Re: [PATCH v9 bpf-next 1/9] x86/Kconfig: select HAVE_ARCH_HUGE_VMALLOC with HAVE_ARCH_HUGE_VMAP

[Song Liu <songliubraving@fb.com>]

> On Mar 29, 2022, at 2:36 PM, Edgecombe, Rick P <rick.p.edgecombe@intel.com> wrote:
> 
> On Tue, 2022-03-29 at 19:13 +0000, Song Liu wrote:
>>> 
>>> I don't think we should tie this to vmap_allow_huge by definition.
>>> Also, what it does is try 2MB pages for allocations larger than
>>> 2MB.
>>> For smaller allocations it doesn't try or "prefer" them.
>> 
>> How about something like:
>> 
>> #define VM_TRY_HUGE_VMAP        0x00001000      /* try PMD_SIZE
>> mapping if size-per-node >= PMD_SIZE */
> 
> Seems reasonable name. I don't know if "size-per-node >= PMD_SIZE" is
> going to be useful information. Maybe something like:
> 
> /* Allow for huge pages on HAVE_ARCH_HUGE_VMALLOC_FLAG arch's */

Sounds great. I updated the version based on this (below). I will split it
into two patches, I guess. 

@Paul, could you please test whether this version fixes the issue you were
seeing?

Thanks,
Song



diff --git a/arch/Kconfig b/arch/Kconfig
index 84bc1de02720..0fb2bd5fd1f8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -858,6 +858,15 @@ config HAVE_ARCH_HUGE_VMALLOC
 	depends on HAVE_ARCH_HUGE_VMAP
 	bool
 
+#
+# HAVE_ARCH_HUGE_VMALLOC_FLAG allows users of __vmalloc_node_range to allocate
+# huge page without HAVE_ARCH_HUGE_VMALLOC. To allocate huge pages, the user
+# need to call __vmalloc_node_range with VM_TRY_HUGE_VMAP.
+#
+config HAVE_ARCH_HUGE_VMALLOC_FLAG
+	depends on HAVE_ARCH_HUGE_VMAP
+	bool
+
 config ARCH_WANT_HUGE_PMD_SHARE
 	bool
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7340d9f01b62..e64f00415575 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -45,7 +45,7 @@ config FORCE_DYNAMIC_FTRACE
 	 in order to test the non static function tracing in the
 	 generic code, as other architectures still use it. But we
 	 only need to keep it around for x86_64. No need to keep it
-	 for x86_32. For x86_32, force DYNAMIC_FTRACE. 
+	 for x86_32. For x86_32, force DYNAMIC_FTRACE.
 #
 # Arch settings
 #
@@ -161,7 +161,7 @@ config X86
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
-	select HAVE_ARCH_HUGE_VMALLOC		if X86_64
+	select HAVE_ARCH_HUGE_VMALLOC_FLAG	if X86_64
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN			if X86_64
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 3b1df7da402d..a48d0690b66f 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -35,6 +35,11 @@ struct notifier_block;		/* in notifier.h */
 #define VM_DEFER_KMEMLEAK	0
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG
+#define VM_TRY_HUGE_VMAP	0x00001000	/* Allow for huge pages on HAVE_ARCH_HUGE_VMALLOC_FLAG arch's */
+#else
+#define VM_TRY_HUGE_VMAP	0
+#endif
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*
@@ -51,7 +56,7 @@ struct vm_struct {
 	unsigned long		size;
 	unsigned long		flags;
 	struct page		**pages;
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
 	unsigned int		page_order;
 #endif
 	unsigned int		nr_pages;
@@ -225,7 +230,7 @@ static inline bool is_vm_area_hugepages(const void *addr)
 	 * prevents that. This only indicates the size of the physical page
 	 * allocated in the vmalloc layer.
 	 */
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
 	return find_vm_area(addr)->page_order > 0;
 #else
 	return false;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 13e9dbeeedf3..5659677b18f3 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -851,13 +851,28 @@ static LIST_HEAD(pack_list);
 #define BPF_HPAGE_MASK PAGE_MASK
 #endif
 
+static void *bpf_prog_pack_vmalloc(unsigned long size)
+{
+#if defined(MODULES_VADDR)
+	unsigned long start = MODULES_VADDR;
+	unsigned long end = MODULES_END;
+#else
+	unsigned long start = VMALLOC_START;
+	unsigned long end = VMALLOC_END;
+#endif
+
+	return __vmalloc_node_range(size, PAGE_SIZE, start, end, GFP_KERNEL, PAGE_KERNEL,
+				    VM_DEFER_KMEMLEAK | VM_TRY_HUGE_VMAP,
+				    NUMA_NO_NODE, __builtin_return_address(0));
+}
+
 static size_t select_bpf_prog_pack_size(void)
 {
 	size_t size;
 	void *ptr;
 
 	size = BPF_HPAGE_SIZE * num_online_nodes();
-	ptr = module_alloc(size);
+	ptr = bpf_prog_pack_vmalloc(size);
 
 	/* Test whether we can get huge pages. If not just use PAGE_SIZE
 	 * packs.
@@ -881,7 +896,7 @@ static struct bpf_prog_pack *alloc_new_pack(void)
 		       GFP_KERNEL);
 	if (!pack)
 		return NULL;
-	pack->ptr = module_alloc(bpf_prog_pack_size);
+	pack->ptr = bpf_prog_pack_vmalloc(bpf_prog_pack_size);
 	if (!pack->ptr) {
 		kfree(pack);
 		return NULL;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e163372d3967..179200bce285 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -46,7 +46,7 @@
 #include "internal.h"
 #include "pgalloc-track.h"
 
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
 static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1;
 
 static int __init set_nohugeiomap(char *str)
@@ -55,11 +55,11 @@ static int __init set_nohugeiomap(char *str)
 	return 0;
 }
 early_param("nohugeiomap", set_nohugeiomap);
-#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+#else /* CONFIG_HAVE_ARCH_HUGE_VMAP || CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG */
 static const unsigned int ioremap_max_page_shift = PAGE_SHIFT;
-#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP || CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG*/
 
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
 static bool __ro_after_init vmap_allow_huge = true;
 
 static int __init set_nohugevmalloc(char *str)
@@ -582,8 +582,9 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
 
 	WARN_ON(page_shift < PAGE_SHIFT);
 
-	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
-			page_shift == PAGE_SHIFT)
+	if ((!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) &&
+	     !IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG)) ||
+	    (page_shift == PAGE_SHIFT))
 		return vmap_small_pages_range_noflush(addr, end, prot, pages);
 
 	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
@@ -2252,7 +2253,7 @@ static struct vm_struct *vmlist __initdata;
 
 static inline unsigned int vm_area_page_order(struct vm_struct *vm)
 {
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
 	return vm->page_order;
 #else
 	return 0;
@@ -2261,7 +2262,7 @@ static inline unsigned int vm_area_page_order(struct vm_struct *vm)
 
 static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order)
 {
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
 	vm->page_order = order;
 #else
 	BUG_ON(order != 0);
@@ -3056,6 +3057,15 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	return NULL;
 }
 
+static bool vmalloc_try_huge_page(unsigned long vm_flags)
+{
+	if (!vmap_allow_huge || (vm_flags & VM_NO_HUGE_VMAP))
+		return false;
+
+	/* VM_TRY_HUGE_VMAP only works for CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG */
+	return vm_flags & VM_TRY_HUGE_VMAP;
+}
+
 /**
  * __vmalloc_node_range - allocate virtually contiguous memory
  * @size:		  allocation size
@@ -3106,7 +3116,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 		return NULL;
 	}
 
-	if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) {
+	if (vmalloc_try_huge_page(vm_flags)) {
 		unsigned long size_per_node;
 
 		/*