From: Ma Wupeng <mawupeng1@huawei.com> hulk inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/9826 -------------------------------- Now PBHA can be enabled via FDT table at early startup. Here is an example for item in FDT table: cpus { arm,pbha-performance-only = <0x01000000 0x00000000 0x00000000 0x00000000>; }; Signed-off-by: Ma Wupeng <mawupeng1@huawei.com> Signed-off-by: Fanhua Li <lifanhua5@huawei.com> Signed-off-by: Jiacheng Yu <yujiacheng3@huawei.com> --- Changes in v3: - fix the for-loop style in update_pbha_perf_only_bit() --- arch/arm64/include/asm/cpufeature.h | 14 +++++ arch/arm64/kernel/cpufeature.c | 89 +++++++++++++++++++++++++---- arch/arm64/kernel/head.S | 3 + 3 files changed, 94 insertions(+), 12 deletions(-) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index e151c688606b..46c5a0afe32a 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -967,6 +967,20 @@ static inline bool system_supports_bbml3(void) int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); bool try_emulate_mrs(struct pt_regs *regs, u32 isn); +#ifdef CONFIG_ARM64_PBHA +extern bool pbha_enabled; + +static inline bool system_supports_pbha(void) +{ + return pbha_enabled; +} +#else +static inline bool system_supports_pbha(void) +{ + return false; +} +#endif + static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) { switch (parange) { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index b218985a3edc..5d4e259ac390 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -76,6 +76,8 @@ #include <linux/cpu.h> #include <linux/kasan.h> #include <linux/percpu.h> +#include <linux/init.h> +#include <linux/libfdt.h> #include <asm/actlr.h> #include <asm/cpu.h> @@ -99,6 +101,7 @@ #include <asm/vectors.h> #include <asm/virt.h> #include <asm/vip_smt.h> +#include <asm/setup.h> /* Kernel representation of AT_HWCAP and AT_HWCAP2 */ static DECLARE_BITMAP(elf_hwcap, MAX_CPU_FEATURES) __read_mostly; @@ -2076,6 +2079,8 @@ static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap, static u8 pbha_stage1_enable_bits; static DEFINE_SPINLOCK(pbha_dt_lock); +bool pbha_enabled; + /* For the value 5, return a bitmap with bits 5, 4, and 1 set. */ static unsigned long decompose_pbha_values(u8 val) { @@ -2110,11 +2115,26 @@ static void stage2_test_pbha_value(u8 val) arm64_pbha_stage2_safe_bits |= val; } +static void update_pbha_perf_only_bit(const u8 *bits, int cnt) +{ + u8 val; + int i; + + /* any listed value is usable at stage 1 */ + for (i = 0; i < cnt; i++) { + val = bits[i]; + if (val > 0xf) + continue; + + pbha_stage1_enable_bits |= val; + set_bit(val, &arm64_pbha_perf_only_values); + } +} + static bool plat_can_use_pbha_stage1(const struct arm64_cpu_capabilities *cap, int scope) { u8 val; - static bool dt_check_done; struct device_node *cpus; const u8 *perf_only_vals; int num_perf_only_vals, i; @@ -2131,7 +2151,7 @@ static bool plat_can_use_pbha_stage1(const struct arm64_cpu_capabilities *cap, return true; spin_lock(&pbha_dt_lock); - if (dt_check_done) + if (pbha_enabled) goto out_unlock; cpus = of_find_node_by_path("/cpus"); @@ -2144,14 +2164,7 @@ static bool plat_can_use_pbha_stage1(const struct arm64_cpu_capabilities *cap, goto done; /* any listed value is usable at stage 1 */ - for (i = 0; i < num_perf_only_vals; i++) { - val = perf_only_vals[i]; - if (val > 0xf) - continue; - - pbha_stage1_enable_bits |= val; - set_bit(val, &arm64_pbha_perf_only_values); - } + update_pbha_perf_only_bit(perf_only_vals, num_perf_only_vals); /* * for stage2 the values are collapsed back to 4 bits that can only @@ -2167,14 +2180,14 @@ static bool plat_can_use_pbha_stage1(const struct arm64_cpu_capabilities *cap, done: of_node_put(cpus); - dt_check_done = true; + pbha_enabled = true; out_unlock: spin_unlock(&pbha_dt_lock); return !!pbha_stage1_enable_bits; } -static void cpu_enable_pbha(struct arm64_cpu_capabilities const *cap) +static void enable_pbha_inner(void) { u64 tcr; @@ -2191,6 +2204,58 @@ static void cpu_enable_pbha(struct arm64_cpu_capabilities const *cap) local_flush_tlb_all(); } +static void cpu_enable_pbha(struct arm64_cpu_capabilities const *cap) +{ + enable_pbha_inner(); +} + +static inline bool cpu_has_pbha(void) +{ + u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + int val = cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_EL1_HPDS_SHIFT); + + return val == 2; +} + +void __init early_pbha_init(void) +{ + void *fdt; + int node; + const u8 *prop; + int size; + + fdt = get_early_fdt_ptr(); + if (!fdt) + return; + + /* arm,pbha-performance-only may exist in both chosen and cpus node */ + node = fdt_path_offset(fdt, "/chosen"); + if (node < 0) + return; + + prop = fdt_getprop(fdt, node, "arm,pbha-performance-only", &size); + if (prop) + goto found; + + node = fdt_path_offset(fdt, "/cpus"); + if (node < 0) + return; + + prop = fdt_getprop(fdt, node, "arm,pbha-performance-only", &size); + if (!prop) + return; + +found: + if (!cpu_has_pbha()) + return; + + update_pbha_perf_only_bit(prop, size); + enable_pbha_inner(); + + pbha_enabled = true; +} + /* * PBHA's behaviour is implementation defined, as is the way it combines * stage1 and stage2 attributes. If the kernel has KVM supported, and booted diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 6517bf2644a0..ec972cc4508f 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -512,6 +512,9 @@ SYM_FUNC_START_LOCAL(__primary_switched) #endif mov x0, x21 // pass FDT address in x0 bl early_fdt_map // Try mapping the FDT early +#ifdef CONFIG_ARM64_PBHA + bl early_pbha_init // Init PBHA early via FDT +#endif mov x0, x20 // pass the full boot status bl init_feature_override // Parse cpu feature overrides #ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS