diff options
| author | Paolo Bonzini <pbonzini@redhat.com> | 2024-05-07 13:03:03 -0400 |
|---|---|---|
| committer | Paolo Bonzini <pbonzini@redhat.com> | 2024-05-07 13:03:03 -0400 |
| commit | aa24865fb5e33701c93521460a2d05ab76d6bddc (patch) | |
| tree | 754ddda12fa38c97f98df5e671b571c37544c71b | |
| parent | a96cb3bf390eebfead5fc7a2092f8452a7997d1b (diff) | |
| parent | 5ef2f3d4e747c7851678ad2b70e37be886a8c9eb (diff) | |
Merge tag 'kvm-riscv-6.10-1' of https://github.com/kvm-riscv/linux into HEAD
KVM/riscv changes for 6.10
- Support guest breakpoints using ebreak
- Introduce per-VCPU mp_state_lock and reset_cntx_lock
- Virtualize SBI PMU snapshot and counter overflow interrupts
- New selftests for SBI PMU and Guest ebreak
67 files changed, 2186 insertions, 403 deletions
@@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index f0a4cf01e85c..78302f6c2580 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -4,7 +4,6 @@ #ifndef __ASSEMBLY__ -#include <asm/page.h> #include <asm/vdso/timebase.h> #include <asm/barrier.h> #include <asm/unistd.h> @@ -95,7 +94,7 @@ const struct vdso_data *__arch_get_vdso_data(void); static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) { - return (void *)vd + PAGE_SIZE; + return (void *)vd + (1U << CONFIG_PAGE_SHIFT); } #endif diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 2468c55933cd..25966995da04 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -168,7 +168,8 @@ #define VSIP_TO_HVIP_SHIFT (IRQ_VS_SOFT - IRQ_S_SOFT) #define VSIP_VALID_MASK ((_AC(1, UL) << IRQ_S_SOFT) | \ (_AC(1, UL) << IRQ_S_TIMER) | \ - (_AC(1, UL) << IRQ_S_EXT)) + (_AC(1, UL) << IRQ_S_EXT) | \ + (_AC(1, UL) << IRQ_PMU_OVF)) /* AIA CSR bits */ #define TOPI_IID_SHIFT 16 @@ -281,7 +282,7 @@ #define CSR_HPMCOUNTER30H 0xc9e #define CSR_HPMCOUNTER31H 0xc9f -#define CSR_SSCOUNTOVF 0xda0 +#define CSR_SCOUNTOVF 0xda0 #define CSR_SSTATUS 0x100 #define CSR_SIE 0x104 diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 484d04a92fa6..d96281278586 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -43,6 +43,17 @@ KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(6) +#define KVM_HEDELEG_DEFAULT (BIT(EXC_INST_MISALIGNED) | \ + BIT(EXC_BREAKPOINT) | \ + BIT(EXC_SYSCALL) | \ + BIT(EXC_INST_PAGE_FAULT) | \ + BIT(EXC_LOAD_PAGE_FAULT) | \ + BIT(EXC_STORE_PAGE_FAULT)) + +#define KVM_HIDELEG_DEFAULT (BIT(IRQ_VS_SOFT) | \ + BIT(IRQ_VS_TIMER) | \ + BIT(IRQ_VS_EXT)) + enum kvm_riscv_hfence_type { KVM_RISCV_HFENCE_UNKNOWN = 0, KVM_RISCV_HFENCE_GVMA_VMID_GPA, @@ -169,6 +180,7 @@ struct kvm_vcpu_csr { struct kvm_vcpu_config { u64 henvcfg; u64 hstateen0; + unsigned long hedeleg; }; struct kvm_vcpu_smstateen_csr { @@ -211,6 +223,7 @@ struct kvm_vcpu_arch { /* CPU context upon Guest VCPU reset */ struct kvm_cpu_context guest_reset_context; + spinlock_t reset_cntx_lock; /* CPU CSR context upon Guest VCPU reset */ struct kvm_vcpu_csr guest_reset_csr; @@ -252,8 +265,9 @@ struct kvm_vcpu_arch { /* Cache pages needed to program page tables with spinlock held */ struct kvm_mmu_memory_cache mmu_page_cache; - /* VCPU power-off state */ - bool power_off; + /* VCPU power state */ + struct kvm_mp_state mp_state; + spinlock_t mp_state_lock; /* Don't run the VCPU (blocked) */ bool pause; @@ -374,8 +388,11 @@ int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq); void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu); bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask); +void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); +void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); +bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu); diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h index 395518a1664e..fa0f535bbbf0 100644 --- a/arch/riscv/include/asm/kvm_vcpu_pmu.h +++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h @@ -20,7 +20,7 @@ static_assert(RISCV_KVM_MAX_COUNTERS <= 64); struct kvm_fw_event { /* Current value of the event */ - unsigned long value; + u64 value; /* Event monitoring status */ bool started; @@ -36,6 +36,7 @@ struct kvm_pmc { bool started; /* Monitoring event ID */ unsigned long event_idx; + struct kvm_vcpu *vcpu; }; /* PMU data structure per vcpu */ @@ -50,6 +51,12 @@ struct kvm_pmu { bool init_done; /* Bit map of all the virtual counter used */ DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS); + /* Bit map of all the virtual counter overflown */ + DECLARE_BITMAP(pmc_overflown, RISCV_KVM_MAX_COUNTERS); + /* The address of the counter snapshot area (guest physical address) */ + gpa_t snapshot_addr; + /* The actual data of the snapshot */ + struct riscv_pmu_snapshot_data *sdata; }; #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu_context) @@ -82,9 +89,14 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba unsigned long ctr_mask, unsigned long flags, unsigned long eidx, u64 evtdata, struct kvm_vcpu_sbi_return *retdata); -int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, +int kvm_riscv_vcpu_pmu_fw_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long saddr_low, + unsigned long saddr_high, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata); void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu); diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 6e68f8dff76b..112a0a0d9f46 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -131,6 +131,8 @@ enum sbi_ext_pmu_fid { SBI_EXT_PMU_COUNTER_START, SBI_EXT_PMU_COUNTER_STOP, SBI_EXT_PMU_COUNTER_FW_READ, + SBI_EXT_PMU_COUNTER_FW_READ_HI, + SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, }; union sbi_pmu_ctr_info { @@ -147,6 +149,13 @@ union sbi_pmu_ctr_info { }; }; +/* Data structure to contain the pmu snapshot data */ +struct riscv_pmu_snapshot_data { + u64 ctr_overflow_mask; + u64 ctr_values[64]; + u64 reserved[447]; +}; + #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0) #define RISCV_PMU_RAW_EVENT_IDX 0x20000 @@ -232,20 +241,22 @@ enum sbi_pmu_ctr_type { #define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF /* Flags defined for config matching function */ -#define SBI_PMU_CFG_FLAG_SKIP_MATCH (1 << 0) -#define SBI_PMU_CFG_FLAG_CLEAR_VALUE (1 << 1) -#define SBI_PMU_CFG_FLAG_AUTO_START (1 << 2) -#define SBI_PMU_CFG_FLAG_SET_VUINH (1 << 3) -#define SBI_PMU_CFG_FLAG_SET_VSINH (1 << 4) -#define SBI_PMU_CFG_FLAG_SET_UINH (1 << 5) -#define SBI_PMU_CFG_FLAG_SET_SINH (1 << 6) -#define SBI_PMU_CFG_FLAG_SET_MINH (1 << 7) +#define SBI_PMU_CFG_FLAG_SKIP_MATCH BIT(0) +#define SBI_PMU_CFG_FLAG_CLEAR_VALUE BIT(1) +#define SBI_PMU_CFG_FLAG_AUTO_START BIT(2) +#define SBI_PMU_CFG_FLAG_SET_VUINH BIT(3) +#define SBI_PMU_CFG_FLAG_SET_VSINH BIT(4) +#define SBI_PMU_CFG_FLAG_SET_UINH BIT(5) +#define SBI_PMU_CFG_FLAG_SET_SINH BIT(6) +#define SBI_PMU_CFG_FLAG_SET_MINH BIT(7) /* Flags defined for counter start function */ -#define SBI_PMU_START_FLAG_SET_INIT_VALUE (1 << 0) +#define SBI_PMU_START_FLAG_SET_INIT_VALUE BIT(0) +#define SBI_PMU_START_FLAG_INIT_SNAPSHOT BIT(1) /* Flags defined for counter stop function */ -#define SBI_PMU_STOP_FLAG_RESET (1 << 0) +#define SBI_PMU_STOP_FLAG_RESET BIT(0) +#define SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT BIT(1) enum sbi_ext_dbcn_fid { SBI_EXT_DBCN_CONSOLE_WRITE = 0, @@ -266,7 +277,7 @@ struct sbi_sta_struct { u8 pad[47]; } __packed; -#define SBI_STA_SHMEM_DISABLE -1 +#define SBI_SHMEM_DISABLE -1 /* SBI spec version fields */ #define SBI_SPEC_VERSION_DEFAULT 0x1 @@ -284,6 +295,7 @@ struct sbi_sta_struct { #define SBI_ERR_ALREADY_AVAILABLE -6 #define SBI_ERR_ALREADY_STARTED -7 #define SBI_ERR_ALREADY_STOPPED -8 +#define SBI_ERR_NO_SHMEM -9 extern unsigned long sbi_spec_version; struct sbiret { @@ -355,8 +367,8 @@ static inline unsigned long sbi_minor_version(void) static inline unsigned long sbi_mk_version(unsigned long major, unsigned long minor) { - return ((major & SBI_SPEC_VERSION_MAJOR_MASK) << - SBI_SPEC_VERSION_MAJOR_SHIFT) | minor; + return ((major & SBI_SPEC_VERSION_MAJOR_MASK) << SBI_SPEC_VERSION_MAJOR_SHIFT) + | (minor & SBI_SPEC_VERSION_MINOR_MASK); } int sbi_err_map_linux_errno(int err); diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index b1c503c2959c..e878e7cc3978 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -167,6 +167,7 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_ZFA, KVM_RISCV_ISA_EXT_ZTSO, KVM_RISCV_ISA_EXT_ZACAS, + KVM_RISCV_ISA_EXT_SSCOFPMF, KVM_RISCV_ISA_EXT_MAX, }; diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c index 0d6225fd3194..fa6b0339a65d 100644 --- a/arch/riscv/kernel/paravirt.c +++ b/arch/riscv/kernel/paravirt.c @@ -62,7 +62,7 @@ static int sbi_sta_steal_time_set_shmem(unsigned long lo, unsigned long hi, ret = sbi_ecall(SBI_EXT_STA, SBI_EXT_STA_STEAL_TIME_SET_SHMEM, lo, hi, flags, 0, 0, 0); if (ret.error) { - if (lo == SBI_STA_SHMEM_DISABLE && hi == SBI_STA_SHMEM_DISABLE) + if (lo == SBI_SHMEM_DISABLE && hi == SBI_SHMEM_DISABLE) pr_warn("Failed to disable steal-time shmem"); else pr_warn("Failed to set steal-time shmem"); @@ -84,8 +84,8 @@ static int pv_time_cpu_online(unsigned int cpu) static int pv_time_cpu_down_prepare(unsigned int cpu) { - return sbi_sta_steal_time_set_shmem(SBI_STA_SHMEM_DISABLE, - SBI_STA_SHMEM_DISABLE, 0); + return sbi_sta_steal_time_set_shmem(SBI_SHMEM_DISABLE, + SBI_SHMEM_DISABLE, 0); } static u64 pv_time_steal_clock(int cpu) diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index a944294f6f23..0f0a9d11bb5f 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -545,6 +545,9 @@ void kvm_riscv_aia_enable(void) enable_percpu_irq(hgei_parent_irq, irq_get_trigger_type(hgei_parent_irq)); csr_set(CSR_HIE, BIT(IRQ_S_GEXT)); + /* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */ + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) + csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF)); } void kvm_riscv_aia_disable(void) @@ -558,6 +561,8 @@ void kvm_riscv_aia_disable(void) return; hgctrl = get_cpu_ptr(&aia_hgei); + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) + csr_clear(CSR_HVIEN, BIT(IRQ_PMU_OVF)); /* Disable per-CPU SGEI interrupt */ csr_clear(CSR_HIE, BIT(IRQ_S_GEXT)); disable_percpu_irq(hgei_parent_irq); diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 225a435d9c9a..bab2ec34cd87 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -22,22 +22,8 @@ long kvm_arch_dev_ioctl(struct file *filp, int kvm_arch_hardware_enable(void) { - unsigned long hideleg, hedeleg; - - hedeleg = 0; - hedeleg |= (1UL << EXC_INST_MISALIGNED); - hedeleg |= (1UL << EXC_BREAKPOINT); - hedeleg |= (1UL << EXC_SYSCALL); - hedeleg |= (1UL << EXC_INST_PAGE_FAULT); - hedeleg |= (1UL << EXC_LOAD_PAGE_FAULT); - hedeleg |= (1UL << EXC_STORE_PAGE_FAULT); - csr_write(CSR_HEDELEG, hedeleg); - - hideleg = 0; - hideleg |= (1UL << IRQ_VS_SOFT); - hideleg |= (1UL << IRQ_VS_TIMER); - hideleg |= (1UL << IRQ_VS_EXT); - csr_write(CSR_HIDELEG, hideleg); + csr_write(CSR_HEDELEG, KVM_HEDELEG_DEFAULT); + csr_write(CSR_HIDELEG, KVM_HIDELEG_DEFAULT); /* VS should access only the time counter directly. Everything else should trap */ csr_write(CSR_HCOUNTEREN, 0x02); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index b5ca9f2e98ac..17e21df36cc1 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -64,7 +64,9 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) memcpy(csr, reset_csr, sizeof(*csr)); + spin_lock(&vcpu->arch.reset_cntx_lock); memcpy(cntx, reset_cntx, sizeof(*cntx)); + spin_unlock(&vcpu->arch.reset_cntx_lock); kvm_riscv_vcpu_fp_reset(vcpu); @@ -102,6 +104,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct kvm_cpu_context *cntx; struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; + spin_lock_init(&vcpu->arch.mp_state_lock); + /* Mark this VCPU never ran */ vcpu->arch.ran_atleast_once = false; vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO; @@ -119,12 +123,16 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) spin_lock_init(&vcpu->arch.hfence_lock); /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ + spin_lock_init(&vcpu->arch.reset_cntx_lock); + + spin_lock(&vcpu->arch.reset_cntx_lock); cntx = &vcpu->arch.guest_reset_context; cntx->sstatus = SR_SPP | SR_SPIE; cntx->hstatus = 0; cntx->hstatus |= HSTATUS_VTW; cntx->hstatus |= HSTATUS_SPVP; cntx->hstatus |= HSTATUS_SPV; + spin_unlock(&vcpu->arch.reset_cntx_lock); if (kvm_riscv_vcpu_alloc_vector_context(vcpu, cntx)) return -ENOMEM; @@ -201,7 +209,7 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) && - !vcpu->arch.power_off && !vcpu->arch.pause); + !kvm_riscv_vcpu_stopped(vcpu) && !vcpu->arch.pause); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) @@ -365,6 +373,13 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) } } + /* Sync up the HVIP.LCOFIP bit changes (only clear) by the guest */ + if ((csr->hvip ^ hvip) & (1UL << IRQ_PMU_OVF)) { + if (!(hvip & (1UL << IRQ_PMU_OVF)) && + !test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask)) + clear_bit(IRQ_PMU_OVF, v->irqs_pending); + } + /* Sync-up AIA high interrupts */ kvm_riscv_vcpu_aia_sync_interrupts(vcpu); @@ -382,7 +397,8 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) if (irq < IRQ_LOCAL_MAX && irq != IRQ_VS_SOFT && irq != IRQ_VS_TIMER && - irq != IRQ_VS_EXT) + irq != IRQ_VS_EXT && + irq != IRQ_PMU_OVF) return -EINVAL; set_bit(irq, vcpu->arch.irqs_pending); @@ -397,14 +413,15 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) { /* - * We only allow VS-mode software, timer, and external + * We only allow VS-mode software, timer, counter overflow and external * interrupts when irq is one of the local interrupts * defined by RISC-V privilege specification. */ if (irq < IRQ_LOCAL_MAX && irq != IRQ_VS_SOFT && irq != IRQ_VS_TIMER && - irq != IRQ_VS_EXT) + irq != IRQ_VS_EXT && + irq != IRQ_PMU_OVF) return -EINVAL; clear_bit(irq, vcpu->arch.irqs_pending); @@ -429,26 +446,42 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) return kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask); } -void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) +void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) { - vcpu->arch.power_off = true; + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); kvm_make_request(KVM_REQ_SLEEP, vcpu); kvm_vcpu_kick(vcpu); } -void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu) +void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) +{ + spin_lock(&vcpu->arch.mp_state_lock); + __kvm_riscv_vcpu_power_off(vcpu); + spin_unlock(&vcpu->arch.mp_state_lock); +} + +void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu) { - vcpu->arch.power_off = false; + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); kvm_vcpu_wake_up(vcpu); } +void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu) +{ + spin_lock(&vcpu->arch.mp_state_lock); + __kvm_riscv_vcpu_power_on(vcpu); + spin_unlock(&vcpu->arch.mp_state_lock); +} + +bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu) +{ + return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_STOPPED; +} + int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - if (vcpu->arch.power_off) - mp_state->mp_state = KVM_MP_STATE_STOPPED; - else - mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + *mp_state = READ_ONCE(vcpu->arch.mp_state); return 0; } @@ -458,25 +491,36 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, { int ret = 0; + spin_lock(&vcpu->arch.mp_state_lock); + switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: - vcpu->arch.power_off = false; + WRITE_ONCE(vcpu->arch.mp_state, *mp_state); break; case KVM_MP_STATE_STOPPED: - kvm_riscv_vcpu_power_off(vcpu); + __kvm_riscv_vcpu_power_off(vcpu); break; default: ret = -EINVAL; } + spin_unlock(&vcpu->arch.mp_state_lock); + return ret; } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - /* TODO; To be implemented later. */ - return -EINVAL; + if (dbg->control & KVM_GUESTDBG_ENABLE) { + vcpu->guest_debug = dbg->control; + vcpu->arch.cfg.hedeleg &= ~BIT(EXC_BREAKPOINT); + } else { + vcpu->guest_debug = 0; + vcpu->arch.cfg.hedeleg |= BIT(EXC_BREAKPOINT); + } + + return 0; } static void kvm_riscv_vcpu_setup_config(struct kvm_vcpu *vcpu) @@ -505,6 +549,10 @@ static void kvm_riscv_vcpu_setup_config(struct kvm_vcpu *vcpu) if (riscv_isa_extension_available(isa, SMSTATEEN)) cfg->hstateen0 |= SMSTATEEN0_SSTATEEN0; } + + cfg->hedeleg = KVM_HEDELEG_DEFAULT; + if (vcpu->guest_debug) + cfg->hedeleg &= ~BIT(EXC_BREAKPOINT); } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -519,6 +567,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) csr_write(CSR_VSEPC, csr->vsepc); csr_write(CSR_VSCAUSE, csr->vscause); csr_write(CSR_VSTVAL, csr->vstval); + csr_write(CSR_HEDELEG, cfg->hedeleg); csr_write(CSR_HVIP, csr->hvip); csr_write(CSR_VSATP, csr->vsatp); csr_write(CSR_HENVCFG, cfg->henvcfg); @@ -584,11 +633,11 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) { kvm_vcpu_srcu_read_unlock(vcpu); rcuwait_wait_event(wait, - (!vcpu->arch.power_off) && (!vcpu->arch.pause), + (!kvm_riscv_vcpu_stopped(vcpu)) && (!vcpu->arch.pause), TASK_INTERRUPTIBLE); kvm_vcpu_srcu_read_lock(vcpu); - if (vcpu->arch.power_off || vcpu->arch.pause) { + if (kvm_riscv_vcpu_stopped(vcpu) || vcpu->arch.pause) { /* * Awaken to handle a signal, request to * sleep again later. diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 2415722c01b8..5761f95abb60 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -204,6 +204,10 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) ret = kvm_riscv_vcpu_sbi_ecall(vcpu, run); break; + case EXC_BREAKPOINT: + run->exit_reason = KVM_EXIT_DEBUG; + ret = 0; + break; default: break; } diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index 994adc26db4b..c676275ea0a0 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -36,6 +36,7 @@ static const unsigned long kvm_isa_ext_arr[] = { /* Multi letter extensions (alphabetically sorted) */ KVM_ISA_EXT_ARR(SMSTATEEN), KVM_ISA_EXT_ARR(SSAIA), + KVM_ISA_EXT_ARR(SSCOFPMF), KVM_ISA_EXT_ARR(SSTC), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), @@ -99,6 +100,9 @@ static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext) switch (ext) { case KVM_RISCV_ISA_EXT_H: return false; + case KVM_RISCV_ISA_EXT_SSCOFPMF: + /* Sscofpmf depends on interrupt filtering defined in ssaia */ + return __riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSAIA); case KVM_RISCV_ISA_EXT_V: return riscv_v_vstate_ctrl_user_allowed(); default: @@ -116,6 +120,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_C: case KVM_RISCV_ISA_EXT_I: case KVM_RISCV_ISA_EXT_M: + /* There is not architectural config bit to disable sscofpmf completely */ + case KVM_RISCV_ISA_EXT_SSCOFPMF: case KVM_RISCV_ISA_EXT_SSTC: case KVM_RISCV_ISA_EXT_SVINVAL: case KVM_RISCV_ISA_EXT_SVNAPOT: diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 86391a5061dd..04db1f993c47 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -14,6 +14,7 @@ #include <asm/csr.h> #include <asm/kvm_vcpu_sbi.h> #include <asm/kvm_vcpu_pmu.h> +#include <asm/sbi.h> #include <linux/bitops.h> #define kvm_pmu_num_counters(pmu) ((pmu)->num_hw_ctrs + (pmu)->num_fw_ctrs) @@ -39,7 +40,7 @@ static u64 kvm_pmu_get_sample_period(struct kvm_pmc *pmc) u64 sample_period; if (!pmc->counter_val) - sample_period = counter_val_mask + 1; + sample_period = counter_val_mask; else sample_period = (-pmc->counter_val) & counter_val_mask; @@ -196,6 +197,36 @@ static int pmu_get_pmc_index(struct kvm_pmu *pmu, unsigned long eidx, return kvm_pmu_get_programmable_pmc_index(pmu, eidx, cbase, cmask); } +static int pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, + unsigned long *out_val) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int fevent_code; + + if (!IS_ENABLED(CONFIG_32BIT)) { + pr_warn("%s: should be invoked for only RV32\n", __func__); + return -EINVAL; + } + + if (cidx >= kvm_pmu_num_counters(kvpmu) || cidx == 1) { + pr_warn("Invalid counter id [%ld]during read\n", cidx); + return -EINVAL; + } + + pmc = &kvpmu->pmc[cidx]; + + if (pmc->cinfo.type != SBI_PMU_CTR_TYPE_FW) + return -EINVAL; + + fevent_code = get_event_code(pmc->event_idx); + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + + *out_val = pmc->counter_val >> 32; + + return 0; +} + static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, unsigned long *out_val) { @@ -204,6 +235,11 @@ static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, u64 enabled, running; int fevent_code; + if (cidx >= kvm_pmu_num_counters(kvpmu) || cidx == 1) { + pr_warn("Invalid counter id [%ld] during read\n", cidx); + return -EINVAL; + } + pmc = &kvpmu->pmc[cidx]; if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { @@ -229,8 +265,50 @@ static int kvm_pmu_validate_counter_mask(struct kvm_pmu *kvpmu, unsigned long ct return 0; } -static int kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr *attr, - unsigned long flags, unsigned long eidx, unsigned long evtdata) +static void kvm_riscv_pmu_overflow(struct perf_event *perf_event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct kvm_vcpu *vcpu = pmc->vcpu; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct riscv_pmu *rpmu = to_riscv_pmu(perf_event->pmu); + u64 period; + + /* + * Stop the event counting by directly accessing the perf_event. + * Otherwise, this needs to deferred via a workqueue. + * That will introduce skew in the counter value because the actual + * physical counter would start after returning from this function. + * It will be stopped again once the workqueue is scheduled + */ + rpmu->pmu.stop(perf_event, PERF_EF_UPDATE); + + /* + * The hw counter would start automatically when this function returns. + * Thus, the host may continue to interrupt and inject it to the guest + * even without the guest configuring the next event. Depending on the hardware + * the host may have some sluggishness only if privilege mode filtering is not + * available. In an ideal world, where qemu is not the only capable hardware, + * this can be removed. + * FYI: ARM64 does this way while x86 doesn't do anything as such. + * TODO: Should we keep it for RISC-V ? + */ + period = -(local64_read(&perf_event->count)); + + local64_set(&perf_event->hw.period_left, 0); + perf_event->attr.sample_period = period; + perf_event->hw.sample_period = period; + + set_bit(pmc->idx, kvpmu->pmc_overflown); + kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_PMU_OVF); + + rpmu->pmu.start(perf_event, PERF_EF_RELOAD); +} + +static long kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr *attr, + unsigned long flags, unsigned long eidx, + unsigned long evtdata) { struct perf_event *event; @@ -247,7 +325,7 @@ static int kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr */ attr->sample_period = kvm_pmu_get_sample_period(pmc); - event = perf_event_create_kernel_counter(attr, -1, current, NULL, pmc); + event = perf_event_create_kernel_counter(attr, -1, current, kvm_riscv_pmu_overflow, pmc); if (IS_ERR(event)) { pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event)); return PTR_ERR(event); @@ -310,6 +388,80 @@ int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, return ret; } +static void kvm_pmu_clear_snapshot_area(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int snapshot_area_size = sizeof(struct riscv_pmu_snapshot_data); + + if (kvpmu->sdata) { + if (kvpmu->snapshot_addr != INVALID_GPA) { + memset(kvpmu->sdata, 0, snapshot_area_size); + kvm_vcpu_write_guest(vcpu, kvpmu->snapshot_addr, + kvpmu->sdata, snapshot_area_size); + } else { + pr_warn("snapshot address invalid\n"); + } + kfree(kvpmu->sdata); + kvpmu->sdata = NULL; + } + kvpmu->snapshot_addr = INVALID_GPA; +} + +int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long saddr_low, + unsigned long saddr_high, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int snapshot_area_size = sizeof(struct riscv_pmu_snapshot_data); + int sbiret = 0; + gpa_t saddr; + unsigned long hva; + bool writable; + + if (!kvpmu || flags) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (saddr_low == SBI_SHMEM_DISABLE && saddr_high == SBI_SHMEM_DISABLE) { + kvm_pmu_clear_snapshot_area(vcpu); + return 0; + } + + saddr = saddr_low; + + if (saddr_high != 0) { + if (IS_ENABLED(CONFIG_32BIT)) + saddr |= ((gpa_t)saddr_high << 32); + else + sbiret = SBI_ERR_INVALID_ADDRESS; + goto out; + } + + hva = kvm_vcpu_gfn_to_hva_prot(vcpu, saddr >> PAGE_SHIFT, &writable); + if (kvm_is_error_hva(hva) || !writable) { + sbiret = SBI_ERR_INVALID_ADDRESS; + goto out; + } + + kvpmu->sdata = kzalloc(snapshot_area_size, GFP_ATOMIC); + if (!kvpmu->sdata) + return -ENOMEM; + + if (kvm_vcpu_write_guest(vcpu, saddr, kvpmu->sdata, snapshot_area_size)) { + kfree(kvpmu->sdata); + sbiret = SBI_ERR_FAILURE; + goto out; + } + + kvpmu->snapshot_addr = saddr; + +out: + retdata->err_val = sbiret; + + return 0; +} + int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, struct kvm_vcpu_sbi_return *retdata) { @@ -343,20 +495,40 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, int i, pmc_index, sbiret = 0; struct kvm_pmc *pmc; int fevent_code; + bool snap_flag_set = flags & SBI_PMU_START_FLAG_INIT_SNAPSHOT; if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { sbiret = SBI_ERR_INVALID_PARAM; goto out; } + if (snap_flag_set) { + if (kvpmu->snapshot_addr == INVALID_GPA) { + sbiret = SBI_ERR_NO_SHMEM; + goto out; + } + if (kvm_vcpu_read_guest(vcpu, kvpmu->snapshot_addr, kvpmu->sdata, + sizeof(struct riscv_pmu_snapshot_data))) { + pr_warn("Unable to read snapshot shared memory while starting counters\n"); + sbiret = SBI_ERR_FAILURE; + goto out; + } + } /* Start the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { pmc_index = i + ctr_base; if (!test_bit(pmc_index, kvpmu->pmc_in_use)) continue; + /* The guest started the counter again. Reset the overflow status */ + clear_bit(pmc_index, kvpmu->pmc_overflown); pmc = &kvpmu->pmc[pmc_index]; - if (flags & SBI_PMU_START_FLAG_SET_INIT_VALUE) + if (flags & SBI_PMU_START_FLAG_SET_INIT_VALUE) { pmc->counter_val = ival; + } else if (snap_flag_set) { + /* The counter index in the snapshot are relative to the counter base */ + pmc->counter_val = kvpmu->sdata->ctr_values[i]; + } + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { fevent_code = get_event_code(pmc->event_idx); if (fevent_code >= SBI_PMU_FW_MAX) { @@ -400,12 +572,19 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, u64 enabled, running; struct kvm_pmc *pmc; int fevent_code; + bool snap_flag_set = flags & SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT; + bool shmem_needs_update = false; if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { sbiret = SBI_ERR_INVALID_PARAM; goto out; } + if (snap_flag_set && kvpmu->snapshot_addr == INVALID_GPA) { + sbiret = SBI_ERR_NO_SHMEM; + goto out; + } + /* Stop the counters that have been configured and requested by the guest */ for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { pmc_index = i + ctr_base; @@ -432,21 +611,49 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, sbiret = SBI_ERR_ALREADY_STOPPED; } - if (flags & SBI_PMU_STOP_FLAG_RESET) { - /* Relase the counter if this is a reset request */ - pmc->counter_val += perf_event_read_value(pmc->perf_event, - &enabled, &running); + if (flags & SBI_PMU_STOP_FLAG_RESET) + /* Release the counter if this is a reset request */ kvm_pmu_release_perf_event(pmc); - } } else { sbiret = SBI_ERR_INVALID_PARAM; } + + if (snap_flag_set && !sbiret) { + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + else if (pmc->perf_event) + pmc->counter_val += perf_event_read_value(pmc->perf_event, + &enabled, &running); + /* + * The counter and overflow indicies in the snapshot region are w.r.to + * cbase. Modify the set bit in the counter mask instead of the pmc_index + * which indicates the absolute counter index. + */ + if (test_bit(pmc_index, kvpmu->pmc_overflown)) + kvpmu->sdata->ctr_overflow_mask |= BIT(i); + kvpmu->sdata->ctr_values[i] = pmc->counter_val; + shmem_needs_update = true; + } + if (flags & SBI_PMU_STOP_FLAG_RESET) { pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; clear_bit(pmc_index, kvpmu->pmc_in_use); + clear_bit(pmc_index, kvpmu->pmc_overflown); + if (snap_flag_set) { + /* + * Only clear the given counter as the caller is responsible to + * validate both the overflow mask and configured counters. + */ + kvpmu->sdata->ctr_overflow_mask &= ~BIT(i); + shmem_needs_update = true; + } } } + if (shmem_needs_update) + kvm_vcpu_write_guest(vcpu, kvpmu->snapshot_addr, kvpmu->sdata, + sizeof(struct riscv_pmu_snapshot_data)); + out: retdata->err_val = sbiret; @@ -458,7 +665,8 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba unsigned long eidx, u64 evtdata, struct kvm_vcpu_sbi_return *retdata) { - int ctr_idx, ret, sbiret = 0; + int ctr_idx, sbiret = 0; + long ret; bool is_fevent; unsigned long event_code; u32 etype = kvm_pmu_get_perf_event_type(eidx); @@ -517,8 +725,10 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba kvpmu->fw_event[event_code].started = true; } else { ret = kvm_pmu_create_perf_event(pmc, &attr, flags, eidx, evtdata); - if (ret) - return ret; + if (ret) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } } set_bit(ctr_idx, kvpmu->pmc_in_use); @@ -530,7 +740,19 @@ out: return 0; } -int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, +int kvm_riscv_vcpu_pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret; + + ret = pmu_fw_ctr_read_hi(vcpu, cidx, &retdata->out_val); + if (ret == -EINVAL) + retdata->err_val = SBI_ERR_INVALID_PARAM; + + return 0; +} + +int kvm_riscv_vcpu_pmu_fw_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, struct kvm_vcpu_sbi_return *retdata) { int ret; @@ -566,6 +788,7 @@ void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) kvpmu->num_hw_ctrs = num_hw_ctrs + 1; kvpmu->num_fw_ctrs = SBI_PMU_FW_MAX; memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); + kvpmu->snapshot_addr = INVALID_GPA; if (kvpmu->num_hw_ctrs > RISCV_KVM_MAX_HW_CTRS) { pr_warn_once("Limiting the hardware counters to 32 as specified by the ISA"); @@ -585,6 +808,7 @@ void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) pmc = &kvpmu->pmc[i]; pmc->idx = i; pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + pmc->vcpu = vcpu; if (i < kvpmu->num_hw_ctrs) { pmc->cinfo.type = SBI_PMU_CTR_TYPE_HW; if (i < 3) @@ -601,7 +825,7 @@ void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) pmc->cinfo.csr = CSR_CYCLE + i; } else { pmc->cinfo.type = SBI_PMU_CTR_TYPE_FW; - pmc->cinfo.width = BITS_PER_LONG - 1; + pmc->cinfo.width = 63; } } @@ -617,14 +841,16 @@ void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) if (!kvpmu) return; - for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_MAX_COUNTERS) { + for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_KVM_MAX_COUNTERS) { pmc = &kvpmu->pmc[i]; pmc->counter_val = 0; kvm_pmu_release_perf_event(pmc); pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; } - bitmap_zero(kvpmu->pmc_in_use, RISCV_MAX_COUNTERS); + bitmap_zero(kvpmu->pmc_in_use, RISCV_KVM_MAX_COUNTERS); + bitmap_zero(kvpmu->pmc_overflown, RISCV_KVM_MAX_COUNTERS); memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); + kvm_pmu_clear_snapshot_area(vcpu); } void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 72a2ffb8dcd1..62f409d4176e 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -138,8 +138,11 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, unsigned long i; struct kvm_vcpu *tmp; - kvm_for_each_vcpu(i, tmp, vcpu->kvm) - tmp->arch.power_off = true; + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + spin_lock(&vcpu->arch.mp_state_lock); + WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); + spin_unlock(&vcpu->arch.mp_state_lock); + } kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); memset(&run->system_event, 0, sizeof(run->system_event)); diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c index 7dca0e9381d9..dce667f4b6ab 100644 --- a/arch/riscv/kvm/vcpu_sbi_hsm.c +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -18,13 +18,20 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) struct kvm_cpu_context *cp = &vcpu->arch.guest_context; struct kvm_vcpu *target_vcpu; unsigned long target_vcpuid = cp->a0; + int ret = 0; target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) return SBI_ERR_INVALID_PARAM; - if (!target_vcpu->arch.power_off) - return SBI_ERR_ALREADY_AVAILABLE; + spin_lock(&target_vcpu->arch.mp_state_lock); + + if (!kvm_riscv_vcpu_stopped(target_vcpu)) { + ret = SBI_ERR_ALREADY_AVAILABLE; + goto out; + } + + spin_lock(&target_vcpu->arch.reset_cntx_lock); reset_cntx = &target_vcpu->arch.guest_reset_context; /* start address */ reset_cntx->sepc = cp->a1; @@ -32,21 +39,35 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) reset_cntx->a0 = target_vcpuid; /* private data passed from kernel */ reset_cntx->a1 = cp->a2; + spin_unlock(&target_vcpu->arch.reset_cntx_lock); + kvm_make_request(KVM_REQ_VCPU_RESET, target_vcpu); - kvm_riscv_vcpu_power_on(target_vcpu); + __kvm_riscv_vcpu_power_on(target_vcpu); - return 0; +out: + spin_unlock(&target_vcpu->arch.mp_state_lock); + + return ret; } static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu) { - if (vcpu->arch.power_off) - return SBI_ERR_FAILURE; + int ret = 0; - kvm_riscv_vcpu_power_off(vcpu); + spin_lock(&vcpu->arch.mp_state_lock); - return 0; + if (kvm_riscv_vcpu_stopped(vcpu)) { + ret = SBI_ERR_FAILURE; + goto out; + } + + __kvm_riscv_vcpu_power_off(vcpu); + +out: + spin_unlock(&vcpu->arch.mp_state_lock); + + return ret; } static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) @@ -58,7 +79,7 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) return SBI_ERR_INVALID_PARAM; - if (!target_vcpu->arch.power_off) + if (!kvm_riscv_vcpu_stopped(target_vcpu)) return SBI_HSM_STATE_STARTED; else if (vcpu->stat.generic.blocking) return SBI_HSM_STATE_SUSPENDED; @@ -71,14 +92,11 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, { int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; - struct kvm *kvm = vcpu->kvm; unsigned long funcid = cp->a6; switch (funcid) { case SBI_EXT_HSM_HART_START: - mutex_lock(&kvm->lock); ret = kvm_sbi_hsm_vcpu_start(vcpu); - mutex_unlock(&kvm->lock); break; case SBI_EXT_HSM_HART_STOP: ret = kvm_sbi_hsm_vcpu_stop(vcpu); diff --git a/arch/riscv/kvm/vcpu_sbi_pmu.c b/arch/riscv/kvm/vcpu_sbi_pmu.c index 7eca72df2cbd..e4be34e03e83 100644 --- a/arch/riscv/kvm/vcpu_sbi_pmu.c +++ b/arch/riscv/kvm/vcpu_sbi_pmu.c @@ -42,9 +42,9 @@ static int kvm_sbi_ext_pmu_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, #endif /* * This can fail if perf core framework fails to create an event. - * Forward the error to userspace because it's an error which - * happened within the host kernel. The other option would be - * to convert to an SBI error and forward to the guest. + * No need to forward the error to userspace and exit the guest. + * The operation can continue without profiling. Forward the + * appropriate SBI error to the guest. */ ret = kvm_riscv_vcpu_pmu_ctr_cfg_match(vcpu, cp->a0, cp->a1, cp->a2, cp->a3, temp, retdata); @@ -62,7 +62,16 @@ static int kvm_sbi_ext_pmu_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, ret = kvm_riscv_vcpu_pmu_ctr_stop(vcpu, cp->a0, cp->a1, cp->a2, retdata); break; case SBI_EXT_PMU_COUNTER_FW_READ: - ret = kvm_riscv_vcpu_pmu_ctr_read(vcpu, cp->a0, retdata); + ret = kvm_riscv_vcpu_pmu_fw_ctr_read(vcpu, cp->a0, retdata); + break; + case SBI_EXT_PMU_COUNTER_FW_READ_HI: + if (IS_ENABLED(CONFIG_32BIT)) + ret = kvm_riscv_vcpu_pmu_fw_ctr_read_hi(vcpu, cp->a0, retdata); + else + retdata->out_val = 0; + break; + case SBI_EXT_PMU_SNAPSHOT_SET_SHMEM: + ret = kvm_riscv_vcpu_pmu_snapshot_set_shmem(vcpu, cp->a0, cp->a1, cp->a2, retdata); break; default: retdata->err_val = SBI_ERR_NOT_SUPPORTED; diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c index d8cf9ca28c61..5f35427114c1 100644 --- a/arch/riscv/kvm/vcpu_sbi_sta.c +++ b/arch/riscv/kvm/vcpu_sbi_sta.c @@ -93,8 +93,8 @@ static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu) if (flags != 0) return SBI_ERR_INVALID_PARAM; - if (shmem_phys_lo == SBI_STA_SHMEM_DISABLE && - shmem_phys_hi == SBI_STA_SHMEM_DISABLE) { + if (shmem_phys_lo == SBI_SHMEM_DISABLE && + shmem_phys_hi == SBI_SHMEM_DISABLE) { vcpu->arch.sta.shmem = INVALID_GPA; return 0; } diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index ce58bc48e5b8..7396b8654f45 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -186,6 +186,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_READONLY_MEM: case KVM_CAP_MP_STATE: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_NR_VCPUS: diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 2641ba620f12..e010bfed8417 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1237,11 +1237,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu = event->pmu; /* - * Make sure we get updated with the first PEBS - * event. It will trigger also during removal, but - * that does not hurt: + * Make sure we get updated with the first PEBS event. + * During removal, ->pebs_data_cfg is still valid for + * the last PEBS event. Don't clear it. */ - if (cpuc->n_pebs == 1) + if ((cpuc->n_pebs == 1) && add) cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index 76f79b68cef8..888ca636f3f3 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -324,6 +324,7 @@ static void decode_ISR(unsigned int val) decode_bits(KERN_DEBUG "ISR", isr_bits, ARRAY_SIZE(isr_bits), val); } +#ifdef CONFIG_I2C_PXA_SLAVE static const struct bits icr_bits[] = { PXA_BIT(ICR_START, "START", NULL), PXA_BIT(ICR_STOP, "STOP", NULL), @@ -342,7 +343,6 @@ static const struct bits icr_bits[] = { PXA_BIT(ICR_UR, "UR", "ur"), }; -#ifdef CONFIG_I2C_PXA_SLAVE static void decode_ICR(unsigned int val) { decode_bits(KERN_DEBUG "ICR", icr_bits, ARRAY_SIZE(icr_bits), val); diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index b4efdddb2ad9..78c490e0505a 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -191,8 +191,6 @@ void riscv_pmu_stop(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); - WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); - if (!(hwc->state & PERF_HES_STOPPED)) { if (rvpmu->ctr_stop) { rvpmu->ctr_stop(event, 0); @@ -408,6 +406,7 @@ struct riscv_pmu *riscv_pmu_alloc(void) cpuc->n_events = 0; for (i = 0; i < RISCV_MAX_COUNTERS; i++) cpuc->events[i] = NULL; + cpuc->snapshot_addr = NULL; } pmu->pmu = (struct pmu) { .event_init = riscv_pmu_event_init, diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 8cbe6e5f9c39..5d699b06dcb6 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -27,7 +27,7 @@ #define ALT_SBI_PMU_OVERFLOW(__ovl) \ asm volatile(ALTERNATIVE_2( \ - "csrr %0, " __stringify(CSR_SSCOUNTOVF), \ + "csrr %0, " __stringify(CSR_SCOUNTOVF), \ "csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF), \ THEAD_VENDOR_ID, ERRATA_THEAD_PMU, \ CONFIG_ERRATA_THEAD_PMU, \ @@ -57,6 +57,11 @@ asm volatile(ALTERNATIVE( \ PMU_FORMAT_ATTR(event, "config:0-47"); PMU_FORMAT_ATTR(firmware, "config:63"); +static bool sbi_v2_available; +static DEFINE_STATIC_KEY_FALSE(sbi_pmu_snapshot_available); +#define sbi_pmu_snapshot_available() \ + static_branch_unlikely(&sbi_pmu_snapshot_available) + static struct attribute *riscv_arch_formats_attr[] = { &format_attr_event.attr, &format_attr_firmware.attr, @@ -384,7 +389,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) cmask = 1; } else if (event->attr.config == PERF_COUNT_HW_INSTRUCTIONS) { cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH; - cmask = 1UL << (CSR_INSTRET - CSR_CYCLE); + cmask = BIT(CSR_INSTRET - CSR_CYCLE); } } @@ -506,24 +511,126 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) return ret; } +static void pmu_sbi_snapshot_free(struct riscv_pmu *pmu) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct cpu_hw_events *cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu); + + if (!cpu_hw_evt->snapshot_addr) + continue; + + free_page((unsigned long)cpu_hw_evt->snapshot_addr); + cpu_hw_evt->snapshot_addr = NULL; + cpu_hw_evt->snapshot_addr_phys = 0; + } +} + +static int pmu_sbi_snapshot_alloc(struct riscv_pmu *pmu) +{ + int cpu; + struct page *snapshot_page; + + for_each_possible_cpu(cpu) { + struct cpu_hw_events *cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu); + + snapshot_page = alloc_page(GFP_ATOMIC | __GFP_ZERO); + if (!snapshot_page) { + pmu_sbi_snapshot_free(pmu); + return -ENOMEM; + } + cpu_hw_evt->snapshot_addr = page_to_virt(snapshot_page); + cpu_hw_evt->snapshot_addr_phys = page_to_phys(snapshot_page); + } + + return 0; +} + +static int pmu_sbi_snapshot_disable(void) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, SBI_SHMEM_DISABLE, + SBI_SHMEM_DISABLE, 0, 0, 0, 0); + if (ret.error) { + pr_warn("failed to disable snapshot shared memory\n"); + return sbi_err_map_linux_errno(ret.error); + } + + return 0; +} + +static int pmu_sbi_snapshot_setup(struct riscv_pmu *pmu, int cpu) +{ + struct cpu_hw_events *cpu_hw_evt; + struct sbiret ret = {0}; + + cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu); + if (!cpu_hw_evt->snapshot_addr_phys) + return -EINVAL; + + if (cpu_hw_evt->snapshot_set_done) + return 0; + + if (IS_ENABLED(CONFIG_32BIT)) + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, + cpu_hw_evt->snapshot_addr_phys, + (u64)(cpu_hw_evt->snapshot_addr_phys) >> 32, 0, 0, 0, 0); + else + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, + cpu_hw_evt->snapshot_addr_phys, 0, 0, 0, 0, 0); + + /* Free up the snapshot area memory and fall back to SBI PMU calls without snapshot */ + if (ret.error) { + if (ret.error != SBI_ERR_NOT_SUPPORTED) + pr_warn("pmu snapshot setup failed with error %ld\n", ret.error); + return sbi_err_map_linux_errno(ret.error); + } + + memset(cpu_hw_evt->snapshot_cval_shcopy, 0, sizeof(u64) * RISCV_MAX_COUNTERS); + cpu_hw_evt->snapshot_set_done = true; + + return 0; +} + static u64 pmu_sbi_ctr_read(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; struct sbiret ret; - union sbi_pmu_ctr_info info; u64 val = 0; + struct riscv_pmu *pmu = to_riscv_pmu(event->pmu); + struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); + struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; + union sbi_pmu_ctr_info info = pmu_ctr_list[idx]; + + /* Read the value from the shared memory directly only if counter is stopped */ + if (sbi_pmu_snapshot_available() && (hwc->state & PERF_HES_STOPPED)) { + val = sdata->ctr_values[idx]; + return val; + } if (pmu_sbi_is_fw_event(event)) { ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_FW_READ, hwc->idx, 0, 0, 0, 0, 0); - if (!ret.error) - val = ret.value; + if (ret.error) + return 0; + + val = ret.value; + if (IS_ENABLED(CONFIG_32BIT) && sbi_v2_available && info.width >= 32) { + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_FW_READ_HI, + hwc->idx, 0, 0, 0, 0, 0); + if (!ret.error) + val |= ((u64)ret.value << 32); + else + WARN_ONCE(1, "Unable to read upper 32 bits of firmware counter error: %ld\n", + ret.error); + } } else { - info = pmu_ctr_list[idx]; val = riscv_pmu_ctr_read_csr(info.csr); if (IS_ENABLED(CONFIG_32BIT)) - val = ((u64)riscv_pmu_ctr_read_csr(info.csr + 0x80)) << 31 | val; + val |= ((u64)riscv_pmu_ctr_read_csr(info.csr + 0x80)) << 32; } return val; @@ -553,6 +660,7 @@ static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival) struct hw_perf_event *hwc = &event->hw; unsigned long flag = SBI_PMU_START_FLAG_SET_INIT_VALUE; + /* There is no benefit setting SNAPSHOT FLAG for a single counter */ #if defined(CONFIG_32BIT) ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, hwc->idx, 1, flag, ival, ival >> 32, 0); @@ -573,16 +681,36 @@ static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag) { struct sbiret ret; struct hw_perf_event *hwc = &event->hw; + struct riscv_pmu *pmu = to_riscv_pmu(event->pmu); + struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); + struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) && (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) pmu_sbi_reset_scounteren((void *)event); + if (sbi_pmu_snapshot_available()) + flag |= SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT; + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, hwc->idx, 1, flag, 0, 0, 0); - if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) && - flag != SBI_PMU_STOP_FLAG_RESET) + if (!ret.error && sbi_pmu_snapshot_available()) { + /* + * The counter snapshot is based on the index base specified by hwc->idx. + * The actual counter value is updated in shared memory at index 0 when counter + * mask is 0x01. To ensure accurate counter values, it's necessary to transfer + * the counter value to shared memory. However, if hwc->idx is zero, the counter + * value is already correctly updated in shared memory, requiring no further + * adjustment. + */ + if (hwc->idx > 0) { + sdata->ctr_values[hwc->idx] = sdata->ctr_values[0]; + sdata->ctr_values[0] = 0; + } + } else if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) && + flag != SBI_PMU_STOP_FLAG_RESET) { pr_err("Stopping counter idx %d failed with error %d\n", hwc->idx, sbi_err_map_linux_errno(ret.error)); + } } static int pmu_sbi_find_num_ctrs(void) @@ -640,10 +768,39 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu) static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) { struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); + struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; + unsigned long flag = 0; + int i, idx; + struct sbiret ret; + u64 temp_ctr_overflow_mask = 0; + + if (sbi_pmu_snapshot_available()) + flag = SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT; + + /* Reset the shadow copy to avoid save/restore any value from previous overflow */ + memset(cpu_hw_evt->snapshot_cval_shcopy, 0, sizeof(u64) * RISCV_MAX_COUNTERS); + + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + /* No need to check the error here as we can't do anything about the error */ + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, i * BITS_PER_LONG, + cpu_hw_evt->used_hw_ctrs[i], flag, 0, 0, 0); + if (!ret.error && sbi_pmu_snapshot_available()) { + /* Save the counter values to avoid clobbering */ + for_each_set_bit(idx, &cpu_hw_evt->used_hw_ctrs[i], BITS_PER_LONG) + cpu_hw_evt->snapshot_cval_shcopy[i * BITS_PER_LONG + idx] = + sdata->ctr_values[idx]; + /* Save the overflow mask to avoid clobbering */ + temp_ctr_overflow_mask |= sdata->ctr_overflow_mask << (i * BITS_PER_LONG); + } + } - /* No need to check the error here as we can't do anything about the error */ - sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, 0, - cpu_hw_evt->used_hw_ctrs[0], 0, 0, 0, 0); + /* Restore the counter values to the shared memory for used hw counters */ + if (sbi_pmu_snapshot_available()) { + for_each_set_bit(idx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS) + sdata->ctr_values[idx] = cpu_hw_evt->snapshot_cval_shcopy[idx]; + if (temp_ctr_overflow_mask) + sdata->ctr_overflow_mask = temp_ctr_overflow_mask; + } } /* @@ -652,11 +809,10 @@ static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) * while the overflowed counters need to be started with updated initialization * value. */ -static inline void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu, - unsigned long ctr_ovf_mask) +static inline void pmu_sbi_start_ovf_ctrs_sbi(struct cpu_hw_events *cpu_hw_evt, + u64 ctr_ovf_mask) { - int idx = 0; - struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); + int idx = 0, i; struct perf_event *event; unsigned long flag = SBI_PMU_START_FLAG_SET_INIT_VALUE; unsigned long ctr_start_mask = 0; @@ -664,11 +820,12 @@ static inline void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu, struct hw_perf_event *hwc; u64 init_val = 0; - ctr_start_mask = cpu_hw_evt->used_hw_ctrs[0] & ~ctr_ovf_mask; - - /* Start all the counters that did not overflow in a single shot */ - sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, 0, ctr_start_mask, - 0, 0, 0, 0); + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + ctr_start_mask = cpu_hw_evt->used_hw_ctrs[i] & ~ctr_ovf_mask; + /* Start all the counters that did not overflow in a single shot */ + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, i * BITS_PER_LONG, ctr_start_mask, + 0, 0, 0, 0); + } /* Reinitialize and start all the counter that overflowed */ while (ctr_ovf_mask) { @@ -691,6 +848,52 @@ static inline void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu, } } +static inline void pmu_sbi_start_ovf_ctrs_snapshot(struct cpu_hw_events *cpu_hw_evt, + u64 ctr_ovf_mask) +{ + int i, idx = 0; + struct perf_event *event; + unsigned long flag = SBI_PMU_START_FLAG_INIT_SNAPSHOT; + u64 max_period, init_val = 0; + struct hw_perf_event *hwc; + struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; + + for_each_set_bit(idx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS) { + if (ctr_ovf_mask & BIT(idx)) { + event = cpu_hw_evt->events[idx]; + hwc = &event->hw; + max_period = riscv_pmu_ctr_get_width_mask(event); + init_val = local64_read(&hwc->prev_count) & max_period; + cpu_hw_evt->snapshot_cval_shcopy[idx] = init_val; + } + /* + * We do not need to update the non-overflow counters the previous + * value should have been there already. + */ + } + + for (i = 0; i < BITS_TO_LONGS(RISCV_MAX_COUNTERS); i++) { + /* Restore the counter values to relative indices for used hw counters */ + for_each_set_bit(idx, &cpu_hw_evt->used_hw_ctrs[i], BITS_PER_LONG) + sdata->ctr_values[idx] = + cpu_hw_evt->snapshot_cval_shcopy[idx + i * BITS_PER_LONG]; + /* Start all the counters in a single shot */ + sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, idx * BITS_PER_LONG, + cpu_hw_evt->used_hw_ctrs[i], flag, 0, 0, 0); + } +} + +static void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu, + u64 ctr_ovf_mask) +{ + struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); + + if (sbi_pmu_snapshot_available()) + pmu_sbi_start_ovf_ctrs_snapshot(cpu_hw_evt, ctr_ovf_mask); + else + pmu_sbi_start_ovf_ctrs_sbi(cpu_hw_evt, ctr_ovf_mask); +} + static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) { struct perf_sample_data data; @@ -700,10 +903,11 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) int lidx, hidx, fidx; struct riscv_pmu *pmu; struct perf_event *event; - unsigned long overflow; - unsigned long overflowed_ctrs = 0; + u64 overflow; + u64 overflowed_ctrs = 0; struct cpu_hw_events *cpu_hw_evt = dev; u64 start_clock = sched_clock(); + struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr; if (WARN_ON_ONCE(!cpu_hw_evt)) return IRQ_NONE; @@ -725,7 +929,10 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) pmu_sbi_stop_hw_ctrs(pmu); /* Overflow status register should only be read after counter are stopped */ - ALT_SBI_PMU_OVERFLOW(overflow); + if (sbi_pmu_snapshot_available()) + overflow = sdata->ctr_overflow_mask; + else + ALT_SBI_PMU_OVERFLOW(overflow); /* * Overflow interrupt pending bit should only be cleared after stopping @@ -751,9 +958,14 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) if (!info || info->type != SBI_PMU_CTR_TYPE_HW) continue; - /* compute hardware counter index */ - hidx = info->csr - CSR_CYCLE; - /* check if the corresponding bit is set in sscountovf */ + if (sbi_pmu_snapshot_available()) + /* SBI implementation already updated the logical indicies */ + hidx = lidx; + else + /* compute hardware counter index */ + hidx = info->csr - CSR_CYCLE; + + /* check if the corresponding bit is set in sscountovf or overflow mask in shmem */ if (!(overflow & BIT(hidx))) continue; @@ -763,7 +975,10 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) */ overflowed_ctrs |= BIT(lidx); hw_evt = &event->hw; + /* Update the event states here so that we know the state while reading */ + hw_evt->state |= PERF_HES_STOPPED; riscv_pmu_event_update(event); + hw_evt->state |= PERF_HES_UPTODATE; perf_sample_data_init(&data, 0, hw_evt->last_period); if (riscv_pmu_event_set_period(event)) { /* @@ -776,6 +991,8 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) */ perf_event_overflow(event, &data, regs); } + /* Reset the state as we are going to start the counter after the loop */ + hw_evt->state = 0; } pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs); @@ -807,6 +1024,9 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) enable_percpu_irq(riscv_pmu_irq, IRQ_TYPE_NONE); } + if (sbi_pmu_snapshot_available()) + return pmu_sbi_snapshot_setup(pmu, cpu); + return 0; } @@ -819,6 +1039,9 @@ static int pmu_sbi_dying_cpu(unsigned int cpu, struct hlist_node *node) /* Disable all counters access for user mode now */ csr_write(CSR_SCOUNTEREN, 0x0); + if (sbi_pmu_snapshot_available()) + return pmu_sbi_snapshot_disable(); + return 0; } @@ -927,6 +1150,12 @@ static inline void riscv_pm_pmu_unregister(struct riscv_pmu *pmu) { } static void riscv_pmu_destroy(struct riscv_pmu *pmu) { + if (sbi_v2_available) { + if (sbi_pmu_snapshot_available()) { + pmu_sbi_snapshot_disable(); + pmu_sbi_snapshot_free(pmu); + } + } riscv_pm_pmu_unregister(pmu); cpuhp_state_remove_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node); } @@ -1094,10 +1323,6 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) pmu->event_unmapped = pmu_sbi_event_unmapped; pmu->csr_index = pmu_sbi_csr_index; - ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node); - if (ret) - return ret; - ret = riscv_pm_pmu_register(pmu); if (ret) goto out_unregister; @@ -1106,8 +1331,34 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) if (ret) goto out_unregister; + /* SBI PMU Snapsphot is only available in SBI v2.0 */ + if (sbi_v2_available) { + ret = pmu_sbi_snapshot_alloc(pmu); + if (ret) + goto out_unregister; + + ret = pmu_sbi_snapshot_setup(pmu, smp_processor_id()); + if (ret) { + /* Snapshot is an optional feature. Continue if not available */ + pmu_sbi_snapshot_free(pmu); + } else { + pr_info("SBI PMU snapshot detected\n"); + /* + * We enable it once here for the boot cpu. If snapshot shmem setup + * fails during cpu hotplug process, it will fail to start the cpu + * as we can not handle hetergenous PMUs with different snapshot + * capability. + */ + static_branch_enable(&sbi_pmu_snapshot_available); + } + } + register_sysctl("kernel", sbi_pmu_sysctl_table); + ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node); + if (ret) + goto out_unregister; + return 0; out_unregister: @@ -1135,6 +1386,9 @@ static int __init pmu_sbi_devinit(void) return 0; } + if (sbi_spec_version >= sbi_mk_version(2, 0)) + sbi_v2_available = true; + ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_RISCV_STARTING, "perf/riscv/pmu:starting", pmu_sbi_starting_cpu, pmu_sbi_dying_cpu); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2391ab3c3231..84d4093ca713 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3042,12 +3042,9 @@ static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - spin_lock(&nn->client_lock); clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); - put_client_renew_locked(clp); - spin_unlock(&nn->client_lock); + drop_client(clp); } static int @@ -6616,7 +6613,7 @@ deleg_reaper(struct nfsd_net *nn) list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ - atomic_inc(&clp->cl_rpc_users); + kref_get(&clp->cl_nfsdfs.cl_ref); set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); clp->cl_ra_time = ktime_get_boottime_seconds(); } diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index a0017724d523..13a9d7acf8f8 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -417,6 +417,7 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); + int rc; spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->on_list) { @@ -430,9 +431,10 @@ smb2_close_cached_fid(struct kref *ref) cfid->dentry = NULL; if (cfid->is_open) { - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); - atomic_dec(&cfid->tcon->num_remote_opens); + if (rc != -EBUSY && rc != -EAGAIN) + atomic_dec(&cfid->tcon->num_remote_opens); } free_cached_dir(cfid); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 226d4835c92d..c71ae5c04306 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -250,6 +250,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { @@ -676,6 +678,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, } #endif /* CONFIG_CIFS_STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { atomic_set(&tcon->num_smbs_sent, 0); spin_lock(&tcon->stat_lock); @@ -755,6 +759,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) } #endif /* STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { i++; seq_printf(m, "\n%d) %s", i, tcon->tree_name); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index aa6f1ecb7c0e..d41eedbff674 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -156,6 +156,7 @@ struct workqueue_struct *decrypt_wq; struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; struct workqueue_struct *deferredclose_wq; +struct workqueue_struct *serverclose_wq; __u32 cifs_lock_secret; /* @@ -1888,6 +1889,13 @@ init_cifs(void) goto out_destroy_cifsoplockd_wq; } + serverclose_wq = alloc_workqueue("serverclose", + WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + if (!serverclose_wq) { + rc = -ENOMEM; + goto out_destroy_serverclose_wq; + } + rc = cifs_init_inodecache(); if (rc) goto out_destroy_deferredclose_wq; @@ -1962,6 +1970,8 @@ out_destroy_decrypt_wq: destroy_workqueue(decrypt_wq); out_destroy_cifsiod_wq: destroy_workqueue(cifsiod_wq); +out_destroy_serverclose_wq: + destroy_workqueue(serverclose_wq); out_clean_proc: cifs_proc_clean(); return rc; @@ -1991,6 +2001,7 @@ exit_cifs(void) destroy_workqueue(cifsoplockd_wq); destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); + destroy_workqueue(serverclose_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 7ed9d05f6890..f6a302205f89 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -442,10 +442,10 @@ struct smb_version_operations { /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ - void (*close)(const unsigned int, struct cifs_tcon *, + int (*close)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* close a file, returning file attributes and timestamps */ - void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, + int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *pfile_info); /* send a flush request to the server */ int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); @@ -1281,7 +1281,6 @@ struct cifs_tcon { struct cached_fids *cfids; /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - struct list_head dfs_ses_list; struct delayed_work dfs_cache_work; #endif struct delayed_work query_interfaces; /* query interfaces workqueue job */ @@ -1440,6 +1439,7 @@ struct cifsFileInfo { bool swapfile:1; bool oplock_break_cancelled:1; bool status_file_deleted:1; /* file has been deleted */ + bool offload:1; /* offload final part of _put to a wq */ unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ int count; @@ -1448,6 +1448,7 @@ struct cifsFileInfo { struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ struct work_struct put; /* work for the final part of _put */ + struct work_struct serverclose; /* work for serverclose */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ char *symlink_target; @@ -1804,7 +1805,6 @@ struct cifs_mount_ctx { struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct list_head dfs_ses_list; }; static inline void __free_dfs_info_param(struct dfs_info3_param *param) @@ -2105,6 +2105,7 @@ extern struct workqueue_struct *decrypt_wq; extern struct workqueue_struct *fileinfo_put_wq; extern struct workqueue_struct *cifsoplockd_wq; extern struct workqueue_struct *deferredclose_wq; +extern struct workqueue_struct *serverclose_wq; extern __u32 cifs_lock_secret; extern mempool_t *cifs_sm_req_poolp; @@ -2324,4 +2325,14 @@ struct smb2_compound_vars { struct kvec ea_iov; }; +static inline bool cifs_ses_exiting(struct cifs_ses *ses) +{ + bool ret; + + spin_lock(&ses->ses_lock); + ret = ses->ses_status == SES_EXITING; + spin_unlock(&ses->ses_lock); + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 0723e1b57256..8e0a348f1f66 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -725,31 +725,31 @@ struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon); void cifs_put_tcon_super(struct super_block *sb); int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry); -/* Put references of @ses and @ses->dfs_root_ses */ +/* Put references of @ses and its children */ static inline void cifs_put_smb_ses(struct cifs_ses *ses) { - struct cifs_ses *rses = ses->dfs_root_ses; + struct cifs_ses *next; - __cifs_put_smb_ses(ses); - if (rses) - __cifs_put_smb_ses(rses); + do { + next = ses->dfs_root_ses; + __cifs_put_smb_ses(ses); + } while ((ses = next)); } -/* Get an active reference of @ses and @ses->dfs_root_ses. +/* Get an active reference of @ses and its children. * * NOTE: make sure to call this function when incrementing reference count of * @ses to ensure that any DFS root session attached to it (@ses->dfs_root_ses) * will also get its reference count incremented. * - * cifs_put_smb_ses() will put both references, so call it when you're done. + * cifs_put_smb_ses() will put all references, so call it when you're done. */ static inline void cifs_smb_ses_inc_refcount(struct cifs_ses *ses) { lockdep_assert_held(&cifs_tcp_ses_lock); - ses->ses_count++; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; + for (; ses; ses = ses->dfs_root_ses) + ses->ses_count++; } static inline bool dfs_src_pathname_equal(const char *s1, const char *s2) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 5aee55551573..23b5709ddc31 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -5854,10 +5854,8 @@ SetEARetry: parm_data->list.EA_flags = 0; /* we checked above that name len is less than 255 */ parm_data->list.name_len = (__u8)name_len; - /* EA names are always ASCII */ - if (ea_name) - strncpy(parm_data->list.name, ea_name, name_len); - parm_data->list.name[name_len] = '\0'; + /* EA names are always ASCII and NUL-terminated */ + strscpy(parm_data->list.name, ea_name ?: "", name_len + 1); parm_data->list.value_len = cpu_to_le16(ea_value_len); /* caller ensures that ea_value_len is less than 64K but we need to ensure that it fits within the smb */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 9b85b5341822..85679ae106fd 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -175,6 +175,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { if (!ses->chans[i].server) @@ -232,7 +234,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { - /* check if iface is still active */ + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + continue; + } + spin_unlock(&ses->ses_lock); + spin_lock(&ses->chan_lock); if (cifs_ses_get_chan_index(ses, server) == CIFS_INVAL_CHAN_INDEX) { @@ -1860,6 +1868,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) ctx->sectype != ses->sectype) return 0; + if (ctx->dfs_root_ses != ses->dfs_root_ses) + return 0; + /* * If an existing session is limited to less channels than * requested, it should not be reused @@ -1963,31 +1974,6 @@ out: return rc; } -/** - * cifs_free_ipc - helper to release the session IPC tcon - * @ses: smb session to unmount the IPC from - * - * Needs to be called everytime a session is destroyed. - * - * On session close, the IPC is closed and the server must release all tcons of the session. - * No need to send a tree disconnect here. - * - * Besides, it will make the server to not close durable and resilient files on session close, as - * specified in MS-SMB2 3.3.5.6 Receiving an SMB2 LOGOFF Request. - */ -static int -cifs_free_ipc(struct cifs_ses *ses) -{ - struct cifs_tcon *tcon = ses->tcon_ipc; - - if (tcon == NULL) - return 0; - - tconInfoFree(tcon); - ses->tcon_ipc = NULL; - return 0; -} - static struct cifs_ses * cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { @@ -2019,48 +2005,52 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) void __cifs_put_smb_ses(struct cifs_ses *ses) { struct TCP_Server_Info *server = ses->server; + struct cifs_tcon *tcon; unsigned int xid; size_t i; + bool do_logoff; int rc; + spin_lock(&cifs_tcp_ses_lock); spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING) { + cifs_dbg(FYI, "%s: id=0x%llx ses_count=%d ses_status=%u ipc=%s\n", + __func__, ses->Suid, ses->ses_count, ses->ses_status, + ses->tcon_ipc ? ses->tcon_ipc->tree_name : "none"); + if (ses->ses_status == SES_EXITING || --ses->ses_count > 0) { spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } - spin_unlock(&ses->ses_lock); + /* ses_count can never go negative */ + WARN_ON(ses->ses_count < 0); - cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); - cifs_dbg(FYI, - "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->tree_name : "NONE"); + spin_lock(&ses->chan_lock); + cifs_chan_clear_need_reconnect(ses, server); + spin_unlock(&ses->chan_lock); - spin_lock(&cifs_tcp_ses_lock); - if (--ses->ses_count > 0) { - spin_unlock(&cifs_tcp_ses_lock); - return; - } - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_GOOD) - ses->ses_status = SES_EXITING; + do_logoff = ses->ses_status == SES_GOOD && server->ops->logoff; + ses->ses_status = SES_EXITING; + tcon = ses->tcon_ipc; + ses->tcon_ipc = NULL; spin_unlock(&ses->ses_lock); spin_unlock(&cifs_tcp_ses_lock); - /* ses_count can never go negative */ - WARN_ON(ses->ses_count < 0); - - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING && server->ops->logoff) { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); + /* + * On session close, the IPC is closed and the server must release all + * tcons of the session. No need to send a tree disconnect here. + * + * Besides, it will make the server to not close durable and resilient + * files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an + * SMB2 LOGOFF Request. + */ + tconInfoFree(tcon); + if (do_logoff) { xid = get_xid(); rc = server->ops->logoff(xid, ses); if (rc) cifs_server_dbg(VFS, "%s: Session Logoff failure rc=%d\n", __func__, rc); _free_xid(xid); - } else { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); } spin_lock(&cifs_tcp_ses_lock); @@ -2373,9 +2363,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) * need to lock before changing something in the session. */ spin_lock(&cifs_tcp_ses_lock); + if (ctx->dfs_root_ses) + cifs_smb_ses_inc_refcount(ctx->dfs_root_ses); ses->dfs_root_ses = ctx->dfs_root_ses; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -3326,6 +3316,9 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) cifs_put_smb_ses(mnt_ctx->ses); else if (mnt_ctx->server) cifs_put_tcp_session(mnt_ctx->server, 0); + mnt_ctx->ses = NULL; + mnt_ctx->tcon = NULL; + mnt_ctx->server = NULL; mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; free_xid(mnt_ctx->xid); } @@ -3604,8 +3597,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) bool isdfs; int rc; - INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list); - rc = dfs_mount_share(&mnt_ctx, &isdfs); if (rc) goto error; @@ -3636,7 +3627,6 @@ out: return rc; error: - dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list); cifs_mount_put_conns(&mnt_ctx); return rc; } @@ -3651,6 +3641,18 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; rc = cifs_mount_get_tcon(&mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx.server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx.ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx.tcon)) + rc = -ENOENT; + } if (rc) goto error; @@ -3988,13 +3990,14 @@ cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) } static struct cifs_tcon * -cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +__cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) { int rc; struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb); struct cifs_ses *ses; struct cifs_tcon *tcon = NULL; struct smb3_fs_context *ctx; + char *origin_fullpath = NULL; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (ctx == NULL) @@ -4018,6 +4021,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->sign = master_tcon->ses->sign; ctx->seal = master_tcon->seal; ctx->witness = master_tcon->use_witness; + ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; rc = cifs_set_vol_auth(ctx, master_tcon->ses); if (rc) { @@ -4037,12 +4041,39 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + spin_lock(&master_tcon->tc_lock); + if (master_tcon->origin_fullpath) { + spin_unlock(&master_tcon->tc_lock); + origin_fullpath = dfs_get_path(cifs_sb, cifs_sb->ctx->source); + if (IS_ERR(origin_fullpath)) { + tcon = ERR_CAST(origin_fullpath); + origin_fullpath = NULL; + cifs_put_smb_ses(ses); + goto out; + } + } else { + spin_unlock(&master_tcon->tc_lock); + } +#endif + tcon = cifs_get_tcon(ses, ctx); if (IS_ERR(tcon)) { cifs_put_smb_ses(ses); goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + if (origin_fullpath) { + spin_lock(&tcon->tc_lock); + tcon->origin_fullpath = origin_fullpath; + spin_unlock(&tcon->tc_lock); + origin_fullpath = NULL; + queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, + dfs_cache_get_ttl() * HZ); + } +#endif + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(ses)) reset_cifs_unix_caps(0, tcon, NULL, ctx); @@ -4051,11 +4082,23 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) out: kfree(ctx->username); kfree_sensitive(ctx->password); + kfree(origin_fullpath); kfree(ctx); return tcon; } +static struct cifs_tcon * +cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +{ + struct cifs_tcon *ret; + + cifs_mount_lock(); + ret = __cifs_construct_tcon(cifs_sb, fsuid); + cifs_mount_unlock(); + return ret; +} + struct cifs_tcon * cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) { diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 449c59830039..3ec965547e3d 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -66,33 +66,20 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) } /* - * Track individual DFS referral servers used by new DFS mount. - * - * On success, their lifetime will be shared by final tcon (dfs_ses_list). - * Otherwise, they will be put by dfs_put_root_smb_sessions() in cifs_mount(). + * Get an active reference of @ses so that next call to cifs_put_tcon() won't + * release it as any new DFS referrals must go through its IPC tcon. */ -static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) +static void add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - struct dfs_root_ses *root_ses; struct cifs_ses *ses = mnt_ctx->ses; if (ses) { - root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL); - if (!root_ses) - return -ENOMEM; - - INIT_LIST_HEAD(&root_ses->list); - spin_lock(&cifs_tcp_ses_lock); cifs_smb_ses_inc_refcount(ses); spin_unlock(&cifs_tcp_ses_lock); - root_ses->ses = ses; - list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list); } - /* Select new DFS referral server so that new referrals go through it */ ctx->dfs_root_ses = ses; - return 0; } static inline int parse_dfs_target(struct smb3_fs_context *ctx, @@ -185,11 +172,8 @@ again: continue; } - if (is_refsrv) { - rc = add_root_smb_session(mnt_ctx); - if (rc) - goto out; - } + if (is_refsrv) + add_root_smb_session(mnt_ctx); rc = ref_walk_advance(rw); if (!rc) { @@ -232,6 +216,7 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_tcon *tcon; char *origin_fullpath; + bool new_tcon = true; int rc; origin_fullpath = dfs_get_path(cifs_sb, ctx->source); @@ -239,6 +224,18 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) return PTR_ERR(origin_fullpath); rc = dfs_referral_walk(mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx->server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx->ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx->tcon)) + rc = -ENOENT; + } if (rc) goto out; @@ -247,15 +244,14 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) if (!tcon->origin_fullpath) { tcon->origin_fullpath = origin_fullpath; origin_fullpath = NULL; + } else { + new_tcon = false; } spin_unlock(&tcon->tc_lock); - if (list_empty(&tcon->dfs_ses_list)) { - list_replace_init(&mnt_ctx->dfs_ses_list, &tcon->dfs_ses_list); + if (new_tcon) { queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, dfs_cache_get_ttl() * HZ); - } else { - dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list); } out: @@ -298,7 +294,6 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) if (rc) return rc; - ctx->dfs_root_ses = mnt_ctx->ses; /* * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally * try to get an DFS referral (even cached) to determine whether it is an DFS mount. @@ -324,7 +319,9 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) *isdfs = true; add_root_smb_session(mnt_ctx); - return __dfs_mount_share(mnt_ctx); + rc = __dfs_mount_share(mnt_ctx); + dfs_put_root_smb_sessions(mnt_ctx); + return rc; } /* Update dfs referral path of superblock */ diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h index 875ab7ae57fc..e5c4dcf83750 100644 --- a/fs/smb/client/dfs.h +++ b/fs/smb/client/dfs.h @@ -7,7 +7,9 @@ #define _CIFS_DFS_H #include "cifsglob.h" +#include "cifsproto.h" #include "fs_context.h" +#include "dfs_cache.h" #include "cifs_unicode.h" #include <linux/namei.h> @@ -114,11 +116,6 @@ static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw) ref_walk_tit(rw)); } -struct dfs_root_ses { - struct list_head list; - struct cifs_ses *ses; -}; - int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs); @@ -133,20 +130,32 @@ static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *p { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses; - return dfs_cache_find(mnt_ctx->xid, ctx->dfs_root_ses, cifs_sb->local_nls, + return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls, cifs_remap(cifs_sb), path, ref, tl); } -static inline void dfs_put_root_smb_sessions(struct list_head *head) +/* + * cifs_get_smb_ses() already guarantees an active reference of + * @ses->dfs_root_ses when a new session is created, so we need to put extra + * references of all DFS root sessions that were used across the mount process + * in dfs_mount_share(). + */ +static inline void dfs_put_root_smb_sessions(struct cifs_mount_ctx *mnt_ctx) { - struct dfs_root_ses *root, *tmp; + const struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct cifs_ses *ses = ctx->dfs_root_ses; + struct cifs_ses *cur; + + if (!ses) + return; - list_for_each_entry_safe(root, tmp, head, list) { - list_del_init(&root->list); - cifs_put_smb_ses(root->ses); - kfree(root); + for (cur = ses; cur; cur = cur->dfs_root_ses) { + if (cur->dfs_root_ses) + cifs_put_smb_ses(cur->dfs_root_ses); } + cifs_put_smb_ses(ses); } #endif /* _CIFS_DFS_H */ diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 508d831fabe3..11c8efecf7aa 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1172,8 +1172,8 @@ static bool is_ses_good(struct cifs_ses *ses) return ret; } -/* Refresh dfs referral of tcon and mark it for reconnect if needed */ -static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_refresh) +/* Refresh dfs referral of @ses and mark it for reconnect if needed */ +static void __refresh_ses_referral(struct cifs_ses *ses, bool force_refresh) { struct TCP_Server_Info *server = ses->server; DFS_CACHE_TGT_LIST(old_tl); @@ -1181,10 +1181,21 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref bool needs_refresh = false; struct cache_entry *ce; unsigned int xid; + char *path = NULL; int rc = 0; xid = get_xid(); + mutex_lock(&server->refpath_lock); + if (server->leaf_fullpath) { + path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC); + if (!path) + rc = -ENOMEM; + } + mutex_unlock(&server->refpath_lock); + if (!path) + goto out; + down_read(&htable_rw_lock); ce = lookup_cache_entry(path); needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce); @@ -1218,19 +1229,17 @@ out: free_xid(xid); dfs_cache_free_tgts(&old_tl); dfs_cache_free_tgts(&new_tl); - return rc; + kfree(path); } -static int refresh_tcon(struct cifs_tcon *tcon, bool force_refresh) +static inline void refresh_ses_referral(struct cifs_ses *ses) { - struct TCP_Server_Info *server = tcon->ses->server; - struct cifs_ses *ses = tcon->ses; + __refresh_ses_referral(ses, false); +} - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, force_refresh); - mutex_unlock(&server->refpath_lock); - return 0; +static inline void force_refresh_ses_referral(struct cifs_ses *ses) +{ + __refresh_ses_referral(ses, true); } /** @@ -1271,34 +1280,20 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) */ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - return refresh_tcon(tcon, true); + force_refresh_ses_referral(tcon->ses); + return 0; } /* Refresh all DFS referrals related to DFS tcon */ void dfs_cache_refresh(struct work_struct *work) { - struct TCP_Server_Info *server; - struct dfs_root_ses *rses; struct cifs_tcon *tcon; struct cifs_ses *ses; tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work); - ses = tcon->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - - list_for_each_entry(rses, &tcon->dfs_ses_list, list) { - ses = rses->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - } + for (ses = tcon->ses; ses; ses = ses->dfs_root_ses) + refresh_ses_referral(ses); queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, atomic_read(&dfs_cache_ttl) * HZ); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index d11dc3aa458b..864b194dbaa0 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -189,6 +189,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; *oplock = 0; if (tcon->ses->server->oplocks) @@ -200,6 +201,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned return PTR_ERR(full_path); } + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -276,6 +281,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned desired_access |= GENERIC_READ; /* is this too little? */ if (OPEN_FMODE(oflags) & FMODE_WRITE) desired_access |= GENERIC_WRITE; + if (rdwr_for_fscache == 1) + desired_access |= GENERIC_READ; disposition = FILE_OVERWRITE_IF; if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) @@ -304,6 +311,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -317,8 +325,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) { cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc); + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access &= ~GENERIC_READ; + rdwr_for_fscache = 2; + goto retry_open; + } goto out; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 16aadce492b2..9be37d0fe724 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -206,12 +206,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) */ } -static inline int cifs_convert_flags(unsigned int flags) +static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache) { if ((flags & O_ACCMODE) == O_RDONLY) return GENERIC_READ; else if ((flags & O_ACCMODE) == O_WRONLY) - return GENERIC_WRITE; + return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE; else if ((flags & O_ACCMODE) == O_RDWR) { /* GENERIC_ALL is too much permission to request can cause unnecessary access denied on create */ @@ -348,11 +348,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ int create_options = CREATE_NOT_DIR; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; if (!server->ops->open) return -ENOSYS; - desired_access = cifs_convert_flags(f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache); /********************************************************************* * open flag mapping table: @@ -389,6 +394,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ if (f_flags & O_DIRECT) create_options |= CREATE_NO_BUFFER; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -400,8 +406,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ }; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) + if (rc) { + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } return rc; + } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -445,6 +459,7 @@ cifs_down_write(struct rw_semaphore *sem) } static void cifsFileInfo_put_work(struct work_struct *work); +void serverclose_work(struct work_struct *work); struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock, @@ -491,6 +506,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); INIT_WORK(&cfile->put, cifsFileInfo_put_work); + INIT_WORK(&cfile->serverclose, serverclose_work); INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close); mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); @@ -582,6 +598,40 @@ static void cifsFileInfo_put_work(struct work_struct *work) cifsFileInfo_put_final(cifs_file); } +void serverclose_work(struct work_struct *work) +{ + struct cifsFileInfo *cifs_file = container_of(work, + struct cifsFileInfo, serverclose); + + struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); + + struct TCP_Server_Info *server = tcon->ses->server; + int rc = 0; + int retries = 0; + int MAX_RETRIES = 4; + + do { + if (server->ops->close_getattr) + rc = server->ops->close_getattr(0, tcon, cifs_file); + else if (server->ops->close) + rc = server->ops->close(0, tcon, &cifs_file->fid); + + if (rc == -EBUSY || rc == -EAGAIN) { + retries++; + msleep(250); + } + } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES) + ); + + if (retries == MAX_RETRIES) + pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES); + + if (cifs_file->offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); +} + /** * cifsFileInfo_put - release a reference of file priv data * @@ -622,10 +672,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; + bool serverclose_offloaded = false; spin_lock(&tcon->open_file_lock); spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); + + cifs_file->offload = offload; if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); spin_unlock(&cifsi->open_file_lock); @@ -667,13 +720,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; + int rc = 0; xid = get_xid(); if (server->ops->close_getattr) - server->ops->close_getattr(xid, tcon, cifs_file); + rc = server->ops->close_getattr(xid, tcon, cifs_file); else if (server->ops->close) - server->ops->close(xid, tcon, &cifs_file->fid); + rc = server->ops->close(xid, tcon, &cifs_file->fid); _free_xid(xid); + + if (rc == -EBUSY || rc == -EAGAIN) { + // Server close failed, hence offloading it as an async op + queue_work(serverclose_wq, &cifs_file->serverclose); + serverclose_offloaded = true; + } } if (oplock_break_cancelled) @@ -681,10 +741,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, cifs_del_pending_open(&open); - if (offload) - queue_work(fileinfo_put_wq, &cifs_file->put); - else - cifsFileInfo_put_final(cifs_file); + // if serverclose has been offloaded to wq (on failure), it will + // handle offloading put as well. If serverclose not offloaded, + // we need to handle offloading put here. + if (!serverclose_offloaded) { + if (offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); + } } int cifs_open(struct inode *inode, struct file *file) @@ -834,11 +899,11 @@ int cifs_open(struct inode *inode, struct file *file) use_cache: fscache_use_cookie(cifs_inode_cookie(file_inode(file)), file->f_mode & FMODE_WRITE); - if (file->f_flags & O_DIRECT && - (!((file->f_flags & O_ACCMODE) != O_RDONLY) || - file->f_flags & O_APPEND)) - cifs_invalidate_cache(file_inode(file), - FSCACHE_INVAL_DIO_WRITE); + if (!(file->f_flags & O_DIRECT)) + goto out; + if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY) + goto out; + cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE); out: free_dentry_path(page); @@ -903,6 +968,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int disposition = FILE_OPEN; int create_options = CREATE_NOT_DIR; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; xid = get_xid(); mutex_lock(&cfile->fh_mutex); @@ -966,7 +1032,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - desired_access = cifs_convert_flags(cfile->f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (cfile->f_flags & O_SYNC) @@ -978,6 +1048,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -1003,6 +1074,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) /* indicate that we need to relock the file */ oparms.reconnect = true; } + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(cfile->f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } if (rc) { mutex_unlock(&cfile->fh_mutex); @@ -1011,6 +1087,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) goto reopen_error_exit; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY reopen_success: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index bdcbe6ff2739..b7bfe705b2c4 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -37,7 +37,7 @@ #include "rfc1002pdu.h" #include "fs_context.h" -static DEFINE_MUTEX(cifs_mount_mutex); +DEFINE_MUTEX(cifs_mount_mutex); static const match_table_t cifs_smb_version_tokens = { { Smb_1, SMB1_VERSION_STRING }, @@ -783,9 +783,9 @@ static int smb3_get_tree(struct fs_context *fc) if (err) return err; - mutex_lock(&cifs_mount_mutex); + cifs_mount_lock(); ret = smb3_get_tree_common(fc); - mutex_unlock(&cifs_mount_mutex); + cifs_mount_unlock(); return ret; } diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 7863f2248c4d..8a35645e0b65 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -304,4 +304,16 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); #define MAX_CACHED_FIDS 16 extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); +extern struct mutex cifs_mount_mutex; + +static inline void cifs_mount_lock(void) +{ + mutex_lock(&cifs_mount_mutex); +} + +static inline void cifs_mount_unlock(void) +{ + mutex_unlock(&cifs_mount_mutex); +} + #endif diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index a3d73720914f..1f2ea9f5cc9a 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -109,6 +109,11 @@ static inline void cifs_readahead_to_fscache(struct inode *inode, __cifs_readahead_to_fscache(inode, pos, len); } +static inline bool cifs_fscache_enabled(struct inode *inode) +{ + return fscache_cookie_enabled(cifs_inode_cookie(inode)); +} + #else /* CONFIG_CIFS_FSCACHE */ static inline void cifs_fscache_fill_coherency(struct inode *inode, @@ -124,6 +129,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {} static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {} static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {} +static inline bool cifs_fscache_enabled(struct inode *inode) { return false; } static inline int cifs_fscache_query_occupancy(struct inode *inode, pgoff_t first, unsigned int nr_pages, diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index c012dfdba80d..855ac5a62edf 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -247,7 +247,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { - if (ses_it->Suid == out.session_id) { + spin_lock(&ses_it->ses_lock); + if (ses_it->ses_status != SES_EXITING && + ses_it->Suid == out.session_id) { ses = ses_it; /* * since we are using the session outside the crit @@ -255,9 +257,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug * so increment its refcount */ cifs_smb_ses_inc_refcount(ses); + spin_unlock(&ses_it->ses_lock); found = true; goto search_end; } + spin_unlock(&ses_it->ses_lock); } } search_end: diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index c3771fc81328..33ac4f8f5050 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -138,9 +138,6 @@ tcon_info_alloc(bool dir_leases_enabled) atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); ret_buf->stats_from_time = ktime_get_real_seconds(); -#ifdef CONFIG_CIFS_DFS_UPCALL - INIT_LIST_HEAD(&ret_buf->dfs_ses_list); -#endif return ret_buf; } @@ -156,9 +153,6 @@ tconInfoFree(struct cifs_tcon *tcon) atomic_dec(&tconInfoAllocCount); kfree(tcon->nativeFileSystem); kfree_sensitive(tcon->password); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_put_root_smb_sessions(&tcon->dfs_ses_list); -#endif kfree(tcon->origin_fullpath); kfree(tcon); } @@ -487,6 +481,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index a9eaba8083b0..212ec6f66ec6 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -753,11 +753,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } -static void +static int cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - CIFSSMBClose(xid, tcon, fid->netfid); + return CIFSSMBClose(xid, tcon, fid->netfid); } static int diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 82b84a4941dd..cc72be5a93a9 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); cifs_stats_inc( @@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 2ed456948f34..b156eefa75d7 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1412,14 +1412,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) memcpy(cfile->fid.create_guid, fid->create_guid, 16); } -static void +static int smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); + return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } -static void +static int smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile) { @@ -1430,7 +1430,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, &file_inf); if (rc) - return; + return rc; inode = d_inode(cfile->dentry); @@ -1459,6 +1459,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* End of file and Attributes should not have to be updated on close */ spin_unlock(&inode->i_lock); + return rc; } static int @@ -2480,6 +2481,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); @@ -3913,7 +3916,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, strcat(message, "W"); } if (!new_oplock) - strncpy(message, "None", sizeof(message)); + strscpy(message, "None"); cinode->oplock = new_oplock; cifs_dbg(FYI, "%s Lease granted on inode %p\n", message, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 3ea688558e6c..c0c4933af5fc 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3628,9 +3628,9 @@ replay_again: memcpy(&pbuf->network_open_info, &rsp->network_open_info, sizeof(pbuf->network_open_info)); + atomic_dec(&tcon->num_remote_opens); } - atomic_dec(&tcon->num_remote_opens); close_exit: SMB2_close_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 5a3ca62d2f07..1d6e54f7879e 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -659,7 +659,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) } spin_unlock(&server->srv_lock); if (!is_binding && !server->session_estab) { - strncpy(shdr->Signature, "BSRSPYL", 8); + strscpy(shdr->Signature, "BSRSPYL"); return 0; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ea48774f6b76..d55b42b2480d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1301,8 +1301,19 @@ xfs_link( */ if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) && tdp->i_projid != sip->i_projid)) { - error = -EXDEV; - goto error_return; + /* + * Project quota setup skips special files which can + * leave inodes in a PROJINHERIT directory without a + * project ID set. We need to allow links to be made + * to these "project-less" inodes because userspace + * expects them to succeed after project ID setup, + * but everything else should be rejected. + */ + if (!special_file(VFS_I(sip)->i_mode) || + sip->i_projid != 0) { + error = -EXDEV; + goto error_return; + } } if (!resblks) { diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index 43282e22ebe1..701974639ff2 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -39,6 +39,14 @@ struct cpu_hw_events { DECLARE_BITMAP(used_hw_ctrs, RISCV_MAX_COUNTERS); /* currently enabled firmware counters */ DECLARE_BITMAP(used_fw_ctrs, RISCV_MAX_COUNTERS); + /* The virtual address of the shared memory where counter snapshot will be taken */ + void *snapshot_addr; + /* The physical address of the shared memory where counter snapshot will be taken */ + phys_addr_t snapshot_addr_phys; + /* Boolean flag to indicate setup is already done */ + bool snapshot_set_done; + /* A shadow copy of the counter values to avoid clobbering during multiple SBI calls */ + u64 snapshot_cval_shcopy[RISCV_MAX_COUNTERS]; }; struct riscv_pmu { diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index c6540ceea143..0982d1d52b24 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -22,7 +22,7 @@ * * @read: returns the current cycle value * @mask: bitmask for two's complement - * subtraction of non 64 bit counters, + * subtraction of non-64-bit counters, * see CYCLECOUNTER_MASK() helper macro * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) @@ -35,7 +35,7 @@ struct cyclecounter { }; /** - * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds + * struct timecounter - layer above a &struct cyclecounter which counts nanoseconds * Contains the state needed by timecounter_read() to detect * cycle counter wrap around. Initialize with * timecounter_init(). Also used to convert cycle counts into the @@ -66,6 +66,8 @@ struct timecounter { * @cycles: Cycles * @mask: bit mask for maintaining the 'frac' field * @frac: pointer to storage for the fractional nanoseconds. + * + * Returns: cycle counter cycles converted to nanoseconds */ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, u64 cycles, u64 mask, u64 *frac) @@ -79,6 +81,7 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, /** * timecounter_adjtime - Shifts the time of the clock. + * @tc: The &struct timecounter to adjust * @delta: Desired change in nanoseconds. */ static inline void timecounter_adjtime(struct timecounter *tc, s64 delta) @@ -107,6 +110,8 @@ extern void timecounter_init(struct timecounter *tc, * * In other words, keeps track of time since the same epoch as * the function which generated the initial time stamp. + * + * Returns: nanoseconds since the initial time stamp */ extern u64 timecounter_read(struct timecounter *tc); @@ -123,6 +128,8 @@ extern u64 timecounter_read(struct timecounter *tc); * * This allows conversion of cycle counter values which were generated * in the past. + * + * Returns: cycle counter converted to nanoseconds since the initial time stamp */ extern u64 timecounter_cyc2time(const struct timecounter *tc, u64 cycle_tstamp); diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7e50cbd97f86..0ea7823b7f31 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -22,14 +22,14 @@ extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* - * ktime_get() family: read the current time in a multitude of ways, + * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * - * To get the time in a different format, use the ones wit + * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. @@ -74,6 +74,8 @@ extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format + * + * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { @@ -86,10 +88,12 @@ static inline ktime_t ktime_get_coarse_real(void) } /** - * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. + * + * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { @@ -102,7 +106,9 @@ static inline ktime_t ktime_get_coarse_boottime(void) } /** - * ktime_get_clocktai - Returns the TAI time of day in ktime_t format + * ktime_get_clocktai - Get the TAI time of day in ktime_t format + * + * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { @@ -144,32 +150,60 @@ static inline u64 ktime_get_coarse_clocktai_ns(void) /** * ktime_mono_to_real - Convert monotonic time to clock realtime + * @mono: monotonic time to convert + * + * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } +/** + * ktime_get_ns - Get the current time in nanoseconds + * + * Returns: current time converted to nanoseconds + */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } +/** + * ktime_get_real_ns - Get the current real/wall time in nanoseconds + * + * Returns: current real time converted to nanoseconds + */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } +/** + * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds + * + * Returns: current boottime converted to nanoseconds + */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } +/** + * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds + * + * Returns: current TAI time converted to nanoseconds + */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } +/** + * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds + * + * Returns: current raw monotonic time converted to nanoseconds + */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); @@ -224,8 +258,8 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/* - * struct ktime_timestanps - Simultaneous mono/boot/real timestamps +/** + * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp @@ -242,7 +276,8 @@ struct ktime_timestamps { * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time - * @clock_was_set_seq: The sequence number of clock was set events + * @cs_id: Clocksource ID + * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { diff --git a/include/linux/timer.h b/include/linux/timer.h index 14a633ba61d6..e67ecd1cbc97 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -22,7 +22,7 @@ #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif -/** +/* * @TIMER_DEFERRABLE: A deferrable timer will work normally when the * system is busy, but will not cause a CPU to come out of idle just * to service it; instead, the timer will be serviced when the CPU @@ -140,7 +140,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { } * or not. Callers must ensure serialization wrt. other operations done * to this timer, eg. interrupt contexts, or other CPUs on SMP. * - * return value: 1 if the timer is pending, 0 if not. + * Returns: 1 if the timer is pending, 0 if not. */ static inline int timer_pending(const struct timer_list * timer) { @@ -175,6 +175,10 @@ extern int timer_shutdown(struct timer_list *timer); * See timer_delete_sync() for detailed explanation. * * Do not use in new code. Use timer_delete_sync() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer_sync(struct timer_list *timer) { @@ -188,6 +192,10 @@ static inline int del_timer_sync(struct timer_list *timer) * See timer_delete() for detailed explanation. * * Do not use in new code. Use timer_delete() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer(struct timer_list *timer) { diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index 5d5c0b8efff2..c71ddb6d4691 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -19,12 +19,6 @@ #include <vdso/time32.h> #include <vdso/time64.h> -#ifdef CONFIG_ARM64 -#include <asm/page-def.h> -#else -#include <asm/page.h> -#endif - #ifdef CONFIG_ARCH_HAS_VDSO_DATA #include <asm/vdso/data.h> #else @@ -132,7 +126,7 @@ extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden */ union vdso_data_store { struct vdso_data data[CS_BASES]; - u8 page[PAGE_SIZE]; + u8 page[1U << CONFIG_PAGE_SHIFT]; }; /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 269e21590df5..1331216a9cae 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -697,6 +697,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu) /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted + * @now: current ktime_t * * Called from interrupt entry when the CPU was idle * @@ -794,7 +795,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * This function returns -1 if NOHZ is not enabled. + * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { @@ -820,7 +821,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * - * This function returns -1 if NOHZ is not enabled. + * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { @@ -1287,6 +1288,8 @@ void tick_nohz_irq_exit(void) /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run + * + * Return: %true if the tick handler has run, otherwise %false */ bool tick_nohz_idle_got_tick(void) { @@ -1305,6 +1308,8 @@ bool tick_nohz_idle_got_tick(void) * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled + * + * Return: the next expiration time */ ktime_t tick_nohz_get_next_hrtimer(void) { @@ -1320,6 +1325,8 @@ ktime_t tick_nohz_get_next_hrtimer(void) * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. + * + * Return: the expected length of the current sleep */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { @@ -1357,8 +1364,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. + * @cpu: target CPU number * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for @cpu */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { @@ -1371,6 +1381,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. + * + * Return: the current idle calls counter value for the current CPU */ unsigned long tick_nohz_get_idle_calls(void) { @@ -1559,7 +1571,7 @@ early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer - * @mode: tick_nohz_mode to setup for + * @hrtimer: whether to use the hrtimer or not */ void tick_setup_sched_timer(bool hrtimer) { diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index e11c4dc65bcb..b4a7822f495d 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -46,8 +46,8 @@ struct tick_device { * @next_tick: Next tick to be fired when in dynticks mode. * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_waketime: Time when the idle was interrupted + * @idle_sleeptime_seq: sequence counter for data consistency * @idle_entrytime: Time when the idle call was entered - * @nohz_mode: Mode - one state of tick_nohz_mode * @last_jiffies: Base jiffies snapshot when next event was last computed * @timer_expires_base: Base time clock monotonic for @timer_expires * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index dee29f1f5b75..3baf2fbe6848 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -64,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of - * LVL_SIZE buckets. Each level is driven by its own clock and therefor each + * LVL_SIZE buckets. Each level is driven by its own clock and therefore each * level has a different granularity. * - * The level granularity is: LVL_CLK_DIV ^ lvl + * The level granularity is: LVL_CLK_DIV ^ level * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and - * therefor the granularity becomes. + * therefore the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading @@ -207,7 +207,7 @@ EXPORT_SYMBOL(jiffies_64); * struct timer_base - Per CPU timer base (number of base depends on config) * @lock: Lock protecting the timer_base * @running_timer: When expiring timers, the lock is dropped. To make - * sure not to race agains deleting/modifying a + * sure not to race against deleting/modifying a * currently running timer, the pointer is set to the * timer, which expires at the moment. If no timer is * running, the pointer is NULL. @@ -737,7 +737,7 @@ static bool timer_is_static_object(void *addr) } /* - * fixup_init is called when: + * timer_fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) @@ -761,7 +761,7 @@ static void stub_timer(struct timer_list *unused) } /* - * fixup_activate is called when: + * timer_fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ @@ -783,7 +783,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) } /* - * fixup_free is called when: + * timer_fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) @@ -801,7 +801,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state) } /* - * fixup_assert_init is called when: + * timer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) @@ -914,7 +914,7 @@ static void do_init_timer(struct timer_list *timer, * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * - * init_timer_key() must be done to a timer prior calling *any* of the + * init_timer_key() must be done to a timer prior to calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, @@ -1417,7 +1417,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown) * If @shutdown is set then the lock has to be taken whether the * timer is pending or not to protect against a concurrent rearm * which might hit between the lockless pending check and the lock - * aquisition. By taking the lock it is ensured that such a newly + * acquisition. By taking the lock it is ensured that such a newly * enqueued timer is dequeued and cannot end up with * timer->function == NULL in the expiry code. * @@ -2306,7 +2306,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, /* * When timer base is not set idle, undo the effect of - * tmigr_cpu_deactivate() to prevent inconsitent states - active + * tmigr_cpu_deactivate() to prevent inconsistent states - active * timer base but inactive timer migration hierarchy. * * When timer base was already marked idle, nothing will be diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c63a0afdcebe..ccba875d2234 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -751,6 +751,33 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, first_childevt = evt = data->evt; + /* + * Walking the hierarchy is required in any case when a + * remote expiry was done before. This ensures to not lose + * already queued events in non active groups (see section + * "Required event and timerqueue update after a remote + * expiry" in the documentation at the top). + * + * The two call sites which are executed without a remote expiry + * before, are not prevented from propagating changes through + * the hierarchy by the return: + * - When entering this path by tmigr_new_timer(), @evt->ignore + * is never set. + * - tmigr_inactive_up() takes care of the propagation by + * itself and ignores the return value. But an immediate + * return is possible if there is a parent, sparing group + * locking at this level, because the upper walking call to + * the parent will take care about removing this event from + * within the group and update next_expiry accordingly. + * + * However if there is no parent, ie: the hierarchy has only a + * single level so @group is the top level group, make sure the + * first event information of the group is updated properly and + * also handled properly, so skip this fast return path. + */ + if (evt->ignore && !remote && group->parent) + return true; + raw_spin_lock(&group->lock); childstate.state = 0; @@ -762,8 +789,11 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, * queue when the expiry time changed only or when it could be ignored. */ if (timerqueue_node_queued(&evt->nextevt)) { - if ((evt->nextevt.expires == nextexp) && !evt->ignore) + if ((evt->nextevt.expires == nextexp) && !evt->ignore) { + /* Make sure not to miss a new CPU event with the same expiry */ + evt->cpu = first_childevt->cpu; goto check_toplvl; + } if (!timerqueue_del(&group->events, &evt->nextevt)) WRITE_ONCE(group->next_expiry, KTIME_MAX); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 545017a3daa4..6b3f01beb294 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1206,15 +1206,6 @@ err_noclose: * MSG_SPLICE_PAGES is used exclusively to reduce the number of * copy operations in this path. Therefore the caller must ensure * that the pages backing @xdr are unchanging. - * - * Note that the send is non-blocking. The caller has incremented - * the reference count on each page backing the RPC message, and - * the network layer will "put" these pages when transmission is - * complete. - * - * This is safe for our RPC services because the memory backing - * the head and tail components is never kmalloc'd. These always - * come from pages in the svc_rqst::rq_pages array. */ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, rpc_fraghdr marker, unsigned int *sentp) @@ -1244,6 +1235,7 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, 1 + count, sizeof(marker) + rqstp->rq_res.len); ret = sock_sendmsg(svsk->sk_sock, &msg); + page_frag_free(buf); if (ret < 0) return ret; *sentp += ret; diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 871e2de3eb05..266c0fe85fef 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -190,6 +190,8 @@ TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test +TEST_GEN_PROGS_riscv += riscv/ebreak_test TEST_GEN_PROGS_riscv += arch_timer TEST_GEN_PROGS_riscv += demand_paging_test TEST_GEN_PROGS_riscv += dirty_log_test diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index ce473fe251dd..5f389166338c 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -50,6 +50,16 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext); +static inline bool __vcpu_has_isa_ext(struct kvm_vcpu *vcpu, uint64_t 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) +{ + return __vcpu_has_ext(vcpu, RISCV_SBI_EXT_REG(sbi_ext)); +} + struct ex_regs { unsigned long ra; unsigned long sp; @@ -154,45 +164,6 @@ void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handle #define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE #define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT -/* SBI return error codes */ -#define SBI_SUCCESS 0 -#define SBI_ERR_FAILURE -1 -#define SBI_ERR_NOT_SUPPORTED -2 -#define SBI_ERR_INVALID_PARAM -3 -#define SBI_ERR_DENIED -4 -#define SBI_ERR_INVALID_ADDRESS -5 -#define SBI_ERR_ALREADY_AVAILABLE -6 -#define SBI_ERR_ALREADY_STARTED -7 -#define SBI_ERR_ALREADY_STOPPED -8 - -#define SBI_EXT_EXPERIMENTAL_START 0x08000000 -#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF - -#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END -#define KVM_RISCV_SELFTESTS_SBI_UCALL 0 -#define KVM_RISCV_SELFTESTS_SBI_UNEXP 1 - -enum sbi_ext_id { - SBI_EXT_BASE = 0x10, - SBI_EXT_STA = 0x535441, -}; - -enum sbi_ext_base_fid { - SBI_EXT_BASE_PROBE_EXT = 3, -}; - -struct sbiret { - long error; - long value; -}; - -struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, - unsigned long arg1, unsigned long arg2, - unsigned long arg3, unsigned long arg4, - unsigned long arg5); - -bool guest_sbi_probe_extension(int extid, long *out_val); - static inline void local_irq_enable(void) { csr_set(CSR_SSTATUS, SR_SIE); diff --git a/tools/testing/selftests/kvm/include/riscv/sbi.h b/tools/testing/selftests/kvm/include/riscv/sbi.h new file mode 100644 index 000000000000..046b432ae896 --- /dev/null +++ b/tools/testing/selftests/kvm/include/riscv/sbi.h @@ -0,0 +1,141 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * RISC-V SBI specific definitions + * + * Copyright (C) 2024 Rivos Inc. + */ + +#ifndef SELFTEST_KVM_SBI_H +#define SELFTEST_KVM_SBI_H + +/* SBI spec version fields */ +#define SBI_SPEC_VERSION_DEFAULT 0x1 +#define SBI_SPEC_VERSION_MAJOR_SHIFT 24 +#define SBI_SPEC_VERSION_MAJOR_MASK 0x7f +#define SBI_SPEC_VERSION_MINOR_MASK 0xffffff + +/* SBI return error codes */ +#define SBI_SUCCESS 0 +#define SBI_ERR_FAILURE -1 +#define SBI_ERR_NOT_SUPPORTED -2 +#define SBI_ERR_INVALID_PARAM -3 +#define SBI_ERR_DENIED -4 +#define SBI_ERR_INVALID_ADDRESS -5 +#define SBI_ERR_ALREADY_AVAILABLE -6 +#define SBI_ERR_ALREADY_STARTED -7 +#define SBI_ERR_ALREADY_STOPPED -8 + +#define SBI_EXT_EXPERIMENTAL_START 0x08000000 +#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF + +#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END +#define KVM_RISCV_SELFTESTS_SBI_UCALL 0 +#define KVM_RISCV_SELFTESTS_SBI_UNEXP 1 + +enum sbi_ext_id { + SBI_EXT_BASE = 0x10, + SBI_EXT_STA = 0x535441, + SBI_EXT_PMU = 0x504D55, +}; + +enum sbi_ext_base_fid { + SBI_EXT_BASE_GET_SPEC_VERSION = 0, + SBI_EXT_BASE_GET_IMP_ID, + SBI_EXT_BASE_GET_IMP_VERSION, + SBI_EXT_BASE_PROBE_EXT = 3, +}; +enum sbi_ext_pmu_fid { + SBI_EXT_PMU_NUM_COUNTERS = 0, + SBI_EXT_PMU_COUNTER_GET_INFO, + SBI_EXT_PMU_COUNTER_CFG_MATCH, + SBI_EXT_PMU_COUNTER_START, + SBI_EXT_PMU_COUNTER_STOP, + SBI_EXT_PMU_COUNTER_FW_READ, + SBI_EXT_PMU_COUNTER_FW_READ_HI, + SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, +}; + +union sbi_pmu_ctr_info { + unsigned long value; + struct { + unsigned long csr:12; + unsigned long width:6; +#if __riscv_xlen == 32 + unsigned long reserved:13; +#else + unsigned long reserved:45; +#endif + unsigned long type:1; + }; +}; + +struct riscv_pmu_snapshot_data { + u64 ctr_overflow_mask; + u64 ctr_values[64]; + u64 reserved[447]; +}; + +struct sbiret { + long error; + long value; +}; + +/** General pmu event codes specified in SBI PMU extension */ +enum sbi_pmu_hw_generic_events_t { + SBI_PMU_HW_NO_EVENT = 0, + SBI_PMU_HW_CPU_CYCLES = 1, + SBI_PMU_HW_INSTRUCTIONS = 2, + SBI_PMU_HW_CACHE_REFERENCES = 3, + SBI_PMU_HW_CACHE_MISSES = 4, + SBI_PMU_HW_BRANCH_INSTRUCTIONS = 5, + SBI_PMU_HW_BRANCH_MISSES = 6, + SBI_PMU_HW_BUS_CYCLES = 7, + SBI_PMU_HW_STALLED_CYCLES_FRONTEND = 8, + SBI_PMU_HW_STALLED_CYCLES_BACKEND = 9, + SBI_PMU_HW_REF_CPU_CYCLES = 10, + + SBI_PMU_HW_GENERAL_MAX, +}; + +/* SBI PMU counter types */ +enum sbi_pmu_ctr_type { + SBI_PMU_CTR_TYPE_HW = 0x0, + SBI_PMU_CTR_TYPE_FW, +}; + +/* Flags defined for config matching function */ +#define SBI_PMU_CFG_FLAG_SKIP_MATCH BIT(0) +#define SBI_PMU_CFG_FLAG_CLEAR_VALUE BIT(1) +#define SBI_PMU_CFG_FLAG_AUTO_START BIT(2) +#define SBI_PMU_CFG_FLAG_SET_VUINH BIT(3) +#define SBI_PMU_CFG_FLAG_SET_VSINH BIT(4) +#define SBI_PMU_CFG_FLAG_SET_UINH BIT(5) +#define SBI_PMU_CFG_FLAG_SET_SINH BIT(6) +#define SBI_PMU_CFG_FLAG_SET_MINH BIT(7) + +/* Flags defined for counter start function */ +#define SBI_PMU_START_FLAG_SET_INIT_VALUE BIT(0) +#define SBI_PMU_START_FLAG_INIT_SNAPSHOT BIT(1) + +/* Flags defined for counter stop function */ +#define SBI_PMU_STOP_FLAG_RESET BIT(0) +#define SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT BIT(1) + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5); + +bool guest_sbi_probe_extension(int extid, long *out_val); + +/* Make SBI version */ +static inline unsigned long sbi_mk_version(unsigned long major, + unsigned long minor) +{ + return ((major & SBI_SPEC_VERSION_MAJOR_MASK) << SBI_SPEC_VERSION_MAJOR_SHIFT) + | (minor & SBI_SPEC_VERSION_MINOR_MASK); +} + +unsigned long get_host_sbi_spec_version(void); + +#endif /* SELFTEST_KVM_SBI_H */ diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h index be46eb32ec27..a695ae36f3e0 100644 --- a/tools/testing/selftests/kvm/include/riscv/ucall.h +++ b/tools/testing/selftests/kvm/include/riscv/ucall.h @@ -3,6 +3,7 @@ #define SELFTEST_KVM_UCALL_H #include "processor.h" +#include "sbi.h" #define UCALL_EXIT_REASON KVM_EXIT_RISCV_SBI diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index e8211f5d6863..ccb35573749c 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -502,3 +502,15 @@ bool guest_sbi_probe_extension(int extid, long *out_val) return true; } + +unsigned long get_host_sbi_spec_version(void) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_GET_SPEC_VERSION, 0, + 0, 0, 0, 0, 0); + + GUEST_ASSERT(!ret.error); + + return ret.value; +} diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index 0f9cabd99fd4..735b78569021 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -85,7 +85,7 @@ struct kvm_vm *test_vm_create(void) int nr_vcpus = test_args.nr_vcpus; vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); - __TEST_REQUIRE(__vcpu_has_ext(vcpus[0], RISCV_ISA_EXT_REG(KVM_RISCV_ISA_EXT_SSTC)), + __TEST_REQUIRE(__vcpu_has_isa_ext(vcpus[0], KVM_RISCV_ISA_EXT_SSTC), "SSTC not available, skipping test\n"); vm_init_vector_tables(vm); diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c new file mode 100644 index 000000000000..823c132069b4 --- /dev/null +++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RISC-V KVM ebreak test. + * + * Copyright 2024 Beijing ESWIN Computing Technology Co., Ltd. + * + */ +#include "kvm_util.h" + +#define LABEL_ADDRESS(v) ((uint64_t)&(v)) + +extern unsigned char sw_bp_1, sw_bp_2; +static uint64_t sw_bp_addr; + +static void guest_code(void) +{ + asm volatile( + ".option push\n" + ".option norvc\n" + "sw_bp_1: ebreak\n" + "sw_bp_2: ebreak\n" + ".option pop\n" + ); + GUEST_ASSERT_EQ(READ_ONCE(sw_bp_addr), LABEL_ADDRESS(sw_bp_2)); + + GUEST_DONE(); +} + +static void guest_breakpoint_handler(struct ex_regs *regs) +{ + WRITE_ONCE(sw_bp_addr, regs->epc); + regs->epc += 4; +} + +int main(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + uint64_t pc; + struct kvm_guest_debug debug = { + .control = KVM_GUESTDBG_ENABLE, + }; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SET_GUEST_DEBUG)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + vm_init_vector_tables(vm); + vcpu_init_vector_tables(vcpu); + vm_install_exception_handler(vm, EXC_BREAKPOINT, + guest_breakpoint_handler); + + /* + * Enable the guest debug. + * ebreak should exit to the VMM with KVM_EXIT_DEBUG reason. + */ + vcpu_guest_debug_set(vcpu, &debug); + vcpu_run(vcpu); + + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG); + + vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &pc); + TEST_ASSERT_EQ(pc, LABEL_ADDRESS(sw_bp_1)); + + /* skip sw_bp_1 */ + vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), pc + 4); + + /* + * Disable all debug controls. + * Guest should handle the ebreak without exiting to the VMM. + */ + memset(&debug, 0, sizeof(debug)); + vcpu_guest_debug_set(vcpu, &debug); + + vcpu_run(vcpu); + + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index b882b7b9b785..222198dd6d04 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -43,6 +43,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_V: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSCOFPMF: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: @@ -408,6 +409,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(V), KVM_ISA_EXT_ARR(SMSTATEEN), KVM_ISA_EXT_ARR(SSAIA), + KVM_ISA_EXT_ARR(SSCOFPMF), KVM_ISA_EXT_ARR(SSTC), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), @@ -931,6 +933,7 @@ KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F); KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D); KVM_ISA_EXT_SIMPLE_CONFIG(h, H); KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN); +KVM_ISA_EXT_SIMPLE_CONFIG(sscofpmf, SSCOFPMF); KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC); KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); @@ -986,6 +989,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_fp_d, &config_h, &config_smstateen, + &config_sscofpmf, &config_sstc, &config_svinval, &config_svnapot, diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c new file mode 100644 index 000000000000..69bb94e6b227 --- /dev/null +++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c @@ -0,0 +1,681 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * sbi_pmu_test.c - Tests the riscv64 SBI PMU functionality. + * + * Copyright (c) 2024, Rivos Inc. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" +#include "sbi.h" +#include "arch_timer.h" + +/* Maximum counters(firmware + hardware) */ +#define RISCV_MAX_PMU_COUNTERS 64 +union sbi_pmu_ctr_info ctrinfo_arr[RISCV_MAX_PMU_COUNTERS]; + +/* Snapshot shared memory data */ +#define PMU_SNAPSHOT_GPA_BASE BIT(30) +static void *snapshot_gva; +static vm_paddr_t snapshot_gpa; + +static int vcpu_shared_irq_count; +static int counter_in_use; + +/* Cache the available counters in a bitmask */ +static unsigned long counter_mask_available; + +static bool illegal_handler_invoked; + +#define SBI_PMU_TEST_BASIC BIT(0) +#define SBI_PMU_TEST_EVENTS BIT(1) +#define SBI_PMU_TEST_SNAPSHOT BIT(2) +#define SBI_PMU_TEST_OVERFLOW BIT(3) + +static int disabled_tests; + +unsigned long pmu_csr_read_num(int csr_num) +{ +#define switchcase_csr_read(__csr_num, __val) {\ + case __csr_num: \ + __val = csr_read(__csr_num); \ + break; } +#define switchcase_csr_read_2(__csr_num, __val) {\ + switchcase_csr_read(__csr_num + 0, __val) \ + switchcase_csr_read(__csr_num + 1, __val)} +#define switchcase_csr_read_4(__csr_num, __val) {\ + switchcase_csr_read_2(__csr_num + 0, __val) \ + switchcase_csr_read_2(__csr_num + 2, __val)} +#define switchcase_csr_read_8(__csr_num, __val) {\ + switchcase_csr_read_4(__csr_num + 0, __val) \ + switchcase_csr_read_4(__csr_num + 4, __val)} +#define switchcase_csr_read_16(__csr_num, __val) {\ + switchcase_csr_read_8(__csr_num + 0, __val) \ + switchcase_csr_read_8(__csr_num + 8, __val)} +#define switchcase_csr_read_32(__csr_num, __val) {\ + switchcase_csr_read_16(__csr_num + 0, __val) \ + switchcase_csr_read_16(__csr_num + 16, __val)} + + unsigned long ret = 0; + + switch (csr_num) { + switchcase_csr_read_32(CSR_CYCLE, ret) + switchcase_csr_read_32(CSR_CYCLEH, ret) + default : + break; + } + + return ret; +#undef switchcase_csr_read_32 +#undef switchcase_csr_read_16 +#undef switchcase_csr_read_8 +#undef switchcase_csr_read_4 +#undef switchcase_csr_read_2 +#undef switchcase_csr_read +} + +static inline void dummy_func_loop(uint64_t iter) +{ + int i = 0; + + while (i < iter) { + asm volatile("nop"); + i++; + } +} + +static void start_counter(unsigned long counter, unsigned long start_flags, + unsigned long ival) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, counter, 1, start_flags, + ival, 0, 0); + __GUEST_ASSERT(ret.error == 0, "Unable to start counter %ld\n", counter); +} + +/* This should be invoked only for reset counter use case */ +static void stop_reset_counter(unsigned long counter, unsigned long stop_flags) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, counter, 1, + stop_flags | SBI_PMU_STOP_FLAG_RESET, 0, 0, 0); + __GUEST_ASSERT(ret.error == SBI_ERR_ALREADY_STOPPED, + "Unable to stop counter %ld\n", counter); +} + +static void stop_counter(unsigned long counter, unsigned long stop_flags) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, counter, 1, stop_flags, + 0, 0, 0); + __GUEST_ASSERT(ret.error == 0, "Unable to stop counter %ld error %ld\n", + counter, ret.error); +} + +static void guest_illegal_exception_handler(struct ex_regs *regs) +{ + __GUEST_ASSERT(regs->cause == EXC_INST_ILLEGAL, + "Unexpected exception handler %lx\n", regs->cause); + + illegal_handler_invoked = true; + /* skip the trapping instruction */ + regs->epc += 4; +} + +static void guest_irq_handler(struct ex_regs *regs) +{ + unsigned int irq_num = regs->cause & ~CAUSE_IRQ_FLAG; + struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva; + unsigned long overflown_mask; + unsigned long counter_val = 0; + + /* Validate that we are in the correct irq handler */ + GUEST_ASSERT_EQ(irq_num, IRQ_PMU_OVF); + + /* Stop all counters first to avoid further interrupts */ + stop_counter(counter_in_use, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT); + + csr_clear(CSR_SIP, BIT(IRQ_PMU_OVF)); + + overflown_mask = READ_ONCE(snapshot_data->ctr_overflow_mask); + GUEST_ASSERT(overflown_mask & 0x01); + + WRITE_ONCE(vcpu_shared_irq_count, vcpu_shared_irq_count+1); + + counter_val = READ_ONCE(snapshot_data->ctr_values[0]); + /* Now start the counter to mimick the real driver behavior */ + start_counter(counter_in_use, SBI_PMU_START_FLAG_SET_INIT_VALUE, counter_val); +} + +static unsigned long get_counter_index(unsigned long cbase, unsigned long cmask, + unsigned long cflags, + unsigned long event) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask, + cflags, event, 0, 0); + __GUEST_ASSERT(ret.error == 0, "config matching failed %ld\n", ret.error); + GUEST_ASSERT(ret.value < RISCV_MAX_PMU_COUNTERS); + GUEST_ASSERT(BIT(ret.value) & counter_mask_available); + + return ret.value; +} + +static unsigned long get_num_counters(void) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_NUM_COUNTERS, 0, 0, 0, 0, 0, 0); + + __GUEST_ASSERT(ret.error == 0, "Unable to retrieve number of counters from SBI PMU"); + __GUEST_ASSERT(ret.value < RISCV_MAX_PMU_COUNTERS, + "Invalid number of counters %ld\n", ret.value); + + return ret.value; +} + +static void update_counter_info(int num_counters) +{ + int i = 0; + struct sbiret ret; + + for (i = 0; i < num_counters; i++) { + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_GET_INFO, i, 0, 0, 0, 0, 0); + + /* There can be gaps in logical counter indicies*/ + if (ret.error) + continue; + GUEST_ASSERT_NE(ret.value, 0); + + ctrinfo_arr[i].value = ret.value; + counter_mask_available |= BIT(i); + } + + GUEST_ASSERT(counter_mask_available > 0); +} + +static unsigned long read_fw_counter(int idx, union sbi_pmu_ctr_info ctrinfo) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_FW_READ, idx, 0, 0, 0, 0, 0); + GUEST_ASSERT(ret.error == 0); + return ret.value; +} + +static unsigned long read_counter(int idx, union sbi_pmu_ctr_info ctrinfo) +{ + unsigned long counter_val = 0; + + __GUEST_ASSERT(ctrinfo.type < 2, "Invalid counter type %d", ctrinfo.type); + + if (ctrinfo.type == SBI_PMU_CTR_TYPE_HW) + counter_val = pmu_csr_read_num(ctrinfo.csr); + else if (ctrinfo.type == SBI_PMU_CTR_TYPE_FW) + counter_val = read_fw_counter(idx, ctrinfo); + + return counter_val; +} + +static inline void verify_sbi_requirement_assert(void) +{ + long out_val = 0; + bool probe; + + probe = guest_sbi_probe_extension(SBI_EXT_PMU, &out_val); + GUEST_ASSERT(probe && out_val == 1); + + if (get_host_sbi_spec_version() < sbi_mk_version(2, 0)) + __GUEST_ASSERT(0, "SBI implementation version doesn't support PMU Snapshot"); +} + +static void snapshot_set_shmem(vm_paddr_t gpa, unsigned long flags) +{ + unsigned long lo = (unsigned long)gpa; +#if __riscv_xlen == 32 + unsigned long hi = (unsigned long)(gpa >> 32); +#else + unsigned long hi = gpa == -1 ? -1 : 0; +#endif + struct sbiret ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, + lo, hi, flags, 0, 0, 0); + + GUEST_ASSERT(ret.value == 0 && ret.error == 0); +} + +static void test_pmu_event(unsigned long event) +{ + unsigned long counter; + unsigned long counter_value_pre, counter_value_post; + unsigned long counter_init_value = 100; + + counter = get_counter_index(0, counter_mask_available, 0, event); + counter_value_pre = read_counter(counter, ctrinfo_arr[counter]); + + /* Do not set the initial value */ + start_counter(counter, 0, 0); + dummy_func_loop(10000); + stop_counter(counter, 0); + + counter_value_post = read_counter(counter, ctrinfo_arr[counter]); + __GUEST_ASSERT(counter_value_post > counter_value_pre, + "Event update verification failed: post [%lx] pre [%lx]\n", + counter_value_post, counter_value_pre); + + /* + * We can't just update the counter without starting it. + * Do start/stop twice to simulate that by first initializing to a very + * high value and a low value after that. + */ + start_counter(counter, SBI_PMU_START_FLAG_SET_INIT_VALUE, ULONG_MAX/2); + stop_counter(counter, 0); + counter_value_pre = read_counter(counter, ctrinfo_arr[counter]); + + start_counter(counter, SBI_PMU_START_FLAG_SET_INIT_VALUE, counter_init_value); + stop_counter(counter, 0); + counter_value_post = read_counter(counter, ctrinfo_arr[counter]); + __GUEST_ASSERT(counter_value_pre > counter_value_post, + "Counter reinitialization verification failed : post [%lx] pre [%lx]\n", + counter_value_post, counter_value_pre); + + /* Now set the initial value and compare */ + start_counter(counter, SBI_PMU_START_FLAG_SET_INIT_VALUE, counter_init_value); + dummy_func_loop(10000); + stop_counter(counter, 0); + + counter_value_post = read_counter(counter, ctrinfo_arr[counter]); + __GUEST_ASSERT(counter_value_post > counter_init_value, + "Event update verification failed: post [%lx] pre [%lx]\n", + counter_value_post, counter_init_value); + + stop_reset_counter(counter, 0); +} + +static void test_pmu_event_snapshot(unsigned long event) +{ + unsigned long counter; + unsigned long counter_value_pre, counter_value_post; + unsigned long counter_init_value = 100; + struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva; + + counter = get_counter_index(0, counter_mask_available, 0, event); + counter_value_pre = read_counter(counter, ctrinfo_arr[counter]); + + /* Do not set the initial value */ + start_counter(counter, 0, 0); + dummy_func_loop(10000); + stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT); + + /* The counter value is updated w.r.t relative index of cbase */ + counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]); + __GUEST_ASSERT(counter_value_post > counter_value_pre, + "Event update verification failed: post [%lx] pre [%lx]\n", + counter_value_post, counter_value_pre); + + /* + * We can't just update the counter without starting it. + * Do start/stop twice to simulate that by first initializing to a very + * high value and a low value after that. + */ + WRITE_ONCE(snapshot_data->ctr_values[0], ULONG_MAX/2); + start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0); + stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT); + counter_value_pre = READ_ONCE(snapshot_data->ctr_values[0]); + + WRITE_ONCE(snapshot_data->ctr_values[0], counter_init_value); + start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0); + stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT); + counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]); + __GUEST_ASSERT(counter_value_pre > counter_value_post, + "Counter reinitialization verification failed : post [%lx] pre [%lx]\n", + counter_value_post, counter_value_pre); + + /* Now set the initial value and compare */ + WRITE_ONCE(snapshot_data->ctr_values[0], counter_init_value); + start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0); + dummy_func_loop(10000); + stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT); + + counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]); + __GUEST_ASSERT(counter_value_post > counter_init_value, + "Event update verification failed: post [%lx] pre [%lx]\n", + counter_value_post, counter_init_value); + + stop_reset_counter(counter, 0); +} + +static void test_pmu_event_overflow(unsigned long event) +{ + unsigned long counter; + unsigned long counter_value_post; + unsigned long counter_init_value = ULONG_MAX - 10000; + struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva; + + counter = get_counter_index(0, counter_mask_available, 0, event); + counter_in_use = counter; + + /* The counter value is updated w.r.t relative index of cbase passed to start/stop */ + WRITE_ONCE(snapshot_data->ctr_values[0], counter_init_value); + start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0); + dummy_func_loop(10000); + udelay(msecs_to_usecs(2000)); + /* irq handler should have stopped the counter */ + stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT); + + counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]); + /* The counter value after stopping should be less the init value due to overflow */ + __GUEST_ASSERT(counter_value_post < counter_init_value, + "counter_value_post %lx counter_init_value %lx for counter\n", + counter_value_post, counter_init_value); + + stop_reset_counter(counter, 0); +} + +static void test_invalid_event(void) +{ + struct sbiret ret; + unsigned long event = 0x1234; /* A random event */ + + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, 0, + counter_mask_available, 0, event, 0, 0); + GUEST_ASSERT_EQ(ret.error, SBI_ERR_NOT_SUPPORTED); +} + +static void test_pmu_events(void) +{ + int num_counters = 0; + + /* Get the counter details */ + num_counters = get_num_counters(); + update_counter_info(num_counters); + + /* Sanity testing for any random invalid event */ + test_invalid_event(); + + /* Only these two events are guaranteed to be present */ + test_pmu_event(SBI_PMU_HW_CPU_CYCLES); + test_pmu_event(SBI_PMU_HW_INSTRUCTIONS); + + GUEST_DONE(); +} + +static void test_pmu_basic_sanity(void) +{ + long out_val = 0; + bool probe; + struct sbiret ret; + int num_counters = 0, i; + union sbi_pmu_ctr_info ctrinfo; + + probe = guest_sbi_probe_extension(SBI_EXT_PMU, &out_val); + GUEST_ASSERT(probe && out_val == 1); + + num_counters = get_num_counters(); + + for (i = 0; i < num_counters; i++) { + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_GET_INFO, i, + 0, 0, 0, 0, 0); + + /* There can be gaps in logical counter indicies*/ + if (ret.error) + continue; + GUEST_ASSERT_NE(ret.value, 0); + + ctrinfo.value = ret.value; + + /** + * Accessibility check of hardware and read capability of firmware counters. + * The spec doesn't mandate any initial value. No need to check any value. + */ + if (ctrinfo.type == SBI_PMU_CTR_TYPE_HW) { + pmu_csr_read_num(ctrinfo.csr); + GUEST_ASSERT(illegal_handler_invoked); + } else if (ctrinfo.type == SBI_PMU_CTR_TYPE_FW) { + read_fw_counter(i, ctrinfo); + } + } + + GUEST_DONE(); +} + +static void test_pmu_events_snaphost(void) +{ + int num_counters = 0; + struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva; + int i; + + /* Verify presence of SBI PMU and minimum requrired SBI version */ + verify_sbi_requirement_assert(); + + snapshot_set_shmem(snapshot_gpa, 0); + + /* Get the counter details */ + num_counters = get_num_counters(); + update_counter_info(num_counters); + + /* Validate shared memory access */ + GUEST_ASSERT_EQ(READ_ONCE(snapshot_data->ctr_overflow_mask), 0); + for (i = 0; i < num_counters; i++) { + if (counter_mask_available & (BIT(i))) + GUEST_ASSERT_EQ(READ_ONCE(snapshot_data->ctr_values[i]), 0); + } + /* Only these two events are guranteed to be present */ + test_pmu_event_snapshot(SBI_PMU_HW_CPU_CYCLES); + test_pmu_event_snapshot(SBI_PMU_HW_INSTRUCTIONS); + + GUEST_DONE(); +} + +static void test_pmu_events_overflow(void) +{ + int num_counters = 0; + + /* Verify presence of SBI PMU and minimum requrired SBI version */ + verify_sbi_requirement_assert(); + + snapshot_set_shmem(snapshot_gpa, 0); + csr_set(CSR_IE, BIT(IRQ_PMU_OVF)); + local_irq_enable(); + + /* Get the counter details */ + num_counters = get_num_counters(); + update_counter_info(num_counters); + + /* + * Qemu supports overflow for cycle/instruction. + * This test may fail on any platform that do not support overflow for these two events. + */ + test_pmu_event_overflow(SBI_PMU_HW_CPU_CYCLES); + GUEST_ASSERT_EQ(vcpu_shared_irq_count, 1); + + test_pmu_event_overflow(SBI_PMU_HW_INSTRUCTIONS); + GUEST_ASSERT_EQ(vcpu_shared_irq_count, 2); + + GUEST_DONE(); +} + +static void run_vcpu(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_DONE: + case UCALL_SYNC: + break; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + break; + } +} + +void test_vm_destroy(struct kvm_vm *vm) +{ + memset(ctrinfo_arr, 0, sizeof(union sbi_pmu_ctr_info) * RISCV_MAX_PMU_COUNTERS); + counter_mask_available = 0; + kvm_vm_free(vm); +} + +static void test_vm_basic_test(void *guest_code) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU), + "SBI PMU not available, skipping test"); + vm_init_vector_tables(vm); + /* Illegal instruction handler is required to verify read access without configuration */ + vm_install_exception_handler(vm, EXC_INST_ILLEGAL, guest_illegal_exception_handler); + + vcpu_init_vector_tables(vcpu); + run_vcpu(vcpu); + + test_vm_destroy(vm); +} + +static void test_vm_events_test(void *guest_code) +{ + struct kvm_vm *vm = NULL; + struct kvm_vcpu *vcpu = NULL; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU), + "SBI PMU not available, skipping test"); + run_vcpu(vcpu); + + test_vm_destroy(vm); +} + +static void test_vm_setup_snapshot_mem(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +{ + /* PMU Snapshot requires single page only */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, PMU_SNAPSHOT_GPA_BASE, 1, 1, 0); + /* PMU_SNAPSHOT_GPA_BASE is identity mapped */ + virt_map(vm, PMU_SNAPSHOT_GPA_BASE, PMU_SNAPSHOT_GPA_BASE, 1); + + snapshot_gva = (void *)(PMU_SNAPSHOT_GPA_BASE); + snapshot_gpa = addr_gva2gpa(vcpu->vm, (vm_vaddr_t)snapshot_gva); + sync_global_to_guest(vcpu->vm, snapshot_gva); + sync_global_to_guest(vcpu->vm, snapshot_gpa); +} + +static void test_vm_events_snapshot_test(void *guest_code) +{ + struct kvm_vm *vm = NULL; + struct kvm_vcpu *vcpu; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU), + "SBI PMU not available, skipping test"); + + test_vm_setup_snapshot_mem(vm, vcpu); + + run_vcpu(vcpu); + + test_vm_destroy(vm); +} + +static void test_vm_events_overflow(void *guest_code) +{ + struct kvm_vm *vm = NULL; + struct kvm_vcpu *vcpu; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU), + "SBI PMU not available, skipping test"); + + __TEST_REQUIRE(__vcpu_has_isa_ext(vcpu, KVM_RISCV_ISA_EXT_SSCOFPMF), + "Sscofpmf is not available, skipping overflow test"); + + test_vm_setup_snapshot_mem(vm, vcpu); + vm_init_vector_tables(vm); + vm_install_interrupt_handler(vm, guest_irq_handler); + + vcpu_init_vector_tables(vcpu); + /* Initialize guest timer frequency. */ + vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency), &timer_freq); + sync_global_to_guest(vm, timer_freq); + + run_vcpu(vcpu); + + test_vm_destroy(vm); +} + +static void test_print_help(char *name) +{ + pr_info("Usage: %s [-h] [-d <test name>]\n", name); + pr_info("\t-d: Test to disable. Available tests are 'basic', 'events', 'snapshot', 'overflow'\n"); + pr_info("\t-h: print this help screen\n"); +} + +static bool parse_args(int argc, char *argv[]) +{ + int opt; + + while ((opt = getopt(argc, argv, "hd:")) != -1) { + switch (opt) { + case 'd': + if (!strncmp("basic", optarg, 5)) + disabled_tests |= SBI_PMU_TEST_BASIC; + else if (!strncmp("events", optarg, 6)) + disabled_tests |= SBI_PMU_TEST_EVENTS; + else if (!strncmp("snapshot", optarg, 8)) + disabled_tests |= SBI_PMU_TEST_SNAPSHOT; + else if (!strncmp("overflow", optarg, 8)) + disabled_tests |= SBI_PMU_TEST_OVERFLOW; + else + goto done; + break; + case 'h': + default: + goto done; + } + } + + return true; +done: + test_print_help(argv[0]); + return false; +} + +int main(int argc, char *argv[]) +{ + if (!parse_args(argc, argv)) + exit(KSFT_SKIP); + + if (!(disabled_tests & SBI_PMU_TEST_BASIC)) { + test_vm_basic_test(test_pmu_basic_sanity); + pr_info("SBI PMU basic test : PASS\n"); + } + + if (!(disabled_tests & SBI_PMU_TEST_EVENTS)) { + test_vm_events_test(test_pmu_events); + pr_info("SBI PMU event verification test : PASS\n"); + } + + if (!(disabled_tests & SBI_PMU_TEST_SNAPSHOT)) { + test_vm_events_snapshot_test(test_pmu_events_snaphost); + pr_info("SBI PMU event verification with snapshot test : PASS\n"); + } + + if (!(disabled_tests & SBI_PMU_TEST_OVERFLOW)) { + test_vm_events_overflow(test_pmu_events_overflow); + pr_info("SBI PMU event verification with overflow test : PASS\n"); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index bae0c5026f82..2ff82c7fd926 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -11,7 +11,9 @@ #include <pthread.h> #include <linux/kernel.h> #include <asm/kvm.h> -#ifndef __riscv +#ifdef __riscv +#include "sbi.h" +#else #include <asm/kvm_para.h> #endif |