summaryrefslogtreecommitdiff
path: root/arch/riscv/kernel
diff options
context:
space:
mode:
authorPalmer Dabbelt <palmer@dabbelt.com>2025-06-05 11:23:07 -0700
committerPalmer Dabbelt <palmer@dabbelt.com>2025-06-05 14:03:16 -0700
commit2670a39b1ea68fb0b9175e26e299f3fe974e0332 (patch)
treee0a6198c7e5e3628e4e3aff52bce963472646647 /arch/riscv/kernel
parent7bc76fb3883aaba56b16dc4009ba8a490b8dc6ab (diff)
parentee0d03053e7009a3a3532fb37f6c94bfa0a8cca3 (diff)
Merge tag 'riscv-mw2-6.16-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/alexghiti/linux into for-next
riscv patches for 6.16-rc1, part 2 * Performance improvements - Add support for vdso getrandom - Implement raid6 calculations using vectors - Introduce svinval tlb invalidation * Cleanup - A bunch of deduplication of the macros we use for manipulating instructions * Misc - Introduce a kunit test for kprobes - Add support for mseal as riscv fits the requirements (thanks to Lorenzo for making sure of that :)) [Palmer: There was a rebase between part 1 and part 2, so I've had to do some more git surgery here... at least two rounds of surgery...] * alex-pr-2: (866 commits) RISC-V: vDSO: Wire up getrandom() vDSO implementation riscv: enable mseal sysmap for RV64 raid6: Add RISC-V SIMD syndrome and recovery calculations riscv: mm: Add support for Svinval extension riscv: Add kprobes KUnit test riscv: kprobes: Remove duplication of RV_EXTRACT_ITYPE_IMM riscv: kprobes: Remove duplication of RV_EXTRACT_UTYPE_IMM riscv: kprobes: Remove duplication of RV_EXTRACT_RD_REG riscv: kprobes: Remove duplication of RVC_EXTRACT_BTYPE_IMM riscv: kprobes: Remove duplication of RVC_EXTRACT_C2_RS1_REG riscv: kproves: Remove duplication of RVC_EXTRACT_JTYPE_IMM riscv: kprobes: Remove duplication of RV_EXTRACT_BTYPE_IMM riscv: kprobes: Remove duplication of RV_EXTRACT_RS1_REG riscv: kprobes: Remove duplication of RV_EXTRACT_JTYPE_IMM riscv: kprobes: Move branch_funct3 to insn.h riscv: kprobes: Move branch_rs2_idx to insn.h Linux 6.15-rc6 Input: xpad - fix xpad_device sorting Input: xpad - add support for several more controllers Input: xpad - fix Share button on Xbox One controllers ...
Diffstat (limited to 'arch/riscv/kernel')
-rw-r--r--arch/riscv/kernel/Makefile4
-rw-r--r--arch/riscv/kernel/probes/uprobes.c10
-rw-r--r--arch/riscv/kernel/process.c6
-rw-r--r--arch/riscv/kernel/traps.c64
-rw-r--r--arch/riscv/kernel/traps_misaligned.c2
-rw-r--r--arch/riscv/kernel/vdso.c2
-rw-r--r--arch/riscv/kernel/vdso/Makefile13
-rw-r--r--arch/riscv/kernel/vdso/getrandom.c10
-rw-r--r--arch/riscv/kernel/vdso/vdso.lds.S3
-rw-r--r--arch/riscv/kernel/vdso/vgetrandom-chacha.S249
10 files changed, 324 insertions, 39 deletions
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 0ead29826419..7ce2307738c2 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -9,8 +9,8 @@ CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
endif
-CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,)
-CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init)
+CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init)
ifdef CONFIG_KEXEC_CORE
AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 4b3dc8beaf77..cc15f7ca6cc1 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
/* Initialize the slot */
void *kaddr = kmap_atomic(page);
void *dst = kaddr + (vaddr & ~PAGE_MASK);
+ unsigned long start = (unsigned long)dst;
memcpy(dst, src, len);
@@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
*(uprobe_opcode_t *)dst = __BUG_INSN_32;
}
+ flush_icache_range(start, start + len);
kunmap_atomic(kaddr);
-
- /*
- * We probably need flush_icache_user_page() but it needs vma.
- * This should work on most of architectures by default. If
- * architecture needs to do something different it can define
- * its own version of the function.
- */
- flush_dcache_page(page);
}
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 7c244de77180..15d8f75902f8 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -275,6 +275,9 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
unsigned long pmm;
u8 pmlen;
+ if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+ return -EINVAL;
+
if (is_compat_thread(ti))
return -EINVAL;
@@ -330,6 +333,9 @@ long get_tagged_addr_ctrl(struct task_struct *task)
struct thread_info *ti = task_thread_info(task);
long ret = 0;
+ if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
+ return -EINVAL;
+
if (is_compat_thread(ti))
return -EINVAL;
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 8ff8e8b36524..9c83848797a7 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -198,47 +198,57 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
DO_ERROR_INFO(do_trap_load_fault,
SIGSEGV, SEGV_ACCERR, "load access fault");
-asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
+enum misaligned_access_type {
+ MISALIGNED_STORE,
+ MISALIGNED_LOAD,
+};
+static const struct {
+ const char *type_str;
+ int (*handler)(struct pt_regs *regs);
+} misaligned_handler[] = {
+ [MISALIGNED_STORE] = {
+ .type_str = "Oops - store (or AMO) address misaligned",
+ .handler = handle_misaligned_store,
+ },
+ [MISALIGNED_LOAD] = {
+ .type_str = "Oops - load address misaligned",
+ .handler = handle_misaligned_load,
+ },
+};
+
+static void do_trap_misaligned(struct pt_regs *regs, enum misaligned_access_type type)
{
+ irqentry_state_t state;
+
if (user_mode(regs)) {
irqentry_enter_from_user_mode(regs);
+ local_irq_enable();
+ } else {
+ state = irqentry_nmi_enter(regs);
+ }
- if (handle_misaligned_load(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - load address misaligned");
+ if (misaligned_handler[type].handler(regs))
+ do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
+ misaligned_handler[type].type_str);
+ if (user_mode(regs)) {
+ local_irq_disable();
irqentry_exit_to_user_mode(regs);
} else {
- irqentry_state_t state = irqentry_nmi_enter(regs);
-
- if (handle_misaligned_load(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - load address misaligned");
-
irqentry_nmi_exit(regs, state);
}
}
-asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs)
+asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
{
- if (user_mode(regs)) {
- irqentry_enter_from_user_mode(regs);
-
- if (handle_misaligned_store(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - store (or AMO) address misaligned");
-
- irqentry_exit_to_user_mode(regs);
- } else {
- irqentry_state_t state = irqentry_nmi_enter(regs);
-
- if (handle_misaligned_store(regs))
- do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc,
- "Oops - store (or AMO) address misaligned");
+ do_trap_misaligned(regs, MISALIGNED_LOAD);
+}
- irqentry_nmi_exit(regs, state);
- }
+asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs)
+{
+ do_trap_misaligned(regs, MISALIGNED_STORE);
}
+
DO_ERROR_INFO(do_trap_store_fault,
SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
DO_ERROR_INFO(do_trap_ecall_s,
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 7443632445d4..56f06a27d45f 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -275,7 +275,7 @@ static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
int __ret; \
\
if (user_mode(regs)) { \
- __ret = __get_user(insn, (type __user *) insn_addr); \
+ __ret = get_user(insn, (type __user *) insn_addr); \
} else { \
insn = *(type *)insn_addr; \
__ret = 0; \
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index cc2895d1fbc2..3a8e038b10a2 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -136,7 +136,7 @@ static int __setup_additional_pages(struct mm_struct *mm,
ret =
_install_special_mapping(mm, vdso_base, vdso_text_len,
- (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+ (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_SEALED_SYSMAP),
vdso_info->cm);
if (IS_ERR(ret))
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 4a5d131506fc..9ebb5e590f93 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -13,9 +13,17 @@ vdso-syms += flush_icache
vdso-syms += hwprobe
vdso-syms += sys_hwprobe
+ifdef CONFIG_VDSO_GETRANDOM
+vdso-syms += getrandom
+endif
+
# Files to link into the vdso
obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
+ifdef CONFIG_VDSO_GETRANDOM
+obj-vdso += vgetrandom-chacha.o
+endif
+
ccflags-y := -fno-stack-protector
ccflags-y += -DDISABLE_BRANCH_PROFILING
ccflags-y += -fno-builtin
@@ -24,6 +32,10 @@ ifneq ($(c-gettimeofday-y),)
CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
endif
+ifneq ($(c-getrandom-y),)
+ CFLAGS_getrandom.o += -fPIC -include $(c-getrandom-y)
+endif
+
CFLAGS_hwprobe.o += -fPIC
# Build rules
@@ -38,6 +50,7 @@ endif
# Disable -pg to prevent insert call site
CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_getrandom.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
# Force dependency
diff --git a/arch/riscv/kernel/vdso/getrandom.c b/arch/riscv/kernel/vdso/getrandom.c
new file mode 100644
index 000000000000..f21922e8cebd
--- /dev/null
+++ b/arch/riscv/kernel/vdso/getrandom.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved.
+ */
+#include <linux/types.h>
+
+ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len)
+{
+ return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len);
+}
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 8e86965a8aae..7c15b0f4ee3b 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -80,6 +80,9 @@ VERSION
#ifndef COMPAT_VDSO
__vdso_riscv_hwprobe;
#endif
+#if defined(CONFIG_VDSO_GETRANDOM) && !defined(COMPAT_VDSO)
+ __vdso_getrandom;
+#endif
local: *;
};
}
diff --git a/arch/riscv/kernel/vdso/vgetrandom-chacha.S b/arch/riscv/kernel/vdso/vgetrandom-chacha.S
new file mode 100644
index 000000000000..5f0dad8f2373
--- /dev/null
+++ b/arch/riscv/kernel/vdso/vgetrandom-chacha.S
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2025 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved.
+ *
+ * Based on arch/loongarch/vdso/vgetrandom-chacha.S.
+ */
+
+#include <asm/asm.h>
+#include <linux/linkage.h>
+
+.text
+
+.macro ROTRI rd rs imm
+ slliw t0, \rs, 32 - \imm
+ srliw \rd, \rs, \imm
+ or \rd, \rd, t0
+.endm
+
+.macro OP_4REG op d0 d1 d2 d3 s0 s1 s2 s3
+ \op \d0, \d0, \s0
+ \op \d1, \d1, \s1
+ \op \d2, \d2, \s2
+ \op \d3, \d3, \s3
+.endm
+
+/*
+ * a0: output bytes
+ * a1: 32-byte key input
+ * a2: 8-byte counter input/output
+ * a3: number of 64-byte blocks to write to output
+ */
+SYM_FUNC_START(__arch_chacha20_blocks_nostack)
+
+#define output a0
+#define key a1
+#define counter a2
+#define nblocks a3
+#define i a4
+#define state0 s0
+#define state1 s1
+#define state2 s2
+#define state3 s3
+#define state4 s4
+#define state5 s5
+#define state6 s6
+#define state7 s7
+#define state8 s8
+#define state9 s9
+#define state10 s10
+#define state11 s11
+#define state12 a5
+#define state13 a6
+#define state14 a7
+#define state15 t1
+#define cnt t2
+#define copy0 t3
+#define copy1 t4
+#define copy2 t5
+#define copy3 t6
+
+/* Packs to be used with OP_4REG */
+#define line0 state0, state1, state2, state3
+#define line1 state4, state5, state6, state7
+#define line2 state8, state9, state10, state11
+#define line3 state12, state13, state14, state15
+
+#define line1_perm state5, state6, state7, state4
+#define line2_perm state10, state11, state8, state9
+#define line3_perm state15, state12, state13, state14
+
+#define copy copy0, copy1, copy2, copy3
+
+#define _16 16, 16, 16, 16
+#define _20 20, 20, 20, 20
+#define _24 24, 24, 24, 24
+#define _25 25, 25, 25, 25
+
+ /*
+ * The ABI requires s0-s9 saved.
+ * This does not violate the stack-less requirement: no sensitive data
+ * is spilled onto the stack.
+ */
+ addi sp, sp, -12*SZREG
+ REG_S s0, (sp)
+ REG_S s1, SZREG(sp)
+ REG_S s2, 2*SZREG(sp)
+ REG_S s3, 3*SZREG(sp)
+ REG_S s4, 4*SZREG(sp)
+ REG_S s5, 5*SZREG(sp)
+ REG_S s6, 6*SZREG(sp)
+ REG_S s7, 7*SZREG(sp)
+ REG_S s8, 8*SZREG(sp)
+ REG_S s9, 9*SZREG(sp)
+ REG_S s10, 10*SZREG(sp)
+ REG_S s11, 11*SZREG(sp)
+
+ ld cnt, (counter)
+
+ li copy0, 0x61707865
+ li copy1, 0x3320646e
+ li copy2, 0x79622d32
+ li copy3, 0x6b206574
+
+.Lblock:
+ /* state[0,1,2,3] = "expand 32-byte k" */
+ mv state0, copy0
+ mv state1, copy1
+ mv state2, copy2
+ mv state3, copy3
+
+ /* state[4,5,..,11] = key */
+ lw state4, (key)
+ lw state5, 4(key)
+ lw state6, 8(key)
+ lw state7, 12(key)
+ lw state8, 16(key)
+ lw state9, 20(key)
+ lw state10, 24(key)
+ lw state11, 28(key)
+
+ /* state[12,13] = counter */
+ mv state12, cnt
+ srli state13, cnt, 32
+
+ /* state[14,15] = 0 */
+ mv state14, zero
+ mv state15, zero
+
+ li i, 10
+.Lpermute:
+ /* odd round */
+ OP_4REG addw line0, line1
+ OP_4REG xor line3, line0
+ OP_4REG ROTRI line3, _16
+
+ OP_4REG addw line2, line3
+ OP_4REG xor line1, line2
+ OP_4REG ROTRI line1, _20
+
+ OP_4REG addw line0, line1
+ OP_4REG xor line3, line0
+ OP_4REG ROTRI line3, _24
+
+ OP_4REG addw line2, line3
+ OP_4REG xor line1, line2
+ OP_4REG ROTRI line1, _25
+
+ /* even round */
+ OP_4REG addw line0, line1_perm
+ OP_4REG xor line3_perm, line0
+ OP_4REG ROTRI line3_perm, _16
+
+ OP_4REG addw line2_perm, line3_perm
+ OP_4REG xor line1_perm, line2_perm
+ OP_4REG ROTRI line1_perm, _20
+
+ OP_4REG addw line0, line1_perm
+ OP_4REG xor line3_perm, line0
+ OP_4REG ROTRI line3_perm, _24
+
+ OP_4REG addw line2_perm, line3_perm
+ OP_4REG xor line1_perm, line2_perm
+ OP_4REG ROTRI line1_perm, _25
+
+ addi i, i, -1
+ bnez i, .Lpermute
+
+ /* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */
+ OP_4REG addw line0, copy
+ sw state0, (output)
+ sw state1, 4(output)
+ sw state2, 8(output)
+ sw state3, 12(output)
+
+ /* from now on state[0,1,2,3] are scratch registers */
+
+ /* state[0,1,2,3] = lo(key) */
+ lw state0, (key)
+ lw state1, 4(key)
+ lw state2, 8(key)
+ lw state3, 12(key)
+
+ /* output[4,5,6,7] = state[0,1,2,3] + state[4,5,6,7] */
+ OP_4REG addw line1, line0
+ sw state4, 16(output)
+ sw state5, 20(output)
+ sw state6, 24(output)
+ sw state7, 28(output)
+
+ /* state[0,1,2,3] = hi(key) */
+ lw state0, 16(key)
+ lw state1, 20(key)
+ lw state2, 24(key)
+ lw state3, 28(key)
+
+ /* output[8,9,10,11] = tmp[0,1,2,3] + state[8,9,10,11] */
+ OP_4REG addw line2, line0
+ sw state8, 32(output)
+ sw state9, 36(output)
+ sw state10, 40(output)
+ sw state11, 44(output)
+
+ /* output[12,13,14,15] = state[12,13,14,15] + [cnt_lo, cnt_hi, 0, 0] */
+ addw state12, state12, cnt
+ srli state0, cnt, 32
+ addw state13, state13, state0
+ sw state12, 48(output)
+ sw state13, 52(output)
+ sw state14, 56(output)
+ sw state15, 60(output)
+
+ /* ++counter */
+ addi cnt, cnt, 1
+
+ /* output += 64 */
+ addi output, output, 64
+ /* --nblocks */
+ addi nblocks, nblocks, -1
+ bnez nblocks, .Lblock
+
+ /* counter = [cnt_lo, cnt_hi] */
+ sd cnt, (counter)
+
+ /* Zero out the potentially sensitive regs, in case nothing uses these
+ * again. As at now copy[0,1,2,3] just contains "expand 32-byte k" and
+ * state[0,...,11] are s0-s11 those we'll restore in the epilogue, we
+ * only need to zero state[12,...,15].
+ */
+ mv state12, zero
+ mv state13, zero
+ mv state14, zero
+ mv state15, zero
+
+ REG_L s0, (sp)
+ REG_L s1, SZREG(sp)
+ REG_L s2, 2*SZREG(sp)
+ REG_L s3, 3*SZREG(sp)
+ REG_L s4, 4*SZREG(sp)
+ REG_L s5, 5*SZREG(sp)
+ REG_L s6, 6*SZREG(sp)
+ REG_L s7, 7*SZREG(sp)
+ REG_L s8, 8*SZREG(sp)
+ REG_L s9, 9*SZREG(sp)
+ REG_L s10, 10*SZREG(sp)
+ REG_L s11, 11*SZREG(sp)
+ addi sp, sp, 12*SZREG
+
+ ret
+SYM_FUNC_END(__arch_chacha20_blocks_nostack)