[PATCH 4/4] mm/vmalloc: Hugepage vmalloc mappings

[Nicholas Piggin <npiggin@gmail.com>]

For platforms that define HAVE_ARCH_HUGE_VMAP, have vmalloc try to
allocate and map PMD-level huge pages when size is appropriate, and
fallback if unsuccessful.

Using 2MB page mappings in an 8MB dentry cache hash brings dTLB misses
for linux kernel tree `git diff` from 45,000 to 8,000 on a Kaby Lake CPU
wth mitigations=off (performance is in the noise, under 1% difference,
page tables are likely to be well cached for this workload).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 include/linux/vmalloc.h |   1 +
 mm/vmalloc.c            | 132 +++++++++++++++++++++++++++++++---------
 2 files changed, 105 insertions(+), 28 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 812bea5866d6..4c92dc608928 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -42,6 +42,7 @@ struct vm_struct {
 	unsigned long		size;
 	unsigned long		flags;
 	struct page		**pages;
+	unsigned int		page_shift;
 	unsigned int		nr_pages;
 	phys_addr_t		phys_addr;
 	const void		*caller;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6a0c97f89091..34de925ed4f4 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -36,6 +36,7 @@
 #include <linux/rbtree_augmented.h>
 
 #include <linux/uaccess.h>
+#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
@@ -439,6 +440,41 @@ static int vmap_pages_range(unsigned long start, unsigned long end,
 	return ret;
 }
 
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+static int vmap_hpages_range(unsigned long start, unsigned long end,
+				   pgprot_t prot, struct page **pages,
+				   unsigned int page_shift)
+{
+	unsigned long addr = start;
+	unsigned int i, nr = (end - start) >> (PAGE_SHIFT + page_shift);
+
+	for (i = 0; i < nr; i++) {
+		int err;
+
+		err = vmap_range_noflush(addr,
+					addr + (PAGE_SIZE << page_shift),
+					__pa(page_address(pages[i])), prot,
+					page_shift);
+		if (err)
+			return err;
+
+		addr += PAGE_SIZE << page_shift;
+	}
+	flush_cache_vmap(start, end);
+
+	return nr;
+}
+#else
+static int vmap_hpages_range(unsigned long start, unsigned long end,
+			   pgprot_t prot, struct page **pages,
+			   unsigned int page_shift)
+{
+	BUG_ON(page_shift != PAGE_SIZE);
+	return vmap_pages_range(start, end, prot, pages);
+}
+#endif
+
+
 int is_vmalloc_or_module_addr(const void *x)
 {
 	/*
@@ -461,7 +497,7 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 {
 	unsigned long addr = (unsigned long) vmalloc_addr;
 	struct page *page = NULL;
-	pgd_t *pgd = pgd_offset_k(addr);
+	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
@@ -473,27 +509,38 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	 */
 	VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
 
+	pgd = pgd_offset_k(addr);
 	if (pgd_none(*pgd))
 		return NULL;
+
 	p4d = p4d_offset(pgd, addr);
 	if (p4d_none(*p4d))
 		return NULL;
-	pud = pud_offset(p4d, addr);
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+	if (p4d_large(*p4d))
+		return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
+#endif
+	if (WARN_ON_ONCE(p4d_bad(*p4d)))
+		return NULL;
 
-	/*
-	 * Don't dereference bad PUD or PMD (below) entries. This will also
-	 * identify huge mappings, which we may encounter on architectures
-	 * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
-	 * identified as vmalloc addresses by is_vmalloc_addr(), but are
-	 * not [unambiguously] associated with a struct page, so there is
-	 * no correct value to return for them.
-	 */
-	WARN_ON_ONCE(pud_bad(*pud));
-	if (pud_none(*pud) || pud_bad(*pud))
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return NULL;
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+	if (pud_large(*pud))
+		return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+#endif
+	if (WARN_ON_ONCE(pud_bad(*pud)))
 		return NULL;
+
 	pmd = pmd_offset(pud, addr);
-	WARN_ON_ONCE(pmd_bad(*pmd));
-	if (pmd_none(*pmd) || pmd_bad(*pmd))
+	if (pmd_none(*pmd))
+		return NULL;
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+	if (pmd_large(*pmd))
+		return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+#endif
+	if (WARN_ON_ONCE(pmd_bad(*pmd)))
 		return NULL;
 
 	ptep = pte_offset_map(pmd, addr);
@@ -501,6 +548,7 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	if (pte_present(pte))
 		page = pte_page(pte);
 	pte_unmap(ptep);
+
 	return page;
 }
 EXPORT_SYMBOL(vmalloc_to_page);
@@ -2184,8 +2232,9 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 		return NULL;
 
 	if (flags & VM_IOREMAP)
-		align = 1ul << clamp_t(int, get_count_order_long(size),
-				       PAGE_SHIFT, IOREMAP_MAX_ORDER);
+		align = max(align,
+				1ul << clamp_t(int, get_count_order_long(size),
+				       PAGE_SHIFT, IOREMAP_MAX_ORDER));
 
 	area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
 	if (unlikely(!area))
@@ -2397,7 +2446,7 @@ static void __vunmap(const void *addr, int deallocate_pages)
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
-			__free_pages(page, 0);
+			__free_pages(page, area->page_shift);
 		}
 
 		kvfree(area->pages);
@@ -2540,14 +2589,17 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node)
 {
 	struct page **pages;
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long size = get_vm_area_size(area);
+	unsigned int page_shift = area->page_shift;
+	unsigned int shift = page_shift + PAGE_SHIFT;
 	unsigned int nr_pages, array_size, i;
 	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
 	const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
 	const gfp_t highmem_mask = (gfp_mask & (GFP_DMA | GFP_DMA32)) ?
-					0 :
-					__GFP_HIGHMEM;
+					0 : __GFP_HIGHMEM;
 
-	nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
+	nr_pages = size >> shift;
 	array_size = (nr_pages * sizeof(struct page *));
 
 	area->nr_pages = nr_pages;
@@ -2568,10 +2620,8 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	for (i = 0; i < area->nr_pages; i++) {
 		struct page *page;
 
-		if (node == NUMA_NO_NODE)
-			page = alloc_page(alloc_mask|highmem_mask);
-		else
-			page = alloc_pages_node(node, alloc_mask|highmem_mask, 0);
+		page = alloc_pages_node(node,
+				alloc_mask|highmem_mask, page_shift);
 
 		if (unlikely(!page)) {
 			/* Successfully allocated i pages, free them in __vunmap() */
@@ -2583,8 +2633,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 			cond_resched();
 	}
 
-	if (map_vm_area(area, prot, pages))
+	if (vmap_hpages_range(addr, addr + size, prot, pages, page_shift) < 0)
 		goto fail;
+
 	return area->addr;
 
 fail:
@@ -2618,22 +2669,39 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 			pgprot_t prot, unsigned long vm_flags, int node,
 			const void *caller)
 {
-	struct vm_struct *area;
+	struct vm_struct *area = NULL;
 	void *addr;
 	unsigned long real_size = size;
+	unsigned long real_align = align;
+	unsigned int shift = PAGE_SHIFT;
 
 	size = PAGE_ALIGN(size);
 	if (!size || (size >> PAGE_SHIFT) > totalram_pages())
 		goto fail;
 
+	if (IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP)) {
+		unsigned long size_per_node;
+
+		size_per_node = size;
+		if (node == NUMA_NO_NODE)
+			size_per_node /= num_online_nodes();
+		if (size_per_node >= PMD_SIZE)
+			shift = PMD_SHIFT;
+	}
+again:
+	align = max(real_align, 1UL << shift);
+	size = ALIGN(real_size, align);
+
 	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
 				vm_flags, start, end, node, gfp_mask, caller);
 	if (!area)
 		goto fail;
 
+	area->page_shift = shift - PAGE_SHIFT;
+
 	addr = __vmalloc_area_node(area, gfp_mask, prot, node);
 	if (!addr)
-		return NULL;
+		goto fail;
 
 	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
@@ -2647,8 +2715,16 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	return addr;
 
 fail:
-	warn_alloc(gfp_mask, NULL,
+	if (shift == PMD_SHIFT) {
+		shift = PAGE_SHIFT;
+		goto again;
+	}
+
+	if (!area) {
+		/* Warn for area allocation, page allocations already warn */
+		warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure: %lu bytes", real_size);
+	}
 	return NULL;
 }
 
-- 
2.20.1