#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
+#include <linux/ptrace.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
#include <asm/elf.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include "internal.h"
-char *task_mem(struct mm_struct *mm, char *buffer)
+void task_mem(struct seq_file *m, struct mm_struct *mm)
{
unsigned long data, text, lib;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
data = mm->total_vm - mm->shared_vm - mm->stack_vm;
text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
- buffer += sprintf(buffer,
+ seq_printf(m,
"VmPeak:\t%8lu kB\n"
"VmSize:\t%8lu kB\n"
"VmLck:\t%8lu kB\n"
data << (PAGE_SHIFT-10),
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
- return buffer;
}
unsigned long task_vsize(struct mm_struct *mm)
return mm->total_vm;
}
-int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+static void pad_len_spaces(struct seq_file *m, int len)
+{
+ len = 25 + sizeof(void*) * 6 - len;
+ if (len < 1)
+ len = 1;
+ seq_printf(m, "%*c", len, ' ');
+}
+
+static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
{
- struct vm_area_struct * vma;
- int result = -ENOENT;
- struct task_struct *task = proc_task(inode);
- struct mm_struct * mm = get_task_mm(task);
+ if (vma && vma != priv->tail_vma) {
+ struct mm_struct *mm = vma->vm_mm;
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ }
+}
+
+static void *m_start(struct seq_file *m, loff_t *pos)
+{
+ struct proc_maps_private *priv = m->private;
+ unsigned long last_addr = m->version;
+ struct mm_struct *mm;
+ struct vm_area_struct *vma, *tail_vma = NULL;
+ loff_t l = *pos;
+ /* Clear the per syscall fields in priv */
+ priv->task = NULL;
+ priv->tail_vma = NULL;
+
+ /*
+ * We remember last_addr rather than next_addr to hit with
+ * mmap_cache most of the time. We have zero last_addr at
+ * the beginning and also after lseek. We will have -1 last_addr
+ * after the end of the vmas.
+ */
+
+ if (last_addr == -1UL)
+ return NULL;
+
+ priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+ if (!priv->task)
+ return NULL;
+
+ mm = mm_for_maps(priv->task);
if (!mm)
- goto out;
+ return NULL;
down_read(&mm->mmap_sem);
- vma = mm->mmap;
- while (vma) {
- if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file)
- break;
+ tail_vma = get_gate_vma(priv->task);
+ priv->tail_vma = tail_vma;
+
+ /* Start with last addr hint */
+ vma = find_vma(mm, last_addr);
+ if (last_addr && vma) {
vma = vma->vm_next;
+ goto out;
}
- if (vma) {
- *mnt = mntget(vma->vm_file->f_vfsmnt);
- *dentry = dget(vma->vm_file->f_dentry);
- result = 0;
+ /*
+ * Check the vma index is within the range and do
+ * sequential scan until m_index.
+ */
+ vma = NULL;
+ if ((unsigned long)l < mm->map_count) {
+ vma = mm->mmap;
+ while (l-- && vma)
+ vma = vma->vm_next;
+ goto out;
}
+ if (l != mm->map_count)
+ tail_vma = NULL; /* After gate vma */
+
+out:
+ if (vma)
+ return vma;
+
+ /* End of vmas has been reached */
+ m->version = (tail_vma != NULL)? 0: -1UL;
up_read(&mm->mmap_sem);
mmput(mm);
-out:
- return result;
+ return tail_vma;
}
-static void pad_len_spaces(struct seq_file *m, int len)
+static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
- len = 25 + sizeof(void*) * 6 - len;
- if (len < 1)
- len = 1;
- seq_printf(m, "%*c", len, ' ');
+ struct proc_maps_private *priv = m->private;
+ struct vm_area_struct *vma = v;
+ struct vm_area_struct *tail_vma = priv->tail_vma;
+
+ (*pos)++;
+ if (vma && (vma != tail_vma) && vma->vm_next)
+ return vma->vm_next;
+ vma_stop(priv, vma);
+ return (vma != tail_vma)? tail_vma: NULL;
}
-struct mem_size_stats
+static void m_stop(struct seq_file *m, void *v)
{
- unsigned long resident;
- unsigned long shared_clean;
- unsigned long shared_dirty;
- unsigned long private_clean;
- unsigned long private_dirty;
-};
+ struct proc_maps_private *priv = m->private;
+ struct vm_area_struct *vma = v;
+
+ vma_stop(priv, vma);
+ if (priv->task)
+ put_task_struct(priv->task);
+}
-static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss)
+static int do_maps_open(struct inode *inode, struct file *file,
+ const struct seq_operations *ops)
+{
+ struct proc_maps_private *priv;
+ int ret = -ENOMEM;
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (priv) {
+ priv->pid = proc_pid(inode);
+ ret = seq_open(file, ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = priv;
+ } else {
+ kfree(priv);
+ }
+ }
+ return ret;
+}
+
+static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
{
- struct task_struct *task = m->private;
- struct vm_area_struct *vma = v;
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
int flags = vma->vm_flags;
unsigned long ino = 0;
+ unsigned long long pgoff = 0;
dev_t dev = 0;
int len;
if (file) {
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
+ struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
+ pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
}
- seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n",
+ seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
vma->vm_start,
vma->vm_end,
flags & VM_READ ? 'r' : '-',
flags & VM_WRITE ? 'w' : '-',
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? 's' : 'p',
- vma->vm_pgoff << PAGE_SHIFT,
+ pgoff,
MAJOR(dev), MINOR(dev), ino, &len);
/*
*/
if (file) {
pad_len_spaces(m, len);
- seq_path(m, file->f_vfsmnt, file->f_dentry, "\n");
+ seq_path(m, &file->f_path, "\n");
} else {
- if (mm) {
- if (vma->vm_start <= mm->start_brk &&
+ const char *name = arch_vma_name(vma);
+ if (!name) {
+ if (mm) {
+ if (vma->vm_start <= mm->start_brk &&
vma->vm_end >= mm->brk) {
- pad_len_spaces(m, len);
- seq_puts(m, "[heap]");
- } else {
- if (vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack) {
-
- pad_len_spaces(m, len);
- seq_puts(m, "[stack]");
+ name = "[heap]";
+ } else if (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack) {
+ name = "[stack]";
+ } else {
+ unsigned long stack_start;
+ struct proc_maps_private *pmp;
+
+ pmp = m->private;
+ stack_start = pmp->task->stack_start;
+
+ if (vma->vm_start <= stack_start &&
+ vma->vm_end >= stack_start) {
+ pad_len_spaces(m, len);
+ seq_printf(m,
+ "[threadstack:%08lx]",
+#ifdef CONFIG_STACK_GROWSUP
+ vma->vm_end - stack_start
+#else
+ stack_start - vma->vm_start
+#endif
+ );
+ }
}
+ } else {
+ name = "[vdso]";
}
- } else {
+ }
+ if (name) {
pad_len_spaces(m, len);
- seq_puts(m, "[vdso]");
+ seq_puts(m, name);
}
}
seq_putc(m, '\n');
+}
+
+static int show_map(struct seq_file *m, void *v)
+{
+ struct vm_area_struct *vma = v;
+ struct proc_maps_private *priv = m->private;
+ struct task_struct *task = priv->task;
- if (mss)
- seq_printf(m,
- "Size: %8lu kB\n"
- "Rss: %8lu kB\n"
- "Shared_Clean: %8lu kB\n"
- "Shared_Dirty: %8lu kB\n"
- "Private_Clean: %8lu kB\n"
- "Private_Dirty: %8lu kB\n",
- (vma->vm_end - vma->vm_start) >> 10,
- mss->resident >> 10,
- mss->shared_clean >> 10,
- mss->shared_dirty >> 10,
- mss->private_clean >> 10,
- mss->private_dirty >> 10);
+ show_map_vma(m, vma);
if (m->count < m->size) /* vma is copied successfully */
m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
return 0;
}
-static int show_map(struct seq_file *m, void *v)
+static const struct seq_operations proc_pid_maps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_map
+};
+
+static int maps_open(struct inode *inode, struct file *file)
{
- return show_map_internal(m, v, 0);
+ return do_maps_open(inode, file, &proc_pid_maps_op);
}
-static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, unsigned long end,
- struct mem_size_stats *mss)
+const struct file_operations proc_maps_operations = {
+ .open = maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+/*
+ * Proportional Set Size(PSS): my share of RSS.
+ *
+ * PSS of a process is the count of pages it has in memory, where each
+ * page is divided by the number of processes sharing it. So if a
+ * process has 1000 pages all to itself, and 1000 shared with one other
+ * process, its PSS will be 1500.
+ *
+ * To keep (accumulated) division errors low, we adopt a 64bit
+ * fixed-point pss counter to minimize division errors. So (pss >>
+ * PSS_SHIFT) would be the real byte count.
+ *
+ * A shift of 12 before division means (assuming 4K page size):
+ * - 1M 3-user-pages add up to 8KB errors;
+ * - supports mapcount up to 2^24, or 16M;
+ * - supports PSS up to 2^52 bytes, or 4PB.
+ */
+#define PSS_SHIFT 12
+
+#ifdef CONFIG_PROC_PAGE_MONITOR
+struct mem_size_stats {
+ struct vm_area_struct *vma;
+ unsigned long resident;
+ unsigned long shared_clean;
+ unsigned long shared_dirty;
+ unsigned long private_clean;
+ unsigned long private_dirty;
+ unsigned long referenced;
+ unsigned long swap;
+ u64 pss;
+};
+
+static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
{
+ struct mem_size_stats *mss = walk->private;
+ struct vm_area_struct *vma = mss->vma;
pte_t *pte, ptent;
spinlock_t *ptl;
- unsigned long pfn;
struct page *page;
+ int mapcount;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- do {
+ for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
+
+ if (is_swap_pte(ptent)) {
+ mss->swap += PAGE_SIZE;
+ continue;
+ }
+
if (!pte_present(ptent))
continue;
- mss->resident += PAGE_SIZE;
- pfn = pte_pfn(ptent);
- if (!pfn_valid(pfn))
+ page = vm_normal_page(vma, addr, ptent);
+ if (!page)
continue;
- page = pfn_to_page(pfn);
- if (page_count(page) >= 2) {
+ mss->resident += PAGE_SIZE;
+ /* Accumulate the size in pages that have been accessed. */
+ if (pte_young(ptent) || PageReferenced(page))
+ mss->referenced += PAGE_SIZE;
+ mapcount = page_mapcount(page);
+ if (mapcount >= 2) {
if (pte_dirty(ptent))
mss->shared_dirty += PAGE_SIZE;
else
mss->shared_clean += PAGE_SIZE;
+ mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
} else {
if (pte_dirty(ptent))
mss->private_dirty += PAGE_SIZE;
else
mss->private_clean += PAGE_SIZE;
+ mss->pss += (PAGE_SIZE << PSS_SHIFT);
}
- } while (pte++, addr += PAGE_SIZE, addr != end);
+ }
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
+ return 0;
}
-static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud,
- unsigned long addr, unsigned long end,
- struct mem_size_stats *mss)
+static int show_smap(struct seq_file *m, void *v)
{
- pmd_t *pmd;
- unsigned long next;
+ struct proc_maps_private *priv = m->private;
+ struct task_struct *task = priv->task;
+ struct vm_area_struct *vma = v;
+ struct mem_size_stats mss;
+ struct mm_walk smaps_walk = {
+ .pmd_entry = smaps_pte_range,
+ .mm = vma->vm_mm,
+ .private = &mss,
+ };
- pmd = pmd_offset(pud, addr);
- do {
- next = pmd_addr_end(addr, end);
- if (pmd_none_or_clear_bad(pmd))
- continue;
- smaps_pte_range(vma, pmd, addr, next, mss);
- } while (pmd++, addr = next, addr != end);
+ memset(&mss, 0, sizeof mss);
+ mss.vma = vma;
+ if (vma->vm_mm && !is_vm_hugetlb_page(vma))
+ walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
+
+ show_map_vma(m, vma);
+
+ seq_printf(m,
+ "Size: %8lu kB\n"
+ "Rss: %8lu kB\n"
+ "Pss: %8lu kB\n"
+ "Shared_Clean: %8lu kB\n"
+ "Shared_Dirty: %8lu kB\n"
+ "Private_Clean: %8lu kB\n"
+ "Private_Dirty: %8lu kB\n"
+ "Referenced: %8lu kB\n"
+ "Swap: %8lu kB\n"
+ "KernelPageSize: %8lu kB\n"
+ "MMUPageSize: %8lu kB\n",
+ (vma->vm_end - vma->vm_start) >> 10,
+ mss.resident >> 10,
+ (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
+ mss.shared_clean >> 10,
+ mss.shared_dirty >> 10,
+ mss.private_clean >> 10,
+ mss.private_dirty >> 10,
+ mss.referenced >> 10,
+ mss.swap >> 10,
+ vma_kernel_pagesize(vma) >> 10,
+ vma_mmu_pagesize(vma) >> 10);
+
+ if (m->count < m->size) /* vma is copied successfully */
+ m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+ return 0;
}
-static inline void smaps_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
- unsigned long addr, unsigned long end,
- struct mem_size_stats *mss)
-{
- pud_t *pud;
- unsigned long next;
+static const struct seq_operations proc_pid_smaps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_smap
+};
- pud = pud_offset(pgd, addr);
- do {
- next = pud_addr_end(addr, end);
- if (pud_none_or_clear_bad(pud))
- continue;
- smaps_pmd_range(vma, pud, addr, next, mss);
- } while (pud++, addr = next, addr != end);
+static int smaps_open(struct inode *inode, struct file *file)
+{
+ return do_maps_open(inode, file, &proc_pid_smaps_op);
}
-static inline void smaps_pgd_range(struct vm_area_struct *vma,
- unsigned long addr, unsigned long end,
- struct mem_size_stats *mss)
+const struct file_operations proc_smaps_operations = {
+ .open = smaps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
+static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
{
- pgd_t *pgd;
- unsigned long next;
+ struct vm_area_struct *vma = walk->private;
+ pte_t *pte, ptent;
+ spinlock_t *ptl;
+ struct page *page;
- pgd = pgd_offset(vma->vm_mm, addr);
- do {
- next = pgd_addr_end(addr, end);
- if (pgd_none_or_clear_bad(pgd))
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ for (; addr != end; pte++, addr += PAGE_SIZE) {
+ ptent = *pte;
+ if (!pte_present(ptent))
continue;
- smaps_pud_range(vma, pgd, addr, next, mss);
- } while (pgd++, addr = next, addr != end);
-}
-static int show_smap(struct seq_file *m, void *v)
-{
- struct vm_area_struct *vma = v;
- struct mem_size_stats mss;
+ page = vm_normal_page(vma, addr, ptent);
+ if (!page)
+ continue;
- memset(&mss, 0, sizeof mss);
- if (vma->vm_mm)
- smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss);
- return show_map_internal(m, v, &mss);
+ /* Clear accessed and referenced bits. */
+ ptep_test_and_clear_young(vma, addr, pte);
+ ClearPageReferenced(page);
+ }
+ pte_unmap_unlock(pte - 1, ptl);
+ cond_resched();
+ return 0;
}
-static void *m_start(struct seq_file *m, loff_t *pos)
+#define CLEAR_REFS_ALL 1
+#define CLEAR_REFS_ANON 2
+#define CLEAR_REFS_MAPPED 3
+
+static ssize_t clear_refs_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
{
- struct task_struct *task = m->private;
- unsigned long last_addr = m->version;
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF];
struct mm_struct *mm;
- struct vm_area_struct *vma, *tail_vma;
- loff_t l = *pos;
-
- /*
- * We remember last_addr rather than next_addr to hit with
- * mmap_cache most of the time. We have zero last_addr at
- * the beginning and also after lseek. We will have -1 last_addr
- * after the end of the vmas.
- */
-
- if (last_addr == -1UL)
- return NULL;
-
+ struct vm_area_struct *vma;
+ long type;
+
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
+ return -EFAULT;
+ if (strict_strtol(strstrip(buffer), 10, &type))
+ return -EINVAL;
+ if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
+ return -EINVAL;
+ task = get_proc_task(file->f_path.dentry->d_inode);
+ if (!task)
+ return -ESRCH;
mm = get_task_mm(task);
- if (!mm)
- return NULL;
-
- tail_vma = get_gate_vma(task);
- down_read(&mm->mmap_sem);
-
- /* Start with last addr hint */
- if (last_addr && (vma = find_vma(mm, last_addr))) {
- vma = vma->vm_next;
- goto out;
+ if (mm) {
+ struct mm_walk clear_refs_walk = {
+ .pmd_entry = clear_refs_pte_range,
+ .mm = mm,
+ };
+ down_read(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ clear_refs_walk.private = vma;
+ if (is_vm_hugetlb_page(vma))
+ continue;
+ /*
+ * Writing 1 to /proc/pid/clear_refs affects all pages.
+ *
+ * Writing 2 to /proc/pid/clear_refs only affects
+ * Anonymous pages.
+ *
+ * Writing 3 to /proc/pid/clear_refs only affects file
+ * mapped pages.
+ */
+ if (type == CLEAR_REFS_ANON && vma->vm_file)
+ continue;
+ if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
+ continue;
+ walk_page_range(vma->vm_start, vma->vm_end,
+ &clear_refs_walk);
+ }
+ flush_tlb_mm(mm);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
}
+ put_task_struct(task);
- /*
- * Check the vma index is within the range and do
- * sequential scan until m_index.
- */
- vma = NULL;
- if ((unsigned long)l < mm->map_count) {
- vma = mm->mmap;
- while (l-- && vma)
- vma = vma->vm_next;
- goto out;
- }
+ return count;
+}
- if (l != mm->map_count)
- tail_vma = NULL; /* After gate vma */
+const struct file_operations proc_clear_refs_operations = {
+ .write = clear_refs_write,
+};
-out:
- if (vma)
- return vma;
+struct pagemapread {
+ u64 __user *out, *end;
+};
- /* End of vmas has been reached */
- m->version = (tail_vma != NULL)? 0: -1UL;
- up_read(&mm->mmap_sem);
- mmput(mm);
- return tail_vma;
+#define PM_ENTRY_BYTES sizeof(u64)
+#define PM_STATUS_BITS 3
+#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
+#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
+#define PM_STATUS(nr) (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
+#define PM_PSHIFT_BITS 6
+#define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
+#define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
+#define PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1)
+#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK)
+
+#define PM_PRESENT PM_STATUS(4LL)
+#define PM_SWAP PM_STATUS(2LL)
+#define PM_NOT_PRESENT PM_PSHIFT(PAGE_SHIFT)
+#define PM_END_OF_BUFFER 1
+
+static int add_to_pagemap(unsigned long addr, u64 pfn,
+ struct pagemapread *pm)
+{
+ if (put_user(pfn, pm->out))
+ return -EFAULT;
+ pm->out++;
+ if (pm->out >= pm->end)
+ return PM_END_OF_BUFFER;
+ return 0;
}
-static void m_stop(struct seq_file *m, void *v)
+static int pagemap_pte_hole(unsigned long start, unsigned long end,
+ struct mm_walk *walk)
{
- struct task_struct *task = m->private;
- struct vm_area_struct *vma = v;
- if (vma && vma != get_gate_vma(task)) {
- struct mm_struct *mm = vma->vm_mm;
- up_read(&mm->mmap_sem);
- mmput(mm);
+ struct pagemapread *pm = walk->private;
+ unsigned long addr;
+ int err = 0;
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+ if (err)
+ break;
}
+ return err;
}
-static void *m_next(struct seq_file *m, void *v, loff_t *pos)
+static u64 swap_pte_to_pagemap_entry(pte_t pte)
{
- struct task_struct *task = m->private;
- struct vm_area_struct *vma = v;
- struct vm_area_struct *tail_vma = get_gate_vma(task);
+ swp_entry_t e = pte_to_swp_entry(pte);
+ return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
+}
- (*pos)++;
- if (vma && (vma != tail_vma) && vma->vm_next)
- return vma->vm_next;
- m_stop(m, v);
- return (vma != tail_vma)? tail_vma: NULL;
+static u64 pte_to_pagemap_entry(pte_t pte)
+{
+ u64 pme = 0;
+ if (is_swap_pte(pte))
+ pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+ else if (pte_present(pte))
+ pme = PM_PFRAME(pte_pfn(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+ return pme;
}
-struct seq_operations proc_pid_maps_op = {
- .start = m_start,
- .next = m_next,
- .stop = m_stop,
- .show = show_map
-};
+static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct vm_area_struct *vma;
+ struct pagemapread *pm = walk->private;
+ pte_t *pte;
+ int err = 0;
+
+ /* find the first VMA at or above 'addr' */
+ vma = find_vma(walk->mm, addr);
+ for (; addr != end; addr += PAGE_SIZE) {
+ u64 pfn = PM_NOT_PRESENT;
+
+ /* check to see if we've left 'vma' behind
+ * and need a new, higher one */
+ if (vma && (addr >= vma->vm_end))
+ vma = find_vma(walk->mm, addr);
+
+ /* check that 'vma' actually covers this address,
+ * and that it isn't a huge page vma */
+ if (vma && (vma->vm_start <= addr) &&
+ !is_vm_hugetlb_page(vma)) {
+ pte = pte_offset_map(pmd, addr);
+ pfn = pte_to_pagemap_entry(*pte);
+ /* unmap before userspace copy */
+ pte_unmap(pte);
+ }
+ err = add_to_pagemap(addr, pfn, pm);
+ if (err)
+ return err;
+ }
-struct seq_operations proc_pid_smaps_op = {
- .start = m_start,
- .next = m_next,
- .stop = m_stop,
- .show = show_smap
-};
+ cond_resched();
-#ifdef CONFIG_NUMA
+ return err;
+}
-struct numa_maps {
- unsigned long pages;
- unsigned long anon;
- unsigned long mapped;
- unsigned long mapcount_max;
- unsigned long node[MAX_NUMNODES];
-};
+static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
+{
+ u64 pme = 0;
+ if (pte_present(pte))
+ pme = PM_PFRAME(pte_pfn(pte) + offset)
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+ return pme;
+}
-/*
- * Calculate numa node maps for a vma
- */
-static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
+static int pagemap_hugetlb_range(pte_t *pte, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
{
- struct page *page;
- unsigned long vaddr;
- struct mm_struct *mm = vma->vm_mm;
- int i;
- struct numa_maps *md = kmalloc(sizeof(struct numa_maps), GFP_KERNEL);
+ struct vm_area_struct *vma;
+ struct pagemapread *pm = walk->private;
+ struct hstate *hs = NULL;
+ int err = 0;
- if (!md)
- return NULL;
- md->pages = 0;
- md->anon = 0;
- md->mapped = 0;
- md->mapcount_max = 0;
- for_each_node(i)
- md->node[i] =0;
-
- for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
- page = follow_page(mm, vaddr, 0);
- if (page) {
- int count = page_mapcount(page);
-
- if (count)
- md->mapped++;
- if (count > md->mapcount_max)
- md->mapcount_max = count;
- md->pages++;
- if (PageAnon(page))
- md->anon++;
- md->node[page_to_nid(page)]++;
+ vma = find_vma(walk->mm, addr);
+ if (vma)
+ hs = hstate_vma(vma);
+ for (; addr != end; addr += PAGE_SIZE) {
+ u64 pfn = PM_NOT_PRESENT;
+
+ if (vma && (addr >= vma->vm_end)) {
+ vma = find_vma(walk->mm, addr);
+ if (vma)
+ hs = hstate_vma(vma);
}
- cond_resched();
+
+ if (vma && (vma->vm_start <= addr) && is_vm_hugetlb_page(vma)) {
+ /* calculate pfn of the "raw" page in the hugepage. */
+ int offset = (addr & ~huge_page_mask(hs)) >> PAGE_SHIFT;
+ pfn = huge_pte_to_pagemap_entry(*pte, offset);
+ }
+ err = add_to_pagemap(addr, pfn, pm);
+ if (err)
+ return err;
}
- return md;
+
+ cond_resched();
+
+ return err;
}
-static int show_numa_map(struct seq_file *m, void *v)
+/*
+ * /proc/pid/pagemap - an array mapping virtual pages to pfns
+ *
+ * For each page in the address space, this file contains one 64-bit entry
+ * consisting of the following:
+ *
+ * Bits 0-55 page frame number (PFN) if present
+ * Bits 0-4 swap type if swapped
+ * Bits 5-55 swap offset if swapped
+ * Bits 55-60 page shift (page size = 1<<page shift)
+ * Bit 61 reserved for future use
+ * Bit 62 page swapped
+ * Bit 63 page present
+ *
+ * If the page is not present but in swap, then the PFN contains an
+ * encoding of the swap file number and the page's offset into the
+ * swap. Unmapped pages return a null PFN. This allows determining
+ * precisely which pages are mapped (or in swap) and comparing mapped
+ * pages between processes.
+ *
+ * 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.
+ */
+static ssize_t pagemap_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
{
- struct task_struct *task = m->private;
- struct vm_area_struct *vma = v;
- struct mempolicy *pol;
- struct numa_maps *md;
- struct zone **z;
- int n;
- int first;
-
- if (!vma->vm_mm)
- return 0;
-
- md = get_numa_maps(vma);
- if (!md)
- return 0;
-
- seq_printf(m, "%08lx", vma->vm_start);
- pol = get_vma_policy(task, vma, vma->vm_start);
- /* Print policy */
- switch (pol->policy) {
- case MPOL_PREFERRED:
- seq_printf(m, " prefer=%d", pol->v.preferred_node);
- break;
- case MPOL_BIND:
- seq_printf(m, " bind={");
- first = 1;
- for (z = pol->v.zonelist->zones; *z; z++) {
-
- if (!first)
- seq_putc(m, ',');
- else
- first = 0;
- seq_printf(m, "%d/%s", (*z)->zone_pgdat->node_id,
- (*z)->name);
- }
- seq_putc(m, '}');
- break;
- case MPOL_INTERLEAVE:
- seq_printf(m, " interleave={");
- first = 1;
- for_each_node(n) {
- if (node_isset(n, pol->v.nodes)) {
- if (!first)
- seq_putc(m,',');
- else
- first = 0;
- seq_printf(m, "%d",n);
- }
- }
- seq_putc(m, '}');
- break;
- default:
- seq_printf(m," default");
- break;
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+ struct page **pages, *page;
+ unsigned long uaddr, uend;
+ struct mm_struct *mm;
+ struct pagemapread pm;
+ int pagecount;
+ int ret = -ESRCH;
+ struct mm_walk pagemap_walk = {};
+ unsigned long src;
+ unsigned long svpfn;
+ unsigned long start_vaddr;
+ unsigned long end_vaddr;
+
+ if (!task)
+ goto out;
+
+ ret = -EACCES;
+ if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ goto out_task;
+
+ ret = -EINVAL;
+ /* file position must be aligned */
+ if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
+ goto out_task;
+
+ ret = 0;
+
+ if (!count)
+ goto out_task;
+
+ mm = get_task_mm(task);
+ if (!mm)
+ goto out_task;
+
+
+ uaddr = (unsigned long)buf & PAGE_MASK;
+ uend = (unsigned long)(buf + count);
+ pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
+ ret = 0;
+ if (pagecount == 0)
+ goto out_mm;
+ pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
+ ret = -ENOMEM;
+ if (!pages)
+ goto out_mm;
+
+ down_read(¤t->mm->mmap_sem);
+ ret = get_user_pages(current, current->mm, uaddr, pagecount,
+ 1, 0, pages, NULL);
+ up_read(¤t->mm->mmap_sem);
+
+ if (ret < 0)
+ goto out_free;
+
+ if (ret != pagecount) {
+ pagecount = ret;
+ ret = -EFAULT;
+ goto out_pages;
}
- seq_printf(m, " MaxRef=%lu Pages=%lu Mapped=%lu",
- md->mapcount_max, md->pages, md->mapped);
- if (md->anon)
- seq_printf(m," Anon=%lu",md->anon);
-
- for_each_online_node(n) {
- if (md->node[n])
- seq_printf(m, " N%d=%lu", n, md->node[n]);
+
+ pm.out = (u64 __user *)buf;
+ pm.end = (u64 __user *)(buf + count);
+
+ pagemap_walk.pmd_entry = pagemap_pte_range;
+ pagemap_walk.pte_hole = pagemap_pte_hole;
+ pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
+ pagemap_walk.mm = mm;
+ pagemap_walk.private = ±
+
+ src = *ppos;
+ svpfn = src / PM_ENTRY_BYTES;
+ start_vaddr = svpfn << PAGE_SHIFT;
+ end_vaddr = TASK_SIZE_OF(task);
+
+ /* watch out for wraparound */
+ if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
+ start_vaddr = end_vaddr;
+
+ /*
+ * 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(start_vaddr, end_vaddr, &pagemap_walk);
+ if (ret == PM_END_OF_BUFFER)
+ ret = 0;
+ /* don't need mmap_sem for these, but this looks cleaner */
+ *ppos += (char __user *)pm.out - buf;
+ if (!ret)
+ ret = (char __user *)pm.out - buf;
+
+out_pages:
+ for (; pagecount; pagecount--) {
+ page = pages[pagecount-1];
+ if (!PageReserved(page))
+ SetPageDirty(page);
+ page_cache_release(page);
}
- seq_putc(m, '\n');
- kfree(md);
- if (m->count < m->size) /* vma is copied successfully */
- m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
- return 0;
+out_free:
+ kfree(pages);
+out_mm:
+ mmput(mm);
+out_task:
+ put_task_struct(task);
+out:
+ return ret;
}
-struct seq_operations proc_pid_numa_maps_op = {
- .start = m_start,
- .next = m_next,
- .stop = m_stop,
- .show = show_numa_map
+const struct file_operations proc_pagemap_operations = {
+ .llseek = mem_lseek, /* borrow this */
+ .read = pagemap_read,
+};
+#endif /* CONFIG_PROC_PAGE_MONITOR */
+
+#ifdef CONFIG_NUMA
+extern int show_numa_map(struct seq_file *m, void *v);
+
+static const struct seq_operations proc_pid_numa_maps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_numa_map,
+};
+
+static int numa_maps_open(struct inode *inode, struct file *file)
+{
+ return do_maps_open(inode, file, &proc_pid_numa_maps_op);
+}
+
+const struct file_operations proc_numa_maps_operations = {
+ .open = numa_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
};
#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff