diff options
| author | Palmer Dabbelt <palmer@rivosinc.com> | 2025-05-09 15:07:20 -0700 |
|---|---|---|
| committer | Palmer Dabbelt <palmer@rivosinc.com> | 2025-05-09 15:07:29 -0700 |
| commit | 91c5822e487aa48a1893a864fe69c2d432244fa2 (patch) | |
| tree | 04cf208f6ea3657cbc114bc284720d893f57c1bf | |
| parent | 1a3f6980889df3fc90ad3e4a525061d2c138adba (diff) | |
| parent | ee293f4771c97525eb9f2069685f8d3057025a88 (diff) | |
| download | linux-for-next.tar.gz | |
Merge branch 'sbiv3' into for-nextfor-next
This is a staging merge, as this branch depends on the SBIv3 freeze and
thus isn't officially ready yet. See
https://lore.kernel.org/all/mhng-4c05b8a8-03ab-4e68-ae73-ed405f196e7c@palmer-ri-x1c9a/
* sbiv3:
riscv: misaligned: add a function to check misalign trap delegability
riscv: misaligned: move emulated access uniformity check in a function
riscv: misaligned: use correct CONFIG_ ifdef for misaligned_access_speed
riscv: misaligned: use on_each_cpu() for scalar misaligned access probing
riscv: misaligned: request misaligned exception from SBI
riscv: sbi: add SBI FWFT extension calls
riscv: sbi: add FWFT extension interface
riscv: sbi: add new SBI error mappings
riscv: sbi: remove useless parenthesis
riscv: sbi: add Firmware Feature (FWFT) SBI extensions definitions
| -rw-r--r-- | arch/riscv/include/asm/cpufeature.h | 8 | ||||
| -rw-r--r-- | arch/riscv/include/asm/sbi.h | 60 | ||||
| -rw-r--r-- | arch/riscv/kernel/sbi.c | 81 | ||||
| -rw-r--r-- | arch/riscv/kernel/traps_misaligned.c | 110 | ||||
| -rw-r--r-- | arch/riscv/kernel/unaligned_access_speed.c | 8 |
5 files changed, 252 insertions, 15 deletions
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index f56b409361fbe0..3a87f612035ca9 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -67,16 +67,22 @@ void __init riscv_user_isa_enable(void); _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate) bool __init check_unaligned_access_emulated_all_cpus(void); +void unaligned_access_init(void); +int cpu_online_unaligned_access_init(unsigned int cpu); #if defined(CONFIG_RISCV_SCALAR_MISALIGNED) -void check_unaligned_access_emulated(struct work_struct *work __always_unused); void unaligned_emulation_finish(void); bool unaligned_ctl_available(void); +bool misaligned_traps_can_delegate(void); DECLARE_PER_CPU(long, misaligned_access_speed); #else static inline bool unaligned_ctl_available(void) { return false; } +static inline bool misaligned_traps_can_delegate(void) +{ + return false; +} #endif bool __init check_vector_unaligned_access_emulated_all_cpus(void); diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 3d250824178bd5..3bbef56bcefcc9 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -35,6 +35,7 @@ enum sbi_ext_id { SBI_EXT_DBCN = 0x4442434E, SBI_EXT_STA = 0x535441, SBI_EXT_NACL = 0x4E41434C, + SBI_EXT_FWFT = 0x46574654, /* Experimentals extensions must lie within this range */ SBI_EXT_EXPERIMENTAL_START = 0x08000000, @@ -402,6 +403,33 @@ enum sbi_ext_nacl_feature { #define SBI_NACL_SHMEM_SRET_X(__i) ((__riscv_xlen / 8) * (__i)) #define SBI_NACL_SHMEM_SRET_X_LAST 31 +/* SBI function IDs for FW feature extension */ +#define SBI_EXT_FWFT_SET 0x0 +#define SBI_EXT_FWFT_GET 0x1 + +enum sbi_fwft_feature_t { + SBI_FWFT_MISALIGNED_EXC_DELEG = 0x0, + SBI_FWFT_LANDING_PAD = 0x1, + SBI_FWFT_SHADOW_STACK = 0x2, + SBI_FWFT_DOUBLE_TRAP = 0x3, + SBI_FWFT_PTE_AD_HW_UPDATING = 0x4, + SBI_FWFT_POINTER_MASKING_PMLEN = 0x5, + SBI_FWFT_LOCAL_RESERVED_START = 0x6, + SBI_FWFT_LOCAL_RESERVED_END = 0x3fffffff, + SBI_FWFT_LOCAL_PLATFORM_START = 0x40000000, + SBI_FWFT_LOCAL_PLATFORM_END = 0x7fffffff, + + SBI_FWFT_GLOBAL_RESERVED_START = 0x80000000, + SBI_FWFT_GLOBAL_RESERVED_END = 0xbfffffff, + SBI_FWFT_GLOBAL_PLATFORM_START = 0xc0000000, + SBI_FWFT_GLOBAL_PLATFORM_END = 0xffffffff, +}; + +#define SBI_FWFT_PLATFORM_FEATURE_BIT BIT(30) +#define SBI_FWFT_GLOBAL_FEATURE_BIT BIT(31) + +#define SBI_FWFT_SET_FLAG_LOCK BIT(0) + /* SBI spec version fields */ #define SBI_SPEC_VERSION_DEFAULT 0x1 #define SBI_SPEC_VERSION_MAJOR_SHIFT 24 @@ -419,6 +447,11 @@ enum sbi_ext_nacl_feature { #define SBI_ERR_ALREADY_STARTED -7 #define SBI_ERR_ALREADY_STOPPED -8 #define SBI_ERR_NO_SHMEM -9 +#define SBI_ERR_INVALID_STATE -10 +#define SBI_ERR_BAD_RANGE -11 +#define SBI_ERR_TIMEOUT -12 +#define SBI_ERR_IO -13 +#define SBI_ERR_DENIED_LOCKED -14 extern unsigned long sbi_spec_version; struct sbiret { @@ -470,6 +503,23 @@ int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask, unsigned long asid); long sbi_probe_extension(int ext); +int sbi_fwft_set(u32 feature, unsigned long value, unsigned long flags); +int sbi_fwft_set_cpumask(const cpumask_t *mask, u32 feature, + unsigned long value, unsigned long flags); +/** + * sbi_fwft_set_online_cpus() - Set a feature on all online cpus + * @feature: The feature to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +static inline int sbi_fwft_set_online_cpus(u32 feature, unsigned long value, + unsigned long flags) +{ + return sbi_fwft_set_cpumask(cpu_online_mask, feature, value, flags); +} + /* Check if current SBI specification version is 0.1 or not */ static inline int sbi_spec_is_0_1(void) { @@ -503,11 +553,21 @@ static inline int sbi_err_map_linux_errno(int err) case SBI_SUCCESS: return 0; case SBI_ERR_DENIED: + case SBI_ERR_DENIED_LOCKED: return -EPERM; case SBI_ERR_INVALID_PARAM: + case SBI_ERR_INVALID_STATE: return -EINVAL; + case SBI_ERR_BAD_RANGE: + return -ERANGE; case SBI_ERR_INVALID_ADDRESS: return -EFAULT; + case SBI_ERR_NO_SHMEM: + return -ENOMEM; + case SBI_ERR_TIMEOUT: + return -ETIME; + case SBI_ERR_IO: + return -EIO; case SBI_ERR_NOT_SUPPORTED: case SBI_ERR_FAILURE: default: diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index 1989b8cade1b98..070014ff35d49c 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -299,6 +299,76 @@ static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask, return 0; } +static bool sbi_fwft_supported; + +/** + * sbi_fwft_set() - Set a feature on the local hart + * @feature: The feature ID to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_fwft_set(u32 feature, unsigned long value, unsigned long flags) +{ + struct sbiret ret; + + if (!sbi_fwft_supported) + return -EOPNOTSUPP; + + ret = sbi_ecall(SBI_EXT_FWFT, SBI_EXT_FWFT_SET, + feature, value, flags, 0, 0, 0); + + return sbi_err_map_linux_errno(ret.error); +} + +struct fwft_set_req { + u32 feature; + unsigned long value; + unsigned long flags; + atomic_t error; +}; + +static void cpu_sbi_fwft_set(void *arg) +{ + struct fwft_set_req *req = arg; + int ret; + + ret = sbi_fwft_set(req->feature, req->value, req->flags); + if (ret) + atomic_set(&req->error, ret); +} + +/** + * sbi_fwft_set_cpumask() - Set a feature for the specified cpumask + * @mask: CPU mask of cpus that need the feature to be set + * @feature: The feature ID to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_fwft_set_cpumask(const cpumask_t *mask, u32 feature, + unsigned long value, unsigned long flags) +{ + struct fwft_set_req req = { + .feature = feature, + .value = value, + .flags = flags, + .error = ATOMIC_INIT(0), + }; + + if (!sbi_fwft_supported) + return -EOPNOTSUPP; + + if (feature & SBI_FWFT_GLOBAL_FEATURE_BIT) + return -EINVAL; + + on_each_cpu_mask(mask, cpu_sbi_fwft_set, &req, 1); + + return atomic_read(&req.error); +} + /** * sbi_set_timer() - Program the timer for next timer event. * @stime_value: The value after which next timer event should fire. @@ -609,7 +679,7 @@ void __init sbi_init(void) } else { __sbi_rfence = __sbi_rfence_v01; } - if ((sbi_spec_version >= sbi_mk_version(0, 3)) && + if (sbi_spec_version >= sbi_mk_version(0, 3) && sbi_probe_extension(SBI_EXT_SRST)) { pr_info("SBI SRST extension detected\n"); pm_power_off = sbi_srst_power_off; @@ -617,11 +687,16 @@ void __init sbi_init(void) sbi_srst_reboot_nb.priority = 192; register_restart_handler(&sbi_srst_reboot_nb); } - if ((sbi_spec_version >= sbi_mk_version(2, 0)) && - (sbi_probe_extension(SBI_EXT_DBCN) > 0)) { + if (sbi_spec_version >= sbi_mk_version(2, 0) && + sbi_probe_extension(SBI_EXT_DBCN) > 0) { pr_info("SBI DBCN extension detected\n"); sbi_debug_console_available = true; } + if (sbi_spec_version >= sbi_mk_version(3, 0) && + sbi_probe_extension(SBI_EXT_FWFT)) { + pr_info("SBI FWFT extension detected\n"); + sbi_fwft_supported = true; + } } else { __sbi_set_timer = __sbi_set_timer_v01; __sbi_send_ipi = __sbi_send_ipi_v01; diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 7443632445d44f..1f2ba769833c9c 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -16,6 +16,7 @@ #include <asm/entry-common.h> #include <asm/hwprobe.h> #include <asm/cpufeature.h> +#include <asm/sbi.h> #include <asm/vector.h> #define INSN_MATCH_LB 0x3 @@ -368,7 +369,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs) perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); -#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS +#ifdef CONFIG_RISCV_SCALAR_MISALIGNED *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED; #endif @@ -626,6 +627,10 @@ bool __init check_vector_unaligned_access_emulated_all_cpus(void) { int cpu; + /* + * While being documented as very slow, schedule_on_each_cpu() is used since + * kernel_vector_begin() expects irqs to be enabled or it will panic() + */ schedule_on_each_cpu(check_vector_unaligned_access_emulated); for_each_online_cpu(cpu) @@ -646,7 +651,7 @@ bool __init check_vector_unaligned_access_emulated_all_cpus(void) static bool unaligned_ctl __read_mostly; -void check_unaligned_access_emulated(struct work_struct *work __always_unused) +static void check_unaligned_access_emulated(void *arg __always_unused) { int cpu = smp_processor_id(); long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu); @@ -657,6 +662,13 @@ void check_unaligned_access_emulated(struct work_struct *work __always_unused) __asm__ __volatile__ ( " "REG_L" %[tmp], 1(%[ptr])\n" : [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory"); +} + +static int cpu_online_check_unaligned_access_emulated(unsigned int cpu) +{ + long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu); + + check_unaligned_access_emulated(NULL); /* * If unaligned_ctl is already set, this means that we detected that all @@ -665,26 +677,35 @@ void check_unaligned_access_emulated(struct work_struct *work __always_unused) */ if (unlikely(unaligned_ctl && (*mas_ptr != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED))) { pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n"); - while (true) - cpu_relax(); + return -EINVAL; } + + return 0; } -bool __init check_unaligned_access_emulated_all_cpus(void) +static bool all_cpus_unaligned_scalar_access_emulated(void) { int cpu; + for_each_online_cpu(cpu) + if (per_cpu(misaligned_access_speed, cpu) != + RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED) + return false; + + return true; +} + +bool __init check_unaligned_access_emulated_all_cpus(void) +{ /* * We can only support PR_UNALIGN controls if all CPUs have misaligned * accesses emulated since tasks requesting such control can run on any * CPU. */ - schedule_on_each_cpu(check_unaligned_access_emulated); + on_each_cpu(check_unaligned_access_emulated, NULL, 1); - for_each_online_cpu(cpu) - if (per_cpu(misaligned_access_speed, cpu) - != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED) - return false; + if (!all_cpus_unaligned_scalar_access_emulated()) + return false; unaligned_ctl = true; return true; @@ -699,4 +720,73 @@ bool __init check_unaligned_access_emulated_all_cpus(void) { return false; } +static int cpu_online_check_unaligned_access_emulated(unsigned int cpu) +{ + return 0; +} +#endif + +static bool misaligned_traps_delegated; + +#ifdef CONFIG_RISCV_SBI + +static int cpu_online_sbi_unaligned_setup(unsigned int cpu) +{ + if (sbi_fwft_set(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0) && + misaligned_traps_delegated) { + pr_crit("Misaligned trap delegation non homogeneous (expected delegated)"); + return -EINVAL; + } + + return 0; +} + +void __init unaligned_access_init(void) +{ + int ret; + + ret = sbi_fwft_set_online_cpus(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0); + if (ret) + return; + + misaligned_traps_delegated = true; + pr_info("SBI misaligned access exception delegation ok\n"); + /* + * Note that we don't have to take any specific action here, if + * the delegation is successful, then + * check_unaligned_access_emulated() will verify that indeed the + * platform traps on misaligned accesses. + */ +} +#else +void __init unaligned_access_init(void) {} + +static int cpu_online_sbi_unaligned_setup(unsigned int cpu __always_unused) +{ + return 0; +} + #endif + +int cpu_online_unaligned_access_init(unsigned int cpu) +{ + int ret; + + ret = cpu_online_sbi_unaligned_setup(cpu); + if (ret) + return ret; + + return cpu_online_check_unaligned_access_emulated(cpu); +} + +bool misaligned_traps_can_delegate(void) +{ + /* + * Either we successfully requested misaligned traps delegation for all + * CPUS or the SBI does not implemented FWFT extension but delegated the + * exception by default. + */ + return misaligned_traps_delegated || + all_cpus_unaligned_scalar_access_emulated(); +} +EXPORT_SYMBOL_GPL(misaligned_traps_can_delegate); diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index 585d2dcf2dab1c..49daa7b39bfaf3 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -141,6 +141,8 @@ static void __init check_unaligned_access_speed_all_cpus(void) unsigned int cpu_count = num_possible_cpus(); struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL); + unaligned_access_init(); + if (!bufs) { pr_warn("Allocation failure, not measuring misaligned performance\n"); return; @@ -236,6 +238,11 @@ arch_initcall_sync(lock_and_set_unaligned_access_static_branch); static int riscv_online_cpu(unsigned int cpu) { + int ret = cpu_online_unaligned_access_init(cpu); + + if (ret) + return ret; + /* We are already set since the last check */ if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { goto exit; @@ -248,7 +255,6 @@ static int riscv_online_cpu(unsigned int cpu) { static struct page *buf; - check_unaligned_access_emulated(NULL); buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); if (!buf) { pr_warn("Allocation failure, not measuring misaligned performance\n"); |