+Paul
> On Mar 25, 2022, at 5:06 PM, Edgecombe, Rick P <rick.p.edgecombe@xxxxxxxxx> wrote:
>
> On Fri, 2022-02-04 at 10:57 -0800, Song Liu wrote:
>> From: Song Liu <songliubraving@xxxxxx>
>>
>> This enables module_alloc() to allocate huge page for 2MB+ requests.
>> To check the difference of this change, we need enable config
>> CONFIG_PTDUMP_DEBUGFS, and call module_alloc(2MB). Before the change,
>> /sys/kernel/debug/page_tables/kernel shows pte for this map. With the
>> change, /sys/kernel/debug/page_tables/ show pmd for thie map.
>>
>> Signed-off-by: Song Liu <songliubraving@xxxxxx>
>> ---
>> arch/x86/Kconfig | 1 +
>> 1 file changed, 1 insertion(+)
>
> Hi,
>
> I just saw this upstream today. Glad to see this functionality, but I
> think turning on huge vmalloc pages for x86 needs a bit more. I’ll
> describe a couple possible failure modes I haven’t actually tested.
>
> One problem is that the direct map permission reset part in vmalloc
> assumes any special permissioned pages are mapped 4k on the direct map.
> Otherwise the operation could fail to reset a page RW if a PTE page
> allocation fails when it tries to split the page to toggle a 4k sized
> region NP/P. If you are not familiar, x86 CPA generally leaves the
> direct map page sizes mirroring the primary alias (vmalloc). So once
> vmalloc has huge pages, the special permissioned direct map aliases
> will have them too. This limitation of HAVE_ARCH_HUGE_VMALLOC is
> actually hinted about in the Kconfig comments, but I guess it wasn’t
> specific that x86 has these properties.
>
> I think to make the vmalloc resetting part safe:
> 1. set_direct_map_invalid/default() needs to support multiple pages
> like this[0].
> 2. vm_remove_mappings() needs to call them with the correct page size
> in the hpage case so they don't cause a split[1].
> 3. Then hibernate needs to be blocked during this operation so it
> doesn’t encounter the now sometimes huge NP pages, which it can’t
> handle. Not sure what the right way to do this is, but potentially like
> in the diff below[1].
>
> Another problem is that CPA will sometimes now split pages of vmalloc
> mappings in cases where it sets a region of an allocation to a
> different permission than the rest (for example regular modules calling
> set_memory_x() on the text section). Before this change, these couldn’t
> fail since the module space mapping would never require a split.
> Modules doesn’t check for failure there, so I’m thinking now it would
> proceed to try to execute NX memory if the split failed. It could only
> happen on allocation of especially large modules. Maybe it should just
> be avoided for now by having regular module allocations pass
> VM_NO_HUGE_VMAP on x86. And BPF could call __vmalloc_node_range()
> directly to get 2MB vmallocs.
I like this direction. But I am afraid this is not enough. Using
VM_NO_HUGE_VMAP in module_alloc() will make sure we don't allocate
huge pages for modules. But other users of __vmalloc_node_range(),
such as vzalloc in Paul's report, may still hit the issue.
Maybe we need another flag VM_FORCE_HUGE_VMAP that bypasses
vmap_allow_huge check. Something like the diff below.
Would this work?
Thanks,
Song
diff --git i/include/linux/vmalloc.h w/include/linux/vmalloc.h
index 3b1df7da402d..a639405dab99 100644
--- i/include/linux/vmalloc.h
+++ w/include/linux/vmalloc.h
@@ -27,6 +27,7 @@ struct notifier_block; /* in notifier.h */
#define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */
#define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */
#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */
+#define VM_FORCE_HUGE_VMAP 0x00000800 /* force PMD_SIZE mapping (bypass vmap_allow_huge check) */
#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
!defined(CONFIG_KASAN_VMALLOC)
diff --git i/kernel/bpf/core.c w/kernel/bpf/core.c
index 13e9dbeeedf3..3cd0ff66d39c 100644
--- i/kernel/bpf/core.c
+++ w/kernel/bpf/core.c
@@ -851,13 +851,22 @@ static LIST_HEAD(pack_list);
#define BPF_HPAGE_MASK PAGE_MASK
#endif
+static void *bpf_prog_pack_vmalloc(unsigned long size)
+{
+ return __vmalloc_node_range(size, MODULE_ALIGN,
+ MODULES_VADDR + get_module_load_offset(),
+ MODULES_END, gfp_mask, PAGE_KERNEL,
+ VM_DEFER_KMEMLEAK | VM_FORCE_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 +890,7 @@ 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 i/mm/vmalloc.c w/mm/vmalloc.c
index e163372d3967..df2dd6779fa8 100644
--- i/mm/vmalloc.c
+++ w/mm/vmalloc.c
@@ -3106,7 +3106,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
return NULL;
}
- if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) {
+ if ((vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) ||
+ (vm_flags & VM_FORCE_HUGE_VMAP)) {
unsigned long size_per_node;
/*
>
> [0]
> https://lore.kernel.org/lkml/20210208084920.2884-5-rppt@xxxxxxxxxx/#t
>
> [1] Untested, but something like this possibly:
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 99e0f3e8d1a5..97c4ca3a29b1 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -42,6 +42,7 @@
> #include <linux/sched/mm.h>
> #include <asm/tlbflush.h>
> #include <asm/shmparam.h>
> +#include <linux/suspend.h>
>
> #include "internal.h"
> #include "pgalloc-track.h"
> @@ -2241,7 +2242,7 @@ EXPORT_SYMBOL(vm_map_ram);
>
> static struct vm_struct *vmlist __initdata;
>
> -static inline unsigned int vm_area_page_order(struct vm_struct *vm)
> +static inline unsigned int vm_area_page_order(const struct vm_struct
> *vm)
> {
> #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
> return vm->page_order;
> @@ -2560,12 +2561,12 @@ struct vm_struct *remove_vm_area(const void
> *addr)
> static inline void set_area_direct_map(const struct vm_struct *area,
> int (*set_direct_map)(struct
> page *page))
> {
> + unsigned int page_order = vm_area_page_order(area);
> int i;
>
> - /* HUGE_VMALLOC passes small pages to set_direct_map */
> - for (i = 0; i < area->nr_pages; i++)
> + for (i = 0; i < area->nr_pages; i += 1U << page_order)
> if (page_address(area->pages[i]))
> - set_direct_map(area->pages[i]);
> + set_direct_map(area->pages[i], 1U <<
> page_order);
> }
>
> /* Handle removing and resetting vm mappings related to the vm_struct.
> */
> @@ -2592,6 +2593,10 @@ static void vm_remove_mappings(struct vm_struct
> *area, int deallocate_pages)
> return;
> }
>
> + /* Hibernate can't handle large NP pages */
> + if (page_order)
> + lock_system_sleep();
> +
> /*
> * If execution gets here, flush the vm mapping and reset the
> direct
> * map. Find the start and end range of the direct mappings to
> make sure
> @@ -2617,6 +2622,9 @@ static void vm_remove_mappings(struct vm_struct
> *area, int deallocate_pages)
> set_area_direct_map(area, set_direct_map_invalid_noflush);
> _vm_unmap_aliases(start, end, flush_dmap);
> set_area_direct_map(area, set_direct_map_default_noflush);
> +
> + if (page_order)
> + unlock_system_sleep();
> }
>
> static void __vunmap(const void *addr, int deallocate_pages)
