NOMMU: Make VMAs per MM as for MMU-mode linux

Make VMAs per mm_struct as for MMU-mode linux.  This solves two problems:

 (1) In SYSV SHM where nattch for a segment does not reflect the number of
     shmat's (and forks) done.

 (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an
     exec'ing process when VM_EXECUTABLE is specified, regardless of the fact
     that a VMA might be shared and already have its vm_mm assigned to another
     process or a dead process.

A new struct (vm_region) is introduced to track a mapped region and to remember
the circumstances under which it may be shared and the vm_list_struct structure
is discarded as it's no longer required.

This patch makes the following additional changes:

 (1) Regions are now allocated with alloc_pages() rather than kmalloc() and
     with no recourse to __GFP_COMP, so the pages are not composite.  Instead,
     each page has a reference on it held by the region.  Anything else that is
     interested in such a page will have to get a reference on it to retain it.
     When the pages are released due to unmapping, each page is passed to
     put_page() and will be freed when the page usage count reaches zero.

 (2) Excess pages are trimmed after an allocation as the allocation must be
     made as a power-of-2 quantity of pages.

 (3) VMAs are added to the parent MM's R/B tree and mmap lists.  As an MM may
     end up with overlapping VMAs within the tree, the VMA struct address is
     appended to the sort key.

 (4) Non-anonymous VMAs are now added to the backing inode's prio list.

 (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of
     the backing region.  The VMA and region structs will be split if
     necessary.

 (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory
     segment instead of all the attachments at that addresss.  Multiple
     shmat()'s return the same address under NOMMU-mode instead of different
     virtual addresses as under MMU-mode.

 (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode.

 (8) /proc/maps is now the global list of mapped regions, and may list bits
     that aren't actually mapped anywhere.

 (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount
     of RAM currently allocated by mmap to hold mappable regions that can't be
     mapped directly.  These are copies of the backing device or file if not
     anonymous.

These changes make NOMMU mode more similar to MMU mode.  The downside is that
NOMMU mode requires some extra memory to track things over NOMMU without this
patch (VMAs are no longer shared, and there are now region structs).

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Mike Frysinger <vapier.adi@gmail.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>

5 files changed, 116 insertions, 98 deletions

diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index aa5b43205e37..22baf1b13493 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1567,11 +1567,9 @@ end_coredump:
 static int elf_fdpic_dump_segments(struct file *file, size_t *size,
                            unsigned long *limit, unsigned long mm_flags)
 {
-        struct vm_list_struct *vml;
-
-        for (vml = current->mm->context.vmlist; vml; vml = vml->next) {
-        struct vm_area_struct *vma = vml->vma;
+        struct vm_area_struct *vma;
 
+        for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
                 if (!maydump(vma, mm_flags))
                         continue;
 
@@ -1617,9 +1615,6 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
         elf_fpxregset_t *xfpu = NULL;
 #endif
         int thread_status_size = 0;
-#ifndef CONFIG_MMU
-        struct vm_list_struct *vml;
-#endif
         elf_addr_t *auxv;
         unsigned long mm_flags;
 
@@ -1685,13 +1680,7 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
         fill_prstatus(prstatus, current, signr);
         elf_core_copy_regs(&prstatus->pr_reg, regs);
 
-#ifdef CONFIG_MMU
         segs = current->mm->map_count;
-#else
-        segs = 0;
-        for (vml = current->mm->context.vmlist; vml; vml = vml->next)
-            segs++;
-#endif
 #ifdef ELF_CORE_EXTRA_PHDRS
         segs += ELF_CORE_EXTRA_PHDRS;
 #endif
@@ -1766,20 +1755,10 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
         mm_flags = current->mm->flags;
 
         /* write program headers for segments dump */
-        for (
-#ifdef CONFIG_MMU
-                vma = current->mm->mmap; vma; vma = vma->vm_next
-#else
-                        vml = current->mm->context.vmlist; vml; vml = vml->next
-#endif
-             ) {
+        for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
                 struct elf_phdr phdr;
                 size_t sz;
 
-#ifndef CONFIG_MMU
-                vma = vml->vma;
-#endif
-
                 sz = vma->vm_end - vma->vm_start;
 
                 phdr.p_type = PT_LOAD;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 3e8aeb8b61ce..cd53ff838498 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -41,8 +41,6 @@ do {						\
         (vmi)->used = 0;                        \
         (vmi)->largest_chunk = 0;               \
 } while(0)
-
-extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
 #endif
 
 extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index b1675c4e66da..43d23948384a 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -74,6 +74,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                 "LowTotal:       %8lu kB\n"
                 "LowFree:        %8lu kB\n"
 #endif
+#ifndef CONFIG_MMU
+                "MmapCopy:       %8lu kB\n"
+#endif
                 "SwapTotal:      %8lu kB\n"
                 "SwapFree:       %8lu kB\n"
                 "Dirty:          %8lu kB\n"
@@ -116,6 +119,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                 K(i.totalram-i.totalhigh),
                 K(i.freeram-i.freehigh),
 #endif
+#ifndef CONFIG_MMU
+                K((unsigned long) atomic_read(&mmap_pages_allocated)),
+#endif
                 K(i.totalswap),
                 K(i.freeswap),
                 K(global_page_state(NR_FILE_DIRTY)),
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 3f87d2632947..b446d7ad0b0d 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -33,33 +33,33 @@
 #include "internal.h"
 
 /*
- * display a single VMA to a sequenced file
+ * display a single region to a sequenced file
  */
-int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+static int nommu_region_show(struct seq_file *m, struct vm_region *region)
 {
         unsigned long ino = 0;
         struct file *file;
         dev_t dev = 0;
         int flags, len;
 
-        flags = vma->vm_flags;
-        file = vma->vm_file;
+        flags = region->vm_flags;
+        file = region->vm_file;
 
         if (file) {
-                struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+                struct inode *inode = region->vm_file->f_path.dentry->d_inode;
                 dev = inode->i_sb->s_dev;
                 ino = inode->i_ino;
         }
 
         seq_printf(m,
                    "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
-                   vma->vm_start,
-                   vma->vm_end,
+                   region->vm_start,
+                   region->vm_end,
                    flags & VM_READ ? 'r' : '-',
                    flags & VM_WRITE ? 'w' : '-',
                    flags & VM_EXEC ? 'x' : '-',
                    flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
-                   ((loff_t)vma->vm_pgoff) << PAGE_SHIFT,
+                   ((loff_t)region->vm_pgoff) << PAGE_SHIFT,
                    MAJOR(dev), MINOR(dev), ino, &len);
 
         if (file) {
@@ -75,61 +75,54 @@ int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 }
 
 /*
- * display a list of all the VMAs the kernel knows about
+ * display a list of all the REGIONs the kernel knows about
  * - nommu kernals have a single flat list
  */
-static int nommu_vma_list_show(struct seq_file *m, void *v)
+static int nommu_region_list_show(struct seq_file *m, void *_p)
 {
-        struct vm_area_struct *vma;
+        struct rb_node *p = _p;
 
-        vma = rb_entry((struct rb_node *) v, struct vm_area_struct, vm_rb);
-        return nommu_vma_show(m, vma);
+        return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb));
 }
 
-static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos)
+static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos)
 {
-        struct rb_node *_rb;
+        struct rb_node *p;
         loff_t pos = *_pos;
-        void *next = NULL;
 
-        down_read(&nommu_vma_sem);
+        down_read(&nommu_region_sem);
 
-        for (_rb = rb_first(&nommu_vma_tree); _rb; _rb = rb_next(_rb)) {
-                if (pos == 0) {
-                        next = _rb;
-                        break;
-                }
-                pos--;
-        }
-
-        return next;
+        for (p = rb_first(&nommu_region_tree); p; p = rb_next(p))
+                if (pos-- == 0)
+                        return p;
+        return NULL;
 }
 
-static void nommu_vma_list_stop(struct seq_file *m, void *v)
+static void nommu_region_list_stop(struct seq_file *m, void *v)
 {
-        up_read(&nommu_vma_sem);
+        up_read(&nommu_region_sem);
 }
 
-static void *nommu_vma_list_next(struct seq_file *m, void *v, loff_t *pos)
+static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos)
 {
         (*pos)++;
         return rb_next((struct rb_node *) v);
 }
 
-static const struct seq_operations proc_nommu_vma_list_seqop = {
-        .start  = nommu_vma_list_start,
-        .next   = nommu_vma_list_next,
-        .stop   = nommu_vma_list_stop,
-        .show   = nommu_vma_list_show
+static struct seq_operations proc_nommu_region_list_seqop = {
+        .start  = nommu_region_list_start,
+        .next   = nommu_region_list_next,
+        .stop   = nommu_region_list_stop,
+        .show   = nommu_region_list_show
 };
 
-static int proc_nommu_vma_list_open(struct inode *inode, struct file *file)
+static int proc_nommu_region_list_open(struct inode *inode, struct file *file)
 {
-        return seq_open(file, &proc_nommu_vma_list_seqop);
+        return seq_open(file, &proc_nommu_region_list_seqop);
 }
 
-static const struct file_operations proc_nommu_vma_list_operations = {
-        .open    = proc_nommu_vma_list_open,
+static const struct file_operations proc_nommu_region_list_operations = {
+        .open    = proc_nommu_region_list_open,
         .read    = seq_read,
         .llseek  = seq_lseek,
         .release = seq_release,
@@ -137,7 +130,7 @@ static const struct file_operations proc_nommu_vma_list_operations = {
 
 static int __init proc_nommu_init(void)
 {
-        proc_create("maps", S_IRUGO, NULL, &proc_nommu_vma_list_operations);
+        proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations);
         return 0;
 }
 
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index d4a8be32b902..ca4a48d0d311 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -15,25 +15,25 @@
  */
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
-        struct vm_list_struct *vml;
+        struct vm_area_struct *vma;
+        struct rb_node *p;
         unsigned long bytes = 0, sbytes = 0, slack = 0;
         
         down_read(&mm->mmap_sem);
-        for (vml = mm->context.vmlist; vml; vml = vml->next) {
-                if (!vml->vma)
-                        continue;
+        for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
+                vma = rb_entry(p, struct vm_area_struct, vm_rb);
 
-                bytes += kobjsize(vml);
+                bytes += kobjsize(vma);
                 if (atomic_read(&mm->mm_count) > 1 ||
-                    atomic_read(&vml->vma->vm_usage) > 1
-                    ) {
-                        sbytes += kobjsize((void *) vml->vma->vm_start);
-                        sbytes += kobjsize(vml->vma);
+                    vma->vm_region ||
+                    vma->vm_flags & VM_MAYSHARE) {
+                        sbytes += kobjsize((void *) vma->vm_start);
+                        if (vma->vm_region)
+                                sbytes += kobjsize(vma->vm_region);
                 } else {
-                        bytes += kobjsize((void *) vml->vma->vm_start);
-                        bytes += kobjsize(vml->vma);
-                        slack += kobjsize((void *) vml->vma->vm_start) -
-                                (vml->vma->vm_end - vml->vma->vm_start);
+                        bytes += kobjsize((void *) vma->vm_start);
+                        slack += kobjsize((void *) vma->vm_start) -
+                                (vma->vm_end - vma->vm_start);
                 }
         }
 
@@ -70,13 +70,14 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 
 unsigned long task_vsize(struct mm_struct *mm)
 {
-        struct vm_list_struct *tbp;
+        struct vm_area_struct *vma;
+        struct rb_node *p;
         unsigned long vsize = 0;
 
         down_read(&mm->mmap_sem);
-        for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) {
-                if (tbp->vma)
-                        vsize += kobjsize((void *) tbp->vma->vm_start);
+        for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
+                vma = rb_entry(p, struct vm_area_struct, vm_rb);
+                vsize += vma->vm_region->vm_end - vma->vm_region->vm_start;
         }
         up_read(&mm->mmap_sem);
         return vsize;
@@ -85,16 +86,15 @@ unsigned long task_vsize(struct mm_struct *mm)
 int task_statm(struct mm_struct *mm, int *shared, int *text,
                int *data, int *resident)
 {
-        struct vm_list_struct *tbp;
+        struct vm_area_struct *vma;
+        struct rb_node *p;
         int size = kobjsize(mm);
 
         down_read(&mm->mmap_sem);
-        for (tbp = mm->context.vmlist; tbp; tbp = tbp->next) {
-                size += kobjsize(tbp);
-                if (tbp->vma) {
-                        size += kobjsize(tbp->vma);
-                        size += kobjsize((void *) tbp->vma->vm_start);
-                }
+        for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
+                vma = rb_entry(p, struct vm_area_struct, vm_rb);
+                size += kobjsize(vma);
+                size += kobjsize((void *) vma->vm_start);
         }
 
         size += (*text = mm->end_code - mm->start_code);
@@ -105,20 +105,62 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
 }
 
 /*
+ * display a single VMA to a sequenced file
+ */
+static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+{
+        unsigned long ino = 0;
+        struct file *file;
+        dev_t dev = 0;
+        int flags, len;
+
+        flags = vma->vm_flags;
+        file = vma->vm_file;
+
+        if (file) {
+                struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+                dev = inode->i_sb->s_dev;
+                ino = inode->i_ino;
+        }
+
+        seq_printf(m,
+                   "%08lx-%08lx %c%c%c%c %08lx %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 ? flags & VM_SHARED ? 'S' : 's' : 'p',
+                   vma->vm_pgoff << PAGE_SHIFT,
+                   MAJOR(dev), MINOR(dev), ino, &len);
+
+        if (file) {
+                len = 25 + sizeof(void *) * 6 - len;
+                if (len < 1)
+                        len = 1;
+                seq_printf(m, "%*c", len, ' ');
+                seq_path(m, &file->f_path, "");
+        }
+
+        seq_putc(m, '\n');
+        return 0;
+}
+
+/*
  * display mapping lines for a particular process's /proc/pid/maps
  */
-static int show_map(struct seq_file *m, void *_vml)
+static int show_map(struct seq_file *m, void *_p)
 {
-        struct vm_list_struct *vml = _vml;
+        struct rb_node *p = _p;
 
-        return nommu_vma_show(m, vml->vma);
+        return nommu_vma_show(m, rb_entry(p, struct vm_area_struct, vm_rb));
 }
 
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
         struct proc_maps_private *priv = m->private;
-        struct vm_list_struct *vml;
         struct mm_struct *mm;
+        struct rb_node *p;
         loff_t n = *pos;
 
         /* pin the task and mm whilst we play with them */
@@ -134,9 +176,9 @@ static void *m_start(struct seq_file *m, loff_t *pos)
         }
 
         /* start from the Nth VMA */
-        for (vml = mm->context.vmlist; vml; vml = vml->next)
+        for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
                 if (n-- == 0)
-                        return vml;
+                        return p;
         return NULL;
 }
 
@@ -152,12 +194,12 @@ static void m_stop(struct seq_file *m, void *_vml)
         }
 }
 
-static void *m_next(struct seq_file *m, void *_vml, loff_t *pos)
+static void *m_next(struct seq_file *m, void *_p, loff_t *pos)
 {
-        struct vm_list_struct *vml = _vml;
+        struct rb_node *p = _p;
 
         (*pos)++;
-        return vml ? vml->next : NULL;
+        return p ? rb_next(p) : NULL;
 }
 
 static const struct seq_operations proc_pid_maps_ops = {