KVM: x86/pmu: Refactoring code by reusing pmc->eventsel for fixed_counters
v2 cover KVM: x86/pmu: Refactoring code by reusing pmc->eventsel for fixed_counters
Hi,
This patch set is essentially triggered by Jim's patch set[1] (especially patch 01 and 04).
The new idea to set up and maintain pmc->eventsel for fixed counters. This would unify all fixed/gp code logic based on the same semantics "pmc->eventsel". (I demonstrated this in patch 01-03, more can be done)
v1 -> v2 Changelog:
- Rename find_perf_hw_id() to pmc_perf_hw_id(); [Paolo]
- Add WARN_ON for amd_pmc_perf_hw_id(); [Paolo]
- Add pmc->intr to drop dummy need_overflow_intr(pmc); [Paolo]
Previous:
https://lore.kernel.org/kvm/[email protected]/T/#t
[1] https://lore.kernel.org/kvm/[email protected]/T/#t
Please check each commit message for more details and let me know if there is any room for improvement,
Thanks.
Like Xu (4):
KVM: x86/pmu: Setup pmc->eventsel for fixed PMCs
KVM: x86/pmu: Refactoring find_arch_event() to pmc_perf_hw_id()
KVM: x86/pmu: Reuse pmc_perf_hw_id() and drop find_fixed_event()
KVM: x86/pmu: Add pmc->intr to refactor kvm_perf_overflow{_intr}()
arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/pmu.c | 58 +++++++++++++-------------------- arch/x86/kvm/pmu.h | 4 +-- arch/x86/kvm/svm/pmu.c | 19 +++++------ arch/x86/kvm/vmx/pmu_intel.c | 54 ++++++++++++++++++++---------- 5 files changed, 69 insertions(+), 67 deletions(-)
Signature · 1 line
2.33.1
PATCH v2 1/4 KVM: x86/pmu: Setup pmc->eventsel for fixed PMCs
From: Like Xu <[email protected]>
The current pmc->eventsel for fixed counter is underutilised. The pmc->eventsel can be setup for all known available fixed counters since we have mapping between fixed pmc index and
the intel_arch_events array.
Either gp or fixed counter, it will simplify the later checks for consistency between eventsel and perf_hw_id.
--- arch/x86/kvm/vmx/pmu_intel.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
arch/x86/kvm/vmx/pmu_intel.c +16 -0
@@ -459,6 +459,21 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)return 1 ; } +static void setup_fixed_pmc_eventsel (struct kvm_pmu *pmu) +{ +size_t size =ARRAY_SIZE (fixed_pmc_events); +struct kvm_pmc *pmc; +u32 event; +int i; + +for (i =0 ; i < pmu->nr_arch_fixed_counters; i++) { + pmc = &pmu->fixed_counters[i]; + event = fixed_pmc_events[array_index_nospec (i, size)]; + pmc->eventsel = (intel_arch_events[event].unit_mask <<8 ) | + intel_arch_events[event].eventsel; + } +} +static void intel_pmu_refresh (struct kvm_vcpu *vcpu) {struct kvm_pmu *pmu =vcpu_to_pmu (vcpu);
@@ -506,6 +521,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) edx.split.bit_width_fixed, x86_pmu.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED ] = ((u64 )1 << edx.split.bit_width_fixed) -1 ; +setup_fixed_pmc_eventsel (pmu); } pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
Signature · 1 line
2.33.1
PATCH v2 2/4 KVM: x86/pmu: Refactoring find_arch_event() to pmc_perf_hw_id()
In reply to Like XuFrom: Like Xu <[email protected]>
The find_arch_event() returns a "unsigned int" value, which is used by the pmc_reprogram_counter() to program a PERF_TYPE_HARDWARE type perf_event.
The returned value is actually the kernel defined gernic perf_hw_id, let's rename it to pmc_perf_hw_id() with simpler incoming parameters for better self-explanation.
--- arch/x86/kvm/pmu.c | 8 +------- arch/x86/kvm/pmu.h | 3 +-- arch/x86/kvm/svm/pmu.c | 8 ++++---- arch/x86/kvm/vmx/pmu_intel.c | 9 +++++---- 4 files changed, 11 insertions(+), 17 deletions(-)
arch/x86/kvm/pmu.c +1 -7
@@ -174,7 +174,6 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)void reprogram_gp_counter (struct kvm_pmc *pmc,u64 eventsel) {unsigned config, type =PERF_TYPE_RAW ; -u8 event_select, unit_mask;struct kvm *kvm = pmc->vcpu->kvm;struct kvm_pmu_event_filter *filter;int i;
@@ -206,17 +205,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)if (!allow_event)return ; - event_select = eventsel &ARCH_PERFMON_EVENTSEL_EVENT ; - unit_mask = (eventsel &ARCH_PERFMON_EVENTSEL_UMASK ) >>8 ; -if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |ARCH_PERFMON_EVENTSEL_INV |ARCH_PERFMON_EVENTSEL_CMASK |HSW_IN_TX |HSW_IN_TX_CHECKPOINTED ))) { - config = kvm_x86_ops.pmu_ops->find_arch_event (pmc_to_pmu (pmc), - event_select, - unit_mask); + config = kvm_x86_ops.pmu_ops->pmc_perf_hw_id (pmc);if (config !=PERF_COUNT_HW_MAX ) type =PERF_TYPE_HARDWARE ; }
arch/x86/kvm/pmu.h +1 -2
@@ -24,8 +24,7 @@ struct kvm_event_hw_type_mapping { };struct kvm_pmu_ops { -unsigned (*find_arch_event)(struct kvm_pmu *pmu,u8 event_select, -u8 unit_mask); +unsigned int (*pmc_perf_hw_id)(struct kvm_pmc *pmc);unsigned (*find_fixed_event)(int idx);bool (*pmc_is_enabled)(struct kvm_pmc *pmc);struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu,int pmc_idx);
arch/x86/kvm/svm/pmu.c +4 -4
@@ -134,10 +134,10 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,return &pmu->gp_counters[msr_to_index (msr)]; } -static unsigned amd_find_arch_event (struct kvm_pmu *pmu, -u8 event_select, -u8 unit_mask) +static unsigned int amd_pmc_perf_hw_id (struct kvm_pmc *pmc) { +u8 event_select = pmc->eventsel &ARCH_PERFMON_EVENTSEL_EVENT ; +u8 unit_mask = (pmc->eventsel &ARCH_PERFMON_EVENTSEL_UMASK ) >>8 ;int i;for (i =0 ; i <ARRAY_SIZE (amd_event_mapping); i++)
@@ -319,7 +319,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) }struct kvm_pmu_ops amd_pmu_ops = { - .find_arch_event = amd_find_arch_event, + .pmc_perf_hw_id = amd_pmc_perf_hw_id, .find_fixed_event = amd_find_fixed_event, .pmc_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
arch/x86/kvm/vmx/pmu_intel.c +5 -4
@@ -68,10 +68,11 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)reprogram_counter (pmu, bit); } -static unsigned intel_find_arch_event (struct kvm_pmu *pmu, -u8 event_select, -u8 unit_mask) +static unsigned int intel_pmc_perf_hw_id (struct kvm_pmc *pmc) { +struct kvm_pmu *pmu =pmc_to_pmu (pmc); +u8 event_select = pmc->eventsel &ARCH_PERFMON_EVENTSEL_EVENT ; +u8 unit_mask = (pmc->eventsel &ARCH_PERFMON_EVENTSEL_UMASK ) >>8 ;int i;for (i =0 ; i <ARRAY_SIZE (intel_arch_events); i++)
@@ -719,7 +720,7 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) }struct kvm_pmu_ops intel_pmu_ops = { - .find_arch_event = intel_find_arch_event, + .pmc_perf_hw_id = intel_pmc_perf_hw_id, .find_fixed_event = intel_find_fixed_event, .pmc_is_enabled = intel_pmc_is_enabled, .pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
Signature · 1 line
2.33.1
PATCH v2 3/4 KVM: x86/pmu: Reuse pmc_perf_hw_id() and drop find_fixed_event()
In reply to Like XuFrom: Like Xu <[email protected]>
Since we set the same semantic event value for the fixed counter in pmc->eventsel, returning the perf_hw_id for the fixed counter via find_fixed_event() can be painlessly replaced by pmc_perf_hw_id() with the help of pmc_is_fixed() check.
--- arch/x86/kvm/pmu.c | 2 +- arch/x86/kvm/pmu.h | 1 - arch/x86/kvm/svm/pmu.c | 11 ++++------- arch/x86/kvm/vmx/pmu_intel.c | 29 ++++++++++++++++------------- 4 files changed, 21 insertions(+), 22 deletions(-)
arch/x86/kvm/pmu.c +1 -1
@@ -262,7 +262,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) pmc->current_config = (u64 )ctrl;pmc_reprogram_counter (pmc,PERF_TYPE_HARDWARE , - kvm_x86_ops.pmu_ops->find_fixed_event (idx), + kvm_x86_ops.pmu_ops->pmc_perf_hw_id (pmc), !(en_field &0x2 ),/* exclude user */ !(en_field &0x1 ),/* exclude kernel */ pmi, false, false);
arch/x86/kvm/pmu.h +0 -1
@@ -25,7 +25,6 @@ struct kvm_event_hw_type_mapping {struct kvm_pmu_ops {unsigned int (*pmc_perf_hw_id)(struct kvm_pmc *pmc); -unsigned (*find_fixed_event)(int idx);bool (*pmc_is_enabled)(struct kvm_pmc *pmc);struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu,int pmc_idx); struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,
arch/x86/kvm/svm/pmu.c +4 -7
@@ -140,6 +140,10 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc)u8 unit_mask = (pmc->eventsel &ARCH_PERFMON_EVENTSEL_UMASK ) >>8 ;int i; +/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ +if (WARN_ON (pmc_is_fixed (pmc))) +return PERF_COUNT_HW_MAX ; +for (i =0 ; i <ARRAY_SIZE (amd_event_mapping); i++)if (amd_event_mapping[i].eventsel == event_select && amd_event_mapping[i].unit_mask == unit_mask)
@@ -151,12 +155,6 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc)return amd_event_mapping[i].event_type; } -/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ -static unsigned amd_find_fixed_event (int idx) -{ -return PERF_COUNT_HW_MAX ; -} -/* check if a PMC is enabled by comparing it against global_ctrl bits. Because * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE). */
@@ -320,7 +318,6 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu)struct kvm_pmu_ops amd_pmu_ops = { .pmc_perf_hw_id = amd_pmc_perf_hw_id, - .find_fixed_event = amd_find_fixed_event, .pmc_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
arch/x86/kvm/vmx/pmu_intel.c +16 -13
@@ -68,6 +68,19 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)reprogram_counter (pmu, bit); } +static inline unsigned int intel_find_fixed_event (int idx) +{ +u32 event; +size_t size =ARRAY_SIZE (fixed_pmc_events); + +if (idx >= size) +return PERF_COUNT_HW_MAX ; + + event = fixed_pmc_events[array_index_nospec (idx, size)]; +return intel_arch_events[event].event_type; +} + +static unsigned int intel_pmc_perf_hw_id (struct kvm_pmc *pmc) {struct kvm_pmu *pmu =pmc_to_pmu (pmc);
@@ -75,6 +88,9 @@ static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)u8 unit_mask = (pmc->eventsel &ARCH_PERFMON_EVENTSEL_UMASK ) >>8 ;int i; +if (pmc_is_fixed (pmc)) +return intel_find_fixed_event (pmc->idx -INTEL_PMC_IDX_FIXED ); +for (i =0 ; i <ARRAY_SIZE (intel_arch_events); i++)if (intel_arch_events[i].eventsel == event_select && intel_arch_events[i].unit_mask == unit_mask
@@ -87,18 +103,6 @@ static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)return intel_arch_events[i].event_type; } -static unsigned intel_find_fixed_event (int idx) -{ -u32 event; -size_t size =ARRAY_SIZE (fixed_pmc_events); - -if (idx >= size) -return PERF_COUNT_HW_MAX ; - - event = fixed_pmc_events[array_index_nospec (idx, size)]; -return intel_arch_events[event].event_type; -} -/* check if a PMC is enabled by comparing it with globl_ctrl bits. */ static bool intel_pmc_is_enabled (struct kvm_pmc *pmc) {
@@ -721,7 +725,6 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)struct kvm_pmu_ops intel_pmu_ops = { .pmc_perf_hw_id = intel_pmc_perf_hw_id, - .find_fixed_event = intel_find_fixed_event, .pmc_is_enabled = intel_pmc_is_enabled, .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
Signature · 1 line
2.33.1
PATCH v2 4/4 KVM: x86/pmu: Add pmc->intr to refactor kvm_perf_overflow{_intr}()
In reply to Like XuFrom: Like Xu <[email protected]>
Depending on whether intr should be triggered or not, KVM registers two different event overflow callbacks in the perf_event context.
The code skeleton of these two functions is very similar, so the pmc->intr can be stored into pmc from pmc_reprogram_counter() which provides smaller instructions footprint against the u-architecture branch predictor.
--- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/pmu.c | 48 ++++++++++++++------------------- 2 files changed, 21 insertions(+), 28 deletions(-)
arch/x86/include/asm/kvm_host.h +1 -0
@@ -496,6 +496,7 @@ struct kvm_pmc {*/ u64 current_config;bool is_paused; +bool intr; };struct kvm_pmu {
arch/x86/kvm/pmu.c +20 -28
69 lines not on this page · raw message
Signature · 1 line
2.33.1