aboutsummaryrefslogtreecommitdiff
path: root/mm/filemap_xip.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/filemap_xip.c')
-rw-r--r--mm/filemap_xip.c107
1 files changed, 76 insertions, 31 deletions
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 3e744abcce9..d8d9fe3f685 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -10,10 +10,14 @@
#include <linux/fs.h>
#include <linux/pagemap.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/uio.h>
#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
#include <linux/sched.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+#include <linux/gfp.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
@@ -21,22 +25,18 @@
* We do use our own empty page to avoid interference with other users
* of ZERO_PAGE(), such as /dev/zero
*/
+static DEFINE_MUTEX(xip_sparse_mutex);
+static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq);
static struct page *__xip_sparse_page;
+/* called under xip_sparse_mutex */
static struct page *xip_sparse_page(void)
{
if (!__xip_sparse_page) {
struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ZERO);
- if (page) {
- static DEFINE_SPINLOCK(xip_alloc_lock);
- spin_lock(&xip_alloc_lock);
- if (!__xip_sparse_page)
- __xip_sparse_page = page;
- else
- __free_page(page);
- spin_unlock(&xip_alloc_lock);
- }
+ if (page)
+ __xip_sparse_page = page;
}
return __xip_sparse_page;
}
@@ -90,8 +90,8 @@ do_xip_mapping_read(struct address_space *mapping,
}
}
nr = nr - offset;
- if (nr > len)
- nr = len;
+ if (nr > len - copied)
+ nr = len - copied;
error = mapping->a_ops->get_xip_mem(mapping, index, 0,
&xip_mem, &xip_pfn);
@@ -167,36 +167,50 @@ __xip_unmap (struct address_space * mapping,
{
struct vm_area_struct *vma;
struct mm_struct *mm;
- struct prio_tree_iter iter;
unsigned long address;
pte_t *pte;
pte_t pteval;
spinlock_t *ptl;
struct page *page;
+ unsigned count;
+ int locked = 0;
+
+ count = read_seqcount_begin(&xip_sparse_seq);
page = __xip_sparse_page;
if (!page)
return;
- spin_lock(&mapping->i_mmap_lock);
- vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+retry:
+ mutex_lock(&mapping->i_mmap_mutex);
+ vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
mm = vma->vm_mm;
address = vma->vm_start +
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
BUG_ON(address < vma->vm_start || address >= vma->vm_end);
- pte = page_check_address(page, mm, address, &ptl);
+ pte = page_check_address(page, mm, address, &ptl, 1);
if (pte) {
/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
pteval = ptep_clear_flush(vma, address, pte);
- page_remove_rmap(page, vma);
- dec_mm_counter(mm, file_rss);
+ page_remove_rmap(page);
+ dec_mm_counter(mm, MM_FILEPAGES);
BUG_ON(pte_dirty(pteval));
pte_unmap_unlock(pte, ptl);
+ /* must invalidate_page _before_ freeing the page */
+ mmu_notifier_invalidate_page(mm, address);
page_cache_release(page);
}
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
+
+ if (locked) {
+ mutex_unlock(&xip_sparse_mutex);
+ } else if (read_seqcount_retry(&xip_sparse_seq, count)) {
+ mutex_lock(&xip_sparse_mutex);
+ locked = 1;
+ goto retry;
+ }
}
/*
@@ -217,7 +231,7 @@ static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
int error;
/* XXX: are VM_FAULT_ codes OK? */
-
+again:
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
@@ -236,8 +250,10 @@ static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
int err;
/* maybe shared writable, allocate new block */
+ mutex_lock(&xip_sparse_mutex);
error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1,
&xip_mem, &xip_pfn);
+ mutex_unlock(&xip_sparse_mutex);
if (error)
return VM_FAULT_SIGBUS;
/* unmap sparse mappings at pgoff from all other vmas */
@@ -248,22 +264,49 @@ found:
xip_pfn);
if (err == -ENOMEM)
return VM_FAULT_OOM;
- BUG_ON(err);
+ /*
+ * err == -EBUSY is fine, we've raced against another thread
+ * that faulted-in the same page
+ */
+ if (err != -EBUSY)
+ BUG_ON(err);
return VM_FAULT_NOPAGE;
} else {
+ int err, ret = VM_FAULT_OOM;
+
+ mutex_lock(&xip_sparse_mutex);
+ write_seqcount_begin(&xip_sparse_seq);
+ error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0,
+ &xip_mem, &xip_pfn);
+ if (unlikely(!error)) {
+ write_seqcount_end(&xip_sparse_seq);
+ mutex_unlock(&xip_sparse_mutex);
+ goto again;
+ }
+ if (error != -ENODATA)
+ goto out;
/* not shared and writable, use xip_sparse_page() */
page = xip_sparse_page();
if (!page)
- return VM_FAULT_OOM;
+ goto out;
+ err = vm_insert_page(vma, (unsigned long)vmf->virtual_address,
+ page);
+ if (err == -ENOMEM)
+ goto out;
- page_cache_get(page);
- vmf->page = page;
- return 0;
+ ret = VM_FAULT_NOPAGE;
+out:
+ write_seqcount_end(&xip_sparse_seq);
+ mutex_unlock(&xip_sparse_mutex);
+
+ return ret;
}
}
-static struct vm_operations_struct xip_file_vm_ops = {
+static const struct vm_operations_struct xip_file_vm_ops = {
.fault = xip_file_fault,
+ .page_mkwrite = filemap_page_mkwrite,
+ .remap_pages = generic_file_remap_pages,
};
int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
@@ -272,7 +315,7 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
file_accessed(file);
vma->vm_ops = &xip_file_vm_ops;
- vma->vm_flags |= VM_CAN_NONLINEAR | VM_MIXEDMAP;
+ vma->vm_flags |= VM_MIXEDMAP;
return 0;
}
EXPORT_SYMBOL_GPL(xip_file_mmap);
@@ -307,8 +350,10 @@ __xip_file_write(struct file *filp, const char __user *buf,
&xip_mem, &xip_pfn);
if (status == -ENODATA) {
/* we allocate a new page unmap it */
+ mutex_lock(&xip_sparse_mutex);
status = a_ops->get_xip_mem(mapping, index, 1,
&xip_mem, &xip_pfn);
+ mutex_unlock(&xip_sparse_mutex);
if (!status)
/* unmap page at pgoff from all other vmas */
__xip_unmap(mapping, index);
@@ -369,8 +414,6 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
pos = *ppos;
count = len;
- vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
-
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
@@ -380,11 +423,13 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
if (count == 0)
goto out_backing;
- ret = remove_suid(filp->f_path.dentry);
+ ret = file_remove_suid(filp);
if (ret)
goto out_backing;
- file_update_time(filp);
+ ret = file_update_time(filp);
+ if (ret)
+ goto out_backing;
ret = __xip_file_write (filp, buf, count, pos, ppos);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-06 21:51:54 +0000