Re: [PATCH v5 5/7] riscv: pmu: Add driver for Control Transfer Records Ext
From: Anup Patel
Date: Thu Nov 19 2026 - 10:32:29 EST
On Wed, Nov 18, 2026 at 3:21 PM Vikram Singh
<vikram.singh3@xxxxxxxxxxxxxxxx> wrote:
>
> This adds support for CTR Ext defined in [0]. The extension
> allows to records a maximum for 256 last branch records.
>
> CTR extension depends on s[m|s]csrind and Sscofpmf extensions.
>
> Co-developed-by: Rajnesh Kanwal <rajnesh.kanwal49@xxxxxxxxx>
> Signed-off-by: Rajnesh Kanwal <rajnesh.kanwal49@xxxxxxxxx>
> Signed-off-by: Vikram Singh <vikram.singh3@xxxxxxxxxxxxxxxx>
> Link: https://lore.kernel.org/r/20261106173942.3175069-6-vikram.singh3@xxxxxxxxxxxxxxxx
> Signed-off-by: Anup Patel <anup@xxxxxxxxxxxxxx>
As mentioned in PATCH1, drop the "Link:" and the subsequent
"Signed-off-by:" lines.
> ---
> MAINTAINERS | 3 +
> drivers/perf/Kconfig | 16 +
> drivers/perf/Makefile | 1 +
> drivers/perf/riscv_ctr.c | 609 +++++++++++++++++++++++++++++++++
> include/linux/perf/riscv_pmu.h | 44 ++-
> 5 files changed, 669 insertions(+), 4 deletions(-)
> create mode 100644 drivers/perf/riscv_ctr.c
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index ccbcdc0799b9..87bba12adc7f 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -24225,8 +24225,11 @@ F: arch/riscv/boot/dts/sifive/
> RISC-V PMU DRIVERS
> M: Atish Patra <atish.patra@xxxxxxxxx>
> R: Anup Patel <anup@xxxxxxxxxxxxxx>
> +R: Vikram Singh <vikram.singh3@xxxxxxxxxxxxxxxx>
> L: linux-riscv@xxxxxxxxxxxxxxxxxxx
> S: Supported
> +F: Documentation/arch/riscv/pmu-sse.rst
Drop this line since it will be added by the SSE patch series.
> +F: drivers/perf/riscv_ctr.c
> F: drivers/perf/riscv_pmu.c
> F: drivers/perf/riscv_pmu_legacy.c
> F: drivers/perf/riscv_pmu_sbi.c
> diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
> index 245e7bb763b9..0b4c04c50c22 100644
> --- a/drivers/perf/Kconfig
> +++ b/drivers/perf/Kconfig
> @@ -129,6 +129,22 @@ config ANDES_CUSTOM_PMU
>
> If you don't know what to do here, say "Y".
>
> +config RISCV_CTR
> + bool "Enable support for Control Transfer Records (CTR)"
> + depends on PERF_EVENTS && RISCV_PMU
> + default y
> + help
> + Enable support for Control Transfer Records (CTR) which
> + allows recording branches, Jumps, Calls, returns etc taken in an
> + execution path. This also supports privilege based filtering. It
> + captures additional relevant information such as cycle count,
> + branch misprediction etc.
> +
> +config RISCV_M_MODE
> + bool "Enable M Mode"
> + depends on RISCV_CTR
> + default n
> +
Drop this "config RISCV_M_MODE" because it is already
defined under arch/riscv
> config ARM_PMU_ACPI
> depends on ARM_PMU && ACPI
> def_bool y
> diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
> index eb8a022dad9a..02cba90afb54 100644
> --- a/drivers/perf/Makefile
> +++ b/drivers/perf/Makefile
> @@ -21,6 +21,7 @@ obj-$(CONFIG_RISCV_PMU) += riscv_pmu.o
> obj-$(CONFIG_RISCV_PMU_LEGACY) += riscv_pmu_legacy.o
> obj-$(CONFIG_RISCV_PMU_SBI) += riscv_pmu_sbi.o
> obj-$(CONFIG_STARFIVE_STARLINK_PMU) += starfive_starlink_pmu.o
> +obj-$(CONFIG_RISCV_CTR) += riscv_ctr.o
Add this line right after the line appending "riscv_pmu_sbi.o"
> obj-$(CONFIG_THUNDERX2_PMU) += thunderx2_pmu.o
> obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o
> obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o
> diff --git a/drivers/perf/riscv_ctr.c b/drivers/perf/riscv_ctr.c
> new file mode 100644
> index 000000000000..1af8a304dd69
> --- /dev/null
> +++ b/drivers/perf/riscv_ctr.c
> @@ -0,0 +1,609 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Control transfer records extension Helpers.
> + *
> + * Copyright (C) 2024 Rivos Inc.
> + *
> + * Author: Rajnesh Kanwal <rkanwal@xxxxxxxxxxxx>
No need to mention author names over here and
all other patches.
> + */
> +
> +#define pr_fmt(fmt) "CTR: " fmt
> +
> +#include <linux/bitfield.h>
> +#include <linux/printk.h>
> +#include <linux/types.h>
> +#include <linux/perf_event.h>
> +#include <linux/perf/riscv_pmu.h>
> +#include <linux/cpufeature.h>
> +#include <asm/hwcap.h>
> +#include <asm/csr_indirect.h>
> +#include <asm/csr.h>
> +
> +#define CTR_BRANCH_FILTERS_INH (CTRCTL_EXCINH | \
> + CTRCTL_INTRINH | \
> + CTRCTL_TRETINH | \
> + CTRCTL_TKBRINH | \
> + CTRCTL_INDCALL_INH | \
> + CTRCTL_DIRCALL_INH | \
> + CTRCTL_INDJUMP_INH | \
> + CTRCTL_DIRJUMP_INH | \
> + CTRCTL_CORSWAP_INH | \
> + CTRCTL_RET_INH | \
> + CTRCTL_INDOJUMP_INH | \
> + CTRCTL_DIROJUMP_INH)
> +
> +#define CTR_BRANCH_ENABLE_BITS (CTRCTL_KERNEL_ENABLE | CTRCTL_U_ENABLE)
> +
> +/* Branch filters not-supported by CTR extension. */
> +#define CTR_EXCLUDE_BRANCH_FILTERS (PERF_SAMPLE_BRANCH_ABORT_TX | \
> + PERF_SAMPLE_BRANCH_IN_TX | \
> + PERF_SAMPLE_BRANCH_PRIV_SAVE | \
> + PERF_SAMPLE_BRANCH_NO_TX | \
> + PERF_SAMPLE_BRANCH_COUNTERS)
> +
> +/* Branch filters supported by CTR extension. */
> +#define CTR_ALLOWED_BRANCH_FILTERS (PERF_SAMPLE_BRANCH_USER | \
> + PERF_SAMPLE_BRANCH_KERNEL | \
> + PERF_SAMPLE_BRANCH_HV | \
> + PERF_SAMPLE_BRANCH_ANY | \
> + PERF_SAMPLE_BRANCH_ANY_CALL | \
> + PERF_SAMPLE_BRANCH_ANY_RETURN | \
> + PERF_SAMPLE_BRANCH_IND_CALL | \
> + PERF_SAMPLE_BRANCH_COND | \
> + PERF_SAMPLE_BRANCH_IND_JUMP | \
> + PERF_SAMPLE_BRANCH_HW_INDEX | \
> + PERF_SAMPLE_BRANCH_NO_FLAGS | \
> + PERF_SAMPLE_BRANCH_NO_CYCLES | \
> + PERF_SAMPLE_BRANCH_CALL_STACK | \
> + PERF_SAMPLE_BRANCH_CALL | \
> + PERF_SAMPLE_BRANCH_TYPE_SAVE)
> +
> +#define CTR_PERF_BRANCH_FILTERS (CTR_ALLOWED_BRANCH_FILTERS | \
> + CTR_EXCLUDE_BRANCH_FILTERS)
> +
> +static u64 allowed_filters __read_mostly;
> +
> +struct ctr_regset {
> + unsigned long src;
> + unsigned long target;
> + unsigned long ctr_data;
> +};
> +
> +enum {
> + CTR_STATE_NONE,
> + CTR_STATE_VALID,
> +};
> +
> +/* Head is the idx of the next available slot. The slot may be already populated
> + * by an old entry which will be lost on new writes.
> + */
> +struct riscv_perf_task_context {
> + int callstack_users;
> + int stack_state;
> + unsigned int num_entries;
> + u32 ctr_status;
> + u64 ctr_control;
> + struct ctr_regset store[MAX_BRANCH_RECORDS];
> +};
> +
> +static inline u64 get_ctr_src_reg(unsigned int ctr_idx)
> +{
> + return csr_indirect_read(CSR_SIREG, CTR_ENTRIES_FIRST, ctr_idx);
> +}
> +
> +static inline void set_ctr_src_reg(unsigned int ctr_idx, u64 value)
> +{
> + return csr_indirect_write(CSR_SIREG, CTR_ENTRIES_FIRST, ctr_idx, value);
> +}
> +
> +static inline u64 get_ctr_tgt_reg(unsigned int ctr_idx)
> +{
> + return csr_indirect_read(CSR_SIREG2, CTR_ENTRIES_FIRST, ctr_idx);
> +}
> +
> +static inline void set_ctr_tgt_reg(unsigned int ctr_idx, u64 value)
> +{
> + return csr_indirect_write(CSR_SIREG2, CTR_ENTRIES_FIRST, ctr_idx, value);
> +}
> +
> +static inline u64 get_ctr_data_reg(unsigned int ctr_idx)
> +{
> + return csr_indirect_read(CSR_SIREG3, CTR_ENTRIES_FIRST, ctr_idx);
> +}
> +
> +static inline void set_ctr_data_reg(unsigned int ctr_idx, u64 value)
> +{
> + return csr_indirect_write(CSR_SIREG3, CTR_ENTRIES_FIRST, ctr_idx, value);
> +}
> +
> +static inline bool ctr_record_valid(u64 ctr_src)
> +{
> + return !!FIELD_GET(CTRSOURCE_VALID, ctr_src);
> +}
> +
> +static inline int ctr_get_mispredict(u64 ctr_target)
> +{
> + return FIELD_GET(CTRTARGET_MISP, ctr_target);
> +}
> +
> +static inline unsigned int ctr_get_cycles(u64 ctr_data)
> +{
> + const unsigned int cce = FIELD_GET(CTRDATA_CCE_MASK, ctr_data);
> + const unsigned int ccm = FIELD_GET(CTRDATA_CCM_MASK, ctr_data);
> +
> + if (ctr_data & CTRDATA_CCV)
> + return 0;
> +
> + /* Formula to calculate cycles from spec: (2^12 + CCM) << CCE-1 */
> + if (cce > 0)
> + return (4096 + ccm) << (cce - 1);
> +
> + return FIELD_GET(CTRDATA_CCM_MASK, ctr_data);
> +}
> +
> +static inline unsigned int ctr_get_type(u64 ctr_data)
> +{
> + return FIELD_GET(CTRDATA_TYPE_MASK, ctr_data);
> +}
> +
> +static inline unsigned int ctr_get_depth(u64 ctr_depth)
> +{
> + /* Depth table from CTR Spec: 2.4 sctrdepth.
> + *
> + * sctrdepth.depth Depth
> + * 000 - 16
> + * 001 - 32
> + * 010 - 64
> + * 011 - 128
> + * 100 - 256
> + *
> + * Depth = 16 * 2 ^ (ctrdepth.depth)
> + * or
> + * Depth = 16 << ctrdepth.depth.
> + */
> + return 16 << FIELD_GET(SCTRDEPTH_MASK, ctr_depth);
> +}
> +
> +static inline struct riscv_perf_task_context *task_context(void *ctx)
> +{
> + return (struct riscv_perf_task_context *)ctx;
> +}
> +
> +/* Reads CTR entry at idx and stores it in entry struct. */
> +static bool get_ctr_regset(struct ctr_regset *entry, unsigned int idx)
> +{
> + entry->src = get_ctr_src_reg(idx);
> +
> + if (!ctr_record_valid(entry->src))
> + return false;
> +
> + entry->src = entry->src;
> + entry->target = get_ctr_tgt_reg(idx);
> + entry->ctr_data = get_ctr_data_reg(idx);
> +
> + return true;
> +}
> +
> +static void set_ctr_regset(struct ctr_regset *entry, unsigned int idx)
> +{
> + set_ctr_src_reg(idx, entry->src);
> + set_ctr_tgt_reg(idx, entry->target);
> + set_ctr_data_reg(idx, entry->ctr_data);
> +}
> +
> +static u64 branch_type_to_ctr(int branch_type)
> +{
> + u64 config = CTR_BRANCH_FILTERS_INH | CTRCTL_LCOFIFRZ;
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_USER)
> + config |= CTRCTL_U_ENABLE;
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_KERNEL)
> + config |= CTRCTL_KERNEL_ENABLE;
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_HV) {
> + if (riscv_isa_extension_available(NULL, H))
> + config |= CTRCTL_KERNEL_ENABLE;
> + }
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_ANY) {
> + config &= ~CTR_BRANCH_FILTERS_INH;
> + return config;
> + }
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
> + config &= ~CTRCTL_INDCALL_INH;
> + config &= ~CTRCTL_DIRCALL_INH;
> + config &= ~CTRCTL_EXCINH;
> + config &= ~CTRCTL_INTRINH;
> + }
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
> + config &= ~(CTRCTL_RET_INH | CTRCTL_TRETINH);
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_IND_CALL)
> + config &= ~CTRCTL_INDCALL_INH;
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_COND)
> + config &= ~CTRCTL_TKBRINH;
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_CALL_STACK)
> + config |= CTRCTL_RASEMU;
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_IND_JUMP) {
> + config &= ~CTRCTL_INDJUMP_INH;
> + config &= ~CTRCTL_INDOJUMP_INH;
> + }
> +
> + if (branch_type & PERF_SAMPLE_BRANCH_CALL)
> + config &= ~CTRCTL_DIRCALL_INH;
> +
> + return config;
> +}
> +
> +static const int ctr_perf_map[] = {
> + [CTRDATA_TYPE_NONE] = PERF_BR_UNKNOWN,
> + [CTRDATA_TYPE_EXCEPTION] = PERF_BR_SYSCALL,
> + [CTRDATA_TYPE_INTERRUPT] = PERF_BR_IRQ,
> + [CTRDATA_TYPE_TRAP_RET] = PERF_BR_ERET,
> + [CTRDATA_TYPE_NONTAKEN_BRANCH] = PERF_BR_COND,
> + [CTRDATA_TYPE_TAKEN_BRANCH] = PERF_BR_COND,
> + [CTRDATA_TYPE_RESERVED_6] = PERF_BR_UNKNOWN,
> + [CTRDATA_TYPE_RESERVED_7] = PERF_BR_UNKNOWN,
> + [CTRDATA_TYPE_INDIRECT_CALL] = PERF_BR_IND_CALL,
> + [CTRDATA_TYPE_DIRECT_CALL] = PERF_BR_CALL,
> + [CTRDATA_TYPE_INDIRECT_JUMP] = PERF_BR_IND,
> + [CTRDATA_TYPE_DIRECT_JUMP] = PERF_BR_UNCOND,
> + [CTRDATA_TYPE_CO_ROUTINE_SWAP] = PERF_BR_UNKNOWN,
> + [CTRDATA_TYPE_RETURN] = PERF_BR_RET,
> + [CTRDATA_TYPE_OTHER_INDIRECT_JUMP] = PERF_BR_IND,
> + [CTRDATA_TYPE_OTHER_DIRECT_JUMP] = PERF_BR_UNCOND,
> +};
> +
> +static void ctr_set_perf_entry_type(struct perf_branch_entry *entry,
> + u64 ctr_data)
> +{
> + int ctr_type = ctr_get_type(ctr_data);
> +
> + entry->type = ctr_perf_map[ctr_type];
> + if (entry->type == PERF_BR_UNKNOWN)
> + pr_warn("%d - unknown branch type captured\n", ctr_type);
> +}
> +
> +static void capture_ctr_flags(struct perf_branch_entry *entry,
> + struct perf_event *event, u64 ctr_data,
> + u64 ctr_target)
> +{
> + if (branch_sample_type(event))
> + ctr_set_perf_entry_type(entry, ctr_data);
> +
> + if (!branch_sample_no_cycles(event))
> + entry->cycles = ctr_get_cycles(ctr_data);
> +
> + if (!branch_sample_no_flags(event)) {
> + entry->abort = 0;
> + entry->mispred = ctr_get_mispredict(ctr_target);
> + entry->predicted = !entry->mispred;
> + }
> +
> + if (branch_sample_priv(event))
> + entry->priv = PERF_BR_PRIV_UNKNOWN;
> +}
> +
> +static void ctr_regset_to_branch_entry(struct cpu_hw_events *cpuc,
> + struct perf_event *event,
> + struct ctr_regset *regset,
> + unsigned int idx)
> +{
> + struct perf_branch_entry *entry = &cpuc->branches->branch_entries[idx];
> +
> + *entry = (struct perf_branch_entry){ };
> + entry->from = regset->src & (~CTRSOURCE_VALID);
> + entry->to = regset->target & (~CTRTARGET_MISP);
> + capture_ctr_flags(entry, event, regset->ctr_data, regset->target);
> +}
> +
> +static void ctr_read_entries(struct cpu_hw_events *cpuc,
> + struct perf_event *event,
> + unsigned int depth)
> +{
> + struct ctr_regset entry = {};
> + u64 ctr_ctl;
> + int i;
> +
> + ctr_ctl = csr_read_clear(CSR_CTRCTL, CTR_BRANCH_ENABLE_BITS);
> +
> + for (i = 0; i < depth; i++) {
> + if (!get_ctr_regset(&entry, i))
> + break;
> +
> + ctr_regset_to_branch_entry(cpuc, event, &entry, i);
> + }
> +
> + csr_set(CSR_CTRCTL, ctr_ctl & CTR_BRANCH_ENABLE_BITS);
> +
> + cpuc->branches->branch_stack.nr = i;
> + cpuc->branches->branch_stack.hw_idx = 0;
> +}
> +
> +bool riscv_pmu_ctr_valid(struct perf_event *event)
> +{
> + u64 branch_type = event->attr.branch_sample_type;
> +
> + if (branch_type & ~allowed_filters) {
> + pr_debug_once("Requested branch filters not supported 0x%llx\n",
> + branch_type & ~allowed_filters);
> + return false;
> + }
> +
> + return true;
> +}
> +
> +void riscv_pmu_ctr_consume(struct cpu_hw_events *cpuc, struct perf_event *event)
> +{
> + unsigned int depth = to_riscv_pmu(event->pmu)->ctr_depth;
> +
> + ctr_read_entries(cpuc, event, depth);
> +
> + /* Clear frozen bit. */
> + csr_clear(CSR_SCTRSTATUS, SCTRSTATUS_FROZEN);
> +}
> +
> +static void riscv_pmu_ctr_reset(void)
> +{
> + /* FIXME: Replace with sctrclr instruction once support is merged
> + * into toolchain.
> + */
> + asm volatile(".4byte 0x10400073\n" ::: "memory");
> + csr_write(CSR_SCTRSTATUS, 0);
> +}
> +
> +static void __riscv_pmu_ctr_restore(void *ctx)
> +{
> + struct riscv_perf_task_context *task_ctx = ctx;
> + unsigned int i;
> +
> + csr_write(CSR_SCTRSTATUS, task_ctx->ctr_status);
> +
> + for (i = 0; i < task_ctx->num_entries; i++)
> + set_ctr_regset(&task_ctx->store[i], i);
> +}
> +
> +static void riscv_pmu_ctr_restore(void *ctx)
> +{
> + if (task_context(ctx)->stack_state == CTR_STATE_NONE ||
> + task_context(ctx)->callstack_users == 0) {
> + return;
> + }
> +
> + riscv_pmu_ctr_reset();
> + __riscv_pmu_ctr_restore(ctx);
> +
> + task_context(ctx)->stack_state = CTR_STATE_NONE;
> +}
> +
> +static void __riscv_pmu_ctr_save(void *ctx, unsigned int depth)
> +{
> + struct riscv_perf_task_context *task_ctx = ctx;
> + struct ctr_regset *dst;
> + unsigned int i;
> +
> + for (i = 0; i < depth; i++) {
> + dst = &task_ctx->store[i];
> + if (!get_ctr_regset(dst, i))
> + break;
> + }
> +
> + task_ctx->num_entries = i;
> +
> + task_ctx->ctr_status = csr_read(CSR_SCTRSTATUS);
> +}
> +
> +static void riscv_pmu_ctr_save(void *ctx, unsigned int depth)
> +{
> + if (task_context(ctx)->stack_state == CTR_STATE_VALID)
> + return;
> +
> + if (task_context(ctx)->callstack_users == 0) {
> + task_context(ctx)->stack_state = CTR_STATE_NONE;
> + return;
> + }
> +
> + __riscv_pmu_ctr_save(ctx, depth);
> +
> + task_context(ctx)->stack_state = CTR_STATE_VALID;
> +}
> +
> +/*
> + * On context switch in, we need to make sure no samples from previous tasks
> + * are left in the CTR.
> + *
> + * On ctxswin, sched_in = true, called after the PMU has started
> + * On ctxswout, sched_in = false, called before the PMU is stopped
> + */
> +void riscv_pmu_ctr_sched_task(struct perf_event_pmu_context *pmu_ctx, struct task_struct *task,
> + bool sched_in)
> +{
> + struct riscv_pmu *rvpmu = to_riscv_pmu(pmu_ctx->pmu);
> + struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
> + void *task_ctx;
> +
> + if (!cpuc->ctr_users)
> + return;
> +
> + /* Save branch records in task_ctx on sched out */
> + task_ctx = pmu_ctx ? task->perf_ctx_data : NULL;
> + if (task_ctx) {
> + if (sched_in)
> + riscv_pmu_ctr_restore(task_ctx);
> + else
> + riscv_pmu_ctr_save(task_ctx, rvpmu->ctr_depth);
> + return;
> + }
> +
> + /* Reset branch records on sched in */
> + if (sched_in)
> + riscv_pmu_ctr_reset();
> +}
> +
> +static inline bool branch_user_callstack(unsigned int br_type)
> +{
> + return (br_type & PERF_SAMPLE_BRANCH_USER) &&
> + (br_type & PERF_SAMPLE_BRANCH_CALL_STACK);
> +}
> +
> +void riscv_pmu_ctr_add(struct perf_event *event)
> +{
> + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
> + struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
> +
> + if (branch_user_callstack(event->attr.branch_sample_type) &&
> + event->ctx->task->perf_ctx_data)
> + task_context(event->ctx->task->perf_ctx_data)->callstack_users++;
> +
> + perf_sched_cb_inc(event->pmu);
> +
> + if (!cpuc->ctr_users++)
> + riscv_pmu_ctr_reset();
> +}
> +
> +void riscv_pmu_ctr_del(struct perf_event *event)
> +{
> + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
> + struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
> +
> + if (branch_user_callstack(event->attr.branch_sample_type) &&
> + event->ctx->task->perf_ctx_data)
> + task_context(event->ctx->task->perf_ctx_data)->callstack_users--;
> +
> + perf_sched_cb_dec(event->pmu);
> + cpuc->ctr_users--;
> + WARN_ON_ONCE(cpuc->ctr_users < 0);
> +}
> +
> +void riscv_pmu_ctr_enable(struct perf_event *event)
> +{
> + u64 branch_type = event->attr.branch_sample_type;
> + u64 ctr;
> +
> + ctr = branch_type_to_ctr(branch_type);
> + csr_write(CSR_CTRCTL, ctr);
> +}
> +
> +void riscv_pmu_ctr_disable(struct perf_event *event)
> +{
> + /* Clear CTRCTL to disable the recording. */
> + csr_write(CSR_CTRCTL, 0);
> +}
> +
> +/*
> + * Check for hardware supported perf filters here. To avoid missing
> + * any new added filter in perf, we do a BUILD_BUG_ON check, so make sure
> + * to update CTR_ALLOWED_BRANCH_FILTERS or CTR_EXCLUDE_BRANCH_FILTERS
> + * defines when adding support for it in below function.
> + */
> +static void __init check_available_filters(void)
> +{
> + u64 ctr_ctl;
> +
> + /*
> + * Ensure both perf branch filter allowed and exclude
> + * masks are always in sync with the generic perf ABI.
> + */
> + BUILD_BUG_ON(CTR_PERF_BRANCH_FILTERS != (PERF_SAMPLE_BRANCH_MAX - 1));
> +
> + allowed_filters = PERF_SAMPLE_BRANCH_USER |
> + PERF_SAMPLE_BRANCH_KERNEL |
> + PERF_SAMPLE_BRANCH_ANY |
> + PERF_SAMPLE_BRANCH_HW_INDEX |
> + PERF_SAMPLE_BRANCH_NO_FLAGS |
> + PERF_SAMPLE_BRANCH_NO_CYCLES |
> + PERF_SAMPLE_BRANCH_TYPE_SAVE;
> +
> + csr_write(CSR_CTRCTL, ~0);
> + ctr_ctl = csr_read(CSR_CTRCTL);
> + csr_write(CSR_CTRCTL, 0);
> +
> + if (riscv_isa_extension_available(NULL, H))
> + allowed_filters |= PERF_SAMPLE_BRANCH_HV;
> +
> + if (ctr_ctl & (CTRCTL_INDCALL_INH | CTRCTL_DIRCALL_INH))
> + allowed_filters |= PERF_SAMPLE_BRANCH_ANY_CALL;
> +
> + if (ctr_ctl & (CTRCTL_RET_INH | CTRCTL_TRETINH))
> + allowed_filters |= PERF_SAMPLE_BRANCH_ANY_RETURN;
> +
> + if (ctr_ctl & CTRCTL_INDCALL_INH)
> + allowed_filters |= PERF_SAMPLE_BRANCH_IND_CALL;
> +
> + if (ctr_ctl & CTRCTL_TKBRINH)
> + allowed_filters |= PERF_SAMPLE_BRANCH_COND;
> +
> + if (ctr_ctl & CTRCTL_RASEMU)
> + allowed_filters |= PERF_SAMPLE_BRANCH_CALL_STACK;
> +
> + if (ctr_ctl & (CTRCTL_INDOJUMP_INH | CTRCTL_INDJUMP_INH))
> + allowed_filters |= PERF_SAMPLE_BRANCH_IND_JUMP;
> +
> + if (ctr_ctl & CTRCTL_DIRCALL_INH)
> + allowed_filters |= PERF_SAMPLE_BRANCH_CALL;
> +}
> +
> +void riscv_pmu_ctr_starting_cpu(void)
> +{
> + if (!riscv_isa_extension_available(NULL, SxCTR) ||
> + !riscv_isa_extension_available(NULL, SSCOFPMF))
> + return;
> +
> + /* Set depth to maximum. */
> + csr_write(CSR_SCTRDEPTH, SCTRDEPTH_MASK);
> +}
> +
> +void riscv_pmu_ctr_dying_cpu(void)
> +{
> + if (!riscv_isa_extension_available(NULL, SxCTR) ||
> + !riscv_isa_extension_available(NULL, SSCOFPMF))
> + return;
> +
> + /* Clear and reset CTR CSRs. */
> + csr_write(CSR_SCTRDEPTH, 0);
> + csr_write(CSR_CTRCTL, 0);
> + riscv_pmu_ctr_reset();
> +}
> +
> +int riscv_pmu_ctr_init(struct riscv_pmu *riscv_pmu)
> +{
> + size_t size = sizeof(struct riscv_perf_task_context);
> +
> + if (!riscv_isa_extension_available(NULL, SxCTR) ||
> + !riscv_isa_extension_available(NULL, SSCOFPMF))
> + return 0;
> +
> + riscv_pmu->pmu.task_ctx_cache =
> + kmem_cache_create("ctr_task_ctx", size, sizeof(u64), 0, NULL);
> + if (!riscv_pmu->pmu.task_ctx_cache)
> + return -ENOMEM;
> +
> + check_available_filters();
> +
> + /* Set depth to maximum. */
> + csr_write(CSR_SCTRDEPTH, SCTRDEPTH_MASK);
> + riscv_pmu->ctr_depth = ctr_get_depth(csr_read(CSR_SCTRDEPTH));
> +
> + pr_info("Perf CTR available, with %d depth\n", riscv_pmu->ctr_depth);
> +
> + return 0;
> +}
> +
> +void riscv_pmu_ctr_finish(struct riscv_pmu *riscv_pmu)
> +{
> + if (!riscv_pmu_ctr_supported(riscv_pmu))
> + return;
> +
> + riscv_pmu->ctr_depth = 0;
> + csr_write(CSR_SCTRDEPTH, 0);
> + csr_write(CSR_CTRCTL, 0);
> + riscv_pmu_ctr_reset();
> +
> + kmem_cache_destroy(riscv_pmu->pmu.task_ctx_cache);
> +}
> diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h
> index c748a06ad751..848977ecf319 100644
> --- a/include/linux/perf/riscv_pmu.h
> +++ b/include/linux/perf/riscv_pmu.h
> @@ -56,9 +56,8 @@ struct cpu_hw_events {
> 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];
> - /* Saved branch records. */
> + /* Saved branch records */
> struct branch_records *branches;
> -
> /* Active events requesting branch records */
> int ctr_users;
> };
> @@ -88,8 +87,7 @@ struct riscv_pmu {
> struct cpu_hw_events __percpu *hw_events;
> struct hlist_node node;
> struct notifier_block riscv_pm_nb;
> -
> - unsigned int ctr_depth;
> + unsigned int ctr_depth;
> };
>
> #define to_riscv_pmu(p) (container_of(p, struct riscv_pmu, pmu))
> @@ -111,6 +109,44 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr);
> int riscv_pmu_get_event_info(u32 type, u64 config, u64 *econfig);
> #endif
>
> +static inline bool riscv_pmu_ctr_supported(struct riscv_pmu *pmu)
> +{
> + return !!pmu->ctr_depth;
> +}
> +
> #endif /* CONFIG_RISCV_PMU */
>
> +#ifdef CONFIG_RISCV_CTR
> +
> +bool riscv_pmu_ctr_valid(struct perf_event *event);
> +void riscv_pmu_ctr_consume(struct cpu_hw_events *cpuc, struct perf_event *event);
> +void riscv_pmu_ctr_sched_task(struct perf_event_pmu_context *pmu_ctx, struct task_struct *task,
> + bool sched_in);
> +void riscv_pmu_ctr_add(struct perf_event *event);
> +void riscv_pmu_ctr_del(struct perf_event *event);
> +void riscv_pmu_ctr_enable(struct perf_event *event);
> +void riscv_pmu_ctr_disable(struct perf_event *event);
> +void riscv_pmu_ctr_dying_cpu(void);
> +void riscv_pmu_ctr_starting_cpu(void);
> +int riscv_pmu_ctr_init(struct riscv_pmu *riscv_pmu);
> +void riscv_pmu_ctr_finish(struct riscv_pmu *riscv_pmu);
> +
> +#else
> +
> +static inline bool riscv_pmu_ctr_valid(struct perf_event *event) { return false; }
> +static inline void riscv_pmu_ctr_consume(struct cpu_hw_events *cpuc,
> + struct perf_event *event) { }
> +static inline void riscv_pmu_ctr_sched_task(struct perf_event_pmu_context *,
> + struct task_struct *task, bool sched_in) { }
> +static void riscv_pmu_ctr_add(struct perf_event *event) { }
> +static void riscv_pmu_ctr_del(struct perf_event *event) { }
> +static inline void riscv_pmu_ctr_enable(struct perf_event *event) { }
> +static inline void riscv_pmu_ctr_disable(struct perf_event *event) { }
> +static inline void riscv_pmu_ctr_dying_cpu(void) { }
> +static inline void riscv_pmu_ctr_starting_cpu(void) { }
> +static inline int riscv_pmu_ctr_init(struct riscv_pmu *riscv_pmu) { return 0; }
> +static inline void riscv_pmu_ctr_finish(struct riscv_pmu *riscv_pmu) { }
> +
> +#endif /* CONFIG_RISCV_CTR */
> +
> #endif /* _RISCV_PMU_H */
> --
> 2.43.0
>
Regards,
Anup