[RFC][PATCH] Anonymous shared memory (ashmem) subsystem

From: John Stultz
Date: Mon Jul 18 2011 - 14:55:38 EST


From: Robert Love <rlove@xxxxxxxxxx>

Recently, Robert Love updated his ashmem patch and posted it here:
http://www.kernel.org/pub/linux/kernel/people/rml/ashmem/

This reminded me that in all the conversations around the Android patches,
I've not seen any discussion on lkml about the ashmem functionality.
Coming from Robert, its very clean and self-contained and seems pretty
interesting. So I wanted to send it out for review and comments.

thanks
-john


The anonymous shared memory (ashmem) subsystem provides a Unix-y,file-based
shared memory interface to user-space. It works like anonymous memory (e.g.
mmapping fd=0) except if you share the file descriptor via the usual means, you
will share the mapping. The shared memory can be accessed via both mmap or file
I/O. The backing store is a simple shmem file.

Additionally, ashmem introduces the concept of page pinning. Pinned pages (the
default) behave like any anonymous memory. Unpinned pages are available to the
kernel for eviction during VM pressure. When repinning the pages, the return
value instructs user-space as to any eviction. In this manner, user-space
processes may implement caching and similar resource management that
efficiently integrates with kernel memory management.

CC: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
CC: Hugh Dickins <hughd@xxxxxxxxxx>
CC: Mel Gorman <mel@xxxxxxxxx>
CC: Dave Hansen <dave@xxxxxxxxxxxxxxxxxx>
CC: Rik van Riel <riel@xxxxxxxxxx>
CC: Eric Anholt <eric@xxxxxxxxxx>
CC: Jesse Barnes <jbarnes@xxxxxxxxxxxxxxxx>
Signed-off-by: Robert Love <rlove@xxxxxxxxxx>
[jstultz: minor whitespace fixes for checkpatch.pl]
Signed-off-by: John Stultz <john.stultz@xxxxxxxxxx>
---
include/linux/ashmem.h | 48 +++
include/linux/mm.h | 1 +
init/Kconfig | 12 +
mm/Makefile | 1 +
mm/ashmem.c | 747 ++++++++++++++++++++++++++++++++++++++++++++++++
mm/shmem.c | 14 +-
6 files changed, 818 insertions(+), 5 deletions(-)
create mode 100644 include/linux/ashmem.h
create mode 100644 mm/ashmem.c

diff --git a/include/linux/ashmem.h b/include/linux/ashmem.h
new file mode 100644
index 0000000..1976b10
--- /dev/null
+++ b/include/linux/ashmem.h
@@ -0,0 +1,48 @@
+/*
+ * include/linux/ashmem.h
+ *
+ * Copyright 2008 Google Inc.
+ * Author: Robert Love
+ *
+ * This file is dual licensed. It may be redistributed and/or modified
+ * under the terms of the Apache 2.0 License OR version 2 of the GNU
+ * General Public License.
+ */
+
+#ifndef _LINUX_ASHMEM_H
+#define _LINUX_ASHMEM_H
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+
+#define ASHMEM_NAME_LEN 256
+
+#define ASHMEM_NAME_DEF "dev/ashmem"
+
+/* Return values from ASHMEM_PIN: Was the mapping purged while unpinned? */
+#define ASHMEM_NOT_PURGED 0
+#define ASHMEM_WAS_PURGED 1
+
+/* Return values from ASHMEM_GET_PIN_STATUS: Is the mapping pinned? */
+#define ASHMEM_IS_UNPINNED 0
+#define ASHMEM_IS_PINNED 1
+
+struct ashmem_pin {
+ __u32 offset; /* offset into region, in bytes, page-aligned */
+ __u32 len; /* length forward from offset, in bytes, page-aligned */
+};
+
+#define __ASHMEMIOC 0x77
+
+#define ASHMEM_SET_NAME _IOW(__ASHMEMIOC, 1, char[ASHMEM_NAME_LEN])
+#define ASHMEM_GET_NAME _IOR(__ASHMEMIOC, 2, char[ASHMEM_NAME_LEN])
+#define ASHMEM_SET_SIZE _IOW(__ASHMEMIOC, 3, size_t)
+#define ASHMEM_GET_SIZE _IO(__ASHMEMIOC, 4)
+#define ASHMEM_SET_PROT_MASK _IOW(__ASHMEMIOC, 5, unsigned long)
+#define ASHMEM_GET_PROT_MASK _IO(__ASHMEMIOC, 6)
+#define ASHMEM_PIN _IOW(__ASHMEMIOC, 7, struct ashmem_pin)
+#define ASHMEM_UNPIN _IOW(__ASHMEMIOC, 8, struct ashmem_pin)
+#define ASHMEM_GET_PIN_STATUS _IO(__ASHMEMIOC, 9)
+#define ASHMEM_PURGE_ALL_CACHES _IO(__ASHMEMIOC, 10)
+
+#endif /* _LINUX_ASHMEM_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9670f71..de20025 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -871,6 +871,7 @@ extern bool skip_free_areas_node(unsigned int flags, int nid);

int shmem_lock(struct file *file, int lock, struct user_struct *user);
struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
+void shmem_set_file(struct vm_area_struct *vma, struct file *file);
int shmem_zero_setup(struct vm_area_struct *);

extern int can_do_mlock(void);
diff --git a/init/Kconfig b/init/Kconfig
index 412c21b..e9f7058 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1081,6 +1081,18 @@ config SHMEM
option replaces shmem and tmpfs with the much simpler ramfs code,
which may be appropriate on small systems without swap.

+config ASHMEM
+ bool "Enable the Anonymous Shared Memory Subsystem"
+ default n
+ depends on SHMEM || TINY_SHMEM
+ help
+ The ashmem subsystem is a new shared memory allocator available to
+ user-space, similar to POSIX SHM but with different behavior and a
+ more Unix-y, file-based API. The ashmem subsystem also supports
+ the eviction of unpinned pages during VM pressure, allowing
+ user-space to implement caches that are automatically shrunk when
+ memory is low.
+
config AIO
bool "Enable AIO support" if EXPERT
default y
diff --git a/mm/Makefile b/mm/Makefile
index 836e416..cd41f09 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_HUGETLBFS) += hugetlb.o
obj-$(CONFIG_NUMA) += mempolicy.o
obj-$(CONFIG_SPARSEMEM) += sparse.o
obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
+obj-$(CONFIG_ASHMEM) += ashmem.o
obj-$(CONFIG_SLOB) += slob.o
obj-$(CONFIG_COMPACTION) += compaction.o
obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
diff --git a/mm/ashmem.c b/mm/ashmem.c
new file mode 100644
index 0000000..7bb3c84
--- /dev/null
+++ b/mm/ashmem.c
@@ -0,0 +1,747 @@
+/* mm/ashmem.c
+**
+** Anonymous Shared Memory Subsystem, ashmem
+**
+** Copyright (C) 2008 Google, Inc.
+**
+** Robert Love <rlove@xxxxxxxxxx>
+**
+** This software is licensed under the terms of the GNU General Public
+** License version 2, as published by the Free Software Foundation, and
+** may be copied, distributed, and modified under those terms.
+**
+** This program is distributed in the hope that it will be useful,
+** but WITHOUT ANY WARRANTY; without even the implied warranty of
+** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+** GNU General Public License for more details.
+*/
+
+#include <linux/module.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/security.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/uaccess.h>
+#include <linux/personality.h>
+#include <linux/bitops.h>
+#include <linux/mutex.h>
+#include <linux/shmem_fs.h>
+#include <linux/ashmem.h>
+
+#define ASHMEM_NAME_PREFIX "dev/ashmem/"
+#define ASHMEM_NAME_PREFIX_LEN (sizeof(ASHMEM_NAME_PREFIX) - 1)
+#define ASHMEM_FULL_NAME_LEN (ASHMEM_NAME_LEN + ASHMEM_NAME_PREFIX_LEN)
+
+/*
+ * ashmem_area - anonymous shared memory area
+ * Lifecycle: From our parent file's open() until its release()
+ * Locking: Protected by `ashmem_mutex'
+ * Big Note: Mappings do NOT pin this structure; it dies on close()
+ */
+struct ashmem_area {
+ char name[ASHMEM_FULL_NAME_LEN]; /* optional name in /proc/pid/maps */
+ struct list_head unpinned_list; /* list of all ashmem areas */
+ struct file *file; /* the shmem-based backing file */
+ size_t size; /* size of the mapping, in bytes */
+ unsigned long prot_mask; /* allowed prot bits, as vm_flags */
+};
+
+/*
+ * ashmem_range - represents an interval of unpinned (evictable) pages
+ * Lifecycle: From unpin to pin
+ * Locking: Protected by `ashmem_mutex'
+ */
+struct ashmem_range {
+ struct list_head lru; /* entry in LRU list */
+ struct list_head unpinned; /* entry in its area's unpinned list */
+ struct ashmem_area *asma; /* associated area */
+ size_t pgstart; /* starting page, inclusive */
+ size_t pgend; /* ending page, inclusive */
+ unsigned int purged; /* ASHMEM_NOT or ASHMEM_WAS_PURGED */
+};
+
+/* LRU list of unpinned pages, protected by ashmem_mutex */
+static LIST_HEAD(ashmem_lru_list);
+
+/* Count of pages on our LRU list, protected by ashmem_mutex */
+static unsigned long lru_count;
+
+/*
+ * ashmem_mutex - protects the list of and each individual ashmem_area
+ *
+ * Lock Ordering: ashmex_mutex -> i_mutex -> i_alloc_sem
+ */
+static DEFINE_MUTEX(ashmem_mutex);
+
+static struct kmem_cache *ashmem_area_cachep __read_mostly;
+static struct kmem_cache *ashmem_range_cachep __read_mostly;
+
+#define range_size(range) \
+ ((range)->pgend - (range)->pgstart + 1)
+
+#define range_on_lru(range) \
+ ((range)->purged == ASHMEM_NOT_PURGED)
+
+#define page_range_subsumes_range(range, start, end) \
+ (((range)->pgstart >= (start)) && ((range)->pgend <= (end)))
+
+#define page_range_subsumed_by_range(range, start, end) \
+ (((range)->pgstart <= (start)) && ((range)->pgend >= (end)))
+
+#define page_in_range(range, page) \
+ (((range)->pgstart <= (page)) && ((range)->pgend >= (page)))
+
+#define page_range_in_range(range, start, end) \
+ (page_in_range(range, start) || page_in_range(range, end) || \
+ page_range_subsumes_range(range, start, end))
+
+#define range_before_page(range, page) \
+ ((range)->pgend < (page))
+
+#define PROT_MASK (PROT_EXEC | PROT_READ | PROT_WRITE)
+
+static inline void lru_add(struct ashmem_range *range)
+{
+ list_add_tail(&range->lru, &ashmem_lru_list);
+ lru_count += range_size(range);
+}
+
+static inline void lru_del(struct ashmem_range *range)
+{
+ list_del(&range->lru);
+ lru_count -= range_size(range);
+}
+
+/*
+ * range_alloc - allocate and initialize a new ashmem_range structure
+ *
+ * 'asma' - associated ashmem_area
+ * 'prev_range' - the previous ashmem_range in the sorted asma->unpinned list
+ * 'purged' - initial purge value (ASMEM_NOT_PURGED or ASHMEM_WAS_PURGED)
+ * 'start' - starting page, inclusive
+ * 'end' - ending page, inclusive
+ *
+ * Caller must hold ashmem_mutex.
+ */
+static int range_alloc(struct ashmem_area *asma,
+ struct ashmem_range *prev_range, unsigned int purged,
+ size_t start, size_t end)
+{
+ struct ashmem_range *range;
+
+ range = kmem_cache_zalloc(ashmem_range_cachep, GFP_KERNEL);
+ if (unlikely(!range))
+ return -ENOMEM;
+
+ range->asma = asma;
+ range->pgstart = start;
+ range->pgend = end;
+ range->purged = purged;
+
+ list_add_tail(&range->unpinned, &prev_range->unpinned);
+
+ if (range_on_lru(range))
+ lru_add(range);
+
+ return 0;
+}
+
+static void range_del(struct ashmem_range *range)
+{
+ list_del(&range->unpinned);
+ if (range_on_lru(range))
+ lru_del(range);
+ kmem_cache_free(ashmem_range_cachep, range);
+}
+
+/*
+ * range_shrink - shrinks a range
+ *
+ * Caller must hold ashmem_mutex.
+ */
+static inline void range_shrink(struct ashmem_range *range,
+ size_t start, size_t end)
+{
+ size_t pre = range_size(range);
+
+ range->pgstart = start;
+ range->pgend = end;
+
+ if (range_on_lru(range))
+ lru_count -= pre - range_size(range);
+}
+
+static int ashmem_open(struct inode *inode, struct file *file)
+{
+ struct ashmem_area *asma;
+ int ret;
+
+ ret = generic_file_open(inode, file);
+ if (unlikely(ret))
+ return ret;
+
+ asma = kmem_cache_zalloc(ashmem_area_cachep, GFP_KERNEL);
+ if (unlikely(!asma))
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&asma->unpinned_list);
+ memcpy(asma->name, ASHMEM_NAME_PREFIX, ASHMEM_NAME_PREFIX_LEN);
+ asma->prot_mask = PROT_MASK;
+ file->private_data = asma;
+
+ return 0;
+}
+
+static int ashmem_release(struct inode *ignored, struct file *file)
+{
+ struct ashmem_area *asma = file->private_data;
+ struct ashmem_range *range, *next;
+
+ mutex_lock(&ashmem_mutex);
+ list_for_each_entry_safe(range, next, &asma->unpinned_list, unpinned)
+ range_del(range);
+ mutex_unlock(&ashmem_mutex);
+
+ if (asma->file)
+ fput(asma->file);
+ kmem_cache_free(ashmem_area_cachep, asma);
+
+ return 0;
+}
+
+static ssize_t ashmem_read(struct file *file, char __user *buf,
+ size_t len, loff_t *pos)
+{
+ struct ashmem_area *asma = file->private_data;
+ int ret = 0;
+
+ mutex_lock(&ashmem_mutex);
+
+ /* If size is not set, or set to 0, always return EOF. */
+ if (asma->size == 0)
+ goto out;
+
+ if (!asma->file) {
+ ret = -EBADF;
+ goto out;
+ }
+
+ ret = asma->file->f_op->read(asma->file, buf, len, pos);
+ if (ret < 0)
+ goto out;
+
+ /** Update backing file pos, since f_ops->read() doesn't */
+ asma->file->f_pos = *pos;
+
+out:
+ mutex_unlock(&ashmem_mutex);
+ return ret;
+}
+
+static loff_t ashmem_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct ashmem_area *asma = file->private_data;
+ int ret;
+
+ mutex_lock(&ashmem_mutex);
+
+ if (asma->size == 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!asma->file) {
+ ret = -EBADF;
+ goto out;
+ }
+
+ ret = asma->file->f_op->llseek(asma->file, offset, origin);
+ if (ret < 0)
+ goto out;
+
+ /** Copy f_pos from backing file, since f_ops->llseek() sets it */
+ file->f_pos = asma->file->f_pos;
+
+out:
+ mutex_unlock(&ashmem_mutex);
+ return ret;
+}
+
+static inline unsigned long calc_vm_may_flags(unsigned long prot)
+{
+ return _calc_vm_trans(prot, PROT_READ, VM_MAYREAD) |
+ _calc_vm_trans(prot, PROT_WRITE, VM_MAYWRITE) |
+ _calc_vm_trans(prot, PROT_EXEC, VM_MAYEXEC);
+}
+
+static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct ashmem_area *asma = file->private_data;
+ int ret = 0;
+
+ mutex_lock(&ashmem_mutex);
+
+ /* user needs to SET_SIZE before mapping */
+ if (unlikely(!asma->size)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* requested protection bits must match our allowed protection mask */
+ if (unlikely((vma->vm_flags & ~calc_vm_prot_bits(asma->prot_mask)) &
+ calc_vm_prot_bits(PROT_MASK))) {
+ ret = -EPERM;
+ goto out;
+ }
+ vma->vm_flags &= ~calc_vm_may_flags(~asma->prot_mask);
+
+ if (!asma->file) {
+ char *name = ASHMEM_NAME_DEF;
+ struct file *vmfile;
+
+ if (asma->name[ASHMEM_NAME_PREFIX_LEN] != '\0')
+ name = asma->name;
+
+ /* ... and allocate the backing shmem file */
+ vmfile = shmem_file_setup(name, asma->size, vma->vm_flags);
+ if (unlikely(IS_ERR(vmfile))) {
+ ret = PTR_ERR(vmfile);
+ goto out;
+ }
+ asma->file = vmfile;
+ }
+ get_file(asma->file);
+
+ if (vma->vm_flags & VM_SHARED)
+ shmem_set_file(vma, asma->file);
+ else {
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = asma->file;
+ }
+ vma->vm_flags |= VM_CAN_NONLINEAR;
+
+out:
+ mutex_unlock(&ashmem_mutex);
+ return ret;
+}
+
+/*
+ * ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab
+ *
+ * The shrink_control object contains two members we (currently) care about:
+ *
+ * 'nr_to_scan' is the number of objects (pages) to prune, or 0 to query how
+ * many objects (pages) we have in total.
+ *
+ * 'gfp_mask' is the mask of the allocation that got us into this mess.
+ *
+ * Return value is the number of objects (pages) remaining, or -1 if we cannot
+ * proceed without risk of deadlock (due to gfp_mask).
+ *
+ * We approximate LRU via least-recently-unpinned, jettisoning unpinned partial
+ * chunks of ashmem regions LRU-wise one-at-a-time until we hit 'nr_to_scan'
+ * pages freed.
+ */
+static int ashmem_shrink(struct shrinker *ignored, struct shrink_control *sc)
+{
+ struct ashmem_range *range, *next;
+ unsigned long nr_to_scan = sc->nr_to_scan;
+ const gfp_t gfp_mask = sc->gfp_mask;
+
+ /* We might recurse into filesystem code, so bail out if necessary */
+ if (nr_to_scan && !(gfp_mask & __GFP_FS))
+ return -1;
+ if (!nr_to_scan)
+ return lru_count;
+
+ mutex_lock(&ashmem_mutex);
+ list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) {
+ struct inode *inode = range->asma->file->f_dentry->d_inode;
+ loff_t start = range->pgstart * PAGE_SIZE;
+ loff_t end = (range->pgend + 1) * PAGE_SIZE - 1;
+
+ vmtruncate_range(inode, start, end);
+ range->purged = ASHMEM_WAS_PURGED;
+ lru_del(range);
+
+ nr_to_scan -= range_size(range);
+ if (nr_to_scan <= 0)
+ break;
+ }
+ mutex_unlock(&ashmem_mutex);
+
+ return lru_count;
+}
+
+static struct shrinker ashmem_shrinker = {
+ .shrink = ashmem_shrink,
+ .seeks = DEFAULT_SEEKS * 4,
+};
+
+static int set_prot_mask(struct ashmem_area *asma, unsigned long prot)
+{
+ int ret = 0;
+
+ mutex_lock(&ashmem_mutex);
+
+ /* the user can only remove, not add, protection bits */
+ if (unlikely((asma->prot_mask & prot) != prot)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* does the application expect PROT_READ to imply PROT_EXEC? */
+ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
+ prot |= PROT_EXEC;
+
+ asma->prot_mask = prot;
+
+out:
+ mutex_unlock(&ashmem_mutex);
+ return ret;
+}
+
+static int set_name(struct ashmem_area *asma, void __user *name)
+{
+ int ret = 0;
+
+ mutex_lock(&ashmem_mutex);
+
+ /* cannot change an existing mapping's name */
+ if (unlikely(asma->file)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (unlikely(copy_from_user(asma->name + ASHMEM_NAME_PREFIX_LEN,
+ name, ASHMEM_NAME_LEN)))
+ ret = -EFAULT;
+ asma->name[ASHMEM_FULL_NAME_LEN-1] = '\0';
+
+out:
+ mutex_unlock(&ashmem_mutex);
+
+ return ret;
+}
+
+static int get_name(struct ashmem_area *asma, void __user *name)
+{
+ int ret = 0;
+
+ mutex_lock(&ashmem_mutex);
+ if (asma->name[ASHMEM_NAME_PREFIX_LEN] != '\0') {
+ size_t len;
+
+ /*
+ * Copying only `len', instead of ASHMEM_NAME_LEN, bytes
+ * prevents us from revealing one user's stack to another.
+ */
+ len = strlen(asma->name + ASHMEM_NAME_PREFIX_LEN) + 1;
+ if (unlikely(copy_to_user(name,
+ asma->name + ASHMEM_NAME_PREFIX_LEN, len)))
+ ret = -EFAULT;
+ } else {
+ if (unlikely(copy_to_user(name, ASHMEM_NAME_DEF,
+ sizeof(ASHMEM_NAME_DEF))))
+ ret = -EFAULT;
+ }
+ mutex_unlock(&ashmem_mutex);
+
+ return ret;
+}
+
+/*
+ * ashmem_pin - pin the given ashmem region, returning whether it was
+ * previously purged (ASHMEM_WAS_PURGED) or not (ASHMEM_NOT_PURGED).
+ *
+ * Caller must hold ashmem_mutex.
+ */
+static int ashmem_pin(struct ashmem_area *asma, size_t pgstart, size_t pgend)
+{
+ struct ashmem_range *range, *next;
+ int ret = ASHMEM_NOT_PURGED;
+
+ list_for_each_entry_safe(range, next, &asma->unpinned_list, unpinned) {
+ /* moved past last applicable page; we can short circuit */
+ if (range_before_page(range, pgstart))
+ break;
+
+ /*
+ * The user can ask us to pin pages that span multiple ranges,
+ * or to pin pages that aren't even unpinned, so this is messy.
+ *
+ * Four cases:
+ * 1. The requested range subsumes an existing range, so we
+ * just remove the entire matching range.
+ * 2. The requested range overlaps the start of an existing
+ * range, so we just update that range.
+ * 3. The requested range overlaps the end of an existing
+ * range, so we just update that range.
+ * 4. The requested range punches a hole in an existing range,
+ * so we have to update one side of the range and then
+ * create a new range for the other side.
+ */
+ if (page_range_in_range(range, pgstart, pgend)) {
+ ret |= range->purged;
+
+ /* Case #1: Easy. Just nuke the whole thing. */
+ if (page_range_subsumes_range(range, pgstart, pgend)) {
+ range_del(range);
+ continue;
+ }
+
+ /* Case #2: We overlap from the start, so adjust it */
+ if (range->pgstart >= pgstart) {
+ range_shrink(range, pgend + 1, range->pgend);
+ continue;
+ }
+
+ /* Case #3: We overlap from the rear, so adjust it */
+ if (range->pgend <= pgend) {
+ range_shrink(range, range->pgstart, pgstart-1);
+ continue;
+ }
+
+ /*
+ * Case #4: We eat a chunk out of the middle. A bit
+ * more complicated, we allocate a new range for the
+ * second half and adjust the first chunk's endpoint.
+ */
+ range_alloc(asma, range, range->purged,
+ pgend + 1, range->pgend);
+ range_shrink(range, range->pgstart, pgstart - 1);
+ break;
+ }
+ }
+
+ return ret;
+}
+
+/*
+ * ashmem_unpin - unpin the given range of pages. Returns zero on success.
+ *
+ * Caller must hold ashmem_mutex.
+ */
+static int ashmem_unpin(struct ashmem_area *asma, size_t pgstart, size_t pgend)
+{
+ struct ashmem_range *range, *next;
+ unsigned int purged = ASHMEM_NOT_PURGED;
+
+restart:
+ list_for_each_entry_safe(range, next, &asma->unpinned_list, unpinned) {
+ /* short circuit: this is our insertion point */
+ if (range_before_page(range, pgstart))
+ break;
+
+ /*
+ * The user can ask us to unpin pages that are already entirely
+ * or partially pinned. We handle those two cases here.
+ */
+ if (page_range_subsumed_by_range(range, pgstart, pgend))
+ return 0;
+ if (page_range_in_range(range, pgstart, pgend)) {
+ pgstart = min_t(size_t, range->pgstart, pgstart),
+ pgend = max_t(size_t, range->pgend, pgend);
+ purged |= range->purged;
+ range_del(range);
+ goto restart;
+ }
+ }
+
+ return range_alloc(asma, range, purged, pgstart, pgend);
+}
+
+/*
+ * ashmem_get_pin_status - Returns ASHMEM_IS_UNPINNED if _any_ pages in the
+ * given interval are unpinned and ASHMEM_IS_PINNED otherwise.
+ *
+ * Caller must hold ashmem_mutex.
+ */
+static int ashmem_get_pin_status(struct ashmem_area *asma, size_t pgstart,
+ size_t pgend)
+{
+ struct ashmem_range *range;
+ int ret = ASHMEM_IS_PINNED;
+
+ list_for_each_entry(range, &asma->unpinned_list, unpinned) {
+ if (range_before_page(range, pgstart))
+ break;
+ if (page_range_in_range(range, pgstart, pgend)) {
+ ret = ASHMEM_IS_UNPINNED;
+ break;
+ }
+ }
+
+ return ret;
+}
+
+static int ashmem_pin_unpin(struct ashmem_area *asma, unsigned long cmd,
+ void __user *p)
+{
+ struct ashmem_pin pin;
+ size_t pgstart, pgend;
+ int ret = -EINVAL;
+
+ if (unlikely(!asma->file))
+ return -EINVAL;
+
+ if (unlikely(copy_from_user(&pin, p, sizeof(pin))))
+ return -EFAULT;
+
+ /* per custom, you can pass zero for len to mean "everything onward" */
+ if (!pin.len)
+ pin.len = PAGE_ALIGN(asma->size) - pin.offset;
+
+ if (unlikely((pin.offset | pin.len) & ~PAGE_MASK))
+ return -EINVAL;
+
+ if (unlikely(((__u32) -1) - pin.offset < pin.len))
+ return -EINVAL;
+
+ if (unlikely(PAGE_ALIGN(asma->size) < pin.offset + pin.len))
+ return -EINVAL;
+
+ pgstart = pin.offset / PAGE_SIZE;
+ pgend = pgstart + (pin.len / PAGE_SIZE) - 1;
+
+ mutex_lock(&ashmem_mutex);
+
+ switch (cmd) {
+ case ASHMEM_PIN:
+ ret = ashmem_pin(asma, pgstart, pgend);
+ break;
+ case ASHMEM_UNPIN:
+ ret = ashmem_unpin(asma, pgstart, pgend);
+ break;
+ case ASHMEM_GET_PIN_STATUS:
+ ret = ashmem_get_pin_status(asma, pgstart, pgend);
+ break;
+ }
+
+ mutex_unlock(&ashmem_mutex);
+
+ return ret;
+}
+
+static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct ashmem_area *asma = file->private_data;
+ long ret = -ENOTTY;
+
+ switch (cmd) {
+ case ASHMEM_SET_NAME:
+ ret = set_name(asma, (void __user *) arg);
+ break;
+ case ASHMEM_GET_NAME:
+ ret = get_name(asma, (void __user *) arg);
+ break;
+ case ASHMEM_SET_SIZE:
+ ret = -EINVAL;
+ if (!asma->file) {
+ ret = 0;
+ asma->size = (size_t) arg;
+ }
+ break;
+ case ASHMEM_GET_SIZE:
+ ret = asma->size;
+ break;
+ case ASHMEM_SET_PROT_MASK:
+ ret = set_prot_mask(asma, arg);
+ break;
+ case ASHMEM_GET_PROT_MASK:
+ ret = asma->prot_mask;
+ break;
+ case ASHMEM_PIN:
+ case ASHMEM_UNPIN:
+ case ASHMEM_GET_PIN_STATUS:
+ ret = ashmem_pin_unpin(asma, cmd, (void __user *) arg);
+ break;
+ case ASHMEM_PURGE_ALL_CACHES:
+ ret = -EPERM;
+ if (capable(CAP_SYS_ADMIN)) {
+ struct shrink_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .nr_to_scan = 0 };
+ ret = ashmem_shrink(&ashmem_shrinker, &sc);
+ sc.nr_to_scan = ret;
+ ashmem_shrink(&ashmem_shrinker, &sc);
+ }
+ break;
+ }
+
+ return ret;
+}
+
+static const struct file_operations ashmem_fops = {
+ .owner = THIS_MODULE,
+ .open = ashmem_open,
+ .release = ashmem_release,
+ .read = ashmem_read,
+ .llseek = ashmem_llseek,
+ .mmap = ashmem_mmap,
+ .unlocked_ioctl = ashmem_ioctl,
+ .compat_ioctl = ashmem_ioctl,
+};
+
+static struct miscdevice ashmem_misc = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "ashmem",
+ .fops = &ashmem_fops,
+};
+
+static int __init ashmem_init(void)
+{
+ int ret;
+
+ ashmem_area_cachep = kmem_cache_create("ashmem_area_cache",
+ sizeof(struct ashmem_area),
+ 0, 0, NULL);
+ if (unlikely(!ashmem_area_cachep)) {
+ printk(KERN_ERR "ashmem: failed to create slab cache\n");
+ return -ENOMEM;
+ }
+
+ ashmem_range_cachep = kmem_cache_create("ashmem_range_cache",
+ sizeof(struct ashmem_range),
+ 0, 0, NULL);
+ if (unlikely(!ashmem_range_cachep)) {
+ printk(KERN_ERR "ashmem: failed to create slab cache\n");
+ return -ENOMEM;
+ }
+
+ ret = misc_register(&ashmem_misc);
+ if (unlikely(ret)) {
+ printk(KERN_ERR "ashmem: failed to register misc device!\n");
+ return ret;
+ }
+
+ register_shrinker(&ashmem_shrinker);
+
+ printk(KERN_INFO "ashmem: initialized\n");
+
+ return 0;
+}
+
+static void __exit ashmem_exit(void)
+{
+ int ret;
+
+ unregister_shrinker(&ashmem_shrinker);
+
+ ret = misc_deregister(&ashmem_misc);
+ if (unlikely(ret))
+ printk(KERN_ERR "ashmem: failed to unregister misc device!\n");
+
+ kmem_cache_destroy(ashmem_range_cachep);
+ kmem_cache_destroy(ashmem_area_cachep);
+
+ printk(KERN_INFO "ashmem: unloaded\n");
+}
+
+module_init(ashmem_init);
+module_exit(ashmem_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/mm/shmem.c b/mm/shmem.c
index fcedf54..f6de1b2 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3015,6 +3015,14 @@ put_memory:
}
EXPORT_SYMBOL_GPL(shmem_file_setup);

+void shmem_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ vma->vm_file = file;
+ vma->vm_ops = &shmem_vm_ops;
+}
+
/**
* shmem_zero_setup - setup a shared anonymous mapping
* @vma: the vma to be mmapped is prepared by do_mmap_pgoff
@@ -3027,11 +3035,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
file = shmem_file_setup("dev/zero", size, vma->vm_flags);
if (IS_ERR(file))
return PTR_ERR(file);
-
- if (vma->vm_file)
- fput(vma->vm_file);
- vma->vm_file = file;
- vma->vm_ops = &shmem_vm_ops;
+ shmem_set_file(vma, file);
vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
--
1.7.3.2.146.gca209

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/