erofs-utils: mkfs,dump: introduce xattr name filter feature

Introduce "-Exattr-name-filter" option to enable the xattr name bloom
filter feature.

Also support listing this feature in dump.erofs.

Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230829145504.93567-4-jefflexu@linux.alibaba.com
[ Gao Xiang: update the commit subject. ]
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>

diff --git a/dump/main.c b/dump/main.c
index 7980f7896956dbaac61db5f0e18b2ba5f242a941..5425b7bd890feb0df50e9f4d22c1160232137e99 100644 (file)
--- a/dump/main.c
+++ b/dump/main.c
@@ -91,6 +91,7 @@ struct erofsdump_feature {
 static struct erofsdump_feature feature_lists[] = {
        { true, EROFS_FEATURE_COMPAT_SB_CHKSUM, "sb_csum" },
        { true, EROFS_FEATURE_COMPAT_MTIME, "mtime" },
+       { true, EROFS_FEATURE_COMPAT_XATTR_FILTER, "xattr_filter" },
        { false, EROFS_FEATURE_INCOMPAT_ZERO_PADDING, "0padding" },
        { false, EROFS_FEATURE_INCOMPAT_COMPR_CFGS, "compr_cfgs" },
        { false, EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER, "big_pcluster" },

diff --git a/include/erofs/config.h b/include/erofs/config.h
index 8f52d2c55713db688ad89c90e06ea6e9b6f853ef..c51f0cd07222842da6c2628bb972ea4a00e272b5 100644 (file)
--- a/include/erofs/config.h
+++ b/include/erofs/config.h
@@ -53,6 +53,7 @@ struct erofs_configure {
        bool c_ignore_mtime;
        bool c_showprogress;
        bool c_extra_ea_name_prefixes;
+       bool c_xattr_name_filter;
 
 #ifdef HAVE_LIBSELINUX
        struct selabel_handle *sehnd;

diff --git a/include/erofs/internal.h b/include/erofs/internal.h
index 3e73eefb02741e9ab4e4e869719f0f183c7ba592..382024a7d4e3bda60aba5d100c1a64b07f4a3252 100644 (file)
--- a/include/erofs/internal.h
+++ b/include/erofs/internal.h
@@ -139,6 +139,7 @@ EROFS_FEATURE_FUNCS(fragments, incompat, INCOMPAT_FRAGMENTS)
 EROFS_FEATURE_FUNCS(dedupe, incompat, INCOMPAT_DEDUPE)
 EROFS_FEATURE_FUNCS(xattr_prefixes, incompat, INCOMPAT_XATTR_PREFIXES)
 EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
+EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER)
 
 #define EROFS_I_EA_INITED      (1 << 0)
 #define EROFS_I_Z_INITED       (1 << 1)

diff --git a/lib/xattr.c b/lib/xattr.c
index 46a301ad992f66cb4e10079ca6b25b30f6b9b94f..65dd9a00f9eae0839d5287329bbabea6d6809e35 100644 (file)
--- a/lib/xattr.c
+++ b/lib/xattr.c
@@ -18,6 +18,7 @@
 #include "erofs/cache.h"
 #include "erofs/io.h"
 #include "erofs/fragments.h"
+#include "erofs/xxhash.h"
 #include "liberofs_private.h"
 
 #define EA_HASHTABLE_BITS 16
@@ -783,6 +784,65 @@ out:
        return ret;
 }
 
+static int erofs_xattr_filter_hashbit(struct xattr_item *item)
+{
+       u8 prefix = item->prefix;
+       const char *key = item->kvbuf;
+       unsigned int len = item->len[0];
+       char *name = NULL;
+       uint32_t hashbit;
+
+       if (prefix & EROFS_XATTR_LONG_PREFIX) {
+               struct ea_type_node *tnode;
+               u16 prefix_len;
+               int ret;
+
+               list_for_each_entry(tnode, &ea_name_prefixes, list) {
+                       if (tnode->index == item->prefix) {
+                               ret = asprintf(&name, "%s%.*s",
+                                              tnode->type.prefix, len, key);
+                               if (ret < 0)
+                                       return -ENOMEM;
+                               break;
+                       }
+               }
+               if (!name)
+                       return -ENOENT;
+
+               if (!match_base_prefix(name, &prefix, &prefix_len)) {
+                       free(name);
+                       return -ENOENT;
+               }
+               key = name + prefix_len;
+               len = strlen(key);
+       }
+
+       hashbit = xxh32(key, len, EROFS_XATTR_FILTER_SEED + prefix) &
+                 (EROFS_XATTR_FILTER_BITS - 1);
+       if (name)
+               free(name);
+       return hashbit;
+}
+
+static u32 erofs_xattr_filter_map(struct list_head *ixattrs)
+{
+       struct inode_xattr_node *node, *n;
+       u32 name_filter;
+       int hashbit;
+
+       name_filter = 0;
+       list_for_each_entry_safe(node, n, ixattrs, list) {
+               hashbit = erofs_xattr_filter_hashbit(node->item);
+               if (hashbit < 0) {
+                       erofs_warn("failed to generate xattr name filter: %s",
+                                  strerror(-hashbit));
+                       return 0;
+               }
+               name_filter |= (1UL << hashbit);
+       }
+       return EROFS_XATTR_FILTER_DEFAULT & ~name_filter;
+}
+
 char *erofs_export_xattr_ibody(struct list_head *ixattrs, unsigned int size)
 {
        struct inode_xattr_node *node, *n;
@@ -797,6 +857,11 @@ char *erofs_export_xattr_ibody(struct list_head *ixattrs, unsigned int size)
        header = (struct erofs_xattr_ibody_header *)buf;
        header->h_shared_count = 0;
 
+       if (cfg.c_xattr_name_filter) {
+               header->h_name_filter =
+                       cpu_to_le32(erofs_xattr_filter_map(ixattrs));
+       }
+
        p = sizeof(struct erofs_xattr_ibody_header);
        list_for_each_entry_safe(node, n, ixattrs, list) {
                struct xattr_item *const item = node->item;

diff --git a/mkfs/main.c b/mkfs/main.c
index c03a7a8a6a8787750f63e586a3a4c5078fa7260f..fad80b152d6dded803ae34f82cd23621dc06c92e 100644 (file)
--- a/mkfs/main.c
+++ b/mkfs/main.c
@@ -245,6 +245,13 @@ handle_fragment:
                                return -EINVAL;
                        cfg.c_dedupe = true;
                }
+
+               if (MATCH_EXTENTED_OPT("xattr-name-filter", token, keylen)) {
+                       if (vallen)
+                               return -EINVAL;
+                       cfg.c_xattr_name_filter = true;
+                       erofs_sb_set_xattr_filter(&sbi);
+               }
        }
        return 0;
 }