Re: RFC: Transparent Hugepage support

[Andrea Arcangeli <aarcange@redhat.com>]

On Tue, Oct 27, 2009 at 08:30:07PM +0100, Andrea Arcangeli wrote:
> generated by mnmap(last4k) I also think I found a minor bug in munmap
> if a partial part of the 2M page is unmapped (currently I'm afraid I'm

Here the incremental fix if somebody is running the patch (this also
frees the page after tlb flush, during development I had to call
put_page to debug something and I forgot to replace it back to
tlb_remove_page ;). In the meantime I'll try to split the patch into
more self contained pieces for easier review (including the kvm patch
to build 3level NPT/EPT).

Then I will continue working on the daemon that will
collapse_huge_page in the madvise(MADV_HUGEPAGE) regions.

This printed 0 before, now it prints 0xff as with transparent hugepage
disabled.

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sys/mman.h>

#define SIZE (2*1024*1024)

int main()
{
	char *p = malloc(SIZE*2-1);
	p = (char *)((unsigned long)(p + SIZE - 1) & ~(SIZE-1));
	*p = 0xff;
	munmap(p+SIZE-4096, 4096);
	printf("%x\n", *(unsigned char *)p);

	return 0;
}


Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
---

diff --git a/include/linux/mm.h b/include/linux/mm.h
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -850,6 +850,9 @@ extern struct page *follow_trans_huge_pm
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
+extern int zap_pmd_trans_huge(struct mmu_gather *tlb,
+			      struct vm_area_struct *vma,
+			      pmd_t *pmd);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			  pmd_t *dst_pmd, pmd_t *src_pmd,
diff --git a/mm/Kconfig b/mm/Kconfig
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -292,8 +292,9 @@ config NOMMU_INITIAL_TRIM_EXCESS
 	  See Documentation/nommu-mmap.txt for more information.
 
 config TRANSPARENT_HUGEPAGE
-	bool "Transparent Hugepage support"
+	bool "Transparent Hugepage support" if EMBEDDED
 	depends on X86_64
+	default y
 	help
 	  Transparent Hugepages allows the kernel to use huge pages and
 	  huge tlb transparently to the applications whenever possible.
@@ -302,4 +303,4 @@ config TRANSPARENT_HUGEPAGE
 	  allocation, by reducing the number of tlb misses and by speeding
 	  up the pagetable walking.
 
-	  If unsure, say N.
+	  If memory constrained on embedded, you may want to say N.
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -12,6 +12,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
+#include <asm/tlb.h>
 #include <asm/pgalloc.h>
 #include "internal.h"
 
@@ -374,3 +375,37 @@ struct page *follow_trans_huge_pmd(struc
 out:
 	return page;
 }
+
+int zap_pmd_trans_huge(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		       pmd_t *pmd)
+{
+	int ret = 0;
+
+	spin_lock(&tlb->mm->page_table_lock);
+	if (likely(pmd_trans_huge(*pmd))) {
+		if (unlikely(pmd_trans_frozen(*pmd))) {
+			spin_unlock(&tlb->mm->page_table_lock);
+			wait_split_huge_page(vma->anon_vma,
+					     pmd);
+		} else {
+			struct page *page;
+			pgtable_t pgtable;
+			pgtable = get_pmd_huge_pte(tlb->mm);
+			page = pfn_to_page(pmd_pfn(*pmd));
+			VM_BUG_ON(!PageCompound(page));
+			pmd_clear(pmd);
+			spin_unlock(&tlb->mm->page_table_lock);
+			page_remove_rmap(page);
+			VM_BUG_ON(page_mapcount(page) < 0);
+			add_mm_counter(tlb->mm, anon_rss,
+				       -1<<(HPAGE_SHIFT-
+					    PAGE_SHIFT));
+			tlb_remove_page(tlb, page);
+			pte_free(tlb->mm, pgtable);
+			ret = 1;
+		}
+	} else
+		spin_unlock(&tlb->mm->page_table_lock);
+
+	return ret;
+}
diff --git a/mm/memory.c b/mm/memory.c
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -913,32 +913,12 @@ static inline unsigned long zap_pmd_rang
 	do {
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*pmd)) {
-			spin_lock(&tlb->mm->page_table_lock);
-			if (likely(pmd_trans_huge(*pmd))) {
-				if (unlikely(pmd_trans_frozen(*pmd))) {
-					spin_unlock(&tlb->mm->page_table_lock);
-					wait_split_huge_page(vma->anon_vma,
-							     pmd);
-				} else {
-					struct page *page;
-					pgtable_t pgtable;
-					pgtable = get_pmd_huge_pte(tlb->mm);
-					page = pfn_to_page(pmd_pfn(*pmd));
-					VM_BUG_ON(!PageCompound(page));
-					pmd_clear(pmd);
-					spin_unlock(&tlb->mm->page_table_lock);
-					page_remove_rmap(page);
-					VM_BUG_ON(page_mapcount(page) < 0);
-					add_mm_counter(tlb->mm, anon_rss,
-						       -1<<(HPAGE_SHIFT-
-							    PAGE_SHIFT));
-					put_page(page);
-					pte_free(tlb->mm, pgtable);
-					(*zap_work)--;
-					continue;
-				}
-			} else
-				spin_unlock(&tlb->mm->page_table_lock);
+			if (next-addr != HPAGE_SIZE)
+				split_huge_page_vma(vma, pmd);
+			else if (zap_pmd_trans_huge(tlb, vma, pmd)) {
+				(*zap_work)--;
+				continue;
+			}
 			/* fall through */
 		}
 		if (pmd_none_or_clear_bad(pmd)) {

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>