#define DEBUG_SUBSYSTEM S_OSC
#include <linux/workqueue.h>
+#include <libcfs/libcfs.h>
+#include <linux/falloc.h>
#include <lprocfs_status.h>
#include <lustre_debug.h>
#include <lustre_dlm.h>
#include <obd_cksum.h>
#include <obd_class.h>
#include <lustre_osc.h>
+#include <linux/falloc.h>
#include "osc_internal.h"
} else {
req->rq_interpret_reply = osc_setattr_interpret;
- CLASSERT(sizeof(*sa) <= sizeof(req->rq_async_args));
- sa = ptlrpc_req_async_args(req);
+ sa = ptlrpc_req_async_args(sa, req);
sa->sa_oa = oa;
sa->sa_upcall = upcall;
sa->sa_cookie = cookie;
- if (rqset == PTLRPCD_SET)
- ptlrpcd_add_req(req);
- else
- ptlrpc_set_add_req(rqset, req);
+ ptlrpc_set_add_req(rqset, req);
}
RETURN(0);
}
req->rq_interpret_reply = osc_ladvise_interpret;
- CLASSERT(sizeof(*la) <= sizeof(req->rq_async_args));
- la = ptlrpc_req_async_args(req);
+ la = ptlrpc_req_async_args(la, req);
la->la_oa = oa;
la->la_upcall = upcall;
la->la_cookie = cookie;
- if (rqset == PTLRPCD_SET)
- ptlrpcd_add_req(req);
- else
- ptlrpc_set_add_req(rqset, req);
+ ptlrpc_set_add_req(rqset, req);
RETURN(0);
}
ptlrpc_request_set_replen(req);
req->rq_interpret_reply = osc_setattr_interpret;
- CLASSERT(sizeof(*sa) <= sizeof(req->rq_async_args));
- sa = ptlrpc_req_async_args(req);
+ sa = ptlrpc_req_async_args(sa, req);
sa->sa_oa = oa;
sa->sa_upcall = upcall;
sa->sa_cookie = cookie;
}
EXPORT_SYMBOL(osc_punch_send);
+/**
+ * osc_fallocate_base() - Handles fallocate request.
+ *
+ * @exp: Export structure
+ * @oa: Attributes passed to OSS from client (obdo structure)
+ * @upcall: Primary & supplementary group information
+ * @cookie: Exclusive identifier
+ * @rqset: Request list.
+ * @mode: Operation done on given range.
+ *
+ * osc_fallocate_base() - Handles fallocate requests only. Only block
+ * allocation or standard preallocate operation is supported currently.
+ * Other mode flags is not supported yet. ftruncate(2) or truncate(2)
+ * is supported via SETATTR request.
+ *
+ * Return: Non-zero on failure and O on success.
+ */
+int osc_fallocate_base(struct obd_export *exp, struct obdo *oa,
+ obd_enqueue_update_f upcall, void *cookie, int mode)
+{
+ struct ptlrpc_request *req;
+ struct osc_setattr_args *sa;
+ struct ost_body *body;
+ struct obd_import *imp = class_exp2cliimp(exp);
+ int rc;
+ ENTRY;
+
+ /*
+ * Only mode == 0 (which is standard prealloc) is supported now.
+ * Punch is not supported yet.
+ */
+ if (mode & ~FALLOC_FL_KEEP_SIZE)
+ RETURN(-EOPNOTSUPP);
+ oa->o_falloc_mode = mode;
+
+ req = ptlrpc_request_alloc(class_exp2cliimp(exp),
+ &RQF_OST_FALLOCATE);
+ if (req == NULL)
+ RETURN(-ENOMEM);
+
+ rc = ptlrpc_request_pack(req, LUSTRE_OST_VERSION, OST_FALLOCATE);
+ if (rc != 0) {
+ ptlrpc_request_free(req);
+ RETURN(rc);
+ }
+
+ body = req_capsule_client_get(&req->rq_pill, &RMF_OST_BODY);
+ LASSERT(body);
+
+ lustre_set_wire_obdo(&imp->imp_connect_data, &body->oa, oa);
+
+ ptlrpc_request_set_replen(req);
+
+ req->rq_interpret_reply = (ptlrpc_interpterer_t)osc_setattr_interpret;
+ BUILD_BUG_ON(sizeof(*sa) > sizeof(req->rq_async_args));
+ sa = ptlrpc_req_async_args(sa, req);
+ sa->sa_oa = oa;
+ sa->sa_upcall = upcall;
+ sa->sa_cookie = cookie;
+
+ ptlrpcd_add_req(req);
+
+ RETURN(0);
+}
+
static int osc_sync_interpret(const struct lu_env *env,
struct ptlrpc_request *req, void *args, int rc)
{
ptlrpc_request_set_replen(req);
req->rq_interpret_reply = osc_sync_interpret;
- CLASSERT(sizeof(*fa) <= sizeof(req->rq_async_args));
- fa = ptlrpc_req_async_args(req);
+ fa = ptlrpc_req_async_args(fa, req);
fa->fa_obj = obj;
fa->fa_oa = oa;
fa->fa_upcall = upcall;
fa->fa_cookie = cookie;
- if (rqset == PTLRPCD_SET)
- ptlrpcd_add_req(req);
- else
- ptlrpc_set_add_req(rqset, req);
+ ptlrpc_set_add_req(rqset, req);
RETURN (0);
}
struct client_obd *cli = &exp->exp_obd->u.cli;
struct ptlrpc_request *req;
struct ost_body *body;
- struct list_head cancels = LIST_HEAD_INIT(cancels);
+ LIST_HEAD(cancels);
int rc, count;
ENTRY;
req->rq_interpret_reply = osc_destroy_interpret;
if (!osc_can_send_destroy(cli)) {
- struct l_wait_info lwi = LWI_INTR(LWI_ON_SIGNAL_NOOP, NULL);
-
/*
* Wait until the number of on-going destroy RPCs drops
* under max_rpc_in_flight
*/
- rc = l_wait_event_exclusive(cli->cl_destroy_waitq,
- osc_can_send_destroy(cli), &lwi);
+ rc = l_wait_event_abortable_exclusive(
+ cli->cl_destroy_waitq,
+ osc_can_send_destroy(cli));
if (rc) {
ptlrpc_req_finished(req);
- RETURN(rc);
+ RETURN(-EINTR);
}
}
oa->o_dirty = cli->cl_dirty_grant;
else
oa->o_dirty = cli->cl_dirty_pages << PAGE_SHIFT;
- if (unlikely(cli->cl_dirty_pages - cli->cl_dirty_transit >
- cli->cl_dirty_max_pages)) {
- CERROR("dirty %lu - %lu > dirty_max %lu\n",
- cli->cl_dirty_pages, cli->cl_dirty_transit,
+ if (unlikely(cli->cl_dirty_pages > cli->cl_dirty_max_pages)) {
+ CERROR("dirty %lu > dirty_max %lu\n",
+ cli->cl_dirty_pages,
cli->cl_dirty_max_pages);
oa->o_undirty = 0;
- } else if (unlikely(atomic_long_read(&obd_dirty_pages) -
- atomic_long_read(&obd_dirty_transit_pages) >
+ } else if (unlikely(atomic_long_read(&obd_dirty_pages) >
(long)(obd_max_dirty_pages + 1))) {
/* The atomic_read() allowing the atomic_inc() are
* not covered by a lock thus they may safely race and trip
* this CERROR() unless we add in a small fudge factor (+1). */
- CERROR("%s: dirty %ld - %ld > system dirty_max %ld\n",
+ CERROR("%s: dirty %ld > system dirty_max %ld\n",
cli_name(cli), atomic_long_read(&obd_dirty_pages),
- atomic_long_read(&obd_dirty_transit_pages),
obd_max_dirty_pages);
oa->o_undirty = 0;
} else if (unlikely(cli->cl_dirty_max_pages - cli->cl_dirty_pages >
/* Do not ask for more than OBD_MAX_GRANT - a margin for server
* to add extent tax, etc.
*/
- oa->o_undirty = min(undirty, OBD_MAX_GRANT -
- (PTLRPC_MAX_BRW_PAGES << PAGE_SHIFT)*4UL);
+ oa->o_undirty = min(undirty, OBD_MAX_GRANT &
+ ~(PTLRPC_MAX_BRW_SIZE * 4UL));
}
oa->o_grant = cli->cl_avail_grant + cli->cl_reserved_grant;
oa->o_dropped = cli->cl_lost_grant;
osc_update_grant(cli, body);
out:
OBD_SLAB_FREE_PTR(aa->aa_oa, osc_obdo_kmem);
+ aa->aa_oa = NULL;
return rc;
}
if (client->cl_import == NULL)
return 0;
- if ((client->cl_import->imp_connect_data.ocd_connect_flags &
- OBD_CONNECT_GRANT_SHRINK) == 0)
- return 0;
+ if (!OCD_HAS_FLAG(&client->cl_import->imp_connect_data, GRANT_SHRINK) ||
+ client->cl_import->imp_grant_shrink_disabled) {
+ osc_update_next_shrink(client);
+ return 0;
+ }
if (ktime_get_seconds() >= next_shrink - 5) {
/* Get the current RPC size directly, instead of going via:
mutex_lock(&client_gtd.gtd_mutex);
list_for_each_entry(cli, &client_gtd.gtd_clients,
cl_grant_chain) {
- if (++rpc_sent < GRANT_SHRINK_RPC_BATCH &&
- osc_should_shrink_grant(cli))
+ if (rpc_sent < GRANT_SHRINK_RPC_BATCH &&
+ osc_should_shrink_grant(cli)) {
osc_shrink_grant(cli);
+ rpc_sent++;
+ }
if (!init_next_shrink) {
if (cli->cl_next_shrink_grant < next_shrink &&
if (client_gtd.gtd_stopped == 1)
return;
- if (next_shrink > ktime_get_seconds())
- schedule_delayed_work(&work, msecs_to_jiffies(
- (next_shrink - ktime_get_seconds()) *
- MSEC_PER_SEC));
- else
+ if (next_shrink > ktime_get_seconds()) {
+ time64_t delay = next_shrink - ktime_get_seconds();
+
+ schedule_delayed_work(&work, cfs_time_seconds(delay));
+ } else {
schedule_work(&work.work);
+ }
+}
+
+void osc_schedule_grant_work(void)
+{
+ cancel_delayed_work_sync(&work);
+ schedule_work(&work.work);
}
/**
}
spin_unlock(&cli->cl_loi_list_lock);
- CDEBUG(D_CACHE, "%s, setting cl_avail_grant: %ld cl_lost_grant: %ld."
- "chunk bits: %d cl_max_extent_pages: %d\n",
- cli_name(cli),
- cli->cl_avail_grant, cli->cl_lost_grant, cli->cl_chunkbits,
- cli->cl_max_extent_pages);
+ CDEBUG(D_CACHE,
+ "%s, setting cl_avail_grant: %ld cl_lost_grant: %ld. chunk bits: %d cl_max_extent_pages: %d\n",
+ cli_name(cli),
+ cli->cl_avail_grant, cli->cl_lost_grant, cli->cl_chunkbits,
+ cli->cl_max_extent_pages);
if (OCD_HAS_FLAG(ocd, GRANT_SHRINK) && list_empty(&cli->cl_grant_chain))
osc_add_grant_list(cli);
/* return error if any niobuf was in error */
for (i = 0; i < niocount; i++) {
- if ((int)remote_rcs[i] < 0)
- return(remote_rcs[i]);
+ if ((int)remote_rcs[i] < 0) {
+ CDEBUG(D_INFO, "rc[%d]: %d req %p\n",
+ i, remote_rcs[i], req);
+ return remote_rcs[i];
+ }
if (remote_rcs[i] != 0) {
CDEBUG(D_INFO, "rc[%d] invalid (%d) req %p\n",
RETURN(rc);
}
+static inline void osc_release_bounce_pages(struct brw_page **pga,
+ u32 page_count)
+{
+#ifdef HAVE_LUSTRE_CRYPTO
+ int i;
+
+ for (i = 0; i < page_count; i++) {
+ if (pga[i]->pg->mapping)
+ /* bounce pages are unmapped */
+ continue;
+ if (pga[i]->flag & OBD_BRW_SYNC)
+ /* sync transfer cannot have encrypted pages */
+ continue;
+ llcrypt_finalize_bounce_page(&pga[i]->pg);
+ pga[i]->count -= pga[i]->bp_count_diff;
+ pga[i]->off += pga[i]->bp_off_diff;
+ }
+#endif
+}
+
static int
osc_brw_prep_request(int cmd, struct client_obd *cli, struct obdo *oa,
u32 page_count, struct brw_page **pga,
struct ptlrpc_request **reqp, int resend)
{
- struct ptlrpc_request *req;
- struct ptlrpc_bulk_desc *desc;
- struct ost_body *body;
- struct obd_ioobj *ioobj;
- struct niobuf_remote *niobuf;
+ struct ptlrpc_request *req;
+ struct ptlrpc_bulk_desc *desc;
+ struct ost_body *body;
+ struct obd_ioobj *ioobj;
+ struct niobuf_remote *niobuf;
int niocount, i, requested_nob, opc, rc, short_io_size = 0;
- struct osc_brw_async_args *aa;
- struct req_capsule *pill;
- struct brw_page *pg_prev;
+ struct osc_brw_async_args *aa;
+ struct req_capsule *pill;
+ struct brw_page *pg_prev;
void *short_io_buf;
const char *obd_name = cli->cl_import->imp_obd->obd_name;
+ struct inode *inode;
- ENTRY;
- if (OBD_FAIL_CHECK(OBD_FAIL_OSC_BRW_PREP_REQ))
- RETURN(-ENOMEM); /* Recoverable */
- if (OBD_FAIL_CHECK(OBD_FAIL_OSC_BRW_PREP_REQ2))
- RETURN(-EINVAL); /* Fatal */
+ ENTRY;
+ inode = page2inode(pga[0]->pg);
+ if (OBD_FAIL_CHECK(OBD_FAIL_OSC_BRW_PREP_REQ))
+ RETURN(-ENOMEM); /* Recoverable */
+ if (OBD_FAIL_CHECK(OBD_FAIL_OSC_BRW_PREP_REQ2))
+ RETURN(-EINVAL); /* Fatal */
if ((cmd & OBD_BRW_WRITE) != 0) {
opc = OST_WRITE;
if (req == NULL)
RETURN(-ENOMEM);
+ if (opc == OST_WRITE && inode && IS_ENCRYPTED(inode)) {
+ for (i = 0; i < page_count; i++) {
+ struct brw_page *pg = pga[i];
+ struct page *data_page = NULL;
+ bool retried = false;
+ bool lockedbymyself;
+
+retry_encrypt:
+ /* The page can already be locked when we arrive here.
+ * This is possible when cl_page_assume/vvp_page_assume
+ * is stuck on wait_on_page_writeback with page lock
+ * held. In this case there is no risk for the lock to
+ * be released while we are doing our encryption
+ * processing, because writeback against that page will
+ * end in vvp_page_completion_write/cl_page_completion,
+ * which means only once the page is fully processed.
+ */
+ lockedbymyself = trylock_page(pg->pg);
+ data_page =
+ llcrypt_encrypt_pagecache_blocks(pg->pg,
+ PAGE_SIZE, 0,
+ GFP_NOFS);
+ if (lockedbymyself)
+ unlock_page(pg->pg);
+ if (IS_ERR(data_page)) {
+ rc = PTR_ERR(data_page);
+ if (rc == -ENOMEM && !retried) {
+ retried = true;
+ rc = 0;
+ goto retry_encrypt;
+ }
+ ptlrpc_request_free(req);
+ RETURN(rc);
+ }
+ /* len is forced to PAGE_SIZE, and poff to 0
+ * so store the old, clear text info
+ */
+ pg->pg = data_page;
+ pg->bp_count_diff = PAGE_SIZE - pg->count;
+ pg->count = PAGE_SIZE;
+ pg->bp_off_diff = pg->off & ~PAGE_MASK;
+ pg->off = pg->off & PAGE_MASK;
+ }
+ }
+
for (niocount = i = 1; i < page_count; i++) {
if (!can_merge_pages(pga[i - 1], pga[i]))
niocount++;
desc = ptlrpc_prep_bulk_imp(req, page_count,
cli->cl_import->imp_connect_data.ocd_brw_size >> LNET_MTU_BITS,
(opc == OST_WRITE ? PTLRPC_BULK_GET_SOURCE :
- PTLRPC_BULK_PUT_SINK) |
- PTLRPC_BULK_BUF_KIOV,
+ PTLRPC_BULK_PUT_SINK),
OST_BULK_PORTAL,
&ptlrpc_bulk_kiov_pin_ops);
LASSERT((pga[0]->flag & OBD_BRW_SRVLOCK) ==
(pg->flag & OBD_BRW_SRVLOCK));
if (short_io_size != 0 && opc == OST_WRITE) {
- unsigned char *ptr = ll_kmap_atomic(pg->pg, KM_USER0);
+ unsigned char *ptr = kmap_atomic(pg->pg);
LASSERT(short_io_size >= requested_nob + pg->count);
memcpy(short_io_buf + requested_nob,
ptr + poff,
pg->count);
- ll_kunmap_atomic(ptr, KM_USER0);
+ kunmap_atomic(ptr);
} else if (short_io_size == 0) {
desc->bd_frag_ops->add_kiov_frag(desc, pg->pg, poff,
pg->count);
}
ptlrpc_request_set_replen(req);
- CLASSERT(sizeof(*aa) <= sizeof(req->rq_async_args));
- aa = ptlrpc_req_async_args(req);
+ aa = ptlrpc_req_async_args(aa, req);
aa->aa_oa = oa;
aa->aa_requested_nob = requested_nob;
aa->aa_nio_count = niocount;
kunmap(pga[i]->pg);
}
- rc = ll_vfs_fsync_range(filp, 0, LLONG_MAX, 1);
+ rc = vfs_fsync_range(filp, 0, LLONG_MAX, 1);
if (rc)
CERROR("%s: sync returns %d\n", dbgcksum_file_name, rc);
filp_close(filp, NULL);
- return;
}
static int
&req->rq_import->imp_connection->c_peer;
struct ost_body *body;
u32 client_cksum = 0;
- ENTRY;
+ struct inode *inode;
- if (rc < 0 && rc != -EDQUOT) {
- DEBUG_REQ(D_INFO, req, "Failed request with rc = %d\n", rc);
- RETURN(rc);
- }
+ ENTRY;
- LASSERTF(req->rq_repmsg != NULL, "rc = %d\n", rc);
- body = req_capsule_server_get(&req->rq_pill, &RMF_OST_BODY);
- if (body == NULL) {
- DEBUG_REQ(D_INFO, req, "Can't unpack body\n");
- RETURN(-EPROTO);
- }
+ if (rc < 0 && rc != -EDQUOT) {
+ DEBUG_REQ(D_INFO, req, "Failed request: rc = %d", rc);
+ RETURN(rc);
+ }
+
+ LASSERTF(req->rq_repmsg != NULL, "rc = %d\n", rc);
+ body = req_capsule_server_get(&req->rq_pill, &RMF_OST_BODY);
+ if (body == NULL) {
+ DEBUG_REQ(D_INFO, req, "cannot unpack body");
+ RETURN(-EPROTO);
+ }
/* set/clear over quota flag for a uid/gid/projid */
if (lustre_msg_get_opc(req->rq_reqmsg) == OST_WRITE &&
unsigned qid[LL_MAXQUOTAS] = {
body->oa.o_uid, body->oa.o_gid,
body->oa.o_projid };
- CDEBUG(D_QUOTA, "setdq for [%u %u %u] with valid %#llx, flags %x\n",
+ CDEBUG(D_QUOTA,
+ "setdq for [%u %u %u] with valid %#llx, flags %x\n",
body->oa.o_uid, body->oa.o_gid, body->oa.o_projid,
body->oa.o_valid, body->oa.o_flags);
- osc_quota_setdq(cli, qid, body->oa.o_valid,
+ osc_quota_setdq(cli, req->rq_xid, qid, body->oa.o_valid,
body->oa.o_flags);
- }
+ }
- osc_update_grant(cli, body);
+ osc_update_grant(cli, body);
- if (rc < 0)
- RETURN(rc);
+ if (rc < 0)
+ RETURN(rc);
- if (aa->aa_oa->o_valid & OBD_MD_FLCKSUM)
- client_cksum = aa->aa_oa->o_cksum; /* save for later */
+ if (aa->aa_oa->o_valid & OBD_MD_FLCKSUM)
+ client_cksum = aa->aa_oa->o_cksum; /* save for later */
- if (lustre_msg_get_opc(req->rq_reqmsg) == OST_WRITE) {
- if (rc > 0) {
- CERROR("Unexpected +ve rc %d\n", rc);
- RETURN(-EPROTO);
- }
+ if (lustre_msg_get_opc(req->rq_reqmsg) == OST_WRITE) {
+ if (rc > 0) {
+ CERROR("%s: unexpected positive size %d\n",
+ obd_name, rc);
+ RETURN(-EPROTO);
+ }
if (req->rq_bulk != NULL &&
sptlrpc_cli_unwrap_bulk_write(req, req->rq_bulk))
- RETURN(-EAGAIN);
+ RETURN(-EAGAIN);
- if ((aa->aa_oa->o_valid & OBD_MD_FLCKSUM) && client_cksum &&
- check_write_checksum(&body->oa, peer, client_cksum,
+ if ((aa->aa_oa->o_valid & OBD_MD_FLCKSUM) && client_cksum &&
+ check_write_checksum(&body->oa, peer, client_cksum,
body->oa.o_cksum, aa))
- RETURN(-EAGAIN);
+ RETURN(-EAGAIN);
- rc = check_write_rcs(req, aa->aa_requested_nob,aa->aa_nio_count,
- aa->aa_page_count, aa->aa_ppga);
- GOTO(out, rc);
- }
+ rc = check_write_rcs(req, aa->aa_requested_nob,
+ aa->aa_nio_count, aa->aa_page_count,
+ aa->aa_ppga);
+ GOTO(out, rc);
+ }
- /* The rest of this function executes only for OST_READs */
+ /* The rest of this function executes only for OST_READs */
if (req->rq_bulk == NULL) {
rc = req_capsule_get_size(&req->rq_pill, &RMF_SHORT_IO,
/* if unwrap_bulk failed, return -EAGAIN to retry */
rc = sptlrpc_cli_unwrap_bulk_read(req, req->rq_bulk, rc);
}
- if (rc < 0)
- GOTO(out, rc = -EAGAIN);
+ if (rc < 0)
+ GOTO(out, rc = -EAGAIN);
- if (rc > aa->aa_requested_nob) {
- CERROR("Unexpected rc %d (%d requested)\n", rc,
- aa->aa_requested_nob);
- RETURN(-EPROTO);
- }
+ if (rc > aa->aa_requested_nob) {
+ CERROR("%s: unexpected size %d, requested %d\n", obd_name,
+ rc, aa->aa_requested_nob);
+ RETURN(-EPROTO);
+ }
if (req->rq_bulk != NULL && rc != req->rq_bulk->bd_nob_transferred) {
- CERROR ("Unexpected rc %d (%d transferred)\n",
- rc, req->rq_bulk->bd_nob_transferred);
- return (-EPROTO);
- }
+ CERROR("%s: unexpected size %d, transferred %d\n", obd_name,
+ rc, req->rq_bulk->bd_nob_transferred);
+ RETURN(-EPROTO);
+ }
if (req->rq_bulk == NULL) {
/* short io */
CDEBUG(D_CACHE, "page %p count %d\n",
aa->aa_ppga[i]->pg, count);
- ptr = ll_kmap_atomic(aa->aa_ppga[i]->pg, KM_USER0);
+ ptr = kmap_atomic(aa->aa_ppga[i]->pg);
memcpy(ptr + (aa->aa_ppga[i]->off & ~PAGE_MASK), buf,
count);
- ll_kunmap_atomic((void *) ptr, KM_USER0);
+ kunmap_atomic((void *) ptr);
buf += count;
nob -= count;
CDEBUG(D_PAGE, "checksum %x confirmed\n", client_cksum);
rc = 0;
}
- } else if (unlikely(client_cksum)) {
- static int cksum_missed;
+ } else if (unlikely(client_cksum)) {
+ static int cksum_missed;
+
+ cksum_missed++;
+ if ((cksum_missed & (-cksum_missed)) == cksum_missed)
+ CERROR("%s: checksum %u requested from %s but not sent\n",
+ obd_name, cksum_missed,
+ libcfs_nid2str(peer->nid));
+ } else {
+ rc = 0;
+ }
+
+ inode = page2inode(aa->aa_ppga[0]->pg);
+ if (inode && IS_ENCRYPTED(inode)) {
+ int idx;
+
+ if (!llcrypt_has_encryption_key(inode)) {
+ CDEBUG(D_SEC, "no enc key for ino %lu\n", inode->i_ino);
+ GOTO(out, rc);
+ }
+ for (idx = 0; idx < aa->aa_page_count; idx++) {
+ struct brw_page *pg = aa->aa_ppga[idx];
+ __u64 *p, *q;
+
+ /* do not decrypt if page is all 0s */
+ p = q = page_address(pg->pg);
+ while (p - q < PAGE_SIZE / sizeof(*p)) {
+ if (*p != 0)
+ break;
+ p++;
+ }
+ if (p - q == PAGE_SIZE / sizeof(*p))
+ continue;
+
+ rc = llcrypt_decrypt_pagecache_blocks(pg->pg,
+ PAGE_SIZE, 0);
+ if (rc)
+ GOTO(out, rc);
+ }
+ }
- cksum_missed++;
- if ((cksum_missed & (-cksum_missed)) == cksum_missed)
- CERROR("Checksum %u requested from %s but not sent\n",
- cksum_missed, libcfs_nid2str(peer->nid));
- } else {
- rc = 0;
- }
out:
if (rc >= 0)
lustre_get_wire_obdo(&req->rq_import->imp_connect_data,
aa->aa_oa, &body->oa);
- RETURN(rc);
+ RETURN(rc);
}
static int osc_brw_redo_request(struct ptlrpc_request *request,
struct osc_brw_async_args *aa, int rc)
{
- struct ptlrpc_request *new_req;
- struct osc_brw_async_args *new_aa;
- struct osc_async_page *oap;
- ENTRY;
+ struct ptlrpc_request *new_req;
+ struct osc_brw_async_args *new_aa;
+ struct osc_async_page *oap;
+ ENTRY;
+ /* The below message is checked in replay-ost-single.sh test_8ae*/
DEBUG_REQ(rc == -EINPROGRESS ? D_RPCTRACE : D_ERROR, request,
"redo for recoverable error %d", rc);
RETURN(rc);
list_for_each_entry(oap, &aa->aa_oaps, oap_rpc_item) {
- if (oap->oap_request != NULL) {
- LASSERTF(request == oap->oap_request,
- "request %p != oap_request %p\n",
- request, oap->oap_request);
- if (oap->oap_interrupted) {
- ptlrpc_req_finished(new_req);
- RETURN(-EINTR);
- }
- }
- }
+ if (oap->oap_request != NULL) {
+ LASSERTF(request == oap->oap_request,
+ "request %p != oap_request %p\n",
+ request, oap->oap_request);
+ }
+ }
/*
* New request takes over pga and oaps from old request.
* Note that copying a list_head doesn't work, need to move it...
new_req->rq_generation_set = 1;
new_req->rq_import_generation = request->rq_import_generation;
- new_aa = ptlrpc_req_async_args(new_req);
+ new_aa = ptlrpc_req_async_args(new_aa, new_req);
INIT_LIST_HEAD(&new_aa->aa_oaps);
list_splice_init(&aa->aa_oaps, &new_aa->aa_oaps);
static void osc_release_ppga(struct brw_page **ppga, size_t count)
{
- LASSERT(ppga != NULL);
- OBD_FREE(ppga, sizeof(*ppga) * count);
+ LASSERT(ppga != NULL);
+ OBD_FREE_PTR_ARRAY(ppga, count);
}
static int brw_interpret(const struct lu_env *env,
rc = osc_brw_fini_request(req, rc);
CDEBUG(D_INODE, "request %p aa %p rc %d\n", req, aa, rc);
+
+ /* restore clear text pages */
+ osc_release_bounce_pages(aa->aa_ppga, aa->aa_page_count);
+
/*
* When server returns -EINPROGRESS, client should always retry
* regardless of the number of times the bulk was resent already.
cl_object_attr_unlock(obj);
}
OBD_SLAB_FREE_PTR(aa->aa_oa, osc_obdo_kmem);
+ aa->aa_oa = NULL;
if (lustre_msg_get_opc(req->rq_reqmsg) == OST_WRITE && rc == 0)
osc_inc_unstable_pages(req);
struct cl_req_attr *crattr = NULL;
loff_t starting_offset = OBD_OBJECT_EOF;
loff_t ending_offset = 0;
- int mpflag = 0;
+ /* '1' for consistency with code that checks !mpflag to restore */
+ int mpflag = 1;
int mem_tight = 0;
int page_count = 0;
bool soft_sync = false;
- bool interrupted = false;
bool ndelay = false;
int i;
int grant = 0;
int rc;
__u32 layout_version = 0;
- struct list_head rpc_list = LIST_HEAD_INIT(rpc_list);
+ LIST_HEAD(rpc_list);
struct ost_body *body;
ENTRY;
LASSERT(!list_empty(ext_list));
mem_tight |= ext->oe_memalloc;
grant += ext->oe_grants;
page_count += ext->oe_nr_pages;
- layout_version = MAX(layout_version, ext->oe_layout_version);
+ layout_version = max(layout_version, ext->oe_layout_version);
if (obj == NULL)
obj = ext->oe_obj;
}
soft_sync = osc_over_unstable_soft_limit(cli);
if (mem_tight)
- mpflag = cfs_memory_pressure_get_and_set();
+ mpflag = memalloc_noreclaim_save();
- OBD_ALLOC(pga, sizeof(*pga) * page_count);
+ OBD_ALLOC_PTR_ARRAY(pga, page_count);
if (pga == NULL)
GOTO(out, rc = -ENOMEM);
else
LASSERT(oap->oap_page_off + oap->oap_count ==
PAGE_SIZE);
- if (oap->oap_interrupted)
- interrupted = true;
}
if (ext->oe_ndelay)
ndelay = true;
req->rq_interpret_reply = brw_interpret;
req->rq_memalloc = mem_tight != 0;
oap->oap_request = ptlrpc_request_addref(req);
- if (interrupted && !req->rq_intr)
- ptlrpc_mark_interrupted(req);
if (ndelay) {
req->rq_no_resend = req->rq_no_delay = 1;
/* probably set a shorter timeout value.
cl_req_attr_set(env, osc2cl(obj), crattr);
lustre_msg_set_jobid(req->rq_reqmsg, crattr->cra_jobid);
- CLASSERT(sizeof(*aa) <= sizeof(req->rq_async_args));
- aa = ptlrpc_req_async_args(req);
+ aa = ptlrpc_req_async_args(aa, req);
INIT_LIST_HEAD(&aa->aa_oaps);
list_splice_init(&rpc_list, &aa->aa_oaps);
INIT_LIST_HEAD(&aa->aa_exts);
}
spin_unlock(&cli->cl_loi_list_lock);
- DEBUG_REQ(D_INODE, req, "%d pages, aa %p. now %ur/%uw in flight",
+ DEBUG_REQ(D_INODE, req, "%d pages, aa %p, now %ur/%uw in flight",
page_count, aa, cli->cl_r_in_flight,
cli->cl_w_in_flight);
OBD_FAIL_TIMEOUT(OBD_FAIL_OSC_DELAY_IO, cfs_fail_val);
EXIT;
out:
- if (mem_tight != 0)
- cfs_memory_pressure_restore(mpflag);
+ if (mem_tight)
+ memalloc_noreclaim_restore(mpflag);
if (rc != 0) {
LASSERT(req == NULL);
if (oa)
OBD_SLAB_FREE_PTR(oa, osc_obdo_kmem);
- if (pga)
- OBD_FREE(pga, sizeof(*pga) * page_count);
+ if (pga) {
+ osc_release_bounce_pages(pga, page_count);
+ osc_release_ppga(pga, page_count);
+ }
/* this should happen rarely and is pretty bad, it makes the
* pending list not follow the dirty order */
while (!list_empty(ext_list)) {
RETURN(rc);
}
-struct ptlrpc_request_set *PTLRPCD_SET = (void *)1;
-
/* When enqueuing asynchronously, locks are not ordered, we can obtain a lock
* from the 2nd OSC before a lock from the 1st one. This does not deadlock with
* other synchronous requests, however keeping some locks and trying to obtain
* release locks just after they are obtained. */
int osc_enqueue_base(struct obd_export *exp, struct ldlm_res_id *res_id,
__u64 *flags, union ldlm_policy_data *policy,
- struct ost_lvb *lvb, int kms_valid,
- osc_enqueue_upcall_f upcall, void *cookie,
- struct ldlm_enqueue_info *einfo,
+ struct ost_lvb *lvb, osc_enqueue_upcall_f upcall,
+ void *cookie, struct ldlm_enqueue_info *einfo,
struct ptlrpc_request_set *rqset, int async,
bool speculative)
{
policy->l_extent.start -= policy->l_extent.start & ~PAGE_MASK;
policy->l_extent.end |= ~PAGE_MASK;
- /*
- * kms is not valid when either object is completely fresh (so that no
- * locks are cached), or object was evicted. In the latter case cached
- * lock cannot be used, because it would prime inode state with
- * potentially stale LVB.
- */
- if (!kms_valid)
- goto no_match;
-
/* Next, search for already existing extent locks that will cover us */
/* If we're trying to read, we also search for an existing PW lock. The
* VFS and page cache already protect us locally, so lots of readers/
}
}
-no_match:
if (*flags & (LDLM_FL_TEST_LOCK | LDLM_FL_MATCH_LOCK))
RETURN(-ENOLCK);
if (async) {
if (!rc) {
struct osc_enqueue_args *aa;
- CLASSERT(sizeof(*aa) <= sizeof(req->rq_async_args));
- aa = ptlrpc_req_async_args(req);
+ aa = ptlrpc_req_async_args(aa, req);
aa->oa_exp = exp;
aa->oa_mode = einfo->ei_mode;
aa->oa_type = einfo->ei_type;
}
req->rq_interpret_reply = osc_enqueue_interpret;
- if (rqset == PTLRPCD_SET)
- ptlrpcd_add_req(req);
- else
- ptlrpc_set_add_req(rqset, req);
+ ptlrpc_set_add_req(rqset, req);
} else if (intent) {
ptlrpc_req_finished(req);
}
RETURN(rc);
}
-int osc_match_base(struct obd_export *exp, struct ldlm_res_id *res_id,
- enum ldlm_type type, union ldlm_policy_data *policy,
- enum ldlm_mode mode, __u64 *flags, void *data,
+int osc_match_base(const struct lu_env *env, struct obd_export *exp,
+ struct ldlm_res_id *res_id, enum ldlm_type type,
+ union ldlm_policy_data *policy, enum ldlm_mode mode,
+ __u64 *flags, struct osc_object *obj,
struct lustre_handle *lockh, int unref)
{
struct obd_device *obd = exp->exp_obd;
if (rc == 0 || lflags & LDLM_FL_TEST_LOCK)
RETURN(rc);
- if (data != NULL) {
+ if (obj != NULL) {
struct ldlm_lock *lock = ldlm_handle2lock(lockh);
LASSERT(lock != NULL);
- if (!osc_set_lock_data(lock, data)) {
+ if (osc_set_lock_data(lock, obj)) {
+ lock_res_and_lock(lock);
+ if (!ldlm_is_lvb_cached(lock)) {
+ LASSERT(lock->l_ast_data == obj);
+ osc_lock_lvb_update(env, obj, lock, NULL);
+ ldlm_set_lvb_cached(lock);
+ }
+ unlock_res_and_lock(lock);
+ } else {
ldlm_lock_decref(lockh, rc);
rc = 0;
}
int rc;
ENTRY;
+ if (obd->obd_osfs_age >= max_age) {
+ CDEBUG(D_SUPER,
+ "%s: use %p cache blocks %llu/%llu objects %llu/%llu\n",
+ obd->obd_name, &obd->obd_osfs,
+ obd->obd_osfs.os_bavail, obd->obd_osfs.os_blocks,
+ obd->obd_osfs.os_ffree, obd->obd_osfs.os_files);
+ spin_lock(&obd->obd_osfs_lock);
+ memcpy(oinfo->oi_osfs, &obd->obd_osfs, sizeof(*oinfo->oi_osfs));
+ spin_unlock(&obd->obd_osfs_lock);
+ oinfo->oi_flags |= OBD_STATFS_FROM_CACHE;
+ if (oinfo->oi_cb_up)
+ oinfo->oi_cb_up(oinfo, 0);
+
+ RETURN(0);
+ }
+
/* We could possibly pass max_age in the request (as an absolute
* timestamp or a "seconds.usec ago") so the target can avoid doing
* extra calls into the filesystem if that isn't necessary (e.g.
}
req->rq_interpret_reply = osc_statfs_interpret;
- CLASSERT(sizeof(*aa) <= sizeof(req->rq_async_args));
- aa = ptlrpc_req_async_args(req);
+ aa = ptlrpc_req_async_args(aa, req);
aa->aa_oi = oinfo;
ptlrpc_set_add_req(rqset, req);
static int osc_iocontrol(unsigned int cmd, struct obd_export *exp, int len,
void *karg, void __user *uarg)
{
- struct obd_device *obd = exp->exp_obd;
- struct obd_ioctl_data *data = karg;
- int err = 0;
- ENTRY;
+ struct obd_device *obd = exp->exp_obd;
+ struct obd_ioctl_data *data = karg;
+ int rc = 0;
+ ENTRY;
if (!try_module_get(THIS_MODULE)) {
CERROR("%s: cannot get module '%s'\n", obd->obd_name,
module_name(THIS_MODULE));
return -EINVAL;
}
- switch (cmd) {
- case OBD_IOC_CLIENT_RECOVER:
- err = ptlrpc_recover_import(obd->u.cli.cl_import,
- data->ioc_inlbuf1, 0);
- if (err > 0)
- err = 0;
- GOTO(out, err);
- case IOC_OSC_SET_ACTIVE:
- err = ptlrpc_set_import_active(obd->u.cli.cl_import,
- data->ioc_offset);
- GOTO(out, err);
- case OBD_IOC_PING_TARGET:
- err = ptlrpc_obd_ping(obd);
- GOTO(out, err);
+ switch (cmd) {
+ case OBD_IOC_CLIENT_RECOVER:
+ rc = ptlrpc_recover_import(obd->u.cli.cl_import,
+ data->ioc_inlbuf1, 0);
+ if (rc > 0)
+ rc = 0;
+ break;
+ case IOC_OSC_SET_ACTIVE:
+ rc = ptlrpc_set_import_active(obd->u.cli.cl_import,
+ data->ioc_offset);
+ break;
default:
- CDEBUG(D_INODE, "unrecognised ioctl %#x by %s\n",
- cmd, current_comm());
- GOTO(out, err = -ENOTTY);
+ rc = -ENOTTY;
+ CDEBUG(D_INODE, "%s: unrecognised ioctl %#x by %s: rc = %d\n",
+ obd->obd_name, cmd, current->comm, rc);
+ break;
}
-out:
+
module_put(THIS_MODULE);
- return err;
+ return rc;
}
int osc_set_info_async(const struct lu_env *env, struct obd_export *exp,
RETURN(0);
}
- if (KEY_IS(KEY_CACHE_SET)) {
- struct client_obd *cli = &obd->u.cli;
-
- LASSERT(cli->cl_cache == NULL); /* only once */
- cli->cl_cache = (struct cl_client_cache *)val;
- cl_cache_incref(cli->cl_cache);
- cli->cl_lru_left = &cli->cl_cache->ccc_lru_left;
-
- /* add this osc into entity list */
- LASSERT(list_empty(&cli->cl_lru_osc));
- spin_lock(&cli->cl_cache->ccc_lru_lock);
- list_add(&cli->cl_lru_osc, &cli->cl_cache->ccc_lru);
- spin_unlock(&cli->cl_cache->ccc_lru_lock);
-
- RETURN(0);
- }
-
if (KEY_IS(KEY_CACHE_LRU_SHRINK)) {
struct client_obd *cli = &obd->u.cli;
long nr = atomic_long_read(&cli->cl_lru_in_list) >> 1;
struct osc_grant_args *aa;
struct obdo *oa;
- CLASSERT(sizeof(*aa) <= sizeof(req->rq_async_args));
- aa = ptlrpc_req_async_args(req);
+ aa = ptlrpc_req_async_args(aa, req);
OBD_SLAB_ALLOC_PTR_GFP(oa, osc_obdo_kmem, GFP_NOFS);
if (!oa) {
ptlrpc_req_finished(req);
spin_lock(&cli->cl_loi_list_lock);
grant = cli->cl_avail_grant + cli->cl_reserved_grant;
- if (data->ocd_connect_flags & OBD_CONNECT_GRANT_PARAM)
+ if (data->ocd_connect_flags & OBD_CONNECT_GRANT_PARAM) {
+ /* restore ocd_grant_blkbits as client page bits */
+ data->ocd_grant_blkbits = PAGE_SHIFT;
grant += cli->cl_dirty_grant;
- else
+ } else {
grant += cli->cl_dirty_pages << PAGE_SHIFT;
+ }
data->ocd_grant = grant ? : 2 * cli_brw_size(obd);
lost_grant = cli->cl_lost_grant;
cli->cl_lost_grant = 0;
}
EXPORT_SYMBOL(osc_cleanup_common);
-static struct obd_ops osc_obd_ops = {
+static const struct obd_ops osc_obd_ops = {
.o_owner = THIS_MODULE,
.o_setup = osc_setup,
.o_precleanup = osc_precleanup,
.o_cleanup = osc_cleanup_common,
.o_add_conn = client_import_add_conn,
.o_del_conn = client_import_del_conn,
- .o_connect = client_connect_import,
+ .o_connect = client_connect_import,
.o_reconnect = osc_reconnect,
.o_disconnect = osc_disconnect,
.o_statfs = osc_statfs,
};
static struct shrinker *osc_cache_shrinker;
-struct list_head osc_shrink_list = LIST_HEAD_INIT(osc_shrink_list);
+LIST_HEAD(osc_shrink_list);
DEFINE_SPINLOCK(osc_shrink_lock);
#ifndef HAVE_SHRINKER_COUNT
.nr_to_scan = shrink_param(sc, nr_to_scan),
.gfp_mask = shrink_param(sc, gfp_mask)
};
-#if !defined(HAVE_SHRINKER_WANT_SHRINK_PTR) && !defined(HAVE_SHRINK_CONTROL)
- struct shrinker *shrinker = NULL;
-#endif
-
(void)osc_cache_shrink_scan(shrinker, &scv);
return osc_cache_shrink_count(shrinker, &scv);
static int __init osc_init(void)
{
- bool enable_proc = true;
- struct obd_type *type;
unsigned int reqpool_size;
unsigned int reqsize;
int rc;
if (rc)
RETURN(rc);
- type = class_search_type(LUSTRE_OSP_NAME);
- if (type != NULL && type->typ_procsym != NULL)
- enable_proc = false;
-
- rc = class_register_type(&osc_obd_ops, NULL, enable_proc, NULL,
+ rc = class_register_type(&osc_obd_ops, NULL, true, NULL,
LUSTRE_OSC_NAME, &osc_device_type);
if (rc)
GOTO(out_kmem, rc);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff