The patch titled
Subject: mm-restructure-memfd-code-fix
has been added to the -mm tree. Its filename is
mm-restructure-memfd-code-fix.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-restructure-memfd-code-fix.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-restructure-memfd-code-fix.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Subject: mm-restructure-memfd-code-fix
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/shmem.c | 237 ---------------------------------------------------
1 file changed, 237 deletions(-)
diff -puN mm/shmem.c~mm-restructure-memfd-code-fix mm/shmem.c
--- a/mm/shmem.c~mm-restructure-memfd-code-fix
+++ a/mm/shmem.c
@@ -2618,243 +2618,6 @@ static loff_t shmem_file_llseek(struct f
return offset;
}
-/*
- * We need a tag: a new tag would expand every radix_tree_node by 8 bytes,
- * so reuse a tag which we firmly believe is never set or cleared on tmpfs
- * or hugetlbfs because they are memory only filesystems.
- */
-#define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE
-#define LAST_SCAN 4 /* about 150ms max */
-
-static void memfd_tag_pins(struct address_space *mapping)
-{
- struct radix_tree_iter iter;
- void __rcu **slot;
- pgoff_t start;
- struct page *page;
-
- lru_add_drain();
- start = 0;
- rcu_read_lock();
-
- radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
- page = radix_tree_deref_slot(slot);
- if (!page || radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
- } else if (page_count(page) - page_mapcount(page) > 1) {
- xa_lock_irq(&mapping->i_pages);
- radix_tree_tag_set(&mapping->i_pages, iter.index,
- MEMFD_TAG_PINNED);
- xa_unlock_irq(&mapping->i_pages);
- }
-
- if (need_resched()) {
- slot = radix_tree_iter_resume(slot, &iter);
- cond_resched_rcu();
- }
- }
- rcu_read_unlock();
-}
-
-/*
- * Setting SEAL_WRITE requires us to verify there's no pending writer. However,
- * via get_user_pages(), drivers might have some pending I/O without any active
- * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages
- * and see whether it has an elevated ref-count. If so, we tag them and wait for
- * them to be dropped.
- * The caller must guarantee that no new user will acquire writable references
- * to those pages to avoid races.
- */
-static int memfd_wait_for_pins(struct address_space *mapping)
-{
- struct radix_tree_iter iter;
- void __rcu **slot;
- pgoff_t start;
- struct page *page;
- int error, scan;
-
- memfd_tag_pins(mapping);
-
- error = 0;
- for (scan = 0; scan <= LAST_SCAN; scan++) {
- if (!radix_tree_tagged(&mapping->i_pages, MEMFD_TAG_PINNED))
- break;
-
- if (!scan)
- lru_add_drain_all();
- else if (schedule_timeout_killable((HZ << scan) / 200))
- scan = LAST_SCAN;
-
- start = 0;
- rcu_read_lock();
- radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter,
- start, MEMFD_TAG_PINNED) {
-
- page = radix_tree_deref_slot(slot);
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
-
- page = NULL;
- }
-
- if (page &&
- page_count(page) - page_mapcount(page) != 1) {
- if (scan < LAST_SCAN)
- goto continue_resched;
-
- /*
- * On the last scan, we clean up all those tags
- * we inserted; but make a note that we still
- * found pages pinned.
- */
- error = -EBUSY;
- }
-
- xa_lock_irq(&mapping->i_pages);
- radix_tree_tag_clear(&mapping->i_pages,
- iter.index, MEMFD_TAG_PINNED);
- xa_unlock_irq(&mapping->i_pages);
-continue_resched:
- if (need_resched()) {
- slot = radix_tree_iter_resume(slot, &iter);
- cond_resched_rcu();
- }
- }
- rcu_read_unlock();
- }
-
- return error;
-}
-
-static unsigned int *memfd_file_seals_ptr(struct file *file)
-{
- if (shmem_file(file))
- return &SHMEM_I(file_inode(file))->seals;
-
-#ifdef CONFIG_HUGETLBFS
- if (is_file_hugepages(file))
- return &HUGETLBFS_I(file_inode(file))->seals;
-#endif
-
- return NULL;
-}
-
-#define F_ALL_SEALS (F_SEAL_SEAL | \
- F_SEAL_SHRINK | \
- F_SEAL_GROW | \
- F_SEAL_WRITE)
-
-static int memfd_add_seals(struct file *file, unsigned int seals)
-{
- struct inode *inode = file_inode(file);
- unsigned int *file_seals;
- int error;
-
- /*
- * SEALING
- * Sealing allows multiple parties to share a tmpfs or hugetlbfs file
- * but restrict access to a specific subset of file operations. Seals
- * can only be added, but never removed. This way, mutually untrusted
- * parties can share common memory regions with a well-defined policy.
- * A malicious peer can thus never perform unwanted operations on a
- * shared object.
- *
- * Seals are only supported on special tmpfs or hugetlbfs files and
- * always affect the whole underlying inode. Once a seal is set, it
- * may prevent some kinds of access to the file. Currently, the
- * following seals are defined:
- * SEAL_SEAL: Prevent further seals from being set on this file
- * SEAL_SHRINK: Prevent the file from shrinking
- * SEAL_GROW: Prevent the file from growing
- * SEAL_WRITE: Prevent write access to the file
- *
- * As we don't require any trust relationship between two parties, we
- * must prevent seals from being removed. Therefore, sealing a file
- * only adds a given set of seals to the file, it never touches
- * existing seals. Furthermore, the "setting seals"-operation can be
- * sealed itself, which basically prevents any further seal from being
- * added.
- *
- * Semantics of sealing are only defined on volatile files. Only
- * anonymous tmpfs and hugetlbfs files support sealing. More
- * importantly, seals are never written to disk. Therefore, there's
- * no plan to support it on other file types.
- */
-
- if (!(file->f_mode & FMODE_WRITE))
- return -EPERM;
- if (seals & ~(unsigned int)F_ALL_SEALS)
- return -EINVAL;
-
- inode_lock(inode);
-
- file_seals = memfd_file_seals_ptr(file);
- if (!file_seals) {
- error = -EINVAL;
- goto unlock;
- }
-
- if (*file_seals & F_SEAL_SEAL) {
- error = -EPERM;
- goto unlock;
- }
-
- if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) {
- error = mapping_deny_writable(file->f_mapping);
- if (error)
- goto unlock;
-
- error = memfd_wait_for_pins(file->f_mapping);
- if (error) {
- mapping_allow_writable(file->f_mapping);
- goto unlock;
- }
- }
-
- *file_seals |= seals;
- error = 0;
-
-unlock:
- inode_unlock(inode);
- return error;
-}
-
-static int memfd_get_seals(struct file *file)
-{
- unsigned int *seals = memfd_file_seals_ptr(file);
-
- return seals ? *seals : -EINVAL;
-}
-
-long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- long error;
-
- switch (cmd) {
- case F_ADD_SEALS:
- /* disallow upper 32bit */
- if (arg > UINT_MAX)
- return -EINVAL;
-
- error = memfd_add_seals(file, arg);
- break;
- case F_GET_SEALS:
- error = memfd_get_seals(file);
- break;
- default:
- error = -EINVAL;
- break;
- }
-
- return error;
-}
-
static long shmem_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
diff -puN mm/memfd.c~mm-restructure-memfd-code-fix mm/memfd.c
_
Patches currently in -mm which might be from akpm@xxxxxxxxxxxxxxxxxxxx are
i-need-old-gcc.patch
mm-pagemap-fix-swap-offset-value-for-pmd-migration-entry-fix.patch
writeback-safer-lock-nesting-fix.patch
arm-arch-arm-include-asm-pageh-needs-personalityh.patch
ocfs2-without-quota-support-try-to-avoid-calling-quota-recovery-checkpatch-fixes.patch
mm.patch
zram-introduce-zram-memory-tracking-update-fix.patch
mm-check-for-sigkill-inside-dup_mmap-loop-fix.patch
list_lru-prefetch-neighboring-list-entries-before-acquiring-lock-fix.patch
mm-oom-cgroup-aware-oom-killer-fix.patch
mm-oom-docs-describe-the-cgroup-aware-oom-killer-fix-2-fix.patch
mm-oom-cgroup-aware-oom-killer-fix-fix.patch
proc-simpler-iterations-for-proc-cmdline-fix.patch
ida-remove-simple_ida_lock-fix.patch
linux-next-git-rejects.patch
kernel-forkc-export-kernel_thread-to-modules.patch
slab-leaks3-default-y.patch
mm-restructure-memfd-code-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
