diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-10 09:23:17 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-10 09:23:17 -0800 |
| commit | 56d428ae1c4e27fbe02cb554b2192cd66e4df05a (patch) | |
| tree | 0fa353d09d206a2206ef8861f489f50c4d80f9fe /arch/riscv/kernel/cpufeature.c | |
| parent | 656d88c3b654c0ccc0ff63aa75101c6c9f0a5300 (diff) | |
| parent | 457926b253200bd9bdfae9a016a3b1d1dc661d55 (diff) | |
Merge tag 'riscv-for-linus-6.7-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux
Pull more RISC-V updates from Palmer Dabbelt:
- Support for handling misaligned accesses in S-mode
- Probing for misaligned access support is now properly cached and
handled in parallel
- PTDUMP now reflects the SW reserved bits, as well as the PBMT and
NAPOT extensions
- Performance improvements for TLB flushing
- Support for many new relocations in the module loader
- Various bug fixes and cleanups
* tag 'riscv-for-linus-6.7-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (51 commits)
riscv: Optimize bitops with Zbb extension
riscv: Rearrange hwcap.h and cpufeature.h
drivers: perf: Do not broadcast to other cpus when starting a counter
drivers: perf: Check find_first_bit() return value
of: property: Add fw_devlink support for msi-parent
RISC-V: Don't fail in riscv_of_parent_hartid() for disabled HARTs
riscv: Fix set_memory_XX() and set_direct_map_XX() by splitting huge linear mappings
riscv: Don't use PGD entries for the linear mapping
RISC-V: Probe misaligned access speed in parallel
RISC-V: Remove __init on unaligned_emulation_finish()
RISC-V: Show accurate per-hart isa in /proc/cpuinfo
RISC-V: Don't rely on positional structure initialization
riscv: Add tests for riscv module loading
riscv: Add remaining module relocations
riscv: Avoid unaligned access when relocating modules
riscv: split cache ops out of dma-noncoherent.c
riscv: Improve flush_tlb_kernel_range()
riscv: Make __flush_tlb_range() loop over pte instead of flushing the whole tlb
riscv: Improve flush_tlb_range() for hugetlb pages
riscv: Improve tlb_flush()
...
Diffstat (limited to 'arch/riscv/kernel/cpufeature.c')
| -rw-r--r-- | arch/riscv/kernel/cpufeature.c | 92 |
1 files changed, 79 insertions, 13 deletions
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 7aeba01dcfd4..b3785ffc1570 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -8,6 +8,7 @@ #include <linux/acpi.h> #include <linux/bitmap.h> +#include <linux/cpuhotplug.h> #include <linux/ctype.h> #include <linux/log2.h> #include <linux/memory.h> @@ -29,6 +30,7 @@ #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; @@ -559,23 +561,21 @@ unsigned long riscv_get_elf_hwcap(void) return hwcap; } -void check_unaligned_access(int cpu) +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; + struct page *page = param; void *dst; void *src; long speed = RISCV_HWPROBE_MISALIGNED_SLOW; - page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE)); - if (!page) { - pr_warn("Can't alloc pages to measure memcpy performance"); - return; - } + if (check_unaligned_access_emulated(cpu)) + return 0; /* Make an unaligned destination buffer. */ dst = (void *)((unsigned long)page_address(page) | 0x1); @@ -629,7 +629,7 @@ void check_unaligned_access(int cpu) pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n", cpu); - goto out; + return 0; } if (word_cycles < byte_cycles) @@ -643,18 +643,84 @@ void check_unaligned_access(int cpu) (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow"); per_cpu(misaligned_access_speed, cpu) = speed; + return 0; +} -out: - __free_pages(page, get_order(MISALIGNED_BUFFER_SIZE)); +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]); +} + +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) + return 0; + + 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); + return 0; } -static int check_unaligned_access_boot_cpu(void) +/* Measure unaligned access on all CPUs present at boot in parallel. */ +static int check_unaligned_access_all_cpus(void) { - check_unaligned_access(0); + 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 callback for any new CPUs that come online. */ + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", + riscv_online_cpu, NULL); + +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_boot_cpu); +arch_initcall(check_unaligned_access_all_cpus); void riscv_user_isa_enable(void) { |
