mirror of
https://github.com/tbsdtv/linux_media.git
synced 2025-07-23 20:51:03 +02:00
eb04e72b34
Evan Green <evan@rivosinc.com> says: 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. An example series in glibc exposing this syscall and using it in an ifunc selector for memcpy can be found at [1]. I was asked about the performance delta between this and something like sysfs. I created a small test program and ran it on a Nezha D1 Allwinner board. Doing each operation 100000 times and dividing, these operations take the following amount of time: - open()+read()+close() of /sys/kernel/cpu_byteorder: 3.8us - access("/sys/kernel/cpu_byteorder", R_OK): 1.3us - riscv_hwprobe() vDSO and syscall: .0094us - riscv_hwprobe() vDSO with no syscall: 0.0091us These numbers get farther apart if we query multiple keys, as sysfs will scale linearly with the number of keys, where the dedicated syscall stays the same. To frame these numbers, I also did a tight fork/exec/wait loop, which I measured as 4.8ms. So doing 4 open/read/close operations is a delta of about 0.3%, versus a single vDSO call is a delta of essentially zero. [1] https://patchwork.ozlabs.org/project/glibc/list/?series=343050 * b4-shazam-merge: RISC-V: Add hwprobe vDSO function and data selftests: Test the new RISC-V hwprobe interface RISC-V: hwprobe: Support probing of misaligned access performance RISC-V: hwprobe: Add support for RISCV_HWPROBE_BASE_BEHAVIOR_IMA RISC-V: Add a syscall for HW probing RISC-V: Move struct riscv_cpuinfo to new header Link: https://lore.kernel.org/r/20230407231103.2622178-1-evan@rivosinc.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
104 lines
2.5 KiB
C
104 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved.
|
|
* Copyright 2010 Tilera Corporation. All Rights Reserved.
|
|
* Copyright 2015 Regents of the University of California, Berkeley
|
|
*
|
|
* See asm-generic/syscall.h for descriptions of what we must do here.
|
|
*/
|
|
|
|
#ifndef _ASM_RISCV_SYSCALL_H
|
|
#define _ASM_RISCV_SYSCALL_H
|
|
|
|
#include <asm/hwprobe.h>
|
|
#include <uapi/linux/audit.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/err.h>
|
|
|
|
/* The array of function pointers for syscalls. */
|
|
extern void * const sys_call_table[];
|
|
extern void * const compat_sys_call_table[];
|
|
|
|
/*
|
|
* Only the low 32 bits of orig_r0 are meaningful, so we return int.
|
|
* This importantly ignores the high bits on 64-bit, so comparisons
|
|
* sign-extend the low 32 bits.
|
|
*/
|
|
static inline int syscall_get_nr(struct task_struct *task,
|
|
struct pt_regs *regs)
|
|
{
|
|
return regs->a7;
|
|
}
|
|
|
|
static inline void syscall_rollback(struct task_struct *task,
|
|
struct pt_regs *regs)
|
|
{
|
|
regs->a0 = regs->orig_a0;
|
|
}
|
|
|
|
static inline long syscall_get_error(struct task_struct *task,
|
|
struct pt_regs *regs)
|
|
{
|
|
unsigned long error = regs->a0;
|
|
|
|
return IS_ERR_VALUE(error) ? error : 0;
|
|
}
|
|
|
|
static inline long syscall_get_return_value(struct task_struct *task,
|
|
struct pt_regs *regs)
|
|
{
|
|
return regs->a0;
|
|
}
|
|
|
|
static inline void syscall_set_return_value(struct task_struct *task,
|
|
struct pt_regs *regs,
|
|
int error, long val)
|
|
{
|
|
regs->a0 = (long) error ?: val;
|
|
}
|
|
|
|
static inline void syscall_get_arguments(struct task_struct *task,
|
|
struct pt_regs *regs,
|
|
unsigned long *args)
|
|
{
|
|
args[0] = regs->orig_a0;
|
|
args++;
|
|
memcpy(args, ®s->a1, 5 * sizeof(args[0]));
|
|
}
|
|
|
|
static inline int syscall_get_arch(struct task_struct *task)
|
|
{
|
|
#ifdef CONFIG_64BIT
|
|
return AUDIT_ARCH_RISCV64;
|
|
#else
|
|
return AUDIT_ARCH_RISCV32;
|
|
#endif
|
|
}
|
|
|
|
typedef long (*syscall_t)(ulong, ulong, ulong, ulong, ulong, ulong, ulong);
|
|
static inline void syscall_handler(struct pt_regs *regs, ulong syscall)
|
|
{
|
|
syscall_t fn;
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
if ((regs->status & SR_UXL) == SR_UXL_32)
|
|
fn = compat_sys_call_table[syscall];
|
|
else
|
|
#endif
|
|
fn = sys_call_table[syscall];
|
|
|
|
regs->a0 = fn(regs->orig_a0, regs->a1, regs->a2,
|
|
regs->a3, regs->a4, regs->a5, regs->a6);
|
|
}
|
|
|
|
static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
|
|
|
|
asmlinkage long sys_riscv_hwprobe(struct riscv_hwprobe *, size_t, size_t,
|
|
unsigned long *, unsigned int);
|
|
#endif /* _ASM_RISCV_SYSCALL_H */
|