1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
From 97fbf32af7a3a3da1fa05a70df380f173b553725 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Tue, 7 Jun 2022 12:22:29 +0800
Subject: [PATCH 12/16] bcache: read jset from NVDIMM pages for journal replay
This patch implements two methods to read jset from media for journal
replay,
- __jnl_rd_bkt() for block device
This is the legacy method to read jset via block device interface.
- __jnl_rd_nvm_bkt() for NVDIMM
This is the method to read jset from NVDIMM memory interface, a.k.a
memcopy() from NVDIMM pages to DRAM pages.
If BCH_FEATURE_INCOMPAT_NVDIMM_META is set in incompat feature set,
during running cache set, journal_read_bucket() will read the journal
content from NVDIMM by __jnl_rd_nvm_bkt(). The linear addresses of
NVDIMM pages to read jset are stored in sb.d[SB_JOURNAL_BUCKETS], which
were initialized and maintained in previous runs of the cache set.
A thing should be noticed is, when bch_journal_read() is called, the
linear address of NVDIMM pages is not loaded and initialized yet, it
is necessary to call __bch_journal_nvdimm_init() before reading the jset
from NVDIMM pages.
The code comments added in journal_read_bucket() is noticed by kernel
test robot and Dan Carpenter, it explains why it is safe to only check
!bch_has_feature_nvdimm_meta() condition in the if() statement when
CONFIG_BCACHE_NVM_PAGES is not configured. To avoid confusion from the
bogus warning message from static checking tool.
Signed-off-by: Coly Li <colyli@suse.de>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jianpeng Ma <jianpeng.ma@intel.com>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
---
drivers/md/bcache/journal.c | 84 ++++++++++++++++++++++++++++++-------
1 file changed, 69 insertions(+), 15 deletions(-)
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 9c325be17830..24615df1f4e6 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -34,18 +34,58 @@ static void journal_read_endio(struct bio *bio)
closure_put(cl);
}
+static struct jset *__jnl_rd_bkt(struct cache *ca, unsigned int bkt_idx,
+ unsigned int len, unsigned int offset,
+ struct closure *cl)
+{
+ sector_t bucket = bucket_to_sector(ca->set, ca->sb.d[bkt_idx]);
+ struct bio *bio = &ca->journal.bio;
+ struct jset *data = ca->set->journal.w[0].data;
+
+ bio_reset(bio, ca->bdev, REQ_OP_READ);
+ bio->bi_iter.bi_sector = bucket + offset;
+ bio->bi_iter.bi_size = len << 9;
+
+ bio->bi_end_io = journal_read_endio;
+ bio->bi_private = cl;
+ bch_bio_map(bio, data);
+
+ closure_bio_submit(ca->set, bio, cl);
+ closure_sync(cl);
+
+ /* Indeed journal.w[0].data */
+ return data;
+}
+
+#if defined(CONFIG_BCACHE_NVM_PAGES)
+
+static struct jset *__jnl_rd_nvm_bkt(struct cache *ca, unsigned int bkt_idx,
+ unsigned int len, unsigned int offset)
+{
+ void *jset_addr;
+ struct jset *data;
+
+ jset_addr = bch_nvmpg_offset_to_ptr(ca->sb.d[bkt_idx]) + (offset << 9);
+ data = ca->set->journal.w[0].data;
+
+ memcpy(data, jset_addr, len << 9);
+
+ /* Indeed journal.w[0].data */
+ return data;
+}
+
+#endif /* CONFIG_BCACHE_NVM_PAGES */
+
static int journal_read_bucket(struct cache *ca, struct list_head *list,
unsigned int bucket_index)
{
struct journal_device *ja = &ca->journal;
- struct bio *bio = &ja->bio;
struct journal_replay *i;
- struct jset *j, *data = ca->set->journal.w[0].data;
+ struct jset *j;
struct closure cl;
unsigned int len, left, offset = 0;
int ret = 0;
- sector_t bucket = bucket_to_sector(ca->set, ca->sb.d[bucket_index]);
closure_init_stack(&cl);
@@ -55,24 +95,27 @@ static int journal_read_bucket(struct cache *ca, struct list_head *list,
reread: left = ca->sb.bucket_size - offset;
len = min_t(unsigned int, left, PAGE_SECTORS << JSET_BITS);
- bio_reset(bio, ca->bdev, REQ_OP_READ);
- bio->bi_iter.bi_sector = bucket + offset;
- bio->bi_iter.bi_size = len << 9;
-
- bio->bi_end_io = journal_read_endio;
- bio->bi_private = &cl;
- bch_bio_map(bio, data);
-
- closure_bio_submit(ca->set, bio, &cl);
- closure_sync(&cl);
+ if (!bch_has_feature_nvdimm_meta(&ca->sb))
+ j = __jnl_rd_bkt(ca, bucket_index, len, offset, &cl);
+ /*
+ * If CONFIG_BCACHE_NVM_PAGES is not defined, the feature bit
+ * BCH_FEATURE_INCOMPAT_NVDIMM_META won't in incompatible
+ * support feature set, a cache device format with feature bit
+ * BCH_FEATURE_INCOMPAT_NVDIMM_META will fail much earlier in
+ * read_super() by bch_has_unknown_incompat_features().
+ * Therefore when CONFIG_BCACHE_NVM_PAGES is not define, it is
+ * safe to ignore the bch_has_feature_nvdimm_meta() condition.
+ */
+#if defined(CONFIG_BCACHE_NVM_PAGES)
+ else
+ j = __jnl_rd_nvm_bkt(ca, bucket_index, len, offset);
+#endif
/* This function could be simpler now since we no longer write
* journal entries that overlap bucket boundaries; this means
* the start of a bucket will always have a valid journal entry
* if it has any journal entries at all.
*/
-
- j = data;
while (len) {
struct list_head *where;
size_t blocks, bytes = set_bytes(j);
@@ -168,6 +211,8 @@ reread: left = ca->sb.bucket_size - offset;
return ret;
}
+static int __bch_journal_nvdimm_init(struct cache *ca);
+
int bch_journal_read(struct cache_set *c, struct list_head *list)
{
#define read_bucket(b) \
@@ -186,6 +231,15 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
unsigned int i, l, r, m;
uint64_t seq;
+ /*
+ * Linear addresses of NVDIMM pages for journaling is not
+ * initialized yet, do it before read jset from NVDIMM pages.
+ */
+ if (bch_has_feature_nvdimm_meta(&ca->sb)) {
+ if (__bch_journal_nvdimm_init(ca) < 0)
+ return -ENXIO;
+ }
+
bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
pr_debug("%u journal buckets\n", ca->sb.njournal_buckets);
--
2.39.2
|
