[PATCH v3 1/6] mm/sparse-vmemmap: drop VMEMMAP_POPULATE_DAX

[Muchun Song <songmuchun@bytedance.com>]

VMEMMAP_POPULATE_DAX currently distinguishes DAX vmemmap population in
two places: it keeps allocations on the normal path and takes a reference
when a backing page is supplied for reuse.

After Device DAX switched to the common per-zone shared tail page, both
conditions can be determined locally. DAX supplies ptpfn for every shared
tail mapping and requests an allocation only for compound head mappings,
whose PFNs are not optimizable. Therefore, vmemmap_optimizable_pfn() alone
selects the correct allocation path.

When ptpfn is supplied, the caller is reusing an existing backing page.
Once the slab allocator is available, take a reference for each reused
mapping to balance the release performed by vmemmap_free(). Although the
buddy allocator is available before slab, no vmemmap population occurs in
that interval. Earlier mappings are backed by memblock/reserved memory and
do not need page reference accounting.

Remove VMEMMAP_POPULATE_DAX and the flags argument from the vmemmap
population helpers.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Qi Zheng <qi.zheng@linux.dev>
---
v2:
- Explain why the buddy-to-slab initialization gap is safe (suggested by
  Qi Zheng)
- Collect Acked-by from Qi Zheng
---
 mm/sparse-vmemmap.c | 36 +++++++++++++-----------------------
 1 file changed, 13 insertions(+), 23 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 111efc802465..8219abc6c3e5 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -32,12 +32,6 @@
 #include <asm/dma.h>
 #include <asm/tlbflush.h>
 
-/*
- * Flags for vmemmap_populate_range and friends.
- */
-/* Vmemmap population for ZONE_DEVICE compound pages */
-#define VMEMMAP_POPULATE_DAX		0x0001
-
 #include "internal.h"
 #include "mm_init.h"
 #include "sparse.h"
@@ -237,7 +231,7 @@ struct page __ref *vmemmap_shared_tail_page(unsigned int order, struct zone *zon
 #endif
 
 static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node,
-		struct vmem_altmap *altmap, unsigned long flags)
+		struct vmem_altmap *altmap)
 {
 	struct zone *zone;
 	struct page *page;
@@ -247,7 +241,7 @@ static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node,
 	 * Device DAX still relies on vmemmap_populate_compound_pages() for
 	 * head/first-tail allocation and tail-page reuse.
 	 */
-	if (!vmemmap_optimizable_pfn(pfn) || flags & VMEMMAP_POPULATE_DAX)
+	if (!vmemmap_optimizable_pfn(pfn))
 		return vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
 
 	zone = pfn_to_zone(pfn, node);
@@ -259,8 +253,7 @@ static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node,
 }
 
 static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
-				       struct vmem_altmap *altmap,
-				       unsigned long ptpfn, unsigned long flags)
+		struct vmem_altmap *altmap, unsigned long ptpfn)
 {
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	unsigned long pfn = page_to_pfn((struct page *)addr);
@@ -269,7 +262,7 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in
 		pte_t entry;
 
 		if (ptpfn == (unsigned long)-1) {
-			void *p = vmemmap_alloc_pte(pfn, node, altmap, flags);
+			void *p = vmemmap_alloc_pte(pfn, node, altmap);
 
 			if (!p)
 				return NULL;
@@ -287,7 +280,7 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in
 			 * Use try_get_page() to prevent the shared page refcount
 			 * from overflowing.
 			 */
-			if ((flags & VMEMMAP_POPULATE_DAX) &&
+			if (slab_is_available() &&
 			    !try_get_page(pfn_to_page(ptpfn)))
 				return NULL;
 		}
@@ -351,8 +344,7 @@ static pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 
 static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
 					      struct vmem_altmap *altmap,
-					      unsigned long ptpfn,
-					      unsigned long flags)
+					      unsigned long ptpfn)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -372,7 +364,7 @@ static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
 	pmd = vmemmap_pmd_populate(pud, addr, node);
 	if (!pmd)
 		return NULL;
-	pte = vmemmap_pte_populate(pmd, addr, node, altmap, ptpfn, flags);
+	pte = vmemmap_pte_populate(pmd, addr, node, altmap, ptpfn);
 	if (!pte)
 		return NULL;
 	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
@@ -383,15 +375,14 @@ static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
 static int __meminit vmemmap_populate_range(unsigned long start,
 					    unsigned long end, int node,
 					    struct vmem_altmap *altmap,
-					    unsigned long ptpfn,
-					    unsigned long flags)
+					    unsigned long ptpfn)
 {
 	unsigned long addr = start;
 	pte_t *pte;
 
 	for (; addr < end; addr += PAGE_SIZE) {
 		pte = vmemmap_populate_address(addr, node, altmap,
-					       ptpfn, flags);
+					       ptpfn);
 		if (!pte)
 			return -ENOMEM;
 	}
@@ -402,7 +393,7 @@ 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)
 {
-	return vmemmap_populate_range(start, end, node, altmap, -1, 0);
+	return vmemmap_populate_range(start, end, node, altmap, -1);
 }
 
 /*
@@ -531,7 +522,6 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 	unsigned long size, addr;
 	pte_t *pte;
 	int rc;
-	unsigned long flags = VMEMMAP_POPULATE_DAX;
 	struct page *page;
 	unsigned int order = pfn_to_section_compound_order(start_pfn);
 
@@ -541,14 +531,14 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 
 	if (reuse_compound_section(start_pfn, pgmap))
 		return vmemmap_populate_range(start, end, node, NULL,
-					      page_to_pfn(page), flags);
+					      page_to_pfn(page));
 
 	size = min(end - start, (1UL << order) * sizeof(struct page));
 	for (addr = start; addr < end; addr += size) {
 		unsigned long next, last = addr + size;
 
 		/* Populate the head page vmemmap page */
-		pte = vmemmap_populate_address(addr, node, NULL, -1, flags);
+		pte = vmemmap_populate_address(addr, node, NULL, -1);
 		if (!pte)
 			return -ENOMEM;
 
@@ -558,7 +548,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 		 */
 		next = addr + PAGE_SIZE;
 		rc = vmemmap_populate_range(next, last, node, NULL,
-					    page_to_pfn(page), flags);
+					    page_to_pfn(page));
 		if (rc)
 			return -ENOMEM;
 	}
-- 
2.54.0