From 6778948f9de86c3cfaf36725a7c87dcff9ba247f Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 08:20:59 +0000
Subject: [PATCH] kernel_5.10 no rt
---
kernel/drivers/block/drbd/drbd_nl.c | 242 +++++++++++++++++++++++++++---------------------
1 files changed, 135 insertions(+), 107 deletions(-)
diff --git a/kernel/drivers/block/drbd/drbd_nl.c b/kernel/drivers/block/drbd/drbd_nl.c
index 5b15ffd..54f77b4 100644
--- a/kernel/drivers/block/drbd/drbd_nl.c
+++ b/kernel/drivers/block/drbd/drbd_nl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
drbd_nl.c
@@ -7,19 +8,6 @@
Copyright (C) 1999-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
- drbd is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
-
- drbd is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with drbd; see the file COPYING. If not, write to
- the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
*/
@@ -114,7 +102,7 @@
if (!info || !info[0])
return 0;
- nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY);
+ nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY);
if (!nla)
return err;
@@ -124,6 +112,35 @@
return err;
} else
nla_nest_end(skb, nla);
+ return 0;
+}
+
+__printf(2, 3)
+static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...)
+{
+ va_list args;
+ struct nlattr *nla, *txt;
+ int err = -EMSGSIZE;
+ int len;
+
+ nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY);
+ if (!nla)
+ return err;
+
+ txt = nla_reserve(skb, T_info_text, 256);
+ if (!txt) {
+ nla_nest_cancel(skb, nla);
+ return err;
+ }
+ va_start(args, fmt);
+ len = vscnprintf(nla_data(txt), 256, fmt, args);
+ va_end(args);
+
+ /* maybe: retry with larger reserve, if truncated */
+ txt->nla_len = nla_attr_size(len+1);
+ nlmsg_trim(skb, (char*)txt + NLA_ALIGN(txt->nla_len));
+ nla_nest_end(skb, nla);
+
return 0;
}
@@ -251,19 +268,18 @@
/* some more paranoia, if the request was over-determined */
if (adm_ctx->device && adm_ctx->resource &&
adm_ctx->device->resource != adm_ctx->resource) {
- pr_warning("request: minor=%u, resource=%s; but that minor belongs to resource %s\n",
- adm_ctx->minor, adm_ctx->resource->name,
- adm_ctx->device->resource->name);
+ pr_warn("request: minor=%u, resource=%s; but that minor belongs to resource %s\n",
+ adm_ctx->minor, adm_ctx->resource->name,
+ adm_ctx->device->resource->name);
drbd_msg_put_info(adm_ctx->reply_skb, "minor exists in different resource");
return ERR_INVALID_REQUEST;
}
if (adm_ctx->device &&
adm_ctx->volume != VOLUME_UNSPECIFIED &&
adm_ctx->volume != adm_ctx->device->vnr) {
- pr_warning("request: minor=%u, volume=%u; but that minor is volume %u in %s\n",
- adm_ctx->minor, adm_ctx->volume,
- adm_ctx->device->vnr,
- adm_ctx->device->resource->name);
+ pr_warn("request: minor=%u, volume=%u; but that minor is volume %u in %s\n",
+ adm_ctx->minor, adm_ctx->volume,
+ adm_ctx->device->vnr, adm_ctx->device->resource->name);
drbd_msg_put_info(adm_ctx->reply_skb, "minor exists as different volume");
return ERR_INVALID_REQUEST;
}
@@ -582,7 +598,7 @@
struct task_struct *opa;
kref_get(&connection->kref);
- /* We may just have force_sig()'ed this thread
+ /* We may have just sent a signal to this thread
* to get it out of some blocking network function.
* Clear signals; otherwise kthread_run(), which internally uses
* wait_on_completion_killable(), will mistake our pending signal
@@ -774,9 +790,11 @@
mutex_lock(&adm_ctx.resource->adm_mutex);
if (info->genlhdr->cmd == DRBD_ADM_PRIMARY)
- retcode = drbd_set_role(adm_ctx.device, R_PRIMARY, parms.assume_uptodate);
+ retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device,
+ R_PRIMARY, parms.assume_uptodate);
else
- retcode = drbd_set_role(adm_ctx.device, R_SECONDARY, 0);
+ retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device,
+ R_SECONDARY, 0);
mutex_unlock(&adm_ctx.resource->adm_mutex);
genl_lock();
@@ -922,7 +940,6 @@
} prev;
sector_t u_size, size;
struct drbd_md *md = &device->ldev->md;
- char ppb[10];
void *buffer;
int md_moved, la_size_changed;
@@ -981,7 +998,7 @@
goto err_out;
}
- if (drbd_get_capacity(device->this_bdev) != size ||
+ if (get_capacity(device->vdisk) != size ||
drbd_bm_capacity(device) != size) {
int err;
err = drbd_bm_resize(device, size, !(flags & DDSF_NO_RESYNC));
@@ -1000,8 +1017,6 @@
/* racy, see comments above. */
drbd_set_my_capacity(device, size);
md->la_size_sect = size;
- drbd_info(device, "size = %s (%llu KB)\n", ppsize(ppb, size>>1),
- (unsigned long long)size>>1);
}
if (rv <= DS_ERROR)
goto err_out;
@@ -1235,6 +1250,21 @@
}
}
+static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
+{
+ /* Fixup max_write_zeroes_sectors after blk_stack_limits():
+ * if we can handle "zeroes" efficiently on the protocol,
+ * we want to do that, even if our backend does not announce
+ * max_write_zeroes_sectors itself. */
+ struct drbd_connection *connection = first_peer_device(device)->connection;
+ /* If the peer announces WZEROES support, use it. Otherwise, rather
+ * send explicit zeroes than rely on some discard-zeroes-data magic. */
+ if (connection->agreed_features & DRBD_FF_WZEROES)
+ q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
+ else
+ q->limits.max_write_zeroes_sectors = 0;
+}
+
static void decide_on_write_same_support(struct drbd_device *device,
struct request_queue *q,
struct request_queue *b, struct o_qlim *o,
@@ -1333,18 +1363,11 @@
decide_on_write_same_support(device, q, b, o, disable_write_same);
if (b) {
- blk_queue_stack_limits(q, b);
-
- if (q->backing_dev_info->ra_pages !=
- b->backing_dev_info->ra_pages) {
- drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
- q->backing_dev_info->ra_pages,
- b->backing_dev_info->ra_pages);
- q->backing_dev_info->ra_pages =
- b->backing_dev_info->ra_pages;
- }
+ blk_stack_limits(&q->limits, &b->limits, 0);
+ blk_queue_update_readahead(q);
}
fixup_discard_if_not_supported(q);
+ fixup_write_zeroes(device, q);
}
void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o)
@@ -1546,7 +1569,8 @@
struct drbd_device *device;
struct disk_conf *new_disk_conf, *old_disk_conf;
struct fifo_buffer *old_plan = NULL, *new_plan = NULL;
- int err, fifo_size;
+ int err;
+ unsigned int fifo_size;
retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR);
if (!adm_ctx.reply_skb)
@@ -1911,8 +1935,7 @@
/* Make sure the new disk is big enough
* (we may currently be R_PRIMARY with no local disk...) */
- if (drbd_get_max_capacity(nbc) <
- drbd_get_capacity(device->this_bdev)) {
+ if (drbd_get_max_capacity(nbc) < get_capacity(device->vdisk)) {
retcode = ERR_DISK_TOO_SMALL;
goto fail;
}
@@ -1941,7 +1964,7 @@
drbd_flush_workqueue(&connection->sender_work);
rv = _drbd_request_state(device, NS(disk, D_ATTACHING), CS_VERBOSE);
- retcode = rv; /* FIXME: Type mismatch. */
+ retcode = (enum drbd_ret_code)rv;
drbd_resume_io(device);
if (rv < SS_SUCCESS)
goto fail;
@@ -1972,11 +1995,21 @@
}
/* Prevent shrinking of consistent devices ! */
- if (drbd_md_test_flag(nbc, MDF_CONSISTENT) &&
- drbd_new_dev_size(device, nbc, nbc->disk_conf->disk_size, 0) < nbc->md.la_size_sect) {
- drbd_warn(device, "refusing to truncate a consistent device\n");
- retcode = ERR_DISK_TOO_SMALL;
- goto force_diskless_dec;
+ {
+ unsigned long long nsz = drbd_new_dev_size(device, nbc, nbc->disk_conf->disk_size, 0);
+ unsigned long long eff = nbc->md.la_size_sect;
+ if (drbd_md_test_flag(nbc, MDF_CONSISTENT) && nsz < eff) {
+ if (nsz == nbc->disk_conf->disk_size) {
+ drbd_warn(device, "truncating a consistent device during attach (%llu < %llu)\n", nsz, eff);
+ } else {
+ drbd_warn(device, "refusing to truncate a consistent device (%llu < %llu)\n", nsz, eff);
+ drbd_msg_sprintf_info(adm_ctx.reply_skb,
+ "To-be-attached device has last effective > current size, and is consistent\n"
+ "(%llu > %llu sectors). Refusing to attach.", eff, nsz);
+ retcode = ERR_IMPLICIT_SHRINK;
+ goto force_diskless_dec;
+ }
+ }
}
lock_all_resources();
@@ -2325,10 +2358,10 @@
}
struct crypto {
- struct crypto_ahash *verify_tfm;
- struct crypto_ahash *csums_tfm;
+ struct crypto_shash *verify_tfm;
+ struct crypto_shash *csums_tfm;
struct crypto_shash *cram_hmac_tfm;
- struct crypto_ahash *integrity_tfm;
+ struct crypto_shash *integrity_tfm;
};
static int
@@ -2346,36 +2379,21 @@
return NO_ERROR;
}
-static int
-alloc_ahash(struct crypto_ahash **tfm, char *tfm_name, int err_alg)
-{
- if (!tfm_name[0])
- return NO_ERROR;
-
- *tfm = crypto_alloc_ahash(tfm_name, 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(*tfm)) {
- *tfm = NULL;
- return err_alg;
- }
-
- return NO_ERROR;
-}
-
static enum drbd_ret_code
alloc_crypto(struct crypto *crypto, struct net_conf *new_net_conf)
{
char hmac_name[CRYPTO_MAX_ALG_NAME];
enum drbd_ret_code rv;
- rv = alloc_ahash(&crypto->csums_tfm, new_net_conf->csums_alg,
+ rv = alloc_shash(&crypto->csums_tfm, new_net_conf->csums_alg,
ERR_CSUMS_ALG);
if (rv != NO_ERROR)
return rv;
- rv = alloc_ahash(&crypto->verify_tfm, new_net_conf->verify_alg,
+ rv = alloc_shash(&crypto->verify_tfm, new_net_conf->verify_alg,
ERR_VERIFY_ALG);
if (rv != NO_ERROR)
return rv;
- rv = alloc_ahash(&crypto->integrity_tfm, new_net_conf->integrity_alg,
+ rv = alloc_shash(&crypto->integrity_tfm, new_net_conf->integrity_alg,
ERR_INTEGRITY_ALG);
if (rv != NO_ERROR)
return rv;
@@ -2393,9 +2411,9 @@
static void free_crypto(struct crypto *crypto)
{
crypto_free_shash(crypto->cram_hmac_tfm);
- crypto_free_ahash(crypto->integrity_tfm);
- crypto_free_ahash(crypto->csums_tfm);
- crypto_free_ahash(crypto->verify_tfm);
+ crypto_free_shash(crypto->integrity_tfm);
+ crypto_free_shash(crypto->csums_tfm);
+ crypto_free_shash(crypto->verify_tfm);
}
int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
@@ -2472,17 +2490,17 @@
rcu_assign_pointer(connection->net_conf, new_net_conf);
if (!rsr) {
- crypto_free_ahash(connection->csums_tfm);
+ crypto_free_shash(connection->csums_tfm);
connection->csums_tfm = crypto.csums_tfm;
crypto.csums_tfm = NULL;
}
if (!ovr) {
- crypto_free_ahash(connection->verify_tfm);
+ crypto_free_shash(connection->verify_tfm);
connection->verify_tfm = crypto.verify_tfm;
crypto.verify_tfm = NULL;
}
- crypto_free_ahash(connection->integrity_tfm);
+ crypto_free_shash(connection->integrity_tfm);
connection->integrity_tfm = crypto.integrity_tfm;
if (connection->cstate >= C_WF_REPORT_PARAMS && connection->agreed_pro_version >= 100)
/* Do this without trying to take connection->data.mutex again. */
@@ -2671,7 +2689,8 @@
}
rcu_read_unlock();
- retcode = conn_request_state(connection, NS(conn, C_UNCONNECTED), CS_VERBOSE);
+ retcode = (enum drbd_ret_code)conn_request_state(connection,
+ NS(conn, C_UNCONNECTED), CS_VERBOSE);
conn_reconfig_done(connection);
mutex_unlock(&adm_ctx.resource->adm_mutex);
@@ -2691,8 +2710,10 @@
static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection, bool force)
{
+ enum drbd_conns cstate;
enum drbd_state_rv rv;
+repeat:
rv = conn_request_state(connection, NS(conn, C_DISCONNECTING),
force ? CS_HARD : 0);
@@ -2710,6 +2731,11 @@
break;
case SS_CW_FAILED_BY_PEER:
+ spin_lock_irq(&connection->resource->req_lock);
+ cstate = connection->cstate;
+ spin_unlock_irq(&connection->resource->req_lock);
+ if (cstate <= C_WF_CONNECTION)
+ goto repeat;
/* The peer probably wants to see us outdated. */
rv = conn_request_state(connection, NS2(conn, C_DISCONNECTING,
disk, D_OUTDATED), 0);
@@ -2777,7 +2803,7 @@
mutex_lock(&adm_ctx.resource->adm_mutex);
rv = conn_try_disconnect(connection, parms.force_disconnect);
if (rv < SS_SUCCESS)
- retcode = rv; /* FIXME: Type mismatch. */
+ retcode = (enum drbd_ret_code)rv;
else
retcode = NO_ERROR;
mutex_unlock(&adm_ctx.resource->adm_mutex);
@@ -3225,7 +3251,7 @@
struct drbd_device *device)
{
struct nlattr *nla;
- nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT);
+ nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_CONTEXT);
if (!nla)
goto nla_put_failure;
if (device &&
@@ -3338,7 +3364,6 @@
if (get_ldev(device)) {
struct drbd_md *md = &device->ldev->md;
u64 *history_uuids = (u64 *)s->history_uuids;
- struct request_queue *q;
int n;
spin_lock_irq(&md->uuid_lock);
@@ -3352,14 +3377,9 @@
spin_unlock_irq(&md->uuid_lock);
s->dev_disk_flags = md->flags;
- q = bdev_get_queue(device->ldev->backing_bdev);
- s->dev_lower_blocked =
- bdi_congested(q->backing_dev_info,
- (1 << WB_async_congested) |
- (1 << WB_sync_congested));
put_ldev(device);
}
- s->dev_size = drbd_get_capacity(device->this_bdev);
+ s->dev_size = get_capacity(device->vdisk);
s->dev_read = device->read_cnt;
s->dev_write = device->writ_cnt;
s->dev_al_writes = device->al_writ_cnt;
@@ -3391,7 +3411,7 @@
{
struct nlattr *resource_filter;
struct drbd_resource *resource;
- struct drbd_device *uninitialized_var(device);
+ struct drbd_device *device;
int minor, err, retcode;
struct drbd_genlmsghdr *dh;
struct device_info device_info;
@@ -3480,7 +3500,7 @@
{
struct nlattr *resource_filter;
struct drbd_resource *resource = NULL, *next_resource;
- struct drbd_connection *uninitialized_var(connection);
+ struct drbd_connection *connection;
int err = 0, retcode;
struct drbd_genlmsghdr *dh;
struct connection_info connection_info;
@@ -3642,7 +3662,7 @@
{
struct nlattr *resource_filter;
struct drbd_resource *resource;
- struct drbd_device *uninitialized_var(device);
+ struct drbd_device *device;
struct drbd_peer_device *peer_device = NULL;
int minor, err, retcode;
struct drbd_genlmsghdr *dh;
@@ -3793,14 +3813,13 @@
if (err)
goto nla_put_failure;
- nla = nla_nest_start(skb, DRBD_NLA_STATE_INFO);
+ nla = nla_nest_start_noflag(skb, DRBD_NLA_STATE_INFO);
if (!nla)
goto nla_put_failure;
if (nla_put_u32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) ||
nla_put_u32(skb, T_current_state, device->state.i) ||
nla_put_u64_0pad(skb, T_ed_uuid, device->ed_uuid) ||
- nla_put_u64_0pad(skb, T_capacity,
- drbd_get_capacity(device->this_bdev)) ||
+ nla_put_u64_0pad(skb, T_capacity, get_capacity(device->vdisk)) ||
nla_put_u64_0pad(skb, T_send_cnt, device->send_cnt) ||
nla_put_u64_0pad(skb, T_recv_cnt, device->recv_cnt) ||
nla_put_u64_0pad(skb, T_read_cnt, device->read_cnt) ||
@@ -3851,7 +3870,7 @@
if (nla_put_u32(skb, T_helper_exit_code,
sib->helper_exit_code))
goto nla_put_failure;
- /* fall through */
+ fallthrough;
case SIB_HELPER_PRE:
if (nla_put_string(skb, T_helper, sib->helper_name))
goto nla_put_failure;
@@ -4598,7 +4617,7 @@
return drbd_notification_header_to_skb(msg, &nh, true);
}
-void notify_resource_state(struct sk_buff *skb,
+int notify_resource_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_resource *resource,
struct resource_info *resource_info,
@@ -4640,16 +4659,17 @@
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;
nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}
-void notify_device_state(struct sk_buff *skb,
+int notify_device_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_device *device,
struct device_info *device_info,
@@ -4689,16 +4709,17 @@
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;
nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}
-void notify_connection_state(struct sk_buff *skb,
+int notify_connection_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_connection *connection,
struct connection_info *connection_info,
@@ -4738,16 +4759,17 @@
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;
nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}
-void notify_peer_device_state(struct sk_buff *skb,
+int notify_peer_device_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_peer_device *peer_device,
struct peer_device_info *peer_device_info,
@@ -4788,13 +4810,14 @@
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;
nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}
void notify_helper(enum drbd_notification_type type,
@@ -4845,7 +4868,7 @@
err, seq);
}
-static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq)
+static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq)
{
struct drbd_genlmsghdr *dh;
int err;
@@ -4859,11 +4882,12 @@
if (nla_put_notification_header(skb, NOTIFY_EXISTS))
goto nla_put_failure;
genlmsg_end(skb, dh);
- return;
+ return 0;
nla_put_failure:
nlmsg_free(skb);
pr_err("Error %d sending event. Event seq:%u\n", err, seq);
+ return err;
}
static void free_state_changes(struct list_head *list)
@@ -4890,6 +4914,7 @@
unsigned int seq = cb->args[2];
unsigned int n;
enum drbd_notification_type flags = 0;
+ int err = 0;
/* There is no need for taking notification_mutex here: it doesn't
matter if the initial state events mix with later state chage
@@ -4898,32 +4923,32 @@
cb->args[5]--;
if (cb->args[5] == 1) {
- notify_initial_state_done(skb, seq);
+ err = notify_initial_state_done(skb, seq);
goto out;
}
n = cb->args[4]++;
if (cb->args[4] < cb->args[3])
flags |= NOTIFY_CONTINUES;
if (n < 1) {
- notify_resource_state_change(skb, seq, state_change->resource,
+ err = notify_resource_state_change(skb, seq, state_change->resource,
NOTIFY_EXISTS | flags);
goto next;
}
n--;
if (n < state_change->n_connections) {
- notify_connection_state_change(skb, seq, &state_change->connections[n],
+ err = notify_connection_state_change(skb, seq, &state_change->connections[n],
NOTIFY_EXISTS | flags);
goto next;
}
n -= state_change->n_connections;
if (n < state_change->n_devices) {
- notify_device_state_change(skb, seq, &state_change->devices[n],
+ err = notify_device_state_change(skb, seq, &state_change->devices[n],
NOTIFY_EXISTS | flags);
goto next;
}
n -= state_change->n_devices;
if (n < state_change->n_devices * state_change->n_connections) {
- notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n],
+ err = notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n],
NOTIFY_EXISTS | flags);
goto next;
}
@@ -4938,7 +4963,10 @@
cb->args[4] = 0;
}
out:
- return skb->len;
+ if (err)
+ return err;
+ else
+ return skb->len;
}
int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb)
--
Gitblit v1.6.2