@@ -88,6 +88,8 @@ static void netfs_free_read_request(struct work_struct *work)
if (rreq->netfs_priv)
rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv);
trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+ if (rreq->cache_resources.ops)
+ rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
kfree(rreq);
netfs_stat_d(&netfs_n_rh_rreq);
}
@@ -154,6 +156,34 @@ static void netfs_clear_unread(struct netfs_read_subrequest *subreq)
iov_iter_zero(iov_iter_count(&iter), &iter);
}
+static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error,
+ bool was_async)
+{
+ struct netfs_read_subrequest *subreq = priv;
+
+ netfs_subreq_terminated(subreq, transferred_or_error, was_async);
+}
+
+/*
+ * Issue a read against the cache.
+ * - Eats the caller's ref on subreq.
+ */
+static void netfs_read_from_cache(struct netfs_read_request *rreq,
+ struct netfs_read_subrequest *subreq,
+ bool seek_data)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ struct iov_iter iter;
+
+ netfs_stat(&netfs_n_rh_read);
+ iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages,
+ subreq->start + subreq->transferred,
+ subreq->len - subreq->transferred);
+
+ cres->ops->read(cres, subreq->start, &iter, seek_data,
+ netfs_cache_read_terminated, subreq);
+}
+
/*
* Fill a subrequest region with zeroes.
*/
@@ -198,6 +228,141 @@ static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async
netfs_put_read_request(rreq, was_async);
}
+/*
+ * Deal with the completion of writing the data to the cache. We have to clear
+ * the PG_fscache bits on the pages involved and release the caller's ref.
+ *
+ * May be called in softirq mode and we inherit a ref from the caller.
+ */
+static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq,
+ bool was_async)
+{
+ struct netfs_read_subrequest *subreq;
+ struct page *page;
+ pgoff_t unlocked = 0;
+ bool have_unlocked = false;
+
+ rcu_read_lock();
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE);
+
+ xas_for_each(&xas, page, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
+ /* We might have multiple writes from the same huge
+ * page, but we mustn't unlock a page more than once.
+ */
+ if (have_unlocked && page->index <= unlocked)
+ continue;
+ unlocked = page->index;
+ end_page_fscache(page);
+ have_unlocked = true;
+ }
+ }
+
+ rcu_read_unlock();
+ netfs_rreq_completed(rreq, was_async);
+}
+
+static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error,
+ bool was_async)
+{
+ struct netfs_read_subrequest *subreq = priv;
+ struct netfs_read_request *rreq = subreq->rreq;
+
+ if (IS_ERR_VALUE(transferred_or_error)) {
+ netfs_stat(&netfs_n_rh_write_failed);
+ } else {
+ netfs_stat(&netfs_n_rh_write_done);
+ }
+
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_term);
+
+ /* If we decrement nr_wr_ops to 0, the ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_wr_ops))
+ netfs_rreq_unmark_after_write(rreq, was_async);
+
+ netfs_put_subrequest(subreq, was_async);
+}
+
+/*
+ * Perform any outstanding writes to the cache. We inherit a ref from the
+ * caller.
+ */
+static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ struct netfs_read_subrequest *subreq, *next, *p;
+ struct iov_iter iter;
+ int ret;
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_write);
+
+ /* We don't want terminating writes trying to wake us up whilst we're
+ * still going through the list.
+ */
+ atomic_inc(&rreq->nr_wr_ops);
+
+ list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) {
+ if (!test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) {
+ list_del_init(&subreq->rreq_link);
+ netfs_put_subrequest(subreq, false);
+ }
+ }
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ /* Amalgamate adjacent writes */
+ while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ next = list_next_entry(subreq, rreq_link);
+ if (next->start != subreq->start + subreq->len)
+ break;
+ subreq->len += next->len;
+ list_del_init(&next->rreq_link);
+ netfs_put_subrequest(next, false);
+ }
+
+ ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
+ rreq->i_size);
+ if (ret < 0) {
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
+ continue;
+ }
+
+ iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages,
+ subreq->start, subreq->len);
+
+ atomic_inc(&rreq->nr_wr_ops);
+ netfs_stat(&netfs_n_rh_write);
+ netfs_get_read_subrequest(subreq);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write);
+ cres->ops->write(cres, subreq->start, &iter,
+ netfs_rreq_copy_terminated, subreq);
+ }
+
+ /* If we decrement nr_wr_ops to 0, the usage ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_wr_ops))
+ netfs_rreq_unmark_after_write(rreq, false);
+}
+
+static void netfs_rreq_write_to_cache_work(struct work_struct *work)
+{
+ struct netfs_read_request *rreq =
+ container_of(work, struct netfs_read_request, work);
+
+ netfs_rreq_do_write_to_cache(rreq);
+}
+
+static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq,
+ bool was_async)
+{
+ if (was_async) {
+ rreq->work.func = netfs_rreq_write_to_cache_work;
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
+ } else {
+ netfs_rreq_do_write_to_cache(rreq);
+ }
+}
+
/*
* Unlock the pages in a read operation. We need to set PG_fscache on any
* pages we're going to write back before we unlock them.
@@ -299,7 +464,10 @@ static void netfs_rreq_short_read(struct netfs_read_request *rreq,
netfs_get_read_subrequest(subreq);
atomic_inc(&rreq->nr_rd_ops);
- netfs_read_from_server(rreq, subreq);
+ if (subreq->source == NETFS_READ_FROM_CACHE)
+ netfs_read_from_cache(rreq, subreq, true);
+ else
+ netfs_read_from_server(rreq, subreq);
}
/*
@@ -344,6 +512,25 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_read_request *rreq)
return false;
}
+/*
+ * Check to see if the data read is still valid.
+ */
+static void netfs_rreq_is_still_valid(struct netfs_read_request *rreq)
+{
+ struct netfs_read_subrequest *subreq;
+
+ if (!rreq->netfs_ops->is_still_valid ||
+ rreq->netfs_ops->is_still_valid(rreq))
+ return;
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ if (subreq->source == NETFS_READ_FROM_CACHE) {
+ subreq->error = -ESTALE;
+ __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags);
+ }
+ }
+}
+
/*
* Assess the state of a read request and decide what to do next.
*
@@ -355,6 +542,8 @@ static void netfs_rreq_assess(struct netfs_read_request *rreq, bool was_async)
trace_netfs_rreq(rreq, netfs_rreq_trace_assess);
again:
+ netfs_rreq_is_still_valid(rreq);
+
if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) &&
test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) {
if (netfs_rreq_perform_resubmissions(rreq))
@@ -367,6 +556,9 @@ static void netfs_rreq_assess(struct netfs_read_request *rreq, bool was_async)
clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
+ if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags))
+ return netfs_rreq_write_to_cache(rreq, was_async);
+
netfs_rreq_completed(rreq, was_async);
}
@@ -504,7 +696,10 @@ static enum netfs_read_source netfs_cache_prepare_read(struct netfs_read_subrequ
loff_t i_size)
{
struct netfs_read_request *rreq = subreq->rreq;
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ if (cres->ops)
+ return cres->ops->prepare_read(subreq, i_size);
if (subreq->start >= rreq->i_size)
return NETFS_FILL_WITH_ZEROES;
return NETFS_DOWNLOAD_FROM_SERVER;
@@ -595,6 +790,9 @@ static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq,
case NETFS_DOWNLOAD_FROM_SERVER:
netfs_read_from_server(rreq, subreq);
break;
+ case NETFS_READ_FROM_CACHE:
+ netfs_read_from_cache(rreq, subreq, false);
+ break;
default:
BUG();
}
@@ -607,9 +805,23 @@ static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq,
return false;
}
+static void netfs_cache_expand_readahead(struct netfs_read_request *rreq,
+ loff_t *_start, size_t *_len, loff_t i_size)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+
+ if (cres->ops && cres->ops->expand_readahead)
+ cres->ops->expand_readahead(cres, _start, _len, i_size);
+}
+
static void netfs_rreq_expand(struct netfs_read_request *rreq,
struct readahead_control *ractl)
{
+ /* Give the cache a chance to change the request parameters. The
+ * resultant request must contain the original region.
+ */
+ netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size);
+
/* Give the netfs a chance to change the request parameters. The
* resultant request must contain the original region.
*/
@@ -661,6 +873,7 @@ void netfs_readahead(struct readahead_control *ractl,
struct netfs_read_request *rreq;
struct page *page;
unsigned int debug_index = 0;
+ int ret;
_enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
@@ -674,6 +887,12 @@ void netfs_readahead(struct readahead_control *ractl,
rreq->start = readahead_pos(ractl);
rreq->len = readahead_length(ractl);
+ if (ops->begin_cache_operation) {
+ ret = ops->begin_cache_operation(rreq);
+ if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+ goto cleanup_free;
+ }
+
netfs_stat(&netfs_n_rh_readahead);
trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
netfs_read_trace_readahead);
@@ -698,6 +917,9 @@ void netfs_readahead(struct readahead_control *ractl,
netfs_rreq_assess(rreq, false);
return;
+cleanup_free:
+ netfs_put_read_request(rreq, false);
+ return;
cleanup:
if (netfs_priv)
ops->cleanup(ractl->mapping, netfs_priv);
@@ -744,6 +966,14 @@ int netfs_readpage(struct file *file,
rreq->start = page_index(page) * PAGE_SIZE;
rreq->len = thp_size(page);
+ if (ops->begin_cache_operation) {
+ ret = ops->begin_cache_operation(rreq);
+ if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) {
+ unlock_page(page);
+ goto out;
+ }
+ }
+
netfs_stat(&netfs_n_rh_readpage);
trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
@@ -768,6 +998,7 @@ int netfs_readpage(struct file *file,
ret = rreq->error;
if (ret == 0 && rreq->submitted < rreq->len)
ret = -EIO;
+out:
netfs_put_read_request(rreq, false);
return ret;
}
@@ -873,6 +1104,12 @@ int netfs_write_begin(struct file *file, struct address_space *mapping,
__set_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags);
netfs_priv = NULL;
+ if (ops->begin_cache_operation) {
+ ret = ops->begin_cache_operation(rreq);
+ if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+ goto error_put;
+ }
+
netfs_stat(&netfs_n_rh_write_begin);
trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin);
@@ -92,6 +92,18 @@ enum netfs_read_source {
NETFS_INVALID_READ,
} __mode(byte);
+typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error,
+ bool was_async);
+
+/*
+ * Resources required to do operations on a cache.
+ */
+struct netfs_cache_resources {
+ const struct netfs_cache_ops *ops;
+ void *cache_priv;
+ void *cache_priv2;
+};
+
/*
* Descriptor for a single component subrequest.
*/
@@ -121,11 +133,13 @@ struct netfs_read_request {
struct work_struct work;
struct inode *inode; /* The file being accessed */
struct address_space *mapping; /* The mapping being accessed */
+ struct netfs_cache_resources cache_resources;
struct list_head subrequests; /* Requests to fetch I/O from disk or net */
void *netfs_priv; /* Private data for the netfs */
unsigned int debug_id;
unsigned int cookie_debug_id;
atomic_t nr_rd_ops; /* Number of read ops in progress */
+ atomic_t nr_wr_ops; /* Number of write ops in progress */
size_t submitted; /* Amount submitted for I/O so far */
size_t len; /* Length of the request */
short error; /* 0 or error that occurred */
@@ -149,6 +163,7 @@ struct netfs_read_request {
struct netfs_read_request_ops {
bool (*is_cache_enabled)(struct inode *inode);
void (*init_rreq)(struct netfs_read_request *rreq, struct file *file);
+ int (*begin_cache_operation)(struct netfs_read_request *rreq);
void (*expand_readahead)(struct netfs_read_request *rreq);
bool (*clamp_length)(struct netfs_read_subrequest *subreq);
void (*issue_op)(struct netfs_read_subrequest *subreq);
@@ -159,6 +174,46 @@ struct netfs_read_request_ops {
void (*cleanup)(struct address_space *mapping, void *netfs_priv);
};
+/*
+ * Table of operations for access to a cache. This is obtained by
+ * rreq->ops->begin_cache_operation().
+ */
+struct netfs_cache_ops {
+ /* End an operation */
+ void (*end_operation)(struct netfs_cache_resources *cres);
+
+ /* Read data from the cache */
+ int (*read)(struct netfs_cache_resources *cres,
+ loff_t start_pos,
+ struct iov_iter *iter,
+ bool seek_data,
+ netfs_io_terminated_t term_func,
+ void *term_func_priv);
+
+ /* Write data to the cache */
+ int (*write)(struct netfs_cache_resources *cres,
+ loff_t start_pos,
+ struct iov_iter *iter,
+ netfs_io_terminated_t term_func,
+ void *term_func_priv);
+
+ /* Expand readahead request */
+ void (*expand_readahead)(struct netfs_cache_resources *cres,
+ loff_t *_start, size_t *_len, loff_t i_size);
+
+ /* Prepare a read operation, shortening it to a cached/uncached
+ * boundary as appropriate.
+ */
+ enum netfs_read_source (*prepare_read)(struct netfs_read_subrequest *subreq,
+ loff_t i_size);
+
+ /* Prepare a write operation, working out what part of the write we can
+ * actually do.
+ */
+ int (*prepare_write)(struct netfs_cache_resources *cres,
+ loff_t *_start, size_t *_len, loff_t i_size);
+};
+
struct readahead_control;
extern void netfs_readahead(struct readahead_control *,
const struct netfs_read_request_ops *,
@@ -43,6 +43,7 @@ enum netfs_sreq_trace {
netfs_sreq_trace_submit,
netfs_sreq_trace_terminated,
netfs_sreq_trace_write,
+ netfs_sreq_trace_write_skip,
netfs_sreq_trace_write_term,
};
@@ -77,6 +78,7 @@ enum netfs_sreq_trace {
EM(netfs_sreq_trace_submit, "SUBMT") \
EM(netfs_sreq_trace_terminated, "TERM ") \
EM(netfs_sreq_trace_write, "WRITE") \
+ EM(netfs_sreq_trace_write_skip, "SKIP ") \
E_(netfs_sreq_trace_write_term, "WTERM")