Add the struct dev_pagemap pointer as a parameter to the architecture specific vmemmap_populate(), vmemmap_populate_hugepages() and vmemmap_populate_basepages() functions.
Currently, the vmemmap optimization for DAX is handled mostly in an architecture-agnostic way via vmemmap_populate_compound_pages(). However, this approach skips crucial architecture-specific initialization steps. For example, the x86 path must call sync_global_pgds() after populating the vmemmap, which is currently being bypassed. To fix this, we need to push the awareness of device memory optimization (via the pgmap) down into the architecture-specific vmemmap_populate() paths. This will allow each architecture to handle the optimization while ensuring their specific initialization routines (like page directory synchronization) are correctly invoked. This is a preparatory patch only; it changes no behavior. The actual architecture-specific implementations and fixes will follow. Signed-off-by: Muchun Song <[email protected]> --- arch/arm64/mm/mmu.c | 6 +++--- arch/loongarch/mm/init.c | 7 ++++--- arch/powerpc/include/asm/book3s/64/radix.h | 3 ++- arch/powerpc/mm/book3s64/radix_pgtable.c | 2 +- arch/powerpc/mm/init_64.c | 4 ++-- arch/riscv/mm/init.c | 4 ++-- arch/s390/mm/vmem.c | 2 +- arch/sparc/mm/init_64.c | 5 +++-- arch/x86/mm/init_64.c | 8 ++++---- include/linux/mm.h | 8 +++++--- mm/hugetlb_vmemmap.c | 4 ++-- mm/sparse-vmemmap.c | 10 ++++++---- 12 files changed, 35 insertions(+), 28 deletions(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index dc8a8281888c..86162aab5185 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1760,7 +1760,7 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); /* [start, end] should be within one section */ @@ -1768,9 +1768,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) || (end - start < PAGES_PER_SECTION * sizeof(struct page))) - return vmemmap_populate_basepages(start, end, node, altmap); + return vmemmap_populate_basepages(start, end, node, altmap, pgmap); else - return vmemmap_populate_hugepages(start, end, node, altmap); + return vmemmap_populate_hugepages(start, end, node, altmap, pgmap); } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index c9c57f08fa2c..d61c2e09caae 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -123,12 +123,13 @@ int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, } int __meminit vmemmap_populate(unsigned long start, unsigned long end, - int node, struct vmem_altmap *altmap) + int node, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { #if CONFIG_PGTABLE_LEVELS == 2 - return vmemmap_populate_basepages(start, end, node, NULL); + return vmemmap_populate_basepages(start, end, node, NULL, pgmap); #else - return vmemmap_populate_hugepages(start, end, node, NULL); + return vmemmap_populate_hugepages(start, end, node, NULL, pgmap); #endif } diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index da954e779744..bde07c6f900f 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -321,7 +321,8 @@ extern int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, - int node, struct vmem_altmap *altmap); + int node, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); void __ref radix__vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); extern void radix__vmemmap_remove_mapping(unsigned long start, diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 10aced261cff..568500343e5f 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1112,7 +1112,7 @@ static inline pte_t *vmemmap_pte_alloc(pmd_t *pmdp, int node, int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { unsigned long addr; unsigned long next; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index b6f3ae03ca9e..8f4aa5b32186 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -275,12 +275,12 @@ static int __meminit __vmemmap_populate(unsigned long start, unsigned long end, } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { #ifdef CONFIG_PPC_BOOK3S_64 if (radix_enabled()) - return radix__vmemmap_populate(start, end, node, altmap); + return radix__vmemmap_populate(start, end, node, altmap, pgmap); #endif return __vmemmap_populate(start, end, node, altmap); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 980f693e6b19..277c89661dff 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1443,7 +1443,7 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { /* * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we @@ -1451,7 +1451,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, * memory hotplug, we are not able to update all the page tables with * the new PMDs. */ - return vmemmap_populate_hugepages(start, end, node, altmap); + return vmemmap_populate_hugepages(start, end, node, altmap, pgmap); } #endif diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index eeadff45e0e1..a7bf8d3d5601 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -506,7 +506,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size) * Add a backed mem_map array to the virtual mem_map array. */ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { int ret; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 367c269305e5..f870ca330f9e 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2591,9 +2591,10 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, } int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, - int node, struct vmem_altmap *altmap) + int node, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { - return vmemmap_populate_hugepages(vstart, vend, node, NULL); + return vmemmap_populate_hugepages(vstart, vend, node, NULL, pgmap); } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 77b889b71cf3..e18cc81a30b4 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1557,7 +1557,7 @@ int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { int err; @@ -1565,15 +1565,15 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, VM_BUG_ON(!PAGE_ALIGNED(end)); if (end - start < PAGES_PER_SECTION * sizeof(struct page)) - err = vmemmap_populate_basepages(start, end, node, NULL); + err = vmemmap_populate_basepages(start, end, node, NULL, pgmap); else if (boot_cpu_has(X86_FEATURE_PSE)) - err = vmemmap_populate_hugepages(start, end, node, altmap); + err = vmemmap_populate_hugepages(start, end, node, altmap, pgmap); else if (altmap) { pr_err_once("%s: no cpu support for altmap allocations\n", __func__); err = -ENOMEM; } else - err = vmemmap_populate_basepages(start, end, node, NULL); + err = vmemmap_populate_basepages(start, end, node, NULL, pgmap); if (!err) sync_global_pgds(start, end - 1); return err; diff --git a/include/linux/mm.h b/include/linux/mm.h index 0b776907152e..bebc5f892f81 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4877,11 +4877,13 @@ void vmemmap_set_pmd(pmd_t *pmd, void *p, int node, int vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next); int vmemmap_populate_basepages(unsigned long start, unsigned long end, - int node, struct vmem_altmap *altmap); + int node, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); int vmemmap_populate_hugepages(unsigned long start, unsigned long end, - int node, struct vmem_altmap *altmap); + int node, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, - struct vmem_altmap *altmap); + struct vmem_altmap *altmap, struct dev_pagemap *pgmap); int vmemmap_populate_hvo(unsigned long start, unsigned long end, unsigned int order, struct zone *zone, unsigned long headsize); diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 4a077d231d3a..50b7123f3bdd 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -829,7 +829,7 @@ void __init hugetlb_vmemmap_init_late(int nid) */ list_del(&m->list); - vmemmap_populate(start, end, nid, NULL); + vmemmap_populate(start, end, nid, NULL, NULL); nr_mmap = end - start; memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE)); @@ -845,7 +845,7 @@ void __init hugetlb_vmemmap_init_late(int nid) if (vmemmap_populate_hvo(start, end, huge_page_order(h), zone, HUGETLB_VMEMMAP_RESERVE_SIZE) < 0) { /* Fallback if HVO population fails */ - vmemmap_populate(start, end, nid, NULL); + vmemmap_populate(start, end, nid, NULL, NULL); nr_mmap = end - start; } else { m->flags |= HUGE_BOOTMEM_ZONES_VALID; diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 0ef96b1afbcc..387337bba05e 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -297,7 +297,8 @@ static int __meminit vmemmap_populate_range(unsigned long start, } int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end, - int node, struct vmem_altmap *altmap) + int node, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { return vmemmap_populate_range(start, end, node, altmap, -1, 0); } @@ -400,7 +401,8 @@ int __weak __meminit vmemmap_check_pmd(pmd_t *pmd, int node, } int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end, - int node, struct vmem_altmap *altmap) + int node, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { unsigned long addr; unsigned long next; @@ -445,7 +447,7 @@ int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end, } } else if (vmemmap_check_pmd(pmd, node, addr, next)) continue; - if (vmemmap_populate_basepages(addr, next, node, altmap)) + if (vmemmap_populate_basepages(addr, next, node, altmap, pgmap)) return -ENOMEM; } return 0; @@ -559,7 +561,7 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (vmemmap_can_optimize(altmap, pgmap)) r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap); else - r = vmemmap_populate(start, end, nid, altmap); + r = vmemmap_populate(start, end, nid, altmap, pgmap); if (r < 0) return NULL; -- 2.20.1
