[PATCH V3 3/4] arm64/mm: Use p4dp_get() for P4D accesses
From: Anshuman Khandual <hidden>
Date: 2026-09-24 06:22:59
Also in:
linux-mm, lkml
Subsystem:
arm64 port (aarch64 architecture), kasan, the rest · Maintainers:
Catalin Marinas, Will Deacon, Andrey Ryabinin, Linus Torvalds
Replace READ_ONCE() with p4dp_get() for P4D accesses in preparation for supporting both D64 and D128 translation table formats. READ_ONCE() cannot currently be used for 128-bit page table entries on arm64 because it does not provide the required 128-bit single-copy atomicity, causing builds to fail for accesses wider than 64 bits. Although LDP/STP provide the required atomicity when FEAT_LSE is available (as required by FEAT_D128), extending READ_ONCE() to support 128-bit accesses is undesirable. READ_ONCE() is a general-purpose API, so doing so could encourage other 128-bit users that would either fail to build in configurations without D128 support or, if D128 becomes a runtime option, silently permit tearing on systems without the required hardware support. Instead, standardize P4D accesses on the existing page-table helpers. These can be overridden on arm64 to provide 128-bit single-copy atomicity when required. For now override p4dp_get() which is same as the generic memory default to avoid build dependency problem for callers in header <asm/pgtable.h>. No functional change intended. Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: kasan-dev@googlegroups.com Signed-off-by: Anshuman Khandual <redacted> --- Changes in V3 - Added platform override for p4dp_get() - Replaced READ_ONCE() in pud_offset_phys() and pud_offset() arch/arm64/include/asm/pgtable.h | 10 ++++++++-- arch/arm64/mm/fault.c | 2 +- arch/arm64/mm/fixmap.c | 2 +- arch/arm64/mm/hugetlbpage.c | 2 +- arch/arm64/mm/kasan_init.c | 4 ++-- arch/arm64/mm/mmu.c | 12 ++++++------ arch/arm64/mm/pageattr.c | 2 +- arch/arm64/mm/trans_pgd.c | 4 ++-- 8 files changed, 22 insertions(+), 16 deletions(-)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b46930f844a2..f235f68a7518 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h@@ -96,6 +96,12 @@ static inline pud_t pudp_get(pud_t *pudp) return READ_ONCE(*pudp); } +#define p4dp_get p4dp_get +static inline p4d_t p4dp_get(p4d_t *p4dp) +{ + return READ_ONCE(*p4dp); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
@@ -976,7 +982,7 @@ static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) { VM_WARN_ON_ONCE(!pgtable_l4_enabled()); - return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); + return p4d_page_paddr(p4dp_get(p4dp)) + pud_index(addr) * sizeof(pud_t); } static inline
@@ -990,7 +996,7 @@ pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) { - return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); + return pud_offset_lockless(p4dp, p4dp_get(p4dp), addr); } #define pud_offset pud_offset
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 435e2e14c070..a6afd8929a10 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c@@ -174,7 +174,7 @@ static void show_pte(unsigned long addr) break; p4dp = p4d_offset_lockless(pgdp, pgd, addr); - p4d = READ_ONCE(*p4dp); + p4d = p4dp_get(p4dp); ptval_to_str(pxd_str, p4d_val(p4d)); pr_cont(", p4d=%s", pxd_str); if (p4d_none(p4d) || p4d_bad(p4d))
diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c
index d9a870836faf..2a0fe0b0f771 100644
--- a/arch/arm64/mm/fixmap.c
+++ b/arch/arm64/mm/fixmap.c@@ -74,7 +74,7 @@ static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr, static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end) { - p4d_t p4d = READ_ONCE(*p4dp); + p4d_t p4d = p4dp_get(p4dp); pud_t *pudp; if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) &&
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index c9ad5e75b073..5771bf49e1fe 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c@@ -288,7 +288,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return NULL; p4dp = p4d_offset(pgdp, addr); - if (!p4d_present(READ_ONCE(*p4dp))) + if (!p4d_present(p4dp_get(p4dp))) return NULL; pudp = pud_offset(p4dp, addr);
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index aad29bcc7622..4dd8c1186471 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c@@ -89,7 +89,7 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early) { - if (p4d_none(READ_ONCE(*p4dp))) { + if (p4d_none(p4dp_get(p4dp))) { phys_addr_t pud_phys = early ? __pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node);
@@ -162,7 +162,7 @@ static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr, do { next = p4d_addr_end(addr, end); kasan_pud_populate(p4dp, addr, next, node, early); - } while (p4dp++, addr = next, addr != end && p4d_none(READ_ONCE(*p4dp))); + } while (p4dp++, addr = next, addr != end && p4d_none(p4dp_get(p4dp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 22efaee79293..83709d987e7c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c@@ -367,7 +367,7 @@ static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, { int ret = 0; unsigned long next; - p4d_t p4d = READ_ONCE(*p4dp); + p4d_t p4d = p4dp_get(p4dp); pud_t *pudp; if (p4d_none(p4d)) {
@@ -457,7 +457,7 @@ static int alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, } do { - p4d_t old_p4d = READ_ONCE(*p4dp); + p4d_t old_p4d = p4dp_get(p4dp); next = p4d_addr_end(addr, end);
@@ -467,7 +467,7 @@ static int alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, goto out; VM_WARN_ON_ONCE(p4d_val(old_p4d) != 0 && - p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp))); + p4d_val(old_p4d) != (p4d_val(p4dp_get(p4dp)))); phys += next - addr; } while (p4dp++, addr = next, addr != end);
@@ -1622,7 +1622,7 @@ static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr, do { next = p4d_addr_end(addr, end); p4dp = p4d_offset(pgdp, addr); - p4d = READ_ONCE(*p4dp); + p4d = p4dp_get(p4dp); if (p4d_none(p4d)) continue;
@@ -1788,7 +1788,7 @@ static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, do { next = p4d_addr_end(addr, end); p4dp = p4d_offset(pgdp, addr); - p4d = READ_ONCE(*p4dp); + p4d = p4dp_get(p4dp); if (p4d_none(p4d)) continue;
@@ -1809,7 +1809,7 @@ static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, */ p4dp = p4d_offset(pgdp, 0UL); for (i = 0; i < PTRS_PER_P4D; i++) { - if (!p4d_none(READ_ONCE(p4dp[i]))) + if (!p4d_none(p4dp_get(p4dp + i))) return; }
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 07b2fa4de57f..826856ef64a8 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c@@ -403,7 +403,7 @@ bool kernel_page_present(struct page *page) return false; p4dp = p4d_offset(pgdp, addr); - if (p4d_none(READ_ONCE(*p4dp))) + if (p4d_none(p4dp_get(p4dp))) return false; pudp = pud_offset(p4dp, addr);
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index d119119455f1..7afe2beca4ba 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c@@ -99,7 +99,7 @@ static int copy_pud(struct trans_pgd_info *info, p4d_t *dst_p4dp, unsigned long next; unsigned long addr = start; - if (p4d_none(READ_ONCE(*dst_p4dp))) { + if (p4d_none(p4dp_get(dst_p4dp))) { dst_pudp = trans_alloc(info); if (!dst_pudp) return -ENOMEM;
@@ -145,7 +145,7 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp, src_p4dp = p4d_offset(src_pgdp, start); do { next = p4d_addr_end(addr, end); - if (p4d_none(READ_ONCE(*src_p4dp))) + if (p4d_none(p4dp_get(src_p4dp))) continue; if (copy_pud(info, dst_p4dp, src_p4dp, addr, next)) return -ENOMEM;
--
2.43.0