diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index 36b955c762ba08e92ca0441ee8fbae9219c1f2fa..6db1a9bbff4ce35d1e05261094bb2efa2ef311a1 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -9,6 +9,24 @@ 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 + +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); + +#endif /* CONFIG_RISCV_ISA_V */ #define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs) diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h new file mode 100644 index 0000000000000000000000000000000000000000..96011861e46b4df24cb973a9066324283ad17b60 --- /dev/null +++ b/arch/riscv/include/asm/xor.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2021 SiFive + */ + +#include +#include +#ifdef CONFIG_RISCV_ISA_V +#include +#include +#include + +static void xor_vector_2(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2) +{ + kernel_vector_begin(); + xor_regs_2_(bytes, p1, p2); + kernel_vector_end(); +} + +static void xor_vector_3(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3) +{ + kernel_vector_begin(); + xor_regs_3_(bytes, p1, p2, p3); + kernel_vector_end(); +} + +static void xor_vector_4(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3, + const unsigned long *__restrict p4) +{ + kernel_vector_begin(); + xor_regs_4_(bytes, p1, p2, p3, p4); + kernel_vector_end(); +} + +static void xor_vector_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) +{ + kernel_vector_begin(); + xor_regs_5_(bytes, p1, p2, p3, p4, p5); + kernel_vector_end(); +} + +static struct xor_block_template xor_block_rvv = { + .name = "rvv", + .do_2 = xor_vector_2, + .do_3 = xor_vector_3, + .do_4 = xor_vector_4, + .do_5 = xor_vector_5 +}; + +#undef XOR_TRY_TEMPLATES +#define XOR_TRY_TEMPLATES \ + do { \ + xor_speed(&xor_block_8regs); \ + xor_speed(&xor_block_32regs); \ + if (has_vector()) { \ + xor_speed(&xor_block_rvv);\ + } \ + } while (0) +#endif diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index f27252a4b5d57c4c614656c2a09460701bf3a0c8..1b8379dd9a5d7629866d883648e3e2433f348a7c 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -25,9 +25,9 @@ SYM_CODE_START(handle_exception) * register will contain 0, and we should continue on the current TP. */ csrrw tp, CSR_SCRATCH, tp - bnez tp, _save_context + bnez tp, .Lsave_context -_restore_kernel_tpsp: +.Lrestore_kernel_tpsp: csrr tp, CSR_SCRATCH REG_S sp, TASK_TI_KERNEL_SP(tp) @@ -39,7 +39,7 @@ _restore_kernel_tpsp: REG_L sp, TASK_TI_KERNEL_SP(tp) #endif -_save_context: +.Lsave_context: REG_S sp, TASK_TI_USER_SP(tp) REG_L sp, TASK_TI_KERNEL_SP(tp) addi sp, sp, -(PT_SIZE_ON_STACK) diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 0097c145385f6794d9424a2034ff64654c4a62ea..d3299ae6cc546d51a63d14d8fa6b99ec957a46b7 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -169,12 +169,12 @@ secondary_start_sbi: XIP_FIXUP_OFFSET a0 call relocate_enable_mmu #endif - call setup_trap_vector + call .Lsetup_trap_vector tail smp_callin #endif /* CONFIG_SMP */ .align 2 -setup_trap_vector: +.Lsetup_trap_vector: /* Set trap vector to exception handler */ la a0, handle_exception csrw CSR_TVEC, a0 @@ -211,7 +211,7 @@ ENTRY(_start_kernel) * not implement PMPs, so we set up a quick trap handler to just skip * touching the PMPs on any trap. */ - la a0, pmp_done + la a0, .Lpmp_done csrw CSR_TVEC, a0 li a0, -1 @@ -219,7 +219,7 @@ ENTRY(_start_kernel) li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X) csrw CSR_PMPCFG0, a0 .align 2 -pmp_done: +.Lpmp_done: /* * The hartid in a0 is expected later on, and we have no firmware @@ -283,12 +283,12 @@ pmp_done: /* Clear BSS for flat non-ELF images */ la a3, __bss_start la a4, __bss_stop - ble a4, a3, clear_bss_done -clear_bss: + ble a4, a3, .Lclear_bss_done +.Lclear_bss: REG_S zero, (a3) add a3, a3, RISCV_SZPTR - blt a3, a4, clear_bss -clear_bss_done: + blt a3, a4, .Lclear_bss +.Lclear_bss_done: #endif la a2, boot_cpu_hartid XIP_FIXUP_OFFSET a2 @@ -312,7 +312,7 @@ clear_bss_done: call relocate_enable_mmu #endif /* CONFIG_MMU */ - call setup_trap_vector + call .Lsetup_trap_vector /* Restore C environment */ la tp, init_task la sp, init_thread_union + THREAD_SIZE diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 8818a8fa9ff3af7b3427e2456f1650c5c6cb7168..ab4dd0594fe7bdc0ee83e4a5975c9760829c4c88 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -85,16 +85,16 @@ ENTRY(MCOUNT_NAME) #ifdef CONFIG_FUNCTION_GRAPH_TRACER la t0, ftrace_graph_return REG_L t1, 0(t0) - bne t1, t4, do_ftrace_graph_caller + bne t1, t4, .Ldo_ftrace_graph_caller la t3, ftrace_graph_entry REG_L t2, 0(t3) la t6, ftrace_graph_entry_stub - bne t2, t6, do_ftrace_graph_caller + bne t2, t6, .Ldo_ftrace_graph_caller #endif la t3, ftrace_trace_function REG_L t5, 0(t3) - bne t5, t4, do_trace + bne t5, t4, .Ldo_trace ret #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -102,7 +102,7 @@ ENTRY(MCOUNT_NAME) * A pseudo representation for the function graph tracer: * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller) */ -do_ftrace_graph_caller: +.Ldo_ftrace_graph_caller: addi a0, s0, -SZREG mv a1, ra #ifdef HAVE_FUNCTION_GRAPH_FP_TEST @@ -118,7 +118,7 @@ do_ftrace_graph_caller: * A pseudo representation for the function tracer: * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller) */ -do_trace: +.Ldo_trace: REG_L a1, -SZREG(s0) mv a0, ra diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index 3348a61de7d998c6a87ce8e7113d67fefc1c955a..2932791e93882176bd1a515781f9e9f0d1145424 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -62,7 +62,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, perf_callchain_store(entry, regs->epc); fp = user_backtrace(entry, fp, regs->ra); - while (fp && !(fp & 0x3) && entry->nr < entry->max_stack) + while (fp && !(fp & 0x7) && entry->nr < entry->max_stack) fp = user_backtrace(entry, fp, 0); } diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 183bf2097d57a9ee554970c8b7549edfd797a1ac..9845db37a935fbd3aa195cd2373d6b5f5b6f75f0 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -12,3 +12,4 @@ lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o lib-$(CONFIG_RISCV_ISA_ZBC) += crc32.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +lib-$(CONFIG_RISCV_ISA_V) += xor.o diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S index 838ff2022fe32d8e16769ef0e5962d9c294b0ed3..1930b388c3a0c67e61e65337f8a763626b74804c 100644 --- a/arch/riscv/lib/memmove.S +++ b/arch/riscv/lib/memmove.S @@ -26,8 +26,8 @@ SYM_FUNC_START_WEAK(memmove) */ /* Return if nothing to do */ - beq a0, a1, return_from_memmove - beqz a2, return_from_memmove + beq a0, a1, .Lreturn_from_memmove + beqz a2, .Lreturn_from_memmove /* * Register Uses @@ -60,7 +60,7 @@ SYM_FUNC_START_WEAK(memmove) * small enough not to bother. */ andi t0, a2, -(2 * SZREG) - beqz t0, byte_copy + beqz t0, .Lbyte_copy /* * Now solve for t5 and t6. @@ -87,14 +87,14 @@ SYM_FUNC_START_WEAK(memmove) */ xor t0, a0, a1 andi t1, t0, (SZREG - 1) - beqz t1, coaligned_copy + beqz t1, .Lcoaligned_copy /* Fall through to misaligned fixup copy */ -misaligned_fixup_copy: - bltu a1, a0, misaligned_fixup_copy_reverse +.Lmisaligned_fixup_copy: + bltu a1, a0, .Lmisaligned_fixup_copy_reverse -misaligned_fixup_copy_forward: - jal t0, byte_copy_until_aligned_forward +.Lmisaligned_fixup_copy_forward: + jal t0, .Lbyte_copy_until_aligned_forward andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */ slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */ @@ -153,10 +153,10 @@ misaligned_fixup_copy_forward: mv t3, t6 /* Fix the dest pointer in case the loop was broken */ add a1, t3, a5 /* Restore the src pointer */ - j byte_copy_forward /* Copy any remaining bytes */ + j .Lbyte_copy_forward /* Copy any remaining bytes */ -misaligned_fixup_copy_reverse: - jal t0, byte_copy_until_aligned_reverse +.Lmisaligned_fixup_copy_reverse: + jal t0, .Lbyte_copy_until_aligned_reverse andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */ slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */ @@ -215,18 +215,18 @@ misaligned_fixup_copy_reverse: mv t4, t5 /* Fix the dest pointer in case the loop was broken */ add a4, t4, a5 /* Restore the src pointer */ - j byte_copy_reverse /* Copy any remaining bytes */ + j .Lbyte_copy_reverse /* Copy any remaining bytes */ /* * Simple copy loops for SZREG co-aligned memory locations. * These also make calls to do byte copies for any unaligned * data at their terminations. */ -coaligned_copy: - bltu a1, a0, coaligned_copy_reverse +.Lcoaligned_copy: + bltu a1, a0, .Lcoaligned_copy_reverse -coaligned_copy_forward: - jal t0, byte_copy_until_aligned_forward +.Lcoaligned_copy_forward: + jal t0, .Lbyte_copy_until_aligned_forward 1: REG_L t1, ( 0 * SZREG)(a1) @@ -235,10 +235,10 @@ coaligned_copy_forward: REG_S t1, (-1 * SZREG)(t3) bne t3, t6, 1b - j byte_copy_forward /* Copy any remaining bytes */ + j .Lbyte_copy_forward /* Copy any remaining bytes */ -coaligned_copy_reverse: - jal t0, byte_copy_until_aligned_reverse +.Lcoaligned_copy_reverse: + jal t0, .Lbyte_copy_until_aligned_reverse 1: REG_L t1, (-1 * SZREG)(a4) @@ -247,7 +247,7 @@ coaligned_copy_reverse: REG_S t1, ( 0 * SZREG)(t4) bne t4, t5, 1b - j byte_copy_reverse /* Copy any remaining bytes */ + j .Lbyte_copy_reverse /* Copy any remaining bytes */ /* * These are basically sub-functions within the function. They @@ -258,7 +258,7 @@ coaligned_copy_reverse: * up from where they were left and we avoid code duplication * without any overhead except the call in and return jumps. */ -byte_copy_until_aligned_forward: +.Lbyte_copy_until_aligned_forward: beq t3, t5, 2f 1: lb t1, 0(a1) @@ -269,7 +269,7 @@ byte_copy_until_aligned_forward: 2: jalr zero, 0x0(t0) /* Return to multibyte copy loop */ -byte_copy_until_aligned_reverse: +.Lbyte_copy_until_aligned_reverse: beq t4, t6, 2f 1: lb t1, -1(a4) @@ -285,10 +285,10 @@ byte_copy_until_aligned_reverse: * These will byte copy until they reach the end of data to copy. * At that point, they will call to return from memmove. */ -byte_copy: - bltu a1, a0, byte_copy_reverse +.Lbyte_copy: + bltu a1, a0, .Lbyte_copy_reverse -byte_copy_forward: +.Lbyte_copy_forward: beq t3, t4, 2f 1: lb t1, 0(a1) @@ -299,7 +299,7 @@ byte_copy_forward: 2: ret -byte_copy_reverse: +.Lbyte_copy_reverse: beq t4, t3, 2f 1: lb t1, -1(a4) @@ -309,7 +309,7 @@ byte_copy_reverse: bne t4, t3, 1b 2: -return_from_memmove: +.Lreturn_from_memmove: ret SYM_FUNC_END(memmove) diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S new file mode 100644 index 0000000000000000000000000000000000000000..b28f2430e52fa50c199cd80153647fde33088e4c --- /dev/null +++ b/arch/riscv/lib/xor.S @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2021 SiFive + */ +#include +#include +#include + +SYM_FUNC_START(xor_regs_2_) + vsetvli a3, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a3 + vxor.vv v16, v0, v8 + add a2, a2, a3 + vse8.v v16, (a1) + add a1, a1, a3 + bnez a0, xor_regs_2_ + ret +SYM_FUNC_END(xor_regs_2_) +EXPORT_SYMBOL(xor_regs_2_) + +SYM_FUNC_START(xor_regs_3_) + vsetvli a4, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a4 + vxor.vv v0, v0, v8 + vle8.v v16, (a3) + add a2, a2, a4 + vxor.vv v16, v0, v16 + add a3, a3, a4 + vse8.v v16, (a1) + add a1, a1, a4 + bnez a0, xor_regs_3_ + ret +SYM_FUNC_END(xor_regs_3_) +EXPORT_SYMBOL(xor_regs_3_) + +SYM_FUNC_START(xor_regs_4_) + vsetvli a5, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a5 + vxor.vv v0, v0, v8 + vle8.v v16, (a3) + add a2, a2, a5 + vxor.vv v0, v0, v16 + vle8.v v24, (a4) + add a3, a3, a5 + vxor.vv v16, v0, v24 + add a4, a4, a5 + vse8.v v16, (a1) + add a1, a1, a5 + bnez a0, xor_regs_4_ + ret +SYM_FUNC_END(xor_regs_4_) +EXPORT_SYMBOL(xor_regs_4_) + +SYM_FUNC_START(xor_regs_5_) + vsetvli a6, a0, e8, m8, ta, ma + vle8.v v0, (a1) + vle8.v v8, (a2) + sub a0, a0, a6 + vxor.vv v0, v0, v8 + vle8.v v16, (a3) + add a2, a2, a6 + vxor.vv v0, v0, v16 + vle8.v v24, (a4) + add a3, a3, a6 + vxor.vv v0, v0, v24 + vle8.v v8, (a5) + add a4, a4, a6 + vxor.vv v16, v0, v8 + add a5, a5, a6 + vse8.v v16, (a1) + add a1, a1, a6 + bnez a0, xor_regs_5_ + ret +SYM_FUNC_END(xor_regs_5_) +EXPORT_SYMBOL(xor_regs_5_)