lib/base64: add support for multiple variants

Patch series " lib/base64: add generic encoder/decoder, migrate users", v5.

This series introduces a generic Base64 encoder/decoder to the kernel
library, eliminating duplicated implementations and delivering significant
performance improvements.

The Base64 API has been extended to support multiple variants (Standard,
URL-safe, and IMAP) as defined in RFC 4648 and RFC 3501.  The API now
takes a variant parameter and an option to control padding.  As part of
this series, users are migrated to the new interface while preserving
their specific formats: fscrypt now uses BASE64_URLSAFE, Ceph uses
BASE64_IMAP, and NVMe is updated to BASE64_STD.

On the encoder side, the implementation processes input in 3-byte blocks,
mapping 24 bits directly to 4 output symbols.  This avoids bit-by-bit
streaming and reduces loop overhead, achieving about a 2.7x speedup
compared to previous implementations.

On the decoder side, replace strchr() lookups with per-variant reverse
tables and process input in 4-character groups.  Each group is mapped to
numeric values and combined into 3 bytes.  Padded and unpadded forms are
validated explicitly, rejecting invalid '=' usage and enforcing tail
rules.  This improves throughput by ~43-52x.

This patch (of 6):

Extend the base64 API to support multiple variants (standard, URL-safe,
and IMAP) as defined in RFC 4648 and RFC 3501.  The API now takes a
variant parameter and an option to control padding.  Update NVMe auth code
to use the new interface with BASE64_STD.

Link: https://lkml.kernel.org/r/20251114055829.87814-1-409411716@gms.tku.edu.tw
Link: https://lkml.kernel.org/r/20251114060045.88792-1-409411716@gms.tku.edu.tw
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Co-developed-by: Guan-Chun Wu <409411716@gms.tku.edu.tw>
Signed-off-by: Guan-Chun Wu <409411716@gms.tku.edu.tw>
Reviewed-by: David Laight <david.laight.linux@gmail.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Keith Busch <kbusch@kernel.org>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: "Theodore Y. Ts'o" <tytso@mit.edu>
Cc: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Cc: Xiubo Li <xiubli@redhat.com>
Cc: Yu-Sheng Huang <home7438072@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c
index 1f51fbebd9fac6bce2de5d29b71d69d866c715b1..e07e7d4bf8b687bfb831e63ac299eba66f9356af 100644 (file)
--- a/drivers/nvme/common/auth.c
+++ b/drivers/nvme/common/auth.c
@@ -178,7 +178,7 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret,
        if (!key)
                return ERR_PTR(-ENOMEM);
 
-       key_len = base64_decode(secret, allocated_len, key->key);
+       key_len = base64_decode(secret, allocated_len, key->key, true, BASE64_STD);
        if (key_len < 0) {
                pr_debug("base64 key decoding error %d\n",
                         key_len);
@@ -663,7 +663,7 @@ int nvme_auth_generate_digest(u8 hmac_id, u8 *psk, size_t psk_len,
        if (ret)
                goto out_free_digest;
 
-       ret = base64_encode(digest, digest_len, enc);
+       ret = base64_encode(digest, digest_len, enc, true, BASE64_STD);
        if (ret < hmac_len) {
                ret = -ENOKEY;
                goto out_free_digest;

diff --git a/include/linux/base64.h b/include/linux/base64.h
index 660d4cb1ef31f871d82b5fa9ff45d38b63a4d72d..a2c6c9222da36a308c4f91267e9c70a4c48c2e5b 100644 (file)
--- a/include/linux/base64.h
+++ b/include/linux/base64.h
@@ -8,9 +8,15 @@
 
 #include <linux/types.h>
 
+enum base64_variant {
+       BASE64_STD,       /* RFC 4648 (standard) */
+       BASE64_URLSAFE,   /* RFC 4648 (base64url) */
+       BASE64_IMAP,      /* RFC 3501 */
+};
+
 #define BASE64_CHARS(nbytes)   DIV_ROUND_UP((nbytes) * 4, 3)
 
-int base64_encode(const u8 *src, int len, char *dst);
-int base64_decode(const char *src, int len, u8 *dst);
+int base64_encode(const u8 *src, int len, char *dst, bool padding, enum base64_variant variant);
+int base64_decode(const char *src, int len, u8 *dst, bool padding, enum base64_variant variant);
 
 #endif /* _LINUX_BASE64_H */

diff --git a/lib/base64.c b/lib/base64.c
index b736a7a431c50ec37c9eb329146fe24eb5d934a2..a7c20a8e8e9874a062b0282970291b6cdece73d8 100644 (file)
--- a/lib/base64.c
+++ b/lib/base64.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * base64.c - RFC4648-compliant base64 encoding
+ * base64.c - Base64 with support for multiple variants
  *
  * Copyright (c) 2020 Hannes Reinecke, SUSE
  *
  * Based on the base64url routines from fs/crypto/fname.c
- * (which are using the URL-safe base64 encoding),
- * modified to use the standard coding table from RFC4648 section 4.
+ * (which are using the URL-safe Base64 encoding),
+ * modified to support multiple Base64 variants.
  */
 
 #include <linux/kernel.h>
@@ -15,26 +15,31 @@
 #include <linux/string.h>
 #include <linux/base64.h>
 
-static const char base64_table[65] =
-       "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+static const char base64_tables[][65] = {
+       [BASE64_STD] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/",
+       [BASE64_URLSAFE] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_",
+       [BASE64_IMAP] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,",
+};
 
 /**
- * base64_encode() - base64-encode some binary data
+ * base64_encode() - Base64-encode some binary data
  * @src: the binary data to encode
  * @srclen: the length of @src in bytes
- * @dst: (output) the base64-encoded string.  Not NUL-terminated.
+ * @dst: (output) the Base64-encoded string.  Not NUL-terminated.
+ * @padding: whether to append '=' padding characters
+ * @variant: which base64 variant to use
  *
- * Encodes data using base64 encoding, i.e. the "Base 64 Encoding" specified
- * by RFC 4648, including the  '='-padding.
+ * Encodes data using the selected Base64 variant.
  *
- * Return: the length of the resulting base64-encoded string in bytes.
+ * Return: the length of the resulting Base64-encoded string in bytes.
  */
-int base64_encode(const u8 *src, int srclen, char *dst)
+int base64_encode(const u8 *src, int srclen, char *dst, bool padding, enum base64_variant variant)
 {
        u32 ac = 0;
        int bits = 0;
        int i;
        char *cp = dst;
+       const char *base64_table = base64_tables[variant];
 
        for (i = 0; i < srclen; i++) {
                ac = (ac << 8) | src[i];
@@ -48,44 +53,49 @@ int base64_encode(const u8 *src, int srclen, char *dst)
                *cp++ = base64_table[(ac << (6 - bits)) & 0x3f];
                bits -= 6;
        }
-       while (bits < 0) {
-               *cp++ = '=';
-               bits += 2;
+       if (padding) {
+               while (bits < 0) {
+                       *cp++ = '=';
+                       bits += 2;
+               }
        }
        return cp - dst;
 }
 EXPORT_SYMBOL_GPL(base64_encode);
 
 /**
- * base64_decode() - base64-decode a string
+ * base64_decode() - Base64-decode a string
  * @src: the string to decode.  Doesn't need to be NUL-terminated.
  * @srclen: the length of @src in bytes
  * @dst: (output) the decoded binary data
+ * @padding: whether to append '=' padding characters
+ * @variant: which base64 variant to use
  *
- * Decodes a string using base64 encoding, i.e. the "Base 64 Encoding"
- * specified by RFC 4648, including the  '='-padding.
+ * Decodes a string using the selected Base64 variant.
  *
  * This implementation hasn't been optimized for performance.
  *
  * Return: the length of the resulting decoded binary data in bytes,
- *        or -1 if the string isn't a valid base64 string.
+ *        or -1 if the string isn't a valid Base64 string.
  */
-int base64_decode(const char *src, int srclen, u8 *dst)
+int base64_decode(const char *src, int srclen, u8 *dst, bool padding, enum base64_variant variant)
 {
        u32 ac = 0;
        int bits = 0;
        int i;
        u8 *bp = dst;
+       const char *base64_table = base64_tables[variant];
 
        for (i = 0; i < srclen; i++) {
                const char *p = strchr(base64_table, src[i]);
-
-               if (src[i] == '=') {
-                       ac = (ac << 6);
-                       bits += 6;
-                       if (bits >= 8)
-                               bits -= 8;
-                       continue;
+               if (padding) {
+                       if (src[i] == '=') {
+                               ac = (ac << 6);
+                               bits += 6;
+                               if (bits >= 8)
+                                       bits -= 8;
+                               continue;
+                       }
                }
                if (p == NULL || src[i] == 0)
                        return -1;