summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/mman.h14
-rw-r--r--arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi2
-rw-r--r--arch/arm64/include/asm/esr.h12
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h10
-rw-r--r--arch/arm64/include/asm/kvm_host.h26
-rw-r--r--arch/arm64/include/asm/kvm_nested.h13
-rw-r--r--arch/arm64/include/asm/kvm_ptrauth.h21
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h1
-rw-r--r--arch/arm64/kernel/head.S29
-rw-r--r--arch/arm64/kernel/ptrace.c5
-rw-r--r--arch/arm64/kvm/Makefile1
-rw-r--r--arch/arm64/kvm/arm.c96
-rw-r--r--arch/arm64/kvm/emulate-nested.c66
-rw-r--r--arch/arm64/kvm/handle_exit.c36
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h62
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c4
-rw-r--r--arch/arm64/kvm/hyp/nvhe/tlb.c3
-rw-r--r--arch/arm64/kvm/hyp/pgtable.c23
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c101
-rw-r--r--arch/arm64/kvm/hyp/vhe/tlb.c3
-rw-r--r--arch/arm64/kvm/mmu.c2
-rw-r--r--arch/arm64/kvm/nested.c8
-rw-r--r--arch/arm64/kvm/pauth.c206
-rw-r--r--arch/arm64/kvm/vgic/vgic-debug.c82
-rw-r--r--arch/arm64/kvm/vgic/vgic-init.c8
-rw-r--r--arch/arm64/kvm/vgic/vgic-its.c352
-rw-r--r--arch/arm64/kvm/vgic/vgic-mmio-v3.c2
-rw-r--r--arch/arm64/kvm/vgic/vgic.c6
-rw-r--r--arch/arm64/kvm/vgic/vgic.h6
-rw-r--r--arch/arm64/net/bpf_jit_comp.c4
-rw-r--r--arch/hexagon/kernel/vmlinux.lds.S1
-rw-r--r--arch/mips/Kconfig18
-rw-r--r--arch/nios2/kernel/prom.c6
-rw-r--r--arch/parisc/include/asm/mman.h14
-rw-r--r--arch/powerpc/include/asm/vdso/gettimeofday.h3
-rw-r--r--arch/riscv/Makefile2
-rw-r--r--arch/riscv/include/asm/pgtable.h6
-rw-r--r--arch/riscv/include/asm/syscall_wrapper.h3
-rw-r--r--arch/riscv/include/asm/uaccess.h4
-rw-r--r--arch/riscv/include/uapi/asm/auxvec.h2
-rw-r--r--arch/riscv/kernel/compat_vdso/Makefile2
-rw-r--r--arch/riscv/kernel/patch.c8
-rw-r--r--arch/riscv/kernel/process.c5
-rw-r--r--arch/riscv/kernel/signal.c15
-rw-r--r--arch/riscv/kernel/traps.c2
-rw-r--r--arch/riscv/kernel/vdso/Makefile1
-rw-r--r--arch/riscv/kvm/aia_aplic.c37
-rw-r--r--arch/riscv/kvm/vcpu_onereg.c2
-rw-r--r--arch/riscv/mm/tlbflush.c4
-rw-r--r--arch/riscv/net/bpf_jit_comp64.c16
-rw-r--r--arch/s390/include/asm/atomic.h44
-rw-r--r--arch/s390/include/asm/atomic_ops.h22
-rw-r--r--arch/s390/include/asm/preempt.h36
-rw-r--r--arch/s390/kernel/entry.S1
-rw-r--r--arch/s390/kernel/perf_pai_crypto.c10
-rw-r--r--arch/s390/kernel/perf_pai_ext.c10
-rw-r--r--arch/s390/mm/fault.c2
-rw-r--r--arch/s390/net/bpf_jit_comp.c46
-rw-r--r--arch/x86/Kbuild2
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/Makefile2
-rw-r--r--arch/x86/boot/compressed/efi_mixed.S20
-rw-r--r--arch/x86/coco/core.c93
-rw-r--r--arch/x86/entry/vdso/Makefile1
-rw-r--r--arch/x86/events/amd/core.c39
-rw-r--r--arch/x86/events/amd/lbr.c16
-rw-r--r--arch/x86/events/intel/ds.c8
-rw-r--r--arch/x86/include/asm/alternative.h4
-rw-r--r--arch/x86/include/asm/asm-prototypes.h1
-rw-r--r--arch/x86/include/asm/coco.h2
-rw-r--r--arch/x86/include/asm/cpufeature.h8
-rw-r--r--arch/x86/include/asm/cpufeatures.h10
-rw-r--r--arch/x86/include/asm/crash_reserve.h2
-rw-r--r--arch/x86/include/asm/disabled-features.h3
-rw-r--r--arch/x86/include/asm/nospec-branch.h21
-rw-r--r--arch/x86/include/asm/required-features.h3
-rw-r--r--arch/x86/include/asm/sev.h8
-rw-r--r--arch/x86/include/asm/x86_init.h3
-rw-r--r--arch/x86/include/uapi/asm/kvm.h23
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h1
-rw-r--r--arch/x86/kernel/callthunks.c4
-rw-r--r--arch/x86/kernel/cpu/amd.c38
-rw-r--r--arch/x86/kernel/cpu/mce/core.c4
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h3
-rw-r--r--arch/x86/kernel/cpu/scattered.c1
-rw-r--r--arch/x86/kernel/eisa.c3
-rw-r--r--arch/x86/kernel/kvm.c11
-rw-r--r--arch/x86/kernel/nmi.c24
-rw-r--r--arch/x86/kernel/probe_roms.c10
-rw-r--r--arch/x86/kernel/setup.c5
-rw-r--r--arch/x86/kernel/sev.c37
-rw-r--r--arch/x86/kernel/x86_init.c2
-rw-r--r--arch/x86/kvm/Kconfig1
-rw-r--r--arch/x86/kvm/cpuid.c42
-rw-r--r--arch/x86/kvm/reverse_cpuid.h2
-rw-r--r--arch/x86/kvm/svm/sev.c60
-rw-r--r--arch/x86/kvm/trace.h10
-rw-r--r--arch/x86/lib/retpoline.S15
-rw-r--r--arch/x86/mm/ident_map.c23
-rw-r--r--arch/x86/mm/mem_encrypt_amd.c18
-rw-r--r--arch/x86/mm/numa_32.c1
-rw-r--r--arch/x86/mm/pat/memtype.c49
-rw-r--r--arch/x86/net/bpf_jit_comp.c19
-rw-r--r--arch/x86/virt/Makefile2
-rw-r--r--arch/x86/virt/svm/sev.c26
106 files changed, 1423 insertions, 787 deletions
diff --git a/arch/arm/include/asm/mman.h b/arch/arm/include/asm/mman.h
new file mode 100644
index 000000000000..2189e507c8e0
--- /dev/null
+++ b/arch/arm/include/asm/mman.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <asm/system_info.h>
+#include <uapi/asm/mman.h>
+
+static inline bool arch_memory_deny_write_exec_supported(void)
+{
+ return cpu_architecture() >= CPU_ARCH_ARMv6;
+}
+#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
+
+#endif /* __ASM_MMAN_H__ */
diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
index f3a6da8b2890..5260c63db007 100644
--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
@@ -944,6 +944,8 @@ ap_spi_fp: &spi10 {
vddrf-supply = <&pp1300_l2c>;
vddch0-supply = <&pp3300_l10c>;
max-speed = <3200000>;
+
+ qcom,local-bd-address-broken;
};
};
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 81606bf7d5ac..7abf09df7033 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -404,6 +404,18 @@ static inline bool esr_fsc_is_access_flag_fault(unsigned long esr)
return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS;
}
+/* Indicate whether ESR.EC==0x1A is for an ERETAx instruction */
+static inline bool esr_iss_is_eretax(unsigned long esr)
+{
+ return esr & ESR_ELx_ERET_ISS_ERET;
+}
+
+/* Indicate which key is used for ERETAx (false: A-Key, true: B-Key) */
+static inline bool esr_iss_is_eretab(unsigned long esr)
+{
+ return esr & ESR_ELx_ERET_ISS_ERETA;
+}
+
const char *esr_get_class_string(unsigned long esr);
#endif /* __ASSEMBLY */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index deaa88b972ec..501e3e019c93 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -125,16 +125,6 @@ static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
vcpu->arch.hcr_el2 |= HCR_TWI;
}
-static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu)
-{
- vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK);
-}
-
-static inline void vcpu_ptrauth_disable(struct kvm_vcpu *vcpu)
-{
- vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK);
-}
-
static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu)
{
return vcpu->arch.vsesr_el2;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 0e6c186a6d6c..23a117cb3e50 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -829,8 +829,6 @@ struct kvm_vcpu_arch {
#define DEBUG_STATE_SAVE_SPE __vcpu_single_flag(iflags, BIT(5))
/* Save TRBE context if active */
#define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6))
-/* vcpu running in HYP context */
-#define VCPU_HYP_CONTEXT __vcpu_single_flag(iflags, BIT(7))
/* SVE enabled for host EL0 */
#define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0))
@@ -908,7 +906,7 @@ struct kvm_vcpu_arch {
* Don't bother with VNCR-based accesses in the nVHE code, it has no
* business dealing with NV.
*/
-static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
+static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
{
#if !defined (__KVM_NVHE_HYPERVISOR__)
if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
@@ -918,6 +916,13 @@ static inline u64 *__ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
return (u64 *)&ctxt->sys_regs[r];
}
+#define __ctxt_sys_reg(c,r) \
+ ({ \
+ BUILD_BUG_ON(__builtin_constant_p(r) && \
+ (r) >= NR_SYS_REGS); \
+ ___ctxt_sys_reg(c, r); \
+ })
+
#define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r))
u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
@@ -1379,4 +1384,19 @@ bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);
(get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \
get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max))
+/* Check for a given level of PAuth support */
+#define kvm_has_pauth(k, l) \
+ ({ \
+ bool pa, pi, pa3; \
+ \
+ pa = kvm_has_feat((k), ID_AA64ISAR1_EL1, APA, l); \
+ pa &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPA, IMP); \
+ pi = kvm_has_feat((k), ID_AA64ISAR1_EL1, API, l); \
+ pi &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPI, IMP); \
+ pa3 = kvm_has_feat((k), ID_AA64ISAR2_EL1, APA3, l); \
+ pa3 &= kvm_has_feat((k), ID_AA64ISAR2_EL1, GPA3, IMP); \
+ \
+ (pa + pi + pa3) == 1; \
+ })
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index c77d795556e1..5e0ab0596246 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -60,7 +60,20 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
return ttbr0 & ~GENMASK_ULL(63, 48);
}
+extern bool forward_smc_trap(struct kvm_vcpu *vcpu);
int kvm_init_nv_sysregs(struct kvm *kvm);
+#ifdef CONFIG_ARM64_PTR_AUTH
+bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr);
+#else
+static inline bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr)
+{
+ /* We really should never execute this... */
+ WARN_ON_ONCE(1);
+ *elr = 0xbad9acc0debadbad;
+ return false;
+}
+#endif
+
#endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h
index 0cd0965255d2..d81bac256abc 100644
--- a/arch/arm64/include/asm/kvm_ptrauth.h
+++ b/arch/arm64/include/asm/kvm_ptrauth.h
@@ -99,5 +99,26 @@ alternative_else_nop_endif
.macro ptrauth_switch_to_hyp g_ctxt, h_ctxt, reg1, reg2, reg3
.endm
#endif /* CONFIG_ARM64_PTR_AUTH */
+
+#else /* !__ASSEMBLY */
+
+#define __ptrauth_save_key(ctxt, key) \
+ do { \
+ u64 __val; \
+ __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \
+ ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \
+ __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \
+ ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val; \
+ } while(0)
+
+#define ptrauth_save_keys(ctxt) \
+ do { \
+ __ptrauth_save_key(ctxt, APIA); \
+ __ptrauth_save_key(ctxt, APIB); \
+ __ptrauth_save_key(ctxt, APDA); \
+ __ptrauth_save_key(ctxt, APDB); \
+ __ptrauth_save_key(ctxt, APGA); \
+ } while(0)
+
#endif /* __ASSEMBLY__ */
#endif /* __ASM_KVM_PTRAUTH_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index ef207a0d4f0d..9943ff0af4c9 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -297,6 +297,7 @@
#define TCR_TBI1 (UL(1) << 38)
#define TCR_HA (UL(1) << 39)
#define TCR_HD (UL(1) << 40)
+#define TCR_TBID0 (UL(1) << 51)
#define TCR_TBID1 (UL(1) << 52)
#define TCR_NFD0 (UL(1) << 53)
#define TCR_NFD1 (UL(1) << 54)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index ce08b744aaab..06234c3a15f3 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -291,6 +291,21 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
blr x2
0:
mov_q x0, HCR_HOST_NVHE_FLAGS
+
+ /*
+ * Compliant CPUs advertise their VHE-onlyness with
+ * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
+ * RES1 in that case. Publish the E2H bit early so that
+ * it can be picked up by the init_el2_state macro.
+ *
+ * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
+ * don't advertise it (they predate this relaxation).
+ */
+ mrs_s x1, SYS_ID_AA64MMFR4_EL1
+ tbz x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
+
+ orr x0, x0, #HCR_E2H
+1:
msr hcr_el2, x0
isb
@@ -303,22 +318,10 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
mov_q x1, INIT_SCTLR_EL1_MMU_OFF
- /*
- * Compliant CPUs advertise their VHE-onlyness with
- * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
- * RES1 in that case.
- *
- * Fruity CPUs seem to have HCR_EL2.E2H set to RES1, but
- * don't advertise it (they predate this relaxation).
- */
- mrs_s x0, SYS_ID_AA64MMFR4_EL1
- ubfx x0, x0, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
- tbnz x0, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
-
mrs x0, hcr_el2
and x0, x0, #HCR_E2H
cbz x0, 2f
-1:
+
/* Set a sane SCTLR_EL1, the VHE way */
pre_disable_mmu_workaround
msr_s SYS_SCTLR_EL12, x1
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 162b030ab9da..0d022599eb61 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -761,7 +761,6 @@ static void sve_init_header_from_task(struct user_sve_header *header,
{
unsigned int vq;
bool active;
- bool fpsimd_only;
enum vec_type task_type;
memset(header, 0, sizeof(*header));
@@ -777,12 +776,10 @@ static void sve_init_header_from_task(struct user_sve_header *header,
case ARM64_VEC_SVE:
if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
header->flags |= SVE_PT_VL_INHERIT;
- fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE);
break;
case ARM64_VEC_SME:
if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
header->flags |= SVE_PT_VL_INHERIT;
- fpsimd_only = false;
break;
default:
WARN_ON_ONCE(1);
@@ -790,7 +787,7 @@ static void sve_init_header_from_task(struct user_sve_header *header,
}
if (active) {
- if (fpsimd_only) {
+ if (target->thread.fp_type == FP_STATE_FPSIMD) {
header->flags |= SVE_PT_REGS_FPSIMD;
} else {
header->flags |= SVE_PT_REGS_SVE;
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index c0c050e53157..04882b577575 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -23,6 +23,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
vgic/vgic-its.o vgic/vgic-debug.o
kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o pmu.o
+kvm-$(CONFIG_ARM64_PTR_AUTH) += pauth.o
always-y := hyp_constants.h hyp-constants.s
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 59b17948e7ed..cdda89378c63 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -35,10 +35,11 @@
#include <asm/virt.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/kvm_pkvm.h>
-#include <asm/kvm_emulate.h>
+#include <asm/kvm_ptrauth.h>
#include <asm/sections.h>
#include <kvm/arm_hypercalls.h>
@@ -240,6 +241,40 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kvm_arm_teardown_hypercalls(kvm);
}
+static bool kvm_has_full_ptr_auth(void)
+{
+ bool apa, gpa, api, gpi, apa3, gpa3;
+ u64 isar1, isar2, val;
+
+ /*
+ * Check that:
+ *
+ * - both Address and Generic auth are implemented for a given
+ * algorithm (Q5, IMPDEF or Q3)
+ * - only a single algorithm is implemented.
+ */
+ if (!system_has_full_ptr_auth())
+ return false;
+
+ isar1 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1);
+ isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1);
+
+ apa = !!FIELD_GET(ID_AA64ISAR1_EL1_APA_MASK, isar1);
+ val = FIELD_GET(ID_AA64ISAR1_EL1_GPA_MASK, isar1);
+ gpa = (val == ID_AA64ISAR1_EL1_GPA_IMP);
+
+ api = !!FIELD_GET(ID_AA64ISAR1_EL1_API_MASK, isar1);
+ val = FIELD_GET(ID_AA64ISAR1_EL1_GPI_MASK, isar1);
+ gpi = (val == ID_AA64ISAR1_EL1_GPI_IMP);
+
+ apa3 = !!FIELD_GET(ID_AA64ISAR2_EL1_APA3_MASK, isar2);
+ val = FIELD_GET(ID_AA64ISAR2_EL1_GPA3_MASK, isar2);
+ gpa3 = (val == ID_AA64ISAR2_EL1_GPA3_IMP);
+
+ return (apa == gpa && api == gpi && apa3 == gpa3 &&
+ (apa + api + apa3) == 1);
+}
+
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -337,7 +372,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_ARM_PTRAUTH_ADDRESS:
case KVM_CAP_ARM_PTRAUTH_GENERIC:
- r = system_has_full_ptr_auth();
+ r = kvm_has_full_ptr_auth();
break;
case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE:
if (kvm)
@@ -448,6 +483,44 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
}
+static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu)
+{
+ if (vcpu_has_ptrauth(vcpu)) {
+ /*
+ * Either we're running running an L2 guest, and the API/APK
+ * bits come from L1's HCR_EL2, or API/APK are both set.
+ */
+ if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) {
+ u64 val;
+
+ val = __vcpu_sys_reg(vcpu, HCR_EL2);
+ val &= (HCR_API | HCR_APK);
+ vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK);
+ vcpu->arch.hcr_el2 |= val;
+ } else {
+ vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK);
+ }
+
+ /*
+ * Save the host keys if there is any chance for the guest
+ * to use pauth, as the entry code will reload the guest
+ * keys in that case.
+ * Protected mode is the exception to that rule, as the
+ * entry into the EL2 code eagerly switch back and forth
+ * between host and hyp keys (and kvm_hyp_ctxt is out of
+ * reach anyway).
+ */
+ if (is_protected_kvm_enabled())
+ return;
+
+ if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) {
+ struct kvm_cpu_context *ctxt;
+ ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt);
+ ptrauth_save_keys(ctxt);
+ }
+ }
+}
+
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct kvm_s2_mmu *mmu;
@@ -486,8 +559,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
else
vcpu_set_wfx_traps(vcpu);
- if (vcpu_has_ptrauth(vcpu))
- vcpu_ptrauth_disable(vcpu);
+ vcpu_set_pauth_traps(vcpu);
+
kvm_arch_vcpu_load_debug_state_flags(vcpu);
if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
@@ -1289,7 +1362,7 @@ static unsigned long system_supported_vcpu_features(void)
if (!system_supports_sve())
clear_bit(KVM_ARM_VCPU_SVE, &features);
- if (!system_has_full_ptr_auth()) {
+ if (!kvm_has_full_ptr_auth()) {
clear_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features);
clear_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features);
}
@@ -2616,14 +2689,11 @@ static __init int kvm_arm_init(void)
if (err)
goto out_hyp;
- if (is_protected_kvm_enabled()) {
- kvm_info("Protected nVHE mode initialized successfully\n");
- } else if (in_hyp_mode) {
- kvm_info("VHE mode initialized successfully\n");
- } else {
- char mode = cpus_have_final_cap(ARM64_KVM_HVHE) ? 'h' : 'n';
- kvm_info("Hyp mode (%cVHE) initialized successfully\n", mode);
- }
+ kvm_info("%s%sVHE mode initialized successfully\n",
+ in_hyp_mode ? "" : (is_protected_kvm_enabled() ?
+ "Protected " : "Hyp "),
+ in_hyp_mode ? "" : (cpus_have_final_cap(ARM64_KVM_HVHE) ?
+ "h" : "n"));
/*
* FIXME: Do something reasonable if kvm_init() fails after pKVM
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 4697ba41b3a9..72d733c74a38 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2117,6 +2117,26 @@ inject:
return true;
}
+static bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit)
+{
+ bool control_bit_set;
+
+ if (!vcpu_has_nv(vcpu))
+ return false;
+
+ control_bit_set = __vcpu_sys_reg(vcpu, HCR_EL2) & control_bit;
+ if (!is_hyp_ctxt(vcpu) && control_bit_set) {
+ kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+ return true;
+ }
+ return false;
+}
+
+bool forward_smc_trap(struct kvm_vcpu *vcpu)
+{
+ return forward_traps(vcpu, HCR_TSC);
+}
+
static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr)
{
u64 mode = spsr & PSR_MODE_MASK;
@@ -2152,37 +2172,39 @@ static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr)
void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
{
- u64 spsr, elr, mode;
- bool direct_eret;
+ u64 spsr, elr, esr;
/*
- * Going through the whole put/load motions is a waste of time
- * if this is a VHE guest hypervisor returning to its own
- * userspace, or the hypervisor performing a local exception
- * return. No need to save/restore registers, no need to
- * switch S2 MMU. Just do the canonical ERET.
+ * Forward this trap to the virtual EL2 if the virtual
+ * HCR_EL2.NV bit is set and this is coming from !EL2.
*/
- spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
- spsr = kvm_check_illegal_exception_return(vcpu, spsr);
-
- mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
-
- direct_eret = (mode == PSR_MODE_EL0t &&
- vcpu_el2_e2h_is_set(vcpu) &&
- vcpu_el2_tge_is_set(vcpu));
- direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t);
-
- if (direct_eret) {
- *vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2);
- *vcpu_cpsr(vcpu) = spsr;
- trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr);
+ if (forward_traps(vcpu, HCR_NV))
return;
+
+ /* Check for an ERETAx */
+ esr = kvm_vcpu_get_esr(vcpu);
+ if (esr_iss_is_eretax(esr) && !kvm_auth_eretax(vcpu, &elr)) {
+ /*
+ * Oh no, ERETAx failed to authenticate. If we have
+ * FPACCOMBINE, deliver an exception right away. If we
+ * don't, then let the mangled ELR value trickle down the
+ * ERET handling, and the guest will have a little surprise.
+ */
+ if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE)) {
+ esr &= ESR_ELx_ERET_ISS_ERETA;
+ esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC);
+ kvm_inject_nested_sync(vcpu, esr);
+ return;
+ }
}
preempt_disable();
kvm_arch_vcpu_put(vcpu);
- elr = __vcpu_sys_reg(vcpu, ELR_EL2);
+ spsr = __vcpu_sys_reg(vcpu, SPSR_EL2);
+ spsr = kvm_check_illegal_exception_return(vcpu, spsr);
+ if (!esr_iss_is_eretax(esr))
+ elr = __vcpu_sys_reg(vcpu, ELR_EL2);
trace_kvm_nested_eret(vcpu, elr, spsr);
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 617ae6dea5d5..b037f0a0e27e 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -56,6 +56,13 @@ static int handle_hvc(struct kvm_vcpu *vcpu)
static int handle_smc(struct kvm_vcpu *vcpu)
{
/*
+ * Forward this trapped smc instruction to the virtual EL2 if
+ * the guest has asked for it.
+ */
+ if (forward_smc_trap(vcpu))
+ return 1;
+
+ /*
* "If an SMC instruction executed at Non-secure EL1 is
* trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
* Trap exception, not a Secure Monitor Call exception [...]"
@@ -207,19 +214,40 @@ static int handle_sve(struct kvm_vcpu *vcpu)
}
/*
- * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into
- * a NOP). If we get here, it is that we didn't fixup ptrauth on exit, and all
- * that we can do is give the guest an UNDEF.
+ * Two possibilities to handle a trapping ptrauth instruction:
+ *
+ * - Guest usage of a ptrauth instruction (which the guest EL1 did not
+ * turn into a NOP). If we get here, it is because we didn't enable
+ * ptrauth for the guest. This results in an UNDEF, as it isn't
+ * supposed to use ptrauth without being told it could.
+ *
+ * - Running an L2 NV guest while L1 has left HCR_EL2.API==0, and for
+ * which we reinject the exception into L1.
+ *
+ * Anything else is an emulation bug (hence the WARN_ON + UNDEF).
*/
static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu)
{
+ if (!vcpu_has_ptrauth(vcpu)) {
+ kvm_inject_undefined(vcpu);
+ return 1;
+ }
+
+ if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+ kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+ return 1;
+ }
+
+ /* Really shouldn't be here! */
+ WARN_ON_ONCE(1);
kvm_inject_undefined(vcpu);
return 1;
}
static int kvm_handle_eret(struct kvm_vcpu *vcpu)
{
- if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET)
+ if (esr_iss_is_eretax(kvm_vcpu_get_esr(vcpu)) &&
+ !vcpu_has_ptrauth(vcpu))
return kvm_handle_ptrauth(vcpu);
/*
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 38b4e2623b02..a92566f36022 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -27,6 +27,7 @@
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
+#include <asm/kvm_ptrauth.h>
#include <asm/fpsimd.h>
#include <asm/debug-monitors.h>
#include <asm/processor.h>
@@ -265,10 +266,8 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
__deactivate_traps_hfgxtr(vcpu);
}
-static inline void ___activate_traps(struct kvm_vcpu *vcpu)
+static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr)
{
- u64 hcr = vcpu->arch.hcr_el2;
-
if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
hcr |= HCR_TVM;
@@ -443,60 +442,6 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
return true;
}
-static inline bool esr_is_ptrauth_trap(u64 esr)
-{
- switch (esr_sys64_to_sysreg(esr)) {
- case SYS_APIAKEYLO_EL1:
- case SYS_APIAKEYHI_EL1:
- case SYS_APIBKEYLO_EL1:
- case SYS_APIBKEYHI_EL1:
- case SYS_APDAKEYLO_EL1:
- case SYS_APDAKEYHI_EL1:
- case SYS_APDBKEYLO_EL1:
- case SYS_APDBKEYHI_EL1:
- case SYS_APGAKEYLO_EL1:
- case SYS_APGAKEYHI_EL1:
- return true;
- }
-
- return false;
-}
-
-#define __ptrauth_save_key(ctxt, key) \
- do { \
- u64 __val; \
- __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \
- ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \
- __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \
- ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val; \
-} while(0)
-
-DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
-
-static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code)
-{
- struct kvm_cpu_context *ctxt;
- u64 val;
-
- if (!vcpu_has_ptrauth(vcpu))
- return false;
-
- ctxt = this_cpu_ptr(&kvm_hyp_ctxt);
- __ptrauth_save_key(ctxt, APIA);
- __ptrauth_save_key(ctxt, APIB);
- __ptrauth_save_key(ctxt, APDA);
- __ptrauth_save_key(ctxt, APDB);
- __ptrauth_save_key(ctxt, APGA);
-
- vcpu_ptrauth_enable(vcpu);
-
- val = read_sysreg(hcr_el2);
- val |= (HCR_API | HCR_APK);
- write_sysreg(val, hcr_el2);
-
- return true;
-}
-
static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *ctxt;
@@ -584,9 +529,6 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
__vgic_v3_perform_cpuif_access(vcpu) == 1)
return true;
- if (esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
- return kvm_hyp_handle_ptrauth(vcpu, exit_code);
-
if (kvm_hyp_handle_cntpct(vcpu))
return true;
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 41d1ba6de41a..6758cd905570 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -40,7 +40,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
{
u64 val;
- ___activate_traps(vcpu);
+ ___activate_traps(vcpu, vcpu->arch.hcr_el2);
__activate_traps_common(vcpu);
val = vcpu->arch.cptr_el2;
@@ -191,7 +191,6 @@ static const exit_handler_fn hyp_exit_handlers[] = {
[ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low,
[ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low,
[ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low,
- [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth,
[ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops,
};
@@ -203,7 +202,6 @@ static const exit_handler_fn pvm_exit_handlers[] = {
[ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low,
[ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low,
[ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low,
- [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth,
[ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops,
};
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index c6e0a49eb860..ca3c09df8d7c 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -221,7 +221,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
/* Switch to requested VMID */
enter_vmid_context(mmu, &cxt, false);
- __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+ __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+ TLBI_TTL_UNKNOWN);
dsb(ish);
__tlbi(vmalle1is);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index d177a9f7a097..9e2bbee77491 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -528,7 +528,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
kvm_clear_pte(ctx->ptep);
dsb(ishst);
- __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), ctx->level);
+ __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), TLBI_TTL_UNKNOWN);
} else {
if (ctx->end - ctx->addr < granule)
return -EINVAL;
@@ -843,12 +843,15 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
* Perform the appropriate TLB invalidation based on the
* evicted pte value (if any).
*/
- if (kvm_pte_table(ctx->old, ctx->level))
- kvm_tlb_flush_vmid_range(mmu, ctx->addr,
- kvm_granule_size(ctx->level));
- else if (kvm_pte_valid(ctx->old))
+ if (kvm_pte_table(ctx->old, ctx->level)) {
+ u64 size = kvm_granule_size(ctx->level);
+ u64 addr = ALIGN_DOWN(ctx->addr, size);
+
+ kvm_tlb_flush_vmid_range(mmu, addr, size);
+ } else if (kvm_pte_valid(ctx->old)) {
kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
ctx->addr, ctx->level);
+ }
}
if (stage2_pte_is_counted(ctx->old))
@@ -896,9 +899,13 @@ static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx,
if (kvm_pte_valid(ctx->old)) {
kvm_clear_pte(ctx->ptep);
- if (!stage2_unmap_defer_tlb_flush(pgt))
- kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
- ctx->addr, ctx->level);
+ if (kvm_pte_table(ctx->old, ctx->level)) {
+ kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr,
+ TLBI_TTL_UNKNOWN);
+ } else if (!stage2_unmap_defer_tlb_flush(pgt)) {
+ kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr,
+ ctx->level);
+ }
}
mm_ops->put_page(ctx->ptep);
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 93f78df8b0f6..d7af5f46f22a 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -33,11 +33,43 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data);
DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
+/*
+ * HCR_EL2 bits that the NV guest can freely change (no RES0/RES1
+ * semantics, irrespective of the configuration), but that cannot be
+ * applied to the actual HW as things would otherwise break badly.
+ *
+ * - TGE: we want the guest to use EL1, which is incompatible with
+ * this bit being set
+ *
+ * - API/APK: they are already accounted for by vcpu_load(), and can
+ * only take effect across a load/put cycle (such as ERET)
+ */
+#define NV_HCR_GUEST_EXCLUDE (HCR_TGE | HCR_API | HCR_APK)
+
+static u64 __compute_hcr(struct kvm_vcpu *vcpu)
+{
+ u64 hcr = vcpu->arch.hcr_el2;
+
+ if (!vcpu_has_nv(vcpu))
+ return hcr;
+
+ if (is_hyp_ctxt(vcpu)) {
+ hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB;
+
+ if (!vcpu_el2_e2h_is_set(vcpu))
+ hcr |= HCR_NV1;
+
+ write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2);
+ }
+
+ return hcr | (__vcpu_sys_reg(vcpu, HCR_EL2) & ~NV_HCR_GUEST_EXCLUDE);
+}
+
static void __activate_traps(struct kvm_vcpu *vcpu)
{
u64 val;
- ___activate_traps(vcpu);
+ ___activate_traps(vcpu, __compute_hcr(vcpu));
if (has_cntpoff()) {
struct timer_map map;
@@ -162,6 +194,8 @@ static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu)
void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
{
+ host_data_ptr(host_ctxt)->__hyp_running_vcpu = vcpu;
+
__vcpu_load_switch_sysregs(vcpu);
__vcpu_load_activate_traps(vcpu);
__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
@@ -171,6 +205,61 @@ void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
{
__vcpu_put_deactivate_traps(vcpu);
__vcpu_put_switch_sysregs(vcpu);
+
+ host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL;
+}
+
+static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ u64 esr = kvm_vcpu_get_esr(vcpu);
+ u64 spsr, elr, mode;
+
+ /*
+ * Going through the whole put/load motions is a waste of time
+ * if this is a VHE guest hypervisor returning to its own
+ * userspace, or the hypervisor performing a local exception
+ * return. No need to save/restore registers, no need to
+ * switch S2 MMU. Just do the canonical ERET.
+ *
+ * Unless the trap has to be forwarded further down the line,
+ * of course...
+ */
+ if ((__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) ||
+ (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_ERET))
+ return false;
+
+ spsr = read_sysreg_el1(SYS_SPSR);
+ mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+ switch (mode) {
+ case PSR_MODE_EL0t:
+ if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
+ return false;
+ break;
+ case PSR_MODE_EL2t:
+ mode = PSR_MODE_EL1t;
+ break;
+ case PSR_MODE_EL2h:
+ mode = PSR_MODE_EL1h;
+ break;
+ default:
+ return false;
+ }
+
+ /* If ERETAx fails, take the slow path */
+ if (esr_iss_is_eretax(esr)) {
+ if (!(vcpu_has_ptrauth(vcpu) && kvm_auth_eretax(vcpu, &elr)))
+ return false;
+ } else {
+ elr = read_sysreg_el1(SYS_ELR);
+ }
+
+ spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+
+ write_sysreg_el2(spsr, SYS_SPSR);
+ write_sysreg_el2(elr, SYS_ELR);
+
+ return true;
}
static const exit_handler_fn hyp_exit_handlers[] = {
@@ -182,7 +271,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
[ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low,
[ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low,
[ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low,
- [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth,
+ [ESR_ELx_EC_ERET] = kvm_hyp_handle_eret,
[ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops,
};
@@ -197,7 +286,7 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
* If we were in HYP context on entry, adjust the PSTATE view
* so that the usual helpers work correctly.
*/
- if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) {
+ if (vcpu_has_nv(vcpu) && (read_sysreg(hcr_el2) & HCR_NV)) {
u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
switch (mode) {
@@ -222,7 +311,6 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
u64 exit_code;
host_ctxt = host_data_ptr(host_ctxt);
- host_ctxt->__hyp_running_vcpu = vcpu;
guest_ctxt = &vcpu->arch.ctxt;
sysreg_save_host_state_vhe(host_ctxt);
@@ -240,11 +328,6 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
sysreg_restore_guest_state_vhe(guest_ctxt);
__debug_switch_to_guest(vcpu);
- if (is_hyp_ctxt(vcpu))
- vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT);
- else
- vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT);
-
do {
/* Jump in the fire! */
exit_code = __guest_enter(vcpu);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 4a653c4a277d..5fa0359f3a87 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -171,7 +171,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
/* Switch to requested VMID */
enter_vmid_context(mmu, &cxt);
- __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+ __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+ TLBI_TTL_UNKNOWN);
dsb(ish);
__tlbi(vmalle1is);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 3afc42d8833e..03cf0a473458 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1639,7 +1639,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
- if (esr_fsc_is_permission_fault(esr)) {
+ if (esr_fsc_is_translation_fault(esr)) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index ced30c90521a..6813c7c7f00a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -35,13 +35,9 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
break;
case SYS_ID_AA64ISAR1_EL1:
- /* Support everything but PtrAuth and Spec Invalidation */
+ /* Support everything but Spec Invalidation */
val &= ~(GENMASK_ULL(63, 56) |
- NV_FTR(ISAR1, SPECRES) |
- NV_FTR(ISAR1, GPI) |
- NV_FTR(ISAR1, GPA) |
- NV_FTR(ISAR1, API) |
- NV_FTR(ISAR1, APA));
+ NV_FTR(ISAR1, SPECRES));
break;
case SYS_ID_AA64PFR0_EL1:
diff --git a/arch/arm64/kvm/pauth.c b/arch/arm64/kvm/pauth.c
new file mode 100644
index 000000000000..d5eb3ae876be
--- /dev/null
+++ b/arch/arm64/kvm/pauth.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 - Google LLC
+ * Author: Marc Zyngier <maz@kernel.org>
+ *
+ * Primitive PAuth emulation for ERETAA/ERETAB.
+ *
+ * This code assumes that is is run from EL2, and that it is part of
+ * the emulation of ERETAx for a guest hypervisor. That's a lot of
+ * baked-in assumptions and shortcuts.
+ *
+ * Do no reuse for anything else!
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/gpr-num.h>
+#include <asm/kvm_emulate.h>
+#include <asm/pointer_auth.h>
+
+/* PACGA Xd, Xn, Xm */
+#define PACGA(d,n,m) \
+ asm volatile(__DEFINE_ASM_GPR_NUMS \
+ ".inst 0x9AC03000 |" \
+ "(.L__gpr_num_%[Rd] << 0) |" \
+ "(.L__gpr_num_%[Rn] << 5) |" \
+ "(.L__gpr_num_%[Rm] << 16)\n" \
+ : [Rd] "=r" ((d)) \
+ : [Rn] "r" ((n)), [Rm] "r" ((m)))
+
+static u64 compute_pac(struct kvm_vcpu *vcpu, u64 ptr,
+ struct ptrauth_key ikey)
+{
+ struct ptrauth_key gkey;
+ u64 mod, pac = 0;
+
+ preempt_disable();
+
+ if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
+ mod = __vcpu_sys_reg(vcpu, SP_EL2);
+ else
+ mod = read_sysreg(sp_el1);
+
+ gkey.lo = read_sysreg_s(SYS_APGAKEYLO_EL1);
+ gkey.hi = read_sysreg_s(SYS_APGAKEYHI_EL1);
+
+ __ptrauth_key_install_nosync(APGA, ikey);
+ isb();
+
+ PACGA(pac, ptr, mod);
+ isb();
+
+ __ptrauth_key_install_nosync(APGA, gkey);
+
+ preempt_enable();
+
+ /* PAC in the top 32bits */
+ return pac;
+}
+
+static bool effective_tbi(struct kvm_vcpu *vcpu, bool bit55)
+{
+ u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+ bool tbi, tbid;
+
+ /*
+ * Since we are authenticating an instruction address, we have
+ * to take TBID into account. If E2H==0, ignore VA[55], as
+ * TCR_EL2 only has a single TBI/TBID. If VA[55] was set in
+ * this case, this is likely a guest bug...
+ */
+ if (!vcpu_el2_e2h_is_set(vcpu)) {
+ tbi = tcr & BIT(20);
+ tbid = tcr & BIT(29);
+ } else if (bit55) {
+ tbi = tcr & TCR_TBI1;
+ tbid = tcr & TCR_TBID1;
+ } else {
+ tbi = tcr & TCR_TBI0;
+ tbid = tcr & TCR_TBID0;
+ }
+
+ return tbi && !tbid;
+}
+
+static int compute_bottom_pac(struct kvm_vcpu *vcpu, bool bit55)
+{
+ static const int maxtxsz = 39; // Revisit these two values once
+ static const int mintxsz = 16; // (if) we support TTST/LVA/LVA2
+ u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+ int txsz;
+
+ if (!vcpu_el2_e2h_is_set(vcpu) || !bit55)
+ txsz = FIELD_GET(TCR_T0SZ_MASK, tcr);
+ else
+ txsz = FIELD_GET(TCR_T1SZ_MASK, tcr);
+
+ return 64 - clamp(txsz, mintxsz, maxtxsz);
+}
+
+static u64 compute_pac_mask(struct kvm_vcpu *vcpu, bool bit55)
+{
+ int bottom_pac;
+ u64 mask;
+
+ bottom_pac = compute_bottom_pac(vcpu, bit55);
+
+ mask = GENMASK(54, bottom_pac);
+ if (!effective_tbi(vcpu, bit55))
+ mask |= GENMASK(63, 56);
+
+ return mask;
+}
+
+static u64 to_canonical_addr(struct kvm_vcpu *vcpu, u64 ptr, u64 mask)
+{
+ bool bit55 = !!(ptr & BIT(55));
+
+ if (bit55)
+ return ptr | mask;
+
+ return ptr & ~mask;
+}
+
+static u64 corrupt_addr(struct kvm_vcpu *vcpu, u64 ptr)
+{
+ bool bit55 = !!(ptr & BIT(55));
+ u64 mask, error_code;
+ int shift;
+
+ if (effective_tbi(vcpu, bit55)) {
+ mask = GENMASK(54, 53);
+ shift = 53;
+ } else {
+ mask = GENMASK(62, 61);
+ shift = 61;
+ }
+
+ if (esr_iss_is_eretab(kvm_vcpu_get_esr(vcpu)))
+ error_code = 2 << shift;
+ else
+ error_code = 1 << shift;
+
+ ptr &= ~mask;
+ ptr |= error_code;
+
+ return ptr;
+}
+
+/*
+ * Authenticate an ERETAA/ERETAB instruction, returning true if the
+ * authentication succeeded and false otherwise. In all cases, *elr
+ * contains the VA to ERET to. Potential exception injection is left
+ * to the caller.
+ */
+bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr)
+{
+ u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL2);
+ u64 esr = kvm_vcpu_get_esr(vcpu);
+ u64 ptr, cptr, pac, mask;
+ struct ptrauth_key ikey;
+
+ *elr = ptr = vcpu_read_sys_reg(vcpu, ELR_EL2);
+
+ /* We assume we're already in the context of an ERETAx */
+ if (esr_iss_is_eretab(esr)) {
+ if (!(sctlr & SCTLR_EL1_EnIB))
+ return true;
+
+ ikey.lo = __vcpu_sys_reg(vcpu, APIBKEYLO_EL1);
+ ikey.hi = __vcpu_sys_reg(vcpu, APIBKEYHI_EL1);
+ } else {
+ if (!(sctlr & SCTLR_EL1_EnIA))
+ return true;
+
+ ikey.lo = __vcpu_sys_reg(vcpu, APIAKEYLO_EL1);
+ ikey.hi = __vcpu_sys_reg(vcpu, APIAKEYHI_EL1);
+ }
+
+ mask = compute_pac_mask(vcpu, !!(ptr & BIT(55)));
+ cptr = to_canonical_addr(vcpu, ptr, mask);
+
+ pac = compute_pac(vcpu, cptr, ikey);
+
+ /*
+ * Slightly deviate from the pseudocode: if we have a PAC
+ * match with the signed pointer, then it must be good.
+ * Anything after this point is pure error handling.
+ */
+ if ((pac & mask) == (ptr & mask)) {
+ *elr = cptr;
+ return true;
+ }
+
+ /*
+ * Authentication failed, corrupt the canonical address if
+ * PAuth2 isn't implemented, or some XORing if it is.
+ */
+ if (!kvm_has_pauth(vcpu->kvm, PAuth2))
+ cptr = corrupt_addr(vcpu, cptr);
+ else
+ cptr = ptr ^ (pac & mask);
+
+ *elr = cptr;
+ return false;
+}
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index 389025ce7749..bcbc8c986b1d 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -28,27 +28,65 @@ struct vgic_state_iter {
int nr_lpis;
int dist_id;
int vcpu_id;
- int intid;
+ unsigned long intid;
int lpi_idx;
- u32 *lpi_array;
};
-static void iter_next(struct vgic_state_iter *iter)
+static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter)
{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+
if (iter->dist_id == 0) {
iter->dist_id++;
return;
}
+ /*
+ * Let the xarray drive the iterator after the last SPI, as the iterator
+ * has exhausted the sequentially-allocated INTID space.
+ */
+ if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1)) {
+ if (iter->lpi_idx < iter->nr_lpis)
+ xa_find_after(&dist->lpi_xa, &iter->intid,
+ VGIC_LPI_MAX_INTID,
+ LPI_XA_MARK_DEBUG_ITER);
+ iter->lpi_idx++;
+ return;
+ }
+
iter->intid++;
if (iter->intid == VGIC_NR_PRIVATE_IRQS &&
++iter->vcpu_id < iter->nr_cpus)
iter->intid = 0;
+}
- if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS)) {
- if (iter->lpi_idx < iter->nr_lpis)
- iter->intid = iter->lpi_array[iter->lpi_idx];
- iter->lpi_idx++;
+static int iter_mark_lpis(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct vgic_irq *irq;
+ unsigned long intid;
+ int nr_lpis = 0;
+
+ xa_for_each(&dist->lpi_xa, intid, irq) {
+ if (!vgic_try_get_irq_kref(irq))
+ continue;
+
+ xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+ nr_lpis++;
+ }
+
+ return nr_lpis;
+}
+
+static void iter_unmark_lpis(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct vgic_irq *irq;
+ unsigned long intid;
+
+ xa_for_each(&dist->lpi_xa, intid, irq) {
+ xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+ vgic_put_irq(kvm, irq);
}
}
@@ -61,15 +99,12 @@ static void iter_init(struct kvm *kvm, struct vgic_state_iter *iter,
iter->nr_cpus = nr_cpus;
iter->nr_spis = kvm->arch.vgic.nr_spis;
- if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
- iter->nr_lpis = vgic_copy_lpi_list(kvm, NULL, &iter->lpi_array);
- if (iter->nr_lpis < 0)
- iter->nr_lpis = 0;
- }
+ if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ iter->nr_lpis = iter_mark_lpis(kvm);
/* Fast forward to the right position if needed */
while (pos--)
- iter_next(iter);
+ iter_next(kvm, iter);
}
static bool end_of_vgic(struct vgic_state_iter *iter)
@@ -114,7 +149,7 @@ static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos)
struct vgic_state_iter *iter = kvm->arch.vgic.iter;
++*pos;
- iter_next(iter);
+ iter_next(kvm, iter);
if (end_of_vgic(iter))
iter = NULL;
return iter;
@@ -134,13 +169,14 @@ static void vgic_debug_stop(struct seq_file *s, void *v)
mutex_lock(&kvm->arch.config_lock);
iter = kvm->arch.vgic.iter;
- kfree(iter->lpi_array);
+ iter_unmark_lpis(kvm);
kfree(iter);
kvm->arch.vgic.iter = NULL;
mutex_unlock(&kvm->arch.config_lock);
}
-static void print_dist_state(struct seq_file *s, struct vgic_dist *dist)
+static void print_dist_state(struct seq_file *s, struct vgic_dist *dist,
+ struct vgic_state_iter *iter)
{
bool v3 = dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3;
@@ -149,7 +185,7 @@ static void print_dist_state(struct seq_file *s, struct vgic_dist *dist)
seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2");
seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis);
if (v3)
- seq_printf(s, "nr_lpis:\t%d\n", atomic_read(&dist->lpi_count));
+ seq_printf(s, "nr_lpis:\t%d\n", iter->nr_lpis);
seq_printf(s, "enabled:\t%d\n", dist->enabled);
seq_printf(s, "\n");
@@ -236,7 +272,7 @@ static int vgic_debug_show(struct seq_file *s, void *v)
unsigned long flags;
if (iter->dist_id == 0) {
- print_dist_state(s, &kvm->arch.vgic);
+ print_dist_state(s, &kvm->arch.vgic, iter);
return 0;
}
@@ -246,11 +282,13 @@ static int vgic_debug_show(struct seq_file *s, void *v)
if (iter->vcpu_id < iter->nr_cpus)
vcpu = kvm_get_vcpu(kvm, iter->vcpu_id);
+ /*
+ * Expect this to succeed, as iter_mark_lpis() takes a reference on
+ * every LPI to be visited.
+ */
irq = vgic_get_irq(kvm, vcpu, iter->intid);
- if (!irq) {
- seq_printf(s, " LPI %4d freed\n", iter->intid);
- return 0;
- }
+ if (WARN_ON_ONCE(!irq))
+ return -EINVAL;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
print_irq_state(s, irq, vcpu);
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index f20941f83a07..aee6083d0da6 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -53,8 +53,6 @@ void kvm_vgic_early_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
- INIT_LIST_HEAD(&dist->lpi_translation_cache);
- raw_spin_lock_init(&dist->lpi_list_lock);
xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ);
}
@@ -305,9 +303,6 @@ int vgic_init(struct kvm *kvm)
}
}
- if (vgic_has_its(kvm))
- vgic_lpi_translation_cache_init(kvm);
-
/*
* If we have GICv4.1 enabled, unconditionally request enable the
* v4 support so that we get HW-accelerated vSGIs. Otherwise, only
@@ -361,9 +356,6 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
dist->vgic_cpu_base = VGIC_ADDR_UNDEF;
}
- if (vgic_has_its(kvm))
- vgic_lpi_translation_cache_destroy(kvm);
-
if (vgic_supports_direct_msis(kvm))
vgic_v4_teardown(kvm);
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index e85a495ada9c..40bb43f20bf3 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -23,6 +23,8 @@
#include "vgic.h"
#include "vgic-mmio.h"
+static struct kvm_device_ops kvm_arm_vgic_its_ops;
+
static int vgic_its_save_tables_v0(struct vgic_its *its);
static int vgic_its_restore_tables_v0(struct vgic_its *its);
static int vgic_its_commit_v0(struct vgic_its *its);
@@ -67,7 +69,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
irq->target_vcpu = vcpu;
irq->group = 1;
- raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+ xa_lock_irqsave(&dist->lpi_xa, flags);
/*
* There could be a race with another vgic_add_lpi(), so we need to
@@ -82,17 +84,14 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
goto out_unlock;
}
- ret = xa_err(xa_store(&dist->lpi_xa, intid, irq, 0));
+ ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0));
if (ret) {
xa_release(&dist->lpi_xa, intid);
kfree(irq);
- goto out_unlock;
}
- atomic_inc(&dist->lpi_count);
-
out_unlock:
- raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+ xa_unlock_irqrestore(&dist->lpi_xa, flags);
if (ret)
return ERR_PTR(ret);
@@ -150,14 +149,6 @@ struct its_ite {
u32 event_id;
};
-struct vgic_translation_cache_entry {
- struct list_head entry;
- phys_addr_t db;
- u32 devid;
- u32 eventid;
- struct vgic_irq *irq;
-};
-
/**
* struct vgic_its_abi - ITS abi ops and settings
* @cte_esz: collection table entry size
@@ -252,8 +243,10 @@ static struct its_ite *find_ite(struct vgic_its *its, u32 device_id,
#define GIC_LPI_OFFSET 8192
-#define VITS_TYPER_IDBITS 16
-#define VITS_TYPER_DEVBITS 16
+#define VITS_TYPER_IDBITS 16
+#define VITS_MAX_EVENTID (BIT(VITS_TYPER_IDBITS) - 1)
+#define VITS_TYPER_DEVBITS 16
+#define VITS_MAX_DEVID (BIT(VITS_TYPER_DEVBITS) - 1)
#define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1)
#define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1)
@@ -316,53 +309,6 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
return 0;
}
-#define GIC_LPI_MAX_INTID ((1 << INTERRUPT_ID_BITS_ITS) - 1)
-
-/*
- * Create a snapshot of the current LPIs targeting @vcpu, so that we can
- * enumerate those LPIs without holding any lock.
- * Returns their number and puts the kmalloc'ed array into intid_ptr.
- */
-int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
- XA_STATE(xas, &dist->lpi_xa, GIC_LPI_OFFSET);
- struct vgic_irq *irq;
- unsigned long flags;
- u32 *intids;
- int irq_count, i = 0;
-
- /*
- * There is an obvious race between allocating the array and LPIs
- * being mapped/unmapped. If we ended up here as a result of a
- * command, we're safe (locks are held, preventing another
- * command). If coming from another path (such as enabling LPIs),
- * we must be careful not to overrun the array.
- */
- irq_count = atomic_read(&dist->lpi_count);
- intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL_ACCOUNT);
- if (!intids)
- return -ENOMEM;
-
- raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
- rcu_read_lock();
-
- xas_for_each(&xas, irq, GIC_LPI_MAX_INTID) {
- if (i == irq_count)
- break;
- /* We don't need to "get" the IRQ, as we hold the list lock. */
- if (vcpu && irq->target_vcpu != vcpu)
- continue;
- intids[i++] = irq->intid;
- }
-
- rcu_read_unlock();
- raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
-
- *intid_ptr = intids;
- return i;
-}
-
static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
{
int ret = 0;
@@ -446,23 +392,18 @@ static u32 max_lpis_propbaser(u64 propbaser)
static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
{
gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ unsigned long intid, flags;
struct vgic_irq *irq;
int last_byte_offset = -1;
int ret = 0;
- u32 *intids;
- int nr_irqs, i;
- unsigned long flags;
u8 pendmask;
- nr_irqs = vgic_copy_lpi_list(vcpu->kvm, vcpu, &intids);
- if (nr_irqs < 0)
- return nr_irqs;
-
- for (i = 0; i < nr_irqs; i++) {
+ xa_for_each(&dist->lpi_xa, intid, irq) {
int byte_offset, bit_nr;
- byte_offset = intids[i] / BITS_PER_BYTE;
- bit_nr = intids[i] % BITS_PER_BYTE;
+ byte_offset = intid / BITS_PER_BYTE;
+ bit_nr = intid % BITS_PER_BYTE;
/*
* For contiguously allocated LPIs chances are we just read
@@ -472,25 +413,23 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
ret = kvm_read_guest_lock(vcpu->kvm,
pendbase + byte_offset,
&pendmask, 1);
- if (ret) {
- kfree(intids);
+ if (ret)
return ret;
- }
+
last_byte_offset = byte_offset;
}
- irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
+ irq = vgic_get_irq(vcpu->kvm, NULL, intid);
if (!irq)
continue;
raw_spin_lock_irqsave(&irq->irq_lock, flags);
- irq->pending_latch = pendmask & (1U << bit_nr);
+ if (irq->target_vcpu == vcpu)
+ irq->pending_latch = pendmask & (1U << bit_nr);
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
vgic_put_irq(vcpu->kvm, irq);
}
- kfree(intids);
-
return ret;
}
@@ -566,51 +505,52 @@ static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm,
return 0;
}
-static struct vgic_irq *__vgic_its_check_cache(struct vgic_dist *dist,
- phys_addr_t db,
- u32 devid, u32 eventid)
+static struct vgic_its *__vgic_doorbell_to_its(struct kvm *kvm, gpa_t db)
{
- struct vgic_translation_cache_entry *cte;
+ struct kvm_io_device *kvm_io_dev;
+ struct vgic_io_device *iodev;
- list_for_each_entry(cte, &dist->lpi_translation_cache, entry) {
- /*
- * If we hit a NULL entry, there is nothing after this
- * point.
- */
- if (!cte->irq)
- break;
+ kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, db);
+ if (!kvm_io_dev)
+ return ERR_PTR(-EINVAL);
- if (cte->db != db || cte->devid != devid ||
- cte->eventid != eventid)
- continue;
+ if (kvm_io_dev->ops != &kvm_io_gic_ops)
+ return ERR_PTR(-EINVAL);
- /*
- * Move this entry to the head, as it is the most
- * recently used.
- */
- if (!list_is_first(&cte->entry, &dist->lpi_translation_cache))
- list_move(&cte->entry, &dist->lpi_translation_cache);
+ iodev = container_of(kvm_io_dev, struct vgic_io_device, dev);
+ if (iodev->iodev_type != IODEV_ITS)
+ return ERR_PTR(-EINVAL);
- return cte->irq;
- }
+ return iodev->its;
+}
+
+static unsigned long vgic_its_cache_key(u32 devid, u32 eventid)
+{
+ return (((unsigned long)devid) << VITS_TYPER_IDBITS) | eventid;
- return NULL;
}
static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db,
u32 devid, u32 eventid)
{
- struct vgic_dist *dist = &kvm->arch.vgic;
+ unsigned long cache_key = vgic_its_cache_key(devid, eventid);
+ struct vgic_its *its;
struct vgic_irq *irq;
- unsigned long flags;
- raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+ if (devid > VITS_MAX_DEVID || eventid > VITS_MAX_EVENTID)
+ return NULL;
- irq = __vgic_its_check_cache(dist, db, devid, eventid);
+ its = __vgic_doorbell_to_its(kvm, db);
+ if (IS_ERR(its))
+ return NULL;
+
+ rcu_read_lock();
+
+ irq = xa_load(&its->translation_cache, cache_key);
if (!vgic_try_get_irq_kref(irq))
irq = NULL;
- raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+ rcu_read_unlock();
return irq;
}
@@ -619,41 +559,13 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its,
u32 devid, u32 eventid,
struct vgic_irq *irq)
{
- struct vgic_dist *dist = &kvm->arch.vgic;
- struct vgic_translation_cache_entry *cte;
- unsigned long flags;
- phys_addr_t db;
+ unsigned long cache_key = vgic_its_cache_key(devid, eventid);
+ struct vgic_irq *old;
/* Do not cache a directly injected interrupt */
if (irq->hw)
return;
- raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
-
- if (unlikely(list_empty(&dist->lpi_translation_cache)))
- goto out;
-
- /*
- * We could have raced with another CPU caching the same
- * translation behind our back, so let's check it is not in
- * already
- */
- db = its->vgic_its_base + GITS_TRANSLATER;
- if (__vgic_its_check_cache(dist, db, devid, eventid))
- goto out;
-
- /* Always reuse the last entry (LRU policy) */
- cte = list_last_entry(&dist->lpi_translation_cache,
- typeof(*cte), entry);
-
- /*
- * Caching the translation implies having an extra reference
- * to the interrupt, so drop the potential reference on what
- * was in the cache, and increment it on the new interrupt.
- */
- if (cte->irq)
- vgic_put_irq(kvm, cte->irq);
-
/*
* The irq refcount is guaranteed to be nonzero while holding the
* its_lock, as the ITE (and the reference it holds) cannot be freed.
@@ -661,39 +573,44 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its,
lockdep_assert_held(&its->its_lock);
vgic_get_irq_kref(irq);
- cte->db = db;
- cte->devid = devid;
- cte->eventid = eventid;
- cte->irq = irq;
+ /*
+ * We could have raced with another CPU caching the same
+ * translation behind our back, ensure we don't leak a
+ * reference if that is the case.
+ */
+ old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT);
+ if (old)
+ vgic_put_irq(kvm, old);
+}
- /* Move the new translation to the head of the list */
- list_move(&cte->entry, &dist->lpi_translation_cache);
+static void vgic_its_invalidate_cache(struct vgic_its *its)
+{
+ struct kvm *kvm = its->dev->kvm;
+ struct vgic_irq *irq;
+ unsigned long idx;
-out:
- raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+ xa_for_each(&its->translation_cache, idx, irq) {
+ xa_erase(&its->translation_cache, idx);
+ vgic_put_irq(kvm, irq);
+ }
}
-void vgic_its_invalidate_cache(struct kvm *kvm)
+void vgic_its_invalidate_all_caches(struct kvm *kvm)
{
- struct vgic_dist *dist = &kvm->arch.vgic;
- struct vgic_translation_cache_entry *cte;
- unsigned long flags;
+ struct kvm_device *dev;
+ struct vgic_its *its;
- raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+ rcu_read_lock();
- list_for_each_entry(cte, &dist->lpi_translation_cache, entry) {
- /*
- * If we hit a NULL entry, there is nothing after this
- * point.
- */
- if (!cte->irq)
- break;
+ list_for_each_entry_rcu(dev, &kvm->devices, vm_node) {
+ if (dev->ops != &kvm_arm_vgic_its_ops)
+ continue;
- vgic_put_irq(kvm, cte->irq);
- cte->irq = NULL;
+ its = dev->private;
+ vgic_its_invalidate_cache(its);
}
- raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+ rcu_read_unlock();
}
int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
@@ -725,8 +642,6 @@ int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi)
{
u64 address;
- struct kvm_io_device *kvm_io_dev;
- struct vgic_io_device *iodev;
if (!vgic_has_its(kvm))
return ERR_PTR(-ENODEV);
@@ -736,18 +651,7 @@ struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi)
address = (u64)msi->address_hi << 32 | msi->address_lo;
- kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address);
- if (!kvm_io_dev)
- return ERR_PTR(-EINVAL);
-
- if (kvm_io_dev->ops != &kvm_io_gic_ops)
- return ERR_PTR(-EINVAL);
-
- iodev = container_of(kvm_io_dev, struct vgic_io_device, dev);
- if (iodev->iodev_type != IODEV_ITS)
- return ERR_PTR(-EINVAL);
-
- return iodev->its;
+ return __vgic_doorbell_to_its(kvm, address);
}
/*
@@ -883,7 +787,7 @@ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its,
* don't bother here since we clear the ITTE anyway and the
* pending state is a property of the ITTE struct.
*/
- vgic_its_invalidate_cache(kvm);
+ vgic_its_invalidate_cache(its);
its_free_ite(kvm, ite);
return 0;
@@ -920,7 +824,7 @@ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
ite->collection = collection;
vcpu = collection_to_vcpu(kvm, collection);
- vgic_its_invalidate_cache(kvm);
+ vgic_its_invalidate_cache(its);
return update_affinity(ite->irq, vcpu);
}
@@ -955,7 +859,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
switch (type) {
case GITS_BASER_TYPE_DEVICE:
- if (id >= BIT_ULL(VITS_TYPER_DEVBITS))
+ if (id > VITS_MAX_DEVID)
return false;
break;
case GITS_BASER_TYPE_COLLECTION:
@@ -1167,7 +1071,8 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
}
/* Requires the its_lock to be held. */
-static void vgic_its_free_device(struct kvm *kvm, struct its_device *device)
+static void vgic_its_free_device(struct kvm *kvm, struct vgic_its *its,
+ struct its_device *device)
{
struct its_ite *ite, *temp;
@@ -1179,7 +1084,7 @@ static void vgic_its_free_device(struct kvm *kvm, struct its_device *device)
list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list)
its_free_ite(kvm, ite);
- vgic_its_invalidate_cache(kvm);
+ vgic_its_invalidate_cache(its);
list_del(&device->dev_list);
kfree(device);
@@ -1191,7 +1096,7 @@ static void vgic_its_free_device_list(struct kvm *kvm, struct vgic_its *its)
struct its_device *cur, *temp;
list_for_each_entry_safe(cur, temp, &its->device_list, dev_list)
- vgic_its_free_device(kvm, cur);
+ vgic_its_free_device(kvm, its, cur);
}
/* its lock must be held */
@@ -1250,7 +1155,7 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
* by removing the mapping and re-establishing it.
*/
if (device)
- vgic_its_free_device(kvm, device);
+ vgic_its_free_device(kvm, its, device);
/*
* The spec does not say whether unmapping a not-mapped device
@@ -1281,7 +1186,7 @@ static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its,
if (!valid) {
vgic_its_free_collection(its, coll_id);
- vgic_its_invalidate_cache(kvm);
+ vgic_its_invalidate_cache(its);
} else {
struct kvm_vcpu *vcpu;
@@ -1372,23 +1277,19 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
int vgic_its_invall(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
- int irq_count, i = 0;
- u32 *intids;
-
- irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids);
- if (irq_count < 0)
- return irq_count;
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct vgic_irq *irq;
+ unsigned long intid;
- for (i = 0; i < irq_count; i++) {
- struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intids[i]);
+ xa_for_each(&dist->lpi_xa, intid, irq) {
+ irq = vgic_get_irq(kvm, NULL, intid);
if (!irq)
continue;
+
update_lpi_config(kvm, irq, vcpu, false);
vgic_put_irq(kvm, irq);
}
- kfree(intids);
-
if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm)
its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe);
@@ -1431,10 +1332,10 @@ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its,
static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
u64 *its_cmd)
{
+ struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu1, *vcpu2;
struct vgic_irq *irq;
- u32 *intids;
- int irq_count, i;
+ unsigned long intid;
/* We advertise GITS_TYPER.PTA==0, making the address the vcpu ID */
vcpu1 = kvm_get_vcpu_by_id(kvm, its_cmd_get_target_addr(its_cmd));
@@ -1446,12 +1347,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
if (vcpu1 == vcpu2)
return 0;
- irq_count = vgic_copy_lpi_list(kvm, vcpu1, &intids);
- if (irq_count < 0)
- return irq_count;
-
- for (i = 0; i < irq_count; i++) {
- irq = vgic_get_irq(kvm, NULL, intids[i]);
+ xa_for_each(&dist->lpi_xa, intid, irq) {
+ irq = vgic_get_irq(kvm, NULL, intid);
if (!irq)
continue;
@@ -1460,9 +1357,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
vgic_put_irq(kvm, irq);
}
- vgic_its_invalidate_cache(kvm);
+ vgic_its_invalidate_cache(its);
- kfree(intids);
return 0;
}
@@ -1813,7 +1709,7 @@ static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
its->enabled = !!(val & GITS_CTLR_ENABLE);
if (!its->enabled)
- vgic_its_invalidate_cache(kvm);
+ vgic_its_invalidate_cache(its);
/*
* Try to process any pending commands. This function bails out early
@@ -1914,47 +1810,6 @@ out:
return ret;
}
-/* Default is 16 cached LPIs per vcpu */
-#define LPI_DEFAULT_PCPU_CACHE_SIZE 16
-
-void vgic_lpi_translation_cache_init(struct kvm *kvm)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
- unsigned int sz;
- int i;
-
- if (!list_empty(&dist->lpi_translation_cache))
- return;
-
- sz = atomic_read(&kvm->online_vcpus) * LPI_DEFAULT_PCPU_CACHE_SIZE;
-
- for (i = 0; i < sz; i++) {
- struct vgic_translation_cache_entry *cte;
-
- /* An allocation failure is not fatal */
- cte = kzalloc(sizeof(*cte), GFP_KERNEL_ACCOUNT);
- if (WARN_ON(!cte))
- break;
-
- INIT_LIST_HEAD(&cte->entry);
- list_add(&cte->entry, &dist->lpi_translation_cache);
- }
-}
-
-void vgic_lpi_translation_cache_destroy(struct kvm *kvm)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
- struct vgic_translation_cache_entry *cte, *tmp;
-
- vgic_its_invalidate_cache(kvm);
-
- list_for_each_entry_safe(cte, tmp,
- &dist->lpi_translation_cache, entry) {
- list_del(&cte->entry);
- kfree(cte);
- }
-}
-
#define INITIAL_BASER_VALUE \
(GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \
GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \
@@ -1987,8 +1842,6 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
kfree(its);
return ret;
}
-
- vgic_lpi_translation_cache_init(dev->kvm);
}
mutex_init(&its->its_lock);
@@ -2006,6 +1859,7 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
INIT_LIST_HEAD(&its->device_list);
INIT_LIST_HEAD(&its->collection_list);
+ xa_init(&its->translation_cache);
dev->kvm->arch.vgic.msis_require_devid = true;
dev->kvm->arch.vgic.has_its = true;
@@ -2036,6 +1890,8 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev)
vgic_its_free_device_list(kvm, its);
vgic_its_free_collection_list(kvm, its);
+ vgic_its_invalidate_cache(its);
+ xa_destroy(&its->translation_cache);
mutex_unlock(&its->its_lock);
kfree(its);
@@ -2438,7 +2294,7 @@ static int vgic_its_restore_dte(struct vgic_its *its, u32 id,
ret = vgic_its_restore_itt(its, dev);
if (ret) {
- vgic_its_free_device(its->dev->kvm, dev);
+ vgic_its_free_device(its->dev->kvm, its, dev);
return ret;
}
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index c15ee1df036a..a3983a631b5a 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -277,7 +277,7 @@ static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
return;
vgic_flush_pending_lpis(vcpu);
- vgic_its_invalidate_cache(vcpu->kvm);
+ vgic_its_invalidate_all_caches(vcpu->kvm);
atomic_set_release(&vgic_cpu->ctlr, 0);
} else {
ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr, 0,
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index fcc5747f51e9..f07b3ddff7d4 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -29,9 +29,8 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
* its->cmd_lock (mutex)
* its->its_lock (mutex)
* vgic_cpu->ap_list_lock must be taken with IRQs disabled
- * kvm->lpi_list_lock must be taken with IRQs disabled
- * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled
- * vgic_irq->irq_lock must be taken with IRQs disabled
+ * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled
+ * vgic_irq->irq_lock must be taken with IRQs disabled
*
* As the ap_list_lock might be taken from the timer interrupt handler,
* we have to disable IRQs before taking this lock and everything lower
@@ -126,7 +125,6 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
__xa_erase(&dist->lpi_xa, irq->intid);
xa_unlock_irqrestore(&dist->lpi_xa, flags);
- atomic_dec(&dist->lpi_count);
kfree_rcu(irq, rcu);
}
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 4b93528e6a89..6106ebd5ba42 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -16,6 +16,7 @@
#define INTERRUPT_ID_BITS_SPIS 10
#define INTERRUPT_ID_BITS_ITS 16
+#define VGIC_LPI_MAX_INTID ((1 << INTERRUPT_ID_BITS_ITS) - 1)
#define VGIC_PRI_BITS 5
#define vgic_irq_is_sgi(intid) ((intid) < VGIC_NR_SGIS)
@@ -328,14 +329,11 @@ static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size)
}
bool vgic_lpis_enabled(struct kvm_vcpu *vcpu);
-int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr);
int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
u32 devid, u32 eventid, struct vgic_irq **irq);
struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi);
int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi);
-void vgic_lpi_translation_cache_init(struct kvm *kvm);
-void vgic_lpi_translation_cache_destroy(struct kvm *kvm);
-void vgic_its_invalidate_cache(struct kvm *kvm);
+void vgic_its_invalidate_all_caches(struct kvm *kvm);
/* GICv4.1 MMIO interface */
int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq);
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index c5b461dda438..122021f9bdfc 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -943,7 +943,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
emit(A64_UXTH(is64, dst, dst), ctx);
break;
case 32:
- emit(A64_REV32(is64, dst, dst), ctx);
+ emit(A64_REV32(0, dst, dst), ctx);
/* upper 32 bits already cleared */
break;
case 64:
@@ -1256,7 +1256,7 @@ emit_cond_jmp:
} else {
emit_a64_mov_i(1, tmp, off, ctx);
if (sign_extend)
- emit(A64_LDRSW(dst, src_adj, off_adj), ctx);
+ emit(A64_LDRSW(dst, src, tmp), ctx);
else
emit(A64_LDR32(dst, src, tmp), ctx);
}
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index 1140051a0c45..1150b77fa281 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -63,6 +63,7 @@ SECTIONS
STABS_DEBUG
DWARF_DEBUG
ELF_DETAILS
+ .hexagon.attributes 0 : { *(.hexagon.attributes) }
DISCARDS
}
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 06ef440d16ce..516dc7022bd7 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -619,15 +619,6 @@ config MACH_EYEQ5
bool
-config FIT_IMAGE_FDT_EPM5
- bool "Include FDT for Mobileye EyeQ5 development platforms"
- depends on MACH_EYEQ5
- default n
- help
- Enable this to include the FDT for the EyeQ5 development platforms
- from Mobileye in the FIT kernel image.
- This requires u-boot on the platform.
-
config MACH_NINTENDO64
bool "Nintendo 64 console"
select CEVT_R4K
@@ -1011,6 +1002,15 @@ config CAVIUM_OCTEON_SOC
endchoice
+config FIT_IMAGE_FDT_EPM5
+ bool "Include FDT for Mobileye EyeQ5 development platforms"
+ depends on MACH_EYEQ5
+ default n
+ help
+ Enable this to include the FDT for the EyeQ5 development platforms
+ from Mobileye in the FIT kernel image.
+ This requires u-boot on the platform.
+
source "arch/mips/alchemy/Kconfig"
source "arch/mips/ath25/Kconfig"
source "arch/mips/ath79/Kconfig"
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index 8d98af5c7201..9a8393e6b4a8 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -21,7 +21,8 @@
void __init early_init_devtree(void *params)
{
- __be32 *dtb = (u32 *)__dtb_start;
+ __be32 __maybe_unused *dtb = (u32 *)__dtb_start;
+
#if defined(CONFIG_NIOS2_DTB_AT_PHYS_ADDR)
if (be32_to_cpup((__be32 *)CONFIG_NIOS2_DTB_PHYS_ADDR) ==
OF_DT_HEADER) {
@@ -30,8 +31,11 @@ void __init early_init_devtree(void *params)
return;
}
#endif
+
+#ifdef CONFIG_NIOS2_DTB_SOURCE_BOOL
if (be32_to_cpu((__be32) *dtb) == OF_DT_HEADER)
params = (void *)__dtb_start;
+#endif
early_init_dt_scan(params);
}
diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h
new file mode 100644
index 000000000000..47c5a1991d10
--- /dev/null
+++ b/arch/parisc/include/asm/mman.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <uapi/asm/mman.h>
+
+/* PARISC cannot allow mdwe as it needs writable stacks */
+static inline bool arch_memory_deny_write_exec_supported(void)
+{
+ return false;
+}
+#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
+
+#endif /* __ASM_MMAN_H__ */
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index f0a4cf01e85c..78302f6c2580 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -4,7 +4,6 @@
#ifndef __ASSEMBLY__
-#include <asm/page.h>
#include <asm/vdso/timebase.h>
#include <asm/barrier.h>
#include <asm/unistd.h>
@@ -95,7 +94,7 @@ const struct vdso_data *__arch_get_vdso_data(void);
static __always_inline
const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
{
- return (void *)vd + PAGE_SIZE;
+ return (void *)vd + (1U << CONFIG_PAGE_SHIFT);
}
#endif
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 252d63942f34..5b3115a19852 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -151,7 +151,7 @@ endif
endif
vdso-install-y += arch/riscv/kernel/vdso/vdso.so.dbg
-vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg:../compat_vdso/compat_vdso.so
+vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg
ifneq ($(CONFIG_XIP_KERNEL),y)
ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_ARCH_CANAAN),yy)
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 97fcde30e247..9f8ea0e33eb1 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -593,6 +593,12 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
return ptep_test_and_clear_young(vma, address, ptep);
}
+#define pgprot_nx pgprot_nx
+static inline pgprot_t pgprot_nx(pgprot_t _prot)
+{
+ return __pgprot(pgprot_val(_prot) & ~_PAGE_EXEC);
+}
+
#define pgprot_noncached pgprot_noncached
static inline pgprot_t pgprot_noncached(pgprot_t _prot)
{
diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h
index 980094c2e976..ac80216549ff 100644
--- a/arch/riscv/include/asm/syscall_wrapper.h
+++ b/arch/riscv/include/asm/syscall_wrapper.h
@@ -36,7 +36,8 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
ulong) \
__attribute__((alias(__stringify(___se_##prefix##name)))); \
__diag_pop(); \
- static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
+ static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
+ __used; \
static long ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__))
#define SC_RISCV_REGS_TO_ARGS(x, ...) \
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index ec0cab9fbddd..72ec1d9bd3f3 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -319,7 +319,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
#define __get_kernel_nofault(dst, src, type, err_label) \
do { \
- long __kr_err; \
+ long __kr_err = 0; \
\
__get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
if (unlikely(__kr_err)) \
@@ -328,7 +328,7 @@ do { \
#define __put_kernel_nofault(dst, src, type, err_label) \
do { \
- long __kr_err; \
+ long __kr_err = 0; \
\
__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
if (unlikely(__kr_err)) \
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
index 10aaa83db89e..95050ebe9ad0 100644
--- a/arch/riscv/include/uapi/asm/auxvec.h
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -34,7 +34,7 @@
#define AT_L3_CACHEGEOMETRY 47
/* entries in ARCH_DLINFO */
-#define AT_VECTOR_SIZE_ARCH 9
+#define AT_VECTOR_SIZE_ARCH 10
#define AT_MINSIGSTKSZ 51
#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile
index 62fa393b2eb2..3df4cb788c1f 100644
--- a/arch/riscv/kernel/compat_vdso/Makefile
+++ b/arch/riscv/kernel/compat_vdso/Makefile
@@ -74,5 +74,5 @@ quiet_cmd_compat_vdsold = VDSOLD $@
rm $@.tmp
# actual build commands
-quiet_cmd_compat_vdsoas = VDSOAS $@
+quiet_cmd_compat_vdsoas = VDSOAS $@
cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $<
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 37e87fdcf6a0..30e12b310cab 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -80,6 +80,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
*/
lockdep_assert_held(&text_mutex);
+ preempt_disable();
+
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
@@ -92,6 +94,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
+ preempt_enable();
+
return 0;
}
NOKPROBE_SYMBOL(__patch_insn_set);
@@ -122,6 +126,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
if (!riscv_patch_in_stop_machine)
lockdep_assert_held(&text_mutex);
+ preempt_disable();
+
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
@@ -134,6 +140,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
+ preempt_enable();
+
return ret;
}
NOKPROBE_SYMBOL(__patch_insn_write);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 92922dbd5b5c..e4bc61c4e58a 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -27,8 +27,6 @@
#include <asm/vector.h>
#include <asm/cpufeature.h>
-register unsigned long gp_in_global __asm__("gp");
-
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
@@ -37,7 +35,7 @@ EXPORT_SYMBOL(__stack_chk_guard);
extern asmlinkage void ret_from_fork(void);
-void arch_cpu_idle(void)
+void noinstr arch_cpu_idle(void)
{
cpu_do_idle();
}
@@ -207,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
if (unlikely(args->fn)) {
/* Kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
- childregs->gp = gp_in_global;
/* Supervisor/Machine, irqs on: */
childregs->status = SR_PP | SR_PIE;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 501e66debf69..5a2edd7f027e 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -119,6 +119,13 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
struct __sc_riscv_v_state __user *state = sc_vec;
void __user *datap;
+ /*
+ * Mark the vstate as clean prior performing the actual copy,
+ * to avoid getting the vstate incorrectly clobbered by the
+ * discarded vector state.
+ */
+ riscv_v_vstate_set_restore(current, regs);
+
/* Copy everything of __sc_riscv_v_state except datap. */
err = __copy_from_user(&current->thread.vstate, &state->v_state,
offsetof(struct __riscv_v_ext_state, datap));
@@ -133,13 +140,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
* Copy the whole vector content from user space datap. Use
* copy_from_user to prevent information leak.
*/
- err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
- if (unlikely(err))
- return err;
-
- riscv_v_vstate_set_restore(current, regs);
-
- return err;
+ return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
}
#else
#define save_v_state(task, regs) (0)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 868d6280cf66..05a16b1f0aee 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -122,7 +122,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
pr_cont("\n");
__show_regs(regs);
- dump_instr(KERN_EMERG, regs);
+ dump_instr(KERN_INFO, regs);
}
force_sig_fault(signo, code, (void __user *)addr);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 9b517fe1b8a8..272c431ac5b9 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -37,6 +37,7 @@ endif
# Disable -pg to prevent insert call site
CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
# Disable profiling and instrumentation for VDSO code
GCOV_PROFILE := n
diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c
index 39e72aa016a4..b467ba5ed910 100644
--- a/arch/riscv/kvm/aia_aplic.c
+++ b/arch/riscv/kvm/aia_aplic.c
@@ -137,11 +137,21 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending)
raw_spin_lock_irqsave(&irqd->lock, flags);
sm = irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK;
- if (!pending &&
- ((sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) ||
- (sm == APLIC_SOURCECFG_SM_LEVEL_LOW)))
+ if (sm == APLIC_SOURCECFG_SM_INACTIVE)
goto skip_write_pending;
+ if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH ||
+ sm == APLIC_SOURCECFG_SM_LEVEL_LOW) {
+ if (!pending)
+ goto skip_write_pending;
+ if ((irqd->state & APLIC_IRQ_STATE_INPUT) &&
+ sm == APLIC_SOURCECFG_SM_LEVEL_LOW)
+ goto skip_write_pending;
+ if (!(irqd->state & APLIC_IRQ_STATE_INPUT) &&
+ sm == APLIC_SOURCECFG_SM_LEVEL_HIGH)
+ goto skip_write_pending;
+ }
+
if (pending)
irqd->state |= APLIC_IRQ_STATE_PENDING;
else
@@ -187,16 +197,31 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled)
static bool aplic_read_input(struct aplic *aplic, u32 irq)
{
- bool ret;
- unsigned long flags;
+ u32 sourcecfg, sm, raw_input, irq_inverted;
struct aplic_irq *irqd;
+ unsigned long flags;
+ bool ret = false;
if (!irq || aplic->nr_irqs <= irq)
return false;
irqd = &aplic->irqs[irq];
raw_spin_lock_irqsave(&irqd->lock, flags);
- ret = (irqd->state & APLIC_IRQ_STATE_INPUT) ? true : false;
+
+ sourcecfg = irqd->sourcecfg;
+ if (sourcecfg & APLIC_SOURCECFG_D)
+ goto skip;
+
+ sm = sourcecfg & APLIC_SOURCECFG_SM_MASK;
+ if (sm == APLIC_SOURCECFG_SM_INACTIVE)
+ goto skip;
+
+ raw_input = (irqd->state & APLIC_IRQ_STATE_INPUT) ? 1 : 0;
+ irq_inverted = (sm == APLIC_SOURCECFG_SM_LEVEL_LOW ||
+ sm == APLIC_SOURCECFG_SM_EDGE_FALL) ? 1 : 0;
+ ret = !!(raw_input ^ irq_inverted);
+
+skip:
raw_spin_unlock_irqrestore(&irqd->lock, flags);
return ret;
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index f4a6124d25c9..994adc26db4b 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -986,7 +986,7 @@ static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu,
static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu)
{
- return copy_isa_ext_reg_indices(vcpu, NULL);;
+ return copy_isa_ext_reg_indices(vcpu, NULL);
}
static int copy_sbi_ext_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 893566e004b7..07d743f87b3f 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -99,7 +99,7 @@ static void __ipi_flush_tlb_range_asid(void *info)
local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
}
-static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
+static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
unsigned long start, unsigned long size,
unsigned long stride)
{
@@ -200,7 +200,7 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- __flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID,
+ __flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID,
start, end - start, PAGE_SIZE);
}
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index aac190085472..1adf2f39ce59 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1463,6 +1463,22 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
if (ret < 0)
return ret;
+ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
+ const struct btf_func_model *fm;
+ int idx;
+
+ fm = bpf_jit_find_kfunc_model(ctx->prog, insn);
+ if (!fm)
+ return -EINVAL;
+
+ for (idx = 0; idx < fm->nr_args; idx++) {
+ u8 reg = bpf_to_rv_reg(BPF_REG_1 + idx, ctx);
+
+ if (fm->arg_size[idx] == sizeof(int))
+ emit_sextw(reg, reg, ctx);
+ }
+ }
+
ret = emit_call(addr, fixed_addr, ctx);
if (ret)
return ret;
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 7138d189cc42..0c4cad7d5a5b 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,31 +15,31 @@
#include <asm/barrier.h>
#include <asm/cmpxchg.h>
-static inline int arch_atomic_read(const atomic_t *v)
+static __always_inline int arch_atomic_read(const atomic_t *v)
{
return __atomic_read(v);
}
#define arch_atomic_read arch_atomic_read
-static inline void arch_atomic_set(atomic_t *v, int i)
+static __always_inline void arch_atomic_set(atomic_t *v, int i)
{
__atomic_set(v, i);
}
#define arch_atomic_set arch_atomic_set
-static inline int arch_atomic_add_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
{
return __atomic_add_barrier(i, &v->counter) + i;
}
#define arch_atomic_add_return arch_atomic_add_return
-static inline int arch_atomic_fetch_add(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
{
return __atomic_add_barrier(i, &v->counter);
}
#define arch_atomic_fetch_add arch_atomic_fetch_add
-static inline void arch_atomic_add(int i, atomic_t *v)
+static __always_inline void arch_atomic_add(int i, atomic_t *v)
{
__atomic_add(i, &v->counter);
}
@@ -50,11 +50,11 @@ static inline void arch_atomic_add(int i, atomic_t *v)
#define arch_atomic_fetch_sub(_i, _v) arch_atomic_fetch_add(-(int)(_i), _v)
#define ATOMIC_OPS(op) \
-static inline void arch_atomic_##op(int i, atomic_t *v) \
+static __always_inline void arch_atomic_##op(int i, atomic_t *v) \
{ \
__atomic_##op(i, &v->counter); \
} \
-static inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
+static __always_inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
{ \
return __atomic_##op##_barrier(i, &v->counter); \
}
@@ -74,7 +74,7 @@ ATOMIC_OPS(xor)
#define arch_atomic_xchg(v, new) (arch_xchg(&((v)->counter), new))
-static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
{
return __atomic_cmpxchg(&v->counter, old, new);
}
@@ -82,31 +82,31 @@ static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
#define ATOMIC64_INIT(i) { (i) }
-static inline s64 arch_atomic64_read(const atomic64_t *v)
+static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
{
return __atomic64_read(v);
}
#define arch_atomic64_read arch_atomic64_read
-static inline void arch_atomic64_set(atomic64_t *v, s64 i)
+static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
{
__atomic64_set(v, i);
}
#define arch_atomic64_set arch_atomic64_set
-static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
{
return __atomic64_add_barrier(i, (long *)&v->counter) + i;
}
#define arch_atomic64_add_return arch_atomic64_add_return
-static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
return __atomic64_add_barrier(i, (long *)&v->counter);
}
#define arch_atomic64_fetch_add arch_atomic64_fetch_add
-static inline void arch_atomic64_add(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
{
__atomic64_add(i, (long *)&v->counter);
}
@@ -114,20 +114,20 @@ static inline void arch_atomic64_add(s64 i, atomic64_t *v)
#define arch_atomic64_xchg(v, new) (arch_xchg(&((v)->counter), new))
-static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
+static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
return __atomic64_cmpxchg((long *)&v->counter, old, new);
}
#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
-#define ATOMIC64_OPS(op) \
-static inline void arch_atomic64_##op(s64 i, atomic64_t *v) \
-{ \
- __atomic64_##op(i, (long *)&v->counter); \
-} \
-static inline long arch_atomic64_fetch_##op(s64 i, atomic64_t *v) \
-{ \
- return __atomic64_##op##_barrier(i, (long *)&v->counter); \
+#define ATOMIC64_OPS(op) \
+static __always_inline void arch_atomic64_##op(s64 i, atomic64_t *v) \
+{ \
+ __atomic64_##op(i, (long *)&v->counter); \
+} \
+static __always_inline long arch_atomic64_fetch_##op(s64 i, atomic64_t *v) \
+{ \
+ return __atomic64_##op##_barrier(i, (long *)&v->counter); \
}
ATOMIC64_OPS(and)
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index 50510e08b893..7fa5f96a553a 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -8,7 +8,7 @@
#ifndef __ARCH_S390_ATOMIC_OPS__
#define __ARCH_S390_ATOMIC_OPS__
-static inline int __atomic_read(const atomic_t *v)
+static __always_inline int __atomic_read(const atomic_t *v)
{
int c;
@@ -18,14 +18,14 @@ static inline int __atomic_read(const atomic_t *v)
return c;
}
-static inline void __atomic_set(atomic_t *v, int i)
+static __always_inline void __atomic_set(atomic_t *v, int i)
{
asm volatile(
" st %1,%0\n"
: "=R" (v->counter) : "d" (i));
}
-static inline s64 __atomic64_read(const atomic64_t *v)
+static __always_inline s64 __atomic64_read(const atomic64_t *v)
{
s64 c;
@@ -35,7 +35,7 @@ static inline s64 __atomic64_read(const atomic64_t *v)
return c;
}
-static inline void __atomic64_set(atomic64_t *v, s64 i)
+static __always_inline void __atomic64_set(atomic64_t *v, s64 i)
{
asm volatile(
" stg %1,%0\n"
@@ -45,7 +45,7 @@ static inline void __atomic64_set(atomic64_t *v, s64 i)
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
#define __ATOMIC_OP(op_name, op_type, op_string, op_barrier) \
-static inline op_type op_name(op_type val, op_type *ptr) \
+static __always_inline op_type op_name(op_type val, op_type *ptr) \
{ \
op_type old; \
\
@@ -96,7 +96,7 @@ __ATOMIC_CONST_OPS(__atomic64_add_const, long, "agsi")
#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
#define __ATOMIC_OP(op_name, op_string) \
-static inline int op_name(int val, int *ptr) \
+static __always_inline int op_name(int val, int *ptr) \
{ \
int old, new; \
\
@@ -122,7 +122,7 @@ __ATOMIC_OPS(__atomic_xor, "xr")
#undef __ATOMIC_OPS
#define __ATOMIC64_OP(op_name, op_string) \
-static inline long op_name(long val, long *ptr) \
+static __always_inline long op_name(long val, long *ptr) \
{ \
long old, new; \
\
@@ -154,7 +154,7 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr")
#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-static inline int __atomic_cmpxchg(int *ptr, int old, int new)
+static __always_inline int __atomic_cmpxchg(int *ptr, int old, int new)
{
asm volatile(
" cs %[old],%[new],%[ptr]"
@@ -164,7 +164,7 @@ static inline int __atomic_cmpxchg(int *ptr, int old, int new)
return old;
}
-static inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new)
+static __always_inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new)
{
int old_expected = old;
@@ -176,7 +176,7 @@ static inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new)
return old == old_expected;
}
-static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
+static __always_inline long __atomic64_cmpxchg(long *ptr, long old, long new)
{
asm volatile(
" csg %[old],%[new],%[ptr]"
@@ -186,7 +186,7 @@ static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
return old;
}
-static inline bool __atomic64_cmpxchg_bool(long *ptr, long old, long new)
+static __always_inline bool __atomic64_cmpxchg_bool(long *ptr, long old, long new)
{
long old_expected = old;
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index bf15da0fedbc..0e3da500e98c 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -12,12 +12,12 @@
#define PREEMPT_NEED_RESCHED 0x80000000
#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED)
-static inline int preempt_count(void)
+static __always_inline int preempt_count(void)
{
return READ_ONCE(S390_lowcore.preempt_count) & ~PREEMPT_NEED_RESCHED;
}
-static inline void preempt_count_set(int pc)
+static __always_inline void preempt_count_set(int pc)
{
int old, new;
@@ -29,22 +29,22 @@ static inline void preempt_count_set(int pc)
old, new) != old);
}
-static inline void set_preempt_need_resched(void)
+static __always_inline void set_preempt_need_resched(void)
{
__atomic_and(~PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count);
}
-static inline void clear_preempt_need_resched(void)
+static __always_inline void clear_preempt_need_resched(void)
{
__atomic_or(PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count);
}
-static inline bool test_preempt_need_resched(void)
+static __always_inline bool test_preempt_need_resched(void)
{
return !(READ_ONCE(S390_lowcore.preempt_count) & PREEMPT_NEED_RESCHED);
}
-static inline void __preempt_count_add(int val)
+static __always_inline void __preempt_count_add(int val)
{
/*
* With some obscure config options and CONFIG_PROFILE_ALL_BRANCHES
@@ -59,17 +59,17 @@ static inline void __preempt_count_add(int val)
__atomic_add(val, &S390_lowcore.preempt_count);
}
-static inline void __preempt_count_sub(int val)
+static __always_inline void __preempt_count_sub(int val)
{
__preempt_count_add(-val);
}
-static inline bool __preempt_count_dec_and_test(void)
+static __always_inline bool __preempt_count_dec_and_test(void)
{
return __atomic_add(-1, &S390_lowcore.preempt_count) == 1;
}
-static inline bool should_resched(int preempt_offset)
+static __always_inline bool should_resched(int preempt_offset)
{
return unlikely(READ_ONCE(S390_lowcore.preempt_count) ==
preempt_offset);
@@ -79,45 +79,45 @@ static inline bool should_resched(int preempt_offset)
#define PREEMPT_ENABLED (0)
-static inline int preempt_count(void)
+static __always_inline int preempt_count(void)
{
return READ_ONCE(S390_lowcore.preempt_count);
}
-static inline void preempt_count_set(int pc)
+static __always_inline void preempt_count_set(int pc)
{
S390_lowcore.preempt_count = pc;
}
-static inline void set_preempt_need_resched(void)
+static __always_inline void set_preempt_need_resched(void)
{
}
-static inline void clear_preempt_need_resched(void)
+static __always_inline void clear_preempt_need_resched(void)
{
}
-static inline bool test_preempt_need_resched(void)
+static __always_inline bool test_preempt_need_resched(void)
{
return false;
}
-static inline void __preempt_count_add(int val)
+static __always_inline void __preempt_count_add(int val)
{
S390_lowcore.preempt_count += val;
}
-static inline void __preempt_count_sub(int val)
+static __always_inline void __preempt_count_sub(int val)
{
S390_lowcore.preempt_count -= val;
}
-static inline bool __preempt_count_dec_and_test(void)
+static __always_inline bool __preempt_count_dec_and_test(void)
{
return !--S390_lowcore.preempt_count && tif_need_resched();
}
-static inline bool should_resched(int preempt_offset)
+static __always_inline bool should_resched(int preempt_offset)
{
return unlikely(preempt_count() == preempt_offset &&
tif_need_resched());
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 787394978bc0..3dc85638bc63 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -635,6 +635,7 @@ SYM_DATA_START_LOCAL(daton_psw)
SYM_DATA_END(daton_psw)
.section .rodata, "a"
+ .balign 8
#define SYSCALL(esame,emu) .quad __s390x_ ## esame
SYM_DATA_START(sys_call_table)
#include "asm/syscall_table.h"
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 823d652e3917..4ad472d130a3 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -90,7 +90,6 @@ static void paicrypt_event_destroy(struct perf_event *event)
event->cpu);
struct paicrypt_map *cpump = mp->mapptr;
- cpump->event = NULL;
static_branch_dec(&pai_key);
mutex_lock(&pai_reserve_mutex);
debug_sprintf_event(cfm_dbg, 5, "%s event %#llx cpu %d users %d"
@@ -356,10 +355,15 @@ static int paicrypt_add(struct perf_event *event, int flags)
static void paicrypt_stop(struct perf_event *event, int flags)
{
- if (!event->attr.sample_period) /* Counting */
+ struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
+ struct paicrypt_map *cpump = mp->mapptr;
+
+ if (!event->attr.sample_period) { /* Counting */
paicrypt_read(event);
- else /* Sampling */
+ } else { /* Sampling */
perf_sched_cb_dec(event->pmu);
+ cpump->event = NULL;
+ }
event->hw.state = PERF_HES_STOPPED;
}
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 616a25606cd6..a6da7e0cc7a6 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -122,7 +122,6 @@ static void paiext_event_destroy(struct perf_event *event)
free_page(PAI_SAVE_AREA(event));
mutex_lock(&paiext_reserve_mutex);
- cpump->event = NULL;
if (refcount_dec_and_test(&cpump->refcnt)) /* Last reference gone */
paiext_free(mp);
paiext_root_free();
@@ -362,10 +361,15 @@ static int paiext_add(struct perf_event *event, int flags)
static void paiext_stop(struct perf_event *event, int flags)
{
- if (!event->attr.sample_period) /* Counting */
+ struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
+ struct paiext_map *cpump = mp->mapptr;
+
+ if (!event->attr.sample_period) { /* Counting */
paiext_read(event);
- else /* Sampling */
+ } else { /* Sampling */
perf_sched_cb_dec(event->pmu);
+ cpump->event = NULL;
+ }
event->hw.state = PERF_HES_STOPPED;
}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index c421dd44ffbe..0c66b32e0f9f 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -75,7 +75,7 @@ static enum fault_type get_fault_type(struct pt_regs *regs)
if (!IS_ENABLED(CONFIG_PGSTE))
return KERNEL_FAULT;
gmap = (struct gmap *)S390_lowcore.gmap;
- if (regs->cr1 == gmap->asce)
+ if (gmap && gmap->asce == regs->cr1)
return GMAP_FAULT;
return KERNEL_FAULT;
}
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index b418333bb086..5af0402e94b8 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -516,11 +516,12 @@ static void bpf_skip(struct bpf_jit *jit, int size)
* PLT for hotpatchable calls. The calling convention is the same as for the
* ftrace hotpatch trampolines: %r0 is return address, %r1 is clobbered.
*/
-extern const char bpf_plt[];
-extern const char bpf_plt_ret[];
-extern const char bpf_plt_target[];
-extern const char bpf_plt_end[];
-#define BPF_PLT_SIZE 32
+struct bpf_plt {
+ char code[16];
+ void *ret;
+ void *target;
+} __packed;
+extern const struct bpf_plt bpf_plt;
asm(
".pushsection .rodata\n"
" .balign 8\n"
@@ -531,15 +532,14 @@ asm(
" .balign 8\n"
"bpf_plt_ret: .quad 0\n"
"bpf_plt_target: .quad 0\n"
- "bpf_plt_end:\n"
" .popsection\n"
);
-static void bpf_jit_plt(void *plt, void *ret, void *target)
+static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target)
{
- memcpy(plt, bpf_plt, BPF_PLT_SIZE);
- *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret;
- *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret;
+ memcpy(plt, &bpf_plt, sizeof(*plt));
+ plt->ret = ret;
+ plt->target = target;
}
/*
@@ -662,9 +662,9 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
jit->prg = ALIGN(jit->prg, 8);
jit->prologue_plt = jit->prg;
if (jit->prg_buf)
- bpf_jit_plt(jit->prg_buf + jit->prg,
+ bpf_jit_plt((struct bpf_plt *)(jit->prg_buf + jit->prg),
jit->prg_buf + jit->prologue_plt_ret, NULL);
- jit->prg += BPF_PLT_SIZE;
+ jit->prg += sizeof(struct bpf_plt);
}
static int get_probe_mem_regno(const u8 *insn)
@@ -2040,9 +2040,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
struct bpf_jit jit;
int pass;
- if (WARN_ON_ONCE(bpf_plt_end - bpf_plt != BPF_PLT_SIZE))
- return orig_fp;
-
if (!fp->jit_requested)
return orig_fp;
@@ -2148,14 +2145,11 @@ bool bpf_jit_supports_far_kfunc_call(void)
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
+ struct bpf_plt expected_plt, current_plt, new_plt, *plt;
struct {
u16 opc;
s32 disp;
} __packed insn;
- char expected_plt[BPF_PLT_SIZE];
- char current_plt[BPF_PLT_SIZE];
- char new_plt[BPF_PLT_SIZE];
- char *plt;
char *ret;
int err;
@@ -2174,18 +2168,18 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
*/
} else {
/* Verify the PLT. */
- plt = (char *)ip + (insn.disp << 1);
- err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE);
+ plt = ip + (insn.disp << 1);
+ err = copy_from_kernel_nofault(&current_plt, plt,
+ sizeof(current_plt));
if (err < 0)
return err;
ret = (char *)ip + 6;
- bpf_jit_plt(expected_plt, ret, old_addr);
- if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE))
+ bpf_jit_plt(&expected_plt, ret, old_addr);
+ if (memcmp(&current_plt, &expected_plt, sizeof(current_plt)))
return -EINVAL;
/* Adjust the call address. */
- bpf_jit_plt(new_plt, ret, new_addr);
- s390_kernel_write(plt + (bpf_plt_target - bpf_plt),
- new_plt + (bpf_plt_target - bpf_plt),
+ bpf_jit_plt(&new_plt, ret, new_addr);
+ s390_kernel_write(&plt->target, &new_plt.target,
sizeof(void *));
}
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 6a1f36df6a18..cf0ad89f5639 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -28,7 +28,7 @@ obj-y += net/
obj-$(CONFIG_KEXEC_FILE) += purgatory/
-obj-y += virt/svm/
+obj-y += virt/
# for cleaning
subdir- += boot tools
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 39886bab943a..4fff6ed46e90 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2439,6 +2439,8 @@ config USE_X86_SEG_SUPPORT
# with named address spaces - see GCC PR sanitizer/111736.
#
depends on !KASAN
+ # -fsanitize=thread (KCSAN) is also incompatible.
+ depends on !KCSAN
config CC_HAS_SLS
def_bool $(cc-option,-mharden-sls=all)
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 662d9d4033e6..5ab93fcdd691 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -251,8 +251,6 @@ archheaders:
libs-y += arch/x86/lib/
-core-y += arch/x86/virt/
-
# drivers-y are linked after core-y
drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
drivers-$(CONFIG_PCI) += arch/x86/pci/
diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S
index 719e939050cb..876fc6d46a13 100644
--- a/arch/x86/boot/compressed/efi_mixed.S
+++ b/arch/x86/boot/compressed/efi_mixed.S
@@ -15,10 +15,12 @@
*/
#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/page_types.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
+#include <asm/setup.h>
.code64
.text
@@ -149,6 +151,7 @@ SYM_FUNC_END(__efi64_thunk)
SYM_FUNC_START(efi32_stub_entry)
call 1f
1: popl %ecx
+ leal (efi32_boot_args - 1b)(%ecx), %ebx
/* Clear BSS */
xorl %eax, %eax
@@ -163,6 +166,7 @@ SYM_FUNC_START(efi32_stub_entry)
popl %ecx
popl %edx
popl %esi
+ movl %esi, 8(%ebx)
jmp efi32_entry
SYM_FUNC_END(efi32_stub_entry)
#endif
@@ -239,8 +243,6 @@ SYM_FUNC_END(efi_enter32)
*
* Arguments: %ecx image handle
* %edx EFI system table pointer
- * %esi struct bootparams pointer (or NULL when not using
- * the EFI handover protocol)
*
* Since this is the point of no return for ordinary execution, no registers
* are considered live except for the function parameters. [Note that the EFI
@@ -266,9 +268,18 @@ SYM_FUNC_START_LOCAL(efi32_entry)
leal (efi32_boot_args - 1b)(%ebx), %ebx
movl %ecx, 0(%ebx)
movl %edx, 4(%ebx)
- movl %esi, 8(%ebx)
movb $0x0, 12(%ebx) // efi_is64
+ /*
+ * Allocate some memory for a temporary struct boot_params, which only
+ * needs the minimal pieces that startup_32() relies on.
+ */
+ subl $PARAM_SIZE, %esp
+ movl %esp, %esi
+ movl $PAGE_SIZE, BP_kernel_alignment(%esi)
+ movl $_end - 1b, BP_init_size(%esi)
+ subl $startup_32 - 1b, BP_init_size(%esi)
+
/* Disable paging */
movl %cr0, %eax
btrl $X86_CR0_PG_BIT, %eax
@@ -294,8 +305,7 @@ SYM_FUNC_START(efi32_pe_entry)
movl 8(%ebp), %ecx // image_handle
movl 12(%ebp), %edx // sys_table
- xorl %esi, %esi
- jmp efi32_entry // pass %ecx, %edx, %esi
+ jmp efi32_entry // pass %ecx, %edx
// no other registers remain live
2: popl %edi // restore callee-save registers
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index d07be9d05cd0..b31ef2424d19 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -3,19 +3,28 @@
* Confidential Computing Platform Capability checks
*
* Copyright (C) 2021 Advanced Micro Devices, Inc.
+ * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*
* Author: Tom Lendacky <thomas.lendacky@amd.com>
*/
#include <linux/export.h>
#include <linux/cc_platform.h>
+#include <linux/string.h>
+#include <linux/random.h>
+#include <asm/archrandom.h>
#include <asm/coco.h>
#include <asm/processor.h>
enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE;
u64 cc_mask __ro_after_init;
+static struct cc_attr_flags {
+ __u64 host_sev_snp : 1,
+ __resv : 63;
+} cc_flags;
+
static bool noinstr intel_cc_platform_has(enum cc_attr attr)
{
switch (attr) {
@@ -89,6 +98,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr)
case CC_ATTR_GUEST_SEV_SNP:
return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
+ case CC_ATTR_HOST_SEV_SNP:
+ return cc_flags.host_sev_snp;
+
default:
return false;
}
@@ -148,3 +160,84 @@ u64 cc_mkdec(u64 val)
}
}
EXPORT_SYMBOL_GPL(cc_mkdec);
+
+static void amd_cc_platform_clear(enum cc_attr attr)
+{
+ switch (attr) {
+ case CC_ATTR_HOST_SEV_SNP:
+ cc_flags.host_sev_snp = 0;
+ break;
+ default:
+ break;
+ }
+}
+
+void cc_platform_clear(enum cc_attr attr)
+{
+ switch (cc_vendor) {
+ case CC_VENDOR_AMD:
+ amd_cc_platform_clear(attr);
+ break;
+ default:
+ break;
+ }
+}
+
+static void amd_cc_platform_set(enum cc_attr attr)
+{
+ switch (attr) {
+ case CC_ATTR_HOST_SEV_SNP:
+ cc_flags.host_sev_snp = 1;
+ break;
+ default:
+ break;
+ }
+}
+
+void cc_platform_set(enum cc_attr attr)
+{
+ switch (cc_vendor) {
+ case CC_VENDOR_AMD:
+ amd_cc_platform_set(attr);
+ break;
+ default:
+ break;
+ }
+}
+
+__init void cc_random_init(void)
+{
+ /*
+ * The seed is 32 bytes (in units of longs), which is 256 bits, which
+ * is the security level that the RNG is targeting.
+ */
+ unsigned long rng_seed[32 / sizeof(long)];
+ size_t i, longs;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+ return;
+
+ /*
+ * Since the CoCo threat model includes the host, the only reliable
+ * source of entropy that can be neither observed nor manipulated is
+ * RDRAND. Usually, RDRAND failure is considered tolerable, but since
+ * CoCo guests have no other unobservable source of entropy, it's
+ * important to at least ensure the RNG gets some initial random seeds.
+ */
+ for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) {
+ longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i);
+
+ /*
+ * A zero return value means that the guest doesn't have RDRAND
+ * or the CPU is physically broken, and in both cases that
+ * means most crypto inside of the CoCo instance will be
+ * broken, defeating the purpose of CoCo in the first place. So
+ * just panic here because it's absolutely unsafe to continue
+ * executing.
+ */
+ if (longs == 0)
+ panic("RDRAND is defective.");
+ }
+ add_device_randomness(rng_seed, sizeof(rng_seed));
+ memzero_explicit(rng_seed, sizeof(rng_seed));
+}
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index fd63051bbbbb..3d64bcc403cf 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_X86_X32_ABI) += vdso-image-x32.o
obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o
OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n
+OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n
OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n
OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index aec16e581f5b..985ef3b47919 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -250,7 +250,7 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
/*
* AMD Performance Monitor Family 17h and later:
*/
-static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+static const u64 amd_zen1_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
@@ -262,10 +262,39 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187,
};
+static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x0964,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9,
+};
+
+static const u64 amd_zen4_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x0964,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9,
+ [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x100000120,
+};
+
static u64 amd_pmu_event_map(int hw_event)
{
- if (boot_cpu_data.x86 >= 0x17)
- return amd_f17h_perfmon_event_map[hw_event];
+ if (cpu_feature_enabled(X86_FEATURE_ZEN4) || boot_cpu_data.x86 >= 0x1a)
+ return amd_zen4_perfmon_event_map[hw_event];
+
+ if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19)
+ return amd_zen2_perfmon_event_map[hw_event];
+
+ if (cpu_feature_enabled(X86_FEATURE_ZEN1))
+ return amd_zen1_perfmon_event_map[hw_event];
return amd_perfmon_event_map[hw_event];
}
@@ -904,8 +933,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
if (!status)
goto done;
- /* Read branch records before unfreezing */
- if (status & GLOBAL_STATUS_LBRS_FROZEN) {
+ /* Read branch records */
+ if (x86_pmu.lbr_nr) {
amd_pmu_lbr_read();
status &= ~GLOBAL_STATUS_LBRS_FROZEN;
}
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index 4a1e600314d5..5149830c7c4f 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -402,10 +402,12 @@ void amd_pmu_lbr_enable_all(void)
wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select);
}
- rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
- rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+ if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ }
- wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN);
}
@@ -418,10 +420,12 @@ void amd_pmu_lbr_disable_all(void)
return;
rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
- rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
-
wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
- wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+
+ if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ }
}
__init int amd_pmu_lbr_init(void)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 2641ba620f12..e010bfed8417 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1237,11 +1237,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
struct pmu *pmu = event->pmu;
/*
- * Make sure we get updated with the first PEBS
- * event. It will trigger also during removal, but
- * that does not hurt:
+ * Make sure we get updated with the first PEBS event.
+ * During removal, ->pebs_data_cfg is still valid for
+ * the last PEBS event. Don't clear it.
*/
- if (cpuc->n_pebs == 1)
+ if ((cpuc->n_pebs == 1) && add)
cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW;
if (needed_cb != pebs_needs_sched_cb(cpuc)) {
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index fcd20c6dc7f9..67b68d0d17d1 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void);
extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
struct module *mod);
extern void *callthunks_translate_call_dest(void *dest);
-extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
+extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip);
#else
static __always_inline void callthunks_patch_builtin_calls(void) {}
static __always_inline void
@@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest)
return dest;
}
static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
- void *func)
+ void *func, void *ip)
{
return 0;
}
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 076bf8dee702..25466c4d2134 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -14,6 +14,7 @@
#include <asm/asm.h>
#include <asm/fred.h>
#include <asm/gsseg.h>
+#include <asm/nospec-branch.h>
#ifndef CONFIG_X86_CMPXCHG64
extern void cmpxchg8b_emu(void);
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index fb7388bbc212..c086699b0d0c 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -22,6 +22,7 @@ static inline void cc_set_mask(u64 mask)
u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
+void cc_random_init(void);
#else
#define cc_vendor (CC_VENDOR_NONE)
@@ -34,6 +35,7 @@ static inline u64 cc_mkdec(u64 val)
{
return val;
}
+static inline void cc_random_init(void) { }
#endif
#endif /* _ASM_X86_COCO_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a1273698fc43..686e92d2663e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -33,6 +33,8 @@ enum cpuid_leafs
CPUID_7_EDX,
CPUID_8000_001F_EAX,
CPUID_8000_0021_EAX,
+ CPUID_LNX_5,
+ NR_CPUID_WORDS,
};
#define X86_CAP_FMT_NUM "%d:%d"
@@ -91,8 +93,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \
REQUIRED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 22))
#define DISABLED_MASK_BIT_SET(feature_bit) \
( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \
@@ -116,8 +119,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \
DISABLED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 22))
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f0337f7bcf16..a38f8f9ba657 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 21 /* N 32-bit words worth of info */
+#define NCAPINTS 22 /* N 32-bit words worth of info */
#define NBUGINTS 2 /* N 32-bit bug flags */
/*
@@ -460,6 +460,14 @@
#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0x80000022, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
+
+/*
* BUG word(s)
*/
#define X86_BUG(x) (NCAPINTS*32 + (x))
diff --git a/arch/x86/include/asm/crash_reserve.h b/arch/x86/include/asm/crash_reserve.h
index 152239f95541..7835b2cdff04 100644
--- a/arch/x86/include/asm/crash_reserve.h
+++ b/arch/x86/include/asm/crash_reserve.h
@@ -39,4 +39,6 @@ static inline unsigned long crash_low_size_default(void)
#endif
}
+#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
+
#endif /* _X86_CRASH_RESERVE_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index da4054fbf533..c492bdc97b05 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -155,6 +155,7 @@
#define DISABLED_MASK18 (DISABLE_IBT)
#define DISABLED_MASK19 (DISABLE_SEV_SNP)
#define DISABLED_MASK20 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index fc3a8a3c7ffe..170c89ed22fc 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -262,11 +262,20 @@
.Lskip_rsb_\@:
.endm
+/*
+ * The CALL to srso_alias_untrain_ret() must be patched in directly at
+ * the spot where untraining must be done, ie., srso_alias_untrain_ret()
+ * must be the target of a CALL instruction instead of indirectly
+ * jumping to a wrapper which then calls it. Therefore, this macro is
+ * called outside of __UNTRAIN_RET below, for the time being, before the
+ * kernel can support nested alternatives with arbitrary nesting.
+ */
+.macro CALL_UNTRAIN_RET
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
-#define CALL_UNTRAIN_RET "call entry_untrain_ret"
-#else
-#define CALL_UNTRAIN_RET ""
+ ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \
+ "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
#endif
+.endm
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the
@@ -282,8 +291,8 @@
.macro __UNTRAIN_RET ibpb_feature, call_depth_insns
#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY)
VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
+ CALL_UNTRAIN_RET
+ ALTERNATIVE_2 "", \
"call entry_ibpb", \ibpb_feature, \
__stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
@@ -342,6 +351,8 @@ extern void retbleed_return_thunk(void);
static inline void retbleed_return_thunk(void) {}
#endif
+extern void srso_alias_untrain_ret(void);
+
#ifdef CONFIG_MITIGATION_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 7ba1726b71c7..e9187ddd3d1f 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -99,6 +99,7 @@
#define REQUIRED_MASK18 0
#define REQUIRED_MASK19 0
#define REQUIRED_MASK20 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 9477b4053bce..7f57382afee4 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -218,17 +218,16 @@ void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
unsigned long npages);
void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
unsigned long npages);
-void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
void snp_set_wakeup_secondary_cpu(void);
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);
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 kdump_sev_callback(void);
void sev_show_status(void);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
@@ -244,12 +243,12 @@ static inline void __init
early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
static inline void __init
early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
-static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { }
static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { }
static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { }
static inline void snp_set_wakeup_secondary_cpu(void) { }
static inline bool snp_init(struct boot_params *bp) { return false; }
static inline void snp_abort(void) { }
+static inline void snp_dmi_setup(void) { }
static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio)
{
return -ENOTTY;
@@ -258,7 +257,6 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
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 kdump_sev_callback(void) { }
static inline void sev_show_status(void) { }
#endif
@@ -270,6 +268,7 @@ int psmash(u64 pfn);
int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable);
int rmp_make_shared(u64 pfn, enum pg_level level);
void snp_leak_pages(u64 pfn, unsigned int npages);
+void kdump_sev_callback(void);
#else
static inline bool snp_probe_rmptable_info(void) { return false; }
static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
@@ -282,6 +281,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as
}
static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
+static inline void kdump_sev_callback(void) { }
#endif
#endif
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index b89b40f250e6..6149eabe200f 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -30,12 +30,13 @@ struct x86_init_mpparse {
* @reserve_resources: reserve the standard resources for the
* platform
* @memory_setup: platform specific memory setup
- *
+ * @dmi_setup: platform specific DMI setup
*/
struct x86_init_resources {
void (*probe_roms)(void);
void (*reserve_resources)(void);
char *(*memory_setup)(void);
+ void (*dmi_setup)(void);
};
/**
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index ad29984d5e39..ef11aa4cab42 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -694,6 +694,7 @@ enum sev_cmd_id {
struct kvm_sev_cmd {
__u32 id;
+ __u32 pad0;
__u64 data;
__u32 error;
__u32 sev_fd;
@@ -704,28 +705,35 @@ struct kvm_sev_launch_start {
__u32 policy;
__u64 dh_uaddr;
__u32 dh_len;
+ __u32 pad0;
__u64 session_uaddr;
__u32 session_len;
+ __u32 pad1;
};
struct kvm_sev_launch_update_data {
__u64 uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_launch_secret {
__u64 hdr_uaddr;
__u32 hdr_len;
+ __u32 pad0;
__u64 guest_uaddr;
__u32 guest_len;
+ __u32 pad1;
__u64 trans_uaddr;
__u32 trans_len;
+ __u32 pad2;
};
struct kvm_sev_launch_measure {
__u64 uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_guest_status {
@@ -738,33 +746,43 @@ struct kvm_sev_dbg {
__u64 src_uaddr;
__u64 dst_uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_attestation_report {
__u8 mnonce[16];
__u64 uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_send_start {
__u32 policy;
+ __u32 pad0;
__u64 pdh_cert_uaddr;
__u32 pdh_cert_len;
+ __u32 pad1;
__u64 plat_certs_uaddr;
__u32 plat_certs_len;
+ __u32 pad2;
__u64 amd_certs_uaddr;
__u32 amd_certs_len;
+ __u32 pad3;
__u64 session_uaddr;
__u32 session_len;
+ __u32 pad4;
};
struct kvm_sev_send_update_data {
__u64 hdr_uaddr;
__u32 hdr_len;
+ __u32 pad0;
__u64 guest_uaddr;
__u32 guest_len;
+ __u32 pad1;
__u64 trans_uaddr;
__u32 trans_len;
+ __u32 pad2;
};
struct kvm_sev_receive_start {
@@ -772,17 +790,22 @@ struct kvm_sev_receive_start {
__u32 policy;
__u64 pdh_uaddr;
__u32 pdh_len;
+ __u32 pad0;
__u64 session_uaddr;
__u32 session_len;
+ __u32 pad1;
};
struct kvm_sev_receive_update_data {
__u64 hdr_uaddr;
__u32 hdr_len;
+ __u32 pad0;
__u64 guest_uaddr;
__u32 guest_len;
+ __u32 pad1;
__u64 trans_uaddr;
__u32 trans_len;
+ __u32 pad2;
};
#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 6bc3456a8ebf..a1efa7907a0b 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -142,7 +142,6 @@ struct kvm_vcpu_pv_apf_data {
__u32 token;
__u8 pad[56];
- __u32 enabled;
};
#define KVM_PV_EOI_BIT 0
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 30335182b6b0..e92ff0c11db8 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -314,7 +314,7 @@ static bool is_callthunk(void *addr)
return !bcmp(pad, insn_buff, tmpl_size);
}
-int x86_call_depth_emit_accounting(u8 **pprog, void *func)
+int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
{
unsigned int tmpl_size = SKL_TMPL_SIZE;
u8 insn_buff[MAX_PATCH_LEN];
@@ -327,7 +327,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
return 0;
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, tmpl_size, *pprog,
+ apply_relocation(insn_buff, tmpl_size, ip,
skl_call_thunk_template, tmpl_size);
memcpy(*pprog, insn_buff, tmpl_size);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 6d8677e80ddb..9bf17c9c29da 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -345,6 +345,28 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
+static void bsp_determine_snp(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+ cc_vendor = CC_VENDOR_AMD;
+
+ if (cpu_has(c, X86_FEATURE_SEV_SNP)) {
+ /*
+ * RMP table entry format is not architectural and is defined by the
+ * per-processor PPR. Restrict SNP support on the known CPU models
+ * for which the RMP table entry format is currently defined for.
+ */
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
+ c->x86 >= 0x19 && snp_probe_rmptable_info()) {
+ cc_platform_set(CC_ATTR_HOST_SEV_SNP);
+ } else {
+ setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
+ }
+ }
+#endif
+}
+
static void bsp_init_amd(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -452,21 +474,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
break;
}
- if (cpu_has(c, X86_FEATURE_SEV_SNP)) {
- /*
- * RMP table entry format is not architectural and it can vary by processor
- * and is defined by the per-processor PPR. Restrict SNP support on the
- * known CPU model and family for which the RMP table entry format is
- * currently defined for.
- */
- if (!boot_cpu_has(X86_FEATURE_ZEN3) &&
- !boot_cpu_has(X86_FEATURE_ZEN4) &&
- !boot_cpu_has(X86_FEATURE_ZEN5))
- setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
- else if (!snp_probe_rmptable_info())
- setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
- }
-
+ bsp_determine_snp(c);
return;
warn:
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b5cc557cfc37..84d41be6d06b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2500,12 +2500,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
return -EINVAL;
b = &per_cpu(mce_banks_array, s->id)[bank];
-
if (!b->init)
return -ENODEV;
b->ctl = new;
+
+ mutex_lock(&mce_sysfs_mutex);
mce_restart();
+ mutex_unlock(&mce_sysfs_mutex);
return size;
}
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 422a4ddc2ab7..7b29ebda024f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -108,7 +108,7 @@ static inline void k8_check_syscfg_dram_mod_en(void)
(boot_cpu_data.x86 >= 0x0f)))
return;
- if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return;
rdmsr(MSR_AMD64_SYSCFG, lo, hi);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index c99f26ebe7a6..1a8687f8073a 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -78,7 +78,8 @@ cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
else
cpu = cpumask_any_but(mask, exclude_cpu);
- if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
+ /* Only continue if tick_nohz_full_mask has been initialized. */
+ if (!tick_nohz_full_enabled())
return cpu;
/* If the CPU picked isn't marked nohz_full nothing more needs doing. */
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 0dad49a09b7a..a515328d9d7d 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -49,6 +49,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
{ X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 },
{ X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 },
+ { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 },
{ 0, 0, 0, 0, 0 }
};
diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c
index e963344b0449..53935b4d62e3 100644
--- a/arch/x86/kernel/eisa.c
+++ b/arch/x86/kernel/eisa.c
@@ -2,6 +2,7 @@
/*
* EISA specific code
*/
+#include <linux/cc_platform.h>
#include <linux/ioport.h>
#include <linux/eisa.h>
#include <linux/io.h>
@@ -12,7 +13,7 @@ static __init int eisa_bus_probe(void)
{
void __iomem *p;
- if (xen_pv_domain() && !xen_initial_domain())
+ if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
return 0;
p = ioremap(0x0FFFD9, 4);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4cadfd606e8e..7f0732bc0ccd 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -65,6 +65,7 @@ static int __init parse_no_stealacc(char *arg)
early_param("no-steal-acc", parse_no_stealacc);
+static DEFINE_PER_CPU_READ_MOSTLY(bool, async_pf_enabled);
static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
static int has_steal_clock = 0;
@@ -244,7 +245,7 @@ noinstr u32 kvm_read_and_reset_apf_flags(void)
{
u32 flags = 0;
- if (__this_cpu_read(apf_reason.enabled)) {
+ if (__this_cpu_read(async_pf_enabled)) {
flags = __this_cpu_read(apf_reason.flags);
__this_cpu_write(apf_reason.flags, 0);
}
@@ -295,7 +296,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
inc_irq_stat(irq_hv_callback_count);
- if (__this_cpu_read(apf_reason.enabled)) {
+ if (__this_cpu_read(async_pf_enabled)) {
token = __this_cpu_read(apf_reason.token);
kvm_async_pf_task_wake(token);
__this_cpu_write(apf_reason.token, 0);
@@ -362,7 +363,7 @@ static void kvm_guest_cpu_init(void)
wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
- __this_cpu_write(apf_reason.enabled, 1);
+ __this_cpu_write(async_pf_enabled, true);
pr_debug("setup async PF for cpu %d\n", smp_processor_id());
}
@@ -383,11 +384,11 @@ static void kvm_guest_cpu_init(void)
static void kvm_pv_disable_apf(void)
{
- if (!__this_cpu_read(apf_reason.enabled))
+ if (!__this_cpu_read(async_pf_enabled))
return;
wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
- __this_cpu_write(apf_reason.enabled, 0);
+ __this_cpu_write(async_pf_enabled, false);
pr_debug("disable async PF for cpu %d\n", smp_processor_id());
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 9a5b372c706f..ed163c8c8604 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -580,7 +580,7 @@ EXPORT_SYMBOL_GPL(asm_exc_nmi_kvm_vmx);
static char *nmi_check_stall_msg[] = {
/* */
-/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler. */
+/* +--------- nmi_seq & 0x1: CPU is currently in NMI handler. */
/* | +------ cpu_is_offline(cpu) */
/* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls): */
/* | | | NMI handler has been invoked. */
@@ -628,22 +628,26 @@ void nmi_backtrace_stall_check(const struct cpumask *btp)
nmi_seq = READ_ONCE(nsp->idt_nmi_seq);
if (nsp->idt_nmi_seq_snap + 1 == nmi_seq && (nmi_seq & 0x1)) {
msgp = "CPU entered NMI handler function, but has not exited";
- } else if ((nsp->idt_nmi_seq_snap & 0x1) != (nmi_seq & 0x1)) {
- msgp = "CPU is handling NMIs";
- } else {
- idx = ((nsp->idt_seq_snap & 0x1) << 2) |
+ } else if (nsp->idt_nmi_seq_snap == nmi_seq ||
+ nsp->idt_nmi_seq_snap + 1 == nmi_seq) {
+ idx = ((nmi_seq & 0x1) << 2) |
(cpu_is_offline(cpu) << 1) |
(nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls));
msgp = nmi_check_stall_msg[idx];
if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1))
modp = ", but OK because ignore_nmis was set";
- if (nmi_seq & 0x1)
- msghp = " (CPU currently in NMI handler function)";
- else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
+ if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
msghp = " (CPU exited one NMI handler function)";
+ else if (nmi_seq & 0x1)
+ msghp = " (CPU currently in NMI handler function)";
+ else
+ msghp = " (CPU was never in an NMI handler function)";
+ } else {
+ msgp = "CPU is handling NMIs";
}
- pr_alert("%s: CPU %d: %s%s%s, last activity: %lu jiffies ago.\n",
- __func__, cpu, msgp, modp, msghp, j - READ_ONCE(nsp->recv_jiffies));
+ pr_alert("%s: CPU %d: %s%s%s\n", __func__, cpu, msgp, modp, msghp);
+ pr_alert("%s: last activity: %lu jiffies ago.\n",
+ __func__, j - READ_ONCE(nsp->recv_jiffies));
}
}
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 319fef37d9dc..cc2c34ba7228 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -203,16 +203,6 @@ void __init probe_roms(void)
unsigned char c;
int i;
- /*
- * The ROM memory range is not part of the e820 table and is therefore not
- * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted
- * memory, and SNP requires encrypted memory to be validated before access.
- * Do that here.
- */
- snp_prep_memory(video_rom_resource.start,
- ((system_rom_resource.end + 1) - video_rom_resource.start),
- SNP_PAGE_STATE_PRIVATE);
-
/* video rom */
upper = adapter_rom_resources[0].start;
for (start = video_rom_resource.start; start < upper; start += 2048) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ef206500ed6f..e125e059e2c4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -9,7 +9,6 @@
#include <linux/console.h>
#include <linux/crash_dump.h>
#include <linux/dma-map-ops.h>
-#include <linux/dmi.h>
#include <linux/efi.h>
#include <linux/ima.h>
#include <linux/init_ohci1394_dma.h>
@@ -36,6 +35,7 @@
#include <asm/bios_ebda.h>
#include <asm/bugs.h>
#include <asm/cacheinfo.h>
+#include <asm/coco.h>
#include <asm/cpu.h>
#include <asm/efi.h>
#include <asm/gart.h>
@@ -902,7 +902,7 @@ void __init setup_arch(char **cmdline_p)
efi_init();
reserve_ibft_region();
- dmi_setup();
+ x86_init.resources.dmi_setup();
/*
* VMware detection requires dmi to be available, so this
@@ -992,6 +992,7 @@ void __init setup_arch(char **cmdline_p)
* memory size.
*/
mem_encrypt_setup_arch();
+ cc_random_init();
efi_fake_memmap();
efi_find_mirror();
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index b59b09c2f284..38ad066179d8 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -23,6 +23,7 @@
#include <linux/platform_device.h>
#include <linux/io.h>
#include <linux/psp-sev.h>
+#include <linux/dmi.h>
#include <uapi/linux/sev-guest.h>
#include <asm/init.h>
@@ -795,21 +796,6 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr
early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
}
-void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op)
-{
- unsigned long vaddr, npages;
-
- vaddr = (unsigned long)__va(paddr);
- npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
-
- if (op == SNP_PAGE_STATE_PRIVATE)
- early_snp_set_memory_private(vaddr, paddr, npages);
- else if (op == SNP_PAGE_STATE_SHARED)
- early_snp_set_memory_shared(vaddr, paddr, npages);
- else
- WARN(1, "invalid memory op %d\n", op);
-}
-
static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
unsigned long vaddr_end, int op)
{
@@ -2136,6 +2122,17 @@ void __head __noreturn snp_abort(void)
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
}
+/*
+ * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
+ * enabled, as the alternative (fallback) logic for DMI probing in the legacy
+ * ROM region can cause a crash since this region is not pre-validated.
+ */
+void __init snp_dmi_setup(void)
+{
+ if (efi_enabled(EFI_CONFIG_TABLES))
+ dmi_setup();
+}
+
static void dump_cpuid_table(void)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -2287,16 +2284,6 @@ static int __init snp_init_platform_device(void)
}
device_initcall(snp_init_platform_device);
-void kdump_sev_callback(void)
-{
- /*
- * Do wbinvd() on remote CPUs when SNP is enabled in order to
- * safely do SNP_SHUTDOWN on the local CPU.
- */
- if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
- wbinvd();
-}
-
void sev_show_status(void)
{
int i;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index a42830dc151b..d5dc5a92635a 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -3,6 +3,7 @@
*
* For licencing details see kernel-base/COPYING
*/
+#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/export.h>
@@ -66,6 +67,7 @@ struct x86_init_ops x86_init __initdata = {
.probe_roms = probe_roms,
.reserve_resources = reserve_standard_io_resources,
.memory_setup = e820__memory_setup_default,
+ .dmi_setup = dmi_setup,
},
.mpparse = {
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3aaf7e86a859..0ebdd088f28b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -122,6 +122,7 @@ config KVM_AMD_SEV
default y
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
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 adba49afb5fe..bfc0bfcb2bc6 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -189,15 +189,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2
return 0;
}
-static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu,
- const char *sig)
+static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries,
+ int nent, const char *sig)
{
struct kvm_hypervisor_cpuid cpuid = {};
struct kvm_cpuid_entry2 *entry;
u32 base;
for_each_possible_hypervisor_cpuid_base(base) {
- entry = kvm_find_cpuid_entry(vcpu, base);
+ entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
if (entry) {
u32 signature[3];
@@ -217,22 +217,29 @@ static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcp
return cpuid;
}
-static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu,
- struct kvm_cpuid_entry2 *entries, int nent)
+static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu,
+ const char *sig)
{
- u32 base = vcpu->arch.kvm_cpuid.base;
-
- if (!base)
- return NULL;
+ return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries,
+ vcpu->arch.cpuid_nent, sig);
+}
- return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES,
+static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries,
+ int nent, u32 kvm_cpuid_base)
+{
+ return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES,
KVM_CPUID_INDEX_NOT_SIGNIFICANT);
}
static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
{
- return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries,
- vcpu->arch.cpuid_nent);
+ u32 base = vcpu->arch.kvm_cpuid.base;
+
+ if (!base)
+ return NULL;
+
+ return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries,
+ vcpu->arch.cpuid_nent, base);
}
void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
@@ -266,6 +273,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
int nent)
{
struct kvm_cpuid_entry2 *best;
+ struct kvm_hypervisor_cpuid kvm_cpuid;
best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
if (best) {
@@ -292,10 +300,12 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
- best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent);
- if (kvm_hlt_in_guest(vcpu->kvm) && best &&
- (best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
- best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
+ kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE);
+ if (kvm_cpuid.base) {
+ best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base);
+ if (kvm_hlt_in_guest(vcpu->kvm) && best)
+ best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
+ }
if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index aadefcaa9561..58ac8d69c94b 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -102,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = {
*/
static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
{
+ BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_1);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_2);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_3);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_4);
+ BUILD_BUG_ON(x86_leaf == CPUID_LNX_5);
BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index ae0ac12382b9..61a7531d41b0 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -84,9 +84,10 @@ struct enc_region {
};
/* Called with the sev_bitmap_lock held, or on shutdown */
-static int sev_flush_asids(int min_asid, int max_asid)
+static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
{
- int ret, asid, error = 0;
+ int ret, error = 0;
+ unsigned int asid;
/* Check if there are any ASIDs to reclaim before performing a flush */
asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
@@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm)
}
/* Must be called with the sev_bitmap_lock held */
-static bool __sev_recycle_asids(int min_asid, int max_asid)
+static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid)
{
if (sev_flush_asids(min_asid, max_asid))
return false;
@@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev)
static int sev_asid_new(struct kvm_sev_info *sev)
{
- int asid, min_asid, max_asid, ret;
+ /*
+ * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
+ * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
+ * Note: min ASID can end up larger than the max if basic SEV support is
+ * effectively disabled by disallowing use of ASIDs for SEV guests.
+ */
+ unsigned int min_asid = sev->es_active ? 1 : min_sev_asid;
+ unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
+ unsigned int asid;
bool retry = true;
+ int ret;
+
+ if (min_asid > max_asid)
+ return -ENOTTY;
WARN_ON(sev->misc_cg);
sev->misc_cg = get_current_misc_cg();
@@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev)
mutex_lock(&sev_bitmap_lock);
- /*
- * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
- * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
- */
- min_asid = sev->es_active ? 1 : min_sev_asid;
- max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
again:
asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
if (asid > max_asid) {
@@ -179,7 +186,8 @@ again:
mutex_unlock(&sev_bitmap_lock);
- return asid;
+ sev->asid = asid;
+ return 0;
e_uncharge:
sev_misc_cg_uncharge(sev);
put_misc_cg(sev->misc_cg);
@@ -187,7 +195,7 @@ e_uncharge:
return ret;
}
-static int sev_get_asid(struct kvm *kvm)
+static unsigned int sev_get_asid(struct kvm *kvm)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -247,21 +255,19 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct sev_platform_init_args init_args = {0};
- int asid, ret;
+ int ret;
if (kvm->created_vcpus)
return -EINVAL;
- ret = -EBUSY;
if (unlikely(sev->active))
- return ret;
+ return -EINVAL;
sev->active = true;
sev->es_active = argp->id == KVM_SEV_ES_INIT;
- asid = sev_asid_new(sev);
- if (asid < 0)
+ ret = sev_asid_new(sev);
+ if (ret)
goto e_no_asid;
- sev->asid = asid;
init_args.probe = false;
ret = sev_platform_init(&init_args);
@@ -287,8 +293,8 @@ e_no_asid:
static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
{
+ unsigned int asid = sev_get_asid(kvm);
struct sev_data_activate activate;
- int asid = sev_get_asid(kvm);
int ret;
/* activate ASID on the given handle */
@@ -2240,8 +2246,10 @@ void __init sev_hardware_setup(void)
goto out;
}
- sev_asid_count = max_sev_asid - min_sev_asid + 1;
- WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+ if (min_sev_asid <= max_sev_asid) {
+ sev_asid_count = max_sev_asid - min_sev_asid + 1;
+ WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+ }
sev_supported = true;
/* SEV-ES support requested? */
@@ -2272,7 +2280,9 @@ void __init sev_hardware_setup(void)
out:
if (boot_cpu_has(X86_FEATURE_SEV))
pr_info("SEV %s (ASIDs %u - %u)\n",
- sev_supported ? "enabled" : "disabled",
+ sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
+ "unusable" :
+ "disabled",
min_sev_asid, max_sev_asid);
if (boot_cpu_has(X86_FEATURE_SEV_ES))
pr_info("SEV-ES %s (ASIDs %u - %u)\n",
@@ -2320,7 +2330,7 @@ int sev_cpu_init(struct svm_cpu_data *sd)
*/
static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
{
- int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid;
+ unsigned int asid = sev_get_asid(vcpu->kvm);
/*
* Note! The address must be a kernel address, as regular page walk
@@ -2638,7 +2648,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
void pre_sev_run(struct vcpu_svm *svm, int cpu)
{
struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
- int asid = sev_get_asid(svm->vcpu.kvm);
+ unsigned int asid = sev_get_asid(svm->vcpu.kvm);
/* Assign the asid allocated with this SEV guest */
svm->asid = asid;
@@ -3174,7 +3184,7 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
unsigned long pfn;
struct page *p;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
/*
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 88659de4d2a7..c6b4b1728006 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -735,13 +735,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit,
* Tracepoint for nested #vmexit because of interrupt pending
*/
TRACE_EVENT(kvm_invlpga,
- TP_PROTO(__u64 rip, int asid, u64 address),
+ TP_PROTO(__u64 rip, unsigned int asid, u64 address),
TP_ARGS(rip, asid, address),
TP_STRUCT__entry(
- __field( __u64, rip )
- __field( int, asid )
- __field( __u64, address )
+ __field( __u64, rip )
+ __field( unsigned int, asid )
+ __field( __u64, address )
),
TP_fast_assign(
@@ -750,7 +750,7 @@ TRACE_EVENT(kvm_invlpga,
__entry->address = address;
),
- TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx",
+ TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx",
__entry->rip, __entry->asid, __entry->address)
);
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 721b528da9ac..e674ccf720b9 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -163,6 +163,7 @@ SYM_CODE_START_NOALIGN(srso_alias_untrain_ret)
lfence
jmp srso_alias_return_thunk
SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
.popsection
.pushsection .text..__x86.rethunk_safe
@@ -224,10 +225,16 @@ SYM_CODE_START(srso_return_thunk)
SYM_CODE_END(srso_return_thunk)
#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
-#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret"
#else /* !CONFIG_MITIGATION_SRSO */
+/* Dummy for the alternative in CALL_UNTRAIN_RET. */
+SYM_CODE_START(srso_alias_untrain_ret)
+ ANNOTATE_UNRET_SAFE
+ ANNOTATE_NOENDBR
+ ret
+ int3
+SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
#define JMP_SRSO_UNTRAIN_RET "ud2"
-#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2"
#endif /* CONFIG_MITIGATION_SRSO */
#ifdef CONFIG_MITIGATION_UNRET_ENTRY
@@ -319,9 +326,7 @@ SYM_FUNC_END(retbleed_untrain_ret)
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
SYM_FUNC_START(entry_untrain_ret)
- ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \
- JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \
- JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS
+ ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
SYM_FUNC_END(entry_untrain_ret)
__EXPORT_THUNK(entry_untrain_ret)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index a204a332c71f..968d7005f4a7 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
for (; addr < end; addr = next) {
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
- bool use_gbpage;
next = (addr & PUD_MASK) + PUD_SIZE;
if (next > end)
next = end;
- /* if this is already a gbpage, this portion is already mapped */
- if (pud_leaf(*pud))
- continue;
-
- /* Is using a gbpage allowed? */
- use_gbpage = info->direct_gbpages;
-
- /* Don't use gbpage if it maps more than the requested region. */
- /* at the begining: */
- use_gbpage &= ((addr & ~PUD_MASK) == 0);
- /* ... or at the end: */
- use_gbpage &= ((next & ~PUD_MASK) == 0);
-
- /* Never overwrite existing mappings */
- use_gbpage &= !pud_present(*pud);
-
- if (use_gbpage) {
+ if (info->direct_gbpages) {
pud_t pudval;
+ if (pud_present(*pud))
+ continue;
+
+ addr &= PUD_MASK;
pudval = __pud((addr - info->offset) | info->page_flag);
set_pud(pud, pudval);
continue;
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 70b91de2e053..422602f6039b 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -492,6 +492,24 @@ void __init sme_early_init(void)
*/
if (sev_status & MSR_AMD64_SEV_ENABLED)
ia32_disable();
+
+ /*
+ * Override init functions that scan the ROM region in SEV-SNP guests,
+ * as this memory is not pre-validated and would thus cause a crash.
+ */
+ if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+ x86_init.mpparse.find_mptable = x86_init_noop;
+ x86_init.pci.init_irq = x86_init_noop;
+ x86_init.resources.probe_roms = x86_init_noop;
+
+ /*
+ * DMI setup behavior for SEV-SNP guests depends on
+ * efi_enabled(EFI_CONFIG_TABLES), which hasn't been
+ * parsed yet. snp_dmi_setup() will run after that
+ * parsing has happened.
+ */
+ x86_init.resources.dmi_setup = snp_dmi_setup;
+ }
}
void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 104544359d69..025fd7ea5d69 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
#include <linux/memblock.h>
#include <linux/init.h>
+#include <asm/pgtable_areas.h>
#include "numa_internal.h"
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 0d72183b5dd0..36b603d0cdde 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -947,6 +947,38 @@ static void free_pfn_range(u64 paddr, unsigned long size)
memtype_free(paddr, paddr + size);
}
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+ pgprot_t *pgprot)
+{
+ unsigned long prot;
+
+ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+ /*
+ * We need the starting PFN and cachemode used for track_pfn_remap()
+ * that covered the whole VMA. For most mappings, we can obtain that
+ * information from the page tables. For COW mappings, we might now
+ * suddenly have anon folios mapped and follow_phys() will fail.
+ *
+ * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+ * detect the PFN. If we need the cachemode as well, we're out of luck
+ * for now and have to fail fork().
+ */
+ if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+ if (pgprot)
+ *pgprot = __pgprot(prot);
+ return 0;
+ }
+ if (is_cow_mapping(vma->vm_flags)) {
+ if (pgprot)
+ return -EINVAL;
+ *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
/*
* track_pfn_copy is called when vma that is covering the pfnmap gets
* copied through copy_page_range().
@@ -957,20 +989,13 @@ static void free_pfn_range(u64 paddr, unsigned long size)
int track_pfn_copy(struct vm_area_struct *vma)
{
resource_size_t paddr;
- unsigned long prot;
unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;
if (vma->vm_flags & VM_PAT) {
- /*
- * reserve the whole chunk covered by vma. We need the
- * starting address and protection from pte.
- */
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, &pgprot))
return -EINVAL;
- }
- pgprot = __pgprot(prot);
+ /* reserve the whole chunk covered by vma. */
return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}
@@ -1045,7 +1070,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size, bool mm_wr_locked)
{
resource_size_t paddr;
- unsigned long prot;
if (vma && !(vma->vm_flags & VM_PAT))
return;
@@ -1053,11 +1077,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
/* free the chunk starting from pfn or the whole chunk */
paddr = (resource_size_t)pfn << PAGE_SHIFT;
if (!paddr && !size) {
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, NULL))
return;
- }
-
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a7ba8e178645..df5fac428408 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -480,7 +480,7 @@ static int emit_call(u8 **pprog, void *func, void *ip)
static int emit_rsb_call(u8 **pprog, void *func, void *ip)
{
OPTIMIZER_HIDE_VAR(func);
- x86_call_depth_emit_accounting(pprog, func);
+ ip += x86_call_depth_emit_accounting(pprog, func, ip);
return emit_patch(pprog, func, ip, 0xE8);
}
@@ -1972,20 +1972,17 @@ populate_extable:
/* call */
case BPF_JMP | BPF_CALL: {
- int offs;
+ u8 *ip = image + addrs[i - 1];
func = (u8 *) __bpf_call_base + imm32;
if (tail_call_reachable) {
RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth);
- if (!imm32)
- return -EINVAL;
- offs = 7 + x86_call_depth_emit_accounting(&prog, func);
- } else {
- if (!imm32)
- return -EINVAL;
- offs = x86_call_depth_emit_accounting(&prog, func);
+ ip += 7;
}
- if (emit_call(&prog, func, image + addrs[i - 1] + offs))
+ if (!imm32)
+ return -EINVAL;
+ ip += x86_call_depth_emit_accounting(&prog, func, ip);
+ if (emit_call(&prog, func, ip))
return -EINVAL;
break;
}
@@ -2835,7 +2832,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
* Direct-call fentry stub, as such it needs accounting for the
* __fentry__ call.
*/
- x86_call_depth_emit_accounting(&prog, NULL);
+ x86_call_depth_emit_accounting(&prog, NULL, image);
}
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
diff --git a/arch/x86/virt/Makefile b/arch/x86/virt/Makefile
index 1e36502cd738..ea343fc392dc 100644
--- a/arch/x86/virt/Makefile
+++ b/arch/x86/virt/Makefile
@@ -1,2 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
-obj-y += vmx/
+obj-y += svm/ vmx/
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index cffe1157a90a..ab0e8448bb6e 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -77,7 +77,7 @@ static int __mfd_enable(unsigned int cpu)
{
u64 val;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
rdmsrl(MSR_AMD64_SYSCFG, val);
@@ -98,7 +98,7 @@ static int __snp_enable(unsigned int cpu)
{
u64 val;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
rdmsrl(MSR_AMD64_SYSCFG, val);
@@ -174,11 +174,11 @@ static int __init snp_rmptable_init(void)
u64 rmptable_size;
u64 val;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
if (!amd_iommu_snp_en)
- return 0;
+ goto nosnp;
if (!probed_rmp_size)
goto nosnp;
@@ -225,7 +225,7 @@ skip_enable:
return 0;
nosnp:
- setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
return -ENOSYS;
}
@@ -246,7 +246,7 @@ static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level)
{
struct rmpentry *large_entry, *entry;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return ERR_PTR(-ENODEV);
entry = get_rmpentry(pfn);
@@ -363,7 +363,7 @@ int psmash(u64 pfn)
unsigned long paddr = pfn << PAGE_SHIFT;
int ret;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return -ENODEV;
if (!pfn_valid(pfn))
@@ -472,7 +472,7 @@ static int rmpupdate(u64 pfn, struct rmp_state *state)
unsigned long paddr = pfn << PAGE_SHIFT;
int ret, level;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return -ENODEV;
level = RMP_TO_PG_LEVEL(state->pagesize);
@@ -558,3 +558,13 @@ void snp_leak_pages(u64 pfn, unsigned int npages)
spin_unlock(&snp_leaked_pages_list_lock);
}
EXPORT_SYMBOL_GPL(snp_leak_pages);
+
+void kdump_sev_callback(void)
+{
+ /*
+ * Do wbinvd() on remote CPUs when SNP is enabled in order to
+ * safely do SNP_SHUTDOWN on the local CPU.
+ */
+ if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+ wbinvd();
+}