Merge tag 'riscv-for-linus-6.8-mw4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - Support for tuning for systems with fast misaligned accesses.

 - Support for SBI-based suspend.

 - Support for the new SBI debug console extension.

 - The T-Head CMOs now use PA-based flushes.

 - Support for enabling the V extension in kernel code.

 - Optimized IP checksum routines.

 - Various ftrace improvements.

 - Support for archrandom, which depends on the Zkr extension.

 - The build is no longer broken under NET=n, KUNIT=y for ports that
   don't define their own ipv6 checksum.

* tag 'riscv-for-linus-6.8-mw4' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (56 commits)
  lib: checksum: Fix build with CONFIG_NET=n
  riscv: lib: Check if output in asm goto supported
  riscv: Fix build error on rv32 + XIP
  riscv: optimize ELF relocation function in riscv
  RISC-V: Implement archrandom when Zkr is available
  riscv: Optimize hweight API with Zbb extension
  riscv: add dependency among Image(.gz), loader(.bin), and vmlinuz.efi
  samples: ftrace: Add RISC-V support for SAMPLE_FTRACE_DIRECT[_MULTI]
  riscv: ftrace: Add DYNAMIC_FTRACE_WITH_DIRECT_CALLS support
  riscv: ftrace: Make function graph use ftrace directly
  riscv: select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
  lib/Kconfig.debug: Update AS_HAS_NON_CONST_LEB128 comment and name
  riscv: Restrict DWARF5 when building with LLVM to known working versions
  riscv: Hoist linker relaxation disabling logic into Kconfig
  kunit: Add tests for csum_ipv6_magic and ip_fast_csum
  riscv: Add checksum library
  riscv: Add checksum header
  riscv: Add static key for misaligned accesses
  asm-generic: Improve csum_fold
  RISC-V: selftests: cbo: Ensure asm operands match constraints
  ...
This commit is contained in:
Linus Torvalds
2024-01-20 11:06:04 -08:00
71 changed files with 2678 additions and 215 deletions

View File

@@ -63,8 +63,8 @@ properties:
mmu-type:
description:
Identifies the MMU address translation mode used on this
hart. These values originate from the RISC-V Privileged
Identifies the largest MMU address translation mode supported by
this hart. These values originate from the RISC-V Privileged
Specification document, available from
https://riscv.org/specifications/
$ref: /schemas/types.yaml#/definitions/string
@@ -80,6 +80,11 @@ properties:
description:
The blocksize in bytes for the Zicbom cache operations.
riscv,cbop-block-size:
$ref: /schemas/types.yaml#/definitions/uint32
description:
The blocksize in bytes for the Zicbop cache operations.
riscv,cboz-block-size:
$ref: /schemas/types.yaml#/definitions/uint32
description:

View File

@@ -48,7 +48,7 @@ properties:
insensitive, letters in the riscv,isa string must be all
lowercase.
$ref: /schemas/types.yaml#/definitions/string
pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[0-9a-z])+)?(?:_[hsxz](?:[0-9a-z])+)*$
deprecated: true
riscv,isa-base:

View File

@@ -20,7 +20,7 @@
| openrisc: | .. |
| parisc: | TODO |
| powerpc: | TODO |
| riscv: | TODO |
| riscv: | ok |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |

View File

@@ -53,6 +53,7 @@ config RISCV
select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USES_CFI_TRAPS if CFI_CLANG
select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP && MMU
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
select ARCH_WANT_FRAME_POINTERS
select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT
@@ -66,9 +67,10 @@ config RISCV
select CLINT_TIMER if !MMU
select CLONE_BACKWARDS
select COMMON_CLK
select CPU_PM if CPU_IDLE || HIBERNATION
select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
select EDAC_SUPPORT
select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
select GENERIC_ARCH_TOPOLOGY
select GENERIC_ATOMIC64 if !64BIT
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
@@ -115,6 +117,7 @@ config RISCV
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS if MMU
select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE)
select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER
@@ -142,6 +145,8 @@ config RISCV
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RETHOOK if !XIP_KERNEL
select HAVE_RSEQ
select HAVE_SAMPLE_FTRACE_DIRECT
select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
@@ -183,6 +188,20 @@ config HAVE_SHADOW_CALL_STACK
# https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a484e843e6eeb51f0cb7b8819e50da6d2444d769
depends on $(ld-option,--no-relax-gp)
config RISCV_USE_LINKER_RELAXATION
def_bool y
# https://github.com/llvm/llvm-project/commit/6611d58f5bbcbec77262d392e2923e1d680f6985
depends on !LD_IS_LLD || LLD_VERSION >= 150000
# https://github.com/llvm/llvm-project/commit/bbc0f99f3bc96f1db16f649fc21dd18e5b0918f6
config ARCH_HAS_BROKEN_DWARF5
def_bool y
depends on RISCV_USE_LINKER_RELAXATION
# https://github.com/llvm/llvm-project/commit/1df5ea29b43690b6622db2cad7b745607ca4de6a
depends on AS_IS_LLVM && AS_VERSION < 180000
# https://github.com/llvm/llvm-project/commit/7ffabb61a5569444b5ac9322e22e5471cc5e4a77
depends on LD_IS_LLD && LLD_VERSION < 180000
config ARCH_MMAP_RND_BITS_MIN
default 18 if 64BIT
default 8
@@ -529,6 +548,28 @@ config RISCV_ISA_V_DEFAULT_ENABLE
If you don't know what to do here, say Y.
config RISCV_ISA_V_UCOPY_THRESHOLD
int "Threshold size for vectorized user copies"
depends on RISCV_ISA_V
default 768
help
Prefer using vectorized copy_to_user()/copy_from_user() when the
workload size exceeds this value.
config RISCV_ISA_V_PREEMPTIVE
bool "Run kernel-mode Vector with kernel preemption"
depends on PREEMPTION
depends on RISCV_ISA_V
default y
help
Usually, in-kernel SIMD routines are run with preemption disabled.
Functions which envoke long running SIMD thus must yield core's
vector unit to prevent blocking other tasks for too long.
This config allows kernel to run SIMD without explicitly disable
preemption. Enabling this config will result in higher memory
consumption due to the allocation of per-task's kernel Vector context.
config TOOLCHAIN_HAS_ZBB
bool
default y
@@ -655,6 +696,20 @@ config RISCV_MISALIGNED
load/store for both kernel and userspace. When disable, misaligned
accesses will generate SIGBUS in userspace and panic in kernel.
config RISCV_EFFICIENT_UNALIGNED_ACCESS
bool "Assume the CPU supports fast unaligned memory accesses"
depends on NONPORTABLE
select DCACHE_WORD_ACCESS if MMU
select HAVE_EFFICIENT_UNALIGNED_ACCESS
help
Say Y here if you want the kernel to assume that the CPU supports
efficient unaligned memory accesses. When enabled, this option
improves the performance of the kernel on such CPUs. However, the
kernel will run much more slowly, or will not be able to run at all,
on CPUs that do not support efficient unaligned memory accesses.
If unsure what to do here, say N.
endmenu # "Platform type"
menu "Kernel features"

View File

@@ -98,6 +98,7 @@ config ERRATA_THEAD_CMO
depends on ERRATA_THEAD && MMU
select DMA_DIRECT_REMAP
select RISCV_DMA_NONCOHERENT
select RISCV_NONSTANDARD_CACHE_OPS
default y
help
This will apply the cache management errata to handle the

View File

@@ -43,8 +43,7 @@ else
KBUILD_LDFLAGS += -melf32lriscv
endif
ifeq ($(CONFIG_LD_IS_LLD),y)
ifeq ($(call test-lt, $(CONFIG_LLD_VERSION), 150000),y)
ifndef CONFIG_RISCV_USE_LINKER_RELAXATION
KBUILD_CFLAGS += -mno-relax
KBUILD_AFLAGS += -mno-relax
ifndef CONFIG_AS_IS_LLVM
@@ -52,7 +51,6 @@ ifndef CONFIG_AS_IS_LLVM
KBUILD_AFLAGS += -Wa,-mno-relax
endif
endif
endif
ifeq ($(CONFIG_SHADOW_CALL_STACK),y)
KBUILD_LDFLAGS += --no-relax-gp
@@ -108,7 +106,9 @@ KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
# unaligned accesses. While unaligned accesses are explicitly allowed in the
# RISC-V ISA, they're emulated by machine mode traps on all extant
# architectures. It's faster to have GCC emit only aligned accesses.
ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS),y)
KBUILD_CFLAGS += $(call cc-option,-mstrict-align)
endif
ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
prepare: stack_protector_prepare
@@ -163,6 +163,8 @@ BOOT_TARGETS := Image Image.gz loader loader.bin xipImage vmlinuz.efi
all: $(notdir $(KBUILD_IMAGE))
loader.bin: loader
Image.gz loader vmlinuz.efi: Image
$(BOOT_TARGETS): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
@$(kecho) ' Kernel: $(boot)/$@ is ready'

View File

@@ -149,6 +149,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_DW=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_SH_SCI=y
CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_HW_RANDOM_VIRTIO=y

View File

@@ -12,8 +12,10 @@
#include <asm/alternative.h>
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/dma-noncoherent.h>
#include <asm/errata_list.h>
#include <asm/hwprobe.h>
#include <asm/io.h>
#include <asm/patch.h>
#include <asm/vendorid_list.h>
@@ -33,6 +35,69 @@ static bool errata_probe_pbmt(unsigned int stage,
return false;
}
/*
* th.dcache.ipa rs1 (invalidate, physical address)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000001 01010 rs1 000 00000 0001011
* th.dcache.iva rs1 (invalidate, virtual address)
* 0000001 00110 rs1 000 00000 0001011
*
* th.dcache.cpa rs1 (clean, physical address)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000001 01001 rs1 000 00000 0001011
* th.dcache.cva rs1 (clean, virtual address)
* 0000001 00101 rs1 000 00000 0001011
*
* th.dcache.cipa rs1 (clean then invalidate, physical address)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000001 01011 rs1 000 00000 0001011
* th.dcache.civa rs1 (clean then invalidate, virtual address)
* 0000001 00111 rs1 000 00000 0001011
*
* th.sync.s (make sure all cache operations finished)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000000 11001 00000 000 00000 0001011
*/
#define THEAD_INVAL_A0 ".long 0x02a5000b"
#define THEAD_CLEAN_A0 ".long 0x0295000b"
#define THEAD_FLUSH_A0 ".long 0x02b5000b"
#define THEAD_SYNC_S ".long 0x0190000b"
#define THEAD_CMO_OP(_op, _start, _size, _cachesize) \
asm volatile("mv a0, %1\n\t" \
"j 2f\n\t" \
"3:\n\t" \
THEAD_##_op##_A0 "\n\t" \
"add a0, a0, %0\n\t" \
"2:\n\t" \
"bltu a0, %2, 3b\n\t" \
THEAD_SYNC_S \
: : "r"(_cachesize), \
"r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \
"r"((unsigned long)(_start) + (_size)) \
: "a0")
static void thead_errata_cache_inv(phys_addr_t paddr, size_t size)
{
THEAD_CMO_OP(INVAL, paddr, size, riscv_cbom_block_size);
}
static void thead_errata_cache_wback(phys_addr_t paddr, size_t size)
{
THEAD_CMO_OP(CLEAN, paddr, size, riscv_cbom_block_size);
}
static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t size)
{
THEAD_CMO_OP(FLUSH, paddr, size, riscv_cbom_block_size);
}
static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops = {
.wback = &thead_errata_cache_wback,
.inv = &thead_errata_cache_inv,
.wback_inv = &thead_errata_cache_wback_inv,
};
static bool errata_probe_cmo(unsigned int stage,
unsigned long arch_id, unsigned long impid)
{
@@ -48,6 +113,7 @@ static bool errata_probe_cmo(unsigned int stage,
if (stage == RISCV_ALTERNATIVES_BOOT) {
riscv_cbom_block_size = L1_CACHE_BYTES;
riscv_noncoherent_supported();
riscv_noncoherent_register_cache_ops(&thead_errata_cmo_ops);
}
return true;
@@ -77,8 +143,7 @@ static u32 thead_errata_probe(unsigned int stage,
if (errata_probe_pbmt(stage, archid, impid))
cpu_req_errata |= BIT(ERRATA_THEAD_PBMT);
if (errata_probe_cmo(stage, archid, impid))
cpu_req_errata |= BIT(ERRATA_THEAD_CMO);
errata_probe_cmo(stage, archid, impid);
if (errata_probe_pmu(stage, archid, impid))
cpu_req_errata |= BIT(ERRATA_THEAD_PMU);

View File

@@ -0,0 +1,78 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Based on arch/x86/include/asm/arch_hweight.h
*/
#ifndef _ASM_RISCV_HWEIGHT_H
#define _ASM_RISCV_HWEIGHT_H
#include <asm/alternative-macros.h>
#include <asm/hwcap.h>
#if (BITS_PER_LONG == 64)
#define CPOPW "cpopw "
#elif (BITS_PER_LONG == 32)
#define CPOPW "cpop "
#else
#error "Unexpected BITS_PER_LONG"
#endif
static __always_inline unsigned int __arch_hweight32(unsigned int w)
{
#ifdef CONFIG_RISCV_ISA_ZBB
asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
asm (".option push\n"
".option arch,+zbb\n"
CPOPW "%0, %0\n"
".option pop\n"
: "+r" (w) : :);
return w;
legacy:
#endif
return __sw_hweight32(w);
}
static inline unsigned int __arch_hweight16(unsigned int w)
{
return __arch_hweight32(w & 0xffff);
}
static inline unsigned int __arch_hweight8(unsigned int w)
{
return __arch_hweight32(w & 0xff);
}
#if BITS_PER_LONG == 64
static __always_inline unsigned long __arch_hweight64(__u64 w)
{
# ifdef CONFIG_RISCV_ISA_ZBB
asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
asm (".option push\n"
".option arch,+zbb\n"
"cpop %0, %0\n"
".option pop\n"
: "+r" (w) : :);
return w;
legacy:
# endif
return __sw_hweight64(w);
}
#else /* BITS_PER_LONG == 64 */
static inline unsigned long __arch_hweight64(__u64 w)
{
return __arch_hweight32((u32)w) +
__arch_hweight32((u32)(w >> 32));
}
#endif /* !(BITS_PER_LONG == 64) */
#endif /* _ASM_RISCV_HWEIGHT_H */

View File

@@ -0,0 +1,72 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Kernel interface for the RISCV arch_random_* functions
*
* Copyright (c) 2023 Rivos Inc.
*
*/
#ifndef ASM_RISCV_ARCHRANDOM_H
#define ASM_RISCV_ARCHRANDOM_H
#include <asm/csr.h>
#include <asm/processor.h>
#define SEED_RETRY_LOOPS 100
static inline bool __must_check csr_seed_long(unsigned long *v)
{
unsigned int retry = SEED_RETRY_LOOPS, valid_seeds = 0;
const int needed_seeds = sizeof(long) / sizeof(u16);
u16 *entropy = (u16 *)v;
do {
/*
* The SEED CSR must be accessed with a read-write instruction.
*/
unsigned long csr_seed = csr_swap(CSR_SEED, 0);
unsigned long opst = csr_seed & SEED_OPST_MASK;
switch (opst) {
case SEED_OPST_ES16:
entropy[valid_seeds++] = csr_seed & SEED_ENTROPY_MASK;
if (valid_seeds == needed_seeds)
return true;
break;
case SEED_OPST_DEAD:
pr_err_once("archrandom: Unrecoverable error\n");
return false;
case SEED_OPST_BIST:
case SEED_OPST_WAIT:
default:
cpu_relax();
continue;
}
} while (--retry);
return false;
}
static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
{
return 0;
}
static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
{
if (!max_longs)
return 0;
/*
* If Zkr is supported and csr_seed_long succeeds, we return one long
* worth of entropy.
*/
if (riscv_has_extension_likely(RISCV_ISA_EXT_ZKR) && csr_seed_long(v))
return 1;
return 0;
}
#endif /* ASM_RISCV_ARCHRANDOM_H */

View File

@@ -6,6 +6,7 @@
#define EX_TYPE_FIXUP 1
#define EX_TYPE_BPF 2
#define EX_TYPE_UACCESS_ERR_ZERO 3
#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD 4
#ifdef CONFIG_MMU
@@ -47,6 +48,11 @@
#define EX_DATA_REG_ZERO_SHIFT 5
#define EX_DATA_REG_ZERO GENMASK(9, 5)
#define EX_DATA_REG_DATA_SHIFT 0
#define EX_DATA_REG_DATA GENMASK(4, 0)
#define EX_DATA_REG_ADDR_SHIFT 5
#define EX_DATA_REG_ADDR GENMASK(9, 5)
#define EX_DATA_REG(reg, gpr) \
"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
@@ -62,6 +68,15 @@
#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \
_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr) \
__DEFINE_ASM_GPR_NUMS \
__ASM_EXTABLE_RAW(#insn, #fixup, \
__stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD), \
"(" \
EX_DATA_REG(DATA, data) " | " \
EX_DATA_REG(ADDR, addr) \
")")
#endif /* __ASSEMBLY__ */
#else /* CONFIG_MMU */

View File

@@ -9,6 +9,33 @@ long long __lshrti3(long long a, int b);
long long __ashrti3(long long a, int b);
long long __ashlti3(long long a, int b);
#ifdef CONFIG_RISCV_ISA_V
#ifdef CONFIG_MMU
asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n);
#endif /* CONFIG_MMU */
void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
const unsigned long *__restrict p2);
void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
const unsigned long *__restrict p2,
const unsigned long *__restrict p3);
void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1,
const unsigned long *__restrict p2,
const unsigned long *__restrict p3,
const unsigned long *__restrict p4);
void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
const unsigned long *__restrict p2,
const unsigned long *__restrict p3,
const unsigned long *__restrict p4,
const unsigned long *__restrict p5);
#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs);
asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs);
#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
#endif /* CONFIG_RISCV_ISA_V */
#define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs)

View File

@@ -271,7 +271,9 @@ legacy:
#include <asm-generic/bitops/fls64.h>
#include <asm-generic/bitops/sched.h>
#include <asm-generic/bitops/hweight.h>
#include <asm/arch_hweight.h>
#include <asm-generic/bitops/const_hweight.h>
#if (BITS_PER_LONG == 64)
#define __AMO(op) "amo" #op ".d"

View File

@@ -0,0 +1,93 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Checksum routines
*
* Copyright (C) 2023 Rivos Inc.
*/
#ifndef __ASM_RISCV_CHECKSUM_H
#define __ASM_RISCV_CHECKSUM_H
#include <linux/in6.h>
#include <linux/uaccess.h>
#define ip_fast_csum ip_fast_csum
extern unsigned int do_csum(const unsigned char *buff, int len);
#define do_csum do_csum
/* Default version is sufficient for 32 bit */
#ifndef CONFIG_32BIT
#define _HAVE_ARCH_IPV6_CSUM
__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__u32 len, __u8 proto, __wsum sum);
#endif
/* Define riscv versions of functions before importing asm-generic/checksum.h */
#include <asm-generic/checksum.h>
/**
* Quickly compute an IP checksum with the assumption that IPv4 headers will
* always be in multiples of 32-bits, and have an ihl of at least 5.
*
* @ihl: the number of 32 bit segments and must be greater than or equal to 5.
* @iph: assumed to be word aligned given that NET_IP_ALIGN is set to 2 on
* riscv, defining IP headers to be aligned.
*/
static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
unsigned long csum = 0;
int pos = 0;
do {
csum += ((const unsigned int *)iph)[pos];
if (IS_ENABLED(CONFIG_32BIT))
csum += csum < ((const unsigned int *)iph)[pos];
} while (++pos < ihl);
/*
* ZBB only saves three instructions on 32-bit and five on 64-bit so not
* worth checking if supported without Alternatives.
*/
if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) &&
IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
unsigned long fold_temp;
asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
:
:
:
: no_zbb);
if (IS_ENABLED(CONFIG_32BIT)) {
asm(".option push \n\
.option arch,+zbb \n\
not %[fold_temp], %[csum] \n\
rori %[csum], %[csum], 16 \n\
sub %[csum], %[fold_temp], %[csum] \n\
.option pop"
: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
} else {
asm(".option push \n\
.option arch,+zbb \n\
rori %[fold_temp], %[csum], 32 \n\
add %[csum], %[fold_temp], %[csum] \n\
srli %[csum], %[csum], 32 \n\
not %[fold_temp], %[csum] \n\
roriw %[csum], %[csum], 16 \n\
subw %[csum], %[fold_temp], %[csum] \n\
.option pop"
: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
}
return (__force __sum16)(csum >> 16);
}
no_zbb:
#ifndef CONFIG_32BIT
csum += ror64(csum, 32);
csum >>= 32;
#endif
return csum_fold((__force __wsum)csum);
}
#endif /* __ASM_RISCV_CHECKSUM_H */

View File

@@ -135,4 +135,6 @@ static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsi
return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
}
DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
#endif

View File

@@ -411,6 +411,15 @@
#define CSR_VTYPE 0xc21
#define CSR_VLENB 0xc22
/* Scalar Crypto Extension - Entropy */
#define CSR_SEED 0x015
#define SEED_OPST_MASK _AC(0xC0000000, UL)
#define SEED_OPST_BIST _AC(0x00000000, UL)
#define SEED_OPST_WAIT _AC(0x40000000, UL)
#define SEED_OPST_ES16 _AC(0x80000000, UL)
#define SEED_OPST_DEAD _AC(0xC0000000, UL)
#define SEED_ENTROPY_MASK _AC(0xFFFF, UL)
#ifdef CONFIG_RISCV_M_MODE
# define CSR_STATUS CSR_MSTATUS
# define CSR_IE CSR_MIE

View File

@@ -4,6 +4,23 @@
#define _ASM_RISCV_ENTRY_COMMON_H
#include <asm/stacktrace.h>
#include <asm/thread_info.h>
#include <asm/vector.h>
static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
unsigned long ti_work)
{
if (ti_work & _TIF_RISCV_V_DEFER_RESTORE) {
clear_thread_flag(TIF_RISCV_V_DEFER_RESTORE);
/*
* We are already called with irq disabled, so go without
* keeping track of riscv_v_flags.
*/
riscv_v_vstate_restore(&current->thread.vstate, regs);
}
}
#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
void handle_page_fault(struct pt_regs *regs);
void handle_break(struct pt_regs *regs);

View File

@@ -24,9 +24,8 @@
#ifdef CONFIG_ERRATA_THEAD
#define ERRATA_THEAD_PBMT 0
#define ERRATA_THEAD_CMO 1
#define ERRATA_THEAD_PMU 2
#define ERRATA_THEAD_NUMBER 3
#define ERRATA_THEAD_PMU 1
#define ERRATA_THEAD_NUMBER 2
#endif
#ifdef __ASSEMBLY__
@@ -94,54 +93,17 @@ asm volatile(ALTERNATIVE( \
#define ALT_THEAD_PMA(_val)
#endif
/*
* th.dcache.ipa rs1 (invalidate, physical address)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000001 01010 rs1 000 00000 0001011
* th.dache.iva rs1 (invalida, virtual address)
* 0000001 00110 rs1 000 00000 0001011
*
* th.dcache.cpa rs1 (clean, physical address)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000001 01001 rs1 000 00000 0001011
* th.dcache.cva rs1 (clean, virtual address)
* 0000001 00101 rs1 000 00000 0001011
*
* th.dcache.cipa rs1 (clean then invalidate, physical address)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000001 01011 rs1 000 00000 0001011
* th.dcache.civa rs1 (... virtual address)
* 0000001 00111 rs1 000 00000 0001011
*
* th.sync.s (make sure all cache operations finished)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000000 11001 00000 000 00000 0001011
*/
#define THEAD_INVAL_A0 ".long 0x0265000b"
#define THEAD_CLEAN_A0 ".long 0x0255000b"
#define THEAD_FLUSH_A0 ".long 0x0275000b"
#define THEAD_SYNC_S ".long 0x0190000b"
#define ALT_CMO_OP(_op, _start, _size, _cachesize) \
asm volatile(ALTERNATIVE_2( \
__nops(6), \
asm volatile(ALTERNATIVE( \
__nops(5), \
"mv a0, %1\n\t" \
"j 2f\n\t" \
"3:\n\t" \
CBO_##_op(a0) \
"add a0, a0, %0\n\t" \
"2:\n\t" \
"bltu a0, %2, 3b\n\t" \
"nop", 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM, \
"mv a0, %1\n\t" \
"j 2f\n\t" \
"3:\n\t" \
THEAD_##_op##_A0 "\n\t" \
"add a0, a0, %0\n\t" \
"2:\n\t" \
"bltu a0, %2, 3b\n\t" \
THEAD_SYNC_S, THEAD_VENDOR_ID, \
ERRATA_THEAD_CMO, CONFIG_ERRATA_THEAD_CMO) \
"bltu a0, %2, 3b\n\t", \
0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM) \
: : "r"(_cachesize), \
"r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \
"r"((unsigned long)(_start) + (_size)) \

View File

@@ -128,7 +128,23 @@ do { \
struct dyn_ftrace;
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
#define ftrace_init_nop ftrace_init_nop
#endif
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
struct ftrace_ops;
struct ftrace_regs;
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs);
#define ftrace_graph_func ftrace_graph_func
static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
{
regs->t1 = addr;
}
#define arch_ftrace_set_direct_caller(fregs, addr) \
__arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
#endif /* __ASSEMBLY__ */
#endif /* CONFIG_DYNAMIC_FTRACE */

View File

@@ -865,7 +865,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
#define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
#ifdef CONFIG_COMPAT
#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE)
#define TASK_SIZE_32 (_AC(0x80000000, UL))
#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
TASK_SIZE_32 : TASK_SIZE_64)
#else

Some files were not shown because too many files have changed in this diff Show More