--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+============================================
+Ampere SoC Performance Monitoring Unit (PMU)
+============================================
+
+Ampere SoC PMU is a generic PMU IP that follows Arm CoreSight PMU architecture.
+Therefore, the driver is implemented as a submodule of arm_cspmu driver. At the
+first phase it's used for counting MCU events on AmpereOne.
+
+
+MCU PMU events
+--------------
+
+The PMU driver supports setting filters for "rank", "bank", and "threshold".
+Note, that the filters are per PMU instance rather than per event.
+
+
+Example for perf tool use::
+
+ / # perf list ampere
+
+ ampere_mcu_pmu_0/act_sent/ [Kernel PMU event]
+ <...>
+ ampere_mcu_pmu_1/rd_sent/ [Kernel PMU event]
+ <...>
+
+ / # perf stat -a -e ampere_mcu_pmu_0/act_sent,bank=5,rank=3,threshold=2/,ampere_mcu_pmu_1/rd_sent/ \
+ sleep 1
nvidia-pmu
meson-ddr-pmu
cxl
+ ampere_cspmu
config CPU_BIG_ENDIAN
bool "Build big-endian kernel"
depends on !LD_IS_LLD || LLD_VERSION >= 130000
+ # https://github.com/llvm/llvm-project/commit/1379b150991f70a5782e9a143c2ba5308da1161c
+ depends on AS_IS_GNU || AS_VERSION >= 150000
help
Say Y if you plan on running a kernel with a big-endian userspace.
u64 reg_id_aa64smfr0;
struct cpuinfo_32bit aarch32;
-
- /* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
- u64 reg_zcr;
-
- /* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
- u64 reg_smcr;
};
DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
#include <linux/bug.h>
#include <linux/jump_label.h>
#include <linux/kernel.h>
+#include <linux/cpumask.h>
/*
* CPU feature register tracking
* method is robust against being called multiple times.
*/
const struct arm64_cpu_capabilities *match_list;
+ const struct cpumask *cpus;
};
static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
#define ARM_CPU_PART_NEOVERSE_N2 0xD49
#define ARM_CPU_PART_CORTEX_A78C 0xD4B
-#define APM_CPU_PART_POTENZA 0x000
+#define APM_CPU_PART_XGENE 0x000
+#define APM_CPU_VAR_POTENZA 0x00
#define CAVIUM_CPU_PART_THUNDERX 0x0A1
#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2
extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused);
extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
-extern u64 read_zcr_features(void);
extern u64 read_smcr_features(void);
/*
#include <asm/atomic_lse.h>
#include <asm/cpucaps.h>
-static __always_inline bool system_uses_lse_atomics(void)
-{
- return alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS);
-}
-
#define __lse_ll_sc_body(op, ...) \
({ \
- system_uses_lse_atomics() ? \
+ alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS) ? \
__lse_##op(__VA_ARGS__) : \
__ll_sc_##op(__VA_ARGS__); \
})
#else /* CONFIG_ARM64_LSE_ATOMICS */
-static inline bool system_uses_lse_atomics(void) { return false; }
-
#define __lse_ll_sc_body(op, ...) __ll_sc_##op(__VA_ARGS__)
#define ARM64_LSE_ATOMIC_INSN(llsc, lse) llsc
}
void mte_zero_clear_page_tags(void *addr);
-void mte_sync_tags(pte_t pte);
+void mte_sync_tags(pte_t pte, unsigned int nr_pages);
void mte_copy_page_tags(void *kto, const void *kfrom);
void mte_thread_init_user(void);
void mte_thread_switch(struct task_struct *next);
static inline void mte_zero_clear_page_tags(void *addr)
{
}
-static inline void mte_sync_tags(pte_t pte)
+static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages)
{
}
static inline void mte_copy_page_tags(void *kto, const void *kfrom)
__func__, pte_val(old_pte), pte_val(pte));
}
-static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
+static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages)
{
if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
__sync_icache_dcache(pte);
*/
if (system_supports_mte() && pte_access_permitted(pte, false) &&
!pte_special(pte) && pte_tagged(pte))
- mte_sync_tags(pte);
-
- __check_safe_pte_update(mm, ptep, pte);
-
- set_pte(ptep, pte);
+ mte_sync_tags(pte, nr_pages);
}
-static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned int nr)
+static inline void set_ptes(struct mm_struct *mm,
+ unsigned long __always_unused addr,
+ pte_t *ptep, pte_t pte, unsigned int nr)
{
page_table_check_ptes_set(mm, ptep, pte, nr);
+ __sync_cache_and_tags(pte, nr);
for (;;) {
- __set_pte_at(mm, addr, ptep, pte);
+ __check_safe_pte_update(mm, ptep, pte);
+ set_pte(ptep, pte);
if (--nr == 0)
break;
ptep++;
- addr += PAGE_SIZE;
pte_val(pte) += PAGE_SIZE;
}
}
#define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
#define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
+static inline void __set_pte_at(struct mm_struct *mm,
+ unsigned long __always_unused addr,
+ pte_t *ptep, pte_t pte, unsigned int nr)
+{
+ __sync_cache_and_tags(pte, nr);
+ __check_safe_pte_update(mm, ptep, pte);
+ set_pte(ptep, pte);
+}
+
static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
page_table_check_pmd_set(mm, pmdp, pmd);
- return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+ return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd),
+ PMD_SIZE >> PAGE_SHIFT);
}
static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
pud_t *pudp, pud_t pud)
{
page_table_check_pud_set(mm, pudp, pud);
- return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+ return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud),
+ PUD_SIZE >> PAGE_SHIFT);
}
#define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d))
ARM64_FTR_END,
};
-static const struct arm64_ftr_bits ftr_zcr[] = {
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
- ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_WIDTH, 0), /* LEN */
- ARM64_FTR_END,
-};
-
-static const struct arm64_ftr_bits ftr_smcr[] = {
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
- SMCR_ELx_LEN_SHIFT, SMCR_ELx_LEN_WIDTH, 0), /* LEN */
- ARM64_FTR_END,
-};
-
/*
* Common ftr bits for a 32bit register with all hidden, strict
* attributes, with 4bit feature fields and a default safe value of
ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3),
- /* Op1 = 0, CRn = 1, CRm = 2 */
- ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
- ARM64_FTR_REG(SYS_SMCR_EL1, ftr_smcr),
-
/* Op1 = 1, CRn = 0, CRm = 0 */
ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid),
if (IS_ENABLED(CONFIG_ARM64_SVE) &&
id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) {
- info->reg_zcr = read_zcr_features();
- init_cpu_ftr_reg(SYS_ZCR_EL1, info->reg_zcr);
+ sve_kernel_enable(NULL);
vec_init_vq_map(ARM64_VEC_SVE);
}
if (IS_ENABLED(CONFIG_ARM64_SME) &&
id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) {
- info->reg_smcr = read_smcr_features();
+ sme_kernel_enable(NULL);
+
/*
* We mask out SMPS since even if the hardware
* supports priorities the kernel does not at present
* and we block access to them.
*/
info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS;
- init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr);
vec_init_vq_map(ARM64_VEC_SME);
}
taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu,
info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0);
+ /* Probe vector lengths */
if (IS_ENABLED(CONFIG_ARM64_SVE) &&
id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) {
- info->reg_zcr = read_zcr_features();
- taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
- info->reg_zcr, boot->reg_zcr);
-
- /* Probe vector lengths */
- if (!system_capabilities_finalized())
+ if (!system_capabilities_finalized()) {
+ sve_kernel_enable(NULL);
vec_update_vq_map(ARM64_VEC_SVE);
+ }
}
if (IS_ENABLED(CONFIG_ARM64_SME) &&
id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) {
- info->reg_smcr = read_smcr_features();
+ sme_kernel_enable(NULL);
+
/*
* We mask out SMPS since even if the hardware
* supports priorities the kernel does not at present
* and we block access to them.
*/
info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS;
- taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu,
- info->reg_smcr, boot->reg_smcr);
/* Probe vector lengths */
if (!system_capabilities_finalized())
early_param("kpti", parse_kpti);
#ifdef CONFIG_ARM64_HW_AFDBM
+static struct cpumask dbm_cpus __read_mostly;
+
static inline void __cpu_enable_hw_dbm(void)
{
u64 tcr = read_sysreg(tcr_el1) | TCR_HD;
static void cpu_enable_hw_dbm(struct arm64_cpu_capabilities const *cap)
{
- if (cpu_can_use_dbm(cap))
+ if (cpu_can_use_dbm(cap)) {
__cpu_enable_hw_dbm();
+ cpumask_set_cpu(smp_processor_id(), &dbm_cpus);
+ }
}
static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap,
int __unused)
{
- static bool detected = false;
/*
* DBM is a non-conflicting feature. i.e, the kernel can safely
* run a mix of CPUs with and without the feature. So, we
* unconditionally enable the capability to allow any late CPU
* to use the feature. We only enable the control bits on the
- * CPU, if it actually supports.
- *
- * We have to make sure we print the "feature" detection only
- * when at least one CPU actually uses it. So check if this CPU
- * can actually use it and print the message exactly once.
- *
- * This is safe as all CPUs (including secondary CPUs - due to the
- * LOCAL_CPU scope - and the hotplugged CPUs - via verification)
- * goes through the "matches" check exactly once. Also if a CPU
- * matches the criteria, it is guaranteed that the CPU will turn
- * the DBM on, as the capability is unconditionally enabled.
+ * CPU, if it is supported.
*/
- if (!detected && cpu_can_use_dbm(cap)) {
- detected = true;
- pr_info("detected: Hardware dirty bit management\n");
- }
return true;
}
static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
{
if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) {
- pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
- smp_processor_id());
cpumask_set_cpu(smp_processor_id(), &amu_cpus);
/* 0 reference values signal broken/disabled counters */
#endif /* CONFIG_ARM64_RAS_EXTN */
#ifdef CONFIG_ARM64_AMU_EXTN
{
- /*
- * The feature is enabled by default if CONFIG_ARM64_AMU_EXTN=y.
- * Therefore, don't provide .desc as we don't want the detection
- * message to be shown until at least one CPU is detected to
- * support the feature.
- */
+ .desc = "Activity Monitors Unit (AMU)",
.capability = ARM64_HAS_AMU_EXTN,
.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
.matches = has_amu,
.cpu_enable = cpu_amu_enable,
+ .cpus = &amu_cpus,
ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, AMU, IMP)
},
#endif /* CONFIG_ARM64_AMU_EXTN */
},
#ifdef CONFIG_ARM64_HW_AFDBM
{
- /*
- * Since we turn this on always, we don't want the user to
- * think that the feature is available when it may not be.
- * So hide the description.
- *
- * .desc = "Hardware pagetable Dirty Bit Management",
- *
- */
+ .desc = "Hardware dirty bit management",
.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
.capability = ARM64_HW_DBM,
.matches = has_hw_dbm,
.cpu_enable = cpu_enable_hw_dbm,
+ .cpus = &dbm_cpus,
ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, DBM)
},
#endif
!caps->matches(caps, cpucap_default_scope(caps)))
continue;
- if (caps->desc)
+ if (caps->desc && !caps->cpus)
pr_info("detected: %s\n", caps->desc);
__set_bit(caps->capability, system_cpucaps);
static void verify_sve_features(void)
{
- u64 safe_zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
- u64 zcr = read_zcr_features();
-
- unsigned int safe_len = safe_zcr & ZCR_ELx_LEN_MASK;
- unsigned int len = zcr & ZCR_ELx_LEN_MASK;
-
- if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SVE)) {
+ if (vec_verify_vq_map(ARM64_VEC_SVE)) {
pr_crit("CPU%d: SVE: vector length support mismatch\n",
smp_processor_id());
cpu_die_early();
}
-
- /* Add checks on other ZCR bits here if necessary */
}
static void verify_sme_features(void)
{
- u64 safe_smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
- u64 smcr = read_smcr_features();
-
- unsigned int safe_len = safe_smcr & SMCR_ELx_LEN_MASK;
- unsigned int len = smcr & SMCR_ELx_LEN_MASK;
-
- if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) {
+ if (vec_verify_vq_map(ARM64_VEC_SME)) {
pr_crit("CPU%d: SME: vector length support mismatch\n",
smp_processor_id());
cpu_die_early();
}
-
- /* Add checks on other SMCR bits here if necessary */
}
static void verify_hyp_capabilities(void)
static void __init setup_system_capabilities(void)
{
+ int i;
/*
* We have finalised the system-wide safe feature
* registers, finalise the capabilities that depend
*/
update_cpu_capabilities(SCOPE_SYSTEM);
enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU);
+
+ for (i = 0; i < ARM64_NCAPS; i++) {
+ const struct arm64_cpu_capabilities *caps = cpucap_ptrs[i];
+
+ if (caps && caps->cpus && caps->desc &&
+ cpumask_any(caps->cpus) < nr_cpu_ids)
+ pr_info("detected: %s on CPU%*pbl\n",
+ caps->desc, cpumask_pr_args(caps->cpus));
+ }
}
void __init setup_cpu_features(void)
isb();
}
-/*
- * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
- * vector length.
- *
- * Use only if SVE is present.
- * This function clobbers the SVE vector length.
- */
-u64 read_zcr_features(void)
-{
- /*
- * Set the maximum possible VL, and write zeroes to all other
- * bits to see if they stick.
- */
- sve_kernel_enable(NULL);
- write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
-
- /* Return LEN value that would be written to get the maximum VL */
- return sve_vq_from_vl(sve_get_vl()) - 1;
-}
-
void __init sve_setup(void)
{
struct vl_info *info = &vl_info[ARM64_VEC_SVE];
- u64 zcr;
DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
unsigned long b;
+ int max_bit;
if (!system_supports_sve())
return;
if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map)))
set_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map);
- zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
- info->max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);
-
- /*
- * Sanity-check that the max VL we determined through CPU features
- * corresponds properly to sve_vq_map. If not, do our best:
- */
- if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SVE,
- info->max_vl)))
- info->max_vl = find_supported_vector_length(ARM64_VEC_SVE,
- info->max_vl);
+ max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX);
+ info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit));
/*
* For the default VL, pick the maximum supported value <= 64.
SYS_SMCR_EL1);
}
-/*
- * Read the pseudo-SMCR used by cpufeatures to identify the supported
- * vector length.
- *
- * Use only if SME is present.
- * This function clobbers the SME vector length.
- */
-u64 read_smcr_features(void)
-{
- sme_kernel_enable(NULL);
-
- /*
- * Set the maximum possible VL.
- */
- write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK,
- SYS_SMCR_EL1);
-
- /* Return LEN value that would be written to get the maximum VL */
- return sve_vq_from_vl(sme_get_vl()) - 1;
-}
-
void __init sme_setup(void)
{
struct vl_info *info = &vl_info[ARM64_VEC_SME];
- u64 smcr;
- int min_bit;
+ int min_bit, max_bit;
if (!system_supports_sme())
return;
* SME doesn't require any particular vector length be
* supported but it does require at least one. We should have
* disabled the feature entirely while bringing up CPUs but
- * let's double check here.
+ * let's double check here. The bitmap is SVE_VQ_MAP sized for
+ * sharing with SVE.
*/
WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX));
min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX);
info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit));
- smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
- info->max_vl = sve_vl_from_vq((smcr & SMCR_ELx_LEN_MASK) + 1);
-
- /*
- * Sanity-check that the max VL we determined through CPU features
- * corresponds properly to sme_vq_map. If not, do our best:
- */
- if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SME,
- info->max_vl)))
- info->max_vl = find_supported_vector_length(ARM64_VEC_SME,
- info->max_vl);
+ max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX);
+ info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit));
WARN_ON(info->min_vl > info->max_vl);
switch (ELF64_R_TYPE(rela[i].r_info)) {
case R_AARCH64_JUMP26:
case R_AARCH64_CALL26:
- if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
- break;
-
/*
* We only have to consider branch targets that resolve
* to symbols that are defined in a different section.
{
int i = 0, j = numrels - 1;
- if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
- return 0;
-
while (i < j) {
if (branch_rela_needs_plt(syms, &rela[i], dstidx))
i++;
EXPORT_SYMBOL_GPL(mte_async_or_asymm_mode);
#endif
-void mte_sync_tags(pte_t pte)
+void mte_sync_tags(pte_t pte, unsigned int nr_pages)
{
struct page *page = pte_page(pte);
- long i, nr_pages = compound_nr(page);
+ unsigned int i;
/* if PG_mte_tagged is set, tags have already been initialised */
for (i = 0; i < nr_pages; i++, page++) {
{
u64 hwid = processor->arm_mpidr;
- if (!(processor->flags & ACPI_MADT_ENABLED)) {
+ if (!acpi_gicc_is_usable(processor)) {
pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
return;
}
break;
case ARM_CPU_IMP_APM:
switch (part_number) {
- case APM_CPU_PART_POTENZA:
+ case APM_CPU_PART_XGENE:
return KVM_ARM_TARGET_XGENE_POTENZA;
}
break;
#include <linux/nodemask.h>
#include <linux/initrd.h>
#include <linux/gfp.h>
+#include <linux/math.h>
#include <linux/memblock.h>
#include <linux/sort.h>
#include <linux/of.h>
{
bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
- if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC))
+ if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) {
+ /*
+ * If no bouncing needed for ZONE_DMA, reduce the swiotlb
+ * buffer for kmalloc() bouncing to 1MB per 1GB of RAM.
+ */
+ unsigned long size =
+ DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
+ swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
swiotlb = true;
+ }
swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
struct acpi_madt_generic_interrupt *gicc =
container_of(entry, struct acpi_madt_generic_interrupt, header);
- if (!(gicc->flags & ACPI_MADT_ENABLED))
+ if (!acpi_gicc_is_usable(gicc))
return -ENODEV;
/* device_declaration means Device object in DSDT, in the
* Note that TVAL is signed, thus has only 31 of its
* 32 bits to express magnitude.
*/
- MIDR_ALL_VERSIONS(MIDR_CPU_MODEL(ARM_CPU_IMP_APM,
- APM_CPU_PART_POTENZA)),
+ MIDR_REV_RANGE(MIDR_CPU_MODEL(ARM_CPU_IMP_APM,
+ APM_CPU_PART_XGENE),
+ APM_CPU_VAR_POTENZA, 0x0, 0xf),
{},
};
u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2;
void __iomem *redist_base;
- /* GICC entry which has !ACPI_MADT_ENABLED is not unusable so skip */
- if (!(gicc->flags & ACPI_MADT_ENABLED))
+ if (!acpi_gicc_is_usable(gicc))
return 0;
redist_base = ioremap(gicc->gicr_base_address, size);
* If GICC is enabled and has valid gicr base address, then it means
* GICR base is presented via GICC
*/
- if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) {
+ if (acpi_gicc_is_usable(gicc) && gicc->gicr_base_address) {
acpi_data.enabled_rdists++;
return 0;
}
* It's perfectly valid firmware can pass disabled GICC entry, driver
* should not treat as errors, skip the entry instead of probe fail.
*/
- if (!(gicc->flags & ACPI_MADT_ENABLED))
+ if (!acpi_gicc_is_usable(gicc))
return 0;
return -ENODEV;
int maint_irq_mode;
static int first_madt = true;
- /* Skip unusable CPUs */
- if (!(gicc->flags & ACPI_MADT_ENABLED))
+ if (!acpi_gicc_is_usable(gicc))
return 0;
maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ?
},
{}
};
+MODULE_DEVICE_TABLE(of, meson_ddr_pmu_dt_match);
static struct platform_driver g12_ddr_pmu_driver = {
.probe = g12_ddr_pmu_probe,
#define CMN_DTM_PMEVCNTSR 0x240
-#define CMN_DTM_UNIT_INFO 0x0910
+#define CMN650_DTM_UNIT_INFO 0x0910
+#define CMN_DTM_UNIT_INFO 0x0960
+#define CMN_DTM_UNIT_INFO_DTC_DOMAIN GENMASK_ULL(1, 0)
#define CMN_DTM_NUM_COUNTERS 4
/* Want more local counters? Why not replicate the whole DTM! Ugh... */
u16 id, logid;
enum cmn_node_type type;
- int dtm;
- union {
- /* DN/HN-F/CXHA */
- struct {
- u8 val : 4;
- u8 count : 4;
- } occupid[SEL_MAX];
- /* XP */
- u8 dtc;
- };
+ u8 dtm;
+ s8 dtc;
+ /* DN/HN-F/CXHA */
+ struct {
+ u8 val : 4;
+ u8 count : 4;
+ } occupid[SEL_MAX];
union {
u8 event[4];
__le32 event_sel;
seq_puts(s, "\n |");
for (x = 0; x < cmn->mesh_x; x++) {
- u8 dtc = cmn->xps[xp_base + x].dtc;
+ s8 dtc = cmn->xps[xp_base + x].dtc;
- if (dtc & (dtc - 1))
+ if (dtc < 0)
seq_puts(s, " DTC ?? |");
else
- seq_printf(s, " DTC %ld |", __ffs(dtc));
+ seq_printf(s, " DTC %d |", dtc);
}
seq_puts(s, "\n |");
for (x = 0; x < cmn->mesh_x; x++)
struct arm_cmn_hw_event {
struct arm_cmn_node *dn;
u64 dtm_idx[4];
- unsigned int dtc_idx;
- u8 dtcs_used;
+ s8 dtc_idx[CMN_MAX_DTCS];
u8 num_dns;
u8 dtm_offset;
bool wide_sel;
#define for_each_hw_dn(hw, dn, i) \
for (i = 0, dn = hw->dn; i < hw->num_dns; i++, dn++)
+/* @i is the DTC number, @idx is the counter index on that DTC */
+#define for_each_hw_dtc_idx(hw, i, idx) \
+ for (int i = 0, idx; i < CMN_MAX_DTCS; i++) if ((idx = hw->dtc_idx[i]) >= 0)
+
static struct arm_cmn_hw_event *to_cmn_hw(struct perf_event *event)
{
BUILD_BUG_ON(sizeof(struct arm_cmn_hw_event) > offsetof(struct hw_perf_event, target));
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
- unsigned int i, pmevcnt = CMN_DT_PMEVCNT(hw->dtc_idx);
u64 count;
- for (i = 0; hw->dtcs_used & (1U << i); i++) {
- writel_relaxed(CMN_COUNTER_INIT, cmn->dtc[i].base + pmevcnt);
- cmn->dtc[i].counters[hw->dtc_idx] = event;
+ for_each_hw_dtc_idx(hw, i, idx) {
+ writel_relaxed(CMN_COUNTER_INIT, cmn->dtc[i].base + CMN_DT_PMEVCNT(idx));
+ cmn->dtc[i].counters[idx] = event;
}
count = arm_cmn_read_dtm(cmn, hw, false);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
u64 delta, new, prev;
unsigned long flags;
- unsigned int i;
- if (hw->dtc_idx == CMN_DT_NUM_COUNTERS) {
- i = __ffs(hw->dtcs_used);
- delta = arm_cmn_read_cc(cmn->dtc + i);
+ if (CMN_EVENT_TYPE(event) == CMN_TYPE_DTC) {
+ delta = arm_cmn_read_cc(cmn->dtc + hw->dtc_idx[0]);
local64_add(delta, &event->count);
return;
}
delta = new - prev;
local_irq_save(flags);
- for (i = 0; hw->dtcs_used & (1U << i); i++) {
- new = arm_cmn_read_counter(cmn->dtc + i, hw->dtc_idx);
+ for_each_hw_dtc_idx(hw, i, idx) {
+ new = arm_cmn_read_counter(cmn->dtc + i, idx);
delta += new << 16;
}
local_irq_restore(flags);
int i;
if (type == CMN_TYPE_DTC) {
- i = __ffs(hw->dtcs_used);
+ i = hw->dtc_idx[0];
writeq_relaxed(CMN_CC_INIT, cmn->dtc[i].base + CMN_DT_PMCCNTR);
cmn->dtc[i].cc_active = true;
} else if (type == CMN_TYPE_WP) {
int i;
if (type == CMN_TYPE_DTC) {
- i = __ffs(hw->dtcs_used);
+ i = hw->dtc_idx[0];
cmn->dtc[i].cc_active = false;
} else if (type == CMN_TYPE_WP) {
int wp_idx = arm_cmn_wp_idx(event);
u8 dtm_count[CMN_MAX_DTMS];
u8 occupid[CMN_MAX_DTMS][SEL_MAX];
u8 wp[CMN_MAX_DTMS][4];
- int dtc_count;
+ int dtc_count[CMN_MAX_DTCS];
bool cycles;
};
return;
}
- val->dtc_count++;
+ for_each_hw_dtc_idx(hw, dtc, idx)
+ val->dtc_count[dtc]++;
for_each_hw_dn(hw, dn, i) {
int wp_idx, dtm = dn->dtm, sel = hw->filter_sel;
goto done;
}
- if (val->dtc_count == CMN_DT_NUM_COUNTERS)
- goto done;
+ for (i = 0; i < CMN_MAX_DTCS; i++)
+ if (val->dtc_count[i] == CMN_DT_NUM_COUNTERS)
+ goto done;
for_each_hw_dn(hw, dn, i) {
int wp_idx, wp_cmb, dtm = dn->dtm, sel = hw->filter_sel;
hw->dn = arm_cmn_node(cmn, type);
if (!hw->dn)
return -EINVAL;
+
+ memset(hw->dtc_idx, -1, sizeof(hw->dtc_idx));
for (dn = hw->dn; dn->type == type; dn++) {
if (bynodeid && dn->id != nodeid) {
hw->dn++;
continue;
}
hw->num_dns++;
+ if (dn->dtc < 0)
+ memset(hw->dtc_idx, 0, cmn->num_dtcs);
+ else
+ hw->dtc_idx[dn->dtc] = 0;
+
if (bynodeid)
break;
}
nodeid, nid.x, nid.y, nid.port, nid.dev, type);
return -EINVAL;
}
- /*
- * Keep assuming non-cycles events count in all DTC domains; turns out
- * it's hard to make a worthwhile optimisation around this, short of
- * going all-in with domain-local counter allocation as well.
- */
- hw->dtcs_used = (1U << cmn->num_dtcs) - 1;
return arm_cmn_validate_group(cmn, event);
}
}
memset(hw->dtm_idx, 0, sizeof(hw->dtm_idx));
- for (i = 0; hw->dtcs_used & (1U << i); i++)
- cmn->dtc[i].counters[hw->dtc_idx] = NULL;
+ for_each_hw_dtc_idx(hw, j, idx)
+ cmn->dtc[j].counters[idx] = NULL;
}
static int arm_cmn_event_add(struct perf_event *event, int flags)
{
struct arm_cmn *cmn = to_cmn(event->pmu);
struct arm_cmn_hw_event *hw = to_cmn_hw(event);
- struct arm_cmn_dtc *dtc = &cmn->dtc[0];
struct arm_cmn_node *dn;
enum cmn_node_type type = CMN_EVENT_TYPE(event);
- unsigned int i, dtc_idx, input_sel;
+ unsigned int input_sel, i = 0;
if (type == CMN_TYPE_DTC) {
- i = 0;
while (cmn->dtc[i].cycles)
if (++i == cmn->num_dtcs)
return -ENOSPC;
cmn->dtc[i].cycles = event;
- hw->dtc_idx = CMN_DT_NUM_COUNTERS;
- hw->dtcs_used = 1U << i;
+ hw->dtc_idx[0] = i;
if (flags & PERF_EF_START)
arm_cmn_event_start(event, 0);
return 0;
}
- /* Grab a free global counter first... */
- dtc_idx = 0;
- while (dtc->counters[dtc_idx])
- if (++dtc_idx == CMN_DT_NUM_COUNTERS)
- return -ENOSPC;
-
- hw->dtc_idx = dtc_idx;
+ /* Grab the global counters first... */
+ for_each_hw_dtc_idx(hw, j, idx) {
+ if (cmn->part == PART_CMN600 && j > 0) {
+ idx = hw->dtc_idx[0];
+ } else {
+ idx = 0;
+ while (cmn->dtc[j].counters[idx])
+ if (++idx == CMN_DT_NUM_COUNTERS)
+ goto free_dtms;
+ }
+ hw->dtc_idx[j] = idx;
+ }
- /* ...then the local counters to feed it. */
+ /* ...then the local counters to feed them */
for_each_hw_dn(hw, dn, i) {
struct arm_cmn_dtm *dtm = &cmn->dtms[dn->dtm] + hw->dtm_offset;
- unsigned int dtm_idx, shift;
+ unsigned int dtm_idx, shift, d = max_t(int, dn->dtc, 0);
u64 reg;
dtm_idx = 0;
tmp = dtm->wp_event[wp_idx ^ 1];
if (tmp >= 0 && CMN_EVENT_WP_COMBINE(event) !=
- CMN_EVENT_WP_COMBINE(dtc->counters[tmp]))
+ CMN_EVENT_WP_COMBINE(cmn->dtc[d].counters[tmp]))
goto free_dtms;
input_sel = CMN__PMEVCNT0_INPUT_SEL_WP + wp_idx;
- dtm->wp_event[wp_idx] = dtc_idx;
+ dtm->wp_event[wp_idx] = hw->dtc_idx[d];
writel_relaxed(cfg, dtm->base + CMN_DTM_WPn_CONFIG(wp_idx));
} else {
struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
dtm->input_sel[dtm_idx] = input_sel;
shift = CMN__PMEVCNTn_GLOBAL_NUM_SHIFT(dtm_idx);
dtm->pmu_config_low &= ~(CMN__PMEVCNT0_GLOBAL_NUM << shift);
- dtm->pmu_config_low |= FIELD_PREP(CMN__PMEVCNT0_GLOBAL_NUM, dtc_idx) << shift;
+ dtm->pmu_config_low |= FIELD_PREP(CMN__PMEVCNT0_GLOBAL_NUM, hw->dtc_idx[d]) << shift;
dtm->pmu_config_low |= CMN__PMEVCNT_PAIRED(dtm_idx);
reg = (u64)le32_to_cpu(dtm->pmu_config_high) << 32 | dtm->pmu_config_low;
writeq_relaxed(reg, dtm->base + CMN_DTM_PMU_CONFIG);
arm_cmn_event_stop(event, PERF_EF_UPDATE);
if (type == CMN_TYPE_DTC)
- cmn->dtc[__ffs(hw->dtcs_used)].cycles = NULL;
+ cmn->dtc[hw->dtc_idx[0]].cycles = NULL;
else
arm_cmn_event_clear(cmn, event, hw->num_dns);
}
{
struct arm_cmn_node *dn, *xp;
int dtc_idx = 0;
- u8 dtcs_present = (1 << cmn->num_dtcs) - 1;
cmn->dtc = devm_kcalloc(cmn->dev, cmn->num_dtcs, sizeof(cmn->dtc[0]), GFP_KERNEL);
if (!cmn->dtc)
cmn->xps = arm_cmn_node(cmn, CMN_TYPE_XP);
+ if (cmn->part == PART_CMN600 && cmn->num_dtcs > 1) {
+ /* We do at least know that a DTC's XP must be in that DTC's domain */
+ dn = arm_cmn_node(cmn, CMN_TYPE_DTC);
+ for (int i = 0; i < cmn->num_dtcs; i++)
+ arm_cmn_node_to_xp(cmn, dn + i)->dtc = i;
+ }
+
for (dn = cmn->dns; dn->type; dn++) {
- if (dn->type == CMN_TYPE_XP) {
- dn->dtc &= dtcs_present;
+ if (dn->type == CMN_TYPE_XP)
continue;
- }
xp = arm_cmn_node_to_xp(cmn, dn);
+ dn->dtc = xp->dtc;
dn->dtm = xp->dtm;
if (cmn->multi_dtm)
dn->dtm += arm_cmn_nid(cmn, dn->id).port / 2;
if (dn->type == CMN_TYPE_DTC) {
- int err;
- /* We do at least know that a DTC's XP must be in that DTC's domain */
- if (xp->dtc == 0xf)
- xp->dtc = 1 << dtc_idx;
- err = arm_cmn_init_dtc(cmn, dn, dtc_idx++);
+ int err = arm_cmn_init_dtc(cmn, dn, dtc_idx++);
+
if (err)
return err;
}
return 0;
}
+static unsigned int arm_cmn_dtc_domain(struct arm_cmn *cmn, void __iomem *xp_region)
+{
+ int offset = CMN_DTM_UNIT_INFO;
+
+ if (cmn->part == PART_CMN650 || cmn->part == PART_CI700)
+ offset = CMN650_DTM_UNIT_INFO;
+
+ return FIELD_GET(CMN_DTM_UNIT_INFO_DTC_DOMAIN, readl_relaxed(xp_region + offset));
+}
+
static void arm_cmn_init_node_info(struct arm_cmn *cmn, u32 offset, struct arm_cmn_node *node)
{
int level;
cmn->mesh_x = xp->logid;
if (cmn->part == PART_CMN600)
- xp->dtc = 0xf;
+ xp->dtc = -1;
else
- xp->dtc = 1 << readl_relaxed(xp_region + CMN_DTM_UNIT_INFO);
+ xp->dtc = arm_cmn_dtc_domain(cmn, xp_region);
xp->dtm = dtm - cmn->dtms;
arm_cmn_init_dtm(dtm++, xp, 0);
# SPDX-License-Identifier: GPL-2.0
#
-# Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
config ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
tristate "ARM Coresight Architecture PMU"
based on ARM CoreSight PMU architecture. Note that this PMU
architecture does not have relationship with the ARM CoreSight
Self-Hosted Tracing.
+
+config NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+ tristate "NVIDIA Coresight Architecture PMU"
+ depends on ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+ help
+ Provides NVIDIA specific attributes for performance monitoring unit
+ (PMU) devices based on ARM CoreSight PMU architecture.
+
+config AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+ tristate "Ampere Coresight Architecture PMU"
+ depends on ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+ help
+ Provides Ampere specific attributes for performance monitoring unit
+ (PMU) devices based on ARM CoreSight PMU architecture.
+
+ In the first phase, the driver enables support on MCU PMU used in
+ AmpereOne SoC family.
-# Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
#
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu_module.o
-arm_cspmu_module-y := arm_cspmu.o nvidia_cspmu.o
+
+arm_cspmu_module-y := arm_cspmu.o
+
+obj-$(CONFIG_NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += nvidia_cspmu.o
+obj-$(CONFIG_AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += ampere_cspmu.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ampere SoC PMU (Performance Monitor Unit)
+ *
+ * Copyright (c) 2023, Ampere Computing LLC
+ */
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include "arm_cspmu.h"
+
+#define PMAUXR0 0xD80
+#define PMAUXR1 0xD84
+#define PMAUXR2 0xD88
+#define PMAUXR3 0xD8C
+
+#define to_ampere_cspmu_ctx(cspmu) ((struct ampere_cspmu_ctx *)(cspmu->impl.ctx))
+
+struct ampere_cspmu_ctx {
+ const char *name;
+ struct attribute **event_attr;
+ struct attribute **format_attr;
+};
+
+static DEFINE_IDA(mcu_pmu_ida);
+
+#define SOC_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end) \
+ static inline u32 get_##_name(const struct perf_event *event) \
+ { \
+ return FIELD_GET(GENMASK_ULL(_end, _start), \
+ event->attr._config); \
+ } \
+
+SOC_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 8);
+SOC_PMU_EVENT_ATTR_EXTRACTOR(threshold, config1, 0, 7);
+SOC_PMU_EVENT_ATTR_EXTRACTOR(rank, config1, 8, 23);
+SOC_PMU_EVENT_ATTR_EXTRACTOR(bank, config1, 24, 55);
+
+static struct attribute *ampereone_mcu_pmu_event_attrs[] = {
+ ARM_CSPMU_EVENT_ATTR(cycle_count, 0x00),
+ ARM_CSPMU_EVENT_ATTR(act_sent, 0x01),
+ ARM_CSPMU_EVENT_ATTR(pre_sent, 0x02),
+ ARM_CSPMU_EVENT_ATTR(rd_sent, 0x03),
+ ARM_CSPMU_EVENT_ATTR(rda_sent, 0x04),
+ ARM_CSPMU_EVENT_ATTR(wr_sent, 0x05),
+ ARM_CSPMU_EVENT_ATTR(wra_sent, 0x06),
+ ARM_CSPMU_EVENT_ATTR(pd_entry_vld, 0x07),
+ ARM_CSPMU_EVENT_ATTR(sref_entry_vld, 0x08),
+ ARM_CSPMU_EVENT_ATTR(prea_sent, 0x09),
+ ARM_CSPMU_EVENT_ATTR(pre_sb_sent, 0x0a),
+ ARM_CSPMU_EVENT_ATTR(ref_sent, 0x0b),
+ ARM_CSPMU_EVENT_ATTR(rfm_sent, 0x0c),
+ ARM_CSPMU_EVENT_ATTR(ref_sb_sent, 0x0d),
+ ARM_CSPMU_EVENT_ATTR(rfm_sb_sent, 0x0e),
+ ARM_CSPMU_EVENT_ATTR(rd_rda_sent, 0x0f),
+ ARM_CSPMU_EVENT_ATTR(wr_wra_sent, 0x10),
+ ARM_CSPMU_EVENT_ATTR(raw_hazard, 0x11),
+ ARM_CSPMU_EVENT_ATTR(war_hazard, 0x12),
+ ARM_CSPMU_EVENT_ATTR(waw_hazard, 0x13),
+ ARM_CSPMU_EVENT_ATTR(rar_hazard, 0x14),
+ ARM_CSPMU_EVENT_ATTR(raw_war_waw_hazard, 0x15),
+ ARM_CSPMU_EVENT_ATTR(hprd_lprd_wr_req_vld, 0x16),
+ ARM_CSPMU_EVENT_ATTR(lprd_req_vld, 0x17),
+ ARM_CSPMU_EVENT_ATTR(hprd_req_vld, 0x18),
+ ARM_CSPMU_EVENT_ATTR(hprd_lprd_req_vld, 0x19),
+ ARM_CSPMU_EVENT_ATTR(prefetch_tgt, 0x1a),
+ ARM_CSPMU_EVENT_ATTR(wr_req_vld, 0x1b),
+ ARM_CSPMU_EVENT_ATTR(partial_wr_req_vld, 0x1c),
+ ARM_CSPMU_EVENT_ATTR(rd_retry, 0x1d),
+ ARM_CSPMU_EVENT_ATTR(wr_retry, 0x1e),
+ ARM_CSPMU_EVENT_ATTR(retry_gnt, 0x1f),
+ ARM_CSPMU_EVENT_ATTR(rank_change, 0x20),
+ ARM_CSPMU_EVENT_ATTR(dir_change, 0x21),
+ ARM_CSPMU_EVENT_ATTR(rank_dir_change, 0x22),
+ ARM_CSPMU_EVENT_ATTR(rank_active, 0x23),
+ ARM_CSPMU_EVENT_ATTR(rank_idle, 0x24),
+ ARM_CSPMU_EVENT_ATTR(rank_pd, 0x25),
+ ARM_CSPMU_EVENT_ATTR(rank_sref, 0x26),
+ ARM_CSPMU_EVENT_ATTR(queue_fill_gt_thresh, 0x27),
+ ARM_CSPMU_EVENT_ATTR(queue_rds_gt_thresh, 0x28),
+ ARM_CSPMU_EVENT_ATTR(queue_wrs_gt_thresh, 0x29),
+ ARM_CSPMU_EVENT_ATTR(phy_updt_complt, 0x2a),
+ ARM_CSPMU_EVENT_ATTR(tz_fail, 0x2b),
+ ARM_CSPMU_EVENT_ATTR(dram_errc, 0x2c),
+ ARM_CSPMU_EVENT_ATTR(dram_errd, 0x2d),
+ ARM_CSPMU_EVENT_ATTR(read_data_return, 0x32),
+ ARM_CSPMU_EVENT_ATTR(chi_wr_data_delta, 0x33),
+ ARM_CSPMU_EVENT_ATTR(zq_start, 0x34),
+ ARM_CSPMU_EVENT_ATTR(zq_latch, 0x35),
+ ARM_CSPMU_EVENT_ATTR(wr_fifo_full, 0x36),
+ ARM_CSPMU_EVENT_ATTR(info_fifo_full, 0x37),
+ ARM_CSPMU_EVENT_ATTR(cmd_fifo_full, 0x38),
+ ARM_CSPMU_EVENT_ATTR(dfi_nop, 0x39),
+ ARM_CSPMU_EVENT_ATTR(dfi_cmd, 0x3a),
+ ARM_CSPMU_EVENT_ATTR(rd_run_len, 0x3b),
+ ARM_CSPMU_EVENT_ATTR(wr_run_len, 0x3c),
+
+ ARM_CSPMU_EVENT_ATTR(cycles, ARM_CSPMU_EVT_CYCLES_DEFAULT),
+ NULL,
+};
+
+static struct attribute *ampereone_mcu_format_attrs[] = {
+ ARM_CSPMU_FORMAT_EVENT_ATTR,
+ ARM_CSPMU_FORMAT_ATTR(threshold, "config1:0-7"),
+ ARM_CSPMU_FORMAT_ATTR(rank, "config1:8-23"),
+ ARM_CSPMU_FORMAT_ATTR(bank, "config1:24-55"),
+ NULL,
+};
+
+static struct attribute **
+ampere_cspmu_get_event_attrs(const struct arm_cspmu *cspmu)
+{
+ const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu);
+
+ return ctx->event_attr;
+}
+
+static struct attribute **
+ampere_cspmu_get_format_attrs(const struct arm_cspmu *cspmu)
+{
+ const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu);
+
+ return ctx->format_attr;
+}
+
+static const char *
+ampere_cspmu_get_name(const struct arm_cspmu *cspmu)
+{
+ const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu);
+
+ return ctx->name;
+}
+
+static u32 ampere_cspmu_event_filter(const struct perf_event *event)
+{
+ /*
+ * PMEVFILTR or PMCCFILTR aren't used in Ampere SoC PMU but are marked
+ * as RES0. Make sure, PMCCFILTR is written zero.
+ */
+ return 0;
+}
+
+static void ampere_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
+ struct hw_perf_event *hwc,
+ u32 filter)
+{
+ struct perf_event *event;
+ unsigned int idx;
+ u32 threshold, rank, bank;
+
+ /*
+ * At this point, all the events have the same filter settings.
+ * Therefore, take the first event and use its configuration.
+ */
+ idx = find_first_bit(cspmu->hw_events.used_ctrs,
+ cspmu->cycle_counter_logical_idx);
+
+ event = cspmu->hw_events.events[idx];
+
+ threshold = get_threshold(event);
+ rank = get_rank(event);
+ bank = get_bank(event);
+
+ writel(threshold, cspmu->base0 + PMAUXR0);
+ writel(rank, cspmu->base0 + PMAUXR1);
+ writel(bank, cspmu->base0 + PMAUXR2);
+}
+
+static int ampere_cspmu_validate_configs(struct perf_event *event,
+ struct perf_event *event2)
+{
+ if (get_threshold(event) != get_threshold(event2) ||
+ get_rank(event) != get_rank(event2) ||
+ get_bank(event) != get_bank(event2))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ampere_cspmu_validate_event(struct arm_cspmu *cspmu,
+ struct perf_event *new)
+{
+ struct perf_event *curr, *leader = new->group_leader;
+ unsigned int idx;
+ int ret;
+
+ ret = ampere_cspmu_validate_configs(new, leader);
+ if (ret)
+ return ret;
+
+ /* We compare the global filter settings to the existing events */
+ idx = find_first_bit(cspmu->hw_events.used_ctrs,
+ cspmu->cycle_counter_logical_idx);
+
+ /* This is the first event, thus any configuration is fine */
+ if (idx == cspmu->cycle_counter_logical_idx)
+ return 0;
+
+ curr = cspmu->hw_events.events[idx];
+
+ return ampere_cspmu_validate_configs(curr, new);
+}
+
+static char *ampere_cspmu_format_name(const struct arm_cspmu *cspmu,
+ const char *name_pattern)
+{
+ struct device *dev = cspmu->dev;
+ int id;
+
+ id = ida_alloc(&mcu_pmu_ida, GFP_KERNEL);
+ if (id < 0)
+ return ERR_PTR(id);
+
+ return devm_kasprintf(dev, GFP_KERNEL, name_pattern, id);
+}
+
+static int ampere_cspmu_init_ops(struct arm_cspmu *cspmu)
+{
+ struct device *dev = cspmu->dev;
+ struct ampere_cspmu_ctx *ctx;
+ struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
+
+ ctx = devm_kzalloc(dev, sizeof(struct ampere_cspmu_ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->event_attr = ampereone_mcu_pmu_event_attrs;
+ ctx->format_attr = ampereone_mcu_format_attrs;
+ ctx->name = ampere_cspmu_format_name(cspmu, "ampere_mcu_pmu_%d");
+ if (IS_ERR_OR_NULL(ctx->name))
+ return ctx->name ? PTR_ERR(ctx->name) : -ENOMEM;
+
+ cspmu->impl.ctx = ctx;
+
+ impl_ops->event_filter = ampere_cspmu_event_filter;
+ impl_ops->set_ev_filter = ampere_cspmu_set_ev_filter;
+ impl_ops->validate_event = ampere_cspmu_validate_event;
+ impl_ops->get_name = ampere_cspmu_get_name;
+ impl_ops->get_event_attrs = ampere_cspmu_get_event_attrs;
+ impl_ops->get_format_attrs = ampere_cspmu_get_format_attrs;
+
+ return 0;
+}
+
+/* Match all Ampere Coresight PMU devices */
+static const struct arm_cspmu_impl_match ampere_cspmu_param = {
+ .pmiidr_val = ARM_CSPMU_IMPL_ID_AMPERE,
+ .module = THIS_MODULE,
+ .impl_init_ops = ampere_cspmu_init_ops
+};
+
+static int __init ampere_cspmu_init(void)
+{
+ int ret;
+
+ ret = arm_cspmu_impl_register(&ere_cspmu_param);
+ if (ret)
+ pr_err("ampere_cspmu backend registration error: %d\n", ret);
+
+ return ret;
+}
+
+static void __exit ampere_cspmu_exit(void)
+{
+ arm_cspmu_impl_unregister(&ere_cspmu_param);
+}
+
+module_init(ampere_cspmu_init);
+module_exit(ampere_cspmu_exit);
+
+MODULE_LICENSE("GPL");
* The user should refer to the vendor technical documentation to get details
* about the supported events.
*
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
*
*/
#include <linux/interrupt.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/module.h>
+#include <linux/mutex.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include "arm_cspmu.h"
-#include "nvidia_cspmu.h"
#define PMUNAME "arm_cspmu"
#define DRVNAME "arm-cs-arch-pmu"
*/
#define HILOHI_MAX_POLL 1000
-/* JEDEC-assigned JEP106 identification code */
-#define ARM_CSPMU_IMPL_ID_NVIDIA 0x36B
-
static unsigned long arm_cspmu_cpuhp_state;
+static DEFINE_MUTEX(arm_cspmu_lock);
+
+static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
+ struct hw_perf_event *hwc, u32 filter);
+
static struct acpi_apmt_node *arm_cspmu_apmt_node(struct device *dev)
{
return *(struct acpi_apmt_node **)dev_get_platdata(dev);
.attrs = arm_cspmu_cpumask_attrs,
};
-struct impl_match {
- u32 pmiidr;
- u32 mask;
- int (*impl_init_ops)(struct arm_cspmu *cspmu);
-};
-
-static const struct impl_match impl_match[] = {
+static struct arm_cspmu_impl_match impl_match[] = {
{
- .pmiidr = ARM_CSPMU_IMPL_ID_NVIDIA,
- .mask = ARM_CSPMU_PMIIDR_IMPLEMENTER,
- .impl_init_ops = nv_cspmu_init_ops
+ .module_name = "nvidia_cspmu",
+ .pmiidr_val = ARM_CSPMU_IMPL_ID_NVIDIA,
+ .pmiidr_mask = ARM_CSPMU_PMIIDR_IMPLEMENTER,
+ .module = NULL,
+ .impl_init_ops = NULL,
},
- {}
+ {
+ .module_name = "ampere_cspmu",
+ .pmiidr_val = ARM_CSPMU_IMPL_ID_AMPERE,
+ .pmiidr_mask = ARM_CSPMU_PMIIDR_IMPLEMENTER,
+ .module = NULL,
+ .impl_init_ops = NULL,
+ },
+
+ {0}
};
+static struct arm_cspmu_impl_match *arm_cspmu_impl_match_get(u32 pmiidr)
+{
+ struct arm_cspmu_impl_match *match = impl_match;
+
+ for (; match->pmiidr_val; match++) {
+ u32 mask = match->pmiidr_mask;
+
+ if ((match->pmiidr_val & mask) == (pmiidr & mask))
+ return match;
+ }
+
+ return NULL;
+}
+
static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu)
{
- int ret;
+ int ret = 0;
struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
struct acpi_apmt_node *apmt_node = arm_cspmu_apmt_node(cspmu->dev);
- const struct impl_match *match = impl_match;
+ struct arm_cspmu_impl_match *match;
/*
* Get PMU implementer and product id from APMT node.
readl(cspmu->base0 + PMIIDR);
/* Find implementer specific attribute ops. */
- for (; match->pmiidr; match++) {
- const u32 mask = match->mask;
+ match = arm_cspmu_impl_match_get(cspmu->impl.pmiidr);
+
+ /* Load implementer module and initialize the callbacks. */
+ if (match) {
+ mutex_lock(&arm_cspmu_lock);
+
+ if (match->impl_init_ops) {
+ /* Prevent unload until PMU registration is done. */
+ if (try_module_get(match->module)) {
+ cspmu->impl.module = match->module;
+ cspmu->impl.match = match;
+ ret = match->impl_init_ops(cspmu);
+ if (ret)
+ module_put(match->module);
+ } else {
+ WARN(1, "arm_cspmu failed to get module: %s\n",
+ match->module_name);
+ ret = -EINVAL;
+ }
+ } else {
+ request_module_nowait(match->module_name);
+ ret = -EPROBE_DEFER;
+ }
- if ((match->pmiidr & mask) == (cspmu->impl.pmiidr & mask)) {
- ret = match->impl_init_ops(cspmu);
- if (ret)
- return ret;
+ mutex_unlock(&arm_cspmu_lock);
- break;
- }
- }
+ if (ret)
+ return ret;
+ } else
+ cspmu->impl.module = THIS_MODULE;
/* Use default callbacks if implementer doesn't provide one. */
CHECK_DEFAULT_IMPL_OPS(impl_ops, get_event_attrs);
CHECK_DEFAULT_IMPL_OPS(impl_ops, event_type);
CHECK_DEFAULT_IMPL_OPS(impl_ops, event_filter);
CHECK_DEFAULT_IMPL_OPS(impl_ops, event_attr_is_visible);
+ CHECK_DEFAULT_IMPL_OPS(impl_ops, set_ev_filter);
return 0;
}
struct attribute_group **attr_groups = NULL;
struct device *dev = cspmu->dev;
const struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
- int ret;
-
- ret = arm_cspmu_init_impl_ops(cspmu);
- if (ret)
- return NULL;
cspmu->identifier = impl_ops->get_identifier(cspmu);
cspmu->name = impl_ops->get_name(cspmu);
static int arm_cspmu_get_event_idx(struct arm_cspmu_hw_events *hw_events,
struct perf_event *event)
{
- int idx;
+ int idx, ret;
struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
if (supports_cycle_counter(cspmu)) {
if (idx >= cspmu->num_logical_ctrs)
return -EAGAIN;
+ if (cspmu->impl.ops.validate_event) {
+ ret = cspmu->impl.ops.validate_event(cspmu, event);
+ if (ret)
+ return ret;
+ }
+
set_bit(idx, hw_events->used_ctrs);
return idx;
if (use_64b_counter_reg(cspmu)) {
offset = counter_offset(sizeof(u64), event->hw.idx);
- writeq(val, cspmu->base1 + offset);
+ if (cspmu->has_atomic_dword)
+ writeq(val, cspmu->base1 + offset);
+ else
+ lo_hi_writeq(val, cspmu->base1 + offset);
} else {
offset = counter_offset(sizeof(u32), event->hw.idx);
writel(hwc->config, cspmu->base0 + offset);
}
-static inline void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
- struct hw_perf_event *hwc,
- u32 filter)
+static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
+ struct hw_perf_event *hwc,
+ u32 filter)
{
u32 offset = PMEVFILTR + (4 * hwc->idx);
arm_cspmu_set_cc_filter(cspmu, filter);
} else {
arm_cspmu_set_event(cspmu, hwc);
- arm_cspmu_set_ev_filter(cspmu, hwc, filter);
+ cspmu->impl.ops.set_ev_filter(cspmu, hwc, filter);
}
hwc->state = 0;
cspmu->pmu = (struct pmu){
.task_ctx_nr = perf_invalid_context,
- .module = THIS_MODULE,
+ .module = cspmu->impl.module,
.pmu_enable = arm_cspmu_enable,
.pmu_disable = arm_cspmu_disable,
.event_init = arm_cspmu_event_init,
if (ret)
return ret;
- ret = arm_cspmu_register_pmu(cspmu);
+ ret = arm_cspmu_init_impl_ops(cspmu);
if (ret)
return ret;
- return 0;
+ ret = arm_cspmu_register_pmu(cspmu);
+
+ /* Matches arm_cspmu_init_impl_ops() above. */
+ if (cspmu->impl.module != THIS_MODULE)
+ module_put(cspmu->impl.module);
+
+ return ret;
}
static int arm_cspmu_device_remove(struct platform_device *pdev)
cpuhp_remove_multi_state(arm_cspmu_cpuhp_state);
}
+int arm_cspmu_impl_register(const struct arm_cspmu_impl_match *impl_match)
+{
+ struct arm_cspmu_impl_match *match;
+ int ret = 0;
+
+ match = arm_cspmu_impl_match_get(impl_match->pmiidr_val);
+
+ if (match) {
+ mutex_lock(&arm_cspmu_lock);
+
+ if (!match->impl_init_ops) {
+ match->module = impl_match->module;
+ match->impl_init_ops = impl_match->impl_init_ops;
+ } else {
+ /* Broken match table may contain non-unique entries */
+ WARN(1, "arm_cspmu backend already registered for module: %s, pmiidr: 0x%x, mask: 0x%x\n",
+ match->module_name,
+ match->pmiidr_val,
+ match->pmiidr_mask);
+
+ ret = -EINVAL;
+ }
+
+ mutex_unlock(&arm_cspmu_lock);
+
+ if (!ret)
+ ret = driver_attach(&arm_cspmu_driver.driver);
+ } else {
+ pr_err("arm_cspmu reg failed, unable to find a match for pmiidr: 0x%x\n",
+ impl_match->pmiidr_val);
+
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(arm_cspmu_impl_register);
+
+static int arm_cspmu_match_device(struct device *dev, const void *match)
+{
+ struct arm_cspmu *cspmu = platform_get_drvdata(to_platform_device(dev));
+
+ return (cspmu && cspmu->impl.match == match) ? 1 : 0;
+}
+
+void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match)
+{
+ struct device *dev;
+ struct arm_cspmu_impl_match *match;
+
+ match = arm_cspmu_impl_match_get(impl_match->pmiidr_val);
+
+ if (WARN_ON(!match))
+ return;
+
+ /* Unbind the driver from all matching backend devices. */
+ while ((dev = driver_find_device(&arm_cspmu_driver.driver, NULL,
+ match, arm_cspmu_match_device)))
+ device_release_driver(dev);
+
+ mutex_lock(&arm_cspmu_lock);
+
+ match->module = NULL;
+ match->impl_init_ops = NULL;
+
+ mutex_unlock(&arm_cspmu_lock);
+}
+EXPORT_SYMBOL_GPL(arm_cspmu_impl_unregister);
+
module_init(arm_cspmu_init);
module_exit(arm_cspmu_exit);
/* SPDX-License-Identifier: GPL-2.0
*
* ARM CoreSight Architecture PMU driver.
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
*
*/
#define ARM_CSPMU_PMIIDR_IMPLEMENTER GENMASK(11, 0)
#define ARM_CSPMU_PMIIDR_PRODUCTID GENMASK(31, 20)
+/* JEDEC-assigned JEP106 identification code */
+#define ARM_CSPMU_IMPL_ID_NVIDIA 0x36B
+#define ARM_CSPMU_IMPL_ID_AMPERE 0xA16
+
struct arm_cspmu;
/* This tracks the events assigned to each counter in the PMU. */
u32 (*event_type)(const struct perf_event *event);
/* Decode filter value from configs */
u32 (*event_filter)(const struct perf_event *event);
+ /* Set event filter */
+ void (*set_ev_filter)(struct arm_cspmu *cspmu,
+ struct hw_perf_event *hwc, u32 filter);
+ /* Implementation specific event validation */
+ int (*validate_event)(struct arm_cspmu *cspmu,
+ struct perf_event *event);
/* Hide/show unsupported events */
umode_t (*event_attr_is_visible)(struct kobject *kobj,
struct attribute *attr, int unused);
};
+/* Vendor/implementer registration parameter. */
+struct arm_cspmu_impl_match {
+ /* Backend module. */
+ struct module *module;
+ const char *module_name;
+ /* PMIIDR value/mask. */
+ u32 pmiidr_val;
+ u32 pmiidr_mask;
+ /* Callback to vendor backend to init arm_cspmu_impl::ops. */
+ int (*impl_init_ops)(struct arm_cspmu *cspmu);
+};
+
/* Vendor/implementer descriptor. */
struct arm_cspmu_impl {
u32 pmiidr;
+ struct module *module;
+ struct arm_cspmu_impl_match *match;
struct arm_cspmu_impl_ops ops;
void *ctx;
};
struct device_attribute *attr,
char *buf);
+/* Register vendor backend. */
+int arm_cspmu_impl_register(const struct arm_cspmu_impl_match *impl_match);
+
+/* Unregister vendor backend. */
+void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match);
+
#endif /* __ARM_CSPMU_H__ */
// SPDX-License-Identifier: GPL-2.0
/*
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
*
*/
/* Support for NVIDIA specific attributes. */
+#include <linux/module.h>
#include <linux/topology.h>
-#include "nvidia_cspmu.h"
+#include "arm_cspmu.h"
#define NV_PCIE_PORT_COUNT 10ULL
#define NV_PCIE_FILTER_ID_MASK GENMASK_ULL(NV_PCIE_PORT_COUNT - 1, 0)
return name;
}
-int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
+static int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
{
u32 prodid;
struct nv_cspmu_ctx *ctx;
return 0;
}
-EXPORT_SYMBOL_GPL(nv_cspmu_init_ops);
+
+/* Match all NVIDIA Coresight PMU devices */
+static const struct arm_cspmu_impl_match nv_cspmu_param = {
+ .pmiidr_val = ARM_CSPMU_IMPL_ID_NVIDIA,
+ .module = THIS_MODULE,
+ .impl_init_ops = nv_cspmu_init_ops
+};
+
+static int __init nvidia_cspmu_init(void)
+{
+ int ret;
+
+ ret = arm_cspmu_impl_register(&nv_cspmu_param);
+ if (ret)
+ pr_err("nvidia_cspmu backend registration error: %d\n", ret);
+
+ return ret;
+}
+
+static void __exit nvidia_cspmu_exit(void)
+{
+ arm_cspmu_impl_unregister(&nv_cspmu_param);
+}
+
+module_init(nvidia_cspmu_init);
+module_exit(nvidia_cspmu_exit);
MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
- *
- */
-
-/* Support for NVIDIA specific attributes. */
-
-#ifndef __NVIDIA_CSPMU_H__
-#define __NVIDIA_CSPMU_H__
-
-#include "arm_cspmu.h"
-
-/* Allocate NVIDIA descriptor. */
-int nv_cspmu_init_ops(struct arm_cspmu *cspmu);
-
-#endif /* __NVIDIA_CSPMU_H__ */
pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
/* store PMMIR register for sysfs */
- if (is_pmuv3p4(pmuver) && (pmceid_raw[1] & BIT(31)))
+ if (is_pmuv3p4(pmuver))
cpu_pmu->reg_pmmir = read_pmmir();
else
cpu_pmu->reg_pmmir = 0;
}
static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
- int (*map_event)(struct perf_event *event),
- const struct attribute_group *events,
- const struct attribute_group *format,
- const struct attribute_group *caps)
+ int (*map_event)(struct perf_event *event))
{
int ret = armv8pmu_probe_pmu(cpu_pmu);
if (ret)
cpu_pmu->name = name;
cpu_pmu->map_event = map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ?
- events : &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ?
- format : &armv8_pmuv3_format_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ?
- caps : &armv8_pmuv3_caps_attr_group;
-
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &armv8_pmuv3_format_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = &armv8_pmuv3_caps_attr_group;
armv8_pmu_register_sysctl_table();
return 0;
}
-static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name,
- int (*map_event)(struct perf_event *event))
-{
- return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL);
-}
-
#define PMUV3_INIT_SIMPLE(name) \
static int name##_pmu_init(struct arm_pmu *cpu_pmu) \
{ \
- return armv8_pmu_init_nogroups(cpu_pmu, #name, armv8_pmuv3_map_event);\
+ return armv8_pmu_init(cpu_pmu, #name, armv8_pmuv3_map_event); \
}
PMUV3_INIT_SIMPLE(armv8_pmuv3)
static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
{
- return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35",
- armv8_a53_map_event);
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35", armv8_a53_map_event);
}
static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
{
- return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53",
- armv8_a53_map_event);
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53", armv8_a53_map_event);
}
static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
{
- return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57",
- armv8_a57_map_event);
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57", armv8_a57_map_event);
}
static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
{
- return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72",
- armv8_a57_map_event);
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72", armv8_a57_map_event);
}
static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
{
- return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73",
- armv8_a73_map_event);
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73", armv8_a73_map_event);
}
static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
{
- return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder",
- armv8_thunder_map_event);
+ return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder", armv8_thunder_map_event);
}
static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
{
- return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan",
- armv8_vulcan_map_event);
+ return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan", armv8_vulcan_map_event);
}
static const struct of_device_id armv8_pmu_of_device_ids[] = {
struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
- event->cpu = pcie_pmu->on_cpu;
+ /* Check the type first before going on, otherwise it's not our event */
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
if (EXT_COUNTER_IS_USED(hisi_pcie_get_event(event)))
hwc->event_base = HISI_PCIE_EXT_CNT;
else
hwc->event_base = HISI_PCIE_CNT;
- if (event->attr.type != event->pmu->type)
- return -ENOENT;
-
/* Sampling is not supported. */
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EOPNOTSUPP;
if (!hisi_pcie_pmu_validate_event_group(event))
return -EINVAL;
+ event->cpu = pcie_pmu->on_cpu;
+
return 0;
}
ret = perf_pmu_register(&pa_pmu->pmu, name, -1);
if (ret) {
dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret);
- cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
- &pa_pmu->node);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+ &pa_pmu->node);
return ret;
}
ret = perf_pmu_register(&sllc_pmu->pmu, name, -1);
if (ret) {
dev_err(sllc_pmu->dev, "PMU register failed, ret = %d\n", ret);
- cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
- &sllc_pmu->node);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+ &sllc_pmu->node);
return ret;
}
ret = perf_pmu_register(&hns3_pmu->pmu, hns3_pmu->pmu.name, -1);
if (ret) {
pci_err(pdev, "failed to register perf PMU, ret = %d.\n", ret);
- cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE,
- &hns3_pmu->node);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE,
+ &hns3_pmu->node);
}
return ret;
struct hns3_pmu *hns3_pmu = pci_get_drvdata(pdev);
perf_pmu_unregister(&hns3_pmu->pmu);
- cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE,
- &hns3_pmu->node);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HNS3_PMU_ONLINE,
+ &hns3_pmu->node);
}
static int hns3_pmu_init_dev(struct pci_dev *pdev)
#include <linux/mfd/syscon.h>
#include <linux/module.h>
#include <linux/of_address.h>
-#include <linux/of_fdt.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
+#include <linux/property.h>
#include <linux/regmap.h>
#include <linux/slab.h>
.id = PCP_PMU_V2,
};
+#ifdef CONFIG_ACPI
+static const struct xgene_pmu_data xgene_pmu_v3_data = {
+ .id = PCP_PMU_V3,
+};
+#endif
+
static const struct xgene_pmu_ops xgene_pmu_ops = {
.mask_int = xgene_pmu_mask_int,
.unmask_int = xgene_pmu_unmask_int,
MODULE_DEVICE_TABLE(of, xgene_pmu_of_match);
#ifdef CONFIG_ACPI
static const struct acpi_device_id xgene_pmu_acpi_match[] = {
- {"APMC0D5B", PCP_PMU_V1},
- {"APMC0D5C", PCP_PMU_V2},
- {"APMC0D83", PCP_PMU_V3},
+ {"APMC0D5B", (kernel_ulong_t)&xgene_pmu_data},
+ {"APMC0D5C", (kernel_ulong_t)&xgene_pmu_v2_data},
+ {"APMC0D83", (kernel_ulong_t)&xgene_pmu_v3_data},
{},
};
MODULE_DEVICE_TABLE(acpi, xgene_pmu_acpi_match);
static int xgene_pmu_probe(struct platform_device *pdev)
{
const struct xgene_pmu_data *dev_data;
- const struct of_device_id *of_id;
struct xgene_pmu *xgene_pmu;
int irq, rc;
int version;
xgene_pmu->dev = &pdev->dev;
platform_set_drvdata(pdev, xgene_pmu);
- version = -EINVAL;
- of_id = of_match_device(xgene_pmu_of_match, &pdev->dev);
- if (of_id) {
- dev_data = (const struct xgene_pmu_data *) of_id->data;
- version = dev_data->id;
- }
-
-#ifdef CONFIG_ACPI
- if (ACPI_COMPANION(&pdev->dev)) {
- const struct acpi_device_id *acpi_id;
-
- acpi_id = acpi_match_device(xgene_pmu_acpi_match, &pdev->dev);
- if (acpi_id)
- version = (int) acpi_id->driver_data;
- }
-#endif
- if (version < 0)
+ dev_data = device_get_match_data(&pdev->dev);
+ if (!dev_data)
return -ENODEV;
+ version = dev_data->id;
if (version == PCP_PMU_V3)
xgene_pmu->ops = &xgene_pmu_v3_ops;
int acpi_parse_mcfg (struct acpi_table_header *header);
void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
+static inline bool acpi_gicc_is_usable(struct acpi_madt_generic_interrupt *gicc)
+{
+ return gicc->flags & ACPI_MADT_ENABLED;
+}
+
/* the following numa functions are architecture-dependent */
void acpi_numa_slit_init (struct acpi_table_slit *slit);
// mov x8, #__NR_sched_yield // Encourage preemption
// svc #0
+#ifdef SSVE
+ mrs x0, S3_3_C4_C2_2 // SVCR should have ZA=0,SM=1
+ and x1, x0, #3
+ cmp x1, #1
+ b.ne svcr_barf
+#endif
+
mov x21, #0
0: mov x0, x21
bl check_zreg
mov x1, #1
svc #0
endfunction
+
+function svcr_barf
+ mov x10, x0
+
+ puts "Bad SVCR: "
+ mov x0, x10
+ bl putdecn
+
+ mov x8, #__NR_exit
+ mov x1, #1
+ svc #0
+endfunction
projects / linux-2.6-microblaze.git / commitdiff