[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240802151430.99114-5-alexghiti@rivosinc.com>
Date: Fri, 2 Aug 2024 17:14:25 +0200
From: Alexandre Ghiti <alexghiti@...osinc.com>
To: Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
Ryan Roberts <ryan.roberts@....com>,
Mark Rutland <mark.rutland@....com>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
Andrew Morton <akpm@...ux-foundation.org>,
linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org,
linux-riscv@...ts.infradead.org,
linux-mm@...ck.org
Cc: Alexandre Ghiti <alexghiti@...osinc.com>
Subject: [PATCH v3 4/9] mm: Use common set_huge_pte_at() function for riscv/arm64
After some adjustments, both architectures have the same implementation
so move it to the generic code.
Signed-off-by: Alexandre Ghiti <alexghiti@...osinc.com>
---
arch/arm64/include/asm/hugetlb.h | 3 --
arch/arm64/mm/hugetlbpage.c | 56 -----------------------------
arch/riscv/include/asm/hugetlb.h | 5 ---
arch/riscv/include/asm/pgtable.h | 8 +++--
arch/riscv/mm/hugetlbpage.c | 62 --------------------------------
include/linux/hugetlb_contpte.h | 5 +++
mm/hugetlb_contpte.c | 59 ++++++++++++++++++++++++++++++
7 files changed, 69 insertions(+), 129 deletions(-)
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 80d25b4eff25..d35093b7ab59 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -27,9 +27,6 @@ static inline void arch_clear_hugetlb_flags(struct folio *folio)
pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
#define arch_make_huge_pte arch_make_huge_pte
-#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 58cb5e06dcb2..c7130d1f07c4 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -145,62 +145,6 @@ static pte_t get_clear_contig_flush(struct mm_struct *mm,
return orig_pte;
}
-/*
- * Changing some bits of contiguous entries requires us to follow a
- * Break-Before-Make approach, breaking the whole contiguous set
- * before we can change any entries. See ARM DDI 0487A.k_iss10775,
- * "Misprogramming of the Contiguous bit", page D4-1762.
- *
- * This helper performs the break step for use cases where the
- * original pte is not needed.
- */
-static void clear_flush(struct mm_struct *mm,
- unsigned long addr,
- pte_t *ptep,
- unsigned long pgsize,
- unsigned long ncontig)
-{
- struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
- unsigned long i, saddr = addr;
-
- for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
- __ptep_get_and_clear(mm, addr, ptep);
-
- flush_tlb_range(&vma, saddr, addr);
-}
-
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned long sz)
-{
- size_t pgsize;
- int i;
- int ncontig;
- unsigned long pfn, dpfn;
- pgprot_t hugeprot;
-
- ncontig = arch_contpte_get_num_contig(ptep, sz, &pgsize);
-
- if (!pte_present(pte)) {
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
- __set_ptes(mm, addr, ptep, pte, 1);
- return;
- }
-
- if (!pte_cont(pte)) {
- __set_ptes(mm, addr, ptep, pte, 1);
- return;
- }
-
- pfn = pte_pfn(pte);
- dpfn = pgsize >> PAGE_SHIFT;
- hugeprot = pte_pgprot(pte);
-
- clear_flush(mm, addr, ptep, pgsize, ncontig);
-
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
-}
-
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long sz)
{
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index d9f9bfb84908..28cbf5d761e1 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -24,11 +24,6 @@ bool arch_hugetlb_migration_supported(struct hstate *h);
void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz);
-#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep, pte_t pte,
- unsigned long sz);
-
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 412ccebcdee9..46b409e558b3 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -628,9 +628,8 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre
extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep);
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
- unsigned long address, pte_t *ptep)
+static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
{
pte_t pte = __pte(atomic_long_xchg((atomic_long_t *)ptep, 0));
@@ -730,6 +729,9 @@ static inline pte_t ptep_get(pte_t *ptep)
#define ptep_get __ptep_get
#endif /* CONFIG_RISCV_ISA_SVNAPOT */
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define ptep_get_and_clear __ptep_get_and_clear
+
#define pgprot_nx pgprot_nx
static inline pgprot_t pgprot_nx(pgprot_t _prot)
{
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index d51863824540..0ecb2846c3f0 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -173,68 +173,6 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
return entry;
}
-static void clear_flush(struct mm_struct *mm,
- unsigned long addr,
- pte_t *ptep,
- unsigned long pgsize,
- unsigned long ncontig)
-{
- struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
- unsigned long i, saddr = addr;
-
- for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
- ptep_get_and_clear(mm, addr, ptep);
-
- flush_tlb_range(&vma, saddr, addr);
-}
-
-/*
- * When dealing with NAPOT mappings, the privileged specification indicates that
- * "if an update needs to be made, the OS generally should first mark all of the
- * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
- * within the range, [...] then update the PTE(s), as described in Section
- * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
- * arm64.
- */
-void set_huge_pte_at(struct mm_struct *mm,
- unsigned long addr,
- pte_t *ptep,
- pte_t pte,
- unsigned long sz)
-{
- unsigned long hugepage_shift, pgsize;
- int i, pte_num;
-
- if (sz >= PGDIR_SIZE)
- hugepage_shift = PGDIR_SHIFT;
- else if (sz >= P4D_SIZE)
- hugepage_shift = P4D_SHIFT;
- else if (sz >= PUD_SIZE)
- hugepage_shift = PUD_SHIFT;
- else if (sz >= PMD_SIZE)
- hugepage_shift = PMD_SHIFT;
- else
- hugepage_shift = PAGE_SHIFT;
-
- pte_num = sz >> hugepage_shift;
- pgsize = 1 << hugepage_shift;
-
- if (!pte_present(pte)) {
- for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
- set_ptes(mm, addr, ptep, pte, 1);
- return;
- }
-
- if (!pte_napot(pte)) {
- set_ptes(mm, addr, ptep, pte, 1);
- return;
- }
-
- clear_flush(mm, addr, ptep, pgsize, pte_num);
-
- set_ptes(mm, addr, ptep, pte, pte_num);
-}
-
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep,
diff --git a/include/linux/hugetlb_contpte.h b/include/linux/hugetlb_contpte.h
index ec4189cd65b8..7acd734a75e8 100644
--- a/include/linux/hugetlb_contpte.h
+++ b/include/linux/hugetlb_contpte.h
@@ -9,4 +9,9 @@
#define __HAVE_ARCH_HUGE_PTEP_GET
extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+extern void set_huge_pte_at(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, pte_t pte,
+ unsigned long sz);
+
#endif /* _LINUX_HUGETLB_CONTPTE_H */
diff --git a/mm/hugetlb_contpte.c b/mm/hugetlb_contpte.c
index 0e3ba6f97c58..9a3a376784b0 100644
--- a/mm/hugetlb_contpte.c
+++ b/mm/hugetlb_contpte.c
@@ -10,6 +10,8 @@
/*
* Any arch that wants to use that needs to define:
* - __ptep_get()
+ * - __set_ptes()
+ * - __ptep_get_and_clear()
* - pte_cont()
* - arch_contpte_get_num_contig()
*/
@@ -17,6 +19,7 @@
/*
* This file implements the following contpte aware API:
* - huge_ptep_get()
+ * - set_huge_pte_at()
*/
pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
@@ -42,3 +45,59 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
}
return orig_pte;
}
+
+/*
+ * ARM64: Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * RISCV: When dealing with NAPOT mappings, the privileged specification
+ * indicates that "if an update needs to be made, the OS generally should first
+ * mark all of the PTEs invalid, then issue SFENCE.VMA instruction(s) covering
+ * all 4 KiB regions within the range, [...] then update the PTE(s), as
+ * described in Section 4.2.1.". That's the equivalent of the Break-Before-Make
+ * approach used by arm64.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ __ptep_get_and_clear(mm, addr, ptep);
+
+ flush_tlb_range(&vma, saddr, addr);
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz)
+{
+ size_t pgsize;
+ int i;
+ int ncontig;
+
+ ncontig = arch_contpte_get_num_contig(ptep, sz, &pgsize);
+
+ if (!pte_present(pte)) {
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
+ __set_ptes(mm, addr, ptep, pte, 1);
+ return;
+ }
+
+ if (!pte_cont(pte)) {
+ __set_ptes(mm, addr, ptep, pte, 1);
+ return;
+ }
+
+ clear_flush(mm, addr, ptep, pgsize, ncontig);
+
+ set_contptes(mm, addr, ptep, pte, ncontig, pgsize);
+}
--
2.39.2
Powered by blists - more mailing lists