From 9370bb92b2d16684ee45cf24e879c93c509162da Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 19 Dec 2024 01:47:39 +0000
Subject: [PATCH] add wifi6 8852be driver
---
kernel/fs/orangefs/inode.c | 882 ++++++++++++++++++++++++++++++++++++++++++++++++++-------
1 files changed, 763 insertions(+), 119 deletions(-)
diff --git a/kernel/fs/orangefs/inode.c b/kernel/fs/orangefs/inode.c
index 3193287..48f0547 100644
--- a/kernel/fs/orangefs/inode.c
+++ b/kernel/fs/orangefs/inode.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/*
* (C) 2001 Clemson University and The University of Chicago
+ * Copyright 2018 Omnibond Systems, L.L.C.
*
* See COPYING in top-level directory.
*/
@@ -14,40 +15,280 @@
#include "orangefs-kernel.h"
#include "orangefs-bufmap.h"
-static int read_one_page(struct page *page)
+static int orangefs_writepage_locked(struct page *page,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ struct orangefs_write_range *wr = NULL;
+ struct iov_iter iter;
+ struct bio_vec bv;
+ size_t len, wlen;
+ ssize_t ret;
+ loff_t off;
+
+ set_page_writeback(page);
+
+ len = i_size_read(inode);
+ if (PagePrivate(page)) {
+ wr = (struct orangefs_write_range *)page_private(page);
+ WARN_ON(wr->pos >= len);
+ off = wr->pos;
+ if (off + wr->len > len)
+ wlen = len - off;
+ else
+ wlen = wr->len;
+ } else {
+ WARN_ON(1);
+ off = page_offset(page);
+ if (off + PAGE_SIZE > len)
+ wlen = len - off;
+ else
+ wlen = PAGE_SIZE;
+ }
+ /* Should've been handled in orangefs_invalidatepage. */
+ WARN_ON(off == len || off + wlen > len);
+
+ bv.bv_page = page;
+ bv.bv_len = wlen;
+ bv.bv_offset = off % PAGE_SIZE;
+ WARN_ON(wlen == 0);
+ iov_iter_bvec(&iter, WRITE, &bv, 1, wlen);
+
+ ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, wlen,
+ len, wr, NULL, NULL);
+ if (ret < 0) {
+ SetPageError(page);
+ mapping_set_error(page->mapping, ret);
+ } else {
+ ret = 0;
+ }
+ kfree(detach_page_private(page));
+ return ret;
+}
+
+static int orangefs_writepage(struct page *page, struct writeback_control *wbc)
{
int ret;
- int max_block;
- ssize_t bytes_read = 0;
- struct inode *inode = page->mapping->host;
- const __u32 blocksize = PAGE_SIZE;
- const __u32 blockbits = PAGE_SHIFT;
- struct iov_iter to;
- struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE};
+ ret = orangefs_writepage_locked(page, wbc);
+ unlock_page(page);
+ end_page_writeback(page);
+ return ret;
+}
- iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE);
+struct orangefs_writepages {
+ loff_t off;
+ size_t len;
+ kuid_t uid;
+ kgid_t gid;
+ int maxpages;
+ int npages;
+ struct page **pages;
+ struct bio_vec *bv;
+};
- gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_readpage called with page %p\n",
- page);
+static int orangefs_writepages_work(struct orangefs_writepages *ow,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = ow->pages[0]->mapping->host;
+ struct orangefs_write_range *wrp, wr;
+ struct iov_iter iter;
+ ssize_t ret;
+ size_t len;
+ loff_t off;
+ int i;
- max_block = ((inode->i_size / blocksize) + 1);
+ len = i_size_read(inode);
- if (page->index < max_block) {
- loff_t blockptr_offset = (((loff_t) page->index) << blockbits);
-
- bytes_read = orangefs_inode_read(inode,
- &to,
- &blockptr_offset,
- inode->i_size);
+ for (i = 0; i < ow->npages; i++) {
+ set_page_writeback(ow->pages[i]);
+ ow->bv[i].bv_page = ow->pages[i];
+ ow->bv[i].bv_len = min(page_offset(ow->pages[i]) + PAGE_SIZE,
+ ow->off + ow->len) -
+ max(ow->off, page_offset(ow->pages[i]));
+ if (i == 0)
+ ow->bv[i].bv_offset = ow->off -
+ page_offset(ow->pages[i]);
+ else
+ ow->bv[i].bv_offset = 0;
}
+ iov_iter_bvec(&iter, WRITE, ow->bv, ow->npages, ow->len);
+
+ WARN_ON(ow->off >= len);
+ if (ow->off + ow->len > len)
+ ow->len = len - ow->off;
+
+ off = ow->off;
+ wr.uid = ow->uid;
+ wr.gid = ow->gid;
+ ret = wait_for_direct_io(ORANGEFS_IO_WRITE, inode, &off, &iter, ow->len,
+ 0, &wr, NULL, NULL);
+ if (ret < 0) {
+ for (i = 0; i < ow->npages; i++) {
+ SetPageError(ow->pages[i]);
+ mapping_set_error(ow->pages[i]->mapping, ret);
+ if (PagePrivate(ow->pages[i])) {
+ wrp = (struct orangefs_write_range *)
+ page_private(ow->pages[i]);
+ ClearPagePrivate(ow->pages[i]);
+ put_page(ow->pages[i]);
+ kfree(wrp);
+ }
+ end_page_writeback(ow->pages[i]);
+ unlock_page(ow->pages[i]);
+ }
+ } else {
+ ret = 0;
+ for (i = 0; i < ow->npages; i++) {
+ if (PagePrivate(ow->pages[i])) {
+ wrp = (struct orangefs_write_range *)
+ page_private(ow->pages[i]);
+ ClearPagePrivate(ow->pages[i]);
+ put_page(ow->pages[i]);
+ kfree(wrp);
+ }
+ end_page_writeback(ow->pages[i]);
+ unlock_page(ow->pages[i]);
+ }
+ }
+ return ret;
+}
+
+static int orangefs_writepages_callback(struct page *page,
+ struct writeback_control *wbc, void *data)
+{
+ struct orangefs_writepages *ow = data;
+ struct orangefs_write_range *wr;
+ int ret;
+
+ if (!PagePrivate(page)) {
+ unlock_page(page);
+ /* It's not private so there's nothing to write, right? */
+ printk("writepages_callback not private!\n");
+ BUG();
+ return 0;
+ }
+ wr = (struct orangefs_write_range *)page_private(page);
+
+ ret = -1;
+ if (ow->npages == 0) {
+ ow->off = wr->pos;
+ ow->len = wr->len;
+ ow->uid = wr->uid;
+ ow->gid = wr->gid;
+ ow->pages[ow->npages++] = page;
+ ret = 0;
+ goto done;
+ }
+ if (!uid_eq(ow->uid, wr->uid) || !gid_eq(ow->gid, wr->gid)) {
+ orangefs_writepages_work(ow, wbc);
+ ow->npages = 0;
+ ret = -1;
+ goto done;
+ }
+ if (ow->off + ow->len == wr->pos) {
+ ow->len += wr->len;
+ ow->pages[ow->npages++] = page;
+ ret = 0;
+ goto done;
+ }
+done:
+ if (ret == -1) {
+ if (ow->npages) {
+ orangefs_writepages_work(ow, wbc);
+ ow->npages = 0;
+ }
+ ret = orangefs_writepage_locked(page, wbc);
+ mapping_set_error(page->mapping, ret);
+ unlock_page(page);
+ end_page_writeback(page);
+ } else {
+ if (ow->npages == ow->maxpages) {
+ orangefs_writepages_work(ow, wbc);
+ ow->npages = 0;
+ }
+ }
+ return ret;
+}
+
+static int orangefs_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct orangefs_writepages *ow;
+ struct blk_plug plug;
+ int ret;
+ ow = kzalloc(sizeof(struct orangefs_writepages), GFP_KERNEL);
+ if (!ow)
+ return -ENOMEM;
+ ow->maxpages = orangefs_bufmap_size_query()/PAGE_SIZE;
+ ow->pages = kcalloc(ow->maxpages, sizeof(struct page *), GFP_KERNEL);
+ if (!ow->pages) {
+ kfree(ow);
+ return -ENOMEM;
+ }
+ ow->bv = kcalloc(ow->maxpages, sizeof(struct bio_vec), GFP_KERNEL);
+ if (!ow->bv) {
+ kfree(ow->pages);
+ kfree(ow);
+ return -ENOMEM;
+ }
+ blk_start_plug(&plug);
+ ret = write_cache_pages(mapping, wbc, orangefs_writepages_callback, ow);
+ if (ow->npages)
+ ret = orangefs_writepages_work(ow, wbc);
+ blk_finish_plug(&plug);
+ kfree(ow->pages);
+ kfree(ow->bv);
+ kfree(ow);
+ return ret;
+}
+
+static int orangefs_launder_page(struct page *);
+
+static int orangefs_readpage(struct file *file, struct page *page)
+{
+ struct inode *inode = page->mapping->host;
+ struct iov_iter iter;
+ struct bio_vec bv;
+ ssize_t ret;
+ loff_t off; /* offset into this page */
+ pgoff_t index; /* which page */
+ struct page *next_page;
+ char *kaddr;
+ loff_t read_size;
+ int buffer_index = -1; /* orangefs shared memory slot */
+ int slot_index; /* index into slot */
+ int remaining;
+
+ /*
+ * Get up to this many bytes from Orangefs at a time and try
+ * to fill them into the page cache at once. Tests with dd made
+ * this seem like a reasonable static number, if there was
+ * interest perhaps this number could be made setable through
+ * sysfs...
+ */
+ read_size = 524288;
+
+ if (PageDirty(page))
+ orangefs_launder_page(page);
+
+ off = page_offset(page);
+ index = off >> PAGE_SHIFT;
+ bv.bv_page = page;
+ bv.bv_len = PAGE_SIZE;
+ bv.bv_offset = 0;
+ iov_iter_bvec(&iter, READ, &bv, 1, PAGE_SIZE);
+
+ ret = wait_for_direct_io(ORANGEFS_IO_READ, inode, &off, &iter,
+ read_size, inode->i_size, NULL, &buffer_index, file);
+ remaining = ret;
/* this will only zero remaining unread portions of the page data */
- iov_iter_zero(~0U, &to);
+ iov_iter_zero(~0U, &iter);
/* takes care of potential aliasing */
flush_dcache_page(page);
- if (bytes_read < 0) {
- ret = bytes_read;
+ if (ret < 0) {
SetPageError(page);
+ unlock_page(page);
+ goto out;
} else {
SetPageUptodate(page);
if (PageError(page))
@@ -56,95 +297,453 @@
}
/* unlock the page after the ->readpage() routine completes */
unlock_page(page);
+
+ if (remaining > PAGE_SIZE) {
+ slot_index = 0;
+ while ((remaining - PAGE_SIZE) >= PAGE_SIZE) {
+ remaining -= PAGE_SIZE;
+ /*
+ * It is an optimization to try and fill more than one
+ * page... by now we've already gotten the single
+ * page we were after, if stuff doesn't seem to
+ * be going our way at this point just return
+ * and hope for the best.
+ *
+ * If we look for pages and they're already there is
+ * one reason to give up, and if they're not there
+ * and we can't create them is another reason.
+ */
+
+ index++;
+ slot_index++;
+ next_page = find_get_page(inode->i_mapping, index);
+ if (next_page) {
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s: found next page, quitting\n",
+ __func__);
+ put_page(next_page);
+ goto out;
+ }
+ next_page = find_or_create_page(inode->i_mapping,
+ index,
+ GFP_KERNEL);
+ /*
+ * I've never hit this, leave it as a printk for
+ * now so it will be obvious.
+ */
+ if (!next_page) {
+ printk("%s: can't create next page, quitting\n",
+ __func__);
+ goto out;
+ }
+ kaddr = kmap_atomic(next_page);
+ orangefs_bufmap_page_fill(kaddr,
+ buffer_index,
+ slot_index);
+ kunmap_atomic(kaddr);
+ SetPageUptodate(next_page);
+ unlock_page(next_page);
+ put_page(next_page);
+ }
+ }
+
+out:
+ if (buffer_index != -1)
+ orangefs_bufmap_put(buffer_index);
return ret;
}
-static int orangefs_readpage(struct file *file, struct page *page)
+static int orangefs_write_begin(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags, struct page **pagep,
+ void **fsdata)
{
- return read_one_page(page);
-}
-
-static int orangefs_readpages(struct file *file,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned nr_pages)
-{
- int page_idx;
+ struct orangefs_write_range *wr;
+ struct page *page;
+ pgoff_t index;
int ret;
- gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpages called\n");
+ index = pos >> PAGE_SHIFT;
- for (page_idx = 0; page_idx < nr_pages; page_idx++) {
- struct page *page;
+ page = grab_cache_page_write_begin(mapping, index, flags);
+ if (!page)
+ return -ENOMEM;
- page = list_entry(pages->prev, struct page, lru);
- list_del(&page->lru);
- if (!add_to_page_cache(page,
- mapping,
- page->index,
- readahead_gfp_mask(mapping))) {
- ret = read_one_page(page);
- gossip_debug(GOSSIP_INODE_DEBUG,
- "failure adding page to cache, read_one_page returned: %d\n",
- ret);
- } else {
- put_page(page);
- }
+ *pagep = page;
+
+ if (PageDirty(page) && !PagePrivate(page)) {
+ /*
+ * Should be impossible. If it happens, launder the page
+ * since we don't know what's dirty. This will WARN in
+ * orangefs_writepage_locked.
+ */
+ ret = orangefs_launder_page(page);
+ if (ret)
+ return ret;
}
- BUG_ON(!list_empty(pages));
+ if (PagePrivate(page)) {
+ struct orangefs_write_range *wr;
+ wr = (struct orangefs_write_range *)page_private(page);
+ if (wr->pos + wr->len == pos &&
+ uid_eq(wr->uid, current_fsuid()) &&
+ gid_eq(wr->gid, current_fsgid())) {
+ wr->len += len;
+ goto okay;
+ } else {
+ ret = orangefs_launder_page(page);
+ if (ret)
+ return ret;
+ }
+ }
+
+ wr = kmalloc(sizeof *wr, GFP_KERNEL);
+ if (!wr)
+ return -ENOMEM;
+
+ wr->pos = pos;
+ wr->len = len;
+ wr->uid = current_fsuid();
+ wr->gid = current_fsgid();
+ attach_page_private(page, wr);
+okay:
return 0;
+}
+
+static int orangefs_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata)
+{
+ struct inode *inode = page->mapping->host;
+ loff_t last_pos = pos + copied;
+
+ /*
+ * No need to use i_size_read() here, the i_size
+ * cannot change under us because we hold the i_mutex.
+ */
+ if (last_pos > inode->i_size)
+ i_size_write(inode, last_pos);
+
+ /* zero the stale part of the page if we did a short copy */
+ if (!PageUptodate(page)) {
+ unsigned from = pos & (PAGE_SIZE - 1);
+ if (copied < len) {
+ zero_user(page, from + copied, len - copied);
+ }
+ /* Set fully written pages uptodate. */
+ if (pos == page_offset(page) &&
+ (len == PAGE_SIZE || pos + len == inode->i_size)) {
+ zero_user_segment(page, from + copied, PAGE_SIZE);
+ SetPageUptodate(page);
+ }
+ }
+
+ set_page_dirty(page);
+ unlock_page(page);
+ put_page(page);
+
+ mark_inode_dirty_sync(file_inode(file));
+ return copied;
}
static void orangefs_invalidatepage(struct page *page,
unsigned int offset,
unsigned int length)
{
- gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_invalidatepage called on page %p "
- "(offset is %u)\n",
- page,
- offset);
+ struct orangefs_write_range *wr;
+ wr = (struct orangefs_write_range *)page_private(page);
- ClearPageUptodate(page);
- ClearPageMappedToDisk(page);
- return;
+ if (offset == 0 && length == PAGE_SIZE) {
+ kfree(detach_page_private(page));
+ return;
+ /* write range entirely within invalidate range (or equal) */
+ } else if (page_offset(page) + offset <= wr->pos &&
+ wr->pos + wr->len <= page_offset(page) + offset + length) {
+ kfree(detach_page_private(page));
+ /* XXX is this right? only caller in fs */
+ cancel_dirty_page(page);
+ return;
+ /* invalidate range chops off end of write range */
+ } else if (wr->pos < page_offset(page) + offset &&
+ wr->pos + wr->len <= page_offset(page) + offset + length &&
+ page_offset(page) + offset < wr->pos + wr->len) {
+ size_t x;
+ x = wr->pos + wr->len - (page_offset(page) + offset);
+ WARN_ON(x > wr->len);
+ wr->len -= x;
+ wr->uid = current_fsuid();
+ wr->gid = current_fsgid();
+ /* invalidate range chops off beginning of write range */
+ } else if (page_offset(page) + offset <= wr->pos &&
+ page_offset(page) + offset + length < wr->pos + wr->len &&
+ wr->pos < page_offset(page) + offset + length) {
+ size_t x;
+ x = page_offset(page) + offset + length - wr->pos;
+ WARN_ON(x > wr->len);
+ wr->pos += x;
+ wr->len -= x;
+ wr->uid = current_fsuid();
+ wr->gid = current_fsgid();
+ /* invalidate range entirely within write range (punch hole) */
+ } else if (wr->pos < page_offset(page) + offset &&
+ page_offset(page) + offset + length < wr->pos + wr->len) {
+ /* XXX what do we do here... should not WARN_ON */
+ WARN_ON(1);
+ /* punch hole */
+ /*
+ * should we just ignore this and write it out anyway?
+ * it hardly makes sense
+ */
+ return;
+ /* non-overlapping ranges */
+ } else {
+ /* WARN if they do overlap */
+ if (!((page_offset(page) + offset + length <= wr->pos) ^
+ (wr->pos + wr->len <= page_offset(page) + offset))) {
+ WARN_ON(1);
+ printk("invalidate range offset %llu length %u\n",
+ page_offset(page) + offset, length);
+ printk("write range offset %llu length %zu\n",
+ wr->pos, wr->len);
+ }
+ return;
+ }
+ /*
+ * Above there are returns where wr is freed or where we WARN.
+ * Thus the following runs if wr was modified above.
+ */
+
+ orangefs_launder_page(page);
}
static int orangefs_releasepage(struct page *page, gfp_t foo)
{
- gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_releasepage called on page %p\n",
- page);
- return 0;
+ return !PagePrivate(page);
}
-/*
- * Having a direct_IO entry point in the address_space_operations
- * struct causes the kernel to allows us to use O_DIRECT on
- * open. Nothing will ever call this thing, but in the future we
- * will need to be able to use O_DIRECT on open in order to support
- * AIO. Modeled after NFS, they do this too.
- */
+static void orangefs_freepage(struct page *page)
+{
+ kfree(detach_page_private(page));
+}
+
+static int orangefs_launder_page(struct page *page)
+{
+ int r = 0;
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 0,
+ };
+ wait_on_page_writeback(page);
+ if (clear_page_dirty_for_io(page)) {
+ r = orangefs_writepage_locked(page, &wbc);
+ end_page_writeback(page);
+ }
+ return r;
+}
static ssize_t orangefs_direct_IO(struct kiocb *iocb,
struct iov_iter *iter)
{
- gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_direct_IO: %pD\n",
- iocb->ki_filp);
+ /*
+ * Comment from original do_readv_writev:
+ * Common entry point for read/write/readv/writev
+ * This function will dispatch it to either the direct I/O
+ * or buffered I/O path depending on the mount options and/or
+ * augmented/extended metadata attached to the file.
+ * Note: File extended attributes override any mount options.
+ */
+ struct file *file = iocb->ki_filp;
+ loff_t pos = iocb->ki_pos;
+ enum ORANGEFS_io_type type = iov_iter_rw(iter) == WRITE ?
+ ORANGEFS_IO_WRITE : ORANGEFS_IO_READ;
+ loff_t *offset = &pos;
+ struct inode *inode = file->f_mapping->host;
+ struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+ struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
+ size_t count = iov_iter_count(iter);
+ ssize_t total_count = 0;
+ ssize_t ret = -EINVAL;
+ int i = 0;
- return -EINVAL;
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s-BEGIN(%pU): count(%d) after estimate_max_iovecs.\n",
+ __func__,
+ handle,
+ (int)count);
+
+ if (type == ORANGEFS_IO_WRITE) {
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s(%pU): proceeding with offset : %llu, "
+ "size %d\n",
+ __func__,
+ handle,
+ llu(*offset),
+ (int)count);
+ }
+
+ if (count == 0) {
+ ret = 0;
+ goto out;
+ }
+
+ while (iov_iter_count(iter)) {
+ size_t each_count = iov_iter_count(iter);
+ size_t amt_complete;
+ i++;
+
+ /* how much to transfer in this loop iteration */
+ if (each_count > orangefs_bufmap_size_query())
+ each_count = orangefs_bufmap_size_query();
+
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s(%pU): size of each_count(%d)\n",
+ __func__,
+ handle,
+ (int)each_count);
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s(%pU): BEFORE wait_for_io: offset is %d\n",
+ __func__,
+ handle,
+ (int)*offset);
+
+ ret = wait_for_direct_io(type, inode, offset, iter,
+ each_count, 0, NULL, NULL, file);
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s(%pU): return from wait_for_io:%d\n",
+ __func__,
+ handle,
+ (int)ret);
+
+ if (ret < 0)
+ goto out;
+
+ *offset += ret;
+ total_count += ret;
+ amt_complete = ret;
+
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s(%pU): AFTER wait_for_io: offset is %d\n",
+ __func__,
+ handle,
+ (int)*offset);
+
+ /*
+ * if we got a short I/O operations,
+ * fall out and return what we got so far
+ */
+ if (amt_complete < each_count)
+ break;
+ } /*end while */
+
+out:
+ if (total_count > 0)
+ ret = total_count;
+ if (ret > 0) {
+ if (type == ORANGEFS_IO_READ) {
+ file_accessed(file);
+ } else {
+ file_update_time(file);
+ if (*offset > i_size_read(inode))
+ i_size_write(inode, *offset);
+ }
+ }
+
+ gossip_debug(GOSSIP_FILE_DEBUG,
+ "%s(%pU): Value(%d) returned.\n",
+ __func__,
+ handle,
+ (int)ret);
+
+ return ret;
}
/** ORANGEFS2 implementation of address space operations */
static const struct address_space_operations orangefs_address_operations = {
+ .writepage = orangefs_writepage,
.readpage = orangefs_readpage,
- .readpages = orangefs_readpages,
+ .writepages = orangefs_writepages,
+ .set_page_dirty = __set_page_dirty_nobuffers,
+ .write_begin = orangefs_write_begin,
+ .write_end = orangefs_write_end,
.invalidatepage = orangefs_invalidatepage,
.releasepage = orangefs_releasepage,
+ .freepage = orangefs_freepage,
+ .launder_page = orangefs_launder_page,
.direct_IO = orangefs_direct_IO,
};
+
+vm_fault_t orangefs_page_mkwrite(struct vm_fault *vmf)
+{
+ struct page *page = vmf->page;
+ struct inode *inode = file_inode(vmf->vma->vm_file);
+ struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+ unsigned long *bitlock = &orangefs_inode->bitlock;
+ vm_fault_t ret;
+ struct orangefs_write_range *wr;
+
+ sb_start_pagefault(inode->i_sb);
+
+ if (wait_on_bit(bitlock, 1, TASK_KILLABLE)) {
+ ret = VM_FAULT_RETRY;
+ goto out;
+ }
+
+ lock_page(page);
+ if (PageDirty(page) && !PagePrivate(page)) {
+ /*
+ * Should be impossible. If it happens, launder the page
+ * since we don't know what's dirty. This will WARN in
+ * orangefs_writepage_locked.
+ */
+ if (orangefs_launder_page(page)) {
+ ret = VM_FAULT_LOCKED|VM_FAULT_RETRY;
+ goto out;
+ }
+ }
+ if (PagePrivate(page)) {
+ wr = (struct orangefs_write_range *)page_private(page);
+ if (uid_eq(wr->uid, current_fsuid()) &&
+ gid_eq(wr->gid, current_fsgid())) {
+ wr->pos = page_offset(page);
+ wr->len = PAGE_SIZE;
+ goto okay;
+ } else {
+ if (orangefs_launder_page(page)) {
+ ret = VM_FAULT_LOCKED|VM_FAULT_RETRY;
+ goto out;
+ }
+ }
+ }
+ wr = kmalloc(sizeof *wr, GFP_KERNEL);
+ if (!wr) {
+ ret = VM_FAULT_LOCKED|VM_FAULT_RETRY;
+ goto out;
+ }
+ wr->pos = page_offset(page);
+ wr->len = PAGE_SIZE;
+ wr->uid = current_fsuid();
+ wr->gid = current_fsgid();
+ attach_page_private(page, wr);
+okay:
+
+ file_update_time(vmf->vma->vm_file);
+ if (page->mapping != inode->i_mapping) {
+ unlock_page(page);
+ ret = VM_FAULT_LOCKED|VM_FAULT_NOPAGE;
+ goto out;
+ }
+
+ /*
+ * We mark the page dirty already here so that when freeze is in
+ * progress, we are guaranteed that writeback during freezing will
+ * see the dirty page and writeprotect it again.
+ */
+ set_page_dirty(page);
+ wait_for_stable_page(page);
+ ret = VM_FAULT_LOCKED;
+out:
+ sb_end_pagefault(inode->i_sb);
+ return ret;
+}
static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
{
@@ -162,7 +761,7 @@
iattr->ia_size);
/* Ensure that we have a up to date size, so we know if it changed. */
- ret = orangefs_inode_getattr(inode, 0, 1, STATX_SIZE);
+ ret = orangefs_inode_getattr(inode, ORANGEFS_GETATTR_SIZE);
if (ret == -ESTALE)
ret = -EIO;
if (ret) {
@@ -172,7 +771,11 @@
}
orig_size = i_size_read(inode);
- truncate_setsize(inode, iattr->ia_size);
+ /* This is truncate_setsize in a different order. */
+ truncate_pagecache(inode, iattr->ia_size);
+ i_size_write(inode, iattr->ia_size);
+ if (iattr->ia_size > orig_size)
+ pagecache_isize_extended(inode, orig_size, iattr->ia_size);
new_op = op_alloc(ORANGEFS_VFS_OP_TRUNCATE);
if (!new_op)
@@ -202,22 +805,33 @@
return ret;
}
-/*
- * Change attributes of an object referenced by dentry.
- */
-int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
+int __orangefs_setattr(struct inode *inode, struct iattr *iattr)
{
- int ret = -EINVAL;
- struct inode *inode = dentry->d_inode;
+ int ret;
- gossip_debug(GOSSIP_INODE_DEBUG,
- "%s: called on %pd\n",
- __func__,
- dentry);
-
- ret = setattr_prepare(dentry, iattr);
- if (ret)
- goto out;
+ if (iattr->ia_valid & ATTR_MODE) {
+ if (iattr->ia_mode & (S_ISVTX)) {
+ if (is_root_handle(inode)) {
+ /*
+ * allow sticky bit to be set on root (since
+ * it shows up that way by default anyhow),
+ * but don't show it to the server
+ */
+ iattr->ia_mode -= S_ISVTX;
+ } else {
+ gossip_debug(GOSSIP_UTILS_DEBUG,
+ "User attempted to set sticky bit on non-root directory; returning EINVAL.\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+ if (iattr->ia_mode & (S_ISUID)) {
+ gossip_debug(GOSSIP_UTILS_DEBUG,
+ "Attempting to set setuid bit (not supported); returning EINVAL.\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ }
if (iattr->ia_valid & ATTR_SIZE) {
ret = orangefs_setattr_size(inode, iattr);
@@ -225,21 +839,51 @@
goto out;
}
+again:
+ spin_lock(&inode->i_lock);
+ if (ORANGEFS_I(inode)->attr_valid) {
+ if (uid_eq(ORANGEFS_I(inode)->attr_uid, current_fsuid()) &&
+ gid_eq(ORANGEFS_I(inode)->attr_gid, current_fsgid())) {
+ ORANGEFS_I(inode)->attr_valid = iattr->ia_valid;
+ } else {
+ spin_unlock(&inode->i_lock);
+ write_inode_now(inode, 1);
+ goto again;
+ }
+ } else {
+ ORANGEFS_I(inode)->attr_valid = iattr->ia_valid;
+ ORANGEFS_I(inode)->attr_uid = current_fsuid();
+ ORANGEFS_I(inode)->attr_gid = current_fsgid();
+ }
setattr_copy(inode, iattr);
+ spin_unlock(&inode->i_lock);
mark_inode_dirty(inode);
- ret = orangefs_inode_setattr(inode, iattr);
- gossip_debug(GOSSIP_INODE_DEBUG,
- "%s: orangefs_inode_setattr returned %d\n",
- __func__,
- ret);
-
- if (!ret && (iattr->ia_valid & ATTR_MODE))
+ if (iattr->ia_valid & ATTR_MODE)
/* change mod on a file that has ACLs */
ret = posix_acl_chmod(inode, inode->i_mode);
+ ret = 0;
out:
- gossip_debug(GOSSIP_INODE_DEBUG, "%s: ret:%d:\n", __func__, ret);
+ return ret;
+}
+
+/*
+ * Change attributes of an object referenced by dentry.
+ */
+int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+ int ret;
+ gossip_debug(GOSSIP_INODE_DEBUG, "__orangefs_setattr: called on %pd\n",
+ dentry);
+ ret = setattr_prepare(dentry, iattr);
+ if (ret)
+ goto out;
+ ret = __orangefs_setattr(d_inode(dentry), iattr);
+ sync_inode_metadata(d_inode(dentry), 1);
+out:
+ gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_setattr: returning %d\n",
+ ret);
return ret;
}
@@ -249,23 +893,21 @@
int orangefs_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
- int ret = -ENOENT;
+ int ret;
struct inode *inode = path->dentry->d_inode;
gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_getattr: called on %pd\n",
- path->dentry);
+ "orangefs_getattr: called on %pd mask %u\n",
+ path->dentry, request_mask);
- ret = orangefs_inode_getattr(inode, 0, 0, request_mask);
+ ret = orangefs_inode_getattr(inode,
+ request_mask & STATX_SIZE ? ORANGEFS_GETATTR_SIZE : 0);
if (ret == 0) {
generic_fillattr(inode, stat);
/* override block size reported to stat */
- if (request_mask & STATX_SIZE)
- stat->result_mask = STATX_BASIC_STATS;
- else
- stat->result_mask = STATX_BASIC_STATS &
- ~STATX_SIZE;
+ if (!(request_mask & STATX_SIZE))
+ stat->result_mask &= ~STATX_SIZE;
stat->attributes_mask = STATX_ATTR_IMMUTABLE |
STATX_ATTR_APPEND;
@@ -287,7 +929,7 @@
gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__);
/* Make sure the permission (and other common attrs) are up to date. */
- ret = orangefs_inode_getattr(inode, 0, 0, STATX_MODE);
+ ret = orangefs_inode_getattr(inode, 0);
if (ret < 0)
return ret;
@@ -307,7 +949,7 @@
iattr.ia_valid |= ATTR_CTIME;
if (flags & S_MTIME)
iattr.ia_valid |= ATTR_MTIME;
- return orangefs_inode_setattr(inode, &iattr);
+ return __orangefs_setattr(inode, &iattr);
}
/* ORANGEFS2 implementation of VFS inode operations for files */
@@ -367,6 +1009,10 @@
struct orangefs_object_kref *ref = (struct orangefs_object_kref *) data;
ORANGEFS_I(inode)->refn.fs_id = ref->fs_id;
ORANGEFS_I(inode)->refn.khandle = ref->khandle;
+ ORANGEFS_I(inode)->attr_valid = 0;
+ hash_init(ORANGEFS_I(inode)->xattr_cache);
+ ORANGEFS_I(inode)->mapping_time = jiffies - 1;
+ ORANGEFS_I(inode)->bitlock = 0;
return 0;
}
@@ -405,10 +1051,14 @@
orangefs_test_inode,
orangefs_set_inode,
ref);
- if (!inode || !(inode->i_state & I_NEW))
+
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+
+ if (!(inode->i_state & I_NEW))
return inode;
- error = orangefs_inode_getattr(inode, 1, 1, STATX_ALL);
+ error = orangefs_inode_getattr(inode, ORANGEFS_GETATTR_NEW);
if (error) {
iget_failed(inode);
return ERR_PTR(error);
@@ -448,22 +1098,16 @@
inode = new_inode(sb);
if (!inode)
- return NULL;
+ return ERR_PTR(-ENOMEM);
orangefs_set_inode(inode, ref);
inode->i_ino = hash; /* needed for stat etc */
- error = orangefs_inode_getattr(inode, 1, 1, STATX_ALL);
+ error = orangefs_inode_getattr(inode, ORANGEFS_GETATTR_NEW);
if (error)
goto out_iput;
orangefs_init_iops(inode);
-
- inode->i_mode = mode;
- inode->i_uid = current_fsuid();
- inode->i_gid = current_fsgid();
- inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
- inode->i_size = PAGE_SIZE;
inode->i_rdev = dev;
error = insert_inode_locked4(inode, hash, orangefs_test_inode, ref);
--
Gitblit v1.6.2