powerpc/book3s64/radix: add support for vmemmap optimization for radix

With 2M PMD-level mapping, we require 32 struct pages and a single vmemmap
page can contain 1024 struct pages (PAGE_SIZE/sizeof(struct page)).  Hence
with 64K page size, we don't use vmemmap deduplication for PMD-level
mapping.

[aneesh.kumar@linux.ibm.com: ppc64: don't include radix headers if CONFIG_PPC_RADIX_MMU=n]
  Link: https://lkml.kernel.org/r/87zg3jw8km.fsf@linux.ibm.com
Link: https://lkml.kernel.org/r/20230724190759.483013-12-aneesh.kumar@linux.ibm.comSigned-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Documentation/mm/vmemmap_dedup.rst

@@ -210,6 +210,7 @@ the device (altmap).
 
 The following page sizes are supported in DAX: PAGE_SIZE (4K on x86_64),
 PMD_SIZE (2M on x86_64) and PUD_SIZE (1G on x86_64).
+For powerpc equivalent details see Documentation/powerpc/vmemmap_dedup.rst
 
 The differences with HugeTLB are relatively minor.
 

Documentation/powerpc/index.rst

@@ -36,6 +36,7 @@ powerpc
     ultravisor
     vas-api
     vcpudispatch_stats
+    vmemmap_dedup
 
     features
 

Documentation/powerpc/vmemmap_dedup.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+==========
+Device DAX
+==========
+
+The device-dax interface uses the tail deduplication technique explained in
+Documentation/mm/vmemmap_dedup.rst
+
+On powerpc, vmemmap deduplication is only used with radix MMU translation. Also
+with a 64K page size, only the devdax namespace with 1G alignment uses vmemmap
+deduplication.
+
+With 2M PMD level mapping, we require 32 struct pages and a single 64K vmemmap
+page can contain 1024 struct pages (64K/sizeof(struct page)). Hence there is no
+vmemmap deduplication possible.
+
+With 1G PUD level mapping, we require 16384 struct pages and a single 64K
+vmemmap page can contain 1024 struct pages (64K/sizeof(struct page)). Hence we
+require 16 64K pages in vmemmap to map the struct page for 1G PUD level mapping.
+
+Here's how things look like on device-dax after the sections are populated::
+ +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ |           |                     |     0     | -------------> |     0     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     1     | -------------> |     1     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
+ |           |                     +-----------+                   | | | | |
+ |           |                     |     3     | ------------------+ | | | |
+ |           |                     +-----------+                     | | | |
+ |           |                     |     4     | --------------------+ | | |
+ |    PUD    |                     +-----------+                       | | |
+ |   level   |                     |     .     | ----------------------+ | |
+ |  mapping  |                     +-----------+                         | |
+ |           |                     |     .     | ------------------------+ |
+ |           |                     +-----------+                           |
+ |           |                     |     15    | --------------------------+
+ |           |                     +-----------+
+ |           |
+ |           |
+ |           |
+ +-----------+
+
+
+With 4K page size, 2M PMD level mapping requires 512 struct pages and a single
+4K vmemmap page contains 64 struct pages(4K/sizeof(struct page)). Hence we
+require 8 4K pages in vmemmap to map the struct page for 2M pmd level mapping.
+
+Here's how things look like on device-dax after the sections are populated::
+
+ +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ |           |                     |     0     | -------------> |     0     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     1     | -------------> |     1     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
+ |           |                     +-----------+                   | | | | |
+ |           |                     |     3     | ------------------+ | | | |
+ |           |                     +-----------+                     | | | |
+ |           |                     |     4     | --------------------+ | | |
+ |    PMD    |                     +-----------+                       | | |
+ |   level   |                     |     5     | ----------------------+ | |
+ |  mapping  |                     +-----------+                         | |
+ |           |                     |     6     | ------------------------+ |
+ |           |                     +-----------+                           |
+ |           |                     |     7     | --------------------------+
+ |           |                     +-----------+
+ |           |
+ |           |
+ |           |
+ +-----------+
+
+With 1G PUD level mapping, we require 262144 struct pages and a single 4K
+vmemmap page can contain 64 struct pages (4K/sizeof(struct page)). Hence we
+require 4096 4K pages in vmemmap to map the struct pages for 1G PUD level
+mapping.
+
+Here's how things look like on device-dax after the sections are populated::
+
+ +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ |           |                     |     0     | -------------> |     0     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     1     | -------------> |     1     |
+ |           |                     +-----------+                +-----------+
+ |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
+ |           |                     +-----------+                   | | | | |
+ |           |                     |     3     | ------------------+ | | | |
+ |           |                     +-----------+                     | | | |
+ |           |                     |     4     | --------------------+ | | |
+ |    PUD    |                     +-----------+                       | | |
+ |   level   |                     |     .     | ----------------------+ | |
+ |  mapping  |                     +-----------+                         | |
+ |           |                     |     .     | ------------------------+ |
+ |           |                     +-----------+                           |
+ |           |                     |   4095    | --------------------------+
+ |           |                     +-----------+
+ |           |
+ |           |
+ |           |
+ +-----------+

arch/powerpc/Kconfig

@@ -174,6 +174,7 @@ config PPC
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP	if PPC_RADIX_MMU
 	select ARCH_WANTS_MODULES_DATA_IN_VMALLOC	if PPC_BOOK3S_32 || PPC_8xx
 	select ARCH_WEAK_RELEASE_ACQUIRE
 	select BINFMT_ELF

arch/powerpc/include/asm/book3s/64/radix.h

@@ -326,6 +326,7 @@ static inline pud_t radix__pud_mkdevmap(pud_t pud)
 }
 
 struct vmem_altmap;
+struct dev_pagemap;
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
 					     unsigned long page_size,
 					     unsigned long phys);
@@ -363,5 +364,15 @@ int radix__remove_section_mapping(unsigned long start, unsigned long end);
 
 void radix__kernel_map_pages(struct page *page, int numpages, int enable);
 
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
+#define vmemmap_can_optimize vmemmap_can_optimize
+bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
+#endif
+
+#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages
+int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
+					      unsigned long start,
+					      unsigned long end, int node,
+					      struct dev_pagemap *pgmap);
 #endif /* __ASSEMBLY__ */
 #endif

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -986,6 +986,15 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
 	return 0;
 }
 
+
+bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+	if (radix_enabled())
+		return __vmemmap_can_optimize(altmap, pgmap);
+
+	return false;
+}
+
 int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
 				unsigned long addr, unsigned long next)
 {
@@ -1193,6 +1202,200 @@ int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, in
 	return 0;
 }
 
+static pte_t * __meminit radix__vmemmap_populate_address(unsigned long addr, int node,
+							 struct vmem_altmap *altmap,
+							 struct page *reuse)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset_k(addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = vmemmap_pud_alloc(p4d, node, addr);
+	if (!pud)
+		return NULL;
+	pmd = vmemmap_pmd_alloc(pud, node, addr);
+	if (!pmd)
+		return NULL;
+	if (pmd_leaf(*pmd))
+		/*
+		 * The second page is mapped as a hugepage due to a nearby request.
+		 * Force our mapping to page size without deduplication
+		 */
+		return NULL;
+	pte = vmemmap_pte_alloc(pmd, node, addr);
+	if (!pte)
+		return NULL;
+	radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL);
+	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+	return pte;
+}
+
+static pte_t * __meminit vmemmap_compound_tail_page(unsigned long addr,
+						    unsigned long pfn_offset, int node)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long map_addr;
+
+	/* the second vmemmap page which we use for duplication */
+	map_addr = addr - pfn_offset * sizeof(struct page) + PAGE_SIZE;
+	pgd = pgd_offset_k(map_addr);
+	p4d = p4d_offset(pgd, map_addr);
+	pud = vmemmap_pud_alloc(p4d, node, map_addr);
+	if (!pud)
+		return NULL;
+	pmd = vmemmap_pmd_alloc(pud, node, map_addr);
+	if (!pmd)
+		return NULL;
+	if (pmd_leaf(*pmd))
+		/*
+		 * The second page is mapped as a hugepage due to a nearby request.
+		 * Force our mapping to page size without deduplication
+		 */
+		return NULL;
+	pte = vmemmap_pte_alloc(pmd, node, map_addr);
+	if (!pte)
+		return NULL;
+	/*
+	 * Check if there exist a mapping to the left
+	 */
+	if (pte_none(*pte)) {
+		/*
+		 * Populate the head page vmemmap page.
+		 * It can fall in different pmd, hence
+		 * vmemmap_populate_address()
+		 */
+		pte = radix__vmemmap_populate_address(map_addr - PAGE_SIZE, node, NULL, NULL);
+		if (!pte)
+			return NULL;
+		/*
+		 * Populate the tail pages vmemmap page
+		 */
+		pte = radix__vmemmap_pte_populate(pmd, map_addr, node, NULL, NULL);
+		if (!pte)
+			return NULL;
+		vmemmap_verify(pte, node, map_addr, map_addr + PAGE_SIZE);
+		return pte;
+	}
+	return pte;
+}
+
+int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
+					      unsigned long start,
+					      unsigned long end, int node,
+					      struct dev_pagemap *pgmap)
+{
+	/*
+	 * we want to map things as base page size mapping so that
+	 * we can save space in vmemmap. We could have huge mapping
+	 * covering out both edges.
+	 */
+	unsigned long addr;
+	unsigned long addr_pfn = start_pfn;
+	unsigned long next;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	for (addr = start; addr < end; addr = next) {
+
+		pgd = pgd_offset_k(addr);
+		p4d = p4d_offset(pgd, addr);
+		pud = vmemmap_pud_alloc(p4d, node, addr);
+		if (!pud)
+			return -ENOMEM;
+		pmd = vmemmap_pmd_alloc(pud, node, addr);
+		if (!pmd)
+			return -ENOMEM;
+
+		if (pmd_leaf(READ_ONCE(*pmd))) {
+			/* existing huge mapping. Skip the range */
+			addr_pfn += (PMD_SIZE >> PAGE_SHIFT);
+			next = pmd_addr_end(addr, end);
+			continue;
+		}
+		pte = vmemmap_pte_alloc(pmd, node, addr);
+		if (!pte)
+			return -ENOMEM;
+		if (!pte_none(*pte)) {
+			/*
+			 * This could be because we already have a compound
+			 * page whose VMEMMAP_RESERVE_NR pages were mapped and
+			 * this request fall in those pages.
+			 */
+			addr_pfn += 1;
+			next = addr + PAGE_SIZE;
+			continue;
+		} else {
+			unsigned long nr_pages = pgmap_vmemmap_nr(pgmap);
+			unsigned long pfn_offset = addr_pfn - ALIGN_DOWN(addr_pfn, nr_pages);
+			pte_t *tail_page_pte;
+
+			/*
+			 * if the address is aligned to huge page size it is the
+			 * head mapping.
+			 */
+			if (pfn_offset == 0) {
+				/* Populate the head page vmemmap page */
+				pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL);
+				if (!pte)
+					return -ENOMEM;
+				vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+				/*
+				 * Populate the tail pages vmemmap page
+				 * It can fall in different pmd, hence
+				 * vmemmap_populate_address()
+				 */
+				pte = radix__vmemmap_populate_address(addr + PAGE_SIZE, node, NULL, NULL);
+				if (!pte)
+					return -ENOMEM;
+
+				addr_pfn += 2;
+				next = addr + 2 * PAGE_SIZE;
+				continue;
+			}
+			/*
+			 * get the 2nd mapping details
+			 * Also create it if that doesn't exist
+			 */
+			tail_page_pte = vmemmap_compound_tail_page(addr, pfn_offset, node);
+			if (!tail_page_pte) {
+
+				pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL);
+				if (!pte)
+					return -ENOMEM;
+				vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+				addr_pfn += 1;
+				next = addr + PAGE_SIZE;
+				continue;
+			}
+
+			pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, pte_page(*tail_page_pte));
+			if (!pte)
+				return -ENOMEM;
+			vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+			addr_pfn += 1;
+			next = addr + PAGE_SIZE;
+			continue;
+		}
+	}
+	return 0;
+}
+
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
 {