* [PATCH v2 1/8] bootconfig: Set CONFIG_BOOT_CONFIG=n by default
From: Masami Hiramatsu @ 2020-02-20 12:18 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Set CONFIG_BOOT_CONFIG=n by default. This also warns
user if CONFIG_BOOT_CONFIG=n but "bootconfig" is given
in the kernel command line.
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
V2: Use pr_warn() for warning message.
Remove unneeded "default n" line from Kconfig.
---
init/Kconfig | 1 -
init/main.c | 8 ++++++++
kernel/trace/Kconfig | 3 ++-
3 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/init/Kconfig b/init/Kconfig
index 452bc1835cd4..e76e9241552c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1227,7 +1227,6 @@ endif
config BOOT_CONFIG
bool "Boot config support"
depends on BLK_DEV_INITRD
- default y
help
Extra boot config allows system admin to pass a config file as
complemental extension of kernel cmdline when booting.
diff --git a/init/main.c b/init/main.c
index f95b014a5479..ae4e37681247 100644
--- a/init/main.c
+++ b/init/main.c
@@ -418,6 +418,14 @@ static void __init setup_boot_config(const char *cmdline)
}
#else
#define setup_boot_config(cmdline) do { } while (0)
+
+static int __init warn_bootconfig(char *str)
+{
+ pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOTCONFIG is not set.\n");
+ return 0;
+}
+early_param("bootconfig", warn_bootconfig);
+
#endif
/* Change NUL term back to "=", to make "param" the whole string. */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 91e885194dbc..795c3e02d3f1 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -143,7 +143,8 @@ if FTRACE
config BOOTTIME_TRACING
bool "Boot-time Tracing support"
- depends on BOOT_CONFIG && TRACING
+ depends on TRACING
+ select BOOT_CONFIG
default y
help
Enable developer to setup ftrace subsystem via supplemental
^ permalink raw reply related
* [PATCH v2 2/8] bootconfig: Add bootconfig magic word for indicating bootconfig explicitly
From: Masami Hiramatsu @ 2020-02-20 12:18 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Add bootconfig magic word to the end of bootconfig on initrd
image for indicating explicitly the bootconfig is there.
Also tools/bootconfig treats wrong size or wrong checksum or
parse error as an error, because if there is a bootconfig magic
word, there must be a bootconfig.
The bootconfig magic word is "#BOOTCONFIG\n", 12 bytes word.
Thus the block image of the initrd file with bootconfig is
as follows.
[Initrd][bootconfig][size][csum][#BOOTCONFIG\n]
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
V2: Update Kconfig comment.
---
Documentation/admin-guide/bootconfig.rst | 10 +++++--
include/linux/bootconfig.h | 3 ++
init/Kconfig | 2 +
init/main.c | 6 +++-
tools/bootconfig/main.c | 43 ++++++++++++++++++++++--------
tools/bootconfig/test-bootconfig.sh | 2 +
6 files changed, 49 insertions(+), 17 deletions(-)
diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
index b342a6796392..5e7609936507 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -102,9 +102,13 @@ Boot Kernel With a Boot Config
==============================
Since the boot configuration file is loaded with initrd, it will be added
-to the end of the initrd (initramfs) image file. The Linux kernel decodes
-the last part of the initrd image in memory to get the boot configuration
-data.
+to the end of the initrd (initramfs) image file with size, checksum and
+12-byte magic word as below.
+
+[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n]
+
+The Linux kernel decodes the last part of the initrd image in memory to
+get the boot configuration data.
Because of this "piggyback" method, there is no need to change or
update the boot loader and the kernel image itself.
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 7e18c939663e..d11e183fcb54 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -10,6 +10,9 @@
#include <linux/kernel.h>
#include <linux/types.h>
+#define BOOTCONFIG_MAGIC "#BOOTCONFIG\n"
+#define BOOTCONFIG_MAGIC_LEN 12
+
/* XBC tree node */
struct xbc_node {
u16 next;
diff --git a/init/Kconfig b/init/Kconfig
index e76e9241552c..6ffaf4940f3e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1231,7 +1231,7 @@ config BOOT_CONFIG
Extra boot config allows system admin to pass a config file as
complemental extension of kernel cmdline when booting.
The boot config file must be attached at the end of initramfs
- with checksum and size.
+ with checksum, size and magic word.
See <file:Documentation/admin-guide/bootconfig.rst> for details.
If unsure, say Y.
diff --git a/init/main.c b/init/main.c
index ae4e37681247..fe3ed874c748 100644
--- a/init/main.c
+++ b/init/main.c
@@ -374,7 +374,11 @@ static void __init setup_boot_config(const char *cmdline)
if (!initrd_end)
goto not_found;
- hdr = (u32 *)(initrd_end - 8);
+ data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
+ if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
+ goto not_found;
+
+ hdr = (u32 *)(data - 8);
size = hdr[0];
csum = hdr[1];
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index e18eeb070562..742271f019a9 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -131,15 +131,26 @@ int load_xbc_from_initrd(int fd, char **buf)
struct stat stat;
int ret;
u32 size = 0, csum = 0, rcsum;
+ char magic[BOOTCONFIG_MAGIC_LEN];
ret = fstat(fd, &stat);
if (ret < 0)
return -errno;
- if (stat.st_size < 8)
+ if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN)
return 0;
- if (lseek(fd, -8, SEEK_END) < 0) {
+ if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) {
+ pr_err("Failed to lseek: %d\n", -errno);
+ return -errno;
+ }
+ if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0)
+ return -errno;
+ /* Check the bootconfig magic bytes */
+ if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0)
+ return 0;
+
+ if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) {
pr_err("Failed to lseek: %d\n", -errno);
return -errno;
}
@@ -150,11 +161,14 @@ int load_xbc_from_initrd(int fd, char **buf)
if (read(fd, &csum, sizeof(u32)) < 0)
return -errno;
- /* Wrong size, maybe no boot config here */
- if (stat.st_size < size + 8)
- return 0;
+ /* Wrong size error */
+ if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) {
+ pr_err("bootconfig size is too big\n");
+ return -E2BIG;
+ }
- if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) {
+ if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN),
+ SEEK_SET) < 0) {
pr_err("Failed to lseek: %d\n", -errno);
return -errno;
}
@@ -163,17 +177,17 @@ int load_xbc_from_initrd(int fd, char **buf)
if (ret < 0)
return ret;
- /* Wrong Checksum, maybe no boot config here */
+ /* Wrong Checksum */
rcsum = checksum((unsigned char *)*buf, size);
if (csum != rcsum) {
pr_err("checksum error: %d != %d\n", csum, rcsum);
- return 0;
+ return -EINVAL;
}
ret = xbc_init(*buf);
- /* Wrong data, maybe no boot config here */
+ /* Wrong data */
if (ret < 0)
- return 0;
+ return ret;
return size;
}
@@ -226,7 +240,8 @@ int delete_xbc(const char *path)
} else if (size > 0) {
ret = fstat(fd, &stat);
if (!ret)
- ret = ftruncate(fd, stat.st_size - size - 8);
+ ret = ftruncate(fd, stat.st_size
+ - size - 8 - BOOTCONFIG_MAGIC_LEN);
if (ret)
ret = -errno;
} /* Ignore if there is no boot config in initrd */
@@ -295,6 +310,12 @@ int apply_xbc(const char *path, const char *xbc_path)
pr_err("Failed to apply a boot config: %d\n", ret);
return ret;
}
+ /* Write a magic word of the bootconfig */
+ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
+ if (ret < 0) {
+ pr_err("Failed to apply a boot config magic: %d\n", ret);
+ return ret;
+ }
close(fd);
free(data);
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index 1de06de328e2..adafb7c50940 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -49,7 +49,7 @@ xpass $BOOTCONF -a $TEMPCONF $INITRD
new_size=$(stat -c %s $INITRD)
echo "File size check"
-xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9)
+xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12)
echo "Apply command repeat test"
xpass $BOOTCONF -a $TEMPCONF $INITRD
^ permalink raw reply related
* [PATCH v2 3/8] tools/bootconfig: Remove unneeded error message silencer
From: Masami Hiramatsu @ 2020-02-20 12:18 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Remove error message silent knob, we don't need it anymore
because we can check if there is a bootconfig by checking
the magic word.
If there is a magic word, but failed to load a bootconfig
from initrd, there is a real problem.
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
tools/bootconfig/include/linux/printk.h | 5 +----
tools/bootconfig/main.c | 8 --------
2 files changed, 1 insertion(+), 12 deletions(-)
diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h
index e978a63d3222..036e667596eb 100644
--- a/tools/bootconfig/include/linux/printk.h
+++ b/tools/bootconfig/include/linux/printk.h
@@ -4,10 +4,7 @@
#include <stdio.h>
-/* controllable printf */
-extern int pr_output;
-#define printk(fmt, ...) \
- (pr_output ? printf(fmt, ##__VA_ARGS__) : 0)
+#define printk(fmt, ...) printf(fmt, ##__VA_ARGS__)
#define pr_err printk
#define pr_warn printk
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 742271f019a9..a9b97814d1a9 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -14,8 +14,6 @@
#include <linux/kernel.h>
#include <linux/bootconfig.h>
-int pr_output = 1;
-
static int xbc_show_array(struct xbc_node *node)
{
const char *val;
@@ -227,13 +225,7 @@ int delete_xbc(const char *path)
return -errno;
}
- /*
- * Suppress error messages in xbc_init() because it can be just a
- * data which concidentally matches the size and checksum footer.
- */
- pr_output = 0;
size = load_xbc_from_initrd(fd, &buf);
- pr_output = 1;
if (size < 0) {
ret = size;
pr_err("Failed to load a boot config from initrd: %d\n", ret);
^ permalink raw reply related
* [PATCH v2 4/8] bootconfig: Remove unneeded checksum
From: Masami Hiramatsu @ 2020-02-20 12:19 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Remove checksum of bootconfig because we already use a magic
word to identify bootconfig. This checksum was used for
checking whether there is a bootconfig at the end of initrd
or not. Since we have a bootconfig magic word to identify
the bootconfig data, we do not this checksum anymore.
Thus the block image of the initrd file with bootconfig is
as follows.
[initrd][bootconfig][size(u32)][#BOOTCONFIG\n]
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
V2: Update Kconfig comment.
---
Documentation/admin-guide/bootconfig.rst | 6 ++--
init/Kconfig | 2 +
init/main.c | 20 +-------------
tools/bootconfig/main.c | 42 ++++++------------------------
tools/bootconfig/test-bootconfig.sh | 2 +
5 files changed, 16 insertions(+), 56 deletions(-)
diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
index 5e7609936507..48675052c963 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -102,10 +102,10 @@ Boot Kernel With a Boot Config
==============================
Since the boot configuration file is loaded with initrd, it will be added
-to the end of the initrd (initramfs) image file with size, checksum and
-12-byte magic word as below.
+to the end of the initrd (initramfs) image file with 4-byte size and 12-byte
+magic word as below.
-[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n]
+[initrd][bootconfig][size][#BOOTCONFIG\n]
The Linux kernel decodes the last part of the initrd image in memory to
get the boot configuration data.
diff --git a/init/Kconfig b/init/Kconfig
index 6ffaf4940f3e..631ef2864608 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1231,7 +1231,7 @@ config BOOT_CONFIG
Extra boot config allows system admin to pass a config file as
complemental extension of kernel cmdline when booting.
The boot config file must be attached at the end of initramfs
- with checksum, size and magic word.
+ with size and magic word.
See <file:Documentation/admin-guide/bootconfig.rst> for details.
If unsure, say Y.
diff --git a/init/main.c b/init/main.c
index fe3ed874c748..821c582af49b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -335,16 +335,6 @@ static char * __init xbc_make_cmdline(const char *key)
return new_cmdline;
}
-u32 boot_config_checksum(unsigned char *p, u32 size)
-{
- u32 ret = 0;
-
- while (size--)
- ret += *p++;
-
- return ret;
-}
-
static int __init bootconfig_params(char *param, char *val,
const char *unused, void *arg)
{
@@ -359,7 +349,7 @@ static int __init bootconfig_params(char *param, char *val,
static void __init setup_boot_config(const char *cmdline)
{
static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
- u32 size, csum;
+ u32 size;
char *data, *copy;
u32 *hdr;
int ret;
@@ -378,9 +368,8 @@ static void __init setup_boot_config(const char *cmdline)
if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
goto not_found;
- hdr = (u32 *)(data - 8);
+ hdr = (u32 *)(data - sizeof(u32));
size = hdr[0];
- csum = hdr[1];
if (size >= XBC_DATA_MAX) {
pr_err("bootconfig size %d greater than max size %d\n",
@@ -392,11 +381,6 @@ static void __init setup_boot_config(const char *cmdline)
if ((unsigned long)data < initrd_start)
goto not_found;
- if (boot_config_checksum((unsigned char *)data, size) != csum) {
- pr_err("bootconfig checksum failed\n");
- return;
- }
-
copy = memblock_alloc(size + 1, SMP_CACHE_BYTES);
if (!copy) {
pr_err("Failed to allocate memory for bootconfig\n");
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index a9b97814d1a9..01acb86c6273 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -75,17 +75,6 @@ static void xbc_show_compact_tree(void)
}
}
-/* Simple real checksum */
-int checksum(unsigned char *buf, int len)
-{
- int i, sum = 0;
-
- for (i = 0; i < len; i++)
- sum += buf[i];
-
- return sum;
-}
-
#define PAGE_SIZE 4096
int load_xbc_fd(int fd, char **buf, int size)
@@ -128,14 +117,14 @@ int load_xbc_from_initrd(int fd, char **buf)
{
struct stat stat;
int ret;
- u32 size = 0, csum = 0, rcsum;
+ u32 size = 0;
char magic[BOOTCONFIG_MAGIC_LEN];
ret = fstat(fd, &stat);
if (ret < 0)
return -errno;
- if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN)
+ if (stat.st_size < 4 + BOOTCONFIG_MAGIC_LEN)
return 0;
if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) {
@@ -148,7 +137,7 @@ int load_xbc_from_initrd(int fd, char **buf)
if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0)
return 0;
- if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) {
+ if (lseek(fd, -(4 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) {
pr_err("Failed to lseek: %d\n", -errno);
return -errno;
}
@@ -156,16 +145,13 @@ int load_xbc_from_initrd(int fd, char **buf)
if (read(fd, &size, sizeof(u32)) < 0)
return -errno;
- if (read(fd, &csum, sizeof(u32)) < 0)
- return -errno;
-
/* Wrong size error */
- if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) {
+ if (stat.st_size < size + 4 + BOOTCONFIG_MAGIC_LEN) {
pr_err("bootconfig size is too big\n");
return -E2BIG;
}
- if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN),
+ if (lseek(fd, stat.st_size - (size + 4 + BOOTCONFIG_MAGIC_LEN),
SEEK_SET) < 0) {
pr_err("Failed to lseek: %d\n", -errno);
return -errno;
@@ -175,13 +161,6 @@ int load_xbc_from_initrd(int fd, char **buf)
if (ret < 0)
return ret;
- /* Wrong Checksum */
- rcsum = checksum((unsigned char *)*buf, size);
- if (csum != rcsum) {
- pr_err("checksum error: %d != %d\n", csum, rcsum);
- return -EINVAL;
- }
-
ret = xbc_init(*buf);
/* Wrong data */
if (ret < 0)
@@ -233,7 +212,7 @@ int delete_xbc(const char *path)
ret = fstat(fd, &stat);
if (!ret)
ret = ftruncate(fd, stat.st_size
- - size - 8 - BOOTCONFIG_MAGIC_LEN);
+ - size - 4 - BOOTCONFIG_MAGIC_LEN);
if (ret)
ret = -errno;
} /* Ignore if there is no boot config in initrd */
@@ -246,7 +225,7 @@ int delete_xbc(const char *path)
int apply_xbc(const char *path, const char *xbc_path)
{
- u32 size, csum;
+ u32 size;
char *buf, *data;
int ret, fd;
@@ -256,15 +235,13 @@ int apply_xbc(const char *path, const char *xbc_path)
return ret;
}
size = strlen(buf) + 1;
- csum = checksum((unsigned char *)buf, size);
/* Prepare xbc_path data */
- data = malloc(size + 8);
+ data = malloc(size + 4);
if (!data)
return -ENOMEM;
strcpy(data, buf);
*(u32 *)(data + size) = size;
- *(u32 *)(data + size + 4) = csum;
/* Check the data format */
ret = xbc_init(buf);
@@ -277,7 +254,6 @@ int apply_xbc(const char *path, const char *xbc_path)
printf("Apply %s to %s\n", xbc_path, path);
printf("\tNumber of nodes: %d\n", ret);
printf("\tSize: %u bytes\n", (unsigned int)size);
- printf("\tChecksum: %d\n", (unsigned int)csum);
/* TODO: Check the options by schema */
xbc_destroy_all();
@@ -297,7 +273,7 @@ int apply_xbc(const char *path, const char *xbc_path)
return fd;
}
/* TODO: Ensure the @path is initramfs/initrd image */
- ret = write(fd, data, size + 8);
+ ret = write(fd, data, size + 4);
if (ret < 0) {
pr_err("Failed to apply a boot config: %d\n", ret);
return ret;
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index adafb7c50940..c5965eff62c5 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -49,7 +49,7 @@ xpass $BOOTCONF -a $TEMPCONF $INITRD
new_size=$(stat -c %s $INITRD)
echo "File size check"
-xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12)
+xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 5 + 12)
echo "Apply command repeat test"
xpass $BOOTCONF -a $TEMPCONF $INITRD
^ permalink raw reply related
* [PATCH v2 5/8] bootconfig: Reject subkey and value on same parent key
From: Masami Hiramatsu @ 2020-02-20 12:19 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Reject if a value node is mixed with subkey node on same
parent key node.
A value node can not co-exist with subkey node under some key
node, e.g.
key = value
key.subkey = another-value
This is not be allowed because bootconfig API is not designed
to handle such case.
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
Documentation/admin-guide/bootconfig.rst | 7 +++++++
lib/bootconfig.c | 16 ++++++++++++----
tools/bootconfig/samples/bad-mixed-kv1.bconf | 3 +++
tools/bootconfig/samples/bad-mixed-kv2.bconf | 3 +++
4 files changed, 25 insertions(+), 4 deletions(-)
create mode 100644 tools/bootconfig/samples/bad-mixed-kv1.bconf
create mode 100644 tools/bootconfig/samples/bad-mixed-kv2.bconf
diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
index 48675052c963..4a106584eb21 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -62,6 +62,13 @@ Or more shorter, written as following::
In both styles, same key words are automatically merged when parsing it
at boot time. So you can append similar trees or key-values.
+Note that a sub-key and a value can not co-exist under a parent key.
+For example, following config is NOT allowed.::
+
+ foo = value1
+ foo.bar = value2 # !ERROR! subkey "bar" and value "value1" can NOT co-exist
+
+
Comments
--------
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 3ea601a2eba5..54ac623ca781 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -533,7 +533,7 @@ struct xbc_node *find_match_node(struct xbc_node *node, char *k)
static int __init __xbc_add_key(char *k)
{
- struct xbc_node *node;
+ struct xbc_node *node, *child;
if (!xbc_valid_keyword(k))
return xbc_parse_error("Invalid keyword", k);
@@ -543,8 +543,12 @@ static int __init __xbc_add_key(char *k)
if (!last_parent) /* the first level */
node = find_match_node(xbc_nodes, k);
- else
- node = find_match_node(xbc_node_get_child(last_parent), k);
+ else {
+ child = xbc_node_get_child(last_parent);
+ if (child && xbc_node_is_value(child))
+ return xbc_parse_error("Subkey is mixed with value", k);
+ node = find_match_node(child, k);
+ }
if (node)
last_parent = node;
@@ -577,7 +581,7 @@ static int __init __xbc_parse_keys(char *k)
static int __init xbc_parse_kv(char **k, char *v)
{
struct xbc_node *prev_parent = last_parent;
- struct xbc_node *node;
+ struct xbc_node *node, *child;
char *next;
int c, ret;
@@ -585,6 +589,10 @@ static int __init xbc_parse_kv(char **k, char *v)
if (ret)
return ret;
+ child = xbc_node_get_child(last_parent);
+ if (child && xbc_node_is_key(child))
+ return xbc_parse_error("Value is mixed with subkey", v);
+
c = __xbc_parse_value(&v, &next);
if (c < 0)
return c;
diff --git a/tools/bootconfig/samples/bad-mixed-kv1.bconf b/tools/bootconfig/samples/bad-mixed-kv1.bconf
new file mode 100644
index 000000000000..1761547dd05c
--- /dev/null
+++ b/tools/bootconfig/samples/bad-mixed-kv1.bconf
@@ -0,0 +1,3 @@
+# value -> subkey pattern
+key = value
+key.subkey = another-value
diff --git a/tools/bootconfig/samples/bad-mixed-kv2.bconf b/tools/bootconfig/samples/bad-mixed-kv2.bconf
new file mode 100644
index 000000000000..6b32e0c3878c
--- /dev/null
+++ b/tools/bootconfig/samples/bad-mixed-kv2.bconf
@@ -0,0 +1,3 @@
+# subkey -> value pattern
+key.subkey = value
+key = another-value
^ permalink raw reply related
* [PATCH v2 6/8] bootconfig: Overwrite value on same key by default
From: Masami Hiramatsu @ 2020-02-20 12:19 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Currently, bootconfig does not overwrite existing value
on same key, but add new value to the tail of an array.
But this looks a bit confusing because similar syntax
configuration always overwrite the value by default.
This changes the behavior to overwrite value on same key.
For example, if there are 2 entries
key = value
...
key = value2
Then, the key is updated as below.
key = value2
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
Documentation/admin-guide/bootconfig.rst | 12 ++++++++++++
lib/bootconfig.c | 18 ++++++++++++++----
tools/bootconfig/test-bootconfig.sh | 16 ++++++++++++++--
3 files changed, 40 insertions(+), 6 deletions(-)
diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
index 4a106584eb21..0c18e3f540e6 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -62,6 +62,18 @@ Or more shorter, written as following::
In both styles, same key words are automatically merged when parsing it
at boot time. So you can append similar trees or key-values.
+Same-key Values
+---------------
+
+If two or more values or arraies share a same-key, the latter one remains.
+For example,::
+
+ foo = bar, baz
+ foo = qux
+
+In this case ``bar`` and ``baz`` is overwritten by ``qux``, and ``foo = qux``
+remains.
+
Note that a sub-key and a value can not co-exist under a parent key.
For example, following config is NOT allowed.::
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 54ac623ca781..9a094162ea3e 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -578,10 +578,18 @@ static int __init __xbc_parse_keys(char *k)
return __xbc_add_key(k);
}
+static void xbc_node_overwrite(struct xbc_node *node, char *v)
+{
+ unsigned long offset = v - xbc_data;
+
+ node->data = (u16)offset | XBC_VALUE;
+ node->next = 0;
+}
+
static int __init xbc_parse_kv(char **k, char *v)
{
struct xbc_node *prev_parent = last_parent;
- struct xbc_node *node, *child;
+ struct xbc_node *child;
char *next;
int c, ret;
@@ -597,9 +605,11 @@ static int __init xbc_parse_kv(char **k, char *v)
if (c < 0)
return c;
- node = xbc_add_sibling(v, XBC_VALUE);
- if (!node)
- return -ENOMEM;
+ if (!child) {
+ if (!xbc_add_sibling(v, XBC_VALUE))
+ return -ENOMEM;
+ } else
+ xbc_node_overwrite(child, v);
if (c == ',') { /* Array */
c = xbc_parse_array(&next);
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index c5965eff62c5..f6948790c693 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -9,7 +9,7 @@ TEMPCONF=`mktemp temp-XXXX.bconf`
NG=0
cleanup() {
- rm -f $INITRD $TEMPCONF
+ rm -f $INITRD $TEMPCONF $OUTFILE
exit $NG
}
@@ -71,7 +71,6 @@ printf " \0\0\0 \0\0\0" >> $INITRD
$BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1
xfail grep -i "failed" $OUTFILE
xfail grep -i "error" $OUTFILE
-rm $OUTFILE
echo "Max node number check"
@@ -96,6 +95,19 @@ truncate -s 32764 $TEMPCONF
echo "\"" >> $TEMPCONF # add 2 bytes + terminal ('\"\n\0')
xpass $BOOTCONF -a $TEMPCONF $INITRD
+echo "Overwrite same-key values"
+cat > $TEMPCONF << EOF
+key = bar, baz
+key = qux
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xfail grep -q "bar" $OUTFILE
+xfail grep -q "baz" $OUTFILE
+xpass grep -q "qux" $OUTFILE
+
echo "=== expected failure cases ==="
for i in samples/bad-* ; do
xfail $BOOTCONF -a $i $INITRD
^ permalink raw reply related
* [PATCH v2 7/8] bootconfig: Add append value operator support
From: Masami Hiramatsu @ 2020-02-20 12:19 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Add append value operator "+=" support to bootconfig syntax.
With this operator, user can add new value to the key as
an entry of array instead of overwriting.
For example,
foo = bar
...
foo += baz
Then the key "foo" has "bar" and "baz" values as an array.
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
Documentation/admin-guide/bootconfig.rst | 8 ++++++++
lib/bootconfig.c | 14 ++++++++++----
tools/bootconfig/test-bootconfig.sh | 13 +++++++++++++
3 files changed, 31 insertions(+), 4 deletions(-)
diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
index 0c18e3f540e6..abe2432b8eec 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -74,6 +74,14 @@ For example,::
In this case ``bar`` and ``baz`` is overwritten by ``qux``, and ``foo = qux``
remains.
+If you want to append the value to existing key as an array member,
+you can use ``+=`` operator. For example::
+
+ foo = bar, baz
+ foo += qux
+
+In this case, the key ``foo`` has ``bar``, ``baz`` and ``qux``.
+
Note that a sub-key and a value can not co-exist under a parent key.
For example, following config is NOT allowed.::
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 9a094162ea3e..4afc768489cd 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -586,7 +586,7 @@ static void xbc_node_overwrite(struct xbc_node *node, char *v)
node->next = 0;
}
-static int __init xbc_parse_kv(char **k, char *v)
+static int __init xbc_parse_kv(char **k, char *v, int op)
{
struct xbc_node *prev_parent = last_parent;
struct xbc_node *child;
@@ -605,7 +605,7 @@ static int __init xbc_parse_kv(char **k, char *v)
if (c < 0)
return c;
- if (!child) {
+ if (op == '+' || !child) {
if (!xbc_add_sibling(v, XBC_VALUE))
return -ENOMEM;
} else
@@ -781,7 +781,7 @@ int __init xbc_init(char *buf)
p = buf;
do {
- q = strpbrk(p, "{}=;\n#");
+ q = strpbrk(p, "{}=+;\n#");
if (!q) {
p = skip_spaces(p);
if (*p != '\0')
@@ -792,8 +792,14 @@ int __init xbc_init(char *buf)
c = *q;
*q++ = '\0';
switch (c) {
+ case '+':
+ if (*q++ != '=') {
+ ret = xbc_parse_error("Wrong + operator", q - 2);
+ break;
+ }
+ /* Fall through */
case '=':
- ret = xbc_parse_kv(&p, q);
+ ret = xbc_parse_kv(&p, q, c);
break;
case '{':
ret = xbc_open_brace(&p, q);
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index f6948790c693..04f65548ca1e 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -108,6 +108,19 @@ xfail grep -q "bar" $OUTFILE
xfail grep -q "baz" $OUTFILE
xpass grep -q "qux" $OUTFILE
+echo "Adding same-key values"
+cat > $TEMPCONF << EOF
+key = bar, baz
+key += qux
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xpass grep -q "bar" $OUTFILE
+xpass grep -q "baz" $OUTFILE
+xpass grep -q "qux" $OUTFILE
+
echo "=== expected failure cases ==="
for i in samples/bad-* ; do
xfail $BOOTCONF -a $i $INITRD
^ permalink raw reply related
* [PATCH v2 8/8] bootconfig: Print array as multiple commands for legacy command line
From: Masami Hiramatsu @ 2020-02-20 12:19 UTC (permalink / raw)
To: Steven Rostedt
Cc: Geert Uytterhoeven, Borislav Petkov, LKML, Ingo Molnar,
Andrew Morton, Masami Hiramatsu, Peter Zijlstra
In-Reply-To: <158220110257.26565.4812934676257459744.stgit@devnote2>
Print arraied values as multiple same options for legacy
kernel command line. With this rule, if the "kernel.*" and
"init.*" array entries in bootconfig are printed out as
multiple same options, e.g.
kernel {
console = "ttyS0,115200"
console += "tty0"
}
will be correctly converted to
console="ttyS0,115200" console="tty0"
in the kernel command line.
Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
---
init/main.c | 22 ++++++++--------------
1 file changed, 8 insertions(+), 14 deletions(-)
diff --git a/init/main.c b/init/main.c
index 821c582af49b..19a5577e0bb0 100644
--- a/init/main.c
+++ b/init/main.c
@@ -268,7 +268,6 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size,
{
struct xbc_node *knode, *vnode;
char *end = buf + size;
- char c = '\"';
const char *val;
int ret;
@@ -279,25 +278,20 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size,
return ret;
vnode = xbc_node_get_child(knode);
- ret = snprintf(buf, rest(buf, end), "%s%c", xbc_namebuf,
- vnode ? '=' : ' ');
- if (ret < 0)
- return ret;
- buf += ret;
- if (!vnode)
+ if (!vnode) {
+ ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf);
+ if (ret < 0)
+ return ret;
+ buf += ret;
continue;
-
- c = '\"';
+ }
xbc_array_for_each_value(vnode, val) {
- ret = snprintf(buf, rest(buf, end), "%c%s", c, val);
+ ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ",
+ xbc_namebuf, val);
if (ret < 0)
return ret;
buf += ret;
- c = ',';
}
- if (rest(buf, end) > 2)
- strcpy(buf, "\" ");
- buf += 2;
}
return buf - (end - size);
^ permalink raw reply related
* Re: [PATCH 4/4] crypto: hisilicon/sec2 - Add pbuffer mode for SEC driver
From: John Garry @ 2020-02-20 12:20 UTC (permalink / raw)
To: Xu Zaibo, herbert, davem
Cc: qianweili, tanghui20, forest.zhouchang, linuxarm, zhangwei375,
shenyang39, yekai13, linux-crypto
In-Reply-To: <bac7ec3e-43e6-9061-fbbe-03f4404f1c50@huawei.com>
On 20/02/2020 12:16, Xu Zaibo wrote:
>
> On 2020/2/20 19:07, John Garry wrote:
>> On 20/02/2020 10:10, Xu Zaibo wrote:
>>> Hi,
>>>
>>>
>>> On 2020/2/20 17:50, John Garry wrote:
>>>> On 20/02/2020 09:04, Zaibo Xu wrote:
>>>>> From: liulongfang <liulongfang@huawei.com>
>>>>>
>>>>> In the scenario of SMMU translation, the SEC performance of short
>>>>> messages
>>>>> (<512Bytes) cannot meet our expectations. To avoid this, we reserve
>>>>> the
>>>>> plat buffer (PBUF) memory for small packets when creating TFM.
>>>>>
>>>>
>>>> I haven't gone through the code here, but why not use this method
>>>> also for non-translated? What are the pros and cons?
>>> Because non-translated has no performance or throughput problems.
>>>
>>
>> OK, so no problem, but I was asking could it be improved, and, if so,
>> what would be the drawbacks?
>>
>> As for the change to check if the IOMMU is translating, it seems exact
>> same as that for the hi1616 driver...
>>
> Currently, I find the only drawback is needing more memory :),
OK, so that is a drawback.
> what's
> your idea?
I am just asking if we get any performance gain for using this same
method for non-IOMMU case, and does the gain (if any) in performance
outweigh the additional memory usage?
> Yes, the same as SEC V1.
So it could be factored out :)
thanks,
john
^ permalink raw reply
* [PATCH] usbvision: deprecate driver
From: Hans Verkuil @ 2020-02-20 12:20 UTC (permalink / raw)
To: Linux Media Mailing List
The driver is deprecated and scheduled for removal by the end
of 2020. The reason is that this driver is for old and obsolete
hardware, and it produces a continuous stream of syzbot errors due
to poor code.
In order to prevent removal the following actions would have to
be taken:
- clean up the code
- convert to the vb2 framework
- fix the disconnect and free-on-last-user handling (i.e., add
a release callback for struct v4l2_device and rework the code
to use that correctly).
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
MAINTAINERS | 2 +-
drivers/media/usb/Kconfig | 1 -
drivers/media/usb/Makefile | 1 -
drivers/staging/media/Kconfig | 4 ++++
drivers/staging/media/Makefile | 1 +
.../{media/usb => staging/media}/usbvision/Kconfig | 7 ++++++-
.../{media/usb => staging/media}/usbvision/Makefile | 0
drivers/staging/media/usbvision/TODO | 11 +++++++++++
.../usb => staging/media}/usbvision/usbvision-cards.c | 0
.../usb => staging/media}/usbvision/usbvision-cards.h | 0
.../usb => staging/media}/usbvision/usbvision-core.c | 0
.../usb => staging/media}/usbvision/usbvision-i2c.c | 0
.../usb => staging/media}/usbvision/usbvision-video.c | 0
.../usb => staging/media}/usbvision/usbvision.h | 0
14 files changed, 23 insertions(+), 4 deletions(-)
rename drivers/{media/usb => staging/media}/usbvision/Kconfig (57%)
rename drivers/{media/usb => staging/media}/usbvision/Makefile (100%)
create mode 100644 drivers/staging/media/usbvision/TODO
rename drivers/{media/usb => staging/media}/usbvision/usbvision-cards.c (100%)
rename drivers/{media/usb => staging/media}/usbvision/usbvision-cards.h (100%)
rename drivers/{media/usb => staging/media}/usbvision/usbvision-core.c (100%)
rename drivers/{media/usb => staging/media}/usbvision/usbvision-i2c.c (100%)
rename drivers/{media/usb => staging/media}/usbvision/usbvision-video.c (100%)
rename drivers/{media/usb => staging/media}/usbvision/usbvision.h (100%)
diff --git a/MAINTAINERS b/MAINTAINERS
index 38fe2f3f7b6f..5a976815a0a4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17444,7 +17444,7 @@ L: linux-media@vger.kernel.org
T: git git://linuxtv.org/media_tree.git
W: https://linuxtv.org
S: Odd Fixes
-F: drivers/media/usb/usbvision/
+F: drivers/staging/media/usbvision/
USB WEBCAM GADGET
M: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
diff --git a/drivers/media/usb/Kconfig b/drivers/media/usb/Kconfig
index 03c2944f6273..e678d3d11467 100644
--- a/drivers/media/usb/Kconfig
+++ b/drivers/media/usb/Kconfig
@@ -25,7 +25,6 @@ if MEDIA_ANALOG_TV_SUPPORT
comment "Analog TV USB devices"
source "drivers/media/usb/pvrusb2/Kconfig"
source "drivers/media/usb/hdpvr/Kconfig"
-source "drivers/media/usb/usbvision/Kconfig"
source "drivers/media/usb/stk1160/Kconfig"
source "drivers/media/usb/go7007/Kconfig"
endif
diff --git a/drivers/media/usb/Makefile b/drivers/media/usb/Makefile
index 21e46b10caa5..169aa07c97bd 100644
--- a/drivers/media/usb/Makefile
+++ b/drivers/media/usb/Makefile
@@ -17,7 +17,6 @@ obj-$(CONFIG_VIDEO_CPIA2) += cpia2/
obj-$(CONFIG_VIDEO_AU0828) += au0828/
obj-$(CONFIG_VIDEO_HDPVR) += hdpvr/
obj-$(CONFIG_VIDEO_PVRUSB2) += pvrusb2/
-obj-$(CONFIG_VIDEO_USBVISION) += usbvision/
obj-$(CONFIG_VIDEO_STK1160) += stk1160/
obj-$(CONFIG_VIDEO_CX231XX) += cx231xx/
obj-$(CONFIG_VIDEO_TM6000) += tm6000/
diff --git a/drivers/staging/media/Kconfig b/drivers/staging/media/Kconfig
index c394abffea86..e59a846bc909 100644
--- a/drivers/staging/media/Kconfig
+++ b/drivers/staging/media/Kconfig
@@ -42,4 +42,8 @@ source "drivers/staging/media/phy-rockchip-dphy-rx0/Kconfig"
source "drivers/staging/media/rkisp1/Kconfig"
+if MEDIA_ANALOG_TV_SUPPORT
+source "drivers/staging/media/usbvision/Kconfig"
+endif
+
endif
diff --git a/drivers/staging/media/Makefile b/drivers/staging/media/Makefile
index ea9fce8014bb..23c682461b62 100644
--- a/drivers/staging/media/Makefile
+++ b/drivers/staging/media/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_VIDEO_IPU3_IMGU) += ipu3/
obj-$(CONFIG_SOC_CAMERA) += soc_camera/
obj-$(CONFIG_PHY_ROCKCHIP_DPHY_RX0) += phy-rockchip-dphy-rx0/
obj-$(CONFIG_VIDEO_ROCKCHIP_ISP1) += rkisp1/
+obj-$(CONFIG_VIDEO_USBVISION) += usbvision/
diff --git a/drivers/media/usb/usbvision/Kconfig b/drivers/staging/media/usbvision/Kconfig
similarity index 57%
rename from drivers/media/usb/usbvision/Kconfig
rename to drivers/staging/media/usbvision/Kconfig
index e1039fdfb0ea..7903f558494e 100644
--- a/drivers/media/usb/usbvision/Kconfig
+++ b/drivers/staging/media/usbvision/Kconfig
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
config VIDEO_USBVISION
- tristate "USB video devices based on Nogatech NT1003/1004/1005"
+ tristate "USB video devices based on Nogatech NT1003/1004/1005 (Deprecated)"
depends on I2C && VIDEO_V4L2
select VIDEO_TUNER
select VIDEO_SAA711X if MEDIA_SUBDRV_AUTOSELECT
@@ -9,5 +9,10 @@ config VIDEO_USBVISION
NT1003/1004/1005 USB Bridges. This driver enables using those
devices.
+ This driver is deprecated and scheduled for removal by the
+ end of 2020. See the TODO file in drivers/staging/media/usbvision
+ for a list of actions that have to be done in order to prevent
+ removal of this driver.
+
To compile this driver as a module, choose M here: the
module will be called usbvision.
diff --git a/drivers/media/usb/usbvision/Makefile b/drivers/staging/media/usbvision/Makefile
similarity index 100%
rename from drivers/media/usb/usbvision/Makefile
rename to drivers/staging/media/usbvision/Makefile
diff --git a/drivers/staging/media/usbvision/TODO b/drivers/staging/media/usbvision/TODO
new file mode 100644
index 000000000000..e9fb4d125581
--- /dev/null
+++ b/drivers/staging/media/usbvision/TODO
@@ -0,0 +1,11 @@
+The driver is deprecated and scheduled for removal by the end
+of 2020.
+
+In order to prevent removal the following actions would have to
+be taken:
+
+- clean up the code
+- convert to the vb2 framework
+- fix the disconnect and free-on-last-user handling (i.e., add
+ a release callback for struct v4l2_device and rework the code
+ to use that correctly).
diff --git a/drivers/media/usb/usbvision/usbvision-cards.c b/drivers/staging/media/usbvision/usbvision-cards.c
similarity index 100%
rename from drivers/media/usb/usbvision/usbvision-cards.c
rename to drivers/staging/media/usbvision/usbvision-cards.c
diff --git a/drivers/media/usb/usbvision/usbvision-cards.h b/drivers/staging/media/usbvision/usbvision-cards.h
similarity index 100%
rename from drivers/media/usb/usbvision/usbvision-cards.h
rename to drivers/staging/media/usbvision/usbvision-cards.h
diff --git a/drivers/media/usb/usbvision/usbvision-core.c b/drivers/staging/media/usbvision/usbvision-core.c
similarity index 100%
rename from drivers/media/usb/usbvision/usbvision-core.c
rename to drivers/staging/media/usbvision/usbvision-core.c
diff --git a/drivers/media/usb/usbvision/usbvision-i2c.c b/drivers/staging/media/usbvision/usbvision-i2c.c
similarity index 100%
rename from drivers/media/usb/usbvision/usbvision-i2c.c
rename to drivers/staging/media/usbvision/usbvision-i2c.c
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/staging/media/usbvision/usbvision-video.c
similarity index 100%
rename from drivers/media/usb/usbvision/usbvision-video.c
rename to drivers/staging/media/usbvision/usbvision-video.c
diff --git a/drivers/media/usb/usbvision/usbvision.h b/drivers/staging/media/usbvision/usbvision.h
similarity index 100%
rename from drivers/media/usb/usbvision/usbvision.h
rename to drivers/staging/media/usbvision/usbvision.h
--
2.24.1
^ permalink raw reply related
* Re: [Xen-devel] [PATCH V3] x86/altp2m: Hypercall to set altp2m view visibility
From: George Dunlap @ 2020-02-20 12:21 UTC (permalink / raw)
To: Alexandru Stefan ISAILA, xen-devel@lists.xenproject.org
Cc: Kevin Tian, Stefano Stabellini, Julien Grall, Jun Nakajima,
Wei Liu, Konrad Rzeszutek Wilk, George Dunlap, Andrew Cooper,
Ian Jackson, Jan Beulich, Roger Pau Monné
In-Reply-To: <20200219091811.9689-1-aisaila@bitdefender.com>
On 2/19/20 9:18 AM, Alexandru Stefan ISAILA wrote:
> At this moment a guest can call vmfunc to change the altp2m view. This
> should be limited in order to avoid any unwanted view switch.
>
> The new xc_altp2m_set_visibility() solves this by making views invisible
> to vmfunc.
> This is done by having a separate arch.altp2m_working_eptp that is
> populated and made invalid in the same places as altp2m_eptp. This is
> written to EPTP_LIST_ADDR.
> The views are made in/visible by marking them with INVALID_MFN or
> copying them back from altp2m_eptp.
> To have consistency the visibility also applies to
> p2m_switch_domain_altp2m_by_id().
So it looks like by default the views are visible, until they're made
non-visible?
Also, does the last line mean that the toolstack can't change to a
"non-visible" altp2m either?
-George
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply
* Re: [PATCH 03/19] fsinfo: Provide a bitmap of supported features [ver #16]
From: David Howells @ 2020-02-20 12:22 UTC (permalink / raw)
To: Darrick J. Wong
Cc: dhowells, viro, raven, mszeredi, christian, linux-api,
linux-fsdevel, linux-kernel
In-Reply-To: <20200219163705.GC9496@magnolia>
Darrick J. Wong <darrick.wong@oracle.com> wrote:
> > +struct fsinfo_features {
> > + __u8 features[(FSINFO_FEAT__NR + 7) / 8];
>
> Hm...the structure size is pretty small (56 bytes) and will expand as we
> add new _FEAT flags. Is this ok because the fsinfo code will truncate
> its response to userspace to whatever buffer size userspace tells it?
Yes. Also, you can ask fsinfo how many feature bits it supports.
I should put this in the struct first rather than putting it elsewhere.
David
^ permalink raw reply
* [Bug 206525] BUG: KASAN: stack-out-of-bounds in test_bit+0x30/0x44 (kernel 5.6-rc1)
From: bugzilla-daemon @ 2020-02-20 12:19 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <bug-206525-206035@https.bugzilla.kernel.org/>
https://bugzilla.kernel.org/show_bug.cgi?id=206525
--- Comment #6 from Nikolay Aleksandrov (nikolay@cumulusnetworks.com) ---
Note that the bug wasn't introduced by my commit, but instead has been there
since:
commit 4f520900522f
Author: Richard Guy Briggs <rgb@redhat.com>
Date: Tue Apr 22 21:31:54 2014 -0400
netlink: have netlink per-protocol bind function return an error code.
which moved the ngroups test_bit() to a local variable. My commit only exposed
the bug since it added the 33rd group. I'm currently preparing a fix and will
post it to netdev after verifying and testing it.
--
You are receiving this mail because:
You are watching the assignee of the bug.
^ permalink raw reply
* Re: [PATCH 5/5] arm64/vdso: Restrict splitting VVAR VMA
From: Vincenzo Frascino @ 2020-02-20 12:22 UTC (permalink / raw)
To: Andrei Vagin
Cc: linux-arm-kernel, linux-kernel, Thomas Gleixner, Dmitry Safonov
In-Reply-To: <20200204175913.74901-6-avagin@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1939 bytes --]
Hi Andrei,
On 04/02/2020 17:59, Andrei Vagin wrote:
> Forbid splitting VVAR VMA resulting in a stricter ABI and reducing the
> amount of corner-cases to consider while working further on VDSO time
> namespace support.
>
> As the offset from timens to VVAR page is computed compile-time, the pages
> in VVAR should stay together and not being partically mremap()'ed.
>
I agree on the concept, but why do we need to redefine mremap?
special_mapping_mremap() (mm/mmap.c +3317) seems doing already the same thing if
we leave mremap == NULL as is.
> Signed-off-by: Andrei Vagin <avagin@gmail.com>
> ---
> arch/arm64/kernel/vdso.c | 13 +++++++++++++
> 1 file changed, 13 insertions(+)
>
> diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
> index 2e553468b183..e6ebdc184c1e 100644
> --- a/arch/arm64/kernel/vdso.c
> +++ b/arch/arm64/kernel/vdso.c
> @@ -229,6 +229,17 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
> return vmf_insert_pfn(vma, vmf->address, pfn);
> }
>
> +static int vvar_mremap(const struct vm_special_mapping *sm,
> + struct vm_area_struct *new_vma)
> +{
> + unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
> +
> + if (new_size != VVAR_NR_PAGES * PAGE_SIZE)
> + return -EINVAL;
> +
> + return 0;
> +}
> +
> static int __setup_additional_pages(enum arch_vdso_type arch_index,
> struct mm_struct *mm,
> struct linux_binprm *bprm,
> @@ -311,6 +322,7 @@ static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
> {
> .name = "[vvar]",
> .fault = vvar_fault,
> + .mremap = vvar_mremap,
> },
> {
> .name = "[vdso]",
> @@ -493,6 +505,7 @@ static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
> {
> .name = "[vvar]",
> .fault = vvar_fault,
> + .mremap = vvar_mremap,
> },
> {
> .name = "[vdso]",
>
--
Regards,
Vincenzo
[-- Attachment #2: pEpkey.asc --]
[-- Type: application/pgp-keys, Size: 14291 bytes --]
^ permalink raw reply
* Re: [PATCH 5/5] arm64/vdso: Restrict splitting VVAR VMA
From: Vincenzo Frascino @ 2020-02-20 12:22 UTC (permalink / raw)
To: Andrei Vagin
Cc: Thomas Gleixner, linux-kernel, linux-arm-kernel, Dmitry Safonov
In-Reply-To: <20200204175913.74901-6-avagin@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1939 bytes --]
Hi Andrei,
On 04/02/2020 17:59, Andrei Vagin wrote:
> Forbid splitting VVAR VMA resulting in a stricter ABI and reducing the
> amount of corner-cases to consider while working further on VDSO time
> namespace support.
>
> As the offset from timens to VVAR page is computed compile-time, the pages
> in VVAR should stay together and not being partically mremap()'ed.
>
I agree on the concept, but why do we need to redefine mremap?
special_mapping_mremap() (mm/mmap.c +3317) seems doing already the same thing if
we leave mremap == NULL as is.
> Signed-off-by: Andrei Vagin <avagin@gmail.com>
> ---
> arch/arm64/kernel/vdso.c | 13 +++++++++++++
> 1 file changed, 13 insertions(+)
>
> diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
> index 2e553468b183..e6ebdc184c1e 100644
> --- a/arch/arm64/kernel/vdso.c
> +++ b/arch/arm64/kernel/vdso.c
> @@ -229,6 +229,17 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
> return vmf_insert_pfn(vma, vmf->address, pfn);
> }
>
> +static int vvar_mremap(const struct vm_special_mapping *sm,
> + struct vm_area_struct *new_vma)
> +{
> + unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
> +
> + if (new_size != VVAR_NR_PAGES * PAGE_SIZE)
> + return -EINVAL;
> +
> + return 0;
> +}
> +
> static int __setup_additional_pages(enum arch_vdso_type arch_index,
> struct mm_struct *mm,
> struct linux_binprm *bprm,
> @@ -311,6 +322,7 @@ static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
> {
> .name = "[vvar]",
> .fault = vvar_fault,
> + .mremap = vvar_mremap,
> },
> {
> .name = "[vdso]",
> @@ -493,6 +505,7 @@ static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
> {
> .name = "[vvar]",
> .fault = vvar_fault,
> + .mremap = vvar_mremap,
> },
> {
> .name = "[vdso]",
>
--
Regards,
Vincenzo
[-- Attachment #2: pEpkey.asc --]
[-- Type: application/pgp-keys, Size: 14291 bytes --]
[-- Attachment #3: Type: text/plain, Size: 176 bytes --]
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [dpdk-dev] [PATCH 4/4] ci: reorganise Travis jobs
From: David Marchand @ 2020-02-20 12:22 UTC (permalink / raw)
To: Thomas Monjalon, Aaron Conole; +Cc: dev, Michael Santana, Bruce Richardson
In-Reply-To: <3732162.jZfb76A358@xps>
On Thu, Feb 20, 2020 at 11:42 AM Thomas Monjalon <thomas@monjalon.net> wrote:
>
> 19/02/2020 22:39, Aaron Conole:
> > David Marchand <david.marchand@redhat.com> writes:
> >
> > > Let's prune the jobs list to limit the amount of time spent by the robot
> > > in Travis.
> > >
> > > Since meson enables automatically the relevant components, there is not
> > > much gain in testing with extra_packages vs required_packages only.
> > >
> > > For a given arch/compiler/env combination, compilation is first tested
> > > in all jobs that run tests or build the docs or run the ABI checks.
> > > In the same context, for jobs that accumulates running tests, building
> > > the docs etc..., those steps are independent and can be split to save
> > > some cpu on Travis.
> > >
> > > With this, we go down from 21 to 15 jobs.
> > >
> > > Note: this patch requires a flush of the existing caches in Travis.
> > >
> > > Signed-off-by: David Marchand <david.marchand@redhat.com>
> > > ---
> >
> > In general, I think the idea with required vs. extra was to have a build
> > that did the minimum required, and one that did all the packages (to
> > allow a minimum vs. full DPDK).
> >
> > At least, that's from
> > http://mails.dpdk.org/archives/dev/2019-January/124007.html
>
> I think the benefit of a minimum build is to have a quick report,
> and easy to setup.
Yes, Travis serves as a first gate when submitting patches.
But since Travis is best effort/free, we can't have a full coverage.
> > Not sure if that's still something anyone cares about.
>
> Given that Travis knows how to satisfy the dependencies,
> and that we must wait for all jobs to finish,
> I don't see any benefit of a minimal setup.
This minimal setup also tests that dpdk dependencies are correct.
If a change makes something rely on libX and libX is in the packages
always installed in Travis, the missing dependency would not get
caught.
But here, this adds too many jobs.
UNH, Intel and other CIs should step in and fill this kind of gap.
--
David Marchand
^ permalink raw reply
* Re: [PATCH] libsolv: upgrade 0.7.10 -> 0.7.11
From: Richard Purdie @ 2020-02-20 12:24 UTC (permalink / raw)
To: Wang Mingyu, openembedded-core
In-Reply-To: <1582191660-130760-1-git-send-email-wangmy@cn.fujitsu.com>
On Thu, 2020-02-20 at 01:40 -0800, Wang Mingyu wrote:
> Signed-off-by: Wang Mingyu <wangmy@cn.fujitsu.com>
> ---
> .../libsolv/{libsolv_0.7.10.bb => libsolv_0.7.11.bb} | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
> rename meta/recipes-extended/libsolv/{libsolv_0.7.10.bb => libsolv_0.7.11.bb} (93%)
>
> diff --git a/meta/recipes-extended/libsolv/libsolv_0.7.10.bb b/meta/recipes-extended/libsolv/libsolv_0.7.11.bb
> similarity index 93%
> rename from meta/recipes-extended/libsolv/libsolv_0.7.10.bb
> rename to meta/recipes-extended/libsolv/libsolv_0.7.11.bb
> index 502f4e0e85..84349606f1 100644
> --- a/meta/recipes-extended/libsolv/libsolv_0.7.10.bb
> +++ b/meta/recipes-extended/libsolv/libsolv_0.7.11.bb
> @@ -10,7 +10,7 @@ DEPENDS = "expat zlib"
> SRC_URI = "git://github.com/openSUSE/libsolv.git \
> "
>
> -SRCREV = "605dd2645ef899e2b7c95709476fb51e28d7e378"
> +SRCREV = "102ac552669181d3e43731aa275bdbbc7ddcb94c"
>
> UPSTREAM_CHECK_GITTAGREGEX = "(?P<pver>\d+(\.\d+)+)"
>
I think this causes:
https://autobuilder.yoctoproject.org/typhoon/#/builders/61/builds/1591
ERROR: core-image-sato-1.0-r0 do_testimage: core-image-sato - FAILED - check the task log and the ssh log
ERROR: Logfile of failure stored in: /home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/build/tmp/work/qemux86-poky-linux/core-image-sato/1.0-r0/temp/log.do_testimage.5108
NOTE: recipe core-image-sato-1.0-r0: task do_testimage: Failed
ERROR: Task (/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/recipes-sato/images/core-image-sato.bb:do_testimage) failed with exit code '1'
Test requires gtk+3 to be installed
Started HTTPService on 0.0.0.0:35043
Traceback (most recent call last):
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/core/decorator/__init__.py", line 36, in wrapped_f
return func(*args, **kwargs)
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/dnf.py", line 181, in test_dnf_exclude
self.dnf_with_repo('install -y curl*')
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/dnf.py", line 69, in dnf_with_repo
output = self.dnf(" ".join(cmdlinerepoopts) + " --nogpgcheck " + command)
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/dnf.py", line 21, in dnf
self.assertEqual(status, expected, message)
AssertionError: 1 != 0 : dnf --repofrompath=oe-testimage-repo-qemux86,http://192.168.7.3:35043/qemux86 --repofrompath=oe-testimage-repo-noarch,http://192.168.7.3:35043/noarch --repofrompath=oe-testimage-repo-core2_32,http://192.168.7.3:35043/core2_32 --nogpgcheck install -y curl*
Added oe-testimage-repo-qemux86 repo from http://192.168.7.3:35043/qemux86
Added oe-testimage-repo-noarch repo from http://192.168.7.3:35043/noarch
Added oe-testimage-repo-core2_32 repo from http://192.168.7.3:35043/core2_32
Last metadata expiration check: 0:00:01 ago on Thu Feb 20 12:13:09 2020.
Package curl-7.68.0-r0.core2_32 is already installed.
Package curl-dev-7.68.0-r0.core2_32 is already installed.
Dependencies resolved.
================================================================================
Package Architecture Version Repository Size
================================================================================
Installing:
curl-dbg core2_32 7.68.0-r0 oe-testimage-repo-core2_32 36 k
curl-doc core2_32 7.68.0-r0 oe-testimage-repo-core2_32 269 k
Transaction Summary
================================================================================
Install 2 Packages
/usr/lib/python3.8/site-packages/dnf/package.py:57: DeprecationWarning: PY_SSIZE_T_CLEAN will be required for '#' formats
return super(Package, self).chksum
Total download size: 305 k
Installed size: 1.6 M
Downloading Packages:
(1/2): curl-dbg-7.68.0-r0.core2_32.rpm 2.6 MB/s | 36 kB 00:00
(2/2): curl-doc-7.68.0-r0.core2_32.rpm 16 MB/s | 269 kB 00:00
--------------------------------------------------------------------------------
Total 14 MB/s | 305 kB 00:00
Running transaction check
Transaction check succeeded.
Running transaction test
Transaction test succeeded.
Running transaction
Failed to obtain the transaction lock (logged in as: root).
The downloaded packages were saved in cache until the next successful transaction.
You can remove cached packages by executing 'dnf clean packages'.
Error: Could not run transaction.
Traceback (most recent call last):
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/core/decorator/__init__.py", line 36, in wrapped_f
return func(*args, **kwargs)
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/dnf.py", line 90, in test_dnf_install
self.dnf_with_repo('remove -y run-postinsts-dev')
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/dnf.py", line 69, in dnf_with_repo
output = self.dnf(" ".join(cmdlinerepoopts) + " --nogpgcheck " + command)
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/dnf.py", line 21, in dnf
self.assertEqual(status, expected, message)
AssertionError: 1 != 0 : dnf --repofrompath=oe-testimage-repo-qemux86,http://192.168.7.3:35043/qemux86 --repofrompath=oe-testimage-repo-noarch,http://192.168.7.3:35043/noarch --repofrompath=oe-testimage-repo-core2_32,http://192.168.7.3:35043/core2_32 --nogpgcheck remove -y run-postinsts-dev
Added oe-testimage-repo-qemux86 repo from http://192.168.7.3:35043/qemux86
Added oe-testimage-repo-noarch repo from http://192.168.7.3:35043/noarch
Added oe-testimage-repo-core2_32 repo from http://192.168.7.3:35043/core2_32
Dependencies resolved.
================================================================================
Package Architecture Version Repository Size
================================================================================
Removing:
run-postinsts-dev noarch 1.0-r10 @oe-repo 0
Transaction Summary
================================================================================
Remove 1 Package
Freed space: 0
Running transaction check
Transaction check succeeded.
Running transaction test
Transaction test succeeded.
Running transaction
Failed to obtain the transaction lock (logged in as: root).
Error: Could not run transaction.
Test case dnf.DnfRepoTest.test_dnf_install_dependency depends on dnf.DnfRepoTest.test_dnf_install but it didn't pass/run.
Test case dnf.DnfRepoTest.test_dnf_install_from_disk depends on dnf.DnfRepoTest.test_dnf_install_dependency but it didn't pass/run.
Test case dnf.DnfRepoTest.test_dnf_install_from_http depends on dnf.DnfRepoTest.test_dnf_install_from_disk but it didn't pass/run.
Test run when enable usrmege
Test case dnf.DnfRepoTest.test_dnf_reinstall depends on dnf.DnfRepoTest.test_dnf_install but it didn't pass/run.
Stopped HTTPService on 0.0.0.0:35043
Test requires opkg to be installed
Test requires pam to be in DISTRO_FEATURES
Traceback (most recent call last):
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/core/decorator/__init__.py", line 36, in wrapped_f
return func(*args, **kwargs)
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/parselogs.py", line 370, in test_parselogs
self.assertEqual(errcount, 0, msg=self.msg)
AssertionError: 6 != 0 : Log: /home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/build/tmp/work/qemux86-poky-linux/core-image-sato-sdk/1.0-r0/target_logs/dnf.log
-----------------------
Central error: 2020-02-20T12:13:10Z CRITICAL Failed to obtain the transaction lock (logged in as: root).
***********************
2020-02-20T12:13:10Z INFO Total 14 MB/s | 305 kB 00:00
2020-02-20T12:13:10Z INFO Running transaction check
2020-02-20T12:13:10Z INFO Transaction check succeeded.
2020-02-20T12:13:10Z INFO Running transaction test
2020-02-20T12:13:10Z INFO Transaction test succeeded.
2020-02-20T12:13:10Z DDEBUG timer: transaction test: 145 ms
2020-02-20T12:13:10Z INFO Running transaction
2020-02-20T12:13:10Z DEBUG RPMDB altered outside of DNF.
2020-02-20T12:13:10Z DDEBUG RPM transaction start.
2020-02-20T12:13:10Z DDEBUG RPM transaction over.
2020-02-20T12:13:10Z CRITICAL Failed to obtain the transaction lock (logged in as: root).
2020-02-20T12:13:10Z DDEBUG Cleaning up.
2020-02-20T12:13:10Z INFO The downloaded packages were saved in cache until the next successful transaction.
2020-02-20T12:13:10Z INFO You can remove cached packages by executing 'dnf clean packages'.
2020-02-20T12:13:10Z SUBDEBUG
Traceback (most recent call last):
File "/usr/lib/python3.8/site-packages/dnf/cli/main.py", line 64, in main
return _main(base, args, cli_class, option_parser_class)
File "/usr/lib/python3.8/site-packages/dnf/cli/main.py", line 99, in _main
return cli_run(cli, base)
File "/usr/lib/python3.8/site-packages/dnf/cli/main.py", line 123, in cli_run
***********************
Central error: raise dnf.exceptions.Error(msg)
***********************
return cli_run(cli, base)
File "/usr/lib/python3.8/site-packages/dnf/cli/main.py", line 123, in cli_run
ret = resolving(cli, base)
File "/usr/lib/python3.8/site-packages/dnf/cli/main.py", line 167, in resolving
base.do_transaction(display=displays)
File "/usr/lib/python3.8/site-packages/dnf/cli/cli.py", line 225, in do_transaction
tid = super(BaseCli, self).do_transaction(display)
File "/usr/lib/python3.8/site-packages/dnf/base.py", line 882, in do_transaction
tid = self._run_transaction(cb=cb)
File "/usr/lib/python3.8/site-packages/dnf/base.py", line 1005, in _run_transaction
raise dnf.exceptions.Error(msg)
dnf.exceptions.Error: Could not run transaction.
2020-02-20T12:13:10Z CRITICAL Error: Could not run transaction.
2020-02-20T12:13:10Z INFO --- logging initialized ---
2020-02-20T12:13:10Z DDEBUG timer: config: 3 msa
2020-02-20T12:13:10Z DEBUG DNF version: 4.2.2
2020-02-20T12:13:10Z DDEBUG Command: dnf --repofrompath=oe-testimage-repo-qemux86,http://192.168.7.3:35043/qemux86 --repofrompath=oe-testimage-repo-noarch,http://192.168.7.3:35043/noarch --repofrompath=oe-testimage-repo-core2_32,http://192.168.7.3:35043/core2_32 --nogpgcheck list run-postinsts-dev
2020-02-20T12:13:10Z DDEBUG Installroot: /
2020-02-20T12:13:10Z DDEBUG Releasever: master
2020-02-20T12:13:10Z DEBUG cachedir: /var/cache/dnf
2020-02-20T12:13:10Z DDEBUG Base command: list
est requires ptest-runner to be installed
Traceback (most recent call last):
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/core/decorator/__init__.py", line 36, in wrapped_f
return func(*args, **kwargs)
File "/home/pokybuild/yocto-worker/pkgman-rpm-non-rpm/build/meta/lib/oeqa/runtime/cases/rpm.py", line 100, in test_rpm_install
self.assertEqual(status, 0, msg=msg)
AssertionError: 1 != 0 : Failed to install base-passwd-doc package: error: db5 error(-30969) from dbenv->open: BDB0091 DB_VERSION_MISMATCH: Database environment version mismatch
error: cannot open Packages index using db5 - (-30969)
error: cannot open Packages database in /var/lib/rpm
^ permalink raw reply
* Re: [PATCH] firmware: imx: Align imx SC msg structs to 4
From: Leonard Crestez @ 2020-02-20 12:25 UTC (permalink / raw)
To: Stephen Boyd
Cc: Aisheng Dong, Shawn Guo, Fabio Estevam, Michael Turquette,
Stefan Agner, Linus Walleij, Alessandro Zummo, Alexandre Belloni,
Anson Huang, Abel Vesa, Franck Lenormand, kernel@pengutronix.de,
dl-linux-imx, linux-arm-kernel@lists.infradead.org,
linux-clk@vger.kernel.org, linux-gpio@vger.kernel.org,
linux-rtc@vger.kernel.org
In-Reply-To: <158215662160.184098.12475377410437970578@swboyd.mtv.corp.google.com>
On 20.02.2020 01:57, Stephen Boyd wrote:
> Quoting Leonard Crestez (2020-02-11 13:24:33)
>> The imx SC api strongly assumes that messages are composed out of
>> 4-bytes words but some of our message structs have sizeof "6" and "7".
>>
>> This produces many oopses with CONFIG_KASAN=y:
>>
>> BUG: KASAN: stack-out-of-bounds in imx_mu_send_data+0x108/0x1f0
>
> Can you share the full kasan bug report instead of the single line?
[ 1.606708] imx-scu scu: NXP i.MX SCU Initialized
[ 1.635265] random: fast init done
[ 1.652200]
==================================================================
[ 1.659118] BUG: KASAN: stack-out-of-bounds in
imx_mu_send_data+0x108/0x1f0
[ 1.666046] Read of size 4 at addr ffff0008c80e6bc4 by task swapper/0/1
[ 1.672642]
[ 1.674134] CPU: 0 PID: 1 Comm: swapper/0 Not tainted
5.4.3-03848-g13efcd6 #54
[ 1.681335] Hardware name: Freescale i.MX8QM MEK (DT)
[ 1.686373] Call trace:
[ 1.688815] dump_backtrace+0x0/0x1e8
[ 1.692458] show_stack+0x14/0x20
[ 1.695766] dump_stack+0xe8/0x140
[ 1.699155] print_address_description.isra.11+0x64/0x348
[ 1.704532] __kasan_report+0x11c/0x230
[ 1.708356] kasan_report+0xc/0x18
[ 1.711743] __asan_load4+0x90/0xb0
[ 1.715218] imx_mu_send_data+0x108/0x1f0
[ 1.719215] msg_submit+0x104/0x180
[ 1.722689] mbox_send_message+0xa8/0x1a0
[ 1.726696] imx_scu_call_rpc+0x168/0x310
[ 1.730679] imx_sc_pd_power+0x180/0x1e0
[ 1.734589] imx_sc_pd_power_on+0x10/0x18
[ 1.738598] genpd_power_on.part.23+0x118/0x2a8
[ 1.743105] genpd_runtime_resume+0x138/0x320
[ 1.747454] __rpm_callback+0xb0/0x1a0
[ 1.751184] rpm_callback+0x34/0xe0
[ 1.754659] rpm_resume+0x5b8/0x7e8
[ 1.758137] __pm_runtime_resume+0x38/0x90
[ 1.762222] imx_clk_scu_probe+0x5c/0x1c8
[ 1.766218] platform_drv_probe+0x6c/0xc8
[ 1.770217] really_probe+0x148/0x428
[ 1.773861] driver_probe_device+0x74/0x130
[ 1.778031] __device_attach_driver+0xc4/0xe8
[ 1.782380] bus_for_each_drv+0xf0/0x158
[ 1.786283] __device_attach+0x158/0x1d8
[ 1.790195] device_initial_probe+0x10/0x18
[ 1.794362] bus_probe_device+0xe0/0xf0
[ 1.798185] device_add+0x660/0x998
[ 1.801659] platform_device_add+0x198/0x340
[ 1.805916] imx_clk_scu_alloc_dev+0x1b8/0x1e8
[ 1.810347] imx8qxp_clk_probe+0x19d0/0x28b8
[ 1.814601] platform_drv_probe+0x6c/0xc8
[ 1.818601] really_probe+0x148/0x428
[ 1.822250] driver_probe_device+0x74/0x130
[ 1.826423] __device_attach_driver+0xc4/0xe8
[ 1.830763] bus_for_each_drv+0xf0/0x158
[ 1.834675] __device_attach+0x158/0x1d8
[ 1.838583] device_initial_probe+0x10/0x18
[ 1.842752] bus_probe_device+0xe0/0xf0
[ 1.846572] device_add+0x660/0x998
[ 1.850058] of_device_add+0x74/0x98
[ 1.853610] of_platform_device_create_pdata+0x11c/0x178
[ 1.858908] of_platform_bus_create+0x404/0x4f0
[ 1.863425] of_platform_populate+0x74/0x110
[ 1.867688] devm_of_platform_populate+0x54/0xb8
[ 1.872291] imx_scu_probe+0x1b8/0x220
[ 1.876022] platform_drv_probe+0x6c/0xc8
[ 1.880021] really_probe+0x148/0x428
[ 1.883671] driver_probe_device+0x74/0x130
[ 1.887841] device_driver_attach+0x94/0xa0
[ 1.892010] __driver_attach+0x70/0x110
[ 1.895832] bus_for_each_dev+0xe8/0x158
[ 1.899741] driver_attach+0x30/0x40
[ 1.903303] bus_add_driver+0x1b0/0x2b8
[ 1.907129] driver_register+0xbc/0x1d0
[ 1.910947] __platform_driver_register+0x7c/0x88
[ 1.915653] imx_scu_driver_init+0x18/0x20
[ 1.919725] do_one_initcall+0xd4/0x244
[ 1.923552] kernel_init_freeable+0x238/0x2d4
[ 1.927889] kernel_init+0x10/0x114
[ 1.931365] ret_from_fork+0x10/0x18
[ 1.934917]
[ 1.936399] The buggy address belongs to the page:
[ 1.941184] page:fffffe0023003980 refcount:0 mapcount:0
mapping:0000000000000000 index:0x0
[ 1.949447] raw: 1ffff00000000000 fffffe0023003988 fffffe0023003988
0000000000000000
[ 1.957170] raw: 0000000000000000 0000000000000000 00000000ffffffff
0000000000000000
[ 1.964894] page dumped because: kasan: bad access detected
[ 1.970449]
[ 1.971933] addr ffff0008c80e6bc4 is located in stack of task
swapper/0/1 at offset 36 in frame:
[ 1.980708] imx_sc_pd_power+0x0/0x1e0
[ 1.984442]
[ 1.985917] this frame has 1 object:
[ 1.989481] [32, 39) 'msg'
[ 1.989484]
[ 1.993732] Memory state around the buggy address:
[ 1.998520] ffff0008c80e6a80: 00 00 00 00 00 00 00 00 00 00 f1 f1 f1
f1 00 00
[ 2.005730] ffff0008c80e6b00: 00 00 f3 f3 f3 f3 00 00 00 00 00 00 00
00 00 00
[ 2.012940] >ffff0008c80e6b80: 00 00 00 00 f1 f1 f1 f1 07 f2 f2 f2 00
00 00 00
[ 2.020141] ^
[ 2.025448] ffff0008c80e6c00: 00 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00
[ 2.032659] ffff0008c80e6c80: 00 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00
[ 2.039862]
==================================================================
This is actually from an NXP release branch but code is very close up
upstream.
>> It shouldn't cause an issues in normal use because these structs are
>> always allocated on the stack.
>
> Is packed necessary for these? I thought that if the beginning of the
> struct was naturally aligned and there was sometimes a byte or two at
> the end then having __packed wasn't useful. So maybe it's better to just
> drop __packed on all these structs and let the compiler decide it can
> add some padding on the stack? Or do we have arrays of these structs
> sitting in memory all next to each other and they need to be that way to
> be sent through the mailbox?
I'm not sure I understand the question: the structs are __packed because
they represent the binary protocol for communicating with the "System
Controller".
Without __packed the compiler could insert padding inside the structs
and break the protocol.
As far as I understand compilers are still allowed to use padding on
stack since that padding is outside the message struct itself.
--
Regards,
Leonard
^ permalink raw reply
* Re: [PATCH] firmware: imx: Align imx SC msg structs to 4
From: Leonard Crestez @ 2020-02-20 12:25 UTC (permalink / raw)
To: Stephen Boyd
Cc: Aisheng Dong, Alessandro Zummo, Alexandre Belloni, Abel Vesa,
Anson Huang, Michael Turquette, Stefan Agner,
linux-clk@vger.kernel.org, Franck Lenormand,
linux-gpio@vger.kernel.org, dl-linux-imx, kernel@pengutronix.de,
Fabio Estevam, Shawn Guo, Linus Walleij,
linux-arm-kernel@lists.infradead.org, linux-rtc@vger.kernel.org
In-Reply-To: <158215662160.184098.12475377410437970578@swboyd.mtv.corp.google.com>
On 20.02.2020 01:57, Stephen Boyd wrote:
> Quoting Leonard Crestez (2020-02-11 13:24:33)
>> The imx SC api strongly assumes that messages are composed out of
>> 4-bytes words but some of our message structs have sizeof "6" and "7".
>>
>> This produces many oopses with CONFIG_KASAN=y:
>>
>> BUG: KASAN: stack-out-of-bounds in imx_mu_send_data+0x108/0x1f0
>
> Can you share the full kasan bug report instead of the single line?
[ 1.606708] imx-scu scu: NXP i.MX SCU Initialized
[ 1.635265] random: fast init done
[ 1.652200]
==================================================================
[ 1.659118] BUG: KASAN: stack-out-of-bounds in
imx_mu_send_data+0x108/0x1f0
[ 1.666046] Read of size 4 at addr ffff0008c80e6bc4 by task swapper/0/1
[ 1.672642]
[ 1.674134] CPU: 0 PID: 1 Comm: swapper/0 Not tainted
5.4.3-03848-g13efcd6 #54
[ 1.681335] Hardware name: Freescale i.MX8QM MEK (DT)
[ 1.686373] Call trace:
[ 1.688815] dump_backtrace+0x0/0x1e8
[ 1.692458] show_stack+0x14/0x20
[ 1.695766] dump_stack+0xe8/0x140
[ 1.699155] print_address_description.isra.11+0x64/0x348
[ 1.704532] __kasan_report+0x11c/0x230
[ 1.708356] kasan_report+0xc/0x18
[ 1.711743] __asan_load4+0x90/0xb0
[ 1.715218] imx_mu_send_data+0x108/0x1f0
[ 1.719215] msg_submit+0x104/0x180
[ 1.722689] mbox_send_message+0xa8/0x1a0
[ 1.726696] imx_scu_call_rpc+0x168/0x310
[ 1.730679] imx_sc_pd_power+0x180/0x1e0
[ 1.734589] imx_sc_pd_power_on+0x10/0x18
[ 1.738598] genpd_power_on.part.23+0x118/0x2a8
[ 1.743105] genpd_runtime_resume+0x138/0x320
[ 1.747454] __rpm_callback+0xb0/0x1a0
[ 1.751184] rpm_callback+0x34/0xe0
[ 1.754659] rpm_resume+0x5b8/0x7e8
[ 1.758137] __pm_runtime_resume+0x38/0x90
[ 1.762222] imx_clk_scu_probe+0x5c/0x1c8
[ 1.766218] platform_drv_probe+0x6c/0xc8
[ 1.770217] really_probe+0x148/0x428
[ 1.773861] driver_probe_device+0x74/0x130
[ 1.778031] __device_attach_driver+0xc4/0xe8
[ 1.782380] bus_for_each_drv+0xf0/0x158
[ 1.786283] __device_attach+0x158/0x1d8
[ 1.790195] device_initial_probe+0x10/0x18
[ 1.794362] bus_probe_device+0xe0/0xf0
[ 1.798185] device_add+0x660/0x998
[ 1.801659] platform_device_add+0x198/0x340
[ 1.805916] imx_clk_scu_alloc_dev+0x1b8/0x1e8
[ 1.810347] imx8qxp_clk_probe+0x19d0/0x28b8
[ 1.814601] platform_drv_probe+0x6c/0xc8
[ 1.818601] really_probe+0x148/0x428
[ 1.822250] driver_probe_device+0x74/0x130
[ 1.826423] __device_attach_driver+0xc4/0xe8
[ 1.830763] bus_for_each_drv+0xf0/0x158
[ 1.834675] __device_attach+0x158/0x1d8
[ 1.838583] device_initial_probe+0x10/0x18
[ 1.842752] bus_probe_device+0xe0/0xf0
[ 1.846572] device_add+0x660/0x998
[ 1.850058] of_device_add+0x74/0x98
[ 1.853610] of_platform_device_create_pdata+0x11c/0x178
[ 1.858908] of_platform_bus_create+0x404/0x4f0
[ 1.863425] of_platform_populate+0x74/0x110
[ 1.867688] devm_of_platform_populate+0x54/0xb8
[ 1.872291] imx_scu_probe+0x1b8/0x220
[ 1.876022] platform_drv_probe+0x6c/0xc8
[ 1.880021] really_probe+0x148/0x428
[ 1.883671] driver_probe_device+0x74/0x130
[ 1.887841] device_driver_attach+0x94/0xa0
[ 1.892010] __driver_attach+0x70/0x110
[ 1.895832] bus_for_each_dev+0xe8/0x158
[ 1.899741] driver_attach+0x30/0x40
[ 1.903303] bus_add_driver+0x1b0/0x2b8
[ 1.907129] driver_register+0xbc/0x1d0
[ 1.910947] __platform_driver_register+0x7c/0x88
[ 1.915653] imx_scu_driver_init+0x18/0x20
[ 1.919725] do_one_initcall+0xd4/0x244
[ 1.923552] kernel_init_freeable+0x238/0x2d4
[ 1.927889] kernel_init+0x10/0x114
[ 1.931365] ret_from_fork+0x10/0x18
[ 1.934917]
[ 1.936399] The buggy address belongs to the page:
[ 1.941184] page:fffffe0023003980 refcount:0 mapcount:0
mapping:0000000000000000 index:0x0
[ 1.949447] raw: 1ffff00000000000 fffffe0023003988 fffffe0023003988
0000000000000000
[ 1.957170] raw: 0000000000000000 0000000000000000 00000000ffffffff
0000000000000000
[ 1.964894] page dumped because: kasan: bad access detected
[ 1.970449]
[ 1.971933] addr ffff0008c80e6bc4 is located in stack of task
swapper/0/1 at offset 36 in frame:
[ 1.980708] imx_sc_pd_power+0x0/0x1e0
[ 1.984442]
[ 1.985917] this frame has 1 object:
[ 1.989481] [32, 39) 'msg'
[ 1.989484]
[ 1.993732] Memory state around the buggy address:
[ 1.998520] ffff0008c80e6a80: 00 00 00 00 00 00 00 00 00 00 f1 f1 f1
f1 00 00
[ 2.005730] ffff0008c80e6b00: 00 00 f3 f3 f3 f3 00 00 00 00 00 00 00
00 00 00
[ 2.012940] >ffff0008c80e6b80: 00 00 00 00 f1 f1 f1 f1 07 f2 f2 f2 00
00 00 00
[ 2.020141] ^
[ 2.025448] ffff0008c80e6c00: 00 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00
[ 2.032659] ffff0008c80e6c80: 00 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00
[ 2.039862]
==================================================================
This is actually from an NXP release branch but code is very close up
upstream.
>> It shouldn't cause an issues in normal use because these structs are
>> always allocated on the stack.
>
> Is packed necessary for these? I thought that if the beginning of the
> struct was naturally aligned and there was sometimes a byte or two at
> the end then having __packed wasn't useful. So maybe it's better to just
> drop __packed on all these structs and let the compiler decide it can
> add some padding on the stack? Or do we have arrays of these structs
> sitting in memory all next to each other and they need to be that way to
> be sent through the mailbox?
I'm not sure I understand the question: the structs are __packed because
they represent the binary protocol for communicating with the "System
Controller".
Without __packed the compiler could insert padding inside the structs
and break the protocol.
As far as I understand compilers are still allowed to use padding on
stack since that padding is outside the message struct itself.
--
Regards,
Leonard
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH v3 05/37] s390/mm: provide memory management functions for protected KVM guests
From: David Hildenbrand @ 2020-02-20 12:25 UTC (permalink / raw)
To: Christian Borntraeger, Janosch Frank
Cc: KVM, Cornelia Huck, Thomas Huth, Ulrich Weigand, Claudio Imbrenda,
linux-s390, Michael Mueller, Vasily Gorbik, Andrea Arcangeli,
linux-mm
In-Reply-To: <20200220104020.5343-6-borntraeger@de.ibm.com>
On 20.02.20 11:39, Christian Borntraeger wrote:
> From: Claudio Imbrenda <imbrenda@linux.ibm.com>
>
> This provides the basic ultravisor calls and page table handling to cope
> with secure guests:
> - provide arch_make_page_accessible
> - make pages accessible after unmapping of secure guests
> - provide the ultravisor commands convert to/from secure
> - provide the ultravisor commands pin/unpin shared
> - provide callbacks to make pages secure (inacccessible)
> - we check for the expected pin count to only make pages secure if the
> host is not accessing them
> - we fence hugetlbfs for secure pages
>
> Co-developed-by: Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
> Signed-off-by: Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
> Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
> [borntraeger@de.ibm.com: patch merging, splitting, fixing]
> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
--
Thanks,
David / dhildenb
^ permalink raw reply
* [PATCH 1/4] ceph: always renew caps if mds_wanted is insufficient
From: Yan, Zheng @ 2020-02-20 12:26 UTC (permalink / raw)
To: ceph-devel; +Cc: jlayton, Yan, Zheng
Not only after mds closes session and caps get dropped. This is
preparation patch for not requesting caps for idle open files.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
---
fs/ceph/caps.c | 36 +++++++++++++++---------------------
fs/ceph/mds_client.c | 5 -----
fs/ceph/super.h | 1 -
3 files changed, 15 insertions(+), 27 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d05717397c2a..293920d013ff 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2659,6 +2659,7 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
}
} else {
int session_readonly = false;
+ int mds_wanted;
if (ci->i_auth_cap &&
(need & (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_EXCL))) {
struct ceph_mds_session *s = ci->i_auth_cap->session;
@@ -2667,32 +2668,27 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
spin_unlock(&s->s_cap_lock);
}
if (session_readonly) {
- dout("get_cap_refs %p needed %s but mds%d readonly\n",
+ dout("get_cap_refs %p need %s but mds%d readonly\n",
inode, ceph_cap_string(need), ci->i_auth_cap->mds);
ret = -EROFS;
goto out_unlock;
}
- if (ci->i_ceph_flags & CEPH_I_CAP_DROPPED) {
- int mds_wanted;
- if (READ_ONCE(mdsc->fsc->mount_state) ==
- CEPH_MOUNT_SHUTDOWN) {
- dout("get_cap_refs %p forced umount\n", inode);
- ret = -EIO;
- goto out_unlock;
- }
- mds_wanted = __ceph_caps_mds_wanted(ci, false);
- if (need & ~(mds_wanted & need)) {
- dout("get_cap_refs %p caps were dropped"
- " (session killed?)\n", inode);
- ret = -ESTALE;
- goto out_unlock;
- }
- if (!(file_wanted & ~mds_wanted))
- ci->i_ceph_flags &= ~CEPH_I_CAP_DROPPED;
+ if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+ dout("get_cap_refs %p forced umount\n", inode);
+ ret = -EIO;
+ goto out_unlock;
+ }
+ mds_wanted = __ceph_caps_mds_wanted(ci, false);
+ if (need & ~mds_wanted) {
+ dout("get_cap_refs %p need %s > mds_wanted %s\n",
+ inode, ceph_cap_string(need),
+ ceph_cap_string(mds_wanted));
+ ret = -ESTALE;
+ goto out_unlock;
}
- dout("get_cap_refs %p have %s needed %s\n", inode,
+ dout("get_cap_refs %p have %s need %s\n", inode,
ceph_cap_string(have), ceph_cap_string(need));
}
out_unlock:
@@ -3646,8 +3642,6 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
goto out_unlock;
if (target < 0) {
- if (cap->mds_wanted | cap->issued)
- ci->i_ceph_flags |= CEPH_I_CAP_DROPPED;
__ceph_remove_cap(cap, false);
goto out_unlock;
}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index fab9d6461a65..98d746b3bb53 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1411,8 +1411,6 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
dout("removing cap %p, ci is %p, inode is %p\n",
cap, ci, &ci->vfs_inode);
spin_lock(&ci->i_ceph_lock);
- if (cap->mds_wanted | cap->issued)
- ci->i_ceph_flags |= CEPH_I_CAP_DROPPED;
__ceph_remove_cap(cap, false);
if (!ci->i_auth_cap) {
struct ceph_cap_flush *cf;
@@ -1578,9 +1576,6 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap,
/* mds did not re-issue stale cap */
spin_lock(&ci->i_ceph_lock);
cap->issued = cap->implemented = CEPH_CAP_PIN;
- /* make sure mds knows what we want */
- if (__ceph_caps_file_wanted(ci) & ~cap->mds_wanted)
- ci->i_ceph_flags |= CEPH_I_CAP_DROPPED;
spin_unlock(&ci->i_ceph_lock);
}
} else if (ev == FORCE_RO) {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 37dc1ac8f6c3..d370f89df358 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -517,7 +517,6 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
#define CEPH_I_POOL_RD (1 << 4) /* can read from pool */
#define CEPH_I_POOL_WR (1 << 5) /* can write to pool */
#define CEPH_I_SEC_INITED (1 << 6) /* security initialized */
-#define CEPH_I_CAP_DROPPED (1 << 7) /* caps were forcibly dropped */
#define CEPH_I_KICK_FLUSH (1 << 8) /* kick flushing caps */
#define CEPH_I_FLUSH_SNAPS (1 << 9) /* need flush snapss */
#define CEPH_I_ERROR_WRITE (1 << 10) /* have seen write errors */
--
2.21.1
^ permalink raw reply related
* [PATCH 2/4] ceph: consider file's last read/write when calculating wanted caps
From: Yan, Zheng @ 2020-02-20 12:26 UTC (permalink / raw)
To: ceph-devel; +Cc: jlayton, Yan, Zheng
In-Reply-To: <20200220122630.63170-1-zyan@redhat.com>
When getting caps for read/write, update corresponding file's last
read/write. If a file hasn't been read/write for 'caps_wanted_delay_max'
seconds, ignore the file when calculating wanted caps.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
---
fs/ceph/caps.c | 149 ++++++++++++++++++++++++-----------
fs/ceph/file.c | 23 +++---
fs/ceph/inode.c | 15 +++-
fs/ceph/ioctl.c | 4 +-
fs/ceph/super.h | 16 +++-
include/linux/ceph/ceph_fs.h | 1 +
6 files changed, 145 insertions(+), 63 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 293920d013ff..ccdc47bd7cf0 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -971,18 +971,44 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
return used;
}
+#define FMODE_WAIT_BIAS 1000
+
/*
* wanted, by virtue of open file modes
*/
int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
{
+ struct ceph_mount_options *opt =
+ ceph_inode_to_client(&ci->vfs_inode)->mount_options;
+ unsigned long used_cutoff =
+ round_jiffies(jiffies - opt->caps_wanted_delay_max * HZ);
+ unsigned long idle_cutoff =
+ round_jiffies(jiffies - opt->caps_wanted_delay_min * HZ);
int i, bits = 0;
+
for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
- if (ci->i_nr_by_mode[i])
+ if (ci->i_file_by_mode[i].nr >= FMODE_WAIT_BIAS) {
+ /* there are cap waiters or lots of open files */
bits |= 1 << i;
+ } else if (ci->i_file_by_mode[i].nr > 0) {
+ if (i == CEPH_FILE_MODE_PIN ||
+ time_after(ci->i_file_by_mode[i].last_used,
+ used_cutoff))
+ bits |= 1 << i;
+ } else if ((ci->i_file_by_mode[i].last_used & 1)) {
+ if (time_after(ci->i_file_by_mode[i].last_used,
+ idle_cutoff)) {
+ bits |= 1 << i;
+ } else {
+ ci->i_file_by_mode[i].last_used &= ~1UL;
+ }
+ }
}
if (bits == 0)
return 0;
+ if (bits == 1 && !S_ISDIR(ci->vfs_inode.i_mode))
+ return 0;
+
return ceph_caps_for_mode(bits >> 1);
}
@@ -1021,14 +1047,6 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check)
return mds_wanted;
}
-/*
- * called under i_ceph_lock
- */
-static int __ceph_is_single_caps(struct ceph_inode_info *ci)
-{
- return rb_first(&ci->i_caps) == rb_last(&ci->i_caps);
-}
-
int ceph_is_any_caps(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1856,10 +1874,6 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
- if (!(flags & CHECK_CAPS_AUTHONLY) ||
- (ci->i_auth_cap && __ceph_is_single_caps(ci)))
- __cap_delay_cancel(mdsc, ci);
-
goto retry_locked;
retry:
spin_lock(&ci->i_ceph_lock);
@@ -2081,9 +2095,16 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
- /* Reschedule delayed caps release if we delayed anything */
- if (delayed)
- __cap_delay_requeue(mdsc, ci, false);
+ if (list_empty(&ci->i_cap_delay_list)) {
+ if (delayed) {
+ /* Reschedule delayed caps release if we delayed anything */
+ __cap_delay_requeue(mdsc, ci, false);
+ } else if ((file_wanted & ~CEPH_CAP_PIN) &&
+ !(used & (CEPH_CAP_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+ /* periodically re-calculate caps wanted by open files */
+ __cap_delay_requeue(mdsc, ci, true);
+ }
+ }
spin_unlock(&ci->i_ceph_lock);
@@ -2549,8 +2570,9 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got,
* FIXME: how does a 0 return differ from -EAGAIN?
*/
enum {
- NON_BLOCKING = 1,
- CHECK_FILELOCK = 2,
+ /* first 8 bits are reserved for CEPH_FILE_MODE_FOO */
+ NON_BLOCKING = (1 << 8),
+ CHECK_FILELOCK = (1 << 9),
};
static int try_get_cap_refs(struct inode *inode, int need, int want,
@@ -2560,7 +2582,6 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
int ret = 0;
int have, implemented;
- int file_wanted;
bool snap_rwsem_locked = false;
dout("get_cap_refs %p need %s want %s\n", inode,
@@ -2576,15 +2597,6 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
goto out_unlock;
}
- /* make sure file is actually open */
- file_wanted = __ceph_caps_file_wanted(ci);
- if ((file_wanted & need) != need) {
- dout("try_get_cap_refs need %s file_wanted %s, EBADF\n",
- ceph_cap_string(need), ceph_cap_string(file_wanted));
- ret = -EBADF;
- goto out_unlock;
- }
-
/* finish pending truncate */
while (ci->i_truncate_pending) {
spin_unlock(&ci->i_ceph_lock);
@@ -2692,6 +2704,9 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
ceph_cap_string(have), ceph_cap_string(need));
}
out_unlock:
+
+ __ceph_touch_fmode(ci, mdsc, flags);
+
spin_unlock(&ci->i_ceph_lock);
if (snap_rwsem_locked)
up_read(&mdsc->snap_rwsem);
@@ -2729,10 +2744,22 @@ static void check_max_size(struct inode *inode, loff_t endoff)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
}
+static inline int get_used_file_mode(int need, int want)
+{
+ int fmode = 0;
+ if (need & CEPH_CAP_FILE_RD)
+ fmode |= CEPH_FILE_MODE_RD;
+ if (need & CEPH_CAP_FILE_WR)
+ fmode |= CEPH_FILE_MODE_WR;
+ if (want & CEPH_CAP_FILE_LAZYIO)
+ fmode |= CEPH_FILE_MODE_LAZY;
+ return fmode;
+}
+
int ceph_try_get_caps(struct inode *inode, int need, int want,
bool nonblock, int *got)
{
- int ret;
+ int ret, flags;
BUG_ON(need & ~CEPH_CAP_FILE_RD);
BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO|CEPH_CAP_FILE_SHARED));
@@ -2740,8 +2767,11 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
if (ret < 0)
return ret;
- ret = try_get_cap_refs(inode, need, want, 0,
- (nonblock ? NON_BLOCKING : 0), got);
+ flags = get_used_file_mode(need, want);
+ if (nonblock)
+ flags |= NON_BLOCKING;
+
+ ret = try_get_cap_refs(inode, need, want, 0, flags, got);
return ret == -EAGAIN ? 0 : ret;
}
@@ -2767,11 +2797,15 @@ int ceph_get_caps(struct file *filp, int need, int want,
fi->filp_gen != READ_ONCE(fsc->filp_gen))
return -EBADF;
+ flags = get_used_file_mode(need, want);
+
while (true) {
if (endoff > 0)
check_max_size(inode, endoff);
- flags = atomic_read(&fi->num_locks) ? CHECK_FILELOCK : 0;
+ flags &= CEPH_FILE_MODE_MASK;
+ if (atomic_read(&fi->num_locks))
+ flags |= CHECK_FILELOCK;
_got = 0;
ret = try_get_cap_refs(inode, need, want, endoff,
flags, &_got);
@@ -2791,6 +2825,8 @@ int ceph_get_caps(struct file *filp, int need, int want,
list_add(&cw.list, &mdsc->cap_wait_list);
spin_unlock(&mdsc->caps_list_lock);
+ /* make sure used fmode not timeout */
+ ceph_get_fmode(ci, flags, FMODE_WAIT_BIAS);
add_wait_queue(&ci->i_cap_wq, &wait);
flags |= NON_BLOCKING;
@@ -2804,6 +2840,7 @@ int ceph_get_caps(struct file *filp, int need, int want,
}
remove_wait_queue(&ci->i_cap_wq, &wait);
+ ceph_put_fmode(ci, flags, FMODE_WAIT_BIAS);
spin_lock(&mdsc->caps_list_lock);
list_del(&cw.list);
@@ -2823,7 +2860,7 @@ int ceph_get_caps(struct file *filp, int need, int want,
if (ret < 0) {
if (ret == -ESTALE) {
/* session was killed, try renew caps */
- ret = ceph_renew_caps(inode);
+ ret = ceph_renew_caps(inode, flags);
if (ret == 0)
continue;
}
@@ -4121,13 +4158,41 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
dout("flush_dirty_caps done\n");
}
+void __ceph_touch_fmode(struct ceph_inode_info *ci,
+ struct ceph_mds_client *mdsc, int fmode)
+{
+ int i;
+ int bits = (fmode << 1);
+ unsigned long now = jiffies | 1;
+ for (i = 1; i < CEPH_FILE_MODE_BITS; i++) {
+ if (bits & (1 << i))
+ ci->i_file_by_mode[i].last_used = now;
+ }
+
+ /* queue periodic check */
+ if (bits && list_empty(&ci->i_cap_delay_list))
+ __cap_delay_requeue(mdsc, ci, true);
+}
+
+void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
+{
+ int i;
+ int bits = (fmode << 1) | 1;
+ spin_lock(&ci->i_ceph_lock);
+ for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
+ if (bits & (1 << i))
+ ci->i_file_by_mode[i].nr += count;
+ }
+ spin_unlock(&ci->i_ceph_lock);
+}
+
void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode)
{
int i;
int bits = (fmode << 1) | 1;
for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
if (bits & (1 << i))
- ci->i_nr_by_mode[i]++;
+ ci->i_file_by_mode[i].nr++;
}
}
@@ -4136,26 +4201,18 @@ void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode)
* we may need to release capabilities to the MDS (or schedule
* their delayed release).
*/
-void ceph_put_fmode(struct ceph_inode_info *ci, int fmode)
+void ceph_put_fmode(struct ceph_inode_info *ci, int fmode, int count)
{
- int i, last = 0;
+ int i;
int bits = (fmode << 1) | 1;
spin_lock(&ci->i_ceph_lock);
for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
if (bits & (1 << i)) {
- BUG_ON(ci->i_nr_by_mode[i] == 0);
- if (--ci->i_nr_by_mode[i] == 0)
- last++;
+ BUG_ON(ci->i_file_by_mode[i].nr < count);
+ ci->i_file_by_mode[i].nr -= count;
}
}
- dout("put_fmode %p fmode %d {%d,%d,%d,%d}\n",
- &ci->vfs_inode, fmode,
- ci->i_nr_by_mode[0], ci->i_nr_by_mode[1],
- ci->i_nr_by_mode[2], ci->i_nr_by_mode[3]);
spin_unlock(&ci->i_ceph_lock);
-
- if (last && ci->i_vino.snap == CEPH_NOSNAP)
- ceph_check_caps(ci, 0, NULL);
}
/*
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 7e0190b1f821..f28f420bad23 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -213,7 +213,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
struct ceph_dir_file_info *dfi =
kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL);
if (!dfi) {
- ceph_put_fmode(ci, fmode); /* clean up */
+ ceph_put_fmode(ci, fmode, 1); /* clean up */
return -ENOMEM;
}
@@ -224,7 +224,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
} else {
fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
if (!fi) {
- ceph_put_fmode(ci, fmode); /* clean up */
+ ceph_put_fmode(ci, fmode, 1); /* clean up */
return -ENOMEM;
}
@@ -263,7 +263,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
case S_IFLNK:
dout("init_file %p %p 0%o (symlink)\n", inode, file,
inode->i_mode);
- ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
+ ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
break;
default:
@@ -273,7 +273,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
* we need to drop the open ref now, since we don't
* have .release set to ceph_release.
*/
- ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
+ ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
BUG_ON(inode->i_fop->release == ceph_release);
/* call the proper open fop */
@@ -285,14 +285,15 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
/*
* try renew caps after session gets killed.
*/
-int ceph_renew_caps(struct inode *inode)
+int ceph_renew_caps(struct inode *inode, int fmode)
{
- struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+ struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req;
int err, flags, wanted;
spin_lock(&ci->i_ceph_lock);
+ __ceph_touch_fmode(ci, mdsc, fmode);
wanted = __ceph_caps_file_wanted(ci);
if (__ceph_is_any_real_caps(ci) &&
(!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
@@ -405,6 +406,7 @@ int ceph_open(struct inode *inode, struct file *file)
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_get_fmode(ci, fmode);
+ __ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
@@ -525,7 +527,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
}
out_req:
if (!req->r_err && req->r_target_inode)
- ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
+ ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode, 1);
ceph_mdsc_put_request(req);
out_ctx:
ceph_release_acl_sec_ctx(&as_ctx);
@@ -542,7 +544,7 @@ int ceph_release(struct inode *inode, struct file *file)
dout("release inode %p dir file %p\n", inode, file);
WARN_ON(!list_empty(&dfi->file_info.rw_contexts));
- ceph_put_fmode(ci, dfi->file_info.fmode);
+ ceph_put_fmode(ci, dfi->file_info.fmode, 1);
if (dfi->last_readdir)
ceph_mdsc_put_request(dfi->last_readdir);
@@ -554,7 +556,8 @@ int ceph_release(struct inode *inode, struct file *file)
dout("release inode %p regular file %p\n", inode, file);
WARN_ON(!list_empty(&fi->rw_contexts));
- ceph_put_fmode(ci, fi->fmode);
+ ceph_put_fmode(ci, fi->fmode, 1);
+
kmem_cache_free(ceph_file_cachep, fi);
}
@@ -1560,7 +1563,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (dirty)
__mark_inode_dirty(inode, dirty);
if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos))
- ceph_check_caps(ci, CHECK_CAPS_NODELAY, NULL);
+ ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
}
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 094b8fc37787..b279bd8e168e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -478,8 +478,10 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_head_snapc = NULL;
ci->i_snap_caps = 0;
- for (i = 0; i < CEPH_FILE_MODE_BITS; i++)
- ci->i_nr_by_mode[i] = 0;
+ for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
+ ci->i_file_by_mode[i].nr = 0;
+ ci->i_file_by_mode[i].last_used = 0;
+ }
mutex_init(&ci->i_truncate_mutex);
ci->i_truncate_seq = 0;
@@ -637,7 +639,7 @@ int ceph_fill_file_size(struct inode *inode, int issued,
if ((issued & (CEPH_CAP_FILE_CACHE|
CEPH_CAP_FILE_BUFFER)) ||
mapping_mapped(inode->i_mapping) ||
- __ceph_caps_file_wanted(ci)) {
+ __ceph_is_file_opened(ci)) {
ci->i_truncate_pending++;
queue_trunc = 1;
}
@@ -1010,6 +1012,13 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
fill_inline = true;
}
+ if (cap_fmode >= 0) {
+ if (!info_caps)
+ pr_warn("mds issued no caps on %llx.%llx\n",
+ ceph_vinop(inode));
+ __ceph_touch_fmode(ci, mdsc, cap_fmode);
+ }
+
spin_unlock(&ci->i_ceph_lock);
if (fill_inline)
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index c90f03beb15d..da0ee54ae5bc 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -243,11 +243,13 @@ static long ceph_ioctl_lazyio(struct file *file)
struct ceph_file_info *fi = file->private_data;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
spin_lock(&ci->i_ceph_lock);
fi->fmode |= CEPH_FILE_MODE_LAZY;
- ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
+ ci->i_file_by_mode[ffs(CEPH_FILE_MODE_LAZY)].nr++;
+ __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_LAZY);
spin_unlock(&ci->i_ceph_lock);
dout("ioctl_layzio: file %p marked lazy\n", file);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d370f89df358..029823643b8b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -361,7 +361,10 @@ struct ceph_inode_info {
dirty|flushing caps */
unsigned i_snap_caps; /* cap bits for snapped files */
- int i_nr_by_mode[CEPH_FILE_MODE_BITS]; /* open file counts */
+ struct {
+ int nr;
+ unsigned long last_used;
+ } i_file_by_mode[CEPH_FILE_MODE_BITS]; /* open file counts */
struct mutex i_truncate_mutex;
u32 i_truncate_seq; /* last truncate to smaller size */
@@ -673,6 +676,10 @@ extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask);
extern int __ceph_caps_used(struct ceph_inode_info *ci);
+static inline bool __ceph_is_file_opened(struct ceph_inode_info *ci)
+{
+ return ci->i_file_by_mode[0].nr;
+}
extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci);
extern int __ceph_caps_wanted(struct ceph_inode_info *ci);
@@ -1074,7 +1081,10 @@ extern int ceph_try_get_caps(struct inode *inode,
/* for counting open files by mode */
extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode);
-extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode);
+extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count);
+extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count);
+extern void __ceph_touch_fmode(struct ceph_inode_info *ci,
+ struct ceph_mds_client *mdsc, int fmode);
/* addr.c */
extern const struct address_space_operations ceph_aops;
@@ -1086,7 +1096,7 @@ extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
/* file.c */
extern const struct file_operations ceph_file_fops;
-extern int ceph_renew_caps(struct inode *inode);
+extern int ceph_renew_caps(struct inode *inode, int fmode);
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode);
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index cb21c5cf12c3..8017130a08a1 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -564,6 +564,7 @@ struct ceph_filelock {
#define CEPH_FILE_MODE_RDWR 3 /* RD | WR */
#define CEPH_FILE_MODE_LAZY 4 /* lazy io */
#define CEPH_FILE_MODE_BITS 4
+#define CEPH_FILE_MODE_MASK ((1 << CEPH_FILE_MODE_BITS) - 1)
int ceph_flags_to_mode(int flags);
--
2.21.1
^ permalink raw reply related
* [PATCH 3/4] ceph: simplify calling of ceph_get_fmode()
From: Yan, Zheng @ 2020-02-20 12:26 UTC (permalink / raw)
To: ceph-devel; +Cc: jlayton, Yan, Zheng
In-Reply-To: <20200220122630.63170-1-zyan@redhat.com>
Call ceph_get_fmode() when initializing file. Because fill_inode()
already calls ceph_touch_fmode() for open file request. It affects
__ceph_caps_file_wanted() for 'caps_wanted_delay_min' seconds, enough
for ceph_get_fmode() to get called by ceph_init_file_info().
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
---
fs/ceph/caps.c | 26 +++-----------------------
fs/ceph/file.c | 21 +++++----------------
fs/ceph/inode.c | 8 +-------
fs/ceph/super.h | 3 +--
4 files changed, 10 insertions(+), 48 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index ccdc47bd7cf0..2f4ff7e9508e 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -606,7 +606,7 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
*/
void ceph_add_cap(struct inode *inode,
struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
+ unsigned issued, unsigned wanted,
unsigned seq, unsigned mseq, u64 realmino, int flags,
struct ceph_cap **new_cap)
{
@@ -622,13 +622,6 @@ void ceph_add_cap(struct inode *inode,
dout("add_cap %p mds%d cap %llx %s seq %d\n", inode,
session->s_mds, cap_id, ceph_cap_string(issued), seq);
- /*
- * If we are opening the file, include file mode wanted bits
- * in wanted.
- */
- if (fmode >= 0)
- wanted |= ceph_caps_for_mode(fmode);
-
spin_lock(&session->s_gen_ttl_lock);
gen = session->s_cap_gen;
spin_unlock(&session->s_gen_ttl_lock);
@@ -753,9 +746,6 @@ void ceph_add_cap(struct inode *inode,
cap->issue_seq = seq;
cap->mseq = mseq;
cap->cap_gen = gen;
-
- if (fmode >= 0)
- __ceph_get_fmode(ci, fmode);
}
/*
@@ -3726,7 +3716,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
/* add placeholder for the export tagert */
int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
tcap = new_cap;
- ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
+ ceph_add_cap(inode, tsession, t_cap_id, issued, 0,
t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
if (!list_empty(&ci->i_cap_flush_list) &&
@@ -3831,7 +3821,7 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
__ceph_caps_issued(ci, &issued);
issued |= __ceph_caps_dirty(ci);
- ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
+ ceph_add_cap(inode, session, cap_id, caps, wanted, seq, mseq,
realmino, CEPH_CAP_FLAG_AUTH, &new_cap);
ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
@@ -4186,16 +4176,6 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
spin_unlock(&ci->i_ceph_lock);
}
-void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode)
-{
- int i;
- int bits = (fmode << 1) | 1;
- for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
- if (bits & (1 << i))
- ci->i_file_by_mode[i].nr++;
- }
-}
-
/*
* Drop open file reference. If we were the last open file,
* we may need to release capabilities to the MDS (or schedule
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f28f420bad23..60a2dfa02ba2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -212,10 +212,8 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
if (isdir) {
struct ceph_dir_file_info *dfi =
kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL);
- if (!dfi) {
- ceph_put_fmode(ci, fmode, 1); /* clean up */
+ if (!dfi)
return -ENOMEM;
- }
file->private_data = dfi;
fi = &dfi->file_info;
@@ -223,15 +221,15 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
dfi->readdir_cache_idx = -1;
} else {
fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
- if (!fi) {
- ceph_put_fmode(ci, fmode, 1); /* clean up */
+ if (!fi)
return -ENOMEM;
- }
file->private_data = fi;
}
+ ceph_get_fmode(ci, fmode, 1);
fi->fmode = fmode;
+
spin_lock_init(&fi->rw_contexts_lock);
INIT_LIST_HEAD(&fi->rw_contexts);
fi->meta_err = errseq_sample(&ci->i_meta_err);
@@ -263,7 +261,6 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
case S_IFLNK:
dout("init_file %p %p 0%o (symlink)\n", inode, file,
inode->i_mode);
- ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
break;
default:
@@ -273,7 +270,6 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
* we need to drop the open ref now, since we don't
* have .release set to ceph_release.
*/
- ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
BUG_ON(inode->i_fop->release == ceph_release);
/* call the proper open fop */
@@ -327,7 +323,6 @@ int ceph_renew_caps(struct inode *inode, int fmode)
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
- req->r_fmode = -1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
@@ -373,9 +368,6 @@ int ceph_open(struct inode *inode, struct file *file)
/* trivially open snapdir */
if (ceph_snap(inode) == CEPH_SNAPDIR) {
- spin_lock(&ci->i_ceph_lock);
- __ceph_get_fmode(ci, fmode);
- spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
@@ -393,7 +385,7 @@ int ceph_open(struct inode *inode, struct file *file)
dout("open %p fmode %d want %s issued %s using existing\n",
inode, fmode, ceph_cap_string(wanted),
ceph_cap_string(issued));
- __ceph_get_fmode(ci, fmode);
+ __ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
/* adjust wanted? */
@@ -405,7 +397,6 @@ int ceph_open(struct inode *inode, struct file *file)
return ceph_init_file(inode, file, fmode);
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
- __ceph_get_fmode(ci, fmode);
__ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
@@ -526,8 +517,6 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
err = finish_open(file, dentry, ceph_open);
}
out_req:
- if (!req->r_err && req->r_target_inode)
- ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode, 1);
ceph_mdsc_put_request(req);
out_ctx:
ceph_release_acl_sec_ctx(&as_ctx);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index b279bd8e168e..bb73b0c8c4d9 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -969,7 +969,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
if (ceph_snap(inode) == CEPH_NOSNAP) {
ceph_add_cap(inode, session,
le64_to_cpu(info->cap.cap_id),
- cap_fmode, info_caps,
+ info_caps,
le32_to_cpu(info->cap.wanted),
le32_to_cpu(info->cap.seq),
le32_to_cpu(info->cap.mseq),
@@ -994,13 +994,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(info_caps));
ci->i_snap_caps |= info_caps;
- if (cap_fmode >= 0)
- __ceph_get_fmode(ci, cap_fmode);
}
- } else if (cap_fmode >= 0) {
- pr_warn("mds issued no caps on %llx.%llx\n",
- ceph_vinop(inode));
- __ceph_get_fmode(ci, cap_fmode);
}
if (iinfo->inline_version > 0 &&
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 029823643b8b..1ea76466efcb 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1038,7 +1038,7 @@ extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx);
extern void ceph_add_cap(struct inode *inode,
struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
+ unsigned issued, unsigned wanted,
unsigned cap, unsigned seq, u64 realmino, int flags,
struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
@@ -1080,7 +1080,6 @@ extern int ceph_try_get_caps(struct inode *inode,
int need, int want, bool nonblock, int *got);
/* for counting open files by mode */
-extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode);
extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count);
extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count);
extern void __ceph_touch_fmode(struct ceph_inode_info *ci,
--
2.21.1
^ permalink raw reply related
* [PATCH 4/4] ceph: remove delay check logic from ceph_check_caps()
From: Yan, Zheng @ 2020-02-20 12:26 UTC (permalink / raw)
To: ceph-devel; +Cc: jlayton, Yan, Zheng
In-Reply-To: <20200220122630.63170-1-zyan@redhat.com>
__ceph_caps_file_wanted() already checks 'caps_wanted_delay_min' and
'caps_wanted_delay_max'. There is no need to duplicte the logic in
ceph_check_caps() and __send_cap()
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
---
fs/ceph/caps.c | 146 ++++++++++++------------------------------------
fs/ceph/file.c | 5 +-
fs/ceph/inode.c | 1 -
fs/ceph/super.h | 8 +--
4 files changed, 41 insertions(+), 119 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 2f4ff7e9508e..39bf41d0fbdb 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -490,13 +490,10 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
struct ceph_inode_info *ci)
{
struct ceph_mount_options *opt = mdsc->fsc->mount_options;
-
- ci->i_hold_caps_min = round_jiffies(jiffies +
- opt->caps_wanted_delay_min * HZ);
ci->i_hold_caps_max = round_jiffies(jiffies +
opt->caps_wanted_delay_max * HZ);
- dout("__cap_set_timeouts %p min %lu max %lu\n", &ci->vfs_inode,
- ci->i_hold_caps_min - jiffies, ci->i_hold_caps_max - jiffies);
+ dout("__cap_set_timeouts %p %lu\n", &ci->vfs_inode,
+ ci->i_hold_caps_max - jiffies);
}
/*
@@ -508,8 +505,7 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
* -> we take mdsc->cap_delay_lock
*/
static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
- struct ceph_inode_info *ci,
- bool set_timeout)
+ struct ceph_inode_info *ci)
{
dout("__cap_delay_requeue %p flags %d at %lu\n", &ci->vfs_inode,
ci->i_ceph_flags, ci->i_hold_caps_max);
@@ -520,8 +516,7 @@ static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
goto no_change;
list_del_init(&ci->i_cap_delay_list);
}
- if (set_timeout)
- __cap_set_timeouts(mdsc, ci);
+ __cap_set_timeouts(mdsc, ci);
list_add_tail(&ci->i_cap_delay_list, &mdsc->cap_delay_list);
no_change:
spin_unlock(&mdsc->cap_delay_lock);
@@ -719,7 +714,7 @@ void ceph_add_cap(struct inode *inode,
dout(" issued %s, mds wanted %s, actual %s, queueing\n",
ceph_cap_string(issued), ceph_cap_string(wanted),
ceph_cap_string(actual_wanted));
- __cap_delay_requeue(mdsc, ci, true);
+ __cap_delay_requeue(mdsc, ci);
}
if (flags & CEPH_CAP_FLAG_AUTH) {
@@ -1299,7 +1294,6 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
struct cap_msg_args arg;
int held, revoking;
int wake = 0;
- int delayed = 0;
int ret;
held = cap->issued | cap->implemented;
@@ -1312,28 +1306,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
ceph_cap_string(revoking));
BUG_ON((retain & CEPH_CAP_PIN) == 0);
- arg.session = cap->session;
-
- /* don't release wanted unless we've waited a bit. */
- if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 &&
- time_before(jiffies, ci->i_hold_caps_min)) {
- dout(" delaying issued %s -> %s, wanted %s -> %s on send\n",
- ceph_cap_string(cap->issued),
- ceph_cap_string(cap->issued & retain),
- ceph_cap_string(cap->mds_wanted),
- ceph_cap_string(want));
- want |= cap->mds_wanted;
- retain |= cap->issued;
- delayed = 1;
- }
- ci->i_ceph_flags &= ~(CEPH_I_NODELAY | CEPH_I_FLUSH);
- if (want & ~cap->mds_wanted) {
- /* user space may open/close single file frequently.
- * This avoids droping mds_wanted immediately after
- * requesting new mds_wanted.
- */
- __cap_set_timeouts(mdsc, ci);
- }
+ ci->i_ceph_flags &= ~CEPH_I_FLUSH;
cap->issued &= retain; /* drop bits we don't want */
if (cap->implemented & ~cap->issued) {
@@ -1348,6 +1321,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
cap->implemented &= cap->issued | used;
cap->mds_wanted = want;
+ arg.session = cap->session;
arg.ino = ceph_vino(inode).ino;
arg.cid = cap->cap_id;
arg.follows = flushing ? ci->i_head_snapc->seq : 0;
@@ -1408,14 +1382,19 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
ret = send_cap_msg(&arg);
if (ret < 0) {
- dout("error sending cap msg, must requeue %p\n", inode);
- delayed = 1;
+ pr_err("error sending cap msg, ino (%llx.%llx) "
+ "flushing %s tid %llu, requeue\n",
+ ceph_vinop(inode), ceph_cap_string(flushing),
+ flush_tid);
+ spin_lock(&ci->i_ceph_lock);
+ __cap_delay_requeue(mdsc, ci);
+ spin_unlock(&ci->i_ceph_lock);
}
if (wake)
wake_up_all(&ci->i_cap_wq);
- return delayed;
+ return ret;
}
static inline int __send_flush_snap(struct inode *inode,
@@ -1679,7 +1658,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
if (((was | ci->i_flushing_caps) & CEPH_CAP_FILE_BUFFER) &&
(mask & CEPH_CAP_FILE_BUFFER))
dirty |= I_DIRTY_DATASYNC;
- __cap_delay_requeue(mdsc, ci, true);
+ __cap_delay_requeue(mdsc, ci);
return dirty;
}
@@ -1830,8 +1809,6 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci)
* versus held caps. Release, flush, ack revoked caps to mds as
* appropriate.
*
- * CHECK_CAPS_NODELAY - caller is delayed work and we should not delay
- * cap release further.
* CHECK_CAPS_AUTHONLY - we should only check the auth cap
* CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without
* further delay.
@@ -1850,17 +1827,10 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
int mds = -1; /* keep track of how far we've gone through i_caps list
to avoid an infinite loop on retry */
struct rb_node *p;
- int delayed = 0, sent = 0;
- bool no_delay = flags & CHECK_CAPS_NODELAY;
bool queue_invalidate = false;
bool tried_invalidate = false;
- /* if we are unmounting, flush any unused caps immediately. */
- if (mdsc->stopping)
- no_delay = true;
-
spin_lock(&ci->i_ceph_lock);
-
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
@@ -1906,14 +1876,13 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
}
dout("check_caps %p file_want %s used %s dirty %s flushing %s"
- " issued %s revoking %s retain %s %s%s%s\n", inode,
+ " issued %s revoking %s retain %s %s%s\n", inode,
ceph_cap_string(file_wanted),
ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
ceph_cap_string(ci->i_flushing_caps),
ceph_cap_string(issued), ceph_cap_string(revoking),
ceph_cap_string(retain),
(flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
- (flags & CHECK_CAPS_NODELAY) ? " NODELAY" : "",
(flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "");
/*
@@ -1921,7 +1890,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
* have cached pages, but don't want them, then try to invalidate.
* If we fail, it's because pages are locked.... try again later.
*/
- if ((!no_delay || mdsc->stopping) &&
+ if ((!(flags & CHECK_CAPS_NOINVAL) || mdsc->stopping) &&
S_ISREG(inode->i_mode) &&
!(ci->i_wb_ref || ci->i_wrbuffer_ref) && /* no dirty pages... */
inode->i_data.nrpages && /* have cached pages */
@@ -2001,21 +1970,6 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
if ((cap->issued & ~retain) == 0)
continue; /* nope, all good */
- if (no_delay)
- goto ack;
-
- /* delay? */
- if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 &&
- time_before(jiffies, ci->i_hold_caps_max)) {
- dout(" delaying issued %s -> %s, wanted %s -> %s\n",
- ceph_cap_string(cap->issued),
- ceph_cap_string(cap->issued & retain),
- ceph_cap_string(cap->mds_wanted),
- ceph_cap_string(want));
- delayed++;
- continue;
- }
-
ack:
if (session && session != cap->session) {
dout("oops, wrong session %p mutex\n", session);
@@ -2076,24 +2030,18 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
}
mds = cap->mds; /* remember mds, so we don't repeat */
- sent++;
/* __send_cap drops i_ceph_lock */
- delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0,
- cap_used, want, retain, flushing,
- flush_tid, oldest_flush_tid);
+ __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0, cap_used, want,
+ retain, flushing, flush_tid, oldest_flush_tid);
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
- if (list_empty(&ci->i_cap_delay_list)) {
- if (delayed) {
- /* Reschedule delayed caps release if we delayed anything */
- __cap_delay_requeue(mdsc, ci, false);
- } else if ((file_wanted & ~CEPH_CAP_PIN) &&
- !(used & (CEPH_CAP_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
- /* periodically re-calculate caps wanted by open files */
- __cap_delay_requeue(mdsc, ci, true);
- }
+ /* periodically re-calculate caps wanted by open files */
+ if (list_empty(&ci->i_cap_delay_list) &&
+ (file_wanted & ~CEPH_CAP_PIN) &&
+ !(used & (CEPH_CAP_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+ __cap_delay_requeue(mdsc, ci);
}
spin_unlock(&ci->i_ceph_lock);
@@ -2123,7 +2071,6 @@ static int try_flush_caps(struct inode *inode, u64 *ptid)
retry_locked:
if (ci->i_dirty_caps && ci->i_auth_cap) {
struct ceph_cap *cap = ci->i_auth_cap;
- int delayed;
if (session != cap->session) {
spin_unlock(&ci->i_ceph_lock);
@@ -2152,18 +2099,10 @@ static int try_flush_caps(struct inode *inode, u64 *ptid)
&oldest_flush_tid);
/* __send_cap drops i_ceph_lock */
- delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
- CEPH_CLIENT_CAPS_SYNC,
- __ceph_caps_used(ci),
- __ceph_caps_wanted(ci),
- (cap->issued | cap->implemented),
- flushing, flush_tid, oldest_flush_tid);
-
- if (delayed) {
- spin_lock(&ci->i_ceph_lock);
- __cap_delay_requeue(mdsc, ci, true);
- spin_unlock(&ci->i_ceph_lock);
- }
+ __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, CEPH_CLIENT_CAPS_SYNC,
+ __ceph_caps_used(ci), __ceph_caps_wanted(ci),
+ (cap->issued | cap->implemented),
+ flushing, flush_tid, oldest_flush_tid);
} else {
if (!list_empty(&ci->i_cap_flush_list)) {
struct ceph_cap_flush *cf =
@@ -2363,22 +2302,13 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
if (cf->caps) {
dout("kick_flushing_caps %p cap %p tid %llu %s\n",
inode, cap, cf->tid, ceph_cap_string(cf->caps));
- ci->i_ceph_flags |= CEPH_I_NODELAY;
-
- ret = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+ __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
(cf->tid < last_snap_flush ?
CEPH_CLIENT_CAPS_PENDING_CAPSNAP : 0),
__ceph_caps_used(ci),
__ceph_caps_wanted(ci),
(cap->issued | cap->implemented),
cf->caps, cf->tid, oldest_flush_tid);
- if (ret) {
- pr_err("kick_flushing_caps: error sending "
- "cap flush, ino (%llx.%llx) "
- "tid %llu flushing %s\n",
- ceph_vinop(inode), cf->tid,
- ceph_cap_string(cf->caps));
- }
} else {
struct ceph_cap_snap *capsnap =
container_of(cf, struct ceph_cap_snap,
@@ -2999,7 +2929,7 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
last ? " last" : "", put ? " put" : "");
- if (last && !flushsnaps)
+ if (last)
ceph_check_caps(ci, 0, NULL);
else if (flushsnaps)
ceph_flush_snaps(ci, NULL);
@@ -3417,10 +3347,10 @@ static void handle_cap_grant(struct inode *inode,
wake_up_all(&ci->i_cap_wq);
if (check_caps == 1)
- ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_AUTHONLY,
+ ceph_check_caps(ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL,
session);
else if (check_caps == 2)
- ceph_check_caps(ci, CHECK_CAPS_NODELAY, session);
+ ceph_check_caps(ci, CHECK_CAPS_NOINVAL, session);
else
mutex_unlock(&session->s_mutex);
}
@@ -4095,7 +4025,6 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
{
struct inode *inode;
struct ceph_inode_info *ci;
- int flags = CHECK_CAPS_NODELAY;
dout("check_delayed_caps\n");
while (1) {
@@ -4115,7 +4044,7 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
if (inode) {
dout("check_delayed_caps on %p\n", inode);
- ceph_check_caps(ci, flags, NULL);
+ ceph_check_caps(ci, 0, NULL);
/* avoid calling iput_final() in tick thread */
ceph_async_iput(inode);
}
@@ -4140,7 +4069,7 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
ihold(inode);
dout("flush_dirty_caps %p\n", inode);
spin_unlock(&mdsc->cap_dirty_lock);
- ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_FLUSH, NULL);
+ ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL);
iput(inode);
spin_lock(&mdsc->cap_dirty_lock);
}
@@ -4161,7 +4090,7 @@ void __ceph_touch_fmode(struct ceph_inode_info *ci,
/* queue periodic check */
if (bits && list_empty(&ci->i_cap_delay_list))
- __cap_delay_requeue(mdsc, ci, true);
+ __cap_delay_requeue(mdsc, ci);
}
void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
@@ -4210,7 +4139,6 @@ int ceph_drop_caps_for_unlink(struct inode *inode)
if (inode->i_nlink == 1) {
drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN);
- ci->i_ceph_flags |= CEPH_I_NODELAY;
if (__ceph_caps_dirty(ci)) {
struct ceph_mds_client *mdsc =
ceph_inode_to_client(inode)->mdsc;
@@ -4266,8 +4194,6 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
if (force || (cap->issued & drop)) {
if (cap->issued & drop) {
int wanted = __ceph_caps_wanted(ci);
- if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0)
- wanted |= cap->mds_wanted;
dout("encode_inode_release %p cap %p "
"%s -> %s, wanted %s -> %s\n", inode, cap,
ceph_cap_string(cap->issued),
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 60a2dfa02ba2..ed70bb448568 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2129,12 +2129,11 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
if (endoff > size) {
int caps_flags = 0;
-
/* Let the MDS know about dst file size change */
- if (ceph_quota_is_max_bytes_approaching(dst_inode, endoff))
- caps_flags |= CHECK_CAPS_NODELAY;
if (ceph_inode_set_size(dst_inode, endoff))
caps_flags |= CHECK_CAPS_AUTHONLY;
+ if (ceph_quota_is_max_bytes_approaching(dst_inode, endoff))
+ caps_flags |= CHECK_CAPS_AUTHONLY;
if (caps_flags)
ceph_check_caps(dst_ci, caps_flags, NULL);
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index bb73b0c8c4d9..5c8d3b01bc5d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -471,7 +471,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_prealloc_cap_flush = NULL;
INIT_LIST_HEAD(&ci->i_cap_flush_list);
init_waitqueue_head(&ci->i_cap_wq);
- ci->i_hold_caps_min = 0;
ci->i_hold_caps_max = 0;
INIT_LIST_HEAD(&ci->i_cap_delay_list);
INIT_LIST_HEAD(&ci->i_cap_snaps);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1ea76466efcb..9ddaaeefc6f0 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -170,9 +170,9 @@ struct ceph_cap {
struct list_head caps_item;
};
-#define CHECK_CAPS_NODELAY 1 /* do not delay any further */
-#define CHECK_CAPS_AUTHONLY 2 /* only check auth cap */
-#define CHECK_CAPS_FLUSH 4 /* flush any dirty caps */
+#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */
+#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */
+#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */
struct ceph_cap_flush {
u64 tid;
@@ -352,7 +352,6 @@ struct ceph_inode_info {
struct ceph_cap_flush *i_prealloc_cap_flush;
struct list_head i_cap_flush_list;
wait_queue_head_t i_cap_wq; /* threads waiting on a capability */
- unsigned long i_hold_caps_min; /* jiffies */
unsigned long i_hold_caps_max; /* jiffies */
struct list_head i_cap_delay_list; /* for delayed cap release to mds */
struct ceph_cap_reservation i_cap_migration_resv;
@@ -514,7 +513,6 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
* Ceph inode.
*/
#define CEPH_I_DIR_ORDERED (1 << 0) /* dentries in dir are ordered */
-#define CEPH_I_NODELAY (1 << 1) /* do not delay cap release */
#define CEPH_I_FLUSH (1 << 2) /* do not delay flush of dirty metadata */
#define CEPH_I_POOL_PERM (1 << 3) /* pool rd/wr bits are valid */
#define CEPH_I_POOL_RD (1 << 4) /* can read from pool */
--
2.21.1
^ permalink raw reply related
* [PATCH v4 6/9] drm/vmwgfx: Support huge page faults
From: Thomas Hellström (VMware) @ 2020-02-20 12:27 UTC (permalink / raw)
To: linux-mm, dri-devel, linux-kernel
Cc: Thomas Hellstrom, Michal Hocko, pv-drivers, Roland Scheidegger,
Dan Williams, Ralph Campbell, Matthew Wilcox (Oracle),
Jérôme Glisse, linux-graphics-maintainer, Andrew Morton,
Christian König, Kirill A. Shutemov
In-Reply-To: <20200220122719.4302-1-thomas_os@shipmail.org>
From: Thomas Hellstrom <thellstrom@vmware.com>
With vmwgfx dirty-tracking we need a specialized huge_fault
callback. Implement and hook it up.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 4 ++
drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 74 +++++++++++++++++++++-
drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c | 5 +-
3 files changed, 81 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index a31e726d6d71..82d86f2d2569 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1428,6 +1428,10 @@ void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo,
pgoff_t start, pgoff_t end);
vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf);
vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf,
+ enum page_entry_size pe_size);
+#endif
/**
* VMW_DEBUG_KMS - Debug output for kernel mode-setting
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
index 17a5dca7b921..cde3e07ebaf7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
@@ -473,7 +473,7 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf)
* a lot of unnecessary write faults.
*/
if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE)
- prot = vma->vm_page_prot;
+ prot = vm_get_page_prot(vma->vm_flags & ~VM_SHARED);
else
prot = vm_get_page_prot(vma->vm_flags);
@@ -486,3 +486,75 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf)
return ret;
}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf,
+ enum page_entry_size pe_size)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
+ vma->vm_private_data;
+ struct vmw_buffer_object *vbo =
+ container_of(bo, struct vmw_buffer_object, base);
+ pgprot_t prot;
+ vm_fault_t ret;
+ pgoff_t fault_page_size;
+ bool write = vmf->flags & FAULT_FLAG_WRITE;
+ bool is_cow_mapping =
+ (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+
+ switch (pe_size) {
+ case PE_SIZE_PMD:
+ fault_page_size = HPAGE_PMD_SIZE >> PAGE_SHIFT;
+ break;
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+ case PE_SIZE_PUD:
+ fault_page_size = HPAGE_PUD_SIZE >> PAGE_SHIFT;
+ break;
+#endif
+ default:
+ WARN_ON_ONCE(1);
+ return VM_FAULT_FALLBACK;
+ }
+
+ /* Always do write dirty-tracking and COW on PTE level. */
+ if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping))
+ return VM_FAULT_FALLBACK;
+
+ ret = ttm_bo_vm_reserve(bo, vmf);
+ if (ret)
+ return ret;
+
+ if (vbo->dirty) {
+ pgoff_t allowed_prefault;
+ unsigned long page_offset;
+
+ page_offset = vmf->pgoff -
+ drm_vma_node_start(&bo->base.vma_node);
+ if (page_offset >= bo->num_pages ||
+ vmw_resources_clean(vbo, page_offset,
+ page_offset + PAGE_SIZE,
+ &allowed_prefault)) {
+ ret = VM_FAULT_SIGBUS;
+ goto out_unlock;
+ }
+
+ /*
+ * Write protect, so we get a new fault on write, and can
+ * split.
+ */
+ prot = vm_get_page_prot(vma->vm_flags & ~VM_SHARED);
+ } else {
+ prot = vm_get_page_prot(vma->vm_flags);
+ }
+
+ ret = ttm_bo_vm_fault_reserved(vmf, prot, 1, fault_page_size);
+ if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
+ return ret;
+
+out_unlock:
+ dma_resv_unlock(bo->base.resv);
+
+ return ret;
+}
+#endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
index ce288756531b..34100d1f5a9d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
@@ -34,7 +34,10 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma)
.page_mkwrite = vmw_bo_vm_mkwrite,
.fault = vmw_bo_vm_fault,
.open = ttm_bo_vm_open,
- .close = ttm_bo_vm_close
+ .close = ttm_bo_vm_close,
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ .huge_fault = vmw_bo_vm_huge_fault,
+#endif
};
struct drm_file *file_priv = filp->private_data;
struct vmw_private *dev_priv = vmw_priv(file_priv->minor->dev);
--
2.21.1
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.