Replace READ_ONCE() with pmdp_get() for PMD 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 PMD accesses on the existing page-table helpers. These can be overridden on arm64 to provide 128-bit single-copy atomicity when required. Override pmdp_get() on arm64 platform. Although the same as the generic MM default fallback for pmdp_get(), it does help avoid a build problem while converting READ_ONCE() in pmdp_test_and_clear_young() because of a cyclic dependency between and . No functional change intended. Cc: Catalin Marinas Cc: Will Deacon Cc: Ryan Roberts Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: kasan-dev@googlegroups.com Reviewed-by: Ryan Roberts Signed-off-by: Anshuman Khandual --- arch/arm64/include/asm/pgtable.h | 11 +++++++++-- 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 | 22 +++++++++++----------- arch/arm64/mm/pageattr.c | 2 +- arch/arm64/mm/trans_pgd.c | 2 +- 8 files changed, 27 insertions(+), 20 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index a474c9fb485a..ab5641f60fa3 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -84,6 +84,12 @@ static inline void arch_leave_lazy_mmu_mode(void) arch_flush_lazy_mmu_mode(); } +#define pmdp_get pmdp_get +static inline pmd_t pmdp_get(const pmd_t *pmdp) +{ + return READ_ONCE(*pmdp); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE @@ -811,7 +817,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) } /* Find an entry in the third-level page table. */ -#define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) +#define pte_offset_phys(dir, addr) (pmd_page_paddr(pmdp_get(dir)) + \ + pte_index(addr) * sizeof(pte_t)) #define pte_set_fixmap(addr) ((pte_t *)set_fixmap_offset(FIX_PTE, addr)) #define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr)) @@ -1291,7 +1298,7 @@ static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { /* Operation applies to PMD table entry only if FEAT_HAFT is enabled */ - VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft()); + VM_WARN_ON(pmd_table(pmdp_get(pmdp)) && !system_supports_haft()); return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index b22736853fcd..33b05a9f13d7 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -188,7 +188,7 @@ static void show_pte(unsigned long addr) break; pmdp = pmd_offset_lockless(pudp, pud, addr); - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get(pmdp); ptval_to_str(pxd_str, pmd_val(pmd)); pr_cont(", pmd=%s", pxd_str); if (pmd_none(pmd) || pmd_bad(pmd)) diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c index f66a0016dd02..3cdac8021d4f 100644 --- a/arch/arm64/mm/fixmap.c +++ b/arch/arm64/mm/fixmap.c @@ -42,7 +42,7 @@ static inline pte_t *fixmap_pte(unsigned long addr) static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr) { - pmd_t pmd = READ_ONCE(*pmdp); + pmd_t pmd = pmdp_get(pmdp); pte_t *ptep; if (pmd_none(pmd)) { diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index ff1f53e435e1..301b5b7265a2 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -304,7 +304,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, addr &= CONT_PMD_MASK; pmdp = pmd_offset(pudp, addr); - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get(pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && pmd_none(pmd)) return NULL; diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 45fbdce684c8..7ca833c5de5e 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -62,7 +62,7 @@ static phys_addr_t __init kasan_alloc_raw_page(int node) static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { - if (pmd_none(READ_ONCE(*pmdp))) { + if (pmd_none(pmdp_get(pmdp))) { phys_addr_t pte_phys = early ? __pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node); @@ -138,7 +138,7 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr, do { next = pmd_addr_end(addr, end); kasan_pte_populate(pmdp, addr, next, node, early); - } while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp))); + } while (pmdp++, addr = next, addr != end && pmd_none(pmdp_get(pmdp))); } static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 140520b351e2..0433033c0a71 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -200,7 +200,7 @@ static int alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, int flags) { unsigned long next; - pmd_t pmd = READ_ONCE(*pmdp); + pmd_t pmd = pmdp_get(pmdp); pte_t *ptep; BUG_ON(pmd_leaf(pmd)); @@ -257,7 +257,7 @@ static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned long next; do { - pmd_t old_pmd = READ_ONCE(*pmdp); + pmd_t old_pmd = pmdp_get(pmdp); next = pmd_addr_end(addr, end); @@ -272,7 +272,7 @@ static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), - READ_ONCE(pmd_val(*pmdp)))); + pmd_val(pmdp_get(pmdp)))); } else { int ret; @@ -282,7 +282,7 @@ static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, return ret; VM_WARN_ON_ONCE(pmd_val(old_pmd) != 0 && - pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); + pmd_val(old_pmd) != pmd_val(pmdp_get(pmdp))); } phys += next - addr; } while (pmdp++, addr = next, addr != end); @@ -293,7 +293,7 @@ static int init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, static bool pmd_range_has_valid_noncont(pmd_t *pmdp) { for (int i = 0; i < CONT_PMDS; i++) { - pte_t pte = pmd_pte(READ_ONCE(pmdp[i])); + pte_t pte = pmd_pte(pmdp_get(pmdp + i)); if (pte_valid(pte) && !pte_cont(pte)) return true; @@ -1553,7 +1553,7 @@ static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr, do { next = pmd_addr_end(addr, end); pmdp = pmd_offset(pudp, addr); - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get(pmdp); if (pmd_none(pmd)) continue; @@ -1708,7 +1708,7 @@ static void free_empty_pmd_table(pud_t *pudp, unsigned long addr, do { next = pmd_addr_end(addr, end); pmdp = pmd_offset(pudp, addr); - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get(pmdp); if (pmd_none(pmd)) continue; @@ -1729,7 +1729,7 @@ static void free_empty_pmd_table(pud_t *pudp, unsigned long addr, */ pmdp = pmd_offset(pudp, 0UL); for (i = 0; i < PTRS_PER_PMD; i++) { - if (!pmd_none(READ_ONCE(pmdp[i]))) + if (!pmd_none(pmdp_get(pmdp + i))) return; } @@ -1881,7 +1881,7 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot)); /* Only allow permission changes for now */ - if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)), + if (!pgattr_change_is_safe(pmd_val(pmdp_get(pmdp)), pmd_val(new_pmd))) return 0; @@ -1906,7 +1906,7 @@ int pud_clear_huge(pud_t *pudp) int pmd_clear_huge(pmd_t *pmdp) { - if (!pmd_leaf(READ_ONCE(*pmdp))) + if (!pmd_leaf(pmdp_get(pmdp))) return 0; pmd_clear(pmdp); return 1; @@ -1917,7 +1917,7 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) pte_t *table; pmd_t pmd; - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get(pmdp); if (!pmd_table(pmd)) { VM_WARN_ON(1); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index de7bf95003ea..bf1fd1258a75 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -362,7 +362,7 @@ bool kernel_page_present(struct page *page) return pud_valid(pud); pmdp = pmd_offset(pudp, addr); - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get(pmdp); if (pmd_none(pmd)) return false; if (pmd_leaf(pmd)) diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index cca9706a875c..b27b2d2c20c3 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -74,7 +74,7 @@ static int copy_pmd(struct trans_pgd_info *info, pud_t *dst_pudp, src_pmdp = pmd_offset(src_pudp, start); do { - pmd_t pmd = READ_ONCE(*src_pmdp); + pmd_t pmd = pmdp_get(src_pmdp); next = pmd_addr_end(addr, end); if (pmd_none(pmd)) -- 2.43.0 Replace READ_ONCE() with pudp_get() for PUD 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 PUD 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 pudp_get() which is same as the generic memory default in order to be consistent with similar helpers. No functional change intended. Cc: Catalin Marinas Cc: Will Deacon Cc: Ryan Roberts Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: kasan-dev@googlegroups.com Reviewed-by: Ryan Roberts Signed-off-by: Anshuman Khandual --- arch/arm64/include/asm/pgtable.h | 9 ++++++++- arch/arm64/mm/fault.c | 2 +- arch/arm64/mm/fixmap.c | 2 +- arch/arm64/mm/hugetlbpage.c | 4 ++-- arch/arm64/mm/kasan_init.c | 4 ++-- arch/arm64/mm/mmu.c | 20 ++++++++++---------- arch/arm64/mm/pageattr.c | 2 +- arch/arm64/mm/trans_pgd.c | 4 ++-- 8 files changed, 27 insertions(+), 20 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index ab5641f60fa3..ad6cd5a71b71 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -90,6 +90,12 @@ static inline pmd_t pmdp_get(const pmd_t *pmdp) return READ_ONCE(*pmdp); } +#define pudp_get pudp_get +static inline pud_t pudp_get(const pud_t *pudp) +{ + return READ_ONCE(*pudp); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE @@ -879,7 +885,8 @@ static inline pmd_t *pud_pgtable(pud_t pud) } /* Find an entry in the second-level page table. */ -#define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) +#define pmd_offset_phys(dir, addr) (pud_page_paddr(pudp_get(dir)) + \ + pmd_index(addr) * sizeof(pmd_t)) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) #define pmd_set_fixmap_offset(pud, addr) pmd_set_fixmap(pmd_offset_phys(pud, addr)) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 33b05a9f13d7..ea0cdc730768 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -181,7 +181,7 @@ static void show_pte(unsigned long addr) break; pudp = pud_offset_lockless(p4dp, p4d, addr); - pud = READ_ONCE(*pudp); + pud = pudp_get(pudp); ptval_to_str(pxd_str, pud_val(pud)); pr_cont(", pud=%s", pxd_str); if (pud_none(pud) || pud_bad(pud)) diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c index 3cdac8021d4f..d9a870836faf 100644 --- a/arch/arm64/mm/fixmap.c +++ b/arch/arm64/mm/fixmap.c @@ -56,7 +56,7 @@ static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr, unsigned long end) { unsigned long next; - pud_t pud = READ_ONCE(*pudp); + pud_t pud = pudp_get(pudp); pmd_t *pmdp; if (pud_none(pud)) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 301b5b7265a2..ce8ecf5a308f 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -262,7 +262,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, WARN_ON(addr & (sz - 1)); ptep = pte_alloc_huge(mm, pmdp, addr); } else if (sz == PMD_SIZE) { - if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp))) + if (want_pmd_share(vma, addr) && pud_none(pudp_get(pudp))) ptep = huge_pmd_share(mm, vma, addr, pudp); else ptep = (pte_t *)pmd_alloc(mm, pudp, addr); @@ -292,7 +292,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return NULL; pudp = pud_offset(p4dp, addr); - pud = READ_ONCE(*pudp); + pud = pudp_get(pudp); if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 7ca833c5de5e..aad29bcc7622 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -76,7 +76,7 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { - if (pud_none(READ_ONCE(*pudp))) { + if (pud_none(pudp_get(pudp))) { phys_addr_t pmd_phys = early ? __pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node); @@ -150,7 +150,7 @@ static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr, do { next = pud_addr_end(addr, end); kasan_pmd_populate(pudp, addr, next, node, early); - } while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp))); + } while (pudp++, addr = next, addr != end && pud_none(pudp_get(pudp))); } static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 0433033c0a71..c14e7404f971 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -309,7 +309,7 @@ static int alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, { int ret; unsigned long next; - pud_t pud = READ_ONCE(*pudp); + pud_t pud = pudp_get(pudp); pmd_t *pmdp; /* @@ -390,7 +390,7 @@ static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, } do { - pud_t old_pud = READ_ONCE(*pudp); + pud_t old_pud = pudp_get(pudp); next = pud_addr_end(addr, end); @@ -408,7 +408,7 @@ static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), - READ_ONCE(pud_val(*pudp)))); + pud_val(pudp_get(pudp)))); } else { ret = alloc_init_cont_pmd(pudp, addr, next, phys, prot, pgtable_alloc, flags); @@ -416,7 +416,7 @@ static int alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, goto out; VM_WARN_ON_ONCE(pud_val(old_pud) != 0 && - pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); + pud_val(old_pud) != pud_val(pudp_get(pudp))); } phys += next - addr; } while (pudp++, addr = next, addr != end); @@ -1591,7 +1591,7 @@ static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr, do { next = pud_addr_end(addr, end); pudp = pud_offset(p4dp, addr); - pud = READ_ONCE(*pudp); + pud = pudp_get(pudp); if (pud_none(pud)) continue; @@ -1748,7 +1748,7 @@ static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr, do { next = pud_addr_end(addr, end); pudp = pud_offset(p4dp, addr); - pud = READ_ONCE(*pudp); + pud = pudp_get(pudp); if (pud_none(pud)) continue; @@ -1769,7 +1769,7 @@ static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr, */ pudp = pud_offset(p4dp, 0UL); for (i = 0; i < PTRS_PER_PUD; i++) { - if (!pud_none(READ_ONCE(pudp[i]))) + if (!pud_none(pudp_get(pudp + i))) return; } @@ -1867,7 +1867,7 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot)); /* Only allow permission changes for now */ - if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)), + if (!pgattr_change_is_safe(pud_val(pudp_get(pudp)), pud_val(new_pud))) return 0; @@ -1898,7 +1898,7 @@ void p4d_clear_huge(p4d_t *p4dp) int pud_clear_huge(pud_t *pudp) { - if (!pud_leaf(READ_ONCE(*pudp))) + if (!pud_leaf(pudp_get(pudp))) return 0; pud_clear(pudp); return 1; @@ -1938,7 +1938,7 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pud_t pud; unsigned long next, end; - pud = READ_ONCE(*pudp); + pud = pudp_get(pudp); if (!pud_table(pud)) { VM_WARN_ON(1); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index bf1fd1258a75..c544a61a5afd 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -355,7 +355,7 @@ bool kernel_page_present(struct page *page) return false; pudp = pud_offset(p4dp, addr); - pud = READ_ONCE(*pudp); + pud = pudp_get(pudp); if (pud_none(pud)) return false; if (pud_leaf(pud)) diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index b27b2d2c20c3..d119119455f1 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -64,7 +64,7 @@ static int copy_pmd(struct trans_pgd_info *info, pud_t *dst_pudp, unsigned long next; unsigned long addr = start; - if (pud_none(READ_ONCE(*dst_pudp))) { + if (pud_none(pudp_get(dst_pudp))) { dst_pmdp = trans_alloc(info); if (!dst_pmdp) return -ENOMEM; @@ -109,7 +109,7 @@ static int copy_pud(struct trans_pgd_info *info, p4d_t *dst_p4dp, src_pudp = pud_offset(src_p4dp, start); do { - pud_t pud = READ_ONCE(*src_pudp); + pud_t pud = pudp_get(src_pudp); next = pud_addr_end(addr, end); if (pud_none(pud)) -- 2.43.0 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. Override p4dp_get() on arm64 platform. Although the same as the generic MM default fallback for p4dp_get(), it does help avoid build problems while converting READ_ONCE() in pud_offset_phys() and pud_offset() because of a cyclic dependency between and . No functional change intended. Cc: Catalin Marinas Cc: Will Deacon Cc: Ryan Roberts Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: kasan-dev@googlegroups.com Reviewed-by: Ryan Roberts Signed-off-by: Anshuman Khandual --- 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 ad6cd5a71b71..7b3463ff2014 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(const pud_t *pudp) return READ_ONCE(*pudp); } +#define p4dp_get p4dp_get +static inline p4d_t p4dp_get(const 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 ea0cdc730768..934b534c5b89 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 ce8ecf5a308f..2620223d9218 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 c14e7404f971..a11c1949561f 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 c544a61a5afd..172bc516164c 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -351,7 +351,7 @@ 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 Replace READ_ONCE() with pgdp_get() for PGD 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 PGD accesses on the existing page-table helpers. These can be overridden on arm64 to provide 128-bit single-copy atomicity when required. Override pgdp_get() on arm64 platform. Although the same as the generic MM default fallback for pgdp_get(), it does help avoid build problems while converting READ_ONCE() in p4d_offset_phys() and p4d_offset() because of a cyclic dependency between and . No functional change intended. Cc: Catalin Marinas Cc: Will Deacon Cc: Ryan Roberts Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: kasan-dev@googlegroups.com Reviewed-by: Ryan Roberts Signed-off-by: Anshuman Khandual --- arch/arm64/include/asm/pgtable.h | 10 ++++++++-- arch/arm64/mm/fault.c | 2 +- arch/arm64/mm/hugetlbpage.c | 2 +- arch/arm64/mm/kasan_init.c | 6 +++--- arch/arm64/mm/mmu.c | 6 +++--- arch/arm64/mm/pageattr.c | 2 +- arch/arm64/mm/trans_pgd.c | 4 ++-- 7 files changed, 19 insertions(+), 13 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7b3463ff2014..a760c65de5cb 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -102,6 +102,12 @@ static inline p4d_t p4dp_get(const p4d_t *p4dp) return READ_ONCE(*p4dp); } +#define pgdp_get pgdp_get +static inline pgd_t pgdp_get(const pgd_t *pgdp) +{ + return READ_ONCE(*pgdp); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE @@ -1102,7 +1108,7 @@ static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) { VM_WARN_ON_ONCE(!pgtable_l5_enabled()); - return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); + return pgd_page_paddr(pgdp_get(pgdp)) + p4d_index(addr) * sizeof(p4d_t); } static inline @@ -1116,7 +1122,7 @@ p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) { - return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); + return p4d_offset_lockless(pgdp, pgdp_get(pgdp), addr); } static inline p4d_t *p4d_set_fixmap(unsigned long addr) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 934b534c5b89..0b489fbeeb07 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -160,7 +160,7 @@ static void show_pte(unsigned long addr) guard(irqsave)(); pgdp = pgd_offset(mm, addr); - pgd = READ_ONCE(*pgdp); + pgd = pgdp_get(pgdp); ptval_to_str(pxd_str, pgd_val(pgd)); pr_alert("[%016lx] pgd=%s", addr, pxd_str); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 2620223d9218..26efacc6c8b5 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -284,7 +284,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, pmd_t *pmdp, pmd; pgdp = pgd_offset(mm, addr); - if (!pgd_present(READ_ONCE(*pgdp))) + if (!pgd_present(pgdp_get(pgdp))) return NULL; p4dp = p4d_offset(pgdp, addr); diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 4dd8c1186471..f61f5bc09467 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -102,7 +102,7 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) { - if (pgd_none(READ_ONCE(*pgdp))) { + if (pgd_none(pgdp_get(pgdp))) { phys_addr_t p4d_phys = early ? __pa_symbol(kasan_early_shadow_p4d) : kasan_alloc_zeroed_page(node); @@ -256,7 +256,7 @@ static int __init root_level_idx(u64 addr) static void __init clone_next_level(u64 addr, pgd_t *tmp_pg_dir, pud_t *pud) { int idx = root_level_idx(addr); - pgd_t pgd = READ_ONCE(swapper_pg_dir[idx]); + pgd_t pgd = pgdp_get(swapper_pg_dir + idx); pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd)); memcpy(pud, pudp, PAGE_SIZE); @@ -280,7 +280,7 @@ static int __init next_level_idx(u64 addr) */ static void __init clear_next_level(int pgd_idx, int start, int end) { - pgd_t pgd = READ_ONCE(swapper_pg_dir[pgd_idx]); + pgd_t pgd = pgdp_get(swapper_pg_dir + pgd_idx); pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd)); memset(&pudp[start], 0, (end - start) * sizeof(pud_t)); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index a11c1949561f..d0a4b8961c7d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -434,7 +434,7 @@ static int alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, { int ret; unsigned long next; - pgd_t pgd = READ_ONCE(*pgdp); + pgd_t pgd = pgdp_get(pgdp); p4d_t *p4dp; if (pgd_none(pgd)) { @@ -1649,7 +1649,7 @@ static void unmap_hotplug_range(unsigned long addr, unsigned long end, do { next = pgd_addr_end(addr, end); pgdp = pgd_offset_k(addr); - pgd = READ_ONCE(*pgdp); + pgd = pgdp_get(pgdp); if (pgd_none(pgd)) continue; @@ -1827,7 +1827,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end, do { next = pgd_addr_end(addr, end); pgdp = pgd_offset_k(addr); - pgd = READ_ONCE(*pgdp); + pgd = pgdp_get(pgdp); if (pgd_none(pgd)) continue; diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 172bc516164c..b3b7c508564f 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -347,7 +347,7 @@ bool kernel_page_present(struct page *page) unsigned long addr = (unsigned long)page_address(page); pgdp = pgd_offset_k(addr); - if (pgd_none(READ_ONCE(*pgdp))) + if (pgd_none(pgdp_get(pgdp))) return false; p4dp = p4d_offset(pgdp, addr); diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 7afe2beca4ba..06470d690f9f 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -134,7 +134,7 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp, unsigned long next; unsigned long addr = start; - if (pgd_none(READ_ONCE(*dst_pgdp))) { + if (pgd_none(pgdp_get(dst_pgdp))) { dst_p4dp = trans_alloc(info); if (!dst_p4dp) return -ENOMEM; @@ -164,7 +164,7 @@ static int copy_page_tables(struct trans_pgd_info *info, pgd_t *dst_pgdp, dst_pgdp = pgd_offset_pgd(dst_pgdp, start); do { next = pgd_addr_end(addr, end); - if (pgd_none(READ_ONCE(*src_pgdp))) + if (pgd_none(pgdp_get(src_pgdp))) continue; if (copy_p4d(info, dst_pgdp, src_pgdp, addr, next)) return -ENOMEM; -- 2.43.0