All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Howells <dhowells@redhat.com>
To: linux-cachefs@redhat.com
Cc: dhowells@redhat.com, Trond Myklebust <trondmy@hammerspace.com>,
	Anna Schumaker <anna.schumaker@netapp.com>,
	Steve French <sfrench@samba.org>,
	Dominique Martinet <asmadeus@codewreck.org>,
	Jeff Layton <jlayton@kernel.org>,
	Matthew Wilcox <willy@infradead.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Omar Sandoval <osandov@osandov.com>,
	JeffleXu <jefflexu@linux.alibaba.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	linux-afs@lists.infradead.org, linux-nfs@vger.kernel.org,
	linux-cifs@vger.kernel.org, ceph-devel@vger.kernel.org,
	v9fs-developer@lists.sourceforge.net,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2 44/67] cachefiles: Implement key to filename encoding
Date: Thu, 09 Dec 2021 17:03:25 +0000	[thread overview]
Message-ID: <163906940529.143852.17352132319136117053.stgit@warthog.procyon.org.uk> (raw)
In-Reply-To: <163906878733.143852.5604115678965006622.stgit@warthog.procyon.org.uk>

Implement a function to encode a binary cookie key as something that can be
used as a filename.  Four options are considered:

 (1) All printable chars with no '/' characters.  Prepend a 'D' to indicate
     the encoding but otherwise use as-is.

 (2) Appears to be an array of __be32.  Encode as 'S' plus a list of
     hex-encoded 32-bit ints separated by commas.  If a number is 0, it is
     rendered as "" instead of "0".

 (3) Appears to be an array of __le32.  Encoded as (2) but with a 'T'
     encoding prefix.

 (4) Encoded as base64 with an 'E' prefix plus a second char indicating how
     much padding is involved.  A non-standard base64 encoding is used
     because '/' cannot be used in the encoded form.

If (1) is not possible, whichever of (2), (3) or (4) produces the shortest
string is selected (hex-encoding a number may be less dense than base64
encoding it).

Note that the prefix characters have to be selected from the set [DEIJST@]
lest cachefilesd remove the files because it recognise the name.

Changes
=======
ver #2:
 - Fix a short allocation that didn't allow for a string terminator[1]

Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-cachefs@redhat.com
Link: https://lore.kernel.org/r/bcefb8f2-576a-b3fc-cc29-89808ebfd7c1@linux.alibaba.com/ [1]
Link: https://lore.kernel.org/r/163819640393.215744.15212364106412961104.stgit@warthog.procyon.org.uk/ # v1
---

 fs/cachefiles/Makefile   |    1 
 fs/cachefiles/internal.h |    5 ++
 fs/cachefiles/key.c      |  138 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 144 insertions(+)
 create mode 100644 fs/cachefiles/key.c

diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile
index d67210ece9cd..6f025940a65c 100644
--- a/fs/cachefiles/Makefile
+++ b/fs/cachefiles/Makefile
@@ -7,6 +7,7 @@ cachefiles-y := \
 	cache.o \
 	daemon.o \
 	interface.o \
+	key.o \
 	main.o \
 	namei.o \
 	security.o \
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index ff378171c71d..28e386b5b1f3 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -173,6 +173,11 @@ extern struct cachefiles_object *cachefiles_grab_object(struct cachefiles_object
 extern void cachefiles_put_object(struct cachefiles_object *object,
 				  enum cachefiles_obj_ref_trace why);
 
+/*
+ * key.c
+ */
+extern bool cachefiles_cook_key(struct cachefiles_object *object);
+
 /*
  * main.c
  */
diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c
new file mode 100644
index 000000000000..bf935e25bdbe
--- /dev/null
+++ b/fs/cachefiles/key.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Key to pathname encoder
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include "internal.h"
+
+static const char cachefiles_charmap[64] =
+	"0123456789"			/* 0 - 9 */
+	"abcdefghijklmnopqrstuvwxyz"	/* 10 - 35 */
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZ"	/* 36 - 61 */
+	"_-"				/* 62 - 63 */
+	;
+
+static const char cachefiles_filecharmap[256] = {
+	/* we skip space and tab and control chars */
+	[33 ... 46] = 1,		/* '!' -> '.' */
+	/* we skip '/' as it's significant to pathwalk */
+	[48 ... 127] = 1,		/* '0' -> '~' */
+};
+
+static inline unsigned int how_many_hex_digits(unsigned int x)
+{
+	return x ? round_up(ilog2(x) + 1, 4) / 4 : 0;
+}
+
+/*
+ * turn the raw key into something cooked
+ * - the key may be up to NAME_MAX in length (including the length word)
+ *   - "base64" encode the strange keys, mapping 3 bytes of raw to four of
+ *     cooked
+ *   - need to cut the cooked key into 252 char lengths (189 raw bytes)
+ */
+bool cachefiles_cook_key(struct cachefiles_object *object)
+{
+	const u8 *key = fscache_get_key(object->cookie), *kend;
+	unsigned char ch;
+	unsigned int acc, i, n, nle, nbe, keylen = object->cookie->key_len;
+	unsigned int b64len, len, print, pad;
+	char *name, sep;
+
+	_enter(",%u,%*phN", keylen, keylen, key);
+
+	BUG_ON(keylen > NAME_MAX - 3);
+
+	print = 1;
+	for (i = 0; i < keylen; i++) {
+		ch = key[i];
+		print &= cachefiles_filecharmap[ch];
+	}
+
+	/* If the path is usable ASCII, then we render it directly */
+	if (print) {
+		len = 1 + keylen;
+		name = kmalloc(len + 1, GFP_KERNEL);
+		if (!name)
+			return false;
+
+		name[0] = 'D'; /* Data object type, string encoding */
+		memcpy(name + 1, key, keylen);
+		goto success;
+	}
+
+	/* See if it makes sense to encode it as "hex,hex,hex" for each 32-bit
+	 * chunk.  We rely on the key having been padded out to a whole number
+	 * of 32-bit words.
+	 */
+	n = round_up(keylen, 4);
+	nbe = nle = 0;
+	for (i = 0; i < n; i += 4) {
+		u32 be = be32_to_cpu(*(__be32 *)(key + i));
+		u32 le = le32_to_cpu(*(__le32 *)(key + i));
+
+		nbe += 1 + how_many_hex_digits(be);
+		nle += 1 + how_many_hex_digits(le);
+	}
+
+	b64len = DIV_ROUND_UP(keylen, 3);
+	pad = b64len * 3 - keylen;
+	b64len = 2 + b64len * 4; /* Length if we base64-encode it */
+	_debug("len=%u nbe=%u nle=%u b64=%u", keylen, nbe, nle, b64len);
+	if (nbe < b64len || nle < b64len) {
+		unsigned int nlen = min(nbe, nle) + 1;
+		name = kmalloc(nlen, GFP_KERNEL);
+		if (!name)
+			return false;
+		sep = (nbe <= nle) ? 'S' : 'T'; /* Encoding indicator */
+		len = 0;
+		for (i = 0; i < n; i += 4) {
+			u32 x;
+			if (nbe <= nle)
+				x = be32_to_cpu(*(__be32 *)(key + i));
+			else
+				x = le32_to_cpu(*(__le32 *)(key + i));
+			name[len++] = sep;
+			if (x != 0)
+				len += snprintf(name + len, nlen - len, "%x", x);
+			sep = ',';
+		}
+		goto success;
+	}
+
+	/* We need to base64-encode it */
+	name = kmalloc(b64len + 1, GFP_KERNEL);
+	if (!name)
+		return false;
+
+	name[0] = 'E';
+	name[1] = '0' + pad;
+	len = 2;
+	kend = key + keylen;
+	do {
+		acc  = *key++;
+		if (key < kend) {
+			acc |= *key++ << 8;
+			if (key < kend)
+				acc |= *key++ << 16;
+		}
+
+		name[len++] = cachefiles_charmap[acc & 63];
+		acc >>= 6;
+		name[len++] = cachefiles_charmap[acc & 63];
+		acc >>= 6;
+		name[len++] = cachefiles_charmap[acc & 63];
+		acc >>= 6;
+		name[len++] = cachefiles_charmap[acc & 63];
+	} while (key < kend);
+
+success:
+	name[len] = 0;
+	object->d_name = name;
+	object->d_name_len = len;
+	_leave(" = %s", object->d_name);
+	return true;
+}



  parent reply	other threads:[~2021-12-09 17:04 UTC|newest]

Thread overview: 88+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-09 16:53 [PATCH v2 00/67] fscache, cachefiles: Rewrite David Howells
2021-12-09 16:53 ` [PATCH v2 01/67] fscache, cachefiles: Disable configuration David Howells
2021-12-09 16:53 ` [PATCH v2 02/67] cachefiles: Delete the cachefiles driver pending rewrite David Howells
2021-12-09 16:54 ` [PATCH v2 03/67] fscache: Remove the contents of the fscache driver, " David Howells
2021-12-09 16:54 ` [PATCH v2 04/67] netfs: Display the netfs inode number in the netfs_read tracepoint David Howells
2021-12-09 16:54 ` [PATCH v2 05/67] netfs: Pass a flag to ->prepare_write() to say if there's no alloc'd space David Howells
2021-12-09 16:54 ` [PATCH v2 06/67] fscache: Introduce new driver David Howells
2021-12-09 16:54 ` [PATCH v2 07/67] fscache: Implement a hash function David Howells
2021-12-09 17:12   ` Linus Torvalds
2021-12-09 21:57   ` David Howells
2021-12-09 22:07     ` Linus Torvalds
2021-12-10 14:35     ` David Howells
2021-12-10 14:41     ` David Howells
2021-12-10 17:33       ` Linus Torvalds
2021-12-09 16:54 ` [PATCH v2 08/67] fscache: Implement cache registration David Howells
2021-12-14 18:36   ` Jeff Layton
2021-12-09 16:55 ` [PATCH v2 09/67] fscache: Implement volume registration David Howells
2021-12-09 17:32   ` Linus Torvalds
2021-12-14 18:52   ` Jeff Layton
2021-12-14 19:57   ` David Howells
2021-12-09 16:55 ` [PATCH v2 10/67] fscache: Implement cookie registration David Howells
2021-12-09 17:21   ` Linus Torvalds
2021-12-09 16:55 ` [PATCH v2 11/67] fscache: Implement cache-level access helpers David Howells
2021-12-09 16:55 ` [PATCH v2 12/67] fscache: Implement volume-level " David Howells
2021-12-09 16:55 ` [PATCH v2 13/67] fscache: Implement cookie-level " David Howells
2021-12-09 16:56 ` [PATCH v2 14/67] fscache: Implement functions add/remove a cache David Howells
2021-12-09 16:56 ` [PATCH v2 15/67] fscache: Provide and use cache methods to lookup/create/free a volume David Howells
2021-12-09 16:56 ` [PATCH v2 16/67] fscache: Add a function for a cache backend to note an I/O error David Howells
2021-12-09 16:57 ` [PATCH v2 17/67] fscache: Implement simple cookie state machine David Howells
2021-12-09 16:57 ` [PATCH v2 18/67] fscache: Implement cookie user counting and resource pinning David Howells
2021-12-09 16:58 ` [PATCH v2 19/67] fscache: Implement cookie invalidation David Howells
2021-12-09 16:58 ` [PATCH v2 20/67] fscache: Provide a means to begin an operation David Howells
2021-12-09 16:58 ` [PATCH v2 21/67] fscache: Count data storage objects in a cache David Howells
2021-12-09 16:58 ` [PATCH v2 22/67] fscache: Provide read/write stat counters for the cache David Howells
2021-12-09 16:58 ` [PATCH v2 23/67] fscache: Provide a function to let the netfs update its coherency data David Howells
2021-12-09 16:59 ` [PATCH v2 24/67] netfs: Pass more information on how to deal with a hole in the cache David Howells
2021-12-09 16:59 ` [PATCH v2 25/67] fscache: Implement raw I/O interface David Howells
2021-12-09 16:59 ` [PATCH v2 26/67] fscache: Implement higher-level write " David Howells
2021-12-09 16:59 ` [PATCH v2 27/67] vfs, fscache: Implement pinning of cache usage for writeback David Howells
2021-12-09 17:00 ` [PATCH v2 28/67] fscache: Provide a function to note the release of a page David Howells
2021-12-09 17:00 ` [PATCH v2 29/67] fscache: Provide a function to resize a cookie David Howells
2021-12-09 17:00 ` [PATCH v2 30/67] cachefiles: Introduce rewritten driver David Howells
2021-12-09 17:00 ` [PATCH v2 31/67] cachefiles: Define structs David Howells
2021-12-09 17:00 ` [PATCH v2 32/67] cachefiles: Add some error injection support David Howells
2021-12-09 17:01 ` [PATCH v2 33/67] cachefiles: Add a couple of tracepoints for logging errors David Howells
2021-12-09 17:01 ` [PATCH v2 34/67] cachefiles: Add cache error reporting macro David Howells
2021-12-09 17:01 ` [PATCH v2 35/67] cachefiles: Add security derivation David Howells
2021-12-09 17:01 ` [PATCH v2 36/67] cachefiles: Register a miscdev and parse commands over it David Howells
2021-12-09 17:01 ` [PATCH v2 37/67] cachefiles: Provide a function to check how much space there is David Howells
2021-12-09 17:01 ` [PATCH v2 38/67] vfs, cachefiles: Mark a backing file in use with an inode flag David Howells
2021-12-09 17:02 ` [PATCH v2 39/67] cachefiles: Implement a function to get/create a directory in the cache David Howells
2021-12-09 17:02 ` [PATCH v2 40/67] cachefiles: Implement cache registration and withdrawal David Howells
2021-12-09 17:02 ` [PATCH v2 41/67] cachefiles: Implement volume support David Howells
2021-12-09 17:03 ` [PATCH v2 42/67] cachefiles: Add tracepoints for calls to the VFS David Howells
2021-12-09 17:03 ` [PATCH v2 43/67] cachefiles: Implement object lifecycle funcs David Howells
2021-12-09 17:03 ` David Howells [this message]
2021-12-09 17:03 ` [PATCH v2 45/67] cachefiles: Implement metadata/coherency data storage in xattrs David Howells
2021-12-09 17:03 ` [PATCH v2 46/67] cachefiles: Mark a backing file in use with an inode flag David Howells
2021-12-09 17:04 ` [PATCH v2 47/67] cachefiles: Implement culling daemon commands David Howells
2021-12-09 17:04 ` [PATCH v2 48/67] cachefiles: Implement backing file wrangling David Howells
2021-12-09 17:05 ` [PATCH v2 49/67] cachefiles: Implement begin and end I/O operation David Howells
2021-12-09 17:05 ` [PATCH v2 50/67] cachefiles: Implement cookie resize for truncate David Howells
2021-12-09 17:05 ` [PATCH v2 51/67] cachefiles: Implement the I/O routines David Howells
2021-12-09 17:06 ` [PATCH v2 52/67] cachefiles: Allow cachefiles to actually function David Howells
2021-12-09 17:06 ` [PATCH v2 53/67] fscache, cachefiles: Display stats of no-space events David Howells
2021-12-09 17:06 ` [PATCH v2 54/67] fscache, cachefiles: Display stat of culling events David Howells
2021-12-09 17:07 ` [PATCH v2 55/67] afs: Handle len being extending over page end in write_begin/write_end David Howells
2021-12-09 17:08 ` [PATCH v2 56/67] afs: Fix afs_write_end() to handle len > page size David Howells
2021-12-09 17:08 ` [PATCH v2 57/67] afs: Convert afs to use the new fscache API David Howells
2021-12-09 17:08 ` [PATCH v2 58/67] afs: Copy local writes to the cache when writing to the server David Howells
2021-12-09 17:08 ` [PATCH v2 59/67] afs: Skip truncation on the server of data we haven't written yet David Howells
2021-12-09 17:09 ` [PATCH v2 60/67] 9p: Use fscache indexing rewrite and reenable caching David Howells
2021-12-09 17:09 ` [PATCH v2 61/67] 9p: Copy local writes to the cache when writing to the server David Howells
2021-12-09 17:09 ` [PATCH v2 62/67] nfs: Convert to new fscache volume/cookie API David Howells
2021-12-11 13:22   ` David Wysochanski
2021-12-11 13:37   ` David Howells
2021-12-09 17:10 ` [PATCH v2 63/67] nfs: Implement cache I/O by accessing the cache directly David Howells
2021-12-09 17:10 ` [PATCH v2 64/67] cifs: Support fscache indexing rewrite (untested) David Howells
2021-12-09 17:10 ` [PATCH v2 65/67] ceph: conversion to new fscache API David Howells
2021-12-09 17:10 ` [PATCH v2 66/67] ceph: add fscache writeback support David Howells
2021-12-09 17:11 ` [PATCH v2 67/67] fscache: Rewrite documentation David Howells
2021-12-10 18:38 ` [PATCH v2 00/67] fscache, cachefiles: Rewrite David Wysochanski
2021-12-11 13:44   ` David Wysochanski
2021-12-13 15:41   ` [PATCH] fscache: Need to go round again after processing LRU_DISCARDING state David Howells
2021-12-13 21:05     ` David Wysochanski
2021-12-13 16:22   ` David Howells
2021-12-13 20:03   ` David Howells
2021-12-13 22:39   ` David Howells

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=163906940529.143852.17352132319136117053.stgit@warthog.procyon.org.uk \
    --to=dhowells@redhat.com \
    --cc=anna.schumaker@netapp.com \
    --cc=asmadeus@codewreck.org \
    --cc=ceph-devel@vger.kernel.org \
    --cc=jefflexu@linux.alibaba.com \
    --cc=jlayton@kernel.org \
    --cc=linux-afs@lists.infradead.org \
    --cc=linux-cachefs@redhat.com \
    --cc=linux-cifs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=osandov@osandov.com \
    --cc=sfrench@samba.org \
    --cc=torvalds@linux-foundation.org \
    --cc=trondmy@hammerspace.com \
    --cc=v9fs-developer@lists.sourceforge.net \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.