[PATCH] core remove PageReserved

Remove PageReserved() calls from core code by tightening VM_RESERVED handling in mm/ to cover PageReserved functionality. PageReserved special casing is removed from get_page and put_page. All setting and clearing of PageReserved is retained, and it is now flagged in the page_alloc checks to help ensure we don't introduce any refcount based freeing of Reserved pages. MAP_PRIVATE, PROT_WRITE of VM_RESERVED regions is tentatively being deprecated. We never completely handled it correctly anyway, and is be reintroduced in future if required (Hugh has a proof of concept). Once PageReserved() calls are removed from kernel/power/swsusp.c, and all arch/ and driver code, the Set and Clear calls, and the PG_reserved bit can be trivially removed. Last real user of PageReserved is swsusp, which uses PageReserved to determine whether a struct page points to valid memory or not. This still needs to be addressed (a generic page_is_ram() should work). A last caveat: the ZERO_PAGE is now refcounted and managed with rmap (and thus mapcounted and count towards shared rss). These writes to the struct page could cause excessive cacheline bouncing on big systems. There are a number of ways this could be addressed if it is an issue. Signed-off-by: Nick Piggin <[email protected]> Refcount bug fix for filemap_xip.c Signed-off-by: Carsten Otte <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
yshchan · Oct 30, 2005 · b581003 · b581003
1 parent f9c98d0
commit b581003
Show file tree

Hide file tree

Showing 22 changed files with 218 additions and 134 deletions.
diff --git a/arch/ppc64/kernel/vdso.c b/arch/ppc64/kernel/vdso.c
@@ -176,13 +176,13 @@ static struct page * vdso_vma_nopage(struct vm_area_struct * vma,
 		return NOPAGE_SIGBUS;
 
 	/*
-	 * Last page is systemcfg, special handling here, no get_page() a
-	 * this is a reserved page
+	 * Last page is systemcfg.
 	 */
 	if ((vma->vm_end - address) <= PAGE_SIZE)
-		return virt_to_page(systemcfg);
+		pg = virt_to_page(systemcfg);
+	else
+		pg = virt_to_page(vbase + offset);
 
-	pg = virt_to_page(vbase + offset);
 	get_page(pg);
 	DBG(" ->page count: %d\n", page_count(pg));
 
@@ -259,7 +259,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack)
 	 * gettimeofday will be totally dead. It's fine to use that for setting
 	 * breakpoints in the vDSO code pages though
 	 */
-	vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+	vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_RESERVED;
 	vma->vm_flags |= mm->def_flags;
 	vma->vm_page_prot = protection_map[vma->vm_flags & 0x7];
 	vma->vm_ops = &vdso_vmops;
@@ -603,6 +603,8 @@ void __init vdso_init(void)
 		ClearPageReserved(pg);
 		get_page(pg);
 	}
+
+	get_page(virt_to_page(systemcfg));
 }
 
 int in_gate_area_no_task(unsigned long addr)

diff --git a/arch/sparc/mm/generic.c b/arch/sparc/mm/generic.c
@@ -73,6 +73,9 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 	int space = GET_IOSPACE(pfn);
 	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
 
+	/* See comment in mm/memory.c remap_pfn_range */
+	vma->vm_flags |= VM_IO | VM_RESERVED;
+
 	prot = __pgprot(pg_iobits);
 	offset -= from;
 	dir = pgd_offset(mm, from);

diff --git a/arch/sparc64/mm/generic.c b/arch/sparc64/mm/generic.c
@@ -127,6 +127,9 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 	int space = GET_IOSPACE(pfn);
 	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
 
+	/* See comment in mm/memory.c remap_pfn_range */
+	vma->vm_flags |= VM_IO | VM_RESERVED;
+
 	prot = __pgprot(pg_iobits);
 	offset -= from;
 	dir = pgd_offset(mm, from);

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
@@ -1886,13 +1886,17 @@ st_unmap_user_pages(struct scatterlist *sgl, const unsigned int nr_pages,
 	int i;
 
 	for (i=0; i < nr_pages; i++) {
-		if (dirtied && !PageReserved(sgl[i].page))
-			SetPageDirty(sgl[i].page);
-		/* unlock_page(sgl[i].page); */
+		struct page *page = sgl[i].page;
+
+		/* XXX: just for debug. Remove when PageReserved is removed */
+		BUG_ON(PageReserved(page));
+		if (dirtied)
+			SetPageDirty(page);
+		/* unlock_page(page); */
 		/* FIXME: cache flush missing for rw==READ
 		 * FIXME: call the correct reference counting function
 		 */
-		page_cache_release(sgl[i].page);
+		page_cache_release(page);
 	}
 
 	return 0;

diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
@@ -4526,12 +4526,16 @@ static int sgl_unmap_user_pages(struct scatterlist *sgl, const unsigned int nr_p
 	int i;
 
 	for (i=0; i < nr_pages; i++) {
-		if (dirtied && !PageReserved(sgl[i].page))
-			SetPageDirty(sgl[i].page);
+		struct page *page = sgl[i].page;
+
+		/* XXX: just for debug. Remove when PageReserved is removed */
+		BUG_ON(PageReserved(page));
+		if (dirtied)
+			SetPageDirty(page);
 		/* FIXME: cache flush missing for rw==READ
 		 * FIXME: call the correct reference counting function
 		 */
-		page_cache_release(sgl[i].page);
+		page_cache_release(page);
 	}
 
 	return 0;

diff --git a/fs/direct-io.c b/fs/direct-io.c
@@ -162,14 +162,16 @@ static int dio_refill_pages(struct dio *dio)
 	up_read(&current->mm->mmap_sem);
 
 	if (ret < 0 && dio->blocks_available && (dio->rw == WRITE)) {
+		struct page *page = ZERO_PAGE(dio->curr_user_address);
 		/*
 		 * A memory fault, but the filesystem has some outstanding
 		 * mapped blocks.  We need to use those blocks up to avoid
 		 * leaking stale data in the file.
 		 */
 		if (dio->page_errors == 0)
 			dio->page_errors = ret;
-		dio->pages[0] = ZERO_PAGE(dio->curr_user_address);
+		page_cache_get(page);
+		dio->pages[0] = page;
 		dio->head = 0;
 		dio->tail = 1;
 		ret = 0;

diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -157,7 +157,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
-#define VM_RESERVED	0x00080000	/* Don't unmap it from swap_out */
+#define VM_RESERVED	0x00080000	/* Pages managed in a special way */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
@@ -338,7 +338,7 @@ static inline void get_page(struct page *page)
 
 static inline void put_page(struct page *page)
 {
-	if (!PageReserved(page) && put_page_testzero(page))
+	if (put_page_testzero(page))
 		__page_cache_release(page);
 }
 
@@ -723,6 +723,7 @@ void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);
 
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
 		int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);
+void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long);
 
 int __set_page_dirty_buffers(struct page *page);
 int __set_page_dirty_nobuffers(struct page *page);

diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
@@ -578,15 +578,23 @@ static int save_highmem_zone(struct zone *zone)
 			continue;
 		page = pfn_to_page(pfn);
 		/*
-		 * This condition results from rvmalloc() sans vmalloc_32()
-		 * and architectural memory reservations. This should be
-		 * corrected eventually when the cases giving rise to this
-		 * are better understood.
+		 * PageReserved results from rvmalloc() sans vmalloc_32()
+		 * and architectural memory reservations.
+		 *
+		 * rvmalloc should not cause this, because all implementations
+		 * appear to always be using vmalloc_32 on architectures with
+		 * highmem. This is a good thing, because we would like to save
+		 * rvmalloc pages.
+		 *
+		 * It appears to be triggered by pages which do not point to
+		 * valid memory (see arch/i386/mm/init.c:one_highpage_init(),
+		 * which sets PageReserved if the page does not point to valid
+		 * RAM.
+		 *
+		 * XXX: must remove usage of PageReserved!
 		 */
-		if (PageReserved(page)) {
-			printk("highmem reserved page?!\n");
+		if (PageReserved(page))
 			continue;
-		}
 		BUG_ON(PageNosave(page));
 		if (PageNosaveFree(page))
 			continue;
@@ -672,10 +680,9 @@ static int saveable(struct zone * zone, unsigned long * zone_pfn)
 		return 0;
 
 	page = pfn_to_page(pfn);
-	BUG_ON(PageReserved(page) && PageNosave(page));
 	if (PageNosave(page))
 		return 0;
-	if (PageReserved(page) && pfn_is_nosave(pfn)) {
+	if (pfn_is_nosave(pfn)) {
 		pr_debug("[nosave pfn 0x%lx]", pfn);
 		return 0;
 	}

diff --git a/mm/bootmem.c b/mm/bootmem.c
@@ -305,6 +305,7 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 				if (j + 16 < BITS_PER_LONG)
 					prefetchw(page + j + 16);
 				__ClearPageReserved(page + j);
+				set_page_count(page + j, 0);
 			}
 			__free_pages(page, order);
 			i += BITS_PER_LONG;

diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
@@ -174,6 +174,7 @@ __xip_unmap (struct address_space * mapping,
 	unsigned long address;
 	pte_t *pte;
 	pte_t pteval;
+	struct page *page = ZERO_PAGE(address);
 
 	spin_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
@@ -185,15 +186,17 @@ __xip_unmap (struct address_space * mapping,
 		 * We need the page_table_lock to protect us from page faults,
 		 * munmap, fork, etc...
 		 */
-		pte = page_check_address(ZERO_PAGE(address), mm,
-					 address);
+		pte = page_check_address(page, mm, address);
 		if (!IS_ERR(pte)) {
 			/* Nuke the page table entry. */
 			flush_cache_page(vma, address, pte_pfn(*pte));
 			pteval = ptep_clear_flush(vma, address, pte);
+			page_remove_rmap(page);
+			dec_mm_counter(mm, file_rss);
 			BUG_ON(pte_dirty(pteval));
 			pte_unmap(pte);
 			spin_unlock(&mm->page_table_lock);
+			page_cache_release(page);
 		}
 	}
 	spin_unlock(&mapping->i_mmap_lock);
@@ -228,7 +231,7 @@ xip_file_nopage(struct vm_area_struct * area,
 
 	page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0);
 	if (!IS_ERR(page)) {
-		return page;
+		goto out;
 	}
 	if (PTR_ERR(page) != -ENODATA)
 		return NULL;
@@ -249,6 +252,8 @@ xip_file_nopage(struct vm_area_struct * area,
 		page = ZERO_PAGE(address);
 	}
 
+out:
+	page_cache_get(page);
 	return page;
 }
 

diff --git a/mm/fremap.c b/mm/fremap.c
@@ -29,19 +29,20 @@ static inline void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 		return;
 	if (pte_present(pte)) {
 		unsigned long pfn = pte_pfn(pte);
+		struct page *page;
 
 		flush_cache_page(vma, addr, pfn);
 		pte = ptep_clear_flush(vma, addr, ptep);
-		if (pfn_valid(pfn)) {
-			struct page *page = pfn_to_page(pfn);
-			if (!PageReserved(page)) {
-				if (pte_dirty(pte))
-					set_page_dirty(page);
-				page_remove_rmap(page);
-				page_cache_release(page);
-				dec_mm_counter(mm, file_rss);
-			}
+		if (unlikely(!pfn_valid(pfn))) {
+			print_bad_pte(vma, pte, addr);
+			return;
 		}
+		page = pfn_to_page(pfn);
+		if (pte_dirty(pte))
+			set_page_dirty(page);
+		page_remove_rmap(page);
+		page_cache_release(page);
+		dec_mm_counter(mm, file_rss);
 	} else {
 		if (!pte_file(pte))
 			free_swap_and_cache(pte_to_swp_entry(pte));
@@ -65,6 +66,8 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	pgd_t *pgd;
 	pte_t pte_val;
 
+	BUG_ON(vma->vm_flags & VM_RESERVED);
+
 	pgd = pgd_offset(mm, addr);
 	spin_lock(&mm->page_table_lock);
 
@@ -125,6 +128,8 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 	pgd_t *pgd;
 	pte_t pte_val;
 
+	BUG_ON(vma->vm_flags & VM_RESERVED);
+
 	pgd = pgd_offset(mm, addr);
 	spin_lock(&mm->page_table_lock);
 

diff --git a/mm/madvise.c b/mm/madvise.c
@@ -126,7 +126,7 @@ static long madvise_dontneed(struct vm_area_struct * vma,
 			     unsigned long start, unsigned long end)
 {
 	*prev = vma;
-	if ((vma->vm_flags & VM_LOCKED) || is_vm_hugetlb_page(vma))
+	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_RESERVED))
 		return -EINVAL;
 
 	if (unlikely(vma->vm_flags & VM_NONLINEAR)) {