summaryrefslogtreecommitdiffstats
path: root/lib/string_helpers.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-07-02 21:08:10 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2021-07-02 21:08:10 +0200
commit71bd9341011f626d692aabe024f099820f02c497 (patch)
treea1c27fd8f17daff36e380800c5b69769d0d9cc99 /lib/string_helpers.c
parentMerge branch 'for-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/c... (diff)
parentipc/util.c: use binary search for max_idx (diff)
downloadlinux-71bd9341011f626d692aabe024f099820f02c497.tar.xz
linux-71bd9341011f626d692aabe024f099820f02c497.zip
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton: "190 patches. Subsystems affected by this patch series: mm (hugetlb, userfaultfd, vmscan, kconfig, proc, z3fold, zbud, ras, mempolicy, memblock, migration, thp, nommu, kconfig, madvise, memory-hotplug, zswap, zsmalloc, zram, cleanups, kfence, and hmm), procfs, sysctl, misc, core-kernel, lib, lz4, checkpatch, init, kprobes, nilfs2, hfs, signals, exec, kcov, selftests, compress/decompress, and ipc" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits) ipc/util.c: use binary search for max_idx ipc/sem.c: use READ_ONCE()/WRITE_ONCE() for use_global_lock ipc: use kmalloc for msg_queue and shmid_kernel ipc sem: use kvmalloc for sem_undo allocation lib/decompressors: remove set but not used variabled 'level' selftests/vm/pkeys: exercise x86 XSAVE init state selftests/vm/pkeys: refill shadow register after implicit kernel write selftests/vm/pkeys: handle negative sys_pkey_alloc() return code selftests/vm/pkeys: fix alloc_random_pkey() to make it really, really random kcov: add __no_sanitize_coverage to fix noinstr for all architectures exec: remove checks in __register_bimfmt() x86: signal: don't do sas_ss_reset() until we are certain that sigframe won't be abandoned hfsplus: report create_date to kstat.btime hfsplus: remove unnecessary oom message nilfs2: remove redundant continue statement in a while-loop kprobes: remove duplicated strong free_insn_page in x86 and s390 init: print out unknown kernel parameters checkpatch: do not complain about positive return values starting with EPOLL checkpatch: improve the indented label test checkpatch: scripts/spdxcheck.py now requires python3 ...
Diffstat (limited to 'lib/string_helpers.c')
-rw-r--r--lib/string_helpers.c102
1 files changed, 61 insertions, 41 deletions
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 7f2d5fbaf243..5a35c7e16e96 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -452,18 +452,20 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
* The process of escaping byte buffer includes several parts. They are applied
* in the following sequence.
*
- * 1. The character is matched to the printable class, if asked, and in
- * case of match it passes through to the output.
- * 2. The character is not matched to the one from @only string and thus
+ * 1. The character is not matched to the one from @only string and thus
* must go as-is to the output.
- * 3. The character is checked if it falls into the class given by @flags.
+ * 2. The character is matched to the printable and ASCII classes, if asked,
+ * and in case of match it passes through to the output.
+ * 3. The character is matched to the printable or ASCII class, if asked,
+ * and in case of match it passes through to the output.
+ * 4. The character is checked if it falls into the class given by @flags.
* %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any
* character. Note that they actually can't go together, otherwise
* %ESCAPE_HEX will be ignored.
*
* Caller must provide valid source and destination pointers. Be aware that
* destination buffer will not be NULL-terminated, thus caller have to append
- * it if needs. The supported flags are::
+ * it if needs. The supported flags are::
*
* %ESCAPE_SPACE: (special white space, not space itself)
* '\f' - form feed
@@ -482,11 +484,27 @@ static bool escape_hex(unsigned char c, char **dst, char *end)
* %ESCAPE_ANY:
* all previous together
* %ESCAPE_NP:
- * escape only non-printable characters (checked by isprint)
+ * escape only non-printable characters, checked by isprint()
* %ESCAPE_ANY_NP:
* all previous together
* %ESCAPE_HEX:
* '\xHH' - byte with hexadecimal value HH (2 digits)
+ * %ESCAPE_NA:
+ * escape only non-ascii characters, checked by isascii()
+ * %ESCAPE_NAP:
+ * escape only non-printable or non-ascii characters
+ * %ESCAPE_APPEND:
+ * append characters from @only to be escaped by the given classes
+ *
+ * %ESCAPE_APPEND would help to pass additional characters to the escaped, when
+ * one of %ESCAPE_NP, %ESCAPE_NA, or %ESCAPE_NAP is provided.
+ *
+ * One notable caveat, the %ESCAPE_NAP, %ESCAPE_NP and %ESCAPE_NA have the
+ * higher priority than the rest of the flags (%ESCAPE_NAP is the highest).
+ * It doesn't make much sense to use either of them without %ESCAPE_OCTAL
+ * or %ESCAPE_HEX, because they cover most of the other character classes.
+ * %ESCAPE_NAP can utilize %ESCAPE_SPACE or %ESCAPE_SPECIAL in addition to
+ * the above.
*
* Return:
* The total size of the escaped output that would be generated for
@@ -500,67 +518,69 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
char *p = dst;
char *end = p + osz;
bool is_dict = only && *only;
+ bool is_append = flags & ESCAPE_APPEND;
while (isz--) {
unsigned char c = *src++;
+ bool in_dict = is_dict && strchr(only, c);
/*
* Apply rules in the following sequence:
- * - the character is printable, when @flags has
- * %ESCAPE_NP bit set
* - the @only string is supplied and does not contain a
* character under question
+ * - the character is printable and ASCII, when @flags has
+ * %ESCAPE_NAP bit set
+ * - the character is printable, when @flags has
+ * %ESCAPE_NP bit set
+ * - the character is ASCII, when @flags has
+ * %ESCAPE_NA bit set
* - the character doesn't fall into a class of symbols
* defined by given @flags
* In these cases we just pass through a character to the
* output buffer.
+ *
+ * When %ESCAPE_APPEND is passed, the characters from @only
+ * have been excluded from the %ESCAPE_NAP, %ESCAPE_NP, and
+ * %ESCAPE_NA cases.
*/
- if ((flags & ESCAPE_NP && isprint(c)) ||
- (is_dict && !strchr(only, c))) {
- /* do nothing */
- } else {
- if (flags & ESCAPE_SPACE && escape_space(c, &p, end))
- continue;
+ if (!(is_append || in_dict) && is_dict &&
+ escape_passthrough(c, &p, end))
+ continue;
- if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end))
- continue;
+ if (!(is_append && in_dict) && isascii(c) && isprint(c) &&
+ flags & ESCAPE_NAP && escape_passthrough(c, &p, end))
+ continue;
- if (flags & ESCAPE_NULL && escape_null(c, &p, end))
- continue;
+ if (!(is_append && in_dict) && isprint(c) &&
+ flags & ESCAPE_NP && escape_passthrough(c, &p, end))
+ continue;
- /* ESCAPE_OCTAL and ESCAPE_HEX always go last */
- if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end))
- continue;
+ if (!(is_append && in_dict) && isascii(c) &&
+ flags & ESCAPE_NA && escape_passthrough(c, &p, end))
+ continue;
- if (flags & ESCAPE_HEX && escape_hex(c, &p, end))
- continue;
- }
+ if (flags & ESCAPE_SPACE && escape_space(c, &p, end))
+ continue;
- escape_passthrough(c, &p, end);
- }
+ if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end))
+ continue;
- return p - dst;
-}
-EXPORT_SYMBOL(string_escape_mem);
+ if (flags & ESCAPE_NULL && escape_null(c, &p, end))
+ continue;
-int string_escape_mem_ascii(const char *src, size_t isz, char *dst,
- size_t osz)
-{
- char *p = dst;
- char *end = p + osz;
+ /* ESCAPE_OCTAL and ESCAPE_HEX always go last */
+ if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end))
+ continue;
- while (isz--) {
- unsigned char c = *src++;
+ if (flags & ESCAPE_HEX && escape_hex(c, &p, end))
+ continue;
- if (!isprint(c) || !isascii(c) || c == '"' || c == '\\')
- escape_hex(c, &p, end);
- else
- escape_passthrough(c, &p, end);
+ escape_passthrough(c, &p, end);
}
return p - dst;
}
-EXPORT_SYMBOL(string_escape_mem_ascii);
+EXPORT_SYMBOL(string_escape_mem);
/*
* Return an allocated string that has been escaped of special characters