diff mbox series

[v5,8/8] mm/vmalloc: Hugepage vmalloc mappings

Message ID 20200821044427.736424-9-npiggin@gmail.com (mailing list archive)
State New, archived
Headers show
Series huge vmalloc mappings | expand

Commit Message

Nicholas Piggin Aug. 21, 2020, 4:44 a.m. UTC
On platforms that define HAVE_ARCH_HUGE_VMAP and support PMD vmaps,
vmalloc will attempt to allocate PMD-sized pages first, before falling
back to small pages.

Allocations which use something other than PAGE_KERNEL protections are
not permitted to use huge pages yet, not all callers expect this (e.g.,
module allocations vs strict module rwx).

This reduces TLB misses by nearly 30x on a `git diff` workload on a
2-node POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%.

This can result in more internal fragmentation and memory overhead for a
given allocation, an option nohugevmalloc is added to disable at boot.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 .../admin-guide/kernel-parameters.txt         |   2 +
 arch/Kconfig                                  |   4 +
 arch/powerpc/Kconfig                          |   1 +
 include/linux/vmalloc.h                       |   1 +
 mm/page_alloc.c                               |   4 +-
 mm/vmalloc.c                                  | 188 +++++++++++++-----
 6 files changed, 152 insertions(+), 48 deletions(-)

Comments

kernel test robot Aug. 21, 2020, 7:17 a.m. UTC | #1
Hi Nicholas,

I love your patch! Yet something to improve:

[auto build test ERROR on powerpc/next]
[also build test ERROR on arm64/for-next/core tip/x86/mm linus/master v5.9-rc1]
[cannot apply to hnaz-linux-mm/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Nicholas-Piggin/huge-vmalloc-mappings/20200821-124543
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: riscv-allnoconfig (attached as .config)
compiler: riscv64-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=riscv 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

   riscv64-linux-ld: mm/page_alloc.o: in function `.L1578':
>> page_alloc.c:(.init.text+0x11a4): undefined reference to `find_vm_area'

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
kernel test robot Aug. 21, 2020, 11:27 a.m. UTC | #2
Hi Nicholas,

I love your patch! Yet something to improve:

[auto build test ERROR on powerpc/next]
[also build test ERROR on linus/master v5.9-rc1 next-20200821]
[cannot apply to hnaz-linux-mm/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Nicholas-Piggin/huge-vmalloc-mappings/20200821-124543
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: sh-allmodconfig (attached as .config)
compiler: sh4-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=sh 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

   sh4-linux-ld: mm/page_alloc.o: in function `alloc_large_system_hash':
>> (.init.text+0x1818): undefined reference to `find_vm_area'

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff mbox series

Patch

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bdc1f33fd3d1..6f0b41289a90 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3190,6 +3190,8 @@ 
 
 	nohugeiomap	[KNL,X86,PPC] Disable kernel huge I/O mappings.
 
+	nohugevmalloc	[PPC] Disable kernel huge vmalloc mappings.
+
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493..b2b89d629317 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -616,6 +616,10 @@  config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 config HAVE_ARCH_HUGE_VMAP
 	bool
 
+config HAVE_ARCH_HUGE_VMALLOC
+	depends on HAVE_ARCH_HUGE_VMAP
+	bool
+
 config ARCH_WANT_HUGE_PMD_SHARE
 	bool
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 95dfd8ef3d4b..044e5a94967a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -175,6 +175,7 @@  config PPC
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
+	select HAVE_ARCH_HUGE_VMALLOC		if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if PPC32 && PPC_PAGE_SHIFT <= 14
 	select HAVE_ARCH_KASAN_VMALLOC		if PPC32 && PPC_PAGE_SHIFT <= 14
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index e3590e93bfff..8f25dbaca0a1 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -58,6 +58,7 @@  struct vm_struct {
 	unsigned long		size;
 	unsigned long		flags;
 	struct page		**pages;
+	unsigned int		page_order;
 	unsigned int		nr_pages;
 	phys_addr_t		phys_addr;
 	const void		*caller;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0e2bab486fea..d785e5335529 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8102,6 +8102,7 @@  void *__init alloc_large_system_hash(const char *tablename,
 	void *table = NULL;
 	gfp_t gfp_flags;
 	bool virt;
+	bool huge;
 
 	/* allow the kernel cmdline to have a say */
 	if (!numentries) {
@@ -8169,6 +8170,7 @@  void *__init alloc_large_system_hash(const char *tablename,
 		} else if (get_order(size) >= MAX_ORDER || hashdist) {
 			table = __vmalloc(size, gfp_flags);
 			virt = true;
+			huge = (find_vm_area(table)->page_order > 0);
 		} else {
 			/*
 			 * If bucketsize is not a power-of-two, we may free
@@ -8185,7 +8187,7 @@  void *__init alloc_large_system_hash(const char *tablename,
 
 	pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
 		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
-		virt ? "vmalloc" : "linear");
+		virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear");
 
 	if (_hash_shift)
 		*_hash_shift = log2qty;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4e5cb7c7f780..564d7497e551 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -45,6 +45,19 @@ 
 #include "internal.h"
 #include "pgalloc-track.h"
 
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+static bool __ro_after_init vmap_allow_huge = true;
+
+static int __init set_nohugevmalloc(char *str)
+{
+	vmap_allow_huge = false;
+	return 0;
+}
+early_param("nohugevmalloc", set_nohugevmalloc);
+#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+static const bool vmap_allow_huge = false;
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+
 bool is_vmalloc_addr(const void *x)
 {
 	unsigned long addr = (unsigned long)x;
@@ -468,31 +481,12 @@  static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long en
 	return 0;
 }
 
-/**
- * map_kernel_range_noflush - map kernel VM area with the specified pages
- * @addr: start of the VM area to map
- * @size: size of the VM area to map
- * @prot: page protection flags to use
- * @pages: pages to map
- *
- * Map PFN_UP(@size) pages at @addr.  The VM area @addr and @size specify should
- * have been allocated using get_vm_area() and its friends.
- *
- * NOTE:
- * This function does NOT do any cache flushing.  The caller is responsible for
- * calling flush_cache_vmap() on to-be-mapped areas before calling this
- * function.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int map_kernel_range_noflush(unsigned long addr, unsigned long size,
-			     pgprot_t prot, struct page **pages)
+static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages)
 {
 	unsigned long start = addr;
-	unsigned long end = addr + size;
-	unsigned long next;
 	pgd_t *pgd;
+	unsigned long next;
 	int err = 0;
 	int nr = 0;
 	pgtbl_mod_mask mask = 0;
@@ -514,6 +508,65 @@  int map_kernel_range_noflush(unsigned long addr, unsigned long size,
 	return 0;
 }
 
+static int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+	WARN_ON(page_shift < PAGE_SHIFT);
+
+	if (page_shift == PAGE_SHIFT) {
+		return vmap_small_pages_range_noflush(addr, end, prot, pages);
+	} else {
+		unsigned int i, nr = (end - addr) >> PAGE_SHIFT;
+
+		for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
+			int err;
+
+			err = vmap_range_noflush(addr, addr + (1UL << page_shift),
+						__pa(page_address(pages[i])), prot, page_shift);
+			if (err)
+				return err;
+
+			addr += 1UL << page_shift;
+		}
+
+		return 0;
+	}
+}
+
+static int vmap_pages_range(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+	int err;
+
+	err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
+	flush_cache_vmap(addr, end);
+	return err;
+}
+
+/**
+ * map_kernel_range_noflush - map kernel VM area with the specified pages
+ * @addr: start of the VM area to map
+ * @size: size of the VM area to map
+ * @prot: page protection flags to use
+ * @pages: pages to map
+ *
+ * Map PFN_UP(@size) pages at @addr.  The VM area @addr and @size specify should
+ * have been allocated using get_vm_area() and its friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing.  The caller is responsible for
+ * calling flush_cache_vmap() on to-be-mapped areas before calling this
+ * function.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int map_kernel_range_noflush(unsigned long addr, unsigned long size,
+			     pgprot_t prot, struct page **pages)
+{
+	return vmap_pages_range_noflush(addr, addr + size, prot, pages, PAGE_SHIFT);
+}
+
 int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
 		struct page **pages)
 {
@@ -2274,9 +2327,11 @@  static struct vm_struct *__get_vm_area_node(unsigned long size,
 	if (unlikely(!size))
 		return NULL;
 
-	if (flags & VM_IOREMAP)
-		align = 1ul << clamp_t(int, get_count_order_long(size),
-				       PAGE_SHIFT, IOREMAP_MAX_ORDER);
+	if (flags & VM_IOREMAP) {
+		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))
@@ -2391,6 +2446,7 @@  static inline void set_area_direct_map(const struct vm_struct *area,
 {
 	int i;
 
+	/* HUGE_VMALLOC passes small pages to set_direct_map */
 	for (i = 0; i < area->nr_pages; i++)
 		if (page_address(area->pages[i]))
 			set_direct_map(area->pages[i]);
@@ -2424,11 +2480,12 @@  static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
 	 * map. Find the start and end range of the direct mappings to make sure
 	 * the vm_unmap_aliases() flush includes the direct map.
 	 */
-	for (i = 0; i < area->nr_pages; i++) {
+	for (i = 0; i < area->nr_pages; i += 1U << area->page_order) {
 		unsigned long addr = (unsigned long)page_address(area->pages[i]);
 		if (addr) {
+			unsigned long page_size = PAGE_SIZE << area->page_order;
 			start = min(addr, start);
-			end = max(addr + PAGE_SIZE, end);
+			end = max(addr + page_size, end);
 			flush_dmap = 1;
 		}
 	}
@@ -2471,11 +2528,11 @@  static void __vunmap(const void *addr, int deallocate_pages)
 	if (deallocate_pages) {
 		int i;
 
-		for (i = 0; i < area->nr_pages; i++) {
+		for (i = 0; i < area->nr_pages; i += 1U << area->page_order) {
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
-			__free_pages(page, 0);
+			__free_pages(page, area->page_order);
 		}
 		atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
 
@@ -2614,9 +2671,12 @@  void *vmap(struct page **pages, unsigned int count,
 EXPORT_SYMBOL(vmap);
 
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
-				 pgprot_t prot, int node)
+				 pgprot_t prot, unsigned int page_shift, int node)
 {
 	struct page **pages;
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long size = get_vm_area_size(area);
+	unsigned int page_order = 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;
@@ -2624,7 +2684,7 @@  static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 					0 :
 					__GFP_HIGHMEM;
 
-	nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
+	nr_pages = size >> PAGE_SHIFT;
 	array_size = (nr_pages * sizeof(struct page *));
 
 	/* Please note that the recursion is strictly bounded. */
@@ -2643,29 +2703,29 @@  static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 	area->pages = pages;
 	area->nr_pages = nr_pages;
+	area->page_order = page_order;
 
-	for (i = 0; i < area->nr_pages; i++) {
+	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
 		struct page *page;
+		int p;
 
-		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_order);
 		if (unlikely(!page)) {
 			/* Successfully allocated i pages, free them in __vunmap() */
 			area->nr_pages = i;
 			atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 			goto fail;
 		}
-		area->pages[i] = page;
+
+		for (p = 0; p < (1U << page_order); p++)
+			area->pages[i + p] = page + p;
+
 		if (gfpflags_allow_blocking(gfp_mask))
 			cond_resched();
 	}
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 
-	if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area),
-			prot, pages) < 0)
+	if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0)
 		goto fail;
 
 	return area->addr;
@@ -2673,7 +2733,7 @@  static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 fail:
 	warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure, allocated %ld of %ld bytes",
-			  (area->nr_pages*PAGE_SIZE), area->size);
+			  (area->nr_pages*PAGE_SIZE), size);
 	__vfree(area->addr);
 	return NULL;
 }
@@ -2704,19 +2764,42 @@  void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	struct vm_struct *area;
 	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;
 
-	area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED |
+	if (vmap_allow_huge && (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))) {
+		unsigned long size_per_node;
+
+		/*
+		 * Try huge pages. Only try for PAGE_KERNEL allocations,
+		 * others like modules don't yet expect huge pages in
+		 * their allocations due to apply_to_page_range not
+		 * supporting them.
+		 */
+
+		size_per_node = size;
+		if (node == NUMA_NO_NODE)
+			size_per_node /= num_online_nodes();
+		if (size_per_node >= PMD_SIZE) {
+			shift = PMD_SHIFT;
+			align = max(real_align, 1UL << shift);
+			size = ALIGN(real_size, 1UL << shift);
+		}
+	}
+
+again:
+	size = PAGE_ALIGN(size);
+	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
 				vm_flags, start, end, node, gfp_mask, caller);
 	if (!area)
 		goto fail;
 
-	addr = __vmalloc_area_node(area, gfp_mask, prot, node);
+	addr = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
 	if (!addr)
-		return NULL;
+		goto fail;
 
 	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
@@ -2730,8 +2813,19 @@  void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	return addr;
 
 fail:
-	warn_alloc(gfp_mask, NULL,
+	if (shift > PAGE_SHIFT) {
+		free_vm_area(area);
+		shift = PAGE_SHIFT;
+		align = real_align;
+		size = real_size;
+		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;
 }
 
@@ -3730,7 +3824,7 @@  static int s_show(struct seq_file *m, void *p)
 		seq_printf(m, " %pS", v->caller);
 
 	if (v->nr_pages)
-		seq_printf(m, " pages=%d", v->nr_pages);
+		seq_printf(m, " pages=%d order=%d", v->nr_pages, v->page_order);
 
 	if (v->phys_addr)
 		seq_printf(m, " phys=%pa", &v->phys_addr);