diff options
Diffstat (limited to 'tools/testing/selftests/kvm/include')
46 files changed, 2067 insertions, 655 deletions
diff --git a/tools/testing/selftests/kvm/include/arm64/arch_timer.h b/tools/testing/selftests/kvm/include/arm64/arch_timer.h index bf461de34785..a5836d4ab7ee 100644 --- a/tools/testing/selftests/kvm/include/arm64/arch_timer.h +++ b/tools/testing/selftests/kvm/include/arm64/arch_timer.h @@ -18,20 +18,20 @@ enum arch_timer { #define CTL_ISTATUS (1 << 2) #define msec_to_cycles(msec) \ - (timer_get_cntfrq() * (uint64_t)(msec) / 1000) + (timer_get_cntfrq() * (u64)(msec) / 1000) #define usec_to_cycles(usec) \ - (timer_get_cntfrq() * (uint64_t)(usec) / 1000000) + (timer_get_cntfrq() * (u64)(usec) / 1000000) #define cycles_to_usec(cycles) \ - ((uint64_t)(cycles) * 1000000 / timer_get_cntfrq()) + ((u64)(cycles) * 1000000 / timer_get_cntfrq()) -static inline uint32_t timer_get_cntfrq(void) +static inline u32 timer_get_cntfrq(void) { return read_sysreg(cntfrq_el0); } -static inline uint64_t timer_get_cntct(enum arch_timer timer) +static inline u64 timer_get_cntct(enum arch_timer timer) { isb(); @@ -48,7 +48,7 @@ static inline uint64_t timer_get_cntct(enum arch_timer timer) return 0; } -static inline void timer_set_cval(enum arch_timer timer, uint64_t cval) +static inline void timer_set_cval(enum arch_timer timer, u64 cval) { switch (timer) { case VIRTUAL: @@ -64,7 +64,7 @@ static inline void timer_set_cval(enum arch_timer timer, uint64_t cval) isb(); } -static inline uint64_t timer_get_cval(enum arch_timer timer) +static inline u64 timer_get_cval(enum arch_timer timer) { switch (timer) { case VIRTUAL: @@ -79,7 +79,7 @@ static inline uint64_t timer_get_cval(enum arch_timer timer) return 0; } -static inline void timer_set_tval(enum arch_timer timer, int32_t tval) +static inline void timer_set_tval(enum arch_timer timer, s32 tval) { switch (timer) { case VIRTUAL: @@ -95,7 +95,7 @@ static inline void timer_set_tval(enum arch_timer timer, int32_t tval) isb(); } -static inline int32_t timer_get_tval(enum arch_timer timer) +static inline s32 timer_get_tval(enum arch_timer timer) { isb(); switch (timer) { @@ -111,7 +111,7 @@ static inline int32_t timer_get_tval(enum arch_timer timer) return 0; } -static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl) +static inline void timer_set_ctl(enum arch_timer timer, u32 ctl) { switch (timer) { case VIRTUAL: @@ -127,7 +127,7 @@ static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl) isb(); } -static inline uint32_t timer_get_ctl(enum arch_timer timer) +static inline u32 timer_get_ctl(enum arch_timer timer) { switch (timer) { case VIRTUAL: @@ -142,17 +142,41 @@ static inline uint32_t timer_get_ctl(enum arch_timer timer) return 0; } -static inline void timer_set_next_cval_ms(enum arch_timer timer, uint32_t msec) +static inline void timer_set_next_cval_ms(enum arch_timer timer, u32 msec) { - uint64_t now_ct = timer_get_cntct(timer); - uint64_t next_ct = now_ct + msec_to_cycles(msec); + u64 now_ct = timer_get_cntct(timer); + u64 next_ct = now_ct + msec_to_cycles(msec); timer_set_cval(timer, next_ct); } -static inline void timer_set_next_tval_ms(enum arch_timer timer, uint32_t msec) +static inline void timer_set_next_tval_ms(enum arch_timer timer, u32 msec) { timer_set_tval(timer, msec_to_cycles(msec)); } +static inline u32 vcpu_get_vtimer_irq(struct kvm_vcpu *vcpu) +{ + u32 intid; + u64 attr; + + attr = vcpu_has_el2(vcpu) ? KVM_ARM_VCPU_TIMER_IRQ_HVTIMER : + KVM_ARM_VCPU_TIMER_IRQ_VTIMER; + vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, attr, &intid); + + return intid; +} + +static inline u32 vcpu_get_ptimer_irq(struct kvm_vcpu *vcpu) +{ + u32 intid; + u64 attr; + + attr = vcpu_has_el2(vcpu) ? KVM_ARM_VCPU_TIMER_IRQ_HPTIMER : + KVM_ARM_VCPU_TIMER_IRQ_PTIMER; + vcpu_device_attr_get(vcpu, KVM_ARM_VCPU_TIMER_CTRL, attr, &intid); + + return intid; +} + #endif /* SELFTEST_KVM_ARCH_TIMER_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/delay.h b/tools/testing/selftests/kvm/include/arm64/delay.h index 329e4f5079ea..6a5d4634af2c 100644 --- a/tools/testing/selftests/kvm/include/arm64/delay.h +++ b/tools/testing/selftests/kvm/include/arm64/delay.h @@ -8,10 +8,10 @@ #include "arch_timer.h" -static inline void __delay(uint64_t cycles) +static inline void __delay(u64 cycles) { enum arch_timer timer = VIRTUAL; - uint64_t start = timer_get_cntct(timer); + u64 start = timer_get_cntct(timer); while ((timer_get_cntct(timer) - start) < cycles) cpu_relax(); diff --git a/tools/testing/selftests/kvm/include/arm64/gic.h b/tools/testing/selftests/kvm/include/arm64/gic.h index baeb3c859389..615745093c98 100644 --- a/tools/testing/selftests/kvm/include/arm64/gic.h +++ b/tools/testing/selftests/kvm/include/arm64/gic.h @@ -48,8 +48,8 @@ void gic_set_dir(unsigned int intid); * split is true, EOI drops the priority and deactivates the interrupt. */ void gic_set_eoi_split(bool split); -void gic_set_priority_mask(uint64_t mask); -void gic_set_priority(uint32_t intid, uint32_t prio); +void gic_set_priority_mask(u64 mask); +void gic_set_priority(u32 intid, u32 prio); void gic_irq_set_active(unsigned int intid); void gic_irq_clear_active(unsigned int intid); bool gic_irq_get_active(unsigned int intid); @@ -57,8 +57,9 @@ void gic_irq_set_pending(unsigned int intid); void gic_irq_clear_pending(unsigned int intid); bool gic_irq_get_pending(unsigned int intid); void gic_irq_set_config(unsigned int intid, bool is_edge); +void gic_irq_set_group(unsigned int intid, bool group); -void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size, - vm_paddr_t pend_table); +void gic_rdist_enable_lpis(gpa_t cfg_table, size_t cfg_table_size, + gpa_t pend_table); #endif /* SELFTEST_KVM_GIC_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h index 3722ed9c8f96..a43a407e2d5c 100644 --- a/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h +++ b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h @@ -5,15 +5,15 @@ #include <linux/sizes.h> -void its_init(vm_paddr_t coll_tbl, size_t coll_tbl_sz, - vm_paddr_t device_tbl, size_t device_tbl_sz, - vm_paddr_t cmdq, size_t cmdq_size); +void its_init(gpa_t coll_tbl, size_t coll_tbl_sz, gpa_t device_tbl, + size_t device_tbl_sz, gpa_t cmdq, size_t cmdq_size); -void its_send_mapd_cmd(void *cmdq_base, u32 device_id, vm_paddr_t itt_base, +void its_send_mapd_cmd(void *cmdq_base, u32 device_id, gpa_t itt_base, size_t itt_size, bool valid); void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool valid); void its_send_mapti_cmd(void *cmdq_base, u32 device_id, u32 event_id, u32 collection_id, u32 intid); void its_send_invall_cmd(void *cmdq_base, u32 collection_id); +void its_send_sync_cmd(void *cmdq_base, u32 vcpu_id); #endif // __SELFTESTS_GIC_V3_ITS_H__ diff --git a/tools/testing/selftests/kvm/include/arm64/gic_v5.h b/tools/testing/selftests/kvm/include/arm64/gic_v5.h new file mode 100644 index 000000000000..eb523d9277cf --- /dev/null +++ b/tools/testing/selftests/kvm/include/arm64/gic_v5.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __SELFTESTS_GIC_V5_H +#define __SELFTESTS_GIC_V5_H + +#include <asm/barrier.h> +#include <asm/sysreg.h> + +#include <linux/bitfield.h> + +#include "processor.h" + +/* + * Definitions for GICv5 instructions for the Current Domain + */ +#define GICV5_OP_GIC_CDAFF sys_insn(1, 0, 12, 1, 3) +#define GICV5_OP_GIC_CDDI sys_insn(1, 0, 12, 2, 0) +#define GICV5_OP_GIC_CDDIS sys_insn(1, 0, 12, 1, 0) +#define GICV5_OP_GIC_CDHM sys_insn(1, 0, 12, 2, 1) +#define GICV5_OP_GIC_CDEN sys_insn(1, 0, 12, 1, 1) +#define GICV5_OP_GIC_CDEOI sys_insn(1, 0, 12, 1, 7) +#define GICV5_OP_GIC_CDPEND sys_insn(1, 0, 12, 1, 4) +#define GICV5_OP_GIC_CDPRI sys_insn(1, 0, 12, 1, 2) +#define GICV5_OP_GIC_CDRCFG sys_insn(1, 0, 12, 1, 5) +#define GICV5_OP_GICR_CDIA sys_insn(1, 0, 12, 3, 0) +#define GICV5_OP_GICR_CDNMIA sys_insn(1, 0, 12, 3, 1) + +/* Definitions for GIC CDAFF */ +#define GICV5_GIC_CDAFF_IAFFID_MASK GENMASK_ULL(47, 32) +#define GICV5_GIC_CDAFF_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDAFF_IRM_MASK BIT_ULL(28) +#define GICV5_GIC_CDAFF_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDDI */ +#define GICV5_GIC_CDDI_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDDI_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDDIS */ +#define GICV5_GIC_CDDIS_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDDIS_TYPE(r) FIELD_GET(GICV5_GIC_CDDIS_TYPE_MASK, r) +#define GICV5_GIC_CDDIS_ID_MASK GENMASK_ULL(23, 0) +#define GICV5_GIC_CDDIS_ID(r) FIELD_GET(GICV5_GIC_CDDIS_ID_MASK, r) + +/* Definitions for GIC CDEN */ +#define GICV5_GIC_CDEN_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDEN_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDHM */ +#define GICV5_GIC_CDHM_HM_MASK BIT_ULL(32) +#define GICV5_GIC_CDHM_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDHM_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDPEND */ +#define GICV5_GIC_CDPEND_PENDING_MASK BIT_ULL(32) +#define GICV5_GIC_CDPEND_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDPEND_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDPRI */ +#define GICV5_GIC_CDPRI_PRIORITY_MASK GENMASK_ULL(39, 35) +#define GICV5_GIC_CDPRI_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDPRI_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GIC CDRCFG */ +#define GICV5_GIC_CDRCFG_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GIC_CDRCFG_ID_MASK GENMASK_ULL(23, 0) + +/* Definitions for GICR CDIA */ +#define GICV5_GICR_CDIA_VALID_MASK BIT_ULL(32) +#define GICV5_GICR_CDIA_VALID(r) FIELD_GET(GICV5_GICR_CDIA_VALID_MASK, r) +#define GICV5_GICR_CDIA_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GICR_CDIA_ID_MASK GENMASK_ULL(23, 0) +#define GICV5_GICR_CDIA_INTID GENMASK_ULL(31, 0) + +/* Definitions for GICR CDNMIA */ +#define GICV5_GICR_CDNMIA_VALID_MASK BIT_ULL(32) +#define GICV5_GICR_CDNMIA_VALID(r) FIELD_GET(GICV5_GICR_CDNMIA_VALID_MASK, r) +#define GICV5_GICR_CDNMIA_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GICR_CDNMIA_ID_MASK GENMASK_ULL(23, 0) + +#define gicr_insn(insn) read_sysreg_s(GICV5_OP_GICR_##insn) +#define gic_insn(v, insn) write_sysreg_s(v, GICV5_OP_GIC_##insn) + +#define __GIC_BARRIER_INSN(op0, op1, CRn, CRm, op2, Rt) \ + __emit_inst(0xd5000000 | \ + sys_insn((op0), (op1), (CRn), (CRm), (op2)) | \ + ((Rt) & 0x1f)) + +#define GSB_SYS_BARRIER_INSN __GIC_BARRIER_INSN(1, 0, 12, 0, 0, 31) +#define GSB_ACK_BARRIER_INSN __GIC_BARRIER_INSN(1, 0, 12, 0, 1, 31) + +#define gsb_ack() asm volatile(GSB_ACK_BARRIER_INSN : : : "memory") +#define gsb_sys() asm volatile(GSB_SYS_BARRIER_INSN : : : "memory") + +#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) + +#define GICV5_IRQ_DEFAULT_PRI 0b10000 + +#define GICV5_ARCH_PPI_SW_PPI 0x3 + +void gicv5_ppi_priority_init(void) +{ + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR0_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR1_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR2_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR3_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR4_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR5_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR6_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR7_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR8_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR9_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR10_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR11_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR12_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR13_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR14_EL1); + write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_DEFAULT_PRI), SYS_ICC_PPI_PRIORITYR15_EL1); + + /* + * Context syncronization required to make sure system register writes + * effects are synchronised. + */ + isb(); +} + +void gicv5_cpu_disable_interrupts(void) +{ + u64 cr0; + + cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 0); + write_sysreg_s(cr0, SYS_ICC_CR0_EL1); +} + +void gicv5_cpu_enable_interrupts(void) +{ + u64 cr0, pcr; + + write_sysreg_s(0, SYS_ICC_PPI_ENABLER0_EL1); + write_sysreg_s(0, SYS_ICC_PPI_ENABLER1_EL1); + + gicv5_ppi_priority_init(); + + pcr = FIELD_PREP(ICC_PCR_EL1_PRIORITY, GICV5_IRQ_DEFAULT_PRI); + write_sysreg_s(pcr, SYS_ICC_PCR_EL1); + + cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 1); + write_sysreg_s(cr0, SYS_ICC_CR0_EL1); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h index e43a57d99b56..4a2033708227 100644 --- a/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h @@ -2,6 +2,11 @@ #ifndef SELFTEST_KVM_UTIL_ARCH_H #define SELFTEST_KVM_UTIL_ARCH_H -struct kvm_vm_arch {}; +struct kvm_mmu_arch {}; + +struct kvm_vm_arch { + bool has_gic; + int gic_fd; +}; #endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h index 1e8d0d531fbd..b8a902ba8573 100644 --- a/tools/testing/selftests/kvm/include/arm64/processor.h +++ b/tools/testing/selftests/kvm/include/arm64/processor.h @@ -62,8 +62,73 @@ MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) | \ MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT)) +/* TCR_EL1 specific flags */ +#define TCR_T0SZ_OFFSET 0 +#define TCR_T0SZ(x) ((UL(64) - (x)) << TCR_T0SZ_OFFSET) + +#define TCR_IRGN0_SHIFT 8 +#define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT) +#define TCR_IRGN0_NC (UL(0) << TCR_IRGN0_SHIFT) +#define TCR_IRGN0_WBWA (UL(1) << TCR_IRGN0_SHIFT) +#define TCR_IRGN0_WT (UL(2) << TCR_IRGN0_SHIFT) +#define TCR_IRGN0_WBnWA (UL(3) << TCR_IRGN0_SHIFT) + +#define TCR_ORGN0_SHIFT 10 +#define TCR_ORGN0_MASK (UL(3) << TCR_ORGN0_SHIFT) +#define TCR_ORGN0_NC (UL(0) << TCR_ORGN0_SHIFT) +#define TCR_ORGN0_WBWA (UL(1) << TCR_ORGN0_SHIFT) +#define TCR_ORGN0_WT (UL(2) << TCR_ORGN0_SHIFT) +#define TCR_ORGN0_WBnWA (UL(3) << TCR_ORGN0_SHIFT) + +#define TCR_SH0_SHIFT 12 +#define TCR_SH0_MASK (UL(3) << TCR_SH0_SHIFT) +#define TCR_SH0_INNER (UL(3) << TCR_SH0_SHIFT) + +#define TCR_TG0_SHIFT 14 +#define TCR_TG0_MASK (UL(3) << TCR_TG0_SHIFT) +#define TCR_TG0_4K (UL(0) << TCR_TG0_SHIFT) +#define TCR_TG0_64K (UL(1) << TCR_TG0_SHIFT) +#define TCR_TG0_16K (UL(2) << TCR_TG0_SHIFT) + +#define TCR_EPD1_SHIFT 23 +#define TCR_EPD1_MASK (UL(1) << TCR_EPD1_SHIFT) + +#define TCR_IPS_SHIFT 32 +#define TCR_IPS_MASK (UL(7) << TCR_IPS_SHIFT) +#define TCR_IPS_52_BITS (UL(6) << TCR_IPS_SHIFT) +#define TCR_IPS_48_BITS (UL(5) << TCR_IPS_SHIFT) +#define TCR_IPS_40_BITS (UL(2) << TCR_IPS_SHIFT) +#define TCR_IPS_36_BITS (UL(1) << TCR_IPS_SHIFT) + +#define TCR_TBI1 (UL(1) << 38) +#define TCR_HA (UL(1) << 39) +#define TCR_DS (UL(1) << 59) + +/* + * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers). + */ +#define PTE_ATTRINDX(t) ((t) << 2) +#define PTE_ATTRINDX_MASK GENMASK(4, 2) +#define PTE_ATTRINDX_SHIFT 2 + +#define PTE_VALID BIT(0) +#define PGD_TYPE_TABLE BIT(1) +#define PUD_TYPE_TABLE BIT(1) +#define PMD_TYPE_TABLE BIT(1) +#define PTE_TYPE_PAGE BIT(1) + +#define PTE_SHARED (UL(3) << 8) /* SH[1:0], inner shareable */ +#define PTE_AF BIT(10) + +#define PTE_ADDR_MASK(page_shift) GENMASK(47, (page_shift)) +#define PTE_ADDR_51_48 GENMASK(15, 12) +#define PTE_ADDR_51_48_SHIFT 12 +#define PTE_ADDR_MASK_LPA2(page_shift) GENMASK(49, (page_shift)) +#define PTE_ADDR_51_50_LPA2 GENMASK(9, 8) +#define PTE_ADDR_51_50_LPA2_SHIFT 8 + void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init); -struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, +struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, u32 vcpu_id, struct kvm_vcpu_init *init, void *guest_code); struct ex_regs { @@ -102,14 +167,8 @@ enum { (v) == VECTOR_SYNC_LOWER_64 || \ (v) == VECTOR_SYNC_LOWER_32) -/* Access flag */ -#define PTE_AF (1ULL << 10) - -/* Access flag update enable/disable */ -#define TCR_EL1_HA (1ULL << 39) - -void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, - uint32_t *ipa16k, uint32_t *ipa64k); +void aarch64_get_supported_page_sizes(u32 ipa, u32 *ipa4k, + u32 *ipa16k, u32 *ipa64k); void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); @@ -120,7 +179,8 @@ void vm_install_exception_handler(struct kvm_vm *vm, void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec, handler_fn handler); -uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva); +u64 *virt_get_pte_hva_at_level(struct kvm_vm *vm, gva_t gva, int level); +u64 *virt_get_pte_hva(struct kvm_vm *vm, gva_t gva); static inline void cpu_relax(void) { @@ -199,6 +259,16 @@ static inline void local_irq_disable(void) asm volatile("msr daifset, #3" : : : "memory"); } +static inline void local_serror_enable(void) +{ + asm volatile("msr daifclr, #4" : : : "memory"); +} + +static inline void local_serror_disable(void) +{ + asm volatile("msr daifset, #4" : : : "memory"); +} + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 @@ -217,9 +287,9 @@ struct arm_smccc_res { * @res: pointer to write the return values from registers x0-x3 * */ -void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, - uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, - uint64_t arg6, struct arm_smccc_res *res); +void smccc_hvc(u32 function_id, u64 arg0, u64 arg1, + u64 arg2, u64 arg3, u64 arg4, u64 arg5, + u64 arg6, struct arm_smccc_res *res); /** * smccc_smc - Invoke a SMCCC function using the smc conduit @@ -228,11 +298,94 @@ void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, * @res: pointer to write the return values from registers x0-x3 * */ -void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, - uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, - uint64_t arg6, struct arm_smccc_res *res); +void smccc_smc(u32 function_id, u64 arg0, u64 arg1, + u64 arg2, u64 arg3, u64 arg4, u64 arg5, + u64 arg6, struct arm_smccc_res *res); /* Execute a Wait For Interrupt instruction. */ void wfi(void); +void test_wants_mte(void); +void test_disable_default_vgic(void); + +bool vm_supports_el2(struct kvm_vm *vm); + +static inline bool test_supports_el2(void) +{ + struct kvm_vm *vm = vm_create(1); + bool supported = vm_supports_el2(vm); + + kvm_vm_free(vm); + return supported; +} + +static inline bool vcpu_has_el2(struct kvm_vcpu *vcpu) +{ + return vcpu->init.features[0] & BIT(KVM_ARM_VCPU_HAS_EL2); +} + +#define MAPPED_EL2_SYSREG(el2, el1) \ + case SYS_##el1: \ + if (vcpu_has_el2(vcpu)) \ + alias = SYS_##el2; \ + break + + +static __always_inline u64 ctxt_reg_alias(struct kvm_vcpu *vcpu, u32 encoding) +{ + u32 alias = encoding; + + BUILD_BUG_ON(!__builtin_constant_p(encoding)); + + switch (encoding) { + MAPPED_EL2_SYSREG(SCTLR_EL2, SCTLR_EL1); + MAPPED_EL2_SYSREG(CPTR_EL2, CPACR_EL1); + MAPPED_EL2_SYSREG(TTBR0_EL2, TTBR0_EL1); + MAPPED_EL2_SYSREG(TTBR1_EL2, TTBR1_EL1); + MAPPED_EL2_SYSREG(TCR_EL2, TCR_EL1); + MAPPED_EL2_SYSREG(VBAR_EL2, VBAR_EL1); + MAPPED_EL2_SYSREG(AFSR0_EL2, AFSR0_EL1); + MAPPED_EL2_SYSREG(AFSR1_EL2, AFSR1_EL1); + MAPPED_EL2_SYSREG(ESR_EL2, ESR_EL1); + MAPPED_EL2_SYSREG(FAR_EL2, FAR_EL1); + MAPPED_EL2_SYSREG(MAIR_EL2, MAIR_EL1); + MAPPED_EL2_SYSREG(TCR2_EL2, TCR2_EL1); + MAPPED_EL2_SYSREG(PIR_EL2, PIR_EL1); + MAPPED_EL2_SYSREG(PIRE0_EL2, PIRE0_EL1); + MAPPED_EL2_SYSREG(POR_EL2, POR_EL1); + MAPPED_EL2_SYSREG(AMAIR_EL2, AMAIR_EL1); + MAPPED_EL2_SYSREG(ELR_EL2, ELR_EL1); + MAPPED_EL2_SYSREG(SPSR_EL2, SPSR_EL1); + MAPPED_EL2_SYSREG(ZCR_EL2, ZCR_EL1); + MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1); + MAPPED_EL2_SYSREG(SCTLR2_EL2, SCTLR2_EL1); + MAPPED_EL2_SYSREG(CNTHCTL_EL2, CNTKCTL_EL1); + case SYS_SP_EL1: + if (!vcpu_has_el2(vcpu)) + return ARM64_CORE_REG(sp_el1); + + alias = SYS_SP_EL2; + break; + default: + BUILD_BUG(); + } + + return KVM_ARM64_SYS_REG(alias); +} + +void kvm_get_default_vcpu_target(struct kvm_vm *vm, struct kvm_vcpu_init *init); + +static inline unsigned int get_current_el(void) +{ + return (read_sysreg(CurrentEL) >> 2) & 0x3; +} + +#define do_smccc(...) \ +do { \ + if (get_current_el() == 2) \ + smccc_smc(__VA_ARGS__); \ + else \ + smccc_hvc(__VA_ARGS__); \ +} while (0) + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/arm64/ucall.h b/tools/testing/selftests/kvm/include/arm64/ucall.h index 4ec801f37f00..2210d3d94c40 100644 --- a/tools/testing/selftests/kvm/include/arm64/ucall.h +++ b/tools/testing/selftests/kvm/include/arm64/ucall.h @@ -10,9 +10,9 @@ * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each * VM), it must not be accessed from host code. */ -extern vm_vaddr_t *ucall_exit_mmio_addr; +extern gva_t *ucall_exit_mmio_addr; -static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +static inline void ucall_arch_do_ucall(gva_t uc) { WRITE_ONCE(*ucall_exit_mmio_addr, uc); } diff --git a/tools/testing/selftests/kvm/include/arm64/vgic.h b/tools/testing/selftests/kvm/include/arm64/vgic.h index c481d0c00a5d..1f8b04373987 100644 --- a/tools/testing/selftests/kvm/include/arm64/vgic.h +++ b/tools/testing/selftests/kvm/include/arm64/vgic.h @@ -11,24 +11,27 @@ #include "kvm_util.h" #define REDIST_REGION_ATTR_ADDR(count, base, flags, index) \ - (((uint64_t)(count) << 52) | \ - ((uint64_t)((base) >> 16) << 16) | \ - ((uint64_t)(flags) << 12) | \ + (((u64)(count) << 52) | \ + ((u64)((base) >> 16) << 16) | \ + ((u64)(flags) << 12) | \ index) -int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs); +bool kvm_supports_vgic_v3(void); +int __vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, u32 nr_irqs); +void __vgic_v3_init(int fd); +int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, u32 nr_irqs); #define VGIC_MAX_RESERVED 1023 -void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); -int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level); +void kvm_irq_set_level_info(int gic_fd, u32 intid, int level); +int _kvm_irq_set_level_info(int gic_fd, u32 intid, int level); -void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); -int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level); +void kvm_arm_irq_line(struct kvm_vm *vm, u32 intid, int level); +int _kvm_arm_irq_line(struct kvm_vm *vm, u32 intid, int level); /* The vcpu arg only applies to private interrupts. */ -void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); -void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu); +void kvm_irq_write_ispendr(int gic_fd, u32 intid, struct kvm_vcpu *vcpu); +void kvm_irq_write_isactiver(int gic_fd, u32 intid, struct kvm_vcpu *vcpu); #define KVM_IRQCHIP_NUM_PINS (1020 - 32) diff --git a/tools/testing/selftests/kvm/include/kvm_syscalls.h b/tools/testing/selftests/kvm/include/kvm_syscalls.h new file mode 100644 index 000000000000..843c9904c46f --- /dev/null +++ b/tools/testing/selftests/kvm/include/kvm_syscalls.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_SYSCALLS_H +#define SELFTEST_KVM_SYSCALLS_H + +#include <sys/syscall.h> + +#define MAP_ARGS0(m,...) +#define MAP_ARGS1(m,t,a,...) m(t,a) +#define MAP_ARGS2(m,t,a,...) m(t,a), MAP_ARGS1(m,__VA_ARGS__) +#define MAP_ARGS3(m,t,a,...) m(t,a), MAP_ARGS2(m,__VA_ARGS__) +#define MAP_ARGS4(m,t,a,...) m(t,a), MAP_ARGS3(m,__VA_ARGS__) +#define MAP_ARGS5(m,t,a,...) m(t,a), MAP_ARGS4(m,__VA_ARGS__) +#define MAP_ARGS6(m,t,a,...) m(t,a), MAP_ARGS5(m,__VA_ARGS__) +#define MAP_ARGS(n,...) MAP_ARGS##n(__VA_ARGS__) + +#define __DECLARE_ARGS(t, a) t a +#define __UNPACK_ARGS(t, a) a + +#define DECLARE_ARGS(nr_args, args...) MAP_ARGS(nr_args, __DECLARE_ARGS, args) +#define UNPACK_ARGS(nr_args, args...) MAP_ARGS(nr_args, __UNPACK_ARGS, args) + +#define __KVM_SYSCALL_ERROR(_name, _ret) \ + "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) + +/* Define a kvm_<syscall>() API to assert success. */ +#define __KVM_SYSCALL_DEFINE(name, nr_args, args...) \ +static inline void kvm_##name(DECLARE_ARGS(nr_args, args)) \ +{ \ + int r; \ + \ + r = name(UNPACK_ARGS(nr_args, args)); \ + TEST_ASSERT(!r, __KVM_SYSCALL_ERROR(#name, r)); \ +} + +/* + * Macro to define syscall APIs, either because KVM selftests doesn't link to + * the standard library, e.g. libnuma, or because there is no library that yet + * provides the syscall. These + */ +#define KVM_SYSCALL_DEFINE(name, nr_args, args...) \ +static inline long name(DECLARE_ARGS(nr_args, args)) \ +{ \ + return syscall(__NR_##name, UNPACK_ARGS(nr_args, args)); \ +} \ +__KVM_SYSCALL_DEFINE(name, nr_args, args) + +/* + * Special case mmap(), as KVM selftest rarely/never specific an address, + * rarely specify an offset, and because the unique return code requires + * special handling anyways. + */ +static inline void *__kvm_mmap(size_t size, int prot, int flags, int fd, + off_t offset) +{ + void *mem; + + mem = mmap(NULL, size, prot, flags, fd, offset); + TEST_ASSERT(mem != MAP_FAILED, __KVM_SYSCALL_ERROR("mmap()", + (int)(unsigned long)MAP_FAILED)); + return mem; +} + +static inline void *kvm_mmap(size_t size, int prot, int flags, int fd) +{ + return __kvm_mmap(size, prot, flags, fd, 0); +} + +static inline int kvm_dup(int fd) +{ + int new_fd = dup(fd); + + TEST_ASSERT(new_fd >= 0, __KVM_SYSCALL_ERROR("dup()", new_fd)); + return new_fd; +} + +__KVM_SYSCALL_DEFINE(munmap, 2, void *, mem, size_t, size); +__KVM_SYSCALL_DEFINE(close, 1, int, fd); +__KVM_SYSCALL_DEFINE(fallocate, 4, int, fd, int, mode, loff_t, offset, loff_t, len); +__KVM_SYSCALL_DEFINE(ftruncate, 2, unsigned int, fd, off_t, length); +__KVM_SYSCALL_DEFINE(madvise, 3, void *, addr, size_t, length, int, advice); + +#endif /* SELFTEST_KVM_SYSCALLS_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 4c4e5a847f67..2ecaaa0e9965 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -18,8 +18,12 @@ #include <asm/atomic.h> #include <asm/kvm.h> +#include <sys/eventfd.h> #include <sys/ioctl.h> +#include <pthread.h> + +#include "kvm_syscalls.h" #include "kvm_util_arch.h" #include "kvm_util_types.h" #include "sparsebit.h" @@ -46,18 +50,28 @@ struct userspace_mem_region { struct hlist_node slot_node; }; +struct kvm_binary_stats { + int fd; + struct kvm_stats_header header; + struct kvm_stats_desc *desc; +}; + struct kvm_vcpu { struct list_head list; - uint32_t id; + u32 id; int fd; struct kvm_vm *vm; struct kvm_run *run; #ifdef __x86_64__ struct kvm_cpuid2 *cpuid; #endif +#ifdef __aarch64__ + struct kvm_vcpu_init init; +#endif + struct kvm_binary_stats stats; struct kvm_dirty_gfn *dirty_gfns; - uint32_t fetch_index; - uint32_t dirty_gfns_count; + u32 fetch_index; + u32 dirty_gfns_count; }; struct userspace_mem_regions { @@ -74,42 +88,51 @@ enum kvm_mem_region_type { NR_MEM_REGIONS, }; +struct kvm_mmu { + bool pgd_created; + u64 pgd; + int pgtable_levels; + + struct kvm_mmu_arch arch; +}; + struct kvm_vm { int mode; unsigned long type; int kvm_fd; int fd; - unsigned int pgtable_levels; unsigned int page_size; unsigned int page_shift; unsigned int pa_bits; unsigned int va_bits; - uint64_t max_gfn; + u64 max_gfn; struct list_head vcpus; struct userspace_mem_regions regions; struct sparsebit *vpages_valid; struct sparsebit *vpages_mapped; bool has_irqchip; - bool pgd_created; - vm_paddr_t ucall_mmio_addr; - vm_paddr_t pgd; - vm_vaddr_t handlers; - uint32_t dirty_ring_size; - uint64_t gpa_tag_mask; + gpa_t ucall_mmio_addr; + gva_t handlers; + u32 dirty_ring_size; + gpa_t gpa_tag_mask; + + /* + * "mmu" is the guest's stage-1, with a short name because the vast + * majority of tests only care about the stage-1 MMU. + */ + struct kvm_mmu mmu; + struct kvm_mmu stage2_mmu; struct kvm_vm_arch arch; - /* Cache of information for binary stats interface */ - int stats_fd; - struct kvm_stats_header stats_header; - struct kvm_stats_desc *stats_desc; + struct kvm_binary_stats stats; /* * KVM region slots. These are the default memslots used by page * allocators, e.g., lib/elf uses the memslots[MEM_REGION_CODE] * memslot. */ - uint32_t memslots[NR_MEM_REGIONS]; + u32 memslots[NR_MEM_REGIONS]; }; struct vcpu_reg_sublist { @@ -141,7 +164,7 @@ struct vcpu_reg_list { else struct userspace_mem_region * -memslot2region(struct kvm_vm *vm, uint32_t memslot); +memslot2region(struct kvm_vm *vm, u32 memslot); static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm, enum kvm_mem_region_type type) @@ -167,24 +190,36 @@ enum vm_guest_mode { VM_MODE_P40V48_4K, VM_MODE_P40V48_16K, VM_MODE_P40V48_64K, - VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_PXXVYY_4K, /* For 48-bit or 57-bit VA, depending on host support */ VM_MODE_P47V64_4K, VM_MODE_P44V64_4K, VM_MODE_P36V48_4K, VM_MODE_P36V48_16K, VM_MODE_P36V48_64K, + VM_MODE_P47V47_16K, VM_MODE_P36V47_16K, + + VM_MODE_P56V57_4K, /* For riscv64 */ + VM_MODE_P56V48_4K, + VM_MODE_P56V39_4K, + VM_MODE_P50V57_4K, + VM_MODE_P50V48_4K, + VM_MODE_P50V39_4K, + VM_MODE_P41V57_4K, + VM_MODE_P41V48_4K, + VM_MODE_P41V39_4K, + NUM_VM_MODES, }; struct vm_shape { - uint32_t type; - uint8_t mode; - uint8_t pad0; - uint16_t pad1; + u32 type; + u8 mode; + u8 pad0; + u16 pad1; }; -kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); +kvm_static_assert(sizeof(struct vm_shape) == sizeof(u64)); #define VM_TYPE_DEFAULT 0 @@ -198,17 +233,17 @@ kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); shape; \ }) -#if defined(__aarch64__) - extern enum vm_guest_mode vm_mode_default; +#if defined(__aarch64__) + #define VM_MODE_DEFAULT vm_mode_default #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 8) #elif defined(__x86_64__) -#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K +#define VM_MODE_DEFAULT VM_MODE_PXXVYY_4K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 8) @@ -224,7 +259,12 @@ extern enum vm_guest_mode vm_mode_default; #error "RISC-V 32-bit kvm selftests not supported" #endif -#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define VM_MODE_DEFAULT vm_mode_default +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__loongarch__) +#define VM_MODE_DEFAULT VM_MODE_P47V47_16K #define MIN_PAGE_SHIFT 12U #define ptes_per_page(page_size) ((page_size) / 8) @@ -243,16 +283,22 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int __open_path_or_exit(const char *path, int flags, const char *enoent_help); int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); -bool get_kvm_param_bool(const char *param); -bool get_kvm_intel_param_bool(const char *param); -bool get_kvm_amd_param_bool(const char *param); +int kvm_get_module_param_integer(const char *module_name, const char *param); +bool kvm_get_module_param_bool(const char *module_name, const char *param); -int get_kvm_param_integer(const char *param); -int get_kvm_intel_param_integer(const char *param); -int get_kvm_amd_param_integer(const char *param); +static inline bool get_kvm_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm", param); +} + +static inline int get_kvm_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm", param); +} unsigned int kvm_check_cap(long cap); @@ -261,9 +307,6 @@ static inline bool kvm_has_cap(long cap) return kvm_check_cap(cap); } -#define __KVM_SYSCALL_ERROR(_name, _ret) \ - "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) - /* * Use the "inner", double-underscore macro when reporting errors from within * other macros so that the name of ioctl() and not its literal numeric value @@ -361,21 +404,22 @@ static inline int vm_check_cap(struct kvm_vm *vm, long cap) return ret; } -static inline int __vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +static inline int __vm_enable_cap(struct kvm_vm *vm, u32 cap, u64 arg0) { struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; return __vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } -static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) + +static inline void vm_enable_cap(struct kvm_vm *vm, u32 cap, u64 arg0) { struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } -static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, - uint64_t size, uint64_t attributes) +static inline void vm_set_memory_attributes(struct kvm_vm *vm, gpa_t gpa, + u64 size, u64 attributes) { struct kvm_memory_attributes attr = { .attributes = attributes, @@ -395,35 +439,35 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, } -static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_mem_set_private(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); } -static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_mem_set_shared(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_set_memory_attributes(vm, gpa, size, 0); } -void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size, +void vm_guest_mem_fallocate(struct kvm_vm *vm, gpa_t gpa, u64 size, bool punch_hole); -static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_guest_mem_fallocate(vm, gpa, size, true); } -static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) +static inline void vm_guest_mem_allocate(struct kvm_vm *vm, gpa_t gpa, + u64 size) { vm_guest_mem_fallocate(vm, gpa, size, false); } -void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); -const char *vm_guest_mode_string(uint32_t i); +void vm_enable_dirty_ring(struct kvm_vm *vm, u32 ring_size); +const char *vm_guest_mode_string(u32 i); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp); @@ -431,7 +475,7 @@ void kvm_vm_release(struct kvm_vm *vmp); void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); int kvm_memfd_alloc(size_t size, bool hugepages); -void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); +void vm_dump(FILE *stream, struct kvm_vm *vm, u8 indent); static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) { @@ -441,7 +485,7 @@ static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) } static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, - uint64_t first_page, uint32_t num_pages) + u64 first_page, u32 num_pages) { struct kvm_clear_dirty_log args = { .dirty_bitmap = log, @@ -453,14 +497,14 @@ static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log vm_ioctl(vm, KVM_CLEAR_DIRTY_LOG, &args); } -static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +static inline u32 kvm_vm_reset_dirty_ring(struct kvm_vm *vm) { return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); } static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm, - uint64_t address, - uint64_t size, bool pio) + u64 address, + u64 size, bool pio) { struct kvm_coalesced_mmio_zone zone = { .addr = address, @@ -472,8 +516,8 @@ static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm, } static inline void kvm_vm_unregister_coalesced_io(struct kvm_vm *vm, - uint64_t address, - uint64_t size, bool pio) + u64 address, + u64 size, bool pio) { struct kvm_coalesced_mmio_zone zone = { .addr = address, @@ -492,6 +536,44 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm) return fd; } +static inline int __kvm_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd, + u32 flags) +{ + struct kvm_irqfd irqfd = { + .fd = eventfd, + .gsi = gsi, + .flags = flags, + .resamplefd = -1, + }; + + return __vm_ioctl(vm, KVM_IRQFD, &irqfd); +} + +static inline void kvm_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd, u32 flags) +{ + int ret = __kvm_irqfd(vm, gsi, eventfd, flags); + + TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_IRQFD, ret, vm); +} + +static inline void kvm_assign_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd) +{ + kvm_irqfd(vm, gsi, eventfd, 0); +} + +static inline void kvm_deassign_irqfd(struct kvm_vm *vm, u32 gsi, int eventfd) +{ + kvm_irqfd(vm, gsi, eventfd, KVM_IRQFD_FLAG_DEASSIGN); +} + +static inline int kvm_new_eventfd(void) +{ + int fd = eventfd(0, 0); + + TEST_ASSERT(fd >= 0, __KVM_SYSCALL_ERROR("eventfd()", fd)); + return fd; +} + static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header) { ssize_t ret; @@ -528,24 +610,62 @@ static inline struct kvm_stats_desc *get_stats_descriptor(struct kvm_stats_desc } void read_stat_data(int stats_fd, struct kvm_stats_header *header, - struct kvm_stats_desc *desc, uint64_t *data, + struct kvm_stats_desc *desc, u64 *data, size_t max_elements); -void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data, - size_t max_elements); +void kvm_get_stat(struct kvm_binary_stats *stats, const char *name, + u64 *data, size_t max_elements); -static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) +#define __get_stat(stats, stat) \ +({ \ + u64 data; \ + \ + kvm_get_stat(stats, #stat, &data, 1); \ + data; \ +}) + +#define vm_get_stat(vm, stat) __get_stat(&(vm)->stats, stat) +#define vcpu_get_stat(vcpu, stat) __get_stat(&(vcpu)->stats, stat) + +static inline bool read_smt_control(char *buf, size_t buf_size) +{ + FILE *f = fopen("/sys/devices/system/cpu/smt/control", "r"); + bool ret; + + if (!f) + return false; + + ret = fread(buf, sizeof(*buf), buf_size, f) > 0; + fclose(f); + + return ret; +} + +static inline bool is_smt_possible(void) +{ + char buf[16]; + + if (read_smt_control(buf, sizeof(buf)) && + (!strncmp(buf, "forceoff", 8) || !strncmp(buf, "notsupported", 12))) + return false; + + return true; +} + +static inline bool is_smt_on(void) { - uint64_t data; + char buf[16]; + + if (read_smt_control(buf, sizeof(buf)) && !strncmp(buf, "on", 2)) + return true; - __vm_get_stat(vm, stat_name, &data, 1); - return data; + return false; } void vm_create_irqchip(struct kvm_vm *vm); -static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, - uint64_t flags) +static inline int __vm_create_guest_memfd(struct kvm_vm *vm, u64 size, + u64 flags) { struct kvm_create_guest_memfd guest_memfd = { .size = size, @@ -555,8 +675,8 @@ static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd); } -static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, - uint64_t flags) +static inline int vm_create_guest_memfd(struct kvm_vm *vm, u64 size, + u64 flags) { int fd = __vm_create_guest_memfd(vm, size, flags); @@ -564,24 +684,23 @@ static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, return fd; } -void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva); -int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva); -void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset); -int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset); +void vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva); +int __vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva); +void vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva, + u32 guest_memfd, u64 guest_memfd_offset); +int __vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, + gpa_t gpa, u64 size, void *hva, + u32 guest_memfd, u64 guest_memfd_offset); void vm_userspace_mem_region_add(struct kvm_vm *vm, - enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags); + enum vm_mem_backing_src_type src_type, + gpa_t gpa, u32 slot, u64 npages, u32 flags); void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset); + gpa_t gpa, u32 slot, u64 npages, u32 flags, + int guest_memfd_fd, u64 guest_memfd_offset); #ifndef vm_arch_has_protected_memory static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) @@ -590,35 +709,34 @@ static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) } #endif -void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); -void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); -void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); -struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); -void vm_populate_vaddr_bitmap(struct kvm_vm *vm); -vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); -vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); -vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); -vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); - -void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, +void vm_mem_region_set_flags(struct kvm_vm *vm, u32 slot, u32 flags); +void vm_mem_region_reload(struct kvm_vm *vm, u32 slot); +void vm_mem_region_move(struct kvm_vm *vm, u32 slot, u64 new_gpa); +void vm_mem_region_delete(struct kvm_vm *vm, u32 slot); +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, u32 vcpu_id); +void vm_populate_gva_bitmap(struct kvm_vm *vm); +gva_t vm_unused_gva_gap(struct kvm_vm *vm, size_t sz, gva_t min_gva); +gva_t vm_alloc(struct kvm_vm *vm, size_t sz, gva_t min_gva); +gva_t __vm_alloc(struct kvm_vm *vm, size_t sz, gva_t min_gva, + enum kvm_mem_region_type type); +gva_t vm_alloc_shared(struct kvm_vm *vm, size_t sz, gva_t min_gva, + enum kvm_mem_region_type type); +gva_t vm_alloc_pages(struct kvm_vm *vm, int nr_pages); +gva_t __vm_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type); +gva_t vm_alloc_page(struct kvm_vm *vm); + +void virt_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa, unsigned int npages); -void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); -void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); -vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); -void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); +void *addr_gpa2hva(struct kvm_vm *vm, gpa_t gpa); +void *addr_gva2hva(struct kvm_vm *vm, gva_t gva); +gpa_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, gpa_t gpa); #ifndef vcpu_arch_put_guest #define vcpu_arch_put_guest(mem, val) do { (mem) = (val); } while (0) #endif -static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) +static inline gpa_t vm_untag_gpa(struct kvm_vm *vm, gpa_t gpa) { return gpa & ~vm->gpa_tag_mask; } @@ -634,8 +752,8 @@ static inline int __vcpu_run(struct kvm_vcpu *vcpu) void vcpu_run_complete_io(struct kvm_vcpu *vcpu); struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu); -static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, uint32_t cap, - uint64_t arg0) +static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, u32 cap, + u64 arg0) { struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; @@ -690,31 +808,34 @@ static inline void vcpu_fpu_set(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_ioctl(vcpu, KVM_SET_FPU, fpu); } -static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, u64 id, void *addr) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + struct kvm_one_reg reg = { .id = id, .addr = (u64)addr }; return __vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); } -static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) + +static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, u64 id, u64 val) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + struct kvm_one_reg reg = { .id = id, .addr = (u64)&val }; return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } -static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) + +static inline u64 vcpu_get_reg(struct kvm_vcpu *vcpu, u64 id) { - uint64_t val; - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + u64 val; + struct kvm_one_reg reg = { .id = id, .addr = (u64)&val }; TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); return val; } -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) + +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u64 id, u64 val) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + struct kvm_one_reg reg = { .id = id, .addr = (u64)&val }; TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); @@ -759,75 +880,75 @@ static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) return fd; } -int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr); +int __kvm_has_device_attr(int dev_fd, u32 group, u64 attr); -static inline void kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) +static inline void kvm_has_device_attr(int dev_fd, u32 group, u64 attr) { int ret = __kvm_has_device_attr(dev_fd, group, attr); TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); } -int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val); +int __kvm_device_attr_get(int dev_fd, u32 group, u64 attr, void *val); -static inline void kvm_device_attr_get(int dev_fd, uint32_t group, - uint64_t attr, void *val) +static inline void kvm_device_attr_get(int dev_fd, u32 group, + u64 attr, void *val) { int ret = __kvm_device_attr_get(dev_fd, group, attr, val); TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_GET_DEVICE_ATTR, ret)); } -int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val); +int __kvm_device_attr_set(int dev_fd, u32 group, u64 attr, void *val); -static inline void kvm_device_attr_set(int dev_fd, uint32_t group, - uint64_t attr, void *val) +static inline void kvm_device_attr_set(int dev_fd, u32 group, + u64 attr, void *val) { int ret = __kvm_device_attr_set(dev_fd, group, attr, val); TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); } -static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr) +static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, u32 group, + u64 attr) { return __kvm_has_device_attr(vcpu->fd, group, attr); } -static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr) +static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, u32 group, + u64 attr) { kvm_has_device_attr(vcpu->fd, group, attr); } -static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { return __kvm_device_attr_get(vcpu->fd, group, attr, val); } -static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { kvm_device_attr_get(vcpu->fd, group, attr, val); } -static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { return __kvm_device_attr_set(vcpu->fd, group, attr, val); } -static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) +static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, u32 group, + u64 attr, void *val) { kvm_device_attr_set(vcpu->fd, group, attr, val); } -int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type); -int __kvm_create_device(struct kvm_vm *vm, uint64_t type); +int __kvm_test_create_device(struct kvm_vm *vm, u64 type); +int __kvm_create_device(struct kvm_vm *vm, u64 type); -static inline int kvm_create_device(struct kvm_vm *vm, uint64_t type) +static inline int kvm_create_device(struct kvm_vm *vm, u64 type) { int fd = __kvm_create_device(vm, type); @@ -841,9 +962,9 @@ void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); * VM VCPU Args Set * * Input Args: - * vm - Virtual Machine + * vcpu - vCPU * num - number of arguments - * ... - arguments, each of type uint64_t + * ... - arguments, each of type u64 * * Output Args: None * @@ -851,40 +972,38 @@ void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); * * Sets the first @num input parameters for the function at @vcpu's entry point, * per the C calling convention of the architecture, to the values given as - * variable args. Each of the variable args is expected to be of type uint64_t. + * variable args. Each of the variable args is expected to be of type u64. * The maximum @num can be is specific to the architecture. */ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...); -void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); -int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); +void kvm_irq_line(struct kvm_vm *vm, u32 irq, int level); +int _kvm_irq_line(struct kvm_vm *vm, u32 irq, int level); #define KVM_MAX_IRQ_ROUTES 4096 struct kvm_irq_routing *kvm_gsi_routing_create(void); void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, - uint32_t gsi, uint32_t pin); + u32 gsi, u32 pin); int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); const char *exit_reason_str(unsigned int exit_reason); -vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, - uint32_t memslot); -vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot, - bool protected); -vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); +gpa_t vm_phy_page_alloc(struct kvm_vm *vm, gpa_t min_gpa, u32 memslot); +gpa_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, gpa_t min_gpa, + u32 memslot, bool protected); +gpa_t vm_alloc_page_table(struct kvm_vm *vm); -static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot) +static inline gpa_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + gpa_t min_gpa, u32 memslot) { /* * By default, allocate memory as protected for VMs that support * protected memory, as the majority of memory for such VMs is * protected, i.e. using shared memory is effectively opt-in. */ - return __vm_phy_pages_alloc(vm, num, paddr_min, memslot, + return __vm_phy_pages_alloc(vm, num, min_gpa, memslot, vm_arch_has_protected_memory(vm)); } @@ -895,8 +1014,8 @@ static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, * calculate the amount of memory needed for per-vCPU data, e.g. stacks. */ struct kvm_vm *____vm_create(struct vm_shape shape); -struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, - uint64_t nr_extra_pages); +struct kvm_vm *__vm_create(struct vm_shape shape, u32 nr_runnable_vcpus, + u64 nr_extra_pages); static inline struct kvm_vm *vm_create_barebones(void) { @@ -913,16 +1032,16 @@ static inline struct kvm_vm *vm_create_barebones_type(unsigned long type) return ____vm_create(shape); } -static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) +static inline struct kvm_vm *vm_create(u32 nr_runnable_vcpus) { return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0); } -struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, - uint64_t extra_mem_pages, +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, u32 nr_vcpus, + u64 extra_mem_pages, void *guest_code, struct kvm_vcpu *vcpus[]); -static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, +static inline struct kvm_vm *vm_create_with_vcpus(u32 nr_vcpus, void *guest_code, struct kvm_vcpu *vcpus[]) { @@ -933,7 +1052,7 @@ static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, + u64 extra_mem_pages, void *guest_code); /* @@ -941,7 +1060,7 @@ struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, * additional pages of guest memory. Returns the VM and vCPU (via out param). */ static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, + u64 extra_mem_pages, void *guest_code) { return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu, @@ -963,9 +1082,38 @@ static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); -void kvm_pin_this_task_to_pcpu(uint32_t pcpu); +void kvm_set_files_rlimit(u32 nr_vcpus); + +int __pin_task_to_cpu(pthread_t task, int cpu); + +static inline void pin_task_to_cpu(pthread_t task, int cpu) +{ + int r; + + r = __pin_task_to_cpu(task, cpu); + TEST_ASSERT(!r, "Failed to set thread affinity to pCPU '%u'", cpu); +} + +static inline int pin_task_to_any_cpu(pthread_t task) +{ + int cpu = sched_getcpu(); + + pin_task_to_cpu(task, cpu); + return cpu; +} + +static inline void pin_self_to_cpu(int cpu) +{ + pin_task_to_cpu(pthread_self(), cpu); +} + +static inline int pin_self_to_any_cpu(void) +{ + return pin_task_to_any_cpu(pthread_self()); +} + void kvm_print_vcpu_pinning_help(void); -void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], +void kvm_parse_vcpu_pinning(const char *pcpus_string, u32 vcpu_to_pcpu[], int nr_vcpus); unsigned long vm_compute_max_gfn(struct kvm_vm *vm); @@ -977,20 +1125,16 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) { unsigned int n; n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); -#ifdef __s390x__ - /* s390 requires 1M aligned guest sizes */ - n = (n + 255) & ~255; -#endif return n; } #define sync_global_to_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) *_p = addr_gva2hva(vm, (gva_t)&(g)); \ memcpy(_p, &(g), sizeof(g)); \ }) #define sync_global_from_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) *_p = addr_gva2hva(vm, (gva_t)&(g)); \ memcpy(&(g), _p, sizeof(g)); \ }) @@ -1001,7 +1145,7 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) * undesirable to change the host's copy of the global. */ #define write_guest_global(vm, g, val) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) *_p = addr_gva2hva(vm, (gva_t)&(g)); \ typeof(g) _val = val; \ \ memcpy(_p, &(_val), sizeof(g)); \ @@ -1010,10 +1154,10 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) void assert_on_unhandled_exception(struct kvm_vcpu *vcpu); void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, - uint8_t indent); + u8 indent); static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, - uint8_t indent) + u8 indent) { vcpu_arch_dump(stream, vcpu, indent); } @@ -1025,10 +1169,10 @@ static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, * vm - Virtual Machine * vcpu_id - The id of the VCPU to add to the VM. */ -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id); void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code); -static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, +static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, u32 vcpu_id, void *guest_code) { struct kvm_vcpu *vcpu = vm_arch_vcpu_add(vm, vcpu_id); @@ -1039,10 +1183,10 @@ static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, } /* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */ -struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id); +struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, u32 vcpu_id); static inline struct kvm_vcpu *vm_vcpu_recreate(struct kvm_vm *vm, - uint32_t vcpu_id) + u32 vcpu_id) { return vm_arch_vcpu_recreate(vm, vcpu_id); } @@ -1057,26 +1201,15 @@ static inline void virt_pgd_alloc(struct kvm_vm *vm) } /* - * VM Virtual Page Map - * - * Input Args: - * vm - Virtual Machine - * vaddr - VM Virtual Address - * paddr - VM Physical Address - * memslot - Memory region slot for new virtual translation tables - * - * Output Args: None - * - * Return: None - * * Within @vm, creates a virtual translation for the page starting - * at @vaddr to the page starting at @paddr. + * at @gva to the page starting at @gpa. */ -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); +void virt_arch_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa); -static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +static inline void virt_pg_map(struct kvm_vm *vm, gva_t gva, gpa_t gpa) { - virt_arch_pg_map(vm, vaddr, paddr); + virt_arch_pg_map(vm, gva, gpa); + sparsebit_set(vm->vpages_mapped, gva >> vm->page_shift); } @@ -1095,9 +1228,9 @@ static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr * Returns the VM physical address of the translated VM virtual * address given by @gva. */ -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); +gpa_t addr_arch_gva2gpa(struct kvm_vm *vm, gva_t gva); -static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +static inline gpa_t addr_gva2gpa(struct kvm_vm *vm, gva_t gva) { return addr_arch_gva2gpa(vm, gva); } @@ -1117,9 +1250,9 @@ static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) * Dumps to the FILE stream given by @stream, the contents of all the * virtual translation tables for the VM given by @vm. */ -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, u8 indent); -static inline void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +static inline void virt_dump(FILE *stream, struct kvm_vm *vm, u8 indent) { virt_arch_dump(stream, vm, indent); } @@ -1130,17 +1263,26 @@ static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0); } +static inline u64 vm_page_align(struct kvm_vm *vm, u64 v) +{ + return (v + vm->page_size - 1) & ~(vm->page_size - 1); +} + /* - * Arch hook that is invoked via a constructor, i.e. before exeucting main(), + * Arch hook that is invoked via a constructor, i.e. before executing main(), * to allow for arch-specific setup that is common to all tests, e.g. computing * the default guest "mode". */ void kvm_selftest_arch_init(void); -void kvm_arch_vm_post_create(struct kvm_vm *vm); +void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus); +void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm); +void kvm_arch_vm_release(struct kvm_vm *vm); + +bool vm_is_gpa_protected(struct kvm_vm *vm, gpa_t gpa); -bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); +u32 guest_get_vcpuid(void); -uint32_t guest_get_vcpuid(void); +bool kvm_arch_has_default_irqchip(void); #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_types.h b/tools/testing/selftests/kvm/include/kvm_util_types.h index ec787b97cf18..ed0087e31674 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_types.h +++ b/tools/testing/selftests/kvm/include/kvm_util_types.h @@ -2,6 +2,8 @@ #ifndef SELFTEST_KVM_UTIL_TYPES_H #define SELFTEST_KVM_UTIL_TYPES_H +#include <linux/types.h> + /* * Provide a version of static_assert() that is guaranteed to have an optional * message param. _GNU_SOURCE is defined for all KVM selftests, _GNU_SOURCE @@ -14,7 +16,9 @@ #define __kvm_static_assert(expr, msg, ...) _Static_assert(expr, msg) #define kvm_static_assert(expr, ...) __kvm_static_assert(expr, ##__VA_ARGS__, #expr) -typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ -typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ +typedef u64 gpa_t; /* Virtual Machine (Guest) physical address */ +typedef u64 gva_t; /* Virtual Machine (Guest) virtual address */ + +#define INVALID_GPA (~(u64)0) #endif /* SELFTEST_KVM_UTIL_TYPES_H */ diff --git a/tools/testing/selftests/kvm/include/loongarch/arch_timer.h b/tools/testing/selftests/kvm/include/loongarch/arch_timer.h new file mode 100644 index 000000000000..3888aeeb3524 --- /dev/null +++ b/tools/testing/selftests/kvm/include/loongarch/arch_timer.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * LoongArch Constant Timer specific interface + */ +#ifndef SELFTEST_KVM_ARCH_TIMER_H +#define SELFTEST_KVM_ARCH_TIMER_H + +#include "processor.h" + +/* LoongArch timer frequency is constant 100MHZ */ +#define TIMER_FREQ (100UL << 20) +#define msec_to_cycles(msec) (TIMER_FREQ * (unsigned long)(msec) / 1000) +#define usec_to_cycles(usec) (TIMER_FREQ * (unsigned long)(usec) / 1000000) +#define cycles_to_usec(cycles) ((unsigned long)(cycles) * 1000000 / TIMER_FREQ) + +static inline unsigned long timer_get_cycles(void) +{ + unsigned long val = 0; + + __asm__ __volatile__( + "rdtime.d %0, $zero\n\t" + : "=r"(val) + : + ); + + return val; +} + +static inline unsigned long timer_get_cfg(void) +{ + return csr_read(LOONGARCH_CSR_TCFG); +} + +static inline unsigned long timer_get_val(void) +{ + return csr_read(LOONGARCH_CSR_TVAL); +} + +static inline void disable_timer(void) +{ + csr_write(0, LOONGARCH_CSR_TCFG); +} + +static inline void timer_irq_enable(void) +{ + unsigned long val; + + val = csr_read(LOONGARCH_CSR_ECFG); + val |= ECFGF_TIMER; + csr_write(val, LOONGARCH_CSR_ECFG); +} + +static inline void timer_irq_disable(void) +{ + unsigned long val; + + val = csr_read(LOONGARCH_CSR_ECFG); + val &= ~ECFGF_TIMER; + csr_write(val, LOONGARCH_CSR_ECFG); +} + +static inline void timer_set_next_cmp_ms(unsigned int msec, bool period) +{ + unsigned long val; + + val = msec_to_cycles(msec) & CSR_TCFG_VAL; + val |= CSR_TCFG_EN; + if (period) + val |= CSR_TCFG_PERIOD; + csr_write(val, LOONGARCH_CSR_TCFG); +} + +static inline void __delay(u64 cycles) +{ + u64 start = timer_get_cycles(); + + while ((timer_get_cycles() - start) < cycles) + cpu_relax(); +} + +static inline void udelay(unsigned long usec) +{ + __delay(usec_to_cycles(usec)); +} +#endif /* SELFTEST_KVM_ARCH_TIMER_H */ diff --git a/tools/testing/selftests/kvm/include/loongarch/kvm_util_arch.h b/tools/testing/selftests/kvm/include/loongarch/kvm_util_arch.h new file mode 100644 index 000000000000..d5095900e442 --- /dev/null +++ b/tools/testing/selftests/kvm/include/loongarch/kvm_util_arch.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_ARCH_H +#define SELFTEST_KVM_UTIL_ARCH_H + +struct kvm_mmu_arch {}; +struct kvm_vm_arch {}; + +#endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/loongarch/pmu.h b/tools/testing/selftests/kvm/include/loongarch/pmu.h new file mode 100644 index 000000000000..478e6a9bbb2b --- /dev/null +++ b/tools/testing/selftests/kvm/include/loongarch/pmu.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * LoongArch PMU specific interface + */ +#ifndef SELFTEST_KVM_PMU_H +#define SELFTEST_KVM_PMU_H + +#include "processor.h" + +#define LOONGARCH_CPUCFG6 0x6 +#define CPUCFG6_PMP BIT(0) +#define CPUCFG6_PAMVER GENMASK(3, 1) +#define CPUCFG6_PMNUM GENMASK(7, 4) +#define CPUCFG6_PMNUM_SHIFT 4 +#define CPUCFG6_PMBITS GENMASK(13, 8) +#define CPUCFG6_PMBITS_SHIFT 8 +#define CPUCFG6_UPM BIT(14) + +/* Performance Counter registers */ +#define LOONGARCH_CSR_PERFCTRL0 0x200 /* perf event 0 config */ +#define LOONGARCH_CSR_PERFCNTR0 0x201 /* perf event 0 count value */ +#define LOONGARCH_CSR_PERFCTRL1 0x202 /* perf event 1 config */ +#define LOONGARCH_CSR_PERFCNTR1 0x203 /* perf event 1 count value */ +#define LOONGARCH_CSR_PERFCTRL2 0x204 /* perf event 2 config */ +#define LOONGARCH_CSR_PERFCNTR2 0x205 /* perf event 2 count value */ +#define LOONGARCH_CSR_PERFCTRL3 0x206 /* perf event 3 config */ +#define LOONGARCH_CSR_PERFCNTR3 0x207 /* perf event 3 count value */ +#define CSR_PERFCTRL_PLV0 BIT(16) +#define CSR_PERFCTRL_PLV1 BIT(17) +#define CSR_PERFCTRL_PLV2 BIT(18) +#define CSR_PERFCTRL_PLV3 BIT(19) +#define CSR_PERFCTRL_PMIE BIT(20) +#define PMU_ENVENT_ENABLED (CSR_PERFCTRL_PLV0 | CSR_PERFCTRL_PLV1 | CSR_PERFCTRL_PLV2 | CSR_PERFCTRL_PLV3) + +/* Hardware event codes (from LoongArch perf_event.c */ +#define LOONGARCH_PMU_EVENT_CYCLES 0x00 /* CPU cycles */ +#define LOONGARCH_PMU_EVENT_INSTR_RETIRED 0x01 /* Instructions retired */ +#define PERF_COUNT_HW_BRANCH_INSTRUCTIONS 0x02 /* Branch instructions */ +#define PERF_COUNT_HW_BRANCH_MISSES 0x03 /* Branch misses */ + +#define NUM_LOOPS 1000 +#define EXPECTED_INSTR_MIN (NUM_LOOPS + 10) /* Loop + overhead */ +#define EXPECTED_CYCLES_MIN NUM_LOOPS /* At least 1 cycle per iteration */ +#define UPPER_BOUND (10 * NUM_LOOPS) + +#define PMU_OVERFLOW (1ULL << 63) + +static inline void pmu_irq_enable(void) +{ + unsigned long val; + + val = csr_read(LOONGARCH_CSR_ECFG); + val |= ECFGF_PMU; + csr_write(val, LOONGARCH_CSR_ECFG); +} + +static inline void pmu_irq_disable(void) +{ + unsigned long val; + + val = csr_read(LOONGARCH_CSR_ECFG); + val &= ~ECFGF_PMU; + csr_write(val, LOONGARCH_CSR_ECFG); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/loongarch/processor.h b/tools/testing/selftests/kvm/include/loongarch/processor.h new file mode 100644 index 000000000000..93dc1fbd2e79 --- /dev/null +++ b/tools/testing/selftests/kvm/include/loongarch/processor.h @@ -0,0 +1,235 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef SELFTEST_KVM_PROCESSOR_H +#define SELFTEST_KVM_PROCESSOR_H + +#ifndef __ASSEMBLER__ +#include "ucall_common.h" + +#else +/* general registers */ +#define zero $r0 +#define ra $r1 +#define tp $r2 +#define sp $r3 +#define a0 $r4 +#define a1 $r5 +#define a2 $r6 +#define a3 $r7 +#define a4 $r8 +#define a5 $r9 +#define a6 $r10 +#define a7 $r11 +#define t0 $r12 +#define t1 $r13 +#define t2 $r14 +#define t3 $r15 +#define t4 $r16 +#define t5 $r17 +#define t6 $r18 +#define t7 $r19 +#define t8 $r20 +#define u0 $r21 +#define fp $r22 +#define s0 $r23 +#define s1 $r24 +#define s2 $r25 +#define s3 $r26 +#define s4 $r27 +#define s5 $r28 +#define s6 $r29 +#define s7 $r30 +#define s8 $r31 +#endif + +/* + * LoongArch page table entry definition + * Original header file arch/loongarch/include/asm/loongarch.h + */ +#define _PAGE_VALID_SHIFT 0 +#define _PAGE_DIRTY_SHIFT 1 +#define _PAGE_PLV_SHIFT 2 /* 2~3, two bits */ +#define PLV_KERN 0 +#define PLV_USER 3 +#define PLV_MASK 0x3 +#define _CACHE_SHIFT 4 /* 4~5, two bits */ +#define _PAGE_PRESENT_SHIFT 7 +#define _PAGE_WRITE_SHIFT 8 + +#define _PAGE_VALID BIT_ULL(_PAGE_VALID_SHIFT) +#define _PAGE_PRESENT BIT_ULL(_PAGE_PRESENT_SHIFT) +#define _PAGE_WRITE BIT_ULL(_PAGE_WRITE_SHIFT) +#define _PAGE_DIRTY BIT_ULL(_PAGE_DIRTY_SHIFT) +#define _PAGE_USER (PLV_USER << _PAGE_PLV_SHIFT) +#define __READABLE (_PAGE_VALID) +#define __WRITEABLE (_PAGE_DIRTY | _PAGE_WRITE) +/* Coherent Cached */ +#define _CACHE_CC BIT_ULL(_CACHE_SHIFT) +#define PS_4K 0x0000000c +#define PS_16K 0x0000000e +#define PS_64K 0x00000010 +#define PS_DEFAULT_SIZE PS_16K + +/* LoongArch Basic CSR registers */ +#define LOONGARCH_CSR_CRMD 0x0 /* Current mode info */ +#define CSR_CRMD_PG_SHIFT 4 +#define CSR_CRMD_PG BIT_ULL(CSR_CRMD_PG_SHIFT) +#define CSR_CRMD_IE_SHIFT 2 +#define CSR_CRMD_IE BIT_ULL(CSR_CRMD_IE_SHIFT) +#define CSR_CRMD_PLV_SHIFT 0 +#define CSR_CRMD_PLV_WIDTH 2 +#define CSR_CRMD_PLV (0x3UL << CSR_CRMD_PLV_SHIFT) +#define PLV_MASK 0x3 +#define LOONGARCH_CSR_PRMD 0x1 +#define LOONGARCH_CSR_EUEN 0x2 +#define LOONGARCH_CSR_ECFG 0x4 +#define ECFGB_PMU 10 +#define ECFGF_PMU (BIT_ULL(ECFGB_PMU)) +#define ECFGB_TIMER 11 +#define ECFGF_TIMER (BIT_ULL(ECFGB_TIMER)) +#define LOONGARCH_CSR_ESTAT 0x5 /* Exception status */ +#define CSR_ESTAT_EXC_SHIFT 16 +#define CSR_ESTAT_EXC_WIDTH 6 +#define CSR_ESTAT_EXC (0x3f << CSR_ESTAT_EXC_SHIFT) +#define EXCCODE_INT 0 /* Interrupt */ +#define INT_PMI 10 /* PMU interrupt */ +#define INT_TI 11 /* Timer interrupt*/ +#define LOONGARCH_CSR_ERA 0x6 /* ERA */ +#define LOONGARCH_CSR_BADV 0x7 /* Bad virtual address */ +#define LOONGARCH_CSR_EENTRY 0xc +#define LOONGARCH_CSR_TLBIDX 0x10 /* TLB Index, EHINV, PageSize */ +#define CSR_TLBIDX_PS_SHIFT 24 +#define CSR_TLBIDX_PS_WIDTH 6 +#define CSR_TLBIDX_PS (0x3fUL << CSR_TLBIDX_PS_SHIFT) +#define CSR_TLBIDX_SIZEM 0x3f000000 +#define CSR_TLBIDX_SIZE CSR_TLBIDX_PS_SHIFT +#define LOONGARCH_CSR_ASID 0x18 /* ASID */ +#define LOONGARCH_CSR_PGDL 0x19 +#define LOONGARCH_CSR_PGDH 0x1a +/* Page table base */ +#define LOONGARCH_CSR_PGD 0x1b +#define LOONGARCH_CSR_PWCTL0 0x1c +#define LOONGARCH_CSR_PWCTL1 0x1d +#define LOONGARCH_CSR_STLBPGSIZE 0x1e +#define LOONGARCH_CSR_CPUID 0x20 +#define LOONGARCH_CSR_KS0 0x30 +#define LOONGARCH_CSR_KS1 0x31 +#define LOONGARCH_CSR_TMID 0x40 +#define LOONGARCH_CSR_TCFG 0x41 +#define CSR_TCFG_VAL (BIT_ULL(48) - BIT_ULL(2)) +#define CSR_TCFG_PERIOD_SHIFT 1 +#define CSR_TCFG_PERIOD (0x1UL << CSR_TCFG_PERIOD_SHIFT) +#define CSR_TCFG_EN (0x1UL) +#define LOONGARCH_CSR_TVAL 0x42 +#define LOONGARCH_CSR_TINTCLR 0x44 /* Timer interrupt clear */ +#define CSR_TINTCLR_TI_SHIFT 0 +#define CSR_TINTCLR_TI (1 << CSR_TINTCLR_TI_SHIFT) +/* TLB refill exception entry */ +#define LOONGARCH_CSR_TLBRENTRY 0x88 +#define LOONGARCH_CSR_TLBRSAVE 0x8b +#define LOONGARCH_CSR_TLBREHI 0x8e +#define CSR_TLBREHI_PS_SHIFT 0 +#define CSR_TLBREHI_PS (0x3fUL << CSR_TLBREHI_PS_SHIFT) + +#define read_cpucfg(reg) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__( \ + "cpucfg %0, %1\n\t" \ + : "=r" (__v) \ + : "r" (reg) \ + : "memory"); \ + __v; \ +}) + +#define csr_read(csr) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__( \ + "csrrd %[val], %[reg]\n\t" \ + : [val] "=r" (__v) \ + : [reg] "i" (csr) \ + : "memory"); \ + __v; \ +}) + +#define csr_write(v, csr) \ +({ \ + register unsigned long __v = v; \ + __asm__ __volatile__ ( \ + "csrwr %[val], %[reg]\n\t" \ + : [val] "+r" (__v) \ + : [reg] "i" (csr) \ + : "memory"); \ + __v; \ +}) + +#define EXREGS_GPRS (32) + +#ifndef __ASSEMBLER__ +void handle_tlb_refill(void); +void handle_exception(void); + +struct ex_regs { + unsigned long regs[EXREGS_GPRS]; + unsigned long pc; + unsigned long estat; + unsigned long badv; + unsigned long prmd; +}; + +#define PC_OFFSET_EXREGS offsetof(struct ex_regs, pc) +#define ESTAT_OFFSET_EXREGS offsetof(struct ex_regs, estat) +#define BADV_OFFSET_EXREGS offsetof(struct ex_regs, badv) +#define PRMD_OFFSET_EXREGS offsetof(struct ex_regs, prmd) +#define EXREGS_SIZE sizeof(struct ex_regs) + +#define VECTOR_NUM 64 + +typedef void(*handler_fn)(struct ex_regs *); + +struct handlers { + handler_fn exception_handlers[VECTOR_NUM]; +}; + +void loongarch_vcpu_setup(struct kvm_vcpu *vcpu); +void vm_init_descriptor_tables(struct kvm_vm *vm); +void vm_install_exception_handler(struct kvm_vm *vm, int vector, handler_fn handler); + +static inline void cpu_relax(void) +{ + asm volatile("nop" ::: "memory"); +} + +static inline void local_irq_enable(void) +{ + unsigned int flags = CSR_CRMD_IE; + register unsigned int mask asm("$t0") = CSR_CRMD_IE; + + __asm__ __volatile__( + "csrxchg %[val], %[mask], %[reg]\n\t" + : [val] "+r" (flags) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) + : "memory"); +} + +static inline void local_irq_disable(void) +{ + unsigned int flags = 0; + register unsigned int mask asm("$t0") = CSR_CRMD_IE; + + __asm__ __volatile__( + "csrxchg %[val], %[mask], %[reg]\n\t" + : [val] "+r" (flags) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) + : "memory"); +} +#else +#define PC_OFFSET_EXREGS ((EXREGS_GPRS + 0) * 8) +#define ESTAT_OFFSET_EXREGS ((EXREGS_GPRS + 1) * 8) +#define BADV_OFFSET_EXREGS ((EXREGS_GPRS + 2) * 8) +#define PRMD_OFFSET_EXREGS ((EXREGS_GPRS + 3) * 8) +#define EXREGS_SIZE ((EXREGS_GPRS + 4) * 8) +#endif + +#endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/loongarch/ucall.h b/tools/testing/selftests/kvm/include/loongarch/ucall.h new file mode 100644 index 000000000000..2210d3d94c40 --- /dev/null +++ b/tools/testing/selftests/kvm/include/loongarch/ucall.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UCALL_H +#define SELFTEST_KVM_UCALL_H + +#include "kvm_util.h" + +#define UCALL_EXIT_REASON KVM_EXIT_MMIO + +/* + * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each + * VM), it must not be accessed from host code. + */ +extern gva_t *ucall_exit_mmio_addr; + +static inline void ucall_arch_do_ucall(gva_t uc) +{ + WRITE_ONCE(*ucall_exit_mmio_addr, uc); +} + +#endif diff --git a/tools/testing/selftests/kvm/include/lru_gen_util.h b/tools/testing/selftests/kvm/include/lru_gen_util.h new file mode 100644 index 000000000000..d32ff5d8ffd0 --- /dev/null +++ b/tools/testing/selftests/kvm/include/lru_gen_util.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Tools for integrating with lru_gen, like parsing the lru_gen debugfs output. + * + * Copyright (C) 2025, Google LLC. + */ +#ifndef SELFTEST_KVM_LRU_GEN_UTIL_H +#define SELFTEST_KVM_LRU_GEN_UTIL_H + +#include <inttypes.h> +#include <limits.h> +#include <stdlib.h> + +#include "test_util.h" + +#define MAX_NR_GENS 16 /* MAX_NR_GENS in include/linux/mmzone.h */ +#define MAX_NR_NODES 4 /* Maximum number of nodes supported by the test */ + +#define LRU_GEN_DEBUGFS "/sys/kernel/debug/lru_gen" +#define LRU_GEN_ENABLED_PATH "/sys/kernel/mm/lru_gen/enabled" +#define LRU_GEN_ENABLED 1 +#define LRU_GEN_MM_WALK 2 + +struct generation_stats { + int gen; + long age_ms; + long nr_anon; + long nr_file; +}; + +struct node_stats { + int node; + int nr_gens; /* Number of populated gens entries. */ + struct generation_stats gens[MAX_NR_GENS]; +}; + +struct memcg_stats { + unsigned long memcg_id; + int nr_nodes; /* Number of populated nodes entries. */ + struct node_stats nodes[MAX_NR_NODES]; +}; + +void lru_gen_read_memcg_stats(struct memcg_stats *stats, const char *memcg); +long lru_gen_sum_memcg_stats(const struct memcg_stats *stats); +long lru_gen_sum_memcg_stats_for_gen(int gen, const struct memcg_stats *stats); +void lru_gen_do_aging(struct memcg_stats *stats, const char *memcg); +int lru_gen_find_generation(const struct memcg_stats *stats, + unsigned long total_pages); +bool lru_gen_usable(void); + +#endif /* SELFTEST_KVM_LRU_GEN_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/memstress.h b/tools/testing/selftests/kvm/include/memstress.h index 9071eb6dea60..0d1d6230cc05 100644 --- a/tools/testing/selftests/kvm/include/memstress.h +++ b/tools/testing/selftests/kvm/include/memstress.h @@ -20,9 +20,9 @@ #define MEMSTRESS_MEM_SLOT_INDEX 1 struct memstress_vcpu_args { - uint64_t gpa; - uint64_t gva; - uint64_t pages; + gpa_t gpa; + gva_t gva; + u64 pages; /* Only used by the host userspace part of the vCPU thread */ struct kvm_vcpu *vcpu; @@ -32,11 +32,11 @@ struct memstress_vcpu_args { struct memstress_args { struct kvm_vm *vm; /* The starting address and size of the guest test region. */ - uint64_t gpa; - uint64_t size; - uint64_t guest_page_size; - uint32_t random_seed; - uint32_t write_percent; + gpa_t gpa; + u64 size; + u64 guest_page_size; + u32 random_seed; + u32 write_percent; /* Run vCPUs in L2 instead of L1, if the architecture supports it. */ bool nested; @@ -45,7 +45,7 @@ struct memstress_args { /* True if all vCPUs are pinned to pCPUs */ bool pin_vcpus; /* The vCPU=>pCPU pinning map. Only valid if pin_vcpus is true. */ - uint32_t vcpu_to_pcpu[KVM_MAX_VCPUS]; + u32 vcpu_to_pcpu[KVM_MAX_VCPUS]; /* Test is done, stop running vCPUs. */ bool stop_vcpus; @@ -56,27 +56,27 @@ struct memstress_args { extern struct memstress_args memstress_args; struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, - uint64_t vcpu_memory_bytes, int slots, + u64 vcpu_memory_bytes, int slots, enum vm_mem_backing_src_type backing_src, bool partition_vcpu_memory_access); void memstress_destroy_vm(struct kvm_vm *vm); -void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent); +void memstress_set_write_percent(struct kvm_vm *vm, u32 write_percent); void memstress_set_random_access(struct kvm_vm *vm, bool random_access); void memstress_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct memstress_vcpu_args *)); void memstress_join_vcpu_threads(int vcpus); -void memstress_guest_code(uint32_t vcpu_id); +void memstress_guest_code(u32 vcpu_id); -uint64_t memstress_nested_pages(int nr_vcpus); +u64 memstress_nested_pages(int nr_vcpus); void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]); void memstress_enable_dirty_logging(struct kvm_vm *vm, int slots); void memstress_disable_dirty_logging(struct kvm_vm *vm, int slots); void memstress_get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots); void memstress_clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], - int slots, uint64_t pages_per_slot); -unsigned long **memstress_alloc_bitmaps(int slots, uint64_t pages_per_slot); + int slots, u64 pages_per_slot); +unsigned long **memstress_alloc_bitmaps(int slots, u64 pages_per_slot); void memstress_free_bitmaps(unsigned long *bitmaps[], int slots); #endif /* SELFTEST_KVM_MEMSTRESS_H */ diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h index b020547403fd..29572a6d789c 100644 --- a/tools/testing/selftests/kvm/include/numaif.h +++ b/tools/testing/selftests/kvm/include/numaif.h @@ -1,55 +1,83 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* - * tools/testing/selftests/kvm/include/numaif.h - * - * Copyright (C) 2020, Google LLC. - * - * This work is licensed under the terms of the GNU GPL, version 2. - * - * Header file that provides access to NUMA API functions not explicitly - * exported to user space. - */ +/* Copyright (C) 2020, Google LLC. */ #ifndef SELFTEST_KVM_NUMAIF_H #define SELFTEST_KVM_NUMAIF_H -#define __NR_get_mempolicy 239 -#define __NR_migrate_pages 256 +#include <dirent.h> -/* System calls */ -long get_mempolicy(int *policy, const unsigned long *nmask, - unsigned long maxnode, void *addr, int flags) +#include <linux/mempolicy.h> + +#include "kvm_syscalls.h" + +KVM_SYSCALL_DEFINE(get_mempolicy, 5, int *, policy, const unsigned long *, nmask, + unsigned long, maxnode, void *, addr, int, flags); + +KVM_SYSCALL_DEFINE(set_mempolicy, 3, int, mode, const unsigned long *, nmask, + unsigned long, maxnode); + +KVM_SYSCALL_DEFINE(set_mempolicy_home_node, 4, unsigned long, start, + unsigned long, len, unsigned long, home_node, + unsigned long, flags); + +KVM_SYSCALL_DEFINE(migrate_pages, 4, int, pid, unsigned long, maxnode, + const unsigned long *, frommask, const unsigned long *, tomask); + +KVM_SYSCALL_DEFINE(move_pages, 6, int, pid, unsigned long, count, void *, pages, + const int *, nodes, int *, status, int, flags); + +KVM_SYSCALL_DEFINE(mbind, 6, void *, addr, unsigned long, size, int, mode, + const unsigned long *, nodemask, unsigned long, maxnode, + unsigned int, flags); + +static inline int get_max_numa_node(void) { - return syscall(__NR_get_mempolicy, policy, nmask, - maxnode, addr, flags); + struct dirent *de; + int max_node = 0; + DIR *d; + + /* + * Assume there's a single node if the kernel doesn't support NUMA, + * or if no nodes are found. + */ + d = opendir("/sys/devices/system/node"); + if (!d) + return 0; + + while ((de = readdir(d)) != NULL) { + int node_id; + char *endptr; + + if (strncmp(de->d_name, "node", 4) != 0) + continue; + + node_id = strtol(de->d_name + 4, &endptr, 10); + if (*endptr != '\0') + continue; + + if (node_id > max_node) + max_node = node_id; + } + closedir(d); + + return max_node; } -long migrate_pages(int pid, unsigned long maxnode, - const unsigned long *frommask, - const unsigned long *tomask) +static bool is_numa_available(void) { - return syscall(__NR_migrate_pages, pid, maxnode, frommask, tomask); + /* + * Probe for NUMA by doing a dummy get_mempolicy(). If the syscall + * fails with ENOSYS, then the kernel was built without NUMA support. + * if the syscall fails with EPERM, then the process/user lacks the + * necessary capabilities (CAP_SYS_NICE). + */ + return !get_mempolicy(NULL, NULL, 0, NULL, 0) || + (errno != ENOSYS && errno != EPERM); } -/* Policies */ -#define MPOL_DEFAULT 0 -#define MPOL_PREFERRED 1 -#define MPOL_BIND 2 -#define MPOL_INTERLEAVE 3 - -#define MPOL_MAX MPOL_INTERLEAVE - -/* Flags for get_mem_policy */ -#define MPOL_F_NODE (1<<0) /* return next il node or node of address */ - /* Warning: MPOL_F_NODE is unsupported and - * subject to change. Don't use. - */ -#define MPOL_F_ADDR (1<<1) /* look up vma using address */ -#define MPOL_F_MEMS_ALLOWED (1<<2) /* query nodes allowed in cpuset */ - -/* Flags for mbind */ -#define MPOL_MF_STRICT (1<<0) /* Verify existing pages in the mapping */ -#define MPOL_MF_MOVE (1<<1) /* Move pages owned by this process to conform to mapping */ -#define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to mapping */ +static inline bool is_multi_numa_node_system(void) +{ + return is_numa_available() && get_max_numa_node() >= 1; +} #endif /* SELFTEST_KVM_NUMAIF_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/arch_timer.h b/tools/testing/selftests/kvm/include/riscv/arch_timer.h index 225d81dad064..28ffc014da2a 100644 --- a/tools/testing/selftests/kvm/include/riscv/arch_timer.h +++ b/tools/testing/selftests/kvm/include/riscv/arch_timer.h @@ -14,25 +14,25 @@ static unsigned long timer_freq; #define msec_to_cycles(msec) \ - ((timer_freq) * (uint64_t)(msec) / 1000) + ((timer_freq) * (u64)(msec) / 1000) #define usec_to_cycles(usec) \ - ((timer_freq) * (uint64_t)(usec) / 1000000) + ((timer_freq) * (u64)(usec) / 1000000) #define cycles_to_usec(cycles) \ - ((uint64_t)(cycles) * 1000000 / (timer_freq)) + ((u64)(cycles) * 1000000 / (timer_freq)) -static inline uint64_t timer_get_cycles(void) +static inline u64 timer_get_cycles(void) { return csr_read(CSR_TIME); } -static inline void timer_set_cmp(uint64_t cval) +static inline void timer_set_cmp(u64 cval) { csr_write(CSR_STIMECMP, cval); } -static inline uint64_t timer_get_cmp(void) +static inline u64 timer_get_cmp(void) { return csr_read(CSR_STIMECMP); } @@ -47,17 +47,17 @@ static inline void timer_irq_disable(void) csr_clear(CSR_SIE, IE_TIE); } -static inline void timer_set_next_cmp_ms(uint32_t msec) +static inline void timer_set_next_cmp_ms(u32 msec) { - uint64_t now_ct = timer_get_cycles(); - uint64_t next_ct = now_ct + msec_to_cycles(msec); + u64 now_ct = timer_get_cycles(); + u64 next_ct = now_ct + msec_to_cycles(msec); timer_set_cmp(next_ct); } -static inline void __delay(uint64_t cycles) +static inline void __delay(u64 cycles) { - uint64_t start = timer_get_cycles(); + u64 start = timer_get_cycles(); while ((timer_get_cycles() - start) < cycles) cpu_relax(); diff --git a/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h index e43a57d99b56..d5095900e442 100644 --- a/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h @@ -2,6 +2,7 @@ #ifndef SELFTEST_KVM_UTIL_ARCH_H #define SELFTEST_KVM_UTIL_ARCH_H +struct kvm_mmu_arch {}; struct kvm_vm_arch {}; #endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index 5f389166338c..e3acf2ae9881 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -9,10 +9,23 @@ #include <linux/stringify.h> #include <asm/csr.h> +#include <asm/vdso/processor.h> #include "kvm_util.h" -static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, - uint64_t idx, uint64_t size) +#define INSN_OPCODE_MASK 0x007c +#define INSN_OPCODE_SHIFT 2 +#define INSN_OPCODE_SYSTEM 28 + +#define INSN_MASK_FUNCT3 0x7000 +#define INSN_SHIFT_FUNCT3 12 + +#define INSN_CSR_MASK 0xfff00000 +#define INSN_CSR_SHIFT 20 + +#define GET_RM(insn) (((insn) & INSN_MASK_FUNCT3) >> INSN_SHIFT_FUNCT3) +#define GET_CSR_NUM(insn) (((insn) & INSN_CSR_MASK) >> INSN_CSR_SHIFT) + +static inline u64 __kvm_reg_id(u64 type, u64 subtype, u64 idx, u64 size) { return KVM_REG_RISCV | type | subtype | idx | size; } @@ -48,19 +61,20 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, KVM_REG_RISCV_SBI_SINGLE, \ idx, KVM_REG_SIZE_ULONG) -bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext); +bool __vcpu_has_ext(struct kvm_vcpu *vcpu, u64 ext); -static inline bool __vcpu_has_isa_ext(struct kvm_vcpu *vcpu, uint64_t isa_ext) +static inline bool __vcpu_has_isa_ext(struct kvm_vcpu *vcpu, u64 isa_ext) { return __vcpu_has_ext(vcpu, RISCV_ISA_EXT_REG(isa_ext)); } -static inline bool __vcpu_has_sbi_ext(struct kvm_vcpu *vcpu, uint64_t sbi_ext) +static inline bool __vcpu_has_sbi_ext(struct kvm_vcpu *vcpu, u64 sbi_ext) { return __vcpu_has_ext(vcpu, RISCV_SBI_EXT_REG(sbi_ext)); } -struct ex_regs { +struct pt_regs { + unsigned long epc; unsigned long ra; unsigned long sp; unsigned long gp; @@ -92,16 +106,19 @@ struct ex_regs { unsigned long t4; unsigned long t5; unsigned long t6; - unsigned long epc; + /* Supervisor/Machine CSRs */ unsigned long status; + unsigned long badaddr; unsigned long cause; + /* a0 value before the syscall */ + unsigned long orig_a0; }; #define NR_VECTORS 2 #define NR_EXCEPTIONS 32 #define EC_MASK (NR_EXCEPTIONS - 1) -typedef void(*exception_handler_fn)(struct ex_regs *); +typedef void(*exception_handler_fn)(struct pt_regs *); void vm_init_vector_tables(struct kvm_vm *vm); void vcpu_init_vector_tables(struct kvm_vcpu *vcpu); @@ -174,4 +191,6 @@ static inline void local_irq_disable(void) csr_clear(CSR_SSTATUS, SR_SIE); } +unsigned long riscv64_get_satp_mode(void); + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/sbi.h b/tools/testing/selftests/kvm/include/riscv/sbi.h index 046b432ae896..16f1815ac48f 100644 --- a/tools/testing/selftests/kvm/include/riscv/sbi.h +++ b/tools/testing/selftests/kvm/include/riscv/sbi.h @@ -97,6 +97,43 @@ enum sbi_pmu_hw_generic_events_t { SBI_PMU_HW_GENERAL_MAX, }; +enum sbi_pmu_fw_generic_events_t { + SBI_PMU_FW_MISALIGNED_LOAD = 0, + SBI_PMU_FW_MISALIGNED_STORE = 1, + SBI_PMU_FW_ACCESS_LOAD = 2, + SBI_PMU_FW_ACCESS_STORE = 3, + SBI_PMU_FW_ILLEGAL_INSN = 4, + SBI_PMU_FW_SET_TIMER = 5, + SBI_PMU_FW_IPI_SENT = 6, + SBI_PMU_FW_IPI_RCVD = 7, + SBI_PMU_FW_FENCE_I_SENT = 8, + SBI_PMU_FW_FENCE_I_RCVD = 9, + SBI_PMU_FW_SFENCE_VMA_SENT = 10, + SBI_PMU_FW_SFENCE_VMA_RCVD = 11, + SBI_PMU_FW_SFENCE_VMA_ASID_SENT = 12, + SBI_PMU_FW_SFENCE_VMA_ASID_RCVD = 13, + + SBI_PMU_FW_HFENCE_GVMA_SENT = 14, + SBI_PMU_FW_HFENCE_GVMA_RCVD = 15, + SBI_PMU_FW_HFENCE_GVMA_VMID_SENT = 16, + SBI_PMU_FW_HFENCE_GVMA_VMID_RCVD = 17, + + SBI_PMU_FW_HFENCE_VVMA_SENT = 18, + SBI_PMU_FW_HFENCE_VVMA_RCVD = 19, + SBI_PMU_FW_HFENCE_VVMA_ASID_SENT = 20, + SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD = 21, + SBI_PMU_FW_MAX, +}; + +/* SBI PMU event types */ +enum sbi_pmu_event_type { + SBI_PMU_EVENT_TYPE_HW = 0x0, + SBI_PMU_EVENT_TYPE_CACHE = 0x1, + SBI_PMU_EVENT_TYPE_RAW = 0x2, + SBI_PMU_EVENT_TYPE_RAW_V2 = 0x3, + SBI_PMU_EVENT_TYPE_FW = 0xf, +}; + /* SBI PMU counter types */ enum sbi_pmu_ctr_type { SBI_PMU_CTR_TYPE_HW = 0x0, diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h index a695ae36f3e0..2de7c6a36096 100644 --- a/tools/testing/selftests/kvm/include/riscv/ucall.h +++ b/tools/testing/selftests/kvm/include/riscv/ucall.h @@ -7,11 +7,11 @@ #define UCALL_EXIT_REASON KVM_EXIT_RISCV_SBI -static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { } -static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +static inline void ucall_arch_do_ucall(gva_t uc) { sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, KVM_RISCV_SELFTESTS_SBI_UCALL, diff --git a/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h index b0ed71302722..6deaf18fec22 100644 --- a/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h +++ b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h @@ -8,6 +8,6 @@ #ifndef SELFTEST_KVM_DIAG318_TEST_HANDLER #define SELFTEST_KVM_DIAG318_TEST_HANDLER -uint64_t get_diag318_info(void); +u64 get_diag318_info(void); #endif diff --git a/tools/testing/selftests/kvm/include/s390/facility.h b/tools/testing/selftests/kvm/include/s390/facility.h index 00a1ced6538b..41a265742666 100644 --- a/tools/testing/selftests/kvm/include/s390/facility.h +++ b/tools/testing/selftests/kvm/include/s390/facility.h @@ -16,7 +16,7 @@ /* alt_stfle_fac_list[16] + stfle_fac_list[16] */ #define NB_STFL_DOUBLEWORDS 32 -extern uint64_t stfl_doublewords[NB_STFL_DOUBLEWORDS]; +extern u64 stfl_doublewords[NB_STFL_DOUBLEWORDS]; extern bool stfle_flag; static inline bool test_bit_inv(unsigned long nr, const unsigned long *ptr) @@ -24,7 +24,7 @@ static inline bool test_bit_inv(unsigned long nr, const unsigned long *ptr) return test_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -static inline void stfle(uint64_t *fac, unsigned int nb_doublewords) +static inline void stfle(u64 *fac, unsigned int nb_doublewords) { register unsigned long r0 asm("0") = nb_doublewords - 1; diff --git a/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h b/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h index e43a57d99b56..d5095900e442 100644 --- a/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h @@ -2,6 +2,7 @@ #ifndef SELFTEST_KVM_UTIL_ARCH_H #define SELFTEST_KVM_UTIL_ARCH_H +struct kvm_mmu_arch {}; struct kvm_vm_arch {}; #endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/s390/ucall.h b/tools/testing/selftests/kvm/include/s390/ucall.h index 8035a872a351..3907d629304f 100644 --- a/tools/testing/selftests/kvm/include/s390/ucall.h +++ b/tools/testing/selftests/kvm/include/s390/ucall.h @@ -6,11 +6,11 @@ #define UCALL_EXIT_REASON KVM_EXIT_S390_SIEIC -static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { } -static inline void ucall_arch_do_ucall(vm_vaddr_t uc) +static inline void ucall_arch_do_ucall(gva_t uc) { /* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */ asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory"); diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h index bc760761e1a3..e027e5790946 100644 --- a/tools/testing/selftests/kvm/include/sparsebit.h +++ b/tools/testing/selftests/kvm/include/sparsebit.h @@ -6,7 +6,7 @@ * * Header file that describes API to the sparsebit library. * This library provides a memory efficient means of storing - * the settings of bits indexed via a uint64_t. Memory usage + * the settings of bits indexed via a u64. Memory usage * is reasonable, significantly less than (2^64 / 8) bytes, as * long as bits that are mostly set or mostly cleared are close * to each other. This library is efficient in memory usage @@ -25,8 +25,8 @@ extern "C" { #endif struct sparsebit; -typedef uint64_t sparsebit_idx_t; -typedef uint64_t sparsebit_num_t; +typedef u64 sparsebit_idx_t; +typedef u64 sparsebit_num_t; struct sparsebit *sparsebit_alloc(void); void sparsebit_free(struct sparsebit **sbitp); diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 3e473058849f..d9b433b834f1 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -8,6 +8,8 @@ #ifndef SELFTEST_KVM_TEST_UTIL_H #define SELFTEST_KVM_TEST_UTIL_H +#include <setjmp.h> +#include <signal.h> #include <stdlib.h> #include <stdarg.h> #include <stdbool.h> @@ -20,9 +22,11 @@ #include <sys/mman.h> #include "kselftest.h" +#include <linux/types.h> + #define msecs_to_usecs(msec) ((msec) * 1000ULL) -static inline int _no_printf(const char *format, ...) { return 0; } +static inline __printf(1, 2) int _no_printf(const char *format, ...) { return 0; } #ifdef DEBUG #define pr_debug(...) printf(__VA_ARGS__) @@ -78,27 +82,44 @@ do { \ __builtin_unreachable(); \ } while (0) +extern sigjmp_buf expect_sigbus_jmpbuf; +void expect_sigbus_handler(int signum); + +#define TEST_EXPECT_SIGBUS(action) \ +do { \ + struct sigaction sa_old, sa_new = { \ + .sa_handler = expect_sigbus_handler, \ + }; \ + \ + sigaction(SIGBUS, &sa_new, &sa_old); \ + if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \ + action; \ + TEST_FAIL("'%s' should have triggered SIGBUS", #action); \ + } \ + sigaction(SIGBUS, &sa_old, NULL); \ +} while (0) + size_t parse_size(const char *size); -int64_t timespec_to_ns(struct timespec ts); -struct timespec timespec_add_ns(struct timespec ts, int64_t ns); +s64 timespec_to_ns(struct timespec ts); +struct timespec timespec_add_ns(struct timespec ts, s64 ns); struct timespec timespec_add(struct timespec ts1, struct timespec ts2); struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); struct timespec timespec_elapsed(struct timespec start); struct timespec timespec_div(struct timespec ts, int divisor); struct guest_random_state { - uint32_t seed; + u32 seed; }; -extern uint32_t guest_random_seed; +extern u32 guest_random_seed; extern struct guest_random_state guest_rng; -struct guest_random_state new_guest_random_state(uint32_t seed); -uint32_t guest_random_u32(struct guest_random_state *state); +struct guest_random_state new_guest_random_state(u32 seed); +u32 guest_random_u32(struct guest_random_state *state); static inline bool __guest_random_bool(struct guest_random_state *state, - uint8_t percent) + u8 percent) { return (guest_random_u32(state) % 100) < percent; } @@ -108,9 +129,9 @@ static inline bool guest_random_bool(struct guest_random_state *state) return __guest_random_bool(state, 50); } -static inline uint64_t guest_random_u64(struct guest_random_state *state) +static inline u64 guest_random_u64(struct guest_random_state *state) { - return ((uint64_t)guest_random_u32(state) << 32) | guest_random_u32(state); + return ((u64)guest_random_u32(state) << 32) | guest_random_u32(state); } enum vm_mem_backing_src_type { @@ -139,7 +160,7 @@ enum vm_mem_backing_src_type { struct vm_mem_backing_src_alias { const char *name; - uint32_t flag; + u32 flag; }; #define MIN_RUN_DELAY_NS 200000UL @@ -147,12 +168,13 @@ struct vm_mem_backing_src_alias { bool thp_configured(void); size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); -const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); -size_t get_backing_src_pagesz(uint32_t i); -bool is_backing_src_hugetlb(uint32_t i); +const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(u32 i); +size_t get_backing_src_pagesz(u32 i); +bool is_backing_src_hugetlb(u32 i); void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); long get_run_delay(void); +bool is_numa_balancing_enabled(void); /* * Whether or not the given source type is shared memory (as opposed to @@ -169,18 +191,18 @@ static inline bool backing_src_can_be_huge(enum vm_mem_backing_src_type t) } /* Aligns x up to the next multiple of size. Size must be a power of 2. */ -static inline uint64_t align_up(uint64_t x, uint64_t size) +static inline u64 align_up(u64 x, u64 size) { - uint64_t mask = size - 1; + u64 mask = size - 1; TEST_ASSERT(size != 0 && !(size & (size - 1)), "size not a power of 2: %lu", size); return ((x + mask) & ~mask); } -static inline uint64_t align_down(uint64_t x, uint64_t size) +static inline u64 align_down(u64 x, u64 size) { - uint64_t x_aligned_up = align_up(x, size); + u64 x_aligned_up = align_up(x, size); if (x == x_aligned_up) return x; @@ -195,7 +217,7 @@ static inline void *align_ptr_up(void *x, size_t size) int atoi_paranoid(const char *num_str); -static inline uint32_t atoi_positive(const char *name, const char *num_str) +static inline u32 atoi_positive(const char *name, const char *num_str) { int num = atoi_paranoid(num_str); @@ -203,7 +225,7 @@ static inline uint32_t atoi_positive(const char *name, const char *num_str) return num; } -static inline uint32_t atoi_non_negative(const char *name, const char *num_str) +static inline u32 atoi_non_negative(const char *name, const char *num_str) { int num = atoi_paranoid(num_str); diff --git a/tools/testing/selftests/kvm/include/timer_test.h b/tools/testing/selftests/kvm/include/timer_test.h index 9b6edaafe6d4..b7d5d2c84701 100644 --- a/tools/testing/selftests/kvm/include/timer_test.h +++ b/tools/testing/selftests/kvm/include/timer_test.h @@ -18,21 +18,21 @@ /* Timer test cmdline parameters */ struct test_args { - uint32_t nr_vcpus; - uint32_t nr_iter; - uint32_t timer_period_ms; - uint32_t migration_freq_ms; - uint32_t timer_err_margin_us; + u32 nr_vcpus; + u32 nr_iter; + u32 timer_period_ms; + u32 migration_freq_ms; + u32 timer_err_margin_us; /* Members of struct kvm_arm_counter_offset */ - uint64_t counter_offset; - uint64_t reserved; + u64 counter_offset; + u64 reserved; }; /* Shared variables between host and guest */ struct test_vcpu_shared_data { - uint32_t nr_iter; + u32 nr_iter; int guest_stage; - uint64_t xcnt; + u64 xcnt; }; extern struct test_args test_args; diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index d9d6581b8d4f..cbdcb0a50c4f 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -21,26 +21,26 @@ enum { #define UCALL_BUFFER_LEN 1024 struct ucall { - uint64_t cmd; - uint64_t args[UCALL_MAX_ARGS]; + u64 cmd; + u64 args[UCALL_MAX_ARGS]; char buffer[UCALL_BUFFER_LEN]; /* Host virtual address of this struct. */ struct ucall *hva; }; -void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); -void ucall_arch_do_ucall(vm_vaddr_t uc); +void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa); +void ucall_arch_do_ucall(gva_t uc); void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu); -void ucall(uint64_t cmd, int nargs, ...); -__printf(2, 3) void ucall_fmt(uint64_t cmd, const char *fmt, ...); -__printf(5, 6) void ucall_assert(uint64_t cmd, const char *exp, +void ucall(u64 cmd, int nargs, ...); +__printf(2, 3) void ucall_fmt(u64 cmd, const char *fmt, ...); +__printf(5, 6) void ucall_assert(u64 cmd, const char *exp, const char *file, unsigned int line, const char *fmt, ...); -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); -void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); -int ucall_nr_pages_required(uint64_t page_size); +u64 get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); +void ucall_init(struct kvm_vm *vm, gpa_t mmio_gpa); +int ucall_nr_pages_required(u64 page_size); /* * Perform userspace call without any associated data. This bare call avoids @@ -48,7 +48,7 @@ int ucall_nr_pages_required(uint64_t page_size); * the full ucall() are problematic and/or unwanted. Note, this will come out * as UCALL_NONE on the backend. */ -#define GUEST_UCALL_NONE() ucall_arch_do_ucall((vm_vaddr_t)NULL) +#define GUEST_UCALL_NONE() ucall_arch_do_ucall((gva_t)NULL) #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) diff --git a/tools/testing/selftests/kvm/include/userfaultfd_util.h b/tools/testing/selftests/kvm/include/userfaultfd_util.h index 60f7f9d435dc..0bc1dc16600e 100644 --- a/tools/testing/selftests/kvm/include/userfaultfd_util.h +++ b/tools/testing/selftests/kvm/include/userfaultfd_util.h @@ -25,7 +25,7 @@ struct uffd_reader_args { struct uffd_desc { int uffd; - uint64_t num_readers; + u64 num_readers; /* Holds the write ends of the pipes for killing the readers. */ int *pipefds; pthread_t *readers; @@ -33,8 +33,8 @@ struct uffd_desc { }; struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, - void *hva, uint64_t len, - uint64_t num_readers, + void *hva, u64 len, + u64 num_readers, uffd_handler_t handler); void uffd_stop_demand_paging(struct uffd_desc *uffd); diff --git a/tools/testing/selftests/kvm/include/x86/apic.h b/tools/testing/selftests/kvm/include/x86/apic.h index 80fe9f69b38d..31887bdc3d6c 100644 --- a/tools/testing/selftests/kvm/include/x86/apic.h +++ b/tools/testing/selftests/kvm/include/x86/apic.h @@ -28,10 +28,13 @@ #define GET_APIC_ID_FIELD(x) (((x) >> 24) & 0xFF) #define APIC_TASKPRI 0x80 #define APIC_PROCPRI 0xA0 +#define GET_APIC_PRI(x) (((x) & GENMASK(7, 4)) >> 4) +#define SET_APIC_PRI(x, y) (((x) & ~GENMASK(7, 4)) | (y << 4)) #define APIC_EOI 0xB0 #define APIC_SPIV 0xF0 #define APIC_SPIV_FOCUS_DISABLED (1 << 9) #define APIC_SPIV_APIC_ENABLED (1 << 8) +#define APIC_ISR 0x100 #define APIC_IRR 0x200 #define APIC_ICR 0x300 #define APIC_LVTCMCI 0x2f0 @@ -67,47 +70,51 @@ #define APIC_TMICT 0x380 #define APIC_TMCCT 0x390 #define APIC_TDCR 0x3E0 +#define APIC_SELF_IPI 0x3F0 + +#define APIC_VECTOR_TO_BIT_NUMBER(v) ((unsigned int)(v) % 32) +#define APIC_VECTOR_TO_REG_OFFSET(v) ((unsigned int)(v) / 32 * 0x10) void apic_disable(void); void xapic_enable(void); void x2apic_enable(void); -static inline uint32_t get_bsp_flag(void) +static inline u32 get_bsp_flag(void) { return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP; } -static inline uint32_t xapic_read_reg(unsigned int reg) +static inline u32 xapic_read_reg(unsigned int reg) { - return ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2]; + return ((volatile u32 *)APIC_DEFAULT_GPA)[reg >> 2]; } -static inline void xapic_write_reg(unsigned int reg, uint32_t val) +static inline void xapic_write_reg(unsigned int reg, u32 val) { - ((volatile uint32_t *)APIC_DEFAULT_GPA)[reg >> 2] = val; + ((volatile u32 *)APIC_DEFAULT_GPA)[reg >> 2] = val; } -static inline uint64_t x2apic_read_reg(unsigned int reg) +static inline u64 x2apic_read_reg(unsigned int reg) { return rdmsr(APIC_BASE_MSR + (reg >> 4)); } -static inline uint8_t x2apic_write_reg_safe(unsigned int reg, uint64_t value) +static inline u8 x2apic_write_reg_safe(unsigned int reg, u64 value) { return wrmsr_safe(APIC_BASE_MSR + (reg >> 4), value); } -static inline void x2apic_write_reg(unsigned int reg, uint64_t value) +static inline void x2apic_write_reg(unsigned int reg, u64 value) { - uint8_t fault = x2apic_write_reg_safe(reg, value); + u8 fault = x2apic_write_reg_safe(reg, value); __GUEST_ASSERT(!fault, "Unexpected fault 0x%x on WRMSR(%x) = %lx\n", fault, APIC_BASE_MSR + (reg >> 4), value); } -static inline void x2apic_write_reg_fault(unsigned int reg, uint64_t value) +static inline void x2apic_write_reg_fault(unsigned int reg, u64 value) { - uint8_t fault = x2apic_write_reg_safe(reg, value); + u8 fault = x2apic_write_reg_safe(reg, value); __GUEST_ASSERT(fault == GP_VECTOR, "Wanted #GP on WRMSR(%x) = %lx, got 0x%x\n", diff --git a/tools/testing/selftests/kvm/include/x86/evmcs.h b/tools/testing/selftests/kvm/include/x86/evmcs.h index 5a74bb30e2f8..be79bda024bf 100644 --- a/tools/testing/selftests/kvm/include/x86/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86/evmcs.h @@ -10,9 +10,9 @@ #include "hyperv.h" #include "vmx.h" -#define u16 uint16_t -#define u32 uint32_t -#define u64 uint64_t +#define u16 u16 +#define u32 u32 +#define u64 u64 #define EVMCS_VERSION 1 @@ -245,7 +245,7 @@ static inline void evmcs_enable(void) enable_evmcs = true; } -static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs) +static inline int evmcs_vmptrld(u64 vmcs_pa, void *vmcs) { current_vp_assist->current_nested_vmcs = vmcs_pa; current_vp_assist->enlighten_vmentry = 1; @@ -265,7 +265,7 @@ static inline bool load_evmcs(struct hyperv_test_pages *hv) return true; } -static inline int evmcs_vmptrst(uint64_t *value) +static inline int evmcs_vmptrst(u64 *value) { *value = current_vp_assist->current_nested_vmcs & ~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; @@ -273,7 +273,7 @@ static inline int evmcs_vmptrst(uint64_t *value) return 0; } -static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) +static inline int evmcs_vmread(u64 encoding, u64 *value) { switch (encoding) { case GUEST_RIP: @@ -672,7 +672,7 @@ static inline int evmcs_vmread(uint64_t encoding, uint64_t *value) return 0; } -static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value) +static inline int evmcs_vmwrite(u64 encoding, u64 value) { switch (encoding) { case GUEST_RIP: @@ -1226,9 +1226,9 @@ static inline int evmcs_vmlaunch(void) "pop %%rbp;" : [ret]"=&a"(ret) : [host_rsp]"r" - ((uint64_t)¤t_evmcs->host_rsp), + ((u64)¤t_evmcs->host_rsp), [host_rip]"r" - ((uint64_t)¤t_evmcs->host_rip) + ((u64)¤t_evmcs->host_rip) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -1265,9 +1265,9 @@ static inline int evmcs_vmresume(void) "pop %%rbp;" : [ret]"=&a"(ret) : [host_rsp]"r" - ((uint64_t)¤t_evmcs->host_rsp), + ((u64)¤t_evmcs->host_rsp), [host_rip]"r" - ((uint64_t)¤t_evmcs->host_rip) + ((u64)¤t_evmcs->host_rip) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; diff --git a/tools/testing/selftests/kvm/include/x86/hyperv.h b/tools/testing/selftests/kvm/include/x86/hyperv.h index f13e532be240..78003f5a22f3 100644 --- a/tools/testing/selftests/kvm/include/x86/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86/hyperv.h @@ -254,12 +254,12 @@ * Issue a Hyper-V hypercall. Returns exception vector raised or 0, 'hv_status' * is set to the hypercall status (if no exception occurred). */ -static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address, - vm_vaddr_t output_address, - uint64_t *hv_status) +static inline u8 __hyperv_hypercall(u64 control, gva_t input_address, + gva_t output_address, + u64 *hv_status) { - uint64_t error_code; - uint8_t vector; + u64 error_code; + u8 vector; /* Note both the hypercall and the "asm safe" clobber r9-r11. */ asm volatile("mov %[output_address], %%r8\n\t" @@ -274,11 +274,11 @@ static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address, } /* Issue a Hyper-V hypercall and assert that it succeeded. */ -static inline void hyperv_hypercall(u64 control, vm_vaddr_t input_address, - vm_vaddr_t output_address) +static inline void hyperv_hypercall(u64 control, gva_t input_address, + gva_t output_address) { - uint64_t hv_status; - uint8_t vector; + u64 hv_status; + u8 vector; vector = __hyperv_hypercall(control, input_address, output_address, &hv_status); @@ -327,27 +327,27 @@ struct hv_vp_assist_page { extern struct hv_vp_assist_page *current_vp_assist; -int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist); +int enable_vp_assist(u64 vp_assist_pa, void *vp_assist); struct hyperv_test_pages { /* VP assist page */ void *vp_assist_hva; - uint64_t vp_assist_gpa; + u64 vp_assist_gpa; void *vp_assist; /* Partition assist page */ void *partition_assist_hva; - uint64_t partition_assist_gpa; + u64 partition_assist_gpa; void *partition_assist; /* Enlightened VMCS */ void *enlightened_vmcs_hva; - uint64_t enlightened_vmcs_gpa; + u64 enlightened_vmcs_gpa; void *enlightened_vmcs; }; struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, - vm_vaddr_t *p_hv_pages_gva); + gva_t *p_hv_pages_gva); /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) diff --git a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h index 972bb1c4ab4c..c33ab6e04171 100644 --- a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h @@ -10,13 +10,35 @@ extern bool is_forced_emulation_enabled; +struct pte_masks { + u64 present; + u64 writable; + u64 user; + u64 readable; + u64 executable; + u64 accessed; + u64 dirty; + u64 huge; + u64 nx; + u64 c; + u64 s; + + u64 always_set; +}; + +struct kvm_mmu_arch { + struct pte_masks pte_masks; +}; + +struct kvm_mmu; + struct kvm_vm_arch { - vm_vaddr_t gdt; - vm_vaddr_t tss; - vm_vaddr_t idt; + gva_t gdt; + gva_t tss; + gva_t idt; - uint64_t c_bit; - uint64_t s_bit; + u64 c_bit; + u64 s_bit; int sev_fd; bool is_pt_protected; }; @@ -40,7 +62,7 @@ do { \ : "+m" (mem) \ : "r" (val) : "memory"); \ } else { \ - uint64_t __old = READ_ONCE(mem); \ + u64 __old = READ_ONCE(mem); \ \ __asm__ __volatile__(KVM_FEP LOCK_PREFIX "cmpxchg %[new], %[ptr]" \ : [ptr] "+m" (mem), [old] "+a" (__old) \ diff --git a/tools/testing/selftests/kvm/include/x86/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h index 3c10c4dc0ae8..98537cc8840d 100644 --- a/tools/testing/selftests/kvm/include/x86/pmu.h +++ b/tools/testing/selftests/kvm/include/x86/pmu.h @@ -5,7 +5,10 @@ #ifndef SELFTEST_KVM_PMU_H #define SELFTEST_KVM_PMU_H -#include <stdint.h> +#include <stdbool.h> + +#include <linux/types.h> +#include <linux/bits.h> #define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300 @@ -61,6 +64,11 @@ #define INTEL_ARCH_BRANCHES_RETIRED RAW_EVENT(0xc4, 0x00) #define INTEL_ARCH_BRANCHES_MISPREDICTED RAW_EVENT(0xc5, 0x00) #define INTEL_ARCH_TOPDOWN_SLOTS RAW_EVENT(0xa4, 0x01) +#define INTEL_ARCH_TOPDOWN_BE_BOUND RAW_EVENT(0xa4, 0x02) +#define INTEL_ARCH_TOPDOWN_BAD_SPEC RAW_EVENT(0x73, 0x00) +#define INTEL_ARCH_TOPDOWN_FE_BOUND RAW_EVENT(0x9c, 0x01) +#define INTEL_ARCH_TOPDOWN_RETIRING RAW_EVENT(0xc2, 0x02) +#define INTEL_ARCH_LBR_INSERTS RAW_EVENT(0xe4, 0x01) #define AMD_ZEN_CORE_CYCLES RAW_EVENT(0x76, 0x00) #define AMD_ZEN_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00) @@ -80,6 +88,11 @@ enum intel_pmu_architectural_events { INTEL_ARCH_BRANCHES_RETIRED_INDEX, INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX, INTEL_ARCH_TOPDOWN_SLOTS_INDEX, + INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX, + INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX, + INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX, + INTEL_ARCH_TOPDOWN_RETIRING_INDEX, + INTEL_ARCH_LBR_INSERTS_INDEX, NR_INTEL_ARCH_EVENTS, }; @@ -91,7 +104,21 @@ enum amd_pmu_zen_events { NR_AMD_ZEN_EVENTS, }; -extern const uint64_t intel_pmu_arch_events[]; -extern const uint64_t amd_pmu_zen_events[]; +extern const u64 intel_pmu_arch_events[]; +extern const u64 amd_pmu_zen_events[]; + +enum pmu_errata { + INSTRUCTIONS_RETIRED_OVERCOUNT, + BRANCHES_RETIRED_OVERCOUNT, +}; + +extern u64 pmu_errata_mask; + +void kvm_init_pmu_errata(void); + +static inline bool this_pmu_has_errata(enum pmu_errata errata) +{ + return pmu_errata_mask & BIT_ULL(errata); +} #endif /* SELFTEST_KVM_PMU_H */ diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index d60da8966772..77f576ee7789 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -21,7 +21,9 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; -extern uint64_t guest_tsc_khz; +extern bool host_cpu_is_hygon; +extern bool host_cpu_is_amd_compatible; +extern u64 guest_tsc_khz; #ifndef MAX_NR_CPUID_ENTRIES #define MAX_NR_CPUID_ENTRIES 100 @@ -34,6 +36,8 @@ extern uint64_t guest_tsc_khz; #define NMI_VECTOR 0x02 +const char *ex_str(int vector); + #define X86_EFLAGS_FIXED (1u << 1) #define X86_CR4_VME (1ul << 0) @@ -183,6 +187,9 @@ struct kvm_x86_cpu_feature { * Extended Leafs, a.k.a. AMD defined */ #define X86_FEATURE_SVM KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 2) +#define X86_FEATURE_PERFCTR_CORE KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 23) +#define X86_FEATURE_PERFCTR_NB KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 24) +#define X86_FEATURE_PERFCTR_LLC KVM_X86_CPU_FEATURE(0x80000001, 0, ECX, 28) #define X86_FEATURE_NX KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 20) #define X86_FEATURE_GBPAGES KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 26) #define X86_FEATURE_RDTSCP KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 27) @@ -196,9 +203,14 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_TSCRATEMSR KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 4) #define X86_FEATURE_PAUSEFILTER KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 10) #define X86_FEATURE_PFTHRESHOLD KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 12) +#define X86_FEATURE_V_VMSAVE_VMLOAD KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 15) #define X86_FEATURE_VGIF KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 16) +#define X86_FEATURE_IDLE_HLT KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 30) #define X86_FEATURE_SEV KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1) #define X86_FEATURE_SEV_ES KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 3) +#define X86_FEATURE_SEV_SNP KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 4) +#define X86_FEATURE_PERFMON_V2 KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 0) +#define X86_FEATURE_LBR_PMC_FREEZE KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 2) /* * KVM defined paravirt features. @@ -258,7 +270,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15) #define X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 16, 23) #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31) -#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 7) +#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 12) #define X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK KVM_X86_CPU_PROPERTY(0xa, 0, ECX, 0, 31) #define X86_PROPERTY_PMU_NR_FIXED_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 0, 4) #define X86_PROPERTY_PMU_FIXED_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 5, 12) @@ -285,6 +297,8 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_GUEST_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 16, 23) #define X86_PROPERTY_SEV_C_BIT KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5) #define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11) +#define X86_PROPERTY_NR_PERFCTR_CORE KVM_X86_CPU_PROPERTY(0x80000022, 0, EBX, 0, 3) +#define X86_PROPERTY_NR_PERFCTR_NB KVM_X86_CPU_PROPERTY(0x80000022, 0, EBX, 10, 15) #define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31) @@ -323,6 +337,11 @@ struct kvm_x86_pmu_feature { #define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 5) #define X86_PMU_FEATURE_BRANCHES_MISPREDICTED KVM_X86_PMU_FEATURE(EBX, 6) #define X86_PMU_FEATURE_TOPDOWN_SLOTS KVM_X86_PMU_FEATURE(EBX, 7) +#define X86_PMU_FEATURE_TOPDOWN_BE_BOUND KVM_X86_PMU_FEATURE(EBX, 8) +#define X86_PMU_FEATURE_TOPDOWN_BAD_SPEC KVM_X86_PMU_FEATURE(EBX, 9) +#define X86_PMU_FEATURE_TOPDOWN_FE_BOUND KVM_X86_PMU_FEATURE(EBX, 10) +#define X86_PMU_FEATURE_TOPDOWN_RETIRING KVM_X86_PMU_FEATURE(EBX, 11) +#define X86_PMU_FEATURE_LBR_INSERTS KVM_X86_PMU_FEATURE(EBX, 12) #define X86_PMU_FEATURE_INSNS_RETIRED_FIXED KVM_X86_PMU_FEATURE(ECX, 0) #define X86_PMU_FEATURE_CPU_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 1) @@ -346,16 +365,6 @@ static inline unsigned int x86_model(unsigned int eax) return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f); } -/* Page table bitfield declarations */ -#define PTE_PRESENT_MASK BIT_ULL(0) -#define PTE_WRITABLE_MASK BIT_ULL(1) -#define PTE_USER_MASK BIT_ULL(2) -#define PTE_ACCESSED_MASK BIT_ULL(5) -#define PTE_DIRTY_MASK BIT_ULL(6) -#define PTE_LARGE_MASK BIT_ULL(7) -#define PTE_GLOBAL_MASK BIT_ULL(8) -#define PTE_NX_MASK BIT_ULL(63) - #define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12) #define PAGE_SHIFT 12 @@ -390,17 +399,17 @@ struct gpr64_regs { }; struct desc64 { - uint16_t limit0; - uint16_t base0; + u16 limit0; + u16 base0; unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; - uint32_t base3; - uint32_t zero1; + u32 base3; + u32 zero1; } __attribute__((packed)); struct desc_ptr { - uint16_t size; - uint64_t address; + u16 size; + u64 address; } __attribute__((packed)); struct kvm_x86_state { @@ -418,16 +427,18 @@ struct kvm_x86_state { struct kvm_msrs msrs; }; -static inline uint64_t get_desc64_base(const struct desc64 *desc) +static inline u64 get_desc64_base(const struct desc64 *desc) { - return ((uint64_t)desc->base3 << 32) | - (desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); + return (u64)desc->base3 << 32 | + (u64)desc->base2 << 24 | + (u64)desc->base1 << 16 | + (u64)desc->base0; } -static inline uint64_t rdtsc(void) +static inline u64 rdtsc(void) { - uint32_t eax, edx; - uint64_t tsc_val; + u32 eax, edx; + u64 tsc_val; /* * The lfence is to wait (on Intel CPUs) until all previous * instructions have been executed. If software requires RDTSC to be @@ -435,39 +446,39 @@ static inline uint64_t rdtsc(void) * execute LFENCE immediately after RDTSC */ __asm__ __volatile__("lfence; rdtsc; lfence" : "=a"(eax), "=d"(edx)); - tsc_val = ((uint64_t)edx) << 32 | eax; + tsc_val = ((u64)edx) << 32 | eax; return tsc_val; } -static inline uint64_t rdtscp(uint32_t *aux) +static inline u64 rdtscp(u32 *aux) { - uint32_t eax, edx; + u32 eax, edx; __asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux)); - return ((uint64_t)edx) << 32 | eax; + return ((u64)edx) << 32 | eax; } -static inline uint64_t rdmsr(uint32_t msr) +static inline u64 rdmsr(u32 msr) { - uint32_t a, d; + u32 a, d; __asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory"); - return a | ((uint64_t) d << 32); + return a | ((u64)d << 32); } -static inline void wrmsr(uint32_t msr, uint64_t value) +static inline void wrmsr(u32 msr, u64 value) { - uint32_t a = value; - uint32_t d = value >> 32; + u32 a = value; + u32 d = value >> 32; __asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory"); } -static inline uint16_t inw(uint16_t port) +static inline u16 inw(u16 port) { - uint16_t tmp; + u16 tmp; __asm__ __volatile__("in %%dx, %%ax" : /* output */ "=a" (tmp) @@ -476,101 +487,124 @@ static inline uint16_t inw(uint16_t port) return tmp; } -static inline uint16_t get_es(void) +static inline u16 get_es(void) { - uint16_t es; + u16 es; __asm__ __volatile__("mov %%es, %[es]" : /* output */ [es]"=rm"(es)); return es; } -static inline uint16_t get_cs(void) +static inline u16 get_cs(void) { - uint16_t cs; + u16 cs; __asm__ __volatile__("mov %%cs, %[cs]" : /* output */ [cs]"=rm"(cs)); return cs; } -static inline uint16_t get_ss(void) +static inline u16 get_ss(void) { - uint16_t ss; + u16 ss; __asm__ __volatile__("mov %%ss, %[ss]" : /* output */ [ss]"=rm"(ss)); return ss; } -static inline uint16_t get_ds(void) +static inline u16 get_ds(void) { - uint16_t ds; + u16 ds; __asm__ __volatile__("mov %%ds, %[ds]" : /* output */ [ds]"=rm"(ds)); return ds; } -static inline uint16_t get_fs(void) +static inline u16 get_fs(void) { - uint16_t fs; + u16 fs; __asm__ __volatile__("mov %%fs, %[fs]" : /* output */ [fs]"=rm"(fs)); return fs; } -static inline uint16_t get_gs(void) +static inline u16 get_gs(void) { - uint16_t gs; + u16 gs; __asm__ __volatile__("mov %%gs, %[gs]" : /* output */ [gs]"=rm"(gs)); return gs; } -static inline uint16_t get_tr(void) +static inline u16 get_tr(void) { - uint16_t tr; + u16 tr; __asm__ __volatile__("str %[tr]" : /* output */ [tr]"=rm"(tr)); return tr; } -static inline uint64_t get_cr0(void) +static inline u64 get_cr0(void) { - uint64_t cr0; + u64 cr0; __asm__ __volatile__("mov %%cr0, %[cr0]" : /* output */ [cr0]"=r"(cr0)); return cr0; } -static inline uint64_t get_cr3(void) +static inline void set_cr0(u64 val) { - uint64_t cr3; + __asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory"); +} + +static inline u64 get_cr3(void) +{ + u64 cr3; __asm__ __volatile__("mov %%cr3, %[cr3]" : /* output */ [cr3]"=r"(cr3)); return cr3; } -static inline uint64_t get_cr4(void) +static inline void set_cr3(u64 val) +{ + __asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory"); +} + +static inline u64 get_cr4(void) { - uint64_t cr4; + u64 cr4; __asm__ __volatile__("mov %%cr4, %[cr4]" : /* output */ [cr4]"=r"(cr4)); return cr4; } -static inline void set_cr4(uint64_t val) +static inline void set_cr4(u64 val) { __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline u64 get_cr8(void) +{ + u64 cr8; + + __asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8)); + return cr8; +} + +static inline void set_cr8(u64 val) +{ + __asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory"); +} + static inline void set_idt(const struct desc_ptr *idt_desc) { __asm__ __volatile__("lidt %0"::"m"(*idt_desc)); @@ -617,14 +651,14 @@ static inline struct desc_ptr get_idt(void) return idt; } -static inline void outl(uint16_t port, uint32_t value) +static inline void outl(u16 port, u32 value) { __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); } -static inline void __cpuid(uint32_t function, uint32_t index, - uint32_t *eax, uint32_t *ebx, - uint32_t *ecx, uint32_t *edx) +static inline void __cpuid(u32 function, u32 index, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) { *eax = function; *ecx = index; @@ -638,35 +672,35 @@ static inline void __cpuid(uint32_t function, uint32_t index, : "memory"); } -static inline void cpuid(uint32_t function, - uint32_t *eax, uint32_t *ebx, - uint32_t *ecx, uint32_t *edx) +static inline void cpuid(u32 function, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) { return __cpuid(function, 0, eax, ebx, ecx, edx); } -static inline uint32_t this_cpu_fms(void) +static inline u32 this_cpu_fms(void) { - uint32_t eax, ebx, ecx, edx; + u32 eax, ebx, ecx, edx; cpuid(1, &eax, &ebx, &ecx, &edx); return eax; } -static inline uint32_t this_cpu_family(void) +static inline u32 this_cpu_family(void) { return x86_family(this_cpu_fms()); } -static inline uint32_t this_cpu_model(void) +static inline u32 this_cpu_model(void) { return x86_model(this_cpu_fms()); } static inline bool this_cpu_vendor_string_is(const char *vendor) { - const uint32_t *chunk = (const uint32_t *)vendor; - uint32_t eax, ebx, ecx, edx; + const u32 *chunk = (const u32 *)vendor; + u32 eax, ebx, ecx, edx; cpuid(0, &eax, &ebx, &ecx, &edx); return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); @@ -685,10 +719,14 @@ static inline bool this_cpu_is_amd(void) return this_cpu_vendor_string_is("AuthenticAMD"); } -static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index, - uint8_t reg, uint8_t lo, uint8_t hi) +static inline bool this_cpu_is_hygon(void) { - uint32_t gprs[4]; + return this_cpu_vendor_string_is("HygonGenuine"); +} + +static inline u32 __this_cpu_has(u32 function, u32 index, u8 reg, u8 lo, u8 hi) +{ + u32 gprs[4]; __cpuid(function, index, &gprs[KVM_CPUID_EAX], &gprs[KVM_CPUID_EBX], @@ -703,7 +741,7 @@ static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature) feature.reg, feature.bit, feature.bit); } -static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property) +static inline u32 this_cpu_property(struct kvm_x86_cpu_property property) { return __this_cpu_has(property.function, property.index, property.reg, property.lo_bit, property.hi_bit); @@ -711,7 +749,7 @@ static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property) static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) { - uint32_t max_leaf; + u32 max_leaf; switch (property.function & 0xc0000000) { case 0: @@ -731,7 +769,7 @@ static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits; + u32 nr_bits; if (feature.f.reg == KVM_CPUID_EBX) { nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); @@ -743,13 +781,13 @@ static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) return nr_bits > feature.f.bit || this_cpu_has(feature.f); } -static __always_inline uint64_t this_cpu_supported_xcr0(void) +static __always_inline u64 this_cpu_supported_xcr0(void) { if (!this_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO)) return 0; return this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) | - ((uint64_t)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); + ((u64)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); } typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -828,7 +866,7 @@ static inline void cpu_relax(void) static inline void udelay(unsigned long usec) { - uint64_t start, now, cycles; + u64 start, now, cycles; GUEST_ASSERT(guest_tsc_khz); cycles = guest_tsc_khz / 1000 * usec; @@ -859,8 +897,8 @@ void kvm_x86_state_cleanup(struct kvm_x86_state *state); const struct kvm_msr_list *kvm_get_msr_index_list(void); const struct kvm_msr_list *kvm_get_feature_msr_index_list(void); -bool kvm_msr_is_in_save_restore_list(uint32_t msr_index); -uint64_t kvm_get_feature_msr(uint64_t msr_index); +bool kvm_msr_is_in_save_restore_list(u32 msr_index); +u64 kvm_get_feature_msr(u64 msr_index); static inline void vcpu_msrs_get(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs) @@ -915,20 +953,20 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) } const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, - uint32_t function, uint32_t index); + u32 function, u32 index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -static inline uint32_t kvm_cpu_fms(void) +static inline u32 kvm_cpu_fms(void) { return get_cpuid_entry(kvm_get_supported_cpuid(), 0x1, 0)->eax; } -static inline uint32_t kvm_cpu_family(void) +static inline u32 kvm_cpu_family(void) { return x86_family(kvm_cpu_fms()); } -static inline uint32_t kvm_cpu_model(void) +static inline u32 kvm_cpu_model(void) { return x86_model(kvm_cpu_fms()); } @@ -941,17 +979,17 @@ static inline bool kvm_cpu_has(struct kvm_x86_cpu_feature feature) return kvm_cpuid_has(kvm_get_supported_cpuid(), feature); } -uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, - struct kvm_x86_cpu_property property); +u32 kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_property property); -static inline uint32_t kvm_cpu_property(struct kvm_x86_cpu_property property) +static inline u32 kvm_cpu_property(struct kvm_x86_cpu_property property) { return kvm_cpuid_property(kvm_get_supported_cpuid(), property); } static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) { - uint32_t max_leaf; + u32 max_leaf; switch (property.function & 0xc0000000) { case 0: @@ -971,7 +1009,7 @@ static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) { - uint32_t nr_bits; + u32 nr_bits; if (feature.f.reg == KVM_CPUID_EBX) { nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); @@ -983,13 +1021,13 @@ static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) return nr_bits > feature.f.bit || kvm_cpu_has(feature.f); } -static __always_inline uint64_t kvm_cpu_supported_xcr0(void) +static __always_inline u64 kvm_cpu_supported_xcr0(void) { if (!kvm_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO)) return 0; return kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) | - ((uint64_t)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); + ((u64)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); } static inline size_t kvm_cpuid2_size(int nr_entries) @@ -1023,8 +1061,8 @@ static inline void vcpu_get_cpuid(struct kvm_vcpu *vcpu) } static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, - uint32_t function, - uint32_t index) + u32 function, + u32 index) { TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first (or equivalent)"); @@ -1035,7 +1073,7 @@ static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *v } static inline struct kvm_cpuid_entry2 *vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, - uint32_t function) + u32 function) { return __vcpu_get_cpuid_entry(vcpu, function, 0); } @@ -1065,10 +1103,10 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_property property, - uint32_t value); -void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); + u32 value); +void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, u8 maxphyaddr); -void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); +void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, u32 function); static inline bool vcpu_cpuid_has(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_feature feature) @@ -1096,8 +1134,8 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu, vcpu_set_or_clear_cpuid_feature(vcpu, feature, false); } -uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index); -int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value); +u64 vcpu_get_msr(struct kvm_vcpu *vcpu, u64 msr_index); +int _vcpu_set_msr(struct kvm_vcpu *vcpu, u64 msr_index, u64 msr_value); /* * Assert on an MSR access(es) and pretty print the MSR name when possible. @@ -1122,14 +1160,14 @@ do { \ * is changing, etc. This is NOT an exhaustive list! The intent is to filter * out MSRs that are not durable _and_ that a selftest wants to write. */ -static inline bool is_durable_msr(uint32_t msr) +static inline bool is_durable_msr(u32 msr) { return msr != MSR_IA32_TSC; } #define vcpu_set_msr(vcpu, msr, val) \ do { \ - uint64_t r, v = val; \ + u64 r, v = val; \ \ TEST_ASSERT_MSR(_vcpu_set_msr(vcpu, msr, v) == 1, \ "KVM_SET_MSRS failed on %s, value = 0x%lx", msr, #msr, v); \ @@ -1141,36 +1179,41 @@ do { \ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); void kvm_init_vm_address_properties(struct kvm_vm *vm); -bool vm_is_unrestricted_guest(struct kvm_vm *vm); struct ex_regs { - uint64_t rax, rcx, rdx, rbx; - uint64_t rbp, rsi, rdi; - uint64_t r8, r9, r10, r11; - uint64_t r12, r13, r14, r15; - uint64_t vector; - uint64_t error_code; - uint64_t rip; - uint64_t cs; - uint64_t rflags; + u64 rax, rcx, rdx, rbx; + u64 rbp, rsi, rdi; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 vector; + u64 error_code; + u64 rip; + u64 cs; + u64 rflags; }; struct idt_entry { - uint16_t offset0; - uint16_t selector; - uint16_t ist : 3; - uint16_t : 5; - uint16_t type : 4; - uint16_t : 1; - uint16_t dpl : 2; - uint16_t p : 1; - uint16_t offset1; - uint32_t offset2; uint32_t reserved; + u16 offset0; + u16 selector; + u16 ist : 3; + u16 : 5; + u16 type : 4; + u16 : 1; + u16 dpl : 2; + u16 p : 1; + u16 offset1; + u32 offset2; u32 reserved; }; void vm_install_exception_handler(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)); +/* + * Exception fixup morphs #DE to an arbitrary magic vector so that '0' can be + * used to signal "no expcetion". + */ +#define KVM_MAGIC_DE_VECTOR 0xff + /* If a toddler were to say "abracadabra". */ #define KVM_EXCEPTION_MAGIC 0xabacadabaULL @@ -1218,8 +1261,8 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe(insn, inputs...) \ ({ \ - uint64_t ign_error_code; \ - uint8_t vector; \ + u64 ign_error_code; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ @@ -1230,7 +1273,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_ec(insn, error_code, inputs...) \ ({ \ - uint8_t vector; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ @@ -1241,10 +1284,10 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_fep(insn, inputs...) \ ({ \ - uint64_t ign_error_code; \ - uint8_t vector; \ + u64 ign_error_code; \ + u8 vector; \ \ - asm volatile(KVM_ASM_SAFE(insn) \ + asm volatile(KVM_ASM_SAFE_FEP(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ : inputs \ : KVM_ASM_SAFE_CLOBBERS); \ @@ -1253,7 +1296,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, #define kvm_asm_safe_ec_fep(insn, error_code, inputs...) \ ({ \ - uint8_t vector; \ + u8 vector; \ \ asm volatile(KVM_ASM_SAFE_FEP(insn) \ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ @@ -1263,11 +1306,11 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, }) #define BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP) \ -static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ +static inline u8 insn##_safe ##_fep(u32 idx, u64 *val) \ { \ - uint64_t error_code; \ - uint8_t vector; \ - uint32_t a, d; \ + u64 error_code; \ + u8 vector; \ + u32 a, d; \ \ asm volatile(KVM_ASM_SAFE##_FEP(#insn) \ : "=a"(a), "=d"(d), \ @@ -1275,7 +1318,7 @@ static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val) \ : "c"(idx) \ : KVM_ASM_SAFE_CLOBBERS); \ \ - *val = (uint64_t)a | ((uint64_t)d << 32); \ + *val = (u64)a | ((u64)d << 32); \ return vector; \ } @@ -1291,12 +1334,12 @@ BUILD_READ_U64_SAFE_HELPERS(rdmsr) BUILD_READ_U64_SAFE_HELPERS(rdpmc) BUILD_READ_U64_SAFE_HELPERS(xgetbv) -static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) +static inline u8 wrmsr_safe(u32 msr, u64 val) { return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr)); } -static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) +static inline u8 xsetbv_safe(u32 index, u64 value) { u32 eax = value; u32 edx = value >> 32; @@ -1306,6 +1349,26 @@ static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) bool kvm_is_tdp_enabled(void); +static inline bool get_kvm_intel_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm_intel", param); +} + +static inline bool get_kvm_amd_param_bool(const char *param) +{ + return kvm_get_module_param_bool("kvm_amd", param); +} + +static inline int get_kvm_intel_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm_intel", param); +} + +static inline int get_kvm_amd_param_integer(const char *param) +{ + return kvm_get_module_param_integer("kvm_amd", param); +} + static inline bool kvm_is_pmu_enabled(void) { return get_kvm_param_bool("enable_pmu"); @@ -1316,30 +1379,80 @@ static inline bool kvm_is_forced_emulation_enabled(void) return !!get_kvm_param_integer("force_emulation_prefix"); } -uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, - int *level); -uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); +static inline bool kvm_is_unrestricted_guest_enabled(void) +{ + return get_kvm_intel_param_bool("unrestricted_guest"); +} + +static inline bool kvm_is_ignore_msrs(void) +{ + return get_kvm_param_bool("ignore_msrs"); +} + +static inline bool kvm_is_lbrv_enabled(void) +{ + return !!get_kvm_amd_param_integer("lbrv"); +} + +u64 *vm_get_pte(struct kvm_vm *vm, gva_t gva); -uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, - uint64_t a3); -uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1); -void xen_hypercall(uint64_t nr, uint64_t a0, void *a1); +u64 kvm_hypercall(u64 nr, u64 a0, u64 a1, u64 a2, u64 a3); +u64 __xen_hypercall(u64 nr, u64 a0, void *a1); +void xen_hypercall(u64 nr, u64 a0, void *a1); -static inline uint64_t __kvm_hypercall_map_gpa_range(uint64_t gpa, - uint64_t size, uint64_t flags) +static inline u64 __kvm_hypercall_map_gpa_range(gpa_t gpa, u64 size, u64 flags) { return kvm_hypercall(KVM_HC_MAP_GPA_RANGE, gpa, size >> PAGE_SHIFT, flags, 0); } -static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size, - uint64_t flags) +static inline void kvm_hypercall_map_gpa_range(gpa_t gpa, u64 size, u64 flags) { - uint64_t ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); + u64 ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); GUEST_ASSERT(!ret); } -void __vm_xsave_require_permission(uint64_t xfeature, const char *name); +/* + * Execute HLT in an STI interrupt shadow to ensure that a pending IRQ that's + * intended to be a wake event arrives *after* HLT is executed. Modern CPUs, + * except for a few oddballs that KVM is unlikely to run on, block IRQs for one + * instruction after STI, *if* RFLAGS.IF=0 before STI. Note, Intel CPUs may + * block other events beyond regular IRQs, e.g. may block NMIs and SMIs too. + */ +static inline void safe_halt(void) +{ + asm volatile("sti; hlt"); +} + +/* + * Enable interrupts and ensure that interrupts are evaluated upon return from + * this function, i.e. execute a nop to consume the STi interrupt shadow. + */ +static inline void sti_nop(void) +{ + asm volatile ("sti; nop"); +} + +/* + * Enable interrupts for one instruction (nop), to allow the CPU to process all + * interrupts that are already pending. + */ +static inline void sti_nop_cli(void) +{ + asm volatile ("sti; nop; cli"); +} + +static inline void sti(void) +{ + asm volatile("sti"); +} + +static inline void cli(void) +{ + asm volatile ("cli"); +} + +void __vm_xsave_require_permission(u64 xfeature, const char *name); #define vm_xsave_require_permission(xfeature) \ __vm_xsave_require_permission(xfeature, #xfeature) @@ -1350,7 +1463,7 @@ enum pg_level { PG_LEVEL_2M, PG_LEVEL_1G, PG_LEVEL_512G, - PG_LEVEL_NUM + PG_LEVEL_256T }; #define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12) @@ -1360,9 +1473,51 @@ enum pg_level { #define PG_SIZE_2M PG_LEVEL_SIZE(PG_LEVEL_2M) #define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G) -void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level); -void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - uint64_t nr_bytes, int level); +#define PTE_PRESENT_MASK(mmu) ((mmu)->arch.pte_masks.present) +#define PTE_WRITABLE_MASK(mmu) ((mmu)->arch.pte_masks.writable) +#define PTE_USER_MASK(mmu) ((mmu)->arch.pte_masks.user) +#define PTE_READABLE_MASK(mmu) ((mmu)->arch.pte_masks.readable) +#define PTE_EXECUTABLE_MASK(mmu) ((mmu)->arch.pte_masks.executable) +#define PTE_ACCESSED_MASK(mmu) ((mmu)->arch.pte_masks.accessed) +#define PTE_DIRTY_MASK(mmu) ((mmu)->arch.pte_masks.dirty) +#define PTE_HUGE_MASK(mmu) ((mmu)->arch.pte_masks.huge) +#define PTE_NX_MASK(mmu) ((mmu)->arch.pte_masks.nx) +#define PTE_C_BIT_MASK(mmu) ((mmu)->arch.pte_masks.c) +#define PTE_S_BIT_MASK(mmu) ((mmu)->arch.pte_masks.s) +#define PTE_ALWAYS_SET_MASK(mmu) ((mmu)->arch.pte_masks.always_set) + +/* + * For PTEs without a PRESENT bit (i.e. EPT entries), treat the PTE as present + * if it's executable or readable, as EPT supports execute-only PTEs, but not + * write-only PTEs. + */ +#define is_present_pte(mmu, pte) \ + (PTE_PRESENT_MASK(mmu) ? \ + !!(*(pte) & PTE_PRESENT_MASK(mmu)) : \ + !!(*(pte) & (PTE_READABLE_MASK(mmu) | PTE_EXECUTABLE_MASK(mmu)))) +#define is_executable_pte(mmu, pte) \ + ((*(pte) & (PTE_EXECUTABLE_MASK(mmu) | PTE_NX_MASK(mmu))) == PTE_EXECUTABLE_MASK(mmu)) +#define is_writable_pte(mmu, pte) (!!(*(pte) & PTE_WRITABLE_MASK(mmu))) +#define is_user_pte(mmu, pte) (!!(*(pte) & PTE_USER_MASK(mmu))) +#define is_accessed_pte(mmu, pte) (!!(*(pte) & PTE_ACCESSED_MASK(mmu))) +#define is_dirty_pte(mmu, pte) (!!(*(pte) & PTE_DIRTY_MASK(mmu))) +#define is_huge_pte(mmu, pte) (!!(*(pte) & PTE_HUGE_MASK(mmu))) +#define is_nx_pte(mmu, pte) (!is_executable_pte(mmu, pte)) + +void tdp_mmu_init(struct kvm_vm *vm, int pgtable_levels, + struct pte_masks *pte_masks); + +void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, gva_t gva, + gpa_t gpa, int level); +void virt_map_level(struct kvm_vm *vm, gva_t gva, gpa_t gpa, + u64 nr_bytes, int level); + +void vm_enable_tdp(struct kvm_vm *vm); +bool kvm_cpu_has_tdp(void); +void tdp_map(struct kvm_vm *vm, gpa_t l2_gpa, gpa_t gpa, u64 size); +void tdp_identity_map_default_memslots(struct kvm_vm *vm); +void tdp_identity_map_1g(struct kvm_vm *vm, u64 addr, u64 size); +u64 *tdp_get_pte(struct kvm_vm *vm, u64 l2_gpa); /* * Basic CPU control in CR0 diff --git a/tools/testing/selftests/kvm/include/x86/sev.h b/tools/testing/selftests/kvm/include/x86/sev.h index 82c11c81a956..1af44c151d60 100644 --- a/tools/testing/selftests/kvm/include/x86/sev.h +++ b/tools/testing/selftests/kvm/include/x86/sev.h @@ -25,19 +25,51 @@ enum sev_guest_state { #define SEV_POLICY_NO_DBG (1UL << 0) #define SEV_POLICY_ES (1UL << 2) +#define SNP_POLICY_SMT (1ULL << 16) +#define SNP_POLICY_RSVD_MBO (1ULL << 17) +#define SNP_POLICY_DBG (1ULL << 19) + #define GHCB_MSR_TERM_REQ 0x100 -void sev_vm_launch(struct kvm_vm *vm, uint32_t policy); -void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement); +static inline bool is_sev_snp_vm(struct kvm_vm *vm) +{ + return vm->type == KVM_X86_SNP_VM; +} + +static inline bool is_sev_es_vm(struct kvm_vm *vm) +{ + return is_sev_snp_vm(vm) || vm->type == KVM_X86_SEV_ES_VM; +} + +static inline bool is_sev_vm(struct kvm_vm *vm) +{ + return is_sev_es_vm(vm) || vm->type == KVM_X86_SEV_VM; +} + +void sev_vm_launch(struct kvm_vm *vm, u32 policy); +void sev_vm_launch_measure(struct kvm_vm *vm, u8 *measurement); void sev_vm_launch_finish(struct kvm_vm *vm); +void snp_vm_launch_start(struct kvm_vm *vm, u64 policy); +void snp_vm_launch_update(struct kvm_vm *vm); +void snp_vm_launch_finish(struct kvm_vm *vm); -struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code, +struct kvm_vm *vm_sev_create_with_one_vcpu(u32 type, void *guest_code, struct kvm_vcpu **cpu); -void vm_sev_launch(struct kvm_vm *vm, uint32_t policy, uint8_t *measurement); +void vm_sev_launch(struct kvm_vm *vm, u64 policy, u8 *measurement); kvm_static_assert(SEV_RET_SUCCESS == 0); /* + * A SEV-SNP VM requires the policy reserved bit to always be set. + * The SMT policy bit is also required to be set based on SMT being + * available and active on the system. + */ +static inline u64 snp_default_policy(void) +{ + return SNP_POLICY_RSVD_MBO | (is_smt_on() ? SNP_POLICY_SMT : 0); +} + +/* * The KVM_MEMORY_ENCRYPT_OP uAPI is utter garbage and takes an "unsigned long" * instead of a proper struct. The size of the parameter is embedded in the * ioctl number, i.e. is ABI and thus immutable. Hack around the mess by @@ -53,7 +85,7 @@ kvm_static_assert(SEV_RET_SUCCESS == 0); unsigned long raw; \ } sev_cmd = { .c = { \ .id = (cmd), \ - .data = (uint64_t)(arg), \ + .data = (u64)(arg), \ .sev_fd = (vm)->arch.sev_fd, \ } }; \ \ @@ -70,6 +102,12 @@ kvm_static_assert(SEV_RET_SUCCESS == 0); void sev_vm_init(struct kvm_vm *vm); void sev_es_vm_init(struct kvm_vm *vm); +void snp_vm_init(struct kvm_vm *vm); + +static inline void vmgexit(void) +{ + __asm__ __volatile__("rep; vmmcall"); +} static inline void sev_register_encrypted_memory(struct kvm_vm *vm, struct userspace_mem_region *region) @@ -82,8 +120,8 @@ static inline void sev_register_encrypted_memory(struct kvm_vm *vm, vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); } -static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, - uint64_t size) +static inline void sev_launch_update_data(struct kvm_vm *vm, gpa_t gpa, + u64 size) { struct kvm_sev_launch_update_data update_data = { .uaddr = (unsigned long)addr_gpa2hva(vm, gpa), @@ -93,4 +131,17 @@ static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa, vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data); } +static inline void snp_launch_update_data(struct kvm_vm *vm, gpa_t gpa, + u64 hva, u64 size, u8 type) +{ + struct kvm_sev_snp_launch_update update_data = { + .uaddr = hva, + .gfn_start = gpa >> PAGE_SHIFT, + .len = size, + .type = type, + }; + + vm_sev_ioctl(vm, KVM_SEV_SNP_LAUNCH_UPDATE, &update_data); +} + #endif /* SELFTEST_KVM_SEV_H */ diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h new file mode 100644 index 000000000000..2d1afa09819b --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86/smm.h @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef SELFTEST_KVM_SMM_H +#define SELFTEST_KVM_SMM_H + +#include "kvm_util.h" + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) + +void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, u64 smram_gpa, + const void *smi_handler, size_t handler_size); + +void inject_smi(struct kvm_vcpu *vcpu); + +#endif /* SELFTEST_KVM_SMM_H */ diff --git a/tools/testing/selftests/kvm/include/x86/svm.h b/tools/testing/selftests/kvm/include/x86/svm.h index 29cffd0a9181..c8539166270e 100644 --- a/tools/testing/selftests/kvm/include/x86/svm.h +++ b/tools/testing/selftests/kvm/include/x86/svm.h @@ -92,19 +92,18 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u32 int_vector; u32 int_state; u8 reserved_3[4]; - u32 exit_code; - u32 exit_code_hi; + u64 exit_code; u64 exit_info_1; u64 exit_info_2; u32 exit_int_info; u32 exit_int_info_err; - u64 nested_ctl; + u64 misc_ctl; u64 avic_vapic_bar; u8 reserved_4[8]; u32 event_inj; u32 event_inj_err; u64 nested_cr3; - u64 virt_ext; + u64 misc_ctl2; u32 clean; u32 reserved_5; u64 next_rip; @@ -156,9 +155,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_ENABLE_SHIFT 31 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) -#define LBR_CTL_ENABLE_MASK BIT_ULL(0) -#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) - #define SVM_INTERRUPT_SHADOW_MASK 1 #define SVM_IOIO_STR_SHIFT 2 @@ -176,8 +172,11 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL #define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL -#define SVM_NESTED_CTL_NP_ENABLE BIT(0) -#define SVM_NESTED_CTL_SEV_ENABLE BIT(1) +#define SVM_MISC_ENABLE_NP BIT(0) +#define SVM_MISC_ENABLE_SEV BIT(1) + +#define SVM_MISC2_ENABLE_V_LBR BIT_ULL(0) +#define SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE BIT_ULL(1) struct __attribute__ ((__packed__)) vmcb_seg { u16 selector; diff --git a/tools/testing/selftests/kvm/include/x86/svm_util.h b/tools/testing/selftests/kvm/include/x86/svm_util.h index b74c6dcddcbd..6c013eb838be 100644 --- a/tools/testing/selftests/kvm/include/x86/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86/svm_util.h @@ -16,17 +16,20 @@ struct svm_test_data { /* VMCB */ struct vmcb *vmcb; /* gva */ void *vmcb_hva; - uint64_t vmcb_gpa; + u64 vmcb_gpa; /* host state-save area */ struct vmcb_save_area *save_area; /* gva */ void *save_area_hva; - uint64_t save_area_gpa; + u64 save_area_gpa; /* MSR-Bitmap */ void *msr; /* gva */ void *msr_hva; - uint64_t msr_gpa; + u64 msr_gpa; + + /* NPT */ + u64 ncr3_gpa; }; static inline void vmmcall(void) @@ -53,9 +56,15 @@ static inline void vmmcall(void) "clgi\n" \ ) -struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); +struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, gva_t *p_svm_gva); void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp); -void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa); +void run_guest(struct vmcb *vmcb, u64 vmcb_gpa); + +static inline bool kvm_cpu_has_npt(void) +{ + return kvm_cpu_has(X86_FEATURE_NPT); +} +void vm_enable_npt(struct kvm_vm *vm); int open_sev_dev_path_or_exit(void); diff --git a/tools/testing/selftests/kvm/include/x86/ucall.h b/tools/testing/selftests/kvm/include/x86/ucall.h index d3825dcc3cd9..0e4950041e3e 100644 --- a/tools/testing/selftests/kvm/include/x86/ucall.h +++ b/tools/testing/selftests/kvm/include/x86/ucall.h @@ -6,7 +6,7 @@ #define UCALL_EXIT_REASON KVM_EXIT_IO -static inline void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa) { } diff --git a/tools/testing/selftests/kvm/include/x86/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h index edb3c391b982..90fffaf91595 100644 --- a/tools/testing/selftests/kvm/include/x86/vmx.h +++ b/tools/testing/selftests/kvm/include/x86/vmx.h @@ -285,16 +285,16 @@ enum vmcs_field { }; struct vmx_msr_entry { - uint32_t index; - uint32_t reserved; - uint64_t value; + u32 index; + u32 reserved; + u64 value; } __attribute__ ((aligned(16))); #include "evmcs.h" -static inline int vmxon(uint64_t phys) +static inline int vmxon(u64 phys) { - uint8_t ret; + u8 ret; __asm__ __volatile__ ("vmxon %[pa]; setna %[ret]" : [ret]"=rm"(ret) @@ -309,9 +309,9 @@ static inline void vmxoff(void) __asm__ __volatile__("vmxoff"); } -static inline int vmclear(uint64_t vmcs_pa) +static inline int vmclear(u64 vmcs_pa) { - uint8_t ret; + u8 ret; __asm__ __volatile__ ("vmclear %[pa]; setna %[ret]" : [ret]"=rm"(ret) @@ -321,9 +321,9 @@ static inline int vmclear(uint64_t vmcs_pa) return ret; } -static inline int vmptrld(uint64_t vmcs_pa) +static inline int vmptrld(u64 vmcs_pa) { - uint8_t ret; + u8 ret; if (enable_evmcs) return -1; @@ -336,10 +336,10 @@ static inline int vmptrld(uint64_t vmcs_pa) return ret; } -static inline int vmptrst(uint64_t *value) +static inline int vmptrst(u64 *value) { - uint64_t tmp; - uint8_t ret; + u64 tmp; + u8 ret; if (enable_evmcs) return evmcs_vmptrst(value); @@ -356,9 +356,9 @@ static inline int vmptrst(uint64_t *value) * A wrapper around vmptrst that ignores errors and returns zero if the * vmptrst instruction fails. */ -static inline uint64_t vmptrstz(void) +static inline u64 vmptrstz(void) { - uint64_t value = 0; + u64 value = 0; vmptrst(&value); return value; } @@ -391,8 +391,8 @@ static inline int vmlaunch(void) "pop %%rcx;" "pop %%rbp;" : [ret]"=&a"(ret) - : [host_rsp]"r"((uint64_t)HOST_RSP), - [host_rip]"r"((uint64_t)HOST_RIP) + : [host_rsp]"r"((u64)HOST_RSP), + [host_rip]"r"((u64)HOST_RIP) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -426,8 +426,8 @@ static inline int vmresume(void) "pop %%rcx;" "pop %%rbp;" : [ret]"=&a"(ret) - : [host_rsp]"r"((uint64_t)HOST_RSP), - [host_rip]"r"((uint64_t)HOST_RIP) + : [host_rsp]"r"((u64)HOST_RSP), + [host_rip]"r"((u64)HOST_RIP) : "memory", "cc", "rbx", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"); return ret; @@ -447,10 +447,10 @@ static inline void vmcall(void) "r10", "r11", "r12", "r13", "r14", "r15"); } -static inline int vmread(uint64_t encoding, uint64_t *value) +static inline int vmread(u64 encoding, u64 *value) { - uint64_t tmp; - uint8_t ret; + u64 tmp; + u8 ret; if (enable_evmcs) return evmcs_vmread(encoding, value); @@ -468,16 +468,16 @@ static inline int vmread(uint64_t encoding, uint64_t *value) * A wrapper around vmread that ignores errors and returns zero if the * vmread instruction fails. */ -static inline uint64_t vmreadz(uint64_t encoding) +static inline u64 vmreadz(u64 encoding) { - uint64_t value = 0; + u64 value = 0; vmread(encoding, &value); return value; } -static inline int vmwrite(uint64_t encoding, uint64_t value) +static inline int vmwrite(u64 encoding, u64 value) { - uint8_t ret; + u8 ret; if (enable_evmcs) return evmcs_vmwrite(encoding, value); @@ -490,43 +490,41 @@ static inline int vmwrite(uint64_t encoding, uint64_t value) return ret; } -static inline uint32_t vmcs_revision(void) +static inline u32 vmcs_revision(void) { return rdmsr(MSR_IA32_VMX_BASIC); } struct vmx_pages { void *vmxon_hva; - uint64_t vmxon_gpa; + u64 vmxon_gpa; void *vmxon; void *vmcs_hva; - uint64_t vmcs_gpa; + u64 vmcs_gpa; void *vmcs; void *msr_hva; - uint64_t msr_gpa; + u64 msr_gpa; void *msr; void *shadow_vmcs_hva; - uint64_t shadow_vmcs_gpa; + u64 shadow_vmcs_gpa; void *shadow_vmcs; void *vmread_hva; - uint64_t vmread_gpa; + u64 vmread_gpa; void *vmread; void *vmwrite_hva; - uint64_t vmwrite_gpa; + u64 vmwrite_gpa; void *vmwrite; - void *eptp_hva; - uint64_t eptp_gpa; - void *eptp; - void *apic_access_hva; - uint64_t apic_access_gpa; + u64 apic_access_gpa; void *apic_access; + + u64 eptp_gpa; }; union vmx_basic { @@ -552,24 +550,15 @@ union vmx_ctrl_msr { }; }; -struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva); +struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, gva_t *p_vmx_gva); bool prepare_for_vmx_operation(struct vmx_pages *vmx); void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); bool load_vmcs(struct vmx_pages *vmx); bool ept_1g_pages_supported(void); -void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, - uint64_t nested_paddr, uint64_t paddr); -void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, - uint64_t nested_paddr, uint64_t paddr, uint64_t size); -void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, - uint32_t memslot); -void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm, - uint64_t addr, uint64_t size); bool kvm_cpu_has_ept(void); -void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, - uint32_t eptp_memslot); +void vm_enable_ept(struct kvm_vm *vm); void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm); #endif /* SELFTEST_KVM_VMX_H */ |