summaryrefslogtreecommitdiffstats
path: root/arch/riscv/kernel/cpufeature.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/riscv/kernel/cpufeature.c')
-rw-r--r--arch/riscv/kernel/cpufeature.c266
1 files changed, 8 insertions, 258 deletions
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 79a5a35fab..5ef48cb20e 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -11,7 +11,6 @@
#include <linux/cpu.h>
#include <linux/cpuhotplug.h>
#include <linux/ctype.h>
-#include <linux/jump_label.h>
#include <linux/log2.h>
#include <linux/memory.h>
#include <linux/module.h>
@@ -21,21 +20,13 @@
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/hwcap.h>
-#include <asm/hwprobe.h>
#include <asm/patch.h>
#include <asm/processor.h>
#include <asm/sbi.h>
#include <asm/vector.h>
-#include "copy-unaligned.h"
-
#define NUM_ALPHA_EXTS ('z' - 'a' + 1)
-#define MISALIGNED_ACCESS_JIFFIES_LG2 1
-#define MISALIGNED_BUFFER_SIZE 0x4000
-#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
-#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
-
unsigned long elf_hwcap __read_mostly;
/* Host ISA bitmap */
@@ -44,11 +35,6 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
/* Per-cpu ISA extensions. */
struct riscv_isainfo hart_isa[NR_CPUS];
-/* Performance information */
-DEFINE_PER_CPU(long, misaligned_access_speed);
-
-static cpumask_t fast_misaligned_access;
-
/**
* riscv_isa_extension_base() - Get base extension word
*
@@ -318,6 +304,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+ __RISCV_ISA_EXT_DATA(xandespmu, RISCV_ISA_EXT_XANDESPMU),
};
const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
@@ -503,6 +490,8 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
struct acpi_table_header *rhct;
acpi_status status;
unsigned int cpu;
+ u64 boot_vendorid;
+ u64 boot_archid;
if (!acpi_disabled) {
status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
@@ -510,6 +499,9 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
return;
}
+ boot_vendorid = riscv_get_mvendorid();
+ boot_archid = riscv_get_marchid();
+
for_each_possible_cpu(cpu) {
struct riscv_isainfo *isainfo = &hart_isa[cpu];
unsigned long this_hwcap = 0;
@@ -557,8 +549,7 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
* CPU cores with the ratified spec will contain non-zero
* marchid.
*/
- if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID &&
- riscv_cached_marchid(cpu) == 0x0) {
+ if (acpi_disabled && boot_vendorid == THEAD_VENDOR_ID && boot_archid == 0x0) {
this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v];
clear_bit(RISCV_ISA_EXT_v, isainfo->isa);
}
@@ -612,7 +603,7 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
if (ext->subset_ext_size) {
for (int j = 0; j < ext->subset_ext_size; j++) {
- if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+ if (riscv_isa_extension_check(ext->subset_ext_ids[j]))
set_bit(ext->subset_ext_ids[j], isainfo->isa);
}
}
@@ -731,247 +722,6 @@ unsigned long riscv_get_elf_hwcap(void)
return hwcap;
}
-static int check_unaligned_access(void *param)
-{
- int cpu = smp_processor_id();
- u64 start_cycles, end_cycles;
- u64 word_cycles;
- u64 byte_cycles;
- int ratio;
- unsigned long start_jiffies, now;
- struct page *page = param;
- void *dst;
- void *src;
- long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
-
- if (check_unaligned_access_emulated(cpu))
- return 0;
-
- /* Make an unaligned destination buffer. */
- dst = (void *)((unsigned long)page_address(page) | 0x1);
- /* Unalign src as well, but differently (off by 1 + 2 = 3). */
- src = dst + (MISALIGNED_BUFFER_SIZE / 2);
- src += 2;
- word_cycles = -1ULL;
- /* Do a warmup. */
- __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
- preempt_disable();
- start_jiffies = jiffies;
- while ((now = jiffies) == start_jiffies)
- cpu_relax();
-
- /*
- * For a fixed amount of time, repeatedly try the function, and take
- * the best time in cycles as the measurement.
- */
- while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
- start_cycles = get_cycles64();
- /* Ensure the CSR read can't reorder WRT to the copy. */
- mb();
- __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
- /* Ensure the copy ends before the end time is snapped. */
- mb();
- end_cycles = get_cycles64();
- if ((end_cycles - start_cycles) < word_cycles)
- word_cycles = end_cycles - start_cycles;
- }
-
- byte_cycles = -1ULL;
- __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
- start_jiffies = jiffies;
- while ((now = jiffies) == start_jiffies)
- cpu_relax();
-
- while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
- start_cycles = get_cycles64();
- mb();
- __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
- mb();
- end_cycles = get_cycles64();
- if ((end_cycles - start_cycles) < byte_cycles)
- byte_cycles = end_cycles - start_cycles;
- }
-
- preempt_enable();
-
- /* Don't divide by zero. */
- if (!word_cycles || !byte_cycles) {
- pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
- cpu);
-
- return 0;
- }
-
- if (word_cycles < byte_cycles)
- speed = RISCV_HWPROBE_MISALIGNED_FAST;
-
- ratio = div_u64((byte_cycles * 100), word_cycles);
- pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n",
- cpu,
- ratio / 100,
- ratio % 100,
- (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
-
- per_cpu(misaligned_access_speed, cpu) = speed;
-
- /*
- * Set the value of fast_misaligned_access of a CPU. These operations
- * are atomic to avoid race conditions.
- */
- if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
- cpumask_set_cpu(cpu, &fast_misaligned_access);
- else
- cpumask_clear_cpu(cpu, &fast_misaligned_access);
-
- return 0;
-}
-
-static void check_unaligned_access_nonboot_cpu(void *param)
-{
- unsigned int cpu = smp_processor_id();
- struct page **pages = param;
-
- if (smp_processor_id() != 0)
- check_unaligned_access(pages[cpu]);
-}
-
-DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
-
-static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
-{
- if (cpumask_weight(mask) == weight)
- static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
- else
- static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
-}
-
-static void set_unaligned_access_static_branches_except_cpu(int cpu)
-{
- /*
- * Same as set_unaligned_access_static_branches, except excludes the
- * given CPU from the result. When a CPU is hotplugged into an offline
- * state, this function is called before the CPU is set to offline in
- * the cpumask, and thus the CPU needs to be explicitly excluded.
- */
-
- cpumask_t fast_except_me;
-
- cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
- cpumask_clear_cpu(cpu, &fast_except_me);
-
- modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
-}
-
-static void set_unaligned_access_static_branches(void)
-{
- /*
- * This will be called after check_unaligned_access_all_cpus so the
- * result of unaligned access speed for all CPUs will be available.
- *
- * To avoid the number of online cpus changing between reading
- * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
- * held before calling this function.
- */
-
- cpumask_t fast_and_online;
-
- cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
-
- modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
-}
-
-static int lock_and_set_unaligned_access_static_branch(void)
-{
- cpus_read_lock();
- set_unaligned_access_static_branches();
- cpus_read_unlock();
-
- return 0;
-}
-
-arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
-
-static int riscv_online_cpu(unsigned int cpu)
-{
- static struct page *buf;
-
- /* We are already set since the last check */
- if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
- goto exit;
-
- buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
- if (!buf) {
- pr_warn("Allocation failure, not measuring misaligned performance\n");
- return -ENOMEM;
- }
-
- check_unaligned_access(buf);
- __free_pages(buf, MISALIGNED_BUFFER_ORDER);
-
-exit:
- set_unaligned_access_static_branches();
-
- return 0;
-}
-
-static int riscv_offline_cpu(unsigned int cpu)
-{
- set_unaligned_access_static_branches_except_cpu(cpu);
-
- return 0;
-}
-
-/* Measure unaligned access on all CPUs present at boot in parallel. */
-static int check_unaligned_access_all_cpus(void)
-{
- unsigned int cpu;
- unsigned int cpu_count = num_possible_cpus();
- struct page **bufs = kzalloc(cpu_count * sizeof(struct page *),
- GFP_KERNEL);
-
- if (!bufs) {
- pr_warn("Allocation failure, not measuring misaligned performance\n");
- return 0;
- }
-
- /*
- * Allocate separate buffers for each CPU so there's no fighting over
- * cache lines.
- */
- for_each_cpu(cpu, cpu_online_mask) {
- bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
- if (!bufs[cpu]) {
- pr_warn("Allocation failure, not measuring misaligned performance\n");
- goto out;
- }
- }
-
- /* Check everybody except 0, who stays behind to tend jiffies. */
- on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
-
- /* Check core 0. */
- smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
-
- /*
- * Setup hotplug callbacks for any new CPUs that come online or go
- * offline.
- */
- cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
- riscv_online_cpu, riscv_offline_cpu);
-
-out:
- unaligned_emulation_finish();
- for_each_cpu(cpu, cpu_online_mask) {
- if (bufs[cpu])
- __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
- }
-
- kfree(bufs);
- return 0;
-}
-
-arch_initcall(check_unaligned_access_all_cpus);
-
void riscv_user_isa_enable(void)
{
if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))