From 7c83232161f609bbc452a1255f823f41afc411dd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Wed, 4 Oct 2023 17:13:59 +0200 Subject: riscv: add support for misaligned trap handling in S-mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Misalignment trap handling is only supported for M-mode and uses direct accesses to user memory. In S-mode, when handling usermode fault, this requires to use the get_user()/put_user() accessors. Implement load_u8(), store_u8() and get_insn() using these accessors for userspace and direct text access for kernel. Signed-off-by: Clément Léger Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20231004151405.521596-3-cleger@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/entry-common.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h index 6e4dee49d84b..7ab5e34318c8 100644 --- a/arch/riscv/include/asm/entry-common.h +++ b/arch/riscv/include/asm/entry-common.h @@ -8,4 +8,18 @@ void handle_page_fault(struct pt_regs *regs); void handle_break(struct pt_regs *regs); +#ifdef CONFIG_RISCV_MISALIGNED +int handle_misaligned_load(struct pt_regs *regs); +int handle_misaligned_store(struct pt_regs *regs); +#else +static inline int handle_misaligned_load(struct pt_regs *regs) +{ + return -1; +} +static inline int handle_misaligned_store(struct pt_regs *regs) +{ + return -1; +} +#endif + #endif /* _ASM_RISCV_ENTRY_COMMON_H */ -- cgit v1.2.3 From 71c54b3d169db5569655cbd2a3616bc701fd5eec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Wed, 4 Oct 2023 17:14:04 +0200 Subject: riscv: report misaligned accesses emulation to hwprobe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hwprobe provides a way to report if misaligned access are emulated. In order to correctly populate that feature, we can check if it actually traps when doing a misaligned access. This can be checked using an exception table entry which will actually be used when a misaligned access is done from kernel mode. Signed-off-by: Clément Léger Link: https://lore.kernel.org/r/20231004151405.521596-8-cleger@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/cpufeature.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index d0345bd659c9..e4ae6af51876 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -32,4 +32,22 @@ extern struct riscv_isainfo hart_isa[NR_CPUS]; void check_unaligned_access(int cpu); +#ifdef CONFIG_RISCV_MISALIGNED +bool unaligned_ctl_available(void); +bool check_unaligned_access_emulated(int cpu); +void unaligned_emulation_finish(void); +#else +static inline bool unaligned_ctl_available(void) +{ + return false; +} + +static inline bool check_unaligned_access_emulated(int cpu) +{ + return false; +} + +static inline void unaligned_emulation_finish(void) {} +#endif + #endif -- cgit v1.2.3 From 9f23a5d2f6b01c2ab91d791109731a0d87ec2239 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Wed, 4 Oct 2023 17:14:05 +0200 Subject: riscv: add support for PR_SET_UNALIGN and PR_GET_UNALIGN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that trap support is ready to handle misalignment errors in S-mode, allow the user to control the behavior of misaligned accesses using prctl(PR_SET_UNALIGN). Add an align_ctl flag in thread_struct which will be used to determine if we should SIGBUS the process or not on such fault. Signed-off-by: Clément Léger Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20231004151405.521596-9-cleger@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/processor.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 3e23e1786d05..adbe520d07c5 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -8,6 +8,7 @@ #include #include +#include #include @@ -82,6 +83,7 @@ struct thread_struct { unsigned long bad_cause; unsigned long vstate_ctrl; struct __riscv_v_ext_state vstate; + unsigned long align_ctl; }; /* Whitelist the fstate from the task_struct for hardened usercopy */ @@ -94,6 +96,7 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, #define INIT_THREAD { \ .sp = sizeof(init_stack) + (long)&init_stack, \ + .align_ctl = PR_UNALIGN_NOPRINT, \ } #define task_pt_regs(tsk) \ @@ -134,6 +137,12 @@ extern long riscv_v_vstate_ctrl_set_current(unsigned long arg); extern long riscv_v_vstate_ctrl_get_current(void); #endif /* CONFIG_RISCV_ISA_V */ +extern int get_unalign_ctl(struct task_struct *tsk, unsigned long addr); +extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); + +#define GET_UNALIGN_CTL(tsk, addr) get_unalign_ctl((tsk), (addr)) +#define SET_UNALIGN_CTL(tsk, val) set_unalign_ctl((tsk), (val)) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_PROCESSOR_H */ -- cgit v1.2.3 From d3eabf2f2c81f8b0de0b75c6f41b875c501eb33b Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Fri, 15 Sep 2023 16:40:44 +0100 Subject: RISC-V: capitalise CMO op macros The CMO op macros initially used lower case, as the original iteration of the ALT_CMO_OP alternative stringified the first parameter to finalise the assembly for the standard variant. As a knock-on, the T-Head versions of these CMOs had to use mixed case defines. Commit dd23e9535889 ("RISC-V: replace cbom instructions with an insn-def") removed the asm construction with stringify, replacing it an insn-def macro, rending the lower-case surplus to requirements. As far as I can tell from a brief check, CBO_zero does not see similar use and didn't require the mixed case define in the first place. Replace the lower case characters now for consistency with other insn-def macros in the standard and T-Head forms, and adjust the callsites. Suggested-by: Andrew Jones Signed-off-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20230915-aloe-dollar-994937477776@spud Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/errata_list.h | 6 +++--- arch/riscv/include/asm/insn-def.h | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 0ac18a4135be..83ed25e43553 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -117,9 +117,9 @@ asm volatile(ALTERNATIVE( \ * | 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_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) \ diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h index 6960beb75f32..e27179b26086 100644 --- a/arch/riscv/include/asm/insn-def.h +++ b/arch/riscv/include/asm/insn-def.h @@ -180,19 +180,19 @@ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(51), \ __RD(0), RS1(gaddr), RS2(vmid)) -#define CBO_inval(base) \ +#define CBO_INVAL(base) \ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ RS1(base), SIMM12(0)) -#define CBO_clean(base) \ +#define CBO_CLEAN(base) \ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ RS1(base), SIMM12(1)) -#define CBO_flush(base) \ +#define CBO_FLUSH(base) \ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ RS1(base), SIMM12(2)) -#define CBO_zero(base) \ +#define CBO_ZERO(base) \ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ RS1(base), SIMM12(4)) -- cgit v1.2.3 From d5d2c264d33b9acf1a0216861942176ee3569258 Mon Sep 17 00:00:00 2001 From: Yu Chien Peter Lin Date: Thu, 21 Sep 2023 10:50:20 +0800 Subject: riscv: Improve PTDUMP to show RSW with non-zero value RSW field can be used to encode 2 bits of software defined information. Currently, PTDUMP only prints "RSW" when its value is 1 or 3. To fix this issue and improve the debugging experience with PTDUMP, we redefine _PAGE_SPECIAL to its original value and use _PAGE_SOFT as the RSW mask, allow it to print the RSW with any non-zero value. This patch also removes the val from the struct prot_bits as it is no longer needed. Signed-off-by: Yu Chien Peter Lin Reviewed-by: Alexandre Ghiti Tested-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230921025022.3989723-2-peterlin@andestech.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/pgtable-bits.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index f896708e8331..179bd4afece4 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -16,9 +16,9 @@ #define _PAGE_GLOBAL (1 << 5) /* Global */ #define _PAGE_ACCESSED (1 << 6) /* Set by hardware on any access */ #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ -#define _PAGE_SOFT (1 << 8) /* Reserved for software */ +#define _PAGE_SOFT (3 << 8) /* Reserved for software */ -#define _PAGE_SPECIAL _PAGE_SOFT +#define _PAGE_SPECIAL (1 << 8) /* RSW: 0x1 */ #define _PAGE_TABLE _PAGE_PRESENT /* -- cgit v1.2.3 From dbfbda3bd6bfb5189e05b9eab8dfaad2d1d23f62 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Tue, 12 Sep 2023 15:25:10 +0800 Subject: riscv: mm: update T-Head memory type definitions Update T-Head memory type definitions according to C910 doc [1] For NC and IO, SH property isn't configurable, hardcoded as SH, so set SH for NOCACHE and IO. And also set bit[61](Bufferable) for NOCACHE according to the table 6.1 in the doc [1]. Link: https://github.com/T-head-Semi/openc910 [1] Signed-off-by: Jisheng Zhang Reviewed-by: Guo Ren Tested-by: Drew Fustini Link: https://lore.kernel.org/r/20230912072510.2510-1-jszhang@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/pgtable-64.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 7a5097202e15..9a2c780a11e9 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -126,14 +126,18 @@ enum napot_cont_order { /* * [63:59] T-Head Memory Type definitions: - * - * 00000 - NC Weakly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable + * bit[63] SO - Strong Order + * bit[62] C - Cacheable + * bit[61] B - Bufferable + * bit[60] SH - Shareable + * bit[59] Sec - Trustable + * 00110 - NC Weakly-ordered, Non-cacheable, Bufferable, Shareable, Non-trustable * 01110 - PMA Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable - * 10000 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable + * 10010 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable */ #define _PAGE_PMA_THEAD ((1UL << 62) | (1UL << 61) | (1UL << 60)) -#define _PAGE_NOCACHE_THEAD 0UL -#define _PAGE_IO_THEAD (1UL << 63) +#define _PAGE_NOCACHE_THEAD ((1UL < 61) | (1UL << 60)) +#define _PAGE_IO_THEAD ((1UL << 63) | (1UL << 60)) #define _PAGE_MTMASK_THEAD (_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59)) static inline u64 riscv_page_mtmask(void) -- cgit v1.2.3 From c5e9b2c2ae82231d85d9650854e7b3e97dde33da Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 30 Oct 2023 14:30:25 +0100 Subject: riscv: Improve tlb_flush() For now, tlb_flush() simply calls flush_tlb_mm() which results in a flush of the whole TLB. So let's use mmu_gather fields to provide a more fine-grained flush of the TLB. Signed-off-by: Alexandre Ghiti Reviewed-by: Andrew Jones Reviewed-by: Samuel Holland Tested-by: Lad Prabhakar # On RZ/Five SMARC Link: https://lore.kernel.org/r/20231030133027.19542-2-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/tlb.h | 8 +++++++- arch/riscv/include/asm/tlbflush.h | 3 +++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index 120bcf2ed8a8..1eb5682b2af6 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -15,7 +15,13 @@ static void tlb_flush(struct mmu_gather *tlb); static inline void tlb_flush(struct mmu_gather *tlb) { - flush_tlb_mm(tlb->mm); +#ifdef CONFIG_MMU + if (tlb->fullmm || tlb->need_flush_all) + flush_tlb_mm(tlb->mm); + else + flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, + tlb_get_unmap_size(tlb)); +#endif } #endif /* _ASM_RISCV_TLB_H */ diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index a09196f8de68..f5c4fb0ae642 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -32,6 +32,8 @@ static inline void local_flush_tlb_page(unsigned long addr) #if defined(CONFIG_SMP) && defined(CONFIG_MMU) void flush_tlb_all(void); void flush_tlb_mm(struct mm_struct *mm); +void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, + unsigned long end, unsigned int page_size); void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr); void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -52,6 +54,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, } #define flush_tlb_mm(mm) flush_tlb_all() +#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all() #endif /* !CONFIG_SMP || !CONFIG_MMU */ /* Flush a range of kernel pages */ -- cgit v1.2.3 From 9d4e8d5fa7dbbb606b355f40d918a1feef821bc5 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 30 Oct 2023 14:30:27 +0100 Subject: riscv: Make __flush_tlb_range() loop over pte instead of flushing the whole tlb Currently, when the range to flush covers more than one page (a 4K page or a hugepage), __flush_tlb_range() flushes the whole tlb. Flushing the whole tlb comes with a greater cost than flushing a single entry so we should flush single entries up to a certain threshold so that: threshold * cost of flushing a single entry < cost of flushing the whole tlb. Co-developed-by: Mayuresh Chitale Signed-off-by: Mayuresh Chitale Signed-off-by: Alexandre Ghiti Reviewed-by: Andrew Jones Tested-by: Lad Prabhakar # On RZ/Five SMARC Reviewed-by: Samuel Holland Tested-by: Samuel Holland Link: https://lore.kernel.org/r/20231030133027.19542-4-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/sbi.h | 3 --- arch/riscv/include/asm/tlbflush.h | 3 +++ 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 5b4a1bf5f439..b79d0228144f 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -273,9 +273,6 @@ void sbi_set_timer(uint64_t stime_value); void sbi_shutdown(void); void sbi_send_ipi(unsigned int cpu); int sbi_remote_fence_i(const struct cpumask *cpu_mask); -int sbi_remote_sfence_vma(const struct cpumask *cpu_mask, - unsigned long start, - unsigned long size); int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask, unsigned long start, diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index f5c4fb0ae642..170a49c531c6 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -11,6 +11,9 @@ #include #include +#define FLUSH_TLB_MAX_SIZE ((unsigned long)-1) +#define FLUSH_TLB_NO_ASID ((unsigned long)-1) + #ifdef CONFIG_MMU extern unsigned long asid_mask; -- cgit v1.2.3 From 5e22bfd520ea8740e9a20314d2a890baf304c9d2 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 30 Oct 2023 14:30:28 +0100 Subject: riscv: Improve flush_tlb_kernel_range() This function used to simply flush the whole tlb of all harts, be more subtile and try to only flush the range. The problem is that we can only use PAGE_SIZE as stride since we don't know the size of the underlying mapping and then this function will be improved only if the size of the region to flush is < threshold * PAGE_SIZE. Signed-off-by: Alexandre Ghiti Reviewed-by: Andrew Jones Tested-by: Lad Prabhakar # On RZ/Five SMARC Reviewed-by: Samuel Holland Tested-by: Samuel Holland Link: https://lore.kernel.org/r/20231030133027.19542-5-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/tlbflush.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 170a49c531c6..8f3418c5f172 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -40,6 +40,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr); void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +void flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, @@ -56,15 +57,15 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, local_flush_tlb_all(); } -#define flush_tlb_mm(mm) flush_tlb_all() -#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all() -#endif /* !CONFIG_SMP || !CONFIG_MMU */ - /* Flush a range of kernel pages */ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) { - flush_tlb_all(); + local_flush_tlb_all(); } +#define flush_tlb_mm(mm) flush_tlb_all() +#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all() +#endif /* !CONFIG_SMP || !CONFIG_MMU */ + #endif /* _ASM_RISCV_TLBFLUSH_H */ -- cgit v1.2.3 From 8fd6c5142395a106b63c8668e9f4a7106b6a0772 Mon Sep 17 00:00:00 2001 From: Charlie Jenkins Date: Wed, 1 Nov 2023 11:33:00 -0700 Subject: riscv: Add remaining module relocations Add all final module relocations and add error logs explaining the ones that are not supported. Implement overflow checks for ADD/SUB/SET/ULEB128 relocations. Signed-off-by: Charlie Jenkins Link: https://lore.kernel.org/r/20231101-module_relocations-v9-2-8dfa3483c400@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/uapi/asm/elf.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h index d696d6610231..11a71b8533d5 100644 --- a/arch/riscv/include/uapi/asm/elf.h +++ b/arch/riscv/include/uapi/asm/elf.h @@ -49,6 +49,7 @@ typedef union __riscv_fp_state elf_fpregset_t; #define R_RISCV_TLS_DTPREL64 9 #define R_RISCV_TLS_TPREL32 10 #define R_RISCV_TLS_TPREL64 11 +#define R_RISCV_IRELATIVE 58 /* Relocation types not used by the dynamic linker */ #define R_RISCV_BRANCH 16 @@ -81,7 +82,6 @@ typedef union __riscv_fp_state elf_fpregset_t; #define R_RISCV_ALIGN 43 #define R_RISCV_RVC_BRANCH 44 #define R_RISCV_RVC_JUMP 45 -#define R_RISCV_LUI 46 #define R_RISCV_GPREL_I 47 #define R_RISCV_GPREL_S 48 #define R_RISCV_TPREL_I 49 @@ -93,6 +93,9 @@ typedef union __riscv_fp_state elf_fpregset_t; #define R_RISCV_SET16 55 #define R_RISCV_SET32 56 #define R_RISCV_32_PCREL 57 +#define R_RISCV_PLT32 59 +#define R_RISCV_SET_ULEB128 60 +#define R_RISCV_SUB_ULEB128 61 #endif /* _UAPI_ASM_RISCV_ELF_H */ -- cgit v1.2.3 From 55e0bf49a0d0387d682d696e41cada071f516075 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Mon, 6 Nov 2023 14:58:55 -0800 Subject: RISC-V: Probe misaligned access speed in parallel Probing for misaligned access speed takes about 0.06 seconds. On a system with 64 cores, doing this in smp_callin() means it's done serially, extending boot time by 3.8 seconds. That's a lot of boot time. Instead of measuring each CPU serially, let's do the measurements on all CPUs in parallel. If we disable preemption on all CPUs, the jiffies stop ticking, so we can do this in stages of 1) everybody except core 0, then 2) core 0. The allocations are all done outside of on_each_cpu() to avoid calling alloc_pages() with interrupts disabled. For hotplugged CPUs that come in after the boot time measurement, register CPU hotplug callbacks, and do the measurement there. Interrupts are enabled in those callbacks, so they're fine to do alloc_pages() in. Reported-by: Jisheng Zhang Closes: https://lore.kernel.org/all/mhng-9359993d-6872-4134-83ce-c97debe1cf9a@palmer-ri-x1c9/T/#mae9b8f40016f9df428829d33360144dc5026bcbf Fixes: 584ea6564bca ("RISC-V: Probe for unaligned access speed") Signed-off-by: Evan Green Link: https://lore.kernel.org/r/20231106225855.3121724-1-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/cpufeature.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 7f1e46a9d445..69f2cae96f0b 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -30,7 +30,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed); /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; -void check_unaligned_access(int cpu); void riscv_user_isa_enable(void); #ifdef CONFIG_RISCV_MISALIGNED -- cgit v1.2.3 From e72c4333d2f2e7f2200f71a88c0480fd2a769a64 Mon Sep 17 00:00:00 2001 From: Xiao Wang Date: Tue, 31 Oct 2023 14:45:52 +0800 Subject: riscv: Rearrange hwcap.h and cpufeature.h Now hwcap.h and cpufeature.h are mutually including each other, and most of the variable/API declarations in hwcap.h are implemented in cpufeature.c, so, it's better to move them into cpufeature.h and leave only macros for ISA extension logical IDs in hwcap.h. BTW, the riscv_isa_extension_mask macro is not used now, so this patch removes it. Suggested-by: Andrew Jones Signed-off-by: Xiao Wang Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20231031064553.2319688-2-xiao.w.wang@intel.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/cpufeature.h | 83 +++++++++++++++++++++++++++++++++ arch/riscv/include/asm/elf.h | 2 +- arch/riscv/include/asm/hwcap.h | 91 ------------------------------------- arch/riscv/include/asm/pgtable.h | 1 + arch/riscv/include/asm/switch_to.h | 2 +- arch/riscv/include/asm/vector.h | 2 +- 6 files changed, 87 insertions(+), 94 deletions(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 69f2cae96f0b..a418c3112cd6 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -7,7 +7,10 @@ #define _ASM_CPUFEATURE_H #include +#include #include +#include +#include /* * These are probed via a device_initcall(), via either the SBI or directly @@ -50,4 +53,84 @@ static inline bool check_unaligned_access_emulated(int cpu) static inline void unaligned_emulation_finish(void) {} #endif +unsigned long riscv_get_elf_hwcap(void); + +struct riscv_isa_ext_data { + const unsigned int id; + const char *name; + const char *property; +}; + +extern const struct riscv_isa_ext_data riscv_isa_ext[]; +extern const size_t riscv_isa_ext_count; +extern bool riscv_isa_fallback; + +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); + +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit); +#define riscv_isa_extension_available(isa_bitmap, ext) \ + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) + +static __always_inline bool +riscv_has_extension_likely(const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, + "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + asm_volatile_goto( + ALTERNATIVE("j %l[l_no]", "nop", 0, %[ext], 1) + : + : [ext] "i" (ext) + : + : l_no); + } else { + if (!__riscv_isa_extension_available(NULL, ext)) + goto l_no; + } + + return true; +l_no: + return false; +} + +static __always_inline bool +riscv_has_extension_unlikely(const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, + "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + asm_volatile_goto( + ALTERNATIVE("nop", "j %l[l_yes]", 0, %[ext], 1) + : + : [ext] "i" (ext) + : + : l_yes); + } else { + if (__riscv_isa_extension_available(NULL, ext)) + goto l_yes; + } + + return false; +l_yes: + return true; +} + +static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext) +{ + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext)) + return true; + + return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); +} + +static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext) +{ + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext)) + return true; + + return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); +} + #endif diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index b3b2dfbdf945..06c236bfab53 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -14,7 +14,7 @@ #include #include #include -#include +#include /* * These are used to set parameters in the core dumps. diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 31774bcdf1c6..141b7109c25c 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -8,9 +8,6 @@ #ifndef _ASM_RISCV_HWCAP_H #define _ASM_RISCV_HWCAP_H -#include -#include -#include #include #define RISCV_ISA_EXT_a ('a' - 'a') @@ -67,92 +64,4 @@ #define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SSAIA #endif -#ifndef __ASSEMBLY__ - -#include -#include - -unsigned long riscv_get_elf_hwcap(void); - -struct riscv_isa_ext_data { - const unsigned int id; - const char *name; - const char *property; -}; - -extern const struct riscv_isa_ext_data riscv_isa_ext[]; -extern const size_t riscv_isa_ext_count; -extern bool riscv_isa_fallback; - -unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); - -#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext) - -bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit); -#define riscv_isa_extension_available(isa_bitmap, ext) \ - __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) - -static __always_inline bool -riscv_has_extension_likely(const unsigned long ext) -{ - compiletime_assert(ext < RISCV_ISA_EXT_MAX, - "ext must be < RISCV_ISA_EXT_MAX"); - - if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( - ALTERNATIVE("j %l[l_no]", "nop", 0, %[ext], 1) - : - : [ext] "i" (ext) - : - : l_no); - } else { - if (!__riscv_isa_extension_available(NULL, ext)) - goto l_no; - } - - return true; -l_no: - return false; -} - -static __always_inline bool -riscv_has_extension_unlikely(const unsigned long ext) -{ - compiletime_assert(ext < RISCV_ISA_EXT_MAX, - "ext must be < RISCV_ISA_EXT_MAX"); - - if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { - asm_volatile_goto( - ALTERNATIVE("nop", "j %l[l_yes]", 0, %[ext], 1) - : - : [ext] "i" (ext) - : - : l_yes); - } else { - if (__riscv_isa_extension_available(NULL, ext)) - goto l_yes; - } - - return false; -l_yes: - return true; -} - -static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext) -{ - if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext)) - return true; - - return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); -} - -static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext) -{ - if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext)) - return true; - - return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); -} -#endif - #endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index c8e8867c42f6..294044429e8e 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -291,6 +291,7 @@ static inline pte_t pud_pte(pud_t pud) } #ifdef CONFIG_RISCV_ISA_SVNAPOT +#include static __always_inline bool has_svnapot(void) { diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index a727be723c56..f90d8e42f3c7 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index c5ee07b3df07..87aaef656257 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include -- cgit v1.2.3 From 457926b253200bd9bdfae9a016a3b1d1dc661d55 Mon Sep 17 00:00:00 2001 From: Xiao Wang Date: Tue, 31 Oct 2023 14:45:53 +0800 Subject: riscv: Optimize bitops with Zbb extension This patch leverages the alternative mechanism to dynamically optimize bitops (including __ffs, __fls, ffs, fls) with Zbb instructions. When Zbb ext is not supported by the runtime CPU, legacy implementation is used. If Zbb is supported, then the optimized variants will be selected via alternative patching. The legacy bitops support is taken from the generic C implementation as fallback. If the parameter is a build-time constant, we leverage compiler builtin to calculate the result directly, this approach is inspired by x86 bitops implementation. EFI stub runs before the kernel, so alternative mechanism should not be used there, this patch introduces a macro NO_ALTERNATIVE for this purpose. Signed-off-by: Xiao Wang Reviewed-by: Charlie Jenkins Link: https://lore.kernel.org/r/20231031064553.2319688-3-xiao.w.wang@intel.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/bitops.h | 254 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 251 insertions(+), 3 deletions(-) (limited to 'arch/riscv/include') diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index 3540b690944b..b212c2708cda 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -15,13 +15,261 @@ #include #include +#if !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) #include -#include -#include #include +#include +#include + +#else +#include +#include + +#if (BITS_PER_LONG == 64) +#define CTZW "ctzw " +#define CLZW "clzw " +#elif (BITS_PER_LONG == 32) +#define CTZW "ctz " +#define CLZW "clz " +#else +#error "Unexpected BITS_PER_LONG" +#endif + +static __always_inline unsigned long variable__ffs(unsigned long word) +{ + int num; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + "ctz %0, %1\n" + ".option pop\n" + : "=r" (word) : "r" (word) :); + + return word; + +legacy: + num = 0; +#if BITS_PER_LONG == 64 + if ((word & 0xffffffff) == 0) { + num += 32; + word >>= 32; + } +#endif + if ((word & 0xffff) == 0) { + num += 16; + word >>= 16; + } + if ((word & 0xff) == 0) { + num += 8; + word >>= 8; + } + if ((word & 0xf) == 0) { + num += 4; + word >>= 4; + } + if ((word & 0x3) == 0) { + num += 2; + word >>= 2; + } + if ((word & 0x1) == 0) + num += 1; + return num; +} + +/** + * __ffs - find first set bit in a long word + * @word: The word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +#define __ffs(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(word) : \ + variable__ffs(word)) + +static __always_inline unsigned long variable__fls(unsigned long word) +{ + int num; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + "clz %0, %1\n" + ".option pop\n" + : "=r" (word) : "r" (word) :); + + return BITS_PER_LONG - 1 - word; + +legacy: + num = BITS_PER_LONG - 1; +#if BITS_PER_LONG == 64 + if (!(word & (~0ul << 32))) { + num -= 32; + word <<= 32; + } +#endif + if (!(word & (~0ul << (BITS_PER_LONG - 16)))) { + num -= 16; + word <<= 16; + } + if (!(word & (~0ul << (BITS_PER_LONG - 8)))) { + num -= 8; + word <<= 8; + } + if (!(word & (~0ul << (BITS_PER_LONG - 4)))) { + num -= 4; + word <<= 4; + } + if (!(word & (~0ul << (BITS_PER_LONG - 2)))) { + num -= 2; + word <<= 2; + } + if (!(word & (~0ul << (BITS_PER_LONG - 1)))) + num -= 1; + return num; +} + +/** + * __fls - find last set bit in a long word + * @word: the word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +#define __fls(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)(BITS_PER_LONG - 1 - __builtin_clzl(word)) : \ + variable__fls(word)) + +static __always_inline int variable_ffs(int x) +{ + int r; + + if (!x) + return 0; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + CTZW "%0, %1\n" + ".option pop\n" + : "=r" (r) : "r" (x) :); + + return r + 1; + +legacy: + r = 1; + if (!(x & 0xffff)) { + x >>= 16; + r += 16; + } + if (!(x & 0xff)) { + x >>= 8; + r += 8; + } + if (!(x & 0xf)) { + x >>= 4; + r += 4; + } + if (!(x & 3)) { + x >>= 2; + r += 2; + } + if (!(x & 1)) { + x >>= 1; + r += 1; + } + return r; +} + +/** + * ffs - find first set bit in a word + * @x: the word to search + * + * This is defined the same way as the libc and compiler builtin ffs routines. + * + * ffs(value) returns 0 if value is 0 or the position of the first set bit if + * value is nonzero. The first (least significant) bit is at position 1. + */ +#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) + +static __always_inline int variable_fls(unsigned int x) +{ + int r; + + if (!x) + return 0; + + asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : : : : legacy); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + CLZW "%0, %1\n" + ".option pop\n" + : "=r" (r) : "r" (x) :); + + return 32 - r; + +legacy: + r = 32; + if (!(x & 0xffff0000u)) { + x <<= 16; + r -= 16; + } + if (!(x & 0xff000000u)) { + x <<= 8; + r -= 8; + } + if (!(x & 0xf0000000u)) { + x <<= 4; + r -= 4; + } + if (!(x & 0xc0000000u)) { + x <<= 2; + r -= 2; + } + if (!(x & 0x80000000u)) { + x <<= 1; + r -= 1; + } + return r; +} + +/** + * fls - find last set bit in a word + * @x: the word to search + * + * This is defined in a similar way as ffs, but returns the position of the most + * significant set bit. + * + * fls(value) returns 0 if value is 0 or the position of the last set bit if + * value is nonzero. The last (most significant) bit is at position 32. + */ +#define fls(x) \ +({ \ + typeof(x) x_ = (x); \ + __builtin_constant_p(x_) ? \ + (int)((x_ != 0) ? (32 - __builtin_clz(x_)) : 0) \ + : \ + variable_fls(x_); \ +}) + +#endif /* !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) */ + +#include #include #include -#include #include -- cgit v1.2.3