From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/net/ceph/osd_client.c | 948 ++++++++++++++++++++++++++++++++++------------------------
1 files changed, 552 insertions(+), 396 deletions(-)
diff --git a/kernel/net/ceph/osd_client.c b/kernel/net/ceph/osd_client.c
index 713fe1f..d594cd5 100644
--- a/kernel/net/ceph/osd_client.c
+++ b/kernel/net/ceph/osd_client.c
@@ -126,6 +126,9 @@
osd_data->type = CEPH_OSD_DATA_TYPE_NONE;
}
+/*
+ * Consumes @pages if @own_pages is true.
+ */
static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
struct page **pages, u64 length, u32 alignment,
bool pages_from_pool, bool own_pages)
@@ -138,6 +141,9 @@
osd_data->own_pages = own_pages;
}
+/*
+ * Consumes a ref on @pagelist.
+ */
static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data,
struct ceph_pagelist *pagelist)
{
@@ -164,14 +170,6 @@
osd_data->bvec_pos = *bvec_pos;
osd_data->num_bvecs = num_bvecs;
}
-
-#define osd_req_op_data(oreq, whch, typ, fld) \
-({ \
- struct ceph_osd_request *__oreq = (oreq); \
- unsigned int __whch = (whch); \
- BUG_ON(__whch >= __oreq->r_num_ops); \
- &__oreq->r_ops[__whch].typ.fld; \
-})
static struct ceph_osd_data *
osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which)
@@ -362,6 +360,8 @@
num_pages = calc_pages_for((u64)osd_data->alignment,
(u64)osd_data->length);
ceph_release_page_vector(osd_data->pages, num_pages);
+ } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
+ ceph_pagelist_release(osd_data->pagelist);
}
ceph_osd_data_init(osd_data);
}
@@ -401,6 +401,9 @@
break;
case CEPH_OSD_OP_LIST_WATCHERS:
ceph_osd_data_release(&op->list_watchers.response_data);
+ break;
+ case CEPH_OSD_OP_COPY_FROM2:
+ ceph_osd_data_release(&op->copy_from.osd_data);
break;
default:
break;
@@ -445,6 +448,7 @@
dest->recovery_deletes = src->recovery_deletes;
dest->flags = src->flags;
+ dest->used_replica = src->used_replica;
dest->paused = src->paused;
dest->epoch = src->epoch;
@@ -468,7 +472,7 @@
{
WARN_ON(!RB_EMPTY_NODE(&req->r_node));
WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node));
- WARN_ON(!list_empty(&req->r_unsafe_item));
+ WARN_ON(!list_empty(&req->r_private_item));
WARN_ON(req->r_osd);
}
@@ -521,53 +525,16 @@
static void request_init(struct ceph_osd_request *req)
{
- /* req only, each op is zeroed in _osd_req_op_init() */
+ /* req only, each op is zeroed in osd_req_op_init() */
memset(req, 0, sizeof(*req));
kref_init(&req->r_kref);
init_completion(&req->r_completion);
RB_CLEAR_NODE(&req->r_node);
RB_CLEAR_NODE(&req->r_mc_node);
- INIT_LIST_HEAD(&req->r_unsafe_item);
+ INIT_LIST_HEAD(&req->r_private_item);
target_init(&req->r_t);
-}
-
-/*
- * This is ugly, but it allows us to reuse linger registration and ping
- * requests, keeping the structure of the code around send_linger{_ping}()
- * reasonable. Setting up a min_nr=2 mempool for each linger request
- * and dealing with copying ops (this blasts req only, watch op remains
- * intact) isn't any better.
- */
-static void request_reinit(struct ceph_osd_request *req)
-{
- struct ceph_osd_client *osdc = req->r_osdc;
- bool mempool = req->r_mempool;
- unsigned int num_ops = req->r_num_ops;
- u64 snapid = req->r_snapid;
- struct ceph_snap_context *snapc = req->r_snapc;
- bool linger = req->r_linger;
- struct ceph_msg *request_msg = req->r_request;
- struct ceph_msg *reply_msg = req->r_reply;
-
- dout("%s req %p\n", __func__, req);
- WARN_ON(kref_read(&req->r_kref) != 1);
- request_release_checks(req);
-
- WARN_ON(kref_read(&request_msg->kref) != 1);
- WARN_ON(kref_read(&reply_msg->kref) != 1);
- target_destroy(&req->r_t);
-
- request_init(req);
- req->r_osdc = osdc;
- req->r_mempool = mempool;
- req->r_num_ops = num_ops;
- req->r_snapid = snapid;
- req->r_snapc = snapc;
- req->r_linger = linger;
- req->r_request = request_msg;
- req->r_reply = reply_msg;
}
struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
@@ -607,12 +574,15 @@
return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
}
-int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp,
+ int num_request_data_items,
+ int num_reply_data_items)
{
struct ceph_osd_client *osdc = req->r_osdc;
struct ceph_msg *msg;
int msg_size;
+ WARN_ON(req->r_request || req->r_reply);
WARN_ON(ceph_oid_empty(&req->r_base_oid));
WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
@@ -634,9 +604,11 @@
msg_size += 4 + 8; /* retry_attempt, features */
if (req->r_mempool)
- msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
+ msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size,
+ num_request_data_items);
else
- msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
+ msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size,
+ num_request_data_items, gfp, true);
if (!msg)
return -ENOMEM;
@@ -649,9 +621,11 @@
msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
if (req->r_mempool)
- msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
+ msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size,
+ num_reply_data_items);
else
- msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, gfp, true);
+ msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size,
+ num_reply_data_items, gfp, true);
if (!msg)
return -ENOMEM;
@@ -659,7 +633,6 @@
return 0;
}
-EXPORT_SYMBOL(ceph_osdc_alloc_messages);
static bool osd_req_opcode_valid(u16 opcode)
{
@@ -672,13 +645,72 @@
}
}
+static void get_num_data_items(struct ceph_osd_request *req,
+ int *num_request_data_items,
+ int *num_reply_data_items)
+{
+ struct ceph_osd_req_op *op;
+
+ *num_request_data_items = 0;
+ *num_reply_data_items = 0;
+
+ for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
+ switch (op->op) {
+ /* request */
+ case CEPH_OSD_OP_WRITE:
+ case CEPH_OSD_OP_WRITEFULL:
+ case CEPH_OSD_OP_SETXATTR:
+ case CEPH_OSD_OP_CMPXATTR:
+ case CEPH_OSD_OP_NOTIFY_ACK:
+ case CEPH_OSD_OP_COPY_FROM2:
+ *num_request_data_items += 1;
+ break;
+
+ /* reply */
+ case CEPH_OSD_OP_STAT:
+ case CEPH_OSD_OP_READ:
+ case CEPH_OSD_OP_LIST_WATCHERS:
+ *num_reply_data_items += 1;
+ break;
+
+ /* both */
+ case CEPH_OSD_OP_NOTIFY:
+ *num_request_data_items += 1;
+ *num_reply_data_items += 1;
+ break;
+ case CEPH_OSD_OP_CALL:
+ *num_request_data_items += 2;
+ *num_reply_data_items += 1;
+ break;
+
+ default:
+ WARN_ON(!osd_req_opcode_valid(op->op));
+ break;
+ }
+ }
+}
+
+/*
+ * oid, oloc and OSD op opcode(s) must be filled in before this function
+ * is called.
+ */
+int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+{
+ int num_request_data_items, num_reply_data_items;
+
+ get_num_data_items(req, &num_request_data_items, &num_reply_data_items);
+ return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items,
+ num_reply_data_items);
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_messages);
+
/*
* This is an osd op init function for opcodes that have no data or
* other information associated with them. It also serves as a
* common init routine for all the other init functions, below.
*/
-static struct ceph_osd_req_op *
-_osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
+struct ceph_osd_req_op *
+osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
u16 opcode, u32 flags)
{
struct ceph_osd_req_op *op;
@@ -693,12 +725,6 @@
return op;
}
-
-void osd_req_op_init(struct ceph_osd_request *osd_req,
- unsigned int which, u16 opcode, u32 flags)
-{
- (void)_osd_req_op_init(osd_req, which, opcode, flags);
-}
EXPORT_SYMBOL(osd_req_op_init);
void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
@@ -706,8 +732,8 @@
u64 offset, u64 length,
u64 truncate_size, u32 truncate_seq)
{
- struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
- opcode, 0);
+ struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which,
+ opcode, 0);
size_t payload_len = 0;
BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
@@ -753,7 +779,7 @@
BUG_ON(which + 1 >= osd_req->r_num_ops);
prev_op = &osd_req->r_ops[which];
- op = _osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags);
+ op = osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags);
/* dup previous one */
op->indata_len = prev_op->indata_len;
op->outdata_len = prev_op->outdata_len;
@@ -768,40 +794,45 @@
EXPORT_SYMBOL(osd_req_op_extent_dup_last);
int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
- u16 opcode, const char *class, const char *method)
+ const char *class, const char *method)
{
- struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
- opcode, 0);
+ struct ceph_osd_req_op *op;
struct ceph_pagelist *pagelist;
size_t payload_len = 0;
size_t size;
+ int ret;
- BUG_ON(opcode != CEPH_OSD_OP_CALL);
+ op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
- pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
+ pagelist = ceph_pagelist_alloc(GFP_NOFS);
if (!pagelist)
return -ENOMEM;
-
- ceph_pagelist_init(pagelist);
op->cls.class_name = class;
size = strlen(class);
BUG_ON(size > (size_t) U8_MAX);
op->cls.class_len = size;
- ceph_pagelist_append(pagelist, class, size);
+ ret = ceph_pagelist_append(pagelist, class, size);
+ if (ret)
+ goto err_pagelist_free;
payload_len += size;
op->cls.method_name = method;
size = strlen(method);
BUG_ON(size > (size_t) U8_MAX);
op->cls.method_len = size;
- ceph_pagelist_append(pagelist, method, size);
+ ret = ceph_pagelist_append(pagelist, method, size);
+ if (ret)
+ goto err_pagelist_free;
payload_len += size;
osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist);
-
op->indata_len = payload_len;
return 0;
+
+err_pagelist_free:
+ ceph_pagelist_release(pagelist);
+ return ret;
}
EXPORT_SYMBOL(osd_req_op_cls_init);
@@ -809,25 +840,28 @@
u16 opcode, const char *name, const void *value,
size_t size, u8 cmp_op, u8 cmp_mode)
{
- struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
- opcode, 0);
+ struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which,
+ opcode, 0);
struct ceph_pagelist *pagelist;
size_t payload_len;
+ int ret;
BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
- pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+ pagelist = ceph_pagelist_alloc(GFP_NOFS);
if (!pagelist)
return -ENOMEM;
- ceph_pagelist_init(pagelist);
-
payload_len = strlen(name);
op->xattr.name_len = payload_len;
- ceph_pagelist_append(pagelist, name, payload_len);
+ ret = ceph_pagelist_append(pagelist, name, payload_len);
+ if (ret)
+ goto err_pagelist_free;
op->xattr.value_len = size;
- ceph_pagelist_append(pagelist, value, size);
+ ret = ceph_pagelist_append(pagelist, value, size);
+ if (ret)
+ goto err_pagelist_free;
payload_len += size;
op->xattr.cmp_op = cmp_op;
@@ -836,6 +870,10 @@
ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist);
op->indata_len = payload_len;
return 0;
+
+err_pagelist_free:
+ ceph_pagelist_release(pagelist);
+ return ret;
}
EXPORT_SYMBOL(osd_req_op_xattr_init);
@@ -843,27 +881,47 @@
* @watch_opcode: CEPH_OSD_WATCH_OP_*
*/
static void osd_req_op_watch_init(struct ceph_osd_request *req, int which,
- u64 cookie, u8 watch_opcode)
+ u8 watch_opcode, u64 cookie, u32 gen)
{
struct ceph_osd_req_op *op;
- op = _osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
+ op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
op->watch.cookie = cookie;
op->watch.op = watch_opcode;
- op->watch.gen = 0;
+ op->watch.gen = gen;
}
+/*
+ * prot_ver, timeout and notify payload (may be empty) should already be
+ * encoded in @request_pl
+ */
+static void osd_req_op_notify_init(struct ceph_osd_request *req, int which,
+ u64 cookie, struct ceph_pagelist *request_pl)
+{
+ struct ceph_osd_req_op *op;
+
+ op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
+ op->notify.cookie = cookie;
+
+ ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl);
+ op->indata_len = request_pl->length;
+}
+
+/*
+ * @flags: CEPH_OSD_OP_ALLOC_HINT_FLAG_*
+ */
void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
unsigned int which,
u64 expected_object_size,
- u64 expected_write_size)
+ u64 expected_write_size,
+ u32 flags)
{
- struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
- CEPH_OSD_OP_SETALLOCHINT,
- 0);
+ struct ceph_osd_req_op *op;
+ op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_SETALLOCHINT, 0);
op->alloc_hint.expected_object_size = expected_object_size;
op->alloc_hint.expected_write_size = expected_write_size;
+ op->alloc_hint.flags = flags;
/*
* CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed
@@ -883,7 +941,7 @@
BUG_ON(length > (u64) SIZE_MAX);
if (length)
ceph_msg_data_add_pages(msg, osd_data->pages,
- length, osd_data->alignment);
+ length, osd_data->alignment, false);
} else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
BUG_ON(!length);
ceph_msg_data_add_pagelist(msg, osd_data->pagelist);
@@ -901,12 +959,6 @@
static u32 osd_req_encode_op(struct ceph_osd_op *dst,
const struct ceph_osd_req_op *src)
{
- if (WARN_ON(!osd_req_opcode_valid(src->op))) {
- pr_err("unrecognized osd opcode %d\n", src->op);
-
- return 0;
- }
-
switch (src->op) {
case CEPH_OSD_OP_STAT:
break;
@@ -945,6 +997,7 @@
cpu_to_le64(src->alloc_hint.expected_object_size);
dst->alloc_hint.expected_write_size =
cpu_to_le64(src->alloc_hint.expected_write_size);
+ dst->alloc_hint.flags = cpu_to_le32(src->alloc_hint.flags);
break;
case CEPH_OSD_OP_SETXATTR:
case CEPH_OSD_OP_CMPXATTR:
@@ -955,6 +1008,14 @@
break;
case CEPH_OSD_OP_CREATE:
case CEPH_OSD_OP_DELETE:
+ break;
+ case CEPH_OSD_OP_COPY_FROM2:
+ dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid);
+ dst->copy_from.src_version =
+ cpu_to_le64(src->copy_from.src_version);
+ dst->copy_from.flags = src->copy_from.flags;
+ dst->copy_from.src_fadvise_flags =
+ cpu_to_le32(src->copy_from.src_fadvise_flags);
break;
default:
pr_err("unsupported osd opcode %s\n",
@@ -1030,16 +1091,24 @@
truncate_size, truncate_seq);
}
- req->r_flags = flags;
req->r_base_oloc.pool = layout->pool_id;
req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
+ req->r_flags = flags | osdc->client->options->read_from_replica;
req->r_snapid = vino.snap;
if (flags & CEPH_OSD_FLAG_WRITE)
req->r_data_offset = off;
- r = ceph_osdc_alloc_messages(req, GFP_NOFS);
+ if (num_ops > 1)
+ /*
+ * This is a special case for ceph_writepages_start(), but it
+ * also covers ceph_uninline_data(). If more multi-op request
+ * use cases emerge, we will need a separate helper.
+ */
+ r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_ops, 0);
+ else
+ r = ceph_osdc_alloc_messages(req, GFP_NOFS);
if (r)
goto fail;
@@ -1408,6 +1477,45 @@
(osdc->osdmap->epoch < osdc->epoch_barrier);
}
+static int pick_random_replica(const struct ceph_osds *acting)
+{
+ int i = prandom_u32() % acting->size;
+
+ dout("%s picked osd%d, primary osd%d\n", __func__,
+ acting->osds[i], acting->primary);
+ return i;
+}
+
+/*
+ * Picks the closest replica based on client's location given by
+ * crush_location option. Prefers the primary if the locality is
+ * the same.
+ */
+static int pick_closest_replica(struct ceph_osd_client *osdc,
+ const struct ceph_osds *acting)
+{
+ struct ceph_options *opt = osdc->client->options;
+ int best_i, best_locality;
+ int i = 0, locality;
+
+ do {
+ locality = ceph_get_crush_locality(osdc->osdmap,
+ acting->osds[i],
+ &opt->crush_locs);
+ if (i == 0 ||
+ (locality >= 0 && best_locality < 0) ||
+ (locality >= 0 && best_locality >= 0 &&
+ locality < best_locality)) {
+ best_i = i;
+ best_locality = locality;
+ }
+ } while (++i < acting->size);
+
+ dout("%s picked osd%d with locality %d, primary osd%d\n", __func__,
+ acting->osds[best_i], best_locality, acting->primary);
+ return best_i;
+}
+
enum calc_target_result {
CALC_TARGET_NO_ACTION = 0,
CALC_TARGET_NEED_RESEND,
@@ -1416,12 +1524,13 @@
static enum calc_target_result calc_target(struct ceph_osd_client *osdc,
struct ceph_osd_request_target *t,
- struct ceph_connection *con,
bool any_change)
{
struct ceph_pg_pool_info *pi;
struct ceph_pg pgid, last_pgid;
struct ceph_osds up, acting;
+ bool is_read = t->flags & CEPH_OSD_FLAG_READ;
+ bool is_write = t->flags & CEPH_OSD_FLAG_WRITE;
bool force_resend = false;
bool unpaused = false;
bool legacy_change = false;
@@ -1452,9 +1561,9 @@
ceph_oid_copy(&t->target_oid, &t->base_oid);
ceph_oloc_copy(&t->target_oloc, &t->base_oloc);
if ((t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) {
- if (t->flags & CEPH_OSD_FLAG_READ && pi->read_tier >= 0)
+ if (is_read && pi->read_tier >= 0)
t->target_oloc.pool = pi->read_tier;
- if (t->flags & CEPH_OSD_FLAG_WRITE && pi->write_tier >= 0)
+ if (is_write && pi->write_tier >= 0)
t->target_oloc.pool = pi->write_tier;
pi = ceph_pg_pool_by_id(osdc->osdmap, t->target_oloc.pool);
@@ -1493,7 +1602,8 @@
unpaused = true;
}
legacy_change = ceph_pg_compare(&t->pgid, &pgid) ||
- ceph_osds_changed(&t->acting, &acting, any_change);
+ ceph_osds_changed(&t->acting, &acting,
+ t->used_replica || any_change);
if (t->pg_num)
split = ceph_pg_is_split(&last_pgid, t->pg_num, pi->pg_num);
@@ -1509,7 +1619,24 @@
t->sort_bitwise = sort_bitwise;
t->recovery_deletes = recovery_deletes;
- t->osd = acting.primary;
+ if ((t->flags & (CEPH_OSD_FLAG_BALANCE_READS |
+ CEPH_OSD_FLAG_LOCALIZE_READS)) &&
+ !is_write && pi->type == CEPH_POOL_TYPE_REP &&
+ acting.size > 1) {
+ int pos;
+
+ WARN_ON(!is_read || acting.osds[0] != acting.primary);
+ if (t->flags & CEPH_OSD_FLAG_BALANCE_READS) {
+ pos = pick_random_replica(&acting);
+ } else {
+ pos = pick_closest_replica(osdc, &acting);
+ }
+ t->osd = acting.osds[pos];
+ t->used_replica = pos > 0;
+ } else {
+ t->osd = acting.primary;
+ t->used_replica = false;
+ }
}
if (unpaused || legacy_change || force_resend || split)
@@ -1845,48 +1972,55 @@
return true;
}
-static void setup_request_data(struct ceph_osd_request *req,
- struct ceph_msg *msg)
+/*
+ * Keep get_num_data_items() in sync with this function.
+ */
+static void setup_request_data(struct ceph_osd_request *req)
{
- u32 data_len = 0;
- int i;
+ struct ceph_msg *request_msg = req->r_request;
+ struct ceph_msg *reply_msg = req->r_reply;
+ struct ceph_osd_req_op *op;
- if (!list_empty(&msg->data))
+ if (req->r_request->num_data_items || req->r_reply->num_data_items)
return;
- WARN_ON(msg->data_length);
- for (i = 0; i < req->r_num_ops; i++) {
- struct ceph_osd_req_op *op = &req->r_ops[i];
-
+ WARN_ON(request_msg->data_length || reply_msg->data_length);
+ for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
switch (op->op) {
/* request */
case CEPH_OSD_OP_WRITE:
case CEPH_OSD_OP_WRITEFULL:
WARN_ON(op->indata_len != op->extent.length);
- ceph_osdc_msg_data_add(msg, &op->extent.osd_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->extent.osd_data);
break;
case CEPH_OSD_OP_SETXATTR:
case CEPH_OSD_OP_CMPXATTR:
WARN_ON(op->indata_len != op->xattr.name_len +
op->xattr.value_len);
- ceph_osdc_msg_data_add(msg, &op->xattr.osd_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->xattr.osd_data);
break;
case CEPH_OSD_OP_NOTIFY_ACK:
- ceph_osdc_msg_data_add(msg,
+ ceph_osdc_msg_data_add(request_msg,
&op->notify_ack.request_data);
+ break;
+ case CEPH_OSD_OP_COPY_FROM2:
+ ceph_osdc_msg_data_add(request_msg,
+ &op->copy_from.osd_data);
break;
/* reply */
case CEPH_OSD_OP_STAT:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->raw_data_in);
break;
case CEPH_OSD_OP_READ:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->extent.osd_data);
break;
case CEPH_OSD_OP_LIST_WATCHERS:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->list_watchers.response_data);
break;
@@ -1895,25 +2029,23 @@
WARN_ON(op->indata_len != op->cls.class_len +
op->cls.method_len +
op->cls.indata_len);
- ceph_osdc_msg_data_add(msg, &op->cls.request_info);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->cls.request_info);
/* optional, can be NONE */
- ceph_osdc_msg_data_add(msg, &op->cls.request_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->cls.request_data);
/* optional, can be NONE */
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->cls.response_data);
break;
case CEPH_OSD_OP_NOTIFY:
- ceph_osdc_msg_data_add(msg,
+ ceph_osdc_msg_data_add(request_msg,
&op->notify.request_data);
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->notify.response_data);
break;
}
-
- data_len += op->indata_len;
}
-
- WARN_ON(data_len != msg->data_length);
}
static void encode_pgid(void **p, const struct ceph_pg *pgid)
@@ -1961,7 +2093,7 @@
req->r_data_offset || req->r_snapc);
}
- setup_request_data(req, msg);
+ setup_request_data(req);
encode_spgid(&p, &req->r_t.spgid); /* actual spg */
ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */
@@ -2195,7 +2327,7 @@
dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
again:
- ct_res = calc_target(osdc, &req->r_t, NULL, false);
+ ct_res = calc_target(osdc, &req->r_t, false);
if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked)
goto promote;
@@ -2229,7 +2361,7 @@
(ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
pool_full(osdc, req->r_t.base_oloc.pool))) {
dout("req %p full/pool_full\n", req);
- if (osdc->abort_on_full) {
+ if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) {
err = -ENOSPC;
} else {
pr_warn_ratelimited("FULL or reached pool quota\n");
@@ -2280,6 +2412,7 @@
atomic_inc(&req->r_osdc->num_requests);
req->r_start_stamp = jiffies;
+ req->r_start_latency = ktime_get();
}
static void submit_request(struct ceph_osd_request *req, bool wrlocked)
@@ -2295,6 +2428,8 @@
WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid));
dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
+
+ req->r_end_latency = ktime_get();
if (req->r_osd)
unlink_request(req->r_osd, req);
@@ -2312,7 +2447,7 @@
static void __complete_request(struct ceph_osd_request *req)
{
- dout("%s req %p tid %llu cb %pf result %d\n", __func__, req,
+ dout("%s req %p tid %llu cb %ps result %d\n", __func__, req,
req->r_tid, req->r_callback, req->r_result);
if (req->r_callback)
@@ -2399,6 +2534,14 @@
}
EXPORT_SYMBOL(ceph_osdc_abort_requests);
+void ceph_osdc_clear_abort_err(struct ceph_osd_client *osdc)
+{
+ down_write(&osdc->lock);
+ osdc->abort_err = 0;
+ up_write(&osdc->lock);
+}
+EXPORT_SYMBOL(ceph_osdc_clear_abort_err);
+
static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
{
if (likely(eb > osdc->epoch_barrier)) {
@@ -2459,7 +2602,7 @@
{
bool victims = false;
- if (osdc->abort_on_full &&
+ if (ceph_test_opt(osdc->client, ABORT_ON_FULL) &&
(ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc)))
for_each_request(osdc, abort_on_full_fn, &victims);
}
@@ -2563,10 +2706,13 @@
WARN_ON(!list_empty(&lreq->pending_lworks));
WARN_ON(lreq->osd);
- if (lreq->reg_req)
- ceph_osdc_put_request(lreq->reg_req);
- if (lreq->ping_req)
- ceph_osdc_put_request(lreq->ping_req);
+ if (lreq->request_pl)
+ ceph_pagelist_release(lreq->request_pl);
+ if (lreq->notify_id_pages)
+ ceph_release_page_vector(lreq->notify_id_pages, 1);
+
+ ceph_osdc_put_request(lreq->reg_req);
+ ceph_osdc_put_request(lreq->ping_req);
target_destroy(&lreq->t);
kfree(lreq);
}
@@ -2835,6 +2981,12 @@
struct ceph_osd_linger_request *lreq = req->r_priv;
mutex_lock(&lreq->lock);
+ if (req != lreq->reg_req) {
+ dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
+ __func__, lreq, lreq->linger_id, req, lreq->reg_req);
+ goto out;
+ }
+
dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq,
lreq->linger_id, req->r_result);
linger_reg_commit_complete(lreq, req->r_result);
@@ -2858,6 +3010,7 @@
}
}
+out:
mutex_unlock(&lreq->lock);
linger_put(lreq);
}
@@ -2880,6 +3033,12 @@
struct ceph_osd_linger_request *lreq = req->r_priv;
mutex_lock(&lreq->lock);
+ if (req != lreq->reg_req) {
+ dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
+ __func__, lreq, lreq->linger_id, req, lreq->reg_req);
+ goto out;
+ }
+
dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__,
lreq, lreq->linger_id, req->r_result, lreq->last_error);
if (req->r_result < 0) {
@@ -2889,48 +3048,64 @@
}
}
+out:
mutex_unlock(&lreq->lock);
linger_put(lreq);
}
static void send_linger(struct ceph_osd_linger_request *lreq)
{
- struct ceph_osd_request *req = lreq->reg_req;
- struct ceph_osd_req_op *op = &req->r_ops[0];
+ struct ceph_osd_client *osdc = lreq->osdc;
+ struct ceph_osd_request *req;
+ int ret;
- verify_osdc_wrlocked(req->r_osdc);
+ verify_osdc_wrlocked(osdc);
+ mutex_lock(&lreq->lock);
dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
- if (req->r_osd)
- cancel_linger_request(req);
+ if (lreq->reg_req) {
+ if (lreq->reg_req->r_osd)
+ cancel_linger_request(lreq->reg_req);
+ ceph_osdc_put_request(lreq->reg_req);
+ }
- request_reinit(req);
- ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
- ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
- req->r_flags = lreq->t.flags;
+ req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO);
+ BUG_ON(!req);
+
+ target_copy(&req->r_t, &lreq->t);
req->r_mtime = lreq->mtime;
- mutex_lock(&lreq->lock);
if (lreq->is_watch && lreq->committed) {
- WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
- op->watch.cookie != lreq->linger_id);
- op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT;
- op->watch.gen = ++lreq->register_gen;
+ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT,
+ lreq->linger_id, ++lreq->register_gen);
dout("lreq %p reconnect register_gen %u\n", lreq,
- op->watch.gen);
+ req->r_ops[0].watch.gen);
req->r_callback = linger_reconnect_cb;
} else {
- if (!lreq->is_watch)
+ if (lreq->is_watch) {
+ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH,
+ lreq->linger_id, 0);
+ } else {
lreq->notify_id = 0;
- else
- WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH);
+
+ refcount_inc(&lreq->request_pl->refcnt);
+ osd_req_op_notify_init(req, 0, lreq->linger_id,
+ lreq->request_pl);
+ ceph_osd_data_pages_init(
+ osd_req_op_data(req, 0, notify, response_data),
+ lreq->notify_id_pages, PAGE_SIZE, 0, false, false);
+ }
dout("lreq %p register\n", lreq);
req->r_callback = linger_commit_cb;
}
- mutex_unlock(&lreq->lock);
+
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ BUG_ON(ret);
req->r_priv = linger_get(lreq);
req->r_linger = true;
+ lreq->reg_req = req;
+ mutex_unlock(&lreq->lock);
submit_request(req, true);
}
@@ -2940,6 +3115,12 @@
struct ceph_osd_linger_request *lreq = req->r_priv;
mutex_lock(&lreq->lock);
+ if (req != lreq->ping_req) {
+ dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
+ __func__, lreq, lreq->linger_id, req, lreq->ping_req);
+ goto out;
+ }
+
dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n",
__func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent,
lreq->last_error);
@@ -2955,6 +3136,7 @@
lreq->register_gen, req->r_ops[0].watch.gen);
}
+out:
mutex_unlock(&lreq->lock);
linger_put(lreq);
}
@@ -2962,8 +3144,8 @@
static void send_linger_ping(struct ceph_osd_linger_request *lreq)
{
struct ceph_osd_client *osdc = lreq->osdc;
- struct ceph_osd_request *req = lreq->ping_req;
- struct ceph_osd_req_op *op = &req->r_ops[0];
+ struct ceph_osd_request *req;
+ int ret;
if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
dout("%s PAUSERD\n", __func__);
@@ -2975,19 +3157,26 @@
__func__, lreq, lreq->linger_id, lreq->ping_sent,
lreq->register_gen);
- if (req->r_osd)
- cancel_linger_request(req);
+ if (lreq->ping_req) {
+ if (lreq->ping_req->r_osd)
+ cancel_linger_request(lreq->ping_req);
+ ceph_osdc_put_request(lreq->ping_req);
+ }
- request_reinit(req);
+ req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO);
+ BUG_ON(!req);
+
target_copy(&req->r_t, &lreq->t);
-
- WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
- op->watch.cookie != lreq->linger_id ||
- op->watch.op != CEPH_OSD_WATCH_OP_PING);
- op->watch.gen = lreq->register_gen;
+ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id,
+ lreq->register_gen);
req->r_callback = linger_ping_cb;
+
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ BUG_ON(ret);
+
req->r_priv = linger_get(lreq);
req->r_linger = true;
+ lreq->ping_req = req;
ceph_osdc_get_request(req);
account_request(req);
@@ -3001,11 +3190,15 @@
struct ceph_osd_client *osdc = lreq->osdc;
struct ceph_osd *osd;
- calc_target(osdc, &lreq->t, NULL, false);
+ down_write(&osdc->lock);
+ linger_register(lreq);
+
+ calc_target(osdc, &lreq->t, false);
osd = lookup_create_osd(osdc, lreq->t.osd, true);
link_linger(osd, lreq);
send_linger(lreq);
+ up_write(&osdc->lock);
}
static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq)
@@ -3030,9 +3223,9 @@
*/
static void __linger_cancel(struct ceph_osd_linger_request *lreq)
{
- if (lreq->is_watch && lreq->ping_req->r_osd)
+ if (lreq->ping_req && lreq->ping_req->r_osd)
cancel_linger_request(lreq->ping_req);
- if (lreq->reg_req->r_osd)
+ if (lreq->reg_req && lreq->reg_req->r_osd)
cancel_linger_request(lreq->reg_req);
cancel_linger_map_check(lreq);
unlink_linger(lreq->osd, lreq);
@@ -3137,17 +3330,24 @@
int ret;
dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
- ret = wait_for_completion_interruptible(&lreq->reg_commit_wait);
+ ret = wait_for_completion_killable(&lreq->reg_commit_wait);
return ret ?: lreq->reg_commit_error;
}
-static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq)
+static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq,
+ unsigned long timeout)
{
- int ret;
+ long left;
dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
- ret = wait_for_completion_interruptible(&lreq->notify_finish_wait);
- return ret ?: lreq->notify_finish_error;
+ left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait,
+ ceph_timeout_jiffies(timeout));
+ if (left <= 0)
+ left = left ?: -ETIMEDOUT;
+ else
+ left = lreq->notify_finish_error; /* completed */
+
+ return left;
}
/*
@@ -3372,9 +3572,6 @@
goto e_inval;
}
- len = ceph_decode_32(p);
- *p += len; /* skip osd_instructions */
-
/* skip the rest */
*p = struct_end;
out:
@@ -3549,6 +3746,26 @@
goto out_unlock_osdc;
}
+ if (m.result == -EAGAIN) {
+ dout("req %p tid %llu EAGAIN\n", req, req->r_tid);
+ unlink_request(osd, req);
+ mutex_unlock(&osd->lock);
+
+ /*
+ * The object is missing on the replica or not (yet)
+ * readable. Clear pgid to force a resend to the primary
+ * via legacy_change.
+ */
+ req->r_t.pgid.pool = 0;
+ req->r_t.pgid.seed = 0;
+ WARN_ON(!req->r_t.used_replica);
+ req->r_flags &= ~(CEPH_OSD_FLAG_BALANCE_READS |
+ CEPH_OSD_FLAG_LOCALIZE_READS);
+ req->r_tid = 0;
+ __submit_request(req, false);
+ goto out_unlock_osdc;
+ }
+
if (m.num_ops != req->r_num_ops) {
pr_err("num_ops %d != %d for tid %llu\n", m.num_ops,
req->r_num_ops, req->r_tid);
@@ -3619,7 +3836,7 @@
struct ceph_osd_client *osdc = lreq->osdc;
enum calc_target_result ct_res;
- ct_res = calc_target(osdc, &lreq->t, NULL, true);
+ ct_res = calc_target(osdc, &lreq->t, true);
if (ct_res == CALC_TARGET_NEED_RESEND) {
struct ceph_osd *osd;
@@ -3665,7 +3882,7 @@
if (!force_resend && !force_resend_writes)
break;
- /* fall through */
+ fallthrough;
case CALC_TARGET_NEED_RESEND:
cancel_linger_map_check(lreq);
/*
@@ -3691,8 +3908,7 @@
n = rb_next(n); /* unlink_request(), check_pool_dne() */
dout("%s req %p tid %llu\n", __func__, req, req->r_tid);
- ct_res = calc_target(osdc, &req->r_t, &req->r_osd->o_con,
- false);
+ ct_res = calc_target(osdc, &req->r_t, false);
switch (ct_res) {
case CALC_TARGET_NO_ACTION:
force_resend_writes = cleared_full ||
@@ -3703,7 +3919,7 @@
!force_resend_writes))
break;
- /* fall through */
+ fallthrough;
case CALC_TARGET_NEED_RESEND:
cancel_map_check(req);
unlink_request(osd, req);
@@ -3801,7 +4017,7 @@
n = rb_next(n);
if (req->r_t.epoch < osdc->osdmap->epoch) {
- ct_res = calc_target(osdc, &req->r_t, NULL, false);
+ ct_res = calc_target(osdc, &req->r_t, false);
if (ct_res == CALC_TARGET_POOL_DNE) {
erase_request(need_resend, req);
check_pool_dne(req);
@@ -4320,9 +4536,7 @@
lreq->notify_id, notify_id);
} else if (!completion_done(&lreq->notify_finish_wait)) {
struct ceph_msg_data *data =
- list_first_entry_or_null(&msg->data,
- struct ceph_msg_data,
- links);
+ msg->num_data_items ? &msg->data[0] : NULL;
if (data) {
if (lreq->preply_pages) {
@@ -4330,9 +4544,7 @@
CEPH_MSG_DATA_PAGES);
*lreq->preply_pages = data->pages;
*lreq->preply_len = data->length;
- } else {
- ceph_release_page_vector(data->pages,
- calc_pages_for(0, data->length));
+ data->own_pages = false;
}
}
lreq->notify_finish_error = return_code;
@@ -4467,26 +4679,6 @@
}
EXPORT_SYMBOL(ceph_osdc_sync);
-static struct ceph_osd_request *
-alloc_linger_request(struct ceph_osd_linger_request *lreq)
-{
- struct ceph_osd_request *req;
-
- req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO);
- if (!req)
- return NULL;
-
- ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
- ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
-
- if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
- ceph_osdc_put_request(req);
- return NULL;
- }
-
- return req;
-}
-
/*
* Returns a handle, caller owns a ref.
*/
@@ -4516,27 +4708,7 @@
lreq->t.flags = CEPH_OSD_FLAG_WRITE;
ktime_get_real_ts64(&lreq->mtime);
- lreq->reg_req = alloc_linger_request(lreq);
- if (!lreq->reg_req) {
- ret = -ENOMEM;
- goto err_put_lreq;
- }
-
- lreq->ping_req = alloc_linger_request(lreq);
- if (!lreq->ping_req) {
- ret = -ENOMEM;
- goto err_put_lreq;
- }
-
- down_write(&osdc->lock);
- linger_register(lreq); /* before osd_req_op_* */
- osd_req_op_watch_init(lreq->reg_req, 0, lreq->linger_id,
- CEPH_OSD_WATCH_OP_WATCH);
- osd_req_op_watch_init(lreq->ping_req, 0, lreq->linger_id,
- CEPH_OSD_WATCH_OP_PING);
linger_submit(lreq);
- up_write(&osdc->lock);
-
ret = linger_reg_commit_wait(lreq);
if (ret) {
linger_cancel(lreq);
@@ -4573,8 +4745,8 @@
ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
req->r_flags = CEPH_OSD_FLAG_WRITE;
ktime_get_real_ts64(&req->r_mtime);
- osd_req_op_watch_init(req, 0, lreq->linger_id,
- CEPH_OSD_WATCH_OP_UNWATCH);
+ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH,
+ lreq->linger_id, 0);
ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
if (ret)
@@ -4599,13 +4771,12 @@
struct ceph_pagelist *pl;
int ret;
- op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
+ op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
- pl = kmalloc(sizeof(*pl), GFP_NOIO);
+ pl = ceph_pagelist_alloc(GFP_NOIO);
if (!pl)
return -ENOMEM;
- ceph_pagelist_init(pl);
ret = ceph_pagelist_encode_64(pl, notify_id);
ret |= ceph_pagelist_encode_64(pl, cookie);
if (payload) {
@@ -4643,12 +4814,12 @@
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = CEPH_OSD_FLAG_READ;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
+ payload_len);
if (ret)
goto out_put_req;
- ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
- payload_len);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
if (ret)
goto out_put_req;
@@ -4660,36 +4831,6 @@
return ret;
}
EXPORT_SYMBOL(ceph_osdc_notify_ack);
-
-static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
- u64 cookie, u32 prot_ver, u32 timeout,
- void *payload, u32 payload_len)
-{
- struct ceph_osd_req_op *op;
- struct ceph_pagelist *pl;
- int ret;
-
- op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
- op->notify.cookie = cookie;
-
- pl = kmalloc(sizeof(*pl), GFP_NOIO);
- if (!pl)
- return -ENOMEM;
-
- ceph_pagelist_init(pl);
- ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
- ret |= ceph_pagelist_encode_32(pl, timeout);
- ret |= ceph_pagelist_encode_32(pl, payload_len);
- ret |= ceph_pagelist_append(pl, payload, payload_len);
- if (ret) {
- ceph_pagelist_release(pl);
- return -ENOMEM;
- }
-
- ceph_osd_data_pagelist_init(&op->notify.request_data, pl);
- op->indata_len = pl->length;
- return 0;
-}
/*
* @timeout: in seconds
@@ -4709,7 +4850,6 @@
size_t *preply_len)
{
struct ceph_osd_linger_request *lreq;
- struct page **pages;
int ret;
WARN_ON(!timeout);
@@ -4722,6 +4862,29 @@
if (!lreq)
return -ENOMEM;
+ lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO);
+ if (!lreq->request_pl) {
+ ret = -ENOMEM;
+ goto out_put_lreq;
+ }
+
+ ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */
+ ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout);
+ ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len);
+ ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len);
+ if (ret) {
+ ret = -ENOMEM;
+ goto out_put_lreq;
+ }
+
+ /* for notify_id */
+ lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO);
+ if (IS_ERR(lreq->notify_id_pages)) {
+ ret = PTR_ERR(lreq->notify_id_pages);
+ lreq->notify_id_pages = NULL;
+ goto out_put_lreq;
+ }
+
lreq->preply_pages = preply_pages;
lreq->preply_len = preply_len;
@@ -4729,38 +4892,11 @@
ceph_oloc_copy(&lreq->t.base_oloc, oloc);
lreq->t.flags = CEPH_OSD_FLAG_READ;
- lreq->reg_req = alloc_linger_request(lreq);
- if (!lreq->reg_req) {
- ret = -ENOMEM;
- goto out_put_lreq;
- }
-
- /* for notify_id */
- pages = ceph_alloc_page_vector(1, GFP_NOIO);
- if (IS_ERR(pages)) {
- ret = PTR_ERR(pages);
- goto out_put_lreq;
- }
-
- down_write(&osdc->lock);
- linger_register(lreq); /* before osd_req_op_* */
- ret = osd_req_op_notify_init(lreq->reg_req, 0, lreq->linger_id, 1,
- timeout, payload, payload_len);
- if (ret) {
- linger_unregister(lreq);
- up_write(&osdc->lock);
- ceph_release_page_vector(pages, 1);
- goto out_put_lreq;
- }
- ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
- response_data),
- pages, PAGE_SIZE, 0, false, true);
linger_submit(lreq);
- up_write(&osdc->lock);
-
ret = linger_reg_commit_wait(lreq);
if (!ret)
- ret = linger_notify_finish_wait(lreq);
+ ret = linger_notify_finish_wait(lreq,
+ msecs_to_jiffies(2 * timeout * MSEC_PER_SEC));
else
dout("lreq %p failed to initiate notify %d\n", lreq, ret);
@@ -4814,20 +4950,26 @@
ret = ceph_start_decoding(p, end, 2, "watch_item_t",
&struct_v, &struct_len);
if (ret)
- return ret;
+ goto bad;
- ceph_decode_copy(p, &item->name, sizeof(item->name));
- item->cookie = ceph_decode_64(p);
- *p += 4; /* skip timeout_seconds */
+ ret = -EINVAL;
+ ceph_decode_copy_safe(p, end, &item->name, sizeof(item->name), bad);
+ ceph_decode_64_safe(p, end, item->cookie, bad);
+ ceph_decode_skip_32(p, end, bad); /* skip timeout seconds */
+
if (struct_v >= 2) {
- ceph_decode_copy(p, &item->addr, sizeof(item->addr));
- ceph_decode_addr(&item->addr);
+ ret = ceph_decode_entity_addr(p, end, &item->addr);
+ if (ret)
+ goto bad;
+ } else {
+ ret = 0;
}
dout("%s %s%llu cookie %llu addr %s\n", __func__,
ENTITY_NAME(item->name), item->cookie,
- ceph_pr_addr(&item->addr.in_addr));
- return 0;
+ ceph_pr_addr(&item->addr));
+bad:
+ return ret;
}
static int decode_watchers(void **p, void *end,
@@ -4883,10 +5025,6 @@
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = CEPH_OSD_FLAG_READ;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
- if (ret)
- goto out_put_req;
-
pages = ceph_alloc_page_vector(1, GFP_NOIO);
if (IS_ERR(pages)) {
ret = PTR_ERR(pages);
@@ -4897,6 +5035,10 @@
ceph_osd_data_pages_init(osd_req_op_data(req, 0, list_watchers,
response_data),
pages, PAGE_SIZE, 0, false, true);
+
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
ceph_osdc_start_request(osdc, req, false);
ret = ceph_osdc_wait_request(osdc, req);
@@ -4944,12 +5086,12 @@
const char *class, const char *method,
unsigned int flags,
struct page *req_page, size_t req_len,
- struct page *resp_page, size_t *resp_len)
+ struct page **resp_pages, size_t *resp_len)
{
struct ceph_osd_request *req;
int ret;
- if (req_len > PAGE_SIZE || (resp_page && *resp_len > PAGE_SIZE))
+ if (req_len > PAGE_SIZE)
return -E2BIG;
req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
@@ -4960,26 +5102,26 @@
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = flags;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
- if (ret)
- goto out_put_req;
-
- ret = osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
+ ret = osd_req_op_cls_init(req, 0, class, method);
if (ret)
goto out_put_req;
if (req_page)
osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len,
0, false, false);
- if (resp_page)
- osd_req_op_cls_response_data_pages(req, 0, &resp_page,
+ if (resp_pages)
+ osd_req_op_cls_response_data_pages(req, 0, resp_pages,
*resp_len, 0, false, false);
+
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
ceph_osdc_start_request(osdc, req, false);
ret = ceph_osdc_wait_request(osdc, req);
if (ret >= 0) {
ret = req->r_ops[0].rval;
- if (resp_page)
+ if (resp_pages)
*resp_len = req->r_ops[0].outdata_len;
}
@@ -4988,6 +5130,24 @@
return ret;
}
EXPORT_SYMBOL(ceph_osdc_call);
+
+/*
+ * reset all osd connections
+ */
+void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc)
+{
+ struct rb_node *n;
+
+ down_write(&osdc->lock);
+ for (n = rb_first(&osdc->osds); n; ) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+
+ n = rb_next(n);
+ if (!reopen_osd(osd))
+ kick_osd_requests(osd);
+ }
+ up_write(&osdc->lock);
+}
/*
* init, shutdown
@@ -5023,11 +5183,12 @@
goto out_map;
err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
- PAGE_SIZE, 10, true, "osd_op");
+ PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op");
if (err < 0)
goto out_mempool;
err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
- PAGE_SIZE, 10, true, "osd_op_reply");
+ PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10,
+ "osd_op_reply");
if (err < 0)
goto out_msgpool;
@@ -5091,84 +5252,85 @@
ceph_msgpool_destroy(&osdc->msgpool_op_reply);
}
-/*
- * Read some contiguous pages. If we cross a stripe boundary, shorten
- * *plen. Return number of bytes read, or error.
- */
-int ceph_osdc_readpages(struct ceph_osd_client *osdc,
- struct ceph_vino vino, struct ceph_file_layout *layout,
- u64 off, u64 *plen,
+static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
+ u64 src_snapid, u64 src_version,
+ struct ceph_object_id *src_oid,
+ struct ceph_object_locator *src_oloc,
+ u32 src_fadvise_flags,
+ u32 dst_fadvise_flags,
+ u32 truncate_seq, u64 truncate_size,
+ u8 copy_from_flags)
+{
+ struct ceph_osd_req_op *op;
+ struct page **pages;
+ void *p, *end;
+
+ pages = ceph_alloc_page_vector(1, GFP_KERNEL);
+ if (IS_ERR(pages))
+ return PTR_ERR(pages);
+
+ op = osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2,
+ dst_fadvise_flags);
+ op->copy_from.snapid = src_snapid;
+ op->copy_from.src_version = src_version;
+ op->copy_from.flags = copy_from_flags;
+ op->copy_from.src_fadvise_flags = src_fadvise_flags;
+
+ p = page_address(pages[0]);
+ end = p + PAGE_SIZE;
+ ceph_encode_string(&p, end, src_oid->name, src_oid->name_len);
+ encode_oloc(&p, end, src_oloc);
+ ceph_encode_32(&p, truncate_seq);
+ ceph_encode_64(&p, truncate_size);
+ op->indata_len = PAGE_SIZE - (end - p);
+
+ ceph_osd_data_pages_init(&op->copy_from.osd_data, pages,
+ op->indata_len, 0, false, true);
+ return 0;
+}
+
+int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
+ u64 src_snapid, u64 src_version,
+ struct ceph_object_id *src_oid,
+ struct ceph_object_locator *src_oloc,
+ u32 src_fadvise_flags,
+ struct ceph_object_id *dst_oid,
+ struct ceph_object_locator *dst_oloc,
+ u32 dst_fadvise_flags,
u32 truncate_seq, u64 truncate_size,
- struct page **pages, int num_pages, int page_align)
+ u8 copy_from_flags)
{
struct ceph_osd_request *req;
- int rc = 0;
+ int ret;
- dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino,
- vino.snap, off, *plen);
- req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1,
- CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
- NULL, truncate_seq, truncate_size,
- false);
- if (IS_ERR(req))
- return PTR_ERR(req);
+ req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL);
+ if (!req)
+ return -ENOMEM;
- /* it may be a short read due to an object boundary */
- osd_req_op_extent_osd_data_pages(req, 0,
- pages, *plen, page_align, false, false);
+ req->r_flags = CEPH_OSD_FLAG_WRITE;
- dout("readpages final extent is %llu~%llu (%llu bytes align %d)\n",
- off, *plen, *plen, page_align);
+ ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc);
+ ceph_oid_copy(&req->r_t.base_oid, dst_oid);
- rc = ceph_osdc_start_request(osdc, req, false);
- if (!rc)
- rc = ceph_osdc_wait_request(osdc, req);
+ ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid,
+ src_oloc, src_fadvise_flags,
+ dst_fadvise_flags, truncate_seq,
+ truncate_size, copy_from_flags);
+ if (ret)
+ goto out;
+ ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
+ if (ret)
+ goto out;
+
+ ceph_osdc_start_request(osdc, req, false);
+ ret = ceph_osdc_wait_request(osdc, req);
+
+out:
ceph_osdc_put_request(req);
- dout("readpages result %d\n", rc);
- return rc;
+ return ret;
}
-EXPORT_SYMBOL(ceph_osdc_readpages);
-
-/*
- * do a synchronous write on N pages
- */
-int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
- struct ceph_file_layout *layout,
- struct ceph_snap_context *snapc,
- u64 off, u64 len,
- u32 truncate_seq, u64 truncate_size,
- struct timespec64 *mtime,
- struct page **pages, int num_pages)
-{
- struct ceph_osd_request *req;
- int rc = 0;
- int page_align = off & ~PAGE_MASK;
-
- req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1,
- CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
- snapc, truncate_seq, truncate_size,
- true);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- /* it may be a short write due to an object boundary */
- osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
- false, false);
- dout("writepages %llu~%llu (%llu bytes)\n", off, len, len);
-
- req->r_mtime = *mtime;
- rc = ceph_osdc_start_request(osdc, req, true);
- if (!rc)
- rc = ceph_osdc_wait_request(osdc, req);
-
- ceph_osdc_put_request(req);
- if (rc == 0)
- rc = len;
- dout("writepages result %d\n", rc);
- return rc;
-}
-EXPORT_SYMBOL(ceph_osdc_writepages);
+EXPORT_SYMBOL(ceph_osdc_copy_from);
int __init ceph_osdc_setup(void)
{
@@ -5287,9 +5449,6 @@
return m;
}
-/*
- * TODO: switch to a msg-owned pagelist
- */
static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
{
struct ceph_msg *m;
@@ -5297,13 +5456,12 @@
u32 front_len = le32_to_cpu(hdr->front_len);
u32 data_len = le32_to_cpu(hdr->data_len);
- m = ceph_msg_new(type, front_len, GFP_NOIO, false);
+ m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false);
if (!m)
return NULL;
if (data_len) {
struct page **pages;
- struct ceph_osd_data osd_data;
pages = ceph_alloc_page_vector(calc_pages_for(0, data_len),
GFP_NOIO);
@@ -5312,9 +5470,7 @@
return NULL;
}
- ceph_osd_data_pages_init(&osd_data, pages, data_len, 0, false,
- false);
- ceph_osdc_msg_data_add(m, &osd_data);
+ ceph_msg_data_add_pages(m, pages, data_len, 0, true);
}
return m;
--
Gitblit v1.6.2