linux/lib/test_printf.c

803 lines
19 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Test cases for printf facility.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/printk.h>
#include <linux/random.h>
#include <linux/rtc.h>
#include <linux/slab.h>
#include <linux/sprintf.h>
#include <linux/string.h>
#include <linux/bitmap.h>
#include <linux/dcache.h>
#include <linux/socket.h>
#include <linux/in.h>
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/property.h>
#include "../tools/testing/selftests/kselftest_module.h"
#define BUF_SIZE 256
#define PAD_SIZE 16
#define FILL_CHAR '$'
lib/test_printf.c: fix clang -Wformat warnings see warnings: | lib/test_printf.c:157:52: error: format specifies type 'unsigned char' | but the argument has type 'int' [-Werror,-Wformat] test("0|1|1|128|255", | "%hhu|%hhu|%hhu|%hhu|%hhu", 0, 1, 257, 128, -1); - | lib/test_printf.c:158:55: error: format specifies type 'char' but the | argument has type 'int' [-Werror,-Wformat] test("0|1|1|-128|-1", | "%hhd|%hhd|%hhd|%hhd|%hhd", 0, 1, 257, 128, -1); - | lib/test_printf.c:159:41: error: format specifies type 'unsigned short' | but the argument has type 'int' [-Werror,-Wformat] | test("2015122420151225", "%ho%ho%#ho", 1037, 5282, -11627); There's an ongoing movement to eventually enable the -Wformat flag for clang. Previous patches have targeted incorrect usage of format specifiers. In this case, however, the "incorrect" format specifiers are intrinsically part of the test cases. Hence, fixing them would be misaligned with their intended purpose. My proposed fix is to simply disable the warnings so that one day a clean build of the kernel with clang (and -Wformat enabled) would be possible. It would also keep us in the green for alot of the CI bots. Link: https://github.com/ClangBuiltLinux/linux/issues/378 Suggested-by: Nathan Chancellor <nathan@kernel.org> Suggested-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Justin Stitt <justinstitt@google.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20220718230626.1029318-1-justinstitt@google.com
2022-07-18 23:06:26 +00:00
#define NOWARN(option, comment, block) \
__diag_push(); \
__diag_ignore_all(#option, comment); \
block \
__diag_pop();
KSTM_MODULE_GLOBALS();
static char *test_buffer __initdata;
static char *alloced_buffer __initdata;
static int __printf(4, 0) __init
do_test(int bufsize, const char *expect, int elen,
const char *fmt, va_list ap)
{
va_list aq;
int ret, written;
total_tests++;
memset(alloced_buffer, FILL_CHAR, BUF_SIZE + 2*PAD_SIZE);
va_copy(aq, ap);
ret = vsnprintf(test_buffer, bufsize, fmt, aq);
va_end(aq);
if (ret != elen) {
pr_warn("vsnprintf(buf, %d, \"%s\", ...) returned %d, expected %d\n",
bufsize, fmt, ret, elen);
return 1;
}
if (memchr_inv(alloced_buffer, FILL_CHAR, PAD_SIZE)) {
pr_warn("vsnprintf(buf, %d, \"%s\", ...) wrote before buffer\n", bufsize, fmt);
return 1;
}
if (!bufsize) {
if (memchr_inv(test_buffer, FILL_CHAR, BUF_SIZE + PAD_SIZE)) {
pr_warn("vsnprintf(buf, 0, \"%s\", ...) wrote to buffer\n",
fmt);
return 1;
}
return 0;
}
written = min(bufsize-1, elen);
if (test_buffer[written]) {
pr_warn("vsnprintf(buf, %d, \"%s\", ...) did not nul-terminate buffer\n",
bufsize, fmt);
return 1;
}
lib/test_printf.c: split write-beyond-buffer check in two Before each invocation of vsnprintf(), do_test() memsets the entire allocated buffer to a sentinel value. That buffer includes leading and trailing padding which is never included in the buffer area handed to vsnprintf (spaces merely for clarity): pad test_buffer pad **** **************** **** Then vsnprintf() is invoked with a bufsize argument <= BUF_SIZE. Suppose bufsize=10, then we'd have e.g. |pad | test_buffer |pad | **** pizza0 **** ****** **** A B C D E where vsnprintf() was given the area from B to D. It is obviously a bug for vsnprintf to touch anything between A and B or between D and E. The former is checked for as one would expect. But for the latter, we are actually a little stricter in that we check the area between C and E. Split that check in two, providing a clearer error message in case it was a genuine buffer overrun and not merely a write within the provided buffer, but after the end of the generated string. So far, no part of the vsnprintf() implementation has had any use for using the whole buffer as scratch space, but it's not unreasonable to allow that, as long as the result is properly nul-terminated and the return value is the right one. However, it is somewhat unusual, and most %<something> won't need this, so keep the [C,D] check, but make it easy for a later patch to make that part opt-out for certain tests. Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Tested-by: Jia He <justin.he@arm.com> Signed-off-by: Jia He <justin.he@arm.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210615154952.2744-4-justin.he@arm.com
2021-06-15 15:49:51 +00:00
if (memchr_inv(test_buffer + written + 1, FILL_CHAR, bufsize - (written + 1))) {
pr_warn("vsnprintf(buf, %d, \"%s\", ...) wrote beyond the nul-terminator\n",
bufsize, fmt);
return 1;
}
lib/test_printf.c: split write-beyond-buffer check in two Before each invocation of vsnprintf(), do_test() memsets the entire allocated buffer to a sentinel value. That buffer includes leading and trailing padding which is never included in the buffer area handed to vsnprintf (spaces merely for clarity): pad test_buffer pad **** **************** **** Then vsnprintf() is invoked with a bufsize argument <= BUF_SIZE. Suppose bufsize=10, then we'd have e.g. |pad | test_buffer |pad | **** pizza0 **** ****** **** A B C D E where vsnprintf() was given the area from B to D. It is obviously a bug for vsnprintf to touch anything between A and B or between D and E. The former is checked for as one would expect. But for the latter, we are actually a little stricter in that we check the area between C and E. Split that check in two, providing a clearer error message in case it was a genuine buffer overrun and not merely a write within the provided buffer, but after the end of the generated string. So far, no part of the vsnprintf() implementation has had any use for using the whole buffer as scratch space, but it's not unreasonable to allow that, as long as the result is properly nul-terminated and the return value is the right one. However, it is somewhat unusual, and most %<something> won't need this, so keep the [C,D] check, but make it easy for a later patch to make that part opt-out for certain tests. Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Tested-by: Jia He <justin.he@arm.com> Signed-off-by: Jia He <justin.he@arm.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210615154952.2744-4-justin.he@arm.com
2021-06-15 15:49:51 +00:00
if (memchr_inv(test_buffer + bufsize, FILL_CHAR, BUF_SIZE + PAD_SIZE - bufsize)) {
pr_warn("vsnprintf(buf, %d, \"%s\", ...) wrote beyond buffer\n", bufsize, fmt);
return 1;
}
if (memcmp(test_buffer, expect, written)) {
pr_warn("vsnprintf(buf, %d, \"%s\", ...) wrote '%s', expected '%.*s'\n",
bufsize, fmt, test_buffer, written, expect);
return 1;
}
return 0;
}
static void __printf(3, 4) __init
__test(const char *expect, int elen, const char *fmt, ...)
{
va_list ap;
int rand;
char *p;
if (elen >= BUF_SIZE) {
pr_err("error in test suite: expected output length %d too long. Format was '%s'.\n",
elen, fmt);
failed_tests++;
return;
}
va_start(ap, fmt);
/*
* Every fmt+args is subjected to four tests: Three where we
* tell vsnprintf varying buffer sizes (plenty, not quite
* enough and 0), and then we also test that kvasprintf would
* be able to print it as expected.
*/
failed_tests += do_test(BUF_SIZE, expect, elen, fmt, ap);
rand = get_random_u32_inclusive(1, elen + 1);
/* Since elen < BUF_SIZE, we have 1 <= rand <= BUF_SIZE. */
failed_tests += do_test(rand, expect, elen, fmt, ap);
failed_tests += do_test(0, expect, elen, fmt, ap);
p = kvasprintf(GFP_KERNEL, fmt, ap);
if (p) {
total_tests++;
if (memcmp(p, expect, elen+1)) {
pr_warn("kvasprintf(..., \"%s\", ...) returned '%s', expected '%s'\n",
fmt, p, expect);
failed_tests++;
}
kfree(p);
}
va_end(ap);
}
#define test(expect, fmt, ...) \
__test(expect, strlen(expect), fmt, ##__VA_ARGS__)
static void __init
test_basic(void)
{
/* Work around annoying "warning: zero-length gnu_printf format string". */
char nul = '\0';
test("", &nul);
test("100%", "100%%");
test("xxx%yyy", "xxx%cyyy", '%');
__test("xxx\0yyy", 7, "xxx%cyyy", '\0');
}
static void __init
test_number(void)
{
test("0x1234abcd ", "%#-12x", 0x1234abcd);
test(" 0x1234abcd", "%#12x", 0x1234abcd);
test("0|001| 12|+123| 1234|-123|-1234", "%d|%03d|%3d|%+d|% d|%+d|% d", 0, 1, 12, 123, 1234, -123, -1234);
lib/test_printf.c: fix clang -Wformat warnings see warnings: | lib/test_printf.c:157:52: error: format specifies type 'unsigned char' | but the argument has type 'int' [-Werror,-Wformat] test("0|1|1|128|255", | "%hhu|%hhu|%hhu|%hhu|%hhu", 0, 1, 257, 128, -1); - | lib/test_printf.c:158:55: error: format specifies type 'char' but the | argument has type 'int' [-Werror,-Wformat] test("0|1|1|-128|-1", | "%hhd|%hhd|%hhd|%hhd|%hhd", 0, 1, 257, 128, -1); - | lib/test_printf.c:159:41: error: format specifies type 'unsigned short' | but the argument has type 'int' [-Werror,-Wformat] | test("2015122420151225", "%ho%ho%#ho", 1037, 5282, -11627); There's an ongoing movement to eventually enable the -Wformat flag for clang. Previous patches have targeted incorrect usage of format specifiers. In this case, however, the "incorrect" format specifiers are intrinsically part of the test cases. Hence, fixing them would be misaligned with their intended purpose. My proposed fix is to simply disable the warnings so that one day a clean build of the kernel with clang (and -Wformat enabled) would be possible. It would also keep us in the green for alot of the CI bots. Link: https://github.com/ClangBuiltLinux/linux/issues/378 Suggested-by: Nathan Chancellor <nathan@kernel.org> Suggested-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Justin Stitt <justinstitt@google.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20220718230626.1029318-1-justinstitt@google.com
2022-07-18 23:06:26 +00:00
NOWARN(-Wformat, "Intentionally test narrowing conversion specifiers.", {
test("0|1|1|128|255", "%hhu|%hhu|%hhu|%hhu|%hhu", 0, 1, 257, 128, -1);
test("0|1|1|-128|-1", "%hhd|%hhd|%hhd|%hhd|%hhd", 0, 1, 257, 128, -1);
test("2015122420151225", "%ho%ho%#ho", 1037, 5282, -11627);
})
/*
* POSIX/C99: »The result of converting zero with an explicit
* precision of zero shall be no characters.« Hence the output
* from the below test should really be "00|0||| ". However,
* the kernel's printf also produces a single 0 in that
* case. This test case simply documents the current
* behaviour.
*/
test("00|0|0|0|0", "%.2d|%.1d|%.0d|%.*d|%1.0d", 0, 0, 0, 0, 0, 0);
}
static void __init
test_string(void)
{
test("", "%s%.0s", "", "123");
test("ABCD|abc|123", "%s|%.3s|%.*s", "ABCD", "abcdef", 3, "123456");
test("1 | 2|3 | 4|5 ", "%-3s|%3s|%-*s|%*s|%*s", "1", "2", 3, "3", 3, "4", -3, "5");
test("1234 ", "%-10.4s", "123456");
test(" 1234", "%10.4s", "123456");
/*
* POSIX and C99 say that a negative precision (which is only
* possible to pass via a * argument) should be treated as if
* the precision wasn't present, and that if the precision is
* omitted (as in %.s), the precision should be taken to be
* 0. However, the kernel's printf behave exactly opposite,
* treating a negative precision as 0 and treating an omitted
* precision specifier as if no precision was given.
*
* These test cases document the current behaviour; should
* anyone ever feel the need to follow the standards more
* closely, this can be revisited.
*/
test(" ", "%4.*s", -5, "123456");
test("123456", "%.s", "123456");
test("a||", "%.s|%.0s|%.*s", "a", "b", 0, "c");
test("a | | ", "%-3.s|%-3.0s|%-3.*s", "a", "b", 0, "c");
}
#define PLAIN_BUF_SIZE 64 /* leave some space so we don't oops */
#if BITS_PER_LONG == 64
#define PTR_WIDTH 16
#define PTR ((void *)0xffff0123456789abUL)
#define PTR_STR "ffff0123456789ab"
#define PTR_VAL_NO_CRNG "(____ptrval____)"
#define ZEROS "00000000" /* hex 32 zero bits */
vsprintf: don't obfuscate NULL and error pointers I don't see what security concern is addressed by obfuscating NULL and IS_ERR() error pointers, printed with %p/%pK. Given the number of sites where %p is used (over 10000) and the fact that NULL pointers aren't uncommon, it probably wouldn't take long for an attacker to find the hash that corresponds to 0. Although harder, the same goes for most common error values, such as -1, -2, -11, -14, etc. The NULL part actually fixes a regression: NULL pointers weren't obfuscated until commit 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") which went into 5.2. I'm tacking the IS_ERR() part on here because error pointers won't leak kernel addresses and printing them as pointers shouldn't be any different from e.g. %d with PTR_ERR_OR_ZERO(). Obfuscating them just makes debugging based on existing pr_debug and friends excruciating. Note that the "always print 0's for %pK when kptr_restrict == 2" behaviour which goes way back is left as is. Example output with the patch applied: ptr error-ptr NULL %p: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %pK, kptr = 0: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %px: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 1: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 2: 0000000000000000 0000000000000000 0000000000000000 Fixes: 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-05-19 11:26:57 +00:00
#define ONES "ffffffff" /* hex 32 one bits */
static int __init
plain_format(void)
{
char buf[PLAIN_BUF_SIZE];
int nchars;
nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR);
if (nchars != PTR_WIDTH)
return -1;
if (strncmp(buf, PTR_VAL_NO_CRNG, PTR_WIDTH) == 0) {
pr_warn("crng possibly not yet initialized. plain 'p' buffer contains \"%s\"",
PTR_VAL_NO_CRNG);
return 0;
}
if (strncmp(buf, ZEROS, strlen(ZEROS)) != 0)
return -1;
return 0;
}
#else
#define PTR_WIDTH 8
#define PTR ((void *)0x456789ab)
#define PTR_STR "456789ab"
#define PTR_VAL_NO_CRNG "(ptrval)"
vsprintf: Prevent crash when dereferencing invalid pointers We already prevent crash when dereferencing some obviously broken pointers. But the handling is not consistent. Sometimes we print "(null)" only for pure NULL pointer, sometimes for pointers in the first page and sometimes also for pointers in the last page (error codes). Note that printk() call this code under logbuf_lock. Any recursive printks are redirected to the printk_safe implementation and the messages are stored into per-CPU buffers. These buffers might be eventually flushed in printk_safe_flush_on_panic() but it is not guaranteed. This patch adds a check using probe_kernel_read(). It is not a full-proof test. But it should help to see the error message in 99% situations where the kernel would silently crash otherwise. Also it makes the error handling unified for "%s" and the many %p* specifiers that need to read the data from a given address. We print: + (null) when accessing data on pure pure NULL address + (efault) when accessing data on an invalid address It does not affect the %p* specifiers that just print the given address in some form, namely %pF, %pf, %pS, %ps, %pB, %pK, %px, and plain %p. Note that we print (efault) from security reasons. In fact, the real address can be seen only by %px or eventually %pK. Link: http://lkml.kernel.org/r/20190417115350.20479-9-pmladek@suse.com To: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Tobin C . Harding" <me@tobin.cc> Cc: Joe Perches <joe@perches.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-04-17 11:53:48 +00:00
#define ZEROS ""
vsprintf: don't obfuscate NULL and error pointers I don't see what security concern is addressed by obfuscating NULL and IS_ERR() error pointers, printed with %p/%pK. Given the number of sites where %p is used (over 10000) and the fact that NULL pointers aren't uncommon, it probably wouldn't take long for an attacker to find the hash that corresponds to 0. Although harder, the same goes for most common error values, such as -1, -2, -11, -14, etc. The NULL part actually fixes a regression: NULL pointers weren't obfuscated until commit 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") which went into 5.2. I'm tacking the IS_ERR() part on here because error pointers won't leak kernel addresses and printing them as pointers shouldn't be any different from e.g. %d with PTR_ERR_OR_ZERO(). Obfuscating them just makes debugging based on existing pr_debug and friends excruciating. Note that the "always print 0's for %pK when kptr_restrict == 2" behaviour which goes way back is left as is. Example output with the patch applied: ptr error-ptr NULL %p: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %pK, kptr = 0: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %px: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 1: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 2: 0000000000000000 0000000000000000 0000000000000000 Fixes: 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-05-19 11:26:57 +00:00
#define ONES ""
static int __init
plain_format(void)
{
/* Format is implicitly tested for 32 bit machines by plain_hash() */
return 0;
}
#endif /* BITS_PER_LONG == 64 */
static int __init
plain_hash_to_buffer(const void *p, char *buf, size_t len)
{
int nchars;
nchars = snprintf(buf, len, "%p", p);
if (nchars != PTR_WIDTH)
return -1;
if (strncmp(buf, PTR_VAL_NO_CRNG, PTR_WIDTH) == 0) {
pr_warn("crng possibly not yet initialized. plain 'p' buffer contains \"%s\"",
PTR_VAL_NO_CRNG);
return 0;
}
return 0;
}
static int __init
plain_hash(void)
{
char buf[PLAIN_BUF_SIZE];
int ret;
ret = plain_hash_to_buffer(PTR, buf, PLAIN_BUF_SIZE);
if (ret)
return ret;
if (strncmp(buf, PTR_STR, PTR_WIDTH) == 0)
return -1;
return 0;
}
/*
* We can't use test() to test %p because we don't know what output to expect
* after an address is hashed.
*/
static void __init
plain(void)
{
int err;
if (no_hash_pointers) {
pr_warn("skipping plain 'p' tests");
skipped_tests += 2;
return;
}
err = plain_hash();
if (err) {
pr_warn("plain 'p' does not appear to be hashed\n");
failed_tests++;
return;
}
err = plain_format();
if (err) {
pr_warn("hashing plain 'p' has unexpected format\n");
failed_tests++;
}
}
static void __init
test_hashed(const char *fmt, const void *p)
{
char buf[PLAIN_BUF_SIZE];
int ret;
/*
* No need to increase failed test counter since this is assumed
* to be called after plain().
*/
ret = plain_hash_to_buffer(p, buf, PLAIN_BUF_SIZE);
if (ret)
return;
test(buf, fmt, p);
}
vsprintf: don't obfuscate NULL and error pointers I don't see what security concern is addressed by obfuscating NULL and IS_ERR() error pointers, printed with %p/%pK. Given the number of sites where %p is used (over 10000) and the fact that NULL pointers aren't uncommon, it probably wouldn't take long for an attacker to find the hash that corresponds to 0. Although harder, the same goes for most common error values, such as -1, -2, -11, -14, etc. The NULL part actually fixes a regression: NULL pointers weren't obfuscated until commit 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") which went into 5.2. I'm tacking the IS_ERR() part on here because error pointers won't leak kernel addresses and printing them as pointers shouldn't be any different from e.g. %d with PTR_ERR_OR_ZERO(). Obfuscating them just makes debugging based on existing pr_debug and friends excruciating. Note that the "always print 0's for %pK when kptr_restrict == 2" behaviour which goes way back is left as is. Example output with the patch applied: ptr error-ptr NULL %p: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %pK, kptr = 0: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %px: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 1: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 2: 0000000000000000 0000000000000000 0000000000000000 Fixes: 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-05-19 11:26:57 +00:00
/*
* NULL pointers aren't hashed.
*/
vsprintf: Prevent crash when dereferencing invalid pointers We already prevent crash when dereferencing some obviously broken pointers. But the handling is not consistent. Sometimes we print "(null)" only for pure NULL pointer, sometimes for pointers in the first page and sometimes also for pointers in the last page (error codes). Note that printk() call this code under logbuf_lock. Any recursive printks are redirected to the printk_safe implementation and the messages are stored into per-CPU buffers. These buffers might be eventually flushed in printk_safe_flush_on_panic() but it is not guaranteed. This patch adds a check using probe_kernel_read(). It is not a full-proof test. But it should help to see the error message in 99% situations where the kernel would silently crash otherwise. Also it makes the error handling unified for "%s" and the many %p* specifiers that need to read the data from a given address. We print: + (null) when accessing data on pure pure NULL address + (efault) when accessing data on an invalid address It does not affect the %p* specifiers that just print the given address in some form, namely %pF, %pf, %pS, %ps, %pB, %pK, %px, and plain %p. Note that we print (efault) from security reasons. In fact, the real address can be seen only by %px or eventually %pK. Link: http://lkml.kernel.org/r/20190417115350.20479-9-pmladek@suse.com To: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Tobin C . Harding" <me@tobin.cc> Cc: Joe Perches <joe@perches.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-04-17 11:53:48 +00:00
static void __init
null_pointer(void)
{
vsprintf: don't obfuscate NULL and error pointers I don't see what security concern is addressed by obfuscating NULL and IS_ERR() error pointers, printed with %p/%pK. Given the number of sites where %p is used (over 10000) and the fact that NULL pointers aren't uncommon, it probably wouldn't take long for an attacker to find the hash that corresponds to 0. Although harder, the same goes for most common error values, such as -1, -2, -11, -14, etc. The NULL part actually fixes a regression: NULL pointers weren't obfuscated until commit 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") which went into 5.2. I'm tacking the IS_ERR() part on here because error pointers won't leak kernel addresses and printing them as pointers shouldn't be any different from e.g. %d with PTR_ERR_OR_ZERO(). Obfuscating them just makes debugging based on existing pr_debug and friends excruciating. Note that the "always print 0's for %pK when kptr_restrict == 2" behaviour which goes way back is left as is. Example output with the patch applied: ptr error-ptr NULL %p: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %pK, kptr = 0: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %px: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 1: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 2: 0000000000000000 0000000000000000 0000000000000000 Fixes: 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-05-19 11:26:57 +00:00
test(ZEROS "00000000", "%p", NULL);
vsprintf: Prevent crash when dereferencing invalid pointers We already prevent crash when dereferencing some obviously broken pointers. But the handling is not consistent. Sometimes we print "(null)" only for pure NULL pointer, sometimes for pointers in the first page and sometimes also for pointers in the last page (error codes). Note that printk() call this code under logbuf_lock. Any recursive printks are redirected to the printk_safe implementation and the messages are stored into per-CPU buffers. These buffers might be eventually flushed in printk_safe_flush_on_panic() but it is not guaranteed. This patch adds a check using probe_kernel_read(). It is not a full-proof test. But it should help to see the error message in 99% situations where the kernel would silently crash otherwise. Also it makes the error handling unified for "%s" and the many %p* specifiers that need to read the data from a given address. We print: + (null) when accessing data on pure pure NULL address + (efault) when accessing data on an invalid address It does not affect the %p* specifiers that just print the given address in some form, namely %pF, %pf, %pS, %ps, %pB, %pK, %px, and plain %p. Note that we print (efault) from security reasons. In fact, the real address can be seen only by %px or eventually %pK. Link: http://lkml.kernel.org/r/20190417115350.20479-9-pmladek@suse.com To: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Tobin C . Harding" <me@tobin.cc> Cc: Joe Perches <joe@perches.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-04-17 11:53:48 +00:00
test(ZEROS "00000000", "%px", NULL);
test("(null)", "%pE", NULL);
}
vsprintf: don't obfuscate NULL and error pointers I don't see what security concern is addressed by obfuscating NULL and IS_ERR() error pointers, printed with %p/%pK. Given the number of sites where %p is used (over 10000) and the fact that NULL pointers aren't uncommon, it probably wouldn't take long for an attacker to find the hash that corresponds to 0. Although harder, the same goes for most common error values, such as -1, -2, -11, -14, etc. The NULL part actually fixes a regression: NULL pointers weren't obfuscated until commit 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") which went into 5.2. I'm tacking the IS_ERR() part on here because error pointers won't leak kernel addresses and printing them as pointers shouldn't be any different from e.g. %d with PTR_ERR_OR_ZERO(). Obfuscating them just makes debugging based on existing pr_debug and friends excruciating. Note that the "always print 0's for %pK when kptr_restrict == 2" behaviour which goes way back is left as is. Example output with the patch applied: ptr error-ptr NULL %p: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %pK, kptr = 0: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %px: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 1: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 2: 0000000000000000 0000000000000000 0000000000000000 Fixes: 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-05-19 11:26:57 +00:00
/*
* Error pointers aren't hashed.
*/
static void __init
error_pointer(void)
{
test(ONES "fffffff5", "%p", ERR_PTR(-11));
test(ONES "fffffff5", "%px", ERR_PTR(-11));
test("(efault)", "%pE", ERR_PTR(-11));
}
vsprintf: Prevent crash when dereferencing invalid pointers We already prevent crash when dereferencing some obviously broken pointers. But the handling is not consistent. Sometimes we print "(null)" only for pure NULL pointer, sometimes for pointers in the first page and sometimes also for pointers in the last page (error codes). Note that printk() call this code under logbuf_lock. Any recursive printks are redirected to the printk_safe implementation and the messages are stored into per-CPU buffers. These buffers might be eventually flushed in printk_safe_flush_on_panic() but it is not guaranteed. This patch adds a check using probe_kernel_read(). It is not a full-proof test. But it should help to see the error message in 99% situations where the kernel would silently crash otherwise. Also it makes the error handling unified for "%s" and the many %p* specifiers that need to read the data from a given address. We print: + (null) when accessing data on pure pure NULL address + (efault) when accessing data on an invalid address It does not affect the %p* specifiers that just print the given address in some form, namely %pF, %pf, %pS, %ps, %pB, %pK, %px, and plain %p. Note that we print (efault) from security reasons. In fact, the real address can be seen only by %px or eventually %pK. Link: http://lkml.kernel.org/r/20190417115350.20479-9-pmladek@suse.com To: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Tobin C . Harding" <me@tobin.cc> Cc: Joe Perches <joe@perches.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-04-17 11:53:48 +00:00
#define PTR_INVALID ((void *)0x000000ab)
static void __init
invalid_pointer(void)
{
test_hashed("%p", PTR_INVALID);
test(ZEROS "000000ab", "%px", PTR_INVALID);
test("(efault)", "%pE", PTR_INVALID);
}
static void __init
symbol_ptr(void)
{
}
static void __init
kernel_ptr(void)
{
/* We can't test this without access to kptr_restrict. */
}
static void __init
struct_resource(void)
{
}
static void __init
addr(void)
{
}
static void __init
escaped_str(void)
{
}
static void __init
hex_string(void)
{
const char buf[3] = {0xc0, 0xff, 0xee};
test("c0 ff ee|c0:ff:ee|c0-ff-ee|c0ffee",
"%3ph|%3phC|%3phD|%3phN", buf, buf, buf, buf);
test("c0 ff ee|c0:ff:ee|c0-ff-ee|c0ffee",
"%*ph|%*phC|%*phD|%*phN", 3, buf, 3, buf, 3, buf, 3, buf);
}
static void __init
mac(void)
{
const u8 addr[6] = {0x2d, 0x48, 0xd6, 0xfc, 0x7a, 0x05};
test("2d:48:d6:fc:7a:05", "%pM", addr);
test("05:7a:fc:d6:48:2d", "%pMR", addr);
test("2d-48-d6-fc-7a-05", "%pMF", addr);
test("2d48d6fc7a05", "%pm", addr);
test("057afcd6482d", "%pmR", addr);
}
static void __init
ip4(void)
{
struct sockaddr_in sa;
sa.sin_family = AF_INET;
sa.sin_port = cpu_to_be16(12345);
sa.sin_addr.s_addr = cpu_to_be32(0x7f000001);
test("127.000.000.001|127.0.0.1", "%pi4|%pI4", &sa.sin_addr, &sa.sin_addr);
test("127.000.000.001|127.0.0.1", "%piS|%pIS", &sa, &sa);
sa.sin_addr.s_addr = cpu_to_be32(0x01020304);
test("001.002.003.004:12345|1.2.3.4:12345", "%piSp|%pISp", &sa, &sa);
}
static void __init
ip6(void)
{
}
static void __init
ip(void)
{
ip4();
ip6();
}
static void __init
uuid(void)
{
const char uuid[16] = {0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf};
test("00010203-0405-0607-0809-0a0b0c0d0e0f", "%pUb", uuid);
test("00010203-0405-0607-0809-0A0B0C0D0E0F", "%pUB", uuid);
test("03020100-0504-0706-0809-0a0b0c0d0e0f", "%pUl", uuid);
test("03020100-0504-0706-0809-0A0B0C0D0E0F", "%pUL", uuid);
}
static struct dentry test_dentry[4] __initdata = {
{ .d_parent = &test_dentry[0],
.d_name = QSTR_INIT(test_dentry[0].d_iname, 3),
.d_iname = "foo" },
{ .d_parent = &test_dentry[0],
.d_name = QSTR_INIT(test_dentry[1].d_iname, 5),
.d_iname = "bravo" },
{ .d_parent = &test_dentry[1],
.d_name = QSTR_INIT(test_dentry[2].d_iname, 4),
.d_iname = "alfa" },
{ .d_parent = &test_dentry[2],
.d_name = QSTR_INIT(test_dentry[3].d_iname, 5),
.d_iname = "romeo" },
};
static void __init
dentry(void)
{
test("foo", "%pd", &test_dentry[0]);
test("foo", "%pd2", &test_dentry[0]);
test("(null)", "%pd", NULL);
test("(efault)", "%pd", PTR_INVALID);
test("(null)", "%pD", NULL);
test("(efault)", "%pD", PTR_INVALID);
test("romeo", "%pd", &test_dentry[3]);
test("alfa/romeo", "%pd2", &test_dentry[3]);
test("bravo/alfa/romeo", "%pd3", &test_dentry[3]);
test("/bravo/alfa/romeo", "%pd4", &test_dentry[3]);
test("/bravo/alfa", "%pd4", &test_dentry[2]);
test("bravo/alfa |bravo/alfa ", "%-12pd2|%*pd2", &test_dentry[2], -12, &test_dentry[2]);
test(" bravo/alfa| bravo/alfa", "%12pd2|%*pd2", &test_dentry[2], 12, &test_dentry[2]);
}
static void __init
struct_va_format(void)
{
}
static void __init
time_and_date(void)
{
/* 1543210543 */
const struct rtc_time tm = {
.tm_sec = 43,
.tm_min = 35,
.tm_hour = 5,
.tm_mday = 26,
.tm_mon = 10,
.tm_year = 118,
};
/* 2019-01-04T15:32:23 */
time64_t t = 1546615943;
test("(%pt?)", "%pt", &tm);
test("2018-11-26T05:35:43", "%ptR", &tm);
test("0118-10-26T05:35:43", "%ptRr", &tm);
test("05:35:43|2018-11-26", "%ptRt|%ptRd", &tm, &tm);
test("05:35:43|0118-10-26", "%ptRtr|%ptRdr", &tm, &tm);
test("05:35:43|2018-11-26", "%ptRttr|%ptRdtr", &tm, &tm);
test("05:35:43 tr|2018-11-26 tr", "%ptRt tr|%ptRd tr", &tm, &tm);
test("2019-01-04T15:32:23", "%ptT", &t);
test("0119-00-04T15:32:23", "%ptTr", &t);
test("15:32:23|2019-01-04", "%ptTt|%ptTd", &t, &t);
test("15:32:23|0119-00-04", "%ptTtr|%ptTdr", &t, &t);
test("2019-01-04 15:32:23", "%ptTs", &t);
test("0119-00-04 15:32:23", "%ptTsr", &t);
test("15:32:23|2019-01-04", "%ptTts|%ptTds", &t, &t);
test("15:32:23|0119-00-04", "%ptTtrs|%ptTdrs", &t, &t);
}
static void __init
struct_clk(void)
{
}
static void __init
large_bitmap(void)
{
const int nbits = 1 << 16;
unsigned long *bits = bitmap_zalloc(nbits, GFP_KERNEL);
if (!bits)
return;
bitmap_set(bits, 1, 20);
bitmap_set(bits, 60000, 15);
test("1-20,60000-60014", "%*pbl", nbits, bits);
bitmap_free(bits);
}
static void __init
bitmap(void)
{
DECLARE_BITMAP(bits, 20);
const int primes[] = {2,3,5,7,11,13,17,19};
int i;
bitmap_zero(bits, 20);
test("00000|00000", "%20pb|%*pb", bits, 20, bits);
test("|", "%20pbl|%*pbl", bits, 20, bits);
for (i = 0; i < ARRAY_SIZE(primes); ++i)
set_bit(primes[i], bits);
test("a28ac|a28ac", "%20pb|%*pb", bits, 20, bits);
test("2-3,5,7,11,13,17,19|2-3,5,7,11,13,17,19", "%20pbl|%*pbl", bits, 20, bits);
bitmap_fill(bits, 20);
test("fffff|fffff", "%20pb|%*pb", bits, 20, bits);
test("0-19|0-19", "%20pbl|%*pbl", bits, 20, bits);
large_bitmap();
}
static void __init
netdev_features(void)
{
}
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
struct page_flags_test {
int width;
int shift;
int mask;
const char *fmt;
const char *name;
};
static const struct page_flags_test pft[] = {
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
{SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK,
"%d", "section"},
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
{NODES_WIDTH, NODES_PGSHIFT, NODES_MASK,
"%d", "node"},
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
{ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK,
"%d", "zone"},
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
{LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK,
"%#x", "lastcpupid"},
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
{KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK,
"%#x", "kasantag"},
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
};
static void __init
page_flags_test(int section, int node, int zone, int last_cpupid,
int kasan_tag, unsigned long flags, const char *name,
char *cmp_buf)
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
{
unsigned long values[] = {section, node, zone, last_cpupid, kasan_tag};
unsigned long size;
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
bool append = false;
int i;
for (i = 0; i < ARRAY_SIZE(values); i++)
flags |= (values[i] & pft[i].mask) << pft[i].shift;
size = scnprintf(cmp_buf, BUF_SIZE, "%#lx(", flags);
if (flags & PAGEFLAGS_MASK) {
size += scnprintf(cmp_buf + size, BUF_SIZE - size, "%s", name);
append = true;
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
}
for (i = 0; i < ARRAY_SIZE(pft); i++) {
if (!pft[i].width)
continue;
if (append)
size += scnprintf(cmp_buf + size, BUF_SIZE - size, "|");
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
size += scnprintf(cmp_buf + size, BUF_SIZE - size, "%s=",
pft[i].name);
size += scnprintf(cmp_buf + size, BUF_SIZE - size, pft[i].fmt,
values[i] & pft[i].mask);
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
append = true;
}
snprintf(cmp_buf + size, BUF_SIZE - size, ")");
test(cmp_buf, "%pGp", &flags);
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
}
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
static void __init
flags(void)
{
unsigned long flags;
char *cmp_buffer;
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
gfp_t gfp;
cmp_buffer = kmalloc(BUF_SIZE, GFP_KERNEL);
if (!cmp_buffer)
return;
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
flags = 0;
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
page_flags_test(0, 0, 0, 0, 0, flags, "", cmp_buffer);
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
flags = 1UL << NR_PAGEFLAGS;
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
page_flags_test(0, 0, 0, 0, 0, flags, "", cmp_buffer);
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
flags |= 1UL << PG_uptodate | 1UL << PG_dirty | 1UL << PG_lru
| 1UL << PG_active | 1UL << PG_swapbacked;
vsprintf: dump full information of page flags in pGp Currently the pGp only shows the names of page flags, rather than the full information including section, node, zone, last cpupid and kasan tag. While it is not easy to parse these information manually because there're so many flavors. Let's interpret them in pGp as well. To be compitable with the existed format of pGp, the new introduced ones also use '|' as the separator, then the user tools parsing pGp won't need to make change, suggested by Matthew. The new information is tracked onto the end of the existed one. On example of the output in mm/slub.c as follows, - Before the patch, [ 6343.396602] Slab 0x000000004382e02b objects=33 used=3 fp=0x000000009ae06ffc flags=0x17ffffc0010200(slab|head) - After the patch, [ 8448.272530] Slab 0x0000000090797883 objects=33 used=3 fp=0x00000000790f1c26 flags=0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) The documentation and test cases are also updated. The output of the test cases as follows, [68599.816764] test_printf: loaded. [68599.819068] test_printf: all 388 tests passed [68599.830367] test_printf: unloaded. [lkp@intel.com: reported issues in the prev version in test_printf.c] Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: kernel test robot <lkp@intel.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210319101246.73513-4-laoar.shao@gmail.com
2021-03-19 10:12:46 +00:00
page_flags_test(1, 1, 1, 0x1fffff, 1, flags,
"uptodate|dirty|lru|active|swapbacked",
cmp_buffer);
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
test("read|exec|mayread|maywrite|mayexec", "%pGv", &flags);
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
gfp = GFP_TRANSHUGE;
test("GFP_TRANSHUGE", "%pGg", &gfp);
gfp = GFP_ATOMIC|__GFP_DMA;
test("GFP_ATOMIC|GFP_DMA", "%pGg", &gfp);
mm: discard __GFP_ATOMIC __GFP_ATOMIC serves little purpose. Its main effect is to set ALLOC_HARDER which adds a few little boosts to increase the chance of an allocation succeeding, one of which is to lower the water-mark at which it will succeed. It is *always* paired with __GFP_HIGH which sets ALLOC_HIGH which also adjusts this watermark. It is probable that other users of __GFP_HIGH should benefit from the other little bonuses that __GFP_ATOMIC gets. __GFP_ATOMIC also gives a warning if used with __GFP_DIRECT_RECLAIM. There is little point to this. We already get a might_sleep() warning if __GFP_DIRECT_RECLAIM is set. __GFP_ATOMIC allows the "watermark_boost" to be side-stepped. It is probable that testing ALLOC_HARDER is a better fit here. __GFP_ATOMIC is used by tegra-smmu.c to check if the allocation might sleep. This should test __GFP_DIRECT_RECLAIM instead. This patch: - removes __GFP_ATOMIC - allows __GFP_HIGH allocations to ignore watermark boosting as well as GFP_ATOMIC requests. - makes other adjustments as suggested by the above. The net result is not change to GFP_ATOMIC allocations. Other allocations that use __GFP_HIGH will benefit from a few different extra privileges. This affects: xen, dm, md, ntfs3 the vermillion frame buffer hibernation ksm swap all of which likely produce more benefit than cost if these selected allocation are more likely to succeed quickly. [mgorman: Minor adjustments to rework on top of a series] Link: https://lkml.kernel.org/r/163712397076.13692.4727608274002939094@noble.neil.brown.name Link: https://lkml.kernel.org/r/20230113111217.14134-7-mgorman@techsingularity.net Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thierry Reding <thierry.reding@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-01-13 11:12:17 +00:00
gfp = __GFP_HIGH;
test("__GFP_HIGH", "%pGg", &gfp);
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
/* Any flags not translated by the table should remain numeric */
gfp = ~__GFP_BITS_MASK;
snprintf(cmp_buffer, BUF_SIZE, "%#lx", (unsigned long) gfp);
test(cmp_buffer, "%pGg", &gfp);
mm: discard __GFP_ATOMIC __GFP_ATOMIC serves little purpose. Its main effect is to set ALLOC_HARDER which adds a few little boosts to increase the chance of an allocation succeeding, one of which is to lower the water-mark at which it will succeed. It is *always* paired with __GFP_HIGH which sets ALLOC_HIGH which also adjusts this watermark. It is probable that other users of __GFP_HIGH should benefit from the other little bonuses that __GFP_ATOMIC gets. __GFP_ATOMIC also gives a warning if used with __GFP_DIRECT_RECLAIM. There is little point to this. We already get a might_sleep() warning if __GFP_DIRECT_RECLAIM is set. __GFP_ATOMIC allows the "watermark_boost" to be side-stepped. It is probable that testing ALLOC_HARDER is a better fit here. __GFP_ATOMIC is used by tegra-smmu.c to check if the allocation might sleep. This should test __GFP_DIRECT_RECLAIM instead. This patch: - removes __GFP_ATOMIC - allows __GFP_HIGH allocations to ignore watermark boosting as well as GFP_ATOMIC requests. - makes other adjustments as suggested by the above. The net result is not change to GFP_ATOMIC allocations. Other allocations that use __GFP_HIGH will benefit from a few different extra privileges. This affects: xen, dm, md, ntfs3 the vermillion frame buffer hibernation ksm swap all of which likely produce more benefit than cost if these selected allocation are more likely to succeed quickly. [mgorman: Minor adjustments to rework on top of a series] Link: https://lkml.kernel.org/r/163712397076.13692.4727608274002939094@noble.neil.brown.name Link: https://lkml.kernel.org/r/20230113111217.14134-7-mgorman@techsingularity.net Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thierry Reding <thierry.reding@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-01-13 11:12:17 +00:00
snprintf(cmp_buffer, BUF_SIZE, "__GFP_HIGH|%#lx",
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
(unsigned long) gfp);
mm: discard __GFP_ATOMIC __GFP_ATOMIC serves little purpose. Its main effect is to set ALLOC_HARDER which adds a few little boosts to increase the chance of an allocation succeeding, one of which is to lower the water-mark at which it will succeed. It is *always* paired with __GFP_HIGH which sets ALLOC_HIGH which also adjusts this watermark. It is probable that other users of __GFP_HIGH should benefit from the other little bonuses that __GFP_ATOMIC gets. __GFP_ATOMIC also gives a warning if used with __GFP_DIRECT_RECLAIM. There is little point to this. We already get a might_sleep() warning if __GFP_DIRECT_RECLAIM is set. __GFP_ATOMIC allows the "watermark_boost" to be side-stepped. It is probable that testing ALLOC_HARDER is a better fit here. __GFP_ATOMIC is used by tegra-smmu.c to check if the allocation might sleep. This should test __GFP_DIRECT_RECLAIM instead. This patch: - removes __GFP_ATOMIC - allows __GFP_HIGH allocations to ignore watermark boosting as well as GFP_ATOMIC requests. - makes other adjustments as suggested by the above. The net result is not change to GFP_ATOMIC allocations. Other allocations that use __GFP_HIGH will benefit from a few different extra privileges. This affects: xen, dm, md, ntfs3 the vermillion frame buffer hibernation ksm swap all of which likely produce more benefit than cost if these selected allocation are more likely to succeed quickly. [mgorman: Minor adjustments to rework on top of a series] Link: https://lkml.kernel.org/r/163712397076.13692.4727608274002939094@noble.neil.brown.name Link: https://lkml.kernel.org/r/20230113111217.14134-7-mgorman@techsingularity.net Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thierry Reding <thierry.reding@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-01-13 11:12:17 +00:00
gfp |= __GFP_HIGH;
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
test(cmp_buffer, "%pGg", &gfp);
kfree(cmp_buffer);
}
static void __init fwnode_pointer(void)
{
const struct software_node first = { .name = "first" };
const struct software_node second = { .name = "second", .parent = &first };
const struct software_node third = { .name = "third", .parent = &second };
const struct software_node *group[] = { &first, &second, &third, NULL };
const char * const full_name_second = "first/second";
const char * const full_name_third = "first/second/third";
const char * const second_name = "second";
const char * const third_name = "third";
int rval;
rval = software_node_register_node_group(group);
if (rval) {
pr_warn("cannot register softnodes; rval %d\n", rval);
return;
}
test(full_name_second, "%pfw", software_node_fwnode(&second));
test(full_name_third, "%pfw", software_node_fwnode(&third));
test(full_name_third, "%pfwf", software_node_fwnode(&third));
test(second_name, "%pfwP", software_node_fwnode(&second));
test(third_name, "%pfwP", software_node_fwnode(&third));
software_node_unregister_node_group(group);
}
static void __init fourcc_pointer(void)
{
struct {
u32 code;
char *str;
} const try[] = {
{ 0x3231564e, "NV12 little-endian (0x3231564e)", },
{ 0xb231564e, "NV12 big-endian (0xb231564e)", },
{ 0x10111213, ".... little-endian (0x10111213)", },
{ 0x20303159, "Y10 little-endian (0x20303159)", },
};
unsigned int i;
for (i = 0; i < ARRAY_SIZE(try); i++)
test(try[i].str, "%p4cc", &try[i].code);
}
printf: add support for printing symbolic error names It has been suggested several times to extend vsnprintf() to be able to convert the numeric value of ENOSPC to print "ENOSPC". This implements that as a %p extension: With %pe, one can do if (IS_ERR(foo)) { pr_err("Sorry, can't do that: %pe\n", foo); return PTR_ERR(foo); } instead of what is seen in quite a few places in the kernel: if (IS_ERR(foo)) { pr_err("Sorry, can't do that: %ld\n", PTR_ERR(foo)); return PTR_ERR(foo); } If the value passed to %pe is an ERR_PTR, but the library function errname() added here doesn't know about the value, the value is simply printed in decimal. If the value passed to %pe is not an ERR_PTR, we treat it as an ordinary %p and thus print the hashed value (passing non-ERR_PTR values to %pe indicates a bug in the caller, but we can't do much about that). With my embedded hat on, and because it's not very invasive to do, I've made it possible to remove this. The errname() function and associated lookup tables take up about 3K. For most, that's probably quite acceptable and a price worth paying for more readable dmesg (once this starts getting used), while for those that disable printk() it's of very little use - I don't see a procfs/sysfs/seq_printf() file reasonably making use of this - and they clearly want to squeeze vmlinux as much as possible. Hence the default y if PRINTK. The symbols to include have been found by massaging the output of find arch include -iname 'errno*.h' | xargs grep -E 'define\s*E' In the cases where some common aliasing exists (e.g. EAGAIN=EWOULDBLOCK on all platforms, EDEADLOCK=EDEADLK on most), I've moved the more popular one (in terms of 'git grep -w Efoo | wc) to the bottom so that one takes precedence. Link: http://lkml.kernel.org/r/20191015190706.15989-1-linux@rasmusvillemoes.dk To: "Jonathan Corbet" <corbet@lwn.net> To: linux-kernel@vger.kernel.org Cc: "Andy Shevchenko" <andy.shevchenko@gmail.com> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Joe Perches" <joe@perches.com> Cc: linux-doc@vger.kernel.org Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Uwe Kleine-König <uwe@kleine-koenig.org> Reviewed-by: Petr Mladek <pmladek@suse.com> [andy.shevchenko@gmail.com: use abs()] Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-10-15 19:07:05 +00:00
static void __init
errptr(void)
{
test("-1234", "%pe", ERR_PTR(-1234));
/* Check that %pe with a non-ERR_PTR gets treated as ordinary %p. */
BUILD_BUG_ON(IS_ERR(PTR));
test_hashed("%pe", PTR);
#ifdef CONFIG_SYMBOLIC_ERRNAME
test("(-ENOTSOCK)", "(%pe)", ERR_PTR(-ENOTSOCK));
test("(-EAGAIN)", "(%pe)", ERR_PTR(-EAGAIN));
BUILD_BUG_ON(EAGAIN != EWOULDBLOCK);
test("(-EAGAIN)", "(%pe)", ERR_PTR(-EWOULDBLOCK));
test("[-EIO ]", "[%-8pe]", ERR_PTR(-EIO));
test("[ -EIO]", "[%8pe]", ERR_PTR(-EIO));
test("-EPROBE_DEFER", "%pe", ERR_PTR(-EPROBE_DEFER));
#endif
}
static void __init
test_pointer(void)
{
plain();
vsprintf: Prevent crash when dereferencing invalid pointers We already prevent crash when dereferencing some obviously broken pointers. But the handling is not consistent. Sometimes we print "(null)" only for pure NULL pointer, sometimes for pointers in the first page and sometimes also for pointers in the last page (error codes). Note that printk() call this code under logbuf_lock. Any recursive printks are redirected to the printk_safe implementation and the messages are stored into per-CPU buffers. These buffers might be eventually flushed in printk_safe_flush_on_panic() but it is not guaranteed. This patch adds a check using probe_kernel_read(). It is not a full-proof test. But it should help to see the error message in 99% situations where the kernel would silently crash otherwise. Also it makes the error handling unified for "%s" and the many %p* specifiers that need to read the data from a given address. We print: + (null) when accessing data on pure pure NULL address + (efault) when accessing data on an invalid address It does not affect the %p* specifiers that just print the given address in some form, namely %pF, %pf, %pS, %ps, %pB, %pK, %px, and plain %p. Note that we print (efault) from security reasons. In fact, the real address can be seen only by %px or eventually %pK. Link: http://lkml.kernel.org/r/20190417115350.20479-9-pmladek@suse.com To: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Tobin C . Harding" <me@tobin.cc> Cc: Joe Perches <joe@perches.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-04-17 11:53:48 +00:00
null_pointer();
vsprintf: don't obfuscate NULL and error pointers I don't see what security concern is addressed by obfuscating NULL and IS_ERR() error pointers, printed with %p/%pK. Given the number of sites where %p is used (over 10000) and the fact that NULL pointers aren't uncommon, it probably wouldn't take long for an attacker to find the hash that corresponds to 0. Although harder, the same goes for most common error values, such as -1, -2, -11, -14, etc. The NULL part actually fixes a regression: NULL pointers weren't obfuscated until commit 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") which went into 5.2. I'm tacking the IS_ERR() part on here because error pointers won't leak kernel addresses and printing them as pointers shouldn't be any different from e.g. %d with PTR_ERR_OR_ZERO(). Obfuscating them just makes debugging based on existing pr_debug and friends excruciating. Note that the "always print 0's for %pK when kptr_restrict == 2" behaviour which goes way back is left as is. Example output with the patch applied: ptr error-ptr NULL %p: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %pK, kptr = 0: 0000000001f8cc5b fffffffffffffff2 0000000000000000 %px: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 1: ffff888048c04020 fffffffffffffff2 0000000000000000 %pK, kptr = 2: 0000000000000000 0000000000000000 0000000000000000 Fixes: 3e5903eb9cff ("vsprintf: Prevent crash when dereferencing invalid pointers") Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-05-19 11:26:57 +00:00
error_pointer();
vsprintf: Prevent crash when dereferencing invalid pointers We already prevent crash when dereferencing some obviously broken pointers. But the handling is not consistent. Sometimes we print "(null)" only for pure NULL pointer, sometimes for pointers in the first page and sometimes also for pointers in the last page (error codes). Note that printk() call this code under logbuf_lock. Any recursive printks are redirected to the printk_safe implementation and the messages are stored into per-CPU buffers. These buffers might be eventually flushed in printk_safe_flush_on_panic() but it is not guaranteed. This patch adds a check using probe_kernel_read(). It is not a full-proof test. But it should help to see the error message in 99% situations where the kernel would silently crash otherwise. Also it makes the error handling unified for "%s" and the many %p* specifiers that need to read the data from a given address. We print: + (null) when accessing data on pure pure NULL address + (efault) when accessing data on an invalid address It does not affect the %p* specifiers that just print the given address in some form, namely %pF, %pf, %pS, %ps, %pB, %pK, %px, and plain %p. Note that we print (efault) from security reasons. In fact, the real address can be seen only by %px or eventually %pK. Link: http://lkml.kernel.org/r/20190417115350.20479-9-pmladek@suse.com To: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Tobin C . Harding" <me@tobin.cc> Cc: Joe Perches <joe@perches.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-04-17 11:53:48 +00:00
invalid_pointer();
symbol_ptr();
kernel_ptr();
struct_resource();
addr();
escaped_str();
hex_string();
mac();
ip();
uuid();
dentry();
struct_va_format();
time_and_date();
struct_clk();
bitmap();
netdev_features();
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
flags();
printf: add support for printing symbolic error names It has been suggested several times to extend vsnprintf() to be able to convert the numeric value of ENOSPC to print "ENOSPC". This implements that as a %p extension: With %pe, one can do if (IS_ERR(foo)) { pr_err("Sorry, can't do that: %pe\n", foo); return PTR_ERR(foo); } instead of what is seen in quite a few places in the kernel: if (IS_ERR(foo)) { pr_err("Sorry, can't do that: %ld\n", PTR_ERR(foo)); return PTR_ERR(foo); } If the value passed to %pe is an ERR_PTR, but the library function errname() added here doesn't know about the value, the value is simply printed in decimal. If the value passed to %pe is not an ERR_PTR, we treat it as an ordinary %p and thus print the hashed value (passing non-ERR_PTR values to %pe indicates a bug in the caller, but we can't do much about that). With my embedded hat on, and because it's not very invasive to do, I've made it possible to remove this. The errname() function and associated lookup tables take up about 3K. For most, that's probably quite acceptable and a price worth paying for more readable dmesg (once this starts getting used), while for those that disable printk() it's of very little use - I don't see a procfs/sysfs/seq_printf() file reasonably making use of this - and they clearly want to squeeze vmlinux as much as possible. Hence the default y if PRINTK. The symbols to include have been found by massaging the output of find arch include -iname 'errno*.h' | xargs grep -E 'define\s*E' In the cases where some common aliasing exists (e.g. EAGAIN=EWOULDBLOCK on all platforms, EDEADLOCK=EDEADLK on most), I've moved the more popular one (in terms of 'git grep -w Efoo | wc) to the bottom so that one takes precedence. Link: http://lkml.kernel.org/r/20191015190706.15989-1-linux@rasmusvillemoes.dk To: "Jonathan Corbet" <corbet@lwn.net> To: linux-kernel@vger.kernel.org Cc: "Andy Shevchenko" <andy.shevchenko@gmail.com> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Joe Perches" <joe@perches.com> Cc: linux-doc@vger.kernel.org Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Uwe Kleine-König <uwe@kleine-koenig.org> Reviewed-by: Petr Mladek <pmladek@suse.com> [andy.shevchenko@gmail.com: use abs()] Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2019-10-15 19:07:05 +00:00
errptr();
fwnode_pointer();
fourcc_pointer();
}
static void __init selftest(void)
{
alloced_buffer = kmalloc(BUF_SIZE + 2*PAD_SIZE, GFP_KERNEL);
if (!alloced_buffer)
return;
test_buffer = alloced_buffer + PAD_SIZE;
test_basic();
test_number();
test_string();
test_pointer();
kfree(alloced_buffer);
}
KSTM_MODULE_LOADERS(test_printf);
MODULE_AUTHOR("Rasmus Villemoes <linux@rasmusvillemoes.dk>");
MODULE_DESCRIPTION("Test cases for printf facility");
MODULE_LICENSE("GPL");