pagemap: remove file header

diff -puN fs/proc/task_mmu.c~pagemap-no-header fs/proc/task_mmu.c
@@ -653,12 +653,12 @@ static ssize_t pagemap_read(struct file 
 		goto out;
 
 	ret = -EIO;
-	svpfn = src / sizeof(unsigned long) - 1;
+	svpfn = src / sizeof(unsigned long);
 	addr = PAGE_SIZE * svpfn;
-	if ((svpfn + 1) * sizeof(unsigned long) != src)
+	if (svpfn * sizeof(unsigned long) != src)
 		goto out;
 	evpfn = min((src + count) / sizeof(unsigned long),
-		    ((~0UL) >> PAGE_SHIFT) + 1) - 1;
+		    ((~0UL) >> PAGE_SHIFT) + 1);
 	count = (evpfn - svpfn) * sizeof(unsigned long);
 	end = PAGE_SIZE * evpfn;
 	//printk("src %ld svpfn %d evpfn %d count %d\n", src, svpfn, evpfn, count);

@@ -690,14 +690,6 @@ static ssize_t pagemap_read(struct file 
 	pm.count = count;
 	pm.out = (unsigned long __user *)buf;
 
-	if (svpfn == -1) {
-		add_to_pagemap(pm.next, 0, &pm);
-		put_user((char)(ntohl(1) != 1), buf);
-		put_user((char)PAGE_SHIFT, buf + 1);
-		put_user((char)sizeof(unsigned long), buf + 2);
-		put_user((char)sizeof(unsigned long), buf + 3);
-	}
-
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, pm.next);
 	while (pm.count > 0 && vma) {

diff -puN fs/proc/task_mmu.c~pagemap-use-PAGE_MASK fs/proc/task_mmu.c
@@ -669,9 +669,9 @@ static ssize_t pagemap_read(struct file 
 		goto out;
 
 	ret = -ENOMEM;
-	uaddr = (unsigned long)buf & ~(PAGE_SIZE-1);
+	uaddr = (unsigned long)buf & PAGE_MASK;
 	uend = (unsigned long)(buf + count);
-	pagecount = (uend - uaddr + PAGE_SIZE-1) / PAGE_SIZE;
+	pagecount = (uend - PAGE_ALIGN(uaddr)) / PAGE_SIZE;
 	pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		goto out_task;

diff -puN fs/proc/task_mmu.c~pagemap-use-ENTRY_SIZE fs/proc/task_mmu.c
@@ -560,14 +560,15 @@ struct pagemapread {
 	unsigned long __user *out;
 };
 
+#define PAGEMAP_ENTRY_SIZE_BYTES sizeof(unsigned long)
+
 static int add_to_pagemap(unsigned long addr, unsigned long pfn,
 			  struct pagemapread *pm)
 {
 	__put_user(pfn, pm->out);
 	pm->out++;
-	pm->pos += sizeof(unsigned long);
-	pm->count -= sizeof(unsigned long);
-	pm->next = addr + PAGE_SIZE;
+	pm->pos += PAGEMAP_ENTRY_SIZE_BYTES;
+	pm->count -= PAGEMAP_ENTRY_SIZE_BYTES;
 	return 0;
 }
 

@@ -653,13 +654,13 @@ static ssize_t pagemap_read(struct file 
 		goto out;
 
 	ret = -EIO;
-	svpfn = src / sizeof(unsigned long);
+	svpfn = src / PAGEMAP_ENTRY_SIZE_BYTES;
 	addr = PAGE_SIZE * svpfn;
-	if (svpfn * sizeof(unsigned long) != src)
+	if (svpfn * PAGEMAP_ENTRY_SIZE_BYTES != src)
 		goto out;
 	evpfn = min((src + count) / sizeof(unsigned long),
 		    ((~0UL) >> PAGE_SHIFT) + 1);
-	count = (evpfn - svpfn) * sizeof(unsigned long);
+	count = (evpfn - svpfn) * PAGEMAP_ENTRY_SIZE_BYTES;
 	end = PAGE_SIZE * evpfn;
 	//printk("src %ld svpfn %d evpfn %d count %d\n", src, svpfn, evpfn, count);
 

diff -puN include/asm-ia64/processor.h~task_size_of include/asm-ia64/processor.h
@@ -31,7 +31,8 @@
  * each (assuming 8KB page size), for a total of 8TB of user virtual
  * address space.
  */
-#define TASK_SIZE		(current->thread.task_size)
+#define TASK_SIZE_OF(tsk)	((tsk)->thread.task_size)
+#define TASK_SIZE       	TASK_SIZE_OF(current)
 
 /*
  * This decides where the kernel will search for a free chunk of vm

diff -puN include/asm-parisc/processor.h~task_size_of include/asm-parisc/processor.h
@@ -32,7 +32,8 @@
 #endif
 #define current_text_addr() ({ void *pc; current_ia(pc); pc; })
 
-#define TASK_SIZE               (current->thread.task_size)
+#define TASK_SIZE_OF(tsk)       ((tsk)->thread.task_size)
+#define TASK_SIZE	         (current->thread.task_size)
 #define TASK_UNMAPPED_BASE      (current->thread.map_base)
 
 #define DEFAULT_TASK_SIZE32	(0xFFF00000UL)

diff -puN include/asm-powerpc/processor.h~task_size_of include/asm-powerpc/processor.h
@@ -107,7 +107,9 @@ extern struct task_struct *last_task_use
  */
 #define TASK_SIZE_USER32 (0x0000000100000000UL - (1*PAGE_SIZE))
 
-#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
+#define TASK_SIZE	  (test_thread_flag(TIF_32BIT) ? \
+		TASK_SIZE_USER32 : TASK_SIZE_USER64)
+#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \
 		TASK_SIZE_USER32 : TASK_SIZE_USER64)
 
 /* This decides where the kernel will search for a free chunk of vm

diff -puN include/asm-s390/processor.h~task_size_of include/asm-s390/processor.h
@@ -75,6 +75,8 @@ extern struct task_struct *last_task_use
 
 # define TASK_SIZE		(test_thread_flag(TIF_31BIT) ? \
 					(0x80000000UL) : (0x40000000000UL))
+# define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_31BIT) ? \
+					(0x80000000UL) : (0x40000000000UL))
 # define TASK_UNMAPPED_BASE	(TASK_SIZE / 2)
 # define DEFAULT_TASK_SIZE	(0x40000000000UL)
 

diff -puN include/linux/sched.h~task_size_of include/linux/sched.h
@@ -1712,6 +1712,10 @@ static inline void inc_syscw(struct task
 }
 #endif
 
+#ifndef TASK_SIZE_OF
+#define TASK_SIZE_OF(tsk)	TASK_SIZE
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif

diff -puN fs/proc/task_mmu.c~walk-empty-ranges fs/proc/task_mmu.c
@@ -553,7 +553,6 @@ const struct file_operations proc_numa_m
 
 #ifdef CONFIG_PROC_PAGEMAP
 struct pagemapread {
-	unsigned long next;
 	unsigned long pos;
 	size_t count;
 	int index;

@@ -561,57 +560,66 @@ struct pagemapread {
 };
 
 #define PAGEMAP_ENTRY_SIZE_BYTES sizeof(unsigned long)
+#define PAGEMAP_END_OF_BUFFER 1
+#define PAGEMAP_NO_PAGE_PRESENT	((unsigned long)-1)
 
 static int add_to_pagemap(unsigned long addr, unsigned long pfn,
 			  struct pagemapread *pm)
 {
-	__put_user(pfn, pm->out);
+	int out_len = PAGEMAP_ENTRY_SIZE_BYTES;
+	if (pm->count < PAGEMAP_ENTRY_SIZE_BYTES)
+		out_len = pm->count;
+	copy_to_user(pm->out, &pfn, out_len);
 	pm->out++;
-	pm->pos += PAGEMAP_ENTRY_SIZE_BYTES;
-	pm->count -= PAGEMAP_ENTRY_SIZE_BYTES;
+	pm->pos += out_len;
+	pm->count -= out_len;
+	if (pm->count <= 0)
+		return PAGEMAP_END_OF_BUFFER;
 	return 0;
 }
 
+static int pagemap_pte_hole(unsigned long start, unsigned long end,
+			    void *private)
+{
+	struct pagemapread *pm = private;
+	unsigned long addr;
+	int err = 0;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		err = add_to_pagemap(addr, PAGEMAP_NO_PAGE_PRESENT, pm);
+		if (err)
+			break;
+	}
+	return err;
+}
+
 static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     void *private)
 {
 	struct pagemapread *pm = private;
 	pte_t *pte;
-	int err;
+	int err = 0;
 
 	pte = pte_offset_map(pmd, addr);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
-		if (addr < pm->next)
-			continue;
-		if (!pte_present(*pte))
-			err = add_to_pagemap(addr, -1, pm);
-		else
-			err = add_to_pagemap(addr, pte_pfn(*pte), pm);
+		unsigned long pfn = PAGEMAP_NO_PAGE_PRESENT;
+		if (pte_present(*pte))
+			pfn = pte_pfn(*pte);
+		err = add_to_pagemap(addr, pte_pfn(*pte), pm);
 		if (err)
-			return err;
-		if (pm->count == 0)
 			break;
 	}
 	pte_unmap(pte - 1);
 
 	cond_resched();
 
-	return 0;
+	return err;
 }
 
-static int pagemap_fill(struct pagemapread *pm, unsigned long end)
-{
-	int ret;
-
-	while (pm->next != end && pm->count > 0) {
-		ret = add_to_pagemap(pm->next, -1UL, pm);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
-static struct mm_walk pagemap_walk = { .pmd_entry = pagemap_pte_range };
+static struct mm_walk pagemap_walk = {
+	.pmd_entry = pagemap_pte_range,
+	.pte_hole = pagemap_pte_hole
+};
 
 /*
  * /proc/pid/pagemap - an array mapping virtual pages to pfns

@@ -625,23 +633,14 @@ static struct mm_walk pagemap_walk = { .
  * Efficient users of this interface will use /proc/pid/maps to
  * determine which areas of memory are actually mapped and llseek to
  * skip over unmapped regions.
- *
- * The first 4 bytes of this file form a simple header:
- *
- * first byte:   0 for big endian, 1 for little
- * second byte:  page shift (eg 12 for 4096 byte pages)
- * third byte:   entry size in bytes (currently either 4 or 8)
- * fourth byte:  header size
  */
 static ssize_t pagemap_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
 	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
-	unsigned long src = *ppos;
 	struct page **pages, *page;
-	unsigned long addr, end, vend, svpfn, evpfn, uaddr, uend;
+	unsigned long uaddr, uend;
 	struct mm_struct *mm;
-	struct vm_area_struct *vma;
 	struct pagemapread pm;
 	int pagecount;
 	int ret = -ESRCH;

@@ -653,17 +652,6 @@ static ssize_t pagemap_read(struct file 
 	if (!ptrace_may_attach(task))
 		goto out;
 
-	ret = -EIO;
-	svpfn = src / PAGEMAP_ENTRY_SIZE_BYTES;
-	addr = PAGE_SIZE * svpfn;
-	if (svpfn * PAGEMAP_ENTRY_SIZE_BYTES != src)
-		goto out;
-	evpfn = min((src + count) / sizeof(unsigned long),
-		    ((~0UL) >> PAGE_SHIFT) + 1);
-	count = (evpfn - svpfn) * PAGEMAP_ENTRY_SIZE_BYTES;
-	end = PAGE_SIZE * evpfn;
-	//printk("src %ld svpfn %d evpfn %d count %d\n", src, svpfn, evpfn, count);
-
 	ret = 0;
 	mm = get_task_mm(task);
 	if (!mm)

@@ -672,7 +660,7 @@ static ssize_t pagemap_read(struct file 
 	ret = -ENOMEM;
 	uaddr = (unsigned long)buf & PAGE_MASK;
 	uend = (unsigned long)(buf + count);
-	pagecount = (uend - PAGE_ALIGN(uaddr)) / PAGE_SIZE;
+	pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
 	pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		goto out_task;

@@ -682,44 +670,38 @@ static ssize_t pagemap_read(struct file 
 			     1, 0, pages, NULL);
 	up_read(&current->mm->mmap_sem);
 
-	//printk("%x(%x):%x %d@%ld (%d pages) -> %d\n", uaddr, buf, uend, count, src, pagecount, ret);
 	if (ret < 0)
 		goto out_free;
 
-	pm.next = addr;
-	pm.pos = src;
+	pm.pos = *ppos;
 	pm.count = count;
 	pm.out = (unsigned long __user *)buf;
 
 	down_read(&mm->mmap_sem);
-	vma = find_vma(mm, pm.next);
-	while (pm.count > 0 && vma) {
-		if (!ptrace_may_attach(task)) {
-			ret = -EIO;
-			up_read(&mm->mmap_sem);
-			goto out_release;
-		}
-		vend = min(vma->vm_start - 1, end - 1) + 1;
-		ret = pagemap_fill(&pm, vend);
-		if (ret || !pm.count)
-			break;
-		vend = min(vma->vm_end - 1, end - 1) + 1;
-		ret = walk_page_range(mm, vma->vm_start, vend,
+	if (!ptrace_may_attach(task)) {
+		ret = -EIO;
+	} else {
+		unsigned long src = *ppos;
+		unsigned long svpfn = src / PAGEMAP_ENTRY_SIZE_BYTES;
+		unsigned long start_vaddr = svpfn << PAGE_SHIFT;
+		unsigned long end_vaddr = TASK_SIZE_OF(task);
+		/*
+		 * The odds are that this will stop walking way
+		 * before end_vaddr, because the length of the
+		 * user buffer is tracked in "pm", and the walk
+		 * will stop when we hit the end of the buffer.
+		 */
+		ret = walk_page_range(mm, start_vaddr, end_vaddr,
 				      &pagemap_walk, &pm);
-		vma = vma->vm_next;
+		if (ret == PAGEMAP_END_OF_BUFFER)
+			ret = 0;
+		/* don't need mmap_sem for these, but this looks cleaner */
+		*ppos = pm.pos;
+		if (!ret)
+			ret = pm.pos - src;
 	}
 	up_read(&mm->mmap_sem);
 
-	//printk("before fill at %ld\n", pm.pos);
-	ret = pagemap_fill(&pm, end);
-
-	printk("after fill at %ld\n", pm.pos);
-	*ppos = pm.pos;
-	if (!ret)
-		ret = pm.pos - src;
-
-out_release:
-	printk("releasing pages\n");
 	for (; pagecount; pagecount--) {
 		page = pages[pagecount-1];
 		if (!PageReserved(page))

@@ -732,7 +714,6 @@ out_free:
 out_task:
 	put_task_struct(task);
 out:
-	printk("returning\n");
 	return ret;
 }
 

diff -puN include/linux/mm.h~walk-empty-ranges include/linux/mm.h
@@ -750,6 +750,7 @@ struct mm_walk {
 	int (*pud_entry)(pud_t *, unsigned long, unsigned long, void *);
 	int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, void *);
 	int (*pte_entry)(pte_t *, unsigned long, unsigned long, void *);
+	int (*pte_hole) (unsigned long, unsigned long, void *);
 };
 
 int walk_page_range(struct mm_struct *, unsigned long addr, unsigned long end,

117 lines not on this page · raw message