[PATCH v4 0/6] RISC-V Hardware Probing User Interface

Heiko Stübner heiko at sntech.de
Tue Mar 21 13:32:49 PDT 2023


Am Dienstag, 14. März 2023, 19:32:14 CET schrieb Evan Green:
> 
> There's been a bunch of off-list discussions about this, including at
> Plumbers.  The original plan was to do something involving providing an
> ISA string to userspace, but ISA strings just aren't sufficient for a
> stable ABI any more: in order to parse an ISA string users need the
> version of the specifications that the string is written to, the version
> of each extension (sometimes at a finer granularity than the RISC-V
> releases/versions encode), and the expected use case for the ISA string
> (ie, is it a U-mode or M-mode string).  That's a lot of complexity to
> try and keep ABI compatible and it's probably going to continue to grow,
> as even if there's no more complexity in the specifications we'll have
> to deal with the various ISA string parsing oddities that end up all
> over userspace.
> 
> Instead this patch set takes a very different approach and provides a set
> of key/value pairs that encode various bits about the system.  The big
> advantage here is that we can clearly define what these mean so we can
> ensure ABI stability, but it also allows us to encode information that's
> unlikely to ever appear in an ISA string (see the misaligned access
> performance, for example).  The resulting interface looks a lot like
> what arm64 and x86 do, and will hopefully fit well into something like
> ACPI in the future.
> 
> The actual user interface is a syscall, with a vDSO function in front of
> it. The vDSO function can answer some queries without a syscall at all,
> and falls back to the syscall for cases it doesn't have answers to.
> Currently we prepopulate it with an array of answers for all keys and
> a CPU set of "all CPUs". This can be adjusted as necessary to provide
> fast answers to the most common queries.

I've built myself a small test-program [see below], to check the feature
on the d1-nezha board. Which is how I found the tiny c-extension issue.

Series works as expected there, so patches 1-4 on a d1-nezha:

Tested-by: Heiko Stuebner <heiko.stuebner at vrull.eu>



hwprobe.c:
----------------
#include <linux/types.h>
#include <sys/syscall.h>
#include <stdio.h>
#include <unistd.h>

#define __NR_riscv_hwprobe 258

struct riscv_hwprobe {
        __s64 key;
        __u64 value;
};

#define RISCV_HWPROBE_KEY_MVENDORID     0
#define RISCV_HWPROBE_KEY_MARCHID       1
#define RISCV_HWPROBE_KEY_MIMPID        2
#define RISCV_HWPROBE_KEY_BASE_BEHAVIOR 3
#define         RISCV_HWPROBE_BASE_BEHAVIOR_IMA (1 << 0)
#define RISCV_HWPROBE_KEY_IMA_EXT_0     4
#define         RISCV_HWPROBE_IMA_FD            (1 << 0)
#define         RISCV_HWPROBE_IMA_C             (1 << 1)
#define RISCV_HWPROBE_KEY_CPUPERF_0     5
#define         RISCV_HWPROBE_MISALIGNED_UNKNOWN        (0 << 0)
#define         RISCV_HWPROBE_MISALIGNED_EMULATED       (1 << 0)
#define         RISCV_HWPROBE_MISALIGNED_SLOW           (2 << 0)
#define         RISCV_HWPROBE_MISALIGNED_FAST           (3 << 0)
#define         RISCV_HWPROBE_MISALIGNED_UNSUPPORTED    (4 << 0)
#define         RISCV_HWPROBE_MISALIGNED_MASK           (7 << 0)

int __riscv_hwprobe (struct riscv_hwprobe *pairs, long pair_count,
  long cpu_count, unsigned long *cpus, unsigned long flags)
{

        return syscall(__NR_riscv_hwprobe, pairs, pair_count, cpu_count, cpus, flags);
}

int main(void)
{
        struct riscv_hwprobe pairs[3];

        pairs[0].key = RISCV_HWPROBE_KEY_MVENDORID;
        pairs[1].key = RISCV_HWPROBE_KEY_MARCHID;
        pairs[2].key = RISCV_HWPROBE_KEY_MIMPID;
        if (__riscv_hwprobe(pairs, 3, 0, NULL, 0) != 0) {
                printf("syscall failed");
                return -1;
        }

        printf("vendorid 0x%x, archid 0x%x, impid 0x%x\n",
               pairs[0].value, pairs[1].value, pairs[2].value);


        pairs[0].key = RISCV_HWPROBE_KEY_CPUPERF_0;
        pairs[1].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR;
        pairs[2].key = RISCV_HWPROBE_KEY_IMA_EXT_0;
        if (__riscv_hwprobe(&pairs[0], 3, 0, NULL, 0) != 0) {
                printf("syscall failed");
                return -1;
        }

        printf("ima-behavior %d, f+d %d, c %d, misaligned access: %s\n",
        ((pairs[1].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA) == RISCV_HWPROBE_BASE_BEHAVIOR_IMA),
        ((pairs[2].value & RISCV_HWPROBE_IMA_FD) == RISCV_HWPROBE_IMA_FD),
        ((pairs[2].value & RISCV_HWPROBE_IMA_C) == RISCV_HWPROBE_IMA_C),
        ((pairs[0].value & RISCV_HWPROBE_MISALIGNED_FAST) == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "not-fast"
        );

        return 0;
}






More information about the linux-riscv mailing list