_algs_aesni),
+ aes_gcm_simdalgs_aesni);
unregister_skciphers:
simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
aesni_simd_skciphers);
@@ -1473,8 +1737,9 @@ unregister_cipher:
static void __exit aesni_exit(void)
{
- simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads),
- aesni_simd_aeads);
+ simd_unregister_aeads(aes_gcm_algs_aesni,
+ ARRAY_SIZE(aes_gcm_algs_aesni),
+ aes_gcm_simdalgs_aesni);
simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
aesni_simd_skciphers);
crypto_unregister_alg(&aesni_cipher_alg);
@@ -1482,7 +1747,7 @@ static void __exit aesni_exit(void)
if (boot_cpu_has(X86_FEATURE_AVX))
simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
#endif /* CONFIG_X86_64 */
- unregister_xts_algs();
+ unregister_avx_algs();
}
late_initcall(aesni_init);
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 98cf3b4e4c9f..9f5e342b9845 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -195,6 +195,7 @@ module_init(crc32_pclmul_mod_init);
module_exit(crc32_pclmul_mod_fini);
MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
+MODULE_DESCRIPTION("CRC32 algorithm (IEEE 802.3) accelerated with PCLMULQDQ");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CRYPTO("crc32");
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
index d55fa9e9b9e6..dcfc0de333de 100644
--- a/arch/x86/crypto/curve25519-x86_64.c
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -1720,5 +1720,6 @@ module_exit(curve25519_mod_exit);
MODULE_ALIAS_CRYPTO("curve25519");
MODULE_ALIAS_CRYPTO("curve25519-x86");
+MODULE_DESCRIPTION("Curve25519 algorithm, ADX optimized");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 1dfb8af48a3c..08ff4b489f7e 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -12,7 +12,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sizes.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/simd.h>
asmlinkage void poly1305_init_x86_64(void *ctx,
@@ -269,7 +269,7 @@ static int __init poly1305_simd_mod_init(void)
boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) &&
cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) &&
/* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */
- boot_cpu_data.x86_model != INTEL_FAM6_SKYLAKE_X)
+ boot_cpu_data.x86_vfm != INTEL_SKYLAKE_X)
static_branch_enable(&poly1305_use_avx512);
return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? crypto_register_shash(&alg) : 0;
}
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 90454cf18e0d..1a1ecfa7f72a 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -5,6 +5,7 @@
* Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
*/
+#include <asm/cpu_device_id.h>
#include <crypto/algapi.h>
#include <crypto/twofish.h>
#include <linux/crypto.h>
@@ -107,10 +108,10 @@ static bool is_blacklisted_cpu(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return false;
- if (boot_cpu_data.x86 == 0x06 &&
- (boot_cpu_data.x86_model == 0x1c ||
- boot_cpu_data.x86_model == 0x26 ||
- boot_cpu_data.x86_model == 0x36)) {
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_ATOM_BONNELL:
+ case INTEL_ATOM_BONNELL_MID:
+ case INTEL_ATOM_SALTWELL:
/*
* On Atom, twofish-3way is slower than original assembler
* implementation. Twofish-3way trades off some performance in
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 11c9b8efdc4c..ed0a5f2dc129 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -89,10 +89,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
cld
- IBRS_ENTER
- UNTRAIN_RET
- CLEAR_BRANCH_HISTORY
-
/*
* SYSENTER doesn't filter flags, so we need to clear NT and AC
* ourselves. To save a few cycles, we can check whether
@@ -116,6 +112,16 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
jnz .Lsysenter_fix_flags
.Lsysenter_flags_fixed:
+ /*
+ * CPU bugs mitigations mechanisms can call other functions. They
+ * should be invoked after making sure TF is cleared because
+ * single-step is ignored only for instructions inside the
+ * entry_SYSENTER_compat function.
+ */
+ IBRS_ENTER
+ UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
+
movq %rsp, %rdi
call do_SYSENTER_32
jmp sysret32_from_system_call
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index c2235bae17ef..8cc9950d7104 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -14,9 +14,12 @@
#endif
#define __SYSCALL(nr, sym) extern long __ia32_##sym(const struct pt_regs *);
-
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __ia32_##sym(const struct pt_regs *);
#include <asm/syscalls_32.h>
-#undef __SYSCALL
+#undef __SYSCALL
+
+#undef __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
/*
* The sys_call_table[] is no longer used for system calls, but
@@ -28,11 +31,10 @@
const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_32.h>
};
-#undef __SYSCALL
+#undef __SYSCALL
#endif
#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
-
long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
{
switch (nr) {
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index 33b3f09e6f15..ba8354424860 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -8,8 +8,12 @@
#include <asm/syscall.h>
#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
#include <asm/syscalls_64.h>
-#undef __SYSCALL
+#undef __SYSCALL
+
+#undef __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
/*
* The sys_call_table[] is no longer used for system calls, but
@@ -20,10 +24,9 @@
const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_64.h>
};
-#undef __SYSCALL
+#undef __SYSCALL
#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-
long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
{
switch (nr) {
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index 03de4a932131..fb77908f44f3 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -8,11 +8,14 @@
#include <asm/syscall.h>
#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
#include <asm/syscalls_x32.h>
-#undef __SYSCALL
+#undef __SYSCALL
-#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+#undef __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
{
switch (nr) {
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index d6ebcab1d8b2..534c74b14fab 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -1,8 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
#
# 32-bit system call numbers and entry vectors
#
# The format is:
-# <number> <abi> <name> <entry point> <compat entry point>
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
#
# The __ia32_sys and __ia32_compat_sys stubs are created on-the-fly for
# sys_*() system calls and compat_sys_*() compat system calls if
@@ -12,7 +13,7 @@
# The abi is always "i386" for this file.
#
0 i386 restart_syscall sys_restart_syscall
-1 i386 exit sys_exit
+1 i386 exit sys_exit - noreturn
2 i386 fork sys_fork
3 i386 read sys_read
4 i386 write sys_write
@@ -263,7 +264,7 @@
249 i386 io_cancel sys_io_cancel
250 i386 fadvise64 sys_ia32_fadvise64
# 251 is available for reuse (was briefly sys_set_zone_reclaim)
-252 i386 exit_group sys_exit_group
+252 i386 exit_group sys_exit_group - noreturn
253 i386 lookup_dcookie
254 i386 epoll_create sys_epoll_create
255 i386 epoll_ctl sys_epoll_ctl
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index a396f6e6ab5b..83073fa3c989 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -1,8 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
#
# 64-bit system call numbers and entry vectors
#
# The format is:
-# <number> <abi> <name> <entry point>
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
#
# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
#
@@ -68,7 +69,7 @@
57 common fork sys_fork
58 common vfork sys_vfork
59 64 execve sys_execve
-60 common exit sys_exit
+60 common exit sys_exit - noreturn
61 common wait4 sys_wait4
62 common kill sys_kill
63 common uname sys_newuname
@@ -239,7 +240,7 @@
228 common clock_gettime sys_clock_gettime
229 common clock_getres sys_clock_getres
230 common clock_nanosleep sys_clock_nanosleep
-231 common exit_group sys_exit_group
+231 common exit_group sys_exit_group - noreturn
232 common epoll_wait sys_epoll_wait
233 common epoll_ctl sys_epoll_ctl
234 common tgkill sys_tgkill
@@ -384,6 +385,7 @@
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
462 common mseal sys_mseal
+467 common uretprobe sys_uretprobe
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1fc4ce44e743..920e3a640cad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -432,8 +432,10 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
* be removed on one CPU at a time AND PMU is disabled
* when we come here
*/
- for (i = 0; i < x86_pmu.num_counters; i++) {
- if (cmpxchg(nb->owners + i, event, NULL) == event)
+ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct perf_event *tmp = event;
+
+ if (try_cmpxchg(nb->owners + i, &tmp, NULL))
break;
}
}
@@ -499,7 +501,7 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
* because of successive calls to x86_schedule_events() from
* hw_perf_group_sched_in() without hw_perf_enable()
*/
- for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+ for_each_set_bit(idx, c->idxmsk, x86_pmu_max_num_counters(NULL)) {
if (new == -1 || hwc->idx == idx)
/* assign free slot, prefer hwc->idx */
old = cmpxchg(nb->owners + idx, NULL, event);
@@ -542,7 +544,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
/*
* initialize all possible NB constraints
*/
- for (i = 0; i < x86_pmu.num_counters; i++) {
+ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
__set_bit(i, nb->event_constraints[i].idxmsk);
nb->event_constraints[i].weight = 1;
}
@@ -735,7 +737,7 @@ static void amd_pmu_check_overflow(void)
* counters are always enabled when this function is called and
* ARCH_PERFMON_EVENTSEL_INT is always set.
*/
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -755,7 +757,7 @@ static void amd_pmu_enable_all(int added)
amd_brs_enable_all();
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
/* only activate events which are marked as active */
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -978,7 +980,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
/* Clear any reserved bits set by buggy microcode */
status &= amd_pmu_global_cntr_mask;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -1313,7 +1315,7 @@ static __initconst const struct x86_pmu amd_pmu = {
.addr_offset = amd_pmu_addr_offset,
.event_map = amd_pmu_event_map,
.max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = AMD64_NUM_COUNTERS,
+ .cntr_mask64 = GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0),
.add = amd_pmu_add_event,
.del = amd_pmu_del_event,
.cntval_bits = 48,
@@ -1412,7 +1414,7 @@ static int __init amd_core_pmu_init(void)
*/
x86_pmu.eventsel = MSR_F15H_PERF_CTL;
x86_pmu.perfctr = MSR_F15H_PERF_CTR;
- x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(AMD64_NUM_COUNTERS_CORE - 1, 0);
/* Check for Performance Monitoring v2 support */
if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
@@ -1422,9 +1424,9 @@ static int __init amd_core_pmu_init(void)
x86_pmu.version = 2;
/* Find the number of available Core PMCs */
- x86_pmu.num_counters = ebx.split.num_core_pmc;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(ebx.split.num_core_pmc - 1, 0);
- amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+ amd_pmu_global_cntr_mask = x86_pmu.cntr_mask64;
/* Update PMC handling functions */
x86_pmu.enable_all = amd_pmu_v2_enable_all;
@@ -1452,12 +1454,12 @@ static int __init amd_core_pmu_init(void)
* even numbered counter that has a consecutive adjacent odd
* numbered counter following it.
*/
- for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+ for (i = 0; i < x86_pmu_max_num_counters(NULL) - 1; i += 2)
even_ctr_mask |= BIT_ULL(i);
pair_constraint = (struct event_constraint)
__EVENT_CONSTRAINT(0, even_ctr_mask, 0,
- x86_pmu.num_counters / 2, 0,
+ x86_pmu_max_num_counters(NULL) / 2, 0,
PERF_X86_EVENT_PAIR);
x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 4ccb8fa483e6..0bfde2ea5cb8 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -162,7 +162,9 @@ static int amd_uncore_add(struct perf_event *event, int flags)
/* if not, take the first available counter */
hwc->idx = -1;
for (i = 0; i < pmu->num_counters; i++) {
- if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
+ struct perf_event *tmp = NULL;
+
+ if (try_cmpxchg(&ctx->events[i], &tmp, event)) {
hwc->idx = i;
break;
}
@@ -196,7 +198,9 @@ static void amd_uncore_del(struct perf_event *event, int flags)
event->pmu->stop(event, PERF_EF_UPDATE);
for (i = 0; i < pmu->num_counters; i++) {
- if (cmpxchg(&ctx->events[i], event, NULL) == event)
+ struct perf_event *tmp = event;
+
+ if (try_cmpxchg(&ctx->events[i], &tmp, NULL))
break;
}
@@ -639,7 +643,7 @@ void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
info.split.aux_data = 0;
info.split.num_pmcs = NUM_COUNTERS_NB;
info.split.gid = 0;
- info.split.cid = topology_die_id(cpu);
+ info.split.cid = topology_logical_package_id(cpu);
if (pmu_version >= 2) {
ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
@@ -654,17 +658,20 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
struct attribute **df_attr = amd_uncore_df_format_attr;
struct amd_uncore_pmu *pmu;
+ int num_counters;
/* Run just once */
if (uncore->init_done)
return amd_uncore_ctx_init(uncore, cpu);
+ num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ if (!num_counters)
+ goto done;
+
/* No grouping, single instance for a system */
uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
- if (!uncore->pmus) {
- uncore->num_pmus = 0;
+ if (!uncore->pmus)
goto done;
- }
/*
* For Family 17h and above, the Northbridge counters are repurposed
@@ -674,7 +681,7 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
pmu = &uncore->pmus[0];
strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
sizeof(pmu->name));
- pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ pmu->num_counters = num_counters;
pmu->msr_base = MSR_F15H_NB_PERF_CTL;
pmu->rdpmc_base = RDPMC_BASE_NB;
pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -785,17 +792,20 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
struct attribute **l3_attr = amd_uncore_l3_format_attr;
struct amd_uncore_pmu *pmu;
+ int num_counters;
/* Run just once */
if (uncore->init_done)
return amd_uncore_ctx_init(uncore, cpu);
+ num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ if (!num_counters)
+ goto done;
+
/* No grouping, single instance for a system */
uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
- if (!uncore->pmus) {
- uncore->num_pmus = 0;
+ if (!uncore->pmus)
goto done;
- }
/*
* For Family 17h and above, L3 cache counters are available instead
@@ -805,7 +815,7 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
pmu = &uncore->pmus[0];
strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
sizeof(pmu->name));
- pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ pmu->num_counters = num_counters;
pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
pmu->rdpmc_base = RDPMC_BASE_LLC;
pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -893,8 +903,8 @@ void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
info.split.aux_data = ecx; /* stash active mask */
info.split.num_pmcs = ebx.split.num_umc_pmc;
- info.split.gid = topology_die_id(cpu);
- info.split.cid = topology_die_id(cpu);
+ info.split.gid = topology_logical_package_id(cpu);
+ info.split.cid = topology_logical_package_id(cpu);
*per_cpu_ptr(uncore->info, cpu) = info;
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 5b0dd07b1ef1..12f2a0c14d33 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -189,29 +189,31 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
#ifdef CONFIG_X86_LOCAL_APIC
-static inline int get_possible_num_counters(void)
+static inline u64 get_possible_counter_mask(void)
{
- int i, num_counters = x86_pmu.num_counters;
+ u64 cntr_mask = x86_pmu.cntr_mask64;
+ int i;
if (!is_hybrid())
- return num_counters;
+ return cntr_mask;
for (i = 0; i < x86_pmu.num_hybrid_pmus; i++)
- num_counters = max_t(int, num_counters, x86_pmu.hybrid_pmu[i].num_counters);
+ cntr_mask |= x86_pmu.hybrid_pmu[i].cntr_mask64;
- return num_counters;
+ return cntr_mask;
}
static bool reserve_pmc_hardware(void)
{
- int i, num_counters = get_possible_num_counters();
+ u64 cntr_mask = get_possible_counter_mask();
+ int i, end;
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
goto perfctr_fail;
}
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
goto eventsel_fail;
}
@@ -219,13 +221,14 @@ static bool reserve_pmc_hardware(void)
return true;
eventsel_fail:
- for (i--; i >= 0; i--)
+ end = i;
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
release_evntsel_nmi(x86_pmu_config_addr(i));
-
- i = num_counters;
+ i = X86_PMC_IDX_MAX;
perfctr_fail:
- for (i--; i >= 0; i--)
+ end = i;
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
release_perfctr_nmi(x86_pmu_event_addr(i));
return false;
@@ -233,9 +236,10 @@ perfctr_fail:
static void release_pmc_hardware(void)
{
- int i, num_counters = get_possible_num_counters();
+ u64 cntr_mask = get_possible_counter_mask();
+ int i;
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
release_perfctr_nmi(x86_pmu_event_addr(i));
release_evntsel_nmi(x86_pmu_config_addr(i));
}
@@ -248,7 +252,8 @@ static void release_pmc_hardware(void) {}
#endif
-bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+ unsigned long *fixed_cntr_mask)
{
u64 val, val_fail = -1, val_new= ~0;
int i, reg, reg_fail = -1, ret = 0;
@@ -259,7 +264,7 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
* Check to see if the BIOS enabled any of the counters, if so
* complain and bail.
*/
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) {
reg = x86_pmu_config_addr(i);
ret = rdmsrl_safe(reg, &val);
if (ret)
@@ -273,12 +278,12 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
}
}
- if (num_counters_fixed) {
+ if (*(u64 *)fixed_cntr_mask) {
reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
ret = rdmsrl_safe(reg, &val);
if (ret)
goto msr_fail;
- for (i = 0; i < num_counters_fixed; i++) {
+ for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) {
if (fixed_counter_disabled(i, pmu))
continue;
if (val & (0x03ULL << i*4)) {
@@ -619,7 +624,7 @@ int x86_pmu_hw_config(struct perf_event *event)
event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
if (event->attr.type == event->pmu->type)
- event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
+ event->hw.config |= x86_pmu_get_event_config(event);
if (event->attr.sample_period && x86_pmu.limit_period) {
s64 left = event->attr.sample_period;
@@ -679,7 +684,7 @@ void x86_pmu_disable_all(void)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
u64 val;
@@ -736,7 +741,7 @@ void x86_pmu_enable_all(int added)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
if (!test_bit(idx, cpuc->active_mask))
@@ -975,7 +980,6 @@ EXPORT_SYMBOL_GPL(perf_assign_events);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
{
- int num_counters = hybrid(cpuc->pmu, num_counters);
struct event_constraint *c;
struct perf_event *e;
int n0, i, wmin, wmax, unsched = 0;
@@ -1051,7 +1055,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
/* slow path */
if (i != n) {
- int gpmax = num_counters;
+ int gpmax = x86_pmu_max_num_counters(cpuc->pmu);
/*
* Do not allow scheduling of more than half the available
@@ -1072,7 +1076,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
* the extra Merge events needed by large increment events.
*/
if (x86_pmu.flags & PMU_FL_PAIR) {
- gpmax = num_counters - cpuc->n_pair;
+ gpmax -= cpuc->n_pair;
WARN_ON(gpmax <= 0);
}
@@ -1157,12 +1161,10 @@ static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event,
*/
static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
{
- int num_counters = hybrid(cpuc->pmu, num_counters);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
struct perf_event *event;
int n, max_count;
- max_count = num_counters + num_counters_fixed;
+ max_count = x86_pmu_num_counters(cpuc->pmu) + x86_pmu_num_counters_fixed(cpuc->pmu);
/* current number of events already accepted */
n = cpuc->n_events;
@@ -1234,8 +1236,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
fallthrough;
case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
- (idx - INTEL_PMC_IDX_FIXED);
+ hwc->event_base = x86_pmu_fixed_ctr_addr(idx - INTEL_PMC_IDX_FIXED);
hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) |
INTEL_PMC_FIXED_RDPMC_BASE;
break;
@@ -1522,13 +1523,13 @@ void perf_event_print_debug(void)
u64 pebs, debugctl;
int cpu = smp_processor_id();
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
- int num_counters = hybrid(cpuc->pmu, num_counters);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+ unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+ unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
unsigned long flags;
int idx;
- if (!num_counters)
+ if (!*(u64 *)cntr_mask)
return;
local_irq_save(flags);
@@ -1555,7 +1556,7 @@ void perf_event_print_debug(void)
}
pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
- for (idx = 0; idx < num_counters; idx++) {
+ for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) {
rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
rdmsrl(x86_pmu_event_addr(idx), pmc_count);
@@ -1568,10 +1569,10 @@ void perf_event_print_debug(void)
pr_info("CPU#%d: gen-PMC%d left: %016llx\n",
cpu, idx, prev_left);
}
- for (idx = 0; idx < num_counters_fixed; idx++) {
+ for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
if (fixed_counter_disabled(idx, cpuc->pmu))
continue;
- rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
+ rdmsrl(x86_pmu_fixed_ctr_addr(idx), pmc_count);
pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
cpu, idx, pmc_count);
@@ -1682,7 +1683,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
*/
apic_write(APIC_LVTPC, APIC_DM_NMI);
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -2038,18 +2039,15 @@ static void _x86_pmu_read(struct perf_event *event)
static_call(x86_pmu_update)(event);
}
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
- u64 intel_ctrl)
+void x86_pmu_show_pmu_cap(struct pmu *pmu)
{
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
- pr_info("... generic registers: %d\n", num_counters);
+ pr_info("... generic registers: %d\n", x86_pmu_num_counters(pmu));
pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask);
pr_info("... max period: %016Lx\n", x86_pmu.max_period);
- pr_info("... fixed-purpose events: %lu\n",
- hweight64((((1ULL << num_counters_fixed) - 1)
- << INTEL_PMC_IDX_FIXED) & intel_ctrl));
- pr_info("... event mask: %016Lx\n", intel_ctrl);
+ pr_info("... fixed-purpose events: %d\n", x86_pmu_num_counters_fixed(pmu));
+ pr_info("... event mask: %016Lx\n", hybrid(pmu, intel_ctrl));
}
static int __init init_hw_perf_events(void)
@@ -2086,7 +2084,7 @@ static int __init init_hw_perf_events(void)
pmu_check_apic();
/* sanity check that the hardware exists or is emulated */
- if (!check_hw_exists(&pmu, x86_pmu.num_counters, x86_pmu.num_counters_fixed))
+ if (!check_hw_exists(&pmu, x86_pmu.cntr_mask, x86_pmu.fixed_cntr_mask))
goto out_bad_pmu;
pr_cont("%s PMU driver.\n", x86_pmu.name);
@@ -2097,14 +2095,17 @@ static int __init init_hw_perf_events(void)
quirk->func();
if (!x86_pmu.intel_ctrl)
- x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+ x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+
+ if (!x86_pmu.config_mask)
+ x86_pmu.config_mask = X86_RAW_EVENT_MASK;
perf_events_lapic_init();
register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
- 0, x86_pmu.num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, x86_pmu.cntr_mask64,
+ 0, x86_pmu_num_counters(NULL), 0, 0);
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
@@ -2113,11 +2114,8 @@ static int __init init_hw_perf_events(void)
pmu.attr_update = x86_pmu.attr_update;
- if (!is_hybrid()) {
- x86_pmu_show_pmu_cap(x86_pmu.num_counters,
- x86_pmu.num_counters_fixed,
- x86_pmu.intel_ctrl);
- }
+ if (!is_hybrid())
+ x86_pmu_show_pmu_cap(NULL);
if (!x86_pmu.read)
x86_pmu.read = _x86_pmu_read;
@@ -2481,10 +2479,10 @@ void perf_clear_dirty_counters(void)
for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
if (i >= INTEL_PMC_IDX_FIXED) {
/* Metrics and fake events don't have corresponding HW counters. */
- if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
+ if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
continue;
- wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
+ wrmsrl(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
} else {
wrmsrl(x86_pmu_event_addr(i), 0);
}
@@ -2547,6 +2545,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
struct device_attribute *attr,
const char *buf, size_t count)
{
+ static DEFINE_MUTEX(rdpmc_mutex);
unsigned long val;
ssize_t ret;
@@ -2560,6 +2559,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
if (x86_pmu.attr_rdpmc_broken)
return -ENOTSUPP;
+ guard(mutex)(&rdpmc_mutex);
+
if (val != x86_pmu.attr_rdpmc) {
/*
* Changing into or out of never available or always available,
@@ -2983,8 +2984,8 @@ void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
* base PMU holds the correct number of counters for P-cores.
*/
cap->version = x86_pmu.version;
- cap->num_counters_gp = x86_pmu.num_counters;
- cap->num_counters_fixed = x86_pmu.num_counters_fixed;
+ cap->num_counters_gp = x86_pmu_num_counters(NULL);
+ cap->num_counters_fixed = x86_pmu_num_counters_fixed(NULL);
cap->bit_width_gp = x86_pmu.cntval_bits;
cap->bit_width_fixed = x86_pmu.cntval_bits;
cap->events_mask = (unsigned int)x86_pmu.events_maskl;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 38c1b1f1deaa..0c9c2706d4ec 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -220,6 +220,17 @@ static struct event_constraint intel_grt_event_constraints[] __read_mostly = {
EVENT_CONSTRAINT_END
};
+static struct event_constraint intel_skt_event_constraints[] __read_mostly = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
+ FIXED_EVENT_CONSTRAINT(0x0073, 4), /* TOPDOWN_BAD_SPECULATION.ALL */
+ FIXED_EVENT_CONSTRAINT(0x019c, 5), /* TOPDOWN_FE_BOUND.ALL */
+ FIXED_EVENT_CONSTRAINT(0x02c2, 6), /* TOPDOWN_RETIRING.ALL */
+ EVENT_CONSTRAINT_END
+};
+
static struct event_constraint intel_skl_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -370,6 +381,55 @@ static struct extra_reg intel_rwc_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
+static struct event_constraint intel_lnc_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
+ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_HEAVY_OPS, 4),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BR_MISPREDICT, 5),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
+
+ INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
+
+ INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
+ INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
+ /*
+ * Generally event codes < 0x90 are restricted to counters 0-3.
+ * The 0x2E and 0x3C are exception, which has no restriction.
+ */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
+
+ INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
+ INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
+ INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
+ INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+ INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
+ INTEL_EVENT_CONSTRAINT(0xce, 0x1),
+
+ INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
+ /*
+ * Generally event codes >= 0x90 are likely to have no restrictions.
+ * The exception are defined as above.
+ */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+ EVENT_CONSTRAINT_END
+};
+
+
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
@@ -2874,26 +2934,26 @@ static void intel_pmu_reset(void)
{
struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
- int num_counters = hybrid(cpuc->pmu, num_counters);
+ unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+ unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
unsigned long flags;
int idx;
- if (!num_counters)
+ if (!*(u64 *)cntr_mask)
return;
local_irq_save(flags);
pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
- for (idx = 0; idx < num_counters; idx++) {
+ for_each_set_bit(idx, cntr_mask, INTEL_PMC_MAX_GENERIC) {
wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
}
- for (idx = 0; idx < num_counters_fixed; idx++) {
+ for_each_set_bit(idx, fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
if (fixed_counter_disabled(idx, cpuc->pmu))
continue;
- wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+ wrmsrl_safe(x86_pmu_fixed_ctr_addr(idx), 0ull);
}
if (ds)
@@ -2940,8 +3000,7 @@ static void x86_pmu_handle_guest_pebs(struct pt_regs *regs,
!guest_pebs_idxs)
return;
- for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs,
- INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed) {
+ for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs, X86_PMC_IDX_MAX) {
event = cpuc->events[bit];
if (!event->attr.precise_ip)
continue;
@@ -4199,7 +4258,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[idx];
arr[idx].msr = x86_pmu_config_addr(idx);
@@ -4217,7 +4276,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
}
- *nr = x86_pmu.num_counters;
+ *nr = x86_pmu_max_num_counters(cpuc->pmu);
return arr;
}
@@ -4232,7 +4291,7 @@ static void core_pmu_enable_all(int added)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
if (!test_bit(idx, cpuc->active_mask) ||
@@ -4573,8 +4632,55 @@ PMU_FORMAT_ATTR(pc, "config:19" );
PMU_FORMAT_ATTR(any, "config:21" ); /* v3 + */
PMU_FORMAT_ATTR(inv, "config:23" );
PMU_FORMAT_ATTR(cmask, "config:24-31" );
-PMU_FORMAT_ATTR(in_tx, "config:32");
-PMU_FORMAT_ATTR(in_tx_cp, "config:33");
+PMU_FORMAT_ATTR(in_tx, "config:32" );
+PMU_FORMAT_ATTR(in_tx_cp, "config:33" );
+PMU_FORMAT_ATTR(eq, "config:36" ); /* v6 + */
+
+static ssize_t umask2_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page)
+{
+ u64 mask = hybrid(dev_get_drvdata(dev), config_mask) & ARCH_PERFMON_EVENTSEL_UMASK2;
+
+ if (mask == ARCH_PERFMON_EVENTSEL_UMASK2)
+ return sprintf(page, "config:8-15,40-47\n");
+
+ /* Roll back to the old format if umask2 is not supported. */
+ return sprintf(page, "config:8-15\n");
+}
+
+static struct device_attribute format_attr_umask2 =
+ __ATTR(umask, 0444, umask2_show, NULL);
+
+static struct attribute *format_evtsel_ext_attrs[] = {
+ &format_attr_umask2.attr,
+ &format_attr_eq.attr,
+ NULL
+};
+
+static umode_t
+evtsel_ext_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ u64 mask;
+
+ /*
+ * The umask and umask2 have different formats but share the
+ * same attr name. In update mode, the previous value of the
+ * umask is unconditionally removed before is_visible. If
+ * umask2 format is not enumerated, it's impossible to roll
+ * back to the old format.
+ * Does the check in umask2_show rather than is_visible.
+ */
+ if (i == 0)
+ return attr->mode;
+
+ mask = hybrid(dev_get_drvdata(dev), config_mask);
+ if (i == 1)
+ return (mask & ARCH_PERFMON_EVENTSEL_EQ) ? attr->mode : 0;
+
+ return 0;
+}
static struct attribute *intel_arch_formats_attr[] = {
&format_attr_event.attr,
@@ -4684,13 +4790,33 @@ static void flip_smm_bit(void *data)
}
}
-static void intel_pmu_check_num_counters(int *num_counters,
- int *num_counters_fixed,
- u64 *intel_ctrl, u64 fixed_mask);
+static void intel_pmu_check_counters_mask(u64 *cntr_mask,
+ u64 *fixed_cntr_mask,
+ u64 *intel_ctrl)
+{
+ unsigned int bit;
+
+ bit = fls64(*cntr_mask);
+ if (bit > INTEL_PMC_MAX_GENERIC) {
+ WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
+ bit, INTEL_PMC_MAX_GENERIC);
+ *cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_GENERIC - 1, 0);
+ }
+ *intel_ctrl = *cntr_mask;
+
+ bit = fls64(*fixed_cntr_mask);
+ if (bit > INTEL_PMC_MAX_FIXED) {
+ WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
+ bit, INTEL_PMC_MAX_FIXED);
+ *fixed_cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
+ }
+
+ *intel_ctrl |= *fixed_cntr_mask << INTEL_PMC_IDX_FIXED;
+}
static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
- int num_counters,
- int num_counters_fixed,
+ u64 cntr_mask,
+ u64 fixed_cntr_mask,
u64 intel_ctrl);
static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
@@ -4698,8 +4824,8 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
static inline bool intel_pmu_broken_perf_cap(void)
{
/* The Perf Metric (Bit 15) is always cleared */
- if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) ||
- (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L))
+ if (boot_cpu_data.x86_vfm == INTEL_METEORLAKE ||
+ boot_cpu_data.x86_vfm == INTEL_METEORLAKE_L)
return true;
return false;
@@ -4707,17 +4833,22 @@ static inline bool intel_pmu_broken_perf_cap(void)
static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
{
- unsigned int sub_bitmaps = cpuid_eax(ARCH_PERFMON_EXT_LEAF);
- unsigned int eax, ebx, ecx, edx;
+ unsigned int sub_bitmaps, eax, ebx, ecx, edx;
+
+ cpuid(ARCH_PERFMON_EXT_LEAF, &sub_bitmaps, &ebx, &ecx, &edx);
+
+ if (ebx & ARCH_PERFMON_EXT_UMASK2)
+ pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2;
+ if (ebx & ARCH_PERFMON_EXT_EQ)
+ pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ;
if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
&eax, &ebx, &ecx, &edx);
- pmu->num_counters = fls(eax);
- pmu->num_counters_fixed = fls(ebx);
+ pmu->cntr_mask64 = eax;
+ pmu->fixed_cntr_mask64 = ebx;
}
-
if (!intel_pmu_broken_perf_cap()) {
/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
@@ -4726,12 +4857,12 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
{
- intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
- &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1);
- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ intel_pmu_check_counters_mask(&pmu->cntr_mask64, &pmu->fixed_cntr_mask64,
+ &pmu->intel_ctrl);
+ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
pmu->unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
- 0, pmu->num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
if (pmu->intel_cap.perf_metrics)
pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
@@ -4744,8 +4875,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
intel_pmu_check_event_constraints(pmu->event_constraints,
- pmu->num_counters,
- pmu->num_counters_fixed,
+ pmu->cntr_mask64,
+ pmu->fixed_cntr_mask64,
pmu->intel_ctrl);
intel_pmu_check_extra_regs(pmu->extra_regs);
@@ -4806,7 +4937,7 @@ static bool init_hybrid_pmu(int cpu)
intel_pmu_check_hybrid_pmus(pmu);
- if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed))
+ if (!check_hw_exists(&pmu->pmu, pmu->cntr_mask, pmu->fixed_cntr_mask))
return false;
pr_info("%s PMU driver: ", pmu->name);
@@ -4816,8 +4947,7 @@ static bool init_hybrid_pmu(int cpu)
pr_cont("\n");
- x86_pmu_show_pmu_cap(pmu->num_counters, pmu->num_counters_fixed,
- pmu->intel_ctrl);
+ x86_pmu_show_pmu_cap(&pmu->pmu);
end:
cpumask_set_cpu(cpu, &pmu->supported_cpus);
@@ -5058,6 +5188,7 @@ static __initconst const struct x86_pmu core_pmu = {
.schedule_events = x86_schedule_events,
.eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
.perfctr = MSR_ARCH_PERFMON_PERFCTR0,
+ .fixedctr = MSR_ARCH_PERFMON_FIXED_CTR0,
.event_map = intel_pmu_event_map,
.max_events = ARRAY_SIZE(intel_perfmon_event_map),
.apic = 1,
@@ -5111,6 +5242,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.schedule_events = x86_schedule_events,
.eventsel = MSR_ARCH_PERFMON_EVENTSEL0,
.perfctr = MSR_ARCH_PERFMON_PERFCTR0,
+ .fixedctr = MSR_ARCH_PERFMON_FIXED_CTR0,
.event_map = intel_pmu_event_map,
.max_events = ARRAY_SIZE(intel_perfmon_event_map),
.apic = 1,
@@ -5187,35 +5319,35 @@ static __init void intel_clovertown_quirk(void)
}
static const struct x86_cpu_desc isolation_ucodes[] = {
- INTEL_CPU_DESC(INTEL_FAM6_HASWELL, 3, 0x0000001f),
- INTEL_CPU_DESC(INTEL_FAM6_HASWELL_L, 1, 0x0000001e),
- INTEL_CPU_DESC(INTEL_FAM6_HASWELL_G, 1, 0x00000015),
- INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 2, 0x00000037),
- INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 4, 0x0000000a),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL, 4, 0x00000023),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_G, 1, 0x00000014),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 2, 0x00000010),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 3, 0x07000009),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 4, 0x0f000009),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 5, 0x0e000002),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 1, 0x0b000014),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c),
- INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 9, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 10, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 11, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 12, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 10, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 11, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 12, 0x0000004e),
- INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 13, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_HASWELL, 3, 0x0000001f),
+ INTEL_CPU_DESC(INTEL_HASWELL_L, 1, 0x0000001e),
+ INTEL_CPU_DESC(INTEL_HASWELL_G, 1, 0x00000015),
+ INTEL_CPU_DESC(INTEL_HASWELL_X, 2, 0x00000037),
+ INTEL_CPU_DESC(INTEL_HASWELL_X, 4, 0x0000000a),
+ INTEL_CPU_DESC(INTEL_BROADWELL, 4, 0x00000023),
+ INTEL_CPU_DESC(INTEL_BROADWELL_G, 1, 0x00000014),
+ INTEL_CPU_DESC(INTEL_BROADWELL_D, 2, 0x00000010),
+ INTEL_CPU_DESC(INTEL_BROADWELL_D, 3, 0x07000009),
+ INTEL_CPU_DESC(INTEL_BROADWELL_D, 4, 0x0f000009),
+ INTEL_CPU_DESC(INTEL_BROADWELL_D, 5, 0x0e000002),
+ INTEL_CPU_DESC(INTEL_BROADWELL_X, 1, 0x0b000014),
+ INTEL_CPU_DESC(INTEL_SKYLAKE_X, 3, 0x00000021),
+ INTEL_CPU_DESC(INTEL_SKYLAKE_X, 4, 0x00000000),
+ INTEL_CPU_DESC(INTEL_SKYLAKE_X, 5, 0x00000000),
+ INTEL_CPU_DESC(INTEL_SKYLAKE_X, 6, 0x00000000),
+ INTEL_CPU_DESC(INTEL_SKYLAKE_X, 7, 0x00000000),
+ INTEL_CPU_DESC(INTEL_SKYLAKE_X, 11, 0x00000000),
+ INTEL_CPU_DESC(INTEL_SKYLAKE_L, 3, 0x0000007c),
+ INTEL_CPU_DESC(INTEL_SKYLAKE, 3, 0x0000007c),
+ INTEL_CPU_DESC(INTEL_KABYLAKE, 9, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE_L, 9, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE_L, 10, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE_L, 11, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE_L, 12, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE, 10, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE, 11, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE, 12, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_KABYLAKE, 13, 0x0000004e),
{}
};
@@ -5232,9 +5364,9 @@ static __init void intel_pebs_isolation_quirk(void)
}
static const struct x86_cpu_desc pebs_ucodes[] = {
- INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE, 7, 0x00000028),
- INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 6, 0x00000618),
- INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 7, 0x0000070c),
+ INTEL_CPU_DESC(INTEL_SANDYBRIDGE, 7, 0x00000028),
+ INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 6, 0x00000618),
+ INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 7, 0x0000070c),
{}
};
@@ -5698,8 +5830,22 @@ exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
return x86_pmu.version >= 2 ? attr->mode : 0;
}
+static umode_t
+td_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ /*
+ * Hide the perf metrics topdown events
+ * if the feature is not enumerated.
+ */
+ if (x86_pmu.num_topdown_events)
+ return x86_pmu.intel_cap.perf_metrics ? attr->mode : 0;
+
+ return attr->mode;
+}
+
static struct attribute_group group_events_td = {
.name = "events",
+ .is_visible = td_is_visible,
};
static struct attribute_group group_events_mem = {
@@ -5733,6 +5879,12 @@ static struct attribute_group group_format_extra_skl = {
.is_visible = exra_is_visible,
};
+static struct attribute_group group_format_evtsel_ext = {
+ .name = "format",
+ .attrs = format_evtsel_ext_attrs,
+ .is_visible = evtsel_ext_is_visible,
+};
+
static struct attribute_group group_default = {
.attrs = intel_pmu_attrs,
.is_visible = default_is_visible,
@@ -5746,6 +5898,7 @@ static const struct attribute_group *attr_update[] = {
&group_caps_lbr,
&group_format_extra,
&group_format_extra_skl,
+ &group_format_evtsel_ext,
&group_default,
NULL,
};
@@ -5773,6 +5926,23 @@ static struct attribute *adl_hybrid_events_attrs[] = {
NULL,
};
+EVENT_ATTR_STR_HYBRID(topdown-retiring, td_retiring_lnl, "event=0xc2,umask=0x02;event=0x00,umask=0x80", hybrid_big_small);
+EVENT_ATTR_STR_HYBRID(topdown-fe-bound, td_fe_bound_lnl, "event=0x9c,umask=0x01;event=0x00,umask=0x82", hybrid_big_small);
+EVENT_ATTR_STR_HYBRID(topdown-be-bound, td_be_bound_lnl, "event=0xa4,umask=0x02;event=0x00,umask=0x83", hybrid_big_small);
+
+static struct attribute *lnl_hybrid_events_attrs[] = {
+ EVENT_PTR(slots_adl),
+ EVENT_PTR(td_retiring_lnl),
+ EVENT_PTR(td_bad_spec_adl),
+ EVENT_PTR(td_fe_bound_lnl),
+ EVENT_PTR(td_be_bound_lnl),
+ EVENT_PTR(td_heavy_ops_adl),
+ EVENT_PTR(td_br_mis_adl),
+ EVENT_PTR(td_fetch_lat_adl),
+ EVENT_PTR(td_mem_bound_adl),
+ NULL
+};
+
/* Must be in IDX order */
EVENT_ATTR_STR_HYBRID(mem-loads, mem_ld_adl, "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3", hybrid_big_small);
EVENT_ATTR_STR_HYBRID(mem-stores, mem_st_adl, "event=0xd0,umask=0x6;event=0xcd,umask=0x2", hybrid_big_small);
@@ -5901,9 +6071,27 @@ static umode_t hybrid_format_is_visible(struct kobject *kobj,
return (cpu >= 0) && (pmu->pmu_type & pmu_attr->pmu_type) ? attr->mode : 0;
}
+static umode_t hybrid_td_is_visible(struct kobject *kobj,
+ struct attribute *attr, int i)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct x86_hybrid_pmu *pmu =
+ container_of(dev_get_drvdata(dev), struct x86_hybrid_pmu, pmu);
+
+ if (!is_attr_for_this_pmu(kobj, attr))
+ return 0;
+
+
+ /* Only the big core supports perf metrics */
+ if (pmu->pmu_type == hybrid_big)
+ return pmu->intel_cap.perf_metrics ? attr->mode : 0;
+
+ return attr->mode;
+}
+
static struct attribute_group hybrid_group_events_td = {
.name = "events",
- .is_visible = hybrid_events_is_visible,
+ .is_visible = hybrid_td_is_visible,
};
static struct attribute_group hybrid_group_events_mem = {
@@ -5948,6 +6136,7 @@ static const struct attribute_group *hybrid_attr_update[] = {
&group_caps_gen,
&group_caps_lbr,
&hybrid_group_format_extra,
+ &group_format_evtsel_ext,
&group_default,
&hybrid_group_cpus,
NULL,
@@ -5955,29 +6144,9 @@ static const struct attribute_group *hybrid_attr_update[] = {
static struct attribute *empty_attrs;
-static void intel_pmu_check_num_counters(int *num_counters,
- int *num_counters_fixed,
- u64 *intel_ctrl, u64 fixed_mask)
-{
- if (*num_counters > INTEL_PMC_MAX_GENERIC) {
- WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
- *num_counters, INTEL_PMC_MAX_GENERIC);
- *num_counters = INTEL_PMC_MAX_GENERIC;
- }
- *intel_ctrl = (1ULL << *num_counters) - 1;
-
- if (*num_counters_fixed > INTEL_PMC_MAX_FIXED) {
- WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
- *num_counters_fixed, INTEL_PMC_MAX_FIXED);
- *num_counters_fixed = INTEL_PMC_MAX_FIXED;
- }
-
- *intel_ctrl |= fixed_mask << INTEL_PMC_IDX_FIXED;
-}
-
static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
- int num_counters,
- int num_counters_fixed,
+ u64 cntr_mask,
+ u64 fixed_cntr_mask,
u64 intel_ctrl)
{
struct event_constraint *c;
@@ -6014,10 +6183,9 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con
* generic counters
*/
if (!use_fixed_pseudo_encoding(c->code))
- c->idxmsk64 |= (1ULL << num_counters) - 1;
+ c->idxmsk64 |= cntr_mask;
}
- c->idxmsk64 &=
- ~(~0ULL << (INTEL_PMC_IDX_FIXED + num_counters_fixed));
+ c->idxmsk64 &= cntr_mask | (fixed_cntr_mask << INTEL_PMC_IDX_FIXED);
c->weight = hweight64(c->idxmsk64);
}
}
@@ -6042,6 +6210,11 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs)
}
}
+static inline int intel_pmu_v6_addr_offset(int index, bool eventsel)
+{
+ return MSR_IA32_PMC_V6_STEP * index;
+}
+
static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = {
{ hybrid_small, "cpu_atom" },
{ hybrid_big, "cpu_core" },
@@ -6068,12 +6241,13 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
pmu->pmu_type = intel_hybrid_pmu_type_map[bit].id;
pmu->name = intel_hybrid_pmu_type_map[bit].name;
- pmu->num_counters = x86_pmu.num_counters;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
+ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
+ pmu->config_mask = X86_RAW_EVENT_MASK;
pmu->unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
- 0, pmu->num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
if (pmu->pmu_type & hybrid_small) {
@@ -6143,6 +6317,21 @@ static __always_inline void intel_pmu_init_grt(struct pmu *pmu)
intel_pmu_ref_cycles_ext();
}
+static __always_inline void intel_pmu_init_lnc(struct pmu *pmu)
+{
+ intel_pmu_init_glc(pmu);
+ hybrid(pmu, event_constraints) = intel_lnc_event_constraints;
+ hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints;
+ hybrid(pmu, extra_regs) = intel_rwc_extra_regs;
+}
+
+static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
+{
+ intel_pmu_init_grt(pmu);
+ hybrid(pmu, event_constraints) = intel_skt_event_constraints;
+ hybrid(pmu, extra_regs) = intel_cmt_extra_regs;
+}
+
__init int intel_pmu_init(void)
{
struct attribute **extra_skl_attr = &empty_attrs;
@@ -6186,14 +6375,14 @@ __init int intel_pmu_init(void)
x86_pmu = intel_pmu;
x86_pmu.version = version;
- x86_pmu.num_counters = eax.split.num_counters;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(eax.split.num_counters - 1, 0);
x86_pmu.cntval_bits = eax.split.bit_width;
x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
x86_pmu.events_maskl = ebx.full;
x86_pmu.events_mask_len = eax.split.mask_length;
- x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
+ x86_pmu.pebs_events_mask = intel_pmu_pebs_mask(x86_pmu.cntr_mask64);
x86_pmu.pebs_capable = PEBS_COUNTER_MASK;
/*
@@ -6203,12 +6392,10 @@ __init int intel_pmu_init(void)
if (version > 1 && version < 5) {
int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
- x86_pmu.num_counters_fixed =
- max((int)edx.split.num_counters_fixed, assume);
-
- fixed_mask = (1L << x86_pmu.num_counters_fixed) - 1;
+ x86_pmu.fixed_cntr_mask64 =
+ GENMASK_ULL(max((int)edx.split.num_counters_fixed, assume) - 1, 0);
} else if (version >= 5)
- x86_pmu.num_counters_fixed = fls(fixed_mask);
+ x86_pmu.fixed_cntr_mask64 = fixed_mask;
if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
@@ -6238,19 +6425,19 @@ __init int intel_pmu_init(void)
/*
* Install the hw-cache-events table:
*/
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_CORE_YONAH:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_CORE_YONAH:
pr_cont("Core events, ");
name = "core";
break;
- case INTEL_FAM6_CORE2_MEROM:
+ case INTEL_CORE2_MEROM:
x86_add_quirk(intel_clovertown_quirk);
fallthrough;
- case INTEL_FAM6_CORE2_MEROM_L:
- case INTEL_FAM6_CORE2_PENRYN:
- case INTEL_FAM6_CORE2_DUNNINGTON:
+ case INTEL_CORE2_MEROM_L:
+ case INTEL_CORE2_PENRYN:
+ case INTEL_CORE2_DUNNINGTON:
memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6262,9 +6449,9 @@ __init int intel_pmu_init(void)
name = "core2";
break;
- case INTEL_FAM6_NEHALEM:
- case INTEL_FAM6_NEHALEM_EP:
- case INTEL_FAM6_NEHALEM_EX:
+ case INTEL_NEHALEM:
+ case INTEL_NEHALEM_EP:
+ case INTEL_NEHALEM_EX:
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -6296,11 +6483,11 @@ __init int intel_pmu_init(void)
name = "nehalem";
break;
- case INTEL_FAM6_ATOM_BONNELL:
- case INTEL_FAM6_ATOM_BONNELL_MID:
- case INTEL_FAM6_ATOM_SALTWELL:
- case INTEL_FAM6_ATOM_SALTWELL_MID:
- case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+ case INTEL_ATOM_BONNELL:
+ case INTEL_ATOM_BONNELL_MID:
+ case INTEL_ATOM_SALTWELL:
+ case INTEL_ATOM_SALTWELL_MID:
+ case INTEL_ATOM_SALTWELL_TABLET:
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6313,11 +6500,11 @@ __init int intel_pmu_init(void)
name = "bonnell";
break;
- case INTEL_FAM6_ATOM_SILVERMONT:
- case INTEL_FAM6_ATOM_SILVERMONT_D:
- case INTEL_FAM6_ATOM_SILVERMONT_MID:
- case INTEL_FAM6_ATOM_AIRMONT:
- case INTEL_FAM6_ATOM_AIRMONT_MID:
+ case INTEL_ATOM_SILVERMONT:
+ case INTEL_ATOM_SILVERMONT_D:
+ case INTEL_ATOM_SILVERMONT_MID:
+ case INTEL_ATOM_AIRMONT:
+ case INTEL_ATOM_AIRMONT_MID:
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -6335,8 +6522,8 @@ __init int intel_pmu_init(void)
name = "silvermont";
break;
- case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_D:
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_D:
memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -6362,7 +6549,7 @@ __init int intel_pmu_init(void)
name = "goldmont";
break;
- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ case INTEL_ATOM_GOLDMONT_PLUS:
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -6391,9 +6578,9 @@ __init int intel_pmu_init(void)
name = "goldmont_plus";
break;
- case INTEL_FAM6_ATOM_TREMONT_D:
- case INTEL_FAM6_ATOM_TREMONT:
- case INTEL_FAM6_ATOM_TREMONT_L:
+ case INTEL_ATOM_TREMONT_D:
+ case INTEL_ATOM_TREMONT:
+ case INTEL_ATOM_TREMONT_L:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6420,10 +6607,10 @@ __init int intel_pmu_init(void)
name = "Tremont";
break;
- case INTEL_FAM6_ATOM_GRACEMONT:
+ case INTEL_ATOM_GRACEMONT:
intel_pmu_init_grt(NULL);
intel_pmu_pebs_data_source_grt();
- x86_pmu.pebs_latency_data = adl_latency_data_small;
+ x86_pmu.pebs_latency_data = grt_latency_data;
x86_pmu.get_event_constraints = tnt_get_event_constraints;
td_attr = tnt_events_attrs;
mem_attr = grt_mem_attrs;
@@ -6432,12 +6619,12 @@ __init int intel_pmu_init(void)
name = "gracemont";
break;
- case INTEL_FAM6_ATOM_CRESTMONT:
- case INTEL_FAM6_ATOM_CRESTMONT_X:
+ case INTEL_ATOM_CRESTMONT:
+ case INTEL_ATOM_CRESTMONT_X:
intel_pmu_init_grt(NULL);
x86_pmu.extra_regs = intel_cmt_extra_regs;
intel_pmu_pebs_data_source_cmt();
- x86_pmu.pebs_latency_data = mtl_latency_data_small;
+ x86_pmu.pebs_latency_data = cmt_latency_data;
x86_pmu.get_event_constraints = cmt_get_event_constraints;
td_attr = cmt_events_attrs;
mem_attr = grt_mem_attrs;
@@ -6446,9 +6633,9 @@ __init int intel_pmu_init(void)
name = "crestmont";
break;
- case INTEL_FAM6_WESTMERE:
- case INTEL_FAM6_WESTMERE_EP:
- case INTEL_FAM6_WESTMERE_EX:
+ case INTEL_WESTMERE:
+ case INTEL_WESTMERE_EP:
+ case INTEL_WESTMERE_EX:
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -6477,8 +6664,8 @@ __init int intel_pmu_init(void)
name = "westmere";
break;
- case INTEL_FAM6_SANDYBRIDGE:
- case INTEL_FAM6_SANDYBRIDGE_X:
+ case INTEL_SANDYBRIDGE:
+ case INTEL_SANDYBRIDGE_X:
x86_add_quirk(intel_sandybridge_quirk);
x86_add_quirk(intel_ht_bug);
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
@@ -6491,7 +6678,7 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
- if (boot_cpu_data.x86_model == INTEL_FAM6_SANDYBRIDGE_X)
+ if (boot_cpu_data.x86_vfm == INTEL_SANDYBRIDGE_X)
x86_pmu.extra_regs = intel_snbep_extra_regs;
else
x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -6517,8 +6704,8 @@ __init int intel_pmu_init(void)
name = "sandybridge";
break;
- case INTEL_FAM6_IVYBRIDGE:
- case INTEL_FAM6_IVYBRIDGE_X:
+ case INTEL_IVYBRIDGE:
+ case INTEL_IVYBRIDGE_X:
x86_add_quirk(intel_ht_bug);
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6534,7 +6721,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
x86_pmu.pebs_prec_dist = true;
- if (boot_cpu_data.x86_model == INTEL_FAM6_IVYBRIDGE_X)
+ if (boot_cpu_data.x86_vfm == INTEL_IVYBRIDGE_X)
x86_pmu.extra_regs = intel_snbep_extra_regs;
else
x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -6556,10 +6743,10 @@ __init int intel_pmu_init(void)
break;
- case INTEL_FAM6_HASWELL:
- case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_HASWELL_L:
- case INTEL_FAM6_HASWELL_G:
+ case INTEL_HASWELL:
+ case INTEL_HASWELL_X:
+ case INTEL_HASWELL_L:
+ case INTEL_HASWELL_G:
x86_add_quirk(intel_ht_bug);
x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
@@ -6589,10 +6776,10 @@ __init int intel_pmu_init(void)
name = "haswell";
break;
- case INTEL_FAM6_BROADWELL:
- case INTEL_FAM6_BROADWELL_D:
- case INTEL_FAM6_BROADWELL_G:
- case INTEL_FAM6_BROADWELL_X:
+ case INTEL_BROADWELL:
+ case INTEL_BROADWELL_D:
+ case INTEL_BROADWELL_G:
+ case INTEL_BROADWELL_X:
x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -6631,8 +6818,8 @@ __init int intel_pmu_init(void)
name = "broadwell";
break;
- case INTEL_FAM6_XEON_PHI_KNL:
- case INTEL_FAM6_XEON_PHI_KNM:
+ case INTEL_XEON_PHI_KNL:
+ case INTEL_XEON_PHI_KNM:
memcpy(hw_cache_event_ids,
slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs,
@@ -6651,15 +6838,15 @@ __init int intel_pmu_init(void)
name = "knights-landing";
break;
- case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_SKYLAKE_X:
pmem = true;
fallthrough;
- case INTEL_FAM6_SKYLAKE_L:
- case INTEL_FAM6_SKYLAKE:
- case INTEL_FAM6_KABYLAKE_L:
- case INTEL_FAM6_KABYLAKE:
- case INTEL_FAM6_COMETLAKE_L:
- case INTEL_FAM6_COMETLAKE:
+ case INTEL_SKYLAKE_L:
+ case INTEL_SKYLAKE:
+ case INTEL_KABYLAKE_L:
+ case INTEL_KABYLAKE:
+ case INTEL_COMETLAKE_L:
+ case INTEL_COMETLAKE:
x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -6708,16 +6895,16 @@ __init int intel_pmu_init(void)
name = "skylake";
break;
- case INTEL_FAM6_ICELAKE_X:
- case INTEL_FAM6_ICELAKE_D:
+ case INTEL_ICELAKE_X:
+ case INTEL_ICELAKE_D:
x86_pmu.pebs_ept = 1;
pmem = true;
fallthrough;
- case INTEL_FAM6_ICELAKE_L:
- case INTEL_FAM6_ICELAKE:
- case INTEL_FAM6_TIGERLAKE_L:
- case INTEL_FAM6_TIGERLAKE:
- case INTEL_FAM6_ROCKETLAKE:
+ case INTEL_ICELAKE_L:
+ case INTEL_ICELAKE:
+ case INTEL_TIGERLAKE_L:
+ case INTEL_TIGERLAKE:
+ case INTEL_ROCKETLAKE:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -6752,16 +6939,22 @@ __init int intel_pmu_init(void)
name = "icelake";
break;
- case INTEL_FAM6_SAPPHIRERAPIDS_X:
- case INTEL_FAM6_EMERALDRAPIDS_X:
+ case INTEL_SAPPHIRERAPIDS_X:
+ case INTEL_EMERALDRAPIDS_X:
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
x86_pmu.extra_regs = intel_glc_extra_regs;
- fallthrough;
- case INTEL_FAM6_GRANITERAPIDS_X:
- case INTEL_FAM6_GRANITERAPIDS_D:
+ pr_cont("Sapphire Rapids events, ");
+ name = "sapphire_rapids";
+ goto glc_common;
+
+ case INTEL_GRANITERAPIDS_X:
+ case INTEL_GRANITERAPIDS_D:
+ x86_pmu.extra_regs = intel_rwc_extra_regs;
+ pr_cont("Granite Rapids events, ");
+ name = "granite_rapids";
+
+ glc_common:
intel_pmu_init_glc(NULL);
- if (!x86_pmu.extra_regs)
- x86_pmu.extra_regs = intel_rwc_extra_regs;
x86_pmu.pebs_ept = 1;
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = glc_get_event_constraints;
@@ -6772,15 +6965,13 @@ __init int intel_pmu_init(void)
td_attr = glc_td_events_attrs;
tsx_attr = glc_tsx_events_attrs;
intel_pmu_pebs_data_source_skl(true);
- pr_cont("Sapphire Rapids events, ");
- name = "sapphire_rapids";
break;
- case INTEL_FAM6_ALDERLAKE:
- case INTEL_FAM6_ALDERLAKE_L:
- case INTEL_FAM6_RAPTORLAKE:
- case INTEL_FAM6_RAPTORLAKE_P:
- case INTEL_FAM6_RAPTORLAKE_S:
+ case INTEL_ALDERLAKE:
+ case INTEL_ALDERLAKE_L:
+ case INTEL_RAPTORLAKE:
+ case INTEL_RAPTORLAKE_P:
+ case INTEL_RAPTORLAKE_S:
/*
* Alder Lake has 2 types of CPU, core and atom.
*
@@ -6788,7 +6979,7 @@ __init int intel_pmu_init(void)
*/
intel_pmu_init_hybrid(hybrid_big_small);
- x86_pmu.pebs_latency_data = adl_latency_data_small;
+ x86_pmu.pebs_latency_data = grt_latency_data;
x86_pmu.get_event_constraints = adl_get_event_constraints;
x86_pmu.hw_config = adl_hw_config;
x86_pmu.get_hybrid_cpu_type = adl_get_hybrid_cpu_type;
@@ -6803,11 +6994,13 @@ __init int intel_pmu_init(void)
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
intel_pmu_init_glc(&pmu->pmu);
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
- pmu->num_counters = x86_pmu.num_counters + 2;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
+ pmu->cntr_mask64 <<= 2;
+ pmu->cntr_mask64 |= 0x3;
+ pmu->fixed_cntr_mask64 <<= 1;
+ pmu->fixed_cntr_mask64 |= 0x1;
} else {
- pmu->num_counters = x86_pmu.num_counters;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
}
/*
@@ -6817,15 +7010,16 @@ __init int intel_pmu_init(void)
* mistakenly add extra counters for P-cores. Correct the number of
* counters here.
*/
- if ((pmu->num_counters > 8) || (pmu->num_counters_fixed > 4)) {
- pmu->num_counters = x86_pmu.num_counters;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+ if ((x86_pmu_num_counters(&pmu->pmu) > 8) || (x86_pmu_num_counters_fixed(&pmu->pmu) > 4)) {
+ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
}
- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
pmu->unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
- 0, pmu->num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
+
pmu->extra_regs = intel_glc_extra_regs;
/* Initialize Atom core specific PerfMon capabilities.*/
@@ -6838,11 +7032,11 @@ __init int intel_pmu_init(void)
name = "alderlake_hybrid";
break;
- case INTEL_FAM6_METEORLAKE:
- case INTEL_FAM6_METEORLAKE_L:
+ case INTEL_METEORLAKE:
+ case INTEL_METEORLAKE_L:
intel_pmu_init_hybrid(hybrid_big_small);
- x86_pmu.pebs_latency_data = mtl_latency_data_small;
+ x86_pmu.pebs_latency_data = cmt_latency_data;
x86_pmu.get_event_constraints = mtl_get_event_constraints;
x86_pmu.hw_config = adl_hw_config;
@@ -6867,6 +7061,33 @@ __init int intel_pmu_init(void)
name = "meteorlake_hybrid";
break;
+ case INTEL_LUNARLAKE_M:
+ case INTEL_ARROWLAKE:
+ intel_pmu_init_hybrid(hybrid_big_small);
+
+ x86_pmu.pebs_latency_data = lnl_latency_data;
+ x86_pmu.get_event_constraints = mtl_get_event_constraints;
+ x86_pmu.hw_config = adl_hw_config;
+
+ td_attr = lnl_hybrid_events_attrs;
+ mem_attr = mtl_hybrid_mem_attrs;
+ tsx_attr = adl_hybrid_tsx_attrs;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
+
+ /* Initialize big core specific PerfMon capabilities.*/
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
+ intel_pmu_init_lnc(&pmu->pmu);
+
+ /* Initialize Atom core specific PerfMon capabilities.*/
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
+ intel_pmu_init_skt(&pmu->pmu);
+
+ intel_pmu_pebs_data_source_lnl();
+ pr_cont("Lunarlake Hybrid events, ");
+ name = "lunarlake_hybrid";
+ break;
+
default:
switch (x86_pmu.version) {
case 1:
@@ -6892,9 +7113,9 @@ __init int intel_pmu_init(void)
* The constraints may be cut according to the CPUID enumeration
* by inserting the EVENT_CONSTRAINT_END.
*/
- if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED)
- x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
- intel_v5_gen_event_constraints[x86_pmu.num_counters_fixed].weight = -1;
+ if (fls64(x86_pmu.fixed_cntr_mask64) > INTEL_PMC_MAX_FIXED)
+ x86_pmu.fixed_cntr_mask64 &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
+ intel_v5_gen_event_constraints[fls64(x86_pmu.fixed_cntr_mask64)].weight = -1;
x86_pmu.event_constraints = intel_v5_gen_event_constraints;
pr_cont("generic architected perfmon, ");
name = "generic_arch_v5+";
@@ -6921,18 +7142,17 @@ __init int intel_pmu_init(void)
x86_pmu.attr_update = hybrid_attr_update;
}
- intel_pmu_check_num_counters(&x86_pmu.num_counters,
- &x86_pmu.num_counters_fixed,
- &x86_pmu.intel_ctrl,
- (u64)fixed_mask);
+ intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
+ &x86_pmu.fixed_cntr_mask64,
+ &x86_pmu.intel_ctrl);
/* AnyThread may be deprecated on arch perfmon v5 or later */
if (x86_pmu.intel_cap.anythread_deprecated)
x86_pmu.format_attrs = intel_arch_formats_attr;
intel_pmu_check_event_constraints(x86_pmu.event_constraints,
- x86_pmu.num_counters,
- x86_pmu.num_counters_fixed,
+ x86_pmu.cntr_mask64,
+ x86_pmu.fixed_cntr_mask64,
x86_pmu.intel_ctrl);
/*
* Access LBR MSR may cause #GP under certain circumstances.
@@ -6973,6 +7193,14 @@ __init int intel_pmu_init(void)
pr_cont("full-width counters, ");
}
+ /* Support V6+ MSR Aliasing */
+ if (x86_pmu.version >= 6) {
+ x86_pmu.perfctr = MSR_IA32_PMC_V6_GP0_CTR;
+ x86_pmu.eventsel = MSR_IA32_PMC_V6_GP0_CFG_A;
+ x86_pmu.fixedctr = MSR_IA32_PMC_V6_FX0_CTR;
+ x86_pmu.addr_offset = intel_pmu_v6_addr_offset;
+ }
+
if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics)
x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9d6e8f13d13a..be58cfb012dd 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -41,7 +41,7 @@
* MSR_CORE_C1_RES: CORE C1 Residency Counter
* perf code: 0x00
* Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
- * MTL,SRF,GRR
+ * MTL,SRF,GRR,ARL,LNL
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
@@ -53,50 +53,50 @@
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
* TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
- * GRR
+ * GRR,ARL,LNL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
* Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- * ICL,TGL,RKL,ADL,RPL,MTL
+ * ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
* Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
* KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- * RPL,SPR,MTL
+ * RPL,SPR,MTL,ARL,LNL
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
* GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- * ADL,RPL,MTL
+ * ADL,RPL,MTL,ARL,LNL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
+ * ARL,LNL
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
+ * KBL,CML,ICL,TGL,RKL
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL,MTL
+ * ADL,RPL,MTL,ARL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL,MTL
+ * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
* Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- * TNT,RKL,ADL,RPL,MTL
+ * TNT,RKL,ADL,RPL,MTL,ARL,LNL
* Scope: Package (physical package)
* MSR_MODULE_C6_RES_MS: Module C6 Residency Counter.
* perf code: 0x00
@@ -637,9 +637,18 @@ static const struct cstate_model adl_cstates __initconst = {
.pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
BIT(PERF_CSTATE_PKG_C3_RES) |
BIT(PERF_CSTATE_PKG_C6_RES) |
- BIT(PERF_CSTATE_PKG_C7_RES) |
BIT(PERF_CSTATE_PKG_C8_RES) |
- BIT(PERF_CSTATE_PKG_C9_RES) |
+ BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
+static const struct cstate_model lnl_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
+ BIT(PERF_CSTATE_CORE_C6_RES) |
+ BIT(PERF_CSTATE_CORE_C7_RES),
+
+ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
+ BIT(PERF_CSTATE_PKG_C3_RES) |
+ BIT(PERF_CSTATE_PKG_C6_RES) |
BIT(PERF_CSTATE_PKG_C10_RES),
};
@@ -763,6 +772,10 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_cstates),
X86_MATCH_VFM(INTEL_METEORLAKE, &adl_cstates),
X86_MATCH_VFM(INTEL_METEORLAKE_L, &adl_cstates),
+ X86_MATCH_VFM(INTEL_ARROWLAKE, &adl_cstates),
+ X86_MATCH_VFM(INTEL_ARROWLAKE_H, &adl_cstates),
+ X86_MATCH_VFM(INTEL_ARROWLAKE_U, &adl_cstates),
+ X86_MATCH_VFM(INTEL_LUNARLAKE_M, &lnl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index e010bfed8417..fa5ea65de0d0 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -63,6 +63,15 @@ union intel_x86_pebs_dse {
unsigned int mtl_fwd_blk:1;
unsigned int ld_reserved4:24;
};
+ struct {
+ unsigned int lnc_dse:8;
+ unsigned int ld_reserved5:2;
+ unsigned int lnc_stlb_miss:1;
+ unsigned int lnc_locked:1;
+ unsigned int lnc_data_blk:1;
+ unsigned int lnc_addr_blk:1;
+ unsigned int ld_reserved6:18;
+ };
};
@@ -77,7 +86,7 @@ union intel_x86_pebs_dse {
#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
/* Version for Sandy Bridge and later */
-static u64 pebs_data_source[] = {
+static u64 pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = {
P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */
OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
@@ -173,6 +182,40 @@ void __init intel_pmu_pebs_data_source_cmt(void)
__intel_pmu_pebs_data_source_cmt(pebs_data_source);
}
+/* Version for Lion Cove and later */
+static u64 lnc_pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = {
+ P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* 0x00: ukn L3 */
+ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 hit */
+ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x02: L1 hit */
+ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x03: LFB/L1 Miss Handling Buffer hit */
+ 0, /* 0x04: Reserved */
+ OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x05: L2 Hit */
+ OP_LH | LEVEL(L2_MHB) | P(SNOOP, NONE), /* 0x06: L2 Miss Handling Buffer Hit */
+ 0, /* 0x07: Reserved */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x08: L3 Hit */
+ 0, /* 0x09: Reserved */
+ 0, /* 0x0a: Reserved */
+ 0, /* 0x0b: Reserved */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* 0x0c: L3 Hit Snoop Fwd */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0d: L3 Hit Snoop HitM */
+ 0, /* 0x0e: Reserved */
+ P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0f: L3 Miss Snoop HitM */
+ OP_LH | LEVEL(MSC) | P(SNOOP, NONE), /* 0x10: Memory-side Cache Hit */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* 0x11: Local Memory Hit */
+};
+
+void __init intel_pmu_pebs_data_source_lnl(void)
+{
+ u64 *data_source;
+
+ data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source;
+ memcpy(data_source, lnc_pebs_data_source, sizeof(lnc_pebs_data_source));
+
+ data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
+ memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+ __intel_pmu_pebs_data_source_cmt(data_source);
+}
+
static u64 precise_store_data(u64 status)
{
union intel_x86_pebs_dse dse;
@@ -257,14 +300,14 @@ static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
}
/* Retrieve the latency data for e-core of ADL */
-static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
- u8 dse, bool tlb, bool lock, bool blk)
+static u64 __grt_latency_data(struct perf_event *event, u64 status,
+ u8 dse, bool tlb, bool lock, bool blk)
{
u64 val;
WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big);
- dse &= PERF_PEBS_DATA_SOURCE_MASK;
+ dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
val = hybrid_var(event->pmu, pebs_data_source)[dse];
pebs_set_tlb_lock(&val, tlb, lock);
@@ -277,27 +320,72 @@ static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
return val;
}
-u64 adl_latency_data_small(struct perf_event *event, u64 status)
+u64 grt_latency_data(struct perf_event *event, u64 status)
{
union intel_x86_pebs_dse dse;
dse.val = status;
- return __adl_latency_data_small(event, status, dse.ld_dse,
- dse.ld_locked, dse.ld_stlb_miss,
- dse.ld_data_blk);
+ return __grt_latency_data(event, status, dse.ld_dse,
+ dse.ld_locked, dse.ld_stlb_miss,
+ dse.ld_data_blk);
}
/* Retrieve the latency data for e-core of MTL */
-u64 mtl_latency_data_small(struct perf_event *event, u64 status)
+u64 cmt_latency_data(struct perf_event *event, u64 status)
{
union intel_x86_pebs_dse dse;
dse.val = status;
- return __adl_latency_data_small(event, status, dse.mtl_dse,
- dse.mtl_stlb_miss, dse.mtl_locked,
- dse.mtl_fwd_blk);
+ return __grt_latency_data(event, status, dse.mtl_dse,
+ dse.mtl_stlb_miss, dse.mtl_locked,
+ dse.mtl_fwd_blk);
+}
+
+static u64 lnc_latency_data(struct perf_event *event, u64 status)
+{
+ union intel_x86_pebs_dse dse;
+ union perf_mem_data_src src;
+ u64 val;
+
+ dse.val = status;
+
+ /* LNC core latency data */
+ val = hybrid_var(event->pmu, pebs_data_source)[status & PERF_PEBS_DATA_SOURCE_MASK];
+ if (!val)
+ val = P(OP, LOAD) | LEVEL(NA) | P(SNOOP, NA);
+
+ if (dse.lnc_stlb_miss)
+ val |= P(TLB, MISS) | P(TLB, L2);
+ else
+ val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+ if (dse.lnc_locked)
+ val |= P(LOCK, LOCKED);
+
+ if (dse.lnc_data_blk)
+ val |= P(BLK, DATA);
+ if (dse.lnc_addr_blk)
+ val |= P(BLK, ADDR);
+ if (!dse.lnc_data_blk && !dse.lnc_addr_blk)
+ val |= P(BLK, NA);
+
+ src.val = val;
+ if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+ src.mem_op = P(OP, STORE);
+
+ return src.val;
+}
+
+u64 lnl_latency_data(struct perf_event *event, u64 status)
+{
+ struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+ if (pmu->pmu_type == hybrid_small)
+ return cmt_latency_data(event, status);
+
+ return lnc_latency_data(event, status);
}
static u64 load_latency_data(struct perf_event *event, u64 status)
@@ -1086,6 +1174,32 @@ struct event_constraint intel_glc_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_lnc_pebs_event_constraints[] = {
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
+
+ INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+ INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf),
+
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),
+
+ /*
+ * Everything else is handled by PMU_FL_PEBS_ALL, because we
+ * need the full constraints from the main table.
+ */
+
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *pebs_constraints = hybrid(event->pmu, pebs_constraints);
@@ -1137,8 +1251,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sche
static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
{
struct debug_store *ds = cpuc->ds;
- int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+ int max_pebs_events = intel_pmu_max_num_pebs(cpuc->pmu);
u64 threshold;
int reserved;
@@ -1146,7 +1259,7 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
return;
if (x86_pmu.flags & PMU_FL_PEBS_ALL)
- reserved = max_pebs_events + num_counters_fixed;
+ reserved = max_pebs_events + x86_pmu_max_num_counters_fixed(cpuc->pmu);
else
reserved = max_pebs_events;
@@ -1831,8 +1944,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
set_linear_ip(regs, basic->ip);
regs->flags = PERF_EFLAGS_EXACT;
- if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY))
- data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+ if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
+ if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
+ data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+ else
+ data->weight.var3_w = 0;
+ }
/*
* The record for MEMINFO is in front of GP
@@ -2157,6 +2274,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
void *base, *at, *top;
short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ int max_pebs_events = intel_pmu_max_num_pebs(NULL);
int bit, i, size;
u64 mask;
@@ -2168,11 +2286,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
ds->pebs_index = ds->pebs_buffer_base;
- mask = (1ULL << x86_pmu.max_pebs_events) - 1;
- size = x86_pmu.max_pebs_events;
+ mask = x86_pmu.pebs_events_mask;
+ size = max_pebs_events;
if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
- mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
- size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+ mask |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
+ size = INTEL_PMC_IDX_FIXED + x86_pmu_max_num_counters_fixed(NULL);
}
if (unlikely(base >= top)) {
@@ -2208,8 +2326,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
pebs_status = p->status = cpuc->pebs_enabled;
bit = find_first_bit((unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events);
- if (bit >= x86_pmu.max_pebs_events)
+ max_pebs_events);
+
+ if (!(x86_pmu.pebs_events_mask & (1 << bit)))
continue;
/*
@@ -2267,12 +2386,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
{
short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
struct debug_store *ds = cpuc->ds;
struct perf_event *event;
void *base, *at, *top;
- int bit, size;
+ int bit;
u64 mask;
if (!x86_pmu.pebs_active)
@@ -2283,12 +2400,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
ds->pebs_index = ds->pebs_buffer_base;
- mask = ((1ULL << max_pebs_events) - 1) |
- (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
- size = INTEL_PMC_IDX_FIXED + num_counters_fixed;
+ mask = hybrid(cpuc->pmu, pebs_events_mask) |
+ (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
if (unlikely(base >= top)) {
- intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
return;
}
@@ -2298,11 +2414,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
pebs_status &= mask;
- for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
counts[bit]++;
}
- for_each_set_bit(bit, (unsigned long *)&mask, size) {
+ for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
if (counts[bit] == 0)
continue;
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 618001c208e8..034a1f6a457c 100644
--- a/arch/x86/events/intel/knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -303,7 +303,7 @@ static const struct x86_pmu knc_pmu __initconst = {
.apic = 1,
.max_period = (1ULL << 39) - 1,
.version = 0,
- .num_counters = 2,
+ .cntr_mask64 = 0x3,
.cntval_bits = 40,
.cntval_mask = (1ULL << 40) - 1,
.get_event_constraints = x86_get_event_constraints,
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index 35936188db01..844bc4fc4724 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -919,7 +919,7 @@ static void p4_pmu_disable_all(void)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[idx];
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -998,7 +998,7 @@ static void p4_pmu_enable_all(int added)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[idx];
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -1040,7 +1040,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
cpuc = this_cpu_ptr(&cpu_hw_events);
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
int overflow;
if (!test_bit(idx, cpuc->active_mask)) {
@@ -1353,7 +1353,7 @@ static __initconst const struct x86_pmu p4_pmu = {
* though leave it restricted at moment assuming
* HT is on
*/
- .num_counters = ARCH_P4_MAX_CCCR,
+ .cntr_mask64 = GENMASK_ULL(ARCH_P4_MAX_CCCR - 1, 0),
.apic = 1,
.cntval_bits = ARCH_P4_CNTRVAL_BITS,
.cntval_mask = ARCH_P4_CNTRVAL_MASK,
@@ -1395,7 +1395,7 @@ __init int p4_pmu_init(void)
*
* Solve this by zero'ing out the registers to mimic a reset.
*/
- for (i = 0; i < x86_pmu.num_counters; i++) {
+ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
reg = x86_pmu_config_addr(i);
wrmsrl_safe(reg, 0ULL);
}
diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
index 408879b0c0d4..a6cffb4f4ef5 100644
--- a/arch/x86/events/intel/p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -214,7 +214,7 @@ static __initconst const struct x86_pmu p6_pmu = {
.apic = 1,
.max_period = (1ULL << 31) - 1,
.version = 0,
- .num_counters = 2,
+ .cntr_mask64 = 0x3,
/*
* Events have 40 bits implemented. However they are designed such
* that bits [32-39] are sign extensions of bit 31. As such the
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 14db6d9d318b..b4aa8daa4773 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -878,7 +878,7 @@ static void pt_update_head(struct pt *pt)
*/
static void *pt_buffer_region(struct pt_buffer *buf)
{
- return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
+ return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
}
/**
@@ -990,7 +990,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg)
* order allocations, there shouldn't be many of these.
*/
list_for_each_entry(topa, &buf->tables, list) {
- if (topa->offset + topa->size > pg << PAGE_SHIFT)
+ if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT)
goto found;
}
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 96906a62aacd..f5e46c04c145 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -33,8 +33,8 @@ struct topa_entry {
u64 rsvd2 : 1;
u64 size : 4;
u64 rsvd3 : 2;
- u64 base : 36;
- u64 rsvd4 : 16;
+ u64 base : 40;
+ u64 rsvd4 : 12;
};
/* TSC to Core Crystal Clock Ratio */
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index c68f5b39952b..64ca8625eb58 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -264,6 +264,9 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box,
return;
}
+ if (intel_generic_uncore_assign_hw_event(event, box))
+ return;
+
hwc->config_base = uncore_event_ctl(box, hwc->idx);
hwc->event_base = uncore_perf_ctr(box, hwc->idx);
}
@@ -844,7 +847,9 @@ static void uncore_pmu_disable(struct pmu *pmu)
static ssize_t uncore_get_attr_cpumask(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask);
+ struct intel_uncore_pmu *pmu = container_of(dev_get_drvdata(dev), struct intel_uncore_pmu, pmu);
+
+ return cpumap_print_to_pagebuf(true, buf, &pmu->cpu_mask);
}
static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
@@ -861,7 +866,10 @@ static const struct attribute_group uncore_pmu_attr_group = {
static inline int uncore_get_box_id(struct intel_uncore_type *type,
struct intel_uncore_pmu *pmu)
{
- return type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx;
+ if (type->boxes)
+ return intel_uncore_find_discovery_unit_id(type->boxes, -1, pmu->pmu_idx);
+
+ return pmu->pmu_idx;
}
void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu)
@@ -962,6 +970,9 @@ static void uncore_type_exit(struct intel_uncore_type *type)
if (type->cleanup_mapping)
type->cleanup_mapping(type);
+ if (type->cleanup_extra_boxes)
+ type->cleanup_extra_boxes(type);
+
if (pmu) {
for (i = 0; i < type->num_boxes; i++, pmu++) {
uncore_pmu_unregister(pmu);
@@ -970,10 +981,7 @@ static void uncore_type_exit(struct intel_uncore_type *type)
kfree(type->pmus);
type->pmus = NULL;
}
- if (type->box_ids) {
- kfree(type->box_ids);
- type->box_ids = NULL;
- }
+
kfree(type->events_group);
type->events_group = NULL;
}
@@ -1077,22 +1085,19 @@ static struct intel_uncore_pmu *
uncore_pci_find_dev_pmu_from_types(struct pci_dev *pdev)
{
struct intel_uncore_type **types = uncore_pci_uncores;
+ struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type;
- u64 box_ctl;
- int i, die;
+ struct rb_node *node;
for (; *types; types++) {
type = *types;
- for (die = 0; die < __uncore_max_dies; die++) {
- for (i = 0; i < type->num_boxes; i++) {
- if (!type->box_ctls[die])
- continue;
- box_ctl = type->box_ctls[die] + type->pci_offsets[i];
- if (pdev->devfn == UNCORE_DISCOVERY_PCI_DEVFN(box_ctl) &&
- pdev->bus->number == UNCORE_DISCOVERY_PCI_BUS(box_ctl) &&
- pci_domain_nr(pdev->bus) == UNCORE_DISCOVERY_PCI_DOMAIN(box_ctl))
- return &type->pmus[i];
- }
+
+ for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+ unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ if (pdev->devfn == UNCORE_DISCOVERY_PCI_DEVFN(unit->addr) &&
+ pdev->bus->number == UNCORE_DISCOVERY_PCI_BUS(unit->addr) &&
+ pci_domain_nr(pdev->bus) == UNCORE_DISCOVERY_PCI_DOMAIN(unit->addr))
+ return &type->pmus[unit->pmu_idx];
}
}
@@ -1368,28 +1373,25 @@ static struct notifier_block uncore_pci_notifier = {
static void uncore_pci_pmus_register(void)
{
struct intel_uncore_type **types = uncore_pci_uncores;
+ struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
+ struct rb_node *node;
struct pci_dev *pdev;
- u64 box_ctl;
- int i, die;
for (; *types; types++) {
type = *types;
- for (die = 0; die < __uncore_max_dies; die++) {
- for (i = 0; i < type->num_boxes; i++) {
- if (!type->box_ctls[die])
- continue;
- box_ctl = type->box_ctls[die] + type->pci_offsets[i];
- pdev = pci_get_domain_bus_and_slot(UNCORE_DISCOVERY_PCI_DOMAIN(box_ctl),
- UNCORE_DISCOVERY_PCI_BUS(box_ctl),
- UNCORE_DISCOVERY_PCI_DEVFN(box_ctl));
- if (!pdev)
- continue;
- pmu = &type->pmus[i];
-
- uncore_pci_pmu_register(pdev, type, pmu, die);
- }
+
+ for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+ unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ pdev = pci_get_domain_bus_and_slot(UNCORE_DISCOVERY_PCI_DOMAIN(unit->addr),
+ UNCORE_DISCOVERY_PCI_BUS(unit->addr),
+ UNCORE_DISCOVERY_PCI_DEVFN(unit->addr));
+
+ if (!pdev)
+ continue;
+ pmu = &type->pmus[unit->pmu_idx];
+ uncore_pci_pmu_register(pdev, type, pmu, unit->die);
}
}
@@ -1454,6 +1456,18 @@ static void uncore_pci_exit(void)
}
}
+static bool uncore_die_has_box(struct intel_uncore_type *type,
+ int die, unsigned int pmu_idx)
+{
+ if (!type->boxes)
+ return true;
+
+ if (intel_uncore_find_discovery_unit_id(type->boxes, die, pmu_idx) < 0)
+ return false;
+
+ return true;
+}
+
static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
int new_cpu)
{
@@ -1469,18 +1483,25 @@ static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
if (old_cpu < 0) {
WARN_ON_ONCE(box->cpu != -1);
- box->cpu = new_cpu;
+ if (uncore_die_has_box(type, die, pmu->pmu_idx)) {
+ box->cpu = new_cpu;
+ cpumask_set_cpu(new_cpu, &pmu->cpu_mask);
+ }
continue;
}
- WARN_ON_ONCE(box->cpu != old_cpu);
+ WARN_ON_ONCE(box->cpu != -1 && box->cpu != old_cpu);
box->cpu = -1;
+ cpumask_clear_cpu(old_cpu, &pmu->cpu_mask);
if (new_cpu < 0)
continue;
+ if (!uncore_die_has_box(type, die, pmu->pmu_idx))
+ continue;
uncore_pmu_cancel_hrtimer(box);
perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu);
box->cpu = new_cpu;
+ cpumask_set_cpu(new_cpu, &pmu->cpu_mask);
}
}
@@ -1503,7 +1524,7 @@ static void uncore_box_unref(struct intel_uncore_type **types, int id)
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[id];
- if (box && atomic_dec_return(&box->refcnt) == 0)
+ if (box && box->cpu >= 0 && atomic_dec_return(&box->refcnt) == 0)
uncore_box_exit(box);
}
}
@@ -1593,7 +1614,7 @@ static int uncore_box_ref(struct intel_uncore_type **types,
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
box = pmu->boxes[id];
- if (box && atomic_inc_return(&box->refcnt) == 1)
+ if (box && box->cpu >= 0 && atomic_inc_return(&box->refcnt) == 1)
uncore_box_init(box);
}
}
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 4838502d89ae..027ef292c602 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -62,7 +62,6 @@ struct intel_uncore_type {
unsigned fixed_ctr;
unsigned fixed_ctl;
unsigned box_ctl;
- u64 *box_ctls; /* Unit ctrl addr of the first box of each die */
union {
unsigned msr_offset;
unsigned mmio_offset;
@@ -76,7 +75,6 @@ struct intel_uncore_type {
u64 *pci_offsets;
u64 *mmio_offsets;
};
- unsigned *box_ids;
struct event_constraint unconstrainted;
struct event_constraint *constraints;
struct intel_uncore_pmu *pmus;
@@ -86,6 +84,7 @@ struct intel_uncore_type {
const struct attribute_group *attr_groups[4];
const struct attribute_group **attr_update;
struct pmu *pmu; /* for custom pmu ops */
+ struct rb_root *boxes;
/*
* Uncore PMU would store relevant platform topology configuration here
* to identify which platform component each PMON block of that type is
@@ -98,6 +97,10 @@ struct intel_uncore_type {
int (*get_topology)(struct intel_uncore_type *type);
void (*set_mapping)(struct intel_uncore_type *type);
void (*cleanup_mapping)(struct intel_uncore_type *type);
+ /*
+ * Optional callbacks for extra uncore units cleanup
+ */
+ void (*cleanup_extra_boxes)(struct intel_uncore_type *type);
};
#define pmu_group attr_groups[0]
@@ -125,6 +128,7 @@ struct intel_uncore_pmu {
int func_id;
bool registered;
atomic_t activeboxes;
+ cpumask_t cpu_mask;
struct intel_uncore_type *type;
struct intel_uncore_box **boxes;
};
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 9a698a92962a..571e44b49691 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -89,9 +89,7 @@ add_uncore_discovery_type(struct uncore_unit_discovery *unit)
if (!type)
return NULL;
- type->box_ctrl_die = kcalloc(__uncore_max_dies, sizeof(u64), GFP_KERNEL);
- if (!type->box_ctrl_die)
- goto free_type;
+ type->units = RB_ROOT;
type->access_type = unit->access_type;
num_discovered_types[type->access_type]++;
@@ -100,12 +98,6 @@ add_uncore_discovery_type(struct uncore_unit_discovery *unit)
rb_add(&type->node, &discovery_tables, __type_less);
return type;
-
-free_type:
- kfree(type);
-
- return NULL;
-
}
static struct intel_uncore_discovery_type *
@@ -120,14 +112,118 @@ get_uncore_discovery_type(struct uncore_unit_discovery *unit)
return add_uncore_discovery_type(unit);
}
+static inline int pmu_idx_cmp(const void *key, const struct rb_node *b)
+{
+ struct intel_uncore_discovery_unit *unit;
+ const unsigned int *id = key;
+
+ unit = rb_entry(b, struct intel_uncore_discovery_unit, node);
+
+ if (unit->pmu_idx > *id)
+ return -1;
+ else if (unit->pmu_idx < *id)
+ return 1;
+
+ return 0;
+}
+
+static struct intel_uncore_discovery_unit *
+intel_uncore_find_discovery_unit(struct rb_root *units, int die,
+ unsigned int pmu_idx)
+{
+ struct intel_uncore_discovery_unit *unit;
+ struct rb_node *pos;
+
+ if (!units)
+ return NULL;
+
+ pos = rb_find_first(&pmu_idx, units, pmu_idx_cmp);
+ if (!pos)
+ return NULL;
+ unit = rb_entry(pos, struct intel_uncore_discovery_unit, node);
+
+ if (die < 0)
+ return unit;
+
+ for (; pos; pos = rb_next(pos)) {
+ unit = rb_entry(pos, struct intel_uncore_discovery_unit, node);
+
+ if (unit->pmu_idx != pmu_idx)
+ break;
+
+ if (unit->die == die)
+ return unit;
+ }
+
+ return NULL;
+}
+
+int intel_uncore_find_discovery_unit_id(struct rb_root *units, int die,
+ unsigned int pmu_idx)
+{
+ struct intel_uncore_discovery_unit *unit;
+
+ unit = intel_uncore_find_discovery_unit(units, die, pmu_idx);
+ if (unit)
+ return unit->id;
+
+ return -1;
+}
+
+static inline bool unit_less(struct rb_node *a, const struct rb_node *b)
+{
+ struct intel_uncore_discovery_unit *a_node, *b_node;
+
+ a_node = rb_entry(a, struct intel_uncore_discovery_unit, node);
+ b_node = rb_entry(b, struct intel_uncore_discovery_unit, node);
+
+ if (a_node->pmu_idx < b_node->pmu_idx)
+ return true;
+ if (a_node->pmu_idx > b_node->pmu_idx)
+ return false;
+
+ if (a_node->die < b_node->die)
+ return true;
+ if (a_node->die > b_node->die)
+ return false;
+
+ return 0;
+}
+
+static inline struct intel_uncore_discovery_unit *
+uncore_find_unit(struct rb_root *root, unsigned int id)
+{
+ struct intel_uncore_discovery_unit *unit;
+ struct rb_node *node;
+
+ for (node = rb_first(root); node; node = rb_next(node)) {
+ unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ if (unit->id == id)
+ return unit;
+ }
+
+ return NULL;
+}
+
+void uncore_find_add_unit(struct intel_uncore_discovery_unit *node,
+ struct rb_root *root, u16 *num_units)
+{
+ struct intel_uncore_discovery_unit *unit = uncore_find_unit(root, node->id);
+
+ if (unit)
+ node->pmu_idx = unit->pmu_idx;
+ else if (num_units)
+ node->pmu_idx = (*num_units)++;
+
+ rb_add(&node->node, root, unit_less);
+}
+
static void
uncore_insert_box_info(struct uncore_unit_discovery *unit,
- int die, bool parsed)
+ int die)
{
+ struct intel_uncore_discovery_unit *node;
struct intel_uncore_discovery_type *type;
- unsigned int *ids;
- u64 *box_offset;
- int i;
if (!unit->ctl || !unit->ctl_offset || !unit->ctr_offset) {
pr_info("Invalid address is detected for uncore type %d box %d, "
@@ -136,71 +232,29 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit,
return;
}
- if (parsed) {
- type = search_uncore_discovery_type(unit->box_type);
- if (!type) {
- pr_info("A spurious uncore type %d is detected, "
- "Disable the uncore type.\n",
- unit->box_type);
- return;
- }
- /* Store the first box of each die */
- if (!type->box_ctrl_die[die])
- type->box_ctrl_die[die] = unit->ctl;
+ node = kzalloc(sizeof(*node), GFP_KERNEL);
+ if (!node)
return;
- }
- type = get_uncore_discovery_type(unit);
- if (!type)
- return;
+ node->die = die;
+ node->id = unit->box_id;
+ node->addr = unit->ctl;
- box_offset = kcalloc(type->num_boxes + 1, sizeof(u64), GFP_KERNEL);
- if (!box_offset)
+ type = get_uncore_discovery_type(unit);
+ if (!type) {
+ kfree(node);
return;
+ }
- ids = kcalloc(type->num_boxes + 1, sizeof(unsigned int), GFP_KERNEL);
- if (!ids)
- goto free_box_offset;
+ uncore_find_add_unit(node, &type->units, &type->num_units);
/* Store generic information for the first box */
- if (!type->num_boxes) {
- type->box_ctrl = unit->ctl;
- type->box_ctrl_die[die] = unit->ctl;
+ if (type->num_units == 1) {
type->num_counters = unit->num_regs;
type->counter_width = unit->bit_width;
type->ctl_offset = unit->ctl_offset;
type->ctr_offset = unit->ctr_offset;
- *ids = unit->box_id;
- goto end;
- }
-
- for (i = 0; i < type->num_boxes; i++) {
- ids[i] = type->ids[i];
- box_offset[i] = type->box_offset[i];
-
- if (unit->box_id == ids[i]) {
- pr_info("Duplicate uncore type %d box ID %d is detected, "
- "Drop the duplicate uncore unit.\n",
- unit->box_type, unit->box_id);
- goto free_ids;
- }
}
- ids[i] = unit->box_id;
- box_offset[i] = unit->ctl - type->box_ctrl;
- kfree(type->ids);
- kfree(type->box_offset);
-end:
- type->ids = ids;
- type->box_offset = box_offset;
- type->num_boxes++;
- return;
-
-free_ids:
- kfree(ids);
-
-free_box_offset:
- kfree(box_offset);
-
}
static bool
@@ -279,7 +333,7 @@ static int parse_discovery_table(struct pci_dev *dev, int die,
if (uncore_ignore_unit(&unit, ignore))
continue;
- uncore_insert_box_info(&unit, die, *parsed);
+ uncore_insert_box_info(&unit, die);
}
*parsed = true;
@@ -339,9 +393,16 @@ err:
void intel_uncore_clear_discovery_tables(void)
{
struct intel_uncore_discovery_type *type, *next;
+ struct intel_uncore_discovery_unit *pos;
+ struct rb_node *node;
rbtree_postorder_for_each_entry_safe(type, next, &discovery_tables, node) {
- kfree(type->box_ctrl_die);
+ while (!RB_EMPTY_ROOT(&type->units)) {
+ node = rb_first(&type->units);
+ pos = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ rb_erase(node, &type->units);
+ kfree(pos);
+ }
kfree(type);
}
}
@@ -366,19 +427,31 @@ static const struct attribute_group generic_uncore_format_group = {
.attrs = generic_uncore_formats_attr,
};
+static u64 intel_generic_uncore_box_ctl(struct intel_uncore_box *box)
+{
+ struct intel_uncore_discovery_unit *unit;
+
+ unit = intel_uncore_find_discovery_unit(box->pmu->type->boxes,
+ -1, box->pmu->pmu_idx);
+ if (WARN_ON_ONCE(!unit))
+ return 0;
+
+ return unit->addr;
+}
+
void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box)
{
- wrmsrl(uncore_msr_box_ctl(box), GENERIC_PMON_BOX_CTL_INT);
+ wrmsrl(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_INT);
}
void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box)
{
- wrmsrl(uncore_msr_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ);
+ wrmsrl(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ);
}
void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box)
{
- wrmsrl(uncore_msr_box_ctl(box), 0);
+ wrmsrl(intel_generic_uncore_box_ctl(box), 0);
}
static void intel_generic_uncore_msr_enable_event(struct intel_uncore_box *box,
@@ -406,10 +479,47 @@ static struct intel_uncore_ops generic_uncore_msr_ops = {
.read_counter = uncore_msr_read_counter,
};
+bool intel_generic_uncore_assign_hw_event(struct perf_event *event,
+ struct intel_uncore_box *box)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 box_ctl;
+
+ if (!box->pmu->type->boxes)
+ return false;
+
+ if (box->io_addr) {
+ hwc->config_base = uncore_pci_event_ctl(box, hwc->idx);
+ hwc->event_base = uncore_pci_perf_ctr(box, hwc->idx);
+ return true;
+ }
+
+ box_ctl = intel_generic_uncore_box_ctl(box);
+ if (!box_ctl)
+ return false;
+
+ if (box->pci_dev) {
+ box_ctl = UNCORE_DISCOVERY_PCI_BOX_CTRL(box_ctl);
+ hwc->config_base = box_ctl + uncore_pci_event_ctl(box, hwc->idx);
+ hwc->event_base = box_ctl + uncore_pci_perf_ctr(box, hwc->idx);
+ return true;
+ }
+
+ hwc->config_base = box_ctl + box->pmu->type->event_ctl + hwc->idx;
+ hwc->event_base = box_ctl + box->pmu->type->perf_ctr + hwc->idx;
+
+ return true;
+}
+
+static inline int intel_pci_uncore_box_ctl(struct intel_uncore_box *box)
+{
+ return UNCORE_DISCOVERY_PCI_BOX_CTRL(intel_generic_uncore_box_ctl(box));
+}
+
void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
+ int box_ctl = intel_pci_uncore_box_ctl(box);
__set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_INT);
@@ -418,7 +528,7 @@ void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box)
void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
+ int box_ctl = intel_pci_uncore_box_ctl(box);
pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_FRZ);
}
@@ -426,7 +536,7 @@ void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box)
void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
+ int box_ctl = intel_pci_uncore_box_ctl(box);
pci_write_config_dword(pdev, box_ctl, 0);
}
@@ -473,34 +583,30 @@ static struct intel_uncore_ops generic_uncore_pci_ops = {
#define UNCORE_GENERIC_MMIO_SIZE 0x4000
-static u64 generic_uncore_mmio_box_ctl(struct intel_uncore_box *box)
-{
- struct intel_uncore_type *type = box->pmu->type;
-
- if (!type->box_ctls || !type->box_ctls[box->dieid] || !type->mmio_offsets)
- return 0;
-
- return type->box_ctls[box->dieid] + type->mmio_offsets[box->pmu->pmu_idx];
-}
-
void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box)
{
- u64 box_ctl = generic_uncore_mmio_box_ctl(box);
+ static struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type = box->pmu->type;
resource_size_t addr;
- if (!box_ctl) {
+ unit = intel_uncore_find_discovery_unit(type->boxes, box->dieid, box->pmu->pmu_idx);
+ if (!unit) {
+ pr_warn("Uncore type %d id %d: Cannot find box control address.\n",
+ type->type_id, box->pmu->pmu_idx);
+ return;
+ }
+
+ if (!unit->addr) {
pr_warn("Uncore type %d box %d: Invalid box control address.\n",
- type->type_id, type->box_ids[box->pmu->pmu_idx]);
+ type->type_id, unit->id);
return;
}
- addr = box_ctl;
+ addr = unit->addr;
box->io_addr = ioremap(addr, UNCORE_GENERIC_MMIO_SIZE);
if (!box->io_addr) {
pr_warn("Uncore type %d box %d: ioremap error for 0x%llx.\n",
- type->type_id, type->box_ids[box->pmu->pmu_idx],
- (unsigned long long)addr);
+ type->type_id, unit->id, (unsigned long long)addr);
return;
}
@@ -560,34 +666,22 @@ static bool uncore_update_uncore_type(enum uncore_access_type type_id,
struct intel_uncore_discovery_type *type)
{
uncore->type_id = type->type;
- uncore->num_boxes = type->num_boxes;
uncore->num_counters = type->num_counters;
uncore->perf_ctr_bits = type->counter_width;
- uncore->box_ids = type->ids;
+ uncore->perf_ctr = (unsigned int)type->ctr_offset;
+ uncore->event_ctl = (unsigned int)type->ctl_offset;
+ uncore->boxes = &type->units;
+ uncore->num_boxes = type->num_units;
switch (type_id) {
case UNCORE_ACCESS_MSR:
uncore->ops = &generic_uncore_msr_ops;
- uncore->perf_ctr = (unsigned int)type->box_ctrl + type->ctr_offset;
- uncore->event_ctl = (unsigned int)type->box_ctrl + type->ctl_offset;
- uncore->box_ctl = (unsigned int)type->box_ctrl;
- uncore->msr_offsets = type->box_offset;
break;
case UNCORE_ACCESS_PCI:
uncore->ops = &generic_uncore_pci_ops;
- uncore->perf_ctr = (unsigned int)UNCORE_DISCOVERY_PCI_BOX_CTRL(type->box_ctrl) + type->ctr_offset;
- uncore->event_ctl = (unsigned int)UNCORE_DISCOVERY_PCI_BOX_CTRL(type->box_ctrl) + type->ctl_offset;
- uncore->box_ctl = (unsigned int)UNCORE_DISCOVERY_PCI_BOX_CTRL(type->box_ctrl);
- uncore->box_ctls = type->box_ctrl_die;
- uncore->pci_offsets = type->box_offset;
break;
case UNCORE_ACCESS_MMIO:
uncore->ops = &generic_uncore_mmio_ops;
- uncore->perf_ctr = (unsigned int)type->ctr_offset;
- uncore->event_ctl = (unsigned int)type->ctl_offset;
- uncore->box_ctl = (unsigned int)type->box_ctrl;
- uncore->box_ctls = type->box_ctrl_die;
- uncore->mmio_offsets = type->box_offset;
uncore->mmio_map_size = UNCORE_GENERIC_MMIO_SIZE;
break;
default:
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index 22e769a81103..0e94aa7db8e7 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -113,19 +113,24 @@ struct uncore_unit_discovery {
};
};
+struct intel_uncore_discovery_unit {
+ struct rb_node node;
+ unsigned int pmu_idx; /* The idx of the corresponding PMU */
+ unsigned int id; /* Unit ID */
+ unsigned int die; /* Die ID */
+ u64 addr; /* Unit Control Address */
+};
+
struct intel_uncore_discovery_type {
struct rb_node node;
enum uncore_access_type access_type;
- u64 box_ctrl; /* Unit ctrl addr of the first box */
- u64 *box_ctrl_die; /* Unit ctrl addr of the first box of each die */
+ struct rb_root units; /* Unit ctrl addr for all units */
u16 type; /* Type ID of the uncore block */
u8 num_counters;
u8 counter_width;
u8 ctl_offset; /* Counter Control 0 offset */
u8 ctr_offset; /* Counter 0 offset */
- u16 num_boxes; /* number of boxes for the uncore block */
- unsigned int *ids; /* Box IDs */
- u64 *box_offset; /* Box offset */
+ u16 num_units; /* number of units */
};
bool intel_uncore_has_discovery_tables(int *ignore);
@@ -156,3 +161,10 @@ u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box,
struct intel_uncore_type **
intel_uncore_generic_init_uncores(enum uncore_access_type type_id, int num_extra);
+
+int intel_uncore_find_discovery_unit_id(struct rb_root *units, int die,
+ unsigned int pmu_idx);
+bool intel_generic_uncore_assign_hw_event(struct perf_event *event,
+ struct intel_uncore_box *box);
+void uncore_find_add_unit(struct intel_uncore_discovery_unit *node,
+ struct rb_root *root, u16 *num_units);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 74b8b21e8990..ca98744343b8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -462,6 +462,7 @@
#define SPR_UBOX_DID 0x3250
/* SPR CHA */
+#define SPR_CHA_EVENT_MASK_EXT 0xffffffff
#define SPR_CHA_PMON_CTL_TID_EN (1 << 16)
#define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
SPR_CHA_PMON_CTL_TID_EN)
@@ -478,6 +479,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -5933,10 +5935,11 @@ static int spr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *ev
struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
bool tie_en = !!(event->hw.config & SPR_CHA_PMON_CTL_TID_EN);
struct intel_uncore_type *type = box->pmu->type;
+ int id = intel_uncore_find_discovery_unit_id(type->boxes, -1, box->pmu->pmu_idx);
if (tie_en) {
reg1->reg = SPR_C0_MSR_PMON_BOX_FILTER0 +
- HSWEP_CBO_MSR_OFFSET * type->box_ids[box->pmu->pmu_idx];
+ HSWEP_CBO_MSR_OFFSET * id;
reg1->config = event->attr.config1 & SPR_CHA_PMON_BOX_FILTER_TID;
reg1->idx = 0;
}
@@ -5958,7 +5961,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = {
static struct attribute *spr_uncore_cha_formats_attr[] = {
&format_attr_event.attr,
- &format_attr_umask_ext4.attr,
+ &format_attr_umask_ext5.attr,
&format_attr_tid_en2.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
@@ -5994,7 +5997,7 @@ ATTRIBUTE_GROUPS(uncore_alias);
static struct intel_uncore_type spr_uncore_chabox = {
.name = "cha",
.event_mask = SPR_CHA_PMON_EVENT_MASK,
- .event_mask_ext = SPR_RAW_EVENT_MASK_EXT,
+ .event_mask_ext = SPR_CHA_EVENT_MASK_EXT,
.num_shared_regs = 1,
.constraints = skx_uncore_chabox_constraints,
.ops = &spr_uncore_chabox_ops,
@@ -6162,7 +6165,55 @@ static struct intel_uncore_type spr_uncore_mdf = {
.name = "mdf",
};
-#define UNCORE_SPR_NUM_UNCORE_TYPES 12
+static void spr_uncore_mmio_offs8_init_box(struct intel_uncore_box *box)
+{
+ __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+ intel_generic_uncore_mmio_init_box(box);
+}
+
+static struct intel_uncore_ops spr_uncore_mmio_offs8_ops = {
+ .init_box = spr_uncore_mmio_offs8_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .disable_box = intel_generic_uncore_mmio_disable_box,
+ .enable_box = intel_generic_uncore_mmio_enable_box,
+ .disable_event = intel_generic_uncore_mmio_disable_event,
+ .enable_event = spr_uncore_mmio_enable_event,
+ .read_counter = uncore_mmio_read_counter,
+};
+
+#define SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT() \
+ SPR_UNCORE_COMMON_FORMAT(), \
+ .ops = &spr_uncore_mmio_offs8_ops
+
+static struct event_constraint spr_uncore_cxlcm_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x02, 0x0f),
+ UNCORE_EVENT_CONSTRAINT(0x05, 0x0f),
+ UNCORE_EVENT_CONSTRAINT(0x40, 0xf0),
+ UNCORE_EVENT_CONSTRAINT(0x41, 0xf0),
+ UNCORE_EVENT_CONSTRAINT(0x42, 0xf0),
+ UNCORE_EVENT_CONSTRAINT(0x43, 0xf0),
+ UNCORE_EVENT_CONSTRAINT(0x4b, 0xf0),
+ UNCORE_EVENT_CONSTRAINT(0x52, 0xf0),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type spr_uncore_cxlcm = {
+ SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT(),
+ .name = "cxlcm",
+ .constraints = spr_uncore_cxlcm_constraints,
+};
+
+static struct intel_uncore_type spr_uncore_cxldp = {
+ SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT(),
+ .name = "cxldp",
+};
+
+static struct intel_uncore_type spr_uncore_hbm = {
+ SPR_UNCORE_COMMON_FORMAT(),
+ .name = "hbm",
+};
+
+#define UNCORE_SPR_NUM_UNCORE_TYPES 15
#define UNCORE_SPR_CHA 0
#define UNCORE_SPR_IIO 1
#define UNCORE_SPR_IMC 6
@@ -6186,6 +6237,9 @@ static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = {
NULL,
NULL,
&spr_uncore_mdf,
+ &spr_uncore_cxlcm,
+ &spr_uncore_cxldp,
+ &spr_uncore_hbm,
};
/*
@@ -6198,6 +6252,24 @@ static u64 spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = {
0, 0x8000, 0x10000, 0x18000
};
+static void spr_extra_boxes_cleanup(struct intel_uncore_type *type)
+{
+ struct intel_uncore_discovery_unit *pos;
+ struct rb_node *node;
+
+ if (!type->boxes)
+ return;
+
+ while (!RB_EMPTY_ROOT(type->boxes)) {
+ node = rb_first(type->boxes);
+ pos = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ rb_erase(node, type->boxes);
+ kfree(pos);
+ }
+ kfree(type->boxes);
+ type->boxes = NULL;
+}
+
static struct intel_uncore_type spr_uncore_upi = {
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.event_mask_ext = SPR_RAW_EVENT_MASK_EXT,
@@ -6212,10 +6284,11 @@ static struct intel_uncore_type spr_uncore_upi = {
.num_counters = 4,
.num_boxes = SPR_UNCORE_UPI_NUM_BOXES,
.perf_ctr_bits = 48,
- .perf_ctr = ICX_UPI_PCI_PMON_CTR0,
- .event_ctl = ICX_UPI_PCI_PMON_CTL0,
+ .perf_ctr = ICX_UPI_PCI_PMON_CTR0 - ICX_UPI_PCI_PMON_BOX_CTL,
+ .event_ctl = ICX_UPI_PCI_PMON_CTL0 - ICX_UPI_PCI_PMON_BOX_CTL,
.box_ctl = ICX_UPI_PCI_PMON_BOX_CTL,
.pci_offsets = spr_upi_pci_offsets,
+ .cleanup_extra_boxes = spr_extra_boxes_cleanup,
};
static struct intel_uncore_type spr_uncore_m3upi = {
@@ -6225,11 +6298,12 @@ static struct intel_uncore_type spr_uncore_m3upi = {
.num_counters = 4,
.num_boxes = SPR_UNCORE_UPI_NUM_BOXES,
.perf_ctr_bits = 48,
- .perf_ctr = ICX_M3UPI_PCI_PMON_CTR0,
- .event_ctl = ICX_M3UPI_PCI_PMON_CTL0,
+ .perf_ctr = ICX_M3UPI_PCI_PMON_CTR0 - ICX_M3UPI_PCI_PMON_BOX_CTL,
+ .event_ctl = ICX_M3UPI_PCI_PMON_CTL0 - ICX_M3UPI_PCI_PMON_BOX_CTL,
.box_ctl = ICX_M3UPI_PCI_PMON_BOX_CTL,
.pci_offsets = spr_upi_pci_offsets,
.constraints = icx_uncore_m3upi_constraints,
+ .cleanup_extra_boxes = spr_extra_boxes_cleanup,
};
enum perf_uncore_spr_iio_freerunning_type_id {
@@ -6460,18 +6534,21 @@ uncore_find_type_by_id(struct intel_uncore_type **types, int type_id)
static int uncore_type_max_boxes(struct intel_uncore_type **types,
int type_id)
{
+ struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type;
- int i, max = 0;
+ struct rb_node *node;
+ int max = 0;
type = uncore_find_type_by_id(types, type_id);
if (!type)
return 0;
- for (i = 0; i < type->num_boxes; i++) {
- if (type->box_ids[i] > max)
- max = type->box_ids[i];
- }
+ for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+ unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ if (unit->id > max)
+ max = unit->id;
+ }
return max + 1;
}
@@ -6513,10 +6590,11 @@ void spr_uncore_cpu_init(void)
static void spr_update_device_location(int type_id)
{
+ struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type;
struct pci_dev *dev = NULL;
+ struct rb_root *root;
u32 device, devfn;
- u64 *ctls;
int die;
if (type_id == UNCORE_SPR_UPI) {
@@ -6530,27 +6608,35 @@ static void spr_update_device_location(int type_id)
} else
return;
- ctls = kcalloc(__uncore_max_dies, sizeof(u64), GFP_KERNEL);
- if (!ctls) {
+ root = kzalloc(sizeof(struct rb_root), GFP_KERNEL);
+ if (!root) {
type->num_boxes = 0;
return;
}
+ *root = RB_ROOT;
while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) {
- if (devfn != dev->devfn)
- continue;
die = uncore_device_to_die(dev);
if (die < 0)
continue;
- ctls[die] = pci_domain_nr(dev->bus) << UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET |
- dev->bus->number << UNCORE_DISCOVERY_PCI_BUS_OFFSET |
- devfn << UNCORE_DISCOVERY_PCI_DEVFN_OFFSET |
- type->box_ctl;
+ unit = kzalloc(sizeof(*unit), GFP_KERNEL);
+ if (!unit)
+ continue;
+ unit->die = die;
+ unit->id = PCI_SLOT(dev->devfn) - PCI_SLOT(devfn);
+ unit->addr = pci_domain_nr(dev->bus) << UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET |
+ dev->bus->number << UNCORE_DISCOVERY_PCI_BUS_OFFSET |
+ devfn << UNCORE_DISCOVERY_PCI_DEVFN_OFFSET |
+ type->box_ctl;
+
+ unit->pmu_idx = unit->id;
+
+ uncore_find_add_unit(unit, root, NULL);
}
- type->box_ctls = ctls;
+ type->boxes = root;
}
int spr_uncore_pci_init(void)
@@ -6623,7 +6709,7 @@ static struct intel_uncore_type gnr_uncore_b2cmi = {
};
static struct intel_uncore_type gnr_uncore_b2cxl = {
- SPR_UNCORE_MMIO_COMMON_FORMAT(),
+ SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT(),
.name = "b2cxl",
};
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 72b022a1e16c..ac1182141bf6 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -476,6 +476,14 @@ struct cpu_hw_events {
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID)
+#define INTEL_HYBRID_LDLAT_CONSTRAINT(c, n) \
+ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_LD_HSW)
+
+#define INTEL_HYBRID_STLAT_CONSTRAINT(c, n) \
+ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_ST_HSW)
+
/* Event constraint, but match on all event flags too. */
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
@@ -655,8 +663,10 @@ enum {
x86_lbr_exclusive_max,
};
-#define PERF_PEBS_DATA_SOURCE_MAX 0x10
+#define PERF_PEBS_DATA_SOURCE_MAX 0x100
#define PERF_PEBS_DATA_SOURCE_MASK (PERF_PEBS_DATA_SOURCE_MAX - 1)
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX 0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK (PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
enum hybrid_cpu_type {
HYBRID_INTEL_NONE,
@@ -684,9 +694,16 @@ struct x86_hybrid_pmu {
cpumask_t supported_cpus;
union perf_capabilities intel_cap;
u64 intel_ctrl;
- int max_pebs_events;
- int num_counters;
- int num_counters_fixed;
+ u64 pebs_events_mask;
+ u64 config_mask;
+ union {
+ u64 cntr_mask64;
+ unsigned long cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
+ union {
+ u64 fixed_cntr_mask64;
+ unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
struct event_constraint unconstrained;
u64 hw_cache_event_ids
@@ -770,12 +787,20 @@ struct x86_pmu {
int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
unsigned eventsel;
unsigned perfctr;
+ unsigned fixedctr;
int (*addr_offset)(int index, bool eventsel);
int (*rdpmc_index)(int index);
u64 (*event_map)(int);
int max_events;
- int num_counters;
- int num_counters_fixed;
+ u64 config_mask;
+ union {
+ u64 cntr_mask64;
+ unsigned long cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
+ union {
+ u64 fixed_cntr_mask64;
+ unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
int cntval_bits;
u64 cntval_mask;
union {
@@ -852,7 +877,7 @@ struct x86_pmu {
pebs_ept :1;
int pebs_record_size;
int pebs_buffer_size;
- int max_pebs_events;
+ u64 pebs_events_mask;
void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
@@ -1120,13 +1145,19 @@ static inline unsigned int x86_pmu_event_addr(int index)
x86_pmu.addr_offset(index, false) : index);
}
+static inline unsigned int x86_pmu_fixed_ctr_addr(int index)
+{
+ return x86_pmu.fixedctr + (x86_pmu.addr_offset ?
+ x86_pmu.addr_offset(index, false) : index);
+}
+
static inline int x86_pmu_rdpmc_index(int index)
{
return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
}
-bool check_hw_exists(struct pmu *pmu, int num_counters,
- int num_counters_fixed);
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+ unsigned long *fixed_cntr_mask);
int x86_add_exclusive(unsigned int what);
@@ -1197,8 +1228,32 @@ void x86_pmu_enable_event(struct perf_event *event);
int x86_pmu_handle_irq(struct pt_regs *regs);
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
- u64 intel_ctrl);
+void x86_pmu_show_pmu_cap(struct pmu *pmu);
+
+static inline int x86_pmu_num_counters(struct pmu *pmu)
+{
+ return hweight64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters(struct pmu *pmu)
+{
+ return fls64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_num_counters_fixed(struct pmu *pmu)
+{
+ return hweight64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters_fixed(struct pmu *pmu)
+{
+ return fls64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline u64 x86_pmu_get_event_config(struct perf_event *event)
+{
+ return event->attr.config & hybrid(event->pmu, config_mask);
+}
extern struct event_constraint emptyconstraint;
@@ -1517,9 +1572,11 @@ void intel_pmu_disable_bts(void);
int intel_pmu_drain_bts_buffer(void);
-u64 adl_latency_data_small(struct perf_event *event, u64 status);
+u64 grt_latency_data(struct perf_event *event, u64 status);
-u64 mtl_latency_data_small(struct perf_event *event, u64 status);
+u64 cmt_latency_data(struct perf_event *event, u64 status);
+
+u64 lnl_latency_data(struct perf_event *event, u64 status);
extern struct event_constraint intel_core2_pebs_event_constraints[];
@@ -1551,6 +1608,8 @@ extern struct event_constraint intel_icl_pebs_event_constraints[];
extern struct event_constraint intel_glc_pebs_event_constraints[];
+extern struct event_constraint intel_lnc_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
@@ -1640,6 +1699,8 @@ void intel_pmu_pebs_data_source_mtl(void);
void intel_pmu_pebs_data_source_cmt(void);
+void intel_pmu_pebs_data_source_lnl(void);
+
int intel_pmu_setup_lbr_filter(struct perf_event *event);
void intel_pt_interrupt(void);
@@ -1661,6 +1722,17 @@ static inline int is_ht_workaround_enabled(void)
return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
}
+static inline u64 intel_pmu_pebs_mask(u64 cntr_mask)
+{
+ return MAX_PEBS_EVENTS_MASK & cntr_mask;
+}
+
+static inline int intel_pmu_max_num_pebs(struct pmu *pmu)
+{
+ static_assert(MAX_PEBS_EVENTS == 32);
+ return fls((u32)hybrid(pmu, pebs_events_mask));
+}
+
#else /* CONFIG_CPU_SUP_INTEL */
static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 0c5e7a7c43ac..b985ca79cf97 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -765,51 +765,51 @@ static struct rapl_model model_amd_hygon = {
};
static const struct x86_cpu_id rapl_model_match[] __initconst = {
- X86_MATCH_FEATURE(X86_FEATURE_RAPL, &model_amd_hygon),
- X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &model_snb),
- X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &model_snbep),
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &model_snb),
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &model_snbep),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &model_hsx),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &model_hsx),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &model_hsx),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &model_knl),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &model_knl),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &model_hsx),
- X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &model_hsw),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &model_hsx),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx),
- X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr),
- X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE_H, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE, &model_skl),
- X86_MATCH_INTEL_FAM6_MODEL(LUNARLAKE_M, &model_skl),
+ X86_MATCH_FEATURE(X86_FEATURE_RAPL, &model_amd_hygon),
+ X86_MATCH_VFM(INTEL_SANDYBRIDGE, &model_snb),
+ X86_MATCH_VFM(INTEL_SANDYBRIDGE_X, &model_snbep),
+ X86_MATCH_VFM(INTEL_IVYBRIDGE, &model_snb),
+ X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &model_snbep),
+ X86_MATCH_VFM(INTEL_HASWELL, &model_hsw),
+ X86_MATCH_VFM(INTEL_HASWELL_X, &model_hsx),
+ X86_MATCH_VFM(INTEL_HASWELL_L, &model_hsw),
+ X86_MATCH_VFM(INTEL_HASWELL_G, &model_hsw),
+ X86_MATCH_VFM(INTEL_BROADWELL, &model_hsw),
+ X86_MATCH_VFM(INTEL_BROADWELL_G, &model_hsw),
+ X86_MATCH_VFM(INTEL_BROADWELL_X, &model_hsx),
+ X86_MATCH_VFM(INTEL_BROADWELL_D, &model_hsx),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &model_knl),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &model_knl),
+ X86_MATCH_VFM(INTEL_SKYLAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_SKYLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_SKYLAKE_X, &model_hsx),
+ X86_MATCH_VFM(INTEL_KABYLAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_KABYLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_CANNONLAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_ATOM_GOLDMONT, &model_hsw),
+ X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D, &model_hsw),
+ X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS, &model_hsw),
+ X86_MATCH_VFM(INTEL_ICELAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_ICELAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, &model_hsx),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, &model_hsx),
+ X86_MATCH_VFM(INTEL_COMETLAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_COMETLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_TIGERLAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_TIGERLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_ALDERLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &model_skl),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &model_spr),
+ X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &model_spr),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &model_skl),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &model_skl),
+ X86_MATCH_VFM(INTEL_METEORLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_METEORLAKE_L, &model_skl),
+ X86_MATCH_VFM(INTEL_ARROWLAKE_H, &model_skl),
+ X86_MATCH_VFM(INTEL_ARROWLAKE, &model_skl),
+ X86_MATCH_VFM(INTEL_LUNARLAKE_M, &model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 3e9acdaeed1e..2fd9b0cf9a5e 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -530,13 +530,13 @@ __init int zhaoxin_pmu_init(void)
pr_info("Version check pass!\n");
x86_pmu.version = version;
- x86_pmu.num_counters = eax.split.num_counters;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(eax.split.num_counters - 1, 0);
x86_pmu.cntval_bits = eax.split.bit_width;
x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
x86_pmu.events_maskl = ebx.full;
x86_pmu.events_mask_len = eax.split.mask_length;
- x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
+ x86_pmu.fixed_cntr_mask64 = GENMASK_ULL(edx.split.num_counters_fixed - 1, 0);
x86_add_quirk(zhaoxin_arch_events_quirk);
switch (boot_cpu_data.x86) {
@@ -604,13 +604,13 @@ __init int zhaoxin_pmu_init(void)
return -ENODEV;
}
- x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
- x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+ x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+ x86_pmu.intel_ctrl |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
- c->weight += x86_pmu.num_counters;
+ c->idxmsk64 |= x86_pmu.cntr_mask64;
+ c->weight += x86_pmu_num_counters(NULL);
}
}
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 768d73de0d09..b4a851d27c7c 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -523,9 +523,9 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
* transition is complete, hv_vtom_set_host_visibility() marks the pages
* as "present" again.
*/
-static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+static int hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
{
- return !set_memory_np(kbuffer, pagecount);
+ return set_memory_np(kbuffer, pagecount);
}
/*
@@ -536,20 +536,19 @@ static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc
* with host. This function works as wrap of hv_mark_gpa_visibility()
* with memory base and size.
*/
-static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc)
+static int hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc)
{
enum hv_mem_host_visibility visibility = enc ?
VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
u64 *pfn_array;
phys_addr_t paddr;
+ int i, pfn, err;
void *vaddr;
int ret = 0;
- bool result = true;
- int i, pfn;
pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
if (!pfn_array) {
- result = false;
+ ret = -ENOMEM;
goto err_set_memory_p;
}
@@ -568,10 +567,8 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
ret = hv_mark_gpa_visibility(pfn, pfn_array,
visibility);
- if (ret) {
- result = false;
+ if (ret)
goto err_free_pfn_array;
- }
pfn = 0;
}
}
@@ -586,10 +583,11 @@ err_set_memory_p:
* order to avoid leaving the memory range in a "broken" state. Setting
* the PRESENT bits shouldn't fail, but return an error if it does.
*/
- if (set_memory_p(kbuffer, pagecount))
- result = false;
+ err = set_memory_p(kbuffer, pagecount);
+ if (err && !ret)
+ ret = err;
- return result;
+ return ret;
}
static bool hv_vtom_tlb_flush_required(bool private)
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 5af926c050f0..21bc53f5ed0c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -78,6 +78,13 @@ static inline bool acpi_skip_set_wakeup_address(void)
#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address
+union acpi_subtable_headers;
+
+int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
+ const unsigned long end);
+
+void asm_acpi_mp_play_dead(u64 reset_vector, u64 pgd_pa);
+
/*
* Check if the CPU can handle C2 and deeper
*/
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index ba99ef75f56c..ca9ae606aab9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -156,102 +156,50 @@ static inline int alternatives_text_reserved(void *start, void *end)
#define ALT_CALL_INSTR "call BUG_func"
-#define b_replacement(num) "664"#num
-#define e_replacement(num) "665"#num
+#define alt_slen "772b-771b"
+#define alt_total_slen "773b-771b"
+#define alt_rlen "775f-774f"
-#define alt_end_marker "663"
-#define alt_slen "662b-661b"
-#define alt_total_slen alt_end_marker"b-661b"
-#define alt_rlen(num) e_replacement(num)"f-"b_replacement(num)"f"
-
-#define OLDINSTR(oldinstr, num) \
- "# ALT: oldnstr\n" \
- "661:\n\t" oldinstr "\n662:\n" \
+#define OLDINSTR(oldinstr) \
+ "# ALT: oldinstr\n" \
+ "771:\n\t" oldinstr "\n772:\n" \
"# ALT: padding\n" \
- ".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * " \
- "((" alt_rlen(num) ")-(" alt_slen ")),0x90\n" \
- alt_end_marker ":\n"
-
-/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))"
-
-/*
- * Pad the second replacement alternative with additional NOPs if it is
- * additionally longer than the first replacement alternative.
- */
-#define OLDINSTR_2(oldinstr, num1, num2) \
- "# ALT: oldinstr2\n" \
- "661:\n\t" oldinstr "\n662:\n" \
- "# ALT: padding2\n" \
- ".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * " \
- "(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n" \
- alt_end_marker ":\n"
-
-#define OLDINSTR_3(oldinsn, n1, n2, n3) \
- "# ALT: oldinstr3\n" \
- "661:\n\t" oldinsn "\n662:\n" \
- "# ALT: padding3\n" \
- ".skip -((" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \
- " - (" alt_slen ")) > 0) * " \
- "(" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \
- " - (" alt_slen ")), 0x90\n" \
- alt_end_marker ":\n"
-
-#define ALTINSTR_ENTRY(ft_flags, num) \
- " .long 661b - .\n" /* label */ \
- " .long " b_replacement(num)"f - .\n" /* new instruction */ \
+ ".skip -(((" alt_rlen ")-(" alt_slen ")) > 0) * " \
+ "((" alt_rlen ")-(" alt_slen ")),0x90\n" \
+ "773:\n"
+
+#define ALTINSTR_ENTRY(ft_flags) \
+ ".pushsection .altinstructions,\"a\"\n" \
+ " .long 771b - .\n" /* label */ \
+ " .long 774f - .\n" /* new instruction */ \
" .4byte " __stringify(ft_flags) "\n" /* feature + flags */ \
" .byte " alt_total_slen "\n" /* source len */ \
- " .byte " alt_rlen(num) "\n" /* replacement len */
+ " .byte " alt_rlen "\n" /* replacement len */ \
+ ".popsection\n"
-#define ALTINSTR_REPLACEMENT(newinstr, num) /* replacement */ \
- "# ALT: replacement " #num "\n" \
- b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n"
+#define ALTINSTR_REPLACEMENT(newinstr) /* replacement */ \
+ ".pushsection .altinstr_replacement, \"ax\"\n" \
+ "# ALT: replacement\n" \
+ "774:\n\t" newinstr "\n775:\n" \
+ ".popsection\n"
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, ft_flags) \
- OLDINSTR(oldinstr, 1) \
- ".pushsection .altinstructions,\"a\"\n" \
- ALTINSTR_ENTRY(ft_flags, 1) \
- ".popsection\n" \
- ".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinstr, 1) \
- ".popsection\n"
+ OLDINSTR(oldinstr) \
+ ALTINSTR_ENTRY(ft_flags) \
+ ALTINSTR_REPLACEMENT(newinstr)
#define ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \
- OLDINSTR_2(oldinstr, 1, 2) \
- ".pushsection .altinstructions,\"a\"\n" \
- ALTINSTR_ENTRY(ft_flags1, 1) \
- ALTINSTR_ENTRY(ft_flags2, 2) \
- ".popsection\n" \
- ".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinstr1, 1) \
- ALTINSTR_REPLACEMENT(newinstr2, 2) \
- ".popsection\n"
+ ALTERNATIVE(ALTERNATIVE(oldinstr, newinstr1, ft_flags1), newinstr2, ft_flags2)
/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
#define ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) \
- ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \
- newinstr_yes, ft_flags)
-
-#define ALTERNATIVE_3(oldinsn, newinsn1, ft_flags1, newinsn2, ft_flags2, \
- newinsn3, ft_flags3) \
- OLDINSTR_3(oldinsn, 1, 2, 3) \
- ".pushsection .altinstructions,\"a\"\n" \
- ALTINSTR_ENTRY(ft_flags1, 1) \
- ALTINSTR_ENTRY(ft_flags2, 2) \
- ALTINSTR_ENTRY(ft_flags3, 3) \
- ".popsection\n" \
- ".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinsn1, 1) \
- ALTINSTR_REPLACEMENT(newinsn2, 2) \
- ALTINSTR_REPLACEMENT(newinsn3, 3) \
- ".popsection\n"
+ ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, newinstr_yes, ft_flags)
+
+#define ALTERNATIVE_3(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, \
+ newinstr3, ft_flags3) \
+ ALTERNATIVE(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2), \
+ newinstr3, ft_flags3)
/*
* Alternative instructions for different CPU types or capabilities.
@@ -266,14 +214,11 @@ static inline int alternatives_text_reserved(void *start, void *end)
* without volatile and memory clobber.
*/
#define alternative(oldinstr, newinstr, ft_flags) \
- asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory")
+ asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory")
#define alternative_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \
asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) ::: "memory")
-#define alternative_ternary(oldinstr, ft_flags, newinstr_yes, newinstr_no) \
- asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) ::: "memory")
-
/*
* Alternative inline assembly with input.
*
@@ -283,18 +228,28 @@ static inline int alternatives_text_reserved(void *start, void *end)
* Leaving an unused argument 0 to keep API compatibility.
*/
#define alternative_input(oldinstr, newinstr, ft_flags, input...) \
- asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \
+ asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) \
: : "i" (0), ## input)
/* Like alternative_input, but with a single output argument */
#define alternative_io(oldinstr, newinstr, ft_flags, output, input...) \
- asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \
+ asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) \
: output : "i" (0), ## input)
-/* Like alternative_io, but for replacing a direct call with another one. */
-#define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \
- asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \
- : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+/*
+ * Like alternative_io, but for replacing a direct call with another one.
+ *
+ * Use the %c operand modifier which is the generic way to print a bare
+ * constant expression with all syntax-specific punctuation omitted. %P
+ * is the x86-specific variant which can handle constants too, for
+ * historical reasons, but it should be used primarily for PIC
+ * references: i.e., if used for a function, it would add the PLT
+ * suffix.
+ */
+#define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \
+ asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \
+ : ALT_OUTPUT_SP(output) \
+ : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
/*
* Like alternative_call, but there are two features and respective functions.
@@ -302,12 +257,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
* Otherwise, if CPU has feature1, function1 is used.
* Otherwise, old function is used.
*/
-#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \
- output, input...) \
- asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \
- "call %c[new2]", ft_flags2) \
- : output, ASM_CALL_CONSTRAINT \
- : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
+#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \
+ output, input...) \
+ asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \
+ "call %c[new2]", ft_flags2) \
+ : ALT_OUTPUT_SP(output) \
+ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
[new2] "i" (newfunc2), ## input)
/*
@@ -322,6 +277,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
*/
#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+#define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__
+
/* Macro for creating assembler functions avoiding any C magic. */
#define DEFINE_ASM_FUNC(func, instr, sec) \
asm (".pushsection " #sec ", \"ax\"\n" \
@@ -388,22 +345,23 @@ void nop_func(void);
* @newinstr. ".skip" directive takes care of proper instruction padding
* in case @newinstr is longer than @oldinstr.
*/
-.macro ALTERNATIVE oldinstr, newinstr, ft_flags
-140:
- \oldinstr
-141:
- .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
-142:
-
- .pushsection .altinstructions,"a"
- altinstr_entry 140b,143f,\ft_flags,142b-140b,144f-143f
- .popsection
+#define __ALTERNATIVE(oldinst, newinst, flag) \
+740: \
+ oldinst ; \
+741: \
+ .skip -(((744f-743f)-(741b-740b)) > 0) * ((744f-743f)-(741b-740b)),0x90 ;\
+742: \
+ .pushsection .altinstructions,"a" ; \
+ altinstr_entry 740b,743f,flag,742b-740b,744f-743f ; \
+ .popsection ; \
+ .pushsection .altinstr_replacement,"ax" ; \
+743: \
+ newinst ; \
+744: \
+ .popsection ;
- .pushsection .altinstr_replacement,"ax"
-143:
- \newinstr
-144:
- .popsection
+.macro ALTERNATIVE oldinstr, newinstr, ft_flags
+ __ALTERNATIVE(\oldinstr, \newinstr, \ft_flags)
.endm
#define old_len 141b-140b
@@ -412,65 +370,18 @@ void nop_func(void);
#define new_len3 146f-145f
/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_2(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
-#define alt_max_3(a, b, c) (alt_max_2(alt_max_2(a, b), c))
-
-
-/*
* Same as ALTERNATIVE macro above but for two alternatives. If CPU
* has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
* @feature2, it replaces @oldinstr with @feature2.
*/
.macro ALTERNATIVE_2 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2
-140:
- \oldinstr
-141:
- .skip -((alt_max_2(new_len1, new_len2) - (old_len)) > 0) * \
- (alt_max_2(new_len1, new_len2) - (old_len)),0x90
-142:
-
- .pushsection .altinstructions,"a"
- altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f
- altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f
- .popsection
-
- .pushsection .altinstr_replacement,"ax"
-143:
- \newinstr1
-144:
- \newinstr2
-145:
- .popsection
+ __ALTERNATIVE(__ALTERNATIVE(\oldinstr, \newinstr1, \ft_flags1),
+ \newinstr2, \ft_flags2)
.endm
.macro ALTERNATIVE_3 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, newinstr3, ft_flags3
-140:
- \oldinstr
-141:
- .skip -((alt_max_3(new_len1, new_len2, new_len3) - (old_len)) > 0) * \
- (alt_max_3(new_len1, new_len2, new_len3) - (old_len)),0x90
-142:
-
- .pushsection .altinstructions,"a"
- altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f
- altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f
- altinstr_entry 140b,145f,\ft_flags3,142b-140b,146f-145f
- .popsection
-
- .pushsection .altinstr_replacement,"ax"
-143:
- \newinstr1
-144:
- \newinstr2
-145:
- \newinstr3
-146:
- .popsection
+ __ALTERNATIVE(ALTERNATIVE_2(\oldinstr, \newinstr1, \ft_flags1, \newinstr2, \ft_flags2),
+ \newinstr3, \ft_flags3)
.endm
/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 5c37944c8a5e..6f3b6aef47ba 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -21,8 +21,8 @@ extern int amd_numa_init(void);
extern int amd_get_subcaches(int);
extern int amd_set_subcaches(int, unsigned long);
-extern int amd_smn_read(u16 node, u32 address, u32 *value);
-extern int amd_smn_write(u16 node, u32 address, u32 value);
+int __must_check amd_smn_read(u16 node, u32 address, u32 *value);
+int __must_check amd_smn_write(u16 node, u32 address, u32 value);
struct amd_l3_cache {
unsigned indices;
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 7cd752557905..31d19c815f99 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -93,7 +93,7 @@
*
*/
enum cfi_mode {
- CFI_DEFAULT, /* FineIBT if hardware has IBT, otherwise kCFI */
+ CFI_AUTO, /* 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 */
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index b6325ee30871..3831f612e89c 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -280,10 +280,10 @@ struct x86_cpu_desc {
u32 x86_microcode_rev;
};
-#define INTEL_CPU_DESC(model, stepping, revision) { \
- .x86_family = 6, \
- .x86_vendor = X86_VENDOR_INTEL, \
- .x86_model = (model), \
+#define INTEL_CPU_DESC(vfm, stepping, revision) { \
+ .x86_family = VFM_FAMILY(vfm), \
+ .x86_vendor = VFM_VENDOR(vfm), \
+ .x86_model = VFM_MODEL(vfm), \
.x86_stepping = (stepping), \
.x86_microcode_rev = (revision), \
}
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 3c7434329661..dd4682857c12 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -18,170 +18,170 @@
/*
* Note: If the comment begins with a quoted string, that string is used
- * in /proc/cpuinfo instead of the macro name. If the string is "",
- * this feature bit is not displayed in /proc/cpuinfo at all.
+ * in /proc/cpuinfo instead of the macro name. Otherwise, this feature
+ * bit is not displayed in /proc/cpuinfo at all.
*
* When adding new features here that depend on other features,
* please update the table in kernel/cpu/cpuid-deps.c as well.
*/
/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */
-#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_FPU ( 0*32+ 0) /* "fpu" Onboard FPU */
+#define X86_FEATURE_VME ( 0*32+ 1) /* "vme" Virtual Mode Extensions */
+#define X86_FEATURE_DE ( 0*32+ 2) /* "de" Debugging Extensions */
+#define X86_FEATURE_PSE ( 0*32+ 3) /* "pse" Page Size Extensions */
+#define X86_FEATURE_TSC ( 0*32+ 4) /* "tsc" Time Stamp Counter */
+#define X86_FEATURE_MSR ( 0*32+ 5) /* "msr" Model-Specific Registers */
+#define X86_FEATURE_PAE ( 0*32+ 6) /* "pae" Physical Address Extensions */
+#define X86_FEATURE_MCE ( 0*32+ 7) /* "mce" Machine Check Exception */
+#define X86_FEATURE_CX8 ( 0*32+ 8) /* "cx8" CMPXCHG8 instruction */
+#define X86_FEATURE_APIC ( 0*32+ 9) /* "apic" Onboard APIC */
+#define X86_FEATURE_SEP ( 0*32+11) /* "sep" SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR ( 0*32+12) /* "mtrr" Memory Type Range Registers */
+#define X86_FEATURE_PGE ( 0*32+13) /* "pge" Page Global Enable */
+#define X86_FEATURE_MCA ( 0*32+14) /* "mca" Machine Check Architecture */
+#define X86_FEATURE_CMOV ( 0*32+15) /* "cmov" CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT ( 0*32+16) /* "pat" Page Attribute Table */
+#define X86_FEATURE_PSE36 ( 0*32+17) /* "pse36" 36-bit PSEs */
+#define X86_FEATURE_PN ( 0*32+18) /* "pn" Processor serial number */
+#define X86_FEATURE_CLFLUSH ( 0*32+19) /* "clflush" CLFLUSH instruction */
#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_ACPI ( 0*32+22) /* "acpi" ACPI via MSR */
+#define X86_FEATURE_MMX ( 0*32+23) /* "mmx" Multimedia Extensions */
+#define X86_FEATURE_FXSR ( 0*32+24) /* "fxsr" FXSAVE/FXRSTOR, CR4.OSFXSR */
#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */
#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */
#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_HT ( 0*32+28) /* "ht" Hyper-Threading */
#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */
+#define X86_FEATURE_IA64 ( 0*32+30) /* "ia64" IA-64 processor */
+#define X86_FEATURE_PBE ( 0*32+31) /* "pbe" Pending Break Enable */
/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */
-#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_SYSCALL ( 1*32+11) /* "syscall" SYSCALL/SYSRET */
+#define X86_FEATURE_MP ( 1*32+19) /* "mp" MP Capable */
+#define X86_FEATURE_NX ( 1*32+20) /* "nx" Execute Disable */
+#define X86_FEATURE_MMXEXT ( 1*32+22) /* "mmxext" AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* "fxsr_opt" FXSAVE/FXRSTOR optimizations */
#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */
-#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */
-#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */
+#define X86_FEATURE_RDTSCP ( 1*32+27) /* "rdtscp" RDTSCP */
+#define X86_FEATURE_LM ( 1*32+29) /* "lm" Long Mode (x86-64, 64-bit support) */
+#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* "3dnowext" AMD 3DNow extensions */
+#define X86_FEATURE_3DNOW ( 1*32+31) /* "3dnow" 3DNow */
/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* "recovery" CPU in recovery mode */
+#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* "longrun" Longrun power control */
+#define X86_FEATURE_LRTI ( 2*32+ 3) /* "lrti" LongRun table interface */
/* Other features, Linux-defined mapping, word 3 */
/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */
-#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) */
-#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */
-#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 */
-#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */
-#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */
-#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
-#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
-#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */
-#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */
-#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
-#define X86_FEATURE_RAPL ( 3*32+29) /* AMD/Hygon RAPL interface */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
+#define X86_FEATURE_CXMMX ( 3*32+ 0) /* "cxmmx" Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* "k6_mtrr" AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* "cyrix_arr" Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
+#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */
+#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) /* "constant_tsc" TSC ticks at a constant rate */
+#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */
+#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* "arch_perfmon" Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */
+#define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */
+#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* syscall in IA32 userspace */
+#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* sysenter in IA32 userspace */
+#define X86_FEATURE_REP_GOOD ( 3*32+16) /* "rep_good" REP microcode works well */
+#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */
+#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */
+#define X86_FEATURE_ACC_POWER ( 3*32+19) /* "acc_power" AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL ( 3*32+20) /* "nopl" The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS ( 3*32+21) /* Always-present feature */
+#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* "xtopology" CPU topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* "tsc_reliable" TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* "nonstop_tsc" TSC does not stop in C states */
+#define X86_FEATURE_CPUID ( 3*32+25) /* "cpuid" CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* "extd_apicid" Extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM ( 3*32+27) /* "amd_dcm" AMD multi-node processor */
+#define X86_FEATURE_APERFMPERF ( 3*32+28) /* "aperfmperf" P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+#define X86_FEATURE_RAPL ( 3*32+29) /* "rapl" AMD/Hygon RAPL interface */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* "nonstop_tsc_s3" TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* "tsc_known_freq" TSC has known frequency */
/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* "pclmulqdq" PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64 ( 4*32+ 2) /* "dtes64" 64-bit Debug Store */
#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */
#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */
-#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */
-#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID ( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */
-#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */
-#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_VMX ( 4*32+ 5) /* "vmx" Hardware virtualization */
+#define X86_FEATURE_SMX ( 4*32+ 6) /* "smx" Safer Mode eXtensions */
+#define X86_FEATURE_EST ( 4*32+ 7) /* "est" Enhanced SpeedStep */
+#define X86_FEATURE_TM2 ( 4*32+ 8) /* "tm2" Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* "ssse3" Supplemental SSE-3 */
+#define X86_FEATURE_CID ( 4*32+10) /* "cid" Context ID */
+#define X86_FEATURE_SDBG ( 4*32+11) /* "sdbg" Silicon Debug */
+#define X86_FEATURE_FMA ( 4*32+12) /* "fma" Fused multiply-add */
+#define X86_FEATURE_CX16 ( 4*32+13) /* "cx16" CMPXCHG16B instruction */
+#define X86_FEATURE_XTPR ( 4*32+14) /* "xtpr" Send Task Priority Messages */
+#define X86_FEATURE_PDCM ( 4*32+15) /* "pdcm" Perf/Debug Capabilities MSR */
+#define X86_FEATURE_PCID ( 4*32+17) /* "pcid" Process Context Identifiers */
+#define X86_FEATURE_DCA ( 4*32+18) /* "dca" Direct Cache Access */
#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */
#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC ( 4*32+21) /* X2APIC */
-#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* TSC deadline timer */
-#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */
-#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */
-#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */
-#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */
+#define X86_FEATURE_X2APIC ( 4*32+21) /* "x2apic" X2APIC */
+#define X86_FEATURE_MOVBE ( 4*32+22) /* "movbe" MOVBE instruction */
+#define X86_FEATURE_POPCNT ( 4*32+23) /* "popcnt" POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* "tsc_deadline_timer" TSC deadline timer */
+#define X86_FEATURE_AES ( 4*32+25) /* "aes" AES instructions */
+#define X86_FEATURE_XSAVE ( 4*32+26) /* "xsave" XSAVE/XRSTOR/XSETBV/XGETBV instructions */
+#define X86_FEATURE_OSXSAVE ( 4*32+27) /* XSAVE instruction enabled in the OS */
+#define X86_FEATURE_AVX ( 4*32+28) /* "avx" Advanced Vector Extensions */
+#define X86_FEATURE_F16C ( 4*32+29) /* "f16c" 16-bit FP conversions */
+#define X86_FEATURE_RDRAND ( 4*32+30) /* "rdrand" RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* "hypervisor" Running on a hypervisor */
/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */
#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */
#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */
+#define X86_FEATURE_ACE2 ( 5*32+ 8) /* "ace2" Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* "ace2_en" ACE v2 enabled */
+#define X86_FEATURE_PHE ( 5*32+10) /* "phe" PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN ( 5*32+11) /* "phe_en" PHE enabled */
+#define X86_FEATURE_PMM ( 5*32+12) /* "pmm" PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN ( 5*32+13) /* "pmm_en" PMM enabled */
/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */
-#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */
-#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */
-#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */
-#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */
-#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
+#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* "lahf_lm" LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* "cmp_legacy" If yes HyperThreading not valid */
+#define X86_FEATURE_SVM ( 6*32+ 2) /* "svm" Secure Virtual Machine */
+#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* "extapic" Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* "cr8_legacy" CR8 in 32-bit mode */
+#define X86_FEATURE_ABM ( 6*32+ 5) /* "abm" Advanced bit manipulation */
+#define X86_FEATURE_SSE4A ( 6*32+ 6) /* "sse4a" SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* "misalignsse" Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* "3dnowprefetch" 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW ( 6*32+ 9) /* "osvw" OS Visible Workaround */
+#define X86_FEATURE_IBS ( 6*32+10) /* "ibs" Instruction Based Sampling */
+#define X86_FEATURE_XOP ( 6*32+11) /* "xop" Extended AVX instructions */
+#define X86_FEATURE_SKINIT ( 6*32+12) /* "skinit" SKINIT/STGI instructions */
+#define X86_FEATURE_WDT ( 6*32+13) /* "wdt" Watchdog timer */
+#define X86_FEATURE_LWP ( 6*32+15) /* "lwp" Light Weight Profiling */
+#define X86_FEATURE_FMA4 ( 6*32+16) /* "fma4" 4 operands MAC instructions */
+#define X86_FEATURE_TCE ( 6*32+17) /* "tce" Translation Cache Extension */
+#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* "nodeid_msr" NodeId MSR */
+#define X86_FEATURE_TBM ( 6*32+21) /* "tbm" Trailing Bit Manipulations */
+#define X86_FEATURE_TOPOEXT ( 6*32+22) /* "topoext" Topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* "perfctr_core" Core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* "perfctr_nb" NB performance counter extensions */
+#define X86_FEATURE_BPEXT ( 6*32+26) /* "bpext" Data breakpoint extension */
+#define X86_FEATURE_PTSC ( 6*32+27) /* "ptsc" Performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* "perfctr_llc" Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX ( 6*32+29) /* "mwaitx" MWAIT extension (MONITORX/MWAITX instructions) */
/*
* Auxiliary flags: Linux defined - For features scattered in various
@@ -189,93 +189,93 @@
*
* Reuse free bits when adding new feature flags!
*/
-#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */
-#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
-#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#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) */
-#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
-#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */
-#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */
-#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
-#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
-#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */
-#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
-#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
-#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */
-#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
-#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
-#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */
-#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */
-#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) /* "" 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 */
+#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* "ring3mwait" Ring 3 MONITOR/MWAIT instructions */
+#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* "cpuid_fault" Intel CPUID faulting */
+#define X86_FEATURE_CPB ( 7*32+ 2) /* "cpb" AMD Core Performance Boost */
+#define X86_FEATURE_EPB ( 7*32+ 3) /* "epb" IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* "cat_l3" Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* "cat_l2" Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* "cdp_l3" Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* "tdx_host_platform" Platform supports being a TDX host */
+#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* "hw_pstate" AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* "proc_feedback" AMD ProcFeedbackInterface */
+#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* Use compacted XSTATE (XSAVES or XSAVEC) */
+#define X86_FEATURE_PTI ( 7*32+11) /* "pti" Kernel Page Table Isolation enabled */
+#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* Set/clear IBRS on kernel entry/exit */
+#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* Fill RSB on VM-Exit */
+#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* "intel_ppin" Intel Processor Inventory Number */
+#define X86_FEATURE_CDP_L2 ( 7*32+15) /* "cdp_l2" Code and Data Prioritization L2 */
+#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD ( 7*32+17) /* "ssbd" Speculative Store Bypass Disable */
+#define X86_FEATURE_MBA ( 7*32+18) /* "mba" Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */
+#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */
+#define X86_FEATURE_USE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */
+#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) /* "ibrs_enhanced" Enhanced IBRS */
+#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* MSR IA32_FEAT_CTL configured */
/* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */
-#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */
+#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* "tpr_shadow" Intel TPR Shadow */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */
+#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */
+#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */
-#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */
-#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */
-#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
-#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
-#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
-#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */
-#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */
-#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */
+#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */
+#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */
+#define X86_FEATURE_EPT_AD ( 8*32+17) /* "ept_ad" Intel Extended Page Table access-dirty bit */
+#define X86_FEATURE_VMCALL ( 8*32+18) /* Hypervisor supports the VMCALL instruction */
+#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* PV vcpu_is_preempted function */
+#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* "tdx_guest" Intel Trust Domain Extensions Guest */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
-#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
-#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */
-#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */
-#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
-#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
-#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
-#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
-#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
-#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */
-#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
-#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
-#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
-#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* "fsgsbase" RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
+#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* "tsc_adjust" TSC adjustment MSR 0x3B */
+#define X86_FEATURE_SGX ( 9*32+ 2) /* "sgx" Software Guard Extensions */
+#define X86_FEATURE_BMI1 ( 9*32+ 3) /* "bmi1" 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE ( 9*32+ 4) /* "hle" Hardware Lock Elision */
+#define X86_FEATURE_AVX2 ( 9*32+ 5) /* "avx2" AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* FPU data pointer updated only on x87 exceptions */
+#define X86_FEATURE_SMEP ( 9*32+ 7) /* "smep" Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2 ( 9*32+ 8) /* "bmi2" 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS ( 9*32+ 9) /* "erms" Enhanced REP MOVSB/STOSB instructions */
+#define X86_FEATURE_INVPCID ( 9*32+10) /* "invpcid" Invalidate Processor Context ID */
+#define X86_FEATURE_RTM ( 9*32+11) /* "rtm" Restricted Transactional Memory */
+#define X86_FEATURE_CQM ( 9*32+12) /* "cqm" Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* Zero out FPU CS and FPU DS */
+#define X86_FEATURE_MPX ( 9*32+14) /* "mpx" Memory Protection Extension */
+#define X86_FEATURE_RDT_A ( 9*32+15) /* "rdt_a" Resource Director Technology Allocation */
+#define X86_FEATURE_AVX512F ( 9*32+16) /* "avx512f" AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ ( 9*32+17) /* "avx512dq" AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED ( 9*32+18) /* "rdseed" RDSEED instruction */
+#define X86_FEATURE_ADX ( 9*32+19) /* "adx" ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP ( 9*32+20) /* "smap" Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* "avx512ifma" AVX-512 Integer Fused Multiply-Add instructions */
+#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* "clflushopt" CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB ( 9*32+24) /* "clwb" CLWB instruction */
+#define X86_FEATURE_INTEL_PT ( 9*32+25) /* "intel_pt" Intel Processor Trace */
+#define X86_FEATURE_AVX512PF ( 9*32+26) /* "avx512pf" AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER ( 9*32+27) /* "avx512er" AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD ( 9*32+28) /* "avx512cd" AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI ( 9*32+29) /* "sha_ni" SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW ( 9*32+30) /* "avx512bw" AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL ( 9*32+31) /* "avx512vl" AVX-512 VL (128/256 Vector Length) Extensions */
/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */
-#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */
-#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */
-#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
-#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
-#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */
+#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* "xsaveopt" XSAVEOPT instruction */
+#define X86_FEATURE_XSAVEC (10*32+ 1) /* "xsavec" XSAVEC instruction */
+#define X86_FEATURE_XGETBV1 (10*32+ 2) /* "xgetbv1" XGETBV with ECX = 1 instruction */
+#define X86_FEATURE_XSAVES (10*32+ 3) /* "xsaves" XSAVES/XRSTORS instructions */
+#define X86_FEATURE_XFD (10*32+ 4) /* eXtended Feature Disabling */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
@@ -283,181 +283,183 @@
*
* Reuse free bits when adding new feature flags!
*/
-#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */
-#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */
-#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
-#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
-#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */
-#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
-#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */
-#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */
-#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */
-#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */
-#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */
-#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */
-#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */
-#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */
-#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
-#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */
-#define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */
-#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
-#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 */
+#define X86_FEATURE_CQM_LLC (11*32+ 0) /* "cqm_llc" LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* "cqm_occup_llc" LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* "cqm_mbm_total" LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* "cqm_mbm_local" LLC Local MBM monitoring */
+#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* LFENCE in user entry SWAPGS path */
+#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* LFENCE in kernel entry SWAPGS path */
+#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* "split_lock_detect" #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* Per-thread Memory Bandwidth Allocation */
+#define X86_FEATURE_SGX1 (11*32+ 8) /* Basic SGX */
+#define X86_FEATURE_SGX2 (11*32+ 9) /* SGX Enclave Dynamic Memory Management (EDMM) */
+#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* Issue an IBPB on kernel entry */
+#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* RET prediction control */
+#define X86_FEATURE_RETPOLINE (11*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* Use LFENCE for Spectre variant 2 */
+#define X86_FEATURE_RETHUNK (11*32+14) /* Use REturn THUNK */
+#define X86_FEATURE_UNRET (11*32+15) /* AMD BTB untrain return */
+#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* Use IBPB during runtime firmware calls */
+#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* Fill RSB on VM exit when EIBRS is enabled */
+#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* SGX EDECCSSA user leaf function */
+#define X86_FEATURE_CALL_DEPTH (11*32+19) /* Call depth tracking for RSB stuffing */
+#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* MSR IA32_TSX_CTRL (Intel) implemented */
+#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) /* "user_shstk" 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 */
-#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
-#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */
-#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */
-#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */
-#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */
-#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */
-#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */
-#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */
-#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */
-#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */
-#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
-#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */
+#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */
+#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */
+#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* Intel Architectural PerfMon Extension */
+#define X86_FEATURE_FZRM (12*32+10) /* Fast zero-length REP MOVSB */
+#define X86_FEATURE_FSRS (12*32+11) /* Fast short REP STOSB */
+#define X86_FEATURE_FSRC (12*32+12) /* Fast short REP {CMPSB,SCASB} */
+#define X86_FEATURE_FRED (12*32+17) /* "fred" Flexible Return and Event Delivery */
+#define X86_FEATURE_LKGS (12*32+18) /* Load "kernel" (userspace) GS */
+#define X86_FEATURE_WRMSRNS (12*32+19) /* Non-serializing WRMSR */
+#define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */
+#define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */
+#define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
-#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
-#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
-#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */
-#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */
-#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
-#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
-#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
-#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */
-#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
-#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
-#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
-#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */
-#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */
-#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */
-#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */
+#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */
+#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */
+#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */
+#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */
+#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */
+#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */
+#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */
+#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */
+#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
+#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */
+#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
-#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
-#define X86_FEATURE_HFI (14*32+19) /* Hardware Feedback Interface */
+#define X86_FEATURE_DTHERM (14*32+ 0) /* "dtherm" Digital Thermal Sensor */
+#define X86_FEATURE_IDA (14*32+ 1) /* "ida" Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT (14*32+ 2) /* "arat" Always Running APIC Timer */
+#define X86_FEATURE_PLN (14*32+ 4) /* "pln" Intel Power Limit Notification */
+#define X86_FEATURE_PTS (14*32+ 6) /* "pts" Intel Package Thermal Status */
+#define X86_FEATURE_HWP (14*32+ 7) /* "hwp" Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* "hwp_notify" HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* "hwp_act_window" HWP Activity Window */
+#define X86_FEATURE_HWP_EPP (14*32+10) /* "hwp_epp" HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* "hwp_pkg_req" HWP Package Level Request */
+#define X86_FEATURE_HWP_HIGHEST_PERF_CHANGE (14*32+15) /* HWP Highest perf change */
+#define X86_FEATURE_HFI (14*32+19) /* "hfi" Hardware Feedback Interface */
/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */
-#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_NPT (15*32+ 0) /* "npt" Nested Page Table support */
+#define X86_FEATURE_LBRV (15*32+ 1) /* "lbrv" LBR Virtualization support */
#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */
#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */
#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */
#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
-#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
-#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */
-#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */
-#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */
-#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* "flushbyasid" Flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* "decodeassists" Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* "pausefilter" Filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* "pfthreshold" Pause filter threshold */
+#define X86_FEATURE_AVIC (15*32+13) /* "avic" Virtual Interrupt Controller */
+#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* "v_vmsave_vmload" Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF (15*32+16) /* "vgif" Virtual GIF */
+#define X86_FEATURE_X2AVIC (15*32+18) /* "x2avic" Virtual x2apic */
+#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
+#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */
+#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
-#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
-#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */
-#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
-#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
-#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
-#define X86_FEATURE_SHSTK (16*32+ 7) /* "" Shadow stack */
-#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
-#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */
-#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */
-#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */
-#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
-#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */
-#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
-#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
-#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */
-#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
-#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */
-#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */
-#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */
-#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */
+#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/
+#define X86_FEATURE_UMIP (16*32+ 2) /* "umip" User Mode Instruction Protection */
+#define X86_FEATURE_PKU (16*32+ 3) /* "pku" Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE (16*32+ 4) /* "ospke" OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG (16*32+ 5) /* "waitpkg" UMONITOR/UMWAIT/TPAUSE Instructions */
+#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* "avx512_vbmi2" Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow stack */
+#define X86_FEATURE_GFNI (16*32+ 8) /* "gfni" Galois Field New Instructions */
+#define X86_FEATURE_VAES (16*32+ 9) /* "vaes" Vector AES */
+#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* "vpclmulqdq" Carry-Less Multiplication Double Quadword */
+#define X86_FEATURE_AVX512_VNNI (16*32+11) /* "avx512_vnni" Vector Neural Network Instructions */
+#define X86_FEATURE_AVX512_BITALG (16*32+12) /* "avx512_bitalg" Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_TME (16*32+13) /* "tme" Intel Total Memory Encryption */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* "avx512_vpopcntdq" POPCNT for vectors of DW/QW */
+#define X86_FEATURE_LA57 (16*32+16) /* "la57" 5-level page tables */
+#define X86_FEATURE_RDPID (16*32+22) /* "rdpid" RDPID instruction */
+#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* "bus_lock_detect" Bus Lock detect */
+#define X86_FEATURE_CLDEMOTE (16*32+25) /* "cldemote" CLDEMOTE instruction */
+#define X86_FEATURE_MOVDIRI (16*32+27) /* "movdiri" MOVDIRI instruction */
+#define X86_FEATURE_MOVDIR64B (16*32+28) /* "movdir64b" MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD (16*32+29) /* "enqcmd" ENQCMD and ENQCMDS instructions */
+#define X86_FEATURE_SGX_LC (16*32+30) /* "sgx_lc" Software Guard Extensions Launch Control */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
-#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
-#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */
-#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */
+#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* "overflow_recov" MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR (17*32+ 1) /* "succor" Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA (17*32+ 3) /* "smca" Scalable MCA */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
-#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
-#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */
-#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
-#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */
-#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
-#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* "" RTM transaction always aborts */
-#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
-#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */
-#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */
-#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */
-#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
-#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */
-#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */
-#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */
-#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */
-#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */
-#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */
-#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
-#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */
-#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
-#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
-#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
+#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* "avx512_4vnniw" AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* "avx512_4fmaps" AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM (18*32+ 4) /* "fsrm" Fast Short Rep Mov */
+#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* "avx512_vp2intersect" AVX-512 Intersect for D/Q */
+#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* SRBDS mitigation MSR available */
+#define X86_FEATURE_MD_CLEAR (18*32+10) /* "md_clear" VERW clears CPU buffers */
+#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* RTM transaction always aborts */
+#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* TSX_FORCE_ABORT */
+#define X86_FEATURE_SERIALIZE (18*32+14) /* "serialize" SERIALIZE instruction */
+#define X86_FEATURE_HYBRID_CPU (18*32+15) /* This part has CPUs of more than one type */
+#define X86_FEATURE_TSXLDTRK (18*32+16) /* "tsxldtrk" TSX Suspend Load Address Tracking */
+#define X86_FEATURE_PCONFIG (18*32+18) /* "pconfig" Intel PCONFIG */
+#define X86_FEATURE_ARCH_LBR (18*32+19) /* "arch_lbr" Intel ARCH LBR */
+#define X86_FEATURE_IBT (18*32+20) /* "ibt" Indirect Branch Tracking */
+#define X86_FEATURE_AMX_BF16 (18*32+22) /* "amx_bf16" AMX bf16 Support */
+#define X86_FEATURE_AVX512_FP16 (18*32+23) /* "avx512_fp16" AVX512 FP16 */
+#define X86_FEATURE_AMX_TILE (18*32+24) /* "amx_tile" AMX tile Support */
+#define X86_FEATURE_AMX_INT8 (18*32+25) /* "amx_int8" AMX int8 Support */
+#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D (18*32+28) /* "flush_l1d" Flush L1D cache */
+#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* "arch_capabilities" IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* IA32_CORE_CAPABILITIES MSR */
+#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */
/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
-#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */
-#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */
-#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */
-#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
-#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */
-#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 */
+#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */
+#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */
+#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */
+#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) /* "debug_swap" AMD SEV-ES full debug state swap support */
+#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
/* 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 */
-#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */
+#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 */
+#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */
-#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */
-#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
-#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
+#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */
+#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
+#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
@@ -465,59 +467,60 @@
*
* Reuse free bits when adding new feature flags!
*/
-#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
-#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
-#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */
-#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */
-#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* "amd_lbr_pmc_freeze" AMD LBR and PMC Freeze */
+#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */
/*
* BUG word(s)
*/
#define X86_BUG(x) (NCAPINTS*32 + (x))
-#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_F00F X86_BUG(0) /* "f00f" Intel F00F */
+#define X86_BUG_FDIV X86_BUG(1) /* "fdiv" FPU FDIV */
+#define X86_BUG_COMA X86_BUG(2) /* "coma" Cyrix 6x86 coma */
#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_11AP X86_BUG(5) /* "11ap" Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* "fxsave_leak" FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* "clflush_monitor" AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* "sysret_ss_attrs" SYSRET doesn't fix up SS attrs */
#ifdef CONFIG_X86_32
/*
* 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional
* to avoid confusion.
*/
-#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#define X86_BUG_ESPFIX X86_BUG(9) /* IRET to 16-bit SS corrupts ESP/RSP high bits */
#endif
-#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
-#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
-#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
-#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
-#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
-#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
-#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
-#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
-#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */
-#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
-#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
-#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
-#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
-#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
-#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */
-#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 */
+#define X86_BUG_NULL_SEG X86_BUG(10) /* "null_seg" Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* "swapgs_fence" SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR X86_BUG(12) /* "monitor" IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400 X86_BUG(13) /* "amd_e400" CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* "cpu_meltdown" CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* "spectre_v1" CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* "spectre_v2" CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* "spec_store_bypass" CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF X86_BUG(18) /* "l1tf" CPU is affected by L1 Terminal Fault */
+#define X86_BUG_MDS X86_BUG(19) /* "mds" CPU is affected by Microarchitectural data sampling */
+#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* "msbds_only" CPU is only affected by the MSDBS variant of BUG_MDS */
+#define X86_BUG_SWAPGS X86_BUG(21) /* "swapgs" CPU is affected by speculation through SWAPGS */
+#define X86_BUG_TAA X86_BUG(22) /* "taa" CPU is affected by TSX Async Abort(TAA) */
+#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */
+#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */
+#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */
+#define X86_BUG_GDS X86_BUG(30) /* "gds" CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" 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 */
-#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
-#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
-#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
+#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */
+#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
+#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 481096177500..521aad70e41b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -229,7 +229,8 @@ static inline bool efi_is_native(void)
static inline void *efi64_zero_upper(void *p)
{
- ((u32 *)p)[1] = 0;
+ if (p)
+ ((u32 *)p)[1] = 0;
return p;
}
@@ -315,6 +316,10 @@ static inline u32 efi64_convert_status(efi_status_t status)
#define __efi64_argmap_clear_memory_attributes(protocol, phys, size, flags) \
((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags))
+/* EFI SMBIOS protocol */
+#define __efi64_argmap_get_next(protocol, smbioshandle, type, record, phandle) \
+ ((protocol), (smbioshandle), (type), efi64_zero_upper(record), \
+ efi64_zero_upper(phandle))
/*
* The macros below handle the plumbing for the argument mapping. To add a
* mapping for a specific EFI method, simply define a macro
@@ -384,23 +389,8 @@ static inline void efi_reserve_boot_services(void)
}
#endif /* CONFIG_EFI */
-#ifdef CONFIG_EFI_FAKE_MEMMAP
-extern void __init efi_fake_memmap_early(void);
-extern void __init efi_fake_memmap(void);
-#else
-static inline void efi_fake_memmap_early(void)
-{
-}
-
-static inline void efi_fake_memmap(void)
-{
-}
-#endif
-
extern int __init efi_memmap_alloc(unsigned int num_entries,
struct efi_memory_map_data *data);
-extern void __efi_memmap_free(u64 phys, unsigned long size,
- unsigned long flags);
extern int __init efi_memmap_install(struct efi_memory_map_data *data);
extern int __init efi_memmap_split_count(efi_memory_desc_t *md,
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 897cf02c20b1..0152a81d9b4a 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -20,8 +20,6 @@
#define ARCH_SUPPORTS_FTRACE_OPS 1
#endif
-#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
-
#ifndef __ASSEMBLY__
extern void __fentry__(void);
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index cc9ccf61b6bd..14d72727d7ee 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -6,6 +6,7 @@
struct x86_mapping_info {
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
+ void (*free_pgt_page)(void *, void *); /* free buf for page table */
void *context; /* context for alloc_pgt_page */
unsigned long page_flag; /* page flag for PMD or PUD entry */
unsigned long offset; /* ident mapping offset */
@@ -16,4 +17,6 @@ struct x86_mapping_info {
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
unsigned long pstart, unsigned long pend);
+void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd);
+
#endif /* _ASM_X86_INIT_H */
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 2f9eeb5c3069..5dbeac48a5b9 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -9,6 +9,7 @@
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS_FMT4 8
#define MAX_PEBS_EVENTS 32
+#define MAX_PEBS_EVENTS_MASK GENMASK_ULL(MAX_PEBS_EVENTS - 1, 0)
#define MAX_FIXED_PEBS_EVENTS 16
/*
diff --git a/arch/x86/include/asm/intel_pconfig.h b/arch/x86/include/asm/intel_pconfig.h
deleted file mode 100644
index 994638ef171b..000000000000
--- a/arch/x86/include/asm/intel_pconfig.h
+++ /dev/null
@@ -1,65 +0,0 @@
-#ifndef _ASM_X86_INTEL_PCONFIG_H
-#define _ASM_X86_INTEL_PCONFIG_H
-
-#include <asm/asm.h>
-#include <asm/processor.h>
-
-enum pconfig_target {
- INVALID_TARGET = 0,
- MKTME_TARGET = 1,
- PCONFIG_TARGET_NR
-};
-
-int pconfig_target_supported(enum pconfig_target target);
-
-enum pconfig_leaf {
- MKTME_KEY_PROGRAM = 0,
- PCONFIG_LEAF_INVALID,
-};
-
-#define PCONFIG ".byte 0x0f, 0x01, 0xc5"
-
-/* Defines and structure for MKTME_KEY_PROGRAM of PCONFIG instruction */
-
-/* mktme_key_program::keyid_ctrl COMMAND, bits [7:0] */
-#define MKTME_KEYID_SET_KEY_DIRECT 0
-#define MKTME_KEYID_SET_KEY_RANDOM 1
-#define MKTME_KEYID_CLEAR_KEY 2
-#define MKTME_KEYID_NO_ENCRYPT 3
-
-/* mktme_key_program::keyid_ctrl ENC_ALG, bits [23:8] */
-#define MKTME_AES_XTS_128 (1 << 8)
-
-/* Return codes from the PCONFIG MKTME_KEY_PROGRAM */
-#define MKTME_PROG_SUCCESS 0
-#define MKTME_INVALID_PROG_CMD 1
-#define MKTME_ENTROPY_ERROR 2
-#define MKTME_INVALID_KEYID 3
-#define MKTME_INVALID_ENC_ALG 4
-#define MKTME_DEVICE_BUSY 5
-
-/* Hardware requires the structure to be 256 byte aligned. Otherwise #GP(0). */
-struct mktme_key_program {
- u16 keyid;
- u32 keyid_ctrl;
- u8 __rsvd[58];
- u8 key_field_1[64];
- u8 key_field_2[64];
-} __packed __aligned(256);
-
-static inline int mktme_key_program(struct mktme_key_program *key_program)
-{
- unsigned long rax = MKTME_KEY_PROGRAM;
-
- if (!pconfig_target_supported(MKTME_TARGET))
- return -ENXIO;
-
- asm volatile(PCONFIG
- : "=a" (rax), "=b" (key_program)
- : "0" (rax), "1" (key_program)
- : "memory", "cc");
-
- return rax;
-}
-
-#endif /* _ASM_X86_INTEL_PCONFIG_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 8c5ae649d2df..cf7fc2b8e3ce 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -54,6 +54,26 @@ static __always_inline void native_halt(void)
asm volatile("hlt": : :"memory");
}
+static __always_inline int native_irqs_disabled_flags(unsigned long flags)
+{
+ return !(flags & X86_EFLAGS_IF);
+}
+
+static __always_inline unsigned long native_local_irq_save(void)
+{
+ unsigned long flags = native_save_fl();
+
+ native_irq_disable();
+
+ return flags;
+}
+
+static __always_inline void native_local_irq_restore(unsigned long flags)
+{
+ if (!native_irqs_disabled_flags(flags))
+ native_irq_enable();
+}
+
#endif
#ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 5187fcf4b610..68ad4f923664 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -9,8 +9,7 @@ BUILD_BUG_ON(1)
* "static_call_update()" calls.
*
* KVM_X86_OP_OPTIONAL() can be used for those functions that can have
- * a NULL definition, for example if "static_call_cond()" will be used
- * at the call sites. KVM_X86_OP_OPTIONAL_RET0() can be used likewise
+ * a NULL definition. KVM_X86_OP_OPTIONAL_RET0() can be used likewise
* to make a definition optional, but in this case the default will
* be __static_call_return0.
*/
@@ -85,7 +84,6 @@ KVM_X86_OP_OPTIONAL(update_cr8_intercept)
KVM_X86_OP(refresh_apicv_exec_ctrl)
KVM_X86_OP_OPTIONAL(hwapic_irr_update)
KVM_X86_OP_OPTIONAL(hwapic_isr_update)
-KVM_X86_OP_OPTIONAL_RET0(guest_apic_has_interrupt)
KVM_X86_OP_OPTIONAL(load_eoi_exitmap)
KVM_X86_OP_OPTIONAL(set_virtual_apic_mode)
KVM_X86_OP_OPTIONAL(set_apic_access_page_addr)
@@ -103,7 +101,6 @@ KVM_X86_OP(write_tsc_multiplier)
KVM_X86_OP(get_exit_info)
KVM_X86_OP(check_intercept)
KVM_X86_OP(handle_exit_irqoff)
-KVM_X86_OP(sched_in)
KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging)
KVM_X86_OP_OPTIONAL(vcpu_blocking)
KVM_X86_OP_OPTIONAL(vcpu_unblocking)
@@ -139,6 +136,9 @@ KVM_X86_OP(vcpu_deliver_sipi_vector)
KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
KVM_X86_OP_OPTIONAL(get_untagged_addr)
KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
+KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
+KVM_X86_OP_OPTIONAL_RET0(private_max_mapping_level)
+KVM_X86_OP_OPTIONAL(gmem_invalidate)
#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 f852b13aeefe..9159bf1a4730 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -9,8 +9,7 @@ BUILD_BUG_ON(1)
* "static_call_update()" calls.
*
* KVM_X86_PMU_OP_OPTIONAL() can be used for those functions that can have
- * a NULL definition, for example if "static_call_cond()" will be used
- * at the call sites.
+ * a NULL definition.
*/
KVM_X86_PMU_OP(rdpmc_ecx_to_pmc)
KVM_X86_PMU_OP(msr_idx_to_pmc)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f8ca74e7678f..950a03e0181e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -121,6 +121,7 @@
KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_HV_TLB_FLUSH \
KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE KVM_ARCH_REQ(34)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -159,7 +160,6 @@
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 256
-#define KVM_NR_FIXED_MTRR_REGION 88
#define KVM_NR_VAR_MTRR 8
#define ASYNC_PF_PER_VCPU 64
@@ -533,12 +533,16 @@ struct kvm_pmc {
};
/* More counters may conflict with other existing Architectural MSRs */
-#define KVM_INTEL_PMC_MAX_GENERIC 8
-#define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1)
-#define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1)
-#define KVM_PMC_MAX_FIXED 3
-#define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1)
-#define KVM_AMD_PMC_MAX_GENERIC 6
+#define KVM_MAX(a, b) ((a) >= (b) ? (a) : (b))
+#define KVM_MAX_NR_INTEL_GP_COUNTERS 8
+#define KVM_MAX_NR_AMD_GP_COUNTERS 6
+#define KVM_MAX_NR_GP_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_GP_COUNTERS, \
+ KVM_MAX_NR_AMD_GP_COUNTERS)
+
+#define KVM_MAX_NR_INTEL_FIXED_COUTNERS 3
+#define KVM_MAX_NR_AMD_FIXED_COUTNERS 0
+#define KVM_MAX_NR_FIXED_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_FIXED_COUTNERS, \
+ KVM_MAX_NR_AMD_FIXED_COUTNERS)
struct kvm_pmu {
u8 version;
@@ -546,16 +550,16 @@ struct kvm_pmu {
unsigned nr_arch_fixed_counters;
unsigned available_event_types;
u64 fixed_ctr_ctrl;
- u64 fixed_ctr_ctrl_mask;
+ u64 fixed_ctr_ctrl_rsvd;
u64 global_ctrl;
u64 global_status;
u64 counter_bitmask[2];
- u64 global_ctrl_mask;
- u64 global_status_mask;
+ u64 global_ctrl_rsvd;
+ u64 global_status_rsvd;
u64 reserved_bits;
u64 raw_event_mask;
- struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
- struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
+ struct kvm_pmc gp_counters[KVM_MAX_NR_GP_COUNTERS];
+ struct kvm_pmc fixed_counters[KVM_MAX_NR_FIXED_COUNTERS];
/*
* Overlay the bitmap with a 64-bit atomic so that all bits can be
@@ -571,9 +575,9 @@ struct kvm_pmu {
u64 ds_area;
u64 pebs_enable;
- u64 pebs_enable_mask;
+ u64 pebs_enable_rsvd;
u64 pebs_data_cfg;
- u64 pebs_data_cfg_mask;
+ u64 pebs_data_cfg_rsvd;
/*
* If a guest counter is cross-mapped to host counter with different
@@ -604,18 +608,12 @@ enum {
KVM_DEBUGREG_WONT_EXIT = 2,
};
-struct kvm_mtrr_range {
- u64 base;
- u64 mask;
- struct list_head node;
-};
-
struct kvm_mtrr {
- struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR];
- mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION];
+ u64 var[KVM_NR_VAR_MTRR * 2];
+ u64 fixed_64k;
+ u64 fixed_16k[2];
+ u64 fixed_4k[8];
u64 deftype;
-
- struct list_head head;
};
/* Hyper-V SynIC timer */
@@ -1207,7 +1205,7 @@ enum kvm_apicv_inhibit {
* APIC acceleration is disabled by a module parameter
* and/or not supported in hardware.
*/
- APICV_INHIBIT_REASON_DISABLE,
+ APICV_INHIBIT_REASON_DISABLED,
/*
* APIC acceleration is inhibited because AutoEOI feature is
@@ -1277,8 +1275,27 @@ enum kvm_apicv_inhibit {
* mapping between logical ID and vCPU.
*/
APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED,
+
+ NR_APICV_INHIBIT_REASONS,
};
+#define __APICV_INHIBIT_REASON(reason) \
+ { BIT(APICV_INHIBIT_REASON_##reason), #reason }
+
+#define APICV_INHIBIT_REASONS \
+ __APICV_INHIBIT_REASON(DISABLED), \
+ __APICV_INHIBIT_REASON(HYPERV), \
+ __APICV_INHIBIT_REASON(ABSENT), \
+ __APICV_INHIBIT_REASON(BLOCKIRQ), \
+ __APICV_INHIBIT_REASON(PHYSICAL_ID_ALIASED), \
+ __APICV_INHIBIT_REASON(APIC_ID_MODIFIED), \
+ __APICV_INHIBIT_REASON(APIC_BASE_MODIFIED), \
+ __APICV_INHIBIT_REASON(NESTED), \
+ __APICV_INHIBIT_REASON(IRQWIN), \
+ __APICV_INHIBIT_REASON(PIT_REINJ), \
+ __APICV_INHIBIT_REASON(SEV), \
+ __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED)
+
struct kvm_arch {
unsigned long n_used_mmu_pages;
unsigned long n_requested_mmu_pages;
@@ -1364,6 +1381,7 @@ struct kvm_arch {
u32 default_tsc_khz;
bool user_set_tsc;
+ u64 apic_bus_cycle_ns;
seqcount_raw_spinlock_t pvclock_sc;
bool use_master_clock;
@@ -1708,13 +1726,11 @@ struct kvm_x86_ops {
void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
void (*enable_irq_window)(struct kvm_vcpu *vcpu);
void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
- bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason);
const unsigned long required_apicv_inhibits;
bool allow_apicv_in_x2apic_without_x2apic_virtualization;
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(int isr);
- bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
@@ -1749,8 +1765,6 @@ struct kvm_x86_ops {
struct x86_exception *exception);
void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
- 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
* value indicates CPU dirty logging is unsupported or disabled.
@@ -1812,6 +1826,9 @@ struct kvm_x86_ops {
gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
+ int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
+ void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end);
+ int (*private_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn);
};
struct kvm_x86_nested_ops {
@@ -1819,7 +1836,7 @@ struct kvm_x86_nested_ops {
bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector,
u32 error_code);
int (*check_events)(struct kvm_vcpu *vcpu);
- bool (*has_events)(struct kvm_vcpu *vcpu);
+ bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection);
void (*triple_fault)(struct kvm_vcpu *vcpu);
int (*get_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
@@ -1853,11 +1870,13 @@ struct kvm_arch_async_pf {
};
extern u32 __read_mostly kvm_nr_uret_msrs;
-extern u64 __read_mostly host_efer;
extern bool __read_mostly allow_smaller_maxphyaddr;
extern bool __read_mostly enable_apicv;
extern struct kvm_x86_ops kvm_x86_ops;
+#define kvm_x86_call(func) static_call(kvm_x86_##func)
+#define kvm_pmu_call(func) static_call(kvm_x86_pmu_##func)
+
#define KVM_X86_OP(func) \
DECLARE_STATIC_CALL(kvm_x86_##func, *(((struct kvm_x86_ops *)0)->func));
#define KVM_X86_OP_OPTIONAL KVM_X86_OP
@@ -1881,7 +1900,7 @@ void kvm_arch_free_vm(struct kvm *kvm);
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))
+ !kvm_x86_call(flush_remote_tlbs)(kvm))
return 0;
else
return -ENOTSUPP;
@@ -1894,7 +1913,7 @@ static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
if (!kvm_x86_ops.flush_remote_tlbs_range)
return -EOPNOTSUPP;
- return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
+ return kvm_x86_call(flush_remote_tlbs_range)(kvm, gfn, nr_pages);
}
#endif /* CONFIG_HYPERV */
@@ -1939,6 +1958,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
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);
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -2292,12 +2312,12 @@ static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{
- static_call_cond(kvm_x86_vcpu_blocking)(vcpu);
+ kvm_x86_call(vcpu_blocking)(vcpu);
}
static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
{
- static_call_cond(kvm_x86_vcpu_unblocking)(vcpu);
+ kvm_x86_call(vcpu_unblocking)(vcpu);
}
static inline int kvm_cpu_get_apicid(int mps_cpu)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index dfd2e9699bd7..3ad29b128943 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -261,7 +261,8 @@ enum mcp_flags {
MCP_DONTLOG = BIT(2), /* only clear, don't log */
MCP_QUEUE_LOG = BIT(3), /* only queue to genpool */
};
-bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
+
+void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
int mce_notify_irq(void);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e022e6eb766c..82c6a4d350e0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -566,6 +566,12 @@
#define MSR_RELOAD_PMC0 0x000014c1
#define MSR_RELOAD_FIXED_CTR0 0x00001309
+/* V6 PMON MSR range */
+#define MSR_IA32_PMC_V6_GP0_CTR 0x1900
+#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901
+#define MSR_IA32_PMC_V6_FX0_CTR 0x1980
+#define MSR_IA32_PMC_V6_STEP 4
+
/* KeyID partitioning between MKTME and TDX */
#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087
@@ -660,6 +666,8 @@
#define MSR_AMD64_RMP_BASE 0xc0010132
#define MSR_AMD64_RMP_END 0xc0010133
+#define MSR_SVSM_CAA 0xc001f000
+
/* AMD Collaborative Processor Performance Control MSRs */
#define MSR_AMD_CPPC_CAP1 0xc00102b0
#define MSR_AMD_CPPC_ENABLE 0xc00102b1
@@ -781,6 +789,8 @@
#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
+#define MSR_K7_HWCR_CPB_DIS_BIT 25
+#define MSR_K7_HWCR_CPB_DIS BIT_ULL(MSR_K7_HWCR_CPB_DIS_BIT)
/* K6 MSRs */
#define MSR_K6_WHCR 0xc0000082
@@ -1164,6 +1174,7 @@
#define MSR_IA32_QM_CTR 0xc8e
#define MSR_IA32_PQR_ASSOC 0xc8f
#define MSR_IA32_L3_CBM_BASE 0xc90
+#define MSR_RMID_SNC_CONFIG 0xca0
#define MSR_IA32_L2_CBM_BASE 0xd10
#define MSR_IA32_MBA_THRTL_BASE 0xd50
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index cc6b8e087192..af4302d79b59 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -54,7 +54,7 @@ static inline void clear_page(void *page)
clear_page_rep, X86_FEATURE_REP_GOOD,
clear_page_erms, X86_FEATURE_ERMS,
"=D" (page),
- "0" (page)
+ "D" (page)
: "cc", "memory", "rax", "rcx");
}
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 3bedee1801e2..c55a79d5feae 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -3,30 +3,30 @@
#define _ASM_X86_PERCPU_H
#ifdef CONFIG_X86_64
-#define __percpu_seg gs
-#define __percpu_rel (%rip)
+# define __percpu_seg gs
+# define __percpu_rel (%rip)
#else
-#define __percpu_seg fs
-#define __percpu_rel
+# define __percpu_seg fs
+# define __percpu_rel
#endif
#ifdef __ASSEMBLY__
#ifdef CONFIG_SMP
-#define __percpu %__percpu_seg:
+# define __percpu %__percpu_seg:
#else
-#define __percpu
+# define __percpu
#endif
#define PER_CPU_VAR(var) __percpu(var)__percpu_rel
#ifdef CONFIG_X86_64_SMP
-#define INIT_PER_CPU_VAR(var) init_per_cpu__##var
+# define INIT_PER_CPU_VAR(var) init_per_cpu__##var
#else
-#define INIT_PER_CPU_VAR(var) var
+# define INIT_PER_CPU_VAR(var) var
#endif
-#else /* ...!ASSEMBLY */
+#else /* !__ASSEMBLY__: */
#include <linux/build_bug.h>
#include <linux/stringify.h>
@@ -37,19 +37,19 @@
#ifdef CONFIG_CC_HAS_NAMED_AS
#ifdef __CHECKER__
-#define __seg_gs __attribute__((address_space(__seg_gs)))
-#define __seg_fs __attribute__((address_space(__seg_fs)))
+# define __seg_gs __attribute__((address_space(__seg_gs)))
+# define __seg_fs __attribute__((address_space(__seg_fs)))
#endif
#ifdef CONFIG_X86_64
-#define __percpu_seg_override __seg_gs
+# define __percpu_seg_override __seg_gs
#else
-#define __percpu_seg_override __seg_fs
+# define __percpu_seg_override __seg_fs
#endif
#define __percpu_prefix ""
-#else /* CONFIG_CC_HAS_NAMED_AS */
+#else /* !CONFIG_CC_HAS_NAMED_AS: */
#define __percpu_seg_override
#define __percpu_prefix "%%"__stringify(__percpu_seg)":"
@@ -68,11 +68,12 @@
* sizeof(this_cpu_off) becames 4.
*/
#ifndef BUILD_VDSO32_64
-#define arch_raw_cpu_ptr(_ptr) \
-({ \
- unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off); \
- tcp_ptr__ += (__force unsigned long)(_ptr); \
- (typeof(*(_ptr)) __kernel __force *)tcp_ptr__; \
+#define arch_raw_cpu_ptr(_ptr) \
+({ \
+ unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off); \
+ \
+ tcp_ptr__ += (__force unsigned long)(_ptr); \
+ (typeof(*(_ptr)) __kernel __force *)tcp_ptr__; \
})
#else
#define arch_raw_cpu_ptr(_ptr) ({ BUILD_BUG(); (typeof(_ptr))0; })
@@ -80,7 +81,8 @@
#define PER_CPU_VAR(var) %__percpu_seg:(var)__percpu_rel
-#else /* CONFIG_SMP */
+#else /* !CONFIG_SMP: */
+
#define __percpu_seg_override
#define __percpu_prefix ""
#define __force_percpu_prefix ""
@@ -96,7 +98,7 @@
#define __force_percpu_arg(x) __force_percpu_prefix "%" #x
/*
- * Initialized pointers to per-cpu variables needed for the boot
+ * Initialized pointers to per-CPU variables needed for the boot
* processor need to use these macros to get the proper address
* offset from __per_cpu_load on SMP.
*
@@ -106,65 +108,128 @@
extern typeof(var) init_per_cpu_var(var)
#ifdef CONFIG_X86_64_SMP
-#define init_per_cpu_var(var) init_per_cpu__##var
+# define init_per_cpu_var(var) init_per_cpu__##var
#else
-#define init_per_cpu_var(var) var
+# define init_per_cpu_var(var) var
#endif
-/* For arch-specific code, we can use direct single-insn ops (they
- * don't give an lvalue though). */
+/*
+ * For arch-specific code, we can use direct single-insn ops (they
+ * don't give an lvalue though).
+ */
-#define __pcpu_type_1 u8
-#define __pcpu_type_2 u16
-#define __pcpu_type_4 u32
-#define __pcpu_type_8 u64
+#define __pcpu_type_1 u8
+#define __pcpu_type_2 u16
+#define __pcpu_type_4 u32
+#define __pcpu_type_8 u64
-#define __pcpu_cast_1(val) ((u8)(((unsigned long) val) & 0xff))
-#define __pcpu_cast_2(val) ((u16)(((unsigned long) val) & 0xffff))
-#define __pcpu_cast_4(val) ((u32)(((unsigned long) val) & 0xffffffff))
-#define __pcpu_cast_8(val) ((u64)(val))
+#define __pcpu_cast_1(val) ((u8)(((unsigned long) val) & 0xff))
+#define __pcpu_cast_2(val) ((u16)(((unsigned long) val) & 0xffff))
+#define __pcpu_cast_4(val) ((u32)(((unsigned long) val) & 0xffffffff))
+#define __pcpu_cast_8(val) ((u64)(val))
-#define __pcpu_op1_1(op, dst) op "b " dst
-#define __pcpu_op1_2(op, dst) op "w " dst
-#define __pcpu_op1_4(op, dst) op "l " dst
-#define __pcpu_op1_8(op, dst) op "q " dst
+#define __pcpu_op1_1(op, dst) op "b " dst
+#define __pcpu_op1_2(op, dst) op "w " dst
+#define __pcpu_op1_4(op, dst) op "l " dst
+#define __pcpu_op1_8(op, dst) op "q " dst
#define __pcpu_op2_1(op, src, dst) op "b " src ", " dst
#define __pcpu_op2_2(op, src, dst) op "w " src ", " dst
#define __pcpu_op2_4(op, src, dst) op "l " src ", " dst
#define __pcpu_op2_8(op, src, dst) op "q " src ", " dst
-#define __pcpu_reg_1(mod, x) mod "q" (x)
-#define __pcpu_reg_2(mod, x) mod "r" (x)
-#define __pcpu_reg_4(mod, x) mod "r" (x)
-#define __pcpu_reg_8(mod, x) mod "r" (x)
+#define __pcpu_reg_1(mod, x) mod "q" (x)
+#define __pcpu_reg_2(mod, x) mod "r" (x)
+#define __pcpu_reg_4(mod, x) mod "r" (x)
+#define __pcpu_reg_8(mod, x) mod "r" (x)
-#define __pcpu_reg_imm_1(x) "qi" (x)
-#define __pcpu_reg_imm_2(x) "ri" (x)
-#define __pcpu_reg_imm_4(x) "ri" (x)
-#define __pcpu_reg_imm_8(x) "re" (x)
+#define __pcpu_reg_imm_1(x) "qi" (x)
+#define __pcpu_reg_imm_2(x) "ri" (x)
+#define __pcpu_reg_imm_4(x) "ri" (x)
+#define __pcpu_reg_imm_8(x) "re" (x)
-#define percpu_to_op(size, qual, op, _var, _val) \
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+
+#define __raw_cpu_read(size, qual, pcp) \
+({ \
+ *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)); \
+})
+
+#define __raw_cpu_write(size, qual, pcp, val) \
+do { \
+ *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val); \
+} while (0)
+
+#define __raw_cpu_read_const(pcp) __raw_cpu_read(, , pcp)
+
+#else /* !CONFIG_USE_X86_SEG_SUPPORT: */
+
+#define __raw_cpu_read(size, qual, _var) \
+({ \
+ __pcpu_type_##size pfo_val__; \
+ \
+ asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), "%[val]") \
+ : [val] __pcpu_reg_##size("=", pfo_val__) \
+ : [var] "m" (__my_cpu_var(_var))); \
+ \
+ (typeof(_var))(unsigned long) pfo_val__; \
+})
+
+#define __raw_cpu_write(size, qual, _var, _val) \
do { \
__pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val); \
+ \
if (0) { \
typeof(_var) pto_tmp__; \
pto_tmp__ = (_val); \
(void)pto_tmp__; \
} \
- asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var])) \
- : [var] "+m" (__my_cpu_var(_var)) \
+ asm qual(__pcpu_op2_##size("mov", "%[val]", __percpu_arg([var])) \
+ : [var] "=m" (__my_cpu_var(_var)) \
: [val] __pcpu_reg_imm_##size(pto_val__)); \
} while (0)
+/*
+ * The generic per-CPU infrastrucutre is not suitable for
+ * reading const-qualified variables.
+ */
+#define __raw_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
+
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
+#define __raw_cpu_read_stable(size, _var) \
+({ \
+ __pcpu_type_##size pfo_val__; \
+ \
+ asm(__pcpu_op2_##size("mov", __force_percpu_arg(a[var]), "%[val]") \
+ : [val] __pcpu_reg_##size("=", pfo_val__) \
+ : [var] "i" (&(_var))); \
+ \
+ (typeof(_var))(unsigned long) pfo_val__; \
+})
+
#define percpu_unary_op(size, qual, op, _var) \
({ \
asm qual (__pcpu_op1_##size(op, __percpu_arg([var])) \
: [var] "+m" (__my_cpu_var(_var))); \
})
+#define percpu_binary_op(size, qual, op, _var, _val) \
+do { \
+ __pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val); \
+ \
+ if (0) { \
+ typeof(_var) pto_tmp__; \
+ pto_tmp__ = (_val); \
+ (void)pto_tmp__; \
+ } \
+ asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var])) \
+ : [var] "+m" (__my_cpu_var(_var)) \
+ : [val] __pcpu_reg_imm_##size(pto_val__)); \
+} while (0)
+
/*
- * Generate a percpu add to memory instruction and optimize code
+ * Generate a per-CPU add to memory instruction and optimize code
* if one is added or subtracted.
*/
#define percpu_add_op(size, qual, var, val) \
@@ -172,6 +237,7 @@ do { \
const int pao_ID__ = (__builtin_constant_p(val) && \
((val) == 1 || (val) == -1)) ? \
(int)(val) : 0; \
+ \
if (0) { \
typeof(var) pao_tmp__; \
pao_tmp__ = (val); \
@@ -182,33 +248,16 @@ do { \
else if (pao_ID__ == -1) \
percpu_unary_op(size, qual, "dec", var); \
else \
- percpu_to_op(size, qual, "add", var, val); \
+ percpu_binary_op(size, qual, "add", var, val); \
} while (0)
-#define percpu_from_op(size, qual, op, _var) \
-({ \
- __pcpu_type_##size pfo_val__; \
- asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]") \
- : [val] __pcpu_reg_##size("=", pfo_val__) \
- : [var] "m" (__my_cpu_var(_var))); \
- (typeof(_var))(unsigned long) pfo_val__; \
-})
-
-#define percpu_stable_op(size, op, _var) \
-({ \
- __pcpu_type_##size pfo_val__; \
- asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]") \
- : [val] __pcpu_reg_##size("=", pfo_val__) \
- : [var] "i" (&(_var))); \
- (typeof(_var))(unsigned long) pfo_val__; \
-})
-
/*
* Add return operation
*/
#define percpu_add_return_op(size, qual, _var, _val) \
({ \
__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val); \
+ \
asm qual (__pcpu_op2_##size("xadd", "%[tmp]", \
__percpu_arg([var])) \
: [tmp] __pcpu_reg_##size("+", paro_tmp__), \
@@ -224,36 +273,42 @@ do { \
#define raw_percpu_xchg_op(_var, _nval) \
({ \
typeof(_var) pxo_old__ = raw_cpu_read(_var); \
+ \
raw_cpu_write(_var, _nval); \
+ \
pxo_old__; \
})
/*
- * this_cpu_xchg() is implemented using cmpxchg without a lock prefix.
- * xchg is expensive due to the implied lock prefix. The processor
- * cannot prefetch cachelines if xchg is used.
+ * this_cpu_xchg() is implemented using CMPXCHG without a LOCK prefix.
+ * XCHG is expensive due to the implied LOCK prefix. The processor
+ * cannot prefetch cachelines if XCHG is used.
*/
#define this_percpu_xchg_op(_var, _nval) \
({ \
typeof(_var) pxo_old__ = this_cpu_read(_var); \
+ \
do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval)); \
+ \
pxo_old__; \
})
/*
- * cmpxchg has no such implied lock semantics as a result it is much
- * more efficient for cpu local operations.
+ * CMPXCHG has no such implied lock semantics as a result it is much
+ * more efficient for CPU-local operations.
*/
#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval) \
({ \
__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval); \
__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \
+ \
asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
__percpu_arg([var])) \
: [oval] "+a" (pco_old__), \
[var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pco_new__) \
: "memory"); \
+ \
(typeof(_var))(unsigned long) pco_old__; \
})
@@ -263,6 +318,7 @@ do { \
__pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \
__pcpu_type_##size pco_old__ = *pco_oval__; \
__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \
+ \
asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
__percpu_arg([var])) \
CC_SET(z) \
@@ -273,10 +329,12 @@ do { \
: "memory"); \
if (unlikely(!success)) \
*pco_oval__ = pco_old__; \
+ \
likely(success); \
})
#if defined(CONFIG_X86_32) && !defined(CONFIG_UML)
+
#define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval) \
({ \
union { \
@@ -302,8 +360,8 @@ do { \
old__.var; \
})
-#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, , pcp, oval, nval)
-#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
+#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, , pcp, oval, nval)
+#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
#define percpu_try_cmpxchg64_op(size, qual, _var, _ovalp, _nval) \
({ \
@@ -332,16 +390,18 @@ do { \
: "memory"); \
if (unlikely(!success)) \
*_oval = old__.var; \
+ \
likely(success); \
})
#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, , pcp, ovalp, nval)
#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, volatile, pcp, ovalp, nval)
-#endif
+
+#endif /* defined(CONFIG_X86_32) && !defined(CONFIG_UML) */
#ifdef CONFIG_X86_64
-#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval);
-#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval);
+#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval);
+#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval);
#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval);
#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval);
@@ -371,8 +431,8 @@ do { \
old__.var; \
})
-#define raw_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, , pcp, oval, nval)
-#define this_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, volatile, pcp, oval, nval)
+#define raw_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, , pcp, oval, nval)
+#define this_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, volatile, pcp, oval, nval)
#define percpu_try_cmpxchg128_op(size, qual, _var, _ovalp, _nval) \
({ \
@@ -406,188 +466,150 @@ do { \
#define raw_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, , pcp, ovalp, nval)
#define this_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, volatile, pcp, ovalp, nval)
-#endif
+
+#endif /* CONFIG_X86_64 */
+
+#define raw_cpu_read_1(pcp) __raw_cpu_read(1, , pcp)
+#define raw_cpu_read_2(pcp) __raw_cpu_read(2, , pcp)
+#define raw_cpu_read_4(pcp) __raw_cpu_read(4, , pcp)
+#define raw_cpu_write_1(pcp, val) __raw_cpu_write(1, , pcp, val)
+#define raw_cpu_write_2(pcp, val) __raw_cpu_write(2, , pcp, val)
+#define raw_cpu_write_4(pcp, val) __raw_cpu_write(4, , pcp, val)
+
+#define this_cpu_read_1(pcp) __raw_cpu_read(1, volatile, pcp)
+#define this_cpu_read_2(pcp) __raw_cpu_read(2, volatile, pcp)
+#define this_cpu_read_4(pcp) __raw_cpu_read(4, volatile, pcp)
+#define this_cpu_write_1(pcp, val) __raw_cpu_write(1, volatile, pcp, val)
+#define this_cpu_write_2(pcp, val) __raw_cpu_write(2, volatile, pcp, val)
+#define this_cpu_write_4(pcp, val) __raw_cpu_write(4, volatile, pcp, val)
+
+#define this_cpu_read_stable_1(pcp) __raw_cpu_read_stable(1, pcp)
+#define this_cpu_read_stable_2(pcp) __raw_cpu_read_stable(2, pcp)
+#define this_cpu_read_stable_4(pcp) __raw_cpu_read_stable(4, pcp)
+
+#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val)
+#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val)
+#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val)
+#define raw_cpu_and_1(pcp, val) percpu_binary_op(1, , "and", (pcp), val)
+#define raw_cpu_and_2(pcp, val) percpu_binary_op(2, , "and", (pcp), val)
+#define raw_cpu_and_4(pcp, val) percpu_binary_op(4, , "and", (pcp), val)
+#define raw_cpu_or_1(pcp, val) percpu_binary_op(1, , "or", (pcp), val)
+#define raw_cpu_or_2(pcp, val) percpu_binary_op(2, , "or", (pcp), val)
+#define raw_cpu_or_4(pcp, val) percpu_binary_op(4, , "or", (pcp), val)
+#define raw_cpu_xchg_1(pcp, val) raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val)
+
+#define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val)
+#define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val)
+#define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val)
+#define this_cpu_and_1(pcp, val) percpu_binary_op(1, volatile, "and", (pcp), val)
+#define this_cpu_and_2(pcp, val) percpu_binary_op(2, volatile, "and", (pcp), val)
+#define this_cpu_and_4(pcp, val) percpu_binary_op(4, volatile, "and", (pcp), val)
+#define this_cpu_or_1(pcp, val) percpu_binary_op(1, volatile, "or", (pcp), val)
+#define this_cpu_or_2(pcp, val) percpu_binary_op(2, volatile, "or", (pcp), val)
+#define this_cpu_or_4(pcp, val) percpu_binary_op(4, volatile, "or", (pcp), val)
+#define this_cpu_xchg_1(pcp, nval) this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_2(pcp, nval) this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_4(pcp, nval) this_percpu_xchg_op(pcp, nval)
+
+#define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val)
+#define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val)
+#define raw_cpu_add_return_4(pcp, val) percpu_add_return_op(4, , pcp, val)
+#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval)
+#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval)
+#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, , pcp, ovalp, nval)
+
+#define this_cpu_add_return_1(pcp, val) percpu_add_return_op(1, volatile, pcp, val)
+#define this_cpu_add_return_2(pcp, val) percpu_add_return_op(2, volatile, pcp, val)
+#define this_cpu_add_return_4(pcp, val) percpu_add_return_op(4, volatile, pcp, val)
+#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
+#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
+#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval)
/*
- * this_cpu_read() makes gcc load the percpu variable every time it is
- * accessed while this_cpu_read_stable() allows the value to be cached.
- * this_cpu_read_stable() is more efficient and can be used if its value
- * is guaranteed to be valid across cpus. The current users include
- * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
- * actually per-thread variables implemented as per-CPU variables and
- * thus stable for the duration of the respective task.
+ * Per-CPU atomic 64-bit operations are only available under 64-bit kernels.
+ * 32-bit kernels must fall back to generic operations.
*/
-#define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp)
-
-#ifdef CONFIG_USE_X86_SEG_SUPPORT
-
-#define __raw_cpu_read(qual, pcp) \
-({ \
- *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)); \
-})
+#ifdef CONFIG_X86_64
-#define __raw_cpu_write(qual, pcp, val) \
-do { \
- *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val); \
-} while (0)
+#define raw_cpu_read_8(pcp) __raw_cpu_read(8, , pcp)
+#define raw_cpu_write_8(pcp, val) __raw_cpu_write(8, , pcp, val)
-#define raw_cpu_read_1(pcp) __raw_cpu_read(, pcp)
-#define raw_cpu_read_2(pcp) __raw_cpu_read(, pcp)
-#define raw_cpu_read_4(pcp) __raw_cpu_read(, pcp)
-#define raw_cpu_write_1(pcp, val) __raw_cpu_write(, pcp, val)
-#define raw_cpu_write_2(pcp, val) __raw_cpu_write(, pcp, val)
-#define raw_cpu_write_4(pcp, val) __raw_cpu_write(, pcp, val)
+#define this_cpu_read_8(pcp) __raw_cpu_read(8, volatile, pcp)
+#define this_cpu_write_8(pcp, val) __raw_cpu_write(8, volatile, pcp, val)
-#define this_cpu_read_1(pcp) __raw_cpu_read(volatile, pcp)
-#define this_cpu_read_2(pcp) __raw_cpu_read(volatile, pcp)
-#define this_cpu_read_4(pcp) __raw_cpu_read(volatile, pcp)
-#define this_cpu_write_1(pcp, val) __raw_cpu_write(volatile, pcp, val)
-#define this_cpu_write_2(pcp, val) __raw_cpu_write(volatile, pcp, val)
-#define this_cpu_write_4(pcp, val) __raw_cpu_write(volatile, pcp, val)
+#define this_cpu_read_stable_8(pcp) __raw_cpu_read_stable(8, pcp)
-#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp) __raw_cpu_read(, pcp)
-#define raw_cpu_write_8(pcp, val) __raw_cpu_write(, pcp, val)
+#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val)
+#define raw_cpu_and_8(pcp, val) percpu_binary_op(8, , "and", (pcp), val)
+#define raw_cpu_or_8(pcp, val) percpu_binary_op(8, , "or", (pcp), val)
+#define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(8, , pcp, val)
+#define raw_cpu_xchg_8(pcp, nval) raw_percpu_xchg_op(pcp, nval)
+#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
-#define this_cpu_read_8(pcp) __raw_cpu_read(volatile, pcp)
-#define this_cpu_write_8(pcp, val) __raw_cpu_write(volatile, pcp, val)
-#endif
+#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val)
+#define this_cpu_and_8(pcp, val) percpu_binary_op(8, volatile, "and", (pcp), val)
+#define this_cpu_or_8(pcp, val) percpu_binary_op(8, volatile, "or", (pcp), val)
+#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
+#define this_cpu_xchg_8(pcp, nval) this_percpu_xchg_op(pcp, nval)
+#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
-#define this_cpu_read_const(pcp) __raw_cpu_read(, pcp)
-#else /* CONFIG_USE_X86_SEG_SUPPORT */
+#define raw_cpu_read_long(pcp) raw_cpu_read_8(pcp)
-#define raw_cpu_read_1(pcp) percpu_from_op(1, , "mov", pcp)
-#define raw_cpu_read_2(pcp) percpu_from_op(2, , "mov", pcp)
-#define raw_cpu_read_4(pcp) percpu_from_op(4, , "mov", pcp)
-#define raw_cpu_write_1(pcp, val) percpu_to_op(1, , "mov", (pcp), val)
-#define raw_cpu_write_2(pcp, val) percpu_to_op(2, , "mov", (pcp), val)
-#define raw_cpu_write_4(pcp, val) percpu_to_op(4, , "mov", (pcp), val)
+#else /* !CONFIG_X86_64: */
-#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp)
-#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp)
-#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp)
-#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val)
-#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val)
-#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val)
+/* There is no generic 64-bit read stable operation for 32-bit targets. */
+#define this_cpu_read_stable_8(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
-#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp)
-#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val)
+#define raw_cpu_read_long(pcp) raw_cpu_read_4(pcp)
-#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
-#endif
+#endif /* CONFIG_X86_64 */
-/*
- * The generic per-cpu infrastrucutre is not suitable for
- * reading const-qualified variables.
- */
-#define this_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
-#endif /* CONFIG_USE_X86_SEG_SUPPORT */
-
-#define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp)
-#define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp)
-#define this_cpu_read_stable_4(pcp) percpu_stable_op(4, "mov", pcp)
-
-#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val)
-#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val)
-#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val)
-#define raw_cpu_and_1(pcp, val) percpu_to_op(1, , "and", (pcp), val)
-#define raw_cpu_and_2(pcp, val) percpu_to_op(2, , "and", (pcp), val)
-#define raw_cpu_and_4(pcp, val) percpu_to_op(4, , "and", (pcp), val)
-#define raw_cpu_or_1(pcp, val) percpu_to_op(1, , "or", (pcp), val)
-#define raw_cpu_or_2(pcp, val) percpu_to_op(2, , "or", (pcp), val)
-#define raw_cpu_or_4(pcp, val) percpu_to_op(4, , "or", (pcp), val)
-#define raw_cpu_xchg_1(pcp, val) raw_percpu_xchg_op(pcp, val)
-#define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val)
-#define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val)
-
-#define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val)
-#define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val)
-#define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val)
-#define this_cpu_and_1(pcp, val) percpu_to_op(1, volatile, "and", (pcp), val)
-#define this_cpu_and_2(pcp, val) percpu_to_op(2, volatile, "and", (pcp), val)
-#define this_cpu_and_4(pcp, val) percpu_to_op(4, volatile, "and", (pcp), val)
-#define this_cpu_or_1(pcp, val) percpu_to_op(1, volatile, "or", (pcp), val)
-#define this_cpu_or_2(pcp, val) percpu_to_op(2, volatile, "or", (pcp), val)
-#define this_cpu_or_4(pcp, val) percpu_to_op(4, volatile, "or", (pcp), val)
-#define this_cpu_xchg_1(pcp, nval) this_percpu_xchg_op(pcp, nval)
-#define this_cpu_xchg_2(pcp, nval) this_percpu_xchg_op(pcp, nval)
-#define this_cpu_xchg_4(pcp, nval) this_percpu_xchg_op(pcp, nval)
-
-#define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val)
-#define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val)
-#define raw_cpu_add_return_4(pcp, val) percpu_add_return_op(4, , pcp, val)
-#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval)
-#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval)
-#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval)
-#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, , pcp, ovalp, nval)
-#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, , pcp, ovalp, nval)
-#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, , pcp, ovalp, nval)
-
-#define this_cpu_add_return_1(pcp, val) percpu_add_return_op(1, volatile, pcp, val)
-#define this_cpu_add_return_2(pcp, val) percpu_add_return_op(2, volatile, pcp, val)
-#define this_cpu_add_return_4(pcp, val) percpu_add_return_op(4, volatile, pcp, val)
-#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
-#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
-#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
-#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval)
-#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval)
-#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval)
+#define this_cpu_read_const(pcp) __raw_cpu_read_const(pcp)
/*
- * Per cpu atomic 64 bit operations are only available under 64 bit.
- * 32 bit must fall back to generic operations.
+ * this_cpu_read() makes the compiler load the per-CPU variable every time
+ * it is accessed while this_cpu_read_stable() allows the value to be cached.
+ * this_cpu_read_stable() is more efficient and can be used if its value
+ * is guaranteed to be valid across CPUs. The current users include
+ * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * actually per-thread variables implemented as per-CPU variables and
+ * thus stable for the duration of the respective task.
*/
-#ifdef CONFIG_X86_64
-#define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp)
-
-#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val)
-#define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val)
-#define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val)
-#define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(8, , pcp, val)
-#define raw_cpu_xchg_8(pcp, nval) raw_percpu_xchg_op(pcp, nval)
-#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval)
-#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
-
-#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val)
-#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
-#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
-#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
-#define this_cpu_xchg_8(pcp, nval) this_percpu_xchg_op(pcp, nval)
-#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
-#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
-
-#define raw_cpu_read_long(pcp) raw_cpu_read_8(pcp)
-#else
-/* There is no generic 64 bit read stable operation for 32 bit targets. */
-#define this_cpu_read_stable_8(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
-
-#define raw_cpu_read_long(pcp) raw_cpu_read_4(pcp)
-#endif
+#define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp)
#define x86_this_cpu_constant_test_bit(_nr, _var) \
({ \
unsigned long __percpu *addr__ = \
(unsigned long __percpu *)&(_var) + ((_nr) / BITS_PER_LONG); \
+ \
!!((1UL << ((_nr) % BITS_PER_LONG)) & raw_cpu_read(*addr__)); \
})
-#define x86_this_cpu_variable_test_bit(_nr, _var) \
-({ \
- bool oldbit; \
- \
- asm volatile("btl %[nr], " __percpu_arg([var]) \
- CC_SET(c) \
- : CC_OUT(c) (oldbit) \
- : [var] "m" (__my_cpu_var(_var)), \
- [nr] "rI" (_nr)); \
- oldbit; \
+#define x86_this_cpu_variable_test_bit(_nr, _var) \
+({ \
+ bool oldbit; \
+ \
+ asm volatile("btl %[nr], " __percpu_arg([var]) \
+ CC_SET(c) \
+ : CC_OUT(c) (oldbit) \
+ : [var] "m" (__my_cpu_var(_var)), \
+ [nr] "rI" (_nr)); \
+ oldbit; \
})
-#define x86_this_cpu_test_bit(_nr, _var) \
- (__builtin_constant_p(_nr) \
- ? x86_this_cpu_constant_test_bit(_nr, _var) \
+#define x86_this_cpu_test_bit(_nr, _var) \
+ (__builtin_constant_p(_nr) \
+ ? x86_this_cpu_constant_test_bit(_nr, _var) \
: x86_this_cpu_variable_test_bit(_nr, _var))
@@ -618,46 +640,47 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
{ [0 ... NR_CPUS-1] = _initvalue }; \
__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
-#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
EXPORT_PER_CPU_SYMBOL(_name)
-#define DECLARE_EARLY_PER_CPU(_type, _name) \
- DECLARE_PER_CPU(_type, _name); \
- extern __typeof__(_type) *_name##_early_ptr; \
+#define DECLARE_EARLY_PER_CPU(_type, _name) \
+ DECLARE_PER_CPU(_type, _name); \
+ extern __typeof__(_type) *_name##_early_ptr; \
extern __typeof__(_type) _name##_early_map[]
-#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name) \
- DECLARE_PER_CPU_READ_MOSTLY(_type, _name); \
- extern __typeof__(_type) *_name##_early_ptr; \
+#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name) \
+ DECLARE_PER_CPU_READ_MOSTLY(_type, _name); \
+ extern __typeof__(_type) *_name##_early_ptr; \
extern __typeof__(_type) _name##_early_map[]
-#define early_per_cpu_ptr(_name) (_name##_early_ptr)
-#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
-#define early_per_cpu(_name, _cpu) \
- *(early_per_cpu_ptr(_name) ? \
- &early_per_cpu_ptr(_name)[_cpu] : \
+#define early_per_cpu_ptr(_name) (_name##_early_ptr)
+#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
+
+#define early_per_cpu(_name, _cpu) \
+ *(early_per_cpu_ptr(_name) ? \
+ &early_per_cpu_ptr(_name)[_cpu] : \
&per_cpu(_name, _cpu))
-#else /* !CONFIG_SMP */
-#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
+#else /* !CONFIG_SMP: */
+#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
DEFINE_PER_CPU(_type, _name) = _initvalue
#define DEFINE_EARLY_PER_CPU_READ_MOSTLY(_type, _name, _initvalue) \
DEFINE_PER_CPU_READ_MOSTLY(_type, _name) = _initvalue
-#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
EXPORT_PER_CPU_SYMBOL(_name)
-#define DECLARE_EARLY_PER_CPU(_type, _name) \
+#define DECLARE_EARLY_PER_CPU(_type, _name) \
DECLARE_PER_CPU(_type, _name)
-#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name) \
+#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name) \
DECLARE_PER_CPU_READ_MOSTLY(_type, _name)
-#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
-#define early_per_cpu_ptr(_name) NULL
+#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
+#define early_per_cpu_ptr(_name) NULL
/* no early_per_cpu_map() */
-#endif /* !CONFIG_SMP */
+#endif /* !CONFIG_SMP */
#endif /* _ASM_X86_PERCPU_H */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 7f1e17250546..91b73571412f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -32,6 +32,8 @@
#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23)
#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
#define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35)
+#define ARCH_PERFMON_EVENTSEL_EQ (1ULL << 36)
+#define ARCH_PERFMON_EVENTSEL_UMASK2 (0xFFULL << 40)
#define INTEL_FIXED_BITS_MASK 0xFULL
#define INTEL_FIXED_BITS_STRIDE 4
@@ -185,6 +187,8 @@ union cpuid10_edx {
* detection/enumeration details:
*/
#define ARCH_PERFMON_EXT_LEAF 0x00000023
+#define ARCH_PERFMON_EXT_UMASK2 0x1
+#define ARCH_PERFMON_EXT_EQ 0x2
#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1
#define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1
@@ -307,6 +311,10 @@ struct x86_pmu_capability {
#define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3)
#define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS)
+/* TOPDOWN_BAD_SPECULATION.ALL: fixed counter 4 (Atom only) */
+/* TOPDOWN_FE_BOUND.ALL: fixed counter 5 (Atom only) */
+/* TOPDOWN_RETIRING.ALL: fixed counter 6 (Atom only) */
+
static inline bool use_fixed_pseudo_encoding(u64 code)
{
return !(code & 0xff);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 65b8e5bb902c..e39311a89bf4 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -140,6 +140,11 @@ static inline int pte_young(pte_t pte)
return pte_flags(pte) & _PAGE_ACCESSED;
}
+static inline bool pte_decrypted(pte_t pte)
+{
+ return cc_mkdec(pte_val(pte)) == pte_val(pte);
+}
+
#define pmd_dirty pmd_dirty
static inline bool pmd_dirty(pmd_t pmd)
{
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b78644962626..2f321137736c 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -549,6 +549,7 @@ enum pg_level {
PG_LEVEL_2M,
PG_LEVEL_1G,
PG_LEVEL_512G,
+ PG_LEVEL_256T,
PG_LEVEL_NUM
};
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cb4f6c513c48..a75a07f4931f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -692,7 +692,17 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu)
#ifdef CONFIG_CPU_SUP_AMD
extern u32 amd_get_highest_perf(void);
-extern void amd_clear_divider(void);
+
+/*
+ * Issue a DIV 0/1 insn to clear any division data from previous DIV
+ * operations.
+ */
+static __always_inline void amd_clear_divider(void)
+{
+ asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0)
+ :: "a" (0), "d" (0), "r" (1));
+}
+
extern void amd_check_microcode(void);
#else
static inline u32 amd_get_highest_perf(void) { return 0; }
diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
new file mode 100644
index 000000000000..24e3a53ca255
--- /dev/null
+++ b/arch/x86/include/asm/runtime-const.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RUNTIME_CONST_H
+#define _ASM_RUNTIME_CONST_H
+
+#define runtime_const_ptr(sym) ({ \
+ typeof(sym) __ret; \
+ asm_inline("mov %1,%0\n1:\n" \
+ ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \
+ ".long 1b - %c2 - .\n\t" \
+ ".popsection" \
+ :"=r" (__ret) \
+ :"i" ((unsigned long)0x0123456789abcdefull), \
+ "i" (sizeof(long))); \
+ __ret; })
+
+// The 'typeof' will create at _least_ a 32-bit type, but
+// will happily also take a bigger type and the 'shrl' will
+// clear the upper bits
+#define runtime_const_shift_right_32(val, sym) ({ \
+ typeof(0u+(val)) __ret = (val); \
+ asm_inline("shrl $12,%k0\n1:\n" \
+ ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \
+ ".long 1b - 1 - .\n\t" \
+ ".popsection" \
+ :"+r" (__ret)); \
+ __ret; })
+
+#define runtime_const_init(type, sym) do { \
+ extern s32 __start_runtime_##type##_##sym[]; \
+ extern s32 __stop_runtime_##type##_##sym[]; \
+ runtime_const_fixup(__runtime_fixup_##type, \
+ (unsigned long)(sym), \
+ __start_runtime_##type##_##sym, \
+ __stop_runtime_##type##_##sym); \
+} while (0)
+
+/*
+ * The text patching is trivial - you can only do this at init time,
+ * when the text section hasn't been marked RO, and before the text
+ * has ever been executed.
+ */
+static inline void __runtime_fixup_ptr(void *where, unsigned long val)
+{
+ *(unsigned long *)where = val;
+}
+
+static inline void __runtime_fixup_shift(void *where, unsigned long val)
+{
+ *(unsigned char *)where = val;
+}
+
+static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
+ unsigned long val, s32 *start, s32 *end)
+{
+ while (start < end) {
+ fn(*start + (void *)start, val);
+ start++;
+ }
+}
+
+#endif
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 9aee31862b4a..4b2abce2e3e7 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -49,8 +49,11 @@ int set_memory_wb(unsigned long addr, int numpages);
int set_memory_np(unsigned long addr, int numpages);
int set_memory_p(unsigned long addr, int numpages);
int set_memory_4k(unsigned long addr, int numpages);
+
+bool set_memory_enc_stop_conversion(void);
int set_memory_encrypted(unsigned long addr, int numpages);
int set_memory_decrypted(unsigned long addr, int numpages);
+
int set_memory_np_noalias(unsigned long addr, int numpages);
int set_memory_nonglobal(unsigned long addr, int numpages);
int set_memory_global(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index e61e68d71cba..0667b2a88614 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -28,6 +28,8 @@
#define NEW_CL_POINTER 0x228 /* Relative to real mode data */
#ifndef __ASSEMBLY__
+#include <linux/cache.h>
+
#include <asm/bootparam.h>
#include <asm/x86_init.h>
@@ -133,6 +135,12 @@ asmlinkage void __init __noreturn x86_64_start_reservations(char *real_mode_data
#endif /* __i386__ */
#endif /* _SETUP */
+#ifdef CONFIG_CMDLINE_BOOL
+extern bool builtin_cmdline_added __ro_after_init;
+#else
+#define builtin_cmdline_added 0
+#endif
+
#else /* __ASSEMBLY */
.macro __RESERVE_BRK name, size
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 5a8246dd532f..98726c2b04f8 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -59,6 +59,14 @@
#define GHCB_MSR_AP_RESET_HOLD_RESULT_POS 12
#define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK GENMASK_ULL(51, 0)
+/* Preferred GHCB GPA Request */
+#define GHCB_MSR_PREF_GPA_REQ 0x010
+#define GHCB_MSR_GPA_VALUE_POS 12
+#define GHCB_MSR_GPA_VALUE_MASK GENMASK_ULL(51, 0)
+
+#define GHCB_MSR_PREF_GPA_RESP 0x011
+#define GHCB_MSR_PREF_GPA_NONE 0xfffffffffffff
+
/* GHCB GPA Register */
#define GHCB_MSR_REG_GPA_REQ 0x012
#define GHCB_MSR_REG_GPA_REQ_VAL(v) \
@@ -93,11 +101,30 @@ enum psc_op {
/* GHCBData[11:0] */ \
GHCB_MSR_PSC_REQ)
+#define GHCB_MSR_PSC_REQ_TO_GFN(msr) (((msr) & GENMASK_ULL(51, 12)) >> 12)
+#define GHCB_MSR_PSC_REQ_TO_OP(msr) (((msr) & GENMASK_ULL(55, 52)) >> 52)
+
#define GHCB_MSR_PSC_RESP 0x015
#define GHCB_MSR_PSC_RESP_VAL(val) \
/* GHCBData[63:32] */ \
(((u64)(val) & GENMASK_ULL(63, 32)) >> 32)
+/* Set highest bit as a generic error response */
+#define GHCB_MSR_PSC_RESP_ERROR (BIT_ULL(63) | GHCB_MSR_PSC_RESP)
+
+/* GHCB Run at VMPL Request/Response */
+#define GHCB_MSR_VMPL_REQ 0x016
+#define GHCB_MSR_VMPL_REQ_LEVEL(v) \
+ /* GHCBData[39:32] */ \
+ (((u64)(v) & GENMASK_ULL(7, 0) << 32) | \
+ /* GHCBDdata[11:0] */ \
+ GHCB_MSR_VMPL_REQ)
+
+#define GHCB_MSR_VMPL_RESP 0x017
+#define GHCB_MSR_VMPL_RESP_VAL(v) \
+ /* GHCBData[63:32] */ \
+ (((u64)(v) & GENMASK_ULL(63, 32)) >> 32)
+
/* GHCB Hypervisor Feature Request/Response */
#define GHCB_MSR_HV_FT_REQ 0x080
#define GHCB_MSR_HV_FT_RESP 0x081
@@ -109,14 +136,26 @@ enum psc_op {
#define GHCB_HV_FT_SNP BIT_ULL(0)
#define GHCB_HV_FT_SNP_AP_CREATION BIT_ULL(1)
+#define GHCB_HV_FT_SNP_MULTI_VMPL BIT_ULL(5)
/*
* SNP Page State Change NAE event
* The VMGEXIT_PSC_MAX_ENTRY determines the size of the PSC structure, which
* is a local stack variable in set_pages_state(). Do not increase this value
* without evaluating the impact to stack usage.
+ *
+ * Use VMGEXIT_PSC_MAX_COUNT in cases where the actual GHCB-defined max value
+ * is needed, such as when processing GHCB requests on the hypervisor side.
*/
#define VMGEXIT_PSC_MAX_ENTRY 64
+#define VMGEXIT_PSC_MAX_COUNT 253
+
+#define VMGEXIT_PSC_ERROR_GENERIC (0x100UL << 32)
+#define VMGEXIT_PSC_ERROR_INVALID_HDR ((1UL << 32) | 1)
+#define VMGEXIT_PSC_ERROR_INVALID_ENTRY ((1UL << 32) | 2)
+
+#define VMGEXIT_PSC_OP_PRIVATE 1
+#define VMGEXIT_PSC_OP_SHARED 2
struct psc_hdr {
u16 cur_entry;
@@ -163,6 +202,10 @@ struct snp_psc_desc {
#define GHCB_TERM_NOT_VMPL0 3 /* SNP guest is not running at VMPL-0 */
#define GHCB_TERM_CPUID 4 /* CPUID-validation failure */
#define GHCB_TERM_CPUID_HV 5 /* CPUID failure during hypervisor fallback */
+#define GHCB_TERM_SECRETS_PAGE 6 /* Secrets page failure */
+#define GHCB_TERM_NO_SVSM 7 /* SVSM is not advertised in the secrets page */
+#define GHCB_TERM_SVSM_VMPL0 8 /* SVSM is present but has set VMPL to 0 */
+#define GHCB_TERM_SVSM_CAA 9 /* SVSM is present but CAA is not page aligned */
#define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ca20cc4e5826..79bbe2be900e 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -91,6 +91,9 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
/* RMUPDATE detected 4K page and 2MB page overlap. */
#define RMPUPDATE_FAIL_OVERLAP 4
+/* PSMASH failed due to concurrent access by another CPU */
+#define PSMASH_FAIL_INUSE 3
+
/* RMP page size */
#define RMP_PG_SIZE_4K 0
#define RMP_PG_SIZE_2M 1
@@ -116,6 +119,54 @@ struct snp_req_data {
unsigned int data_npages;
};
+#define MAX_AUTHTAG_LEN 32
+
+/* See SNP spec SNP_GUEST_REQUEST section for the structure */
+enum msg_type {
+ SNP_MSG_TYPE_INVALID = 0,
+ SNP_MSG_CPUID_REQ,
+ SNP_MSG_CPUID_RSP,
+ SNP_MSG_KEY_REQ,
+ SNP_MSG_KEY_RSP,
+ SNP_MSG_REPORT_REQ,
+ SNP_MSG_REPORT_RSP,
+ SNP_MSG_EXPORT_REQ,
+ SNP_MSG_EXPORT_RSP,
+ SNP_MSG_IMPORT_REQ,
+ SNP_MSG_IMPORT_RSP,
+ SNP_MSG_ABSORB_REQ,
+ SNP_MSG_ABSORB_RSP,
+ SNP_MSG_VMRK_REQ,
+ SNP_MSG_VMRK_RSP,
+
+ SNP_MSG_TYPE_MAX
+};
+
+enum aead_algo {
+ SNP_AEAD_INVALID,
+ SNP_AEAD_AES_256_GCM,
+};
+
+struct snp_guest_msg_hdr {
+ u8 authtag[MAX_AUTHTAG_LEN];
+ u64 msg_seqno;
+ u8 rsvd1[8];
+ u8 algo;
+ u8 hdr_version;
+ u16 hdr_sz;
+ u8 msg_type;
+ u8 msg_version;
+ u16 msg_sz;
+ u32 rsvd2;
+ u8 msg_vmpck;
+ u8 rsvd3[35];
+} __packed;
+
+struct snp_guest_msg {
+ struct snp_guest_msg_hdr hdr;
+ u8 payload[4000];
+} __packed;
+
struct sev_guest_platform_data {
u64 secrets_gpa;
};
@@ -152,10 +203,119 @@ struct snp_secrets_page {
u8 vmpck2[VMPCK_KEY_LEN];
u8 vmpck3[VMPCK_KEY_LEN];
struct secrets_os_area os_area;
- u8 rsvd3[3840];
+
+ u8 vmsa_tweak_bitmap[64];
+
+ /* SVSM fields */
+ u64 svsm_base;
+ u64 svsm_size;
+ u64 svsm_caa;
+ u32 svsm_max_version;
+ u8 svsm_guest_vmpl;
+ u8 rsvd3[3];
+
+ /* Remainder of page */
+ u8 rsvd4[3744];
} __packed;
+/*
+ * The SVSM Calling Area (CA) related structures.
+ */
+struct svsm_ca {
+ u8 call_pending;
+ u8 mem_available;
+ u8 rsvd1[6];
+
+ u8 svsm_buffer[PAGE_SIZE - 8];
+};
+
+#define SVSM_SUCCESS 0
+#define SVSM_ERR_INCOMPLETE 0x80000000
+#define SVSM_ERR_UNSUPPORTED_PROTOCOL 0x80000001
+#define SVSM_ERR_UNSUPPORTED_CALL 0x80000002
+#define SVSM_ERR_INVALID_ADDRESS 0x80000003
+#define SVSM_ERR_INVALID_FORMAT 0x80000004
+#define SVSM_ERR_INVALID_PARAMETER 0x80000005
+#define SVSM_ERR_INVALID_REQUEST 0x80000006
+#define SVSM_ERR_BUSY 0x80000007
+#define SVSM_PVALIDATE_FAIL_SIZEMISMATCH 0x80001006
+
+/*
+ * The SVSM PVALIDATE related structures
+ */
+struct svsm_pvalidate_entry {
+ u64 page_size : 2,
+ action : 1,
+ ignore_cf : 1,
+ rsvd : 8,
+ pfn : 52;
+};
+
+struct svsm_pvalidate_call {
+ u16 num_entries;
+ u16 cur_index;
+
+ u8 rsvd1[4];
+
+ struct svsm_pvalidate_entry entry[];
+};
+
+#define SVSM_PVALIDATE_MAX_COUNT ((sizeof_field(struct svsm_ca, svsm_buffer) - \
+ offsetof(struct svsm_pvalidate_call, entry)) / \
+ sizeof(struct svsm_pvalidate_entry))
+
+/*
+ * The SVSM Attestation related structures
+ */
+struct svsm_loc_entry {
+ u64 pa;
+ u32 len;
+ u8 rsvd[4];
+};
+
+struct svsm_attest_call {
+ struct svsm_loc_entry report_buf;
+ struct svsm_loc_entry nonce;
+ struct svsm_loc_entry manifest_buf;
+ struct svsm_loc_entry certificates_buf;
+
+ /* For attesting a single service */
+ u8 service_guid[16];
+ u32 service_manifest_ver;
+ u8 rsvd[4];
+};
+
+/*
+ * SVSM protocol structure
+ */
+struct svsm_call {
+ struct svsm_ca *caa;
+ u64 rax;
+ u64 rcx;
+ u64 rdx;
+ u64 r8;
+ u64 r9;
+ u64 rax_out;
+ u64 rcx_out;
+ u64 rdx_out;
+ u64 r8_out;
+ u64 r9_out;
+};
+
+#define SVSM_CORE_CALL(x) ((0ULL << 32) | (x))
+#define SVSM_CORE_REMAP_CA 0
+#define SVSM_CORE_PVALIDATE 1
+#define SVSM_CORE_CREATE_VCPU 2
+#define SVSM_CORE_DELETE_VCPU 3
+
+#define SVSM_ATTEST_CALL(x) ((1ULL << 32) | (x))
+#define SVSM_ATTEST_SERVICES 0
+#define SVSM_ATTEST_SINGLE_SERVICE 1
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
+
+extern u8 snp_vmpl;
+
extern void __sev_es_ist_enter(struct pt_regs *regs);
extern void __sev_es_ist_exit(void);
static __always_inline void sev_es_ist_enter(struct pt_regs *regs)
@@ -181,6 +341,14 @@ static __always_inline void sev_es_nmi_complete(void)
extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
extern void sev_enable(struct boot_params *bp);
+/*
+ * RMPADJUST modifies the RMP permissions of a page of a lesser-
+ * privileged (numerically higher) VMPL.
+ *
+ * If the guest is running at a higher-privilege than the privilege
+ * level the instruction is targeting, the instruction will succeed,
+ * otherwise, it will fail.
+ */
static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs)
{
int rc;
@@ -225,11 +393,16 @@ bool snp_init(struct boot_params *bp);
void __noreturn snp_abort(void);
void snp_dmi_setup(void);
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
+int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input);
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
u64 snp_get_unsupported_features(u64 status);
u64 sev_get_status(void);
void sev_show_status(void);
-#else
+void snp_update_svsm_ca(void);
+
+#else /* !CONFIG_AMD_MEM_ENCRYPT */
+
+#define snp_vmpl 0
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
static inline void sev_es_ist_exit(void) { }
static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; }
@@ -253,12 +426,17 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
{
return -ENOTTY;
}
-
+static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input)
+{
+ return -ENOTTY;
+}
static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
static inline u64 snp_get_unsupported_features(u64 status) { return 0; }
static inline u64 sev_get_status(void) { return 0; }
static inline void sev_show_status(void) { }
-#endif
+static inline void snp_update_svsm_ca(void) { }
+
+#endif /* CONFIG_AMD_MEM_ENCRYPT */
#ifdef CONFIG_KVM_AMD_SEV
bool snp_probe_rmptable_info(void);
diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index 42fee8959df7..4cb77e004615 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -21,6 +21,8 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clon
void shstk_free(struct task_struct *p);
int setup_signal_shadow_stack(struct ksignal *ksig);
int restore_signal_shadow_stack(void);
+int shstk_update_last_frame(unsigned long val);
+bool shstk_is_enabled(void);
#else
static inline long shstk_prctl(struct task_struct *task, int option,
unsigned long arg2) { return -EINVAL; }
@@ -31,6 +33,8 @@ static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p,
static inline void shstk_free(struct task_struct *p) {}
static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
static inline int restore_signal_shadow_stack(void) { return 0; }
+static inline int shstk_update_last_frame(unsigned long val) { return 0; }
+static inline bool shstk_is_enabled(void) { return false; }
#endif /* CONFIG_X86_USER_SHADOW_STACK */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index a35936b512fe..ca073f40698f 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -35,6 +35,7 @@ struct smp_ops {
int (*cpu_disable)(void);
void (*cpu_die)(unsigned int cpu);
void (*play_dead)(void);
+ void (*stop_this_cpu)(void);
void (*send_call_func_ipi)(const struct cpumask *mask);
void (*send_call_func_single_ipi)(int cpu);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 728c98175b9c..f0dea3750ca9 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -285,7 +285,14 @@ 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)
+#define SVM_SEV_FEAT_SNP_ACTIVE BIT(0)
+#define SVM_SEV_FEAT_RESTRICTED_INJECTION BIT(3)
+#define SVM_SEV_FEAT_ALTERNATE_INJECTION BIT(4)
+#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5)
+
+#define SVM_SEV_FEAT_INT_INJ_MODES \
+ (SVM_SEV_FEAT_RESTRICTED_INJECTION | \
+ SVM_SEV_FEAT_ALTERNATE_INJECTION)
struct vmcb_seg {
u16 selector;
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 405efb3e4996..94408a784c8e 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -28,9 +28,6 @@ static inline cycles_t get_cycles(void)
}
#define get_cycles get_cycles
-extern struct system_counterval_t convert_art_to_tsc(u64 art);
-extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns);
-
extern void tsc_early_init(void);
extern void tsc_init(void);
extern void mark_tsc_unstable(char *reason);
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 761173ccc33c..6c9e5bdd3916 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -56,6 +56,5 @@
# define __ARCH_WANT_SYS_FORK
# define __ARCH_WANT_SYS_VFORK
# define __ARCH_WANT_SYS_CLONE
-# define __ARCH_WANT_SYS_CLONE3
#endif /* _ASM_X86_UNISTD_H */
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index 0ef36190abe6..b2d2df026f6e 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -328,9 +328,8 @@ static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles,
* due to unsigned comparison.
*
* Due to the MSB/Sign-bit being used as invalid marker (see
- * arch_vdso_cycles_valid() above), the effective mask is S64_MAX,
- * but that case is also unlikely and will also take the unlikely path
- * here.
+ * arch_vdso_cycles_ok() above), the effective mask is S64_MAX, but that
+ * case is also unlikely and will also take the unlikely path here.
*/
if (unlikely(delta > vd->max_cycles)) {
/*
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
index be199a9b2676..93226281b450 100644
--- a/arch/x86/include/asm/vdso/vsyscall.h
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -4,7 +4,6 @@
#ifndef __ASSEMBLY__
-#include <linux/hrtimer.h>
#include <linux/timekeeper_internal.h>
#include <vdso/datapage.h>
#include <asm/vgtod.h>
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 7aa38b2ad8a9..a0ce291abcae 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -14,11 +14,6 @@
#include <uapi/linux/time.h>
-#ifdef BUILD_VDSO32_64
-typedef u64 gtod_long_t;
-#else
-typedef unsigned long gtod_long_t;
-#endif
#endif /* CONFIG_GENERIC_GETTIMEOFDAY */
#endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..c9cf43d5ef23 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,51 +7,321 @@
#include <linux/stringify.h>
/*
- * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - Low bandwidth TDX hypercalls (x86_64 only) are similar to LB
+ * hypercalls. They also have up to 6 input and 6 output on registers
+ * arguments, with different argument to register mapping:
+ * %r12 (arg0), %rbx (arg1), %r13 (arg2), %rdx (arg3),
+ * %rsi (arg4), %rdi (arg5).
+ *
+ * - High bandwidth (HB) hypercalls are I/O port based only. They have
+ * up to 7 input and 7 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
*
* The new vmcall interface instead uses a set of flags to select
* bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * into arg3 by any user and are automatically replaced by the port
+ * number if the I/O port method is used.
*/
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT 0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB BIT(0)
+#define VMWARE_HYPERVISOR_OUT BIT(1)
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB BIT(0)
-#define VMWARE_HYPERVISOR_OUT BIT(1)
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB (VMWARE_HYPERVISOR_PORT | \
+ VMWARE_HYPERVISOR_HB)
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL \
- ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax", \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
+#define VMWARE_HYPERVISOR_MAGIC 0x564d5868U
+#define VMWARE_CMD_GETVERSION 10
+#define VMWARE_CMD_GETHZ 45
+#define VMWARE_CMD_GETVCPU_INFO 68
+#define VMWARE_CMD_STEALCLOCK 91
/*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * Hypercall command mask:
+ * bits [6:0] command, range [0, 127]
+ * bits [19:16] sub-command, range [0, 15]
*/
-#define VMWARE_HYPERCALL_HB_OUT \
- ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \
- "rep outsb", \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
+#define VMWARE_CMD_MASK 0xf007fU
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
+
+extern unsigned long vmware_hypercall_slow(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5);
+
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC 1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5);
/*
- * The high bandwidth in call. The low word of edx is presumed to have the
- * HB bit set.
+ * The low bandwidth call. The low word of %edx is presumed to have OUT bit
+ * set. The high word of %edx may contain input data from the caller.
*/
-#define VMWARE_HYPERCALL_HB_IN \
- ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \
- "rep insb", \
- "vmcall", X86_FEATURE_VMCALL, \
+#define VMWARE_HYPERCALL \
+ ALTERNATIVE_2("movw %[port], %%dx\n\t" \
+ "inl (%%dx), %%eax", \
+ "vmcall", X86_FEATURE_VMCALL, \
"vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+static inline
+unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
+{
+ unsigned long out0;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ NULL, NULL, NULL, NULL, NULL);
+
+ if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
+ return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
+ NULL, NULL, NULL, NULL, NULL);
+
+ asm_inline volatile (VMWARE_HYPERCALL
+ : "=a" (out0)
+ : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (0)
+ : "cc", "memory");
+ return out0;
+}
+
+static inline
+unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
+ u32 *out1, u32 *out2)
+{
+ unsigned long out0;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, NULL, NULL, NULL);
+
+ if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
+ return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
+ out1, out2, NULL, NULL, NULL);
+
+ asm_inline volatile (VMWARE_HYPERCALL
+ : "=a" (out0), "=b" (*out1), "=c" (*out2)
+ : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (0)
+ : "cc", "memory");
+ return out0;
+}
+
+static inline
+unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1,
+ u32 *out1, u32 *out2, u32 *out3)
+{
+ unsigned long out0;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, out3, NULL, NULL);
+
+ if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
+ return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
+ out1, out2, out3, NULL, NULL);
+
+ asm_inline volatile (VMWARE_HYPERCALL
+ : "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
+ : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (0)
+ : "cc", "memory");
+ return out0;
+}
+
+static inline
+unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1,
+ unsigned long in3, unsigned long in4,
+ unsigned long in5, u32 *out2)
+{
+ unsigned long out0;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ NULL, out2, NULL, NULL, NULL);
+
+ if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
+ return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
+ NULL, out2, NULL, NULL, NULL);
+
+ asm_inline volatile (VMWARE_HYPERCALL
+ : "=a" (out0), "=c" (*out2)
+ : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (in3),
+ "S" (in4),
+ "D" (in5)
+ : "cc", "memory");
+ return out0;
+}
+
+static inline
+unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1,
+ unsigned long in3, u32 *out2,
+ u32 *out3, u32 *out4, u32 *out5)
+{
+ unsigned long out0;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, 0, 0,
+ NULL, out2, out3, out4, out5);
+
+ if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
+ return vmware_hypercall_slow(cmd, in1, in3, 0, 0,
+ NULL, out2, out3, out4, out5);
+
+ asm_inline volatile (VMWARE_HYPERCALL
+ : "=a" (out0), "=c" (*out2), "=d" (*out3), "=S" (*out4),
+ "=D" (*out5)
+ : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (in3)
+ : "cc", "memory");
+ return out0;
+}
+
+static inline
+unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1,
+ unsigned long in3, unsigned long in4,
+ unsigned long in5, u32 *out1,
+ u32 *out2, u32 *out3)
+{
+ unsigned long out0;
+
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ out1, out2, out3, NULL, NULL);
+
+ if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
+ return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
+ out1, out2, out3, NULL, NULL);
+
+ asm_inline volatile (VMWARE_HYPERCALL
+ : "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
+ : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (in3),
+ "S" (in4),
+ "D" (in5)
+ : "cc", "memory");
+ return out0;
+}
+
+#ifdef CONFIG_X86_64
+#define VMW_BP_CONSTRAINT "r"
+#else
+#define VMW_BP_CONSTRAINT "m"
+#endif
+
+/*
+ * High bandwidth calls are not supported on encrypted memory guests.
+ * The caller should check cc_platform_has(CC_ATTR_MEM_ENCRYPT) and use
+ * low bandwidth hypercall if memory encryption is set.
+ * This assumption simplifies HB hypercall implementation to just I/O port
+ * based approach without alternative patching.
+ */
+static inline
+unsigned long vmware_hypercall_hb_out(unsigned long cmd, unsigned long in2,
+ unsigned long in3, unsigned long in4,
+ unsigned long in5, unsigned long in6,
+ u32 *out1)
+{
+ unsigned long out0;
+
+ asm_inline volatile (
+ UNWIND_HINT_SAVE
+ "push %%" _ASM_BP "\n\t"
+ UNWIND_HINT_UNDEFINED
+ "mov %[in6], %%" _ASM_BP "\n\t"
+ "rep outsb\n\t"
+ "pop %%" _ASM_BP "\n\t"
+ UNWIND_HINT_RESTORE
+ : "=a" (out0), "=b" (*out1)
+ : "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (cmd),
+ "c" (in2),
+ "d" (in3 | VMWARE_HYPERVISOR_PORT_HB),
+ "S" (in4),
+ "D" (in5),
+ [in6] VMW_BP_CONSTRAINT (in6)
+ : "cc", "memory");
+ return out0;
+}
+
+static inline
+unsigned long vmware_hypercall_hb_in(unsigned long cmd, unsigned long in2,
+ unsigned long in3, unsigned long in4,
+ unsigned long in5, unsigned long in6,
+ u32 *out1)
+{
+ unsigned long out0;
+
+ asm_inline volatile (
+ UNWIND_HINT_SAVE
+ "push %%" _ASM_BP "\n\t"
+ UNWIND_HINT_UNDEFINED
+ "mov %[in6], %%" _ASM_BP "\n\t"
+ "rep insb\n\t"
+ "pop %%" _ASM_BP "\n\t"
+ UNWIND_HINT_RESTORE
+ : "=a" (out0), "=b" (*out1)
+ : "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (cmd),
+ "c" (in2),
+ "d" (in3 | VMWARE_HYPERVISOR_PORT_HB),
+ "S" (in4),
+ "D" (in5),
+ [in6] VMW_BP_CONSTRAINT (in6)
+ : "cc", "memory");
+ return out0;
+}
+#undef VMW_BP_CONSTRAINT
+#undef VMWARE_HYPERCALL
+
#endif
diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h
index 695f36664889..09b1d7e607c1 100644
--- a/arch/x86/include/asm/vmxfeatures.h
+++ b/arch/x86/include/asm/vmxfeatures.h
@@ -9,85 +9,85 @@
/*
* Note: If the comment begins with a quoted string, that string is used
- * in /proc/cpuinfo instead of the macro name. If the string is "",
- * this feature bit is not displayed in /proc/cpuinfo at all.
+ * in /proc/cpuinfo instead of the macro name. Otherwise, this feature bit
+ * is not displayed in /proc/cpuinfo at all.
*/
/* Pin-Based VM-Execution Controls, EPT/VPID, APIC and VM-Functions, word 0 */
-#define VMX_FEATURE_INTR_EXITING ( 0*32+ 0) /* "" VM-Exit on vectored interrupts */
-#define VMX_FEATURE_NMI_EXITING ( 0*32+ 3) /* "" VM-Exit on NMIs */
+#define VMX_FEATURE_INTR_EXITING ( 0*32+ 0) /* VM-Exit on vectored interrupts */
+#define VMX_FEATURE_NMI_EXITING ( 0*32+ 3) /* VM-Exit on NMIs */
#define VMX_FEATURE_VIRTUAL_NMIS ( 0*32+ 5) /* "vnmi" NMI virtualization */
-#define VMX_FEATURE_PREEMPTION_TIMER ( 0*32+ 6) /* VMX Preemption Timer */
-#define VMX_FEATURE_POSTED_INTR ( 0*32+ 7) /* Posted Interrupts */
+#define VMX_FEATURE_PREEMPTION_TIMER ( 0*32+ 6) /* "preemption_timer" VMX Preemption Timer */
+#define VMX_FEATURE_POSTED_INTR ( 0*32+ 7) /* "posted_intr" Posted Interrupts */
/* EPT/VPID features, scattered to bits 16-23 */
-#define VMX_FEATURE_INVVPID ( 0*32+ 16) /* INVVPID is supported */
+#define VMX_FEATURE_INVVPID ( 0*32+ 16) /* "invvpid" INVVPID is supported */
#define VMX_FEATURE_EPT_EXECUTE_ONLY ( 0*32+ 17) /* "ept_x_only" EPT entries can be execute only */
-#define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* EPT Accessed/Dirty bits */
-#define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* 1GB EPT pages */
-#define VMX_FEATURE_EPT_5LEVEL ( 0*32+ 20) /* 5-level EPT paging */
+#define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* "ept_ad" EPT Accessed/Dirty bits */
+#define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* "ept_1gb" 1GB EPT pages */
+#define VMX_FEATURE_EPT_5LEVEL ( 0*32+ 20) /* "ept_5level" 5-level EPT paging */
/* Aggregated APIC features 24-27 */
-#define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* TPR shadow + virt APIC */
-#define VMX_FEATURE_APICV ( 0*32+ 25) /* TPR shadow + APIC reg virt + virt intr delivery + posted interrupts */
+#define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* "flexpriority" TPR shadow + virt APIC */
+#define VMX_FEATURE_APICV ( 0*32+ 25) /* "apicv" TPR shadow + APIC reg virt + virt intr delivery + posted interrupts */
/* VM-Functions, shifted to bits 28-31 */
-#define VMX_FEATURE_EPTP_SWITCHING ( 0*32+ 28) /* EPTP switching (in guest) */
+#define VMX_FEATURE_EPTP_SWITCHING ( 0*32+ 28) /* "eptp_switching" EPTP switching (in guest) */
/* Primary Processor-Based VM-Execution Controls, word 1 */
-#define VMX_FEATURE_INTR_WINDOW_EXITING ( 1*32+ 2) /* "" VM-Exit if INTRs are unblocked in guest */
+#define VMX_FEATURE_INTR_WINDOW_EXITING ( 1*32+ 2) /* VM-Exit if INTRs are unblocked in guest */
#define VMX_FEATURE_USE_TSC_OFFSETTING ( 1*32+ 3) /* "tsc_offset" Offset hardware TSC when read in guest */
-#define VMX_FEATURE_HLT_EXITING ( 1*32+ 7) /* "" VM-Exit on HLT */
-#define VMX_FEATURE_INVLPG_EXITING ( 1*32+ 9) /* "" VM-Exit on INVLPG */
-#define VMX_FEATURE_MWAIT_EXITING ( 1*32+ 10) /* "" VM-Exit on MWAIT */
-#define VMX_FEATURE_RDPMC_EXITING ( 1*32+ 11) /* "" VM-Exit on RDPMC */
-#define VMX_FEATURE_RDTSC_EXITING ( 1*32+ 12) /* "" VM-Exit on RDTSC */
-#define VMX_FEATURE_CR3_LOAD_EXITING ( 1*32+ 15) /* "" VM-Exit on writes to CR3 */
-#define VMX_FEATURE_CR3_STORE_EXITING ( 1*32+ 16) /* "" VM-Exit on reads from CR3 */
-#define VMX_FEATURE_TERTIARY_CONTROLS ( 1*32+ 17) /* "" Enable Tertiary VM-Execution Controls */
-#define VMX_FEATURE_CR8_LOAD_EXITING ( 1*32+ 19) /* "" VM-Exit on writes to CR8 */
-#define VMX_FEATURE_CR8_STORE_EXITING ( 1*32+ 20) /* "" VM-Exit on reads from CR8 */
+#define VMX_FEATURE_HLT_EXITING ( 1*32+ 7) /* VM-Exit on HLT */
+#define VMX_FEATURE_INVLPG_EXITING ( 1*32+ 9) /* VM-Exit on INVLPG */
+#define VMX_FEATURE_MWAIT_EXITING ( 1*32+ 10) /* VM-Exit on MWAIT */
+#define VMX_FEATURE_RDPMC_EXITING ( 1*32+ 11) /* VM-Exit on RDPMC */
+#define VMX_FEATURE_RDTSC_EXITING ( 1*32+ 12) /* VM-Exit on RDTSC */
+#define VMX_FEATURE_CR3_LOAD_EXITING ( 1*32+ 15) /* VM-Exit on writes to CR3 */
+#define VMX_FEATURE_CR3_STORE_EXITING ( 1*32+ 16) /* VM-Exit on reads from CR3 */
+#define VMX_FEATURE_TERTIARY_CONTROLS ( 1*32+ 17) /* Enable Tertiary VM-Execution Controls */
+#define VMX_FEATURE_CR8_LOAD_EXITING ( 1*32+ 19) /* VM-Exit on writes to CR8 */
+#define VMX_FEATURE_CR8_STORE_EXITING ( 1*32+ 20) /* VM-Exit on reads from CR8 */
#define VMX_FEATURE_VIRTUAL_TPR ( 1*32+ 21) /* "vtpr" TPR virtualization, a.k.a. TPR shadow */
-#define VMX_FEATURE_NMI_WINDOW_EXITING ( 1*32+ 22) /* "" VM-Exit if NMIs are unblocked in guest */
-#define VMX_FEATURE_MOV_DR_EXITING ( 1*32+ 23) /* "" VM-Exit on accesses to debug registers */
-#define VMX_FEATURE_UNCOND_IO_EXITING ( 1*32+ 24) /* "" VM-Exit on *all* IN{S} and OUT{S}*/
-#define VMX_FEATURE_USE_IO_BITMAPS ( 1*32+ 25) /* "" VM-Exit based on I/O port */
+#define VMX_FEATURE_NMI_WINDOW_EXITING ( 1*32+ 22) /* VM-Exit if NMIs are unblocked in guest */
+#define VMX_FEATURE_MOV_DR_EXITING ( 1*32+ 23) /* VM-Exit on accesses to debug registers */
+#define VMX_FEATURE_UNCOND_IO_EXITING ( 1*32+ 24) /* VM-Exit on *all* IN{S} and OUT{S}*/
+#define VMX_FEATURE_USE_IO_BITMAPS ( 1*32+ 25) /* VM-Exit based on I/O port */
#define VMX_FEATURE_MONITOR_TRAP_FLAG ( 1*32+ 27) /* "mtf" VMX single-step VM-Exits */
-#define VMX_FEATURE_USE_MSR_BITMAPS ( 1*32+ 28) /* "" VM-Exit based on MSR index */
-#define VMX_FEATURE_MONITOR_EXITING ( 1*32+ 29) /* "" VM-Exit on MONITOR (MWAIT's accomplice) */
-#define VMX_FEATURE_PAUSE_EXITING ( 1*32+ 30) /* "" VM-Exit on PAUSE (unconditionally) */
-#define VMX_FEATURE_SEC_CONTROLS ( 1*32+ 31) /* "" Enable Secondary VM-Execution Controls */
+#define VMX_FEATURE_USE_MSR_BITMAPS ( 1*32+ 28) /* VM-Exit based on MSR index */
+#define VMX_FEATURE_MONITOR_EXITING ( 1*32+ 29) /* VM-Exit on MONITOR (MWAIT's accomplice) */
+#define VMX_FEATURE_PAUSE_EXITING ( 1*32+ 30) /* VM-Exit on PAUSE (unconditionally) */
+#define VMX_FEATURE_SEC_CONTROLS ( 1*32+ 31) /* Enable Secondary VM-Execution Controls */
/* Secondary Processor-Based VM-Execution Controls, word 2 */
#define VMX_FEATURE_VIRT_APIC_ACCESSES ( 2*32+ 0) /* "vapic" Virtualize memory mapped APIC accesses */
-#define VMX_FEATURE_EPT ( 2*32+ 1) /* Extended Page Tables, a.k.a. Two-Dimensional Paging */
-#define VMX_FEATURE_DESC_EXITING ( 2*32+ 2) /* "" VM-Exit on {S,L}*DT instructions */
-#define VMX_FEATURE_RDTSCP ( 2*32+ 3) /* "" Enable RDTSCP in guest */
-#define VMX_FEATURE_VIRTUAL_X2APIC ( 2*32+ 4) /* "" Virtualize X2APIC for the guest */
-#define VMX_FEATURE_VPID ( 2*32+ 5) /* Virtual Processor ID (TLB ASID modifier) */
-#define VMX_FEATURE_WBINVD_EXITING ( 2*32+ 6) /* "" VM-Exit on WBINVD */
-#define VMX_FEATURE_UNRESTRICTED_GUEST ( 2*32+ 7) /* Allow Big Real Mode and other "invalid" states */
+#define VMX_FEATURE_EPT ( 2*32+ 1) /* "ept" Extended Page Tables, a.k.a. Two-Dimensional Paging */
+#define VMX_FEATURE_DESC_EXITING ( 2*32+ 2) /* VM-Exit on {S,L}*DT instructions */
+#define VMX_FEATURE_RDTSCP ( 2*32+ 3) /* Enable RDTSCP in guest */
+#define VMX_FEATURE_VIRTUAL_X2APIC ( 2*32+ 4) /* Virtualize X2APIC for the guest */
+#define VMX_FEATURE_VPID ( 2*32+ 5) /* "vpid" Virtual Processor ID (TLB ASID modifier) */
+#define VMX_FEATURE_WBINVD_EXITING ( 2*32+ 6) /* VM-Exit on WBINVD */
+#define VMX_FEATURE_UNRESTRICTED_GUEST ( 2*32+ 7) /* "unrestricted_guest" Allow Big Real Mode and other "invalid" states */
#define VMX_FEATURE_APIC_REGISTER_VIRT ( 2*32+ 8) /* "vapic_reg" Hardware emulation of reads to the virtual-APIC */
#define VMX_FEATURE_VIRT_INTR_DELIVERY ( 2*32+ 9) /* "vid" Evaluation and delivery of pending virtual interrupts */
#define VMX_FEATURE_PAUSE_LOOP_EXITING ( 2*32+ 10) /* "ple" Conditionally VM-Exit on PAUSE at CPL0 */
-#define VMX_FEATURE_RDRAND_EXITING ( 2*32+ 11) /* "" VM-Exit on RDRAND*/
-#define VMX_FEATURE_INVPCID ( 2*32+ 12) /* "" Enable INVPCID in guest */
-#define VMX_FEATURE_VMFUNC ( 2*32+ 13) /* "" Enable VM-Functions (leaf dependent) */
-#define VMX_FEATURE_SHADOW_VMCS ( 2*32+ 14) /* VMREAD/VMWRITE in guest can access shadow VMCS */
-#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */
-#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* "" VM-Exit on RDSEED */
+#define VMX_FEATURE_RDRAND_EXITING ( 2*32+ 11) /* VM-Exit on RDRAND*/
+#define VMX_FEATURE_INVPCID ( 2*32+ 12) /* Enable INVPCID in guest */
+#define VMX_FEATURE_VMFUNC ( 2*32+ 13) /* Enable VM-Functions (leaf dependent) */
+#define VMX_FEATURE_SHADOW_VMCS ( 2*32+ 14) /* "shadow_vmcs" VMREAD/VMWRITE in guest can access shadow VMCS */
+#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* VM-Exit on ENCLS (leaf dependent) */
+#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* VM-Exit on RDSEED */
#define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */
-#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */
-#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */
-#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */
+#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "ept_violation_ve" Conditionally reflect EPT violations as #VE exceptions */
+#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* Suppress VMX indicators in Processor Trace */
+#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* Enable XSAVES and XRSTORS in guest */
#define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
-#define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */
-#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */
-#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */
-#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */
-#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* "" VM-Exit when bus lock caused */
-#define VMX_FEATURE_NOTIFY_VM_EXITING ( 2*32+ 31) /* VM-Exit when no event windows after notify window */
+#define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* Processor Trace logs GPAs */
+#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* "tsc_scaling" Scale hardware TSC when read in guest */
+#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* "usr_wait_pause" Enable TPAUSE, UMONITOR, UMWAIT in guest */
+#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* VM-Exit on ENCLV (leaf dependent) */
+#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* VM-Exit when bus lock caused */
+#define VMX_FEATURE_NOTIFY_VM_EXITING ( 2*32+ 31) /* "notify_vm_exiting" VM-Exit when no event windows after notify window */
/* Tertiary Processor-Based VM-Execution Controls, word 3 */
-#define VMX_FEATURE_IPI_VIRT ( 3*32+ 4) /* Enable IPI virtualization */
+#define VMX_FEATURE_IPI_VIRT ( 3*32+ 4) /* "ipi_virt" Enable IPI virtualization */
#endif /* _ASM_X86_VMXFEATURES_H */
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index e8d7d4941c4c..422a47746657 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -5,45 +5,12 @@
#include <linux/bitops.h>
#include <linux/wordpart.h>
-/*
- * This is largely generic for little-endian machines, but the
- * optimal byte mask counting is probably going to be something
- * that is architecture-specific. If you have a reliably fast
- * bit count instruction, that might be better than the multiply
- * and shift, for example.
- */
struct word_at_a_time {
const unsigned long one_bits, high_bits;
};
#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
-#ifdef CONFIG_64BIT
-
-/*
- * Jan Achrenius on G+: microoptimized version of
- * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
- * that works for the bytemasks without having to
- * mask them first.
- */
-static inline long count_masked_bytes(unsigned long mask)
-{
- return mask*0x0001020304050608ul >> 56;
-}
-
-#else /* 32-bit case */
-
-/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
-static inline long count_masked_bytes(long mask)
-{
- /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
- long a = (0x0ff0001+mask) >> 23;
- /* Fix the 1 for 00 case */
- return a & mask;
-}
-
-#endif
-
/* Return nonzero if it has a zero */
static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
{
@@ -57,6 +24,22 @@ static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits,
return bits;
}
+#ifdef CONFIG_64BIT
+
+/* Keep the initial has_zero() value for both bitmask and size calc */
+#define create_zero_mask(bits) (bits)
+
+static inline unsigned long zero_bytemask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+#define find_zero(bits) (__ffs(bits) >> 3)
+
+#else
+
+/* Create the final mask for both bytemask and size */
static inline unsigned long create_zero_mask(unsigned long bits)
{
bits = (bits - 1) & ~bits;
@@ -66,11 +49,17 @@ static inline unsigned long create_zero_mask(unsigned long bits)
/* The mask we created is directly usable as a bytemask */
#define zero_bytemask(mask) (mask)
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
static inline unsigned long find_zero(unsigned long mask)
{
- return count_masked_bytes(mask);
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
}
+#endif
+
/*
* Load an unaligned word from kernel space.
*
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 6149eabe200f..213cf5379a5a 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -149,12 +149,22 @@ struct x86_init_acpi {
* @enc_status_change_finish Notify HV after the encryption status of a range is changed
* @enc_tlb_flush_required Returns true if a TLB flush is needed before changing page encryption status
* @enc_cache_flush_required Returns true if a cache flush is needed before changing page encryption status
+ * @enc_kexec_begin Begin the two-step process of converting shared memory back
+ * to private. It stops the new conversions from being started
+ * and waits in-flight conversions to finish, if possible.
+ * @enc_kexec_finish Finish the two-step process of converting shared memory to
+ * private. All memory is private after the call when
+ * the function returns.
+ * It is called on only one CPU while the others are shut down
+ * and with interrupts disabled.
*/
struct x86_guest {
- bool (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc);
- bool (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc);
+ int (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc);
+ int (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc);
bool (*enc_tlb_flush_required)(bool enc);
bool (*enc_cache_flush_required)(void);
+ void (*enc_kexec_begin)(void);
+ void (*enc_kexec_finish)(void);
};
/**
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 9fae1b73b529..bf57a824f722 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -106,6 +106,7 @@ struct kvm_ioapic_state {
#define KVM_RUN_X86_SMM (1 << 0)
#define KVM_RUN_X86_BUS_LOCK (1 << 1)
+#define KVM_RUN_X86_GUEST_MODE (1 << 2)
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
@@ -697,6 +698,11 @@ enum sev_cmd_id {
/* Second time is the charm; improved versions of the above ioctls. */
KVM_SEV_INIT2,
+ /* SNP-specific commands */
+ KVM_SEV_SNP_LAUNCH_START = 100,
+ KVM_SEV_SNP_LAUNCH_UPDATE,
+ KVM_SEV_SNP_LAUNCH_FINISH,
+
KVM_SEV_NR_MAX,
};
@@ -824,6 +830,48 @@ struct kvm_sev_receive_update_data {
__u32 pad2;
};
+struct kvm_sev_snp_launch_start {
+ __u64 policy;
+ __u8 gosvw[16];
+ __u16 flags;
+ __u8 pad0[6];
+ __u64 pad1[4];
+};
+
+/* Kept in sync with firmware values for simplicity. */
+#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1
+#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3
+#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4
+#define KVM_SEV_SNP_PAGE_TYPE_SECRETS 0x5
+#define KVM_SEV_SNP_PAGE_TYPE_CPUID 0x6
+
+struct kvm_sev_snp_launch_update {
+ __u64 gfn_start;
+ __u64 uaddr;
+ __u64 len;
+ __u8 type;
+ __u8 pad0;
+ __u16 flags;
+ __u32 pad1;
+ __u64 pad2[4];
+};
+
+#define KVM_SEV_SNP_ID_BLOCK_SIZE 96
+#define KVM_SEV_SNP_ID_AUTH_SIZE 4096
+#define KVM_SEV_SNP_FINISH_DATA_SIZE 32
+
+struct kvm_sev_snp_launch_finish {
+ __u64 id_block_uaddr;
+ __u64 id_auth_uaddr;
+ __u8 id_block_en;
+ __u8 auth_key_en;
+ __u8 vcek_disabled;
+ __u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE];
+ __u8 pad0[3];
+ __u16 flags;
+ __u64 pad1[4];
+};
+
#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
@@ -874,5 +922,6 @@ struct kvm_hyperv_eventfd {
#define KVM_X86_SW_PROTECTED_VM 1
#define KVM_X86_SEV_VM 2
#define KVM_X86_SEV_ES_VM 3
+#define KVM_X86_SNP_VM 4
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index 80e1df482337..1814b413fd57 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -115,6 +115,7 @@
#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0
#define SVM_VMGEXIT_AP_CREATE 1
#define SVM_VMGEXIT_AP_DESTROY 2
+#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018
#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd
#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe
#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 20a0dd51700a..a847180836e4 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -17,7 +17,6 @@ CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_early_printk.o = -pg
CFLAGS_REMOVE_head64.o = -pg
CFLAGS_REMOVE_head32.o = -pg
-CFLAGS_REMOVE_sev.o = -pg
CFLAGS_REMOVE_rethook.o = -pg
endif
@@ -26,19 +25,16 @@ KASAN_SANITIZE_dumpstack.o := n
KASAN_SANITIZE_dumpstack_$(BITS).o := n
KASAN_SANITIZE_stacktrace.o := n
KASAN_SANITIZE_paravirt.o := n
-KASAN_SANITIZE_sev.o := n
# With some compiler versions the generated code results in boot hangs, caused
# by several compilation units. To be safe, disable all instrumentation.
KCSAN_SANITIZE := n
KMSAN_SANITIZE_head$(BITS).o := n
KMSAN_SANITIZE_nmi.o := n
-KMSAN_SANITIZE_sev.o := n
# If instrumentation of the following files is enabled, boot hangs during
# first second.
KCOV_INSTRUMENT_head$(BITS).o := n
-KCOV_INSTRUMENT_sev.o := n
CFLAGS_irq.o := -I $(src)/../include/asm/trace
@@ -142,8 +138,6 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o
obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o
obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o
-obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o
-
obj-$(CONFIG_CFI_CLANG) += cfi.o
obj-$(CONFIG_CALL_THUNKS) += callthunks.o
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index fc17b3f136fe..842a5f449404 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_ACPI) += boot.o
obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o
obj-$(CONFIG_ACPI_APEI) += apei.o
obj-$(CONFIG_ACPI_CPPC_LIB) += cppc.o
+obj-$(CONFIG_ACPI_MADT_WAKEUP) += madt_wakeup.o madt_playdead.o
ifneq ($(CONFIG_ACPI_PROCESSOR),)
obj-y += cstate.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 4bf82dbd2a6b..9f4618dcd704 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -67,13 +67,6 @@ static bool has_lapic_cpus __initdata;
static bool acpi_support_online_capable;
#endif
-#ifdef CONFIG_X86_64
-/* Physical address of the Multiprocessor Wakeup Structure mailbox */
-static u64 acpi_mp_wake_mailbox_paddr;
-/* Virtual address of the Multiprocessor Wakeup Structure mailbox */
-static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox;
-#endif
-
#ifdef CONFIG_X86_IO_APIC
/*
* Locks related to IOAPIC hotplug
@@ -341,60 +334,6 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e
return 0;
}
-
-#ifdef CONFIG_X86_64
-static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip)
-{
- /*
- * Remap mailbox memory only for the first call to acpi_wakeup_cpu().
- *
- * Wakeup of secondary CPUs is fully serialized in the core code.
- * No need to protect acpi_mp_wake_mailbox from concurrent accesses.
- */
- if (!acpi_mp_wake_mailbox) {
- acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr,
- sizeof(*acpi_mp_wake_mailbox),
- MEMREMAP_WB);
- }
-
- /*
- * Mailbox memory is shared between the firmware and OS. Firmware will
- * listen on mailbox command address, and once it receives the wakeup
- * command, the CPU associated with the given apicid will be booted.
- *
- * The value of 'apic_id' and 'wakeup_vector' must be visible to the
- * firmware before the wakeup command is visible. smp_store_release()
- * ensures ordering and visibility.
- */
- acpi_mp_wake_mailbox->apic_id = apicid;
- acpi_mp_wake_mailbox->wakeup_vector = start_ip;
- smp_store_release(&acpi_mp_wake_mailbox->command,
- ACPI_MP_WAKE_COMMAND_WAKEUP);
-
- /*
- * Wait for the CPU to wake up.
- *
- * The CPU being woken up is essentially in a spin loop waiting to be
- * woken up. It should not take long for it wake up and acknowledge by
- * zeroing out ->command.
- *
- * ACPI specification doesn't provide any guidance on how long kernel
- * has to wait for a wake up acknowledgement. It also doesn't provide
- * a way to cancel a wake up request if it takes too long.
- *
- * In TDX environment, the VMM has control over how long it takes to
- * wake up secondary. It can postpone scheduling secondary vCPU
- * indefinitely. Giving up on wake up request and reporting error opens
- * possible attack vector for VMM: it can wake up a secondary CPU when
- * kernel doesn't expect it. Wait until positive result of the wake up
- * request.
- */
- while (READ_ONCE(acpi_mp_wake_mailbox->command))
- cpu_relax();
-
- return 0;
-}
-#endif /* CONFIG_X86_64 */
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
@@ -1124,29 +1063,6 @@ static int __init acpi_parse_madt_lapic_entries(void)
}
return 0;
}
-
-#ifdef CONFIG_X86_64
-static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
- const unsigned long end)
-{
- struct acpi_madt_multiproc_wakeup *mp_wake;
-
- if (!IS_ENABLED(CONFIG_SMP))
- return -ENODEV;
-
- mp_wake = (struct acpi_madt_multiproc_wakeup *)header;
- if (BAD_MADT_ENTRY(mp_wake, end))
- return -EINVAL;
-
- acpi_table_print_madt_entry(&header->common);
-
- acpi_mp_wake_mailbox_paddr = mp_wake->base_address;
-
- apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu);
-
- return 0;
-}
-#endif /* CONFIG_X86_64 */
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_IO_APIC
@@ -1343,7 +1259,7 @@ static void __init acpi_process_madt(void)
smp_found_config = 1;
}
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_ACPI_MADT_WAKEUP
/*
* Parse MADT MP Wake entry.
*/
diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S
new file mode 100644
index 000000000000..4e498d28cdc8
--- /dev/null
+++ b/arch/x86/kernel/acpi/madt_playdead.S
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
+#include <asm/page_types.h>
+#include <asm/processor-flags.h>
+
+ .text
+ .align PAGE_SIZE
+
+/*
+ * asm_acpi_mp_play_dead() - Hand over control of the CPU to the BIOS
+ *
+ * rdi: Address of the ACPI MADT MPWK ResetVector
+ * rsi: PGD of the identity mapping
+ */
+SYM_FUNC_START(asm_acpi_mp_play_dead)
+ /* Turn off global entries. Following CR3 write will flush them. */
+ movq %cr4, %rdx
+ andq $~(X86_CR4_PGE), %rdx
+ movq %rdx, %cr4
+
+ /* Switch to identity mapping */
+ movq %rsi, %cr3
+
+ /* Jump to reset vector */
+ ANNOTATE_RETPOLINE_SAFE
+ jmp *%rdi
+SYM_FUNC_END(asm_acpi_mp_play_dead)
diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c
new file mode 100644
index 000000000000..6cfe762be28b
--- /dev/null
+++ b/arch/x86/kernel/acpi/madt_wakeup.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/acpi.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/kexec.h>
+#include <linux/memblock.h>
+#include <linux/pgtable.h>
+#include <linux/sched/hotplug.h>
+#include <asm/apic.h>
+#include <asm/barrier.h>
+#include <asm/init.h>
+#include <asm/intel_pt.h>
+#include <asm/nmi.h>
+#include <asm/processor.h>
+#include <asm/reboot.h>
+
+/* Physical address of the Multiprocessor Wakeup Structure mailbox */
+static u64 acpi_mp_wake_mailbox_paddr __ro_after_init;
+
+/* Virtual address of the Multiprocessor Wakeup Structure mailbox */
+static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox __ro_after_init;
+
+static u64 acpi_mp_pgd __ro_after_init;
+static u64 acpi_mp_reset_vector_paddr __ro_after_init;
+
+static void acpi_mp_stop_this_cpu(void)
+{
+ asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd);
+}
+
+static void acpi_mp_play_dead(void)
+{
+ play_dead_common();
+ asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd);
+}
+
+static void acpi_mp_cpu_die(unsigned int cpu)
+{
+ u32 apicid = per_cpu(x86_cpu_to_apicid, cpu);
+ unsigned long timeout;
+
+ /*
+ * Use TEST mailbox command to prove that BIOS got control over
+ * the CPU before declaring it dead.
+ *
+ * BIOS has to clear 'command' field of the mailbox.
+ */
+ acpi_mp_wake_mailbox->apic_id = apicid;
+ smp_store_release(&acpi_mp_wake_mailbox->command,
+ ACPI_MP_WAKE_COMMAND_TEST);
+
+ /* Don't wait longer than a second. */
+ timeout = USEC_PER_SEC;
+ while (READ_ONCE(acpi_mp_wake_mailbox->command) && --timeout)
+ udelay(1);
+
+ if (!timeout)
+ pr_err("Failed to hand over CPU %d to BIOS\n", cpu);
+}
+
+/* The argument is required to match type of x86_mapping_info::alloc_pgt_page */
+static void __init *alloc_pgt_page(void *dummy)
+{
+ return memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static void __init free_pgt_page(void *pgt, void *dummy)
+{
+ return memblock_free(pgt, PAGE_SIZE);
+}
+
+/*
+ * Make sure asm_acpi_mp_play_dead() is present in the identity mapping at
+ * the same place as in the kernel page tables. asm_acpi_mp_play_dead() switches
+ * to the identity mapping and the function has be present at the same spot in
+ * the virtual address space before and after switching page tables.
+ */
+static int __init init_transition_pgtable(pgd_t *pgd)
+{
+ pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
+ unsigned long vaddr, paddr;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ vaddr = (unsigned long)asm_acpi_mp_play_dead;
+ pgd += pgd_index(vaddr);
+ if (!pgd_present(*pgd)) {
+ p4d = (p4d_t *)alloc_pgt_page(NULL);
+ if (!p4d)
+ return -ENOMEM;
+ set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
+ }
+ p4d = p4d_offset(pgd, vaddr);
+ if (!p4d_present(*p4d)) {
+ pud = (pud_t *)alloc_pgt_page(NULL);
+ if (!pud)
+ return -ENOMEM;
+ set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
+ }
+ pud = pud_offset(p4d, vaddr);
+ if (!pud_present(*pud)) {
+ pmd = (pmd_t *)alloc_pgt_page(NULL);
+ if (!pmd)
+ return -ENOMEM;
+ set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+ }
+ pmd = pmd_offset(pud, vaddr);
+ if (!pmd_present(*pmd)) {
+ pte = (pte_t *)alloc_pgt_page(NULL);
+ if (!pte)
+ return -ENOMEM;
+ set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
+ }
+ pte = pte_offset_kernel(pmd, vaddr);
+
+ paddr = __pa(vaddr);
+ set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
+
+ return 0;
+}
+
+static int __init acpi_mp_setup_reset(u64 reset_vector)
+{
+ struct x86_mapping_info info = {
+ .alloc_pgt_page = alloc_pgt_page,
+ .free_pgt_page = free_pgt_page,
+ .page_flag = __PAGE_KERNEL_LARGE_EXEC,
+ .kernpg_flag = _KERNPG_TABLE_NOENC,
+ };
+ pgd_t *pgd;
+
+ pgd = alloc_pgt_page(NULL);
+ if (!pgd)
+ return -ENOMEM;
+
+ for (int i = 0; i < nr_pfn_mapped; i++) {
+ unsigned long mstart, mend;
+
+ mstart = pfn_mapped[i].start << PAGE_SHIFT;
+ mend = pfn_mapped[i].end << PAGE_SHIFT;
+ if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
+ kernel_ident_mapping_free(&info, pgd);
+ return -ENOMEM;
+ }
+ }
+
+ if (kernel_ident_mapping_init(&info, pgd,
+ PAGE_ALIGN_DOWN(reset_vector),
+ PAGE_ALIGN(reset_vector + 1))) {
+ kernel_ident_mapping_free(&info, pgd);
+ return -ENOMEM;
+ }
+
+ if (init_transition_pgtable(pgd)) {
+ kernel_ident_mapping_free(&info, pgd);
+ return -ENOMEM;
+ }
+
+ smp_ops.play_dead = acpi_mp_play_dead;
+ smp_ops.stop_this_cpu = acpi_mp_stop_this_cpu;
+ smp_ops.cpu_die = acpi_mp_cpu_die;
+
+ acpi_mp_reset_vector_paddr = reset_vector;
+ acpi_mp_pgd = __pa(pgd);
+
+ return 0;
+}
+
+static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip)
+{
+ if (!acpi_mp_wake_mailbox_paddr) {
+ pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n");
+ return -EOPNOTSUPP;
+ }
+
+ /*
+ * Remap mailbox memory only for the first call to acpi_wakeup_cpu().
+ *
+ * Wakeup of secondary CPUs is fully serialized in the core code.
+ * No need to protect acpi_mp_wake_mailbox from concurrent accesses.
+ */
+ if (!acpi_mp_wake_mailbox) {
+ acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr,
+ sizeof(*acpi_mp_wake_mailbox),
+ MEMREMAP_WB);
+ }
+
+ /*
+ * Mailbox memory is shared between the firmware and OS. Firmware will
+ * listen on mailbox command address, and once it receives the wakeup
+ * command, the CPU associated with the given apicid will be booted.
+ *
+ * The value of 'apic_id' and 'wakeup_vector' must be visible to the
+ * firmware before the wakeup command is visible. smp_store_release()
+ * ensures ordering and visibility.
+ */
+ acpi_mp_wake_mailbox->apic_id = apicid;
+ acpi_mp_wake_mailbox->wakeup_vector = start_ip;
+ smp_store_release(&acpi_mp_wake_mailbox->command,
+ ACPI_MP_WAKE_COMMAND_WAKEUP);
+
+ /*
+ * Wait for the CPU to wake up.
+ *
+ * The CPU being woken up is essentially in a spin loop waiting to be
+ * woken up. It should not take long for it wake up and acknowledge by
+ * zeroing out ->command.
+ *
+ * ACPI specification doesn't provide any guidance on how long kernel
+ * has to wait for a wake up acknowledgment. It also doesn't provide
+ * a way to cancel a wake up request if it takes too long.
+ *
+ * In TDX environment, the VMM has control over how long it takes to
+ * wake up secondary. It can postpone scheduling secondary vCPU
+ * indefinitely. Giving up on wake up request and reporting error opens
+ * possible attack vector for VMM: it can wake up a secondary CPU when
+ * kernel doesn't expect it. Wait until positive result of the wake up
+ * request.
+ */
+ while (READ_ONCE(acpi_mp_wake_mailbox->command))
+ cpu_relax();
+
+ return 0;
+}
+
+static void acpi_mp_disable_offlining(struct acpi_madt_multiproc_wakeup *mp_wake)
+{
+ cpu_hotplug_disable_offlining();
+
+ /*
+ * ACPI MADT doesn't allow to offline a CPU after it was onlined. This
+ * limits kexec: the second kernel won't be able to use more than one CPU.
+ *
+ * To prevent a kexec kernel from onlining secondary CPUs invalidate the
+ * mailbox address in the ACPI MADT wakeup structure which prevents a
+ * kexec kernel to use it.
+ *
+ * This is safe as the booting kernel has the mailbox address cached
+ * already and acpi_wakeup_cpu() uses the cached value to bring up the
+ * secondary CPUs.
+ *
+ * Note: This is a Linux specific convention and not covered by the
+ * ACPI specification.
+ */
+ mp_wake->mailbox_address = 0;
+}
+
+int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
+ const unsigned long end)
+{
+ struct acpi_madt_multiproc_wakeup *mp_wake;
+
+ mp_wake = (struct acpi_madt_multiproc_wakeup *)header;
+
+ /*
+ * Cannot use the standard BAD_MADT_ENTRY() to sanity check the @mp_wake
+ * entry. 'sizeof (struct acpi_madt_multiproc_wakeup)' can be larger
+ * than the actual size of the MP wakeup entry in ACPI table because the
+ * 'reset_vector' is only available in the V1 MP wakeup structure.
+ */
+ if (!mp_wake)
+ return -EINVAL;
+ if (end - (unsigned long)mp_wake < ACPI_MADT_MP_WAKEUP_SIZE_V0)
+ return -EINVAL;
+ if (mp_wake->header.length < ACPI_MADT_MP_WAKEUP_SIZE_V0)
+ return -EINVAL;
+
+ acpi_table_print_madt_entry(&header->common);
+
+ acpi_mp_wake_mailbox_paddr = mp_wake->mailbox_address;
+
+ if (mp_wake->version >= ACPI_MADT_MP_WAKEUP_VERSION_V1 &&
+ mp_wake->header.length >= ACPI_MADT_MP_WAKEUP_SIZE_V1) {
+ if (acpi_mp_setup_reset(mp_wake->reset_vector)) {
+ pr_warn("Failed to setup MADT reset vector\n");
+ acpi_mp_disable_offlining(mp_wake);
+ }
+ } else {
+ /*
+ * CPU offlining requires version 1 of the ACPI MADT wakeup
+ * structure.
+ */
+ acpi_mp_disable_offlining(mp_wake);
+ }
+
+ apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu);
+
+ return 0;
+}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 89de61243272..d17518ca19b8 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -432,6 +432,11 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
return 5;
}
+static inline u8 * instr_va(struct alt_instr *i)
+{
+ return (u8 *)&i->instr_offset + i->instr_offset;
+}
+
/*
* Replace instructions with better alternatives for this CPU type. This runs
* before SMP is initialized to avoid SMP problems with self modifying code.
@@ -447,7 +452,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
{
u8 insn_buff[MAX_PATCH_LEN];
u8 *instr, *replacement;
- struct alt_instr *a;
+ struct alt_instr *a, *b;
DPRINTK(ALT, "alt table %px, -> %px", start, end);
@@ -473,7 +478,18 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
for (a = start; a < end; a++) {
int insn_buff_sz = 0;
- instr = (u8 *)&a->instr_offset + a->instr_offset;
+ /*
+ * In case of nested ALTERNATIVE()s the outer alternative might
+ * add more padding. To ensure consistent patching find the max
+ * padding for all alt_instr entries for this site (nested
+ * alternatives result in consecutive entries).
+ */
+ for (b = a+1; b < end && instr_va(b) == instr_va(a); b++) {
+ u8 len = max(a->instrlen, b->instrlen);
+ a->instrlen = b->instrlen = len;
+ }
+
+ instr = instr_va(a);
replacement = (u8 *)&a->repl_offset + a->repl_offset;
BUG_ON(a->instrlen > sizeof(insn_buff));
BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
@@ -885,8 +901,8 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
#endif /* CONFIG_X86_KERNEL_IBT */
-#ifdef CONFIG_FINEIBT
-#define __CFI_DEFAULT CFI_DEFAULT
+#ifdef CONFIG_CFI_AUTO_DEFAULT
+#define __CFI_DEFAULT CFI_AUTO
#elif defined(CONFIG_CFI_CLANG)
#define __CFI_DEFAULT CFI_KCFI
#else
@@ -994,7 +1010,7 @@ static __init int cfi_parse_cmdline(char *str)
}
if (!strcmp(str, "auto")) {
- cfi_mode = CFI_DEFAULT;
+ cfi_mode = CFI_AUTO;
} else if (!strcmp(str, "off")) {
cfi_mode = CFI_OFF;
cfi_rand = false;
@@ -1254,7 +1270,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
"FineIBT preamble wrong size: %ld", fineibt_preamble_size))
return;
- if (cfi_mode == CFI_DEFAULT) {
+ if (cfi_mode == CFI_AUTO) {
cfi_mode = CFI_KCFI;
if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
cfi_mode = CFI_FINEIBT;
@@ -1641,7 +1657,7 @@ static noinline void __init alt_reloc_selftest(void)
*/
asm_inline volatile (
ALTERNATIVE("", "lea %[mem], %%" _ASM_ARG1 "; call __alt_reloc_selftest;", X86_FEATURE_ALWAYS)
- : /* output */
+ : ASM_CALL_CONSTRAINT
: [mem] "m" (__alt_reloc_selftest_addr)
: _ASM_ARG1
);
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 027a8c7a2c9e..059e5c16af05 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -180,6 +180,43 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev,
return dev;
}
+/*
+ * SMN accesses may fail in ways that are difficult to detect here in the called
+ * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do
+ * their own checking based on what behavior they expect.
+ *
+ * For SMN reads, the returned value may be zero if the register is Read-as-Zero.
+ * Or it may be a "PCI Error Response", e.g. all 0xFFs. The "PCI Error Response"
+ * can be checked here, and a proper error code can be returned.
+ *
+ * But the Read-as-Zero response cannot be verified here. A value of 0 may be
+ * correct in some cases, so callers must check that this correct is for the
+ * register/fields they need.
+ *
+ * For SMN writes, success can be determined through a "write and read back"
+ * However, this is not robust when done here.
+ *
+ * Possible issues:
+ *
+ * 1) Bits that are "Write-1-to-Clear". In this case, the read value should
+ * *not* match the write value.
+ *
+ * 2) Bits that are "Read-as-Zero"/"Writes-Ignored". This information cannot be
+ * known here.
+ *
+ * 3) Bits that are "Reserved / Set to 1". Ditto above.
+ *
+ * Callers of amd_smn_write() should do the "write and read back" check
+ * themselves, if needed.
+ *
+ * For #1, they can see if their target bits got cleared.
+ *
+ * For #2 and #3, they can check if their target bits got set as intended.
+ *
+ * This matches what is done for RDMSR/WRMSR. As long as there's no #GP, then
+ * the operation is considered a success, and the caller does their own
+ * checking.
+ */
static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write)
{
struct pci_dev *root;
@@ -202,9 +239,6 @@ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write)
err = (write ? pci_write_config_dword(root, 0x64, *value)
: pci_read_config_dword(root, 0x64, value));
- if (err)
- pr_warn("Error %s SMN address 0x%x.\n",
- (write ? "writing to" : "reading from"), address);
out_unlock:
mutex_unlock(&smn_mutex);
@@ -213,7 +247,7 @@ out:
return err;
}
-int amd_smn_read(u16 node, u32 address, u32 *value)
+int __must_check amd_smn_read(u16 node, u32 address, u32 *value)
{
int err = __amd_smn_rw(node, address, value, false);
@@ -226,7 +260,7 @@ int amd_smn_read(u16 node, u32 address, u32 *value)
}
EXPORT_SYMBOL_GPL(amd_smn_read);
-int amd_smn_write(u16 node, u32 address, u32 value)
+int __must_check amd_smn_write(u16 node, u32 address, u32 value)
{
return __amd_smn_rw(node, address, &value, true);
}
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a02bba0ed6b9..5857a0f5d514 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -34,7 +34,7 @@ obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o
ifdef CONFIG_CPU_SUP_INTEL
-obj-y += intel.o intel_pconfig.o tsx.o
+obj-y += intel.o tsx.o
obj-$(CONFIG_PM) += intel_epb.o
endif
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 44df3f11e731..be5889bded49 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1220,14 +1220,3 @@ void amd_check_microcode(void)
on_each_cpu(zenbleed_check_cpu, NULL, 1);
}
-
-/*
- * Issue a DIV 0/1 insn to clear any division data from previous DIV
- * operations.
- */
-void noinstr amd_clear_divider(void)
-{
- asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0)
- :: "a" (0), "d" (0), "r" (1));
-}
-EXPORT_SYMBOL_GPL(amd_clear_divider);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b6f927f6c567..45675da354f3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1625,6 +1625,7 @@ static bool __init spec_ctrl_bhi_dis(void)
enum bhi_mitigations {
BHI_MITIGATION_OFF,
BHI_MITIGATION_ON,
+ BHI_MITIGATION_VMEXIT_ONLY,
};
static enum bhi_mitigations bhi_mitigation __ro_after_init =
@@ -1639,6 +1640,8 @@ static int __init spectre_bhi_parse_cmdline(char *str)
bhi_mitigation = BHI_MITIGATION_OFF;
else if (!strcmp(str, "on"))
bhi_mitigation = BHI_MITIGATION_ON;
+ else if (!strcmp(str, "vmexit"))
+ bhi_mitigation = BHI_MITIGATION_VMEXIT_ONLY;
else
pr_err("Ignoring unknown spectre_bhi option (%s)", str);
@@ -1659,19 +1662,22 @@ static void __init bhi_select_mitigation(void)
return;
}
+ /* Mitigate in hardware if supported */
if (spec_ctrl_bhi_dis())
return;
if (!IS_ENABLED(CONFIG_X86_64))
return;
- /* Mitigate KVM by default */
- setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
- pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
+ if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
+ pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n");
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+ return;
+ }
- /* Mitigate syscalls when the mitigation is forced =on */
+ pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n");
setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
- pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
}
static void __init spectre_v2_select_mitigation(void)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fdf3489d92a4..08b95a35b5cb 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -72,19 +72,19 @@ static bool cpu_model_supports_sld __ro_after_init;
*/
static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c)
{
- switch (c->x86_model) {
- case INTEL_FAM6_CORE_YONAH:
- case INTEL_FAM6_CORE2_MEROM:
- case INTEL_FAM6_CORE2_MEROM_L:
- case INTEL_FAM6_CORE2_PENRYN:
- case INTEL_FAM6_CORE2_DUNNINGTON:
- case INTEL_FAM6_NEHALEM:
- case INTEL_FAM6_NEHALEM_G:
- case INTEL_FAM6_NEHALEM_EP:
- case INTEL_FAM6_NEHALEM_EX:
- case INTEL_FAM6_WESTMERE:
- case INTEL_FAM6_WESTMERE_EP:
- case INTEL_FAM6_SANDYBRIDGE:
+ switch (c->x86_vfm) {
+ case INTEL_CORE_YONAH:
+ case INTEL_CORE2_MEROM:
+ case INTEL_CORE2_MEROM_L:
+ case INTEL_CORE2_PENRYN:
+ case INTEL_CORE2_DUNNINGTON:
+ case INTEL_NEHALEM:
+ case INTEL_NEHALEM_G:
+ case INTEL_NEHALEM_EP:
+ case INTEL_NEHALEM_EX:
+ case INTEL_WESTMERE:
+ case INTEL_WESTMERE_EP:
+ case INTEL_SANDYBRIDGE:
setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP);
}
}
@@ -106,9 +106,9 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
*/
if (c->x86 != 6)
return;
- switch (c->x86_model) {
- case INTEL_FAM6_XEON_PHI_KNL:
- case INTEL_FAM6_XEON_PHI_KNM:
+ switch (c->x86_vfm) {
+ case INTEL_XEON_PHI_KNL:
+ case INTEL_XEON_PHI_KNM:
break;
default:
return;
@@ -134,32 +134,32 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
* - Release note from 20180108 microcode release
*/
struct sku_microcode {
- u8 model;
+ u32 vfm;
u8 stepping;
u32 microcode;
};
static const struct sku_microcode spectre_bad_microcodes[] = {
- { INTEL_FAM6_KABYLAKE, 0x0B, 0x80 },
- { INTEL_FAM6_KABYLAKE, 0x0A, 0x80 },
- { INTEL_FAM6_KABYLAKE, 0x09, 0x80 },
- { INTEL_FAM6_KABYLAKE_L, 0x0A, 0x80 },
- { INTEL_FAM6_KABYLAKE_L, 0x09, 0x80 },
- { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e },
- { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c },
- { INTEL_FAM6_BROADWELL, 0x04, 0x28 },
- { INTEL_FAM6_BROADWELL_G, 0x01, 0x1b },
- { INTEL_FAM6_BROADWELL_D, 0x02, 0x14 },
- { INTEL_FAM6_BROADWELL_D, 0x03, 0x07000011 },
- { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 },
- { INTEL_FAM6_HASWELL_L, 0x01, 0x21 },
- { INTEL_FAM6_HASWELL_G, 0x01, 0x18 },
- { INTEL_FAM6_HASWELL, 0x03, 0x23 },
- { INTEL_FAM6_HASWELL_X, 0x02, 0x3b },
- { INTEL_FAM6_HASWELL_X, 0x04, 0x10 },
- { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a },
+ { INTEL_KABYLAKE, 0x0B, 0x80 },
+ { INTEL_KABYLAKE, 0x0A, 0x80 },
+ { INTEL_KABYLAKE, 0x09, 0x80 },
+ { INTEL_KABYLAKE_L, 0x0A, 0x80 },
+ { INTEL_KABYLAKE_L, 0x09, 0x80 },
+ { INTEL_SKYLAKE_X, 0x03, 0x0100013e },
+ { INTEL_SKYLAKE_X, 0x04, 0x0200003c },
+ { INTEL_BROADWELL, 0x04, 0x28 },
+ { INTEL_BROADWELL_G, 0x01, 0x1b },
+ { INTEL_BROADWELL_D, 0x02, 0x14 },
+ { INTEL_BROADWELL_D, 0x03, 0x07000011 },
+ { INTEL_BROADWELL_X, 0x01, 0x0b000025 },
+ { INTEL_HASWELL_L, 0x01, 0x21 },
+ { INTEL_HASWELL_G, 0x01, 0x18 },
+ { INTEL_HASWELL, 0x03, 0x23 },
+ { INTEL_HASWELL_X, 0x02, 0x3b },
+ { INTEL_HASWELL_X, 0x04, 0x10 },
+ { INTEL_IVYBRIDGE_X, 0x04, 0x42a },
/* Observed in the wild */
- { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b },
- { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 },
+ { INTEL_SANDYBRIDGE_X, 0x06, 0x61b },
+ { INTEL_SANDYBRIDGE_X, 0x07, 0x712 },
};
static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
@@ -173,11 +173,8 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_HYPERVISOR))
return false;
- if (c->x86 != 6)
- return false;
-
for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
- if (c->x86_model == spectre_bad_microcodes[i].model &&
+ if (c->x86_vfm == spectre_bad_microcodes[i].vfm &&
c->x86_stepping == spectre_bad_microcodes[i].stepping)
return (c->microcode <= spectre_bad_microcodes[i].microcode);
}
@@ -190,83 +187,35 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
#define TME_ACTIVATE_LOCKED(x) (x & 0x1)
#define TME_ACTIVATE_ENABLED(x) (x & 0x2)
-#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128 0
-
#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */
-#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED 0
-#define MKTME_DISABLED 1
-#define MKTME_UNINITIALIZED 2
-static int mktme_status = MKTME_UNINITIALIZED;
-
static void detect_tme_early(struct cpuinfo_x86 *c)
{
- u64 tme_activate, tme_policy, tme_crypto_algs;
- int keyid_bits = 0, nr_keyids = 0;
- static u64 tme_activate_cpu0 = 0;
+ u64 tme_activate;
+ int keyid_bits;
rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
- if (mktme_status != MKTME_UNINITIALIZED) {
- if (tme_activate != tme_activate_cpu0) {
- /* Broken BIOS? */
- pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
- pr_err_once("x86/tme: MKTME is not usable\n");
- mktme_status = MKTME_DISABLED;
-
- /* Proceed. We may need to exclude bits from x86_phys_bits. */
- }
- } else {
- tme_activate_cpu0 = tme_activate;
- }
-
if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
pr_info_once("x86/tme: not enabled by BIOS\n");
- mktme_status = MKTME_DISABLED;
clear_cpu_cap(c, X86_FEATURE_TME);
return;
}
-
- if (mktme_status != MKTME_UNINITIALIZED)
- goto detect_keyid_bits;
-
- pr_info("x86/tme: enabled by BIOS\n");
-
- tme_policy = TME_ACTIVATE_POLICY(tme_activate);
- if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
- pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
- tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
- if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
- pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
- tme_crypto_algs);
- mktme_status = MKTME_DISABLED;
- }
-detect_keyid_bits:
+ pr_info_once("x86/tme: enabled by BIOS\n");
keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
- nr_keyids = (1UL << keyid_bits) - 1;
- if (nr_keyids) {
- pr_info_once("x86/mktme: enabled by BIOS\n");
- pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
- } else {
- pr_info_once("x86/mktme: disabled by BIOS\n");
- }
-
- if (mktme_status == MKTME_UNINITIALIZED) {
- /* MKTME is usable */
- mktme_status = MKTME_ENABLED;
- }
+ if (!keyid_bits)
+ return;
/*
- * KeyID bits effectively lower the number of physical address
- * bits. Update cpuinfo_x86::x86_phys_bits accordingly.
+ * KeyID bits are set by BIOS and can be present regardless
+ * of whether the kernel is using them. They effectively lower
+ * the number of physical address bits.
+ *
+ * Update cpuinfo_x86::x86_phys_bits accordingly.
*/
c->x86_phys_bits -= keyid_bits;
+ pr_info_once("x86/mktme: BIOS enabled: x86_phys_bits reduced by %d\n",
+ keyid_bits);
}
void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c)
@@ -320,7 +269,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
* need the microcode to have already been loaded... so if it is
* not, recommend a BIOS update and disable large pages.
*/
- if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 &&
+ if (c->x86_vfm == INTEL_ATOM_BONNELL && c->x86_stepping <= 2 &&
c->microcode < 0x20e) {
pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n");
clear_cpu_cap(c, X86_FEATURE_PSE);
@@ -352,17 +301,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
}
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
- if (c->x86 == 6) {
- switch (c->x86_model) {
- case INTEL_FAM6_ATOM_SALTWELL_MID:
- case INTEL_FAM6_ATOM_SALTWELL_TABLET:
- case INTEL_FAM6_ATOM_SILVERMONT_MID:
- case INTEL_FAM6_ATOM_AIRMONT_NP:
- set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
- break;
- default:
- break;
- }
+ switch (c->x86_vfm) {
+ case INTEL_ATOM_SALTWELL_MID:
+ case INTEL_ATOM_SALTWELL_TABLET:
+ case INTEL_ATOM_SILVERMONT_MID:
+ case INTEL_ATOM_AIRMONT_NP:
+ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
+ break;
}
/*
@@ -401,7 +346,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
* should be false so that __flush_tlb_all() causes CR3 instead of CR4.PGE
* to be modified.
*/
- if (c->x86 == 5 && c->x86_model == 9) {
+ if (c->x86_vfm == INTEL_QUARK_X1000) {
pr_info("Disabling PGE capability bit\n");
setup_clear_cpu_cap(X86_FEATURE_PGE);
}
@@ -633,12 +578,13 @@ static void init_intel(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_PEBS);
}
- if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) &&
- (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
+ if (boot_cpu_has(X86_FEATURE_CLFLUSH) &&
+ (c->x86_vfm == INTEL_CORE2_DUNNINGTON ||
+ c->x86_vfm == INTEL_NEHALEM_EX ||
+ c->x86_vfm == INTEL_WESTMERE_EX))
set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
- if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_MWAIT) &&
- ((c->x86_model == INTEL_FAM6_ATOM_GOLDMONT)))
+ if (boot_cpu_has(X86_FEATURE_MWAIT) && c->x86_vfm == INTEL_ATOM_GOLDMONT)
set_cpu_bug(c, X86_BUG_MONITOR);
#ifdef CONFIG_X86_64
@@ -1254,9 +1200,9 @@ void handle_bus_lock(struct pt_regs *regs)
* feature even though they do not enumerate IA32_CORE_CAPABILITIES.
*/
static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, 0),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE_L, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, 0),
{}
};
diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c
deleted file mode 100644
index 5be2b1790282..000000000000
--- a/arch/x86/kernel/cpu/intel_pconfig.c
+++ /dev/null
@@ -1,84 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Intel PCONFIG instruction support.
- *
- * Copyright (C) 2017 Intel Corporation
- *
- * Author:
- * Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
- */
-#include <linux/bug.h>
-#include <linux/limits.h>
-
-#include <asm/cpufeature.h>
-#include <asm/intel_pconfig.h>
-
-#define PCONFIG_CPUID 0x1b
-
-#define PCONFIG_CPUID_SUBLEAF_MASK ((1 << 12) - 1)
-
-/* Subleaf type (EAX) for PCONFIG CPUID leaf (0x1B) */
-enum {
- PCONFIG_CPUID_SUBLEAF_INVALID = 0,
- PCONFIG_CPUID_SUBLEAF_TARGETID = 1,
-};
-
-/* Bitmask of supported targets */
-static u64 targets_supported __read_mostly;
-
-int pconfig_target_supported(enum pconfig_target target)
-{
- /*
- * We would need to re-think the implementation once we get > 64
- * PCONFIG targets. Spec allows up to 2^32 targets.
- */
- BUILD_BUG_ON(PCONFIG_TARGET_NR >= 64);
-
- if (WARN_ON_ONCE(target >= 64))
- return 0;
- return targets_supported & (1ULL << target);
-}
-
-static int __init intel_pconfig_init(void)
-{
- int subleaf;
-
- if (!boot_cpu_has(X86_FEATURE_PCONFIG))
- return 0;
-
- /*
- * Scan subleafs of PCONFIG CPUID leaf.
- *
- * Subleafs of the same type need not to be consecutive.
- *
- * Stop on the first invalid subleaf type. All subleafs after the first
- * invalid are invalid too.
- */
- for (subleaf = 0; subleaf < INT_MAX; subleaf++) {
- struct cpuid_regs regs;
-
- cpuid_count(PCONFIG_CPUID, subleaf,
- &regs.eax, &regs.ebx, &regs.ecx, &regs.edx);
-
- switch (regs.eax & PCONFIG_CPUID_SUBLEAF_MASK) {
- case PCONFIG_CPUID_SUBLEAF_INVALID:
- /* Stop on the first invalid subleaf */
- goto out;
- case PCONFIG_CPUID_SUBLEAF_TARGETID:
- /* Mark supported PCONFIG targets */
- if (regs.ebx < 64)
- targets_supported |= (1ULL << regs.ebx);
- if (regs.ecx < 64)
- targets_supported |= (1ULL << regs.ecx);
- if (regs.edx < 64)
- targets_supported |= (1ULL << regs.edx);
- break;
- default:
- /* Unknown CPUID.PCONFIG subleaf: ignore */
- break;
- }
- }
-out:
- return 0;
-}
-arch_initcall(intel_pconfig_init);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index ad0623b659ed..b85ec7a4ec9e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -677,10 +677,9 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
* is already totally * confused. In this case it's likely it will
* not fully execute the machine check handler either.
*/
-bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
+void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
- bool error_seen = false;
struct mce m;
int i;
@@ -754,8 +753,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
continue;
log_it:
- error_seen = true;
-
if (flags & MCP_DONTLOG)
goto clear_it;
@@ -787,8 +784,6 @@ clear_it:
*/
sync_core();
-
- return error_seen;
}
EXPORT_SYMBOL_GPL(machine_check_poll);
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 94953d749475..49ed3428785d 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -487,12 +487,16 @@ static void prepare_msrs(void *info)
wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
}
- wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
+
+ if (m.misc)
+ wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
} else {
wrmsrl(MSR_IA32_MCx_STATUS(b), m.status);
wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr);
- wrmsrl(MSR_IA32_MCx_MISC(b), m.misc);
+
+ if (m.misc)
+ wrmsrl(MSR_IA32_MCx_MISC(b), m.misc);
}
}
@@ -795,4 +799,5 @@ static void __exit inject_exit(void)
module_init(inject_init);
module_exit(inject_exit);
+MODULE_DESCRIPTION("Machine check injection support");
MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index 1db560ed2ca3..68f537347466 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -30,8 +30,7 @@ dump_array()
# If the /* comment */ starts with a quote string, grab that.
VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')"
- [ -z "$VALUE" ] && VALUE="\"$NAME\""
- [ "$VALUE" = '""' ] && continue
+ [ ! "$VALUE" ] && continue
# Name is uppercase, VALUE is all lowercase
VALUE="$(echo "$VALUE" | tr A-Z a-z)"
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index a113d9aba553..1930fce9dfe9 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -19,7 +19,6 @@
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/err.h>
-#include <linux/cacheinfo.h>
#include <linux/cpuhotplug.h>
#include <asm/cpu_device_id.h>
@@ -60,7 +59,8 @@ static void mba_wrmsr_intel(struct msr_param *m);
static void cat_wrmsr(struct msr_param *m);
static void mba_wrmsr_amd(struct msr_param *m);
-#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
+#define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains)
+#define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains)
struct rdt_hw_resource rdt_resources_all[] = {
[RDT_RESOURCE_L3] =
@@ -68,8 +68,10 @@ struct rdt_hw_resource rdt_resources_all[] = {
.r_resctrl = {
.rid = RDT_RESOURCE_L3,
.name = "L3",
- .cache_level = 3,
- .domains = domain_init(RDT_RESOURCE_L3),
+ .ctrl_scope = RESCTRL_L3_CACHE,
+ .mon_scope = RESCTRL_L3_CACHE,
+ .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L3),
+ .mon_domains = mon_domain_init(RDT_RESOURCE_L3),
.parse_ctrlval = parse_cbm,
.format_str = "%d=%0*x",
.fflags = RFTYPE_RES_CACHE,
@@ -82,8 +84,8 @@ struct rdt_hw_resource rdt_resources_all[] = {
.r_resctrl = {
.rid = RDT_RESOURCE_L2,
.name = "L2",
- .cache_level = 2,
- .domains = domain_init(RDT_RESOURCE_L2),
+ .ctrl_scope = RESCTRL_L2_CACHE,
+ .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L2),
.parse_ctrlval = parse_cbm,
.format_str = "%d=%0*x",
.fflags = RFTYPE_RES_CACHE,
@@ -96,8 +98,8 @@ struct rdt_hw_resource rdt_resources_all[] = {
.r_resctrl = {
.rid = RDT_RESOURCE_MBA,
.name = "MB",
- .cache_level = 3,
- .domains = domain_init(RDT_RESOURCE_MBA),
+ .ctrl_scope = RESCTRL_L3_CACHE,
+ .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_MBA),
.parse_ctrlval = parse_bw,
.format_str = "%d=%*u",
.fflags = RFTYPE_RES_MB,
@@ -108,8 +110,8 @@ struct rdt_hw_resource rdt_resources_all[] = {
.r_resctrl = {
.rid = RDT_RESOURCE_SMBA,
.name = "SMBA",
- .cache_level = 3,
- .domains = domain_init(RDT_RESOURCE_SMBA),
+ .ctrl_scope = RESCTRL_L3_CACHE,
+ .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_SMBA),
.parse_ctrlval = parse_bw,
.format_str = "%d=%*u",
.fflags = RFTYPE_RES_MB,
@@ -306,8 +308,8 @@ static void rdt_get_cdp_l2_config(void)
static void mba_wrmsr_amd(struct msr_param *m)
{
+ struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom);
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
for (i = m->low; i < m->high; i++)
@@ -330,8 +332,8 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
static void mba_wrmsr_intel(struct msr_param *m)
{
+ struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom);
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
/* Write the delay values for mba. */
@@ -341,23 +343,38 @@ static void mba_wrmsr_intel(struct msr_param *m)
static void cat_wrmsr(struct msr_param *m)
{
+ struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(m->dom);
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
for (i = m->low; i < m->high; i++)
wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
}
-struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
+struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r)
{
- struct rdt_domain *d;
+ struct rdt_ctrl_domain *d;
lockdep_assert_cpus_held();
- list_for_each_entry(d, &r->domains, list) {
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
/* Find the domain that contains this CPU */
- if (cpumask_test_cpu(cpu, &d->cpu_mask))
+ if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
+ return d;
+ }
+
+ return NULL;
+}
+
+struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r)
+{
+ struct rdt_mon_domain *d;
+
+ lockdep_assert_cpus_held();
+
+ list_for_each_entry(d, &r->mon_domains, hdr.list) {
+ /* Find the domain that contains this CPU */
+ if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
return d;
}
@@ -379,24 +396,21 @@ void rdt_ctrl_update(void *arg)
}
/*
- * rdt_find_domain - Find a domain in a resource that matches input resource id
+ * rdt_find_domain - Search for a domain id in a resource domain list.
*
- * Search resource r's domain list to find the resource id. If the resource
- * id is found in a domain, return the domain. Otherwise, if requested by
- * caller, return the first domain whose id is bigger than the input id.
- * The domain list is sorted by id in ascending order.
+ * Search the domain list to find the domain id. If the domain id is
+ * found, return the domain. NULL otherwise. If the domain id is not
+ * found (and NULL returned) then the first domain with id bigger than
+ * the input id can be returned to the caller via @pos.
*/
-struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
- struct list_head **pos)
+struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,
+ struct list_head **pos)
{
- struct rdt_domain *d;
+ struct rdt_domain_hdr *d;
struct list_head *l;
- if (id < 0)
- return ERR_PTR(-ENODEV);
-
- list_for_each(l, &r->domains) {
- d = list_entry(l, struct rdt_domain, list);
+ list_for_each(l, h) {
+ d = list_entry(l, struct rdt_domain_hdr, list);
/* When id is found, return its domain. */
if (id == d->id)
return d;
@@ -425,18 +439,23 @@ static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
*dc = r->default_ctrl;
}
-static void domain_free(struct rdt_hw_domain *hw_dom)
+static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom)
+{
+ kfree(hw_dom->ctrl_val);
+ kfree(hw_dom);
+}
+
+static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom)
{
kfree(hw_dom->arch_mbm_total);
kfree(hw_dom->arch_mbm_local);
- kfree(hw_dom->ctrl_val);
kfree(hw_dom);
}
-static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
+static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *d)
{
+ struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
struct msr_param m;
u32 *dc;
@@ -461,7 +480,7 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
* @num_rmid: The size of the MBM counter array
* @hw_dom: The domain that owns the allocated arrays
*/
-static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
+static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
{
size_t tsize;
@@ -484,37 +503,45 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
return 0;
}
-/*
- * domain_add_cpu - Add a cpu to a resource's domain list.
- *
- * If an existing domain in the resource r's domain list matches the cpu's
- * resource id, add the cpu in the domain.
- *
- * Otherwise, a new domain is allocated and inserted into the right position
- * in the domain list sorted by id in ascending order.
- *
- * The order in the domain list is visible to users when we print entries
- * in the schemata file and schemata input is validated to have the same order
- * as this list.
- */
-static void domain_add_cpu(int cpu, struct rdt_resource *r)
+static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
{
- int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
+ switch (scope) {
+ case RESCTRL_L2_CACHE:
+ case RESCTRL_L3_CACHE:
+ return get_cpu_cacheinfo_id(cpu, scope);
+ case RESCTRL_L3_NODE:
+ return cpu_to_node(cpu);
+ default:
+ break;
+ }
+
+ return -EINVAL;
+}
+
+static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
+{
+ int id = get_domain_id_from_scope(cpu, r->ctrl_scope);
+ struct rdt_hw_ctrl_domain *hw_dom;
struct list_head *add_pos = NULL;
- struct rdt_hw_domain *hw_dom;
- struct rdt_domain *d;
+ struct rdt_domain_hdr *hdr;
+ struct rdt_ctrl_domain *d;
int err;
lockdep_assert_held(&domain_list_lock);
- d = rdt_find_domain(r, id, &add_pos);
- if (IS_ERR(d)) {
- pr_warn("Couldn't find cache id for CPU %d\n", cpu);
+ if (id < 0) {
+ pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n",
+ cpu, r->ctrl_scope, r->name);
return;
}
- if (d) {
- cpumask_set_cpu(cpu, &d->cpu_mask);
+ hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos);
+ if (hdr) {
+ if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
+ return;
+ d = container_of(hdr, struct rdt_ctrl_domain, hdr);
+
+ cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
if (r->cache.arch_has_per_cpu_cfg)
rdt_domain_reconfigure_cdp(r);
return;
@@ -525,64 +552,187 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
return;
d = &hw_dom->d_resctrl;
- d->id = id;
- cpumask_set_cpu(cpu, &d->cpu_mask);
+ d->hdr.id = id;
+ d->hdr.type = RESCTRL_CTRL_DOMAIN;
+ cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
rdt_domain_reconfigure_cdp(r);
- if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
- domain_free(hw_dom);
+ if (domain_setup_ctrlval(r, d)) {
+ ctrl_domain_free(hw_dom);
return;
}
- if (r->mon_capable && arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
- domain_free(hw_dom);
+ list_add_tail_rcu(&d->hdr.list, add_pos);
+
+ err = resctrl_online_ctrl_domain(r, d);
+ if (err) {
+ list_del_rcu(&d->hdr.list);
+ synchronize_rcu();
+ ctrl_domain_free(hw_dom);
+ }
+}
+
+static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
+{
+ int id = get_domain_id_from_scope(cpu, r->mon_scope);
+ struct list_head *add_pos = NULL;
+ struct rdt_hw_mon_domain *hw_dom;
+ struct rdt_domain_hdr *hdr;
+ struct rdt_mon_domain *d;
+ int err;
+
+ lockdep_assert_held(&domain_list_lock);
+
+ if (id < 0) {
+ pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n",
+ cpu, r->mon_scope, r->name);
return;
}
- list_add_tail_rcu(&d->list, add_pos);
+ hdr = rdt_find_domain(&r->mon_domains, id, &add_pos);
+ if (hdr) {
+ if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
+ return;
+ d = container_of(hdr, struct rdt_mon_domain, hdr);
+
+ cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
+ return;
+ }
- err = resctrl_online_domain(r, d);
+ hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu));
+ if (!hw_dom)
+ return;
+
+ d = &hw_dom->d_resctrl;
+ d->hdr.id = id;
+ d->hdr.type = RESCTRL_MON_DOMAIN;
+ d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+ if (!d->ci) {
+ pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
+ mon_domain_free(hw_dom);
+ return;
+ }
+ cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
+
+ arch_mon_domain_online(r, d);
+
+ if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
+ mon_domain_free(hw_dom);
+ return;
+ }
+
+ list_add_tail_rcu(&d->hdr.list, add_pos);
+
+ err = resctrl_online_mon_domain(r, d);
if (err) {
- list_del_rcu(&d->list);
+ list_del_rcu(&d->hdr.list);
synchronize_rcu();
- domain_free(hw_dom);
+ mon_domain_free(hw_dom);
}
}
-static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+static void domain_add_cpu(int cpu, struct rdt_resource *r)
+{
+ if (r->alloc_capable)
+ domain_add_cpu_ctrl(cpu, r);
+ if (r->mon_capable)
+ domain_add_cpu_mon(cpu, r);
+}
+
+static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
{
- int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
- struct rdt_hw_domain *hw_dom;
- struct rdt_domain *d;
+ int id = get_domain_id_from_scope(cpu, r->ctrl_scope);
+ struct rdt_hw_ctrl_domain *hw_dom;
+ struct rdt_domain_hdr *hdr;
+ struct rdt_ctrl_domain *d;
lockdep_assert_held(&domain_list_lock);
- d = rdt_find_domain(r, id, NULL);
- if (IS_ERR_OR_NULL(d)) {
- pr_warn("Couldn't find cache id for CPU %d\n", cpu);
+ if (id < 0) {
+ pr_warn_once("Can't find control domain id for CPU:%d scope:%d for resource %s\n",
+ cpu, r->ctrl_scope, r->name);
+ return;
+ }
+
+ hdr = rdt_find_domain(&r->ctrl_domains, id, NULL);
+ if (!hdr) {
+ pr_warn("Can't find control domain for id=%d for CPU %d for resource %s\n",
+ id, cpu, r->name);
return;
}
- hw_dom = resctrl_to_arch_dom(d);
- cpumask_clear_cpu(cpu, &d->cpu_mask);
- if (cpumask_empty(&d->cpu_mask)) {
- resctrl_offline_domain(r, d);
- list_del_rcu(&d->list);
+ if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
+ return;
+
+ d = container_of(hdr, struct rdt_ctrl_domain, hdr);
+ hw_dom = resctrl_to_arch_ctrl_dom(d);
+
+ cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+ if (cpumask_empty(&d->hdr.cpu_mask)) {
+ resctrl_offline_ctrl_domain(r, d);
+ list_del_rcu(&d->hdr.list);
synchronize_rcu();
/*
- * rdt_domain "d" is going to be freed below, so clear
+ * rdt_ctrl_domain "d" is going to be freed below, so clear
* its pointer from pseudo_lock_region struct.
*/
if (d->plr)
d->plr->d = NULL;
- domain_free(hw_dom);
+ ctrl_domain_free(hw_dom);
return;
}
}
+static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
+{
+ int id = get_domain_id_from_scope(cpu, r->mon_scope);
+ struct rdt_hw_mon_domain *hw_dom;
+ struct rdt_domain_hdr *hdr;
+ struct rdt_mon_domain *d;
+
+ lockdep_assert_held(&domain_list_lock);
+
+ if (id < 0) {
+ pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n",
+ cpu, r->mon_scope, r->name);
+ return;
+ }
+
+ hdr = rdt_find_domain(&r->mon_domains, id, NULL);
+ if (!hdr) {
+ pr_warn("Can't find monitor domain for id=%d for CPU %d for resource %s\n",
+ id, cpu, r->name);
+ return;
+ }
+
+ if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
+ return;
+
+ d = container_of(hdr, struct rdt_mon_domain, hdr);
+ hw_dom = resctrl_to_arch_mon_dom(d);
+
+ cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
+ if (cpumask_empty(&d->hdr.cpu_mask)) {
+ resctrl_offline_mon_domain(r, d);
+ list_del_rcu(&d->hdr.list);
+ synchronize_rcu();
+ mon_domain_free(hw_dom);
+
+ return;
+ }
+}
+
+static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+{
+ if (r->alloc_capable)
+ domain_remove_cpu_ctrl(cpu, r);
+ if (r->mon_capable)
+ domain_remove_cpu_mon(cpu, r);
+}
+
static void clear_closid_rmid(int cpu)
{
struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index b7291f60399c..50fa1fe9a073 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -60,7 +60,7 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
}
int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
- struct rdt_domain *d)
+ struct rdt_ctrl_domain *d)
{
struct resctrl_staged_config *cfg;
u32 closid = data->rdtgrp->closid;
@@ -69,7 +69,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
cfg = &d->staged_config[s->conf_type];
if (cfg->have_new_ctrl) {
- rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
+ rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
return -EINVAL;
}
@@ -139,7 +139,7 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
* resource type.
*/
int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
- struct rdt_domain *d)
+ struct rdt_ctrl_domain *d)
{
struct rdtgroup *rdtgrp = data->rdtgrp;
struct resctrl_staged_config *cfg;
@@ -148,7 +148,7 @@ int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
cfg = &d->staged_config[s->conf_type];
if (cfg->have_new_ctrl) {
- rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
+ rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
return -EINVAL;
}
@@ -208,8 +208,8 @@ static int parse_line(char *line, struct resctrl_schema *s,
struct resctrl_staged_config *cfg;
struct rdt_resource *r = s->res;
struct rdt_parse_data data;
+ struct rdt_ctrl_domain *d;
char *dom = NULL, *id;
- struct rdt_domain *d;
unsigned long dom_id;
/* Walking r->domains, ensure it can't race with cpuhp */
@@ -231,8 +231,8 @@ next:
return -EINVAL;
}
dom = strim(dom);
- list_for_each_entry(d, &r->domains, list) {
- if (d->id == dom_id) {
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+ if (d->hdr.id == dom_id) {
data.buf = dom;
data.rdtgrp = rdtgrp;
if (r->parse_ctrlval(&data, s, d))
@@ -272,15 +272,15 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
}
}
-int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
u32 closid, enum resctrl_conf_type t, u32 cfg_val)
{
+ struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
u32 idx = get_config_index(closid, t);
struct msr_param msr_param;
- if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+ if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
return -EINVAL;
hw_dom->ctrl_val[idx] = cfg_val;
@@ -297,17 +297,17 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
{
struct resctrl_staged_config *cfg;
- struct rdt_hw_domain *hw_dom;
+ struct rdt_hw_ctrl_domain *hw_dom;
struct msr_param msr_param;
+ struct rdt_ctrl_domain *d;
enum resctrl_conf_type t;
- struct rdt_domain *d;
u32 idx;
/* Walking r->domains, ensure it can't race with cpuhp */
lockdep_assert_cpus_held();
- list_for_each_entry(d, &r->domains, list) {
- hw_dom = resctrl_to_arch_dom(d);
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+ hw_dom = resctrl_to_arch_ctrl_dom(d);
msr_param.res = NULL;
for (t = 0; t < CDP_NUM_TYPES; t++) {
cfg = &hw_dom->d_resctrl.staged_config[t];
@@ -330,7 +330,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
}
}
if (msr_param.res)
- smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
+ smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
}
return 0;
@@ -430,10 +430,10 @@ out:
return ret ?: nbytes;
}
-u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
+u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
u32 closid, enum resctrl_conf_type type)
{
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
u32 idx = get_config_index(closid, type);
return hw_dom->ctrl_val[idx];
@@ -442,7 +442,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
{
struct rdt_resource *r = schema->res;
- struct rdt_domain *dom;
+ struct rdt_ctrl_domain *dom;
bool sep = false;
u32 ctrl_val;
@@ -450,7 +450,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
lockdep_assert_cpus_held();
seq_printf(s, "%*s:", max_name_width, schema->name);
- list_for_each_entry(dom, &r->domains, list) {
+ list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
if (sep)
seq_puts(s, ";");
@@ -460,7 +460,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
ctrl_val = resctrl_arch_get_config(r, dom, closid,
schema->conf_type);
- seq_printf(s, r->format_str, dom->id, max_data_width,
+ seq_printf(s, r->format_str, dom->hdr.id, max_data_width,
ctrl_val);
sep = true;
}
@@ -489,7 +489,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
} else {
seq_printf(s, "%s:%d=%x\n",
rdtgrp->plr->s->res->name,
- rdtgrp->plr->d->id,
+ rdtgrp->plr->d->hdr.id,
rdtgrp->plr->cbm);
}
} else {
@@ -514,8 +514,8 @@ static int smp_mon_event_count(void *arg)
}
void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
- struct rdt_domain *d, struct rdtgroup *rdtgrp,
- int evtid, int first)
+ struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+ cpumask_t *cpumask, int evtid, int first)
{
int cpu;
@@ -529,7 +529,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
rr->evtid = evtid;
rr->r = r;
rr->d = d;
- rr->val = 0;
rr->first = first;
rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
if (IS_ERR(rr->arch_mon_ctx)) {
@@ -537,7 +536,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
return;
}
- cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU);
+ cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
/*
* cpumask_any_housekeeping() prefers housekeeping CPUs, but
@@ -546,7 +545,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
* counters on some platforms if its called in IRQ context.
*/
if (tick_nohz_full_cpu(cpu))
- smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+ smp_call_function_any(cpumask, mon_event_count, rr, 1);
else
smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
@@ -556,12 +555,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
int rdtgroup_mondata_show(struct seq_file *m, void *arg)
{
struct kernfs_open_file *of = m->private;
+ struct rdt_domain_hdr *hdr;
+ struct rmid_read rr = {0};
+ struct rdt_mon_domain *d;
u32 resid, evtid, domid;
struct rdtgroup *rdtgrp;
struct rdt_resource *r;
union mon_data_bits md;
- struct rdt_domain *d;
- struct rmid_read rr;
int ret = 0;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
@@ -574,15 +574,40 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
resid = md.u.rid;
domid = md.u.domid;
evtid = md.u.evtid;
-
r = &rdt_resources_all[resid].r_resctrl;
- d = rdt_find_domain(r, domid, NULL);
- if (IS_ERR_OR_NULL(d)) {
+
+ if (md.u.sum) {
+ /*
+ * This file requires summing across all domains that share
+ * the L3 cache id that was provided in the "domid" field of the
+ * mon_data_bits union. Search all domains in the resource for
+ * one that matches this cache id.
+ */
+ list_for_each_entry(d, &r->mon_domains, hdr.list) {
+ if (d->ci->id == domid) {
+ rr.ci = d->ci;
+ mon_event_read(&rr, r, NULL, rdtgrp,
+ &d->ci->shared_cpu_map, evtid, false);
+ goto checkresult;
+ }
+ }
ret = -ENOENT;
goto out;
+ } else {
+ /*
+ * This file provides data from a single domain. Search
+ * the resource to find the domain with "domid".
+ */
+ hdr = rdt_find_domain(&r->mon_domains, domid, NULL);
+ if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
+ ret = -ENOENT;
+ goto out;
+ }
+ d = container_of(hdr, struct rdt_mon_domain, hdr);
+ mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false);
}
- mon_event_read(&rr, r, d, rdtgrp, evtid, false);
+checkresult:
if (rr.err == -EIO)
seq_puts(m, "Error\n");
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index f1d926832ec8..955999aecfca 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -127,29 +127,54 @@ struct mon_evt {
};
/**
- * union mon_data_bits - Monitoring details for each event file
+ * union mon_data_bits - Monitoring details for each event file.
* @priv: Used to store monitoring event data in @u
- * as kernfs private data
- * @rid: Resource id associated with the event file
- * @evtid: Event id associated with the event file
- * @domid: The domain to which the event file belongs
- * @u: Name of the bit fields struct
+ * as kernfs private data.
+ * @u.rid: Resource id associated with the event file.
+ * @u.evtid: Event id associated with the event file.
+ * @u.sum: Set when event must be summed across multiple
+ * domains.
+ * @u.domid: When @u.sum is zero this is the domain to which
+ * the event file belongs. When @sum is one this
+ * is the id of the L3 cache that all domains to be
+ * summed share.
+ * @u: Name of the bit fields struct.
*/
union mon_data_bits {
void *priv;
struct {
unsigned int rid : 10;
- enum resctrl_event_id evtid : 8;
+ enum resctrl_event_id evtid : 7;
+ unsigned int sum : 1;
unsigned int domid : 14;
} u;
};
+/**
+ * struct rmid_read - Data passed across smp_call*() to read event count.
+ * @rgrp: Resource group for which the counter is being read. If it is a parent
+ * resource group then its event count is summed with the count from all
+ * its child resource groups.
+ * @r: Resource describing the properties of the event being read.
+ * @d: Domain that the counter should be read from. If NULL then sum all
+ * domains in @r sharing L3 @ci.id
+ * @evtid: Which monitor event to read.
+ * @first: Initialize MBM counter when true.
+ * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @err: Error encountered when reading counter.
+ * @val: Returned value of event counter. If @rgrp is a parent resource group,
+ * @val includes the sum of event counts from its child resource groups.
+ * If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id,
+ * (summed across child resource groups if @rgrp is a parent resource group).
+ * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only).
+ */
struct rmid_read {
struct rdtgroup *rgrp;
struct rdt_resource *r;
- struct rdt_domain *d;
+ struct rdt_mon_domain *d;
enum resctrl_event_id evtid;
bool first;
+ struct cacheinfo *ci;
int err;
u64 val;
void *arch_mon_ctx;
@@ -232,7 +257,7 @@ struct mongroup {
*/
struct pseudo_lock_region {
struct resctrl_schema *s;
- struct rdt_domain *d;
+ struct rdt_ctrl_domain *d;
u32 cbm;
wait_queue_head_t lock_thread_wq;
int thread_done;
@@ -355,25 +380,41 @@ struct arch_mbm_state {
};
/**
- * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share
- * a resource
+ * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share
+ * a resource for a control function
* @d_resctrl: Properties exposed to the resctrl file system
* @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID)
+ *
+ * Members of this structure are accessed via helpers that provide abstraction.
+ */
+struct rdt_hw_ctrl_domain {
+ struct rdt_ctrl_domain d_resctrl;
+ u32 *ctrl_val;
+};
+
+/**
+ * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share
+ * a resource for a monitor function
+ * @d_resctrl: Properties exposed to the resctrl file system
* @arch_mbm_total: arch private state for MBM total bandwidth
* @arch_mbm_local: arch private state for MBM local bandwidth
*
* Members of this structure are accessed via helpers that provide abstraction.
*/
-struct rdt_hw_domain {
- struct rdt_domain d_resctrl;
- u32 *ctrl_val;
+struct rdt_hw_mon_domain {
+ struct rdt_mon_domain d_resctrl;
struct arch_mbm_state *arch_mbm_total;
struct arch_mbm_state *arch_mbm_local;
};
-static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
+static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r)
{
- return container_of(r, struct rdt_hw_domain, d_resctrl);
+ return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl);
+}
+
+static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r)
+{
+ return container_of(r, struct rdt_hw_mon_domain, d_resctrl);
}
/**
@@ -385,7 +426,7 @@ static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
*/
struct msr_param {
struct rdt_resource *res;
- struct rdt_domain *dom;
+ struct rdt_ctrl_domain *dom;
u32 low;
u32 high;
};
@@ -458,9 +499,9 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
}
int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
- struct rdt_domain *d);
+ struct rdt_ctrl_domain *d);
int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
- struct rdt_domain *d);
+ struct rdt_ctrl_domain *d);
extern struct mutex rdtgroup_mutex;
@@ -493,6 +534,8 @@ static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
+
/*
* To return the common struct rdt_resource, which is contained in struct
* rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource.
@@ -558,27 +601,28 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn);
int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
umode_t mask);
-struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
- struct list_head **pos);
+struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,
+ struct list_head **pos);
ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off);
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v);
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
unsigned long cbm, int closid, bool exclusive);
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
unsigned long cbm);
enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
int rdtgroup_tasks_assigned(struct rdtgroup *r);
int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm);
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
int rdt_pseudo_lock_init(void);
void rdt_pseudo_lock_release(void);
int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
-struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
+struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r);
+struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r);
int closids_supported(void);
void closid_free(int closid);
int alloc_rmid(u32 closid);
@@ -589,19 +633,19 @@ bool __init rdt_cpu_has(int flag);
void mon_event_count(void *info);
int rdtgroup_mondata_show(struct seq_file *m, void *arg);
void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
- struct rdt_domain *d, struct rdtgroup *rdtgrp,
- int evtid, int first);
-void mbm_setup_overflow_handler(struct rdt_domain *dom,
+ struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+ cpumask_t *cpumask, int evtid, int first);
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
unsigned long delay_ms,
int exclude_cpu);
void mbm_handle_overflow(struct work_struct *work);
void __init intel_rdt_mbm_apply_quirk(void);
bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
int exclude_cpu);
void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_domain *d);
-void __check_limbo(struct rdt_domain *d, bool force_free);
+bool has_busy_rmid(struct rdt_mon_domain *d);
+void __check_limbo(struct rdt_mon_domain *d, bool force_free);
void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
void __init thread_throttle_mode_init(void);
void __init mbm_config_rftype_init(const char *config);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 366f496ca3ce..851b561850e0 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -15,6 +15,8 @@
* Software Developer Manual June 2016, volume 3, section 17.17.
*/
+#define pr_fmt(fmt) "resctrl: " fmt
+
#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/sizes.h>
@@ -97,6 +99,8 @@ unsigned int resctrl_rmid_realloc_limit;
#define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5))
+static int snc_nodes_per_l3_cache = 1;
+
/*
* The correction factor table is documented in Documentation/arch/x86/resctrl.rst.
* If rmid > rmid threshold, MBM total and local values should be multiplied
@@ -185,7 +189,43 @@ static inline struct rmid_entry *__rmid_entry(u32 idx)
return entry;
}
-static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+/*
+ * When Sub-NUMA Cluster (SNC) mode is not enabled (as indicated by
+ * "snc_nodes_per_l3_cache == 1") no translation of the RMID value is
+ * needed. The physical RMID is the same as the logical RMID.
+ *
+ * On a platform with SNC mode enabled, Linux enables RMID sharing mode
+ * via MSR 0xCA0 (see the "RMID Sharing Mode" section in the "Intel
+ * Resource Director Technology Architecture Specification" for a full
+ * description of RMID sharing mode).
+ *
+ * In RMID sharing mode there are fewer "logical RMID" values available
+ * to accumulate data ("physical RMIDs" are divided evenly between SNC
+ * nodes that share an L3 cache). Linux creates an rdt_mon_domain for
+ * each SNC node.
+ *
+ * The value loaded into IA32_PQR_ASSOC is the "logical RMID".
+ *
+ * Data is collected independently on each SNC node and can be retrieved
+ * using the "physical RMID" value computed by this function and loaded
+ * into IA32_QM_EVTSEL. @cpu can be any CPU in the SNC node.
+ *
+ * The scope of the IA32_QM_EVTSEL and IA32_QM_CTR MSRs is at the L3
+ * cache. So a "physical RMID" may be read from any CPU that shares
+ * the L3 cache with the desired SNC node, not just from a CPU in
+ * the specific SNC node.
+ */
+static int logical_rmid_to_physical_rmid(int cpu, int lrmid)
+{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
+ if (snc_nodes_per_l3_cache == 1)
+ return lrmid;
+
+ return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+}
+
+static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
{
u64 msr_val;
@@ -197,7 +237,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
* IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
* are error bits.
*/
- wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+ wrmsr(MSR_IA32_QM_EVTSEL, eventid, prmid);
rdmsrl(MSR_IA32_QM_CTR, msr_val);
if (msr_val & RMID_VAL_ERROR)
@@ -209,7 +249,7 @@ static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
return 0;
}
-static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom,
u32 rmid,
enum resctrl_event_id eventid)
{
@@ -228,19 +268,22 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
return NULL;
}
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
u32 unused, u32 rmid,
enum resctrl_event_id eventid)
{
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+ int cpu = cpumask_any(&d->hdr.cpu_mask);
struct arch_mbm_state *am;
+ u32 prmid;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
if (am) {
memset(am, 0, sizeof(*am));
+ prmid = logical_rmid_to_physical_rmid(cpu, rmid);
/* Record any initial, non-zero count value. */
- __rmid_read(rmid, eventid, &am->prev_msr);
+ __rmid_read_phys(prmid, eventid, &am->prev_msr);
}
}
@@ -248,9 +291,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
* Assumes that hardware counters are also reset and thus that there is
* no need to record initial non-zero counts.
*/
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
{
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
if (is_mbm_total_enabled())
memset(hw_dom->arch_mbm_total, 0,
@@ -269,22 +312,22 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
return chunks >> shift;
}
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
u32 unused, u32 rmid, enum resctrl_event_id eventid,
u64 *val, void *ignored)
{
+ struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ int cpu = cpumask_any(&d->hdr.cpu_mask);
struct arch_mbm_state *am;
u64 msr_val, chunks;
+ u32 prmid;
int ret;
resctrl_arch_rmid_read_context_check();
- if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
- return -EINVAL;
-
- ret = __rmid_read(rmid, eventid, &msr_val);
+ prmid = logical_rmid_to_physical_rmid(cpu, rmid);
+ ret = __rmid_read_phys(prmid, eventid, &msr_val);
if (ret)
return ret;
@@ -320,7 +363,7 @@ static void limbo_release_entry(struct rmid_entry *entry)
* decrement the count. If the busy count gets to zero on an RMID, we
* free the RMID
*/
-void __check_limbo(struct rdt_domain *d, bool force_free)
+void __check_limbo(struct rdt_mon_domain *d, bool force_free)
{
struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
u32 idx_limit = resctrl_arch_system_num_rmid_idx();
@@ -364,7 +407,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
* CLOSID and RMID because there may be dependencies between them
* on some architectures.
*/
- trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->id, val);
+ trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val);
}
if (force_free || !rmid_dirty) {
@@ -378,7 +421,7 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
}
-bool has_busy_rmid(struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_mon_domain *d)
{
u32 idx_limit = resctrl_arch_system_num_rmid_idx();
@@ -479,7 +522,7 @@ int alloc_rmid(u32 closid)
static void add_rmid_to_limbo(struct rmid_entry *entry)
{
struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
- struct rdt_domain *d;
+ struct rdt_mon_domain *d;
u32 idx;
lockdep_assert_held(&rdtgroup_mutex);
@@ -490,7 +533,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
entry->busy = 0;
- list_for_each_entry(d, &r->domains, list) {
+ list_for_each_entry(d, &r->mon_domains, hdr.list) {
/*
* For the first limbo RMID in the domain,
* setup up the limbo worker.
@@ -532,7 +575,7 @@ void free_rmid(u32 closid, u32 rmid)
list_add_tail(&entry->list, &rmid_free_lru);
}
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid,
+static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
u32 rmid, enum resctrl_event_id evtid)
{
u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
@@ -549,7 +592,10 @@ static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid,
static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
{
+ int cpu = smp_processor_id();
+ struct rdt_mon_domain *d;
struct mbm_state *m;
+ int err, ret;
u64 tval = 0;
if (rr->first) {
@@ -560,14 +606,47 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
return 0;
}
- rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid,
- &tval, rr->arch_mon_ctx);
- if (rr->err)
- return rr->err;
+ if (rr->d) {
+ /* Reading a single domain, must be on a CPU in that domain. */
+ if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
+ return -EINVAL;
+ rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
+ rr->evtid, &tval, rr->arch_mon_ctx);
+ if (rr->err)
+ return rr->err;
- rr->val += tval;
+ rr->val += tval;
- return 0;
+ return 0;
+ }
+
+ /* Summing domains that share a cache, must be on a CPU for that cache. */
+ if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+ return -EINVAL;
+
+ /*
+ * Legacy files must report the sum of an event across all
+ * domains that share the same L3 cache instance.
+ * Report success if a read from any domain succeeds, -EINVAL
+ * (translated to "Unavailable" for user space) if reading from
+ * all domains fail for any reason.
+ */
+ ret = -EINVAL;
+ list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
+ if (d->ci->id != rr->ci->id)
+ continue;
+ err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
+ rr->evtid, &tval, rr->arch_mon_ctx);
+ if (!err) {
+ rr->val += tval;
+ ret = 0;
+ }
+ }
+
+ if (ret)
+ rr->err = ret;
+
+ return ret;
}
/*
@@ -668,12 +747,12 @@ void mon_event_count(void *info)
* throttle MSRs already have low percentage values. To avoid
* unnecessarily restricting such rdtgroups, we also increase the bandwidth.
*/
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
{
u32 closid, rmid, cur_msr_val, new_msr_val;
struct mbm_state *pmbm_data, *cmbm_data;
+ struct rdt_ctrl_domain *dom_mba;
struct rdt_resource *r_mba;
- struct rdt_domain *dom_mba;
u32 cur_bw, user_bw, idx;
struct list_head *head;
struct rdtgroup *entry;
@@ -688,7 +767,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
idx = resctrl_arch_rmid_idx_encode(closid, rmid);
pmbm_data = &dom_mbm->mbm_local[idx];
- dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
+ dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
if (!dom_mba) {
pr_warn_once("Failure to get domain for MBA update\n");
return;
@@ -734,12 +813,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
}
-static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
u32 closid, u32 rmid)
{
- struct rmid_read rr;
+ struct rmid_read rr = {0};
- rr.first = false;
rr.r = r;
rr.d = d;
@@ -792,17 +870,17 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
void cqm_handle_limbo(struct work_struct *work)
{
unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
- struct rdt_domain *d;
+ struct rdt_mon_domain *d;
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
- d = container_of(work, struct rdt_domain, cqm_limbo.work);
+ d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
__check_limbo(d, false);
if (has_busy_rmid(d)) {
- d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+ d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
RESCTRL_PICK_ANY_CPU);
schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
delay);
@@ -820,13 +898,13 @@ void cqm_handle_limbo(struct work_struct *work)
* @exclude_cpu: Which CPU the handler should not run on,
* RESCTRL_PICK_ANY_CPU to pick any CPU.
*/
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
int cpu;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
+ cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
dom->cqm_work_cpu = cpu;
if (cpu < nr_cpu_ids)
@@ -837,9 +915,9 @@ void mbm_handle_overflow(struct work_struct *work)
{
unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
struct rdtgroup *prgrp, *crgrp;
+ struct rdt_mon_domain *d;
struct list_head *head;
struct rdt_resource *r;
- struct rdt_domain *d;
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
@@ -852,7 +930,7 @@ void mbm_handle_overflow(struct work_struct *work)
goto out_unlock;
r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
- d = container_of(work, struct rdt_domain, mbm_over.work);
+ d = container_of(work, struct rdt_mon_domain, mbm_over.work);
list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
@@ -869,7 +947,7 @@ void mbm_handle_overflow(struct work_struct *work)
* Re-check for housekeeping CPUs. This allows the overflow handler to
* move off a nohz_full CPU quickly.
*/
- d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+ d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
RESCTRL_PICK_ANY_CPU);
schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
@@ -886,7 +964,7 @@ out_unlock:
* @exclude_cpu: Which CPU the handler should not run on,
* RESCTRL_PICK_ANY_CPU to pick any CPU.
*/
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
@@ -898,7 +976,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
*/
if (!resctrl_mounted || !resctrl_arch_mon_capable())
return;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
+ cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
dom->mbm_work_cpu = cpu;
if (cpu < nr_cpu_ids)
@@ -1015,6 +1093,88 @@ static void l3_mon_evt_init(struct rdt_resource *r)
list_add_tail(&mbm_local_event.list, &r->evt_list);
}
+/*
+ * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
+ * which indicates that RMIDs are configured in legacy mode.
+ * This mode is incompatible with Linux resctrl semantics
+ * as RMIDs are partitioned between SNC nodes, which requires
+ * a user to know which RMID is allocated to a task.
+ * Clearing bit 0 reconfigures the RMID counters for use
+ * in RMID sharing mode. This mode is better for Linux.
+ * The RMID space is divided between all SNC nodes with the
+ * RMIDs renumbered to start from zero in each node when
+ * counting operations from tasks. Code to read the counters
+ * must adjust RMID counter numbers based on SNC node. See
+ * logical_rmid_to_physical_rmid() for code that does this.
+ */
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+ if (snc_nodes_per_l3_cache > 1)
+ msr_clear_bit(MSR_RMID_SNC_CONFIG, 0);
+}
+
+/* CPU models that support MSR_RMID_SNC_CONFIG */
+static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
+ X86_MATCH_VFM(INTEL_ICELAKE_X, 0),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0),
+ X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, 0),
+ X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, 0),
+ X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, 0),
+ {}
+};
+
+/*
+ * There isn't a simple hardware bit that indicates whether a CPU is running
+ * in Sub-NUMA Cluster (SNC) mode. Infer the state by comparing the
+ * number of CPUs sharing the L3 cache with CPU0 to the number of CPUs in
+ * the same NUMA node as CPU0.
+ * It is not possible to accurately determine SNC state if the system is
+ * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes
+ * to L3 caches. It will be OK if system is booted with hyperthreading
+ * disabled (since this doesn't affect the ratio).
+ */
+static __init int snc_get_config(void)
+{
+ struct cacheinfo *ci = get_cpu_cacheinfo_level(0, RESCTRL_L3_CACHE);
+ const cpumask_t *node0_cpumask;
+ int cpus_per_node, cpus_per_l3;
+ int ret;
+
+ if (!x86_match_cpu(snc_cpu_ids) || !ci)
+ return 1;
+
+ cpus_read_lock();
+ if (num_online_cpus() != num_present_cpus())
+ pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
+ cpus_read_unlock();
+
+ node0_cpumask = cpumask_of_node(cpu_to_node(0));
+
+ cpus_per_node = cpumask_weight(node0_cpumask);
+ cpus_per_l3 = cpumask_weight(&ci->shared_cpu_map);
+
+ if (!cpus_per_node || !cpus_per_l3)
+ return 1;
+
+ ret = cpus_per_l3 / cpus_per_node;
+
+ /* sanity check: Only valid results are 1, 2, 3, 4 */
+ switch (ret) {
+ case 1:
+ break;
+ case 2 ... 4:
+ pr_info("Sub-NUMA Cluster mode detected with %d nodes per L3 cache\n", ret);
+ rdt_resources_all[RDT_RESOURCE_L3].r_resctrl.mon_scope = RESCTRL_L3_NODE;
+ break;
+ default:
+ pr_warn("Ignore improbable SNC node count %d\n", ret);
+ ret = 1;
+ break;
+ }
+
+ return ret;
+}
+
int __init rdt_get_mon_l3_config(struct rdt_resource *r)
{
unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
@@ -1022,9 +1182,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
unsigned int threshold;
int ret;
+ snc_nodes_per_l3_cache = snc_get_config();
+
resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
- hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
- r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+ hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
+ r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index aacf236dfe3b..e69489d48625 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -11,7 +11,6 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/debugfs.h>
@@ -221,7 +220,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
int cpu;
int ret;
- for_each_cpu(cpu, &plr->d->cpu_mask) {
+ for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
if (!pm_req) {
rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
@@ -292,12 +291,15 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
*/
static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
{
- struct cpu_cacheinfo *ci;
+ enum resctrl_scope scope = plr->s->res->ctrl_scope;
+ struct cacheinfo *ci;
int ret;
- int i;
+
+ if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+ return -ENODEV;
/* Pick the first cpu we find that is associated with the cache. */
- plr->cpu = cpumask_first(&plr->d->cpu_mask);
+ plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
if (!cpu_online(plr->cpu)) {
rdt_last_cmd_printf("CPU %u associated with cache not online\n",
@@ -306,15 +308,11 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
goto out_region;
}
- ci = get_cpu_cacheinfo(plr->cpu);
-
- plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
-
- for (i = 0; i < ci->num_leaves; i++) {
- if (ci->info_list[i].level == plr->s->res->cache_level) {
- plr->line_size = ci->info_list[i].coherency_line_size;
- return 0;
- }
+ ci = get_cpu_cacheinfo_level(plr->cpu, scope);
+ if (ci) {
+ plr->line_size = ci->coherency_line_size;
+ plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
+ return 0;
}
ret = -1;
@@ -810,7 +808,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
* Return: true if @cbm overlaps with pseudo-locked region on @d, false
* otherwise.
*/
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
{
unsigned int cbm_len;
unsigned long cbm_b;
@@ -837,11 +835,11 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm
* if it is not possible to test due to memory allocation issue,
* false otherwise.
*/
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
{
+ struct rdt_ctrl_domain *d_i;
cpumask_var_t cpu_with_psl;
struct rdt_resource *r;
- struct rdt_domain *d_i;
bool ret = false;
/* Walking r->domains, ensure it can't race with cpuhp */
@@ -855,10 +853,10 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
* associated with them.
*/
for_each_alloc_capable_rdt_resource(r) {
- list_for_each_entry(d_i, &r->domains, list) {
+ list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) {
if (d_i->plr)
cpumask_or(cpu_with_psl, cpu_with_psl,
- &d_i->cpu_mask);
+ &d_i->hdr.cpu_mask);
}
}
@@ -866,7 +864,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
* Next test if new pseudo-locked region would intersect with
* existing region.
*/
- if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+ if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
ret = true;
free_cpumask_var(cpu_with_psl);
@@ -1198,7 +1196,7 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
}
plr->thread_done = 0;
- cpu = cpumask_first(&plr->d->cpu_mask);
+ cpu = cpumask_first(&plr->d->hdr.cpu_mask);
if (!cpu_online(cpu)) {
ret = -ENODEV;
goto out;
@@ -1528,7 +1526,7 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
* may be scheduled elsewhere and invalidate entries in the
* pseudo-locked region.
*/
- if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) {
+ if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
mutex_unlock(&rdtgroup_mutex);
return -EINVAL;
}
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 02f213f1c51c..d7163b764c62 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -12,7 +12,6 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
#include <linux/fs.h>
@@ -92,13 +91,13 @@ void rdt_last_cmd_printf(const char *fmt, ...)
void rdt_staged_configs_clear(void)
{
+ struct rdt_ctrl_domain *dom;
struct rdt_resource *r;
- struct rdt_domain *dom;
lockdep_assert_held(&rdtgroup_mutex);
for_each_alloc_capable_rdt_resource(r) {
- list_for_each_entry(dom, &r->domains, list)
+ list_for_each_entry(dom, &r->ctrl_domains, hdr.list)
memset(dom->staged_config, 0, sizeof(dom->staged_config));
}
}
@@ -317,7 +316,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
rdt_last_cmd_puts("Cache domain offline\n");
ret = -ENODEV;
} else {
- mask = &rdtgrp->plr->d->cpu_mask;
+ mask = &rdtgrp->plr->d->hdr.cpu_mask;
seq_printf(s, is_cpu_list(of) ?
"%*pbl\n" : "%*pb\n",
cpumask_pr_args(mask));
@@ -1012,7 +1011,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
unsigned long sw_shareable = 0, hw_shareable = 0;
unsigned long exclusive = 0, pseudo_locked = 0;
struct rdt_resource *r = s->res;
- struct rdt_domain *dom;
+ struct rdt_ctrl_domain *dom;
int i, hwb, swb, excl, psl;
enum rdtgrp_mode mode;
bool sep = false;
@@ -1021,12 +1020,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
hw_shareable = r->cache.shareable_bits;
- list_for_each_entry(dom, &r->domains, list) {
+ list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
if (sep)
seq_putc(seq, ';');
sw_shareable = 0;
exclusive = 0;
- seq_printf(seq, "%d=", dom->id);
+ seq_printf(seq, "%d=", dom->hdr.id);
for (i = 0; i < closids_supported(); i++) {
if (!closid_allocated(i))
continue;
@@ -1243,7 +1242,7 @@ static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
*
* Return: false if CBM does not overlap, true if it does.
*/
-static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_ctrl_domain *d,
unsigned long cbm, int closid,
enum resctrl_conf_type type, bool exclusive)
{
@@ -1298,7 +1297,7 @@ static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d
*
* Return: true if CBM overlap detected, false if there is no overlap
*/
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
unsigned long cbm, int closid, bool exclusive)
{
enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
@@ -1329,10 +1328,10 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
{
int closid = rdtgrp->closid;
+ struct rdt_ctrl_domain *d;
struct resctrl_schema *s;
struct rdt_resource *r;
bool has_cache = false;
- struct rdt_domain *d;
u32 ctrl;
/* Walking r->domains, ensure it can't race with cpuhp */
@@ -1343,7 +1342,7 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
continue;
has_cache = true;
- list_for_each_entry(d, &r->domains, list) {
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
ctrl = resctrl_arch_get_config(r, d, closid,
s->conf_type);
if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
@@ -1448,20 +1447,19 @@ out:
* bitmap functions work correctly.
*/
unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
- struct rdt_domain *d, unsigned long cbm)
+ struct rdt_ctrl_domain *d, unsigned long cbm)
{
- struct cpu_cacheinfo *ci;
unsigned int size = 0;
- int num_b, i;
+ struct cacheinfo *ci;
+ int num_b;
+
+ if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE))
+ return size;
num_b = bitmap_weight(&cbm, r->cache.cbm_len);
- ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
- for (i = 0; i < ci->num_leaves; i++) {
- if (ci->info_list[i].level == r->cache_level) {
- size = ci->info_list[i].size / r->cache.cbm_len * num_b;
- break;
- }
- }
+ ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope);
+ if (ci)
+ size = ci->size / r->cache.cbm_len * num_b;
return size;
}
@@ -1477,9 +1475,9 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
{
struct resctrl_schema *schema;
enum resctrl_conf_type type;
+ struct rdt_ctrl_domain *d;
struct rdtgroup *rdtgrp;
struct rdt_resource *r;
- struct rdt_domain *d;
unsigned int size;
int ret = 0;
u32 closid;
@@ -1503,7 +1501,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
rdtgrp->plr->d,
rdtgrp->plr->cbm);
- seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+ seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size);
}
goto out;
}
@@ -1515,7 +1513,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
type = schema->conf_type;
sep = false;
seq_printf(s, "%*s:", max_name_width, schema->name);
- list_for_each_entry(d, &r->domains, list) {
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
if (sep)
seq_putc(s, ';');
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
@@ -1533,7 +1531,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
else
size = rdtgroup_cbm_to_size(r, d, ctrl);
}
- seq_printf(s, "%d=%u", d->id, size);
+ seq_printf(s, "%d=%u", d->hdr.id, size);
sep = true;
}
seq_putc(s, '\n');
@@ -1591,21 +1589,21 @@ static void mon_event_config_read(void *info)
mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
}
-static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mon_info)
+static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info *mon_info)
{
- smp_call_function_any(&d->cpu_mask, mon_event_config_read, mon_info, 1);
+ smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1);
}
static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
{
struct mon_config_info mon_info = {0};
- struct rdt_domain *dom;
+ struct rdt_mon_domain *dom;
bool sep = false;
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
- list_for_each_entry(dom, &r->domains, list) {
+ list_for_each_entry(dom, &r->mon_domains, hdr.list) {
if (sep)
seq_puts(s, ";");
@@ -1613,7 +1611,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
mon_info.evtid = evtid;
mondata_config_read(dom, &mon_info);
- seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config);
+ seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
sep = true;
}
seq_puts(s, "\n");
@@ -1658,7 +1656,7 @@ static void mon_event_config_write(void *info)
}
static void mbm_config_write_domain(struct rdt_resource *r,
- struct rdt_domain *d, u32 evtid, u32 val)
+ struct rdt_mon_domain *d, u32 evtid, u32 val)
{
struct mon_config_info mon_info = {0};
@@ -1679,7 +1677,7 @@ static void mbm_config_write_domain(struct rdt_resource *r,
* are scoped at the domain level. Writing any of these MSRs
* on one CPU is observed by all the CPUs in the domain.
*/
- smp_call_function_any(&d->cpu_mask, mon_event_config_write,
+ smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write,
&mon_info, 1);
/*
@@ -1699,7 +1697,7 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
char *dom_str = NULL, *id_str;
unsigned long dom_id, val;
- struct rdt_domain *d;
+ struct rdt_mon_domain *d;
/* Walking r->domains, ensure it can't race with cpuhp */
lockdep_assert_cpus_held();
@@ -1729,8 +1727,8 @@ next:
return -EINVAL;
}
- list_for_each_entry(d, &r->domains, list) {
- if (d->id == dom_id) {
+ list_for_each_entry(d, &r->mon_domains, hdr.list) {
+ if (d->hdr.id == dom_id) {
mbm_config_write_domain(r, d, evtid, val);
goto next;
}
@@ -2258,9 +2256,9 @@ static inline bool is_mba_linear(void)
static int set_cache_qos_cfg(int level, bool enable)
{
void (*update)(void *arg);
+ struct rdt_ctrl_domain *d;
struct rdt_resource *r_l;
cpumask_var_t cpu_mask;
- struct rdt_domain *d;
int cpu;
/* Walking r->domains, ensure it can't race with cpuhp */
@@ -2277,14 +2275,14 @@ static int set_cache_qos_cfg(int level, bool enable)
return -ENOMEM;
r_l = &rdt_resources_all[level].r_resctrl;
- list_for_each_entry(d, &r_l->domains, list) {
+ list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) {
if (r_l->cache.arch_has_per_cpu_cfg)
/* Pick all the CPUs in the domain instance */
- for_each_cpu(cpu, &d->cpu_mask)
+ for_each_cpu(cpu, &d->hdr.cpu_mask)
cpumask_set_cpu(cpu, cpu_mask);
else
/* Pick one CPU from each domain instance to update MSR */
- cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+ cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
}
/* Update QOS_CFG MSR on all the CPUs in cpu_mask */
@@ -2310,10 +2308,10 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
l3_qos_cfg_update(&hw_res->cdp_enabled);
}
-static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
+static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d)
{
u32 num_closid = resctrl_arch_get_num_closid(r);
- int cpu = cpumask_any(&d->cpu_mask);
+ int cpu = cpumask_any(&d->hdr.cpu_mask);
int i;
d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
@@ -2328,7 +2326,7 @@ static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
}
static void mba_sc_domain_destroy(struct rdt_resource *r,
- struct rdt_domain *d)
+ struct rdt_ctrl_domain *d)
{
kfree(d->mbps_val);
d->mbps_val = NULL;
@@ -2336,14 +2334,18 @@ static void mba_sc_domain_destroy(struct rdt_resource *r,
/*
* MBA software controller is supported only if
- * MBM is supported and MBA is in linear scale.
+ * MBM is supported and MBA is in linear scale,
+ * and the MBM monitor scope is the same as MBA
+ * control scope.
*/
static bool supports_mba_mbps(void)
{
+ struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
return (is_mbm_local_enabled() &&
- r->alloc_capable && is_mba_linear());
+ r->alloc_capable && is_mba_linear() &&
+ r->ctrl_scope == rmbm->mon_scope);
}
/*
@@ -2354,7 +2356,7 @@ static int set_mba_sc(bool mba_sc)
{
struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
u32 num_closid = resctrl_arch_get_num_closid(r);
- struct rdt_domain *d;
+ struct rdt_ctrl_domain *d;
int i;
if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
@@ -2362,7 +2364,7 @@ static int set_mba_sc(bool mba_sc)
r->membw.mba_sc = mba_sc;
- list_for_each_entry(d, &r->domains, list) {
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
for (i = 0; i < num_closid; i++)
d->mbps_val[i] = MBA_MAX_MBPS;
}
@@ -2626,7 +2628,7 @@ static int rdt_get_tree(struct fs_context *fc)
{
struct rdt_fs_context *ctx = rdt_fc2context(fc);
unsigned long flags = RFTYPE_CTRL_BASE;
- struct rdt_domain *dom;
+ struct rdt_mon_domain *dom;
struct rdt_resource *r;
int ret;
@@ -2701,7 +2703,7 @@ static int rdt_get_tree(struct fs_context *fc)
if (is_mbm_enabled()) {
r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
- list_for_each_entry(dom, &r->domains, list)
+ list_for_each_entry(dom, &r->mon_domains, hdr.list)
mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
RESCTRL_PICK_ANY_CPU);
}
@@ -2751,6 +2753,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct rdt_fs_context *ctx = rdt_fc2context(fc);
struct fs_parse_result result;
+ const char *msg;
int opt;
opt = fs_parse(fc, rdt_fs_parameters, param, &result);
@@ -2765,8 +2768,9 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
ctx->enable_cdpl2 = true;
return 0;
case Opt_mba_mbps:
+ msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope";
if (!supports_mba_mbps())
- return -EINVAL;
+ return invalfc(fc, msg);
ctx->enable_mba_mbps = true;
return 0;
case Opt_debug:
@@ -2811,9 +2815,9 @@ static int rdt_init_fs_context(struct fs_context *fc)
static int reset_all_ctrls(struct rdt_resource *r)
{
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
- struct rdt_hw_domain *hw_dom;
+ struct rdt_hw_ctrl_domain *hw_dom;
struct msr_param msr_param;
- struct rdt_domain *d;
+ struct rdt_ctrl_domain *d;
int i;
/* Walking r->domains, ensure it can't race with cpuhp */
@@ -2825,16 +2829,16 @@ static int reset_all_ctrls(struct rdt_resource *r)
/*
* Disable resource control for this resource by setting all
- * CBMs in all domains to the maximum mask value. Pick one CPU
+ * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU
* from each domain to update the MSRs below.
*/
- list_for_each_entry(d, &r->domains, list) {
- hw_dom = resctrl_to_arch_dom(d);
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+ hw_dom = resctrl_to_arch_ctrl_dom(d);
for (i = 0; i < hw_res->num_closid; i++)
hw_dom->ctrl_val[i] = r->default_ctrl;
msr_param.dom = d;
- smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
+ smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
}
return 0;
@@ -3002,62 +3006,126 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
return ret;
}
+static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname)
+{
+ struct kernfs_node *kn;
+
+ kn = kernfs_find_and_get(pkn, name);
+ if (!kn)
+ return;
+ kernfs_put(kn);
+
+ if (kn->dir.subdirs <= 1)
+ kernfs_remove(kn);
+ else
+ kernfs_remove_by_name(kn, subname);
+}
+
/*
* Remove all subdirectories of mon_data of ctrl_mon groups
- * and monitor groups with given domain id.
+ * and monitor groups for the given domain.
+ * Remove files and directories containing "sum" of domain data
+ * when last domain being summed is removed.
*/
static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- unsigned int dom_id)
+ struct rdt_mon_domain *d)
{
struct rdtgroup *prgrp, *crgrp;
+ char subname[32];
+ bool snc_mode;
char name[32];
+ snc_mode = r->mon_scope == RESCTRL_L3_NODE;
+ sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+ if (snc_mode)
+ sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
+
list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
- sprintf(name, "mon_%s_%02d", r->name, dom_id);
- kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);
+ mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname);
list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
- kernfs_remove_by_name(crgrp->mon.mon_data_kn, name);
+ mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname);
}
}
-static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
- struct rdt_domain *d,
- struct rdt_resource *r, struct rdtgroup *prgrp)
+static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
+ struct rdt_resource *r, struct rdtgroup *prgrp,
+ bool do_sum)
{
+ struct rmid_read rr = {0};
union mon_data_bits priv;
- struct kernfs_node *kn;
struct mon_evt *mevt;
- struct rmid_read rr;
- char name[32];
int ret;
- sprintf(name, "mon_%s_%02d", r->name, d->id);
- /* create the directory */
- kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
- if (IS_ERR(kn))
- return PTR_ERR(kn);
-
- ret = rdtgroup_kn_set_ugid(kn);
- if (ret)
- goto out_destroy;
-
- if (WARN_ON(list_empty(&r->evt_list))) {
- ret = -EPERM;
- goto out_destroy;
- }
+ if (WARN_ON(list_empty(&r->evt_list)))
+ return -EPERM;
priv.u.rid = r->rid;
- priv.u.domid = d->id;
+ priv.u.domid = do_sum ? d->ci->id : d->hdr.id;
+ priv.u.sum = do_sum;
list_for_each_entry(mevt, &r->evt_list, list) {
priv.u.evtid = mevt->evtid;
ret = mon_addfile(kn, mevt->name, priv.priv);
if (ret)
+ return ret;
+
+ if (!do_sum && is_mbm_event(mevt->evtid))
+ mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true);
+ }
+
+ return 0;
+}
+
+static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
+ struct rdt_mon_domain *d,
+ struct rdt_resource *r, struct rdtgroup *prgrp)
+{
+ struct kernfs_node *kn, *ckn;
+ char name[32];
+ bool snc_mode;
+ int ret = 0;
+
+ lockdep_assert_held(&rdtgroup_mutex);
+
+ snc_mode = r->mon_scope == RESCTRL_L3_NODE;
+ sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+ kn = kernfs_find_and_get(parent_kn, name);
+ if (kn) {
+ /*
+ * rdtgroup_mutex will prevent this directory from being
+ * removed. No need to keep this hold.
+ */
+ kernfs_put(kn);
+ } else {
+ kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+ if (IS_ERR(kn))
+ return PTR_ERR(kn);
+
+ ret = rdtgroup_kn_set_ugid(kn);
+ if (ret)
+ goto out_destroy;
+ ret = mon_add_all_files(kn, d, r, prgrp, snc_mode);
+ if (ret)
+ goto out_destroy;
+ }
+
+ if (snc_mode) {
+ sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id);
+ ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
+ if (IS_ERR(ckn)) {
+ ret = -EINVAL;
+ goto out_destroy;
+ }
+
+ ret = rdtgroup_kn_set_ugid(ckn);
+ if (ret)
goto out_destroy;
- if (is_mbm_event(mevt->evtid))
- mon_event_read(&rr, r, d, prgrp, mevt->evtid, true);
+ ret = mon_add_all_files(ckn, d, r, prgrp, false);
+ if (ret)
+ goto out_destroy;
}
+
kernfs_activate(kn);
return 0;
@@ -3071,7 +3139,7 @@ out_destroy:
* and "monitor" groups with given domain id.
*/
static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- struct rdt_domain *d)
+ struct rdt_mon_domain *d)
{
struct kernfs_node *parent_kn;
struct rdtgroup *prgrp, *crgrp;
@@ -3093,13 +3161,13 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
struct rdt_resource *r,
struct rdtgroup *prgrp)
{
- struct rdt_domain *dom;
+ struct rdt_mon_domain *dom;
int ret;
/* Walking r->domains, ensure it can't race with cpuhp */
lockdep_assert_cpus_held();
- list_for_each_entry(dom, &r->domains, list) {
+ list_for_each_entry(dom, &r->mon_domains, hdr.list) {
ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
if (ret)
return ret;
@@ -3198,7 +3266,7 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
* Set the RDT domain up to start off with all usable allocations. That is,
* all shareable and unused bits. All-zero CBM is invalid.
*/
-static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
+static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schema *s,
u32 closid)
{
enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
@@ -3258,7 +3326,7 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
*/
tmp_cbm = cfg->new_ctrl;
if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
- rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id);
+ rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id);
return -ENOSPC;
}
cfg->have_new_ctrl = true;
@@ -3278,10 +3346,10 @@ static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
*/
static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
{
- struct rdt_domain *d;
+ struct rdt_ctrl_domain *d;
int ret;
- list_for_each_entry(d, &s->res->domains, list) {
+ list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
ret = __init_one_rdt_domain(d, s, closid);
if (ret < 0)
return ret;
@@ -3294,9 +3362,9 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
{
struct resctrl_staged_config *cfg;
- struct rdt_domain *d;
+ struct rdt_ctrl_domain *d;
- list_for_each_entry(d, &r->domains, list) {
+ list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
if (is_mba_sc(r)) {
d->mbps_val[closid] = MBA_MAX_MBPS;
continue;
@@ -3920,29 +3988,33 @@ static void __init rdtgroup_setup_default(void)
mutex_unlock(&rdtgroup_mutex);
}
-static void domain_destroy_mon_state(struct rdt_domain *d)
+static void domain_destroy_mon_state(struct rdt_mon_domain *d)
{
bitmap_free(d->rmid_busy_llc);
kfree(d->mbm_total);
kfree(d->mbm_local);
}
-void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
{
mutex_lock(&rdtgroup_mutex);
if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
mba_sc_domain_destroy(r, d);
- if (!r->mon_capable)
- goto out_unlock;
+ mutex_unlock(&rdtgroup_mutex);
+}
+
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+ mutex_lock(&rdtgroup_mutex);
/*
* If resctrl is mounted, remove all the
* per domain monitor data directories.
*/
if (resctrl_mounted && resctrl_arch_mon_capable())
- rmdir_mondata_subdir_allrdtgrp(r, d->id);
+ rmdir_mondata_subdir_allrdtgrp(r, d);
if (is_mbm_enabled())
cancel_delayed_work(&d->mbm_over);
@@ -3961,11 +4033,10 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
domain_destroy_mon_state(d);
-out_unlock:
mutex_unlock(&rdtgroup_mutex);
}
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
{
u32 idx_limit = resctrl_arch_system_num_rmid_idx();
size_t tsize;
@@ -3996,7 +4067,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
return 0;
}
-int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
{
int err = 0;
@@ -4005,11 +4076,18 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
/* RDT_RESOURCE_MBA is never mon_capable */
err = mba_sc_domain_allocate(r, d);
- goto out_unlock;
}
- if (!r->mon_capable)
- goto out_unlock;
+ mutex_unlock(&rdtgroup_mutex);
+
+ return err;
+}
+
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+ int err;
+
+ mutex_lock(&rdtgroup_mutex);
err = domain_setup_mon_state(r, d);
if (err)
@@ -4060,8 +4138,8 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
void resctrl_offline_cpu(unsigned int cpu)
{
struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+ struct rdt_mon_domain *d;
struct rdtgroup *rdtgrp;
- struct rdt_domain *d;
mutex_lock(&rdtgroup_mutex);
list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
@@ -4074,7 +4152,7 @@ void resctrl_offline_cpu(unsigned int cpu)
if (!l3->mon_capable)
goto out_unlock;
- d = get_domain_from_cpu(cpu, l3);
+ d = get_mon_domain_from_cpu(cpu, l3);
if (d) {
if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
cancel_delayed_work(&d->mbm_over);
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index af5aa2c754c2..c84c30188fdf 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -45,6 +45,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 },
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
+ { X86_FEATURE_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 },
{ X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 },
{ X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 },
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 11f83d07925e..00189cdeb775 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -41,80 +41,97 @@
#define CPUID_VMWARE_INFO_LEAF 0x40000000
#define CPUID_VMWARE_FEATURES_LEAF 0x40000010
-#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
-#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
-#define VMWARE_HYPERVISOR_MAGIC 0x564D5868
-
-#define VMWARE_CMD_GETVERSION 10
-#define VMWARE_CMD_GETHZ 45
-#define VMWARE_CMD_GETVCPU_INFO 68
-#define VMWARE_CMD_LEGACY_X2APIC 3
-#define VMWARE_CMD_VCPU_RESERVED 31
-#define VMWARE_CMD_STEALCLOCK 91
+#define GETVCPU_INFO_LEGACY_X2APIC BIT(3)
+#define GETVCPU_INFO_VCPU_RESERVED BIT(31)
#define STEALCLOCK_NOT_AVAILABLE (-1)
#define STEALCLOCK_DISABLED 0
#define STEALCLOCK_ENABLED 1
-#define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \
- __asm__("inl (%%dx), %%eax" : \
- "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
- "a"(VMWARE_HYPERVISOR_MAGIC), \
- "c"(VMWARE_CMD_##cmd), \
- "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) : \
- "memory")
-
-#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
- __asm__("vmcall" : \
- "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
- "a"(VMWARE_HYPERVISOR_MAGIC), \
- "c"(VMWARE_CMD_##cmd), \
- "d"(0), "b"(UINT_MAX) : \
- "memory")
-
-#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx) \
- __asm__("vmmcall" : \
- "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \
- "a"(VMWARE_HYPERVISOR_MAGIC), \
- "c"(VMWARE_CMD_##cmd), \
- "d"(0), "b"(UINT_MAX) : \
- "memory")
-
-#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do { \
- switch (vmware_hypercall_mode) { \
- case CPUID_VMWARE_FEATURES_ECX_VMCALL: \
- VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
- break; \
- case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
- VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx); \
- break; \
- default: \
- VMWARE_PORT(cmd, eax, ebx, ecx, edx); \
- break; \
- } \
- } while (0)
-
struct vmware_steal_time {
union {
- uint64_t clock; /* stolen time counter in units of vtsc */
+ u64 clock; /* stolen time counter in units of vtsc */
struct {
/* only for little-endian */
- uint32_t clock_low;
- uint32_t clock_high;
+ u32 clock_low;
+ u32 clock_high;
};
};
- uint64_t reserved[7];
+ u64 reserved[7];
};
static unsigned long vmware_tsc_khz __ro_after_init;
static u8 vmware_hypercall_mode __ro_after_init;
+unsigned long vmware_hypercall_slow(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5)
+{
+ unsigned long out0, rbx, rcx, rdx, rsi, rdi;
+
+ switch (vmware_hypercall_mode) {
+ case CPUID_VMWARE_FEATURES_ECX_VMCALL:
+ asm_inline volatile ("vmcall"
+ : "=a" (out0), "=b" (rbx), "=c" (rcx),
+ "=d" (rdx), "=S" (rsi), "=D" (rdi)
+ : "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (in3),
+ "S" (in4),
+ "D" (in5)
+ : "cc", "memory");
+ break;
+ case CPUID_VMWARE_FEATURES_ECX_VMMCALL:
+ asm_inline volatile ("vmmcall"
+ : "=a" (out0), "=b" (rbx), "=c" (rcx),
+ "=d" (rdx), "=S" (rsi), "=D" (rdi)
+ : "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (in3),
+ "S" (in4),
+ "D" (in5)
+ : "cc", "memory");
+ break;
+ default:
+ asm_inline volatile ("movw %[port], %%dx; inl (%%dx), %%eax"
+ : "=a" (out0), "=b" (rbx), "=c" (rcx),
+ "=d" (rdx), "=S" (rsi), "=D" (rdi)
+ : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (in3),
+ "S" (in4),
+ "D" (in5)
+ : "cc", "memory");
+ break;
+ }
+
+ if (out1)
+ *out1 = rbx;
+ if (out2)
+ *out2 = rcx;
+ if (out3)
+ *out3 = rdx;
+ if (out4)
+ *out4 = rsi;
+ if (out5)
+ *out5 = rdi;
+
+ return out0;
+}
+
static inline int __vmware_platform(void)
{
- uint32_t eax, ebx, ecx, edx;
- VMWARE_CMD(GETVERSION, eax, ebx, ecx, edx);
- return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
+ u32 eax, ebx, ecx;
+
+ eax = vmware_hypercall3(VMWARE_CMD_GETVERSION, 0, &ebx, &ecx);
+ return eax != UINT_MAX && ebx == VMWARE_HYPERVISOR_MAGIC;
}
static unsigned long vmware_get_tsc_khz(void)
@@ -166,21 +183,12 @@ static void __init vmware_cyc2ns_setup(void)
pr_info("using clock offset of %llu ns\n", d->cyc2ns_offset);
}
-static int vmware_cmd_stealclock(uint32_t arg1, uint32_t arg2)
+static int vmware_cmd_stealclock(u32 addr_hi, u32 addr_lo)
{
- uint32_t result, info;
-
- asm volatile (VMWARE_HYPERCALL :
- "=a"(result),
- "=c"(info) :
- "a"(VMWARE_HYPERVISOR_MAGIC),
- "b"(0),
- "c"(VMWARE_CMD_STEALCLOCK),
- "d"(0),
- "S"(arg1),
- "D"(arg2) :
- "memory");
- return result;
+ u32 info;
+
+ return vmware_hypercall5(VMWARE_CMD_STEALCLOCK, 0, 0, addr_hi, addr_lo,
+ &info);
}
static bool stealclock_enable(phys_addr_t pa)
@@ -215,15 +223,15 @@ static bool vmware_is_stealclock_available(void)
* Return:
* The steal clock reading in ns.
*/
-static uint64_t vmware_steal_clock(int cpu)
+static u64 vmware_steal_clock(int cpu)
{
struct vmware_steal_time *steal = &per_cpu(vmw_steal_time, cpu);
- uint64_t clock;
+ u64 clock;
if (IS_ENABLED(CONFIG_64BIT))
clock = READ_ONCE(steal->clock);
else {
- uint32_t initial_high, low, high;
+ u32 initial_high, low, high;
do {
initial_high = READ_ONCE(steal->clock_high);
@@ -235,7 +243,7 @@ static uint64_t vmware_steal_clock(int cpu)
high = READ_ONCE(steal->clock_high);
} while (initial_high != high);
- clock = ((uint64_t)high << 32) | low;
+ clock = ((u64)high << 32) | low;
}
return mul_u64_u32_shr(clock, vmware_cyc2ns.cyc2ns_mul,
@@ -389,13 +397,13 @@ static void __init vmware_set_capabilities(void)
static void __init vmware_platform_setup(void)
{
- uint32_t eax, ebx, ecx, edx;
- uint64_t lpj, tsc_khz;
+ u32 eax, ebx, ecx;
+ u64 lpj, tsc_khz;
- VMWARE_CMD(GETHZ, eax, ebx, ecx, edx);
+ eax = vmware_hypercall3(VMWARE_CMD_GETHZ, UINT_MAX, &ebx, &ecx);
if (ebx != UINT_MAX) {
- lpj = tsc_khz = eax | (((uint64_t)ebx) << 32);
+ lpj = tsc_khz = eax | (((u64)ebx) << 32);
do_div(tsc_khz, 1000);
WARN_ON(tsc_khz >> 32);
pr_info("TSC freq read from hypervisor : %lu.%03lu MHz\n",
@@ -446,7 +454,7 @@ static u8 __init vmware_select_hypercall(void)
* If !boot_cpu_has(X86_FEATURE_HYPERVISOR), vmware_hypercall_mode
* intentionally defaults to 0.
*/
-static uint32_t __init vmware_platform(void)
+static u32 __init vmware_platform(void)
{
if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
unsigned int eax;
@@ -474,12 +482,65 @@ static uint32_t __init vmware_platform(void)
/* Checks if hypervisor supports x2apic without VT-D interrupt remapping. */
static bool __init vmware_legacy_x2apic_available(void)
{
- uint32_t eax, ebx, ecx, edx;
- VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx);
- return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) &&
- (eax & BIT(VMWARE_CMD_LEGACY_X2APIC));
+ u32 eax;
+
+ eax = vmware_hypercall1(VMWARE_CMD_GETVCPU_INFO, 0);
+ return !(eax & GETVCPU_INFO_VCPU_RESERVED) &&
+ (eax & GETVCPU_INFO_LEGACY_X2APIC);
}
+#ifdef CONFIG_INTEL_TDX_GUEST
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5)
+{
+ struct tdx_module_args args = {};
+
+ if (!hypervisor_is_type(X86_HYPER_VMWARE)) {
+ pr_warn_once("Incorrect usage\n");
+ return ULONG_MAX;
+ }
+
+ if (cmd & ~VMWARE_CMD_MASK) {
+ pr_warn_once("Out of range command %lx\n", cmd);
+ return ULONG_MAX;
+ }
+
+ args.rbx = in1;
+ args.rdx = in3;
+ args.rsi = in4;
+ args.rdi = in5;
+ args.r10 = VMWARE_TDX_VENDOR_LEAF;
+ args.r11 = VMWARE_TDX_HCALL_FUNC;
+ args.r12 = VMWARE_HYPERVISOR_MAGIC;
+ args.r13 = cmd;
+ /* CPL */
+ args.r15 = 0;
+
+ __tdx_hypercall(&args);
+
+ if (out1)
+ *out1 = args.rbx;
+ if (out2)
+ *out2 = args.r13;
+ if (out3)
+ *out3 = args.rdx;
+ if (out4)
+ *out4 = args.rsi;
+ if (out5)
+ *out5 = args.rdi;
+
+ return args.r12;
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall);
+#endif
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb,
struct pt_regs *regs)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index f06501445cd9..340af8155658 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -128,6 +128,18 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
+
+ /*
+ * Non-crash kexec calls enc_kexec_begin() while scheduling is still
+ * active. This allows the callback to wait until all in-flight
+ * shared<->private conversions are complete. In a crash scenario,
+ * enc_kexec_begin() gets called after all but one CPU have been shut
+ * down and interrupts have been disabled. This allows the callback to
+ * detect a race with the conversion and report it.
+ */
+ x86_platform.guest.enc_kexec_begin();
+ x86_platform.guest.enc_kexec_finish();
+
crash_save_cpu(regs, safe_smp_processor_id());
}
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 8e3c53b4d070..64280879c68c 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -83,7 +83,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
if (ret)
- return ret;
+ return pcibios_err_to_errno(ret);
if (!pin)
return 0;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 68b09f718f10..4893d30ce438 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -828,7 +828,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
/*
* Find the highest page frame number we have available
*/
-static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type)
+static unsigned long __init e820__end_ram_pfn(unsigned long limit_pfn)
{
int i;
unsigned long last_pfn = 0;
@@ -839,7 +839,8 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type
unsigned long start_pfn;
unsigned long end_pfn;
- if (entry->type != type)
+ if (entry->type != E820_TYPE_RAM &&
+ entry->type != E820_TYPE_ACPI)
continue;
start_pfn = entry->addr >> PAGE_SHIFT;
@@ -865,12 +866,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type
unsigned long __init e820__end_of_ram_pfn(void)
{
- return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM);
+ return e820__end_ram_pfn(MAX_ARCH_PFN);
}
unsigned long __init e820__end_of_low_ram_pfn(void)
{
- return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM);
+ return e820__end_ram_pfn(1UL << (32 - PAGE_SHIFT));
}
static void __init early_panic(char *msg)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 59f4aefc6bc1..29d1f9104e94 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -17,8 +17,8 @@
#include <linux/bcma/bcma.h>
#include <linux/bcma/bcma_regs.h>
#include <linux/platform_data/x86/apple.h>
-#include <drm/i915_drm.h>
-#include <drm/i915_pciids.h>
+#include <drm/intel/i915_drm.h>
+#include <drm/intel/i915_pciids.h>
#include <asm/pci-direct.h>
#include <asm/dma.h>
#include <asm/io_apic.h>
@@ -518,47 +518,46 @@ static const struct intel_early_ops gen11_early_ops __initconst = {
/* Intel integrated GPUs for which we need to reserve "stolen memory" */
static const struct pci_device_id intel_early_ids[] __initconst = {
- INTEL_I830_IDS(&i830_early_ops),
- INTEL_I845G_IDS(&i845_early_ops),
- INTEL_I85X_IDS(&i85x_early_ops),
- INTEL_I865G_IDS(&i865_early_ops),
- INTEL_I915G_IDS(&gen3_early_ops),
- INTEL_I915GM_IDS(&gen3_early_ops),
- INTEL_I945G_IDS(&gen3_early_ops),
- INTEL_I945GM_IDS(&gen3_early_ops),
- INTEL_VLV_IDS(&gen6_early_ops),
- INTEL_PINEVIEW_G_IDS(&gen3_early_ops),
- INTEL_PINEVIEW_M_IDS(&gen3_early_ops),
- INTEL_I965G_IDS(&gen3_early_ops),
- INTEL_G33_IDS(&gen3_early_ops),
- INTEL_I965GM_IDS(&gen3_early_ops),
- INTEL_GM45_IDS(&gen3_early_ops),
- INTEL_G45_IDS(&gen3_early_ops),
- INTEL_IRONLAKE_D_IDS(&gen3_early_ops),
- INTEL_IRONLAKE_M_IDS(&gen3_early_ops),
- INTEL_SNB_D_IDS(&gen6_early_ops),
- INTEL_SNB_M_IDS(&gen6_early_ops),
- INTEL_IVB_M_IDS(&gen6_early_ops),
- INTEL_IVB_D_IDS(&gen6_early_ops),
- INTEL_HSW_IDS(&gen6_early_ops),
- INTEL_BDW_IDS(&gen8_early_ops),
- INTEL_CHV_IDS(&chv_early_ops),
- INTEL_SKL_IDS(&gen9_early_ops),
- INTEL_BXT_IDS(&gen9_early_ops),
- INTEL_KBL_IDS(&gen9_early_ops),
- INTEL_CFL_IDS(&gen9_early_ops),
- INTEL_GLK_IDS(&gen9_early_ops),
- INTEL_CNL_IDS(&gen9_early_ops),
- INTEL_ICL_11_IDS(&gen11_early_ops),
- INTEL_EHL_IDS(&gen11_early_ops),
- INTEL_JSL_IDS(&gen11_early_ops),
- INTEL_TGL_12_IDS(&gen11_early_ops),
- INTEL_RKL_IDS(&gen11_early_ops),
- INTEL_ADLS_IDS(&gen11_early_ops),
- INTEL_ADLP_IDS(&gen11_early_ops),
- INTEL_ADLN_IDS(&gen11_early_ops),
- INTEL_RPLS_IDS(&gen11_early_ops),
- INTEL_RPLP_IDS(&gen11_early_ops),
+ INTEL_I830_IDS(INTEL_VGA_DEVICE, &i830_early_ops),
+ INTEL_I845G_IDS(INTEL_VGA_DEVICE, &i845_early_ops),
+ INTEL_I85X_IDS(INTEL_VGA_DEVICE, &i85x_early_ops),
+ INTEL_I865G_IDS(INTEL_VGA_DEVICE, &i865_early_ops),
+ INTEL_I915G_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_I915GM_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_I945G_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_I945GM_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_VLV_IDS(INTEL_VGA_DEVICE, &gen6_early_ops),
+ INTEL_PNV_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_I965G_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_G33_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_I965GM_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_GM45_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_G45_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_ILK_IDS(INTEL_VGA_DEVICE, &gen3_early_ops),
+ INTEL_SNB_IDS(INTEL_VGA_DEVICE, &gen6_early_ops),
+ INTEL_IVB_IDS(INTEL_VGA_DEVICE, &gen6_early_ops),
+ INTEL_HSW_IDS(INTEL_VGA_DEVICE, &gen6_early_ops),
+ INTEL_BDW_IDS(INTEL_VGA_DEVICE, &gen8_early_ops),
+ INTEL_CHV_IDS(INTEL_VGA_DEVICE, &chv_early_ops),
+ INTEL_SKL_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_BXT_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_KBL_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_CFL_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_WHL_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_CML_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_GLK_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_CNL_IDS(INTEL_VGA_DEVICE, &gen9_early_ops),
+ INTEL_ICL_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_EHL_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_JSL_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_TGL_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_RKL_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_ADLS_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_ADLP_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_ADLN_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_RPLS_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_RPLU_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
+ INTEL_RPLP_IDS(INTEL_VGA_DEVICE, &gen11_early_ops),
};
struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0);
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 05df04f39628..2ee0b9c53dcc 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -106,21 +106,17 @@ static inline u64 xfeatures_mask_independent(void)
* Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
* supports modified optimization which is not supported by XSAVE.
*
- * We use XSAVE as a fallback.
- *
- * The 661 label is defined in the ALTERNATIVE* macros as the address of the
- * original instruction which gets replaced. We need to use it here as the
- * address of the instruction where we might get an exception at.
+ * Use XSAVE as a fallback.
*/
#define XSTATE_XSAVE(st, lmask, hmask, err) \
- asm volatile(ALTERNATIVE_3(XSAVE, \
+ asm volatile("1: " ALTERNATIVE_3(XSAVE, \
XSAVEOPT, X86_FEATURE_XSAVEOPT, \
XSAVEC, X86_FEATURE_XSAVEC, \
XSAVES, X86_FEATURE_XSAVES) \
"\n" \
"xor %[err], %[err]\n" \
"3:\n" \
- _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
+ _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
: [err] "=r" (err) \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
@@ -130,11 +126,11 @@ static inline u64 xfeatures_mask_independent(void)
* XSAVE area format.
*/
#define XSTATE_XRESTORE(st, lmask, hmask) \
- asm volatile(ALTERNATIVE(XRSTOR, \
+ asm volatile("1: " ALTERNATIVE(XRSTOR, \
XRSTORS, X86_FEATURE_XSAVES) \
"\n" \
"3:\n" \
- _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE) \
+ _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \
: \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b8441147eb5e..f63f8fd00a91 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -835,6 +835,13 @@ void __noreturn stop_this_cpu(void *dummy)
*/
cpumask_clear_cpu(cpu, &cpus_stop_mask);
+#ifdef CONFIG_SMP
+ if (smp_ops.stop_this_cpu) {
+ smp_ops.stop_this_cpu();
+ unreachable();
+ }
+#endif
+
for (;;) {
/*
* Use native_halt() so that memory contents don't change
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f3130f762784..0e0a4cf6b5eb 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -12,6 +12,7 @@
#include <linux/delay.h>
#include <linux/objtool.h>
#include <linux/pgtable.h>
+#include <linux/kexec.h>
#include <acpi/reboot.h>
#include <asm/io.h>
#include <asm/apic.h>
@@ -716,6 +717,14 @@ static void native_machine_emergency_restart(void)
void native_machine_shutdown(void)
{
+ /*
+ * Call enc_kexec_begin() while all CPUs are still active and
+ * interrupts are enabled. This will allow all in-flight memory
+ * conversions to finish cleanly.
+ */
+ if (kexec_in_progress)
+ x86_platform.guest.enc_kexec_begin();
+
/* Stop the cpus and apics */
#ifdef CONFIG_X86_IO_APIC
/*
@@ -752,6 +761,9 @@ void native_machine_shutdown(void)
#ifdef CONFIG_X86_64
x86_platform.iommu_shutdown();
#endif
+
+ if (kexec_in_progress)
+ x86_platform.guest.enc_kexec_finish();
}
static void __machine_emergency_restart(int emergency)
@@ -868,6 +880,12 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
cpu_emergency_disable_virtualization();
atomic_dec(&waiting_for_crash_ipi);
+
+ if (smp_ops.stop_this_cpu) {
+ smp_ops.stop_this_cpu();
+ unreachable();
+ }
+
/* Assume hlt works */
halt();
for (;;)
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 56cab1bb25f5..042c9a0334e9 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -5,6 +5,8 @@
*/
#include <linux/linkage.h>
+#include <linux/stringify.h>
+#include <asm/alternative.h>
#include <asm/page_types.h>
#include <asm/kexec.h>
#include <asm/processor-flags.h>
@@ -145,16 +147,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
* Set cr4 to a known state:
* - physical address extension enabled
* - 5-level paging, if it was enabled before
+ * - Machine check exception on TDX guest, if it was enabled before.
+ * Clearing MCE might not be allowed in TDX guests, depending on setup.
+ *
+ * Use R13 that contains the original CR4 value, read in relocate_kernel().
+ * PAE is always set in the original CR4.
*/
- movl $X86_CR4_PAE, %eax
- testq $X86_CR4_LA57, %r13
- jz 1f
- orl $X86_CR4_LA57, %eax
-1:
- movq %rax, %cr4
-
- jmp 1f
-1:
+ andl $(X86_CR4_PAE | X86_CR4_LA57), %r13d
+ ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %r13d), X86_FEATURE_TDX_GUEST
+ movq %r13, %cr4
/* Flush the TLB (needed?) */
movq %r9, %cr3
@@ -165,9 +166,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
* used by kexec. Flush the caches before copying the kernel.
*/
testq %r12, %r12
- jz 1f
+ jz .Lsme_off
wbinvd
-1:
+.Lsme_off:
movq %rcx, %r11
call swap_pages
@@ -187,7 +188,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
*/
testq %r11, %r11
- jnz 1f
+ jnz .Lrelocate
xorl %eax, %eax
xorl %ebx, %ebx
xorl %ecx, %ecx
@@ -208,7 +209,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
ret
int3
-1:
+.Lrelocate:
popq %rdx
leaq PAGE_SIZE(%r10), %rsp
ANNOTATE_RETPOLINE_SAFE
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 05c5aa951da7..5d34cad9b7b1 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -165,6 +165,7 @@ unsigned long saved_video_mode;
static char __initdata command_line[COMMAND_LINE_SIZE];
#ifdef CONFIG_CMDLINE_BOOL
static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+bool builtin_cmdline_added __ro_after_init;
#endif
#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
@@ -765,6 +766,7 @@ void __init setup_arch(char **cmdline_p)
strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
}
#endif
+ builtin_cmdline_added = true;
#endif
strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
@@ -995,7 +997,6 @@ void __init setup_arch(char **cmdline_p)
mem_encrypt_setup_arch();
cc_random_init();
- efi_fake_memmap();
efi_find_mirror();
efi_esrt_init();
efi_mokvar_table_init();
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 6f1e9883f074..059685612362 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -577,3 +577,19 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long arg2)
return wrss_control(true);
return -EINVAL;
}
+
+int shstk_update_last_frame(unsigned long val)
+{
+ unsigned long ssp;
+
+ if (!features_enabled(ARCH_SHSTK_SHSTK))
+ return 0;
+
+ ssp = get_user_shstk_addr();
+ return write_user_shstk_64((u64 __user *)ssp, (u64)val);
+}
+
+bool shstk_is_enabled(void)
+{
+ return features_enabled(ARCH_SHSTK_SHSTK);
+}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 06b170759e5b..d4462fb26299 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -50,9 +50,9 @@ int tsc_clocksource_reliable;
static int __read_mostly tsc_force_recalibrate;
-static u32 art_to_tsc_numerator;
-static u32 art_to_tsc_denominator;
-static u64 art_to_tsc_offset;
+static struct clocksource_base art_base_clk = {
+ .id = CSID_X86_ART,
+};
static bool have_art;
struct cyc2ns {
@@ -1074,7 +1074,7 @@ core_initcall(cpufreq_register_tsc_scaling);
*/
static void __init detect_art(void)
{
- unsigned int unused[2];
+ unsigned int unused;
if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF)
return;
@@ -1089,13 +1089,14 @@ static void __init detect_art(void)
tsc_async_resets)
return;
- cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator,
- &art_to_tsc_numerator, unused, unused+1);
+ cpuid(ART_CPUID_LEAF, &art_base_clk.denominator,
+ &art_base_clk.numerator, &art_base_clk.freq_khz, &unused);
- if (art_to_tsc_denominator < ART_MIN_DENOMINATOR)
+ art_base_clk.freq_khz /= KHZ;
+ if (art_base_clk.denominator < ART_MIN_DENOMINATOR)
return;
- rdmsrl(MSR_IA32_TSC_ADJUST, art_to_tsc_offset);
+ rdmsrl(MSR_IA32_TSC_ADJUST, art_base_clk.offset);
/* Make this sticky over multiple CPU init calls */
setup_force_cpu_cap(X86_FEATURE_ART);
@@ -1296,67 +1297,6 @@ int unsynchronized_tsc(void)
return 0;
}
-/*
- * Convert ART to TSC given numerator/denominator found in detect_art()
- */
-struct system_counterval_t convert_art_to_tsc(u64 art)
-{
- u64 tmp, res, rem;
-
- rem = do_div(art, art_to_tsc_denominator);
-
- res = art * art_to_tsc_numerator;
- tmp = rem * art_to_tsc_numerator;
-
- do_div(tmp, art_to_tsc_denominator);
- res += tmp + art_to_tsc_offset;
-
- return (struct system_counterval_t) {
- .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC,
- .cycles = res,
- };
-}
-EXPORT_SYMBOL(convert_art_to_tsc);
-
-/**
- * convert_art_ns_to_tsc() - Convert ART in nanoseconds to TSC.
- * @art_ns: ART (Always Running Timer) in unit of nanoseconds
- *
- * PTM requires all timestamps to be in units of nanoseconds. When user
- * software requests a cross-timestamp, this function converts system timestamp
- * to TSC.
- *
- * This is valid when CPU feature flag X86_FEATURE_TSC_KNOWN_FREQ is set
- * indicating the tsc_khz is derived from CPUID[15H]. Drivers should check
- * that this flag is set before conversion to TSC is attempted.
- *
- * Return:
- * struct system_counterval_t - system counter value with the ID of the
- * corresponding clocksource:
- * cycles: System counter value
- * cs_id: The clocksource ID for validating comparability
- */
-
-struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns)
-{
- u64 tmp, res, rem;
-
- rem = do_div(art_ns, USEC_PER_SEC);
-
- res = art_ns * tsc_khz;
- tmp = rem * tsc_khz;
-
- do_div(tmp, USEC_PER_SEC);
- res += tmp;
-
- return (struct system_counterval_t) {
- .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC,
- .cycles = res,
- };
-}
-EXPORT_SYMBOL(convert_art_ns_to_tsc);
-
-
static void tsc_refine_calibration_work(struct work_struct *work);
static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
/**
@@ -1458,8 +1398,10 @@ out:
if (tsc_unstable)
goto unreg;
- if (boot_cpu_has(X86_FEATURE_ART))
+ if (boot_cpu_has(X86_FEATURE_ART)) {
have_art = true;
+ clocksource_tsc.base = &art_base_clk;
+ }
clocksource_register_khz(&clocksource_tsc, tsc_khz);
unreg:
clocksource_unregister(&clocksource_tsc_early);
@@ -1484,8 +1426,10 @@ static int __init init_tsc_clocksource(void)
* the refined calibration and directly register it as a clocksource.
*/
if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
- if (boot_cpu_has(X86_FEATURE_ART))
+ if (boot_cpu_has(X86_FEATURE_ART)) {
have_art = true;
+ clocksource_tsc.base = &art_base_clk;
+ }
clocksource_register_khz(&clocksource_tsc, tsc_khz);
clocksource_unregister(&clocksource_tsc_early);
@@ -1509,10 +1453,12 @@ static bool __init determine_cpu_tsc_frequencies(bool early)
if (early) {
cpu_khz = x86_platform.calibrate_cpu();
- if (tsc_early_khz)
+ if (tsc_early_khz) {
tsc_khz = tsc_early_khz;
- else
+ } else {
tsc_khz = x86_platform.calibrate_tsc();
+ clocksource_tsc.freq_khz = tsc_khz;
+ }
} else {
/* We should not be here with non-native cpu calibration */
WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu);
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 6c07f6daaa22..5a952c5ea66b 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -12,6 +12,7 @@
#include <linux/ptrace.h>
#include <linux/uprobes.h>
#include <linux/uaccess.h>
+#include <linux/syscalls.h>
#include <linux/kdebug.h>
#include <asm/processor.h>
@@ -308,6 +309,122 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
}
#ifdef CONFIG_X86_64
+
+asm (
+ ".pushsection .rodata\n"
+ ".global uretprobe_trampoline_entry\n"
+ "uretprobe_trampoline_entry:\n"
+ "pushq %rax\n"
+ "pushq %rcx\n"
+ "pushq %r11\n"
+ "movq $" __stringify(__NR_uretprobe) ", %rax\n"
+ "syscall\n"
+ ".global uretprobe_syscall_check\n"
+ "uretprobe_syscall_check:\n"
+ "popq %r11\n"
+ "popq %rcx\n"
+
+ /* The uretprobe syscall replaces stored %rax value with final
+ * return address, so we don't restore %rax in here and just
+ * call ret.
+ */
+ "retq\n"
+ ".global uretprobe_trampoline_end\n"
+ "uretprobe_trampoline_end:\n"
+ ".popsection\n"
+);
+
+extern u8 uretprobe_trampoline_entry[];
+extern u8 uretprobe_trampoline_end[];
+extern u8 uretprobe_syscall_check[];
+
+void *arch_uprobe_trampoline(unsigned long *psize)
+{
+ static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+ struct pt_regs *regs = task_pt_regs(current);
+
+ /*
+ * At the moment the uretprobe syscall trampoline is supported
+ * only for native 64-bit process, the compat process still uses
+ * standard breakpoint.
+ */
+ if (user_64bit_mode(regs)) {
+ *psize = uretprobe_trampoline_end - uretprobe_trampoline_entry;
+ return uretprobe_trampoline_entry;
+ }
+
+ *psize = UPROBE_SWBP_INSN_SIZE;
+ return &insn;
+}
+
+static unsigned long trampoline_check_ip(void)
+{
+ unsigned long tramp = uprobe_get_trampoline_vaddr();
+
+ return tramp + (uretprobe_syscall_check - uretprobe_trampoline_entry);
+}
+
+SYSCALL_DEFINE0(uretprobe)
+{
+ struct pt_regs *regs = task_pt_regs(current);
+ unsigned long err, ip, sp, r11_cx_ax[3];
+
+ if (regs->ip != trampoline_check_ip())
+ goto sigill;
+
+ err = copy_from_user(r11_cx_ax, (void __user *)regs->sp, sizeof(r11_cx_ax));
+ if (err)
+ goto sigill;
+
+ /* expose the "right" values of r11/cx/ax/sp to uprobe_consumer/s */
+ regs->r11 = r11_cx_ax[0];
+ regs->cx = r11_cx_ax[1];
+ regs->ax = r11_cx_ax[2];
+ regs->sp += sizeof(r11_cx_ax);
+ regs->orig_ax = -1;
+
+ ip = regs->ip;
+ sp = regs->sp;
+
+ uprobe_handle_trampoline(regs);
+
+ /*
+ * Some of the uprobe consumers has changed sp, we can do nothing,
+ * just return via iret.
+ * .. or shadow stack is enabled, in which case we need to skip
+ * return through the user space stack address.
+ */
+ if (regs->sp != sp || shstk_is_enabled())
+ return regs->ax;
+ regs->sp -= sizeof(r11_cx_ax);
+
+ /* for the case uprobe_consumer has changed r11/cx */
+ r11_cx_ax[0] = regs->r11;
+ r11_cx_ax[1] = regs->cx;
+
+ /*
+ * ax register is passed through as return value, so we can use
+ * its space on stack for ip value and jump to it through the
+ * trampoline's ret instruction
+ */
+ r11_cx_ax[2] = regs->ip;
+ regs->ip = ip;
+
+ err = copy_to_user((void __user *)regs->sp, r11_cx_ax, sizeof(r11_cx_ax));
+ if (err)
+ goto sigill;
+
+ /* ensure sysret, see do_syscall_64() */
+ regs->r11 = regs->flags;
+ regs->cx = regs->ip;
+
+ return regs->ax;
+
+sigill:
+ force_sig(SIGILL);
+ return -1;
+}
+
/*
* If arch_uprobe->insn doesn't use rip-relative addressing, return
* immediately. Otherwise, rewrite the instruction so that it accesses
@@ -1076,8 +1193,13 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
return orig_ret_vaddr;
nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
- if (likely(!nleft))
+ if (likely(!nleft)) {
+ if (shstk_update_last_frame(trampoline_vaddr)) {
+ force_sig(SIGSEGV);
+ return -1;
+ }
return orig_ret_vaddr;
+ }
if (nleft != rasize) {
pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3509afc6a672..6e73403e874f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -357,6 +357,9 @@ SECTIONS
PERCPU_SECTION(INTERNODE_CACHE_BYTES)
#endif
+ RUNTIME_CONST(shift, d_hash_shift)
+ RUNTIME_CONST(ptr, dentry_hashtable)
+
. = ALIGN(PAGE_SIZE);
/* freed after init ends here */
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index d5dc5a92635a..82b128d3f309 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -134,10 +134,12 @@ struct x86_cpuinit_ops x86_cpuinit = {
static void default_nmi_init(void) { };
-static bool enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return true; }
-static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return true; }
+static int enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return 0; }
+static int enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return 0; }
static bool enc_tlb_flush_required_noop(bool enc) { return false; }
static bool enc_cache_flush_required_noop(void) { return false; }
+static void enc_kexec_begin_noop(void) {}
+static void enc_kexec_finish_noop(void) {}
static bool is_private_mmio_noop(u64 addr) {return false; }
struct x86_platform_ops x86_platform __ro_after_init = {
@@ -161,6 +163,8 @@ struct x86_platform_ops x86_platform __ro_after_init = {
.enc_status_change_finish = enc_status_change_finish_noop,
.enc_tlb_flush_required = enc_tlb_flush_required_noop,
.enc_cache_flush_required = enc_cache_flush_required_noop,
+ .enc_kexec_begin = enc_kexec_begin_noop,
+ .enc_kexec_finish = enc_kexec_finish_noop,
},
};
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index fec95a770270..4287a8071a3a 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -44,6 +44,7 @@ config KVM
select KVM_VFIO
select HAVE_KVM_PM_NOTIFIER if PM
select KVM_GENERIC_HARDWARE_ENABLING
+ select KVM_GENERIC_PRE_FAULT_MEMORY
select KVM_WERROR if WERROR
help
Support hosting fully virtualized guest machines using hardware
@@ -139,6 +140,9 @@ config KVM_AMD_SEV
depends on KVM_AMD && X86_64
depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
select ARCH_HAS_CC_PLATFORM
+ select KVM_GENERIC_PRIVATE_MEM
+ select HAVE_KVM_GMEM_PREPARE
+ select HAVE_KVM_GMEM_INVALIDATE
help
Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
with Encrypted State (SEV-ES) on AMD processors.
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f2f2be5d1141..2617be544480 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -335,6 +335,18 @@ static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent)
#endif
}
+static bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0);
+ if (!entry)
+ return false;
+
+ return is_guest_vendor_amd(entry->ebx, entry->ecx, entry->edx) ||
+ is_guest_vendor_hygon(entry->ebx, entry->ecx, entry->edx);
+}
+
static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
@@ -388,7 +400,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
vcpu->arch.cpuid_nent));
/* Invoke the vendor callback only after the above state is updated. */
- static_call(kvm_x86_vcpu_after_set_cpuid)(vcpu);
+ kvm_x86_call(vcpu_after_set_cpuid)(vcpu);
/*
* Except for the MMU, which needs to do its thing any vendor specific
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 23dbb9eb277c..41697cca354e 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -102,24 +102,6 @@ static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu,
*reg &= ~__feature_bit(x86_feature);
}
-static inline bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0);
- return best &&
- (is_guest_vendor_amd(best->ebx, best->ecx, best->edx) ||
- is_guest_vendor_hygon(best->ebx, best->ecx, best->edx));
-}
-
-static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0);
- return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx);
-}
-
static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu)
{
return vcpu->arch.is_amd_compatible;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5d4c86133453..e72aed25d721 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1069,7 +1069,7 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
asm("push %[flags]; popf; " CALL_NOSPEC
- : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags));
+ : "=a"(rc), ASM_CALL_CONSTRAINT : [thunk_target]"r"(fop), [flags]"r"(flags));
return rc;
}
@@ -2354,50 +2354,6 @@ setup_syscalls_segments(struct desc_struct *cs, struct desc_struct *ss)
ss->avl = 0;
}
-static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
-{
- u32 eax, ebx, ecx, edx;
-
- eax = ecx = 0;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true);
- return is_guest_vendor_intel(ebx, ecx, edx);
-}
-
-static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
-{
- const struct x86_emulate_ops *ops = ctxt->ops;
- u32 eax, ebx, ecx, edx;
-
- /*
- * syscall should always be enabled in longmode - so only become
- * vendor specific (cpuid) if other modes are active...
- */
- if (ctxt->mode == X86EMUL_MODE_PROT64)
- return true;
-
- eax = 0x00000000;
- ecx = 0x00000000;
- ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true);
- /*
- * remark: Intel CPUs only support "syscall" in 64bit longmode. Also a
- * 64bit guest with a 32bit compat-app running will #UD !! While this
- * behaviour can be fixed (by emulating) into AMD response - CPUs of
- * AMD can't behave like Intel.
- */
- if (is_guest_vendor_intel(ebx, ecx, edx))
- return false;
-
- if (is_guest_vendor_amd(ebx, ecx, edx) ||
- is_guest_vendor_hygon(ebx, ecx, edx))
- return true;
-
- /*
- * default: (not Intel, not AMD, not Hygon), apply Intel's
- * stricter rules...
- */
- return false;
-}
-
static int em_syscall(struct x86_emulate_ctxt *ctxt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
@@ -2411,7 +2367,15 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
ctxt->mode == X86EMUL_MODE_VM86)
return emulate_ud(ctxt);
- if (!(em_syscall_is_enabled(ctxt)))
+ /*
+ * Intel compatible CPUs only support SYSCALL in 64-bit mode, whereas
+ * AMD allows SYSCALL in any flavor of protected mode. Note, it's
+ * infeasible to emulate Intel behavior when running on AMD hardware,
+ * as SYSCALL won't fault in the "wrong" mode, i.e. there is no #UD
+ * for KVM to trap-and-emulate, unlike emulating AMD on Intel.
+ */
+ if (ctxt->mode != X86EMUL_MODE_PROT64 &&
+ ctxt->ops->guest_cpuid_is_intel_compatible(ctxt))
return emulate_ud(ctxt);
ops->get_msr(ctxt, MSR_EFER, &efer);
@@ -2471,11 +2435,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
return emulate_gp(ctxt, 0);
/*
- * Not recognized on AMD in compat mode (but is recognized in legacy
- * mode).
+ * Intel's architecture allows SYSENTER in compatibility mode, but AMD
+ * does not. Note, AMD does allow SYSENTER in legacy protected mode.
*/
- if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA)
- && !vendor_intel(ctxt))
+ if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA) &&
+ !ctxt->ops->guest_cpuid_is_intel_compatible(ctxt))
return emulate_ud(ctxt);
/* sysenter/sysexit have not been tested in 64bit mode. */
@@ -2647,7 +2611,14 @@ static void string_registers_quirk(struct x86_emulate_ctxt *ctxt)
* manner when ECX is zero due to REP-string optimizations.
*/
#ifdef CONFIG_X86_64
- if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt))
+ u32 eax, ebx, ecx, edx;
+
+ if (ctxt->ad_bytes != 4)
+ return;
+
+ eax = ecx = 0;
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true);
+ if (!is_guest_vendor_intel(ebx, ecx, edx))
return;
*reg_write(ctxt, VCPU_REGS_RCX) = 0;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 8a47f8541eab..4f0a94346d00 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1417,7 +1417,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
}
/* vmcall/vmmcall */
- static_call(kvm_x86_patch_hypercall)(vcpu, instructions + i);
+ kvm_x86_call(patch_hypercall)(vcpu, instructions + i);
i += 3;
/* ret */
@@ -1737,7 +1737,8 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
data = (u64)vcpu->arch.virtual_tsc_khz * 1000;
break;
case HV_X64_MSR_APIC_FREQUENCY:
- data = APIC_BUS_FREQUENCY;
+ data = div64_u64(1000000000ULL,
+ vcpu->kvm->arch.apic_bus_cycle_ns);
break;
default:
kvm_pr_unimpl_rdmsr(vcpu, msr);
@@ -1985,7 +1986,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
*/
gva = entries[i] & PAGE_MASK;
for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++)
- static_call(kvm_x86_flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE);
+ kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE);
++vcpu->stat.tlb_flush;
}
@@ -2526,7 +2527,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
* hypercall generates UD from non zero cpl and real mode
* per HYPER-V spec
*/
- if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || !is_protmode(vcpu)) {
+ if (kvm_x86_call(get_cpl)(vcpu) != 0 || !is_protmode(vcpu)) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index ad9ca8a60144..3d7eb11d0e45 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -157,7 +157,7 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
{
__kvm_migrate_apic_timer(vcpu);
__kvm_migrate_pit_timer(vcpu);
- static_call_cond(kvm_x86_migrate_timers)(vcpu);
+ kvm_x86_call(migrate_timers)(vcpu);
}
bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index c2d7cfe82d00..76d46b2f41dd 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -106,7 +106,6 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
int apic_has_pending_timer(struct kvm_vcpu *vcpu);
int kvm_setup_default_irq_routing(struct kvm *kvm);
-int kvm_setup_empty_irq_routing(struct kvm *kvm);
int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq,
struct dest_map *dest_map);
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 68f3f6c26046..8136695f7b96 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -395,13 +395,6 @@ int kvm_setup_default_irq_routing(struct kvm *kvm)
ARRAY_SIZE(default_routing), 0);
}
-static const struct kvm_irq_routing_entry empty_routing[] = {};
-
-int kvm_setup_empty_irq_routing(struct kvm *kvm)
-{
- return kvm_set_irq_routing(kvm, empty_routing, 0, 0);
-}
-
void kvm_arch_post_irq_routing_update(struct kvm *kvm)
{
if (!irqchip_split(kvm))
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 75eae9c4998a..b1eb46e26b2e 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -98,7 +98,7 @@ static inline unsigned long kvm_register_read_raw(struct kvm_vcpu *vcpu, int reg
return 0;
if (!kvm_register_is_available(vcpu, reg))
- static_call(kvm_x86_cache_reg)(vcpu, reg);
+ kvm_x86_call(cache_reg)(vcpu, reg);
return vcpu->arch.regs[reg];
}
@@ -138,7 +138,7 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
might_sleep(); /* on svm */
if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
- static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_PDPTR);
+ kvm_x86_call(cache_reg)(vcpu, VCPU_EXREG_PDPTR);
return vcpu->arch.walk_mmu->pdptrs[index];
}
@@ -153,7 +153,7 @@ static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask)
ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS;
if ((tmask & vcpu->arch.cr0_guest_owned_bits) &&
!kvm_register_is_available(vcpu, VCPU_EXREG_CR0))
- static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_CR0);
+ kvm_x86_call(cache_reg)(vcpu, VCPU_EXREG_CR0);
return vcpu->arch.cr0 & mask;
}
@@ -175,7 +175,7 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
ulong tmask = mask & KVM_POSSIBLE_CR4_GUEST_BITS;
if ((tmask & vcpu->arch.cr4_guest_owned_bits) &&
!kvm_register_is_available(vcpu, VCPU_EXREG_CR4))
- static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_CR4);
+ kvm_x86_call(cache_reg)(vcpu, VCPU_EXREG_CR4);
return vcpu->arch.cr4 & mask;
}
@@ -190,7 +190,7 @@ static __always_inline bool kvm_is_cr4_bit_set(struct kvm_vcpu *vcpu,
static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu)
{
if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3))
- static_call(kvm_x86_cache_reg)(vcpu, VCPU_EXREG_CR3);
+ kvm_x86_call(cache_reg)(vcpu, VCPU_EXREG_CR3);
return vcpu->arch.cr3;
}
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 29ea4313e1bb..55a18e2f2dcd 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -223,6 +223,7 @@ struct x86_emulate_ops {
bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt);
bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt);
bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);
+ bool (*guest_cpuid_is_intel_compatible)(struct x86_emulate_ctxt *ctxt);
void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index acd7d48100a1..a7172ba59ad2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -738,8 +738,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
if (unlikely(apic->apicv_active)) {
/* need to update RVI */
kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
- static_call_cond(kvm_x86_hwapic_irr_update)(apic->vcpu,
- apic_find_highest_irr(apic));
+ kvm_x86_call(hwapic_irr_update)(apic->vcpu,
+ apic_find_highest_irr(apic));
} else {
apic->irr_pending = false;
kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
@@ -765,7 +765,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
* just set SVI.
*/
if (unlikely(apic->apicv_active))
- static_call_cond(kvm_x86_hwapic_isr_update)(vec);
+ kvm_x86_call(hwapic_isr_update)(vec);
else {
++apic->isr_count;
BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -810,7 +810,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
* and must be left alone.
*/
if (unlikely(apic->apicv_active))
- static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic));
+ kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic));
else {
--apic->isr_count;
BUG_ON(apic->isr_count < 0);
@@ -946,7 +946,7 @@ static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
{
int highest_irr;
if (kvm_x86_ops.sync_pir_to_irr)
- highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);
+ highest_irr = kvm_x86_call(sync_pir_to_irr)(apic->vcpu);
else
highest_irr = apic_find_highest_irr(apic);
if (highest_irr == -1 || (highest_irr & 0xF0) <= ppr)
@@ -1338,8 +1338,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
apic->regs + APIC_TMR);
}
- static_call(kvm_x86_deliver_interrupt)(apic, delivery_mode,
- trig_mode, vector);
+ kvm_x86_call(deliver_interrupt)(apic, delivery_mode,
+ trig_mode, vector);
break;
case APIC_DM_REMRD:
@@ -1557,7 +1557,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
remaining = 0;
ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period);
- return div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->divide_count));
+ return div64_u64(ns, (apic->vcpu->kvm->arch.apic_bus_cycle_ns *
+ apic->divide_count));
}
static void __report_tpr_access(struct kvm_lapic *apic, bool write)
@@ -1973,7 +1974,8 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
static inline u64 tmict_to_ns(struct kvm_lapic *apic, u32 tmict)
{
- return (u64)tmict * APIC_BUS_CYCLE_NS * (u64)apic->divide_count;
+ return (u64)tmict * apic->vcpu->kvm->arch.apic_bus_cycle_ns *
+ (u64)apic->divide_count;
}
static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor)
@@ -2103,7 +2105,7 @@ static void cancel_hv_timer(struct kvm_lapic *apic)
{
WARN_ON(preemptible());
WARN_ON(!apic->lapic_timer.hv_timer_in_use);
- static_call(kvm_x86_cancel_hv_timer)(apic->vcpu);
+ kvm_x86_call(cancel_hv_timer)(apic->vcpu);
apic->lapic_timer.hv_timer_in_use = false;
}
@@ -2120,7 +2122,7 @@ static bool start_hv_timer(struct kvm_lapic *apic)
if (!ktimer->tscdeadline)
return false;
- if (static_call(kvm_x86_set_hv_timer)(vcpu, ktimer->tscdeadline, &expired))
+ if (kvm_x86_call(set_hv_timer)(vcpu, ktimer->tscdeadline, &expired))
return false;
ktimer->hv_timer_in_use = true;
@@ -2575,7 +2577,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) {
kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
- static_call_cond(kvm_x86_set_virtual_apic_mode)(vcpu);
+ kvm_x86_call(set_virtual_apic_mode)(vcpu);
}
apic->base_address = apic->vcpu->arch.apic_base &
@@ -2685,7 +2687,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
u64 msr_val;
int i;
- static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu);
+ kvm_x86_call(apicv_pre_state_restore)(vcpu);
if (!init_event) {
msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
@@ -2740,9 +2742,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
vcpu->arch.pv_eoi.msr_val = 0;
apic_update_ppr(apic);
if (apic->apicv_active) {
- static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu);
- static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, -1);
- static_call_cond(kvm_x86_hwapic_isr_update)(-1);
+ kvm_x86_call(apicv_post_state_restore)(vcpu);
+ kvm_x86_call(hwapic_irr_update)(vcpu, -1);
+ kvm_x86_call(hwapic_isr_update)(-1);
}
vcpu->arch.apic_arb_prio = 0;
@@ -2838,7 +2840,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
vcpu->arch.apic = apic;
if (kvm_x86_ops.alloc_apic_backing_page)
- apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu);
+ apic->regs = kvm_x86_call(alloc_apic_backing_page)(vcpu);
else
apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
if (!apic->regs) {
@@ -3017,7 +3019,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
struct kvm_lapic *apic = vcpu->arch.apic;
int r;
- static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu);
+ kvm_x86_call(apicv_pre_state_restore)(vcpu);
kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
/* set SPIV separately to get count of SW disabled APICs right */
@@ -3044,9 +3046,10 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
kvm_lapic_set_reg(apic, APIC_TMCCT, 0);
kvm_apic_update_apicv(vcpu);
if (apic->apicv_active) {
- static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu);
- static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic));
- static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic));
+ kvm_x86_call(apicv_post_state_restore)(vcpu);
+ kvm_x86_call(hwapic_irr_update)(vcpu,
+ apic_find_highest_irr(apic));
+ kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic));
}
kvm_make_request(KVM_REQ_EVENT, vcpu);
if (ioapic_in_kernel(vcpu->kvm))
@@ -3334,7 +3337,8 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
/* evaluate pending_events before reading the vector */
smp_rmb();
sipi_vector = apic->sipi_vector;
- static_call(kvm_x86_vcpu_deliver_sipi_vector)(vcpu, sipi_vector);
+ kvm_x86_call(vcpu_deliver_sipi_vector)(vcpu,
+ sipi_vector);
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index a69e706b9080..7ef8ae73e82d 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -16,8 +16,7 @@
#define APIC_DEST_NOSHORT 0x0
#define APIC_DEST_MASK 0x800
-#define APIC_BUS_CYCLE_NS 1
-#define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS)
+#define APIC_BUS_CYCLE_NS_DEFAULT 1
#define APIC_BROADCAST 0xFF
#define X2APIC_BROADCAST 0xFFFFFFFFul
@@ -236,7 +235,7 @@ static inline bool kvm_apic_has_pending_init_or_sipi(struct kvm_vcpu *vcpu)
static inline bool kvm_apic_init_sipi_allowed(struct kvm_vcpu *vcpu)
{
return !is_smm(vcpu) &&
- !static_call(kvm_x86_apic_init_signal_blocked)(vcpu);
+ !kvm_x86_call(apic_init_signal_blocked)(vcpu);
}
static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 2e454316f2a2..4341e0e28571 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -57,12 +57,6 @@ static __always_inline u64 rsvd_bits(int s, int e)
return ((2ULL << (e - s)) - 1) << s;
}
-/*
- * The number of non-reserved physical address bits irrespective of features
- * that repurpose legal bits, e.g. MKTME.
- */
-extern u8 __read_mostly shadow_phys_bits;
-
static inline gfn_t kvm_mmu_max_gfn(void)
{
/*
@@ -76,30 +70,11 @@ static inline gfn_t kvm_mmu_max_gfn(void)
* than hardware's real MAXPHYADDR. Using the host MAXPHYADDR
* disallows such SPTEs entirely and simplifies the TDP MMU.
*/
- int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52;
+ int max_gpa_bits = likely(tdp_enabled) ? kvm_host.maxphyaddr : 52;
return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1;
}
-static inline u8 kvm_get_shadow_phys_bits(void)
-{
- /*
- * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
- * in CPU detection code, but the processor treats those reduced bits as
- * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
- * the physical address bits reported by CPUID.
- */
- if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
- return cpuid_eax(0x80000008) & 0xff;
-
- /*
- * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
- * custom CPUID. Proceed with whatever the kernel found since these features
- * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
- */
- return boot_cpu_data.x86_phys_bits;
-}
-
u8 kvm_mmu_get_max_tdp_level(void);
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
@@ -163,8 +138,8 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
if (!VALID_PAGE(root_hpa))
return;
- static_call(kvm_x86_load_mmu_pgd)(vcpu, root_hpa,
- vcpu->arch.mmu->root_role.level);
+ kvm_x86_call(load_mmu_pgd)(vcpu, root_hpa,
+ vcpu->arch.mmu->root_role.level);
}
static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu,
@@ -199,7 +174,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
{
/* strip nested paging fault error codes */
unsigned int pfec = access;
- unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);
+ unsigned long rflags = kvm_x86_call(get_rflags)(vcpu);
/*
* For explicit supervisor accesses, SMAP is disabled if EFLAGS.AC = 1.
@@ -246,14 +221,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
return -(u32)fault & errcode;
}
-bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma);
-
-static inline bool kvm_mmu_honors_guest_mtrrs(struct kvm *kvm)
-{
- return __kvm_mmu_honors_guest_mtrrs(kvm_arch_has_noncoherent_dma(kvm));
-}
-
-void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
+bool kvm_mmu_may_ignore_guest_pat(void);
int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8d74bdef68c1..901be9e420a4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -722,7 +722,7 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
if (sp->role.passthrough)
return sp->gfn;
- if (!sp->role.direct)
+ if (sp->shadowed_translation)
return sp->shadowed_translation[index] >> PAGE_SHIFT;
return sp->gfn + (index << ((sp->role.level - 1) * SPTE_LEVEL_BITS));
@@ -736,7 +736,7 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
*/
static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index)
{
- if (sp_has_gptes(sp))
+ if (sp->shadowed_translation)
return sp->shadowed_translation[index] & ACC_ALL;
/*
@@ -757,7 +757,7 @@ static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index)
static void kvm_mmu_page_set_translation(struct kvm_mmu_page *sp, int index,
gfn_t gfn, unsigned int access)
{
- if (sp_has_gptes(sp)) {
+ if (sp->shadowed_translation) {
sp->shadowed_translation[index] = (gfn << PAGE_SHIFT) | access;
return;
}
@@ -1700,8 +1700,7 @@ static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
hlist_del(&sp->hash_link);
list_del(&sp->link);
free_page((unsigned long)sp->spt);
- if (!sp->role.direct)
- free_page((unsigned long)sp->shadowed_translation);
+ free_page((unsigned long)sp->shadowed_translation);
kmem_cache_free(mmu_page_header_cache, sp);
}
@@ -2203,7 +2202,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
sp = kvm_mmu_memory_cache_alloc(caches->page_header_cache);
sp->spt = kvm_mmu_memory_cache_alloc(caches->shadow_page_cache);
- if (!role.direct)
+ if (!role.direct && role.level <= KVM_MAX_HUGEPAGE_LEVEL)
sp->shadowed_translation = kvm_mmu_memory_cache_alloc(caches->shadowed_info_cache);
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
@@ -3308,7 +3307,7 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu,
return RET_PF_CONTINUE;
}
-static bool page_fault_can_be_fast(struct kvm_page_fault *fault)
+static bool page_fault_can_be_fast(struct kvm *kvm, struct kvm_page_fault *fault)
{
/*
* Page faults with reserved bits set, i.e. faults on MMIO SPTEs, only
@@ -3320,6 +3319,26 @@ static bool page_fault_can_be_fast(struct kvm_page_fault *fault)
return false;
/*
+ * For hardware-protected VMs, certain conditions like attempting to
+ * perform a write to a page which is not in the state that the guest
+ * expects it to be in can result in a nested/extended #PF. In this
+ * case, the below code might misconstrue this situation as being the
+ * result of a write-protected access, and treat it as a spurious case
+ * rather than taking any action to satisfy the real source of the #PF
+ * such as generating a KVM_EXIT_MEMORY_FAULT. This can lead to the
+ * guest spinning on a #PF indefinitely, so don't attempt the fast path
+ * in this case.
+ *
+ * Note that the kvm_mem_is_private() check might race with an
+ * attribute update, but this will either result in the guest spinning
+ * on RET_PF_SPURIOUS until the update completes, or an actual spurious
+ * case might go down the slow path. Either case will resolve itself.
+ */
+ if (kvm->arch.has_private_mem &&
+ fault->is_private != kvm_mem_is_private(kvm, fault->gfn))
+ return false;
+
+ /*
* #PF can be fast if:
*
* 1. The shadow page table entry is not present and A/D bits are
@@ -3419,7 +3438,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
u64 *sptep;
uint retry_count = 0;
- if (!page_fault_can_be_fast(fault))
+ if (!page_fault_can_be_fast(vcpu->kvm, fault))
return ret;
walk_shadow_page_lockless_begin(vcpu);
@@ -3428,7 +3447,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
u64 new_spte;
if (tdp_mmu_enabled)
- sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte);
+ sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->gfn, &spte);
else
sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte);
@@ -3438,7 +3457,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
* available as the vCPU holds a reference to its root(s).
*/
if (WARN_ON_ONCE(!sptep))
- spte = REMOVED_SPTE;
+ spte = FROZEN_SPTE;
if (!is_shadow_present_pte(spte))
break;
@@ -4271,7 +4290,16 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu))
return;
- kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, true, NULL);
+ r = kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code,
+ true, NULL, NULL);
+
+ /*
+ * Account fixed page faults, otherwise they'll never be counted, but
+ * ignore stats for all other return times. Page-ready "faults" aren't
+ * truly spurious and never trigger emulation
+ */
+ if (r == RET_PF_FIXED)
+ vcpu->stat.pf_fixed++;
}
static inline u8 kvm_max_level_for_order(int order)
@@ -4291,6 +4319,25 @@ static inline u8 kvm_max_level_for_order(int order)
return PG_LEVEL_4K;
}
+static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
+ u8 max_level, int gmem_order)
+{
+ u8 req_max_level;
+
+ if (max_level == PG_LEVEL_4K)
+ return PG_LEVEL_4K;
+
+ max_level = min(kvm_max_level_for_order(gmem_order), max_level);
+ if (max_level == PG_LEVEL_4K)
+ return PG_LEVEL_4K;
+
+ req_max_level = kvm_x86_call(private_max_mapping_level)(kvm, pfn);
+ if (req_max_level)
+ max_level = min(max_level, req_max_level);
+
+ return req_max_level;
+}
+
static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
struct kvm_page_fault *fault)
{
@@ -4308,9 +4355,9 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
return r;
}
- fault->max_level = min(kvm_max_level_for_order(max_order),
- fault->max_level);
fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+ fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn,
+ fault->max_level, max_order);
return RET_PF_CONTINUE;
}
@@ -4561,7 +4608,10 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
if (WARN_ON_ONCE(error_code >> 32))
error_code = lower_32_bits(error_code);
- /* Ensure the above sanity check also covers KVM-defined flags. */
+ /*
+ * Restrict KVM-defined flags to bits 63:32 so that it's impossible for
+ * them to conflict with #PF error codes, which are limited to 32 bits.
+ */
BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK));
vcpu->arch.l1tf_flush_l1d = true;
@@ -4621,38 +4671,23 @@ out_unlock:
}
#endif
-bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma)
+bool kvm_mmu_may_ignore_guest_pat(void)
{
/*
- * If host MTRRs are ignored (shadow_memtype_mask is non-zero), and the
- * VM has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is
- * to honor the memtype from the guest's MTRRs so that guest accesses
- * to memory that is DMA'd aren't cached against the guest's wishes.
- *
- * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs,
- * e.g. KVM will force UC memtype for host MMIO.
+ * When EPT is enabled (shadow_memtype_mask is non-zero), the CPU does
+ * not support self-snoop (or is affected by an erratum), and the VM
+ * has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is to
+ * honor the memtype from the guest's PAT so that guest accesses to
+ * memory that is DMA'd aren't cached against the guest's wishes. As a
+ * result, KVM _may_ ignore guest PAT, whereas without non-coherent DMA,
+ * KVM _always_ ignores or honors guest PAT, i.e. doesn't toggle SPTE
+ * bits in response to non-coherent device (un)registration.
*/
- return vm_has_noncoherent_dma && shadow_memtype_mask;
+ return !static_cpu_has(X86_FEATURE_SELFSNOOP) && shadow_memtype_mask;
}
int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
- /*
- * If the guest's MTRRs may be used to compute the "real" memtype,
- * restrict the mapping level to ensure KVM uses a consistent memtype
- * across the entire mapping.
- */
- if (kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) {
- for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) {
- int page_num = KVM_PAGES_PER_HPAGE(fault->max_level);
- gfn_t base = gfn_round_for_level(fault->gfn,
- fault->max_level);
-
- if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num))
- break;
- }
- }
-
#ifdef CONFIG_X86_64
if (tdp_mmu_enabled)
return kvm_tdp_mmu_page_fault(vcpu, fault);
@@ -4661,6 +4696,79 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
return direct_page_fault(vcpu, fault);
}
+static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
+ u8 *level)
+{
+ int r;
+
+ /*
+ * Restrict to TDP page fault, since that's the only case where the MMU
+ * is indexed by GPA.
+ */
+ if (vcpu->arch.mmu->page_fault != kvm_tdp_page_fault)
+ return -EOPNOTSUPP;
+
+ do {
+ if (signal_pending(current))
+ return -EINTR;
+ cond_resched();
+ r = kvm_mmu_do_page_fault(vcpu, gpa, error_code, true, NULL, level);
+ } while (r == RET_PF_RETRY);
+
+ if (r < 0)
+ return r;
+
+ switch (r) {
+ case RET_PF_FIXED:
+ case RET_PF_SPURIOUS:
+ return 0;
+
+ case RET_PF_EMULATE:
+ return -ENOENT;
+
+ case RET_PF_RETRY:
+ case RET_PF_CONTINUE:
+ case RET_PF_INVALID:
+ default:
+ WARN_ONCE(1, "could not fix page fault during prefault");
+ return -EIO;
+ }
+}
+
+long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
+ struct kvm_pre_fault_memory *range)
+{
+ u64 error_code = PFERR_GUEST_FINAL_MASK;
+ u8 level = PG_LEVEL_4K;
+ u64 end;
+ int r;
+
+ /*
+ * reload is efficient when called repeatedly, so we can do it on
+ * every iteration.
+ */
+ kvm_mmu_reload(vcpu);
+
+ if (kvm_arch_has_private_mem(vcpu->kvm) &&
+ kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
+ error_code |= PFERR_PRIVATE_ACCESS;
+
+ /*
+ * Shadow paging uses GVA for kvm page fault, so restrict to
+ * two-dimensional paging.
+ */
+ r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
+ if (r < 0)
+ return r;
+
+ /*
+ * If the mapping that covers range->gpa can use a huge page, it
+ * may start below it or end after range->gpa + range->size.
+ */
+ end = (range->gpa & KVM_HPAGE_MASK(level)) + KVM_HPAGE_SIZE(level);
+ return min(range->size, end - range->gpa);
+}
+
static void nonpaging_init_context(struct kvm_mmu *context)
{
context->page_fault = nonpaging_page_fault;
@@ -4988,7 +5096,7 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
static inline u64 reserved_hpa_bits(void)
{
- return rsvd_bits(shadow_phys_bits, 63);
+ return rsvd_bits(kvm_host.maxphyaddr, 63);
}
/*
@@ -5633,7 +5741,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
* stale entries. Flushing on alloc also allows KVM to skip the TLB
* flush when freeing a root (see kvm_tdp_mmu_put_root()).
*/
- static_call(kvm_x86_flush_tlb_current)(vcpu);
+ kvm_x86_call(flush_tlb_current)(vcpu);
out:
return r;
}
@@ -5886,14 +5994,24 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
}
if (r == RET_PF_INVALID) {
+ vcpu->stat.pf_taken++;
+
r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false,
- &emulation_type);
+ &emulation_type, NULL);
if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm))
return -EIO;
}
if (r < 0)
return r;
+
+ if (r == RET_PF_FIXED)
+ vcpu->stat.pf_fixed++;
+ else if (r == RET_PF_EMULATE)
+ vcpu->stat.pf_emulate++;
+ else if (r == RET_PF_SPURIOUS)
+ vcpu->stat.pf_spurious++;
+
if (r != RET_PF_EMULATE)
return 1;
@@ -5995,7 +6113,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
if (is_noncanonical_address(addr, vcpu))
return;
- static_call(kvm_x86_flush_tlb_gva)(vcpu, addr);
+ kvm_x86_call(flush_tlb_gva)(vcpu, addr);
}
if (!mmu->sync_spte)
@@ -6787,6 +6905,7 @@ restart:
return need_tlb_flush;
}
+EXPORT_SYMBOL_GPL(kvm_zap_gfn_range);
static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm,
const struct kvm_memory_slot *slot)
@@ -6917,7 +7036,6 @@ static unsigned long mmu_shrink_scan(struct shrinker *shrink,
list_for_each_entry(kvm, &vm_list, vm_list) {
int idx;
- LIST_HEAD(invalid_list);
/*
* Never scan more than sc->nr_to_scan VM instances.
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index ce2fcd19ba6b..1721d97743e9 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -288,7 +288,8 @@ static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
}
static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
- u64 err, bool prefetch, int *emulation_type)
+ u64 err, bool prefetch,
+ int *emulation_type, u8 *level)
{
struct kvm_page_fault fault = {
.addr = cr2_or_gpa,
@@ -318,14 +319,6 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn);
}
- /*
- * Async #PF "faults", a.k.a. prefetch faults, are not faults from the
- * guest perspective and have already been counted at the time of the
- * original fault.
- */
- if (!prefetch)
- vcpu->stat.pf_taken++;
-
if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp)
r = kvm_tdp_page_fault(vcpu, &fault);
else
@@ -344,20 +337,9 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
if (fault.write_fault_to_shadow_pgtable && emulation_type)
*emulation_type |= EMULTYPE_WRITE_PF_TO_SP;
+ if (level)
+ *level = fault.goal_level;
- /*
- * Similar to above, prefetch faults aren't truly spurious, and the
- * async #PF path doesn't do emulation. Do count faults that are fixed
- * by the async #PF handler though, otherwise they'll never be counted.
- */
- if (r == RET_PF_FIXED)
- vcpu->stat.pf_fixed++;
- else if (prefetch)
- ;
- else if (r == RET_PF_EMULATE)
- vcpu->stat.pf_emulate++;
- else if (r == RET_PF_SPURIOUS)
- vcpu->stat.pf_spurious++;
return r;
}
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index d3dbcf382ed2..69941cebb3a8 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -911,7 +911,8 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
gpa_t pte_gpa;
gfn_t gfn;
- if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE))
+ if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE ||
+ !sp->shadowed_translation))
return 0;
first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index a5e014d7bc62..d4527965e48c 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -43,7 +43,25 @@ u64 __read_mostly shadow_acc_track_mask;
u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
-u8 __read_mostly shadow_phys_bits;
+static u8 __init kvm_get_host_maxphyaddr(void)
+{
+ /*
+ * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
+ * in CPU detection code, but the processor treats those reduced bits as
+ * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
+ * the physical address bits reported by CPUID, i.e. the raw MAXPHYADDR,
+ * when reasoning about CPU behavior with respect to MAXPHYADDR.
+ */
+ if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
+ return cpuid_eax(0x80000008) & 0xff;
+
+ /*
+ * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
+ * custom CPUID. Proceed with whatever the kernel found since these features
+ * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
+ */
+ return boot_cpu_data.x86_phys_bits;
+}
void __init kvm_mmu_spte_module_init(void)
{
@@ -55,6 +73,8 @@ void __init kvm_mmu_spte_module_init(void)
* will change when the vendor module is (re)loaded.
*/
allow_mmio_caching = enable_mmio_caching;
+
+ kvm_host.maxphyaddr = kvm_get_host_maxphyaddr();
}
static u64 generation_mmio_spte_mask(u64 gen)
@@ -190,8 +210,8 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
spte |= PT_PAGE_SIZE_MASK;
if (shadow_memtype_mask)
- spte |= static_call(kvm_x86_get_mt_mask)(vcpu, gfn,
- kvm_is_mmio_pfn(pfn));
+ spte |= kvm_x86_call(get_mt_mask)(vcpu, gfn,
+ kvm_is_mmio_pfn(pfn));
if (host_writable)
spte |= shadow_host_writable_mask;
else
@@ -271,18 +291,12 @@ static u64 make_spte_executable(u64 spte)
* This is used during huge page splitting to build the SPTEs that make up the
* new page table.
*/
-u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte, union kvm_mmu_page_role role,
- int index)
+u64 make_huge_page_split_spte(struct kvm *kvm, u64 huge_spte,
+ union kvm_mmu_page_role role, int index)
{
- u64 child_spte;
-
- if (WARN_ON_ONCE(!is_shadow_present_pte(huge_spte)))
- return 0;
+ u64 child_spte = huge_spte;
- if (WARN_ON_ONCE(!is_large_pte(huge_spte)))
- return 0;
-
- child_spte = huge_spte;
+ KVM_BUG_ON(!is_shadow_present_pte(huge_spte) || !is_large_pte(huge_spte), kvm);
/*
* The child_spte already has the base address of the huge page being
@@ -383,7 +397,7 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
* not set any RWX bits.
*/
if (WARN_ON((mmio_value & mmio_mask) != mmio_value) ||
- WARN_ON(mmio_value && (REMOVED_SPTE & mmio_mask) == mmio_value))
+ WARN_ON(mmio_value && (FROZEN_SPTE & mmio_mask) == mmio_value))
mmio_value = 0;
if (!mmio_value)
@@ -441,8 +455,6 @@ void kvm_mmu_reset_all_pte_masks(void)
u8 low_phys_bits;
u64 mask;
- shadow_phys_bits = kvm_get_shadow_phys_bits();
-
/*
* If the CPU has 46 or less physical address bits, then set an
* appropriate mask to guard against L1TF attacks. Otherwise, it is
@@ -494,7 +506,7 @@ void kvm_mmu_reset_all_pte_masks(void)
* 52-bit physical addresses then there are no reserved PA bits in the
* PTEs and so the reserved PA approach must be disabled.
*/
- if (shadow_phys_bits < 52)
+ if (kvm_host.maxphyaddr < 52)
mask = BIT_ULL(51) | PT_PRESENT_MASK;
else
mask = 0;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 52fa004a1fbc..ef793c459b05 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -202,7 +202,7 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
/*
* If a thread running without exclusive control of the MMU lock must perform a
- * multi-part operation on an SPTE, it can set the SPTE to REMOVED_SPTE as a
+ * multi-part operation on an SPTE, it can set the SPTE to FROZEN_SPTE as a
* non-present intermediate value. Other threads which encounter this value
* should not modify the SPTE.
*
@@ -212,14 +212,14 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
*
* Only used by the TDP MMU.
*/
-#define REMOVED_SPTE (SHADOW_NONPRESENT_VALUE | 0x5a0ULL)
+#define FROZEN_SPTE (SHADOW_NONPRESENT_VALUE | 0x5a0ULL)
/* Removed SPTEs must not be misconstrued as shadow present PTEs. */
-static_assert(!(REMOVED_SPTE & SPTE_MMU_PRESENT_MASK));
+static_assert(!(FROZEN_SPTE & SPTE_MMU_PRESENT_MASK));
-static inline bool is_removed_spte(u64 spte)
+static inline bool is_frozen_spte(u64 spte)
{
- return spte == REMOVED_SPTE;
+ return spte == FROZEN_SPTE;
}
/* Get an SPTE's index into its parent's page table (and the spt array). */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 36539c1b36cd..c7dc49ee7388 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -365,8 +365,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
* value to the removed SPTE value.
*/
for (;;) {
- old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, REMOVED_SPTE);
- if (!is_removed_spte(old_spte))
+ old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, FROZEN_SPTE);
+ if (!is_frozen_spte(old_spte))
break;
cpu_relax();
}
@@ -397,11 +397,11 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
* No retry is needed in the atomic update path as the
* sole concern is dropping a Dirty bit, i.e. no other
* task can zap/remove the SPTE as mmu_lock is held for
- * write. Marking the SPTE as a removed SPTE is not
+ * write. Marking the SPTE as a frozen SPTE is not
* strictly necessary for the same reason, but using
- * the remove SPTE value keeps the shared/exclusive
+ * the frozen SPTE value keeps the shared/exclusive
* paths consistent and allows the handle_changed_spte()
- * call below to hardcode the new value to REMOVED_SPTE.
+ * call below to hardcode the new value to FROZEN_SPTE.
*
* Note, even though dropping a Dirty bit is the only
* scenario where a non-atomic update could result in a
@@ -413,10 +413,10 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
* it here.
*/
old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte,
- REMOVED_SPTE, level);
+ FROZEN_SPTE, level);
}
handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn,
- old_spte, REMOVED_SPTE, level, shared);
+ old_spte, FROZEN_SPTE, level, shared);
}
call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
@@ -490,19 +490,19 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
*/
if (!was_present && !is_present) {
/*
- * If this change does not involve a MMIO SPTE or removed SPTE,
+ * If this change does not involve a MMIO SPTE or frozen SPTE,
* it is unexpected. Log the change, though it should not
* impact the guest since both the former and current SPTEs
* are nonpresent.
*/
if (WARN_ON_ONCE(!is_mmio_spte(kvm, old_spte) &&
!is_mmio_spte(kvm, new_spte) &&
- !is_removed_spte(new_spte)))
+ !is_frozen_spte(new_spte)))
pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
"should not be replaced with another,\n"
"different nonpresent SPTE, unless one or both\n"
"are MMIO SPTEs, or the new SPTE is\n"
- "a temporary removed SPTE.\n"
+ "a temporary frozen SPTE.\n"
"as_id: %d gfn: %llx old_spte: %llx new_spte: %llx level: %d",
as_id, gfn, old_spte, new_spte, level);
return;
@@ -530,7 +530,8 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
kvm_set_pfn_accessed(spte_to_pfn(old_spte));
}
-static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte)
+static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter,
+ u64 new_spte)
{
u64 *sptep = rcu_dereference(iter->sptep);
@@ -540,7 +541,7 @@ static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte)
* and pre-checking before inserting a new SPTE is advantageous as it
* avoids unnecessary work.
*/
- WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+ WARN_ON_ONCE(iter->yielded || is_frozen_spte(iter->old_spte));
/*
* Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
@@ -572,9 +573,9 @@ static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte)
* no side-effects other than setting iter->old_spte to the last
* known value of the spte.
*/
-static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm,
- struct tdp_iter *iter,
- u64 new_spte)
+static inline int __must_check tdp_mmu_set_spte_atomic(struct kvm *kvm,
+ struct tdp_iter *iter,
+ u64 new_spte)
{
int ret;
@@ -590,8 +591,8 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm,
return 0;
}
-static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
- struct tdp_iter *iter)
+static inline int __must_check tdp_mmu_zap_spte_atomic(struct kvm *kvm,
+ struct tdp_iter *iter)
{
int ret;
@@ -603,26 +604,26 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
* in its place before the TLBs are flushed.
*
* Delay processing of the zapped SPTE until after TLBs are flushed and
- * the REMOVED_SPTE is replaced (see below).
+ * the FROZEN_SPTE is replaced (see below).
*/
- ret = __tdp_mmu_set_spte_atomic(iter, REMOVED_SPTE);
+ ret = __tdp_mmu_set_spte_atomic(iter, FROZEN_SPTE);
if (ret)
return ret;
kvm_flush_remote_tlbs_gfn(kvm, iter->gfn, iter->level);
/*
- * No other thread can overwrite the removed SPTE as they must either
+ * No other thread can overwrite the frozen SPTE as they must either
* wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not
- * overwrite the special removed SPTE value. Use the raw write helper to
+ * overwrite the special frozen SPTE value. Use the raw write helper to
* avoid an unnecessary check on volatile bits.
*/
__kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE);
/*
* Process the zapped SPTE after flushing TLBs, and after replacing
- * REMOVED_SPTE with 0. This minimizes the amount of time vCPUs are
- * blocked by the REMOVED_SPTE and reduces contention on the child
+ * FROZEN_SPTE with 0. This minimizes the amount of time vCPUs are
+ * blocked by the FROZEN_SPTE and reduces contention on the child
* SPTEs.
*/
handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
@@ -652,12 +653,12 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep,
/*
* No thread should be using this function to set SPTEs to or from the
- * temporary removed SPTE value.
+ * temporary frozen SPTE value.
* If operating under the MMU lock in read mode, tdp_mmu_set_spte_atomic
* should be used. If operating under the MMU lock in write mode, the
- * use of the removed SPTE should not be necessary.
+ * use of the frozen SPTE should not be necessary.
*/
- WARN_ON_ONCE(is_removed_spte(old_spte) || is_removed_spte(new_spte));
+ WARN_ON_ONCE(is_frozen_spte(old_spte) || is_frozen_spte(new_spte));
old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level);
@@ -1126,7 +1127,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
* If SPTE has been frozen by another thread, just give up and
* retry, avoiding unnecessary page table allocation and free.
*/
- if (is_removed_spte(iter.old_spte))
+ if (is_frozen_spte(iter.old_spte))
goto retry;
if (iter.level == fault->goal_level)
@@ -1339,17 +1340,15 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
return spte_set;
}
-static struct kvm_mmu_page *__tdp_mmu_alloc_sp_for_split(gfp_t gfp)
+static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(void)
{
struct kvm_mmu_page *sp;
- gfp |= __GFP_ZERO;
-
- sp = kmem_cache_alloc(mmu_page_header_cache, gfp);
+ sp = kmem_cache_zalloc(mmu_page_header_cache, GFP_KERNEL_ACCOUNT);
if (!sp)
return NULL;
- sp->spt = (void *)__get_free_page(gfp);
+ sp->spt = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
if (!sp->spt) {
kmem_cache_free(mmu_page_header_cache, sp);
return NULL;
@@ -1358,47 +1357,6 @@ static struct kvm_mmu_page *__tdp_mmu_alloc_sp_for_split(gfp_t gfp)
return sp;
}
-static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm,
- struct tdp_iter *iter,
- bool shared)
-{
- struct kvm_mmu_page *sp;
-
- kvm_lockdep_assert_mmu_lock_held(kvm, shared);
-
- /*
- * Since we are allocating while under the MMU lock we have to be
- * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct
- * reclaim and to avoid making any filesystem callbacks (which can end
- * up invoking KVM MMU notifiers, resulting in a deadlock).
- *
- * If this allocation fails we drop the lock and retry with reclaim
- * allowed.
- */
- sp = __tdp_mmu_alloc_sp_for_split(GFP_NOWAIT | __GFP_ACCOUNT);
- if (sp)
- return sp;
-
- rcu_read_unlock();
-
- if (shared)
- read_unlock(&kvm->mmu_lock);
- else
- write_unlock(&kvm->mmu_lock);
-
- iter->yielded = true;
- sp = __tdp_mmu_alloc_sp_for_split(GFP_KERNEL_ACCOUNT);
-
- if (shared)
- read_lock(&kvm->mmu_lock);
- else
- write_lock(&kvm->mmu_lock);
-
- rcu_read_lock();
-
- return sp;
-}
-
/* Note, the caller is responsible for initializing @sp. */
static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
struct kvm_mmu_page *sp, bool shared)
@@ -1445,7 +1403,6 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm,
{
struct kvm_mmu_page *sp = NULL;
struct tdp_iter iter;
- int ret = 0;
rcu_read_lock();
@@ -1469,17 +1426,31 @@ retry:
continue;
if (!sp) {
- sp = tdp_mmu_alloc_sp_for_split(kvm, &iter, shared);
+ rcu_read_unlock();
+
+ if (shared)
+ read_unlock(&kvm->mmu_lock);
+ else
+ write_unlock(&kvm->mmu_lock);
+
+ sp = tdp_mmu_alloc_sp_for_split();
+
+ if (shared)
+ read_lock(&kvm->mmu_lock);
+ else
+ write_lock(&kvm->mmu_lock);
+
if (!sp) {
- ret = -ENOMEM;
trace_kvm_mmu_split_huge_page(iter.gfn,
iter.old_spte,
- iter.level, ret);
- break;
+ iter.level, -ENOMEM);
+ return -ENOMEM;
}
- if (iter.yielded)
- continue;
+ rcu_read_lock();
+
+ iter.yielded = true;
+ continue;
}
tdp_mmu_init_child_sp(sp, &iter);
@@ -1500,7 +1471,7 @@ retry:
if (sp)
tdp_mmu_free_sp(sp);
- return ret;
+ return 0;
}
@@ -1801,12 +1772,11 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
*
* WARNING: This function is only intended to be called during fast_page_fault.
*/
-u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr,
+u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn,
u64 *spte)
{
struct tdp_iter iter;
struct kvm_mmu *mmu = vcpu->arch.mmu;
- gfn_t gfn = addr >> PAGE_SHIFT;
tdp_ptep_t sptep = NULL;
tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 58b55e61bd33..1b74e058a81c 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -64,7 +64,7 @@ static inline void kvm_tdp_mmu_walk_lockless_end(void)
int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
int *root_level);
-u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr,
+u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn,
u64 *spte);
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index a67c28a56417..05490b9d8a43 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -19,33 +19,21 @@
#include <asm/mtrr.h>
#include "cpuid.h"
-#include "mmu.h"
-#define IA32_MTRR_DEF_TYPE_E (1ULL << 11)
-#define IA32_MTRR_DEF_TYPE_FE (1ULL << 10)
-#define IA32_MTRR_DEF_TYPE_TYPE_MASK (0xff)
-
-static bool is_mtrr_base_msr(unsigned int msr)
-{
- /* MTRR base MSRs use even numbers, masks use odd numbers. */
- return !(msr & 0x1);
-}
-
-static struct kvm_mtrr_range *var_mtrr_msr_to_range(struct kvm_vcpu *vcpu,
- unsigned int msr)
+static u64 *find_mtrr(struct kvm_vcpu *vcpu, unsigned int msr)
{
- int index = (msr - MTRRphysBase_MSR(0)) / 2;
-
- return &vcpu->arch.mtrr_state.var_ranges[index];
-}
+ int index;
-static bool msr_mtrr_valid(unsigned msr)
-{
switch (msr) {
case MTRRphysBase_MSR(0) ... MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1):
+ index = msr - MTRRphysBase_MSR(0);
+ return &vcpu->arch.mtrr_state.var[index];
case MSR_MTRRfix64K_00000:
+ return &vcpu->arch.mtrr_state.fixed_64k;
case MSR_MTRRfix16K_80000:
case MSR_MTRRfix16K_A0000:
+ index = msr - MSR_MTRRfix16K_80000;
+ return &vcpu->arch.mtrr_state.fixed_16k[index];
case MSR_MTRRfix4K_C0000:
case MSR_MTRRfix4K_C8000:
case MSR_MTRRfix4K_D0000:
@@ -54,10 +42,14 @@ static bool msr_mtrr_valid(unsigned msr)
case MSR_MTRRfix4K_E8000:
case MSR_MTRRfix4K_F0000:
case MSR_MTRRfix4K_F8000:
+ index = msr - MSR_MTRRfix4K_C0000;
+ return &vcpu->arch.mtrr_state.fixed_4k[index];
case MSR_MTRRdefType:
- return true;
+ return &vcpu->arch.mtrr_state.deftype;
+ default:
+ break;
}
- return false;
+ return NULL;
}
static bool valid_mtrr_type(unsigned t)
@@ -70,9 +62,6 @@ static bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
int i;
u64 mask;
- if (!msr_mtrr_valid(msr))
- return false;
-
if (msr == MSR_MTRRdefType) {
if (data & ~0xcff)
return false;
@@ -85,8 +74,9 @@ static bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
}
/* variable MTRRs */
- WARN_ON(!(msr >= MTRRphysBase_MSR(0) &&
- msr <= MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1)));
+ if (WARN_ON_ONCE(!(msr >= MTRRphysBase_MSR(0) &&
+ msr <= MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1))))
+ return false;
mask = kvm_vcpu_reserved_gpa_bits_raw(vcpu);
if ((msr & 1) == 0) {
@@ -94,309 +84,32 @@ static bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
if (!valid_mtrr_type(data & 0xff))
return false;
mask |= 0xf00;
- } else
+ } else {
/* MTRR mask */
mask |= 0x7ff;
-
- return (data & mask) == 0;
-}
-
-static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state)
-{
- return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_E);
-}
-
-static bool fixed_mtrr_is_enabled(struct kvm_mtrr *mtrr_state)
-{
- return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_FE);
-}
-
-static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
-{
- return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
-}
-
-static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu)
-{
- /*
- * Intel SDM 11.11.2.2: all MTRRs are disabled when
- * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC
- * memory type is applied to all of physical memory.
- *
- * However, virtual machines can be run with CPUID such that
- * there are no MTRRs. In that case, the firmware will never
- * enable MTRRs and it is obviously undesirable to run the
- * guest entirely with UC memory and we use WB.
- */
- if (guest_cpuid_has(vcpu, X86_FEATURE_MTRR))
- return MTRR_TYPE_UNCACHABLE;
- else
- return MTRR_TYPE_WRBACK;
-}
-
-/*
-* Three terms are used in the following code:
-* - segment, it indicates the address segments covered by fixed MTRRs.
-* - unit, it corresponds to the MSR entry in the segment.
-* - range, a range is covered in one memory cache type.
-*/
-struct fixed_mtrr_segment {
- u64 start;
- u64 end;
-
- int range_shift;
-
- /* the start position in kvm_mtrr.fixed_ranges[]. */
- int range_start;
-};
-
-static struct fixed_mtrr_segment fixed_seg_table[] = {
- /* MSR_MTRRfix64K_00000, 1 unit. 64K fixed mtrr. */
- {
- .start = 0x0,
- .end = 0x80000,
- .range_shift = 16, /* 64K */
- .range_start = 0,
- },
-
- /*
- * MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000, 2 units,
- * 16K fixed mtrr.
- */
- {
- .start = 0x80000,
- .end = 0xc0000,
- .range_shift = 14, /* 16K */
- .range_start = 8,
- },
-
- /*
- * MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000, 8 units,
- * 4K fixed mtrr.
- */
- {
- .start = 0xc0000,
- .end = 0x100000,
- .range_shift = 12, /* 12K */
- .range_start = 24,
- }
-};
-
-/*
- * The size of unit is covered in one MSR, one MSR entry contains
- * 8 ranges so that unit size is always 8 * 2^range_shift.
- */
-static u64 fixed_mtrr_seg_unit_size(int seg)
-{
- return 8 << fixed_seg_table[seg].range_shift;
-}
-
-static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit)
-{
- switch (msr) {
- case MSR_MTRRfix64K_00000:
- *seg = 0;
- *unit = 0;
- break;
- case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000:
- *seg = 1;
- *unit = array_index_nospec(
- msr - MSR_MTRRfix16K_80000,
- MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1);
- break;
- case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000:
- *seg = 2;
- *unit = array_index_nospec(
- msr - MSR_MTRRfix4K_C0000,
- MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1);
- break;
- default:
- return false;
}
- return true;
-}
-
-static void fixed_mtrr_seg_unit_range(int seg, int unit, u64 *start, u64 *end)
-{
- struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
- u64 unit_size = fixed_mtrr_seg_unit_size(seg);
-
- *start = mtrr_seg->start + unit * unit_size;
- *end = *start + unit_size;
- WARN_ON(*end > mtrr_seg->end);
-}
-
-static int fixed_mtrr_seg_unit_range_index(int seg, int unit)
-{
- struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
-
- WARN_ON(mtrr_seg->start + unit * fixed_mtrr_seg_unit_size(seg)
- > mtrr_seg->end);
-
- /* each unit has 8 ranges. */
- return mtrr_seg->range_start + 8 * unit;
-}
-
-static int fixed_mtrr_seg_end_range_index(int seg)
-{
- struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
- int n;
-
- n = (mtrr_seg->end - mtrr_seg->start) >> mtrr_seg->range_shift;
- return mtrr_seg->range_start + n - 1;
-}
-
-static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end)
-{
- int seg, unit;
-
- if (!fixed_msr_to_seg_unit(msr, &seg, &unit))
- return false;
-
- fixed_mtrr_seg_unit_range(seg, unit, start, end);
- return true;
-}
-
-static int fixed_msr_to_range_index(u32 msr)
-{
- int seg, unit;
-
- if (!fixed_msr_to_seg_unit(msr, &seg, &unit))
- return -1;
-
- return fixed_mtrr_seg_unit_range_index(seg, unit);
-}
-
-static int fixed_mtrr_addr_to_seg(u64 addr)
-{
- struct fixed_mtrr_segment *mtrr_seg;
- int seg, seg_num = ARRAY_SIZE(fixed_seg_table);
-
- for (seg = 0; seg < seg_num; seg++) {
- mtrr_seg = &fixed_seg_table[seg];
- if (mtrr_seg->start <= addr && addr < mtrr_seg->end)
- return seg;
- }
-
- return -1;
-}
-
-static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg)
-{
- struct fixed_mtrr_segment *mtrr_seg;
- int index;
-
- mtrr_seg = &fixed_seg_table[seg];
- index = mtrr_seg->range_start;
- index += (addr - mtrr_seg->start) >> mtrr_seg->range_shift;
- return index;
-}
-
-static u64 fixed_mtrr_range_end_addr(int seg, int index)
-{
- struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
- int pos = index - mtrr_seg->range_start;
-
- return mtrr_seg->start + ((pos + 1) << mtrr_seg->range_shift);
-}
-
-static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end)
-{
- u64 mask;
-
- *start = range->base & PAGE_MASK;
-
- mask = range->mask & PAGE_MASK;
-
- /* This cannot overflow because writing to the reserved bits of
- * variable MTRRs causes a #GP.
- */
- *end = (*start | ~mask) + 1;
-}
-
-static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr)
-{
- struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
- gfn_t start, end;
-
- if (!kvm_mmu_honors_guest_mtrrs(vcpu->kvm))
- return;
-
- if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType)
- return;
-
- /* fixed MTRRs. */
- if (fixed_msr_to_range(msr, &start, &end)) {
- if (!fixed_mtrr_is_enabled(mtrr_state))
- return;
- } else if (msr == MSR_MTRRdefType) {
- start = 0x0;
- end = ~0ULL;
- } else {
- /* variable range MTRRs. */
- var_mtrr_range(var_mtrr_msr_to_range(vcpu, msr), &start, &end);
- }
-
- kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end));
-}
-
-static bool var_mtrr_range_is_valid(struct kvm_mtrr_range *range)
-{
- return (range->mask & (1 << 11)) != 0;
-}
-
-static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
- struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
- struct kvm_mtrr_range *tmp, *cur;
-
- cur = var_mtrr_msr_to_range(vcpu, msr);
-
- /* remove the entry if it's in the list. */
- if (var_mtrr_range_is_valid(cur))
- list_del(&cur->node);
-
- /*
- * Set all illegal GPA bits in the mask, since those bits must
- * implicitly be 0. The bits are then cleared when reading them.
- */
- if (is_mtrr_base_msr(msr))
- cur->base = data;
- else
- cur->mask = data | kvm_vcpu_reserved_gpa_bits_raw(vcpu);
-
- /* add it to the list if it's enabled. */
- if (var_mtrr_range_is_valid(cur)) {
- list_for_each_entry(tmp, &mtrr_state->head, node)
- if (cur->base >= tmp->base)
- break;
- list_add_tail(&cur->node, &tmp->node);
- }
+ return (data & mask) == 0;
}
int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
- int index;
+ u64 *mtrr;
- if (!kvm_mtrr_valid(vcpu, msr, data))
+ mtrr = find_mtrr(vcpu, msr);
+ if (!mtrr)
return 1;
- index = fixed_msr_to_range_index(msr);
- if (index >= 0)
- *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data;
- else if (msr == MSR_MTRRdefType)
- vcpu->arch.mtrr_state.deftype = data;
- else
- set_var_mtrr_msr(vcpu, msr, data);
+ if (!kvm_mtrr_valid(vcpu, msr, data))
+ return 1;
- update_mtrr(vcpu, msr);
+ *mtrr = data;
return 0;
}
int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
- int index;
+ u64 *mtrr;
/* MSR_MTRRcap is a readonly MSR. */
if (msr == MSR_MTRRcap) {
@@ -410,311 +123,10 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
return 0;
}
- if (!msr_mtrr_valid(msr))
+ mtrr = find_mtrr(vcpu, msr);
+ if (!mtrr)
return 1;
- index = fixed_msr_to_range_index(msr);
- if (index >= 0) {
- *pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index];
- } else if (msr == MSR_MTRRdefType) {
- *pdata = vcpu->arch.mtrr_state.deftype;
- } else {
- /* Variable MTRRs */
- if (is_mtrr_base_msr(msr))
- *pdata = var_mtrr_msr_to_range(vcpu, msr)->base;
- else
- *pdata = var_mtrr_msr_to_range(vcpu, msr)->mask;
-
- *pdata &= ~kvm_vcpu_reserved_gpa_bits_raw(vcpu);
- }
-
+ *pdata = *mtrr;
return 0;
}
-
-void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu)
-{
- INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head);
-}
-
-struct mtrr_iter {
- /* input fields. */
- struct kvm_mtrr *mtrr_state;
- u64 start;
- u64 end;
-
- /* output fields. */
- int mem_type;
- /* mtrr is completely disabled? */
- bool mtrr_disabled;
- /* [start, end) is not fully covered in MTRRs? */
- bool partial_map;
-
- /* private fields. */
- union {
- /* used for fixed MTRRs. */
- struct {
- int index;
- int seg;
- };
-
- /* used for var MTRRs. */
- struct {
- struct kvm_mtrr_range *range;
- /* max address has been covered in var MTRRs. */
- u64 start_max;
- };
- };
-
- bool fixed;
-};
-
-static bool mtrr_lookup_fixed_start(struct mtrr_iter *iter)
-{
- int seg, index;
-
- if (!fixed_mtrr_is_enabled(iter->mtrr_state))
- return false;
-
- seg = fixed_mtrr_addr_to_seg(iter->start);
- if (seg < 0)
- return false;
-
- iter->fixed = true;
- index = fixed_mtrr_addr_seg_to_range_index(iter->start, seg);
- iter->index = index;
- iter->seg = seg;
- return true;
-}
-
-static bool match_var_range(struct mtrr_iter *iter,
- struct kvm_mtrr_range *range)
-{
- u64 start, end;
-
- var_mtrr_range(range, &start, &end);
- if (!(start >= iter->end || end <= iter->start)) {
- iter->range = range;
-
- /*
- * the function is called when we do kvm_mtrr.head walking.
- * Range has the minimum base address which interleaves
- * [looker->start_max, looker->end).
- */
- iter->partial_map |= iter->start_max < start;
-
- /* update the max address has been covered. */
- iter->start_max = max(iter->start_max, end);
- return true;
- }
-
- return false;
-}
-
-static void __mtrr_lookup_var_next(struct mtrr_iter *iter)
-{
- struct kvm_mtrr *mtrr_state = iter->mtrr_state;
-
- list_for_each_entry_continue(iter->range, &mtrr_state->head, node)
- if (match_var_range(iter, iter->range))
- return;
-
- iter->range = NULL;
- iter->partial_map |= iter->start_max < iter->end;
-}
-
-static void mtrr_lookup_var_start(struct mtrr_iter *iter)
-{
- struct kvm_mtrr *mtrr_state = iter->mtrr_state;
-
- iter->fixed = false;
- iter->start_max = iter->start;
- iter->range = NULL;
- iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
-
- __mtrr_lookup_var_next(iter);
-}
-
-static void mtrr_lookup_fixed_next(struct mtrr_iter *iter)
-{
- /* terminate the lookup. */
- if (fixed_mtrr_range_end_addr(iter->seg, iter->index) >= iter->end) {
- iter->fixed = false;
- iter->range = NULL;
- return;
- }
-
- iter->index++;
-
- /* have looked up for all fixed MTRRs. */
- if (iter->index >= ARRAY_SIZE(iter->mtrr_state->fixed_ranges))
- return mtrr_lookup_var_start(iter);
-
- /* switch to next segment. */
- if (iter->index > fixed_mtrr_seg_end_range_index(iter->seg))
- iter->seg++;
-}
-
-static void mtrr_lookup_var_next(struct mtrr_iter *iter)
-{
- __mtrr_lookup_var_next(iter);
-}
-
-static void mtrr_lookup_start(struct mtrr_iter *iter)
-{
- if (!mtrr_is_enabled(iter->mtrr_state)) {
- iter->mtrr_disabled = true;
- return;
- }
-
- if (!mtrr_lookup_fixed_start(iter))
- mtrr_lookup_var_start(iter);
-}
-
-static void mtrr_lookup_init(struct mtrr_iter *iter,
- struct kvm_mtrr *mtrr_state, u64 start, u64 end)
-{
- iter->mtrr_state = mtrr_state;
- iter->start = start;
- iter->end = end;
- iter->mtrr_disabled = false;
- iter->partial_map = false;
- iter->fixed = false;
- iter->range = NULL;
-
- mtrr_lookup_start(iter);
-}
-
-static bool mtrr_lookup_okay(struct mtrr_iter *iter)
-{
- if (iter->fixed) {
- iter->mem_type = iter->mtrr_state->fixed_ranges[iter->index];
- return true;
- }
-
- if (iter->range) {
- iter->mem_type = iter->range->base & 0xff;
- return true;
- }
-
- return false;
-}
-
-static void mtrr_lookup_next(struct mtrr_iter *iter)
-{
- if (iter->fixed)
- mtrr_lookup_fixed_next(iter);
- else
- mtrr_lookup_var_next(iter);
-}
-
-#define mtrr_for_each_mem_type(_iter_, _mtrr_, _gpa_start_, _gpa_end_) \
- for (mtrr_lookup_init(_iter_, _mtrr_, _gpa_start_, _gpa_end_); \
- mtrr_lookup_okay(_iter_); mtrr_lookup_next(_iter_))
-
-u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
- struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
- struct mtrr_iter iter;
- u64 start, end;
- int type = -1;
- const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK)
- | (1 << MTRR_TYPE_WRTHROUGH);
-
- start = gfn_to_gpa(gfn);
- end = start + PAGE_SIZE;
-
- mtrr_for_each_mem_type(&iter, mtrr_state, start, end) {
- int curr_type = iter.mem_type;
-
- /*
- * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR
- * Precedences.
- */
-
- if (type == -1) {
- type = curr_type;
- continue;
- }
-
- /*
- * If two or more variable memory ranges match and the
- * memory types are identical, then that memory type is
- * used.
- */
- if (type == curr_type)
- continue;
-
- /*
- * If two or more variable memory ranges match and one of
- * the memory types is UC, the UC memory type used.
- */
- if (curr_type == MTRR_TYPE_UNCACHABLE)
- return MTRR_TYPE_UNCACHABLE;
-
- /*
- * If two or more variable memory ranges match and the
- * memory types are WT and WB, the WT memory type is used.
- */
- if (((1 << type) & wt_wb_mask) &&
- ((1 << curr_type) & wt_wb_mask)) {
- type = MTRR_TYPE_WRTHROUGH;
- continue;
- }
-
- /*
- * For overlaps not defined by the above rules, processor
- * behavior is undefined.
- */
-
- /* We use WB for this undefined behavior. :( */
- return MTRR_TYPE_WRBACK;
- }
-
- if (iter.mtrr_disabled)
- return mtrr_disabled_type(vcpu);
-
- /* not contained in any MTRRs. */
- if (type == -1)
- return mtrr_default_type(mtrr_state);
-
- /*
- * We just check one page, partially covered by MTRRs is
- * impossible.
- */
- WARN_ON(iter.partial_map);
-
- return type;
-}
-EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
-
-bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
- int page_num)
-{
- struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
- struct mtrr_iter iter;
- u64 start, end;
- int type = -1;
-
- start = gfn_to_gpa(gfn);
- end = gfn_to_gpa(gfn + page_num);
- mtrr_for_each_mem_type(&iter, mtrr_state, start, end) {
- if (type == -1) {
- type = iter.mem_type;
- continue;
- }
-
- if (type != iter.mem_type)
- return false;
- }
-
- if (iter.mtrr_disabled)
- return true;
-
- if (!iter.partial_map)
- return true;
-
- if (type == -1)
- return true;
-
- return type == mtrr_default_type(mtrr_state);
-}
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index a593b03c9aed..47a46283c866 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -34,16 +34,16 @@ EXPORT_SYMBOL_GPL(kvm_pmu_eventsel);
/* Precise Distribution of Instructions Retired (PDIR) */
static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = {
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, NULL),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, NULL),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, NULL),
/* Instruction-Accurate PDIR (PDIR++) */
- X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, NULL),
{}
};
/* Precise Distribution (PDist) */
static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = {
- X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, NULL),
{}
};
@@ -69,7 +69,7 @@ static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = {
* code. Each pmc, stored in kvm_pmc.idx field, is unique across
* all perf counters (both gp and fixed). The mapping relationship
* between pmc and perf counters is as the following:
- * * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters
+ * * Intel: [0 .. KVM_MAX_NR_INTEL_GP_COUNTERS-1] <=> gp counters
* [KVM_FIXED_PMC_BASE_IDX .. KVM_FIXED_PMC_BASE_IDX + 2] <=> fixed
* * AMD: [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H
* and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters
@@ -194,7 +194,7 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config,
attr.sample_period = get_sample_period(pmc, pmc->counter);
if ((attr.config & HSW_IN_TX_CHECKPOINTED) &&
- guest_cpuid_is_intel(pmc->vcpu)) {
+ (boot_cpu_has(X86_FEATURE_RTM) || boot_cpu_has(X86_FEATURE_HLE))) {
/*
* HSW_IN_TX_CHECKPOINTED is not supported with nonzero
* period. Just clear the sample period so at least
@@ -469,11 +469,11 @@ static int reprogram_counter(struct kvm_pmc *pmc)
if (pmc_is_fixed(pmc)) {
fixed_ctr_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl,
pmc->idx - KVM_FIXED_PMC_BASE_IDX);
- if (fixed_ctr_ctrl & 0x1)
+ if (fixed_ctr_ctrl & INTEL_FIXED_0_KERNEL)
eventsel |= ARCH_PERFMON_EVENTSEL_OS;
- if (fixed_ctr_ctrl & 0x2)
+ if (fixed_ctr_ctrl & INTEL_FIXED_0_USER)
eventsel |= ARCH_PERFMON_EVENTSEL_USR;
- if (fixed_ctr_ctrl & 0x8)
+ if (fixed_ctr_ctrl & INTEL_FIXED_0_ENABLE_PMI)
eventsel |= ARCH_PERFMON_EVENTSEL_INT;
new_config = (u64)fixed_ctr_ctrl;
}
@@ -521,9 +521,9 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
}
/*
- * Unused perf_events are only released if the corresponding MSRs
- * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
- * triggers KVM_REQ_PMU if cleanup is needed.
+ * Release unused perf_events if the corresponding guest MSRs weren't
+ * accessed during the last vCPU time slice (need_cleanup is set when
+ * the vCPU is scheduled back in).
*/
if (unlikely(pmu->need_cleanup))
kvm_pmu_cleanup(vcpu);
@@ -542,7 +542,7 @@ int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx)
if (!kvm_pmu_ops.check_rdpmc_early)
return 0;
- return static_call(kvm_x86_pmu_check_rdpmc_early)(vcpu, idx);
+ return kvm_pmu_call(check_rdpmc_early)(vcpu, idx);
}
bool is_vmware_backdoor_pmc(u32 pmc_idx)
@@ -591,12 +591,12 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
- pmc = static_call(kvm_x86_pmu_rdpmc_ecx_to_pmc)(vcpu, idx, &mask);
+ pmc = kvm_pmu_call(rdpmc_ecx_to_pmc)(vcpu, idx, &mask);
if (!pmc)
return 1;
if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCE) &&
- (static_call(kvm_x86_get_cpl)(vcpu) != 0) &&
+ (kvm_x86_call(get_cpl)(vcpu) != 0) &&
kvm_is_cr0_bit_set(vcpu, X86_CR0_PE))
return 1;
@@ -607,7 +607,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
{
if (lapic_in_kernel(vcpu)) {
- static_call_cond(kvm_x86_pmu_deliver_pmi)(vcpu);
+ kvm_pmu_call(deliver_pmi)(vcpu);
kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
}
}
@@ -622,14 +622,14 @@ bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
default:
break;
}
- return static_call(kvm_x86_pmu_msr_idx_to_pmc)(vcpu, msr) ||
- static_call(kvm_x86_pmu_is_valid_msr)(vcpu, msr);
+ return kvm_pmu_call(msr_idx_to_pmc)(vcpu, msr) ||
+ kvm_pmu_call(is_valid_msr)(vcpu, msr);
}
static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
- struct kvm_pmc *pmc = static_call(kvm_x86_pmu_msr_idx_to_pmc)(vcpu, msr);
+ struct kvm_pmc *pmc = kvm_pmu_call(msr_idx_to_pmc)(vcpu, msr);
if (pmc)
__set_bit(pmc->idx, pmu->pmc_in_use);
@@ -654,7 +654,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = 0;
break;
default:
- return static_call(kvm_x86_pmu_get_msr)(vcpu, msr_info);
+ return kvm_pmu_call(get_msr)(vcpu, msr_info);
}
return 0;
@@ -681,13 +681,13 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!msr_info->host_initiated)
break;
- if (data & pmu->global_status_mask)
+ if (data & pmu->global_status_rsvd)
return 1;
pmu->global_status = data;
break;
case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
- data &= ~pmu->global_ctrl_mask;
+ data &= ~pmu->global_ctrl_rsvd;
fallthrough;
case MSR_CORE_PERF_GLOBAL_CTRL:
if (!kvm_valid_perf_global_ctrl(pmu, data))
@@ -704,7 +704,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
* GLOBAL_OVF_CTRL, a.k.a. GLOBAL STATUS_RESET, clears bits in
* GLOBAL_STATUS, and so the set of reserved bits is the same.
*/
- if (data & pmu->global_status_mask)
+ if (data & pmu->global_status_rsvd)
return 1;
fallthrough;
case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
@@ -713,7 +713,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
default:
kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
- return static_call(kvm_x86_pmu_set_msr)(vcpu, msr_info);
+ return kvm_pmu_call(set_msr)(vcpu, msr_info);
}
return 0;
@@ -740,7 +740,7 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu)
pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
- static_call_cond(kvm_x86_pmu_reset)(vcpu);
+ kvm_pmu_call(reset)(vcpu);
}
@@ -768,17 +768,17 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
pmu->reserved_bits = 0xffffffff00200000ull;
pmu->raw_event_mask = X86_RAW_EVENT_MASK;
- pmu->global_ctrl_mask = ~0ull;
- pmu->global_status_mask = ~0ull;
- pmu->fixed_ctr_ctrl_mask = ~0ull;
- pmu->pebs_enable_mask = ~0ull;
- pmu->pebs_data_cfg_mask = ~0ull;
+ pmu->global_ctrl_rsvd = ~0ull;
+ pmu->global_status_rsvd = ~0ull;
+ pmu->fixed_ctr_ctrl_rsvd = ~0ull;
+ pmu->pebs_enable_rsvd = ~0ull;
+ pmu->pebs_data_cfg_rsvd = ~0ull;
bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX);
if (!vcpu->kvm->arch.enable_pmu)
return;
- static_call(kvm_x86_pmu_refresh)(vcpu);
+ kvm_pmu_call(refresh)(vcpu);
/*
* At RESET, both Intel and AMD CPUs set all enable bits for general
@@ -796,7 +796,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
memset(pmu, 0, sizeof(*pmu));
- static_call(kvm_x86_pmu_init)(vcpu);
+ kvm_pmu_call(init)(vcpu);
kvm_pmu_refresh(vcpu);
}
@@ -818,7 +818,7 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
pmc_stop_counter(pmc);
}
- static_call_cond(kvm_x86_pmu_cleanup)(vcpu);
+ kvm_pmu_call(cleanup)(vcpu);
bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
}
@@ -846,8 +846,8 @@ static inline bool cpl_is_matched(struct kvm_pmc *pmc)
} else {
config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl,
pmc->idx - KVM_FIXED_PMC_BASE_IDX);
- select_os = config & 0x1;
- select_user = config & 0x2;
+ select_os = config & INTEL_FIXED_0_KERNEL;
+ select_user = config & INTEL_FIXED_0_USER;
}
/*
@@ -857,7 +857,8 @@ static inline bool cpl_is_matched(struct kvm_pmc *pmc)
if (select_os == select_user)
return select_os;
- return (static_call(kvm_x86_get_cpl)(pmc->vcpu) == 0) ? select_os : select_user;
+ return (kvm_x86_call(get_cpl)(pmc->vcpu) == 0) ? select_os :
+ select_user;
}
void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel)
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 4d52b0b539ba..ad89d0bd6005 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -14,7 +14,8 @@
MSR_IA32_MISC_ENABLE_BTS_UNAVAIL)
/* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */
-#define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf)
+#define fixed_ctrl_field(ctrl_reg, idx) \
+ (((ctrl_reg) >> ((idx) * INTEL_FIXED_BITS_STRIDE)) & INTEL_FIXED_BITS_MASK)
#define VMWARE_BACKDOOR_PMC_HOST_TSC 0x10000
#define VMWARE_BACKDOOR_PMC_REAL_TIME 0x10001
@@ -129,7 +130,7 @@ static inline bool pmc_is_fixed(struct kvm_pmc *pmc)
static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu,
u64 data)
{
- return !(pmu->global_ctrl_mask & data);
+ return !(pmu->global_ctrl_rsvd & data);
}
/* returns general purpose PMC with the specified MSR. Note that it can be
@@ -170,7 +171,8 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
if (pmc_is_fixed(pmc))
return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
- pmc->idx - KVM_FIXED_PMC_BASE_IDX) & 0x3;
+ pmc->idx - KVM_FIXED_PMC_BASE_IDX) &
+ (INTEL_FIXED_0_KERNEL | INTEL_FIXED_0_USER);
return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
}
@@ -217,7 +219,7 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops)
kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp,
pmu_ops->MAX_NR_GP_COUNTERS);
kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed,
- KVM_PMC_MAX_FIXED);
+ KVM_MAX_NR_FIXED_COUNTERS);
kvm_pmu_eventsel.INSTRUCTIONS_RETIRED =
perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS);
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
index d06d43d8d2aa..00e3c27d2a87 100644
--- a/arch/x86/kvm/smm.c
+++ b/arch/x86/kvm/smm.c
@@ -200,11 +200,11 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu,
enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR);
enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR);
- static_call(kvm_x86_get_gdt)(vcpu, &dt);
+ kvm_x86_call(get_gdt)(vcpu, &dt);
smram->gdtr.base = dt.address;
smram->gdtr.limit = dt.size;
- static_call(kvm_x86_get_idt)(vcpu, &dt);
+ kvm_x86_call(get_idt)(vcpu, &dt);
smram->idtr.base = dt.address;
smram->idtr.limit = dt.size;
@@ -220,7 +220,7 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu,
smram->smm_revision = 0x00020000;
smram->smbase = vcpu->arch.smbase;
- smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+ smram->int_shadow = kvm_x86_call(get_interrupt_shadow)(vcpu);
}
#ifdef CONFIG_X86_64
@@ -250,13 +250,13 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu,
enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR);
- static_call(kvm_x86_get_idt)(vcpu, &dt);
+ kvm_x86_call(get_idt)(vcpu, &dt);
smram->idtr.limit = dt.size;
smram->idtr.base = dt.address;
enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR);
- static_call(kvm_x86_get_gdt)(vcpu, &dt);
+ kvm_x86_call(get_gdt)(vcpu, &dt);
smram->gdtr.limit = dt.size;
smram->gdtr.base = dt.address;
@@ -267,7 +267,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu,
enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
- smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+ smram->int_shadow = kvm_x86_call(get_interrupt_shadow)(vcpu);
}
#endif
@@ -297,7 +297,7 @@ void enter_smm(struct kvm_vcpu *vcpu)
* Kill the VM in the unlikely case of failure, because the VM
* can be in undefined state in this case.
*/
- if (static_call(kvm_x86_enter_smm)(vcpu, &smram))
+ if (kvm_x86_call(enter_smm)(vcpu, &smram))
goto error;
kvm_smm_changed(vcpu, true);
@@ -305,24 +305,24 @@ void enter_smm(struct kvm_vcpu *vcpu)
if (kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram)))
goto error;
- if (static_call(kvm_x86_get_nmi_mask)(vcpu))
+ if (kvm_x86_call(get_nmi_mask)(vcpu))
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
else
- static_call(kvm_x86_set_nmi_mask)(vcpu, true);
+ kvm_x86_call(set_nmi_mask)(vcpu, true);
kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0x8000);
- static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+ kvm_x86_call(set_interrupt_shadow)(vcpu, 0);
cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
- static_call(kvm_x86_set_cr0)(vcpu, cr0);
+ kvm_x86_call(set_cr0)(vcpu, cr0);
- static_call(kvm_x86_set_cr4)(vcpu, 0);
+ kvm_x86_call(set_cr4)(vcpu, 0);
/* Undocumented: IDT limit is set to zero on entry to SMM. */
dt.address = dt.size = 0;
- static_call(kvm_x86_set_idt)(vcpu, &dt);
+ kvm_x86_call(set_idt)(vcpu, &dt);
if (WARN_ON_ONCE(kvm_set_dr(vcpu, 7, DR7_FIXED_1)))
goto error;
@@ -354,7 +354,7 @@ void enter_smm(struct kvm_vcpu *vcpu)
#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- if (static_call(kvm_x86_set_efer)(vcpu, 0))
+ if (kvm_x86_call(set_efer)(vcpu, 0))
goto error;
#endif
@@ -479,11 +479,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
dt.address = smstate->gdtr.base;
dt.size = smstate->gdtr.limit;
- static_call(kvm_x86_set_gdt)(vcpu, &dt);
+ kvm_x86_call(set_gdt)(vcpu, &dt);
dt.address = smstate->idtr.base;
dt.size = smstate->idtr.limit;
- static_call(kvm_x86_set_idt)(vcpu, &dt);
+ kvm_x86_call(set_idt)(vcpu, &dt);
rsm_load_seg_32(vcpu, &smstate->es, smstate->es_sel, VCPU_SREG_ES);
rsm_load_seg_32(vcpu, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS);
@@ -501,7 +501,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
if (r != X86EMUL_CONTINUE)
return r;
- static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+ kvm_x86_call(set_interrupt_shadow)(vcpu, 0);
ctxt->interruptibility = (u8)smstate->int_shadow;
return r;
@@ -535,13 +535,13 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
dt.size = smstate->idtr.limit;
dt.address = smstate->idtr.base;
- static_call(kvm_x86_set_idt)(vcpu, &dt);
+ kvm_x86_call(set_idt)(vcpu, &dt);
rsm_load_seg_64(vcpu, &smstate->ldtr, VCPU_SREG_LDTR);
dt.size = smstate->gdtr.limit;
dt.address = smstate->gdtr.base;
- static_call(kvm_x86_set_gdt)(vcpu, &dt);
+ kvm_x86_call(set_gdt)(vcpu, &dt);
r = rsm_enter_protected_mode(vcpu, smstate->cr0, smstate->cr3, smstate->cr4);
if (r != X86EMUL_CONTINUE)
@@ -554,7 +554,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
rsm_load_seg_64(vcpu, &smstate->fs, VCPU_SREG_FS);
rsm_load_seg_64(vcpu, &smstate->gs, VCPU_SREG_GS);
- static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+ kvm_x86_call(set_interrupt_shadow)(vcpu, 0);
ctxt->interruptibility = (u8)smstate->int_shadow;
return X86EMUL_CONTINUE;
@@ -576,7 +576,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
return X86EMUL_UNHANDLEABLE;
if ((vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK) == 0)
- static_call(kvm_x86_set_nmi_mask)(vcpu, false);
+ kvm_x86_call(set_nmi_mask)(vcpu, false);
kvm_smm_changed(vcpu, false);
@@ -628,7 +628,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
* state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (static_call(kvm_x86_leave_smm)(vcpu, &smram))
+ if (kvm_x86_call(leave_smm)(vcpu, &smram))
return X86EMUL_UNHANDLEABLE;
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 55b9a6d96bcf..6f704c1037e5 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1181,7 +1181,7 @@ int svm_allocate_nested(struct vcpu_svm *svm)
if (svm->nested.initialized)
return 0;
- vmcb02_page = snp_safe_alloc_page(&svm->vcpu);
+ vmcb02_page = snp_safe_alloc_page();
if (!vmcb02_page)
return -ENOMEM;
svm->nested.vmcb02.ptr = page_address(vmcb02_page);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index dfcc38bd97d3..22d5a65b410c 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -199,8 +199,8 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
kvm_pmu_cap.num_counters_gp);
if (pmu->version > 1) {
- pmu->global_ctrl_mask = ~((1ull << pmu->nr_arch_gp_counters) - 1);
- pmu->global_status_mask = pmu->global_ctrl_mask;
+ pmu->global_ctrl_rsvd = ~((1ull << pmu->nr_arch_gp_counters) - 1);
+ pmu->global_status_rsvd = pmu->global_ctrl_rsvd;
}
pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
@@ -217,10 +217,9 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
int i;
- BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > AMD64_NUM_COUNTERS_CORE);
- BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > INTEL_PMC_MAX_GENERIC);
+ BUILD_BUG_ON(KVM_MAX_NR_AMD_GP_COUNTERS > AMD64_NUM_COUNTERS_CORE);
- for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC ; i++) {
+ for (i = 0; i < KVM_MAX_NR_AMD_GP_COUNTERS; i++) {
pmu->gp_counters[i].type = KVM_PMC_GP;
pmu->gp_counters[i].vcpu = vcpu;
pmu->gp_counters[i].idx = i;
@@ -238,6 +237,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = {
.refresh = amd_pmu_refresh,
.init = amd_pmu_init,
.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
- .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC,
+ .MAX_NR_GP_COUNTERS = KVM_MAX_NR_AMD_GP_COUNTERS,
.MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS,
};
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 95095a233a45..a16c873b3232 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -19,12 +19,14 @@
#include <linux/misc_cgroup.h>
#include <linux/processor.h>
#include <linux/trace_events.h>
+#include <uapi/linux/sev-guest.h>
#include <asm/pkru.h>
#include <asm/trapnr.h>
#include <asm/fpu/xcr.h>
#include <asm/fpu/xstate.h>
#include <asm/debugreg.h>
+#include <asm/sev.h>
#include "mmu.h"
#include "x86.h"
@@ -37,7 +39,7 @@
#define GHCB_VERSION_DEFAULT 2ULL
#define GHCB_VERSION_MIN 1ULL
-#define GHCB_HV_FT_SUPPORTED GHCB_HV_FT_SNP
+#define GHCB_HV_FT_SUPPORTED (GHCB_HV_FT_SNP | GHCB_HV_FT_SNP_AP_CREATION)
/* enable/disable SEV support */
static bool sev_enabled = true;
@@ -47,6 +49,10 @@ module_param_named(sev, sev_enabled, bool, 0444);
static bool sev_es_enabled = true;
module_param_named(sev_es, sev_es_enabled, bool, 0444);
+/* enable/disable SEV-SNP support */
+static bool sev_snp_enabled = true;
+module_param_named(sev_snp, sev_snp_enabled, bool, 0444);
+
/* enable/disable SEV-ES DebugSwap support */
static bool sev_es_debug_swap_enabled = true;
module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
@@ -56,6 +62,23 @@ static u64 sev_supported_vmsa_features;
#define AP_RESET_HOLD_NAE_EVENT 1
#define AP_RESET_HOLD_MSR_PROTO 2
+/* As defined by SEV-SNP Firmware ABI, under "Guest Policy". */
+#define SNP_POLICY_MASK_API_MINOR GENMASK_ULL(7, 0)
+#define SNP_POLICY_MASK_API_MAJOR GENMASK_ULL(15, 8)
+#define SNP_POLICY_MASK_SMT BIT_ULL(16)
+#define SNP_POLICY_MASK_RSVD_MBO BIT_ULL(17)
+#define SNP_POLICY_MASK_DEBUG BIT_ULL(19)
+#define SNP_POLICY_MASK_SINGLE_SOCKET BIT_ULL(20)
+
+#define SNP_POLICY_MASK_VALID (SNP_POLICY_MASK_API_MINOR | \
+ SNP_POLICY_MASK_API_MAJOR | \
+ SNP_POLICY_MASK_SMT | \
+ SNP_POLICY_MASK_RSVD_MBO | \
+ SNP_POLICY_MASK_DEBUG | \
+ SNP_POLICY_MASK_SINGLE_SOCKET)
+
+#define INITIAL_VMSA_GPA 0xFFFFFFFFF000
+
static u8 sev_enc_bit;
static DECLARE_RWSEM(sev_deactivate_lock);
static DEFINE_MUTEX(sev_bitmap_lock);
@@ -66,6 +89,8 @@ static unsigned int nr_asids;
static unsigned long *sev_asid_bitmap;
static unsigned long *sev_reclaim_asid_bitmap;
+static int snp_decommission_context(struct kvm *kvm);
+
struct enc_region {
struct list_head list;
unsigned long npages;
@@ -92,12 +117,17 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
down_write(&sev_deactivate_lock);
wbinvd_on_all_cpus();
- ret = sev_guest_df_flush(&error);
+
+ if (sev_snp_enabled)
+ ret = sev_do_cmd(SEV_CMD_SNP_DF_FLUSH, NULL, &error);
+ else
+ ret = sev_guest_df_flush(&error);
up_write(&sev_deactivate_lock);
if (ret)
- pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error);
+ pr_err("SEV%s: DF_FLUSH failed, ret=%d, error=%#x\n",
+ sev_snp_enabled ? "-SNP" : "", ret, error);
return ret;
}
@@ -233,6 +263,53 @@ static void sev_decommission(unsigned int handle)
sev_guest_decommission(&decommission, NULL);
}
+/*
+ * Transition a page to hypervisor-owned/shared state in the RMP table. This
+ * should not fail under normal conditions, but leak the page should that
+ * happen since it will no longer be usable by the host due to RMP protections.
+ */
+static int kvm_rmp_make_shared(struct kvm *kvm, u64 pfn, enum pg_level level)
+{
+ if (KVM_BUG_ON(rmp_make_shared(pfn, level), kvm)) {
+ snp_leak_pages(pfn, page_level_size(level) >> PAGE_SHIFT);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/*
+ * Certain page-states, such as Pre-Guest and Firmware pages (as documented
+ * in Chapter 5 of the SEV-SNP Firmware ABI under "Page States") cannot be
+ * directly transitioned back to normal/hypervisor-owned state via RMPUPDATE
+ * unless they are reclaimed first.
+ *
+ * Until they are reclaimed and subsequently transitioned via RMPUPDATE, they
+ * might not be usable by the host due to being set as immutable or still
+ * being associated with a guest ASID.
+ *
+ * Bug the VM and leak the page if reclaim fails, or if the RMP entry can't be
+ * converted back to shared, as the page is no longer usable due to RMP
+ * protections, and it's infeasible for the guest to continue on.
+ */
+static int snp_page_reclaim(struct kvm *kvm, u64 pfn)
+{
+ struct sev_data_snp_page_reclaim data = {0};
+ int fw_err, rc;
+
+ data.paddr = __sme_set(pfn << PAGE_SHIFT);
+ rc = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &fw_err);
+ if (KVM_BUG(rc, kvm, "Failed to reclaim PFN %llx, rc %d fw_err %d", pfn, rc, fw_err)) {
+ snp_leak_pages(pfn, 1);
+ return -EIO;
+ }
+
+ if (kvm_rmp_make_shared(kvm, pfn, PG_LEVEL_4K))
+ return -EIO;
+
+ return rc;
+}
+
static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
{
struct sev_data_deactivate deactivate;
@@ -250,6 +327,78 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
sev_decommission(handle);
}
+/*
+ * This sets up bounce buffers/firmware pages to handle SNP Guest Request
+ * messages (e.g. attestation requests). See "SNP Guest Request" in the GHCB
+ * 2.0 specification for more details.
+ *
+ * Technically, when an SNP Guest Request is issued, the guest will provide its
+ * own request/response pages, which could in theory be passed along directly
+ * to firmware rather than using bounce pages. However, these pages would need
+ * special care:
+ *
+ * - Both pages are from shared guest memory, so they need to be protected
+ * from migration/etc. occurring while firmware reads/writes to them. At a
+ * minimum, this requires elevating the ref counts and potentially needing
+ * an explicit pinning of the memory. This places additional restrictions
+ * on what type of memory backends userspace can use for shared guest
+ * memory since there is some reliance on using refcounted pages.
+ *
+ * - The response page needs to be switched to Firmware-owned[1] state
+ * before the firmware can write to it, which can lead to potential
+ * host RMP #PFs if the guest is misbehaved and hands the host a
+ * guest page that KVM might write to for other reasons (e.g. virtio
+ * buffers/etc.).
+ *
+ * Both of these issues can be avoided completely by using separately-allocated
+ * bounce pages for both the request/response pages and passing those to
+ * firmware instead. So that's what is being set up here.
+ *
+ * Guest requests rely on message sequence numbers to ensure requests are
+ * issued to firmware in the order the guest issues them, so concurrent guest
+ * requests generally shouldn't happen. But a misbehaved guest could issue
+ * concurrent guest requests in theory, so a mutex is used to serialize
+ * access to the bounce buffers.
+ *
+ * [1] See the "Page States" section of the SEV-SNP Firmware ABI for more
+ * details on Firmware-owned pages, along with "RMP and VMPL Access Checks"
+ * in the APM for details on the related RMP restrictions.
+ */
+static int snp_guest_req_init(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
+ struct page *req_page;
+
+ req_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ if (!req_page)
+ return -ENOMEM;
+
+ sev->guest_resp_buf = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ if (!sev->guest_resp_buf) {
+ __free_page(req_page);
+ return -EIO;
+ }
+
+ sev->guest_req_buf = page_address(req_page);
+ mutex_init(&sev->guest_req_mutex);
+
+ return 0;
+}
+
+static void snp_guest_req_cleanup(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
+
+ if (sev->guest_resp_buf)
+ snp_free_firmware_page(sev->guest_resp_buf);
+
+ if (sev->guest_req_buf)
+ __free_page(virt_to_page(sev->guest_req_buf));
+
+ sev->guest_req_buf = NULL;
+ sev->guest_resp_buf = NULL;
+}
+
static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
struct kvm_sev_init *data,
unsigned long vm_type)
@@ -288,6 +437,9 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
if (sev->es_active && !sev->ghcb_version)
sev->ghcb_version = GHCB_VERSION_DEFAULT;
+ if (vm_type == KVM_X86_SNP_VM)
+ sev->vmsa_features |= SVM_SEV_FEAT_SNP_ACTIVE;
+
ret = sev_asid_new(sev);
if (ret)
goto e_no_asid;
@@ -297,6 +449,10 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
if (ret)
goto e_free;
+ /* This needs to happen after SEV/SNP firmware initialization. */
+ if (vm_type == KVM_X86_SNP_VM && snp_guest_req_init(kvm))
+ goto e_free;
+
INIT_LIST_HEAD(&sev->regions_list);
INIT_LIST_HEAD(&sev->mirror_vms);
sev->need_init = false;
@@ -348,7 +504,8 @@ static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp)
return -EINVAL;
if (kvm->arch.vm_type != KVM_X86_SEV_VM &&
- kvm->arch.vm_type != KVM_X86_SEV_ES_VM)
+ kvm->arch.vm_type != KVM_X86_SEV_ES_VM &&
+ kvm->arch.vm_type != KVM_X86_SNP_VM)
return -EINVAL;
if (copy_from_user(&data, u64_to_user_ptr(argp->data), sizeof(data)))
@@ -1999,6 +2156,410 @@ int sev_dev_get_attr(u32 group, u64 attr, u64 *val)
}
}
+/*
+ * The guest context contains all the information, keys and metadata
+ * associated with the guest that the firmware tracks to implement SEV
+ * and SNP features. The firmware stores the guest context in hypervisor
+ * provide page via the SNP_GCTX_CREATE command.
+ */
+static void *snp_context_create(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct sev_data_snp_addr data = {};
+ void *context;
+ int rc;
+
+ /* Allocate memory for context page */
+ context = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT);
+ if (!context)
+ return NULL;
+
+ data.address = __psp_pa(context);
+ rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_GCTX_CREATE, &data, &argp->error);
+ if (rc) {
+ pr_warn("Failed to create SEV-SNP context, rc %d fw_error %d",
+ rc, argp->error);
+ snp_free_firmware_page(context);
+ return NULL;
+ }
+
+ return context;
+}
+
+static int snp_bind_asid(struct kvm *kvm, int *error)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ struct sev_data_snp_activate data = {0};
+
+ data.gctx_paddr = __psp_pa(sev->snp_context);
+ data.asid = sev_get_asid(kvm);
+ return sev_issue_cmd(kvm, SEV_CMD_SNP_ACTIVATE, &data, error);
+}
+
+static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ struct sev_data_snp_launch_start start = {0};
+ struct kvm_sev_snp_launch_start params;
+ int rc;
+
+ if (!sev_snp_guest(kvm))
+ return -ENOTTY;
+
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
+ return -EFAULT;
+
+ /* Don't allow userspace to allocate memory for more than 1 SNP context. */
+ if (sev->snp_context)
+ return -EINVAL;
+
+ sev->snp_context = snp_context_create(kvm, argp);
+ if (!sev->snp_context)
+ return -ENOTTY;
+
+ if (params.flags)
+ return -EINVAL;
+
+ if (params.policy & ~SNP_POLICY_MASK_VALID)
+ return -EINVAL;
+
+ /* Check for policy bits that must be set */
+ if (!(params.policy & SNP_POLICY_MASK_RSVD_MBO) ||
+ !(params.policy & SNP_POLICY_MASK_SMT))
+ return -EINVAL;
+
+ if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET)
+ return -EINVAL;
+
+ start.gctx_paddr = __psp_pa(sev->snp_context);
+ start.policy = params.policy;
+ memcpy(start.gosvw, params.gosvw, sizeof(params.gosvw));
+ rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_START, &start, &argp->error);
+ if (rc) {
+ pr_debug("%s: SEV_CMD_SNP_LAUNCH_START firmware command failed, rc %d\n",
+ __func__, rc);
+ goto e_free_context;
+ }
+
+ sev->fd = argp->sev_fd;
+ rc = snp_bind_asid(kvm, &argp->error);
+ if (rc) {
+ pr_debug("%s: Failed to bind ASID to SEV-SNP context, rc %d\n",
+ __func__, rc);
+ goto e_free_context;
+ }
+
+ return 0;
+
+e_free_context:
+ snp_decommission_context(kvm);
+
+ return rc;
+}
+
+struct sev_gmem_populate_args {
+ __u8 type;
+ int sev_fd;
+ int fw_error;
+};
+
+static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pfn,
+ void __user *src, int order, void *opaque)
+{
+ struct sev_gmem_populate_args *sev_populate_args = opaque;
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ int n_private = 0, ret, i;
+ int npages = (1 << order);
+ gfn_t gfn;
+
+ if (WARN_ON_ONCE(sev_populate_args->type != KVM_SEV_SNP_PAGE_TYPE_ZERO && !src))
+ return -EINVAL;
+
+ for (gfn = gfn_start, i = 0; gfn < gfn_start + npages; gfn++, i++) {
+ struct sev_data_snp_launch_update fw_args = {0};
+ bool assigned;
+ int level;
+
+ if (!kvm_mem_is_private(kvm, gfn)) {
+ pr_debug("%s: Failed to ensure GFN 0x%llx has private memory attribute set\n",
+ __func__, gfn);
+ ret = -EINVAL;
+ goto err;
+ }
+
+ ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level);
+ if (ret || assigned) {
+ pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n",
+ __func__, gfn, ret, assigned);
+ ret = -EINVAL;
+ goto err;
+ }
+
+ if (src) {
+ void *vaddr = kmap_local_pfn(pfn + i);
+
+ ret = copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE);
+ if (ret)
+ goto err;
+ kunmap_local(vaddr);
+ }
+
+ ret = rmp_make_private(pfn + i, gfn << PAGE_SHIFT, PG_LEVEL_4K,
+ sev_get_asid(kvm), true);
+ if (ret)
+ goto err;
+
+ n_private++;
+
+ fw_args.gctx_paddr = __psp_pa(sev->snp_context);
+ fw_args.address = __sme_set(pfn_to_hpa(pfn + i));
+ fw_args.page_size = PG_LEVEL_TO_RMP(PG_LEVEL_4K);
+ fw_args.page_type = sev_populate_args->type;
+
+ ret = __sev_issue_cmd(sev_populate_args->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
+ &fw_args, &sev_populate_args->fw_error);
+ if (ret)
+ goto fw_err;
+ }
+
+ return 0;
+
+fw_err:
+ /*
+ * If the firmware command failed handle the reclaim and cleanup of that
+ * PFN specially vs. prior pages which can be cleaned up below without
+ * needing to reclaim in advance.
+ *
+ * Additionally, when invalid CPUID function entries are detected,
+ * firmware writes the expected values into the page and leaves it
+ * unencrypted so it can be used for debugging and error-reporting.
+ *
+ * Copy this page back into the source buffer so userspace can use this
+ * information to provide information on which CPUID leaves/fields
+ * failed CPUID validation.
+ */
+ if (!snp_page_reclaim(kvm, pfn + i) &&
+ sev_populate_args->type == KVM_SEV_SNP_PAGE_TYPE_CPUID &&
+ sev_populate_args->fw_error == SEV_RET_INVALID_PARAM) {
+ void *vaddr = kmap_local_pfn(pfn + i);
+
+ if (copy_to_user(src + i * PAGE_SIZE, vaddr, PAGE_SIZE))
+ pr_debug("Failed to write CPUID page back to userspace\n");
+
+ kunmap_local(vaddr);
+ }
+
+ /* pfn + i is hypervisor-owned now, so skip below cleanup for it. */
+ n_private--;
+
+err:
+ pr_debug("%s: exiting with error ret %d (fw_error %d), restoring %d gmem PFNs to shared.\n",
+ __func__, ret, sev_populate_args->fw_error, n_private);
+ for (i = 0; i < n_private; i++)
+ kvm_rmp_make_shared(kvm, pfn + i, PG_LEVEL_4K);
+
+ return ret;
+}
+
+static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ struct sev_gmem_populate_args sev_populate_args = {0};
+ struct kvm_sev_snp_launch_update params;
+ struct kvm_memory_slot *memslot;
+ long npages, count;
+ void __user *src;
+ int ret = 0;
+
+ if (!sev_snp_guest(kvm) || !sev->snp_context)
+ return -EINVAL;
+
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
+ return -EFAULT;
+
+ pr_debug("%s: GFN start 0x%llx length 0x%llx type %d flags %d\n", __func__,
+ params.gfn_start, params.len, params.type, params.flags);
+
+ if (!PAGE_ALIGNED(params.len) || params.flags ||
+ (params.type != KVM_SEV_SNP_PAGE_TYPE_NORMAL &&
+ params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO &&
+ params.type != KVM_SEV_SNP_PAGE_TYPE_UNMEASURED &&
+ params.type != KVM_SEV_SNP_PAGE_TYPE_SECRETS &&
+ params.type != KVM_SEV_SNP_PAGE_TYPE_CPUID))
+ return -EINVAL;
+
+ npages = params.len / PAGE_SIZE;
+
+ /*
+ * For each GFN that's being prepared as part of the initial guest
+ * state, the following pre-conditions are verified:
+ *
+ * 1) The backing memslot is a valid private memslot.
+ * 2) The GFN has been set to private via KVM_SET_MEMORY_ATTRIBUTES
+ * beforehand.
+ * 3) The PFN of the guest_memfd has not already been set to private
+ * in the RMP table.
+ *
+ * The KVM MMU relies on kvm->mmu_invalidate_seq to retry nested page
+ * faults if there's a race between a fault and an attribute update via
+ * KVM_SET_MEMORY_ATTRIBUTES, and a similar approach could be utilized
+ * here. However, kvm->slots_lock guards against both this as well as
+ * concurrent memslot updates occurring while these checks are being
+ * performed, so use that here to make it easier to reason about the
+ * initial expected state and better guard against unexpected
+ * situations.
+ */
+ mutex_lock(&kvm->slots_lock);
+
+ memslot = gfn_to_memslot(kvm, params.gfn_start);
+ if (!kvm_slot_can_be_private(memslot)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ sev_populate_args.sev_fd = argp->sev_fd;
+ sev_populate_args.type = params.type;
+ src = params.type == KVM_SEV_SNP_PAGE_TYPE_ZERO ? NULL : u64_to_user_ptr(params.uaddr);
+
+ count = kvm_gmem_populate(kvm, params.gfn_start, src, npages,
+ sev_gmem_post_populate, &sev_populate_args);
+ if (count < 0) {
+ argp->error = sev_populate_args.fw_error;
+ pr_debug("%s: kvm_gmem_populate failed, ret %ld (fw_error %d)\n",
+ __func__, count, argp->error);
+ ret = -EIO;
+ } else {
+ params.gfn_start += count;
+ params.len -= count * PAGE_SIZE;
+ if (params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO)
+ params.uaddr += count * PAGE_SIZE;
+
+ ret = 0;
+ if (copy_to_user(u64_to_user_ptr(argp->data), &params, sizeof(params)))
+ ret = -EFAULT;
+ }
+
+out:
+ mutex_unlock(&kvm->slots_lock);
+
+ return ret;
+}
+
+static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ struct sev_data_snp_launch_update data = {};
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
+ int ret;
+
+ data.gctx_paddr = __psp_pa(sev->snp_context);
+ data.page_type = SNP_PAGE_TYPE_VMSA;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct vcpu_svm *svm = to_svm(vcpu);
+ u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
+
+ ret = sev_es_sync_vmsa(svm);
+ if (ret)
+ return ret;
+
+ /* Transition the VMSA page to a firmware state. */
+ ret = rmp_make_private(pfn, INITIAL_VMSA_GPA, PG_LEVEL_4K, sev->asid, true);
+ if (ret)
+ return ret;
+
+ /* Issue the SNP command to encrypt the VMSA */
+ data.address = __sme_pa(svm->sev_es.vmsa);
+ ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
+ &data, &argp->error);
+ if (ret) {
+ snp_page_reclaim(kvm, pfn);
+
+ return ret;
+ }
+
+ svm->vcpu.arch.guest_state_protected = true;
+ /*
+ * SEV-ES (and thus SNP) guest mandates LBR Virtualization to
+ * be _always_ ON. Enable it only after setting
+ * guest_state_protected because KVM_SET_MSRS allows dynamic
+ * toggling of LBRV (for performance reason) on write access to
+ * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set.
+ */
+ svm_enable_lbrv(vcpu);
+ }
+
+ return 0;
+}
+
+static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ struct kvm_sev_snp_launch_finish params;
+ struct sev_data_snp_launch_finish *data;
+ void *id_block = NULL, *id_auth = NULL;
+ int ret;
+
+ if (!sev_snp_guest(kvm))
+ return -ENOTTY;
+
+ if (!sev->snp_context)
+ return -EINVAL;
+
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
+ return -EFAULT;
+
+ if (params.flags)
+ return -EINVAL;
+
+ /* Measure all vCPUs using LAUNCH_UPDATE before finalizing the launch flow. */
+ ret = snp_launch_update_vmsa(kvm, argp);
+ if (ret)
+ return ret;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
+ if (!data)
+ return -ENOMEM;
+
+ if (params.id_block_en) {
+ id_block = psp_copy_user_blob(params.id_block_uaddr, KVM_SEV_SNP_ID_BLOCK_SIZE);
+ if (IS_ERR(id_block)) {
+ ret = PTR_ERR(id_block);
+ goto e_free;
+ }
+
+ data->id_block_en = 1;
+ data->id_block_paddr = __sme_pa(id_block);
+
+ id_auth = psp_copy_user_blob(params.id_auth_uaddr, KVM_SEV_SNP_ID_AUTH_SIZE);
+ if (IS_ERR(id_auth)) {
+ ret = PTR_ERR(id_auth);
+ goto e_free_id_block;
+ }
+
+ data->id_auth_paddr = __sme_pa(id_auth);
+
+ if (params.auth_key_en)
+ data->auth_key_en = 1;
+ }
+
+ data->vcek_disabled = params.vcek_disabled;
+
+ memcpy(data->host_data, params.host_data, KVM_SEV_SNP_FINISH_DATA_SIZE);
+ data->gctx_paddr = __psp_pa(sev->snp_context);
+ ret = sev_issue_cmd(kvm, SEV_CMD_SNP_LAUNCH_FINISH, data, &argp->error);
+
+ kfree(id_auth);
+
+e_free_id_block:
+ kfree(id_block);
+
+e_free:
+ kfree(data);
+
+ return ret;
+}
+
int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
{
struct kvm_sev_cmd sev_cmd;
@@ -2022,6 +2583,15 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
goto out;
}
+ /*
+ * Once KVM_SEV_INIT2 initializes a KVM instance as an SNP guest, only
+ * allow the use of SNP-specific commands.
+ */
+ if (sev_snp_guest(kvm) && sev_cmd.id < KVM_SEV_SNP_LAUNCH_START) {
+ r = -EPERM;
+ goto out;
+ }
+
switch (sev_cmd.id) {
case KVM_SEV_ES_INIT:
if (!sev_es_enabled) {
@@ -2086,6 +2656,15 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
case KVM_SEV_RECEIVE_FINISH:
r = sev_receive_finish(kvm, &sev_cmd);
break;
+ case KVM_SEV_SNP_LAUNCH_START:
+ r = snp_launch_start(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_SNP_LAUNCH_UPDATE:
+ r = snp_launch_update(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_SNP_LAUNCH_FINISH:
+ r = snp_launch_finish(kvm, &sev_cmd);
+ break;
default:
r = -EINVAL;
goto out;
@@ -2281,6 +2860,31 @@ e_source_fput:
return ret;
}
+static int snp_decommission_context(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ struct sev_data_snp_addr data = {};
+ int ret;
+
+ /* If context is not created then do nothing */
+ if (!sev->snp_context)
+ return 0;
+
+ /* Do the decommision, which will unbind the ASID from the SNP context */
+ data.address = __sme_pa(sev->snp_context);
+ down_write(&sev_deactivate_lock);
+ ret = sev_do_cmd(SEV_CMD_SNP_DECOMMISSION, &data, NULL);
+ up_write(&sev_deactivate_lock);
+
+ if (WARN_ONCE(ret, "Failed to release guest context, ret %d", ret))
+ return ret;
+
+ snp_free_firmware_page(sev->snp_context);
+ sev->snp_context = NULL;
+
+ return 0;
+}
+
void sev_vm_destroy(struct kvm *kvm)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -2322,7 +2926,19 @@ void sev_vm_destroy(struct kvm *kvm)
}
}
- sev_unbind_asid(kvm, sev->handle);
+ if (sev_snp_guest(kvm)) {
+ snp_guest_req_cleanup(kvm);
+
+ /*
+ * Decomission handles unbinding of the ASID. If it fails for
+ * some unexpected reason, just leak the ASID.
+ */
+ if (snp_decommission_context(kvm))
+ return;
+ } else {
+ sev_unbind_asid(kvm, sev->handle);
+ }
+
sev_asid_free(sev);
}
@@ -2336,11 +2952,16 @@ void __init sev_set_cpu_caps(void)
kvm_cpu_cap_set(X86_FEATURE_SEV_ES);
kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_ES_VM);
}
+ if (sev_snp_enabled) {
+ kvm_cpu_cap_set(X86_FEATURE_SEV_SNP);
+ kvm_caps.supported_vm_types |= BIT(KVM_X86_SNP_VM);
+ }
}
void __init sev_hardware_setup(void)
{
unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
+ bool sev_snp_supported = false;
bool sev_es_supported = false;
bool sev_supported = false;
@@ -2427,6 +3048,7 @@ void __init sev_hardware_setup(void)
sev_es_asid_count = min_sev_asid - 1;
WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count));
sev_es_supported = true;
+ sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
out:
if (boot_cpu_has(X86_FEATURE_SEV))
@@ -2439,9 +3061,15 @@ out:
pr_info("SEV-ES %s (ASIDs %u - %u)\n",
sev_es_supported ? "enabled" : "disabled",
min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1);
+ if (boot_cpu_has(X86_FEATURE_SEV_SNP))
+ pr_info("SEV-SNP %s (ASIDs %u - %u)\n",
+ sev_snp_supported ? "enabled" : "disabled",
+ min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1);
sev_enabled = sev_supported;
sev_es_enabled = sev_es_supported;
+ sev_snp_enabled = sev_snp_supported;
+
if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) ||
!cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP))
sev_es_debug_swap_enabled = false;
@@ -2520,7 +3148,13 @@ do_wbinvd:
void sev_guest_memory_reclaimed(struct kvm *kvm)
{
- if (!sev_guest(kvm))
+ /*
+ * With SNP+gmem, private/encrypted memory is unreachable via the
+ * hva-based mmu notifiers, so these events are only actually
+ * pertaining to shared pages where there is no need to perform
+ * the WBINVD to flush associated caches.
+ */
+ if (!sev_guest(kvm) || sev_snp_guest(kvm))
return;
wbinvd_on_all_cpus();
@@ -2535,11 +3169,24 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
svm = to_svm(vcpu);
+ /*
+ * If it's an SNP guest, then the VMSA was marked in the RMP table as
+ * a guest-owned page. Transition the page to hypervisor state before
+ * releasing it back to the system.
+ */
+ if (sev_snp_guest(vcpu->kvm)) {
+ u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
+
+ if (kvm_rmp_make_shared(vcpu->kvm, pfn, PG_LEVEL_4K))
+ goto skip_vmsa_free;
+ }
+
if (vcpu->arch.guest_state_protected)
sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa);
__free_page(virt_to_page(svm->sev_es.vmsa));
+skip_vmsa_free:
if (svm->sev_es.ghcb_sa_free)
kvfree(svm->sev_es.ghcb_sa);
}
@@ -2735,6 +3382,13 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
if (!kvm_ghcb_sw_scratch_is_valid(svm))
goto vmgexit_err;
break;
+ case SVM_VMGEXIT_AP_CREATION:
+ if (!sev_snp_guest(vcpu->kvm))
+ goto vmgexit_err;
+ if (lower_32_bits(control->exit_info_1) != SVM_VMGEXIT_AP_DESTROY)
+ if (!kvm_ghcb_rax_is_valid(svm))
+ goto vmgexit_err;
+ break;
case SVM_VMGEXIT_NMI_COMPLETE:
case SVM_VMGEXIT_AP_HLT_LOOP:
case SVM_VMGEXIT_AP_JUMP_TABLE:
@@ -2742,6 +3396,18 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
case SVM_VMGEXIT_HV_FEATURES:
case SVM_VMGEXIT_TERM_REQUEST:
break;
+ case SVM_VMGEXIT_PSC:
+ if (!sev_snp_guest(vcpu->kvm) || !kvm_ghcb_sw_scratch_is_valid(svm))
+ goto vmgexit_err;
+ break;
+ case SVM_VMGEXIT_GUEST_REQUEST:
+ case SVM_VMGEXIT_EXT_GUEST_REQUEST:
+ if (!sev_snp_guest(vcpu->kvm) ||
+ !PAGE_ALIGNED(control->exit_info_1) ||
+ !PAGE_ALIGNED(control->exit_info_2) ||
+ control->exit_info_1 == control->exit_info_2)
+ goto vmgexit_err;
+ break;
default:
reason = GHCB_ERR_INVALID_EVENT;
goto vmgexit_err;
@@ -2929,6 +3595,534 @@ static void set_ghcb_msr(struct vcpu_svm *svm, u64 value)
svm->vmcb->control.ghcb_gpa = value;
}
+static int snp_rmptable_psmash(kvm_pfn_t pfn)
+{
+ int ret;
+
+ pfn = pfn & ~(KVM_PAGES_PER_HPAGE(PG_LEVEL_2M) - 1);
+
+ /*
+ * PSMASH_FAIL_INUSE indicates another processor is modifying the
+ * entry, so retry until that's no longer the case.
+ */
+ do {
+ ret = psmash(pfn);
+ } while (ret == PSMASH_FAIL_INUSE);
+
+ return ret;
+}
+
+static int snp_complete_psc_msr(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ if (vcpu->run->hypercall.ret)
+ set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
+ else
+ set_ghcb_msr(svm, GHCB_MSR_PSC_RESP);
+
+ return 1; /* resume guest */
+}
+
+static int snp_begin_psc_msr(struct vcpu_svm *svm, u64 ghcb_msr)
+{
+ u64 gpa = gfn_to_gpa(GHCB_MSR_PSC_REQ_TO_GFN(ghcb_msr));
+ u8 op = GHCB_MSR_PSC_REQ_TO_OP(ghcb_msr);
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+
+ if (op != SNP_PAGE_STATE_PRIVATE && op != SNP_PAGE_STATE_SHARED) {
+ set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
+ return 1; /* resume guest */
+ }
+
+ if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) {
+ set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
+ return 1; /* resume guest */
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_HYPERCALL;
+ vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE;
+ vcpu->run->hypercall.args[0] = gpa;
+ vcpu->run->hypercall.args[1] = 1;
+ vcpu->run->hypercall.args[2] = (op == SNP_PAGE_STATE_PRIVATE)
+ ? KVM_MAP_GPA_RANGE_ENCRYPTED
+ : KVM_MAP_GPA_RANGE_DECRYPTED;
+ vcpu->run->hypercall.args[2] |= KVM_MAP_GPA_RANGE_PAGE_SZ_4K;
+
+ vcpu->arch.complete_userspace_io = snp_complete_psc_msr;
+
+ return 0; /* forward request to userspace */
+}
+
+struct psc_buffer {
+ struct psc_hdr hdr;
+ struct psc_entry entries[];
+} __packed;
+
+static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc);
+
+static void snp_complete_psc(struct vcpu_svm *svm, u64 psc_ret)
+{
+ svm->sev_es.psc_inflight = 0;
+ svm->sev_es.psc_idx = 0;
+ svm->sev_es.psc_2m = false;
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, psc_ret);
+}
+
+static void __snp_complete_one_psc(struct vcpu_svm *svm)
+{
+ struct psc_buffer *psc = svm->sev_es.ghcb_sa;
+ struct psc_entry *entries = psc->entries;
+ struct psc_hdr *hdr = &psc->hdr;
+ __u16 idx;
+
+ /*
+ * Everything in-flight has been processed successfully. Update the
+ * corresponding entries in the guest's PSC buffer and zero out the
+ * count of in-flight PSC entries.
+ */
+ for (idx = svm->sev_es.psc_idx; svm->sev_es.psc_inflight;
+ svm->sev_es.psc_inflight--, idx++) {
+ struct psc_entry *entry = &entries[idx];
+
+ entry->cur_page = entry->pagesize ? 512 : 1;
+ }
+
+ hdr->cur_entry = idx;
+}
+
+static int snp_complete_one_psc(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ struct psc_buffer *psc = svm->sev_es.ghcb_sa;
+
+ if (vcpu->run->hypercall.ret) {
+ snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
+ return 1; /* resume guest */
+ }
+
+ __snp_complete_one_psc(svm);
+
+ /* Handle the next range (if any). */
+ return snp_begin_psc(svm, psc);
+}
+
+static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc)
+{
+ struct psc_entry *entries = psc->entries;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct psc_hdr *hdr = &psc->hdr;
+ struct psc_entry entry_start;
+ u16 idx, idx_start, idx_end;
+ int npages;
+ bool huge;
+ u64 gfn;
+
+ if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) {
+ snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
+ return 1;
+ }
+
+next_range:
+ /* There should be no other PSCs in-flight at this point. */
+ if (WARN_ON_ONCE(svm->sev_es.psc_inflight)) {
+ snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
+ return 1;
+ }
+
+ /*
+ * The PSC descriptor buffer can be modified by a misbehaved guest after
+ * validation, so take care to only use validated copies of values used
+ * for things like array indexing.
+ */
+ idx_start = hdr->cur_entry;
+ idx_end = hdr->end_entry;
+
+ if (idx_end >= VMGEXIT_PSC_MAX_COUNT) {
+ snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_HDR);
+ return 1;
+ }
+
+ /* Find the start of the next range which needs processing. */
+ for (idx = idx_start; idx <= idx_end; idx++, hdr->cur_entry++) {
+ entry_start = entries[idx];
+
+ gfn = entry_start.gfn;
+ huge = entry_start.pagesize;
+ npages = huge ? 512 : 1;
+
+ if (entry_start.cur_page > npages || !IS_ALIGNED(gfn, npages)) {
+ snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_ENTRY);
+ return 1;
+ }
+
+ if (entry_start.cur_page) {
+ /*
+ * If this is a partially-completed 2M range, force 4K handling
+ * for the remaining pages since they're effectively split at
+ * this point. Subsequent code should ensure this doesn't get
+ * combined with adjacent PSC entries where 2M handling is still
+ * possible.
+ */
+ npages -= entry_start.cur_page;
+ gfn += entry_start.cur_page;
+ huge = false;
+ }
+
+ if (npages)
+ break;
+ }
+
+ if (idx > idx_end) {
+ /* Nothing more to process. */
+ snp_complete_psc(svm, 0);
+ return 1;
+ }
+
+ svm->sev_es.psc_2m = huge;
+ svm->sev_es.psc_idx = idx;
+ svm->sev_es.psc_inflight = 1;
+
+ /*
+ * Find all subsequent PSC entries that contain adjacent GPA
+ * ranges/operations and can be combined into a single
+ * KVM_HC_MAP_GPA_RANGE exit.
+ */
+ while (++idx <= idx_end) {
+ struct psc_entry entry = entries[idx];
+
+ if (entry.operation != entry_start.operation ||
+ entry.gfn != entry_start.gfn + npages ||
+ entry.cur_page || !!entry.pagesize != huge)
+ break;
+
+ svm->sev_es.psc_inflight++;
+ npages += huge ? 512 : 1;
+ }
+
+ switch (entry_start.operation) {
+ case VMGEXIT_PSC_OP_PRIVATE:
+ case VMGEXIT_PSC_OP_SHARED:
+ vcpu->run->exit_reason = KVM_EXIT_HYPERCALL;
+ vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE;
+ vcpu->run->hypercall.args[0] = gfn_to_gpa(gfn);
+ vcpu->run->hypercall.args[1] = npages;
+ vcpu->run->hypercall.args[2] = entry_start.operation == VMGEXIT_PSC_OP_PRIVATE
+ ? KVM_MAP_GPA_RANGE_ENCRYPTED
+ : KVM_MAP_GPA_RANGE_DECRYPTED;
+ vcpu->run->hypercall.args[2] |= entry_start.pagesize
+ ? KVM_MAP_GPA_RANGE_PAGE_SZ_2M
+ : KVM_MAP_GPA_RANGE_PAGE_SZ_4K;
+ vcpu->arch.complete_userspace_io = snp_complete_one_psc;
+ return 0; /* forward request to userspace */
+ default:
+ /*
+ * Only shared/private PSC operations are currently supported, so if the
+ * entire range consists of unsupported operations (e.g. SMASH/UNSMASH),
+ * then consider the entire range completed and avoid exiting to
+ * userspace. In theory snp_complete_psc() can always be called directly
+ * at this point to complete the current range and start the next one,
+ * but that could lead to unexpected levels of recursion.
+ */
+ __snp_complete_one_psc(svm);
+ goto next_range;
+ }
+
+ unreachable();
+}
+
+static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ WARN_ON(!mutex_is_locked(&svm->sev_es.snp_vmsa_mutex));
+
+ /* Mark the vCPU as offline and not runnable */
+ vcpu->arch.pv.pv_unhalted = false;
+ vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+
+ /* Clear use of the VMSA */
+ svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+
+ if (VALID_PAGE(svm->sev_es.snp_vmsa_gpa)) {
+ gfn_t gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa);
+ struct kvm_memory_slot *slot;
+ kvm_pfn_t pfn;
+
+ slot = gfn_to_memslot(vcpu->kvm, gfn);
+ if (!slot)
+ return -EINVAL;
+
+ /*
+ * The new VMSA will be private memory guest memory, so
+ * retrieve the PFN from the gmem backend.
+ */
+ if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, NULL))
+ return -EINVAL;
+
+ /*
+ * From this point forward, the VMSA will always be a
+ * guest-mapped page rather than the initial one allocated
+ * by KVM in svm->sev_es.vmsa. In theory, svm->sev_es.vmsa
+ * could be free'd and cleaned up here, but that involves
+ * cleanups like wbinvd_on_all_cpus() which would ideally
+ * be handled during teardown rather than guest boot.
+ * Deferring that also allows the existing logic for SEV-ES
+ * VMSAs to be re-used with minimal SNP-specific changes.
+ */
+ svm->sev_es.snp_has_guest_vmsa = true;
+
+ /* Use the new VMSA */
+ svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn);
+
+ /* Mark the vCPU as runnable */
+ vcpu->arch.pv.pv_unhalted = false;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+ svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
+
+ /*
+ * gmem pages aren't currently migratable, but if this ever
+ * changes then care should be taken to ensure
+ * svm->sev_es.vmsa is pinned through some other means.
+ */
+ kvm_release_pfn_clean(pfn);
+ }
+
+ /*
+ * When replacing the VMSA during SEV-SNP AP creation,
+ * mark the VMCB dirty so that full state is always reloaded.
+ */
+ vmcb_mark_all_dirty(svm->vmcb);
+
+ return 0;
+}
+
+/*
+ * Invoked as part of svm_vcpu_reset() processing of an init event.
+ */
+void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ int ret;
+
+ if (!sev_snp_guest(vcpu->kvm))
+ return;
+
+ mutex_lock(&svm->sev_es.snp_vmsa_mutex);
+
+ if (!svm->sev_es.snp_ap_waiting_for_reset)
+ goto unlock;
+
+ svm->sev_es.snp_ap_waiting_for_reset = false;
+
+ ret = __sev_snp_update_protected_guest_state(vcpu);
+ if (ret)
+ vcpu_unimpl(vcpu, "snp: AP state update on init failed\n");
+
+unlock:
+ mutex_unlock(&svm->sev_es.snp_vmsa_mutex);
+}
+
+static int sev_snp_ap_creation(struct vcpu_svm *svm)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_vcpu *target_vcpu;
+ struct vcpu_svm *target_svm;
+ unsigned int request;
+ unsigned int apic_id;
+ bool kick;
+ int ret;
+
+ request = lower_32_bits(svm->vmcb->control.exit_info_1);
+ apic_id = upper_32_bits(svm->vmcb->control.exit_info_1);
+
+ /* Validate the APIC ID */
+ target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, apic_id);
+ if (!target_vcpu) {
+ vcpu_unimpl(vcpu, "vmgexit: invalid AP APIC ID [%#x] from guest\n",
+ apic_id);
+ return -EINVAL;
+ }
+
+ ret = 0;
+
+ target_svm = to_svm(target_vcpu);
+
+ /*
+ * The target vCPU is valid, so the vCPU will be kicked unless the
+ * request is for CREATE_ON_INIT. For any errors at this stage, the
+ * kick will place the vCPU in an non-runnable state.
+ */
+ kick = true;
+
+ mutex_lock(&target_svm->sev_es.snp_vmsa_mutex);
+
+ target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
+ target_svm->sev_es.snp_ap_waiting_for_reset = true;
+
+ /* Interrupt injection mode shouldn't change for AP creation */
+ if (request < SVM_VMGEXIT_AP_DESTROY) {
+ u64 sev_features;
+
+ sev_features = vcpu->arch.regs[VCPU_REGS_RAX];
+ sev_features ^= sev->vmsa_features;
+
+ if (sev_features & SVM_SEV_FEAT_INT_INJ_MODES) {
+ vcpu_unimpl(vcpu, "vmgexit: invalid AP injection mode [%#lx] from guest\n",
+ vcpu->arch.regs[VCPU_REGS_RAX]);
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+
+ switch (request) {
+ case SVM_VMGEXIT_AP_CREATE_ON_INIT:
+ kick = false;
+ fallthrough;
+ case SVM_VMGEXIT_AP_CREATE:
+ if (!page_address_valid(vcpu, svm->vmcb->control.exit_info_2)) {
+ vcpu_unimpl(vcpu, "vmgexit: invalid AP VMSA address [%#llx] from guest\n",
+ svm->vmcb->control.exit_info_2);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Malicious guest can RMPADJUST a large page into VMSA which
+ * will hit the SNP erratum where the CPU will incorrectly signal
+ * an RMP violation #PF if a hugepage collides with the RMP entry
+ * of VMSA page, reject the AP CREATE request if VMSA address from
+ * guest is 2M aligned.
+ */
+ if (IS_ALIGNED(svm->vmcb->control.exit_info_2, PMD_SIZE)) {
+ vcpu_unimpl(vcpu,
+ "vmgexit: AP VMSA address [%llx] from guest is unsafe as it is 2M aligned\n",
+ svm->vmcb->control.exit_info_2);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2;
+ break;
+ case SVM_VMGEXIT_AP_DESTROY:
+ break;
+ default:
+ vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n",
+ request);
+ ret = -EINVAL;
+ break;
+ }
+
+out:
+ if (kick) {
+ kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
+ kvm_vcpu_kick(target_vcpu);
+ }
+
+ mutex_unlock(&target_svm->sev_es.snp_vmsa_mutex);
+
+ return ret;
+}
+
+static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa)
+{
+ struct sev_data_snp_guest_request data = {0};
+ struct kvm *kvm = svm->vcpu.kvm;
+ struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
+ sev_ret_code fw_err = 0;
+ int ret;
+
+ if (!sev_snp_guest(kvm))
+ return -EINVAL;
+
+ mutex_lock(&sev->guest_req_mutex);
+
+ if (kvm_read_guest(kvm, req_gpa, sev->guest_req_buf, PAGE_SIZE)) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
+ data.gctx_paddr = __psp_pa(sev->snp_context);
+ data.req_paddr = __psp_pa(sev->guest_req_buf);
+ data.res_paddr = __psp_pa(sev->guest_resp_buf);
+
+ /*
+ * Firmware failures are propagated on to guest, but any other failure
+ * condition along the way should be reported to userspace. E.g. if
+ * the PSP is dead and commands are timing out.
+ */
+ ret = sev_issue_cmd(kvm, SEV_CMD_SNP_GUEST_REQUEST, &data, &fw_err);
+ if (ret && !fw_err)
+ goto out_unlock;
+
+ if (kvm_write_guest(kvm, resp_gpa, sev->guest_resp_buf, PAGE_SIZE)) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, SNP_GUEST_ERR(0, fw_err));
+
+ ret = 1; /* resume guest */
+
+out_unlock:
+ mutex_unlock(&sev->guest_req_mutex);
+ return ret;
+}
+
+static int snp_handle_ext_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa)
+{
+ struct kvm *kvm = svm->vcpu.kvm;
+ u8 msg_type;
+
+ if (!sev_snp_guest(kvm))
+ return -EINVAL;
+
+ if (kvm_read_guest(kvm, req_gpa + offsetof(struct snp_guest_msg_hdr, msg_type),
+ &msg_type, 1))
+ return -EIO;
+
+ /*
+ * As per GHCB spec, requests of type MSG_REPORT_REQ also allow for
+ * additional certificate data to be provided alongside the attestation
+ * report via the guest-provided data pages indicated by RAX/RBX. The
+ * certificate data is optional and requires additional KVM enablement
+ * to provide an interface for userspace to provide it, but KVM still
+ * needs to be able to handle extended guest requests either way. So
+ * provide a stub implementation that will always return an empty
+ * certificate table in the guest-provided data pages.
+ */
+ if (msg_type == SNP_MSG_REPORT_REQ) {
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ u64 data_npages;
+ gpa_t data_gpa;
+
+ if (!kvm_ghcb_rax_is_valid(svm) || !kvm_ghcb_rbx_is_valid(svm))
+ goto request_invalid;
+
+ data_gpa = vcpu->arch.regs[VCPU_REGS_RAX];
+ data_npages = vcpu->arch.regs[VCPU_REGS_RBX];
+
+ if (!PAGE_ALIGNED(data_gpa))
+ goto request_invalid;
+
+ /*
+ * As per GHCB spec (see "SNP Extended Guest Request"), the
+ * certificate table is terminated by 24-bytes of zeroes.
+ */
+ if (data_npages && kvm_clear_guest(kvm, data_gpa, 24))
+ return -EIO;
+ }
+
+ return snp_handle_guest_req(svm, req_gpa, resp_gpa);
+
+request_invalid:
+ ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+ return 1; /* resume guest */
+}
+
static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
@@ -3008,6 +4202,38 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
set_ghcb_msr_bits(svm, GHCB_MSR_HV_FT_RESP,
GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS);
break;
+ case GHCB_MSR_PREF_GPA_REQ:
+ if (!sev_snp_guest(vcpu->kvm))
+ goto out_terminate;
+
+ set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_NONE, GHCB_MSR_GPA_VALUE_MASK,
+ GHCB_MSR_GPA_VALUE_POS);
+ set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_RESP, GHCB_MSR_INFO_MASK,
+ GHCB_MSR_INFO_POS);
+ break;
+ case GHCB_MSR_REG_GPA_REQ: {
+ u64 gfn;
+
+ if (!sev_snp_guest(vcpu->kvm))
+ goto out_terminate;
+
+ gfn = get_ghcb_msr_bits(svm, GHCB_MSR_GPA_VALUE_MASK,
+ GHCB_MSR_GPA_VALUE_POS);
+
+ svm->sev_es.ghcb_registered_gpa = gfn_to_gpa(gfn);
+
+ set_ghcb_msr_bits(svm, gfn, GHCB_MSR_GPA_VALUE_MASK,
+ GHCB_MSR_GPA_VALUE_POS);
+ set_ghcb_msr_bits(svm, GHCB_MSR_REG_GPA_RESP, GHCB_MSR_INFO_MASK,
+ GHCB_MSR_INFO_POS);
+ break;
+ }
+ case GHCB_MSR_PSC_REQ:
+ if (!sev_snp_guest(vcpu->kvm))
+ goto out_terminate;
+
+ ret = snp_begin_psc_msr(svm, control->ghcb_gpa);
+ break;
case GHCB_MSR_TERM_REQ: {
u64 reason_set, reason_code;
@@ -3020,12 +4246,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
reason_set, reason_code);
- vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
- vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
- vcpu->run->system_event.ndata = 1;
- vcpu->run->system_event.data[0] = control->ghcb_gpa;
-
- return 0;
+ goto out_terminate;
}
default:
/* Error, keep GHCB MSR value as-is */
@@ -3036,6 +4257,14 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
control->ghcb_gpa, ret);
return ret;
+
+out_terminate:
+ vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+ vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
+ vcpu->run->system_event.ndata = 1;
+ vcpu->run->system_event.data[0] = control->ghcb_gpa;
+
+ return 0;
}
int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
@@ -3071,6 +4300,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb);
sev_es_sync_from_ghcb(svm);
+
+ /* SEV-SNP guest requires that the GHCB GPA must be registered */
+ if (sev_snp_guest(svm->vcpu.kvm) && !ghcb_gpa_is_registered(svm, ghcb_gpa)) {
+ vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB GPA [%#llx] is not registered.\n", ghcb_gpa);
+ return -EINVAL;
+ }
+
ret = sev_es_validate_vmgexit(svm);
if (ret)
return ret;
@@ -3145,6 +4381,28 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
vcpu->run->system_event.ndata = 1;
vcpu->run->system_event.data[0] = control->ghcb_gpa;
break;
+ case SVM_VMGEXIT_PSC:
+ ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);
+ if (ret)
+ break;
+
+ ret = snp_begin_psc(svm, svm->sev_es.ghcb_sa);
+ break;
+ case SVM_VMGEXIT_AP_CREATION:
+ ret = sev_snp_ap_creation(svm);
+ if (ret) {
+ ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+ }
+
+ ret = 1;
+ break;
+ case SVM_VMGEXIT_GUEST_REQUEST:
+ ret = snp_handle_guest_req(svm, control->exit_info_1, control->exit_info_2);
+ break;
+ case SVM_VMGEXIT_EXT_GUEST_REQUEST:
+ ret = snp_handle_ext_guest_req(svm, control->exit_info_1, control->exit_info_2);
+ break;
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
vcpu_unimpl(vcpu,
"vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
@@ -3238,7 +4496,7 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
* the VMSA will be NULL if this vCPU is the destination for intrahost
* migration, and will be copied later.
*/
- if (svm->sev_es.vmsa)
+ if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
/* Can't intercept CR register access, HV can't modify CR registers */
@@ -3310,6 +4568,8 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
GHCB_VERSION_MIN,
sev_enc_bit));
+
+ mutex_init(&svm->sev_es.snp_vmsa_mutex);
}
void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
@@ -3331,9 +4591,9 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
* isn't saved by VMRUN, that isn't already saved by VMSAVE (performed
* by common SVM code).
*/
- hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+ hostsa->xcr0 = kvm_host.xcr0;
hostsa->pkru = read_pkru();
- hostsa->xss = host_xss;
+ hostsa->xss = kvm_host.xss;
/*
* If DebugSwap is enabled, debug registers are loaded but NOT saved by
@@ -3389,13 +4649,13 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
}
}
-struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
+struct page *snp_safe_alloc_page_node(int node, gfp_t gfp)
{
unsigned long pfn;
struct page *p;
if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
- return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ return alloc_pages_node(node, gfp | __GFP_ZERO, 0);
/*
* Allocate an SNP-safe page to workaround the SNP erratum where
@@ -3406,7 +4666,7 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
* Allocate one extra page, choose a page which is not
* 2MB-aligned, and free the other.
*/
- p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+ p = alloc_pages_node(node, gfp | __GFP_ZERO, 1);
if (!p)
return NULL;
@@ -3420,3 +4680,271 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
return p;
}
+
+void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
+{
+ struct kvm_memory_slot *slot;
+ struct kvm *kvm = vcpu->kvm;
+ int order, rmp_level, ret;
+ bool assigned;
+ kvm_pfn_t pfn;
+ gfn_t gfn;
+
+ gfn = gpa >> PAGE_SHIFT;
+
+ /*
+ * The only time RMP faults occur for shared pages is when the guest is
+ * triggering an RMP fault for an implicit page-state change from
+ * shared->private. Implicit page-state changes are forwarded to
+ * userspace via KVM_EXIT_MEMORY_FAULT events, however, so RMP faults
+ * for shared pages should not end up here.
+ */
+ if (!kvm_mem_is_private(kvm, gfn)) {
+ pr_warn_ratelimited("SEV: Unexpected RMP fault for non-private GPA 0x%llx\n",
+ gpa);
+ return;
+ }
+
+ slot = gfn_to_memslot(kvm, gfn);
+ if (!kvm_slot_can_be_private(slot)) {
+ pr_warn_ratelimited("SEV: Unexpected RMP fault, non-private slot for GPA 0x%llx\n",
+ gpa);
+ return;
+ }
+
+ ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &order);
+ if (ret) {
+ pr_warn_ratelimited("SEV: Unexpected RMP fault, no backing page for private GPA 0x%llx\n",
+ gpa);
+ return;
+ }
+
+ ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
+ if (ret || !assigned) {
+ pr_warn_ratelimited("SEV: Unexpected RMP fault, no assigned RMP entry found for GPA 0x%llx PFN 0x%llx error %d\n",
+ gpa, pfn, ret);
+ goto out_no_trace;
+ }
+
+ /*
+ * There are 2 cases where a PSMASH may be needed to resolve an #NPF
+ * with PFERR_GUEST_RMP_BIT set:
+ *
+ * 1) RMPADJUST/PVALIDATE can trigger an #NPF with PFERR_GUEST_SIZEM
+ * bit set if the guest issues them with a smaller granularity than
+ * what is indicated by the page-size bit in the 2MB RMP entry for
+ * the PFN that backs the GPA.
+ *
+ * 2) Guest access via NPT can trigger an #NPF if the NPT mapping is
+ * smaller than what is indicated by the 2MB RMP entry for the PFN
+ * that backs the GPA.
+ *
+ * In both these cases, the corresponding 2M RMP entry needs to
+ * be PSMASH'd to 512 4K RMP entries. If the RMP entry is already
+ * split into 4K RMP entries, then this is likely a spurious case which
+ * can occur when there are concurrent accesses by the guest to a 2MB
+ * GPA range that is backed by a 2MB-aligned PFN who's RMP entry is in
+ * the process of being PMASH'd into 4K entries. These cases should
+ * resolve automatically on subsequent accesses, so just ignore them
+ * here.
+ */
+ if (rmp_level == PG_LEVEL_4K)
+ goto out;
+
+ ret = snp_rmptable_psmash(pfn);
+ if (ret) {
+ /*
+ * Look it up again. If it's 4K now then the PSMASH may have
+ * raced with another process and the issue has already resolved
+ * itself.
+ */
+ if (!snp_lookup_rmpentry(pfn, &assigned, &rmp_level) &&
+ assigned && rmp_level == PG_LEVEL_4K)
+ goto out;
+
+ pr_warn_ratelimited("SEV: Unable to split RMP entry for GPA 0x%llx PFN 0x%llx ret %d\n",
+ gpa, pfn, ret);
+ }
+
+ kvm_zap_gfn_range(kvm, gfn, gfn + PTRS_PER_PMD);
+out:
+ trace_kvm_rmp_fault(vcpu, gpa, pfn, error_code, rmp_level, ret);
+out_no_trace:
+ put_page(pfn_to_page(pfn));
+}
+
+static bool is_pfn_range_shared(kvm_pfn_t start, kvm_pfn_t end)
+{
+ kvm_pfn_t pfn = start;
+
+ while (pfn < end) {
+ int ret, rmp_level;
+ bool assigned;
+
+ ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
+ if (ret) {
+ pr_warn_ratelimited("SEV: Failed to retrieve RMP entry: PFN 0x%llx GFN start 0x%llx GFN end 0x%llx RMP level %d error %d\n",
+ pfn, start, end, rmp_level, ret);
+ return false;
+ }
+
+ if (assigned) {
+ pr_debug("%s: overlap detected, PFN 0x%llx start 0x%llx end 0x%llx RMP level %d\n",
+ __func__, pfn, start, end, rmp_level);
+ return false;
+ }
+
+ pfn++;
+ }
+
+ return true;
+}
+
+static u8 max_level_for_order(int order)
+{
+ if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+ return PG_LEVEL_2M;
+
+ return PG_LEVEL_4K;
+}
+
+static bool is_large_rmp_possible(struct kvm *kvm, kvm_pfn_t pfn, int order)
+{
+ kvm_pfn_t pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
+
+ /*
+ * If this is a large folio, and the entire 2M range containing the
+ * PFN is currently shared, then the entire 2M-aligned range can be
+ * set to private via a single 2M RMP entry.
+ */
+ if (max_level_for_order(order) > PG_LEVEL_4K &&
+ is_pfn_range_shared(pfn_aligned, pfn_aligned + PTRS_PER_PMD))
+ return true;
+
+ return false;
+}
+
+int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ kvm_pfn_t pfn_aligned;
+ gfn_t gfn_aligned;
+ int level, rc;
+ bool assigned;
+
+ if (!sev_snp_guest(kvm))
+ return 0;
+
+ rc = snp_lookup_rmpentry(pfn, &assigned, &level);
+ if (rc) {
+ pr_err_ratelimited("SEV: Failed to look up RMP entry: GFN %llx PFN %llx error %d\n",
+ gfn, pfn, rc);
+ return -ENOENT;
+ }
+
+ if (assigned) {
+ pr_debug("%s: already assigned: gfn %llx pfn %llx max_order %d level %d\n",
+ __func__, gfn, pfn, max_order, level);
+ return 0;
+ }
+
+ if (is_large_rmp_possible(kvm, pfn, max_order)) {
+ level = PG_LEVEL_2M;
+ pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
+ gfn_aligned = ALIGN_DOWN(gfn, PTRS_PER_PMD);
+ } else {
+ level = PG_LEVEL_4K;
+ pfn_aligned = pfn;
+ gfn_aligned = gfn;
+ }
+
+ rc = rmp_make_private(pfn_aligned, gfn_to_gpa(gfn_aligned), level, sev->asid, false);
+ if (rc) {
+ pr_err_ratelimited("SEV: Failed to update RMP entry: GFN %llx PFN %llx level %d error %d\n",
+ gfn, pfn, level, rc);
+ return -EINVAL;
+ }
+
+ pr_debug("%s: updated: gfn %llx pfn %llx pfn_aligned %llx max_order %d level %d\n",
+ __func__, gfn, pfn, pfn_aligned, max_order, level);
+
+ return 0;
+}
+
+void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
+{
+ kvm_pfn_t pfn;
+
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+ return;
+
+ pr_debug("%s: PFN start 0x%llx PFN end 0x%llx\n", __func__, start, end);
+
+ for (pfn = start; pfn < end;) {
+ bool use_2m_update = false;
+ int rc, rmp_level;
+ bool assigned;
+
+ rc = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
+ if (rc || !assigned)
+ goto next_pfn;
+
+ use_2m_update = IS_ALIGNED(pfn, PTRS_PER_PMD) &&
+ end >= (pfn + PTRS_PER_PMD) &&
+ rmp_level > PG_LEVEL_4K;
+
+ /*
+ * If an unaligned PFN corresponds to a 2M region assigned as a
+ * large page in the RMP table, PSMASH the region into individual
+ * 4K RMP entries before attempting to convert a 4K sub-page.
+ */
+ if (!use_2m_update && rmp_level > PG_LEVEL_4K) {
+ /*
+ * This shouldn't fail, but if it does, report it, but
+ * still try to update RMP entry to shared and pray this
+ * was a spurious error that can be addressed later.
+ */
+ rc = snp_rmptable_psmash(pfn);
+ WARN_ONCE(rc, "SEV: Failed to PSMASH RMP entry for PFN 0x%llx error %d\n",
+ pfn, rc);
+ }
+
+ rc = rmp_make_shared(pfn, use_2m_update ? PG_LEVEL_2M : PG_LEVEL_4K);
+ if (WARN_ONCE(rc, "SEV: Failed to update RMP entry for PFN 0x%llx error %d\n",
+ pfn, rc))
+ goto next_pfn;
+
+ /*
+ * SEV-ES avoids host/guest cache coherency issues through
+ * WBINVD hooks issued via MMU notifiers during run-time, and
+ * KVM's VM destroy path at shutdown. Those MMU notifier events
+ * don't cover gmem since there is no requirement to map pages
+ * to a HVA in order to use them for a running guest. While the
+ * shutdown path would still likely cover things for SNP guests,
+ * userspace may also free gmem pages during run-time via
+ * hole-punching operations on the guest_memfd, so flush the
+ * cache entries for these pages before free'ing them back to
+ * the host.
+ */
+ clflush_cache_range(__va(pfn_to_hpa(pfn)),
+ use_2m_update ? PMD_SIZE : PAGE_SIZE);
+next_pfn:
+ pfn += use_2m_update ? PTRS_PER_PMD : 1;
+ cond_resched();
+ }
+}
+
+int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+ int level, rc;
+ bool assigned;
+
+ if (!sev_snp_guest(kvm))
+ return 0;
+
+ rc = snp_lookup_rmpentry(pfn, &assigned, &level);
+ if (rc || !assigned)
+ return PG_LEVEL_4K;
+
+ return level;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c95d3900fe56..c115d26844f7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -53,6 +53,7 @@
#include "svm_onhyperv.h"
MODULE_AUTHOR("Qumranet");
+MODULE_DESCRIPTION("KVM support for SVM (AMD-V) extensions");
MODULE_LICENSE("GPL");
#ifdef MODULE
@@ -570,6 +571,11 @@ static void __svm_write_tsc_multiplier(u64 multiplier)
__this_cpu_write(current_tsc_ratio, multiplier);
}
+static __always_inline struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd)
+{
+ return page_address(sd->save_area) + 0x400;
+}
+
static inline void kvm_cpu_svm_disable(void)
{
uint64_t efer;
@@ -674,12 +680,9 @@ static int svm_hardware_enable(void)
* TSC_AUX field now to avoid a RDMSR on every vCPU run.
*/
if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
- struct sev_es_save_area *hostsa;
u32 __maybe_unused msr_hi;
- hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
-
- rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi);
+ rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi);
}
return 0;
@@ -704,7 +707,7 @@ static int svm_cpu_init(int cpu)
int ret = -ENOMEM;
memset(sd, 0, sizeof(struct svm_cpu_data));
- sd->save_area = snp_safe_alloc_page(NULL);
+ sd->save_area = snp_safe_alloc_page_node(cpu_to_node(cpu), GFP_KERNEL);
if (!sd->save_area)
return ret;
@@ -1202,7 +1205,7 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- if (guest_cpuid_is_intel(vcpu)) {
+ if (guest_cpuid_is_intel_compatible(vcpu)) {
/*
* We must intercept SYSENTER_EIP and SYSENTER_ESP
* accesses because the processor only stores 32 bits.
@@ -1404,6 +1407,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
svm->spec_ctrl = 0;
svm->virt_spec_ctrl = 0;
+ if (init_event)
+ sev_snp_init_protected_guest_state(vcpu);
+
init_vmcb(vcpu);
if (!init_event)
@@ -1427,7 +1433,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
svm = to_svm(vcpu);
err = -ENOMEM;
- vmcb01_page = snp_safe_alloc_page(vcpu);
+ vmcb01_page = snp_safe_alloc_page();
if (!vmcb01_page)
goto out;
@@ -1436,7 +1442,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
* SEV-ES guests require a separate VMSA page used to contain
* the encrypted register state of the guest.
*/
- vmsa_page = snp_safe_alloc_page(vcpu);
+ vmsa_page = snp_safe_alloc_page();
if (!vmsa_page)
goto error_free_vmcb_page;
}
@@ -1501,11 +1507,6 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
}
-static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd)
-{
- return page_address(sd->save_area) + 0x400;
-}
-
static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1551,6 +1552,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
struct vcpu_svm *svm = to_svm(vcpu);
struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
+ if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
+ shrink_ple_window(vcpu);
+
if (sd->current_vmcb != svm->vmcb) {
sd->current_vmcb = svm->vmcb;
@@ -2050,6 +2054,7 @@ static int pf_interception(struct kvm_vcpu *vcpu)
static int npf_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ int rc;
u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
@@ -2063,11 +2068,19 @@ static int npf_interception(struct kvm_vcpu *vcpu)
if (WARN_ON_ONCE(error_code & PFERR_SYNTHETIC_MASK))
error_code &= ~PFERR_SYNTHETIC_MASK;
+ if (sev_snp_guest(vcpu->kvm) && (error_code & PFERR_GUEST_ENC_MASK))
+ error_code |= PFERR_PRIVATE_ACCESS;
+
trace_kvm_page_fault(vcpu, fault_address, error_code);
- return kvm_mmu_page_fault(vcpu, fault_address, error_code,
- static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
- svm->vmcb->control.insn_bytes : NULL,
- svm->vmcb->control.insn_len);
+ rc = kvm_mmu_page_fault(vcpu, fault_address, error_code,
+ static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
+ svm->vmcb->control.insn_bytes : NULL,
+ svm->vmcb->control.insn_len);
+
+ if (rc > 0 && error_code & PFERR_GUEST_RMP_MASK)
+ sev_handle_rmp_fault(vcpu, fault_address, error_code);
+
+ return rc;
}
static int db_interception(struct kvm_vcpu *vcpu)
@@ -2875,12 +2888,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_SYSENTER_EIP:
msr_info->data = (u32)svm->vmcb01.ptr->save.sysenter_eip;
- if (guest_cpuid_is_intel(vcpu))
+ if (guest_cpuid_is_intel_compatible(vcpu))
msr_info->data |= (u64)svm->sysenter_eip_hi << 32;
break;
case MSR_IA32_SYSENTER_ESP:
msr_info->data = svm->vmcb01.ptr->save.sysenter_esp;
- if (guest_cpuid_is_intel(vcpu))
+ if (guest_cpuid_is_intel_compatible(vcpu))
msr_info->data |= (u64)svm->sysenter_esp_hi << 32;
break;
case MSR_TSC_AUX:
@@ -3107,11 +3120,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
* 32 bit part of these msrs to support Intel's
* implementation of SYSENTER/SYSEXIT.
*/
- svm->sysenter_eip_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0;
+ svm->sysenter_eip_hi = guest_cpuid_is_intel_compatible(vcpu) ? (data >> 32) : 0;
break;
case MSR_IA32_SYSENTER_ESP:
svm->vmcb01.ptr->save.sysenter_esp = (u32)data;
- svm->sysenter_esp_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0;
+ svm->sysenter_esp_hi = guest_cpuid_is_intel_compatible(vcpu) ? (data >> 32) : 0;
break;
case MSR_TSC_AUX:
/*
@@ -4372,11 +4385,11 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LBRV);
/*
- * Intercept VMLOAD if the vCPU mode is Intel in order to emulate that
+ * Intercept VMLOAD if the vCPU model is Intel in order to emulate that
* VMLOAD drops bits 63:32 of SYSENTER (ignoring the fact that exposing
* SVM on Intel is bonkers and extremely unlikely to work).
*/
- if (!guest_cpuid_is_intel(vcpu))
+ if (!guest_cpuid_is_intel_compatible(vcpu))
kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER);
@@ -4595,12 +4608,6 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
vcpu->arch.at_instruction_boundary = true;
}
-static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
- if (!kvm_pause_in_guest(vcpu->kvm))
- shrink_ple_window(vcpu);
-}
-
static void svm_setup_mce(struct kvm_vcpu *vcpu)
{
/* [63:9] are reserved. */
@@ -4937,8 +4944,11 @@ static int svm_vm_init(struct kvm *kvm)
if (type != KVM_X86_DEFAULT_VM &&
type != KVM_X86_SW_PROTECTED_VM) {
- kvm->arch.has_protected_state = (type == KVM_X86_SEV_ES_VM);
+ kvm->arch.has_protected_state =
+ (type == KVM_X86_SEV_ES_VM || type == KVM_X86_SNP_VM);
to_kvm_sev_info(kvm)->need_init = true;
+
+ kvm->arch.has_private_mem = (type == KVM_X86_SNP_VM);
}
if (!pause_filter_count || !pause_filter_thresh)
@@ -4955,7 +4965,7 @@ static int svm_vm_init(struct kvm *kvm)
static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu)
{
- struct page *page = snp_safe_alloc_page(vcpu);
+ struct page *page = snp_safe_alloc_page();
if (!page)
return NULL;
@@ -5060,8 +5070,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.check_intercept = svm_check_intercept,
.handle_exit_irqoff = svm_handle_exit_irqoff,
- .sched_in = svm_sched_in,
-
.nested_ops = &svm_nested_ops,
.deliver_interrupt = svm_deliver_interrupt,
@@ -5095,6 +5103,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
.alloc_apic_backing_page = svm_alloc_apic_backing_page,
+
+ .gmem_prepare = sev_gmem_prepare,
+ .gmem_invalidate = sev_gmem_invalidate,
+ .private_max_mapping_level = sev_private_max_mapping_level,
};
/*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 0f1472690b59..76107c7d0595 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -94,6 +94,10 @@ struct kvm_sev_info {
struct list_head mirror_entry; /* Use as a list entry of mirrors */
struct misc_cg *misc_cg; /* For misc cgroup accounting */
atomic_t migration_in_progress;
+ void *snp_context; /* SNP guest context page */
+ void *guest_req_buf; /* Bounce buffer for SNP Guest Request input */
+ void *guest_resp_buf; /* Bounce buffer for SNP Guest Request output */
+ struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */
};
struct kvm_svm {
@@ -209,6 +213,18 @@ struct vcpu_sev_es_state {
u32 ghcb_sa_len;
bool ghcb_sa_sync;
bool ghcb_sa_free;
+
+ /* SNP Page-State-Change buffer entries currently being processed */
+ u16 psc_idx;
+ u16 psc_inflight;
+ bool psc_2m;
+
+ u64 ghcb_registered_gpa;
+
+ struct mutex snp_vmsa_mutex; /* Used to handle concurrent updates of VMSA. */
+ gpa_t snp_vmsa_gpa;
+ bool snp_ap_waiting_for_reset;
+ bool snp_has_guest_vmsa;
};
struct vcpu_svm {
@@ -350,6 +366,23 @@ static __always_inline bool sev_es_guest(struct kvm *kvm)
#endif
}
+static __always_inline bool sev_snp_guest(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_AMD_SEV
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+ return (sev->vmsa_features & SVM_SEV_FEAT_SNP_ACTIVE) &&
+ !WARN_ON_ONCE(!sev_es_guest(kvm));
+#else
+ return false;
+#endif
+}
+
+static inline bool ghcb_gpa_is_registered(struct vcpu_svm *svm, u64 val)
+{
+ return svm->sev_es.ghcb_registered_gpa == val;
+}
+
static inline void vmcb_mark_all_dirty(struct vmcb *vmcb)
{
vmcb->control.clean = 0;
@@ -638,7 +671,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
/* avic.c */
#define AVIC_REQUIRED_APICV_INHIBITS \
( \
- BIT(APICV_INHIBIT_REASON_DISABLE) | \
+ BIT(APICV_INHIBIT_REASON_DISABLED) | \
BIT(APICV_INHIBIT_REASON_ABSENT) | \
BIT(APICV_INHIBIT_REASON_HYPERV) | \
BIT(APICV_INHIBIT_REASON_NESTED) | \
@@ -696,7 +729,13 @@ void sev_guest_memory_reclaimed(struct kvm *kvm);
int sev_handle_vmgexit(struct kvm_vcpu *vcpu);
/* These symbols are used in common code and are stubbed below. */
-struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
+
+struct page *snp_safe_alloc_page_node(int node, gfp_t gfp);
+static inline struct page *snp_safe_alloc_page(void)
+{
+ return snp_safe_alloc_page_node(numa_node_id(), GFP_KERNEL_ACCOUNT);
+}
+
void sev_free_vcpu(struct kvm_vcpu *vcpu);
void sev_vm_destroy(struct kvm *kvm);
void __init sev_set_cpu_caps(void);
@@ -705,9 +744,20 @@ void sev_hardware_unsetup(void);
int sev_cpu_init(struct svm_cpu_data *sd);
int sev_dev_get_attr(u32 group, u64 attr, u64 *val);
extern unsigned int max_sev_asid;
+void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
+void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
+int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
+void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
+int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
#else
-static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
- return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+static inline struct page *snp_safe_alloc_page_node(int node, gfp_t gfp)
+{
+ return alloc_pages_node(node, gfp | __GFP_ZERO, 0);
+}
+
+static inline struct page *snp_safe_alloc_page(void)
+{
+ return snp_safe_alloc_page_node(numa_node_id(), GFP_KERNEL_ACCOUNT);
}
static inline void sev_free_vcpu(struct kvm_vcpu *vcpu) {}
@@ -718,6 +768,18 @@ static inline void sev_hardware_unsetup(void) {}
static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; }
static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; }
#define max_sev_asid 0
+static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {}
+static inline void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) {}
+static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
+{
+ return 0;
+}
+static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {}
+static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+ return 0;
+}
+
#endif
/* vmenter.S */
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index e19fed438a67..d3aeffd6ae75 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -314,12 +314,12 @@ TRACE_EVENT(name, \
__entry->guest_rip = kvm_rip_read(vcpu); \
__entry->isa = isa; \
__entry->vcpu_id = vcpu->vcpu_id; \
- static_call(kvm_x86_get_exit_info)(vcpu, \
- &__entry->exit_reason, \
- &__entry->info1, \
- &__entry->info2, \
- &__entry->intr_info, \
- &__entry->error_code); \
+ kvm_x86_call(get_exit_info)(vcpu, \
+ &__entry->exit_reason, \
+ &__entry->info1, \
+ &__entry->info2, \
+ &__entry->intr_info, \
+ &__entry->error_code); \
), \
\
TP_printk("vcpu %u reason %s%s%s rip 0x%lx info1 0x%016llx " \
@@ -828,7 +828,8 @@ TRACE_EVENT(kvm_emulate_insn,
),
TP_fast_assign(
- __entry->csbase = static_call(kvm_x86_get_segment_base)(vcpu, VCPU_SREG_CS);
+ __entry->csbase = kvm_x86_call(get_segment_base)(vcpu,
+ VCPU_SREG_CS);
__entry->len = vcpu->arch.emulate_ctxt->fetch.ptr
- vcpu->arch.emulate_ctxt->fetch.data;
__entry->rip = vcpu->arch.emulate_ctxt->_eip - __entry->len;
@@ -1375,6 +1376,10 @@ TRACE_EVENT(kvm_hv_stimer_cleanup,
__entry->vcpu_id, __entry->timer_index)
);
+#define kvm_print_apicv_inhibit_reasons(inhibits) \
+ (inhibits), (inhibits) ? " " : "", \
+ (inhibits) ? __print_flags(inhibits, "|", APICV_INHIBIT_REASONS) : ""
+
TRACE_EVENT(kvm_apicv_inhibit_changed,
TP_PROTO(int reason, bool set, unsigned long inhibits),
TP_ARGS(reason, set, inhibits),
@@ -1391,9 +1396,10 @@ TRACE_EVENT(kvm_apicv_inhibit_changed,
__entry->inhibits = inhibits;
),
- TP_printk("%s reason=%u, inhibits=0x%lx",
+ TP_printk("%s reason=%u, inhibits=0x%lx%s%s",
__entry->set ? "set" : "cleared",
- __entry->reason, __entry->inhibits)
+ __entry->reason,
+ kvm_print_apicv_inhibit_reasons(__entry->inhibits))
);
TRACE_EVENT(kvm_apicv_accept_irq,
@@ -1834,6 +1840,37 @@ TRACE_EVENT(kvm_vmgexit_msr_protocol_exit,
__entry->vcpu_id, __entry->ghcb_gpa, __entry->result)
);
+/*
+ * Tracepoint for #NPFs due to RMP faults.
+ */
+TRACE_EVENT(kvm_rmp_fault,
+ TP_PROTO(struct kvm_vcpu *vcpu, u64 gpa, u64 pfn, u64 error_code,
+ int rmp_level, int psmash_ret),
+ TP_ARGS(vcpu, gpa, pfn, error_code, rmp_level, psmash_ret),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, vcpu_id)
+ __field(u64, gpa)
+ __field(u64, pfn)
+ __field(u64, error_code)
+ __field(int, rmp_level)
+ __field(int, psmash_ret)
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu->vcpu_id;
+ __entry->gpa = gpa;
+ __entry->pfn = pfn;
+ __entry->error_code = error_code;
+ __entry->rmp_level = rmp_level;
+ __entry->psmash_ret = psmash_ret;
+ ),
+
+ TP_printk("vcpu %u gpa %016llx pfn 0x%llx error_code 0x%llx rmp_level %d psmash_ret %d",
+ __entry->vcpu_id, __entry->gpa, __entry->pfn,
+ __entry->error_code, __entry->rmp_level, __entry->psmash_ret)
+);
+
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index d4ed681785fd..0bf35ebe8a1b 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -8,7 +8,7 @@
#include "posted_intr.h"
#define VMX_REQUIRED_APICV_INHIBITS \
- (BIT(APICV_INHIBIT_REASON_DISABLE)| \
+ (BIT(APICV_INHIBIT_REASON_DISABLED) | \
BIT(APICV_INHIBIT_REASON_ABSENT) | \
BIT(APICV_INHIBIT_REASON_HYPERV) | \
BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \
@@ -97,7 +97,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
.hwapic_irr_update = vmx_hwapic_irr_update,
.hwapic_isr_update = vmx_hwapic_isr_update,
- .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
.sync_pir_to_irr = vmx_sync_pir_to_irr,
.deliver_interrupt = vmx_deliver_interrupt,
.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
@@ -122,8 +121,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.check_intercept = vmx_check_intercept,
.handle_exit_irqoff = vmx_handle_exit_irqoff,
- .sched_in = vmx_sched_in,
-
.cpu_dirty_log_size = PML_ENTITY_NUM,
.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 643935a0f70a..2392a7ef254d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -12,6 +12,7 @@
#include "mmu.h"
#include "nested.h"
#include "pmu.h"
+#include "posted_intr.h"
#include "sgx.h"
#include "trace.h"
#include "vmx.h"
@@ -2425,7 +2426,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
if (cpu_has_load_ia32_efer()) {
if (guest_efer & EFER_LMA)
exec_control |= VM_ENTRY_IA32E_MODE;
- if (guest_efer != host_efer)
+ if (guest_efer != kvm_host.efer)
exec_control |= VM_ENTRY_LOAD_IA32_EFER;
}
vm_entry_controls_set(vmx, exec_control);
@@ -2438,7 +2439,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
* bits may be modified by vmx_set_efer() in prepare_vmcs02().
*/
exec_control = __vm_exit_controls_get(vmcs01);
- if (cpu_has_load_ia32_efer() && guest_efer != host_efer)
+ if (cpu_has_load_ia32_efer() && guest_efer != kvm_host.efer)
exec_control |= VM_EXIT_LOAD_IA32_EFER;
else
exec_control &= ~VM_EXIT_LOAD_IA32_EFER;
@@ -3899,8 +3900,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
if (!pi_test_and_clear_on(vmx->nested.pi_desc))
return 0;
- max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
- if (max_irr != 256) {
+ max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
+ if (max_irr > 0) {
vapic_page = vmx->nested.virtual_apic_map.hva;
if (!vapic_page)
goto mmio_needed;
@@ -4031,10 +4032,46 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->nested.preemption_timer_expired;
}
-static bool vmx_has_nested_events(struct kvm_vcpu *vcpu)
+static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection)
{
- return nested_vmx_preemption_timer_pending(vcpu) ||
- to_vmx(vcpu)->nested.mtf_pending;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ void *vapic = vmx->nested.virtual_apic_map.hva;
+ int max_irr, vppr;
+
+ if (nested_vmx_preemption_timer_pending(vcpu) ||
+ vmx->nested.mtf_pending)
+ return true;
+
+ /*
+ * Virtual Interrupt Delivery doesn't require manual injection. Either
+ * the interrupt is already in GUEST_RVI and will be recognized by CPU
+ * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move
+ * the interrupt from the PIR to RVI prior to entering the guest.
+ */
+ if (for_injection)
+ return false;
+
+ if (!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+ __vmx_interrupt_blocked(vcpu))
+ return false;
+
+ if (!vapic)
+ return false;
+
+ vppr = *((u32 *)(vapic + APIC_PROCPRI));
+
+ max_irr = vmx_get_rvi();
+ if ((max_irr & 0xf0) > (vppr & 0xf0))
+ return true;
+
+ if (vmx->nested.pi_pending && vmx->nested.pi_desc &&
+ pi_test_on(vmx->nested.pi_desc)) {
+ max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
+ if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0))
+ return true;
+ }
+
+ return false;
}
/*
@@ -4665,7 +4702,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
return vmcs_read64(GUEST_IA32_EFER);
if (cpu_has_load_ia32_efer())
- return host_efer;
+ return kvm_host.efer;
for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) {
if (vmx->msr_autoload.guest.val[i].index == MSR_EFER)
@@ -4676,7 +4713,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
if (efer_msr)
return efer_msr->data;
- return host_efer;
+ return kvm_host.efer;
}
static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index be40474de6e4..83382a4d1d66 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -348,14 +348,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
switch (msr) {
case MSR_CORE_PERF_FIXED_CTR_CTRL:
- if (data & pmu->fixed_ctr_ctrl_mask)
+ if (data & pmu->fixed_ctr_ctrl_rsvd)
return 1;
if (pmu->fixed_ctr_ctrl != data)
reprogram_fixed_counters(pmu, data);
break;
case MSR_IA32_PEBS_ENABLE:
- if (data & pmu->pebs_enable_mask)
+ if (data & pmu->pebs_enable_rsvd)
return 1;
if (pmu->pebs_enable != data) {
@@ -371,7 +371,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
pmu->ds_area = data;
break;
case MSR_PEBS_DATA_CFG:
- if (data & pmu->pebs_data_cfg_mask)
+ if (data & pmu->pebs_data_cfg_rsvd)
return 1;
pmu->pebs_data_cfg = data;
@@ -436,8 +436,8 @@ static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index)
};
u64 eventsel;
- BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_PMC_MAX_FIXED);
- BUILD_BUG_ON(index >= KVM_PMC_MAX_FIXED);
+ BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_MAX_NR_INTEL_FIXED_COUTNERS);
+ BUILD_BUG_ON(index >= KVM_MAX_NR_INTEL_FIXED_COUTNERS);
/*
* Yell if perf reports support for a fixed counter but perf doesn't
@@ -448,6 +448,14 @@ static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index)
return eventsel;
}
+static void intel_pmu_enable_fixed_counter_bits(struct kvm_pmu *pmu, u64 bits)
+{
+ int i;
+
+ for (i = 0; i < pmu->nr_arch_fixed_counters; i++)
+ pmu->fixed_ctr_ctrl_rsvd &= ~intel_fixed_bits_by_idx(i, bits);
+}
+
static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -456,8 +464,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
union cpuid10_eax eax;
union cpuid10_edx edx;
u64 perf_capabilities;
- u64 counter_mask;
- int i;
+ u64 counter_rsvd;
memset(&lbr_desc->records, 0, sizeof(lbr_desc->records));
@@ -501,22 +508,24 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
((u64)1 << edx.split.bit_width_fixed) - 1;
}
- for (i = 0; i < pmu->nr_arch_fixed_counters; i++)
- pmu->fixed_ctr_ctrl_mask &= ~(0xbull << (i * 4));
- counter_mask = ~(((1ull << pmu->nr_arch_gp_counters) - 1) |
+ intel_pmu_enable_fixed_counter_bits(pmu, INTEL_FIXED_0_KERNEL |
+ INTEL_FIXED_0_USER |
+ INTEL_FIXED_0_ENABLE_PMI);
+
+ counter_rsvd = ~(((1ull << pmu->nr_arch_gp_counters) - 1) |
(((1ull << pmu->nr_arch_fixed_counters) - 1) << KVM_FIXED_PMC_BASE_IDX));
- pmu->global_ctrl_mask = counter_mask;
+ pmu->global_ctrl_rsvd = counter_rsvd;
/*
* GLOBAL_STATUS and GLOBAL_OVF_CONTROL (a.k.a. GLOBAL_STATUS_RESET)
* share reserved bit definitions. The kernel just happens to use
* OVF_CTRL for the names.
*/
- pmu->global_status_mask = pmu->global_ctrl_mask
+ pmu->global_status_rsvd = pmu->global_ctrl_rsvd
& ~(MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF |
MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD);
if (vmx_pt_mode_is_host_guest())
- pmu->global_status_mask &=
+ pmu->global_status_rsvd &=
~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI;
entry = kvm_find_cpuid_entry_index(vcpu, 7, 0);
@@ -544,15 +553,12 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
if (perf_capabilities & PERF_CAP_PEBS_FORMAT) {
if (perf_capabilities & PERF_CAP_PEBS_BASELINE) {
- pmu->pebs_enable_mask = counter_mask;
+ pmu->pebs_enable_rsvd = counter_rsvd;
pmu->reserved_bits &= ~ICL_EVENTSEL_ADAPTIVE;
- for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
- pmu->fixed_ctr_ctrl_mask &=
- ~(1ULL << (KVM_FIXED_PMC_BASE_IDX + i * 4));
- }
- pmu->pebs_data_cfg_mask = ~0xff00000full;
+ pmu->pebs_data_cfg_rsvd = ~0xff00000full;
+ intel_pmu_enable_fixed_counter_bits(pmu, ICL_FIXED_0_ADAPTIVE);
} else {
- pmu->pebs_enable_mask =
+ pmu->pebs_enable_rsvd =
~((1ull << pmu->nr_arch_gp_counters) - 1);
}
}
@@ -564,14 +570,14 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
- for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) {
+ for (i = 0; i < KVM_MAX_NR_INTEL_GP_COUNTERS; i++) {
pmu->gp_counters[i].type = KVM_PMC_GP;
pmu->gp_counters[i].vcpu = vcpu;
pmu->gp_counters[i].idx = i;
pmu->gp_counters[i].current_config = 0;
}
- for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
+ for (i = 0; i < KVM_MAX_NR_INTEL_FIXED_COUTNERS; i++) {
pmu->fixed_counters[i].type = KVM_PMC_FIXED;
pmu->fixed_counters[i].vcpu = vcpu;
pmu->fixed_counters[i].idx = i + KVM_FIXED_PMC_BASE_IDX;
@@ -731,6 +737,6 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = {
.deliver_pmi = intel_pmu_deliver_pmi,
.cleanup = intel_pmu_cleanup,
.EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT,
- .MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC,
+ .MAX_NR_GP_COUNTERS = KVM_MAX_NR_INTEL_GP_COUNTERS,
.MIN_NR_GP_COUNTERS = 1,
};
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 6b2a0226257e..1715d2ab07be 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -1,6 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_X86_VMX_POSTED_INTR_H
#define __KVM_X86_VMX_POSTED_INTR_H
+
+#include <linux/find.h>
#include <asm/posted_intr.h>
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
@@ -12,4 +14,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
void vmx_pi_start_assignment(struct kvm *kvm);
+static inline int pi_find_highest_vector(struct pi_desc *pi_desc)
+{
+ int vec;
+
+ vec = find_last_bit((unsigned long *)pi_desc->pir, 256);
+ return vec < 256 ? vec : -1;
+}
+
#endif /* __KVM_X86_VMX_POSTED_INTR_H */
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 01936013428b..56fd150a6f24 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -188,12 +188,13 @@ struct __packed vmcs12 {
};
/*
- * VMCS12_REVISION is an arbitrary id that should be changed if the content or
- * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and
- * VMPTRLD verifies that the VMCS region that L1 is loading contains this id.
+ * VMCS12_REVISION is KVM's arbitrary ID for the layout of struct vmcs12. KVM
+ * enumerates this value to L1 via MSR_IA32_VMX_BASIC, and checks the revision
+ * ID during nested VMPTRLD to verify that L1 is loading a VMCS that adhere's
+ * to KVM's virtual CPU definition.
*
- * IMPORTANT: Changing this value will break save/restore compatibility with
- * older kvm releases.
+ * DO NOT change this value, as it will break save/restore compatibility with
+ * older KVM releases.
*/
#define VMCS12_REVISION 0x11e57ed0
@@ -206,7 +207,8 @@ struct __packed vmcs12 {
#define VMCS12_SIZE KVM_STATE_NESTED_VMX_VMCS_SIZE
/*
- * For save/restore compatibility, the vmcs12 field offsets must not change.
+ * For save/restore compatibility, the vmcs12 field offsets must not change,
+ * although appending fields and/or filling gaps is obviously allowed.
*/
#define CHECK_OFFSET(field, loc) \
ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b3c83c06f826..f18c2d8c7476 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -74,6 +74,7 @@
#include "posted_intr.h"
MODULE_AUTHOR("Qumranet");
+MODULE_DESCRIPTION("KVM support for VMX (Intel VT-x) extensions");
MODULE_LICENSE("GPL");
#ifdef MODULE
@@ -259,7 +260,7 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
return 0;
}
- if (host_arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+ if (kvm_host.arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
return 0;
}
@@ -404,7 +405,7 @@ static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
* and VM-Exit.
*/
vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) &&
- (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
+ (kvm_host.arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
!boot_cpu_has_bug(X86_BUG_MDS) &&
!boot_cpu_has_bug(X86_BUG_TAA);
@@ -1123,12 +1124,12 @@ static bool update_transition_efer(struct vcpu_vmx *vmx)
* atomically, since it's faster than switching it manually.
*/
if (cpu_has_load_ia32_efer() ||
- (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
+ (enable_ept && ((vmx->vcpu.arch.efer ^ kvm_host.efer) & EFER_NX))) {
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
- if (guest_efer != host_efer)
+ if (guest_efer != kvm_host.efer)
add_atomic_switch_msr(vmx, MSR_EFER,
- guest_efer, host_efer, false);
+ guest_efer, kvm_host.efer, false);
else
clear_atomic_switch_msr(vmx, MSR_EFER);
return false;
@@ -1141,7 +1142,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx)
clear_atomic_switch_msr(vmx, MSR_EFER);
guest_efer &= ~ignore_bits;
- guest_efer |= host_efer & ignore_bits;
+ guest_efer |= kvm_host.efer & ignore_bits;
vmx->guest_uret_msrs[i].data = guest_efer;
vmx->guest_uret_msrs[i].mask = ~ignore_bits;
@@ -1411,6 +1412,38 @@ static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
}
#endif
+static void grow_ple_window(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned int old = vmx->ple_window;
+
+ vmx->ple_window = __grow_ple_window(old, ple_window,
+ ple_window_grow,
+ ple_window_max);
+
+ if (vmx->ple_window != old) {
+ vmx->ple_window_dirty = true;
+ trace_kvm_ple_window_update(vcpu->vcpu_id,
+ vmx->ple_window, old);
+ }
+}
+
+static void shrink_ple_window(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned int old = vmx->ple_window;
+
+ vmx->ple_window = __shrink_ple_window(old, ple_window,
+ ple_window_shrink,
+ ple_window);
+
+ if (vmx->ple_window != old) {
+ vmx->ple_window_dirty = true;
+ trace_kvm_ple_window_update(vcpu->vcpu_id,
+ vmx->ple_window, old);
+ }
+}
+
void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
struct loaded_vmcs *buddy)
{
@@ -1486,6 +1519,9 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
+ shrink_ple_window(vcpu);
+
vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
vmx_vcpu_pi_load(vcpu, cpu);
@@ -2525,17 +2561,15 @@ static bool cpu_has_sgx(void)
*/
static bool cpu_has_perf_global_ctrl_bug(void)
{
- if (boot_cpu_data.x86 == 0x6) {
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_NEHALEM_EP: /* AAK155 */
- case INTEL_FAM6_NEHALEM: /* AAP115 */
- case INTEL_FAM6_WESTMERE: /* AAT100 */
- case INTEL_FAM6_WESTMERE_EP: /* BC86,AAY89,BD102 */
- case INTEL_FAM6_NEHALEM_EX: /* BA97 */
- return true;
- default:
- break;
- }
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_NEHALEM_EP: /* AAK155 */
+ case INTEL_NEHALEM: /* AAP115 */
+ case INTEL_WESTMERE: /* AAT100 */
+ case INTEL_WESTMERE_EP: /* BC86,AAY89,BD102 */
+ case INTEL_NEHALEM_EX: /* BA97 */
+ return true;
+ default:
+ break;
}
return false;
@@ -2834,9 +2868,6 @@ int vmx_hardware_enable(void)
return r;
}
- if (enable_ept)
- ept_sync_global();
-
return 0;
}
@@ -4108,26 +4139,6 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
}
}
-bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- void *vapic_page;
- u32 vppr;
- int rvi;
-
- if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
- !nested_cpu_has_vid(get_vmcs12(vcpu)) ||
- WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn))
- return false;
-
- rvi = vmx_get_rvi();
-
- vapic_page = vmx->nested.virtual_apic_map.hva;
- vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
-
- return ((rvi & 0xf0) > (vppr & 0xf0));
-}
-
void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4357,7 +4368,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
}
if (cpu_has_load_ia32_efer())
- vmcs_write64(HOST_IA32_EFER, host_efer);
+ vmcs_write64(HOST_IA32_EFER, kvm_host.efer);
}
void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
@@ -5052,14 +5063,19 @@ int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !vmx_nmi_blocked(vcpu);
}
+bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu)
+{
+ return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) ||
+ (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+ (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
+}
+
bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu)
{
if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
return false;
- return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) ||
- (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
- (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
+ return __vmx_interrupt_blocked(vcpu);
}
int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
@@ -5897,38 +5913,6 @@ int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
return 1;
}
-static void grow_ple_window(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned int old = vmx->ple_window;
-
- vmx->ple_window = __grow_ple_window(old, ple_window,
- ple_window_grow,
- ple_window_max);
-
- if (vmx->ple_window != old) {
- vmx->ple_window_dirty = true;
- trace_kvm_ple_window_update(vcpu->vcpu_id,
- vmx->ple_window, old);
- }
-}
-
-static void shrink_ple_window(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned int old = vmx->ple_window;
-
- vmx->ple_window = __shrink_ple_window(old, ple_window,
- ple_window_shrink,
- ple_window);
-
- if (vmx->ple_window != old) {
- vmx->ple_window_dirty = true;
- trace_kvm_ple_window_update(vcpu->vcpu_id,
- vmx->ple_window, old);
- }
-}
-
/*
* Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
* exiting, so only get here on cpu with PAUSE-Loop-Exiting.
@@ -6677,9 +6661,10 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu)
bool flush_l1d;
/*
- * Clear the per-vcpu flush bit, it gets set again
- * either from vcpu_run() or from one of the unsafe
- * VMEXIT handlers.
+ * Clear the per-vcpu flush bit, it gets set again if the vCPU
+ * is reloaded, i.e. if the vCPU is scheduled out or if KVM
+ * exits to userspace, or if KVM reaches one of the unsafe
+ * VMEXIT handlers, e.g. if KVM calls into the emulator.
*/
flush_l1d = vcpu->arch.l1tf_flush_l1d;
vcpu->arch.l1tf_flush_l1d = false;
@@ -7665,39 +7650,25 @@ int vmx_vm_init(struct kvm *kvm)
u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
- /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in
- * memory aliases with conflicting memory types and sometimes MCEs.
- * We have to be careful as to what are honored and when.
- *
- * For MMIO, guest CD/MTRR are ignored. The EPT memory type is set to
- * UC. The effective memory type is UC or WC depending on guest PAT.
- * This was historically the source of MCEs and we want to be
- * conservative.
- *
- * When there is no need to deal with noncoherent DMA (e.g., no VT-d
- * or VT-d has snoop control), guest CD/MTRR/PAT are all ignored. The
- * EPT memory type is set to WB. The effective memory type is forced
- * WB.
- *
- * Otherwise, we trust guest. Guest CD/MTRR/PAT are all honored. The
- * EPT memory type is used to emulate guest CD/MTRR.
+ /*
+ * Force UC for host MMIO regions, as allowing the guest to access MMIO
+ * with cacheable accesses will result in Machine Checks.
*/
-
if (is_mmio)
return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
- if (!kvm_arch_has_noncoherent_dma(vcpu->kvm))
+ /*
+ * Force WB and ignore guest PAT if the VM does NOT have a non-coherent
+ * device attached and the CPU doesn't support self-snoop. Letting the
+ * guest control memory types on Intel CPUs without self-snoop may
+ * result in unexpected behavior, and so KVM's (historical) ABI is to
+ * trust the guest to behave only as a last resort.
+ */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP) &&
+ !kvm_arch_has_noncoherent_dma(vcpu->kvm))
return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT;
- if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) {
- if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
- return MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT;
- else
- return (MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT) |
- VMX_EPT_IPAT_BIT;
- }
-
- return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT;
+ return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT);
}
static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl)
@@ -8179,12 +8150,6 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
}
#endif
-void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
- if (!kvm_pause_in_guest(vcpu->kvm))
- shrink_ple_window(vcpu);
-}
-
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8396,18 +8361,16 @@ static void __init vmx_setup_me_spte_mask(void)
u64 me_mask = 0;
/*
- * kvm_get_shadow_phys_bits() returns shadow_phys_bits. Use
- * the former to avoid exposing shadow_phys_bits.
- *
* On pre-MKTME system, boot_cpu_data.x86_phys_bits equals to
- * shadow_phys_bits. On MKTME and/or TDX capable systems,
+ * kvm_host.maxphyaddr. On MKTME and/or TDX capable systems,
* boot_cpu_data.x86_phys_bits holds the actual physical address
- * w/o the KeyID bits, and shadow_phys_bits equals to MAXPHYADDR
- * reported by CPUID. Those bits between are KeyID bits.
+ * w/o the KeyID bits, and kvm_host.maxphyaddr equals to
+ * MAXPHYADDR reported by CPUID. Those bits between are KeyID bits.
*/
- if (boot_cpu_data.x86_phys_bits != kvm_get_shadow_phys_bits())
+ if (boot_cpu_data.x86_phys_bits != kvm_host.maxphyaddr)
me_mask = rsvd_bits(boot_cpu_data.x86_phys_bits,
- kvm_get_shadow_phys_bits() - 1);
+ kvm_host.maxphyaddr - 1);
+
/*
* Unlike SME, host kernel doesn't support setting up any
* MKTME KeyID on Intel platforms. No memory encryption
@@ -8629,9 +8592,9 @@ static void __vmx_exit(void)
static void vmx_exit(void)
{
kvm_exit();
+ __vmx_exit();
kvm_x86_vendor_exit();
- __vmx_exit();
}
module_exit(vmx_exit);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 7b64e271a931..42498fa63abb 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -406,6 +406,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu);
void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
bool vmx_nmi_blocked(struct kvm_vcpu *vcpu);
+bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
@@ -727,7 +728,7 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
return true;
return allow_smaller_maxphyaddr &&
- cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits();
+ cpuid_maxphyaddr(vcpu) < kvm_host.maxphyaddr;
}
static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 502704596c83..ce3221cd1d01 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -46,10 +46,8 @@ bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu);
void vmx_migrate_timers(struct kvm_vcpu *vcpu);
void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
-bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason);
void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
void vmx_hwapic_isr_update(int max_isr);
-bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu);
int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu);
void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
int trig_mode, int vector);
@@ -111,8 +109,6 @@ u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu);
u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
void vmx_write_tsc_offset(struct kvm_vcpu *vcpu);
void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu);
-void vmx_request_immediate_exit(struct kvm_vcpu *vcpu);
-void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu);
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
#ifdef CONFIG_X86_64
int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0763a0f72a06..af6c8cf6a37a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -100,6 +100,9 @@
struct kvm_caps kvm_caps __read_mostly;
EXPORT_SYMBOL_GPL(kvm_caps);
+struct kvm_host_values kvm_host __read_mostly;
+EXPORT_SYMBOL_GPL(kvm_host);
+
#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e))
#define emul_to_vcpu(ctxt) \
@@ -220,21 +223,12 @@ static struct kvm_user_return_msrs __percpu *user_return_msrs;
| XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \
| XFEATURE_MASK_PKRU | XFEATURE_MASK_XTILE)
-u64 __read_mostly host_efer;
-EXPORT_SYMBOL_GPL(host_efer);
-
bool __read_mostly allow_smaller_maxphyaddr = 0;
EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
bool __read_mostly enable_apicv = true;
EXPORT_SYMBOL_GPL(enable_apicv);
-u64 __read_mostly host_xss;
-EXPORT_SYMBOL_GPL(host_xss);
-
-u64 __read_mostly host_arch_capabilities;
-EXPORT_SYMBOL_GPL(host_arch_capabilities);
-
const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
KVM_GENERIC_VM_STATS(),
STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
@@ -308,8 +302,6 @@ const struct kvm_stats_header kvm_vcpu_stats_header = {
sizeof(kvm_vcpu_stats_desc),
};
-u64 __read_mostly host_xcr0;
-
static struct kmem_cache *x86_emulator_cache;
/*
@@ -833,7 +825,7 @@ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
*/
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl)
{
- if (static_call(kvm_x86_get_cpl)(vcpu) <= required_cpl)
+ if (kvm_x86_call(get_cpl)(vcpu) <= required_cpl)
return true;
kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
return false;
@@ -917,7 +909,7 @@ static bool kvm_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE))
return false;
- return static_call(kvm_x86_is_valid_cr0)(vcpu, cr0);
+ return kvm_x86_call(is_valid_cr0)(vcpu, cr0);
}
void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0)
@@ -954,11 +946,6 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon
if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS)
kvm_mmu_reset_context(vcpu);
-
- if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
- kvm_mmu_honors_guest_mtrrs(vcpu->kvm) &&
- !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
- kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
}
EXPORT_SYMBOL_GPL(kvm_post_set_cr0);
@@ -981,7 +968,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if (!is_pae(vcpu))
return 1;
- static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
+ kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
if (cs_l)
return 1;
}
@@ -995,7 +982,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
(is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)))
return 1;
- static_call(kvm_x86_set_cr0)(vcpu, cr0);
+ kvm_x86_call(set_cr0)(vcpu, cr0);
kvm_post_set_cr0(vcpu, old_cr0, cr0);
@@ -1016,11 +1003,11 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) {
- if (vcpu->arch.xcr0 != host_xcr0)
+ if (vcpu->arch.xcr0 != kvm_host.xcr0)
xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
- vcpu->arch.ia32_xss != host_xss)
+ vcpu->arch.ia32_xss != kvm_host.xss)
wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
}
@@ -1047,12 +1034,12 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) {
- if (vcpu->arch.xcr0 != host_xcr0)
- xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
+ if (vcpu->arch.xcr0 != kvm_host.xcr0)
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, kvm_host.xcr0);
if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
- vcpu->arch.ia32_xss != host_xss)
- wrmsrl(MSR_IA32_XSS, host_xss);
+ vcpu->arch.ia32_xss != kvm_host.xss)
+ wrmsrl(MSR_IA32_XSS, kvm_host.xss);
}
}
@@ -1113,7 +1100,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu)
{
/* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */
- if (static_call(kvm_x86_get_cpl)(vcpu) != 0 ||
+ if (kvm_x86_call(get_cpl)(vcpu) != 0 ||
__kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) {
kvm_inject_gp(vcpu, 0);
return 1;
@@ -1138,7 +1125,7 @@ EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4);
static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
return __kvm_is_valid_cr4(vcpu, cr4) &&
- static_call(kvm_x86_is_valid_cr4)(vcpu, cr4);
+ kvm_x86_call(is_valid_cr4)(vcpu, cr4);
}
void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4)
@@ -1206,7 +1193,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
return 1;
}
- static_call(kvm_x86_set_cr4)(vcpu, cr4);
+ kvm_x86_call(set_cr4)(vcpu, cr4);
kvm_post_set_cr4(vcpu, old_cr4, cr4);
@@ -1345,7 +1332,7 @@ void kvm_update_dr7(struct kvm_vcpu *vcpu)
dr7 = vcpu->arch.guest_debug_dr7;
else
dr7 = vcpu->arch.dr7;
- static_call(kvm_x86_set_dr7)(vcpu, dr7);
+ kvm_x86_call(set_dr7)(vcpu, dr7);
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED;
if (dr7 & DR7_BP_EN_MASK)
vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED;
@@ -1461,10 +1448,10 @@ static const u32 msrs_to_save_pmu[] = {
MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
- MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
+ MSR_CORE_PERF_GLOBAL_CTRL,
MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
- /* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */
+ /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */
MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3,
MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5,
@@ -1477,7 +1464,7 @@ static const u32 msrs_to_save_pmu[] = {
MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
- /* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */
+ /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */
MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
@@ -1619,7 +1606,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
static u64 kvm_get_arch_capabilities(void)
{
- u64 data = host_arch_capabilities & KVM_SUPPORTED_ARCH_CAP;
+ u64 data = kvm_host.arch_capabilities & KVM_SUPPORTED_ARCH_CAP;
/*
* If nx_huge_pages is enabled, KVM's shadow paging will ensure that
@@ -1688,7 +1675,7 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
rdmsrl_safe(msr->index, &msr->data);
break;
default:
- return static_call(kvm_x86_get_msr_feature)(msr);
+ return kvm_x86_call(get_msr_feature)(msr);
}
return 0;
}
@@ -1762,7 +1749,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
efer &= ~EFER_LMA;
efer |= vcpu->arch.efer & EFER_LMA;
- r = static_call(kvm_x86_set_efer)(vcpu, efer);
+ r = kvm_x86_call(set_efer)(vcpu, efer);
if (r) {
WARN_ON(r > 0);
return r;
@@ -1877,11 +1864,11 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
* incomplete and conflicting architectural behavior. Current
* AMD CPUs completely ignore bits 63:32, i.e. they aren't
* reserved and always read as zeros. Enforce Intel's reserved
- * bits check if and only if the guest CPU is Intel, and clear
- * the bits in all other cases. This ensures cross-vendor
- * migration will provide consistent behavior for the guest.
+ * bits check if the guest CPU is Intel compatible, otherwise
+ * clear the bits. This ensures cross-vendor migration will
+ * provide consistent behavior for the guest.
*/
- if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0)
+ if (guest_cpuid_is_intel_compatible(vcpu) && (data >> 32) != 0)
return 1;
data = (u32)data;
@@ -1892,7 +1879,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
msr.index = index;
msr.host_initiated = host_initiated;
- return static_call(kvm_x86_set_msr)(vcpu, &msr);
+ return kvm_x86_call(set_msr)(vcpu, &msr);
}
static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
@@ -1934,7 +1921,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
msr.index = index;
msr.host_initiated = host_initiated;
- ret = static_call(kvm_x86_get_msr)(vcpu, &msr);
+ ret = kvm_x86_call(get_msr)(vcpu, &msr);
if (!ret)
*data = msr.data;
return ret;
@@ -2002,7 +1989,7 @@ static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
static int complete_fast_msr_access(struct kvm_vcpu *vcpu)
{
- return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error);
+ return kvm_x86_call(complete_emulated_msr)(vcpu, vcpu->run->msr.error);
}
static int complete_fast_rdmsr(struct kvm_vcpu *vcpu)
@@ -2066,7 +2053,7 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
trace_kvm_msr_read_ex(ecx);
}
- return static_call(kvm_x86_complete_emulated_msr)(vcpu, r);
+ return kvm_x86_call(complete_emulated_msr)(vcpu, r);
}
EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr);
@@ -2091,7 +2078,7 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
trace_kvm_msr_write_ex(ecx, data);
}
- return static_call(kvm_x86_complete_emulated_msr)(vcpu, r);
+ return kvm_x86_call(complete_emulated_msr)(vcpu, r);
}
EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
@@ -2616,12 +2603,12 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset)
if (is_guest_mode(vcpu))
vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset(
l1_offset,
- static_call(kvm_x86_get_l2_tsc_offset)(vcpu),
- static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu));
+ kvm_x86_call(get_l2_tsc_offset)(vcpu),
+ kvm_x86_call(get_l2_tsc_multiplier)(vcpu));
else
vcpu->arch.tsc_offset = l1_offset;
- static_call(kvm_x86_write_tsc_offset)(vcpu);
+ kvm_x86_call(write_tsc_offset)(vcpu);
}
static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier)
@@ -2632,12 +2619,12 @@ static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multipli
if (is_guest_mode(vcpu))
vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier(
l1_multiplier,
- static_call(kvm_x86_get_l2_tsc_multiplier)(vcpu));
+ kvm_x86_call(get_l2_tsc_multiplier)(vcpu));
else
vcpu->arch.tsc_scaling_ratio = l1_multiplier;
if (kvm_caps.has_tsc_control)
- static_call(kvm_x86_write_tsc_multiplier)(vcpu);
+ kvm_x86_call(write_tsc_multiplier)(vcpu);
}
static inline bool kvm_check_tsc_unstable(void)
@@ -3610,7 +3597,7 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu)
static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu)
{
++vcpu->stat.tlb_flush;
- static_call(kvm_x86_flush_tlb_all)(vcpu);
+ kvm_x86_call(flush_tlb_all)(vcpu);
/* Flushing all ASIDs flushes the current ASID... */
kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
@@ -3631,7 +3618,7 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
kvm_mmu_sync_prev_roots(vcpu);
}
- static_call(kvm_x86_flush_tlb_guest)(vcpu);
+ kvm_x86_call(flush_tlb_guest)(vcpu);
/*
* Flushing all "guest" TLB is always a superset of Hyper-V's fine
@@ -3644,7 +3631,7 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
{
++vcpu->stat.tlb_flush;
- static_call(kvm_x86_flush_tlb_current)(vcpu);
+ kvm_x86_call(flush_tlb_current)(vcpu);
}
/*
@@ -4703,8 +4690,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
case KVM_CAP_IRQFD_RESAMPLE:
case KVM_CAP_MEMORY_FAULT_INFO:
+ case KVM_CAP_X86_GUEST_MODE:
r = 1;
break;
+ case KVM_CAP_PRE_FAULT_MEMORY:
+ r = tdp_enabled;
+ break;
+ case KVM_CAP_X86_APIC_BUS_CYCLES_NS:
+ r = APIC_BUS_CYCLE_NS_DEFAULT;
+ break;
case KVM_CAP_EXIT_HYPERCALL:
r = KVM_EXIT_HYPERCALL_VALID_MASK;
break;
@@ -4753,7 +4747,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
* fringe case that is not enabled except via specific settings
* of the module parameters.
*/
- r = static_call(kvm_x86_has_emulated_msr)(kvm, MSR_IA32_SMBASE);
+ r = kvm_x86_call(has_emulated_msr)(kvm, MSR_IA32_SMBASE);
break;
case KVM_CAP_NR_VCPUS:
r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
@@ -4833,7 +4827,7 @@ static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val)
{
if (attr->group) {
if (kvm_x86_ops.dev_get_attr)
- return static_call(kvm_x86_dev_get_attr)(attr->group, attr->attr, val);
+ return kvm_x86_call(dev_get_attr)(attr->group, attr->attr, val);
return -ENXIO;
}
@@ -4995,16 +4989,25 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+ vcpu->arch.l1tf_flush_l1d = true;
+
+ if (vcpu->scheduled_out && pmu->version && pmu->event_count) {
+ pmu->need_cleanup = true;
+ kvm_make_request(KVM_REQ_PMU, vcpu);
+ }
+
/* Address WBINVD may be executed by guest */
if (need_emulate_wbinvd(vcpu)) {
- if (static_call(kvm_x86_has_wbinvd_exit)())
+ if (kvm_x86_call(has_wbinvd_exit)())
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
else if (vcpu->cpu != -1 && vcpu->cpu != cpu)
smp_call_function_single(vcpu->cpu,
wbinvd_ipi, NULL, 1);
}
- static_call(kvm_x86_vcpu_load)(vcpu, cpu);
+ kvm_x86_call(vcpu_load)(vcpu, cpu);
/* Save host pkru register if supported */
vcpu->arch.host_pkru = read_pkru();
@@ -5112,14 +5115,14 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
srcu_read_unlock(&vcpu->kvm->srcu, idx);
}
- static_call(kvm_x86_vcpu_put)(vcpu);
+ kvm_x86_call(vcpu_put)(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
- static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+ kvm_x86_call(sync_pir_to_irr)(vcpu);
return kvm_apic_get_state(vcpu, s);
}
@@ -5236,7 +5239,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
kvm_apic_after_set_mcg_cap(vcpu);
- static_call(kvm_x86_setup_mce)(vcpu);
+ kvm_x86_call(setup_mce)(vcpu);
out:
return r;
}
@@ -5396,11 +5399,11 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->interrupt.injected =
vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
events->interrupt.nr = vcpu->arch.interrupt.nr;
- events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+ events->interrupt.shadow = kvm_x86_call(get_interrupt_shadow)(vcpu);
events->nmi.injected = vcpu->arch.nmi_injected;
events->nmi.pending = kvm_get_nr_pending_nmis(vcpu);
- events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu);
+ events->nmi.masked = kvm_x86_call(get_nmi_mask)(vcpu);
/* events->sipi_vector is never valid when reporting to user space */
@@ -5482,8 +5485,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.interrupt.nr = events->interrupt.nr;
vcpu->arch.interrupt.soft = events->interrupt.soft;
if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
- static_call(kvm_x86_set_interrupt_shadow)(vcpu,
- events->interrupt.shadow);
+ kvm_x86_call(set_interrupt_shadow)(vcpu,
+ events->interrupt.shadow);
vcpu->arch.nmi_injected = events->nmi.injected;
if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
@@ -5492,7 +5495,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
if (events->nmi.pending)
kvm_make_request(KVM_REQ_NMI, vcpu);
}
- static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);
+ kvm_x86_call(set_nmi_mask)(vcpu, events->nmi.masked);
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR &&
lapic_in_kernel(vcpu))
@@ -5840,7 +5843,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
if (!kvm_x86_ops.enable_l2_tlb_flush)
return -ENOTTY;
- return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu);
+ return kvm_x86_call(enable_l2_tlb_flush)(vcpu);
case KVM_CAP_HYPERV_ENFORCE_CPUID:
return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]);
@@ -5879,8 +5882,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EINVAL;
if (!lapic_in_kernel(vcpu))
goto out;
- u.lapic = kzalloc(sizeof(struct kvm_lapic_state),
- GFP_KERNEL_ACCOUNT);
+ u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
r = -ENOMEM;
if (!u.lapic)
@@ -6073,7 +6075,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave))
break;
- u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT);
+ u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
r = -ENOMEM;
if (!u.xsave)
break;
@@ -6104,7 +6106,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
case KVM_GET_XSAVE2: {
int size = vcpu->arch.guest_fpu.uabi_size;
- u.xsave = kzalloc(size, GFP_KERNEL_ACCOUNT);
+ u.xsave = kzalloc(size, GFP_KERNEL);
r = -ENOMEM;
if (!u.xsave)
break;
@@ -6122,7 +6124,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
}
case KVM_GET_XCRS: {
- u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT);
+ u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
r = -ENOMEM;
if (!u.xcrs)
break;
@@ -6330,14 +6332,14 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr)
if (addr > (unsigned int)(-3 * PAGE_SIZE))
return -EINVAL;
- ret = static_call(kvm_x86_set_tss_addr)(kvm, addr);
+ ret = kvm_x86_call(set_tss_addr)(kvm, addr);
return ret;
}
static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
u64 ident_addr)
{
- return static_call(kvm_x86_set_identity_map_addr)(kvm, ident_addr);
+ return kvm_x86_call(set_identity_map_addr)(kvm, ident_addr);
}
static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
@@ -6543,9 +6545,6 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
goto split_irqchip_unlock;
if (kvm->created_vcpus)
goto split_irqchip_unlock;
- r = kvm_setup_empty_irq_routing(kvm);
- if (r)
- goto split_irqchip_unlock;
/* Pairs with irqchip_in_kernel. */
smp_wmb();
kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
@@ -6650,14 +6649,14 @@ split_irqchip_unlock:
if (!kvm_x86_ops.vm_copy_enc_context_from)
break;
- r = static_call(kvm_x86_vm_copy_enc_context_from)(kvm, cap->args[0]);
+ r = kvm_x86_call(vm_copy_enc_context_from)(kvm, cap->args[0]);
break;
case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
r = -EINVAL;
if (!kvm_x86_ops.vm_move_enc_context_from)
break;
- r = static_call(kvm_x86_vm_move_enc_context_from)(kvm, cap->args[0]);
+ r = kvm_x86_call(vm_move_enc_context_from)(kvm, cap->args[0]);
break;
case KVM_CAP_EXIT_HYPERCALL:
if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) {
@@ -6692,7 +6691,9 @@ split_irqchip_unlock:
break;
mutex_lock(&kvm->lock);
- if (kvm->arch.max_vcpu_ids == cap->args[0]) {
+ if (kvm->arch.bsp_vcpu_id > cap->args[0]) {
+ ;
+ } else if (kvm->arch.max_vcpu_ids == cap->args[0]) {
r = 0;
} else if (!kvm->arch.max_vcpu_ids) {
kvm->arch.max_vcpu_ids = cap->args[0];
@@ -6745,6 +6746,30 @@ split_irqchip_unlock:
}
mutex_unlock(&kvm->lock);
break;
+ case KVM_CAP_X86_APIC_BUS_CYCLES_NS: {
+ u64 bus_cycle_ns = cap->args[0];
+ u64 unused;
+
+ /*
+ * Guard against overflow in tmict_to_ns(). 128 is the highest
+ * divide value that can be programmed in APIC_TDCR.
+ */
+ r = -EINVAL;
+ if (!bus_cycle_ns ||
+ check_mul_overflow((u64)U32_MAX * 128, bus_cycle_ns, &unused))
+ break;
+
+ r = 0;
+ mutex_lock(&kvm->lock);
+ if (!irqchip_in_kernel(kvm))
+ r = -ENXIO;
+ else if (kvm->created_vcpus)
+ r = -EINVAL;
+ else
+ kvm->arch.apic_bus_cycle_ns = bus_cycle_ns;
+ mutex_unlock(&kvm->lock);
+ break;
+ }
default:
r = -EINVAL;
break;
@@ -7213,6 +7238,9 @@ set_pit2_out:
mutex_lock(&kvm->lock);
if (kvm->created_vcpus)
r = -EBUSY;
+ else if (arg > KVM_MAX_VCPU_IDS ||
+ (kvm->arch.max_vcpu_ids && arg > kvm->arch.max_vcpu_ids))
+ r = -EINVAL;
else
kvm->arch.bsp_vcpu_id = arg;
mutex_unlock(&kvm->lock);
@@ -7289,7 +7317,7 @@ set_pit2_out:
if (!kvm_x86_ops.mem_enc_ioctl)
goto out;
- r = static_call(kvm_x86_mem_enc_ioctl)(kvm, argp);
+ r = kvm_x86_call(mem_enc_ioctl)(kvm, argp);
break;
}
case KVM_MEMORY_ENCRYPT_REG_REGION: {
@@ -7303,7 +7331,7 @@ set_pit2_out:
if (!kvm_x86_ops.mem_enc_register_region)
goto out;
- r = static_call(kvm_x86_mem_enc_register_region)(kvm, &region);
+ r = kvm_x86_call(mem_enc_register_region)(kvm, &region);
break;
}
case KVM_MEMORY_ENCRYPT_UNREG_REGION: {
@@ -7317,7 +7345,7 @@ set_pit2_out:
if (!kvm_x86_ops.mem_enc_unregister_region)
goto out;
- r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, &region);
+ r = kvm_x86_call(mem_enc_unregister_region)(kvm, &region);
break;
}
#ifdef CONFIG_KVM_HYPERV
@@ -7411,17 +7439,20 @@ static void kvm_probe_msr_to_save(u32 msr_index)
intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2))
return;
break;
- case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX:
+ case MSR_ARCH_PERFMON_PERFCTR0 ...
+ MSR_ARCH_PERFMON_PERFCTR0 + KVM_MAX_NR_GP_COUNTERS - 1:
if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >=
kvm_pmu_cap.num_counters_gp)
return;
break;
- case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX:
+ case MSR_ARCH_PERFMON_EVENTSEL0 ...
+ MSR_ARCH_PERFMON_EVENTSEL0 + KVM_MAX_NR_GP_COUNTERS - 1:
if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >=
kvm_pmu_cap.num_counters_gp)
return;
break;
- case MSR_ARCH_PERFMON_FIXED_CTR0 ... MSR_ARCH_PERFMON_FIXED_CTR_MAX:
+ case MSR_ARCH_PERFMON_FIXED_CTR0 ...
+ MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_MAX_NR_FIXED_COUNTERS - 1:
if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >=
kvm_pmu_cap.num_counters_fixed)
return;
@@ -7452,7 +7483,7 @@ static void kvm_init_msr_lists(void)
{
unsigned i;
- BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3,
+ BUILD_BUG_ON_MSG(KVM_MAX_NR_FIXED_COUNTERS != 3,
"Please update the fixed PMCs in msrs_to_save_pmu[]");
num_msrs_to_save = 0;
@@ -7468,7 +7499,8 @@ static void kvm_init_msr_lists(void)
}
for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
- if (!static_call(kvm_x86_has_emulated_msr)(NULL, emulated_msrs_all[i]))
+ if (!kvm_x86_call(has_emulated_msr)(NULL,
+ emulated_msrs_all[i]))
continue;
emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
@@ -7527,13 +7559,13 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
void kvm_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
- static_call(kvm_x86_set_segment)(vcpu, var, seg);
+ kvm_x86_call(set_segment)(vcpu, var, seg);
}
void kvm_get_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
- static_call(kvm_x86_get_segment)(vcpu, var, seg);
+ kvm_x86_call(get_segment)(vcpu, var, seg);
}
gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access,
@@ -7556,7 +7588,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
}
EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read);
@@ -7566,7 +7598,7 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
access |= PFERR_WRITE_MASK;
return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
}
@@ -7619,7 +7651,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
unsigned offset;
int ret;
@@ -7644,7 +7676,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception)
{
- u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
/*
* FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
@@ -7667,7 +7699,7 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
if (system)
access |= PFERR_IMPLICIT_ACCESS;
- else if (static_call(kvm_x86_get_cpl)(vcpu) == 3)
+ else if (kvm_x86_call(get_cpl)(vcpu) == 3)
access |= PFERR_USER_MASK;
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
@@ -7712,7 +7744,7 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v
if (system)
access |= PFERR_IMPLICIT_ACCESS;
- else if (static_call(kvm_x86_get_cpl)(vcpu) == 3)
+ else if (kvm_x86_call(get_cpl)(vcpu) == 3)
access |= PFERR_USER_MASK;
return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
@@ -7733,8 +7765,8 @@ EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type,
void *insn, int insn_len)
{
- return static_call(kvm_x86_check_emulate_instruction)(vcpu, emul_type,
- insn, insn_len);
+ return kvm_x86_call(check_emulate_instruction)(vcpu, emul_type,
+ insn, insn_len);
}
int handle_ud(struct kvm_vcpu *vcpu)
@@ -7784,8 +7816,8 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
bool write)
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u64 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0)
- | (write ? PFERR_WRITE_MASK : 0);
+ u64 access = ((kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0)
+ | (write ? PFERR_WRITE_MASK : 0);
/*
* currently PKRU is only applied to ept enabled guest so
@@ -8211,7 +8243,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
- return static_call(kvm_x86_get_segment_base)(vcpu, seg);
+ return kvm_x86_call(get_segment_base)(vcpu, seg);
}
static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address)
@@ -8224,7 +8256,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
if (!need_emulate_wbinvd(vcpu))
return X86EMUL_CONTINUE;
- if (static_call(kvm_x86_has_wbinvd_exit)()) {
+ if (kvm_x86_call(has_wbinvd_exit)()) {
int cpu = get_cpu();
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
@@ -8328,27 +8360,27 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val)
static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
{
- return static_call(kvm_x86_get_cpl)(emul_to_vcpu(ctxt));
+ return kvm_x86_call(get_cpl)(emul_to_vcpu(ctxt));
}
static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
- static_call(kvm_x86_get_gdt)(emul_to_vcpu(ctxt), dt);
+ kvm_x86_call(get_gdt)(emul_to_vcpu(ctxt), dt);
}
static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
- static_call(kvm_x86_get_idt)(emul_to_vcpu(ctxt), dt);
+ kvm_x86_call(get_idt)(emul_to_vcpu(ctxt), dt);
}
static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
- static_call(kvm_x86_set_gdt)(emul_to_vcpu(ctxt), dt);
+ kvm_x86_call(set_gdt)(emul_to_vcpu(ctxt), dt);
}
static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt)
{
- static_call(kvm_x86_set_idt)(emul_to_vcpu(ctxt), dt);
+ kvm_x86_call(set_idt)(emul_to_vcpu(ctxt), dt);
}
static unsigned long emulator_get_cached_segment_base(
@@ -8495,8 +8527,8 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
struct x86_instruction_info *info,
enum x86_intercept_stage stage)
{
- return static_call(kvm_x86_check_intercept)(emul_to_vcpu(ctxt), info, stage,
- &ctxt->exception);
+ return kvm_x86_call(check_intercept)(emul_to_vcpu(ctxt), info, stage,
+ &ctxt->exception);
}
static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
@@ -8521,6 +8553,11 @@ static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt)
return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID);
}
+static bool emulator_guest_cpuid_is_intel_compatible(struct x86_emulate_ctxt *ctxt)
+{
+ return guest_cpuid_is_intel_compatible(emul_to_vcpu(ctxt));
+}
+
static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
{
return kvm_register_read_raw(emul_to_vcpu(ctxt), reg);
@@ -8533,7 +8570,7 @@ static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulon
static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
{
- static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked);
+ kvm_x86_call(set_nmi_mask)(emul_to_vcpu(ctxt), masked);
}
static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt)
@@ -8578,7 +8615,8 @@ static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt,
if (!kvm_x86_ops.get_untagged_addr)
return addr;
- return static_call(kvm_x86_get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags);
+ return kvm_x86_call(get_untagged_addr)(emul_to_vcpu(ctxt),
+ addr, flags);
}
static const struct x86_emulate_ops emulate_ops = {
@@ -8619,6 +8657,7 @@ static const struct x86_emulate_ops emulate_ops = {
.guest_has_movbe = emulator_guest_has_movbe,
.guest_has_fxsr = emulator_guest_has_fxsr,
.guest_has_rdpid = emulator_guest_has_rdpid,
+ .guest_cpuid_is_intel_compatible = emulator_guest_cpuid_is_intel_compatible,
.set_nmi_mask = emulator_set_nmi_mask,
.is_smm = emulator_is_smm,
.is_guest_mode = emulator_is_guest_mode,
@@ -8630,7 +8669,7 @@ static const struct x86_emulate_ops emulate_ops = {
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
{
- u32 int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+ u32 int_shadow = kvm_x86_call(get_interrupt_shadow)(vcpu);
/*
* an sti; sti; sequence only disable interrupts for the first
* instruction. So, if the last instruction, be it emulated or
@@ -8641,7 +8680,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
if (int_shadow & mask)
mask = 0;
if (unlikely(int_shadow || mask)) {
- static_call(kvm_x86_set_interrupt_shadow)(vcpu, mask);
+ kvm_x86_call(set_interrupt_shadow)(vcpu, mask);
if (!mask)
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
@@ -8682,7 +8721,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
int cs_db, cs_l;
- static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
+ kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
ctxt->gpa_available = false;
ctxt->eflags = kvm_get_rflags(vcpu);
@@ -8738,9 +8777,8 @@ static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data,
*/
memset(&info, 0, sizeof(info));
- static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1],
- &info[2], (u32 *)&info[3],
- (u32 *)&info[4]);
+ kvm_x86_call(get_exit_info)(vcpu, (u32 *)&info[0], &info[1], &info[2],
+ (u32 *)&info[3], (u32 *)&info[4]);
run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION;
@@ -8817,7 +8855,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
kvm_queue_exception(vcpu, UD_VECTOR);
- if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) {
+ if (!is_guest_mode(vcpu) && kvm_x86_call(get_cpl)(vcpu) == 0) {
prepare_emulation_ctxt_failure_exit(vcpu);
return 0;
}
@@ -8975,10 +9013,10 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu)
int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
- unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);
+ unsigned long rflags = kvm_x86_call(get_rflags)(vcpu);
int r;
- r = static_call(kvm_x86_skip_emulated_instruction)(vcpu);
+ r = kvm_x86_call(skip_emulated_instruction)(vcpu);
if (unlikely(!r))
return 0;
@@ -9000,19 +9038,17 @@ EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu)
{
- u32 shadow;
-
if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF)
return true;
/*
- * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active,
- * but AMD CPUs do not. MOV/POP SS blocking is rare, check that first
- * to avoid the relatively expensive CPUID lookup.
+ * Intel compatible CPUs inhibit code #DBs when MOV/POP SS blocking is
+ * active, but AMD compatible CPUs do not.
*/
- shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
- return (shadow & KVM_X86_SHADOW_INT_MOV_SS) &&
- guest_cpuid_is_intel(vcpu);
+ if (!guest_cpuid_is_intel_compatible(vcpu))
+ return false;
+
+ return kvm_x86_call(get_interrupt_shadow)(vcpu) & KVM_X86_SHADOW_INT_MOV_SS;
}
static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu,
@@ -9284,7 +9320,7 @@ restart:
writeback:
if (writeback) {
- unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);
+ unsigned long rflags = kvm_x86_call(get_rflags)(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
@@ -9301,7 +9337,7 @@ writeback:
kvm_rip_write(vcpu, ctxt->eip);
if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
r = kvm_vcpu_do_singlestep(vcpu);
- static_call_cond(kvm_x86_update_emulated_instruction)(vcpu);
+ kvm_x86_call(update_emulated_instruction)(vcpu);
__kvm_set_rflags(vcpu, ctxt->eflags);
}
@@ -9700,7 +9736,7 @@ static int kvm_x86_check_processor_compatibility(void)
__cr4_reserved_bits(cpu_has, &boot_cpu_data))
return -EIO;
- return static_call(kvm_x86_check_processor_compatibility)();
+ return kvm_x86_call(check_processor_compatibility)();
}
static void kvm_x86_check_cpu_compat(void *ret)
@@ -9772,19 +9808,19 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P;
if (boot_cpu_has(X86_FEATURE_XSAVE)) {
- host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0;
+ kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+ kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
}
- rdmsrl_safe(MSR_EFER, &host_efer);
+ rdmsrl_safe(MSR_EFER, &kvm_host.efer);
if (boot_cpu_has(X86_FEATURE_XSAVES))
- rdmsrl(MSR_IA32_XSS, host_xss);
+ rdmsrl(MSR_IA32_XSS, kvm_host.xss);
kvm_init_pmu_capability(ops->pmu_ops);
if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
- rdmsrl(MSR_IA32_ARCH_CAPABILITIES, host_arch_capabilities);
+ rdmsrl(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
r = ops->hardware_setup();
if (r != 0)
@@ -9843,7 +9879,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
out_unwind_ops:
kvm_x86_ops.hardware_enable = NULL;
- static_call(kvm_x86_hardware_unsetup)();
+ kvm_x86_call(hardware_unsetup)();
out_mmu_exit:
kvm_mmu_vendor_module_exit();
out_free_percpu:
@@ -9874,7 +9910,7 @@ void kvm_x86_vendor_exit(void)
irq_work_sync(&pvclock_irq_work);
cancel_work_sync(&pvclock_gtod_work);
#endif
- static_call(kvm_x86_hardware_unsetup)();
+ kvm_x86_call(hardware_unsetup)();
kvm_mmu_vendor_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
@@ -10000,7 +10036,8 @@ EXPORT_SYMBOL_GPL(kvm_apicv_activated);
bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu)
{
ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons);
- ulong vcpu_reasons = static_call(kvm_x86_vcpu_get_apicv_inhibit_reasons)(vcpu);
+ ulong vcpu_reasons =
+ kvm_x86_call(vcpu_get_apicv_inhibit_reasons)(vcpu);
return (vm_reasons | vcpu_reasons) == 0;
}
@@ -10009,6 +10046,10 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_apicv_activated);
static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
enum kvm_apicv_inhibit reason, bool set)
{
+ const struct trace_print_flags apicv_inhibits[] = { APICV_INHIBIT_REASONS };
+
+ BUILD_BUG_ON(ARRAY_SIZE(apicv_inhibits) != NR_APICV_INHIBIT_REASONS);
+
if (set)
__set_bit(reason, inhibits);
else
@@ -10020,7 +10061,7 @@ static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
static void kvm_apicv_init(struct kvm *kvm)
{
enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT :
- APICV_INHIBIT_REASON_DISABLE;
+ APICV_INHIBIT_REASON_DISABLED;
set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true);
@@ -10182,7 +10223,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
a2 = kvm_rdx_read(vcpu);
a3 = kvm_rsi_read(vcpu);
op_64_bit = is_64_bit_hypercall(vcpu);
- cpl = static_call(kvm_x86_get_cpl)(vcpu);
+ cpl = kvm_x86_call(get_cpl)(vcpu);
ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl);
if (nr == KVM_HC_MAP_GPA_RANGE && !ret)
@@ -10214,7 +10255,7 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
return X86EMUL_PROPAGATE_FAULT;
}
- static_call(kvm_x86_patch_hypercall)(vcpu, instruction);
+ kvm_x86_call(patch_hypercall)(vcpu, instruction);
return emulator_write_emulated(ctxt, rip, instruction, 3,
&ctxt->exception);
@@ -10231,7 +10272,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
{
struct kvm_run *kvm_run = vcpu->run;
- kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu);
+ kvm_run->if_flag = kvm_x86_call(get_if_flag)(vcpu);
kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
@@ -10241,6 +10282,8 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
if (is_smm(vcpu))
kvm_run->flags |= KVM_RUN_X86_SMM;
+ if (is_guest_mode(vcpu))
+ kvm_run->flags |= KVM_RUN_X86_GUEST_MODE;
}
static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -10266,7 +10309,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
tpr = kvm_lapic_get_cr8(vcpu);
- static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr);
+ kvm_x86_call(update_cr8_intercept)(vcpu, tpr, max_irr);
}
@@ -10296,7 +10339,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu)
vcpu->arch.exception.error_code,
vcpu->arch.exception.injected);
- static_call(kvm_x86_inject_exception)(vcpu);
+ kvm_x86_call(inject_exception)(vcpu);
}
/*
@@ -10382,9 +10425,9 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
else if (kvm_is_exception_pending(vcpu))
; /* see above */
else if (vcpu->arch.nmi_injected)
- static_call(kvm_x86_inject_nmi)(vcpu);
+ kvm_x86_call(inject_nmi)(vcpu);
else if (vcpu->arch.interrupt.injected)
- static_call(kvm_x86_inject_irq)(vcpu, true);
+ kvm_x86_call(inject_irq)(vcpu, true);
/*
* Exceptions that morph to VM-Exits are handled above, and pending
@@ -10469,7 +10512,8 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
*/
#ifdef CONFIG_KVM_SMM
if (vcpu->arch.smi_pending) {
- r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY;
+ r = can_inject ? kvm_x86_call(smi_allowed)(vcpu, true) :
+ -EBUSY;
if (r < 0)
goto out;
if (r) {
@@ -10478,27 +10522,29 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
enter_smm(vcpu);
can_inject = false;
} else
- static_call(kvm_x86_enable_smi_window)(vcpu);
+ kvm_x86_call(enable_smi_window)(vcpu);
}
#endif
if (vcpu->arch.nmi_pending) {
- r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY;
+ r = can_inject ? kvm_x86_call(nmi_allowed)(vcpu, true) :
+ -EBUSY;
if (r < 0)
goto out;
if (r) {
--vcpu->arch.nmi_pending;
vcpu->arch.nmi_injected = true;
- static_call(kvm_x86_inject_nmi)(vcpu);
+ kvm_x86_call(inject_nmi)(vcpu);
can_inject = false;
- WARN_ON(static_call(kvm_x86_nmi_allowed)(vcpu, true) < 0);
+ WARN_ON(kvm_x86_call(nmi_allowed)(vcpu, true) < 0);
}
if (vcpu->arch.nmi_pending)
- static_call(kvm_x86_enable_nmi_window)(vcpu);
+ kvm_x86_call(enable_nmi_window)(vcpu);
}
if (kvm_cpu_has_injectable_intr(vcpu)) {
- r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY;
+ r = can_inject ? kvm_x86_call(interrupt_allowed)(vcpu, true) :
+ -EBUSY;
if (r < 0)
goto out;
if (r) {
@@ -10506,17 +10552,17 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
if (!WARN_ON_ONCE(irq == -1)) {
kvm_queue_interrupt(vcpu, irq, false);
- static_call(kvm_x86_inject_irq)(vcpu, false);
- WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0);
+ kvm_x86_call(inject_irq)(vcpu, false);
+ WARN_ON(kvm_x86_call(interrupt_allowed)(vcpu, true) < 0);
}
}
if (kvm_cpu_has_injectable_intr(vcpu))
- static_call(kvm_x86_enable_irq_window)(vcpu);
+ kvm_x86_call(enable_irq_window)(vcpu);
}
if (is_guest_mode(vcpu) &&
kvm_x86_ops.nested_ops->has_events &&
- kvm_x86_ops.nested_ops->has_events(vcpu))
+ kvm_x86_ops.nested_ops->has_events(vcpu, true))
*req_immediate_exit = true;
/*
@@ -10557,7 +10603,7 @@ static void process_nmi(struct kvm_vcpu *vcpu)
* blocks NMIs). KVM will immediately inject one of the two NMIs, and
* will request an NMI window to handle the second NMI.
*/
- if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected)
+ if (kvm_x86_call(get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected)
limit = 1;
else
limit = 2;
@@ -10566,14 +10612,14 @@ static void process_nmi(struct kvm_vcpu *vcpu)
* Adjust the limit to account for pending virtual NMIs, which aren't
* tracked in vcpu->arch.nmi_pending.
*/
- if (static_call(kvm_x86_is_vnmi_pending)(vcpu))
+ if (kvm_x86_call(is_vnmi_pending)(vcpu))
limit--;
vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit);
if (vcpu->arch.nmi_pending &&
- (static_call(kvm_x86_set_vnmi_pending)(vcpu)))
+ (kvm_x86_call(set_vnmi_pending)(vcpu)))
vcpu->arch.nmi_pending--;
if (vcpu->arch.nmi_pending)
@@ -10584,7 +10630,7 @@ static void process_nmi(struct kvm_vcpu *vcpu)
int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu)
{
return vcpu->arch.nmi_pending +
- static_call(kvm_x86_is_vnmi_pending)(vcpu);
+ kvm_x86_call(is_vnmi_pending)(vcpu);
}
void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
@@ -10618,7 +10664,7 @@ void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
apic->apicv_active = activate;
kvm_apic_update_apicv(vcpu);
- static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu);
+ kvm_x86_call(refresh_apicv_exec_ctrl)(vcpu);
/*
* When APICv gets disabled, we may still have injected interrupts
@@ -10718,7 +10764,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
- static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+ kvm_x86_call(sync_pir_to_irr)(vcpu);
if (irqchip_split(vcpu->kvm))
kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
@@ -10743,17 +10789,17 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
bitmap_or((ulong *)eoi_exit_bitmap,
vcpu->arch.ioapic_handled_vectors,
to_hv_synic(vcpu)->vec_bitmap, 256);
- static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+ kvm_x86_call(load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
return;
}
#endif
- static_call_cond(kvm_x86_load_eoi_exitmap)(
+ kvm_x86_call(load_eoi_exitmap)(
vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
}
void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
{
- static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm);
+ kvm_x86_call(guest_memory_reclaimed)(kvm);
}
static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
@@ -10761,7 +10807,7 @@ static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
if (!lapic_in_kernel(vcpu))
return;
- static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu);
+ kvm_x86_call(set_apic_access_page_addr)(vcpu);
}
/*
@@ -10925,10 +10971,18 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
kvm_check_async_pf_completion(vcpu);
if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
- static_call(kvm_x86_msr_filter_changed)(vcpu);
+ kvm_x86_call(msr_filter_changed)(vcpu);
if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
- static_call(kvm_x86_update_cpu_dirty_logging)(vcpu);
+ kvm_x86_call(update_cpu_dirty_logging)(vcpu);
+
+ if (kvm_check_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) {
+ kvm_vcpu_reset(vcpu, true);
+ if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) {
+ r = 1;
+ goto out;
+ }
+ }
}
if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win ||
@@ -10950,7 +11004,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto out;
}
if (req_int_win)
- static_call(kvm_x86_enable_irq_window)(vcpu);
+ kvm_x86_call(enable_irq_window)(vcpu);
if (kvm_lapic_enabled(vcpu)) {
update_cr8_intercept(vcpu);
@@ -10965,7 +11019,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
preempt_disable();
- static_call(kvm_x86_prepare_switch_to_guest)(vcpu);
+ kvm_x86_call(prepare_switch_to_guest)(vcpu);
/*
* Disable IRQs before setting IN_GUEST_MODE. Posted interrupt
@@ -11001,7 +11055,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
* i.e. they can post interrupts even if APICv is temporarily disabled.
*/
if (kvm_lapic_enabled(vcpu))
- static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+ kvm_x86_call(sync_pir_to_irr)(vcpu);
if (kvm_vcpu_exit_request(vcpu)) {
vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -11045,12 +11099,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
(kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED));
- exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu, req_immediate_exit);
+ exit_fastpath = kvm_x86_call(vcpu_run)(vcpu,
+ req_immediate_exit);
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
if (kvm_lapic_enabled(vcpu))
- static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+ kvm_x86_call(sync_pir_to_irr)(vcpu);
if (unlikely(kvm_vcpu_exit_request(vcpu))) {
exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
@@ -11069,7 +11124,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
- static_call(kvm_x86_sync_dirty_debug_regs)(vcpu);
+ kvm_x86_call(sync_dirty_debug_regs)(vcpu);
kvm_update_dr0123(vcpu);
kvm_update_dr7(vcpu);
}
@@ -11098,7 +11153,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (vcpu->arch.xfd_no_write_intercept)
fpu_sync_guest_vmexit_xfd_state();
- static_call(kvm_x86_handle_exit_irqoff)(vcpu);
+ kvm_x86_call(handle_exit_irqoff)(vcpu);
if (vcpu->arch.guest_fpu.xfd_err)
wrmsrl(MSR_IA32_XFD_ERR, 0);
@@ -11131,6 +11186,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_vcpu_srcu_read_lock(vcpu);
/*
+ * Call this to ensure WC buffers in guest are evicted after each VM
+ * Exit, so that the evicted WC writes can be snooped across all cpus
+ */
+ smp_mb__after_srcu_read_lock();
+
+ /*
* Profile KVM exit RIPs:
*/
if (unlikely(prof_on == KVM_PROFILING)) {
@@ -11144,13 +11205,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (vcpu->arch.apic_attention)
kvm_lapic_sync_from_vapic(vcpu);
- r = static_call(kvm_x86_handle_exit)(vcpu, exit_fastpath);
+ r = kvm_x86_call(handle_exit)(vcpu, exit_fastpath);
return r;
cancel_injection:
if (req_immediate_exit)
kvm_make_request(KVM_REQ_EVENT, vcpu);
- static_call(kvm_x86_cancel_injection)(vcpu);
+ kvm_x86_call(cancel_injection)(vcpu);
if (unlikely(vcpu->arch.apic_attention))
kvm_lapic_sync_from_vapic(vcpu);
out:
@@ -11200,7 +11261,10 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu)
* causes a spurious wakeup from HLT).
*/
if (is_guest_mode(vcpu)) {
- if (kvm_check_nested_events(vcpu) < 0)
+ int r = kvm_check_nested_events(vcpu);
+
+ WARN_ON_ONCE(r == -EBUSY);
+ if (r < 0)
return 0;
}
@@ -11237,7 +11301,6 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
int r;
vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
- vcpu->arch.l1tf_flush_l1d = true;
for (;;) {
/*
@@ -11387,7 +11450,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
kvm_vcpu_srcu_read_lock(vcpu);
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
- if (kvm_run->immediate_exit) {
+ if (!vcpu->wants_to_run) {
r = -EINTR;
goto out;
}
@@ -11465,12 +11528,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
WARN_ON_ONCE(vcpu->mmio_needed);
}
- if (kvm_run->immediate_exit) {
+ if (!vcpu->wants_to_run) {
r = -EINTR;
goto out;
}
- r = static_call(kvm_x86_vcpu_pre_run)(vcpu);
+ r = kvm_x86_call(vcpu_pre_run)(vcpu);
if (r <= 0)
goto out;
@@ -11598,10 +11661,10 @@ static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);
- static_call(kvm_x86_get_idt)(vcpu, &dt);
+ kvm_x86_call(get_idt)(vcpu, &dt);
sregs->idt.limit = dt.size;
sregs->idt.base = dt.address;
- static_call(kvm_x86_get_gdt)(vcpu, &dt);
+ kvm_x86_call(get_gdt)(vcpu, &dt);
sregs->gdt.limit = dt.size;
sregs->gdt.base = dt.address;
@@ -11743,7 +11806,13 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason,
has_error_code, error_code);
- if (ret) {
+
+ /*
+ * Report an error userspace if MMIO is needed, as KVM doesn't support
+ * MMIO during a task switch (or any other complex operation).
+ */
+ if (ret || vcpu->mmio_needed) {
+ vcpu->mmio_needed = false;
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
@@ -11801,27 +11870,27 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs,
dt.size = sregs->idt.limit;
dt.address = sregs->idt.base;
- static_call(kvm_x86_set_idt)(vcpu, &dt);
+ kvm_x86_call(set_idt)(vcpu, &dt);
dt.size = sregs->gdt.limit;
dt.address = sregs->gdt.base;
- static_call(kvm_x86_set_gdt)(vcpu, &dt);
+ kvm_x86_call(set_gdt)(vcpu, &dt);
vcpu->arch.cr2 = sregs->cr2;
*mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
vcpu->arch.cr3 = sregs->cr3;
kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
- static_call_cond(kvm_x86_post_set_cr3)(vcpu, sregs->cr3);
+ kvm_x86_call(post_set_cr3)(vcpu, sregs->cr3);
kvm_set_cr8(vcpu, sregs->cr8);
*mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
- static_call(kvm_x86_set_efer)(vcpu, sregs->efer);
+ kvm_x86_call(set_efer)(vcpu, sregs->efer);
*mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
- static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0);
+ kvm_x86_call(set_cr0)(vcpu, sregs->cr0);
*mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
- static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4);
+ kvm_x86_call(set_cr4)(vcpu, sregs->cr4);
if (update_pdptrs) {
idx = srcu_read_lock(&vcpu->kvm->srcu);
@@ -11999,7 +12068,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
*/
kvm_set_rflags(vcpu, rflags);
- static_call(kvm_x86_update_exception_bitmap)(vcpu);
+ kvm_x86_call(update_exception_bitmap)(vcpu);
kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm);
@@ -12136,7 +12205,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
if (id >= kvm->arch.max_vcpu_ids)
return -EINVAL;
- return static_call(kvm_x86_vcpu_precreate)(kvm);
+ return kvm_x86_call(vcpu_precreate)(kvm);
}
int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
@@ -12207,14 +12276,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.hv_root_tdp = INVALID_PAGE;
#endif
- r = static_call(kvm_x86_vcpu_create)(vcpu);
+ r = kvm_x86_call(vcpu_create)(vcpu);
if (r)
goto free_guest_fpu;
vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
kvm_xen_init_vcpu(vcpu);
- kvm_vcpu_mtrr_init(vcpu);
vcpu_load(vcpu);
kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz);
kvm_vcpu_reset(vcpu, false);
@@ -12265,7 +12333,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
kvmclock_reset(vcpu);
- static_call(kvm_x86_vcpu_free)(vcpu);
+ kvm_x86_call(vcpu_free)(vcpu);
kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
@@ -12383,7 +12451,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1);
kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600);
- static_call(kvm_x86_vcpu_reset)(vcpu, init_event);
+ kvm_x86_call(vcpu_reset)(vcpu, init_event);
kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0xfff0);
@@ -12402,10 +12470,10 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
else
new_cr0 |= X86_CR0_NW | X86_CR0_CD;
- static_call(kvm_x86_set_cr0)(vcpu, new_cr0);
- static_call(kvm_x86_set_cr4)(vcpu, 0);
- static_call(kvm_x86_set_efer)(vcpu, 0);
- static_call(kvm_x86_update_exception_bitmap)(vcpu);
+ kvm_x86_call(set_cr0)(vcpu, new_cr0);
+ kvm_x86_call(set_cr4)(vcpu, 0);
+ kvm_x86_call(set_efer)(vcpu, 0);
+ kvm_x86_call(update_exception_bitmap)(vcpu);
/*
* On the standard CR0/CR4/EFER modification paths, there are several
@@ -12462,7 +12530,7 @@ int kvm_arch_hardware_enable(void)
if (ret)
return ret;
- ret = static_call(kvm_x86_hardware_enable)();
+ ret = kvm_x86_call(hardware_enable)();
if (ret != 0)
return ret;
@@ -12544,7 +12612,7 @@ int kvm_arch_hardware_enable(void)
void kvm_arch_hardware_disable(void)
{
- static_call(kvm_x86_hardware_disable)();
+ kvm_x86_call(hardware_disable)();
drop_user_return_notifiers();
}
@@ -12558,18 +12626,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
}
-void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
- struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-
- vcpu->arch.l1tf_flush_l1d = true;
- if (pmu->version && unlikely(pmu->event_count)) {
- pmu->need_cleanup = true;
- kvm_make_request(KVM_REQ_PMU, vcpu);
- }
- static_call(kvm_x86_sched_in)(vcpu, cpu);
-}
-
void kvm_arch_free_vm(struct kvm *kvm)
{
#if IS_ENABLED(CONFIG_HYPERV)
@@ -12597,7 +12653,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm_mmu_init_vm(kvm);
- ret = static_call(kvm_x86_vm_init)(kvm);
+ ret = kvm_x86_call(vm_init)(kvm);
if (ret)
goto out_uninit_mmu;
@@ -12620,6 +12676,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
kvm->arch.default_tsc_khz = max_tsc_khz ? : tsc_khz;
+ kvm->arch.apic_bus_cycle_ns = APIC_BUS_CYCLE_NS_DEFAULT;
kvm->arch.guest_can_read_msr_platform_info = true;
kvm->arch.enable_pmu = enable_pmu;
@@ -12771,7 +12828,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
mutex_unlock(&kvm->slots_lock);
}
kvm_unload_vcpu_mmus(kvm);
- static_call_cond(kvm_x86_vm_destroy)(kvm);
+ kvm_x86_call(vm_destroy)(kvm);
kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
kvm_pic_destroy(kvm);
kvm_ioapic_destroy(kvm);
@@ -13100,12 +13157,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
kvm_arch_free_memslot(kvm, old);
}
-static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
-{
- return (is_guest_mode(vcpu) &&
- static_call(kvm_x86_guest_apic_has_interrupt)(vcpu));
-}
-
static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
{
if (!list_empty_careful(&vcpu->async_pf.done))
@@ -13123,22 +13174,23 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
(vcpu->arch.nmi_pending &&
- static_call(kvm_x86_nmi_allowed)(vcpu, false)))
+ kvm_x86_call(nmi_allowed)(vcpu, false)))
return true;
#ifdef CONFIG_KVM_SMM
if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
(vcpu->arch.smi_pending &&
- static_call(kvm_x86_smi_allowed)(vcpu, false)))
+ kvm_x86_call(smi_allowed)(vcpu, false)))
return true;
#endif
if (kvm_test_request(KVM_REQ_PMI, vcpu))
return true;
- if (kvm_arch_interrupt_allowed(vcpu) &&
- (kvm_cpu_has_interrupt(vcpu) ||
- kvm_guest_apic_has_interrupt(vcpu)))
+ if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu))
+ return true;
+
+ if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu))
return true;
if (kvm_hv_has_stimer_pending(vcpu))
@@ -13146,7 +13198,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (is_guest_mode(vcpu) &&
kvm_x86_ops.nested_ops->has_events &&
- kvm_x86_ops.nested_ops->has_events(vcpu))
+ kvm_x86_ops.nested_ops->has_events(vcpu, false))
return true;
if (kvm_xen_has_pending_events(vcpu))
@@ -13163,7 +13215,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu)
{
return kvm_vcpu_apicv_active(vcpu) &&
- static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu);
+ kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu);
}
bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu)
@@ -13191,7 +13243,7 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
if (vcpu->arch.guest_state_protected)
return true;
- return static_call(kvm_x86_get_cpl)(vcpu) == 0;
+ return kvm_x86_call(get_cpl)(vcpu) == 0;
}
unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
@@ -13206,7 +13258,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
{
- return static_call(kvm_x86_interrupt_allowed)(vcpu, false);
+ return kvm_x86_call(interrupt_allowed)(vcpu, false);
}
unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu)
@@ -13232,7 +13284,7 @@ unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
{
unsigned long rflags;
- rflags = static_call(kvm_x86_get_rflags)(vcpu);
+ rflags = kvm_x86_call(get_rflags)(vcpu);
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
rflags &= ~X86_EFLAGS_TF;
return rflags;
@@ -13244,7 +13296,7 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
rflags |= X86_EFLAGS_TF;
- static_call(kvm_x86_set_rflags)(vcpu, rflags);
+ kvm_x86_call(set_rflags)(vcpu, rflags);
}
void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
@@ -13356,7 +13408,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu)
return false;
if (vcpu->arch.apf.send_user_only &&
- static_call(kvm_x86_get_cpl)(vcpu) == 0)
+ kvm_x86_call(get_cpl)(vcpu) == 0)
return false;
if (is_guest_mode(vcpu)) {
@@ -13467,7 +13519,7 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
void kvm_arch_start_assignment(struct kvm *kvm)
{
if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1)
- static_call_cond(kvm_x86_pi_start_assignment)(kvm);
+ kvm_x86_call(pi_start_assignment)(kvm);
}
EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
@@ -13486,13 +13538,13 @@ EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm)
{
/*
- * Non-coherent DMA assignment and de-assignment will affect
- * whether KVM honors guest MTRRs and cause changes in memtypes
- * in TDP.
- * So, pass %true unconditionally to indicate non-coherent DMA was,
- * or will be involved, and that zapping SPTEs might be necessary.
+ * Non-coherent DMA assignment and de-assignment may affect whether or
+ * not KVM honors guest PAT, and thus may cause changes in EPT SPTEs
+ * due to toggling the "ignore PAT" bit. Zap all SPTEs when the first
+ * (or last) non-coherent device is (un)registered to so that new SPTEs
+ * with the correct "ignore guest PAT" setting are created.
*/
- if (__kvm_mmu_honors_guest_mtrrs(true))
+ if (kvm_mmu_may_ignore_guest_pat())
kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL));
}
@@ -13530,9 +13582,8 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
irqfd->producer = prod;
kvm_arch_start_assignment(irqfd->kvm);
- ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm,
- prod->irq, irqfd->gsi, 1);
-
+ ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
+ prod->irq, irqfd->gsi, 1);
if (ret)
kvm_arch_end_assignment(irqfd->kvm);
@@ -13555,7 +13606,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
* when the irq is masked/disabled or the consumer side (KVM
* int this case doesn't want to receive the interrupts.
*/
- ret = static_call(kvm_x86_pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0);
+ ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
+ prod->irq, irqfd->gsi, 0);
if (ret)
printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
" fails: %d\n", irqfd->consumer.token, ret);
@@ -13566,7 +13618,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set)
{
- return static_call(kvm_x86_pi_update_irte)(kvm, host_irq, guest_irq, set);
+ return kvm_x86_call(pi_update_irte)(kvm, host_irq, guest_irq, set);
}
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
@@ -13589,6 +13641,24 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
+#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+bool kvm_arch_gmem_prepare_needed(struct kvm *kvm)
+{
+ return kvm->arch.vm_type == KVM_X86_SNP_VM;
+}
+
+int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
+{
+ return kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order);
+}
+#endif
+
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
+{
+ kvm_x86_call(gmem_invalidate)(start, end);
+}
+#endif
int kvm_spec_ctrl_test_value(u64 value)
{
@@ -13974,6 +14044,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault);
static int __init kvm_x86_init(void)
{
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index d80a4c6b5a38..50596f6f8320 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -33,6 +33,20 @@ struct kvm_caps {
u64 supported_perf_cap;
};
+struct kvm_host_values {
+ /*
+ * The host's raw MAXPHYADDR, i.e. the number of non-reserved physical
+ * address bits irrespective of features that repurpose legal bits,
+ * e.g. MKTME.
+ */
+ u8 maxphyaddr;
+
+ u64 efer;
+ u64 xcr0;
+ u64 xss;
+ u64 arch_capabilities;
+};
+
void kvm_spurious_fault(void);
#define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \
@@ -159,7 +173,7 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
if (!is_long_mode(vcpu))
return false;
- static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
+ kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
return cs_l;
}
@@ -311,12 +325,8 @@ int handle_ud(struct kvm_vcpu *vcpu);
void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu,
struct kvm_queued_exception *ex);
-void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
-u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
-bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
- int page_num);
bool kvm_vector_hashing_enabled(void);
void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code);
int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
@@ -325,11 +335,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
int emulation_type, void *insn, int insn_len);
fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
-extern u64 host_xcr0;
-extern u64 host_xss;
-extern u64 host_arch_capabilities;
-
extern struct kvm_caps kvm_caps;
+extern struct kvm_host_values kvm_host;
extern bool enable_pmu;
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index f65b35a05d91..622fe24da910 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -741,7 +741,7 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
} else {
void __user * hva = u64_to_user_ptr(data->u.shared_info.hva);
- if (!PAGE_ALIGNED(hva) || !access_ok(hva, PAGE_SIZE)) {
+ if (!PAGE_ALIGNED(hva)) {
r = -EINVAL;
} else if (!hva) {
kvm_gpc_deactivate(&kvm->arch.xen.shinfo_cache);
@@ -1270,7 +1270,7 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data)
instructions[0] = 0xb8;
/* vmcall / vmmcall */
- static_call(kvm_x86_patch_hypercall)(vcpu, instructions + 5);
+ kvm_x86_call(patch_hypercall)(vcpu, instructions + 5);
/* ret */
instructions[8] = 0xc3;
@@ -1650,7 +1650,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
params[5] = (u64)kvm_r9_read(vcpu);
}
#endif
- cpl = static_call(kvm_x86_get_cpl)(vcpu);
+ cpl = kvm_x86_call(get_cpl)(vcpu);
trace_kvm_xen_hypercall(cpl, input, params[0], params[1], params[2],
params[3], params[4], params[5]);
diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c
index 80570eb3c89b..384da1fdd5c6 100644
--- a/arch/x86/lib/cmdline.c
+++ b/arch/x86/lib/cmdline.c
@@ -6,8 +6,10 @@
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/ctype.h>
+
#include <asm/setup.h>
#include <asm/cmdline.h>
+#include <asm/bug.h>
static inline int myisspace(u8 c)
{
@@ -205,12 +207,18 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size,
int cmdline_find_option_bool(const char *cmdline, const char *option)
{
+ if (IS_ENABLED(CONFIG_CMDLINE_BOOL))
+ WARN_ON_ONCE(!builtin_cmdline_added);
+
return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option);
}
int cmdline_find_option(const char *cmdline, const char *option, char *buffer,
int bufsize)
{
+ if (IS_ENABLED(CONFIG_CMDLINE_BOOL))
+ WARN_ON_ONCE(!builtin_cmdline_added);
+
return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option,
buffer, bufsize);
}
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index a1cb3a4e6742..a314622aa093 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -44,21 +44,23 @@
or %rdx, %rax
.else
cmp $TASK_SIZE_MAX-\size+1, %eax
-.if \size != 8
jae .Lbad_get_user
-.else
- jae .Lbad_get_user_8
-.endif
sbb %edx, %edx /* array_index_mask_nospec() */
and %edx, %eax
.endif
.endm
+.macro UACCESS op src dst
+1: \op \src,\dst
+ _ASM_EXTABLE_UA(1b, __get_user_handle_exception)
+.endm
+
+
.text
SYM_FUNC_START(__get_user_1)
check_range size=1
ASM_STAC
-1: movzbl (%_ASM_AX),%edx
+ UACCESS movzbl (%_ASM_AX),%edx
xor %eax,%eax
ASM_CLAC
RET
@@ -68,7 +70,7 @@ EXPORT_SYMBOL(__get_user_1)
SYM_FUNC_START(__get_user_2)
check_range size=2
ASM_STAC
-2: movzwl (%_ASM_AX),%edx
+ UACCESS movzwl (%_ASM_AX),%edx
xor %eax,%eax
ASM_CLAC
RET
@@ -78,7 +80,7 @@ EXPORT_SYMBOL(__get_user_2)
SYM_FUNC_START(__get_user_4)
check_range size=4
ASM_STAC
-3: movl (%_ASM_AX),%edx
+ UACCESS movl (%_ASM_AX),%edx
xor %eax,%eax
ASM_CLAC
RET
@@ -89,10 +91,11 @@ SYM_FUNC_START(__get_user_8)
check_range size=8
ASM_STAC
#ifdef CONFIG_X86_64
-4: movq (%_ASM_AX),%rdx
+ UACCESS movq (%_ASM_AX),%rdx
#else
-4: movl (%_ASM_AX),%edx
-5: movl 4(%_ASM_AX),%ecx
+ xor %ecx,%ecx
+ UACCESS movl (%_ASM_AX),%edx
+ UACCESS movl 4(%_ASM_AX),%ecx
#endif
xor %eax,%eax
ASM_CLAC
@@ -104,7 +107,7 @@ EXPORT_SYMBOL(__get_user_8)
SYM_FUNC_START(__get_user_nocheck_1)
ASM_STAC
ASM_BARRIER_NOSPEC
-6: movzbl (%_ASM_AX),%edx
+ UACCESS movzbl (%_ASM_AX),%edx
xor %eax,%eax
ASM_CLAC
RET
@@ -114,7 +117,7 @@ EXPORT_SYMBOL(__get_user_nocheck_1)
SYM_FUNC_START(__get_user_nocheck_2)
ASM_STAC
ASM_BARRIER_NOSPEC
-7: movzwl (%_ASM_AX),%edx
+ UACCESS movzwl (%_ASM_AX),%edx
xor %eax,%eax
ASM_CLAC
RET
@@ -124,7 +127,7 @@ EXPORT_SYMBOL(__get_user_nocheck_2)
SYM_FUNC_START(__get_user_nocheck_4)
ASM_STAC
ASM_BARRIER_NOSPEC
-8: movl (%_ASM_AX),%edx
+ UACCESS movl (%_ASM_AX),%edx
xor %eax,%eax
ASM_CLAC
RET
@@ -135,10 +138,11 @@ SYM_FUNC_START(__get_user_nocheck_8)
ASM_STAC
ASM_BARRIER_NOSPEC
#ifdef CONFIG_X86_64
-9: movq (%_ASM_AX),%rdx
+ UACCESS movq (%_ASM_AX),%rdx
#else
-9: movl (%_ASM_AX),%edx
-10: movl 4(%_ASM_AX),%ecx
+ xor %ecx,%ecx
+ UACCESS movl (%_ASM_AX),%edx
+ UACCESS movl 4(%_ASM_AX),%ecx
#endif
xor %eax,%eax
ASM_CLAC
@@ -154,36 +158,3 @@ SYM_CODE_START_LOCAL(__get_user_handle_exception)
mov $(-EFAULT),%_ASM_AX
RET
SYM_CODE_END(__get_user_handle_exception)
-
-#ifdef CONFIG_X86_32
-SYM_CODE_START_LOCAL(__get_user_8_handle_exception)
- ASM_CLAC
-.Lbad_get_user_8:
- xor %edx,%edx
- xor %ecx,%ecx
- mov $(-EFAULT),%_ASM_AX
- RET
-SYM_CODE_END(__get_user_8_handle_exception)
-#endif
-
-/* get_user */
- _ASM_EXTABLE_UA(1b, __get_user_handle_exception)
- _ASM_EXTABLE_UA(2b, __get_user_handle_exception)
- _ASM_EXTABLE_UA(3b, __get_user_handle_exception)
-#ifdef CONFIG_X86_64
- _ASM_EXTABLE_UA(4b, __get_user_handle_exception)
-#else
- _ASM_EXTABLE_UA(4b, __get_user_8_handle_exception)
- _ASM_EXTABLE_UA(5b, __get_user_8_handle_exception)
-#endif
-
-/* __get_user */
- _ASM_EXTABLE_UA(6b, __get_user_handle_exception)
- _ASM_EXTABLE_UA(7b, __get_user_handle_exception)
- _ASM_EXTABLE_UA(8b, __get_user_handle_exception)
-#ifdef CONFIG_X86_64
- _ASM_EXTABLE_UA(9b, __get_user_handle_exception)
-#else
- _ASM_EXTABLE_UA(9b, __get_user_8_handle_exception)
- _ASM_EXTABLE_UA(10b, __get_user_8_handle_exception)
-#endif
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index e0411a3774d4..5eecb45d05d5 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -25,6 +25,9 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n)
static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
{
+ const void *orig_to = to;
+ const size_t orig_n = n;
+
if (unlikely(!n))
return;
@@ -39,7 +42,7 @@ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, si
}
rep_movs(to, (const void *)from, n);
/* KMSAN must treat values read from devices as initialized. */
- kmsan_unpoison_memory(to, n);
+ kmsan_unpoison_memory(orig_to, orig_n);
}
static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..c45127265f2f 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -4,6 +4,79 @@
* included by both the compressed kernel and the regular kernel.
*/
+static void free_pte(struct x86_mapping_info *info, pmd_t *pmd)
+{
+ pte_t *pte = pte_offset_kernel(pmd, 0);
+
+ info->free_pgt_page(pte, info->context);
+}
+
+static void free_pmd(struct x86_mapping_info *info, pud_t *pud)
+{
+ pmd_t *pmd = pmd_offset(pud, 0);
+ int i;
+
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ if (!pmd_present(pmd[i]))
+ continue;
+
+ if (pmd_leaf(pmd[i]))
+ continue;
+
+ free_pte(info, &pmd[i]);
+ }
+
+ info->free_pgt_page(pmd, info->context);
+}
+
+static void free_pud(struct x86_mapping_info *info, p4d_t *p4d)
+{
+ pud_t *pud = pud_offset(p4d, 0);
+ int i;
+
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ if (!pud_present(pud[i]))
+ continue;
+
+ if (pud_leaf(pud[i]))
+ continue;
+
+ free_pmd(info, &pud[i]);
+ }
+
+ info->free_pgt_page(pud, info->context);
+}
+
+static void free_p4d(struct x86_mapping_info *info, pgd_t *pgd)
+{
+ p4d_t *p4d = p4d_offset(pgd, 0);
+ int i;
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ if (!p4d_present(p4d[i]))
+ continue;
+
+ free_pud(info, &p4d[i]);
+ }
+
+ if (pgtable_l5_enabled())
+ info->free_pgt_page(p4d, info->context);
+}
+
+void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd)
+{
+ int i;
+
+ for (i = 0; i < PTRS_PER_PGD; i++) {
+ if (!pgd_present(pgd[i]))
+ continue;
+
+ free_p4d(info, &pgd[i]);
+ }
+
+ info->free_pgt_page(pgd, info->context);
+}
+
static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
unsigned long addr, unsigned long end)
{
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7e177856ee4f..d8dbeac8b206 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -469,7 +469,9 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
!e820__mapped_any(paddr & PAGE_MASK, paddr_next,
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & PAGE_MASK, paddr_next,
- E820_TYPE_RESERVED_KERN))
+ E820_TYPE_RESERVED_KERN) &&
+ !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+ E820_TYPE_ACPI))
set_pte_init(pte, __pte(0), init);
continue;
}
@@ -524,7 +526,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
!e820__mapped_any(paddr & PMD_MASK, paddr_next,
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & PMD_MASK, paddr_next,
- E820_TYPE_RESERVED_KERN))
+ E820_TYPE_RESERVED_KERN) &&
+ !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+ E820_TYPE_ACPI))
set_pmd_init(pmd, __pmd(0), init);
continue;
}
@@ -611,7 +615,9 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
!e820__mapped_any(paddr & PUD_MASK, paddr_next,
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & PUD_MASK, paddr_next,
- E820_TYPE_RESERVED_KERN))
+ E820_TYPE_RESERVED_KERN) &&
+ !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+ E820_TYPE_ACPI))
set_pud_init(pud, __pud(0), init);
continue;
}
@@ -698,7 +704,9 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
!e820__mapped_any(paddr & P4D_MASK, paddr_next,
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & P4D_MASK, paddr_next,
- E820_TYPE_RESERVED_KERN))
+ E820_TYPE_RESERVED_KERN) &&
+ !e820__mapped_any(paddr & P4D_MASK, paddr_next,
+ E820_TYPE_ACPI))
set_p4d_init(p4d, __p4d(0), init);
continue;
}
@@ -980,8 +988,6 @@ static void __meminit free_pagetable(struct page *page, int order)
/* bootmem page has reserved flag */
if (PageReserved(page)) {
- __ClearPageReserved(page);
-
magic = page->index;
if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
while (nr_pages--)
@@ -1354,18 +1360,6 @@ void __init mem_init(void)
preallocate_vmalloc_pages();
}
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask)
-{
- /*
- * More CPUs always led to greater speedups on tested systems, up to
- * all the nodes' CPUs. Use all since the system is otherwise idle
- * now.
- */
- return max_t(int, cpumask_weight(node_cpumask), 1);
-}
-#endif
-
int kernel_set_to_readonly;
void mark_rodata_ro(void)
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 422602f6039b..86a476a426c2 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -2,7 +2,7 @@
/*
* AMD Memory Encryption Support
*
- * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ * Copyright (C) 2016-2024 Advanced Micro Devices, Inc.
*
* Author: Tom Lendacky <thomas.lendacky@amd.com>
*/
@@ -283,7 +283,7 @@ static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc)
#endif
}
-static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
+static int amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
{
/*
* To maintain the security guarantees of SEV-SNP guests, make sure
@@ -292,11 +292,11 @@ static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool
if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc)
snp_set_memory_shared(vaddr, npages);
- return true;
+ return 0;
}
/* Return true unconditionally: return value doesn't matter for the SEV side */
-static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
+static int amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
{
/*
* After memory is mapped encrypted in the page table, validate it
@@ -308,7 +308,7 @@ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool e
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc);
- return true;
+ return 0;
}
static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
@@ -510,6 +510,12 @@ void __init sme_early_init(void)
*/
x86_init.resources.dmi_setup = snp_dmi_setup;
}
+
+ /*
+ * Switch the SVSM CA mapping (if active) from identity mapped to
+ * kernel mapped.
+ */
+ snp_update_svsm_ca();
}
void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 19fdfbb171ed..44f7b2ea6a07 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -662,8 +662,9 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
/*
* Lookup the page table entry for a virtual address in a specific pgd.
- * Return a pointer to the entry, the level of the mapping, and the effective
- * NX and RW bits of all page table levels.
+ * Return a pointer to the entry (or NULL if the entry does not exist),
+ * the level of the entry, and the effective NX and RW bits of all
+ * page table levels.
*/
pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
unsigned int *level, bool *nx, bool *rw)
@@ -672,13 +673,14 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
pud_t *pud;
pmd_t *pmd;
- *level = PG_LEVEL_NONE;
+ *level = PG_LEVEL_256T;
*nx = false;
*rw = true;
if (pgd_none(*pgd))
return NULL;
+ *level = PG_LEVEL_512G;
*nx |= pgd_flags(*pgd) & _PAGE_NX;
*rw &= pgd_flags(*pgd) & _PAGE_RW;
@@ -686,10 +688,10 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
if (p4d_none(*p4d))
return NULL;
- *level = PG_LEVEL_512G;
if (p4d_leaf(*p4d) || !p4d_present(*p4d))
return (pte_t *)p4d;
+ *level = PG_LEVEL_1G;
*nx |= p4d_flags(*p4d) & _PAGE_NX;
*rw &= p4d_flags(*p4d) & _PAGE_RW;
@@ -697,10 +699,10 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
if (pud_none(*pud))
return NULL;
- *level = PG_LEVEL_1G;
if (pud_leaf(*pud) || !pud_present(*pud))
return (pte_t *)pud;
+ *level = PG_LEVEL_2M;
*nx |= pud_flags(*pud) & _PAGE_NX;
*rw &= pud_flags(*pud) & _PAGE_RW;
@@ -708,15 +710,13 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
if (pmd_none(*pmd))
return NULL;
- *level = PG_LEVEL_2M;
if (pmd_leaf(*pmd) || !pmd_present(*pmd))
return (pte_t *)pmd;
+ *level = PG_LEVEL_4K;
*nx |= pmd_flags(*pmd) & _PAGE_NX;
*rw &= pmd_flags(*pmd) & _PAGE_RW;
- *level = PG_LEVEL_4K;
-
return pte_offset_kernel(pmd, address);
}
@@ -736,9 +736,8 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
* Lookup the page table entry for a virtual address. Return a pointer
* to the entry and the level of the mapping.
*
- * Note: We return pud and pmd either when the entry is marked large
- * or when the present bit is not set. Otherwise we would return a
- * pointer to a nonexisting mapping.
+ * Note: the function returns p4d, pud or pmd either when the entry is marked
+ * large or when the present bit is not set. Otherwise it returns NULL.
*/
pte_t *lookup_address(unsigned long address, unsigned int *level)
{
@@ -1120,8 +1119,8 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
lpinc = PMD_SIZE;
/*
* Clear the PSE flags if the PRESENT flag is not set
- * otherwise pmd_present/pmd_huge will return true
- * even on a non present pmd.
+ * otherwise pmd_present() will return true even on a non
+ * present pmd.
*/
if (!(pgprot_val(ref_prot) & _PAGE_PRESENT))
pgprot_val(ref_prot) &= ~_PAGE_PSE;
@@ -2196,7 +2195,8 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
/* Notify hypervisor that we are about to set/clr encryption attribute. */
- if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc))
+ ret = x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
+ if (ret)
goto vmm_fail;
ret = __change_page_attr_set_clr(&cpa, 1);
@@ -2214,24 +2214,61 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
return ret;
/* Notify hypervisor that we have successfully set/clr encryption attribute. */
- if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
+ ret = x86_platform.guest.enc_status_change_finish(addr, numpages, enc);
+ if (ret)
goto vmm_fail;
return 0;
vmm_fail:
- WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n",
- (void *)addr, numpages, enc ? "private" : "shared");
+ WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s: %d\n",
+ (void *)addr, numpages, enc ? "private" : "shared", ret);
+
+ return ret;
+}
+
+/*
+ * The lock serializes conversions between private and shared memory.
+ *
+ * It is taken for read on conversion. A write lock guarantees that no
+ * concurrent conversions are in progress.
+ */
+static DECLARE_RWSEM(mem_enc_lock);
+
+/*
+ * Stop new private<->shared conversions.
+ *
+ * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete.
+ * The lock is not released to prevent new conversions from being started.
+ */
+bool set_memory_enc_stop_conversion(void)
+{
+ /*
+ * In a crash scenario, sleep is not allowed. Try to take the lock.
+ * Failure indicates that there is a race with the conversion.
+ */
+ if (oops_in_progress)
+ return down_write_trylock(&mem_enc_lock);
+
+ down_write(&mem_enc_lock);
- return -EIO;
+ return true;
}
static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
{
- if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
- return __set_memory_enc_pgtable(addr, numpages, enc);
+ int ret = 0;
- return 0;
+ if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+ if (!down_read_trylock(&mem_enc_lock))
+ return -EBUSY;
+
+ ret = __set_memory_enc_pgtable(addr, numpages, enc);
+
+ up_read(&mem_enc_lock);
+ }
+
+ return ret;
}
int set_memory_encrypted(unsigned long addr, int numpages)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5159c7a22922..d25d81c8ecc0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1234,13 +1234,11 @@ bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
}
static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
- bool *regs_used, bool *tail_call_seen)
+ bool *regs_used)
{
int i;
for (i = 1; i <= insn_cnt; i++, insn++) {
- if (insn->code == (BPF_JMP | BPF_TAIL_CALL))
- *tail_call_seen = true;
if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6)
regs_used[0] = true;
if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7)
@@ -1324,7 +1322,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
struct bpf_insn *insn = bpf_prog->insnsi;
bool callee_regs_used[4] = {};
int insn_cnt = bpf_prog->len;
- bool tail_call_seen = false;
bool seen_exit = false;
u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
u64 arena_vm_start, user_vm_start;
@@ -1336,11 +1333,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena);
- detect_reg_usage(insn, insn_cnt, callee_regs_used,
- &tail_call_seen);
-
- /* tail call's presence in current prog implies it is reachable */
- tail_call_reachable |= tail_call_seen;
+ detect_reg_usage(insn, insn_cnt, callee_regs_used);
emit_prologue(&prog, bpf_prog->aux->stack_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
@@ -3363,7 +3356,7 @@ out_image:
*
* Both cases are serious bugs and justify WARN_ON.
*/
- if (WARN_ON(bpf_jit_binary_pack_finalize(prog, header, rw_header))) {
+ if (WARN_ON(bpf_jit_binary_pack_finalize(header, rw_header))) {
/* header has been freed */
header = NULL;
goto out_image;
@@ -3442,7 +3435,7 @@ void bpf_jit_free(struct bpf_prog *prog)
* before freeing it.
*/
if (jit_data) {
- bpf_jit_binary_pack_finalize(prog, jit_data->header,
+ bpf_jit_binary_pack_finalize(jit_data->header,
jit_data->rw_header);
kvfree(jit_data->addrs);
kfree(jit_data);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 8edd62206604..b433b1753016 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -216,7 +216,7 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
}
static const struct x86_cpu_id intel_mid_cpu_ids[] = {
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, NULL),
+ X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID, NULL),
{}
};
@@ -233,9 +233,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
return 0;
ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
- if (ret < 0) {
+ if (ret) {
dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret);
- return ret;
+ return pcibios_err_to_errno(ret);
}
id = x86_match_cpu(intel_mid_cpu_ids);
@@ -243,7 +243,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
model = id->model;
switch (model) {
- case INTEL_FAM6_ATOM_SILVERMONT_MID:
+ case VFM_MODEL(INTEL_ATOM_SILVERMONT_MID):
polarity_low = false;
/* Special treatment for IRQ0 */
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 652cd53e77f6..0f2fe524f60d 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -38,10 +38,10 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev)
u8 gsi;
rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
- if (rc < 0) {
+ if (rc) {
dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n",
rc);
- return rc;
+ return pcibios_err_to_errno(rc);
}
/* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/
pirq = gsi;
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index 6b9c6deca8ba..44c30ce6360a 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -165,14 +165,13 @@ static void punit_s2idle_check_register(struct punit_device *punit_device) {}
static void punit_s2idle_check_unregister(void) {}
#endif
-#define X86_MATCH(model, data) \
- X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
- X86_FEATURE_MWAIT, data)
+#define X86_MATCH(vfm, data) \
+ X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_MWAIT, data)
static const struct x86_cpu_id intel_punit_cpu_ids[] = {
- X86_MATCH(ATOM_SILVERMONT, &punit_device_byt),
- X86_MATCH(ATOM_SILVERMONT_MID, &punit_device_tng),
- X86_MATCH(ATOM_AIRMONT, &punit_device_cht),
+ X86_MATCH(INTEL_ATOM_SILVERMONT, &punit_device_byt),
+ X86_MATCH(INTEL_ATOM_SILVERMONT_MID, &punit_device_tng),
+ X86_MATCH(INTEL_ATOM_AIRMONT, &punit_device_cht),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids);
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index 543df9a1379d..500cab4a7f7c 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -5,5 +5,4 @@ GCOV_PROFILE := n
obj-$(CONFIG_EFI) += memmap.o quirks.o efi.o efi_$(BITS).o \
efi_stub_$(BITS).o
obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o
-obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_mem.o
obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index f090ec972d7b..88a96816de9a 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -226,8 +226,6 @@ int __init efi_memblock_x86_reserve_range(void)
if (add_efi_memmap || do_efi_soft_reserve())
do_add_efi_memmap();
- efi_fake_memmap_early();
-
WARN(efi.memmap.desc_version != 1,
"Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
efi.memmap.desc_version);
diff --git a/arch/x86/platform/efi/fake_mem.c b/arch/x86/platform/efi/fake_mem.c
deleted file mode 100644
index 41d57cad3d84..000000000000
--- a/arch/x86/platform/efi/fake_mem.c
+++ /dev/null
@@ -1,197 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * fake_mem.c
- *
- * Copyright (C) 2015 FUJITSU LIMITED
- * Author: Taku Izumi <izumi.taku@jp.fujitsu.com>
- *
- * This code introduces new boot option named "efi_fake_mem"
- * By specifying this parameter, you can add arbitrary attribute to
- * specific memory range by updating original (firmware provided) EFI
- * memmap.
- */
-
-#include <linux/kernel.h>
-#include <linux/efi.h>
-#include <linux/init.h>
-#include <linux/memblock.h>
-#include <linux/types.h>
-#include <linux/sort.h>
-#include <asm/e820/api.h>
-#include <asm/efi.h>
-
-#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
-
-static struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
-static int nr_fake_mem;
-
-static int __init cmp_fake_mem(const void *x1, const void *x2)
-{
- const struct efi_mem_range *m1 = x1;
- const struct efi_mem_range *m2 = x2;
-
- if (m1->range.start < m2->range.start)
- return -1;
- if (m1->range.start > m2->range.start)
- return 1;
- return 0;
-}
-
-static void __init efi_fake_range(struct efi_mem_range *efi_range)
-{
- struct efi_memory_map_data data = { 0 };
- int new_nr_map = efi.memmap.nr_map;
- efi_memory_desc_t *md;
- void *new_memmap;
-
- /* count up the number of EFI memory descriptor */
- for_each_efi_memory_desc(md)
- new_nr_map += efi_memmap_split_count(md, &efi_range->range);
-
- /* allocate memory for new EFI memmap */
- if (efi_memmap_alloc(new_nr_map, &data) != 0)
- return;
-
- /* create new EFI memmap */
- new_memmap = early_memremap(data.phys_map, data.size);
- if (!new_memmap) {
- __efi_memmap_free(data.phys_map, data.size, data.flags);
- return;
- }
-
- efi_memmap_insert(&efi.memmap, new_memmap, efi_range);
-
- /* swap into new EFI memmap */
- early_memunmap(new_memmap, data.size);
-
- efi_memmap_install(&data);
-}
-
-void __init efi_fake_memmap(void)
-{
- int i;
-
- if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
- return;
-
- for (i = 0; i < nr_fake_mem; i++)
- efi_fake_range(&efi_fake_mems[i]);
-
- /* print new EFI memmap */
- efi_print_memmap();
-}
-
-static int __init setup_fake_mem(char *p)
-{
- u64 start = 0, mem_size = 0, attribute = 0;
- int i;
-
- if (!p)
- return -EINVAL;
-
- while (*p != '\0') {
- mem_size = memparse(p, &p);
- if (*p == '@')
- start = memparse(p+1, &p);
- else
- break;
-
- if (*p == ':')
- attribute = simple_strtoull(p+1, &p, 0);
- else
- break;
-
- if (nr_fake_mem >= EFI_MAX_FAKEMEM)
- break;
-
- efi_fake_mems[nr_fake_mem].range.start = start;
- efi_fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
- efi_fake_mems[nr_fake_mem].attribute = attribute;
- nr_fake_mem++;
-
- if (*p == ',')
- p++;
- }
-
- sort(efi_fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
- cmp_fake_mem, NULL);
-
- for (i = 0; i < nr_fake_mem; i++)
- pr_info("efi_fake_mem: add attr=0x%016llx to [mem 0x%016llx-0x%016llx]",
- efi_fake_mems[i].attribute, efi_fake_mems[i].range.start,
- efi_fake_mems[i].range.end);
-
- return *p == '\0' ? 0 : -EINVAL;
-}
-
-early_param("efi_fake_mem", setup_fake_mem);
-
-void __init efi_fake_memmap_early(void)
-{
- int i;
-
- /*
- * The late efi_fake_mem() call can handle all requests if
- * EFI_MEMORY_SP support is disabled.
- */
- if (!efi_soft_reserve_enabled())
- return;
-
- if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
- return;
-
- /*
- * Given that efi_fake_memmap() needs to perform memblock
- * allocations it needs to run after e820__memblock_setup().
- * However, if efi_fake_mem specifies EFI_MEMORY_SP for a given
- * address range that potentially needs to mark the memory as
- * reserved prior to e820__memblock_setup(). Update e820
- * directly if EFI_MEMORY_SP is specified for an
- * EFI_CONVENTIONAL_MEMORY descriptor.
- */
- for (i = 0; i < nr_fake_mem; i++) {
- struct efi_mem_range *mem = &efi_fake_mems[i];
- efi_memory_desc_t *md;
- u64 m_start, m_end;
-
- if ((mem->attribute & EFI_MEMORY_SP) == 0)
- continue;
-
- m_start = mem->range.start;
- m_end = mem->range.end;
- for_each_efi_memory_desc(md) {
- u64 start, end, size;
-
- if (md->type != EFI_CONVENTIONAL_MEMORY)
- continue;
-
- start = md->phys_addr;
- end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
-
- if (m_start <= end && m_end >= start)
- /* fake range overlaps descriptor */;
- else
- continue;
-
- /*
- * Trim the boundary of the e820 update to the
- * descriptor in case the fake range overlaps
- * !EFI_CONVENTIONAL_MEMORY
- */
- start = max(start, m_start);
- end = min(end, m_end);
- size = end - start + 1;
-
- if (end <= start)
- continue;
-
- /*
- * Ensure each efi_fake_mem instance results in
- * a unique e820 resource
- */
- e820__range_remove(start, size, E820_TYPE_RAM, 1);
- e820__range_add(start, size, E820_TYPE_SOFT_RESERVED);
- e820__update_table(e820_table);
- }
- }
-}
diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c
index 6ed1935504b9..061b8ecc71a1 100644
--- a/arch/x86/platform/efi/memmap.c
+++ b/arch/x86/platform/efi/memmap.c
@@ -30,6 +30,7 @@ static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size)
return PFN_PHYS(page_to_pfn(p));
}
+static
void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags)
{
if (flags & EFI_MEMMAP_MEMBLOCK) {
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 7be71c2cdc83..f83bbe0acd4a 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -22,6 +22,7 @@
#include <asm/mpspec_def.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
+#include <asm/cpu_device_id.h>
#include <asm/io_apic.h>
#include <asm/intel-mid.h>
#include <asm/io.h>
@@ -55,9 +56,8 @@ static void __init intel_mid_time_init(void)
static void intel_mid_arch_setup(void)
{
- switch (boot_cpu_data.x86_model) {
- case 0x3C:
- case 0x4A:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_ATOM_SILVERMONT_MID:
x86_platform.legacy.rtc = 1;
break;
default:
diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c
index fdd49d70b437..c81cea208c2c 100644
--- a/arch/x86/platform/intel/iosf_mbi.c
+++ b/arch/x86/platform/intel/iosf_mbi.c
@@ -62,7 +62,7 @@ static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr)
fail_read:
dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
- return result;
+ return pcibios_err_to_errno(result);
}
static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr)
@@ -91,7 +91,7 @@ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr)
fail_write:
dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
- return result;
+ return pcibios_err_to_errno(result);
}
int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 89df5d89d664..51655133eee3 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -9,6 +9,10 @@
#include <linux/cache.h>
#include <asm/syscall.h>
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
+ unsigned long, unsigned long,
+ unsigned long, unsigned long);
+
/*
* Below you can see, in terms of #define's, the differences between the x86-64
* and the UML syscall table.
@@ -22,15 +26,13 @@
#define sys_vm86 sys_ni_syscall
#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native)
+#define __SYSCALL_NORETURN __SYSCALL
#define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
#include <asm/syscalls_32.h>
+#undef __SYSCALL
-#undef __SYSCALL
#define __SYSCALL(nr, sym) sym,
-
-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
#include <asm/syscalls_32.h>
};
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index b0b4cfd2308c..943d414f2109 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -9,6 +9,10 @@
#include <linux/cache.h>
#include <asm/syscall.h>
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
+ unsigned long, unsigned long,
+ unsigned long, unsigned long);
+
/*
* Below you can see, in terms of #define's, the differences between the x86-64
* and the UML syscall table.
@@ -18,14 +22,13 @@
#define sys_iopl sys_ni_syscall
#define sys_ioperm sys_ni_syscall
+#define __SYSCALL_NORETURN __SYSCALL
+
#define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
#include <asm/syscalls_64.h>
+#undef __SYSCALL
-#undef __SYSCALL
#define __SYSCALL(nr, sym) sym,
-
-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
#include <asm/syscalls_64.h>
};
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 0ae10535c699..0ce17766c0e5 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -120,7 +120,7 @@ static __init void snp_enable(void *arg)
bool snp_probe_rmptable_info(void)
{
- u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end;
+ u64 rmp_sz, rmp_base, rmp_end;
rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
rdmsrl(MSR_AMD64_RMP_END, rmp_end);
@@ -137,28 +137,11 @@ bool snp_probe_rmptable_info(void)
rmp_sz = rmp_end - rmp_base + 1;
- /*
- * Calculate the amount the memory that must be reserved by the BIOS to
- * address the whole RAM, including the bookkeeping area. The RMP itself
- * must also be covered.
- */
- max_rmp_pfn = max_pfn;
- if (PHYS_PFN(rmp_end) > max_pfn)
- max_rmp_pfn = PHYS_PFN(rmp_end);
-
- calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
-
- if (calc_rmp_sz > rmp_sz) {
- pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
- calc_rmp_sz, rmp_sz);
- return false;
- }
-
probed_rmp_base = rmp_base;
probed_rmp_size = rmp_sz;
pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n",
- probed_rmp_base, probed_rmp_base + probed_rmp_size - 1);
+ rmp_base, rmp_end);
return true;
}
@@ -206,9 +189,8 @@ void __init snp_fixup_e820_tables(void)
*/
static int __init snp_rmptable_init(void)
{
+ u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val;
void *rmptable_start;
- u64 rmptable_size;
- u64 val;
if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
@@ -219,10 +201,28 @@ static int __init snp_rmptable_init(void)
if (!probed_rmp_size)
goto nosnp;
+ rmp_end = probed_rmp_base + probed_rmp_size - 1;
+
+ /*
+ * Calculate the amount the memory that must be reserved by the BIOS to
+ * address the whole RAM, including the bookkeeping area. The RMP itself
+ * must also be covered.
+ */
+ max_rmp_pfn = max_pfn;
+ if (PFN_UP(rmp_end) > max_pfn)
+ max_rmp_pfn = PFN_UP(rmp_end);
+
+ calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
+ if (calc_rmp_sz > probed_rmp_size) {
+ pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
+ calc_rmp_sz, probed_rmp_size);
+ goto nosnp;
+ }
+
rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB);
if (!rmptable_start) {
pr_err("Failed to map RMP table\n");
- return 1;
+ goto nosnp;
}
/*
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 49a1c6890b55..4e2b2e2ac9f9 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -33,7 +33,7 @@
#include <asm/msr.h>
#include <asm/cpufeature.h>
#include <asm/tdx.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/processor.h>
#include <asm/mce.h>
#include "tdx.h"
@@ -1426,9 +1426,9 @@ static void __init check_tdx_erratum(void)
* private memory poisons that memory, and a subsequent read of
* that memory triggers #MC.
*/
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_SAPPHIRERAPIDS_X:
- case INTEL_FAM6_EMERALDRAPIDS_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_SAPPHIRERAPIDS_X:
+ case INTEL_EMERALDRAPIDS_X:
setup_force_cpu_bug(X86_BUG_TDX_PW_MCE);
}
}
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 8b045dd25196..bb0f3f368446 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -10,8 +10,6 @@
#include <xen/xen.h>
#include <xen/interface/physdev.h>
#include "xen-ops.h"
-#include "pmu.h"
-#include "smp.h"
static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
{
diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index 532410998684..b8c9f2a7d9b6 100644
--- a/arch/x86/xen/debugfs.c
+++ b/arch/x86/xen/debugfs.c
@@ -3,7 +3,7 @@
#include <linux/debugfs.h>
#include <linux/slab.h>
-#include "debugfs.h"
+#include "xen-ops.h"
static struct dentry *d_xen_debug;
diff --git a/arch/x86/xen/debugfs.h b/arch/x86/xen/debugfs.h
deleted file mode 100644
index 6b813ad1091c..000000000000
--- a/arch/x86/xen/debugfs.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_DEBUGFS_H
-#define _XEN_DEBUGFS_H
-
-struct dentry * __init xen_init_debugfs(void);
-
-#endif /* _XEN_DEBUGFS_H */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0305485edcd3..84e5adbd0925 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -20,8 +20,6 @@
#include <asm/setup.h>
#include "xen-ops.h"
-#include "smp.h"
-#include "pmu.h"
EXPORT_SYMBOL_GPL(hypercall_page);
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index c001a2296582..24d2957a4726 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -28,8 +28,6 @@
#include <asm/xen/page.h>
#include "xen-ops.h"
-#include "mmu.h"
-#include "smp.h"
static unsigned long shared_info_pfn;
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 9ba53814ed6a..2c12ae42dc8b 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -85,10 +85,6 @@
#endif
#include "xen-ops.h"
-#include "mmu.h"
-#include "smp.h"
-#include "multicalls.h"
-#include "pmu.h"
#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 60e9c37fd79f..c4c479373249 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -5,8 +5,7 @@
#include <asm/xen/hypercall.h>
#include <xen/interface/memory.h>
-#include "multicalls.h"
-#include "mmu.h"
+#include "xen-ops.h"
unsigned long arbitrary_virt_to_mfn(void *vaddr)
{
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
deleted file mode 100644
index 6e4c6bd62203..000000000000
--- a/arch/x86/xen/mmu.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_MMU_H
-
-#include <linux/linkage.h>
-#include <asm/page.h>
-
-enum pt_level {
- PT_PGD,
- PT_P4D,
- PT_PUD,
- PT_PMD,
- PT_PTE
-};
-
-
-bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-
-void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
-
-pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
-void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
- pte_t *ptep, pte_t pte);
-
-unsigned long xen_read_cr2_direct(void);
-
-extern void xen_init_mmu_ops(void);
-extern void xen_hvm_init_mmu_ops(void);
-#endif /* _XEN_MMU_H */
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index 509bdee3ab90..337955652202 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -5,7 +5,7 @@
#include <xen/interface/xen.h>
#include <xen/hvm.h>
-#include "mmu.h"
+#include "xen-ops.h"
#ifdef CONFIG_PROC_VMCORE
/*
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 54e0d311dcc9..f1ce39d6d32c 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -82,9 +82,7 @@
#include <xen/hvc-console.h>
#include <xen/swiotlb-xen.h>
-#include "multicalls.h"
-#include "mmu.h"
-#include "debugfs.h"
+#include "xen-ops.h"
/*
* Prototypes for functions called via PV_CALLEE_SAVE_REGS_THUNK() in order
@@ -128,7 +126,7 @@ static DEFINE_SPINLOCK(xen_reservation_lock);
* looking at another vcpu's cr3 value, it should use this variable.
*/
DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */
-DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */
+static DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */
static phys_addr_t xen_pt_base, xen_pt_size __initdata;
@@ -305,16 +303,17 @@ static void xen_set_pte(pte_t *ptep, pte_t pteval)
__xen_set_pte(ptep, pteval);
}
-pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep)
+static pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
{
/* Just return the pte as-is. We preserve the bits on commit */
trace_xen_mmu_ptep_modify_prot_start(vma->vm_mm, addr, ptep, *ptep);
return *ptep;
}
-void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
- pte_t *ptep, pte_t pte)
+static void xen_ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr,
+ pte_t *ptep, pte_t pte)
{
struct mmu_update u;
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 07054572297f..d4cefd8a9af4 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -23,26 +23,21 @@
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/debugfs.h>
+#include <linux/jump_label.h>
+#include <linux/printk.h>
#include <asm/xen/hypercall.h>
-#include "multicalls.h"
-#include "debugfs.h"
+#include "xen-ops.h"
#define MC_BATCH 32
-#define MC_DEBUG 0
-
#define MC_ARGS (MC_BATCH * 16)
struct mc_buffer {
unsigned mcidx, argidx, cbidx;
struct multicall_entry entries[MC_BATCH];
-#if MC_DEBUG
- struct multicall_entry debug[MC_BATCH];
- void *caller[MC_BATCH];
-#endif
unsigned char args[MC_ARGS];
struct callback {
void (*fn)(void *);
@@ -50,13 +45,98 @@ struct mc_buffer {
} callbacks[MC_BATCH];
};
+struct mc_debug_data {
+ struct multicall_entry entries[MC_BATCH];
+ void *caller[MC_BATCH];
+ size_t argsz[MC_BATCH];
+ unsigned long *args[MC_BATCH];
+};
+
static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
+static struct mc_debug_data mc_debug_data_early __initdata;
+static struct mc_debug_data __percpu *mc_debug_data __refdata =
+ &mc_debug_data_early;
DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
+static struct static_key mc_debug __ro_after_init;
+static bool mc_debug_enabled __initdata;
+
+static int __init xen_parse_mc_debug(char *arg)
+{
+ mc_debug_enabled = true;
+ static_key_slow_inc(&mc_debug);
+
+ return 0;
+}
+early_param("xen_mc_debug", xen_parse_mc_debug);
+
+static int __init mc_debug_enable(void)
+{
+ struct mc_debug_data __percpu *mcdb;
+ unsigned long flags;
+
+ if (!mc_debug_enabled)
+ return 0;
+
+ mcdb = alloc_percpu(struct mc_debug_data);
+ if (!mcdb) {
+ pr_err("xen_mc_debug inactive\n");
+ static_key_slow_dec(&mc_debug);
+ return -ENOMEM;
+ }
+
+ /* Be careful when switching to percpu debug data. */
+ local_irq_save(flags);
+ xen_mc_flush();
+ mc_debug_data = mcdb;
+ local_irq_restore(flags);
+
+ pr_info("xen_mc_debug active\n");
+
+ return 0;
+}
+early_initcall(mc_debug_enable);
+
+/* Number of parameters of hypercalls used via multicalls. */
+static const uint8_t hpcpars[] = {
+ [__HYPERVISOR_mmu_update] = 4,
+ [__HYPERVISOR_stack_switch] = 2,
+ [__HYPERVISOR_fpu_taskswitch] = 1,
+ [__HYPERVISOR_update_descriptor] = 2,
+ [__HYPERVISOR_update_va_mapping] = 3,
+ [__HYPERVISOR_mmuext_op] = 4,
+};
+
+static void print_debug_data(struct mc_buffer *b, struct mc_debug_data *mcdb,
+ int idx)
+{
+ unsigned int arg;
+ unsigned int opidx = mcdb->entries[idx].op & 0xff;
+ unsigned int pars = 0;
+
+ pr_err(" call %2d: op=%lu result=%ld caller=%pS ", idx + 1,
+ mcdb->entries[idx].op, b->entries[idx].result,
+ mcdb->caller[idx]);
+ if (opidx < ARRAY_SIZE(hpcpars))
+ pars = hpcpars[opidx];
+ if (pars) {
+ pr_cont("pars=");
+ for (arg = 0; arg < pars; arg++)
+ pr_cont("%lx ", mcdb->entries[idx].args[arg]);
+ }
+ if (mcdb->argsz[idx]) {
+ pr_cont("args=");
+ for (arg = 0; arg < mcdb->argsz[idx] / 8; arg++)
+ pr_cont("%lx ", mcdb->args[idx][arg]);
+ }
+ pr_cont("\n");
+}
+
void xen_mc_flush(void)
{
struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
struct multicall_entry *mc;
+ struct mc_debug_data *mcdb = NULL;
int ret = 0;
unsigned long flags;
int i;
@@ -69,10 +149,11 @@ void xen_mc_flush(void)
trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
-#if MC_DEBUG
- memcpy(b->debug, b->entries,
- b->mcidx * sizeof(struct multicall_entry));
-#endif
+ if (static_key_false(&mc_debug)) {
+ mcdb = this_cpu_ptr(mc_debug_data);
+ memcpy(mcdb->entries, b->entries,
+ b->mcidx * sizeof(struct multicall_entry));
+ }
switch (b->mcidx) {
case 0:
@@ -103,21 +184,14 @@ void xen_mc_flush(void)
pr_err("%d of %d multicall(s) failed: cpu %d\n",
ret, b->mcidx, smp_processor_id());
for (i = 0; i < b->mcidx; i++) {
- if (b->entries[i].result < 0) {
-#if MC_DEBUG
- pr_err(" call %2d: op=%lu arg=[%lx] result=%ld\t%pS\n",
- i + 1,
- b->debug[i].op,
- b->debug[i].args[0],
- b->entries[i].result,
- b->caller[i]);
-#else
+ if (static_key_false(&mc_debug)) {
+ print_debug_data(b, mcdb, i);
+ } else if (b->entries[i].result < 0) {
pr_err(" call %2d: op=%lu arg=[%lx] result=%ld\n",
i + 1,
b->entries[i].op,
b->entries[i].args[0],
b->entries[i].result);
-#endif
}
}
}
@@ -155,9 +229,13 @@ struct multicall_space __xen_mc_entry(size_t args)
}
ret.mc = &b->entries[b->mcidx];
-#if MC_DEBUG
- b->caller[b->mcidx] = __builtin_return_address(0);
-#endif
+ if (static_key_false(&mc_debug)) {
+ struct mc_debug_data *mcdb = this_cpu_ptr(mc_debug_data);
+
+ mcdb->caller[b->mcidx] = __builtin_return_address(0);
+ mcdb->argsz[b->mcidx] = args;
+ mcdb->args[b->mcidx] = (unsigned long *)(&b->args[argidx]);
+ }
b->mcidx++;
ret.args = &b->args[argidx];
b->argidx = argidx + args;
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
deleted file mode 100644
index c3867b585e0d..000000000000
--- a/arch/x86/xen/multicalls.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_MULTICALLS_H
-#define _XEN_MULTICALLS_H
-
-#include <trace/events/xen.h>
-
-#include "xen-ops.h"
-
-/* Multicalls */
-struct multicall_space
-{
- struct multicall_entry *mc;
- void *args;
-};
-
-/* Allocate room for a multicall and its args */
-struct multicall_space __xen_mc_entry(size_t args);
-
-DECLARE_PER_CPU(unsigned long, xen_mc_irq_flags);
-
-/* Call to start a batch of multiple __xen_mc_entry()s. Must be
- paired with xen_mc_issue() */
-static inline void xen_mc_batch(void)
-{
- unsigned long flags;
-
- /* need to disable interrupts until this entry is complete */
- local_irq_save(flags);
- trace_xen_mc_batch(xen_get_lazy_mode());
- __this_cpu_write(xen_mc_irq_flags, flags);
-}
-
-static inline struct multicall_space xen_mc_entry(size_t args)
-{
- xen_mc_batch();
- return __xen_mc_entry(args);
-}
-
-/* Flush all pending multicalls */
-void xen_mc_flush(void);
-
-/* Issue a multicall if we're not in a lazy mode */
-static inline void xen_mc_issue(unsigned mode)
-{
- trace_xen_mc_issue(mode);
-
- if ((xen_get_lazy_mode() & mode) == 0)
- xen_mc_flush();
-
- /* restore flags saved in xen_mc_batch */
- local_irq_restore(this_cpu_read(xen_mc_irq_flags));
-}
-
-/* Set up a callback to be called when the current batch is flushed */
-void xen_mc_callback(void (*fn)(void *), void *data);
-
-/*
- * Try to extend the arguments of the previous multicall command. The
- * previous command's op must match. If it does, then it attempts to
- * extend the argument space allocated to the multicall entry by
- * arg_size bytes.
- *
- * The returned multicall_space will return with mc pointing to the
- * command on success, or NULL on failure, and args pointing to the
- * newly allocated space.
- */
-struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
-
-#endif /* _XEN_MULTICALLS_H */
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 99918beccd80..7c735b730acd 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -81,7 +81,6 @@
#include <xen/balloon.h>
#include <xen/grant_table.h>
-#include "multicalls.h"
#include "xen-ops.h"
#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *))
@@ -730,7 +729,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
* immediate unmapping.
*/
map_ops[i].status = GNTST_general_error;
- unmap[0].host_addr = map_ops[i].host_addr,
+ unmap[0].host_addr = map_ops[i].host_addr;
unmap[0].handle = map_ops[i].handle;
map_ops[i].handle = INVALID_GRANT_HANDLE;
if (map_ops[i].flags & GNTMAP_device_map)
@@ -740,7 +739,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
if (kmap_ops) {
kmap_ops[i].status = GNTST_general_error;
- unmap[1].host_addr = kmap_ops[i].host_addr,
+ unmap[1].host_addr = kmap_ops[i].host_addr;
unmap[1].handle = kmap_ops[i].handle;
kmap_ops[i].handle = INVALID_GRANT_HANDLE;
if (kmap_ops[i].flags & GNTMAP_device_map)
@@ -795,7 +794,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
#ifdef CONFIG_XEN_DEBUG_FS
#include <linux/debugfs.h>
-#include "debugfs.h"
static int p2m_dump_show(struct seq_file *m, void *v)
{
static const char * const type_name[] = {
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 246d67dab510..f06987b0efc3 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -10,7 +10,6 @@
#include <xen/interface/xenpmu.h>
#include "xen-ops.h"
-#include "pmu.h"
/* x86_pmu.handle_irq definition */
#include "../events/perf_event.h"
diff --git a/arch/x86/xen/pmu.h b/arch/x86/xen/pmu.h
deleted file mode 100644
index 65c58894fc79..000000000000
--- a/arch/x86/xen/pmu.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __XEN_PMU_H
-#define __XEN_PMU_H
-
-#include <xen/interface/xenpmu.h>
-
-extern bool is_xen_pmu;
-
-irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
-#ifdef CONFIG_XEN_HAVE_VPMU
-void xen_pmu_init(int cpu);
-void xen_pmu_finish(int cpu);
-#else
-static inline void xen_pmu_init(int cpu) {}
-static inline void xen_pmu_finish(int cpu) {}
-#endif
-bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
-bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
-int pmu_apic_update(uint32_t reg);
-unsigned long long xen_read_pmc(int counter);
-
-#endif /* __XEN_PMU_H */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 380591028cb8..a0c3e77e3d5b 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -34,7 +34,6 @@
#include <xen/features.h>
#include <xen/hvc-console.h>
#include "xen-ops.h"
-#include "mmu.h"
#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 935771726f9c..05f92c812ac8 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -9,7 +9,6 @@
#include <xen/hvc-console.h>
#include "xen-ops.h"
-#include "smp.h"
static DEFINE_PER_CPU(struct xen_common_irq, xen_resched_irq) = { .irq = -1 };
static DEFINE_PER_CPU(struct xen_common_irq, xen_callfunc_irq) = { .irq = -1 };
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
deleted file mode 100644
index b8efdbc693f7..000000000000
--- a/arch/x86/xen/smp.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_SMP_H
-
-#ifdef CONFIG_SMP
-
-void asm_cpu_bringup_and_idle(void);
-asmlinkage void cpu_bringup_and_idle(void);
-
-extern void xen_send_IPI_mask(const struct cpumask *mask,
- int vector);
-extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
- int vector);
-extern void xen_send_IPI_allbutself(int vector);
-extern void xen_send_IPI_all(int vector);
-extern void xen_send_IPI_self(int vector);
-
-extern int xen_smp_intr_init(unsigned int cpu);
-extern void xen_smp_intr_free(unsigned int cpu);
-int xen_smp_intr_init_pv(unsigned int cpu);
-void xen_smp_intr_free_pv(unsigned int cpu);
-
-void xen_smp_count_cpus(void);
-void xen_smp_cpus_done(unsigned int max_cpus);
-
-void xen_smp_send_reschedule(int cpu);
-void xen_smp_send_call_function_ipi(const struct cpumask *mask);
-void xen_smp_send_call_function_single_ipi(int cpu);
-
-void __noreturn xen_cpu_bringup_again(unsigned long stack);
-
-struct xen_common_irq {
- int irq;
- char *name;
-};
-#else /* CONFIG_SMP */
-
-static inline int xen_smp_intr_init(unsigned int cpu)
-{
- return 0;
-}
-static inline void xen_smp_intr_free(unsigned int cpu) {}
-
-static inline int xen_smp_intr_init_pv(unsigned int cpu)
-{
- return 0;
-}
-static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
-static inline void xen_smp_count_cpus(void) { }
-#endif /* CONFIG_SMP */
-
-#endif
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index ac95d1981cc0..485c1d8804f7 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -5,8 +5,6 @@
#include <xen/events.h>
#include "xen-ops.h"
-#include "smp.h"
-
static void __init xen_hvm_smp_prepare_boot_cpu(void)
{
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index ac41d83b38d3..7ea57f728b89 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -46,9 +46,6 @@
#include <xen/hvc-console.h>
#include "xen-ops.h"
-#include "mmu.h"
-#include "smp.h"
-#include "pmu.h"
cpumask_var_t xen_cpu_initialized_map;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 5c6fc16e4b92..8e4efe0fb6f9 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -18,7 +18,6 @@
static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(char *, irq_name);
static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest);
-static bool xen_pvspin = true;
static void xen_qlock_kick(int cpu)
{
@@ -68,7 +67,7 @@ void xen_init_lock_cpu(int cpu)
int irq;
char *name;
- if (!xen_pvspin)
+ if (nopvspin)
return;
WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
@@ -95,7 +94,7 @@ void xen_uninit_lock_cpu(int cpu)
{
int irq;
- if (!xen_pvspin)
+ if (nopvspin)
return;
kfree(per_cpu(irq_name, cpu));
@@ -125,10 +124,10 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
void __init xen_init_spinlocks(void)
{
/* Don't need to use pvqspinlock code if there is only 1 vCPU. */
- if (num_possible_cpus() == 1 || nopvspin)
- xen_pvspin = false;
+ if (num_possible_cpus() == 1)
+ nopvspin = true;
- if (!xen_pvspin) {
+ if (nopvspin) {
printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
static_branch_disable(&virt_spin_lock_key);
return;
@@ -143,12 +142,3 @@ void __init xen_init_spinlocks(void)
pv_ops.lock.kick = xen_qlock_kick;
pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
}
-
-static __init int xen_parse_nopvspin(char *arg)
-{
- pr_notice("\"xen_nopvspin\" is deprecated, please use \"nopvspin\" instead\n");
- xen_pvspin = false;
- return 0;
-}
-early_param("xen_nopvspin", xen_parse_nopvspin);
-
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 1d83152c761b..77a6ea1c60e4 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -15,8 +15,6 @@
#include <asm/fixmap.h>
#include "xen-ops.h"
-#include "mmu.h"
-#include "pmu.h"
static DEFINE_PER_CPU(u64, spec_ctrl);
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 52fa5609b7f6..96521b1874ac 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -30,7 +30,7 @@
#include "xen-ops.h"
/* Minimum amount of time until next clock event fires */
-#define TIMER_SLOP 100000
+#define TIMER_SLOP 1
static u64 xen_sched_clock_offset __read_mostly;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 79cf93f2c92f..e7775dff9452 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -5,8 +5,15 @@
#include <linux/init.h>
#include <linux/clocksource.h>
#include <linux/irqreturn.h>
+#include <linux/linkage.h>
+
+#include <xen/interface/xenpmu.h>
#include <xen/xen-ops.h>
+#include <asm/page.h>
+
+#include <trace/events/xen.h>
+
/* These are code, but not functions. Defined in entry.S */
extern const char xen_failsafe_callback[];
@@ -23,14 +30,11 @@ void xen_copy_trap_info(struct trap_info *traps);
DECLARE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info);
DECLARE_PER_CPU(unsigned long, xen_cr3);
-DECLARE_PER_CPU(unsigned long, xen_current_cr3);
extern struct start_info *xen_start_info;
extern struct shared_info xen_dummy_shared_info;
extern struct shared_info *HYPERVISOR_shared_info;
-extern bool xen_fifo_events;
-
void xen_setup_mfn_list_list(void);
void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
@@ -177,4 +181,142 @@ static inline void xen_hvm_post_suspend(int suspend_cancelled) {}
void xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns);
+struct dentry * __init xen_init_debugfs(void);
+
+enum pt_level {
+ PT_PGD,
+ PT_P4D,
+ PT_PUD,
+ PT_PMD,
+ PT_PTE
+};
+
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
+unsigned long xen_read_cr2_direct(void);
+void xen_init_mmu_ops(void);
+void xen_hvm_init_mmu_ops(void);
+
+/* Multicalls */
+struct multicall_space
+{
+ struct multicall_entry *mc;
+ void *args;
+};
+
+/* Allocate room for a multicall and its args */
+struct multicall_space __xen_mc_entry(size_t args);
+
+DECLARE_PER_CPU(unsigned long, xen_mc_irq_flags);
+
+/* Call to start a batch of multiple __xen_mc_entry()s. Must be
+ paired with xen_mc_issue() */
+static inline void xen_mc_batch(void)
+{
+ unsigned long flags;
+
+ /* need to disable interrupts until this entry is complete */
+ local_irq_save(flags);
+ trace_xen_mc_batch(xen_get_lazy_mode());
+ __this_cpu_write(xen_mc_irq_flags, flags);
+}
+
+static inline struct multicall_space xen_mc_entry(size_t args)
+{
+ xen_mc_batch();
+ return __xen_mc_entry(args);
+}
+
+/* Flush all pending multicalls */
+void xen_mc_flush(void);
+
+/* Issue a multicall if we're not in a lazy mode */
+static inline void xen_mc_issue(unsigned mode)
+{
+ trace_xen_mc_issue(mode);
+
+ if ((xen_get_lazy_mode() & mode) == 0)
+ xen_mc_flush();
+
+ /* restore flags saved in xen_mc_batch */
+ local_irq_restore(this_cpu_read(xen_mc_irq_flags));
+}
+
+/* Set up a callback to be called when the current batch is flushed */
+void xen_mc_callback(void (*fn)(void *), void *data);
+
+/*
+ * Try to extend the arguments of the previous multicall command. The
+ * previous command's op must match. If it does, then it attempts to
+ * extend the argument space allocated to the multicall entry by
+ * arg_size bytes.
+ *
+ * The returned multicall_space will return with mc pointing to the
+ * command on success, or NULL on failure, and args pointing to the
+ * newly allocated space.
+ */
+struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
+
+extern bool is_xen_pmu;
+
+irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
+#ifdef CONFIG_XEN_HAVE_VPMU
+void xen_pmu_init(int cpu);
+void xen_pmu_finish(int cpu);
+#else
+static inline void xen_pmu_init(int cpu) {}
+static inline void xen_pmu_finish(int cpu) {}
+#endif
+bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
+bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
+int pmu_apic_update(uint32_t reg);
+unsigned long long xen_read_pmc(int counter);
+
+#ifdef CONFIG_SMP
+
+void asm_cpu_bringup_and_idle(void);
+asmlinkage void cpu_bringup_and_idle(void);
+
+extern void xen_send_IPI_mask(const struct cpumask *mask,
+ int vector);
+extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
+ int vector);
+extern void xen_send_IPI_allbutself(int vector);
+extern void xen_send_IPI_all(int vector);
+extern void xen_send_IPI_self(int vector);
+
+extern int xen_smp_intr_init(unsigned int cpu);
+extern void xen_smp_intr_free(unsigned int cpu);
+int xen_smp_intr_init_pv(unsigned int cpu);
+void xen_smp_intr_free_pv(unsigned int cpu);
+
+void xen_smp_count_cpus(void);
+void xen_smp_cpus_done(unsigned int max_cpus);
+
+void xen_smp_send_reschedule(int cpu);
+void xen_smp_send_call_function_ipi(const struct cpumask *mask);
+void xen_smp_send_call_function_single_ipi(int cpu);
+
+void __noreturn xen_cpu_bringup_again(unsigned long stack);
+
+struct xen_common_irq {
+ int irq;
+ char *name;
+};
+#else /* CONFIG_SMP */
+
+static inline int xen_smp_intr_init(unsigned int cpu)
+{
+ return 0;
+}
+static inline void xen_smp_intr_free(unsigned int cpu) {}
+
+static inline int xen_smp_intr_init_pv(unsigned int cpu)
+{
+ return 0;
+}
+static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
+static inline void xen_smp_count_cpus(void) { }
+#endif /* CONFIG_SMP */
+
#endif /* XEN_OPS_H */