From 114d5c85a39a0e35024ff5156a160eef1907f3e6 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 +++ arch/riscv/mm/tlbflush.c | 7 +++++++ 3 files changed, 17 insertions(+), 1 deletion(-) 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 */ diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 77be59aadc73..fa03289853d8 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -132,6 +132,13 @@ void flush_tlb_mm(struct mm_struct *mm) __flush_tlb_range(mm, 0, -1, PAGE_SIZE); } +void flush_tlb_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + unsigned int page_size) +{ + __flush_tlb_range(mm, start, end - start, page_size); +} + void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) { __flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE); -- cgit v1.2.3 From 9e113064b4c291ad06a7a3864691288bd2cf014f Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 30 Oct 2023 14:30:26 +0100 Subject: riscv: Improve flush_tlb_range() for hugetlb pages flush_tlb_range() uses a fixed stride of PAGE_SIZE and in its current form, when a hugetlb mapping needs to be flushed, flush_tlb_range() flushes the whole tlb: so set a stride of the size of the hugetlb mapping in order to only flush the hugetlb mapping. However, if the hugepage is a NAPOT region, all PTEs that constitute this mapping must be invalidated, so the stride size must actually be the size of the PTE. Note that THPs are directly handled by flush_pmd_tlb_range(). Signed-off-by: Alexandre Ghiti Reviewed-by: Samuel Holland Tested-by: Lad Prabhakar # On RZ/Five SMARC Link: https://lore.kernel.org/r/20231030133027.19542-3-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/tlbflush.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index fa03289853d8..b6d712a82306 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include @@ -147,7 +148,33 @@ 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) { - __flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE); + unsigned long stride_size; + + if (!is_vm_hugetlb_page(vma)) { + stride_size = PAGE_SIZE; + } else { + stride_size = huge_page_size(hstate_vma(vma)); + + /* + * As stated in the privileged specification, every PTE in a + * NAPOT region must be invalidated, so reset the stride in that + * case. + */ + if (has_svnapot()) { + if (stride_size >= PGDIR_SIZE) + stride_size = PGDIR_SIZE; + else if (stride_size >= P4D_SIZE) + stride_size = P4D_SIZE; + else if (stride_size >= PUD_SIZE) + stride_size = PUD_SIZE; + else if (stride_size >= PMD_SIZE) + stride_size = PMD_SIZE; + else + stride_size = PAGE_SIZE; + } + } + + __flush_tlb_range(vma->vm_mm, start, end - start, stride_size); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, -- cgit v1.2.3 From ba6f35964c518b4520bc3f2fe25d8457cb4a7be5 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 + arch/riscv/kernel/sbi.c | 32 ++++------- arch/riscv/mm/tlbflush.c | 115 +++++++++++++++++++------------------- 4 files changed, 72 insertions(+), 81 deletions(-) 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; diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index c672c8ba9a2a..5a62ed1da453 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -11,6 +11,7 @@ #include #include #include +#include /* default SBI version is 0.1 */ unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT; @@ -376,32 +377,15 @@ int sbi_remote_fence_i(const struct cpumask *cpu_mask) } EXPORT_SYMBOL(sbi_remote_fence_i); -/** - * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote - * harts for the specified virtual address range. - * @cpu_mask: A cpu mask containing all the target harts. - * @start: Start of the virtual address - * @size: Total size of the virtual address range. - * - * Return: 0 on success, appropriate linux error code otherwise. - */ -int sbi_remote_sfence_vma(const struct cpumask *cpu_mask, - unsigned long start, - unsigned long size) -{ - return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, - cpu_mask, start, size, 0, 0); -} -EXPORT_SYMBOL(sbi_remote_sfence_vma); - /** * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given - * remote harts for a virtual address range belonging to a specific ASID. + * remote harts for a virtual address range belonging to a specific ASID or not. * * @cpu_mask: A cpu mask containing all the target harts. * @start: Start of the virtual address * @size: Total size of the virtual address range. - * @asid: The value of address space identifier (ASID). + * @asid: The value of address space identifier (ASID), or FLUSH_TLB_NO_ASID + * for flushing all address spaces. * * Return: 0 on success, appropriate linux error code otherwise. */ @@ -410,8 +394,12 @@ int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask, unsigned long size, unsigned long asid) { - return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, - cpu_mask, start, size, asid, 0); + if (asid == FLUSH_TLB_NO_ASID) + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, + cpu_mask, start, size, 0, 0); + else + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, + cpu_mask, start, size, asid, 0); } EXPORT_SYMBOL(sbi_remote_sfence_vma_asid); diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index b6d712a82306..e46fefc70927 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -9,28 +9,50 @@ static inline void local_flush_tlb_all_asid(unsigned long asid) { - __asm__ __volatile__ ("sfence.vma x0, %0" - : - : "r" (asid) - : "memory"); + if (asid != FLUSH_TLB_NO_ASID) + __asm__ __volatile__ ("sfence.vma x0, %0" + : + : "r" (asid) + : "memory"); + else + local_flush_tlb_all(); } static inline void local_flush_tlb_page_asid(unsigned long addr, unsigned long asid) { - __asm__ __volatile__ ("sfence.vma %0, %1" - : - : "r" (addr), "r" (asid) - : "memory"); + if (asid != FLUSH_TLB_NO_ASID) + __asm__ __volatile__ ("sfence.vma %0, %1" + : + : "r" (addr), "r" (asid) + : "memory"); + else + local_flush_tlb_page(addr); } -static inline void local_flush_tlb_range(unsigned long start, - unsigned long size, unsigned long stride) +/* + * Flush entire TLB if number of entries to be flushed is greater + * than the threshold below. + */ +static unsigned long tlb_flush_all_threshold __read_mostly = 64; + +static void local_flush_tlb_range_threshold_asid(unsigned long start, + unsigned long size, + unsigned long stride, + unsigned long asid) { - if (size <= stride) - local_flush_tlb_page(start); - else - local_flush_tlb_all(); + unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride); + int i; + + if (nr_ptes_in_range > tlb_flush_all_threshold) { + local_flush_tlb_all_asid(asid); + return; + } + + for (i = 0; i < nr_ptes_in_range; ++i) { + local_flush_tlb_page_asid(start, asid); + start += stride; + } } static inline void local_flush_tlb_range_asid(unsigned long start, @@ -38,8 +60,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start, { if (size <= stride) local_flush_tlb_page_asid(start, asid); - else + else if (size == FLUSH_TLB_MAX_SIZE) local_flush_tlb_all_asid(asid); + else + local_flush_tlb_range_threshold_asid(start, size, stride, asid); } static void __ipi_flush_tlb_all(void *info) @@ -52,7 +76,7 @@ void flush_tlb_all(void) if (riscv_use_ipi_for_rfence()) on_each_cpu(__ipi_flush_tlb_all, NULL, 1); else - sbi_remote_sfence_vma(NULL, 0, -1); + sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID); } struct flush_tlb_range_data { @@ -69,18 +93,12 @@ static void __ipi_flush_tlb_range_asid(void *info) local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid); } -static void __ipi_flush_tlb_range(void *info) -{ - struct flush_tlb_range_data *d = info; - - local_flush_tlb_range(d->start, d->size, d->stride); -} - static void __flush_tlb_range(struct mm_struct *mm, unsigned long start, unsigned long size, unsigned long stride) { struct flush_tlb_range_data ftd; struct cpumask *cmask = mm_cpumask(mm); + unsigned long asid = FLUSH_TLB_NO_ASID; unsigned int cpuid; bool broadcast; @@ -90,39 +108,24 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start, cpuid = get_cpu(); /* check if the tlbflush needs to be sent to other CPUs */ broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids; - if (static_branch_unlikely(&use_asid_allocator)) { - unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask; - - if (broadcast) { - if (riscv_use_ipi_for_rfence()) { - ftd.asid = asid; - ftd.start = start; - ftd.size = size; - ftd.stride = stride; - on_each_cpu_mask(cmask, - __ipi_flush_tlb_range_asid, - &ftd, 1); - } else - sbi_remote_sfence_vma_asid(cmask, - start, size, asid); - } else { - local_flush_tlb_range_asid(start, size, stride, asid); - } + + if (static_branch_unlikely(&use_asid_allocator)) + asid = atomic_long_read(&mm->context.id) & asid_mask; + + if (broadcast) { + if (riscv_use_ipi_for_rfence()) { + ftd.asid = asid; + ftd.start = start; + ftd.size = size; + ftd.stride = stride; + on_each_cpu_mask(cmask, + __ipi_flush_tlb_range_asid, + &ftd, 1); + } else + sbi_remote_sfence_vma_asid(cmask, + start, size, asid); } else { - if (broadcast) { - if (riscv_use_ipi_for_rfence()) { - ftd.asid = 0; - ftd.start = start; - ftd.size = size; - ftd.stride = stride; - on_each_cpu_mask(cmask, - __ipi_flush_tlb_range, - &ftd, 1); - } else - sbi_remote_sfence_vma(cmask, start, size); - } else { - local_flush_tlb_range(start, size, stride); - } + local_flush_tlb_range_asid(start, size, stride, asid); } put_cpu(); @@ -130,7 +133,7 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start, void flush_tlb_mm(struct mm_struct *mm) { - __flush_tlb_range(mm, 0, -1, PAGE_SIZE); + __flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); } void flush_tlb_mm_range(struct mm_struct *mm, -- cgit v1.2.3 From 62b78fd5fe39b5b82e4b4b8d0ba87ad40d1a99bb 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 ++++++----- arch/riscv/mm/tlbflush.c | 34 ++++++++++++++++++++++++---------- 2 files changed, 30 insertions(+), 15 deletions(-) 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 */ diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index e46fefc70927..e6659d7368b3 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -97,20 +97,27 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start, unsigned long size, unsigned long stride) { struct flush_tlb_range_data ftd; - struct cpumask *cmask = mm_cpumask(mm); + const struct cpumask *cmask; unsigned long asid = FLUSH_TLB_NO_ASID; - unsigned int cpuid; bool broadcast; - if (cpumask_empty(cmask)) - return; + if (mm) { + unsigned int cpuid; + + cmask = mm_cpumask(mm); + if (cpumask_empty(cmask)) + return; - cpuid = get_cpu(); - /* check if the tlbflush needs to be sent to other CPUs */ - broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids; + cpuid = get_cpu(); + /* check if the tlbflush needs to be sent to other CPUs */ + broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids; - if (static_branch_unlikely(&use_asid_allocator)) - asid = atomic_long_read(&mm->context.id) & asid_mask; + if (static_branch_unlikely(&use_asid_allocator)) + asid = atomic_long_read(&mm->context.id) & asid_mask; + } else { + cmask = cpu_online_mask; + broadcast = true; + } if (broadcast) { if (riscv_use_ipi_for_rfence()) { @@ -128,7 +135,8 @@ static void __flush_tlb_range(struct mm_struct *mm, unsigned long start, local_flush_tlb_range_asid(start, size, stride, asid); } - put_cpu(); + if (mm) + put_cpu(); } void flush_tlb_mm(struct mm_struct *mm) @@ -179,6 +187,12 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, __flush_tlb_range(vma->vm_mm, start, end - start, stride_size); } + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + __flush_tlb_range(NULL, start, end - start, PAGE_SIZE); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) -- cgit v1.2.3