* [PATCH 5.10 01/48] Input: i8042 - add deferred probe support
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 02/48] Input: i8042 - enable deferred probe quirk for ASUS UM325UA Greg Kroah-Hartman
` (49 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Takashi Iwai, Samuel Čavoj,
Dmitry Torokhov, Sasha Levin
From: Takashi Iwai <tiwai@suse.de>
[ Upstream commit 9222ba68c3f4065f6364b99cc641b6b019ef2d42 ]
We've got a bug report about the non-working keyboard on ASUS ZenBook
UX425UA. It seems that the PS/2 device isn't ready immediately at
boot but takes some seconds to get ready. Until now, the only
workaround is to defer the probe, but it's available only when the
driver is a module. However, many distros, including openSUSE as in
the original report, build the PS/2 input drivers into kernel, hence
it won't work easily.
This patch adds the support for the deferred probe for i8042 stuff as
a workaround of the problem above. When the deferred probe mode is
enabled and the device couldn't be probed, it'll be repeated with the
standard deferred probe mechanism.
The deferred probe mode is enabled either via the new option
i8042.probe_defer or via the quirk table entry. As of this patch, the
quirk table contains only ASUS ZenBook UX425UA.
The deferred probe part is based on Fabio's initial work.
BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1190256
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Samuel Čavoj <samuel@cavoj.net>
Link: https://lore.kernel.org/r/20211117063757.11380-1-tiwai@suse.de
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
.../admin-guide/kernel-parameters.txt | 2 +
drivers/input/serio/i8042-x86ia64io.h | 14 +++++
drivers/input/serio/i8042.c | 54 ++++++++++++-------
3 files changed, 51 insertions(+), 19 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ccaa72562538e..d00618967854d 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1617,6 +1617,8 @@
architectures force reset to be always executed
i8042.unlock [HW] Unlock (ignore) the keylock
i8042.kbdreset [HW] Reset device connected to KBD port
+ i8042.probe_defer
+ [HW] Allow deferred probing upon i8042 probe errors
i810= [HW,DRM]
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index aedd055410443..1acc7c8449294 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -995,6 +995,17 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
{ }
};
+static const struct dmi_system_id i8042_dmi_probe_defer_table[] __initconst = {
+ {
+ /* ASUS ZenBook UX425UA */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"),
+ },
+ },
+ { }
+};
+
#endif /* CONFIG_X86 */
#ifdef CONFIG_PNP
@@ -1315,6 +1326,9 @@ static int __init i8042_platform_init(void)
if (dmi_check_system(i8042_dmi_kbdreset_table))
i8042_kbdreset = true;
+ if (dmi_check_system(i8042_dmi_probe_defer_table))
+ i8042_probe_defer = true;
+
/*
* A20 was already enabled during early kernel init. But some buggy
* BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index abae23af0791e..a9f68f535b727 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -45,6 +45,10 @@ static bool i8042_unlock;
module_param_named(unlock, i8042_unlock, bool, 0);
MODULE_PARM_DESC(unlock, "Ignore keyboard lock.");
+static bool i8042_probe_defer;
+module_param_named(probe_defer, i8042_probe_defer, bool, 0);
+MODULE_PARM_DESC(probe_defer, "Allow deferred probing.");
+
enum i8042_controller_reset_mode {
I8042_RESET_NEVER,
I8042_RESET_ALWAYS,
@@ -711,7 +715,7 @@ static int i8042_set_mux_mode(bool multiplex, unsigned char *mux_version)
* LCS/Telegraphics.
*/
-static int __init i8042_check_mux(void)
+static int i8042_check_mux(void)
{
unsigned char mux_version;
@@ -740,10 +744,10 @@ static int __init i8042_check_mux(void)
/*
* The following is used to test AUX IRQ delivery.
*/
-static struct completion i8042_aux_irq_delivered __initdata;
-static bool i8042_irq_being_tested __initdata;
+static struct completion i8042_aux_irq_delivered;
+static bool i8042_irq_being_tested;
-static irqreturn_t __init i8042_aux_test_irq(int irq, void *dev_id)
+static irqreturn_t i8042_aux_test_irq(int irq, void *dev_id)
{
unsigned long flags;
unsigned char str, data;
@@ -770,7 +774,7 @@ static irqreturn_t __init i8042_aux_test_irq(int irq, void *dev_id)
* verifies success by readinng CTR. Used when testing for presence of AUX
* port.
*/
-static int __init i8042_toggle_aux(bool on)
+static int i8042_toggle_aux(bool on)
{
unsigned char param;
int i;
@@ -798,7 +802,7 @@ static int __init i8042_toggle_aux(bool on)
* the presence of an AUX interface.
*/
-static int __init i8042_check_aux(void)
+static int i8042_check_aux(void)
{
int retval = -1;
bool irq_registered = false;
@@ -1005,7 +1009,7 @@ static int i8042_controller_init(void)
if (i8042_command(&ctr[n++ % 2], I8042_CMD_CTL_RCTR)) {
pr_err("Can't read CTR while initializing i8042\n");
- return -EIO;
+ return i8042_probe_defer ? -EPROBE_DEFER : -EIO;
}
} while (n < 2 || ctr[0] != ctr[1]);
@@ -1320,7 +1324,7 @@ static void i8042_shutdown(struct platform_device *dev)
i8042_controller_reset(false);
}
-static int __init i8042_create_kbd_port(void)
+static int i8042_create_kbd_port(void)
{
struct serio *serio;
struct i8042_port *port = &i8042_ports[I8042_KBD_PORT_NO];
@@ -1349,7 +1353,7 @@ static int __init i8042_create_kbd_port(void)
return 0;
}
-static int __init i8042_create_aux_port(int idx)
+static int i8042_create_aux_port(int idx)
{
struct serio *serio;
int port_no = idx < 0 ? I8042_AUX_PORT_NO : I8042_MUX_PORT_NO + idx;
@@ -1386,13 +1390,13 @@ static int __init i8042_create_aux_port(int idx)
return 0;
}
-static void __init i8042_free_kbd_port(void)
+static void i8042_free_kbd_port(void)
{
kfree(i8042_ports[I8042_KBD_PORT_NO].serio);
i8042_ports[I8042_KBD_PORT_NO].serio = NULL;
}
-static void __init i8042_free_aux_ports(void)
+static void i8042_free_aux_ports(void)
{
int i;
@@ -1402,7 +1406,7 @@ static void __init i8042_free_aux_ports(void)
}
}
-static void __init i8042_register_ports(void)
+static void i8042_register_ports(void)
{
int i;
@@ -1443,7 +1447,7 @@ static void i8042_free_irqs(void)
i8042_aux_irq_registered = i8042_kbd_irq_registered = false;
}
-static int __init i8042_setup_aux(void)
+static int i8042_setup_aux(void)
{
int (*aux_enable)(void);
int error;
@@ -1485,7 +1489,7 @@ static int __init i8042_setup_aux(void)
return error;
}
-static int __init i8042_setup_kbd(void)
+static int i8042_setup_kbd(void)
{
int error;
@@ -1535,7 +1539,7 @@ static int i8042_kbd_bind_notifier(struct notifier_block *nb,
return 0;
}
-static int __init i8042_probe(struct platform_device *dev)
+static int i8042_probe(struct platform_device *dev)
{
int error;
@@ -1600,6 +1604,7 @@ static struct platform_driver i8042_driver = {
.pm = &i8042_pm_ops,
#endif
},
+ .probe = i8042_probe,
.remove = i8042_remove,
.shutdown = i8042_shutdown,
};
@@ -1610,7 +1615,6 @@ static struct notifier_block i8042_kbd_bind_notifier_block = {
static int __init i8042_init(void)
{
- struct platform_device *pdev;
int err;
dbg_init();
@@ -1626,17 +1630,29 @@ static int __init i8042_init(void)
/* Set this before creating the dev to allow i8042_command to work right away */
i8042_present = true;
- pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0);
- if (IS_ERR(pdev)) {
- err = PTR_ERR(pdev);
+ err = platform_driver_register(&i8042_driver);
+ if (err)
goto err_platform_exit;
+
+ i8042_platform_device = platform_device_alloc("i8042", -1);
+ if (!i8042_platform_device) {
+ err = -ENOMEM;
+ goto err_unregister_driver;
}
+ err = platform_device_add(i8042_platform_device);
+ if (err)
+ goto err_free_device;
+
bus_register_notifier(&serio_bus, &i8042_kbd_bind_notifier_block);
panic_blink = i8042_panic_blink;
return 0;
+err_free_device:
+ platform_device_put(i8042_platform_device);
+err_unregister_driver:
+ platform_driver_unregister(&i8042_driver);
err_platform_exit:
i8042_platform_exit();
return err;
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 02/48] Input: i8042 - enable deferred probe quirk for ASUS UM325UA
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 01/48] Input: i8042 - add deferred probe support Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 03/48] tomoyo: Check exceeded quota early in tomoyo_domain_quota_is_ok() Greg Kroah-Hartman
` (48 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Samuel Čavoj, Dmitry Torokhov,
Sasha Levin
From: Samuel Čavoj <samuel@cavoj.net>
[ Upstream commit 44ee250aeeabb28b52a10397ac17ffb8bfe94839 ]
The ASUS UM325UA suffers from the same issue as the ASUS UX425UA, which
is a very similar laptop. The i8042 device is not usable immediately
after boot and fails to initialize, requiring a deferred retry.
Enable the deferred probe quirk for the UM325UA.
BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1190256
Signed-off-by: Samuel Čavoj <samuel@cavoj.net>
Link: https://lore.kernel.org/r/20211204015615.232948-1-samuel@cavoj.net
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/input/serio/i8042-x86ia64io.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 1acc7c8449294..148a7c5fd0e22 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -1003,6 +1003,13 @@ static const struct dmi_system_id i8042_dmi_probe_defer_table[] __initconst = {
DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"),
},
},
+ {
+ /* ASUS ZenBook UM325UA */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"),
+ },
+ },
{ }
};
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 03/48] tomoyo: Check exceeded quota early in tomoyo_domain_quota_is_ok().
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 01/48] Input: i8042 - add deferred probe support Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 02/48] Input: i8042 - enable deferred probe quirk for ASUS UM325UA Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 04/48] tomoyo: use hwight16() " Greg Kroah-Hartman
` (47 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Dmitry Vyukov, Tetsuo Handa, Sasha Levin
From: Dmitry Vyukov <dvyukov@google.com>
[ Upstream commit 04e57a2d952bbd34bc45744e72be3eecdc344294 ]
If tomoyo is used in a testing/fuzzing environment in learning mode,
for lots of domains the quota will be exceeded and stay exceeded
for prolonged periods of time. In such cases it's pointless (and slow)
to walk the whole acl list again and again just to rediscover that
the quota is exceeded. We already have the TOMOYO_DIF_QUOTA_WARNED flag
that notes the overflow condition. Check it early to avoid the slowdown.
[penguin-kernel]
This patch causes a user visible change that the learning mode will not be
automatically resumed after the quota is increased. To resume the learning
mode, administrator will need to explicitly clear TOMOYO_DIF_QUOTA_WARNED
flag after increasing the quota. But I think that this change is generally
preferable, for administrator likely wants to optimize the acl list for
that domain before increasing the quota, or that domain likely hits the
quota again. Therefore, don't try to care to clear TOMOYO_DIF_QUOTA_WARNED
flag automatically when the quota for that domain changed.
Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
security/tomoyo/util.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c
index cd458e10cf2af..ee9c2aa0c8df9 100644
--- a/security/tomoyo/util.c
+++ b/security/tomoyo/util.c
@@ -1046,6 +1046,8 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
return false;
if (!domain)
return true;
+ if (READ_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED]))
+ return false;
list_for_each_entry_rcu(ptr, &domain->acl_info_list, list,
srcu_read_lock_held(&tomoyo_ss)) {
u16 perm;
@@ -1091,14 +1093,12 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
if (count < tomoyo_profile(domain->ns, domain->profile)->
pref[TOMOYO_PREF_MAX_LEARNING_ENTRY])
return true;
- if (!domain->flags[TOMOYO_DIF_QUOTA_WARNED]) {
- domain->flags[TOMOYO_DIF_QUOTA_WARNED] = true;
- /* r->granted = false; */
- tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]);
+ WRITE_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED], true);
+ /* r->granted = false; */
+ tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]);
#ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
- pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n",
- domain->domainname->name);
+ pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n",
+ domain->domainname->name);
#endif
- }
return false;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 04/48] tomoyo: use hwight16() in tomoyo_domain_quota_is_ok()
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (2 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 03/48] tomoyo: Check exceeded quota early in tomoyo_domain_quota_is_ok() Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 05/48] parisc: Clear stale IIR value on instruction access rights trap Greg Kroah-Hartman
` (46 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Tetsuo Handa, Sasha Levin
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
[ Upstream commit f702e1107601230eec707739038a89018ea3468d ]
hwight16() is much faster. While we are at it, no need to include
"perm =" part into data_race() macro, for perm is a local variable
that cannot be accessed by other threads.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
security/tomoyo/util.c | 17 +++++++----------
1 file changed, 7 insertions(+), 10 deletions(-)
diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c
index ee9c2aa0c8df9..11dd8260c9cc7 100644
--- a/security/tomoyo/util.c
+++ b/security/tomoyo/util.c
@@ -1051,7 +1051,6 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
list_for_each_entry_rcu(ptr, &domain->acl_info_list, list,
srcu_read_lock_held(&tomoyo_ss)) {
u16 perm;
- u8 i;
if (ptr->is_deleted)
continue;
@@ -1062,23 +1061,23 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
*/
switch (ptr->type) {
case TOMOYO_TYPE_PATH_ACL:
- data_race(perm = container_of(ptr, struct tomoyo_path_acl, head)->perm);
+ perm = data_race(container_of(ptr, struct tomoyo_path_acl, head)->perm);
break;
case TOMOYO_TYPE_PATH2_ACL:
- data_race(perm = container_of(ptr, struct tomoyo_path2_acl, head)->perm);
+ perm = data_race(container_of(ptr, struct tomoyo_path2_acl, head)->perm);
break;
case TOMOYO_TYPE_PATH_NUMBER_ACL:
- data_race(perm = container_of(ptr, struct tomoyo_path_number_acl, head)
+ perm = data_race(container_of(ptr, struct tomoyo_path_number_acl, head)
->perm);
break;
case TOMOYO_TYPE_MKDEV_ACL:
- data_race(perm = container_of(ptr, struct tomoyo_mkdev_acl, head)->perm);
+ perm = data_race(container_of(ptr, struct tomoyo_mkdev_acl, head)->perm);
break;
case TOMOYO_TYPE_INET_ACL:
- data_race(perm = container_of(ptr, struct tomoyo_inet_acl, head)->perm);
+ perm = data_race(container_of(ptr, struct tomoyo_inet_acl, head)->perm);
break;
case TOMOYO_TYPE_UNIX_ACL:
- data_race(perm = container_of(ptr, struct tomoyo_unix_acl, head)->perm);
+ perm = data_race(container_of(ptr, struct tomoyo_unix_acl, head)->perm);
break;
case TOMOYO_TYPE_MANUAL_TASK_ACL:
perm = 0;
@@ -1086,9 +1085,7 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
default:
perm = 1;
}
- for (i = 0; i < 16; i++)
- if (perm & (1 << i))
- count++;
+ count += hweight16(perm);
}
if (count < tomoyo_profile(domain->ns, domain->profile)->
pref[TOMOYO_PREF_MAX_LEARNING_ENTRY])
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 05/48] parisc: Clear stale IIR value on instruction access rights trap
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (3 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 04/48] tomoyo: use hwight16() " Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 06/48] platform/x86: apple-gmux: use resource_size() with res Greg Kroah-Hartman
` (45 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Helge Deller, Sasha Levin, John David Anglin
From: Helge Deller <deller@gmx.de>
[ Upstream commit 484730e5862f6b872dca13840bed40fd7c60fa26 ]
When a trap 7 (Instruction access rights) occurs, this means the CPU
couldn't execute an instruction due to missing execute permissions on
the memory region. In this case it seems the CPU didn't even fetched
the instruction from memory and thus did not store it in the cr19 (IIR)
register before calling the trap handler. So, the trap handler will find
some random old stale value in cr19.
This patch simply overwrites the stale IIR value with a constant magic
"bad food" value (0xbaadf00d), in the hope people don't start to try to
understand the various random IIR values in trap 7 dumps.
Noticed-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/parisc/kernel/traps.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index a52c7abf2ca49..43f56335759a4 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -729,6 +729,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
}
mmap_read_unlock(current->mm);
}
+ /* CPU could not fetch instruction, so clear stale IIR value. */
+ regs->iir = 0xbaadf00d;
fallthrough;
case 27:
/* Data memory protection ID trap */
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 06/48] platform/x86: apple-gmux: use resource_size() with res
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (4 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 05/48] parisc: Clear stale IIR value on instruction access rights trap Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 07/48] memblock: fix memblock_phys_alloc() section mismatch error Greg Kroah-Hartman
` (44 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Wang Qing, Hans de Goede, Sasha Levin
From: Wang Qing <wangqing@vivo.com>
[ Upstream commit eb66fb03a727cde0ab9b1a3858de55c26f3007da ]
This should be (res->end - res->start + 1) here actually,
use resource_size() derectly.
Signed-off-by: Wang Qing <wangqing@vivo.com>
Link: https://lore.kernel.org/r/1639484316-75873-1-git-send-email-wangqing@vivo.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/platform/x86/apple-gmux.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index 9aae45a452002..57553f9b4d1dc 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -625,7 +625,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
}
gmux_data->iostart = res->start;
- gmux_data->iolen = res->end - res->start;
+ gmux_data->iolen = resource_size(res);
if (gmux_data->iolen < GMUX_MIN_IO_LEN) {
pr_err("gmux I/O region too small (%lu < %u)\n",
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 07/48] memblock: fix memblock_phys_alloc() section mismatch error
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (5 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 06/48] platform/x86: apple-gmux: use resource_size() with res Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 08/48] recordmcount.pl: fix typo in s390 mcount regex Greg Kroah-Hartman
` (43 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, k2ci, Mike Rapoport, Jackie Liu,
Mike Rapoport, Sasha Levin
From: Jackie Liu <liuyun01@kylinos.cn>
[ Upstream commit d7f55471db2719629f773c2d6b5742a69595bfd3 ]
Fix modpost Section mismatch error in memblock_phys_alloc()
[...]
WARNING: modpost: vmlinux.o(.text.unlikely+0x1dcc): Section mismatch in reference
from the function memblock_phys_alloc() to the function .init.text:memblock_phys_alloc_range()
The function memblock_phys_alloc() references
the function __init memblock_phys_alloc_range().
This is often because memblock_phys_alloc lacks a __init
annotation or the annotation of memblock_phys_alloc_range is wrong.
ERROR: modpost: Section mismatches detected.
Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them.
[...]
memblock_phys_alloc() is a one-line wrapper, make it __always_inline to
avoid these section mismatches.
Reported-by: k2ci <kernel-bot@kylinos.cn>
Suggested-by: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
[rppt: slightly massaged changelog ]
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Link: https://lore.kernel.org/r/20211217020754.2874872-1-liu.yun@linux.dev
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
include/linux/memblock.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 1a8d25f2e0412..3baea2ef33fbb 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -387,8 +387,8 @@ phys_addr_t memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t end, int nid, bool exact_nid);
phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
-static inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
- phys_addr_t align)
+static __always_inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
+ phys_addr_t align)
{
return memblock_phys_alloc_range(size, align, 0,
MEMBLOCK_ALLOC_ACCESSIBLE);
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 08/48] recordmcount.pl: fix typo in s390 mcount regex
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (6 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 07/48] memblock: fix memblock_phys_alloc() section mismatch error Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 09/48] selinux: initialize proto variable in selinux_ip_postroute_compat() Greg Kroah-Hartman
` (42 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Miroslav Benes, Jerome Marchand,
Heiko Carstens
From: Heiko Carstens <hca@linux.ibm.com>
commit 4eb1782eaa9fa1c224ad1fa0d13a9f09c3ab2d80 upstream.
Commit 85bf17b28f97 ("recordmcount.pl: look for jgnop instruction as well
as bcrl on s390") added a new alternative mnemonic for the existing brcl
instruction. This is required for the combination old gcc version (pre 9.0)
and binutils since version 2.37.
However at the same time this commit introduced a typo, replacing brcl with
bcrl. As a result no mcount locations are detected anymore with old gcc
versions (pre 9.0) and binutils before version 2.37.
Fix this by using the correct mnemonic again.
Reported-by: Miroslav Benes <mbenes@suse.cz>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: <stable@vger.kernel.org>
Fixes: 85bf17b28f97 ("recordmcount.pl: look for jgnop instruction as well as bcrl on s390")
Link: https://lore.kernel.org/r/alpine.LSU.2.21.2112230949520.19849@pobox.suse.cz
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
scripts/recordmcount.pl | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -252,7 +252,7 @@ if ($arch eq "x86_64") {
} elsif ($arch eq "s390" && $bits == 64) {
if ($cc =~ /-DCC_USING_HOTPATCH/) {
- $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(bcrl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$";
+ $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(brcl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$";
$mcount_adjust = 0;
} else {
$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_(PC|PLT)32DBL\\s+_mcount\\+0x2\$";
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 09/48] selinux: initialize proto variable in selinux_ip_postroute_compat()
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (7 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 08/48] recordmcount.pl: fix typo in s390 mcount regex Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 10/48] scsi: lpfc: Terminate string in lpfc_debugfs_nvmeio_trc_write() Greg Kroah-Hartman
` (41 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Tom Rix, Paul Moore
From: Tom Rix <trix@redhat.com>
commit 732bc2ff080c447f8524f40c970c481f5da6eed3 upstream.
Clang static analysis reports this warning
hooks.c:5765:6: warning: 4th function call argument is an uninitialized
value
if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto))
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
selinux_parse_skb() can return ok without setting proto. The later call
to selinux_xfrm_postroute_last() does an early check of proto and can
return ok if the garbage proto value matches. So initialize proto.
Cc: stable@vger.kernel.org
Fixes: eef9b41622f2 ("selinux: cleanup selinux_xfrm_sock_rcv_skb() and selinux_xfrm_postroute_last()")
Signed-off-by: Tom Rix <trix@redhat.com>
[PM: typo/spelling and checkpatch.pl description fixes]
Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
security/selinux/hooks.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5665,7 +5665,7 @@ static unsigned int selinux_ip_postroute
struct common_audit_data ad;
struct lsm_network_audit net = {0,};
char *addrp;
- u8 proto;
+ u8 proto = 0;
if (sk == NULL)
return NF_ACCEPT;
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 10/48] scsi: lpfc: Terminate string in lpfc_debugfs_nvmeio_trc_write()
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (8 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 09/48] selinux: initialize proto variable in selinux_ip_postroute_compat() Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 11/48] net/mlx5: DR, Fix NULL vs IS_ERR checking in dr_domain_init_resources Greg Kroah-Hartman
` (40 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, James Smart, Dan Carpenter,
Martin K. Petersen, Sasha Levin
From: Dan Carpenter <dan.carpenter@oracle.com>
[ Upstream commit 9020be114a47bf7ff33e179b3bb0016b91a098e6 ]
The "mybuf" string comes from the user, so we need to ensure that it is NUL
terminated.
Link: https://lore.kernel.org/r/20211214070527.GA27934@kili
Fixes: bd2cdd5e400f ("scsi: lpfc: NVME Initiator: Add debugfs support")
Reviewed-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/scsi/lpfc/lpfc_debugfs.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index b89c5513243e8..beaf3a8d206f8 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -2956,8 +2956,8 @@ lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf,
char mybuf[64];
char *pbuf;
- if (nbytes > 64)
- nbytes = 64;
+ if (nbytes > 63)
+ nbytes = 63;
memset(mybuf, 0, sizeof(mybuf));
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 11/48] net/mlx5: DR, Fix NULL vs IS_ERR checking in dr_domain_init_resources
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (9 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 10/48] scsi: lpfc: Terminate string in lpfc_debugfs_nvmeio_trc_write() Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 12/48] net/mlx5e: Wrap the tx reporter dump callback to extract the sq Greg Kroah-Hartman
` (39 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Miaoqian Lin, Saeed Mahameed, Sasha Levin
From: Miaoqian Lin <linmq006@gmail.com>
[ Upstream commit 6b8b42585886c59a008015083282aae434349094 ]
The mlx5_get_uars_page() function returns error pointers.
Using IS_ERR() to check the return value to fix this.
Fixes: 4ec9e7b02697 ("net/mlx5: DR, Expose steering domain functionality")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 00d861361428f..16a7c7ec5e138 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2019 Mellanox Technologies. */
#include <linux/mlx5/eswitch.h>
+#include <linux/err.h>
#include "dr_types.h"
#define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type) \
@@ -69,9 +70,9 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn)
}
dmn->uar = mlx5_get_uars_page(dmn->mdev);
- if (!dmn->uar) {
+ if (IS_ERR(dmn->uar)) {
mlx5dr_err(dmn, "Couldn't allocate UAR\n");
- ret = -ENOMEM;
+ ret = PTR_ERR(dmn->uar);
goto clean_pd;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 12/48] net/mlx5e: Wrap the tx reporter dump callback to extract the sq
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (10 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 11/48] net/mlx5: DR, Fix NULL vs IS_ERR checking in dr_domain_init_resources Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 13/48] net/mlx5e: Fix ICOSQ recovery flow for XSK Greg Kroah-Hartman
` (38 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Aya Levin, Amir Tzin, Saeed Mahameed,
Sasha Levin
From: Amir Tzin <amirtz@nvidia.com>
[ Upstream commit 918fc3855a6507a200e9cf22c20be852c0982687 ]
Function mlx5e_tx_reporter_dump_sq() casts its void * argument to struct
mlx5e_txqsq *, but in TX-timeout-recovery flow the argument is actually
of type struct mlx5e_tx_timeout_ctx *.
mlx5_core 0000:08:00.1 enp8s0f1: TX timeout detected
mlx5_core 0000:08:00.1 enp8s0f1: TX timeout on queue: 1, SQ: 0x11ec, CQ: 0x146d, SQ Cons: 0x0 SQ Prod: 0x1, usecs since last trans: 21565000
BUG: stack guard page was hit at 0000000093f1a2de (stack is 00000000b66ea0dc..000000004d932dae)
kernel stack overflow (page fault): 0000 [#1] SMP NOPTI
CPU: 5 PID: 95 Comm: kworker/u20:1 Tainted: G W OE 5.13.0_mlnx #1
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core]
RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
[mlx5_core]
Call Trace:
mlx5e_tx_reporter_dump+0x43/0x1c0 [mlx5_core]
devlink_health_do_dump.part.91+0x71/0xd0
devlink_health_report+0x157/0x1b0
mlx5e_reporter_tx_timeout+0xb9/0xf0 [mlx5_core]
? mlx5e_tx_reporter_err_cqe_recover+0x1d0/0x1d0
[mlx5_core]
? mlx5e_health_queue_dump+0xd0/0xd0 [mlx5_core]
? update_load_avg+0x19b/0x550
? set_next_entity+0x72/0x80
? pick_next_task_fair+0x227/0x340
? finish_task_switch+0xa2/0x280
mlx5e_tx_timeout_work+0x83/0xb0 [mlx5_core]
process_one_work+0x1de/0x3a0
worker_thread+0x2d/0x3c0
? process_one_work+0x3a0/0x3a0
kthread+0x115/0x130
? kthread_park+0x90/0x90
ret_from_fork+0x1f/0x30
--[ end trace 51ccabea504edaff ]---
RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
PKRU: 55555554
Kernel panic - not syncing: Fatal exception
Kernel Offset: disabled
end Kernel panic - not syncing: Fatal exception
To fix this bug add a wrapper for mlx5e_tx_reporter_dump_sq() which
extracts the sq from struct mlx5e_tx_timeout_ctx and set it as the
TX-timeout-recovery flow dump callback.
Fixes: 5f29458b77d5 ("net/mlx5e: Support dump callback in TX reporter")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
.../net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 8be6eaa3eeb14..13dd34c571b9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -335,6 +335,14 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms
return mlx5e_health_fmsg_named_obj_nest_end(fmsg);
}
+static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg,
+ void *ctx)
+{
+ struct mlx5e_tx_timeout_ctx *to_ctx = ctx;
+
+ return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq);
+}
+
static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
struct devlink_fmsg *fmsg)
{
@@ -418,7 +426,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
to_ctx.sq = sq;
err_ctx.ctx = &to_ctx;
err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
- err_ctx.dump = mlx5e_tx_reporter_dump_sq;
+ err_ctx.dump = mlx5e_tx_reporter_timeout_dump;
snprintf(err_str, sizeof(err_str),
"TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u",
sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 13/48] net/mlx5e: Fix ICOSQ recovery flow for XSK
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (11 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 12/48] net/mlx5e: Wrap the tx reporter dump callback to extract the sq Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 14/48] udp: using datalen to cap ipv6 udp max gso segments Greg Kroah-Hartman
` (37 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Maxim Mikityanskiy, Aya Levin,
Saeed Mahameed, Sasha Levin
From: Maxim Mikityanskiy <maximmi@mellanox.com>
[ Upstream commit 19c4aba2d4e23997061fb11aed8a3e41334bfa14 ]
There are two ICOSQs per channel: one is needed for RX, and the other
for async operations (XSK TX, kTLS offload). Currently, the recovery
flow for both is the same, and async ICOSQ is mistakenly treated like
the regular ICOSQ.
This patch prevents running the regular ICOSQ recovery on async ICOSQ.
The purpose of async ICOSQ is to handle XSK wakeup requests and post
kTLS offload RX parameters, it has nothing to do with RQ and XSKRQ UMRs,
so the regular recovery sequence is not applicable here.
Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 --
.../net/ethernet/mellanox/mlx5/core/en_main.c | 30 ++++++++++++++-----
2 files changed, 22 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 9da34f82d4668..73060b30fece3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -916,9 +916,6 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
void mlx5e_close_rq(struct mlx5e_rq *rq);
struct mlx5e_sq_param;
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
- struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
-void mlx5e_close_icosq(struct mlx5e_icosq *sq);
int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
struct mlx5e_xdpsq *sq, bool is_redirect);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6ec4b96497ffb..3f5a2bb9b3c0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1051,9 +1051,20 @@ static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
mlx5e_reporter_icosq_cqe_err(sq);
}
+static void mlx5e_async_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+ struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+ recover_work);
+
+ /* Not implemented yet. */
+
+ netdev_warn(sq->channel->netdev, "async_icosq recovery is not implemented\n");
+}
+
static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
struct mlx5e_sq_param *param,
- struct mlx5e_icosq *sq)
+ struct mlx5e_icosq *sq,
+ work_func_t recover_work_func)
{
void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq);
struct mlx5_core_dev *mdev = c->mdev;
@@ -1073,7 +1084,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
if (err)
goto err_sq_wq_destroy;
- INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work);
+ INIT_WORK(&sq->recover_work, recover_work_func);
return 0;
@@ -1423,13 +1434,14 @@ static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
mlx5e_reporter_tx_err_cqe(sq);
}
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
- struct mlx5e_sq_param *param, struct mlx5e_icosq *sq)
+static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+ struct mlx5e_sq_param *param, struct mlx5e_icosq *sq,
+ work_func_t recover_work_func)
{
struct mlx5e_create_sq_param csp = {};
int err;
- err = mlx5e_alloc_icosq(c, param, sq);
+ err = mlx5e_alloc_icosq(c, param, sq, recover_work_func);
if (err)
return err;
@@ -1459,7 +1471,7 @@ void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
synchronize_net(); /* Sync with NAPI. */
}
-void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
{
struct mlx5e_channel *c = sq->channel;
@@ -1862,11 +1874,13 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
spin_lock_init(&c->async_icosq_lock);
- err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq);
+ err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq,
+ mlx5e_async_icosq_err_cqe_work);
if (err)
goto err_disable_napi;
- err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
+ err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq,
+ mlx5e_icosq_err_cqe_work);
if (err)
goto err_close_async_icosq;
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 14/48] udp: using datalen to cap ipv6 udp max gso segments
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (12 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 13/48] net/mlx5e: Fix ICOSQ recovery flow for XSK Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 15/48] selftests: Calculate udpgso segment count without header adjustment Greg Kroah-Hartman
` (36 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Coco Li, Willem de Bruijn,
Jakub Kicinski, Sasha Levin
From: Coco Li <lixiaoyan@google.com>
[ Upstream commit 736ef37fd9a44f5966e25319d08ff7ea99ac79e8 ]
The max number of UDP gso segments is intended to cap to
UDP_MAX_SEGMENTS, this is checked in udp_send_skb().
skb->len contains network and transport header len here, we should use
only data len instead.
This is the ipv6 counterpart to the below referenced commit,
which missed the ipv6 change
Fixes: 158390e45612 ("udp: using datalen to cap max gso segments")
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20211223222441.2975883-1-lixiaoyan@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/ipv6/udp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 8a1863146f34c..069551a04369e 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1189,7 +1189,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
kfree_skb(skb);
return -EINVAL;
}
- if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+ if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
return -EINVAL;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 15/48] selftests: Calculate udpgso segment count without header adjustment
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (13 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 14/48] udp: using datalen to cap ipv6 udp max gso segments Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 16/48] net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register Greg Kroah-Hartman
` (35 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Coco Li, Willem de Bruijn,
Jakub Kicinski, Sasha Levin
From: Coco Li <lixiaoyan@google.com>
[ Upstream commit 5471d5226c3b39b3d2f7011c082d5715795bd65c ]
The below referenced commit correctly updated the computation of number
of segments (gso_size) by using only the gso payload size and
removing the header lengths.
With this change the regression test started failing. Update
the tests to match this new behavior.
Both IPv4 and IPv6 tests are updated, as a separate patch in this series
will update udp_v6_send_skb to match this change in udp_send_skb.
Fixes: 158390e45612 ("udp: using datalen to cap max gso segments")
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20211223222441.2975883-2-lixiaoyan@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
tools/testing/selftests/net/udpgso.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index c66da6ffd6d8d..7badaf215de28 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -156,13 +156,13 @@ struct testcase testcases_v4[] = {
},
{
/* send max number of min sized segments */
- .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+ .tlen = UDP_MAX_SEGMENTS,
.gso_len = 1,
- .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+ .r_num_mss = UDP_MAX_SEGMENTS,
},
{
/* send max number + 1 of min sized segments: fail */
- .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4 + 1,
+ .tlen = UDP_MAX_SEGMENTS + 1,
.gso_len = 1,
.tfail = true,
},
@@ -259,13 +259,13 @@ struct testcase testcases_v6[] = {
},
{
/* send max number of min sized segments */
- .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+ .tlen = UDP_MAX_SEGMENTS,
.gso_len = 1,
- .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+ .r_num_mss = UDP_MAX_SEGMENTS,
},
{
/* send max number + 1 of min sized segments: fail */
- .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6 + 1,
+ .tlen = UDP_MAX_SEGMENTS + 1,
.gso_len = 1,
.tfail = true,
},
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 16/48] net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (14 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 15/48] selftests: Calculate udpgso segment count without header adjustment Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 19:02 ` Florian Fainelli
2022-01-03 14:23 ` [PATCH 5.10 17/48] sctp: use call_rcu to free endpoint Greg Kroah-Hartman
` (34 subsequent siblings)
50 siblings, 1 reply; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Miaoqian Lin, Jakub Kicinski, Sasha Levin
From: Miaoqian Lin <linmq006@gmail.com>
[ Upstream commit b45396afa4177f2b1ddfeff7185da733fade1dc3 ]
The fixed_phy_get_gpiod function() returns NULL, it doesn't return error
pointers, using NULL checking to fix this.i
Fixes: 5468e82f7034 ("net: phy: fixed-phy: Drop GPIO from fixed_phy_add()")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Link: https://lore.kernel.org/r/20211224021500.10362-1-linmq006@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/phy/fixed_phy.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 18d81f43f2a88..dd30a6883a027 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -239,8 +239,8 @@ static struct phy_device *__fixed_phy_register(unsigned int irq,
/* Check if we have a GPIO associated with this fixed phy */
if (!gpiod) {
gpiod = fixed_phy_get_gpiod(np);
- if (IS_ERR(gpiod))
- return ERR_CAST(gpiod);
+ if (!gpiod)
+ return ERR_PTR(-EINVAL);
}
/* Get the next available PHY address, up to PHY_MAX_ADDR */
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* Re: [PATCH 5.10 16/48] net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register
2022-01-03 14:23 ` [PATCH 5.10 16/48] net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register Greg Kroah-Hartman
@ 2022-01-03 19:02 ` Florian Fainelli
0 siblings, 0 replies; 53+ messages in thread
From: Florian Fainelli @ 2022-01-03 19:02 UTC (permalink / raw)
To: Greg Kroah-Hartman, linux-kernel
Cc: stable, Miaoqian Lin, Jakub Kicinski, Sasha Levin
On 1/3/2022 6:23 AM, Greg Kroah-Hartman wrote:
> From: Miaoqian Lin <linmq006@gmail.com>
>
> [ Upstream commit b45396afa4177f2b1ddfeff7185da733fade1dc3 ]
>
> The fixed_phy_get_gpiod function() returns NULL, it doesn't return error
> pointers, using NULL checking to fix this.i
>
> Fixes: 5468e82f7034 ("net: phy: fixed-phy: Drop GPIO from fixed_phy_add()")
> Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
> Link: https://lore.kernel.org/r/20211224021500.10362-1-linmq006@gmail.com
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
> Signed-off-by: Sasha Levin <sashal@kernel.org>
Same regression as with 5.4, this breaks any platform using fixed PHYs
without a GPIO, which is the vast majority of them.
--
Florian
^ permalink raw reply [flat|nested] 53+ messages in thread
* [PATCH 5.10 17/48] sctp: use call_rcu to free endpoint
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (15 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 16/48] net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 18/48] net/smc: fix using of uninitialized completions Greg Kroah-Hartman
` (33 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, syzbot+9276d76e83e3bcde6c99,
Lee Jones, Xin Long, David S. Miller, Sasha Levin
From: Xin Long <lucien.xin@gmail.com>
[ Upstream commit 5ec7d18d1813a5bead0b495045606c93873aecbb ]
This patch is to delay the endpoint free by calling call_rcu() to fix
another use-after-free issue in sctp_sock_dump():
BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20
Call Trace:
__lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218
lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844
__raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
_raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168
spin_lock_bh include/linux/spinlock.h:334 [inline]
__lock_sock+0x203/0x350 net/core/sock.c:2253
lock_sock_nested+0xfe/0x120 net/core/sock.c:2774
lock_sock include/net/sock.h:1492 [inline]
sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324
sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091
sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527
__inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049
inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065
netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244
__netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352
netlink_dump_start include/linux/netlink.h:216 [inline]
inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170
__sock_diag_cmd net/core/sock_diag.c:232 [inline]
sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263
netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477
sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274
This issue occurs when asoc is peeled off and the old sk is freed after
getting it by asoc->base.sk and before calling lock_sock(sk).
To prevent the sk free, as a holder of the sk, ep should be alive when
calling lock_sock(). This patch uses call_rcu() and moves sock_put and
ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to
hold the ep under rcu_read_lock in sctp_transport_traverse_process().
If sctp_endpoint_hold() returns true, it means this ep is still alive
and we have held it and can continue to dump it; If it returns false,
it means this ep is dead and can be freed after rcu_read_unlock, and
we should skip it.
In sctp_sock_dump(), after locking the sk, if this ep is different from
tsp->asoc->ep, it means during this dumping, this asoc was peeled off
before calling lock_sock(), and the sk should be skipped; If this ep is
the same with tsp->asoc->ep, it means no peeloff happens on this asoc,
and due to lock_sock, no peeloff will happen either until release_sock.
Note that delaying endpoint free won't delay the port release, as the
port release happens in sctp_endpoint_destroy() before calling call_rcu().
Also, freeing endpoint by call_rcu() makes it safe to access the sk by
asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv().
Thanks Jones to bring this issue up.
v1->v2:
- improve the changelog.
- add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed.
Reported-by: syzbot+9276d76e83e3bcde6c99@syzkaller.appspotmail.com
Reported-by: Lee Jones <lee.jones@linaro.org>
Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
include/net/sctp/sctp.h | 6 +++---
include/net/sctp/structs.h | 3 ++-
net/sctp/diag.c | 12 ++++++------
net/sctp/endpointola.c | 23 +++++++++++++++--------
net/sctp/socket.c | 23 +++++++++++++++--------
5 files changed, 41 insertions(+), 26 deletions(-)
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 4fc747b778eb6..33475d061823e 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -103,6 +103,7 @@ extern struct percpu_counter sctp_sockets_allocated;
int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);
+typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *);
void sctp_transport_walk_start(struct rhashtable_iter *iter);
void sctp_transport_walk_stop(struct rhashtable_iter *iter);
struct sctp_transport *sctp_transport_get_next(struct net *net,
@@ -113,9 +114,8 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
struct net *net,
const union sctp_addr *laddr,
const union sctp_addr *paddr, void *p);
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
- int (*cb_done)(struct sctp_transport *, void *),
- struct net *net, int *pos, void *p);
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+ struct net *net, int *pos, void *p);
int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p);
int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
struct sctp_info *info);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 51d698f2656fc..be9ff0422c162 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1339,6 +1339,7 @@ struct sctp_endpoint {
u32 secid;
u32 peer_secid;
+ struct rcu_head rcu;
};
/* Recover the outter endpoint structure. */
@@ -1354,7 +1355,7 @@ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base)
struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t);
void sctp_endpoint_free(struct sctp_endpoint *);
void sctp_endpoint_put(struct sctp_endpoint *);
-void sctp_endpoint_hold(struct sctp_endpoint *);
+int sctp_endpoint_hold(struct sctp_endpoint *ep);
void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *);
struct sctp_association *sctp_endpoint_lookup_assoc(
const struct sctp_endpoint *ep,
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 493fc01e5d2b7..babadd6720a2b 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -292,9 +292,8 @@ out:
return err;
}
-static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
+static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
{
- struct sctp_endpoint *ep = tsp->asoc->ep;
struct sctp_comm_param *commp = p;
struct sock *sk = ep->base.sk;
struct sk_buff *skb = commp->skb;
@@ -304,6 +303,8 @@ static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
int err = 0;
lock_sock(sk);
+ if (ep != tsp->asoc->ep)
+ goto release;
list_for_each_entry(assoc, &ep->asocs, asocs) {
if (cb->args[4] < cb->args[1])
goto next;
@@ -346,9 +347,8 @@ release:
return err;
}
-static int sctp_sock_filter(struct sctp_transport *tsp, void *p)
+static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
{
- struct sctp_endpoint *ep = tsp->asoc->ep;
struct sctp_comm_param *commp = p;
struct sock *sk = ep->base.sk;
const struct inet_diag_req_v2 *r = commp->r;
@@ -507,8 +507,8 @@ skip:
if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
goto done;
- sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
- net, &pos, &commp);
+ sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump,
+ net, &pos, &commp);
cb->args[2] = pos;
done:
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 48c9c2c7602f7..efffde7f2328e 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -184,6 +184,18 @@ void sctp_endpoint_free(struct sctp_endpoint *ep)
}
/* Final destructor for endpoint. */
+static void sctp_endpoint_destroy_rcu(struct rcu_head *head)
+{
+ struct sctp_endpoint *ep = container_of(head, struct sctp_endpoint, rcu);
+ struct sock *sk = ep->base.sk;
+
+ sctp_sk(sk)->ep = NULL;
+ sock_put(sk);
+
+ kfree(ep);
+ SCTP_DBG_OBJCNT_DEC(ep);
+}
+
static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
{
struct sock *sk;
@@ -213,18 +225,13 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
if (sctp_sk(sk)->bind_hash)
sctp_put_port(sk);
- sctp_sk(sk)->ep = NULL;
- /* Give up our hold on the sock */
- sock_put(sk);
-
- kfree(ep);
- SCTP_DBG_OBJCNT_DEC(ep);
+ call_rcu(&ep->rcu, sctp_endpoint_destroy_rcu);
}
/* Hold a reference to an endpoint. */
-void sctp_endpoint_hold(struct sctp_endpoint *ep)
+int sctp_endpoint_hold(struct sctp_endpoint *ep)
{
- refcount_inc(&ep->base.refcnt);
+ return refcount_inc_not_zero(&ep->base.refcnt);
}
/* Release a reference to an endpoint and clean up if there are
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index e872bc50bbe61..0a9e2c7d8e5f5 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5223,11 +5223,12 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
}
EXPORT_SYMBOL_GPL(sctp_transport_lookup_process);
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
- int (*cb_done)(struct sctp_transport *, void *),
- struct net *net, int *pos, void *p) {
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+ struct net *net, int *pos, void *p)
+{
struct rhashtable_iter hti;
struct sctp_transport *tsp;
+ struct sctp_endpoint *ep;
int ret;
again:
@@ -5236,26 +5237,32 @@ again:
tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
- ret = cb(tsp, p);
- if (ret)
- break;
+ ep = tsp->asoc->ep;
+ if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */
+ ret = cb(ep, tsp, p);
+ if (ret)
+ break;
+ sctp_endpoint_put(ep);
+ }
(*pos)++;
sctp_transport_put(tsp);
}
sctp_transport_walk_stop(&hti);
if (ret) {
- if (cb_done && !cb_done(tsp, p)) {
+ if (cb_done && !cb_done(ep, tsp, p)) {
(*pos)++;
+ sctp_endpoint_put(ep);
sctp_transport_put(tsp);
goto again;
}
+ sctp_endpoint_put(ep);
sctp_transport_put(tsp);
}
return ret;
}
-EXPORT_SYMBOL_GPL(sctp_for_each_transport);
+EXPORT_SYMBOL_GPL(sctp_transport_traverse_process);
/* 7.2.1 Association Status (SCTP_STATUS)
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 18/48] net/smc: fix using of uninitialized completions
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (16 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 17/48] sctp: use call_rcu to free endpoint Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 19/48] net: usb: pegasus: Do not drop long Ethernet frames Greg Kroah-Hartman
` (32 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Karsten Graul, David S. Miller, Sasha Levin
From: Karsten Graul <kgraul@linux.ibm.com>
[ Upstream commit 6d7373dabfd3933ee30c40fc8c09d2a788f6ece1 ]
In smc_wr_tx_send_wait() the completion on index specified by
pend->idx is initialized and after smc_wr_tx_send() was called the wait
for completion starts. pend->idx is used to get the correct index for
the wait, but the pend structure could already be cleared in
smc_wr_tx_process_cqe().
Introduce pnd_idx to hold and use a local copy of the correct index.
Fixes: 09c61d24f96d ("net/smc: wait for departure of an IB message")
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/smc/smc_wr.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 9dbe4804853e0..a71c9631f1ad3 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -288,18 +288,20 @@ int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv,
unsigned long timeout)
{
struct smc_wr_tx_pend *pend;
+ u32 pnd_idx;
int rc;
pend = container_of(priv, struct smc_wr_tx_pend, priv);
pend->compl_requested = 1;
- init_completion(&link->wr_tx_compl[pend->idx]);
+ pnd_idx = pend->idx;
+ init_completion(&link->wr_tx_compl[pnd_idx]);
rc = smc_wr_tx_send(link, priv);
if (rc)
return rc;
/* wait for completion by smc_wr_tx_process_cqe() */
rc = wait_for_completion_interruptible_timeout(
- &link->wr_tx_compl[pend->idx], timeout);
+ &link->wr_tx_compl[pnd_idx], timeout);
if (rc <= 0)
rc = -ENODATA;
if (rc > 0)
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 19/48] net: usb: pegasus: Do not drop long Ethernet frames
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (17 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 18/48] net/smc: fix using of uninitialized completions Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 20/48] net: ag71xx: Fix a potential double free in error handling paths Greg Kroah-Hartman
` (31 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Matthias-Christian Ott, Andrew Lunn,
David S. Miller, Sasha Levin
From: Matthias-Christian Ott <ott@mirix.org>
[ Upstream commit ca506fca461b260ab32952b610c3d4aadc6c11fd ]
The D-Link DSB-650TX (2001:4002) is unable to receive Ethernet frames
that are longer than 1518 octets, for example, Ethernet frames that
contain 802.1Q VLAN tags.
The frames are sent to the pegasus driver via USB but the driver
discards them because they have the Long_pkt field set to 1 in the
received status report. The function read_bulk_callback of the pegasus
driver treats such received "packets" (in the terminology of the
hardware) as errors but the field simply does just indicate that the
Ethernet frame (MAC destination to FCS) is longer than 1518 octets.
It seems that in the 1990s there was a distinction between
"giant" (> 1518) and "runt" (< 64) frames and the hardware includes
flags to indicate this distinction. It seems that the purpose of the
distinction "giant" frames was to not allow infinitely long frames due
to transmission errors and to allow hardware to have an upper limit of
the frame size. However, the hardware already has such limit with its
2048 octet receive buffer and, therefore, Long_pkt is merely a
convention and should not be treated as a receive error.
Actually, the hardware is even able to receive Ethernet frames with 2048
octets which exceeds the claimed limit frame size limit of the driver of
1536 octets (PEGASUS_MTU).
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Matthias-Christian Ott <ott@mirix.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/usb/pegasus.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 2a748a924f838..138279bbb544b 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -518,11 +518,11 @@ static void read_bulk_callback(struct urb *urb)
goto goon;
rx_status = buf[count - 2];
- if (rx_status & 0x1e) {
+ if (rx_status & 0x1c) {
netif_dbg(pegasus, rx_err, net,
"RX packet error %x\n", rx_status);
net->stats.rx_errors++;
- if (rx_status & 0x06) /* long or runt */
+ if (rx_status & 0x04) /* runt */
net->stats.rx_length_errors++;
if (rx_status & 0x08)
net->stats.rx_crc_errors++;
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 20/48] net: ag71xx: Fix a potential double free in error handling paths
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (18 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 19/48] net: usb: pegasus: Do not drop long Ethernet frames Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 21/48] net: lantiq_xrx200: fix statistics of received bytes Greg Kroah-Hartman
` (30 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Christophe JAILLET, David S. Miller,
Sasha Levin
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
[ Upstream commit 1cd5384c88af5b59bf9f3b6c1a151bc14b88c2cd ]
'ndev' is a managed resource allocated with devm_alloc_etherdev(), so there
is no need to call free_netdev() explicitly or there will be a double
free().
Simplify all error handling paths accordingly.
Fixes: d51b6ce441d3 ("net: ethernet: add ag71xx driver")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/atheros/ag71xx.c | 23 ++++++++---------------
1 file changed, 8 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index a60ce90305819..c26c9b0c00d8f 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1904,15 +1904,12 @@ static int ag71xx_probe(struct platform_device *pdev)
ag->mac_reset = devm_reset_control_get(&pdev->dev, "mac");
if (IS_ERR(ag->mac_reset)) {
netif_err(ag, probe, ndev, "missing mac reset\n");
- err = PTR_ERR(ag->mac_reset);
- goto err_free;
+ return PTR_ERR(ag->mac_reset);
}
ag->mac_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
- if (!ag->mac_base) {
- err = -ENOMEM;
- goto err_free;
- }
+ if (!ag->mac_base)
+ return -ENOMEM;
ndev->irq = platform_get_irq(pdev, 0);
err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt,
@@ -1920,7 +1917,7 @@ static int ag71xx_probe(struct platform_device *pdev)
if (err) {
netif_err(ag, probe, ndev, "unable to request IRQ %d\n",
ndev->irq);
- goto err_free;
+ return err;
}
ndev->netdev_ops = &ag71xx_netdev_ops;
@@ -1948,10 +1945,8 @@ static int ag71xx_probe(struct platform_device *pdev)
ag->stop_desc = dmam_alloc_coherent(&pdev->dev,
sizeof(struct ag71xx_desc),
&ag->stop_desc_dma, GFP_KERNEL);
- if (!ag->stop_desc) {
- err = -ENOMEM;
- goto err_free;
- }
+ if (!ag->stop_desc)
+ return -ENOMEM;
ag->stop_desc->data = 0;
ag->stop_desc->ctrl = 0;
@@ -1968,7 +1963,7 @@ static int ag71xx_probe(struct platform_device *pdev)
err = of_get_phy_mode(np, &ag->phy_if_mode);
if (err) {
netif_err(ag, probe, ndev, "missing phy-mode property in DT\n");
- goto err_free;
+ return err;
}
netif_napi_add(ndev, &ag->napi, ag71xx_poll, AG71XX_NAPI_WEIGHT);
@@ -1976,7 +1971,7 @@ static int ag71xx_probe(struct platform_device *pdev)
err = clk_prepare_enable(ag->clk_eth);
if (err) {
netif_err(ag, probe, ndev, "Failed to enable eth clk.\n");
- goto err_free;
+ return err;
}
ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0);
@@ -2012,8 +2007,6 @@ err_mdio_remove:
ag71xx_mdio_remove(ag);
err_put_clk:
clk_disable_unprepare(ag->clk_eth);
-err_free:
- free_netdev(ndev);
return err;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 21/48] net: lantiq_xrx200: fix statistics of received bytes
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (19 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 20/48] net: ag71xx: Fix a potential double free in error handling paths Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.10 22/48] NFC: st21nfca: Fix memory leak in device probe and remove Greg Kroah-Hartman
` (29 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Aleksander Jan Bajkowski,
David S. Miller, Sasha Levin
From: Aleksander Jan Bajkowski <olek2@wp.pl>
[ Upstream commit 5be60a945329d82f06fc755a43eeefbfc5f77d72 ]
Received frames have FCS truncated. There is no need
to subtract FCS length from the statistics.
Fixes: fe1a56420cf2 ("net: lantiq: Add Lantiq / Intel VRX200 Ethernet driver")
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/lantiq_xrx200.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 072075bc60ee9..500511b72ac60 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -209,7 +209,7 @@ static int xrx200_hw_receive(struct xrx200_chan *ch)
skb->protocol = eth_type_trans(skb, net_dev);
netif_receive_skb(skb);
net_dev->stats.rx_packets++;
- net_dev->stats.rx_bytes += len - ETH_FCS_LEN;
+ net_dev->stats.rx_bytes += len;
return 0;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 22/48] NFC: st21nfca: Fix memory leak in device probe and remove
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (20 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 21/48] net: lantiq_xrx200: fix statistics of received bytes Greg Kroah-Hartman
@ 2022-01-03 14:23 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 23/48] net/smc: improved fix wait on already cleared link Greg Kroah-Hartman
` (28 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:23 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Hulk Robot, Wei Yongjun,
David S. Miller, Sasha Levin
From: Wei Yongjun <weiyongjun1@huawei.com>
[ Upstream commit 1b9dadba502234eea7244879b8d5d126bfaf9f0c ]
'phy->pending_skb' is alloced when device probe, but forgot to free
in the error handling path and remove path, this cause memory leak
as follows:
unreferenced object 0xffff88800bc06800 (size 512):
comm "8", pid 11775, jiffies 4295159829 (age 9.032s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<00000000d66c09ce>] __kmalloc_node_track_caller+0x1ed/0x450
[<00000000c93382b3>] kmalloc_reserve+0x37/0xd0
[<000000005fea522c>] __alloc_skb+0x124/0x380
[<0000000019f29f9a>] st21nfca_hci_i2c_probe+0x170/0x8f2
Fix it by freeing 'pending_skb' in error and remove.
Fixes: 68957303f44a ("NFC: ST21NFCA: Add driver for STMicroelectronics ST21NFCA NFC Chip")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/nfc/st21nfca/i2c.c | 29 ++++++++++++++++++++---------
1 file changed, 20 insertions(+), 9 deletions(-)
diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
index 23ed11f91213d..6ea59426ab0bf 100644
--- a/drivers/nfc/st21nfca/i2c.c
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -533,7 +533,8 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
phy->gpiod_ena = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
if (IS_ERR(phy->gpiod_ena)) {
nfc_err(dev, "Unable to get ENABLE GPIO\n");
- return PTR_ERR(phy->gpiod_ena);
+ r = PTR_ERR(phy->gpiod_ena);
+ goto out_free;
}
phy->se_status.is_ese_present =
@@ -544,7 +545,7 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
r = st21nfca_hci_platform_init(phy);
if (r < 0) {
nfc_err(&client->dev, "Unable to reboot st21nfca\n");
- return r;
+ goto out_free;
}
r = devm_request_threaded_irq(&client->dev, client->irq, NULL,
@@ -553,15 +554,23 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
ST21NFCA_HCI_DRIVER_NAME, phy);
if (r < 0) {
nfc_err(&client->dev, "Unable to register IRQ handler\n");
- return r;
+ goto out_free;
}
- return st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
- ST21NFCA_FRAME_HEADROOM,
- ST21NFCA_FRAME_TAILROOM,
- ST21NFCA_HCI_LLC_MAX_PAYLOAD,
- &phy->hdev,
- &phy->se_status);
+ r = st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
+ ST21NFCA_FRAME_HEADROOM,
+ ST21NFCA_FRAME_TAILROOM,
+ ST21NFCA_HCI_LLC_MAX_PAYLOAD,
+ &phy->hdev,
+ &phy->se_status);
+ if (r)
+ goto out_free;
+
+ return 0;
+
+out_free:
+ kfree_skb(phy->pending_skb);
+ return r;
}
static int st21nfca_hci_i2c_remove(struct i2c_client *client)
@@ -574,6 +583,8 @@ static int st21nfca_hci_i2c_remove(struct i2c_client *client)
if (phy->powered)
st21nfca_hci_i2c_disable(phy);
+ if (phy->pending_skb)
+ kfree_skb(phy->pending_skb);
return 0;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 23/48] net/smc: improved fix wait on already cleared link
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (21 preceding siblings ...)
2022-01-03 14:23 ` [PATCH 5.10 22/48] NFC: st21nfca: Fix memory leak in device probe and remove Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 24/48] net/smc: dont send CDC/LLC message if link not ready Greg Kroah-Hartman
` (27 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Karsten Graul, David S. Miller, Sasha Levin
From: Karsten Graul <kgraul@linux.ibm.com>
[ Upstream commit 95f7f3e7dc6bd2e735cb5de11734ea2222b1e05a ]
Commit 8f3d65c16679 ("net/smc: fix wait on already cleared link")
introduced link refcounting to avoid waits on already cleared links.
This patch extents and improves the refcounting to cover all
remaining possible cases for this kind of error situation.
Fixes: 15e1b99aadfb ("net/smc: no WR buffer wait for terminating link group")
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/smc/smc_cdc.c | 7 +++++-
net/smc/smc_core.c | 20 ++++++++-------
net/smc/smc_llc.c | 63 +++++++++++++++++++++++++++++++++++-----------
net/smc/smc_tx.c | 22 ++++------------
net/smc/smc_wr.h | 14 +++++++++++
5 files changed, 85 insertions(+), 41 deletions(-)
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index b1ce6ccbfaec8..3602829006dda 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -150,9 +150,11 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn)
again:
link = conn->lnk;
+ if (!smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_cdc_get_free_slot(conn, link, &wr_buf, NULL, &pend);
if (rc)
- return rc;
+ goto put_out;
spin_lock_bh(&conn->send_lock);
if (link != conn->lnk) {
@@ -160,6 +162,7 @@ again:
spin_unlock_bh(&conn->send_lock);
smc_wr_tx_put_slot(link,
(struct smc_wr_tx_pend_priv *)pend);
+ smc_wr_tx_link_put(link);
if (again)
return -ENOLINK;
again = true;
@@ -167,6 +170,8 @@ again:
}
rc = smc_cdc_msg_send(conn, wr_buf, pend);
spin_unlock_bh(&conn->send_lock);
+put_out:
+ smc_wr_tx_link_put(link);
return rc;
}
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 3f1343dfa16ba..135949ef85b3c 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -550,7 +550,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
to_lnk = &lgr->lnk[i];
break;
}
- if (!to_lnk) {
+ if (!to_lnk || !smc_wr_tx_link_hold(to_lnk)) {
smc_lgr_terminate_sched(lgr);
return NULL;
}
@@ -582,24 +582,26 @@ again:
read_unlock_bh(&lgr->conns_lock);
/* pre-fetch buffer outside of send_lock, might sleep */
rc = smc_cdc_get_free_slot(conn, to_lnk, &wr_buf, NULL, &pend);
- if (rc) {
- smcr_link_down_cond_sched(to_lnk);
- return NULL;
- }
+ if (rc)
+ goto err_out;
/* avoid race with smcr_tx_sndbuf_nonempty() */
spin_lock_bh(&conn->send_lock);
conn->lnk = to_lnk;
rc = smc_switch_cursor(smc, pend, wr_buf);
spin_unlock_bh(&conn->send_lock);
sock_put(&smc->sk);
- if (rc) {
- smcr_link_down_cond_sched(to_lnk);
- return NULL;
- }
+ if (rc)
+ goto err_out;
goto again;
}
read_unlock_bh(&lgr->conns_lock);
+ smc_wr_tx_link_put(to_lnk);
return to_lnk;
+
+err_out:
+ smcr_link_down_cond_sched(to_lnk);
+ smc_wr_tx_link_put(to_lnk);
+ return NULL;
}
static void smcr_buf_unuse(struct smc_buf_desc *rmb_desc,
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index d8fe4e1f24d1f..f1d323439a2af 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -383,9 +383,11 @@ int smc_llc_send_confirm_link(struct smc_link *link,
struct smc_wr_buf *wr_buf;
int rc;
+ if (!smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
confllc = (struct smc_llc_msg_confirm_link *)wr_buf;
memset(confllc, 0, sizeof(*confllc));
confllc->hd.common.type = SMC_LLC_CONFIRM_LINK;
@@ -402,6 +404,8 @@ int smc_llc_send_confirm_link(struct smc_link *link,
confllc->max_links = SMC_LLC_ADD_LNK_MAX_LINKS;
/* send llc message */
rc = smc_wr_tx_send(link, pend);
+put_out:
+ smc_wr_tx_link_put(link);
return rc;
}
@@ -415,9 +419,11 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link,
struct smc_link *link;
int i, rc, rtok_ix;
+ if (!smc_wr_tx_link_hold(send_link))
+ return -ENOLINK;
rc = smc_llc_add_pending_send(send_link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf;
memset(rkeyllc, 0, sizeof(*rkeyllc));
rkeyllc->hd.common.type = SMC_LLC_CONFIRM_RKEY;
@@ -444,6 +450,8 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link,
(u64)sg_dma_address(rmb_desc->sgt[send_link->link_idx].sgl));
/* send llc message */
rc = smc_wr_tx_send(send_link, pend);
+put_out:
+ smc_wr_tx_link_put(send_link);
return rc;
}
@@ -456,9 +464,11 @@ static int smc_llc_send_delete_rkey(struct smc_link *link,
struct smc_wr_buf *wr_buf;
int rc;
+ if (!smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
rkeyllc = (struct smc_llc_msg_delete_rkey *)wr_buf;
memset(rkeyllc, 0, sizeof(*rkeyllc));
rkeyllc->hd.common.type = SMC_LLC_DELETE_RKEY;
@@ -467,6 +477,8 @@ static int smc_llc_send_delete_rkey(struct smc_link *link,
rkeyllc->rkey[0] = htonl(rmb_desc->mr_rx[link->link_idx]->rkey);
/* send llc message */
rc = smc_wr_tx_send(link, pend);
+put_out:
+ smc_wr_tx_link_put(link);
return rc;
}
@@ -480,9 +492,11 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
struct smc_wr_buf *wr_buf;
int rc;
+ if (!smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
addllc = (struct smc_llc_msg_add_link *)wr_buf;
memset(addllc, 0, sizeof(*addllc));
@@ -504,6 +518,8 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
}
/* send llc message */
rc = smc_wr_tx_send(link, pend);
+put_out:
+ smc_wr_tx_link_put(link);
return rc;
}
@@ -517,9 +533,11 @@ int smc_llc_send_delete_link(struct smc_link *link, u8 link_del_id,
struct smc_wr_buf *wr_buf;
int rc;
+ if (!smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
delllc = (struct smc_llc_msg_del_link *)wr_buf;
memset(delllc, 0, sizeof(*delllc));
@@ -536,6 +554,8 @@ int smc_llc_send_delete_link(struct smc_link *link, u8 link_del_id,
delllc->reason = htonl(reason);
/* send llc message */
rc = smc_wr_tx_send(link, pend);
+put_out:
+ smc_wr_tx_link_put(link);
return rc;
}
@@ -547,9 +567,11 @@ static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16])
struct smc_wr_buf *wr_buf;
int rc;
+ if (!smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
testllc = (struct smc_llc_msg_test_link *)wr_buf;
memset(testllc, 0, sizeof(*testllc));
testllc->hd.common.type = SMC_LLC_TEST_LINK;
@@ -557,6 +579,8 @@ static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16])
memcpy(testllc->user_data, user_data, sizeof(testllc->user_data));
/* send llc message */
rc = smc_wr_tx_send(link, pend);
+put_out:
+ smc_wr_tx_link_put(link);
return rc;
}
@@ -567,13 +591,16 @@ static int smc_llc_send_message(struct smc_link *link, void *llcbuf)
struct smc_wr_buf *wr_buf;
int rc;
- if (!smc_link_usable(link))
+ if (!smc_wr_tx_link_hold(link))
return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
memcpy(wr_buf, llcbuf, sizeof(union smc_llc_msg));
- return smc_wr_tx_send(link, pend);
+ rc = smc_wr_tx_send(link, pend);
+put_out:
+ smc_wr_tx_link_put(link);
+ return rc;
}
/* schedule an llc send on link, may wait for buffers,
@@ -586,13 +613,16 @@ static int smc_llc_send_message_wait(struct smc_link *link, void *llcbuf)
struct smc_wr_buf *wr_buf;
int rc;
- if (!smc_link_usable(link))
+ if (!smc_wr_tx_link_hold(link))
return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
memcpy(wr_buf, llcbuf, sizeof(union smc_llc_msg));
- return smc_wr_tx_send_wait(link, pend, SMC_LLC_WAIT_TIME);
+ rc = smc_wr_tx_send_wait(link, pend, SMC_LLC_WAIT_TIME);
+put_out:
+ smc_wr_tx_link_put(link);
+ return rc;
}
/********************************* receive ***********************************/
@@ -672,9 +702,11 @@ static int smc_llc_add_link_cont(struct smc_link *link,
struct smc_buf_desc *rmb;
u8 n;
+ if (!smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
if (rc)
- return rc;
+ goto put_out;
addc_llc = (struct smc_llc_msg_add_link_cont *)wr_buf;
memset(addc_llc, 0, sizeof(*addc_llc));
@@ -706,7 +738,10 @@ static int smc_llc_add_link_cont(struct smc_link *link,
addc_llc->hd.length = sizeof(struct smc_llc_msg_add_link_cont);
if (lgr->role == SMC_CLNT)
addc_llc->hd.flags |= SMC_LLC_FLAG_RESP;
- return smc_wr_tx_send(link, pend);
+ rc = smc_wr_tx_send(link, pend);
+put_out:
+ smc_wr_tx_link_put(link);
+ return rc;
}
static int smc_llc_cli_rkey_exchange(struct smc_link *link,
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index ff02952b3d03e..52ef1fca0b604 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -479,7 +479,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn,
/* Wakeup sndbuf consumers from any context (IRQ or process)
* since there is more data to transmit; usable snd_wnd as max transmit
*/
-static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
+static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
{
struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
struct smc_link *link = conn->lnk;
@@ -488,8 +488,11 @@ static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
struct smc_wr_buf *wr_buf;
int rc;
+ if (!link || !smc_wr_tx_link_hold(link))
+ return -ENOLINK;
rc = smc_cdc_get_free_slot(conn, link, &wr_buf, &wr_rdma_buf, &pend);
if (rc < 0) {
+ smc_wr_tx_link_put(link);
if (rc == -EBUSY) {
struct smc_sock *smc =
container_of(conn, struct smc_sock, conn);
@@ -530,22 +533,7 @@ static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
out_unlock:
spin_unlock_bh(&conn->send_lock);
- return rc;
-}
-
-static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
-{
- struct smc_link *link = conn->lnk;
- int rc = -ENOLINK;
-
- if (!link)
- return rc;
-
- atomic_inc(&link->wr_tx_refcnt);
- if (smc_link_usable(link))
- rc = _smcr_tx_sndbuf_nonempty(conn);
- if (atomic_dec_and_test(&link->wr_tx_refcnt))
- wake_up_all(&link->wr_tx_wait);
+ smc_wr_tx_link_put(link);
return rc;
}
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 423b8709f1c9e..2bc626f230a56 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -60,6 +60,20 @@ static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val)
atomic_long_set(wr_tx_id, val);
}
+static inline bool smc_wr_tx_link_hold(struct smc_link *link)
+{
+ if (!smc_link_usable(link))
+ return false;
+ atomic_inc(&link->wr_tx_refcnt);
+ return true;
+}
+
+static inline void smc_wr_tx_link_put(struct smc_link *link)
+{
+ if (atomic_dec_and_test(&link->wr_tx_refcnt))
+ wake_up_all(&link->wr_tx_wait);
+}
+
static inline void smc_wr_wakeup_tx_wait(struct smc_link *lnk)
{
wake_up_all(&lnk->wr_tx_wait);
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 24/48] net/smc: dont send CDC/LLC message if link not ready
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (22 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 23/48] net/smc: improved fix wait on already cleared link Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 25/48] net/smc: fix kernel panic caused by race of smc_sock Greg Kroah-Hartman
` (26 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Dust Li, David S. Miller, Sasha Levin
From: Dust Li <dust.li@linux.alibaba.com>
[ Upstream commit 90cee52f2e780345d3629e278291aea5ac74f40f ]
We found smc_llc_send_link_delete_all() sometimes wait
for 2s timeout when testing with RDMA link up/down.
It is possible when a smc_link is in ACTIVATING state,
the underlaying QP is still in RESET or RTR state, which
cannot send any messages out.
smc_llc_send_link_delete_all() use smc_link_usable() to
checks whether the link is usable, if the QP is still in
RESET or RTR state, but the smc_link is in ACTIVATING, this
LLC message will always fail without any CQE entering the
CQ, and we will always wait 2s before timeout.
Since we cannot send any messages through the QP before
the QP enter RTS. I add a wrapper smc_link_sendable()
which checks the state of QP along with the link state.
And replace smc_link_usable() with smc_link_sendable()
in all LLC & CDC message sending routine.
Fixes: 5f08318f617b ("smc: connection data control (CDC)")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/smc/smc_core.c | 2 +-
net/smc/smc_core.h | 6 ++++++
net/smc/smc_llc.c | 2 +-
net/smc/smc_wr.c | 4 ++--
net/smc/smc_wr.h | 2 +-
5 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 135949ef85b3c..fb4327a81a0f0 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -226,7 +226,7 @@ static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr)
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
struct smc_link *lnk = &lgr->lnk[i];
- if (smc_link_usable(lnk))
+ if (smc_link_sendable(lnk))
lnk->state = SMC_LNK_INACTIVE;
}
wake_up_all(&lgr->llc_msg_waiter);
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 4745a9a5a28f5..9364d0f35ccec 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -359,6 +359,12 @@ static inline bool smc_link_usable(struct smc_link *lnk)
return true;
}
+static inline bool smc_link_sendable(struct smc_link *lnk)
+{
+ return smc_link_usable(lnk) &&
+ lnk->qp_attr.cur_qp_state == IB_QPS_RTS;
+}
+
static inline bool smc_link_active(struct smc_link *lnk)
{
return lnk->state == SMC_LNK_ACTIVE;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index f1d323439a2af..ee1f0fdba0855 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1358,7 +1358,7 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn)
delllc.reason = htonl(rsn);
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
- if (!smc_link_usable(&lgr->lnk[i]))
+ if (!smc_link_sendable(&lgr->lnk[i]))
continue;
if (!smc_llc_send_message_wait(&lgr->lnk[i], &delllc))
break;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index a71c9631f1ad3..cae22d240e0a6 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -169,7 +169,7 @@ void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context)
static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
{
*idx = link->wr_tx_cnt;
- if (!smc_link_usable(link))
+ if (!smc_link_sendable(link))
return -ENOLINK;
for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) {
if (!test_and_set_bit(*idx, link->wr_tx_mask))
@@ -212,7 +212,7 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
} else {
rc = wait_event_interruptible_timeout(
link->wr_tx_wait,
- !smc_link_usable(link) ||
+ !smc_link_sendable(link) ||
lgr->terminating ||
(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
SMC_WR_TX_WAIT_FREE_SLOT_TIME);
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 2bc626f230a56..102d515757ee2 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -62,7 +62,7 @@ static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val)
static inline bool smc_wr_tx_link_hold(struct smc_link *link)
{
- if (!smc_link_usable(link))
+ if (!smc_link_sendable(link))
return false;
atomic_inc(&link->wr_tx_refcnt);
return true;
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 25/48] net/smc: fix kernel panic caused by race of smc_sock
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (23 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 24/48] net/smc: dont send CDC/LLC message if link not ready Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 26/48] igc: Fix TX timestamp support for non-MSI-X platforms Greg Kroah-Hartman
` (25 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Wen Gu, Dust Li, David S. Miller,
Sasha Levin
From: Dust Li <dust.li@linux.alibaba.com>
[ Upstream commit 349d43127dac00c15231e8ffbcaabd70f7b0e544 ]
A crash occurs when smc_cdc_tx_handler() tries to access smc_sock
but smc_release() has already freed it.
[ 4570.695099] BUG: unable to handle page fault for address: 000000002eae9e88
[ 4570.696048] #PF: supervisor write access in kernel mode
[ 4570.696728] #PF: error_code(0x0002) - not-present page
[ 4570.697401] PGD 0 P4D 0
[ 4570.697716] Oops: 0002 [#1] PREEMPT SMP NOPTI
[ 4570.698228] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.16.0-rc4+ #111
[ 4570.699013] Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 8c24b4c 04/0
[ 4570.699933] RIP: 0010:_raw_spin_lock+0x1a/0x30
<...>
[ 4570.711446] Call Trace:
[ 4570.711746] <IRQ>
[ 4570.711992] smc_cdc_tx_handler+0x41/0xc0
[ 4570.712470] smc_wr_tx_tasklet_fn+0x213/0x560
[ 4570.712981] ? smc_cdc_tx_dismisser+0x10/0x10
[ 4570.713489] tasklet_action_common.isra.17+0x66/0x140
[ 4570.714083] __do_softirq+0x123/0x2f4
[ 4570.714521] irq_exit_rcu+0xc4/0xf0
[ 4570.714934] common_interrupt+0xba/0xe0
Though smc_cdc_tx_handler() checked the existence of smc connection,
smc_release() may have already dismissed and released the smc socket
before smc_cdc_tx_handler() further visits it.
smc_cdc_tx_handler() |smc_release()
if (!conn) |
|
|smc_cdc_tx_dismiss_slots()
| smc_cdc_tx_dismisser()
|
|sock_put(&smc->sk) <- last sock_put,
| smc_sock freed
bh_lock_sock(&smc->sk) (panic) |
To make sure we won't receive any CDC messages after we free the
smc_sock, add a refcount on the smc_connection for inflight CDC
message(posted to the QP but haven't received related CQE), and
don't release the smc_connection until all the inflight CDC messages
haven been done, for both success or failed ones.
Using refcount on CDC messages brings another problem: when the link
is going to be destroyed, smcr_link_clear() will reset the QP, which
then remove all the pending CQEs related to the QP in the CQ. To make
sure all the CQEs will always come back so the refcount on the
smc_connection can always reach 0, smc_ib_modify_qp_reset() was replaced
by smc_ib_modify_qp_error().
And remove the timeout in smc_wr_tx_wait_no_pending_sends() since we
need to wait for all pending WQEs done, or we may encounter use-after-
free when handling CQEs.
For IB device removal routine, we need to wait for all the QPs on that
device been destroyed before we can destroy CQs on the device, or
the refcount on smc_connection won't reach 0 and smc_sock cannot be
released.
Fixes: 5f08318f617b ("smc: connection data control (CDC)")
Reported-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/smc/smc.h | 5 +++++
net/smc/smc_cdc.c | 52 +++++++++++++++++++++-------------------------
net/smc/smc_cdc.h | 2 +-
net/smc/smc_core.c | 25 +++++++++++++++++-----
net/smc/smc_ib.c | 4 ++--
net/smc/smc_ib.h | 1 +
net/smc/smc_wr.c | 41 +++---------------------------------
net/smc/smc_wr.h | 3 +--
8 files changed, 57 insertions(+), 76 deletions(-)
diff --git a/net/smc/smc.h b/net/smc/smc.h
index d65e15f0c944c..e6919fe31617b 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -170,6 +170,11 @@ struct smc_connection {
u16 tx_cdc_seq; /* sequence # for CDC send */
u16 tx_cdc_seq_fin; /* sequence # - tx completed */
spinlock_t send_lock; /* protect wr_sends */
+ atomic_t cdc_pend_tx_wr; /* number of pending tx CDC wqe
+ * - inc when post wqe,
+ * - dec on polled tx cqe
+ */
+ wait_queue_head_t cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/
struct delayed_work tx_work; /* retry of smc_cdc_msg_send */
u32 tx_off; /* base offset in peer rmb */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 3602829006dda..0c490cdde6a49 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -31,10 +31,6 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
struct smc_sock *smc;
int diff;
- if (!conn)
- /* already dismissed */
- return;
-
smc = container_of(conn, struct smc_sock, conn);
bh_lock_sock(&smc->sk);
if (!wc_status) {
@@ -51,6 +47,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
conn);
conn->tx_cdc_seq_fin = cdcpend->ctrl_seq;
}
+
+ if (atomic_dec_and_test(&conn->cdc_pend_tx_wr) &&
+ unlikely(wq_has_sleeper(&conn->cdc_pend_tx_wq)))
+ wake_up(&conn->cdc_pend_tx_wq);
+ WARN_ON(atomic_read(&conn->cdc_pend_tx_wr) < 0);
+
smc_tx_sndbuf_nonfull(smc);
bh_unlock_sock(&smc->sk);
}
@@ -107,6 +109,10 @@ int smc_cdc_msg_send(struct smc_connection *conn,
conn->tx_cdc_seq++;
conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed);
+
+ atomic_inc(&conn->cdc_pend_tx_wr);
+ smp_mb__after_atomic(); /* Make sure cdc_pend_tx_wr added before post */
+
rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
if (!rc) {
smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
@@ -114,6 +120,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
} else {
conn->tx_cdc_seq--;
conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
+ atomic_dec(&conn->cdc_pend_tx_wr);
}
return rc;
@@ -136,7 +143,18 @@ int smcr_cdc_msg_send_validation(struct smc_connection *conn,
peer->token = htonl(local->token);
peer->prod_flags.failover_validation = 1;
+ /* We need to set pend->conn here to make sure smc_cdc_tx_handler()
+ * can handle properly
+ */
+ smc_cdc_add_pending_send(conn, pend);
+
+ atomic_inc(&conn->cdc_pend_tx_wr);
+ smp_mb__after_atomic(); /* Make sure cdc_pend_tx_wr added before post */
+
rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
+ if (unlikely(rc))
+ atomic_dec(&conn->cdc_pend_tx_wr);
+
return rc;
}
@@ -193,31 +211,9 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
return rc;
}
-static bool smc_cdc_tx_filter(struct smc_wr_tx_pend_priv *tx_pend,
- unsigned long data)
+void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn)
{
- struct smc_connection *conn = (struct smc_connection *)data;
- struct smc_cdc_tx_pend *cdc_pend =
- (struct smc_cdc_tx_pend *)tx_pend;
-
- return cdc_pend->conn == conn;
-}
-
-static void smc_cdc_tx_dismisser(struct smc_wr_tx_pend_priv *tx_pend)
-{
- struct smc_cdc_tx_pend *cdc_pend =
- (struct smc_cdc_tx_pend *)tx_pend;
-
- cdc_pend->conn = NULL;
-}
-
-void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
-{
- struct smc_link *link = conn->lnk;
-
- smc_wr_tx_dismiss_slots(link, SMC_CDC_MSG_TYPE,
- smc_cdc_tx_filter, smc_cdc_tx_dismisser,
- (unsigned long)conn);
+ wait_event(conn->cdc_pend_tx_wq, !atomic_read(&conn->cdc_pend_tx_wr));
}
/* Send a SMC-D CDC header.
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 0a0a89abd38b2..696cc11f2303b 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -291,7 +291,7 @@ int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
struct smc_rdma_wr **wr_rdma_buf,
struct smc_cdc_tx_pend **pend);
-void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
+void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn);
int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
struct smc_cdc_tx_pend *pend);
int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index fb4327a81a0f0..2a22dc85951ee 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -657,7 +657,7 @@ void smc_conn_free(struct smc_connection *conn)
smc_ism_unset_conn(conn);
tasklet_kill(&conn->rx_tsklet);
} else {
- smc_cdc_tx_dismiss_slots(conn);
+ smc_cdc_wait_pend_tx_wr(conn);
if (current_work() != &conn->abort_work)
cancel_work_sync(&conn->abort_work);
}
@@ -734,7 +734,7 @@ void smcr_link_clear(struct smc_link *lnk, bool log)
smc_llc_link_clear(lnk, log);
smcr_buf_unmap_lgr(lnk);
smcr_rtoken_clear_link(lnk);
- smc_ib_modify_qp_reset(lnk);
+ smc_ib_modify_qp_error(lnk);
smc_wr_free_link(lnk);
smc_ib_destroy_queue_pair(lnk);
smc_ib_dealloc_protection_domain(lnk);
@@ -878,7 +878,7 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft)
else
tasklet_unlock_wait(&conn->rx_tsklet);
} else {
- smc_cdc_tx_dismiss_slots(conn);
+ smc_cdc_wait_pend_tx_wr(conn);
}
smc_lgr_unregister_conn(conn);
smc_close_active_abort(smc);
@@ -1002,11 +1002,16 @@ void smc_smcd_terminate_all(struct smcd_dev *smcd)
/* Called when an SMCR device is removed or the smc module is unloaded.
* If smcibdev is given, all SMCR link groups using this device are terminated.
* If smcibdev is NULL, all SMCR link groups are terminated.
+ *
+ * We must wait here for QPs been destroyed before we destroy the CQs,
+ * or we won't received any CQEs and cdc_pend_tx_wr cannot reach 0 thus
+ * smc_sock cannot be released.
*/
void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
{
struct smc_link_group *lgr, *lg;
LIST_HEAD(lgr_free_list);
+ LIST_HEAD(lgr_linkdown_list);
int i;
spin_lock_bh(&smc_lgr_list.lock);
@@ -1018,7 +1023,7 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) {
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (lgr->lnk[i].smcibdev == smcibdev)
- smcr_link_down_cond_sched(&lgr->lnk[i]);
+ list_move_tail(&lgr->list, &lgr_linkdown_list);
}
}
}
@@ -1030,6 +1035,16 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
__smc_lgr_terminate(lgr, false);
}
+ list_for_each_entry_safe(lgr, lg, &lgr_linkdown_list, list) {
+ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+ if (lgr->lnk[i].smcibdev == smcibdev) {
+ mutex_lock(&lgr->llc_conf_mutex);
+ smcr_link_down_cond(&lgr->lnk[i]);
+ mutex_unlock(&lgr->llc_conf_mutex);
+ }
+ }
+ }
+
if (smcibdev) {
if (atomic_read(&smcibdev->lnk_cnt))
wait_event(smcibdev->lnks_deleted,
@@ -1129,7 +1144,6 @@ static void smcr_link_down(struct smc_link *lnk)
if (!lgr || lnk->state == SMC_LNK_UNUSED || list_empty(&lgr->list))
return;
- smc_ib_modify_qp_reset(lnk);
to_lnk = smc_switch_conns(lgr, lnk, true);
if (!to_lnk) { /* no backup link available */
smcr_link_clear(lnk, true);
@@ -1357,6 +1371,7 @@ create:
conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
conn->urg_state = SMC_URG_READ;
+ init_waitqueue_head(&conn->cdc_pend_tx_wq);
INIT_WORK(&smc->conn.abort_work, smc_conn_abort_work);
if (ini->is_smcd) {
conn->rx_off = sizeof(struct smcd_cdc_msg);
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index fc766b537ac7a..f1ffbd414602e 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -100,12 +100,12 @@ int smc_ib_modify_qp_rts(struct smc_link *lnk)
IB_QP_MAX_QP_RD_ATOMIC);
}
-int smc_ib_modify_qp_reset(struct smc_link *lnk)
+int smc_ib_modify_qp_error(struct smc_link *lnk)
{
struct ib_qp_attr qp_attr;
memset(&qp_attr, 0, sizeof(qp_attr));
- qp_attr.qp_state = IB_QPS_RESET;
+ qp_attr.qp_state = IB_QPS_ERR;
return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE);
}
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 2ce481187dd0b..f90d15eae2aab 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -74,6 +74,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk);
int smc_ib_ready_link(struct smc_link *lnk);
int smc_ib_modify_qp_rts(struct smc_link *lnk);
int smc_ib_modify_qp_reset(struct smc_link *lnk);
+int smc_ib_modify_qp_error(struct smc_link *lnk);
long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
struct smc_buf_desc *buf_slot, u8 link_idx);
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index cae22d240e0a6..5a81f8c9ebf90 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -62,13 +62,9 @@ static inline bool smc_wr_is_tx_pend(struct smc_link *link)
}
/* wait till all pending tx work requests on the given link are completed */
-int smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
+void smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
{
- if (wait_event_timeout(link->wr_tx_wait, !smc_wr_is_tx_pend(link),
- SMC_WR_TX_WAIT_PENDING_TIME))
- return 0;
- else /* timeout */
- return -EPIPE;
+ wait_event(link->wr_tx_wait, !smc_wr_is_tx_pend(link));
}
static inline int smc_wr_tx_find_pending_index(struct smc_link *link, u64 wr_id)
@@ -87,7 +83,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
struct smc_wr_tx_pend pnd_snd;
struct smc_link *link;
u32 pnd_snd_idx;
- int i;
link = wc->qp->qp_context;
@@ -115,14 +110,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask))
return;
if (wc->status) {
- for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
- /* clear full struct smc_wr_tx_pend including .priv */
- memset(&link->wr_tx_pends[i], 0,
- sizeof(link->wr_tx_pends[i]));
- memset(&link->wr_tx_bufs[i], 0,
- sizeof(link->wr_tx_bufs[i]));
- clear_bit(i, link->wr_tx_mask);
- }
/* terminate link */
smcr_link_down_cond_sched(link);
}
@@ -351,25 +338,6 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
return rc;
}
-void smc_wr_tx_dismiss_slots(struct smc_link *link, u8 wr_tx_hdr_type,
- smc_wr_tx_filter filter,
- smc_wr_tx_dismisser dismisser,
- unsigned long data)
-{
- struct smc_wr_tx_pend_priv *tx_pend;
- struct smc_wr_rx_hdr *wr_tx;
- int i;
-
- for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
- wr_tx = (struct smc_wr_rx_hdr *)&link->wr_tx_bufs[i];
- if (wr_tx->type != wr_tx_hdr_type)
- continue;
- tx_pend = &link->wr_tx_pends[i].priv;
- if (filter(tx_pend, data))
- dismisser(tx_pend);
- }
-}
-
/****************************** receive queue ********************************/
int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler)
@@ -574,10 +542,7 @@ void smc_wr_free_link(struct smc_link *lnk)
smc_wr_wakeup_reg_wait(lnk);
smc_wr_wakeup_tx_wait(lnk);
- if (smc_wr_tx_wait_no_pending_sends(lnk))
- memset(lnk->wr_tx_mask, 0,
- BITS_TO_LONGS(SMC_WR_BUF_CNT) *
- sizeof(*lnk->wr_tx_mask));
+ smc_wr_tx_wait_no_pending_sends(lnk);
wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt)));
wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt)));
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 102d515757ee2..cb58e60078f57 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -22,7 +22,6 @@
#define SMC_WR_BUF_CNT 16 /* # of ctrl buffers per link */
#define SMC_WR_TX_WAIT_FREE_SLOT_TIME (10 * HZ)
-#define SMC_WR_TX_WAIT_PENDING_TIME (5 * HZ)
#define SMC_WR_TX_SIZE 44 /* actual size of wr_send data (<=SMC_WR_BUF_SIZE) */
@@ -122,7 +121,7 @@ void smc_wr_tx_dismiss_slots(struct smc_link *lnk, u8 wr_rx_hdr_type,
smc_wr_tx_filter filter,
smc_wr_tx_dismisser dismisser,
unsigned long data);
-int smc_wr_tx_wait_no_pending_sends(struct smc_link *link);
+void smc_wr_tx_wait_no_pending_sends(struct smc_link *link);
int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler);
int smc_wr_rx_post_init(struct smc_link *link);
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 26/48] igc: Fix TX timestamp support for non-MSI-X platforms
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (24 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 25/48] net/smc: fix kernel panic caused by race of smc_sock Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 27/48] ionic: Initialize the lif->dbid_inuse bitmap Greg Kroah-Hartman
` (24 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, James McLaughlin,
Vinicius Costa Gomes, Nechama Kraus, Tony Nguyen, Sasha Levin
From: James McLaughlin <james.mclaughlin@qsc.com>
[ Upstream commit f85846bbf43de38fb2c89fe7d2a085608c4eb25a ]
Time synchronization was not properly enabled on non-MSI-X platforms.
Fixes: 2c344ae24501 ("igc: Add support for TX timestamping")
Signed-off-by: James McLaughlin <james.mclaughlin@qsc.com>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Tested-by: Nechama Kraus <nechamax.kraus@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/intel/igc/igc_main.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index cae090a072524..61cebb7df6bcb 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -4422,6 +4422,9 @@ static irqreturn_t igc_intr_msi(int irq, void *data)
mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
+ if (icr & IGC_ICR_TS)
+ igc_tsync_interrupt(adapter);
+
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
@@ -4465,6 +4468,9 @@ static irqreturn_t igc_intr(int irq, void *data)
mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
+ if (icr & IGC_ICR_TS)
+ igc_tsync_interrupt(adapter);
+
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 27/48] ionic: Initialize the lif->dbid_inuse bitmap
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (25 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 26/48] igc: Fix TX timestamp support for non-MSI-X platforms Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 28/48] net/mlx5e: Fix wrong features assignment in case of error Greg Kroah-Hartman
` (23 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Christophe JAILLET, Shannon Nelson,
Jakub Kicinski, Sasha Levin
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
[ Upstream commit 140c7bc7d1195750342ea0e6ab76179499ae7cd7 ]
When allocated, this bitmap is not initialized. Only the first bit is set a
few lines below.
Use bitmap_zalloc() to make sure that it is cleared before being used.
Fixes: 6461b446f2a0 ("ionic: Add interrupts and doorbells")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Link: https://lore.kernel.org/r/6a478eae0b5e6c63774e1f0ddb1a3f8c38fa8ade.1640527506.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/pensando/ionic/ionic_lif.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 1b44155fa24b2..e95c09dc2c30d 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -2836,7 +2836,7 @@ int ionic_lif_init(struct ionic_lif *lif)
return -EINVAL;
}
- lif->dbid_inuse = bitmap_alloc(lif->dbid_count, GFP_KERNEL);
+ lif->dbid_inuse = bitmap_zalloc(lif->dbid_count, GFP_KERNEL);
if (!lif->dbid_inuse) {
dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n");
return -ENOMEM;
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 28/48] net/mlx5e: Fix wrong features assignment in case of error
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (26 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 27/48] ionic: Initialize the lif->dbid_inuse bitmap Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 29/48] selftests/net: udpgso_bench_tx: fix dst ip argument Greg Kroah-Hartman
` (22 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Gal Pressman, Saeed Mahameed, Sasha Levin
From: Gal Pressman <gal@nvidia.com>
[ Upstream commit 992d8a4e38f0527f24e273ce3a9cd6dea1a6a436 ]
In case of an error in mlx5e_set_features(), 'netdev->features' must be
updated with the correct state of the device to indicate which features
were updated successfully.
To do that we maintain a copy of 'netdev->features' and update it after
successful feature changes, so we can assign it to back to
'netdev->features' if needed.
However, since not all netdev features are handled by the driver (e.g.
GRO/TSO/etc), some features may not be updated correctly in case of an
error updating another feature.
For example, while requesting to disable TSO (feature which is not
handled by the driver) and enable HW-GRO, if an error occurs during
HW-GRO enable, 'oper_features' will be assigned with 'netdev->features'
and HW-GRO turned off. TSO will remain enabled in such case, which is a
bug.
To solve that, instead of using 'netdev->features' as the baseline of
'oper_features' and changing it on set feature success, use 'features'
instead and update it in case of errors.
Fixes: 75b81ce719b7 ("net/mlx5e: Don't override netdev features field unless in error flow")
Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3f5a2bb9b3c0b..2f6c3a5813ed1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3935,12 +3935,11 @@ static int set_feature_arfs(struct net_device *netdev, bool enable)
static int mlx5e_handle_feature(struct net_device *netdev,
netdev_features_t *features,
- netdev_features_t wanted_features,
netdev_features_t feature,
mlx5e_feature_handler feature_handler)
{
- netdev_features_t changes = wanted_features ^ netdev->features;
- bool enable = !!(wanted_features & feature);
+ netdev_features_t changes = *features ^ netdev->features;
+ bool enable = !!(*features & feature);
int err;
if (!(changes & feature))
@@ -3948,22 +3947,22 @@ static int mlx5e_handle_feature(struct net_device *netdev,
err = feature_handler(netdev, enable);
if (err) {
+ MLX5E_SET_FEATURE(features, feature, !enable);
netdev_err(netdev, "%s feature %pNF failed, err %d\n",
enable ? "Enable" : "Disable", &feature, err);
return err;
}
- MLX5E_SET_FEATURE(features, feature, enable);
return 0;
}
int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
{
- netdev_features_t oper_features = netdev->features;
+ netdev_features_t oper_features = features;
int err = 0;
#define MLX5E_HANDLE_FEATURE(feature, handler) \
- mlx5e_handle_feature(netdev, &oper_features, features, feature, handler)
+ mlx5e_handle_feature(netdev, &oper_features, feature, handler)
err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER,
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 29/48] selftests/net: udpgso_bench_tx: fix dst ip argument
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (27 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 28/48] net/mlx5e: Fix wrong features assignment in case of error Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 30/48] net/ncsi: check for error return from call to nla_put_u32 Greg Kroah-Hartman
` (21 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Jianguo Wu, Willem de Bruijn,
Jakub Kicinski, Sasha Levin
From: wujianguo <wujianguo@chinatelecom.cn>
[ Upstream commit 9c1952aeaa98b3cfc49e2a79cb2c7d6a674213e9 ]
udpgso_bench_tx call setup_sockaddr() for dest address before
parsing all arguments, if we specify "-p ${dst_port}" after "-D ${dst_ip}",
then ${dst_port} will be ignored, and using default cfg_port 8000.
This will cause test case "multiple GRO socks" failed in udpgro.sh.
Setup sockaddr after parsing all arguments.
Fixes: 3a687bef148d ("selftests: udp gso benchmark")
Signed-off-by: Jianguo Wu <wujianguo@chinatelecom.cn>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/ff620d9f-5b52-06ab-5286-44b945453002@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
tools/testing/selftests/net/udpgso_bench_tx.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index 17512a43885e7..f1fdaa2702913 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -419,6 +419,7 @@ static void usage(const char *filepath)
static void parse_opts(int argc, char **argv)
{
+ const char *bind_addr = NULL;
int max_len, hdrlen;
int c;
@@ -446,7 +447,7 @@ static void parse_opts(int argc, char **argv)
cfg_cpu = strtol(optarg, NULL, 0);
break;
case 'D':
- setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+ bind_addr = optarg;
break;
case 'l':
cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
@@ -492,6 +493,11 @@ static void parse_opts(int argc, char **argv)
}
}
+ if (!bind_addr)
+ bind_addr = cfg_family == PF_INET6 ? "::" : "0.0.0.0";
+
+ setup_sockaddr(cfg_family, bind_addr, &cfg_dst_addr);
+
if (optind != argc)
usage(argv[0]);
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 30/48] net/ncsi: check for error return from call to nla_put_u32
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (28 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 29/48] selftests/net: udpgso_bench_tx: fix dst ip argument Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 31/48] fsl/fman: Fix missing put_device() call in fman_port_probe Greg Kroah-Hartman
` (20 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Jiasheng Jiang, Jakub Kicinski, Sasha Levin
From: Jiasheng Jiang <jiasheng@iscas.ac.cn>
[ Upstream commit 92a34ab169f9eefe29cd420ce96b0a0a2a1da853 ]
As we can see from the comment of the nla_put() that it could return
-EMSGSIZE if the tailroom of the skb is insufficient.
Therefore, it should be better to check the return value of the
nla_put_u32 and return the error code if error accurs.
Also, there are many other functions have the same problem, and if this
patch is correct, I will commit a new version to fix all.
Fixes: 955dc68cb9b2 ("net/ncsi: Add generic netlink family")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Link: https://lore.kernel.org/r/20211229032118.1706294-1-jiasheng@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/ncsi/ncsi-netlink.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index bb5f1650f11cb..c189b4c8a1823 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -112,7 +112,11 @@ static int ncsi_write_package_info(struct sk_buff *skb,
pnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR);
if (!pnest)
return -ENOMEM;
- nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
+ rc = nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
+ if (rc) {
+ nla_nest_cancel(skb, pnest);
+ return rc;
+ }
if ((0x1 << np->id) == ndp->package_whitelist)
nla_put_flag(skb, NCSI_PKG_ATTR_FORCED);
cnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR_CHANNEL_LIST);
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 31/48] fsl/fman: Fix missing put_device() call in fman_port_probe
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (29 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 30/48] net/ncsi: check for error return from call to nla_put_u32 Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 32/48] i2c: validate user data in compat ioctl Greg Kroah-Hartman
` (19 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Miaoqian Lin, David S. Miller, Sasha Levin
From: Miaoqian Lin <linmq006@gmail.com>
[ Upstream commit bf2b09fedc17248b315f80fb249087b7d28a69a6 ]
The reference taken by 'of_find_device_by_node()' must be released when
not needed anymore.
Add the corresponding 'put_device()' in the and error handling paths.
Fixes: 18a6c85fcc78 ("fsl/fman: Add FMan Port Support")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/freescale/fman/fman_port.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index d9baac0dbc7d0..4c9d05c45c033 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1805,7 +1805,7 @@ static int fman_port_probe(struct platform_device *of_dev)
fman = dev_get_drvdata(&fm_pdev->dev);
if (!fman) {
err = -EINVAL;
- goto return_err;
+ goto put_device;
}
err = of_property_read_u32(port_node, "cell-index", &val);
@@ -1813,7 +1813,7 @@ static int fman_port_probe(struct platform_device *of_dev)
dev_err(port->dev, "%s: reading cell-index for %pOF failed\n",
__func__, port_node);
err = -EINVAL;
- goto return_err;
+ goto put_device;
}
port_id = (u8)val;
port->dts_params.id = port_id;
@@ -1847,7 +1847,7 @@ static int fman_port_probe(struct platform_device *of_dev)
} else {
dev_err(port->dev, "%s: Illegal port type\n", __func__);
err = -EINVAL;
- goto return_err;
+ goto put_device;
}
port->dts_params.type = port_type;
@@ -1861,7 +1861,7 @@ static int fman_port_probe(struct platform_device *of_dev)
dev_err(port->dev, "%s: incorrect qman-channel-id\n",
__func__);
err = -EINVAL;
- goto return_err;
+ goto put_device;
}
port->dts_params.qman_channel_id = qman_channel_id;
}
@@ -1871,7 +1871,7 @@ static int fman_port_probe(struct platform_device *of_dev)
dev_err(port->dev, "%s: of_address_to_resource() failed\n",
__func__);
err = -ENOMEM;
- goto return_err;
+ goto put_device;
}
port->dts_params.fman = fman;
@@ -1896,6 +1896,8 @@ static int fman_port_probe(struct platform_device *of_dev)
return 0;
+put_device:
+ put_device(&fm_pdev->dev);
return_err:
of_node_put(port_node);
free_port:
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 32/48] i2c: validate user data in compat ioctl
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (30 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 31/48] fsl/fman: Fix missing put_device() call in fman_port_probe Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 33/48] nfc: uapi: use kernel size_t to fix user-space builds Greg Kroah-Hartman
` (18 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Pavel Skripkin, Wolfram Sang,
Sasha Levin, syzbot+e417648b303855b91d8a
From: Pavel Skripkin <paskripkin@gmail.com>
[ Upstream commit bb436283e25aaf1533ce061605d23a9564447bdf ]
Wrong user data may cause warning in i2c_transfer(), ex: zero msgs.
Userspace should not be able to trigger warnings, so this patch adds
validation checks for user data in compact ioctl to prevent reported
warnings
Reported-and-tested-by: syzbot+e417648b303855b91d8a@syzkaller.appspotmail.com
Fixes: 7d5cb45655f2 ("i2c compat ioctls: move to ->compat_ioctl()")
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/i2c/i2c-dev.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index f358120d59b38..dafad891998ec 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -536,6 +536,9 @@ static long compat_i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned lo
sizeof(rdwr_arg)))
return -EFAULT;
+ if (!rdwr_arg.msgs || rdwr_arg.nmsgs == 0)
+ return -EINVAL;
+
if (rdwr_arg.nmsgs > I2C_RDWR_IOCTL_MAX_MSGS)
return -EINVAL;
--
2.34.1
^ permalink raw reply related [flat|nested] 53+ messages in thread* [PATCH 5.10 33/48] nfc: uapi: use kernel size_t to fix user-space builds
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (31 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 32/48] i2c: validate user data in compat ioctl Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 34/48] uapi: fix linux/nfc.h userspace compilation errors Greg Kroah-Hartman
` (17 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Krzysztof Kozlowski, David S. Miller
From: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
commit 79b69a83705e621b258ac6d8ae6d3bfdb4b930aa upstream.
Fix user-space builds if it includes /usr/include/linux/nfc.h before
some of other headers:
/usr/include/linux/nfc.h:281:9: error: unknown type name ‘size_t’
281 | size_t service_name_len;
| ^~~~~~
Fixes: d646960f7986 ("NFC: Initial LLCP support")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/uapi/linux/nfc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -278,7 +278,7 @@ struct sockaddr_nfc_llcp {
__u8 dsap; /* Destination SAP, if known */
__u8 ssap; /* Source SAP to be bound to */
char service_name[NFC_LLCP_MAX_SERVICE_NAME]; /* Service name URI */;
- size_t service_name_len;
+ __kernel_size_t service_name_len;
};
/* NFC socket protocols */
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 34/48] uapi: fix linux/nfc.h userspace compilation errors
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (32 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 33/48] nfc: uapi: use kernel size_t to fix user-space builds Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 35/48] drm/amdgpu: When the VCN(1.0) block is suspended, powergating is explicitly enabled Greg Kroah-Hartman
` (16 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Dmitry V. Levin, Krzysztof Kozlowski,
David S. Miller
From: Dmitry V. Levin <ldv@altlinux.org>
commit 7175f02c4e5f5a9430113ab9ca0fd0ce98b28a51 upstream.
Replace sa_family_t with __kernel_sa_family_t to fix the following
linux/nfc.h userspace compilation errors:
/usr/include/linux/nfc.h:266:2: error: unknown type name 'sa_family_t'
sa_family_t sa_family;
/usr/include/linux/nfc.h:274:2: error: unknown type name 'sa_family_t'
sa_family_t sa_family;
Fixes: 23b7869c0fd0 ("NFC: add the NFC socket raw protocol")
Fixes: d646960f7986 ("NFC: Initial LLCP support")
Cc: <stable@vger.kernel.org>
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/uapi/linux/nfc.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -263,7 +263,7 @@ enum nfc_sdp_attr {
#define NFC_SE_ENABLED 0x1
struct sockaddr_nfc {
- sa_family_t sa_family;
+ __kernel_sa_family_t sa_family;
__u32 dev_idx;
__u32 target_idx;
__u32 nfc_protocol;
@@ -271,7 +271,7 @@ struct sockaddr_nfc {
#define NFC_LLCP_MAX_SERVICE_NAME 63
struct sockaddr_nfc_llcp {
- sa_family_t sa_family;
+ __kernel_sa_family_t sa_family;
__u32 dev_idx;
__u32 target_idx;
__u32 nfc_protocol;
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 35/48] drm/amdgpu: When the VCN(1.0) block is suspended, powergating is explicitly enabled
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (33 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 34/48] uapi: fix linux/nfc.h userspace compilation errors Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 36/48] drm/amdgpu: add support for IP discovery gc_info table v2 Greg Kroah-Hartman
` (15 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, chen gong, Evan Quan, Alex Deucher
From: chen gong <curry.gong@amd.com>
commit b7865173cf6ae59942e2c69326a06e1c1df5ecf6 upstream.
Play a video on the raven (or PCO, raven2) platform, and then do the S3
test. When resume, the following error will be reported:
amdgpu 0000:02:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring
vcn_dec test failed (-110)
[drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block
<vcn_v1_0> failed -110
amdgpu 0000:02:00.0: amdgpu: amdgpu_device_ip_resume failed (-110).
PM: dpm_run_callback(): pci_pm_resume+0x0/0x90 returns -110
[why]
When playing the video: The power state flag of the vcn block is set to
POWER_STATE_ON.
When doing suspend: There is no change to the power state flag of the
vcn block, it is still POWER_STATE_ON.
When doing resume: Need to open the power gate of the vcn block and set
the power state flag of the VCN block to POWER_STATE_ON.
But at this time, the power state flag of the vcn block is already
POWER_STATE_ON. The power status flag check in the "8f2cdef drm/amd/pm:
avoid duplicate powergate/ungate setting" patch will return the
amdgpu_dpm_set_powergating_by_smu function directly.
As a result, the gate of the power was not opened, causing the
subsequent ring test to fail.
[how]
In the suspend function of the vcn block, explicitly change the power
state flag of the vcn block to POWER_STATE_OFF.
BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1828
Signed-off-by: chen gong <curry.gong@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 7 +++++++
1 file changed, 7 insertions(+)
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -254,6 +254,13 @@ static int vcn_v1_0_suspend(void *handle
{
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ bool idle_work_unexecuted;
+
+ idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.idle_work);
+ if (idle_work_unexecuted) {
+ if (adev->pm.dpm_enabled)
+ amdgpu_dpm_enable_uvd(adev, false);
+ }
r = vcn_v1_0_hw_fini(adev);
if (r)
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 36/48] drm/amdgpu: add support for IP discovery gc_info table v2
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (34 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 35/48] drm/amdgpu: When the VCN(1.0) block is suspended, powergating is explicitly enabled Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 37/48] xhci: Fresco FL1100 controller should not have BROKEN_MSI quirk set Greg Kroah-Hartman
` (14 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Hawking Zhang, Alex Deucher
From: Alex Deucher <alexander.deucher@amd.com>
commit 5e713c6afa34c0fd6f113bf7bb1c2847172d7b20 upstream.
Used on gfx9 based systems. Fixes incorrect CU counts reported
in the kernel log.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1833
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 76 ++++++++++++++++++--------
drivers/gpu/drm/amd/include/discovery.h | 49 ++++++++++++++++
2 files changed, 103 insertions(+), 22 deletions(-)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -372,10 +372,15 @@ int amdgpu_discovery_get_ip_version(stru
return -EINVAL;
}
+union gc_info {
+ struct gc_info_v1_0 v1;
+ struct gc_info_v2_0 v2;
+};
+
int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
{
struct binary_header *bhdr;
- struct gc_info_v1_0 *gc_info;
+ union gc_info *gc_info;
if (!adev->mman.discovery_bin) {
DRM_ERROR("ip discovery uninitialized\n");
@@ -383,27 +388,54 @@ int amdgpu_discovery_get_gfx_info(struct
}
bhdr = (struct binary_header *)adev->mman.discovery_bin;
- gc_info = (struct gc_info_v1_0 *)(adev->mman.discovery_bin +
+ gc_info = (union gc_info *)(adev->mman.discovery_bin +
le16_to_cpu(bhdr->table_list[GC].offset));
-
- adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se);
- adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->gc_num_wgp0_per_sa) +
- le32_to_cpu(gc_info->gc_num_wgp1_per_sa));
- adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->gc_num_sa_per_se);
- adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->gc_num_rb_per_se);
- adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->gc_num_gl2c);
- adev->gfx.config.max_gprs = le32_to_cpu(gc_info->gc_num_gprs);
- adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->gc_num_max_gs_thds);
- adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->gc_gs_table_depth);
- adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->gc_gsprim_buff_depth);
- adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->gc_double_offchip_lds_buffer);
- adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->gc_wave_size);
- adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->gc_max_waves_per_simd);
- adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->gc_max_scratch_slots_per_cu);
- adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->gc_lds_size);
- adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->gc_num_sc_per_se) /
- le32_to_cpu(gc_info->gc_num_sa_per_se);
- adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->gc_num_packer_per_sc);
-
+ switch (gc_info->v1.header.version_major) {
+ case 1:
+ adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v1.gc_num_se);
+ adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->v1.gc_num_wgp0_per_sa) +
+ le32_to_cpu(gc_info->v1.gc_num_wgp1_per_sa));
+ adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+ adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v1.gc_num_rb_per_se);
+ adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v1.gc_num_gl2c);
+ adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v1.gc_num_gprs);
+ adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v1.gc_num_max_gs_thds);
+ adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v1.gc_gs_table_depth);
+ adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v1.gc_gsprim_buff_depth);
+ adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v1.gc_double_offchip_lds_buffer);
+ adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v1.gc_wave_size);
+ adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v1.gc_max_waves_per_simd);
+ adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v1.gc_max_scratch_slots_per_cu);
+ adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v1.gc_lds_size);
+ adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v1.gc_num_sc_per_se) /
+ le32_to_cpu(gc_info->v1.gc_num_sa_per_se);
+ adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v1.gc_num_packer_per_sc);
+ break;
+ case 2:
+ adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v2.gc_num_se);
+ adev->gfx.config.max_cu_per_sh = le32_to_cpu(gc_info->v2.gc_num_cu_per_sh);
+ adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+ adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v2.gc_num_rb_per_se);
+ adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v2.gc_num_tccs);
+ adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v2.gc_num_gprs);
+ adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v2.gc_num_max_gs_thds);
+ adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v2.gc_gs_table_depth);
+ adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v2.gc_gsprim_buff_depth);
+ adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v2.gc_double_offchip_lds_buffer);
+ adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v2.gc_wave_size);
+ adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v2.gc_max_waves_per_simd);
+ adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v2.gc_max_scratch_slots_per_cu);
+ adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v2.gc_lds_size);
+ adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) /
+ le32_to_cpu(gc_info->v2.gc_num_sh_per_se);
+ adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc);
+ break;
+ default:
+ dev_err(adev->dev,
+ "Unhandled GC info table %d.%d\n",
+ gc_info->v1.header.version_major,
+ gc_info->v1.header.version_minor);
+ return -EINVAL;
+ }
return 0;
}
--- a/drivers/gpu/drm/amd/include/discovery.h
+++ b/drivers/gpu/drm/amd/include/discovery.h
@@ -143,6 +143,55 @@ struct gc_info_v1_0 {
uint32_t gc_num_gl2a;
};
+struct gc_info_v1_1 {
+ struct gpu_info_header header;
+
+ uint32_t gc_num_se;
+ uint32_t gc_num_wgp0_per_sa;
+ uint32_t gc_num_wgp1_per_sa;
+ uint32_t gc_num_rb_per_se;
+ uint32_t gc_num_gl2c;
+ uint32_t gc_num_gprs;
+ uint32_t gc_num_max_gs_thds;
+ uint32_t gc_gs_table_depth;
+ uint32_t gc_gsprim_buff_depth;
+ uint32_t gc_parameter_cache_depth;
+ uint32_t gc_double_offchip_lds_buffer;
+ uint32_t gc_wave_size;
+ uint32_t gc_max_waves_per_simd;
+ uint32_t gc_max_scratch_slots_per_cu;
+ uint32_t gc_lds_size;
+ uint32_t gc_num_sc_per_se;
+ uint32_t gc_num_sa_per_se;
+ uint32_t gc_num_packer_per_sc;
+ uint32_t gc_num_gl2a;
+ uint32_t gc_num_tcp_per_sa;
+ uint32_t gc_num_sdp_interface;
+ uint32_t gc_num_tcps;
+};
+
+struct gc_info_v2_0 {
+ struct gpu_info_header header;
+
+ uint32_t gc_num_se;
+ uint32_t gc_num_cu_per_sh;
+ uint32_t gc_num_sh_per_se;
+ uint32_t gc_num_rb_per_se;
+ uint32_t gc_num_tccs;
+ uint32_t gc_num_gprs;
+ uint32_t gc_num_max_gs_thds;
+ uint32_t gc_gs_table_depth;
+ uint32_t gc_gsprim_buff_depth;
+ uint32_t gc_parameter_cache_depth;
+ uint32_t gc_double_offchip_lds_buffer;
+ uint32_t gc_wave_size;
+ uint32_t gc_max_waves_per_simd;
+ uint32_t gc_max_scratch_slots_per_cu;
+ uint32_t gc_lds_size;
+ uint32_t gc_num_sc_per_se;
+ uint32_t gc_num_packer_per_sc;
+};
+
typedef struct harvest_info_header {
uint32_t signature; /* Table Signature */
uint32_t version; /* Table Version */
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 37/48] xhci: Fresco FL1100 controller should not have BROKEN_MSI quirk set.
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (35 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 36/48] drm/amdgpu: add support for IP discovery gc_info table v2 Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 38/48] usb: gadget: f_fs: Clear ffs_eventfd in ffs_data_clear Greg Kroah-Hartman
` (13 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Nikolay Martynov, Mathias Nyman
From: Mathias Nyman <mathias.nyman@linux.intel.com>
commit e4844092581ceec22489b66c42edc88bc6079783 upstream.
The Fresco Logic FL1100 controller needs the TRUST_TX_LENGTH quirk like
other Fresco controllers, but should not have the BROKEN_MSI quirks set.
BROKEN_MSI quirk causes issues in detecting usb drives connected to docks
with this FL1100 controller.
The BROKEN_MSI flag was apparently accidentally set together with the
TRUST_TX_LENGTH quirk
Original patch went to stable so this should go there as well.
Fixes: ea0f69d82119 ("xhci: Enable trust tx length quirk for Fresco FL11 USB controller")
Cc: stable@vger.kernel.org
cc: Nikolay Martynov <mar.kolya@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20211221112825.54690-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/xhci-pci.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -122,7 +122,6 @@ static void xhci_pci_quirks(struct devic
/* Look for vendor-specific quirks */
if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
(pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK ||
- pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1100 ||
pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1400)) {
if (pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK &&
pdev->revision == 0x0) {
@@ -157,6 +156,10 @@ static void xhci_pci_quirks(struct devic
pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009)
xhci->quirks |= XHCI_BROKEN_STREAMS;
+ if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
+ pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1100)
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+
if (pdev->vendor == PCI_VENDOR_ID_NEC)
xhci->quirks |= XHCI_NEC_HOST;
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 38/48] usb: gadget: f_fs: Clear ffs_eventfd in ffs_data_clear.
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (36 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 37/48] xhci: Fresco FL1100 controller should not have BROKEN_MSI quirk set Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 39/48] usb: mtu3: add memory barrier before set GPDs HWO Greg Kroah-Hartman
` (12 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Vincent Pelletier
From: Vincent Pelletier <plr.vincent@gmail.com>
commit b1e0887379422975f237d43d8839b751a6bcf154 upstream.
ffs_data_clear is indirectly called from both ffs_fs_kill_sb and
ffs_ep0_release, so it ends up being called twice when userland closes ep0
and then unmounts f_fs.
If userland provided an eventfd along with function's USB descriptors, it
ends up calling eventfd_ctx_put as many times, causing a refcount
underflow.
NULL-ify ffs_eventfd to prevent these extraneous eventfd_ctx_put calls.
Also, set epfiles to NULL right after de-allocating it, for readability.
For completeness, ffs_data_clear actually ends up being called thrice, the
last call being before the whole ffs structure gets freed, so when this
specific sequence happens there is a second underflow happening (but not
being reported):
/sys/kernel/debug/tracing# modprobe usb_f_fs
/sys/kernel/debug/tracing# echo ffs_data_clear > set_ftrace_filter
/sys/kernel/debug/tracing# echo function > current_tracer
/sys/kernel/debug/tracing# echo 1 > tracing_on
(setup gadget, run and kill function userland process, teardown gadget)
/sys/kernel/debug/tracing# echo 0 > tracing_on
/sys/kernel/debug/tracing# cat trace
smartcard-openp-436 [000] ..... 1946.208786: ffs_data_clear <-ffs_data_closed
smartcard-openp-431 [000] ..... 1946.279147: ffs_data_clear <-ffs_data_closed
smartcard-openp-431 [000] .n... 1946.905512: ffs_data_clear <-ffs_data_put
Warning output corresponding to above trace:
[ 1946.284139] WARNING: CPU: 0 PID: 431 at lib/refcount.c:28 refcount_warn_saturate+0x110/0x15c
[ 1946.293094] refcount_t: underflow; use-after-free.
[ 1946.298164] Modules linked in: usb_f_ncm(E) u_ether(E) usb_f_fs(E) hci_uart(E) btqca(E) btrtl(E) btbcm(E) btintel(E) bluetooth(E) nls_ascii(E) nls_cp437(E) vfat(E) fat(E) bcm2835_v4l2(CE) bcm2835_mmal_vchiq(CE) videobuf2_vmalloc(E) videobuf2_memops(E) sha512_generic(E) videobuf2_v4l2(E) sha512_arm(E) videobuf2_common(E) videodev(E) cpufreq_dt(E) snd_bcm2835(CE) brcmfmac(E) mc(E) vc4(E) ctr(E) brcmutil(E) snd_soc_core(E) snd_pcm_dmaengine(E) drbg(E) snd_pcm(E) snd_timer(E) snd(E) soundcore(E) drm_kms_helper(E) cec(E) ansi_cprng(E) rc_core(E) syscopyarea(E) raspberrypi_cpufreq(E) sysfillrect(E) sysimgblt(E) cfg80211(E) max17040_battery(OE) raspberrypi_hwmon(E) fb_sys_fops(E) regmap_i2c(E) ecdh_generic(E) rfkill(E) ecc(E) bcm2835_rng(E) rng_core(E) vchiq(CE) leds_gpio(E) libcomposite(E) fuse(E) configfs(E) ip_tables(E) x_tables(E) autofs4(E) ext4(E) crc16(E) mbcache(E) jbd2(E) crc32c_generic(E) sdhci_iproc(E) sdhci_pltfm(E) sdhci(E)
[ 1946.399633] CPU: 0 PID: 431 Comm: smartcard-openp Tainted: G C OE 5.15.0-1-rpi #1 Debian 5.15.3-1
[ 1946.417950] Hardware name: BCM2835
[ 1946.425442] Backtrace:
[ 1946.432048] [<c08d60a0>] (dump_backtrace) from [<c08d62ec>] (show_stack+0x20/0x24)
[ 1946.448226] r7:00000009 r6:0000001c r5:c04a948c r4:c0a64e2c
[ 1946.458412] [<c08d62cc>] (show_stack) from [<c08d9ae0>] (dump_stack+0x28/0x30)
[ 1946.470380] [<c08d9ab8>] (dump_stack) from [<c0123500>] (__warn+0xe8/0x154)
[ 1946.482067] r5:c04a948c r4:c0a71dc8
[ 1946.490184] [<c0123418>] (__warn) from [<c08d6948>] (warn_slowpath_fmt+0xa0/0xe4)
[ 1946.506758] r7:00000009 r6:0000001c r5:c0a71dc8 r4:c0a71e04
[ 1946.517070] [<c08d68ac>] (warn_slowpath_fmt) from [<c04a948c>] (refcount_warn_saturate+0x110/0x15c)
[ 1946.535309] r8:c0100224 r7:c0dfcb84 r6:ffffffff r5:c3b84c00 r4:c24a17c0
[ 1946.546708] [<c04a937c>] (refcount_warn_saturate) from [<c0380134>] (eventfd_ctx_put+0x48/0x74)
[ 1946.564476] [<c03800ec>] (eventfd_ctx_put) from [<bf5464e8>] (ffs_data_clear+0xd0/0x118 [usb_f_fs])
[ 1946.582664] r5:c3b84c00 r4:c2695b00
[ 1946.590668] [<bf546418>] (ffs_data_clear [usb_f_fs]) from [<bf547cc0>] (ffs_data_closed+0x9c/0x150 [usb_f_fs])
[ 1946.609608] r5:bf54d014 r4:c2695b00
[ 1946.617522] [<bf547c24>] (ffs_data_closed [usb_f_fs]) from [<bf547da0>] (ffs_fs_kill_sb+0x2c/0x30 [usb_f_fs])
[ 1946.636217] r7:c0dfcb84 r6:c3a12260 r5:bf54d014 r4:c229f000
[ 1946.646273] [<bf547d74>] (ffs_fs_kill_sb [usb_f_fs]) from [<c0326d50>] (deactivate_locked_super+0x54/0x9c)
[ 1946.664893] r5:bf54d014 r4:c229f000
[ 1946.672921] [<c0326cfc>] (deactivate_locked_super) from [<c0326df8>] (deactivate_super+0x60/0x64)
[ 1946.690722] r5:c2a09000 r4:c229f000
[ 1946.698706] [<c0326d98>] (deactivate_super) from [<c0349a28>] (cleanup_mnt+0xe4/0x14c)
[ 1946.715553] r5:c2a09000 r4:00000000
[ 1946.723528] [<c0349944>] (cleanup_mnt) from [<c0349b08>] (__cleanup_mnt+0x1c/0x20)
[ 1946.739922] r7:c0dfcb84 r6:c3a12260 r5:c3a126fc r4:00000000
[ 1946.750088] [<c0349aec>] (__cleanup_mnt) from [<c0143d10>] (task_work_run+0x84/0xb8)
[ 1946.766602] [<c0143c8c>] (task_work_run) from [<c010bdc8>] (do_work_pending+0x470/0x56c)
[ 1946.783540] r7:5ac3c35a r6:c0d0424c r5:c200bfb0 r4:c200a000
[ 1946.793614] [<c010b958>] (do_work_pending) from [<c01000c0>] (slow_work_pending+0xc/0x20)
[ 1946.810553] Exception stack(0xc200bfb0 to 0xc200bff8)
[ 1946.820129] bfa0: 00000000 00000000 000000aa b5e21430
[ 1946.837104] bfc0: bef867a0 00000001 bef86840 00000034 bef86838 bef86790 bef86794 bef867a0
[ 1946.854125] bfe0: 00000000 bef86798 b67b7a1c b6d626a4 60000010 b5a23760
[ 1946.865335] r10:00000000 r9:c200a000 r8:c0100224 r7:00000034 r6:bef86840 r5:00000001
[ 1946.881914] r4:bef867a0
[ 1946.888793] ---[ end trace 7387f2a9725b28d0 ]---
Fixes: 5e33f6fdf735 ("usb: gadget: ffs: add eventfd notification about ffs events")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Vincent Pelletier <plr.vincent@gmail.com>
Link: https://lore.kernel.org/r/f79eeea29f3f98de6782a064ec0f7351ad2f598f.1639793920.git.plr.vincent@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/gadget/function/f_fs.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1772,11 +1772,15 @@ static void ffs_data_clear(struct ffs_da
BUG_ON(ffs->gadget);
- if (ffs->epfiles)
+ if (ffs->epfiles) {
ffs_epfiles_destroy(ffs->epfiles, ffs->eps_count);
+ ffs->epfiles = NULL;
+ }
- if (ffs->ffs_eventfd)
+ if (ffs->ffs_eventfd) {
eventfd_ctx_put(ffs->ffs_eventfd);
+ ffs->ffs_eventfd = NULL;
+ }
kfree(ffs->raw_descs_data);
kfree(ffs->raw_strings);
@@ -1789,7 +1793,6 @@ static void ffs_data_reset(struct ffs_da
ffs_data_clear(ffs);
- ffs->epfiles = NULL;
ffs->raw_descs_data = NULL;
ffs->raw_descs = NULL;
ffs->raw_strings = NULL;
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 39/48] usb: mtu3: add memory barrier before set GPDs HWO
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (37 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 38/48] usb: gadget: f_fs: Clear ffs_eventfd in ffs_data_clear Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 40/48] usb: mtu3: fix list_head check warning Greg Kroah-Hartman
` (11 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Eddie Hung, Chunfeng Yun
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
commit a7aae769ca626819a7f9f078ebdc69a8a1b00c81 upstream.
There is a seldom issue that the controller access invalid address
and trigger devapc or emimpu violation. That is due to memory access
is out of order and cause gpd data is not correct.
Add mb() to prohibit compiler or cpu from reordering to make sure GPD
is fully written before setting its HWO.
Fixes: 48e0d3735aa5 ("usb: mtu3: supports new QMU format")
Cc: stable@vger.kernel.org
Reported-by: Eddie Hung <eddie.hung@mediatek.com>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/20211218095749.6250-2-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/mtu3/mtu3_qmu.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
--- a/drivers/usb/mtu3/mtu3_qmu.c
+++ b/drivers/usb/mtu3/mtu3_qmu.c
@@ -273,6 +273,8 @@ static int mtu3_prepare_tx_gpd(struct mt
gpd->dw3_info |= cpu_to_le32(GPD_EXT_FLAG_ZLP);
}
+ /* prevent reorder, make sure GPD's HWO is set last */
+ mb();
gpd->dw0_info |= cpu_to_le32(GPD_FLAGS_IOC | GPD_FLAGS_HWO);
mreq->gpd = gpd;
@@ -306,6 +308,8 @@ static int mtu3_prepare_rx_gpd(struct mt
gpd->next_gpd = cpu_to_le32(lower_32_bits(enq_dma));
ext_addr |= GPD_EXT_NGP(mtu, upper_32_bits(enq_dma));
gpd->dw3_info = cpu_to_le32(ext_addr);
+ /* prevent reorder, make sure GPD's HWO is set last */
+ mb();
gpd->dw0_info |= cpu_to_le32(GPD_FLAGS_IOC | GPD_FLAGS_HWO);
mreq->gpd = gpd;
@@ -445,7 +449,8 @@ static void qmu_tx_zlp_error_handler(str
return;
}
mtu3_setbits(mbase, MU3D_EP_TXCR0(mep->epnum), TX_TXPKTRDY);
-
+ /* prevent reorder, make sure GPD's HWO is set last */
+ mb();
/* by pass the current GDP */
gpd_current->dw0_info |= cpu_to_le32(GPD_FLAGS_BPS | GPD_FLAGS_HWO);
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 40/48] usb: mtu3: fix list_head check warning
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (38 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 39/48] usb: mtu3: add memory barrier before set GPDs HWO Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 41/48] usb: mtu3: set interval of FS intr and isoc endpoint Greg Kroah-Hartman
` (10 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Yuwen Ng, Chunfeng Yun
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
commit 8c313e3bfd9adae8d5c4ba1cc696dcbc86fbf9bf upstream.
This is caused by uninitialization of list_head.
BUG: KASAN: use-after-free in __list_del_entry_valid+0x34/0xe4
Call trace:
dump_backtrace+0x0/0x298
show_stack+0x24/0x34
dump_stack+0x130/0x1a8
print_address_description+0x88/0x56c
__kasan_report+0x1b8/0x2a0
kasan_report+0x14/0x20
__asan_load8+0x9c/0xa0
__list_del_entry_valid+0x34/0xe4
mtu3_req_complete+0x4c/0x300 [mtu3]
mtu3_gadget_stop+0x168/0x448 [mtu3]
usb_gadget_unregister_driver+0x204/0x3a0
unregister_gadget_item+0x44/0xa4
Fixes: 83374e035b62 ("usb: mtu3: add tracepoints to help debug")
Cc: stable@vger.kernel.org
Reported-by: Yuwen Ng <yuwen.ng@mediatek.com>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/20211218095749.6250-3-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/mtu3/mtu3_gadget.c | 1 +
1 file changed, 1 insertion(+)
--- a/drivers/usb/mtu3/mtu3_gadget.c
+++ b/drivers/usb/mtu3/mtu3_gadget.c
@@ -235,6 +235,7 @@ struct usb_request *mtu3_alloc_request(s
mreq->request.dma = DMA_ADDR_INVALID;
mreq->epnum = mep->epnum;
mreq->mep = mep;
+ INIT_LIST_HEAD(&mreq->list);
trace_mtu3_alloc_request(mreq);
return &mreq->request;
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 41/48] usb: mtu3: set interval of FS intr and isoc endpoint
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (39 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 40/48] usb: mtu3: fix list_head check warning Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 42/48] binder: fix async_free_space accounting for empty parcels Greg Kroah-Hartman
` (9 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Chunfeng Yun
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
commit 43f3b8cbcf93da7c2755af4a543280c31f4adf16 upstream.
Add support to set interval also for FS intr and isoc endpoint.
Fixes: 4d79e042ed8b ("usb: mtu3: add support for usb3.1 IP")
Cc: stable@vger.kernel.org
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/20211218095749.6250-4-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/mtu3/mtu3_gadget.c | 7 +++++++
1 file changed, 7 insertions(+)
--- a/drivers/usb/mtu3/mtu3_gadget.c
+++ b/drivers/usb/mtu3/mtu3_gadget.c
@@ -93,6 +93,13 @@ static int mtu3_ep_enable(struct mtu3_ep
mult = usb_endpoint_maxp_mult(desc) - 1;
}
break;
+ case USB_SPEED_FULL:
+ if (usb_endpoint_xfer_isoc(desc))
+ interval = clamp_val(desc->bInterval, 1, 16);
+ else if (usb_endpoint_xfer_int(desc))
+ interval = clamp_val(desc->bInterval, 1, 255);
+
+ break;
default:
break; /*others are ignored */
}
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 42/48] binder: fix async_free_space accounting for empty parcels
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (40 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 41/48] usb: mtu3: set interval of FS intr and isoc endpoint Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 43/48] scsi: vmw_pvscsi: Set residual data length conditionally Greg Kroah-Hartman
` (8 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Todd Kjos
From: Todd Kjos <tkjos@google.com>
commit cfd0d84ba28c18b531648c9d4a35ecca89ad9901 upstream.
In 4.13, commit 74310e06be4d ("android: binder: Move buffer out of area shared with user space")
fixed a kernel structure visibility issue. As part of that patch,
sizeof(void *) was used as the buffer size for 0-length data payloads so
the driver could detect abusive clients sending 0-length asynchronous
transactions to a server by enforcing limits on async_free_size.
Unfortunately, on the "free" side, the accounting of async_free_space
did not add the sizeof(void *) back. The result was that up to 8-bytes of
async_free_space were leaked on every async transaction of 8-bytes or
less. These small transactions are uncommon, so this accounting issue
has gone undetected for several years.
The fix is to use "buffer_size" (the allocated buffer size) instead of
"size" (the logical buffer size) when updating the async_free_space
during the free operation. These are the same except for this
corner case of asynchronous transactions with payloads < 8 bytes.
Fixes: 74310e06be4d ("android: binder: Move buffer out of area shared with user space")
Signed-off-by: Todd Kjos <tkjos@google.com>
Cc: stable@vger.kernel.org # 4.14+
Link: https://lore.kernel.org/r/20211220190150.2107077-1-tkjos@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/android/binder_alloc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -662,7 +662,7 @@ static void binder_free_buf_locked(struc
BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);
if (buffer->async_transaction) {
- alloc->free_async_space += size + sizeof(struct binder_buffer);
+ alloc->free_async_space += buffer_size + sizeof(struct binder_buffer);
binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
"%d: binder_free_buf size %zd async free %zd\n",
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 43/48] scsi: vmw_pvscsi: Set residual data length conditionally
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (41 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 42/48] binder: fix async_free_space accounting for empty parcels Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 44/48] Input: appletouch - initialize work before device registration Greg Kroah-Hartman
` (7 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Matt Wang, Martin K. Petersen,
Vishal Bhakta, VMware PV-Drivers, James E.J. Bottomley,
linux-scsi, Alexey Makhalov, Shmulik Ladkani
From: Alexey Makhalov <amakhalov@vmware.com>
commit 142c779d05d1fef75134c3cb63f52ccbc96d9e1f upstream.
The PVSCSI implementation in the VMware hypervisor under specific
configuration ("SCSI Bus Sharing" set to "Physical") returns zero dataLen
in the completion descriptor for READ CAPACITY(16). As a result, the kernel
can not detect proper disk geometry. This can be recognized by the kernel
message:
[ 0.776588] sd 1:0:0:0: [sdb] Sector size 0 reported, assuming 512.
The PVSCSI implementation in QEMU does not set dataLen at all, keeping it
zeroed. This leads to a boot hang as was reported by Shmulik Ladkani.
It is likely that the controller returns the garbage at the end of the
buffer. Residual length should be set by the driver in that case. The SCSI
layer will erase corresponding data. See commit bdb2b8cab439 ("[SCSI] erase
invalid data returned by device") for details.
Commit e662502b3a78 ("scsi: vmw_pvscsi: Set correct residual data length")
introduced the issue by setting residual length unconditionally, causing
the SCSI layer to erase the useful payload beyond dataLen when this value
is returned as 0.
As a result, considering existing issues in implementations of PVSCSI
controllers, we do not want to call scsi_set_resid() when dataLen ==
0. Calling scsi_set_resid() has no effect if dataLen equals buffer length.
Link: https://lore.kernel.org/lkml/20210824120028.30d9c071@blondie/
Link: https://lore.kernel.org/r/20211220190514.55935-1-amakhalov@vmware.com
Fixes: e662502b3a78 ("scsi: vmw_pvscsi: Set correct residual data length")
Cc: Matt Wang <wwentao@vmware.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Vishal Bhakta <vbhakta@vmware.com>
Cc: VMware PV-Drivers <pv-drivers@vmware.com>
Cc: James E.J. Bottomley <jejb@linux.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: stable@vger.kernel.org
Reported-and-suggested-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: Alexey Makhalov <amakhalov@vmware.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/scsi/vmw_pvscsi.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -591,9 +591,12 @@ static void pvscsi_complete_request(stru
* Commands like INQUIRY may transfer less data than
* requested by the initiator via bufflen. Set residual
* count to make upper layer aware of the actual amount
- * of data returned.
+ * of data returned. There are cases when controller
+ * returns zero dataLen with non zero data - do not set
+ * residual count in that case.
*/
- scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen);
+ if (e->dataLen && (e->dataLen < scsi_bufflen(cmd)))
+ scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen);
cmd->result = (DID_OK << 16);
break;
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 44/48] Input: appletouch - initialize work before device registration
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (42 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 43/48] scsi: vmw_pvscsi: Set residual data length conditionally Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 45/48] Input: spaceball - fix parsing of movement data packets Greg Kroah-Hartman
` (6 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Pavel Skripkin, Dmitry Torokhov,
syzbot+b88c5eae27386b252bbd
From: Pavel Skripkin <paskripkin@gmail.com>
commit 9f3ccdc3f6ef10084ceb3a47df0961bec6196fd0 upstream.
Syzbot has reported warning in __flush_work(). This warning is caused by
work->func == NULL, which means missing work initialization.
This may happen, since input_dev->close() calls
cancel_work_sync(&dev->work), but dev->work initalization happens _after_
input_register_device() call.
So this patch moves dev->work initialization before registering input
device
Fixes: 5a6eb676d3bc ("Input: appletouch - improve powersaving for Geyser3 devices")
Reported-and-tested-by: syzbot+b88c5eae27386b252bbd@syzkaller.appspotmail.com
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Link: https://lore.kernel.org/r/20211230141151.17300-1-paskripkin@gmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/input/mouse/appletouch.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/input/mouse/appletouch.c
+++ b/drivers/input/mouse/appletouch.c
@@ -916,6 +916,8 @@ static int atp_probe(struct usb_interfac
set_bit(BTN_TOOL_TRIPLETAP, input_dev->keybit);
set_bit(BTN_LEFT, input_dev->keybit);
+ INIT_WORK(&dev->work, atp_reinit);
+
error = input_register_device(dev->input);
if (error)
goto err_free_buffer;
@@ -923,8 +925,6 @@ static int atp_probe(struct usb_interfac
/* save our data pointer in this interface device */
usb_set_intfdata(iface, dev);
- INIT_WORK(&dev->work, atp_reinit);
-
return 0;
err_free_buffer:
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 45/48] Input: spaceball - fix parsing of movement data packets
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (43 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 44/48] Input: appletouch - initialize work before device registration Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 46/48] net: fix use-after-free in tw_timer_handler Greg Kroah-Hartman
` (5 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Leo L. Schwab, Dmitry Torokhov
From: Leo L. Schwab <ewhac@ewhac.org>
commit bc7ec91718c49d938849697cfad98fcd9877cc26 upstream.
The spaceball.c module was not properly parsing the movement reports
coming from the device. The code read axis data as signed 16-bit
little-endian values starting at offset 2.
In fact, axis data in Spaceball movement reports are signed 16-bit
big-endian values starting at offset 3. This was determined first by
visually inspecting the data packets, and later verified by consulting:
http://spacemice.org/pdf/SpaceBall_2003-3003_Protocol.pdf
If this ever worked properly, it was in the time before Git...
Signed-off-by: Leo L. Schwab <ewhac@ewhac.org>
Link: https://lore.kernel.org/r/20211221101630.1146385-1-ewhac@ewhac.org
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/input/joystick/spaceball.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
--- a/drivers/input/joystick/spaceball.c
+++ b/drivers/input/joystick/spaceball.c
@@ -19,6 +19,7 @@
#include <linux/module.h>
#include <linux/input.h>
#include <linux/serio.h>
+#include <asm/unaligned.h>
#define DRIVER_DESC "SpaceTec SpaceBall 2003/3003/4000 FLX driver"
@@ -75,9 +76,15 @@ static void spaceball_process_packet(str
case 'D': /* Ball data */
if (spaceball->idx != 15) return;
- for (i = 0; i < 6; i++)
+ /*
+ * Skip first three bytes; read six axes worth of data.
+ * Axis values are signed 16-bit big-endian.
+ */
+ data += 3;
+ for (i = 0; i < ARRAY_SIZE(spaceball_axes); i++) {
input_report_abs(dev, spaceball_axes[i],
- (__s16)((data[2 * i + 3] << 8) | data[2 * i + 2]));
+ (__s16)get_unaligned_be16(&data[i * 2]));
+ }
break;
case 'K': /* Button data */
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 46/48] net: fix use-after-free in tw_timer_handler
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (44 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 45/48] Input: spaceball - fix parsing of movement data packets Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 47/48] perf script: Fix CPU filtering of a scripts switch events Greg Kroah-Hartman
` (4 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Muchun Song, Cong Wang, Fam Zheng,
Jakub Kicinski
From: Muchun Song <songmuchun@bytedance.com>
commit e22e45fc9e41bf9fcc1e92cfb78eb92786728ef0 upstream.
A real world panic issue was found as follow in Linux 5.4.
BUG: unable to handle page fault for address: ffffde49a863de28
PGD 7e6fe62067 P4D 7e6fe62067 PUD 7e6fe63067 PMD f51e064067 PTE 0
RIP: 0010:tw_timer_handler+0x20/0x40
Call Trace:
<IRQ>
call_timer_fn+0x2b/0x120
run_timer_softirq+0x1ef/0x450
__do_softirq+0x10d/0x2b8
irq_exit+0xc7/0xd0
smp_apic_timer_interrupt+0x68/0x120
apic_timer_interrupt+0xf/0x20
This issue was also reported since 2017 in the thread [1],
unfortunately, the issue was still can be reproduced after fixing
DCCP.
The ipv4_mib_exit_net is called before tcp_sk_exit_batch when a net
namespace is destroyed since tcp_sk_ops is registered befrore
ipv4_mib_ops, which means tcp_sk_ops is in the front of ipv4_mib_ops
in the list of pernet_list. There will be a use-after-free on
net->mib.net_statistics in tw_timer_handler after ipv4_mib_exit_net
if there are some inflight time-wait timers.
This bug is not introduced by commit f2bf415cfed7 ("mib: add net to
NET_ADD_STATS_BH") since the net_statistics is a global variable
instead of dynamic allocation and freeing. Actually, commit
61a7e26028b9 ("mib: put net statistics on struct net") introduces
the bug since it put net statistics on struct net and free it when
net namespace is destroyed.
Moving init_ipv4_mibs() to the front of tcp_init() to fix this bug
and replace pr_crit() with panic() since continuing is meaningless
when init_ipv4_mibs() fails.
[1] https://groups.google.com/g/syzkaller/c/p1tn-_Kc6l4/m/smuL_FMAAgAJ?pli=1
Fixes: 61a7e26028b9 ("mib: put net statistics on struct net")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: Cong Wang <cong.wang@bytedance.com>
Cc: Fam Zheng <fam.zheng@bytedance.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20211228104145.9426-1-songmuchun@bytedance.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv4/af_inet.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -2003,6 +2003,10 @@ static int __init inet_init(void)
ip_init();
+ /* Initialise per-cpu ipv4 mibs */
+ if (init_ipv4_mibs())
+ panic("%s: Cannot init ipv4 mibs\n", __func__);
+
/* Setup TCP slab cache for open requests. */
tcp_init();
@@ -2033,12 +2037,6 @@ static int __init inet_init(void)
if (init_inet_pernet_ops())
pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
- /*
- * Initialise per-cpu ipv4 mibs
- */
-
- if (init_ipv4_mibs())
- pr_crit("%s: Cannot init ipv4 mibs\n", __func__);
ipv4_proc_init();
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 47/48] perf script: Fix CPU filtering of a scripts switch events
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (45 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 46/48] net: fix use-after-free in tw_timer_handler Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.10 48/48] bpf: Add kconfig knob for disabling unpriv bpf by default Greg Kroah-Hartman
` (3 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Adrian Hunter, Namhyung Kim,
Jiri Olsa, Riccardo Mancini, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
commit 5e0c325cdb714409a5b242c9e73a1b61157abb36 upstream.
CPU filtering was not being applied to a script's switch events.
Fixes: 5bf83c29a0ad2e78 ("perf script: Add scripting operation process_switch()")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20211215080636.149562-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
tools/perf/builtin-script.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2354,7 +2354,7 @@ static int process_switch_event(struct p
if (perf_event__process_switch(tool, event, sample, machine) < 0)
return -1;
- if (scripting_ops && scripting_ops->process_switch)
+ if (scripting_ops && scripting_ops->process_switch && !filter_cpu(sample))
scripting_ops->process_switch(event, sample, machine);
if (!script->show_switch_events)
^ permalink raw reply [flat|nested] 53+ messages in thread* [PATCH 5.10 48/48] bpf: Add kconfig knob for disabling unpriv bpf by default
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (46 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 47/48] perf script: Fix CPU filtering of a scripts switch events Greg Kroah-Hartman
@ 2022-01-03 14:24 ` Greg Kroah-Hartman
2022-01-04 1:27 ` [PATCH 5.10 00/48] 5.10.90-rc1 review Guenter Roeck
` (2 subsequent siblings)
50 siblings, 0 replies; 53+ messages in thread
From: Greg Kroah-Hartman @ 2022-01-03 14:24 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Daniel Borkmann, Alexei Starovoitov,
Salvatore Bonaccorso
From: Daniel Borkmann <daniel@iogearbox.net>
commit 08389d888287c3823f80b0216766b71e17f0aba5 upstream.
Add a kconfig knob which allows for unprivileged bpf to be disabled by default.
If set, the knob sets /proc/sys/kernel/unprivileged_bpf_disabled to value of 2.
This still allows a transition of 2 -> {0,1} through an admin. Similarly,
this also still keeps 1 -> {1} behavior intact, so that once set to permanently
disabled, it cannot be undone aside from a reboot.
We've also added extra2 with max of 2 for the procfs handler, so that an admin
still has a chance to toggle between 0 <-> 2.
Either way, as an additional alternative, applications can make use of CAP_BPF
that we added a while ago.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/74ec548079189e4e4dffaeb42b8987bb3c852eee.1620765074.git.daniel@iogearbox.net
Cc: Salvatore Bonaccorso <carnil@debian.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
Documentation/admin-guide/sysctl/kernel.rst | 17 +++++++++++++---
init/Kconfig | 10 +++++++++
kernel/bpf/syscall.c | 3 +-
kernel/sysctl.c | 29 +++++++++++++++++++++++-----
4 files changed, 50 insertions(+), 9 deletions(-)
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -1457,11 +1457,22 @@ unprivileged_bpf_disabled
=========================
Writing 1 to this entry will disable unprivileged calls to ``bpf()``;
-once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` will return
-``-EPERM``.
+once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` or ``CAP_BPF``
+will return ``-EPERM``. Once set to 1, this can't be cleared from the
+running kernel anymore.
-Once set, this can't be cleared.
+Writing 2 to this entry will also disable unprivileged calls to ``bpf()``,
+however, an admin can still change this setting later on, if needed, by
+writing 0 or 1 to this entry.
+If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in the kernel config, then this
+entry will default to 2 instead of 0.
+
+= =============================================================
+0 Unprivileged calls to ``bpf()`` are enabled
+1 Unprivileged calls to ``bpf()`` are disabled without recovery
+2 Unprivileged calls to ``bpf()`` are disabled
+= =============================================================
watchdog
========
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1722,6 +1722,16 @@ config BPF_JIT_DEFAULT_ON
def_bool ARCH_WANT_DEFAULT_BPF_JIT || BPF_JIT_ALWAYS_ON
depends on HAVE_EBPF_JIT && BPF_JIT
+config BPF_UNPRIV_DEFAULT_OFF
+ bool "Disable unprivileged BPF by default"
+ depends on BPF_SYSCALL
+ help
+ Disables unprivileged BPF by default by setting the corresponding
+ /proc/sys/kernel/unprivileged_bpf_disabled knob to 2. An admin can
+ still reenable it by setting it to 0 later on, or permanently
+ disable it by setting it to 1 (from which no other transition to
+ 0 is possible anymore).
+
source "kernel/bpf/preload/Kconfig"
config USERFAULTFD
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -50,7 +50,8 @@ static DEFINE_SPINLOCK(map_idr_lock);
static DEFINE_IDR(link_idr);
static DEFINE_SPINLOCK(link_idr_lock);
-int sysctl_unprivileged_bpf_disabled __read_mostly;
+int sysctl_unprivileged_bpf_disabled __read_mostly =
+ IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0;
static const struct bpf_map_ops * const bpf_map_types[] = {
#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -233,7 +233,27 @@ static int bpf_stats_handler(struct ctl_
mutex_unlock(&bpf_stats_enabled_mutex);
return ret;
}
-#endif
+
+static int bpf_unpriv_handler(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret, unpriv_enable = *(int *)table->data;
+ bool locked_state = unpriv_enable == 1;
+ struct ctl_table tmp = *table;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ tmp.data = &unpriv_enable;
+ ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ if (write && !ret) {
+ if (locked_state && unpriv_enable != 1)
+ return -EPERM;
+ *(int *)table->data = unpriv_enable;
+ }
+ return ret;
+}
+#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */
/*
* /proc/sys support
@@ -2626,10 +2646,9 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_unprivileged_bpf_disabled,
.maxlen = sizeof(sysctl_unprivileged_bpf_disabled),
.mode = 0644,
- /* only handle a transition from default "0" to "1" */
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ONE,
- .extra2 = SYSCTL_ONE,
+ .proc_handler = bpf_unpriv_handler,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &two,
},
{
.procname = "bpf_stats_enabled",
^ permalink raw reply [flat|nested] 53+ messages in thread* Re: [PATCH 5.10 00/48] 5.10.90-rc1 review
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (47 preceding siblings ...)
2022-01-03 14:24 ` [PATCH 5.10 48/48] bpf: Add kconfig knob for disabling unpriv bpf by default Greg Kroah-Hartman
@ 2022-01-04 1:27 ` Guenter Roeck
2022-01-04 5:43 ` Naresh Kamboju
2022-01-04 9:53 ` Jon Hunter
50 siblings, 0 replies; 53+ messages in thread
From: Guenter Roeck @ 2022-01-04 1:27 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: linux-kernel, torvalds, akpm, shuah, patches, lkft-triage, pavel,
jonathanh, f.fainelli, stable
On Mon, Jan 03, 2022 at 03:23:37PM +0100, Greg Kroah-Hartman wrote:
> This is the start of the stable review cycle for the 5.10.90 release.
> There are 48 patches in this series, all will be posted as a response
> to this one. If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Wed, 05 Jan 2022 14:20:40 +0000.
> Anything received after that time might be too late.
>
Build results:
total: 159 pass: 159 fail: 0
Qemu test results:
total: 472 pass: 472 fail: 0
Tested-by: Guenter Roeck <linux@roeck-us.net>
Guenter
^ permalink raw reply [flat|nested] 53+ messages in thread* Re: [PATCH 5.10 00/48] 5.10.90-rc1 review
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (48 preceding siblings ...)
2022-01-04 1:27 ` [PATCH 5.10 00/48] 5.10.90-rc1 review Guenter Roeck
@ 2022-01-04 5:43 ` Naresh Kamboju
2022-01-04 9:53 ` Jon Hunter
50 siblings, 0 replies; 53+ messages in thread
From: Naresh Kamboju @ 2022-01-04 5:43 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: linux-kernel, torvalds, akpm, linux, shuah, patches, lkft-triage,
pavel, jonathanh, f.fainelli, stable
On Mon, 3 Jan 2022 at 19:59, Greg Kroah-Hartman
<gregkh@linuxfoundation.org> wrote:
>
> This is the start of the stable review cycle for the 5.10.90 release.
> There are 48 patches in this series, all will be posted as a response
> to this one. If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Wed, 05 Jan 2022 14:20:40 +0000.
> Anything received after that time might be too late.
>
> The whole patch series can be found in one patch at:
> https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.90-rc1.gz
> or in the git tree and branch at:
> git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
> and the diffstat can be found below.
>
> thanks,
>
> greg k-h
Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.
Tested-by: Linux Kernel Functional Testing <lkft@linaro.org>
## Build
* kernel: 5.10.90-rc1
* git: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
* git branch: linux-5.10.y
* git commit: 38b2ec850bfc4ecc2b202c3b232d5ac92bd4365e
* git describe: v5.10.89-49-g38b2ec850bfc
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.10.y/build/v5.10.89-49-g38b2ec850bfc
## No Test Regressions (compared to v5.10.88-77-g44b3abecd41b)
## No Metric Regressions (compared to v5.10.88-77-g44b3abecd41b)
## No Test Fixes (compared to v5.10.88-77-g44b3abecd41b)
## No Metric Fixes (compared to v5.10.88-77-g44b3abecd41b)
## Test result summary
total: 93907, pass: 80491, fail: 576, skip: 11894, xfail: 946
## Build Summary
* arc: 10 total, 10 passed, 0 failed
* arm: 259 total, 255 passed, 4 failed
* arm64: 37 total, 37 passed, 0 failed
* dragonboard-410c: 1 total, 1 passed, 0 failed
* hi6220-hikey: 1 total, 1 passed, 0 failed
* i386: 36 total, 36 passed, 0 failed
* juno-r2: 1 total, 1 passed, 0 failed
* mips: 34 total, 30 passed, 4 failed
* parisc: 12 total, 12 passed, 0 failed
* powerpc: 52 total, 46 passed, 6 failed
* riscv: 24 total, 16 passed, 8 failed
* s390: 18 total, 18 passed, 0 failed
* sh: 24 total, 24 passed, 0 failed
* sparc: 12 total, 12 passed, 0 failed
* x15: 1 total, 1 passed, 0 failed
* x86: 1 total, 1 passed, 0 failed
* x86_64: 37 total, 37 passed, 0 failed
## Test suites summary
* fwts
* kselftest-android
* kselftest-arm64
* kselftest-arm64/arm64.btitest.bti_c_func
* kselftest-arm64/arm64.btitest.bti_j_func
* kselftest-arm64/arm64.btitest.bti_jc_func
* kselftest-arm64/arm64.btitest.bti_none_func
* kselftest-arm64/arm64.btitest.nohint_func
* kselftest-arm64/arm64.btitest.paciasp_func
* kselftest-arm64/arm64.nobtitest.bti_c_func
* kselftest-arm64/arm64.nobtitest.bti_j_func
* kselftest-arm64/arm64.nobtitest.bti_jc_func
* kselftest-arm64/arm64.nobtitest.bti_none_func
* kselftest-arm64/arm64.nobtitest.nohint_func
* kselftest-arm64/arm64.nobtitest.paciasp_func
* kselftest-bpf
* kselftest-breakpoints
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-drivers
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-kexec
* kselftest-kvm
* kselftest-lib
* kselftest-livepatch
* kselftest-membarrier
* kselftest-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* kselftest-net
* kselftest-netfilter
* kselftest-nsfs
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-tc-testing
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-vm
* kselftest-x86
* kselftest-zram
* kunit
* kvm-unit-tests
* libgpiod
* libhugetlbfs
* linux-log-parser
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-containers-tests
* ltp-controllers-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-mm-tests
* ltp-nptl-tests
* ltp-open-posix-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-syscalls-tests
* ltp-tracing-tests
* network-basic-tests
* packetdrill
* perf
* rcutorture
* ssuite
* v4l2-compliance
--
Linaro LKFT
https://lkft.linaro.org
^ permalink raw reply [flat|nested] 53+ messages in thread* Re: [PATCH 5.10 00/48] 5.10.90-rc1 review
2022-01-03 14:23 [PATCH 5.10 00/48] 5.10.90-rc1 review Greg Kroah-Hartman
` (49 preceding siblings ...)
2022-01-04 5:43 ` Naresh Kamboju
@ 2022-01-04 9:53 ` Jon Hunter
50 siblings, 0 replies; 53+ messages in thread
From: Jon Hunter @ 2022-01-04 9:53 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Greg Kroah-Hartman, torvalds, akpm, linux, shuah, patches,
lkft-triage, pavel, jonathanh, f.fainelli, stable, linux-tegra
On Mon, 03 Jan 2022 15:23:37 +0100, Greg Kroah-Hartman wrote:
> This is the start of the stable review cycle for the 5.10.90 release.
> There are 48 patches in this series, all will be posted as a response
> to this one. If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Wed, 05 Jan 2022 14:20:40 +0000.
> Anything received after that time might be too late.
>
> The whole patch series can be found in one patch at:
> https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.90-rc1.gz
> or in the git tree and branch at:
> git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
> and the diffstat can be found below.
>
> thanks,
>
> greg k-h
All tests passing for Tegra ...
Test results for stable-v5.10:
10 builds: 10 pass, 0 fail
28 boots: 28 pass, 0 fail
75 tests: 75 pass, 0 fail
Linux version: 5.10.90-rc1-g38b2ec850bfc
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,
tegra194-p2972-0000, tegra194-p3509-0000+p3668-0000,
tegra20-ventana, tegra210-p2371-2180,
tegra210-p3450-0000, tegra30-cardhu-a04
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Jon
^ permalink raw reply [flat|nested] 53+ messages in thread