mm/sparse-vmemmap.c - linux - Git at Google

 // SPDX-License-Identifier: GPL-2.0
 /*
  * Virtual Memory Map support
  *
  * (C) 2007 sgi. Christoph Lameter.
  *
  * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn,
  * virt_to_page, page_address() to be implemented as a base offset
  * calculation without memory access.
  *
  * However, virtual mappings need a page table and TLBs. Many Linux
  * architectures already map their physical space using 1-1 mappings
  * via TLBs. For those arches the virtual memory map is essentially
  * for free if we use the same page size as the 1-1 mappings. In that
  * case the overhead consists of a few additional pages that are
  * allocated to create a view of memory for vmemmap.
  *
  * The architecture is expected to provide a vmemmap_populate() function
  * to instantiate the mapping.
  */
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/memblock.h>
 #include <linux/memremap.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
 #include <asm/dma.h>
 #include <asm/pgalloc.h>

 /*
  * Allocate a block of memory to be used to back the virtual memory map
  * or to back the page tables that are used to create the mapping.
  * Uses the main allocators if they are available, else bootmem.
  */

 static void * __ref __earlyonly_bootmem_alloc(int node,
 				unsigned long size,
 				unsigned long align,
 				unsigned long goal)
 {
 	return memblock_alloc_try_nid_raw(size, align, goal,
 					       MEMBLOCK_ALLOC_ACCESSIBLE, node);
 }

 void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 {
 	/* If the main allocator is up use that, fallback to bootmem. */
 	if (slab_is_available()) {
 		gfp_t gfp_mask = GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
 		int order = get_order(size);
 		static bool warned;
 		struct page *page;

 		page = alloc_pages_node(node, gfp_mask, order);
 		if (page)
 			return page_address(page);

 		if (!warned) {
 			warn_alloc(gfp_mask & ~__GFP_NOWARN, NULL,
 				   "vmemmap alloc failure: order:%u", order);
 			warned = true;
 		}
 		return NULL;
 	} else
 		return __earlyonly_bootmem_alloc(node, size, size,
 				__pa(MAX_DMA_ADDRESS));
 }

 /* need to make sure size is all the same during early stage */
 void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
 {
 	void *ptr = sparse_buffer_alloc(size);

 	if (!ptr)
 		ptr = vmemmap_alloc_block(size, node);
 	return ptr;
 }

 static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap)
 {
 	return altmap->base_pfn + altmap->reserve + altmap->alloc
 		+ altmap->align;
 }

 static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
 {
 	unsigned long allocated = altmap->alloc + altmap->align;

 	if (altmap->free > allocated)
 		return altmap->free - allocated;
 	return 0;
 }

 /**
  * altmap_alloc_block_buf - allocate pages from the device page map
  * @altmap:	device page map
  * @size:	size (in bytes) of the allocation
  *
  * Allocations are aligned to the size of the request.
  */
 void * __meminit altmap_alloc_block_buf(unsigned long size,
 		struct vmem_altmap *altmap)
 {
 	unsigned long pfn, nr_pfns, nr_align;

 	if (size & ~PAGE_MASK) {
 		pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n",
 				__func__, size);
 		return NULL;
 	}

 	pfn = vmem_altmap_next_pfn(altmap);
 	nr_pfns = size >> PAGE_SHIFT;
 	nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG);
 	nr_align = ALIGN(pfn, nr_align) - pfn;
 	if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap))
 		return NULL;

 	altmap->alloc += nr_pfns;
 	altmap->align += nr_align;
 	pfn += nr_align;

 	pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n",
 			__func__, pfn, altmap->alloc, altmap->align, nr_pfns);
 	return __va(__pfn_to_phys(pfn));
 }

 void __meminit vmemmap_verify(pte_t *pte, int node,
 				unsigned long start, unsigned long end)
 {
 	unsigned long pfn = pte_pfn(*pte);
 	int actual_node = early_pfn_to_nid(pfn);

 	if (node_distance(actual_node, node) > LOCAL_DISTANCE)
 		pr_warn("[%lx-%lx] potential offnode page_structs\n",
 			start, end - 1);
 }

 pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
 {
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte)) {
 		pte_t entry;
 		void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
 	}
 	return pte;
 }

 static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
 {
 	void *p = vmemmap_alloc_block(size, node);

 	if (!p)
 		return NULL;
 	memset(p, 0, size);

 	return p;
 }

 pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 {
 	pmd_t *pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd)) {
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pmd_populate_kernel(&init_mm, pmd, p);
 	}
 	return pmd;
 }

 pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
 {
 	pud_t *pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pud_populate(&init_mm, pud, p);
 	}
 	return pud;
 }

 p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
 {
 	p4d_t *p4d = p4d_offset(pgd, addr);
 	if (p4d_none(*p4d)) {
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		p4d_populate(&init_mm, p4d, p);
 	}
 	return p4d;
 }

 pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 {
 	pgd_t *pgd = pgd_offset_k(addr);
 	if (pgd_none(*pgd)) {
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		pgd_populate(&init_mm, pgd, p);
 	}
 	return pgd;
 }

 int __meminit vmemmap_populate_basepages(unsigned long start,
 					 unsigned long end, int node)
 {
 	unsigned long addr = start;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;

 	for (; addr < end; addr += PAGE_SIZE) {
 		pgd = vmemmap_pgd_populate(addr, node);
 		if (!pgd)
 			return -ENOMEM;
 		p4d = vmemmap_p4d_populate(pgd, addr, node);
 		if (!p4d)
 			return -ENOMEM;
 		pud = vmemmap_pud_populate(p4d, addr, node);
 		if (!pud)
 			return -ENOMEM;
 		pmd = vmemmap_pmd_populate(pud, addr, node);
 		if (!pmd)
 			return -ENOMEM;
 		pte = vmemmap_pte_populate(pmd, addr, node);
 		if (!pte)
 			return -ENOMEM;
 		vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
 	}

 	return 0;
 }

 struct page * __meminit __populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
 {
 	unsigned long start;
 	unsigned long end;

 	/*
 	 * The minimum granularity of memmap extensions is
 	 * PAGES_PER_SUBSECTION as allocations are tracked in the
 	 * 'subsection_map' bitmap of the section.
 	 */
 	end = ALIGN(pfn + nr_pages, PAGES_PER_SUBSECTION);
 	pfn &= PAGE_SUBSECTION_MASK;
 	nr_pages = end - pfn;

 	start = (unsigned long) pfn_to_page(pfn);
 	end = start + nr_pages * sizeof(struct page);

 	if (vmemmap_populate(start, end, nid, altmap))
 		return NULL;

 	return pfn_to_page(pfn);
 }
	// SPDX-License-Identifier: GPL-2.0
	/*
	* Virtual Memory Map support
	*
	* (C) 2007 sgi. Christoph Lameter.
	*
	* Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn,
	* virt_to_page, page_address() to be implemented as a base offset
	* calculation without memory access.
	*
	* However, virtual mappings need a page table and TLBs. Many Linux
	* architectures already map their physical space using 1-1 mappings
	* via TLBs. For those arches the virtual memory map is essentially
	* for free if we use the same page size as the 1-1 mappings. In that
	* case the overhead consists of a few additional pages that are
	* allocated to create a view of memory for vmemmap.
	*
	* The architecture is expected to provide a vmemmap_populate() function
	* to instantiate the mapping.
	*/
	#include <linux/mm.h>
	#include <linux/mmzone.h>
	#include <linux/memblock.h>
	#include <linux/memremap.h>
	#include <linux/highmem.h>
	#include <linux/slab.h>
	#include <linux/spinlock.h>
	#include <linux/vmalloc.h>
	#include <linux/sched.h>
	#include <asm/dma.h>
	#include <asm/pgalloc.h>

	/*
	* Allocate a block of memory to be used to back the virtual memory map
	* or to back the page tables that are used to create the mapping.
	* Uses the main allocators if they are available, else bootmem.
	*/

	static void * __ref __earlyonly_bootmem_alloc(int node,
	unsigned long size,
	unsigned long align,
	unsigned long goal)
	{
	return memblock_alloc_try_nid_raw(size, align, goal,
	MEMBLOCK_ALLOC_ACCESSIBLE, node);
	}

	void * __meminit vmemmap_alloc_block(unsigned long size, int node)
	{
	/* If the main allocator is up use that, fallback to bootmem. */
	if (slab_is_available()) {
	gfp_t gfp_mask = GFP_KERNEL\|__GFP_RETRY_MAYFAIL\|__GFP_NOWARN;
	int order = get_order(size);
	static bool warned;
	struct page *page;

	page = alloc_pages_node(node, gfp_mask, order);
	if (page)
	return page_address(page);

	if (!warned) {
	warn_alloc(gfp_mask & ~__GFP_NOWARN, NULL,
	"vmemmap alloc failure: order:%u", order);
	warned = true;
	}
	return NULL;
	} else
	return __earlyonly_bootmem_alloc(node, size, size,
	__pa(MAX_DMA_ADDRESS));
	}

	/* need to make sure size is all the same during early stage */
	void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
	{
	void *ptr = sparse_buffer_alloc(size);

	if (!ptr)
	ptr = vmemmap_alloc_block(size, node);
	return ptr;
	}

	static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap)
	{
	return altmap->base_pfn + altmap->reserve + altmap->alloc
	+ altmap->align;
	}

	static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
	{
	unsigned long allocated = altmap->alloc + altmap->align;

	if (altmap->free > allocated)
	return altmap->free - allocated;
	return 0;
	}

	/**
	* altmap_alloc_block_buf - allocate pages from the device page map
	* @altmap: device page map
	* @size: size (in bytes) of the allocation
	*
	* Allocations are aligned to the size of the request.
	*/
	void * __meminit altmap_alloc_block_buf(unsigned long size,
	struct vmem_altmap *altmap)
	{
	unsigned long pfn, nr_pfns, nr_align;

	if (size & ~PAGE_MASK) {
	pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n",
	__func__, size);
	return NULL;
	}

	pfn = vmem_altmap_next_pfn(altmap);
	nr_pfns = size >> PAGE_SHIFT;
	nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG);
	nr_align = ALIGN(pfn, nr_align) - pfn;
	if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap))
	return NULL;

	altmap->alloc += nr_pfns;
	altmap->align += nr_align;
	pfn += nr_align;

	pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n",
	__func__, pfn, altmap->alloc, altmap->align, nr_pfns);
	return __va(__pfn_to_phys(pfn));
	}

	void __meminit vmemmap_verify(pte_t *pte, int node,
	unsigned long start, unsigned long end)
	{
	unsigned long pfn = pte_pfn(*pte);
	int actual_node = early_pfn_to_nid(pfn);

	if (node_distance(actual_node, node) > LOCAL_DISTANCE)
	pr_warn("[%lx-%lx] potential offnode page_structs\n",
	start, end - 1);
	}

	pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
	{
	pte_t *pte = pte_offset_kernel(pmd, addr);
	if (pte_none(*pte)) {
	pte_t entry;
	void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
	if (!p)
	return NULL;
	entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
	set_pte_at(&init_mm, addr, pte, entry);
	}
	return pte;
	}

	static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
	{
	void *p = vmemmap_alloc_block(size, node);

	if (!p)
	return NULL;
	memset(p, 0, size);

	return p;
	}

	pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
	{
	pmd_t *pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd)) {
	void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
	if (!p)
	return NULL;
	pmd_populate_kernel(&init_mm, pmd, p);
	}
	return pmd;
	}

	pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
	{
	pud_t *pud = pud_offset(p4d, addr);
	if (pud_none(*pud)) {
	void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
	if (!p)
	return NULL;
	pud_populate(&init_mm, pud, p);
	}
	return pud;
	}

	p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
	{
	p4d_t *p4d = p4d_offset(pgd, addr);
	if (p4d_none(*p4d)) {
	void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
	if (!p)
	return NULL;
	p4d_populate(&init_mm, p4d, p);
	}
	return p4d;
	}

	pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
	{
	pgd_t *pgd = pgd_offset_k(addr);
	if (pgd_none(*pgd)) {
	void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
	if (!p)
	return NULL;
	pgd_populate(&init_mm, pgd, p);
	}
	return pgd;
	}

	int __meminit vmemmap_populate_basepages(unsigned long start,
	unsigned long end, int node)
	{
	unsigned long addr = start;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	for (; addr < end; addr += PAGE_SIZE) {
	pgd = vmemmap_pgd_populate(addr, node);
	if (!pgd)
	return -ENOMEM;
	p4d = vmemmap_p4d_populate(pgd, addr, node);
	if (!p4d)
	return -ENOMEM;
	pud = vmemmap_pud_populate(p4d, addr, node);
	if (!pud)
	return -ENOMEM;
	pmd = vmemmap_pmd_populate(pud, addr, node);
	if (!pmd)
	return -ENOMEM;
	pte = vmemmap_pte_populate(pmd, addr, node);
	if (!pte)
	return -ENOMEM;
	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
	}

	return 0;
	}

	struct page * __meminit __populate_section_memmap(unsigned long pfn,
	unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
	{
	unsigned long start;
	unsigned long end;

	/*
	* The minimum granularity of memmap extensions is
	* PAGES_PER_SUBSECTION as allocations are tracked in the
	* 'subsection_map' bitmap of the section.
	*/
	end = ALIGN(pfn + nr_pages, PAGES_PER_SUBSECTION);
	pfn &= PAGE_SUBSECTION_MASK;
	nr_pages = end - pfn;

	start = (unsigned long) pfn_to_page(pfn);
	end = start + nr_pages * sizeof(struct page);

	if (vmemmap_populate(start, end, nid, altmap))
	return NULL;

	return pfn_to_page(pfn);
	}