summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Makefile3
-rw-r--r--mm/filemap.c344
-rw-r--r--mm/iov_iter.c224
-rw-r--r--mm/process_vm_access.c250
-rw-r--r--mm/shmem.c79
-rw-r--r--mm/slab.c183
-rw-r--r--mm/slob.c10
-rw-r--r--mm/slub.c5
-rw-r--r--mm/util.c48
9 files changed, 552 insertions, 594 deletions
diff --git a/mm/Makefile b/mm/Makefile
index 9e5aaf92197..b484452dac5 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -17,7 +17,8 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
util.o mmzone.o vmstat.o backing-dev.o \
mm_init.o mmu_context.o percpu.o slab_common.o \
compaction.o balloon_compaction.o vmacache.o \
- interval_tree.o list_lru.o workingset.o $(mmu-y)
+ interval_tree.o list_lru.o workingset.o \
+ iov_iter.o $(mmu-y)
obj-y += init-mm.o
diff --git a/mm/filemap.c b/mm/filemap.c
index 27ebc0c9571..a82fbe4c9e8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -77,7 +77,7 @@
* ->mmap_sem
* ->lock_page (access_process_vm)
*
- * ->i_mutex (generic_file_buffered_write)
+ * ->i_mutex (generic_perform_write)
* ->mmap_sem (fault_in_pages_readable->do_page_fault)
*
* bdi->wb.list_lock
@@ -1428,7 +1428,8 @@ static void shrink_readahead_size_eio(struct file *filp,
* do_generic_file_read - generic file read routine
* @filp: the file to read
* @ppos: current file position
- * @desc: read_descriptor
+ * @iter: data destination
+ * @written: already copied
*
* This is a generic file read routine, and uses the
* mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -1436,8 +1437,8 @@ static void shrink_readahead_size_eio(struct file *filp,
* This is really ugly. But the goto's actually try to clarify some
* of the logic when it comes to error handling etc.
*/
-static void do_generic_file_read(struct file *filp, loff_t *ppos,
- read_descriptor_t *desc)
+static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
+ struct iov_iter *iter, ssize_t written)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
@@ -1447,12 +1448,12 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos,
pgoff_t prev_index;
unsigned long offset; /* offset into pagecache page */
unsigned int prev_offset;
- int error;
+ int error = 0;
index = *ppos >> PAGE_CACHE_SHIFT;
prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT;
prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1);
- last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+ last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
for (;;) {
@@ -1487,7 +1488,7 @@ find_page:
if (!page->mapping)
goto page_not_up_to_date_locked;
if (!mapping->a_ops->is_partially_uptodate(page,
- desc, offset))
+ offset, iter->count))
goto page_not_up_to_date_locked;
unlock_page(page);
}
@@ -1537,24 +1538,23 @@ page_ok:
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
- *
- * The file_read_actor routine returns how many bytes were
- * actually used..
- * NOTE! This may not be the same as how much of a user buffer
- * we filled up (we may be padding etc), so we can only update
- * "pos" here (the actor routine has to update the user buffer
- * pointers and the remaining count).
*/
- ret = file_read_actor(desc, page, offset, nr);
+
+ ret = copy_page_to_iter(page, offset, nr, iter);
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
prev_offset = offset;
page_cache_release(page);
- if (ret == nr && desc->count)
- continue;
- goto out;
+ written += ret;
+ if (!iov_iter_count(iter))
+ goto out;
+ if (ret < nr) {
+ error = -EFAULT;
+ goto out;
+ }
+ continue;
page_not_up_to_date:
/* Get exclusive access to the page ... */
@@ -1589,6 +1589,7 @@ readpage:
if (unlikely(error)) {
if (error == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
+ error = 0;
goto find_page;
}
goto readpage_error;
@@ -1619,7 +1620,6 @@ readpage:
readpage_error:
/* UHHUH! A synchronous read error occurred. Report it */
- desc->error = error;
page_cache_release(page);
goto out;
@@ -1630,16 +1630,17 @@ no_cached_page:
*/
page = page_cache_alloc_cold(mapping);
if (!page) {
- desc->error = -ENOMEM;
+ error = -ENOMEM;
goto out;
}
error = add_to_page_cache_lru(page, mapping,
index, GFP_KERNEL);
if (error) {
page_cache_release(page);
- if (error == -EEXIST)
+ if (error == -EEXIST) {
+ error = 0;
goto find_page;
- desc->error = error;
+ }
goto out;
}
goto readpage;
@@ -1652,44 +1653,7 @@ out:
*ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
file_accessed(filp);
-}
-
-int file_read_actor(read_descriptor_t *desc, struct page *page,
- unsigned long offset, unsigned long size)
-{
- char *kaddr;
- unsigned long left, count = desc->count;
-
- if (size > count)
- size = count;
-
- /*
- * Faults on the destination of a read are common, so do it before
- * taking the kmap.
- */
- if (!fault_in_pages_writeable(desc->arg.buf, size)) {
- kaddr = kmap_atomic(page);
- left = __copy_to_user_inatomic(desc->arg.buf,
- kaddr + offset, size);
- kunmap_atomic(kaddr);
- if (left == 0)
- goto success;
- }
-
- /* Do it the slow way */
- kaddr = kmap(page);
- left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
- kunmap(page);
-
- if (left) {
- size -= left;
- desc->error = -EFAULT;
- }
-success:
- desc->count = count - size;
- desc->written += size;
- desc->arg.buf += size;
- return size;
+ return written ? written : error;
}
/*
@@ -1747,14 +1711,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
{
struct file *filp = iocb->ki_filp;
ssize_t retval;
- unsigned long seg = 0;
size_t count;
loff_t *ppos = &iocb->ki_pos;
+ struct iov_iter i;
count = 0;
retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
if (retval)
return retval;
+ iov_iter_init(&i, iov, nr_segs, count, 0);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
@@ -1776,6 +1741,11 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
if (retval > 0) {
*ppos = pos + retval;
count -= retval;
+ /*
+ * If we did a short DIO read we need to skip the
+ * section of the iov that we've already read data into.
+ */
+ iov_iter_advance(&i, retval);
}
/*
@@ -1792,39 +1762,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
}
}
- count = retval;
- for (seg = 0; seg < nr_segs; seg++) {
- read_descriptor_t desc;
- loff_t offset = 0;
-
- /*
- * If we did a short DIO read we need to skip the section of the
- * iov that we've already read data into.
- */
- if (count) {
- if (count > iov[seg].iov_len) {
- count -= iov[seg].iov_len;
- continue;
- }
- offset = count;
- count = 0;
- }
-
- desc.written = 0;
- desc.arg.buf = iov[seg].iov_base + offset;
- desc.count = iov[seg].iov_len - offset;
- if (desc.count == 0)
- continue;
- desc.error = 0;
- do_generic_file_read(filp, ppos, &desc);
- retval += desc.written;
- if (desc.error) {
- retval = retval ?: desc.error;
- break;
- }
- if (desc.count > 0)
- break;
- }
+ retval = do_generic_file_read(filp, ppos, &i, retval);
out:
return retval;
}
@@ -2335,150 +2273,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
}
EXPORT_SYMBOL(read_cache_page_gfp);
-static size_t __iovec_copy_from_user_inatomic(char *vaddr,
- const struct iovec *iov, size_t base, size_t bytes)
-{
- size_t copied = 0, left = 0;
-
- while (bytes) {
- char __user *buf = iov->iov_base + base;
- int copy = min(bytes, iov->iov_len - base);
-
- base = 0;
- left = __copy_from_user_inatomic(vaddr, buf, copy);
- copied += copy;
- bytes -= copy;
- vaddr += copy;
- iov++;
-
- if (unlikely(left))
- break;
- }
- return copied - left;
-}
-
-/*
- * Copy as much as we can into the page and return the number of bytes which
- * were successfully copied. If a fault is encountered then return the number of
- * bytes which were copied.
- */
-size_t iov_iter_copy_from_user_atomic(struct page *page,
- struct iov_iter *i, unsigned long offset, size_t bytes)
-{
- char *kaddr;
- size_t copied;
-
- BUG_ON(!in_atomic());
- kaddr = kmap_atomic(page);
- if (likely(i->nr_segs == 1)) {
- int left;
- char __user *buf = i->iov->iov_base + i->iov_offset;
- left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
- copied = bytes - left;
- } else {
- copied = __iovec_copy_from_user_inatomic(kaddr + offset,
- i->iov, i->iov_offset, bytes);
- }
- kunmap_atomic(kaddr);
-
- return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
-
-/*
- * This has the same sideeffects and return value as
- * iov_iter_copy_from_user_atomic().
- * The difference is that it attempts to resolve faults.
- * Page must not be locked.
- */
-size_t iov_iter_copy_from_user(struct page *page,
- struct iov_iter *i, unsigned long offset, size_t bytes)
-{
- char *kaddr;
- size_t copied;
-
- kaddr = kmap(page);
- if (likely(i->nr_segs == 1)) {
- int left;
- char __user *buf = i->iov->iov_base + i->iov_offset;
- left = __copy_from_user(kaddr + offset, buf, bytes);
- copied = bytes - left;
- } else {
- copied = __iovec_copy_from_user_inatomic(kaddr + offset,
- i->iov, i->iov_offset, bytes);
- }
- kunmap(page);
- return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user);
-
-void iov_iter_advance(struct iov_iter *i, size_t bytes)
-{
- BUG_ON(i->count < bytes);
-
- if (likely(i->nr_segs == 1)) {
- i->iov_offset += bytes;
- i->count -= bytes;
- } else {
- const struct iovec *iov = i->iov;
- size_t base = i->iov_offset;
- unsigned long nr_segs = i->nr_segs;
-
- /*
- * The !iov->iov_len check ensures we skip over unlikely
- * zero-length segments (without overruning the iovec).
- */
- while (bytes || unlikely(i->count && !iov->iov_len)) {
- int copy;
-
- copy = min(bytes, iov->iov_len - base);
- BUG_ON(!i->count || i->count < copy);
- i->count -= copy;
- bytes -= copy;
- base += copy;
- if (iov->iov_len == base) {
- iov++;
- nr_segs--;
- base = 0;
- }
- }
- i->iov = iov;
- i->iov_offset = base;
- i->nr_segs = nr_segs;
- }
-}
-EXPORT_SYMBOL(iov_iter_advance);
-
-/*
- * Fault in the first iovec of the given iov_iter, to a maximum length
- * of bytes. Returns 0 on success, or non-zero if the memory could not be
- * accessed (ie. because it is an invalid address).
- *
- * writev-intensive code may want this to prefault several iovecs -- that
- * would be possible (callers must not rely on the fact that _only_ the
- * first iovec will be faulted with the current implementation).
- */
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
-{
- char __user *buf = i->iov->iov_base + i->iov_offset;
- bytes = min(bytes, i->iov->iov_len - i->iov_offset);
- return fault_in_pages_readable(buf, bytes);
-}
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
-
-/*
- * Return the count of just the current iov_iter segment.
- */
-size_t iov_iter_single_seg_count(const struct iov_iter *i)
-{
- const struct iovec *iov = i->iov;
- if (i->nr_segs == 1)
- return i->count;
- else
- return min(i->count, iov->iov_len - i->iov_offset);
-}
-EXPORT_SYMBOL(iov_iter_single_seg_count);
-
/*
* Performs necessary checks before doing a write
*
@@ -2585,7 +2379,7 @@ EXPORT_SYMBOL(pagecache_write_end);
ssize_t
generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long *nr_segs, loff_t pos, loff_t *ppos,
+ unsigned long *nr_segs, loff_t pos,
size_t count, size_t ocount)
{
struct file *file = iocb->ki_filp;
@@ -2646,7 +2440,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
i_size_write(inode, pos);
mark_inode_dirty(inode);
}
- *ppos = pos;
+ iocb->ki_pos = pos;
}
out:
return written;
@@ -2692,7 +2486,7 @@ found:
}
EXPORT_SYMBOL(grab_cache_page_write_begin);
-static ssize_t generic_perform_write(struct file *file,
+ssize_t generic_perform_write(struct file *file,
struct iov_iter *i, loff_t pos)
{
struct address_space *mapping = file->f_mapping;
@@ -2742,9 +2536,7 @@ again:
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
- pagefault_disable();
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
- pagefault_enable();
flush_dcache_page(page);
mark_page_accessed(page);
@@ -2782,27 +2574,7 @@ again:
return written ? written : status;
}
-
-ssize_t
-generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos, loff_t *ppos,
- size_t count, ssize_t written)
-{
- struct file *file = iocb->ki_filp;
- ssize_t status;
- struct iov_iter i;
-
- iov_iter_init(&i, iov, nr_segs, count, written);
- status = generic_perform_write(file, &i, pos);
-
- if (likely(status >= 0)) {
- written += status;
- *ppos = pos + status;
- }
-
- return written ? written : status;
-}
-EXPORT_SYMBOL(generic_file_buffered_write);
+EXPORT_SYMBOL(generic_perform_write);
/**
* __generic_file_aio_write - write data to a file
@@ -2824,16 +2596,18 @@ EXPORT_SYMBOL(generic_file_buffered_write);
* avoid syncing under i_mutex.
*/
ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
+ unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
- loff_t pos;
- ssize_t written;
+ loff_t pos = iocb->ki_pos;
+ ssize_t written = 0;
ssize_t err;
+ ssize_t status;
+ struct iov_iter from;
ocount = 0;
err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
@@ -2841,12 +2615,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
return err;
count = ocount;
- pos = *ppos;
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
- written = 0;
-
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
goto out;
@@ -2862,45 +2633,47 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
if (err)
goto out;
+ iov_iter_init(&from, iov, nr_segs, count, 0);
+
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
loff_t endbyte;
- ssize_t written_buffered;
- written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
- ppos, count, ocount);
+ written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
+ count, ocount);
if (written < 0 || written == count)
goto out;
+ iov_iter_advance(&from, written);
+
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
pos += written;
count -= written;
- written_buffered = generic_file_buffered_write(iocb, iov,
- nr_segs, pos, ppos, count,
- written);
+
+ status = generic_perform_write(file, &from, pos);
/*
- * If generic_file_buffered_write() retuned a synchronous error
+ * If generic_perform_write() returned a synchronous error
* then we want to return the number of bytes which were
* direct-written, or the error code if that was zero. Note
* that this differs from normal direct-io semantics, which
* will return -EFOO even if some bytes were written.
*/
- if (written_buffered < 0) {
- err = written_buffered;
+ if (unlikely(status < 0) && !written) {
+ err = status;
goto out;
}
-
+ iocb->ki_pos = pos + status;
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
*/
- endbyte = pos + written_buffered - written - 1;
+ endbyte = pos + status - 1;
err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
if (err == 0) {
- written = written_buffered;
+ written += status;
invalidate_mapping_pages(mapping,
pos >> PAGE_CACHE_SHIFT,
endbyte >> PAGE_CACHE_SHIFT);
@@ -2911,8 +2684,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
*/
}
} else {
- written = generic_file_buffered_write(iocb, iov, nr_segs,
- pos, ppos, count, written);
+ written = generic_perform_write(file, &from, pos);
+ if (likely(written >= 0))
+ iocb->ki_pos = pos + written;
}
out:
current->backing_dev_info = NULL;
@@ -2941,7 +2715,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
BUG_ON(iocb->ki_pos != pos);
mutex_lock(&inode->i_mutex);
- ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+ ret = __generic_file_aio_write(iocb, iov, nr_segs);
mutex_unlock(&inode->i_mutex);
if (ret > 0) {
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
new file mode 100644
index 00000000000..10e46cd721d
--- /dev/null
+++ b/mm/iov_iter.c
@@ -0,0 +1,224 @@
+#include <linux/export.h>
+#include <linux/uio.h>
+#include <linux/pagemap.h>
+
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+ struct iov_iter *i)
+{
+ size_t skip, copy, left, wanted;
+ const struct iovec *iov;
+ char __user *buf;
+ void *kaddr, *from;
+
+ if (unlikely(bytes > i->count))
+ bytes = i->count;
+
+ if (unlikely(!bytes))
+ return 0;
+
+ wanted = bytes;
+ iov = i->iov;
+ skip = i->iov_offset;
+ buf = iov->iov_base + skip;
+ copy = min(bytes, iov->iov_len - skip);
+
+ if (!fault_in_pages_writeable(buf, copy)) {
+ kaddr = kmap_atomic(page);
+ from = kaddr + offset;
+
+ /* first chunk, usually the only one */
+ left = __copy_to_user_inatomic(buf, from, copy);
+ copy -= left;
+ skip += copy;
+ from += copy;
+ bytes -= copy;
+
+ while (unlikely(!left && bytes)) {
+ iov++;
+ buf = iov->iov_base;
+ copy = min(bytes, iov->iov_len);
+ left = __copy_to_user_inatomic(buf, from, copy);
+ copy -= left;
+ skip = copy;
+ from += copy;
+ bytes -= copy;
+ }
+ if (likely(!bytes)) {
+ kunmap_atomic(kaddr);
+ goto done;
+ }
+ offset = from - kaddr;
+ buf += copy;
+ kunmap_atomic(kaddr);
+ copy = min(bytes, iov->iov_len - skip);
+ }
+ /* Too bad - revert to non-atomic kmap */
+ kaddr = kmap(page);
+ from = kaddr + offset;
+ left = __copy_to_user(buf, from, copy);
+ copy -= left;
+ skip += copy;
+ from += copy;
+ bytes -= copy;
+ while (unlikely(!left && bytes)) {
+ iov++;
+ buf = iov->iov_base;
+ copy = min(bytes, iov->iov_len);
+ left = __copy_to_user(buf, from, copy);
+ copy -= left;
+ skip = copy;
+ from += copy;
+ bytes -= copy;
+ }
+ kunmap(page);
+done:
+ i->count -= wanted - bytes;
+ i->nr_segs -= iov - i->iov;
+ i->iov = iov;
+ i->iov_offset = skip;
+ return wanted - bytes;
+}
+EXPORT_SYMBOL(copy_page_to_iter);
+
+static size_t __iovec_copy_from_user_inatomic(char *vaddr,
+ const struct iovec *iov, size_t base, size_t bytes)
+{
+ size_t copied = 0, left = 0;
+
+ while (bytes) {
+ char __user *buf = iov->iov_base + base;
+ int copy = min(bytes, iov->iov_len - base);
+
+ base = 0;
+ left = __copy_from_user_inatomic(vaddr, buf, copy);
+ copied += copy;
+ bytes -= copy;
+ vaddr += copy;
+ iov++;
+
+ if (unlikely(left))
+ break;
+ }
+ return copied - left;
+}
+
+/*
+ * Copy as much as we can into the page and return the number of bytes which
+ * were successfully copied. If a fault is encountered then return the number of
+ * bytes which were copied.
+ */
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+ struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+ char *kaddr;
+ size_t copied;
+
+ kaddr = kmap_atomic(page);
+ if (likely(i->nr_segs == 1)) {
+ int left;
+ char __user *buf = i->iov->iov_base + i->iov_offset;
+ left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
+ copied = bytes - left;
+ } else {
+ copied = __iovec_copy_from_user_inatomic(kaddr + offset,
+ i->iov, i->iov_offset, bytes);
+ }
+ kunmap_atomic(kaddr);
+
+ return copied;
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
+
+/*
+ * This has the same sideeffects and return value as
+ * iov_iter_copy_from_user_atomic().
+ * The difference is that it attempts to resolve faults.
+ * Page must not be locked.
+ */
+size_t iov_iter_copy_from_user(struct page *page,
+ struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+ char *kaddr;
+ size_t copied;
+
+ kaddr = kmap(page);
+ if (likely(i->nr_segs == 1)) {
+ int left;
+ char __user *buf = i->iov->iov_base + i->iov_offset;
+ left = __copy_from_user(kaddr + offset, buf, bytes);
+ copied = bytes - left;
+ } else {
+ copied = __iovec_copy_from_user_inatomic(kaddr + offset,
+ i->iov, i->iov_offset, bytes);
+ }
+ kunmap(page);
+ return copied;
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user);
+
+void iov_iter_advance(struct iov_iter *i, size_t bytes)
+{
+ BUG_ON(i->count < bytes);
+
+ if (likely(i->nr_segs == 1)) {
+ i->iov_offset += bytes;
+ i->count -= bytes;
+ } else {
+ const struct iovec *iov = i->iov;
+ size_t base = i->iov_offset;
+ unsigned long nr_segs = i->nr_segs;
+
+ /*
+ * The !iov->iov_len check ensures we skip over unlikely
+ * zero-length segments (without overruning the iovec).
+ */
+ while (bytes || unlikely(i->count && !iov->iov_len)) {
+ int copy;
+
+ copy = min(bytes, iov->iov_len - base);
+ BUG_ON(!i->count || i->count < copy);
+ i->count -= copy;
+ bytes -= copy;
+ base += copy;
+ if (iov->iov_len == base) {
+ iov++;
+ nr_segs--;
+ base = 0;
+ }
+ }
+ i->iov = iov;
+ i->iov_offset = base;
+ i->nr_segs = nr_segs;
+ }
+}
+EXPORT_SYMBOL(iov_iter_advance);
+
+/*
+ * Fault in the first iovec of the given iov_iter, to a maximum length
+ * of bytes. Returns 0 on success, or non-zero if the memory could not be
+ * accessed (ie. because it is an invalid address).
+ *
+ * writev-intensive code may want this to prefault several iovecs -- that
+ * would be possible (callers must not rely on the fact that _only_ the
+ * first iovec will be faulted with the current implementation).
+ */
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
+{
+ char __user *buf = i->iov->iov_base + i->iov_offset;
+ bytes = min(bytes, i->iov->iov_len - i->iov_offset);
+ return fault_in_pages_readable(buf, bytes);
+}
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
+
+/*
+ * Return the count of just the current iov_iter segment.
+ */
+size_t iov_iter_single_seg_count(const struct iov_iter *i)
+{
+ const struct iovec *iov = i->iov;
+ if (i->nr_segs == 1)
+ return i->count;
+ else
+ return min(i->count, iov->iov_len - i->iov_offset);
+}
+EXPORT_SYMBOL(iov_iter_single_seg_count);
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index cb79065c19e..8505c9262b3 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -23,129 +23,44 @@
/**
* process_vm_rw_pages - read/write pages from task specified
- * @task: task to read/write from
- * @mm: mm for task
- * @process_pages: struct pages area that can store at least
- * nr_pages_to_copy struct page pointers
- * @pa: address of page in task to start copying from/to
+ * @pages: array of pointers to pages we want to copy
* @start_offset: offset in page to start copying from/to
* @len: number of bytes to copy
- * @lvec: iovec array specifying where to copy to/from
- * @lvec_cnt: number of elements in iovec array
- * @lvec_current: index in iovec array we are up to
- * @lvec_offset: offset in bytes from current iovec iov_base we are up to
+ * @iter: where to copy to/from locally
* @vm_write: 0 means copy from, 1 means copy to
- * @nr_pages_to_copy: number of pages to copy
- * @bytes_copied: returns number of bytes successfully copied
* Returns 0 on success, error code otherwise
*/
-static int process_vm_rw_pages(struct task_struct *task,
- struct mm_struct *mm,
- struct page **process_pages,
- unsigned long pa,
- unsigned long start_offset,
- unsigned long len,
- const struct iovec *lvec,
- unsigned long lvec_cnt,
- unsigned long *lvec_current,
- size_t *lvec_offset,
- int vm_write,
- unsigned int nr_pages_to_copy,
- ssize_t *bytes_copied)
+static int process_vm_rw_pages(struct page **pages,
+ unsigned offset,
+ size_t len,
+ struct iov_iter *iter,
+ int vm_write)
{
- int pages_pinned;
- void *target_kaddr;
- int pgs_copied = 0;
- int j;
- int ret;
- ssize_t bytes_to_copy;
- ssize_t rc = 0;
-
- *bytes_copied = 0;
-
- /* Get the pages we're interested in */
- down_read(&mm->mmap_sem);
- pages_pinned = get_user_pages(task, mm, pa,
- nr_pages_to_copy,
- vm_write, 0, process_pages, NULL);
- up_read(&mm->mmap_sem);
-
- if (pages_pinned != nr_pages_to_copy) {
- rc = -EFAULT;
- goto end;
- }
-
/* Do the copy for each page */
- for (pgs_copied = 0;
- (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt);
- pgs_copied++) {
- /* Make sure we have a non zero length iovec */
- while (*lvec_current < lvec_cnt
- && lvec[*lvec_current].iov_len == 0)
- (*lvec_current)++;
- if (*lvec_current == lvec_cnt)
- break;
-
- /*
- * Will copy smallest of:
- * - bytes remaining in page
- * - bytes remaining in destination iovec
- */
- bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset,
- len - *bytes_copied);
- bytes_to_copy = min_t(ssize_t, bytes_to_copy,
- lvec[*lvec_current].iov_len
- - *lvec_offset);
-
- target_kaddr = kmap(process_pages[pgs_copied]) + start_offset;
-
- if (vm_write)
- ret = copy_from_user(target_kaddr,
- lvec[*lvec_current].iov_base
- + *lvec_offset,
- bytes_to_copy);
- else
- ret = copy_to_user(lvec[*lvec_current].iov_base
- + *lvec_offset,
- target_kaddr, bytes_to_copy);
- kunmap(process_pages[pgs_copied]);
- if (ret) {
- *bytes_copied += bytes_to_copy - ret;
- pgs_copied++;
- rc = -EFAULT;
- goto end;
- }
- *bytes_copied += bytes_to_copy;
- *lvec_offset += bytes_to_copy;
- if (*lvec_offset == lvec[*lvec_current].iov_len) {
- /*
- * Need to copy remaining part of page into the
- * next iovec if there are any bytes left in page
- */
- (*lvec_current)++;
- *lvec_offset = 0;
- start_offset = (start_offset + bytes_to_copy)
- % PAGE_SIZE;
- if (start_offset)
- pgs_copied--;
+ while (len && iov_iter_count(iter)) {
+ struct page *page = *pages++;
+ size_t copy = PAGE_SIZE - offset;
+ size_t copied;
+
+ if (copy > len)
+ copy = len;
+
+ if (vm_write) {
+ if (copy > iov_iter_count(iter))
+ copy = iov_iter_count(iter);
+ copied = iov_iter_copy_from_user(page, iter,
+ offset, copy);
+ iov_iter_advance(iter, copied);
+ set_page_dirty_lock(page);
} else {
- start_offset = 0;
- }
- }
-
-end:
- if (vm_write) {
- for (j = 0; j < pages_pinned; j++) {
- if (j < pgs_copied)
- set_page_dirty_lock(process_pages[j]);
- put_page(process_pages[j]);
+ copied = copy_page_to_iter(page, offset, copy, iter);
}
- } else {
- for (j = 0; j < pages_pinned; j++)
- put_page(process_pages[j]);
+ len -= copied;
+ if (copied < copy && iov_iter_count(iter))
+ return -EFAULT;
+ offset = 0;
}
-
- return rc;
+ return 0;
}
/* Maximum number of pages kmalloc'd to hold struct page's during copy */
@@ -155,67 +70,60 @@ end:
* process_vm_rw_single_vec - read/write pages from task specified
* @addr: start memory address of target process
* @len: size of area to copy to/from
- * @lvec: iovec array specifying where to copy to/from locally
- * @lvec_cnt: number of elements in iovec array
- * @lvec_current: index in iovec array we are up to
- * @lvec_offset: offset in bytes from current iovec iov_base we are up to
+ * @iter: where to copy to/from locally
* @process_pages: struct pages area that can store at least
* nr_pages_to_copy struct page pointers
* @mm: mm for task
* @task: task to read/write from
* @vm_write: 0 means copy from, 1 means copy to
- * @bytes_copied: returns number of bytes successfully copied
* Returns 0 on success or on failure error code
*/
static int process_vm_rw_single_vec(unsigned long addr,
unsigned long len,
- const struct iovec *lvec,
- unsigned long lvec_cnt,
- unsigned long *lvec_current,
- size_t *lvec_offset,
+ struct iov_iter *iter,
struct page **process_pages,
struct mm_struct *mm,
struct task_struct *task,
- int vm_write,
- ssize_t *bytes_copied)
+ int vm_write)
{
unsigned long pa = addr & PAGE_MASK;
unsigned long start_offset = addr - pa;
unsigned long nr_pages;
- ssize_t bytes_copied_loop;
ssize_t rc = 0;
- unsigned long nr_pages_copied = 0;
- unsigned long nr_pages_to_copy;
unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
/ sizeof(struct pages *);
- *bytes_copied = 0;
-
/* Work out address and page range required */
if (len == 0)
return 0;
nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
- while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) {
- nr_pages_to_copy = min(nr_pages - nr_pages_copied,
- max_pages_per_loop);
+ while (!rc && nr_pages && iov_iter_count(iter)) {
+ int pages = min(nr_pages, max_pages_per_loop);
+ size_t bytes;
- rc = process_vm_rw_pages(task, mm, process_pages, pa,
- start_offset, len,
- lvec, lvec_cnt,
- lvec_current, lvec_offset,
- vm_write, nr_pages_to_copy,
- &bytes_copied_loop);
- start_offset = 0;
- *bytes_copied += bytes_copied_loop;
+ /* Get the pages we're interested in */
+ down_read(&mm->mmap_sem);
+ pages = get_user_pages(task, mm, pa, pages,
+ vm_write, 0, process_pages, NULL);
+ up_read(&mm->mmap_sem);
- if (rc < 0) {
- return rc;
- } else {
- len -= bytes_copied_loop;
- nr_pages_copied += nr_pages_to_copy;
- pa += nr_pages_to_copy * PAGE_SIZE;
- }
+ if (pages <= 0)
+ return -EFAULT;
+
+ bytes = pages * PAGE_SIZE - start_offset;
+ if (bytes > len)
+ bytes = len;
+
+ rc = process_vm_rw_pages(process_pages,
+ start_offset, bytes, iter,
+ vm_write);
+ len -= bytes;
+ start_offset = 0;
+ nr_pages -= pages;
+ pa += pages * PAGE_SIZE;
+ while (pages)
+ put_page(process_pages[--pages]);
}
return rc;
@@ -228,8 +136,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
/**
* process_vm_rw_core - core of reading/writing pages from task specified
* @pid: PID of process to read/write from/to
- * @lvec: iovec array specifying where to copy to/from locally
- * @liovcnt: size of lvec array
+ * @iter: where to copy to/from locally
* @rvec: iovec array specifying where to copy to/from in the other process
* @riovcnt: size of rvec array
* @flags: currently unused
@@ -238,8 +145,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
* return less bytes than expected if an error occurs during the copying
* process.
*/
-static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
- unsigned long liovcnt,
+static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
const struct iovec *rvec,
unsigned long riovcnt,
unsigned long flags, int vm_write)
@@ -250,13 +156,10 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
struct mm_struct *mm;
unsigned long i;
ssize_t rc = 0;
- ssize_t bytes_copied_loop;
- ssize_t bytes_copied = 0;
unsigned long nr_pages = 0;
unsigned long nr_pages_iov;
- unsigned long iov_l_curr_idx = 0;
- size_t iov_l_curr_offset = 0;
ssize_t iov_len;
+ size_t total_len = iov_iter_count(iter);
/*
* Work out how many pages of struct pages we're going to need
@@ -310,24 +213,20 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
goto put_task_struct;
}
- for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) {
+ for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++)
rc = process_vm_rw_single_vec(
(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
- lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset,
- process_pages, mm, task, vm_write, &bytes_copied_loop);
- bytes_copied += bytes_copied_loop;
- if (rc != 0) {
- /* If we have managed to copy any data at all then
- we return the number of bytes copied. Otherwise
- we return the error code */
- if (bytes_copied)
- rc = bytes_copied;
- goto put_mm;
- }
- }
+ iter, process_pages, mm, task, vm_write);
+
+ /* copied = space before - space after */
+ total_len -= iov_iter_count(iter);
+
+ /* If we have managed to copy any data at all then
+ we return the number of bytes copied. Otherwise
+ we return the error code */
+ if (total_len)
+ rc = total_len;
- rc = bytes_copied;
-put_mm:
mmput(mm);
put_task_struct:
@@ -363,6 +262,7 @@ static ssize_t process_vm_rw(pid_t pid,
struct iovec iovstack_r[UIO_FASTIOV];
struct iovec *iov_l = iovstack_l;
struct iovec *iov_r = iovstack_r;
+ struct iov_iter iter;
ssize_t rc;
if (flags != 0)
@@ -378,13 +278,14 @@ static ssize_t process_vm_rw(pid_t pid,
if (rc <= 0)
goto free_iovecs;
+ iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
+
rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
iovstack_r, &iov_r);
if (rc <= 0)
goto free_iovecs;
- rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
- vm_write);
+ rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
free_iovecs:
if (iov_r != iovstack_r)
@@ -424,6 +325,7 @@ compat_process_vm_rw(compat_pid_t pid,
struct iovec iovstack_r[UIO_FASTIOV];
struct iovec *iov_l = iovstack_l;
struct iovec *iov_r = iovstack_r;
+ struct iov_iter iter;
ssize_t rc = -EFAULT;
if (flags != 0)
@@ -439,14 +341,14 @@ compat_process_vm_rw(compat_pid_t pid,
&iov_l);
if (rc <= 0)
goto free_iovecs;
+ iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
UIO_FASTIOV, iovstack_r,
&iov_r);
if (rc <= 0)
goto free_iovecs;
- rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
- vm_write);
+ rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
free_iovecs:
if (iov_r != iovstack_r)
diff --git a/mm/shmem.c b/mm/shmem.c
index 70273f8df58..9f70e02111c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1402,13 +1402,25 @@ shmem_write_end(struct file *file, struct address_space *mapping,
return copied;
}
-static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor)
+static ssize_t shmem_file_aio_read(struct kiocb *iocb,
+ const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
- struct inode *inode = file_inode(filp);
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
pgoff_t index;
unsigned long offset;
enum sgp_type sgp = SGP_READ;
+ int error = 0;
+ ssize_t retval;
+ size_t count;
+ loff_t *ppos = &iocb->ki_pos;
+ struct iov_iter iter;
+
+ retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+ if (retval)
+ return retval;
+ iov_iter_init(&iter, iov, nr_segs, count, 0);
/*
* Might this read be for a stacking filesystem? Then when reading
@@ -1436,10 +1448,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_
break;
}
- desc->error = shmem_getpage(inode, index, &page, sgp, NULL);
- if (desc->error) {
- if (desc->error == -EINVAL)
- desc->error = 0;
+ error = shmem_getpage(inode, index, &page, sgp, NULL);
+ if (error) {
+ if (error == -EINVAL)
+ error = 0;
break;
}
if (page)
@@ -1483,61 +1495,26 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
- *
- * The actor routine returns how many bytes were actually used..
- * NOTE! This may not be the same as how much of a user buffer
- * we filled up (we may be padding etc), so we can only update
- * "pos" here (the actor routine has to update the user buffer
- * pointers and the remaining count).
*/
- ret = actor(desc, page, offset, nr);
+ ret = copy_page_to_iter(page, offset, nr, &iter);
+ retval += ret;
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
page_cache_release(page);
- if (ret != nr || !desc->count)
+ if (!iov_iter_count(&iter))
break;
-
+ if (ret < nr) {
+ error = -EFAULT;
+ break;
+ }
cond_resched();
}
*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
- file_accessed(filp);
-}
-
-static ssize_t shmem_file_aio_read(struct kiocb *iocb,
- const struct iovec *iov, unsigned long nr_segs, loff_t pos)
-{
- struct file *filp = iocb->ki_filp;
- ssize_t retval;
- unsigned long seg;
- size_t count;
- loff_t *ppos = &iocb->ki_pos;
-
- retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
- if (retval)
- return retval;
-
- for (seg = 0; seg < nr_segs; seg++) {
- read_descriptor_t desc;
-
- desc.written = 0;
- desc.arg.buf = iov[seg].iov_base;
- desc.count = iov[seg].iov_len;
- if (desc.count == 0)
- continue;
- desc.error = 0;
- do_shmem_file_read(filp, ppos, &desc, file_read_actor);
- retval += desc.written;
- if (desc.error) {
- retval = retval ?: desc.error;
- break;
- }
- if (desc.count > 0)
- break;
- }
- return retval;
+ file_accessed(file);
+ return retval ? retval : error;
}
static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
@@ -1576,7 +1553,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- nr_pages = min(req_pages, pipe->buffers);
+ nr_pages = min(req_pages, spd.nr_pages_max);
spd.nr_pages = find_get_pages_contig(mapping, index,
nr_pages, spd.pages);
diff --git a/mm/slab.c b/mm/slab.c
index 3db4cb06e32..388cb1ae6fb 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -157,6 +157,17 @@
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif
+#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \
+ <= SLAB_OBJ_MIN_SIZE) ? 1 : 0)
+
+#if FREELIST_BYTE_INDEX
+typedef unsigned char freelist_idx_t;
+#else
+typedef unsigned short freelist_idx_t;
+#endif
+
+#define SLAB_OBJ_MAX_NUM (1 << sizeof(freelist_idx_t) * BITS_PER_BYTE)
+
/*
* true if a page was allocated from pfmemalloc reserves for network-based
* swap
@@ -277,8 +288,8 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
* OTOH the cpuarrays can contain lots of objects,
* which could lock up otherwise freeable slabs.
*/
-#define REAPTIMEOUT_CPUC (2*HZ)
-#define REAPTIMEOUT_LIST3 (4*HZ)
+#define REAPTIMEOUT_AC (2*HZ)
+#define REAPTIMEOUT_NODE (4*HZ)
#if STATS
#define STATS_INC_ACTIVE(x) ((x)->num_active++)
@@ -565,9 +576,31 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
return cachep->array[smp_processor_id()];
}
-static size_t slab_mgmt_size(size_t nr_objs, size_t align)
+static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
+ size_t idx_size, size_t align)
{
- return ALIGN(nr_objs * sizeof(unsigned int), align);
+ int nr_objs;
+ size_t freelist_size;
+
+ /*
+ * Ignore padding for the initial guess. The padding
+ * is at most @align-1 bytes, and @buffer_size is at
+ * least @align. In the worst case, this result will
+ * be one greater than the number of objects that fit
+ * into the memory allocation when taking the padding
+ * into account.
+ */
+ nr_objs = slab_size / (buffer_size + idx_size);
+
+ /*
+ * This calculated number will be either the right
+ * amount, or one greater than what we want.
+ */
+ freelist_size = slab_size - nr_objs * buffer_size;
+ if (freelist_size < ALIGN(nr_objs * idx_size, align))
+ nr_objs--;
+
+ return nr_objs;
}
/*
@@ -600,25 +633,9 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
nr_objs = slab_size / buffer_size;
} else {
- /*
- * Ignore padding for the initial guess. The padding
- * is at most @align-1 bytes, and @buffer_size is at
- * least @align. In the worst case, this result will
- * be one greater than the number of objects that fit
- * into the memory allocation when taking the padding
- * into account.
- */
- nr_objs = (slab_size) / (buffer_size + sizeof(unsigned int));
-
- /*
- * This calculated number will be either the right
- * amount, or one greater than what we want.
- */
- if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size
- > slab_size)
- nr_objs--;
-
- mgmt_size = slab_mgmt_size(nr_objs, align);
+ nr_objs = calculate_nr_objs(slab_size, buffer_size,
+ sizeof(freelist_idx_t), align);
+ mgmt_size = ALIGN(nr_objs * sizeof(freelist_idx_t), align);
}
*num = nr_objs;
*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
@@ -1067,7 +1084,7 @@ static int init_cache_node_node(int node)
list_for_each_entry(cachep, &slab_caches, list) {
/*
- * Set up the size64 kmemlist for cpu before we can
+ * Set up the kmem_cache_node for cpu before we can
* begin anything. Make sure some other cpu on this
* node has not already allocated this
*/
@@ -1076,12 +1093,12 @@ static int init_cache_node_node(int node)
if (!n)
return -ENOMEM;
kmem_cache_node_init(n);
- n->next_reap = jiffies + REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ n->next_reap = jiffies + REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
/*
- * The l3s don't come and go as CPUs come and
- * go. slab_mutex is sufficient
+ * The kmem_cache_nodes don't come and go as CPUs
+ * come and go. slab_mutex is sufficient
* protection here.
*/
cachep->node[node] = n;
@@ -1406,8 +1423,8 @@ static void __init set_up_node(struct kmem_cache *cachep, int index)
for_each_online_node(node) {
cachep->node[node] = &init_kmem_cache_node[index + node];
cachep->node[node]->next_reap = jiffies +
- REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
}
}
@@ -2010,6 +2027,10 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
if (!num)
continue;
+ /* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */
+ if (num > SLAB_OBJ_MAX_NUM)
+ break;
+
if (flags & CFLGS_OFF_SLAB) {
/*
* Max number of objs-per-slab for caches which
@@ -2017,7 +2038,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
* looping condition in cache_grow().
*/
offslab_limit = size;
- offslab_limit /= sizeof(unsigned int);
+ offslab_limit /= sizeof(freelist_idx_t);
if (num > offslab_limit)
break;
@@ -2103,8 +2124,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
}
}
cachep->node[numa_mem_id()]->next_reap =
- jiffies + REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ jiffies + REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
cpu_cache_get(cachep)->avail = 0;
cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
@@ -2243,7 +2264,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
* it too early on. Always use on-slab management when
* SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
*/
- if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init &&
+ if ((size >= (PAGE_SIZE >> 5)) && !slab_early_init &&
!(flags & SLAB_NOLEAKTRACE))
/*
* Size is large, assume best to place the slab management obj
@@ -2252,6 +2273,12 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
flags |= CFLGS_OFF_SLAB;
size = ALIGN(size, cachep->align);
+ /*
+ * We should restrict the number of objects in a slab to implement
+ * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
+ */
+ if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
+ size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
left_over = calculate_slab_order(cachep, size, cachep->align, flags);
@@ -2259,7 +2286,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
return -E2BIG;
freelist_size =
- ALIGN(cachep->num * sizeof(unsigned int), cachep->align);
+ ALIGN(cachep->num * sizeof(freelist_idx_t), cachep->align);
/*
* If the slab has been placed off-slab, and we have enough space then
@@ -2272,7 +2299,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
if (flags & CFLGS_OFF_SLAB) {
/* really off slab. No need for manual alignment */
- freelist_size = cachep->num * sizeof(unsigned int);
+ freelist_size = cachep->num * sizeof(freelist_idx_t);
#ifdef CONFIG_PAGE_POISONING
/* If we're going to use the generic kernel_map_pages()
@@ -2300,10 +2327,10 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
if (flags & CFLGS_OFF_SLAB) {
cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
/*
- * This is a possibility for one of the malloc_sizes caches.
+ * This is a possibility for one of the kmalloc_{dma,}_caches.
* But since we go off slab only for object size greater than
- * PAGE_SIZE/8, and malloc_sizes gets created in ascending order,
- * this should not happen at all.
+ * PAGE_SIZE/8, and kmalloc_{dma,}_caches get created
+ * in ascending order,this should not happen at all.
* But leave a BUG_ON for some lucky dude.
*/
BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
@@ -2511,14 +2538,17 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
/*
* Get the memory for a slab management obj.
- * For a slab cache when the slab descriptor is off-slab, slab descriptors
- * always come from malloc_sizes caches. The slab descriptor cannot
- * come from the same cache which is getting created because,
- * when we are searching for an appropriate cache for these
- * descriptors in kmem_cache_create, we search through the malloc_sizes array.
- * If we are creating a malloc_sizes cache here it would not be visible to
- * kmem_find_general_cachep till the initialization is complete.
- * Hence we cannot have freelist_cache same as the original cache.
+ *
+ * For a slab cache when the slab descriptor is off-slab, the
+ * slab descriptor can't come from the same cache which is being created,
+ * Because if it is the case, that means we defer the creation of
+ * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point.
+ * And we eventually call down to __kmem_cache_create(), which
+ * in turn looks up in the kmalloc_{dma,}_caches for the disired-size one.
+ * This is a "chicken-and-egg" problem.
+ *
+ * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches,
+ * which are all initialized during kmem_cache_init().
*/
static void *alloc_slabmgmt(struct kmem_cache *cachep,
struct page *page, int colour_off,
@@ -2542,9 +2572,15 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep,
return freelist;
}
-static inline unsigned int *slab_freelist(struct page *page)
+static inline freelist_idx_t get_free_obj(struct page *page, unsigned char idx)
{
- return (unsigned int *)(page->freelist);
+ return ((freelist_idx_t *)page->freelist)[idx];
+}
+
+static inline void set_free_obj(struct page *page,
+ unsigned char idx, freelist_idx_t val)
+{
+ ((freelist_idx_t *)(page->freelist))[idx] = val;
}
static void cache_init_objs(struct kmem_cache *cachep,
@@ -2589,7 +2625,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
if (cachep->ctor)
cachep->ctor(objp);
#endif
- slab_freelist(page)[i] = i;
+ set_free_obj(page, i, i);
}
}
@@ -2608,7 +2644,7 @@ static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
{
void *objp;
- objp = index_to_obj(cachep, page, slab_freelist(page)[page->active]);
+ objp = index_to_obj(cachep, page, get_free_obj(page, page->active));
page->active++;
#if DEBUG
WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
@@ -2629,7 +2665,7 @@ static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
/* Verify double free bug */
for (i = page->active; i < cachep->num; i++) {
- if (slab_freelist(page)[i] == objnr) {
+ if (get_free_obj(page, i) == objnr) {
printk(KERN_ERR "slab: double free detected in cache "
"'%s', objp %p\n", cachep->name, objp);
BUG();
@@ -2637,7 +2673,7 @@ static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
}
#endif
page->active--;
- slab_freelist(page)[page->active] = objnr;
+ set_free_obj(page, page->active, objnr);
}
/*
@@ -2886,9 +2922,9 @@ retry:
/* move slabp to correct slabp list: */
list_del(&page->lru);
if (page->active == cachep->num)
- list_add(&page->list, &n->slabs_full);
+ list_add(&page->lru, &n->slabs_full);
else
- list_add(&page->list, &n->slabs_partial);
+ list_add(&page->lru, &n->slabs_partial);
}
must_grow:
@@ -3245,11 +3281,11 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags,
flags);
- if (likely(ptr))
+ if (likely(ptr)) {
kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size);
-
- if (unlikely((flags & __GFP_ZERO) && ptr))
- memset(ptr, 0, cachep->object_size);
+ if (unlikely(flags & __GFP_ZERO))
+ memset(ptr, 0, cachep->object_size);
+ }
return ptr;
}
@@ -3310,17 +3346,17 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
flags);
prefetchw(objp);
- if (likely(objp))
+ if (likely(objp)) {
kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size);
-
- if (unlikely((flags & __GFP_ZERO) && objp))
- memset(objp, 0, cachep->object_size);
+ if (unlikely(flags & __GFP_ZERO))
+ memset(objp, 0, cachep->object_size);
+ }
return objp;
}
/*
- * Caller needs to acquire correct kmem_list's list_lock
+ * Caller needs to acquire correct kmem_cache_node's list_lock
*/
static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
int node)
@@ -3574,11 +3610,6 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
struct kmem_cache *cachep;
void *ret;
- /* If you want to save a few bytes .text space: replace
- * __ with kmem_.
- * Then kmalloc uses the uninlined functions instead of the inline
- * functions.
- */
cachep = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
@@ -3670,7 +3701,7 @@ EXPORT_SYMBOL(kfree);
/*
* This initializes kmem_cache_node or resizes various caches for all nodes.
*/
-static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp)
+static int alloc_kmem_cache_node(struct kmem_cache *cachep, gfp_t gfp)
{
int node;
struct kmem_cache_node *n;
@@ -3726,8 +3757,8 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp)
}
kmem_cache_node_init(n);
- n->next_reap = jiffies + REAPTIMEOUT_LIST3 +
- ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+ n->next_reap = jiffies + REAPTIMEOUT_NODE +
+ ((unsigned long)cachep) % REAPTIMEOUT_NODE;
n->shared = new_shared;
n->alien = new_alien;
n->free_limit = (1 + nr_cpus_node(node)) *
@@ -3813,7 +3844,7 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
kfree(ccold);
}
kfree(new);
- return alloc_kmemlist(cachep, gfp);
+ return alloc_kmem_cache_node(cachep, gfp);
}
static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
@@ -3982,7 +4013,7 @@ static void cache_reap(struct work_struct *w)
if (time_after(n->next_reap, jiffies))
goto next;
- n->next_reap = jiffies + REAPTIMEOUT_LIST3;
+ n->next_reap = jiffies + REAPTIMEOUT_NODE;
drain_array(searchp, n, n->shared, 0, node);
@@ -4003,7 +4034,7 @@ next:
next_reap_node();
out:
/* Set up the next iteration */
- schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_CPUC));
+ schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_AC));
}
#ifdef CONFIG_SLABINFO
@@ -4210,7 +4241,7 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c,
for (j = page->active; j < c->num; j++) {
/* Skip freed item */
- if (slab_freelist(page)[j] == i) {
+ if (get_free_obj(page, j) == i) {
active = false;
break;
}
diff --git a/mm/slob.c b/mm/slob.c
index 4bf8809dfcc..730cad45d4b 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -111,13 +111,13 @@ static inline int slob_page_free(struct page *sp)
static void set_slob_page_free(struct page *sp, struct list_head *list)
{
- list_add(&sp->list, list);
+ list_add(&sp->lru, list);
__SetPageSlobFree(sp);
}
static inline void clear_slob_page_free(struct page *sp)
{
- list_del(&sp->list);
+ list_del(&sp->lru);
__ClearPageSlobFree(sp);
}
@@ -282,7 +282,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
spin_lock_irqsave(&slob_lock, flags);
/* Iterate through each partially free page, try to find room */
- list_for_each_entry(sp, slob_list, list) {
+ list_for_each_entry(sp, slob_list, lru) {
#ifdef CONFIG_NUMA
/*
* If there's a node specification, search for a partial
@@ -296,7 +296,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
continue;
/* Attempt to alloc */
- prev = sp->list.prev;
+ prev = sp->lru.prev;
b = slob_page_alloc(sp, size, align);
if (!b)
continue;
@@ -322,7 +322,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
spin_lock_irqsave(&slob_lock, flags);
sp->units = SLOB_UNITS(PAGE_SIZE);
sp->freelist = b;
- INIT_LIST_HEAD(&sp->list);
+ INIT_LIST_HEAD(&sp->lru);
set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
set_slob_page_free(sp, slob_list);
b = slob_page_alloc(sp, size, align);
diff --git a/mm/slub.c b/mm/slub.c
index f620bbf4054..5e234f1f885 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1352,11 +1352,12 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
page = alloc_slab_page(alloc_gfp, node, oo);
if (unlikely(!page)) {
oo = s->min;
+ alloc_gfp = flags;
/*
* Allocation may have failed due to fragmentation.
* Try a lower order alloc if possible
*/
- page = alloc_slab_page(flags, node, oo);
+ page = alloc_slab_page(alloc_gfp, node, oo);
if (page)
stat(s, ORDER_FALLBACK);
@@ -1366,7 +1367,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
int pages = 1 << oo_order(oo);
- kmemcheck_alloc_shadow(page, oo_order(oo), flags, node);
+ kmemcheck_alloc_shadow(page, oo_order(oo), alloc_gfp, node);
/*
* Objects from caches that have a constructor don't get
diff --git a/mm/util.c b/mm/util.c
index d7813e6d4cc..f380af7ea77 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -446,6 +446,54 @@ unsigned long vm_commit_limit(void)
return allowed;
}
+/**
+ * get_cmdline() - copy the cmdline value to a buffer.
+ * @task: the task whose cmdline value to copy.
+ * @buffer: the buffer to copy to.
+ * @buflen: the length of the buffer. Larger cmdline values are truncated
+ * to this length.
+ * Returns the size of the cmdline field copied. Note that the copy does
+ * not guarantee an ending NULL byte.
+ */
+int get_cmdline(struct task_struct *task, char *buffer, int buflen)
+{
+ int res = 0;
+ unsigned int len;
+ struct mm_struct *mm = get_task_mm(task);
+ if (!mm)
+ goto out;
+ if (!mm->arg_end)
+ goto out_mm; /* Shh! No looking before we're done */
+
+ len = mm->arg_end - mm->arg_start;
+
+ if (len > buflen)
+ len = buflen;
+
+ res = access_process_vm(task, mm->arg_start, buffer, len, 0);
+
+ /*
+ * If the nul at the end of args has been overwritten, then
+ * assume application is using setproctitle(3).
+ */
+ if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
+ len = strnlen(buffer, res);
+ if (len < res) {
+ res = len;
+ } else {
+ len = mm->env_end - mm->env_start;
+ if (len > buflen - res)
+ len = buflen - res;
+ res += access_process_vm(task, mm->env_start,
+ buffer+res, len, 0);
+ res = strnlen(buffer, res);
+ }
+ }
+out_mm:
+ mmput(mm);
+out:
+ return res;
+}
/* Tracepoints definitions. */
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-29 11:37:42 +0000