summaryrefslogtreecommitdiffstats
path: root/kernel/mm/fadvise.c
diff options
context:
space:
mode:
authorYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 12:17:53 -0700
committerYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 15:44:42 -0700
commit9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (patch)
tree1c9cafbcd35f783a87880a10f85d1a060db1a563 /kernel/mm/fadvise.c
parent98260f3884f4a202f9ca5eabed40b1354c489b29 (diff)
Add the rt linux 4.1.3-rt3 as base
Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
Diffstat (limited to 'kernel/mm/fadvise.c')
-rw-r--r--kernel/mm/fadvise.c162
1 files changed, 162 insertions, 0 deletions
diff --git a/kernel/mm/fadvise.c b/kernel/mm/fadvise.c
new file mode 100644
index 000000000..4a3907cf7
--- /dev/null
+++ b/kernel/mm/fadvise.c
@@ -0,0 +1,162 @@
+/*
+ * mm/fadvise.c
+ *
+ * Copyright (C) 2002, Linus Torvalds
+ *
+ * 11Jan2003 Andrew Morton
+ * Initial version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
+#include <linux/fadvise.h>
+#include <linux/writeback.h>
+#include <linux/syscalls.h>
+#include <linux/swap.h>
+
+#include <asm/unistd.h>
+
+/*
+ * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
+ * deactivate the pages and clear PG_Referenced.
+ */
+SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
+{
+ struct fd f = fdget(fd);
+ struct inode *inode;
+ struct address_space *mapping;
+ struct backing_dev_info *bdi;
+ loff_t endbyte; /* inclusive */
+ pgoff_t start_index;
+ pgoff_t end_index;
+ unsigned long nrpages;
+ int ret = 0;
+
+ if (!f.file)
+ return -EBADF;
+
+ inode = file_inode(f.file);
+ if (S_ISFIFO(inode->i_mode)) {
+ ret = -ESPIPE;
+ goto out;
+ }
+
+ mapping = f.file->f_mapping;
+ if (!mapping || len < 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (IS_DAX(inode)) {
+ switch (advice) {
+ case POSIX_FADV_NORMAL:
+ case POSIX_FADV_RANDOM:
+ case POSIX_FADV_SEQUENTIAL:
+ case POSIX_FADV_WILLNEED:
+ case POSIX_FADV_NOREUSE:
+ case POSIX_FADV_DONTNEED:
+ /* no bad return value, but ignore advice */
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ goto out;
+ }
+
+ /* Careful about overflows. Len == 0 means "as much as possible" */
+ endbyte = offset + len;
+ if (!len || endbyte < len)
+ endbyte = -1;
+ else
+ endbyte--; /* inclusive */
+
+ bdi = inode_to_bdi(mapping->host);
+
+ switch (advice) {
+ case POSIX_FADV_NORMAL:
+ f.file->f_ra.ra_pages = bdi->ra_pages;
+ spin_lock(&f.file->f_lock);
+ f.file->f_mode &= ~FMODE_RANDOM;
+ spin_unlock(&f.file->f_lock);
+ break;
+ case POSIX_FADV_RANDOM:
+ spin_lock(&f.file->f_lock);
+ f.file->f_mode |= FMODE_RANDOM;
+ spin_unlock(&f.file->f_lock);
+ break;
+ case POSIX_FADV_SEQUENTIAL:
+ f.file->f_ra.ra_pages = bdi->ra_pages * 2;
+ spin_lock(&f.file->f_lock);
+ f.file->f_mode &= ~FMODE_RANDOM;
+ spin_unlock(&f.file->f_lock);
+ break;
+ case POSIX_FADV_WILLNEED:
+ /* First and last PARTIAL page! */
+ start_index = offset >> PAGE_CACHE_SHIFT;
+ end_index = endbyte >> PAGE_CACHE_SHIFT;
+
+ /* Careful about overflow on the "+1" */
+ nrpages = end_index - start_index + 1;
+ if (!nrpages)
+ nrpages = ~0UL;
+
+ /*
+ * Ignore return value because fadvise() shall return
+ * success even if filesystem can't retrieve a hint,
+ */
+ force_page_cache_readahead(mapping, f.file, start_index,
+ nrpages);
+ break;
+ case POSIX_FADV_NOREUSE:
+ break;
+ case POSIX_FADV_DONTNEED:
+ if (!bdi_write_congested(bdi))
+ __filemap_fdatawrite_range(mapping, offset, endbyte,
+ WB_SYNC_NONE);
+
+ /*
+ * First and last FULL page! Partial pages are deliberately
+ * preserved on the expectation that it is better to preserve
+ * needed memory than to discard unneeded memory.
+ */
+ start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
+ end_index = (endbyte >> PAGE_CACHE_SHIFT);
+
+ if (end_index >= start_index) {
+ unsigned long count = invalidate_mapping_pages(mapping,
+ start_index, end_index);
+
+ /*
+ * If fewer pages were invalidated than expected then
+ * it is possible that some of the pages were on
+ * a per-cpu pagevec for a remote CPU. Drain all
+ * pagevecs and try again.
+ */
+ if (count < (end_index - start_index + 1)) {
+ lru_add_drain_all();
+ invalidate_mapping_pages(mapping, start_index,
+ end_index);
+ }
+ }
+ break;
+ default:
+ ret = -EINVAL;
+ }
+out:
+ fdput(f);
+ return ret;
+}
+
+#ifdef __ARCH_WANT_SYS_FADVISE64
+
+SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
+{
+ return sys_fadvise64_64(fd, offset, len, advice);
+}
+
+#endif