The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 2f2bd7cbd1d1548137b351040dc4e037d18cdfdc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112326-feminine-mutilator-50ef@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
2f2bd7cbd1d1 ("hid: lenovo: Resend all settings on reset_resume for compact keyboards")
24401f291dcc ("HID: lenovo: Add support for ThinkPad TrackPoint Keyboard II")
ef550c5d0a8e ("HID: lenovo: Rename fn_lock sysfs attr handlers to make them generic")
b72cdfa82424 ("HID: lenovo: Merge tpkbd and cptkbd data structures")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 2f2bd7cbd1d1548137b351040dc4e037d18cdfdc Mon Sep 17 00:00:00 2001
From: Jamie Lentin <jm(a)lentin.co.uk>
Date: Mon, 2 Oct 2023 15:09:14 +0000
Subject: [PATCH] hid: lenovo: Resend all settings on reset_resume for compact
keyboards
The USB Compact Keyboard variant requires a reset_resume function to
restore keyboard configuration after a suspend in some situations. Move
configuration normally done on probe to lenovo_features_set_cptkbd(), then
recycle this for use on reset_resume.
Without, the keyboard and driver would end up in an inconsistent state,
breaking middle-button scrolling amongst other problems, and twiddling
sysfs values wouldn't help as the middle-button mode won't be set until
the driver is reloaded.
Tested on a USB and Bluetooth Thinkpad Compact Keyboard.
CC: stable(a)vger.kernel.org
Fixes: 94eefa271323 ("HID: lenovo: Use native middle-button mode for compact keyboards")
Signed-off-by: Jamie Lentin <jm(a)lentin.co.uk>
Signed-off-by: Martin Kepplinger <martink(a)posteo.de>
Link: https://lore.kernel.org/r/20231002150914.22101-1-martink@posteo.de
Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org>
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 9c1181313e44..7c1b33be9d13 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -526,6 +526,19 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev)
int ret;
struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev);
+ /*
+ * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
+ * regular keys
+ */
+ ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
+ if (ret)
+ hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
+
+ /* Switch middle button to native mode */
+ ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);
+ if (ret)
+ hid_warn(hdev, "Failed to switch middle button: %d\n", ret);
+
ret = lenovo_send_cmd_cptkbd(hdev, 0x05, cptkbd_data->fn_lock);
if (ret)
hid_err(hdev, "Fn-lock setting failed: %d\n", ret);
@@ -1148,22 +1161,6 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev)
}
hid_set_drvdata(hdev, cptkbd_data);
- /*
- * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
- * regular keys (Compact only)
- */
- if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD ||
- hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) {
- ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
- if (ret)
- hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
- }
-
- /* Switch middle button to native mode */
- ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);
- if (ret)
- hid_warn(hdev, "Failed to switch middle button: %d\n", ret);
-
/* Set keyboard settings to known state */
cptkbd_data->middlebutton_state = 0;
cptkbd_data->fn_lock = true;
@@ -1286,6 +1283,24 @@ static int lenovo_probe(struct hid_device *hdev,
return ret;
}
+#ifdef CONFIG_PM
+static int lenovo_reset_resume(struct hid_device *hdev)
+{
+ switch (hdev->product) {
+ case USB_DEVICE_ID_LENOVO_CUSBKBD:
+ case USB_DEVICE_ID_LENOVO_TPIIUSBKBD:
+ if (hdev->type == HID_TYPE_USBMOUSE)
+ lenovo_features_set_cptkbd(hdev);
+
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+#endif
+
static void lenovo_remove_tpkbd(struct hid_device *hdev)
{
struct lenovo_drvdata *data_pointer = hid_get_drvdata(hdev);
@@ -1402,6 +1417,9 @@ static struct hid_driver lenovo_driver = {
.raw_event = lenovo_raw_event,
.event = lenovo_event,
.report_fixup = lenovo_report_fixup,
+#ifdef CONFIG_PM
+ .reset_resume = lenovo_reset_resume,
+#endif
};
module_hid_driver(lenovo_driver);
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 2f2bd7cbd1d1548137b351040dc4e037d18cdfdc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112325-paycheck-recovery-4d99@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
2f2bd7cbd1d1 ("hid: lenovo: Resend all settings on reset_resume for compact keyboards")
24401f291dcc ("HID: lenovo: Add support for ThinkPad TrackPoint Keyboard II")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 2f2bd7cbd1d1548137b351040dc4e037d18cdfdc Mon Sep 17 00:00:00 2001
From: Jamie Lentin <jm(a)lentin.co.uk>
Date: Mon, 2 Oct 2023 15:09:14 +0000
Subject: [PATCH] hid: lenovo: Resend all settings on reset_resume for compact
keyboards
The USB Compact Keyboard variant requires a reset_resume function to
restore keyboard configuration after a suspend in some situations. Move
configuration normally done on probe to lenovo_features_set_cptkbd(), then
recycle this for use on reset_resume.
Without, the keyboard and driver would end up in an inconsistent state,
breaking middle-button scrolling amongst other problems, and twiddling
sysfs values wouldn't help as the middle-button mode won't be set until
the driver is reloaded.
Tested on a USB and Bluetooth Thinkpad Compact Keyboard.
CC: stable(a)vger.kernel.org
Fixes: 94eefa271323 ("HID: lenovo: Use native middle-button mode for compact keyboards")
Signed-off-by: Jamie Lentin <jm(a)lentin.co.uk>
Signed-off-by: Martin Kepplinger <martink(a)posteo.de>
Link: https://lore.kernel.org/r/20231002150914.22101-1-martink@posteo.de
Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org>
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 9c1181313e44..7c1b33be9d13 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -526,6 +526,19 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev)
int ret;
struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev);
+ /*
+ * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
+ * regular keys
+ */
+ ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
+ if (ret)
+ hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
+
+ /* Switch middle button to native mode */
+ ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);
+ if (ret)
+ hid_warn(hdev, "Failed to switch middle button: %d\n", ret);
+
ret = lenovo_send_cmd_cptkbd(hdev, 0x05, cptkbd_data->fn_lock);
if (ret)
hid_err(hdev, "Fn-lock setting failed: %d\n", ret);
@@ -1148,22 +1161,6 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev)
}
hid_set_drvdata(hdev, cptkbd_data);
- /*
- * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
- * regular keys (Compact only)
- */
- if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD ||
- hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) {
- ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
- if (ret)
- hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
- }
-
- /* Switch middle button to native mode */
- ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);
- if (ret)
- hid_warn(hdev, "Failed to switch middle button: %d\n", ret);
-
/* Set keyboard settings to known state */
cptkbd_data->middlebutton_state = 0;
cptkbd_data->fn_lock = true;
@@ -1286,6 +1283,24 @@ static int lenovo_probe(struct hid_device *hdev,
return ret;
}
+#ifdef CONFIG_PM
+static int lenovo_reset_resume(struct hid_device *hdev)
+{
+ switch (hdev->product) {
+ case USB_DEVICE_ID_LENOVO_CUSBKBD:
+ case USB_DEVICE_ID_LENOVO_TPIIUSBKBD:
+ if (hdev->type == HID_TYPE_USBMOUSE)
+ lenovo_features_set_cptkbd(hdev);
+
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+#endif
+
static void lenovo_remove_tpkbd(struct hid_device *hdev)
{
struct lenovo_drvdata *data_pointer = hid_get_drvdata(hdev);
@@ -1402,6 +1417,9 @@ static struct hid_driver lenovo_driver = {
.raw_event = lenovo_raw_event,
.event = lenovo_event,
.report_fixup = lenovo_report_fixup,
+#ifdef CONFIG_PM
+ .reset_resume = lenovo_reset_resume,
+#endif
};
module_hid_driver(lenovo_driver);
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 2f2bd7cbd1d1548137b351040dc4e037d18cdfdc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112323-entwine-outskirts-8f2a@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
2f2bd7cbd1d1 ("hid: lenovo: Resend all settings on reset_resume for compact keyboards")
24401f291dcc ("HID: lenovo: Add support for ThinkPad TrackPoint Keyboard II")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 2f2bd7cbd1d1548137b351040dc4e037d18cdfdc Mon Sep 17 00:00:00 2001
From: Jamie Lentin <jm(a)lentin.co.uk>
Date: Mon, 2 Oct 2023 15:09:14 +0000
Subject: [PATCH] hid: lenovo: Resend all settings on reset_resume for compact
keyboards
The USB Compact Keyboard variant requires a reset_resume function to
restore keyboard configuration after a suspend in some situations. Move
configuration normally done on probe to lenovo_features_set_cptkbd(), then
recycle this for use on reset_resume.
Without, the keyboard and driver would end up in an inconsistent state,
breaking middle-button scrolling amongst other problems, and twiddling
sysfs values wouldn't help as the middle-button mode won't be set until
the driver is reloaded.
Tested on a USB and Bluetooth Thinkpad Compact Keyboard.
CC: stable(a)vger.kernel.org
Fixes: 94eefa271323 ("HID: lenovo: Use native middle-button mode for compact keyboards")
Signed-off-by: Jamie Lentin <jm(a)lentin.co.uk>
Signed-off-by: Martin Kepplinger <martink(a)posteo.de>
Link: https://lore.kernel.org/r/20231002150914.22101-1-martink@posteo.de
Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org>
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 9c1181313e44..7c1b33be9d13 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -526,6 +526,19 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev)
int ret;
struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev);
+ /*
+ * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
+ * regular keys
+ */
+ ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
+ if (ret)
+ hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
+
+ /* Switch middle button to native mode */
+ ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);
+ if (ret)
+ hid_warn(hdev, "Failed to switch middle button: %d\n", ret);
+
ret = lenovo_send_cmd_cptkbd(hdev, 0x05, cptkbd_data->fn_lock);
if (ret)
hid_err(hdev, "Fn-lock setting failed: %d\n", ret);
@@ -1148,22 +1161,6 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev)
}
hid_set_drvdata(hdev, cptkbd_data);
- /*
- * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
- * regular keys (Compact only)
- */
- if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD ||
- hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) {
- ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
- if (ret)
- hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
- }
-
- /* Switch middle button to native mode */
- ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);
- if (ret)
- hid_warn(hdev, "Failed to switch middle button: %d\n", ret);
-
/* Set keyboard settings to known state */
cptkbd_data->middlebutton_state = 0;
cptkbd_data->fn_lock = true;
@@ -1286,6 +1283,24 @@ static int lenovo_probe(struct hid_device *hdev,
return ret;
}
+#ifdef CONFIG_PM
+static int lenovo_reset_resume(struct hid_device *hdev)
+{
+ switch (hdev->product) {
+ case USB_DEVICE_ID_LENOVO_CUSBKBD:
+ case USB_DEVICE_ID_LENOVO_TPIIUSBKBD:
+ if (hdev->type == HID_TYPE_USBMOUSE)
+ lenovo_features_set_cptkbd(hdev);
+
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+#endif
+
static void lenovo_remove_tpkbd(struct hid_device *hdev)
{
struct lenovo_drvdata *data_pointer = hid_get_drvdata(hdev);
@@ -1402,6 +1417,9 @@ static struct hid_driver lenovo_driver = {
.raw_event = lenovo_raw_event,
.event = lenovo_event,
.report_fixup = lenovo_report_fixup,
+#ifdef CONFIG_PM
+ .reset_resume = lenovo_reset_resume,
+#endif
};
module_hid_driver(lenovo_driver);
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 06035f019422ba17e85c11e70d6d8bdbe9fa1afd
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112354-accurate-robin-211c@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
06035f019422 ("selftests/resctrl: Fix feature checks")
d56e5da0e0f5 ("selftests/resctrl: Refactor feature check to use resource and feature name")
caddc0fbe495 ("selftests/resctrl: Move resctrl FS mount/umount to higher level")
91db4fd9019a ("selftests/resctrl: Remove duplicate codes that clear each test result file")
c2b1790747a5 ("selftests/resctrl: Use correct exit code when tests fail")
a967e17f9184 ("selftests/resctrl: Use remount_resctrlfs() consistently with boolean")
e48c32306bce ("selftests/resctrl: Change name from CBM_MASK_PATH to INFO_PATH")
d577380da04e ("selftests/resctrl: Print a message if the result of MBM&CMT tests is failed on Intel CPU")
6220f69e72a5 ("selftests/resctrl: Extend CPU vendor detection")
4e5cb354c85e ("selftests/resctrl: Fix unmount resctrl FS")
f1dd71982d19 ("selftests/resctrl: Skip the test if requested resctrl feature is not supported")
c9fb4e7cee1e ("selftests/resctrl: Modularize resctrl test suite main() function")
09a67934625a ("selftests/resctrl: Don't hard code value of "no_of_bits" variable")
ee0415681eb6 ("selftests/resctrl: Use resctrl/info for feature detection")
03216ed7bb4d ("selftests/resctrl: Share show_cache_info() by CAT and CMT tests")
ca2f4214f967 ("selftests/resctrl: Call kselftest APIs to log test results")
2f320911d9fa ("selftests/resctrl: Rename CQM test as CMT test")
2428673638ea ("selftests/resctrl: Clean up resctrl features check")
896016d2ad05 ("selftests/resctrl: Fix compilation issues for other global variables")
8236c51d85a6 ("selftests/resctrl: Fix compilation issues for global variables")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 06035f019422ba17e85c11e70d6d8bdbe9fa1afd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen(a)linux.intel.com>
Date: Mon, 2 Oct 2023 12:48:12 +0300
Subject: [PATCH] selftests/resctrl: Fix feature checks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The MBA and CMT tests expect support of other features to be able to
run.
When platform only supports MBA but not MBM, MBA test will fail with:
Failed to open total bw file: No such file or directory
When platform only supports CMT but not CAT, CMT test will fail with:
Failed to open bit mask file '/sys/fs/resctrl/info/L3/cbm_mask': No such file or directory
It leads to the test reporting test fail (even if no test was run at
all).
Extend feature checks to cover these two conditions to show these tests
were skipped rather than failed.
Fixes: ee0415681eb6 ("selftests/resctrl: Use resctrl/info for feature detection")
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre(a)intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Cc: <stable(a)vger.kernel.org> # selftests/resctrl: Refactor feature check to use resource and feature name
Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org>
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index a19dcc3f8fb0..2bbe3045a018 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -130,7 +130,9 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("MB", NULL) || (get_vendor() != ARCH_INTEL)) {
+ if (!validate_resctrl_feature_request("MB", NULL) ||
+ !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
+ (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
goto cleanup;
}
@@ -153,7 +155,8 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy")) {
+ if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") ||
+ !validate_resctrl_feature_request("L3", NULL)) {
ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
goto cleanup;
}
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 06035f019422ba17e85c11e70d6d8bdbe9fa1afd
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112352-mountable-parameter-9b0d@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
06035f019422 ("selftests/resctrl: Fix feature checks")
d56e5da0e0f5 ("selftests/resctrl: Refactor feature check to use resource and feature name")
caddc0fbe495 ("selftests/resctrl: Move resctrl FS mount/umount to higher level")
91db4fd9019a ("selftests/resctrl: Remove duplicate codes that clear each test result file")
c2b1790747a5 ("selftests/resctrl: Use correct exit code when tests fail")
a967e17f9184 ("selftests/resctrl: Use remount_resctrlfs() consistently with boolean")
e48c32306bce ("selftests/resctrl: Change name from CBM_MASK_PATH to INFO_PATH")
d577380da04e ("selftests/resctrl: Print a message if the result of MBM&CMT tests is failed on Intel CPU")
6220f69e72a5 ("selftests/resctrl: Extend CPU vendor detection")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 06035f019422ba17e85c11e70d6d8bdbe9fa1afd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen(a)linux.intel.com>
Date: Mon, 2 Oct 2023 12:48:12 +0300
Subject: [PATCH] selftests/resctrl: Fix feature checks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The MBA and CMT tests expect support of other features to be able to
run.
When platform only supports MBA but not MBM, MBA test will fail with:
Failed to open total bw file: No such file or directory
When platform only supports CMT but not CAT, CMT test will fail with:
Failed to open bit mask file '/sys/fs/resctrl/info/L3/cbm_mask': No such file or directory
It leads to the test reporting test fail (even if no test was run at
all).
Extend feature checks to cover these two conditions to show these tests
were skipped rather than failed.
Fixes: ee0415681eb6 ("selftests/resctrl: Use resctrl/info for feature detection")
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre(a)intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Cc: <stable(a)vger.kernel.org> # selftests/resctrl: Refactor feature check to use resource and feature name
Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org>
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index a19dcc3f8fb0..2bbe3045a018 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -130,7 +130,9 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("MB", NULL) || (get_vendor() != ARCH_INTEL)) {
+ if (!validate_resctrl_feature_request("MB", NULL) ||
+ !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
+ (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
goto cleanup;
}
@@ -153,7 +155,8 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy")) {
+ if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") ||
+ !validate_resctrl_feature_request("L3", NULL)) {
ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
goto cleanup;
}
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 06035f019422ba17e85c11e70d6d8bdbe9fa1afd
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112350-eskimo-unneeded-8119@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
06035f019422 ("selftests/resctrl: Fix feature checks")
d56e5da0e0f5 ("selftests/resctrl: Refactor feature check to use resource and feature name")
caddc0fbe495 ("selftests/resctrl: Move resctrl FS mount/umount to higher level")
91db4fd9019a ("selftests/resctrl: Remove duplicate codes that clear each test result file")
c2b1790747a5 ("selftests/resctrl: Use correct exit code when tests fail")
a967e17f9184 ("selftests/resctrl: Use remount_resctrlfs() consistently with boolean")
e48c32306bce ("selftests/resctrl: Change name from CBM_MASK_PATH to INFO_PATH")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 06035f019422ba17e85c11e70d6d8bdbe9fa1afd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen(a)linux.intel.com>
Date: Mon, 2 Oct 2023 12:48:12 +0300
Subject: [PATCH] selftests/resctrl: Fix feature checks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The MBA and CMT tests expect support of other features to be able to
run.
When platform only supports MBA but not MBM, MBA test will fail with:
Failed to open total bw file: No such file or directory
When platform only supports CMT but not CAT, CMT test will fail with:
Failed to open bit mask file '/sys/fs/resctrl/info/L3/cbm_mask': No such file or directory
It leads to the test reporting test fail (even if no test was run at
all).
Extend feature checks to cover these two conditions to show these tests
were skipped rather than failed.
Fixes: ee0415681eb6 ("selftests/resctrl: Use resctrl/info for feature detection")
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre(a)intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Cc: <stable(a)vger.kernel.org> # selftests/resctrl: Refactor feature check to use resource and feature name
Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org>
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index a19dcc3f8fb0..2bbe3045a018 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -130,7 +130,9 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("MB", NULL) || (get_vendor() != ARCH_INTEL)) {
+ if (!validate_resctrl_feature_request("MB", NULL) ||
+ !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
+ (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
goto cleanup;
}
@@ -153,7 +155,8 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy")) {
+ if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") ||
+ !validate_resctrl_feature_request("L3", NULL)) {
ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
goto cleanup;
}
The patch below does not apply to the 6.5-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x 06035f019422ba17e85c11e70d6d8bdbe9fa1afd
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112348-tradition-grandma-cb3c@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
06035f019422 ("selftests/resctrl: Fix feature checks")
d56e5da0e0f5 ("selftests/resctrl: Refactor feature check to use resource and feature name")
caddc0fbe495 ("selftests/resctrl: Move resctrl FS mount/umount to higher level")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 06035f019422ba17e85c11e70d6d8bdbe9fa1afd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen(a)linux.intel.com>
Date: Mon, 2 Oct 2023 12:48:12 +0300
Subject: [PATCH] selftests/resctrl: Fix feature checks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The MBA and CMT tests expect support of other features to be able to
run.
When platform only supports MBA but not MBM, MBA test will fail with:
Failed to open total bw file: No such file or directory
When platform only supports CMT but not CAT, CMT test will fail with:
Failed to open bit mask file '/sys/fs/resctrl/info/L3/cbm_mask': No such file or directory
It leads to the test reporting test fail (even if no test was run at
all).
Extend feature checks to cover these two conditions to show these tests
were skipped rather than failed.
Fixes: ee0415681eb6 ("selftests/resctrl: Use resctrl/info for feature detection")
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre(a)intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Cc: <stable(a)vger.kernel.org> # selftests/resctrl: Refactor feature check to use resource and feature name
Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org>
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index a19dcc3f8fb0..2bbe3045a018 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -130,7 +130,9 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("MB", NULL) || (get_vendor() != ARCH_INTEL)) {
+ if (!validate_resctrl_feature_request("MB", NULL) ||
+ !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
+ (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
goto cleanup;
}
@@ -153,7 +155,8 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy")) {
+ if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") ||
+ !validate_resctrl_feature_request("L3", NULL)) {
ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
goto cleanup;
}
The patch below does not apply to the 6.5-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x d56e5da0e0f557a206bace16bbbdad00a5800e34
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112330-wildfowl-gutter-2ce0@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
d56e5da0e0f5 ("selftests/resctrl: Refactor feature check to use resource and feature name")
caddc0fbe495 ("selftests/resctrl: Move resctrl FS mount/umount to higher level")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From d56e5da0e0f557a206bace16bbbdad00a5800e34 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen(a)linux.intel.com>
Date: Mon, 2 Oct 2023 12:48:11 +0300
Subject: [PATCH] selftests/resctrl: Refactor feature check to use resource and
feature name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Feature check in validate_resctrl_feature_request() takes in the test
name string and maps that to what to check per test.
Pass resource and feature names to validate_resctrl_feature_request()
directly rather than deriving them from the test name inside the
function which makes the feature check easier to extend for new test
cases.
Use !! in the return statement to make the boolean conversion more
obvious even if it is not strictly necessary from correctness point of
view (to avoid it looking like the function is returning a freed
pointer).
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre(a)intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Cc: <stable(a)vger.kernel.org> # selftests/resctrl: Remove duplicate feature check from CMT test
Cc: <stable(a)vger.kernel.org> # selftests/resctrl: Move _GNU_SOURCE define into Makefile
Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org>
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index d9b5df95849d..8578a8b4e145 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -27,10 +27,6 @@
#define RESCTRL_PATH "/sys/fs/resctrl"
#define PHYS_ID_PATH "/sys/devices/system/cpu/cpu"
#define INFO_PATH "/sys/fs/resctrl/info"
-#define L3_PATH "/sys/fs/resctrl/info/L3"
-#define MB_PATH "/sys/fs/resctrl/info/MB"
-#define L3_MON_PATH "/sys/fs/resctrl/info/L3_MON"
-#define L3_MON_FEATURES_PATH "/sys/fs/resctrl/info/L3_MON/mon_features"
#define ARCH_INTEL 1
#define ARCH_AMD 2
@@ -87,7 +83,7 @@ int get_resource_id(int cpu_no, int *resource_id);
int mount_resctrlfs(void);
int umount_resctrlfs(void);
int validate_bw_report_request(char *bw_report);
-bool validate_resctrl_feature_request(const char *resctrl_val);
+bool validate_resctrl_feature_request(const char *resource, const char *feature);
char *fgrep(FILE *inf, const char *str);
int taskset_benchmark(pid_t bm_pid, int cpu_no);
void run_benchmark(int signum, siginfo_t *info, void *ucontext);
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 495aeee5b734..a19dcc3f8fb0 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -103,7 +103,9 @@ static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request(MBM_STR) || (get_vendor() != ARCH_INTEL)) {
+ if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") ||
+ !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
+ (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n");
goto cleanup;
}
@@ -128,7 +130,7 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request(MBA_STR) || (get_vendor() != ARCH_INTEL)) {
+ if (!validate_resctrl_feature_request("MB", NULL) || (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
goto cleanup;
}
@@ -151,7 +153,7 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
return;
}
- if (!validate_resctrl_feature_request(CMT_STR)) {
+ if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy")) {
ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
goto cleanup;
}
@@ -176,7 +178,7 @@ static void run_cat_test(int cpu_no, int no_of_bits)
return;
}
- if (!validate_resctrl_feature_request(CAT_STR)) {
+ if (!validate_resctrl_feature_request("L3", NULL)) {
ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n");
goto cleanup;
}
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index bd36ee206602..3a8111362d26 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -8,6 +8,8 @@
* Sai Praneeth Prakhya <sai.praneeth.prakhya(a)intel.com>,
* Fenghua Yu <fenghua.yu(a)intel.com>
*/
+#include <limits.h>
+
#include "resctrl.h"
static int find_resctrl_mount(char *buffer)
@@ -604,63 +606,46 @@ char *fgrep(FILE *inf, const char *str)
/*
* validate_resctrl_feature_request - Check if requested feature is valid.
- * @resctrl_val: Requested feature
+ * @resource: Required resource (e.g., MB, L3, L2, L3_MON, etc.)
+ * @feature: Required monitor feature (in mon_features file). Can only be
+ * set for L3_MON. Must be NULL for all other resources.
*
- * Return: True if the feature is supported, else false. False is also
- * returned if resctrl FS is not mounted.
+ * Return: True if the resource/feature is supported, else false. False is
+ * also returned if resctrl FS is not mounted.
*/
-bool validate_resctrl_feature_request(const char *resctrl_val)
+bool validate_resctrl_feature_request(const char *resource, const char *feature)
{
+ char res_path[PATH_MAX];
struct stat statbuf;
- bool found = false;
char *res;
FILE *inf;
int ret;
- if (!resctrl_val)
+ if (!resource)
return false;
ret = find_resctrl_mount(NULL);
if (ret)
return false;
- if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) {
- if (!stat(L3_PATH, &statbuf))
- return true;
- } else if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
- if (!stat(MB_PATH, &statbuf))
- return true;
- } else if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
- !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
- if (!stat(L3_MON_PATH, &statbuf)) {
- inf = fopen(L3_MON_FEATURES_PATH, "r");
- if (!inf)
- return false;
-
- if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
- res = fgrep(inf, "llc_occupancy");
- if (res) {
- found = true;
- free(res);
- }
- }
-
- if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
- res = fgrep(inf, "mbm_total_bytes");
- if (res) {
- free(res);
- res = fgrep(inf, "mbm_local_bytes");
- if (res) {
- found = true;
- free(res);
- }
- }
- }
- fclose(inf);
- }
- }
+ snprintf(res_path, sizeof(res_path), "%s/%s", INFO_PATH, resource);
+
+ if (stat(res_path, &statbuf))
+ return false;
+
+ if (!feature)
+ return true;
+
+ snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource);
+ inf = fopen(res_path, "r");
+ if (!inf)
+ return false;
+
+ res = fgrep(inf, feature);
+ free(res);
+ fclose(inf);
- return found;
+ return !!res;
}
int filter_dmesg(void)
The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 3aff5146445582454c35900f3c0c972987cdd595
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112321-epic-pamphlet-c600@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
3aff51464455 ("selftests/resctrl: Extend signal handler coverage to unmount on receiving signal")
e33cb5702a9f ("selftests/resctrl: Make benchmark command const and build it with pointers")
b1a901e078c4 ("selftests/resctrl: Simplify span lifetime")
47e36f16c784 ("selftests/resctrl: Remove bw_report and bm_type from main()")
4a28c7665c2a ("selftests/resctrl: Ensure the benchmark commands fits to its array")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 3aff5146445582454c35900f3c0c972987cdd595 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen(a)linux.intel.com>
Date: Mon, 2 Oct 2023 12:48:08 +0300
Subject: [PATCH] selftests/resctrl: Extend signal handler coverage to unmount
on receiving signal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Unmounting resctrl FS has been moved into the per test functions in
resctrl_tests.c by commit caddc0fbe495 ("selftests/resctrl: Move
resctrl FS mount/umount to higher level"). In case a signal (SIGINT,
SIGTERM, or SIGHUP) is received, the running selftest is aborted by
ctrlc_handler() which then unmounts resctrl fs before exiting. The
current section between signal_handler_register() and
signal_handler_unregister(), however, does not cover the entire
duration when resctrl FS is mounted.
Move signal_handler_register() and signal_handler_unregister() calls
from per test files into resctrl_tests.c to properly unmount resctrl
fs. In order to not add signal_handler_register()/unregister() n times,
create helpers test_prepare() and test_cleanup().
Do not call ksft_exit_fail_msg() in test_prepare() but only in the per
test function to keep the control flow cleaner without adding calls to
exit() deep into the call chain.
Adjust child process kill() call in ctrlc_handler() to only be invoked
if the child was already forked.
Fixes: caddc0fbe495 ("selftests/resctrl: Move resctrl FS mount/umount to higher level")
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng(a)jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre(a)intel.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org>
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 97b87285ab2a..224ba8544d8a 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -167,12 +167,6 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
strcpy(param.filename, RESULT_FILE_NAME1);
param.num_of_runs = 0;
param.cpu_no = sibling_cpu_no;
- } else {
- ret = signal_handler_register();
- if (ret) {
- kill(bm_pid, SIGKILL);
- goto out;
- }
}
remove(param.filename);
@@ -209,10 +203,8 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
}
close(pipefd[0]);
kill(bm_pid, SIGKILL);
- signal_handler_unregister();
}
-out:
cat_test_cleanup();
return ret;
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 823672a20a43..495aeee5b734 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -67,21 +67,45 @@ void tests_cleanup(void)
cat_test_cleanup();
}
-static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
+static int test_prepare(void)
{
int res;
- ksft_print_msg("Starting MBM BW change ...\n");
+ res = signal_handler_register();
+ if (res) {
+ ksft_print_msg("Failed to register signal handler\n");
+ return res;
+ }
res = mount_resctrlfs();
if (res) {
- ksft_exit_fail_msg("Failed to mount resctrl FS\n");
+ signal_handler_unregister();
+ ksft_print_msg("Failed to mount resctrl FS\n");
+ return res;
+ }
+ return 0;
+}
+
+static void test_cleanup(void)
+{
+ umount_resctrlfs();
+ signal_handler_unregister();
+}
+
+static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
+{
+ int res;
+
+ ksft_print_msg("Starting MBM BW change ...\n");
+
+ if (test_prepare()) {
+ ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
return;
}
if (!validate_resctrl_feature_request(MBM_STR) || (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n");
- goto umount;
+ goto cleanup;
}
res = mbm_bw_change(cpu_no, benchmark_cmd);
@@ -89,8 +113,8 @@ static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
if ((get_vendor() == ARCH_INTEL) && res)
ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
-umount:
- umount_resctrlfs();
+cleanup:
+ test_cleanup();
}
static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
@@ -99,22 +123,21 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
ksft_print_msg("Starting MBA Schemata change ...\n");
- res = mount_resctrlfs();
- if (res) {
- ksft_exit_fail_msg("Failed to mount resctrl FS\n");
+ if (test_prepare()) {
+ ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
return;
}
if (!validate_resctrl_feature_request(MBA_STR) || (get_vendor() != ARCH_INTEL)) {
ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
- goto umount;
+ goto cleanup;
}
res = mba_schemata_change(cpu_no, benchmark_cmd);
ksft_test_result(!res, "MBA: schemata change\n");
-umount:
- umount_resctrlfs();
+cleanup:
+ test_cleanup();
}
static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
@@ -123,15 +146,14 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
ksft_print_msg("Starting CMT test ...\n");
- res = mount_resctrlfs();
- if (res) {
- ksft_exit_fail_msg("Failed to mount resctrl FS\n");
+ if (test_prepare()) {
+ ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
return;
}
if (!validate_resctrl_feature_request(CMT_STR)) {
ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
- goto umount;
+ goto cleanup;
}
res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd);
@@ -139,8 +161,8 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
if ((get_vendor() == ARCH_INTEL) && res)
ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
-umount:
- umount_resctrlfs();
+cleanup:
+ test_cleanup();
}
static void run_cat_test(int cpu_no, int no_of_bits)
@@ -149,22 +171,21 @@ static void run_cat_test(int cpu_no, int no_of_bits)
ksft_print_msg("Starting CAT test ...\n");
- res = mount_resctrlfs();
- if (res) {
- ksft_exit_fail_msg("Failed to mount resctrl FS\n");
+ if (test_prepare()) {
+ ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
return;
}
if (!validate_resctrl_feature_request(CAT_STR)) {
ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n");
- goto umount;
+ goto cleanup;
}
res = cat_perf_miss_val(cpu_no, no_of_bits, "L3");
ksft_test_result(!res, "CAT: test\n");
-umount:
- umount_resctrlfs();
+cleanup:
+ test_cleanup();
}
int main(int argc, char **argv)
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 01bbe11a8983..b8ca6fa40b3b 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -468,7 +468,9 @@ pid_t bm_pid, ppid;
void ctrlc_handler(int signum, siginfo_t *info, void *ptr)
{
- kill(bm_pid, SIGKILL);
+ /* Only kill child after bm_pid is set after fork() */
+ if (bm_pid)
+ kill(bm_pid, SIGKILL);
umount_resctrlfs();
tests_cleanup();
ksft_print_msg("Ending\n\n");
@@ -485,6 +487,8 @@ int signal_handler_register(void)
struct sigaction sigact = {};
int ret = 0;
+ bm_pid = 0;
+
sigact.sa_sigaction = ctrlc_handler;
sigemptyset(&sigact.sa_mask);
sigact.sa_flags = SA_SIGINFO;
@@ -706,10 +710,6 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
ksft_print_msg("Benchmark PID: %d\n", bm_pid);
- ret = signal_handler_register();
- if (ret)
- goto out;
-
/*
* The cast removes constness but nothing mutates benchmark_cmd within
* the context of this process. At the receiving process, it becomes
@@ -721,19 +721,19 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
/* Taskset benchmark to specified cpu */
ret = taskset_benchmark(bm_pid, param->cpu_no);
if (ret)
- goto unregister;
+ goto out;
/* Write benchmark to specified control&monitoring grp in resctrl FS */
ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
resctrl_val);
if (ret)
- goto unregister;
+ goto out;
if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
ret = initialize_mem_bw_imc();
if (ret)
- goto unregister;
+ goto out;
initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp,
param->cpu_no, resctrl_val);
@@ -748,7 +748,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
sizeof(pipe_message)) {
perror("# failed reading message from child process");
close(pipefd[0]);
- goto unregister;
+ goto out;
}
}
close(pipefd[0]);
@@ -757,7 +757,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
if (sigqueue(bm_pid, SIGUSR1, value) == -1) {
perror("# sigqueue SIGUSR1 to child");
ret = errno;
- goto unregister;
+ goto out;
}
/* Give benchmark enough time to fully run */
@@ -786,8 +786,6 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
}
}
-unregister:
- signal_handler_unregister();
out:
kill(bm_pid, SIGKILL);
This is a backport of commits
0220575e65a ("ASoC: soc-dai: add flag to mute and unmute stream during trigger")
805ce81826c8 ("ASoC: codecs: wsa883x: make use of new mute_unmute_on_trigger flag")
which specifically fix a loud crackling noise when starting a stream on
the Lenovo ThinkPad X13s.
These backports should apply to any stable tree which already has commit
3efcb471f871 ("ASoC: soc-pcm.c: Make sure DAI parameters cleared if the
DAI becomes inactive") backported (e.g. 6.6.2 and 6.5.12).
Note that the interaction of these commits resulted in a bad merge in
mainline which is fixed up here:
https://lore.kernel.org/lkml/20231123091815.21933-1-johan+linaro@kernel.org/
Johan
Srinivas Kandagatla (2):
ASoC: soc-dai: add flag to mute and unmute stream during trigger
ASoC: codecs: wsa883x: make use of new mute_unmute_on_trigger flag
include/sound/soc-dai.h | 1 +
sound/soc/codecs/wsa883x.c | 7 +------
sound/soc/soc-dai.c | 7 +++++++
sound/soc/soc-pcm.c | 12 ++++++++----
4 files changed, 17 insertions(+), 10 deletions(-)
--
2.41.0
Hi Greg and Sasha,
On Fri, Oct 27, 2023 at 01:52:11PM +0200, Johan Hovold wrote:
> On Fri, Oct 27, 2023 at 11:57:45AM +0100, Srinivas Kandagatla wrote:
> > Click/Pop Noise was a long pending issue with WSA Codecs which are prone
> > to accumlate DC when ports are active but without any data streams.
> > There are multiple places in the current setup, where this could happen
> > in both startup as well as shutdown path.
> >
> > This patchset adds a new flag mute_unmute_on_trigger to dai_ops to let
> > generic code do the mute/unmute on trigger.
> >
> > This patches help fix those issues by making sure the PA is Muted/Unmuted
> > inline with the stream start/stop events.
> >
> > Srinivas Kandagatla (2):
> > ASoC: soc-dai: add flag to mute and unmute stream during trigger
> > ASoC: codecs: wsa883x: make use of new mute_unmute_on_trigger flag
>
> I've verified that this fixes the pop sounds when starting and stopping
> a stream on the X13s, even if the click sound when killing pulseaudio
> (e.g. on reboot) is still there (as with the previous fixes).
>
> Tested-by: Johan Hovold <johan+linaro(a)kernel.org>
>
> If these are accepted, can we get them backported to 6.5 as well?
These fixes are now in 6.7-rc1 as
f0220575e65a ("ASoC: soc-dai: add flag to mute and unmute stream during trigger")
805ce81826c8 ("ASoC: codecs: wsa883x: make use of new mute_unmute_on_trigger flag")
As these fix a loud scary crackling noise on the Lenovo ThinkPad X13s,
is it possible to get these backported at least to stable 6.6 and 6.5?
Johan
This device has a silicon bug that makes it report a timeout interrupt
but no data in the FIFO.
The datasheet states the following in the errata section 18.1.4:
"If the host reads the receive FIFO at the same time as a
time-out interrupt condition happens, the host might read 0xCC
(time-out) in the Interrupt Indication Register (IIR), but bit 0
of the Line Status Register (LSR) is not set (means there is no
data in the receive FIFO)."
The errata description seems to indicate it concerns only polled mode of
operation when reading bit 0 of the LSR register. However, tests have
shown and NXP has confirmed that the RXLVL register also yields 0 when
the bug is triggered, and hence the IRQ driven implementation in this
driver is equally affected.
This bug has hit us on production units and when it does, sc16is7xx_irq()
would spin forever because sc16is7xx_port_irq() keeps seeing an
interrupt in the IIR register that is not cleared because the driver
does not call into sc16is7xx_handle_rx() unless the RXLVL register
reports at least one byte in the FIFO.
Fix this by always reading one byte from the FIFO when this condition
is detected in order to clear the interrupt. This approach was
confirmed to be correct by NXP through their support channels.
Signed-off-by: Daniel Mack <daniel(a)zonque.org>
Co-Developed-by: Maxim Popov <maxim.snafu(a)gmail.com>
Tested by: Hugo Villeneuve <hvilleneuve(a)dimonoff.com>
Cc: stable(a)vger.kernel.org
---
v5: slightly reworded commit log again, added Hugo's Tested-By
v4: NXP has confirmed the fix; update the commit log accordingly
v3: re-added the additional Co-Developed-by and stable@ tags
v2: reworded the commit log a bit for more context.
drivers/tty/serial/sc16is7xx.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 289ca7d4e566..76f76e510ed1 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -765,6 +765,18 @@ static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
case SC16IS7XX_IIR_RTOI_SRC:
case SC16IS7XX_IIR_XOFFI_SRC:
rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
+
+ /*
+ * There is a silicon bug that makes the chip report a
+ * time-out interrupt but no data in the FIFO. This is
+ * described in errata section 18.1.4.
+ *
+ * When this happens, read one byte from the FIFO to
+ * clear the interrupt.
+ */
+ if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
+ rxlen = 1;
+
if (rxlen)
sc16is7xx_handle_rx(port, rxlen, iir);
break;
--
2.41.0
Hello, all:
This list has been migrated to the new vger infrastructure. No action is
required on your part and there should be no change in how you interact with
this list.
This message acts as a verification test that the archives are properly
updating.
If something isn't working or looking right, please reach out to
helpdesk(a)kernel.org.
Best regards,
-K
The patch titled
Subject: mm,oom_reaper: avoid run queue_oom_reaper if task is not oom
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
mmoom_reaper-avoid-run-queue_oom_reaper-if-task-is-not-oom.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: gaoxu <gaoxu2(a)hihonor.com>
Subject: mm,oom_reaper: avoid run queue_oom_reaper if task is not oom
Date: Wed, 22 Nov 2023 12:46:44 +0000
queue_oom_reaper() tests and sets tsk->signal->oom_mm->flags. However, it
is necessary to check if 'tsk' is an OOM victim before executing
'queue_oom_reaper' because the variable may be NULL.
We encountered such an issue, and the log is as follows:
[3701:11_see]Out of memory: Killed process 3154 (system_server)
total-vm:23662044kB, anon-rss:0kB, file-rss:0kB, shmem-rss:0kB,
UID:1000 pgtables:4056kB oom_score_adj:-900
[3701:11_see][RB/E]rb_sreason_str_set: sreason_str set null_pointer
[3701:11_see][RB/E]rb_sreason_str_set: sreason_str set unknown_addr
[3701:11_see]Unable to handle kernel NULL pointer dereference at virtual
address 0000000000000328
[3701:11_see]user pgtable: 4k pages, 39-bit VAs, pgdp=3D00000000821de000
[3701:11_see][0000000000000328] pgd=3D0000000000000000,
p4d=3D0000000000000000,pud=3D0000000000000000
[3701:11_see]tracing off
[3701:11_see]Internal error: Oops: 96000005 [#1] PREEMPT SMP
[3701:11_see]Call trace:
[3701:11_see] queue_oom_reaper+0x30/0x170
[3701:11_see] __oom_kill_process+0x590/0x860
[3701:11_see] oom_kill_process+0x140/0x274
[3701:11_see] out_of_memory+0x2f4/0x54c
[3701:11_see] __alloc_pages_slowpath+0x5d8/0xaac
[3701:11_see] __alloc_pages+0x774/0x800
[3701:11_see] wp_page_copy+0xc4/0x116c
[3701:11_see] do_wp_page+0x4bc/0x6fc
[3701:11_see] handle_pte_fault+0x98/0x2a8
[3701:11_see] __handle_mm_fault+0x368/0x700
[3701:11_see] do_handle_mm_fault+0x160/0x2cc
[3701:11_see] do_page_fault+0x3e0/0x818
[3701:11_see] do_mem_abort+0x68/0x17c
[3701:11_see] el0_da+0x3c/0xa0
[3701:11_see] el0t_64_sync_handler+0xc4/0xec
[3701:11_see] el0t_64_sync+0x1b4/0x1b8
[3701:11_see]tracing off
Link: https://lkml.kernel.org/r/400d13bddb524ef6af37cb2220808c75@hihonor.com
Signed-off-by: Gao Xu <gaoxu2(a)hihonor.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/oom_kill.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/oom_kill.c~mmoom_reaper-avoid-run-queue_oom_reaper-if-task-is-not-oom
+++ a/mm/oom_kill.c
@@ -984,7 +984,7 @@ static void __oom_kill_process(struct ta
}
rcu_read_unlock();
- if (can_oom_reap)
+ if (can_oom_reap && tsk_is_oom_victim(victim))
queue_oom_reaper(victim);
mmdrop(mm);
_
Patches currently in -mm which might be from gaoxu2(a)hihonor.com are
mmoom_reaper-avoid-run-queue_oom_reaper-if-task-is-not-oom.patch
Not all LJCA chips implement SPI and on chips without SPI reading
the SPI descriptors will timeout.
On laptop models like the Dell Latitude 9420, this is expected behavior
and not an error.
Modify the driver to continue without instantiating a SPI auxbus child,
instead of failing to probe() the whole LJCA chip.
Fixes: acd6199f195d ("usb: Add support for Intel LJCA device")
Cc: stable(a)vger.kernel.org
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
Reviewed-by: Wentong Wu <wentong.wu(a)intel.com>
Link: https://lore.kernel.org/r/20231104175104.38786-1-hdegoede@redhat.com
---
Changes in v3:
- Fix commit-id in fixes tag
Changes in v2:
- Small commit msg + comment fixes
- Add Fixes tag + Cc: stable
---
drivers/usb/misc/usb-ljca.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c
index c9decd0396d4..a280d3a54b18 100644
--- a/drivers/usb/misc/usb-ljca.c
+++ b/drivers/usb/misc/usb-ljca.c
@@ -656,10 +656,11 @@ static int ljca_enumerate_spi(struct ljca_adapter *adap)
unsigned int i;
int ret;
+ /* Not all LJCA chips implement SPI, a timeout reading the descriptors is normal */
ret = ljca_send(adap, LJCA_CLIENT_MNG, LJCA_MNG_ENUM_SPI, NULL, 0, buf,
sizeof(buf), true, LJCA_ENUM_CLIENT_TIMEOUT_MS);
if (ret < 0)
- return ret;
+ return (ret == -ETIMEDOUT) ? 0 : ret;
/* check firmware response */
desc = (struct ljca_spi_descriptor *)buf;
--
2.41.0
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x cca42bd8eb1b54a4c9bbf48c79d120e66619a3e4
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112203-roping-darling-f64a@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
cca42bd8eb1b ("rcutorture: Fix stuttering races and other issues")
10af43671e8b ("torture: Move stutter_wait() timeouts to hrtimers")
5d248bb39fe1 ("torture: Add lock_torture writer_fifo module parameter")
f8619c300f49 ("locktorture: Add long_hold to adjust lock-hold delays")
45bcf0bd8cbe ("locktorture: With nested locks, occasionally skip main lock")
b63343207da2 ("locktorture: Add nested_[un]lock() hooks and nlocks parameter")
c24501b24074 ("locktorture: Make the rt_boost factor a tunable")
e01f3a1a589e ("locktorture: Allow non-rtmutex lock types to be boosted")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From cca42bd8eb1b54a4c9bbf48c79d120e66619a3e4 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel(a)joelfernandes.org>
Date: Sat, 29 Jul 2023 14:27:31 +0000
Subject: [PATCH] rcutorture: Fix stuttering races and other issues
The stuttering code isn't functioning as expected. Ideally, it should
pause the torture threads for a designated period before resuming. Yet,
it fails to halt the test for the correct duration. Additionally, a race
condition exists, potentially causing the stuttering code to pause for
an extended period if the 'spt' variable is non-zero due to the stutter
orchestration thread's inadequate CPU time.
Moreover, over-stuttering can hinder RCU's progress on TREE07 kernels.
This happens as the stuttering code may run within a softirq due to RCU
callbacks. Consequently, ksoftirqd keeps a CPU busy for several seconds,
thus obstructing RCU's progress. This situation triggers a warning
message in the logs:
[ 2169.481783] rcu_torture_writer: rtort_pipe_count: 9
This warning suggests that an RCU torture object, although invisible to
RCU readers, couldn't make it past the pipe array and be freed -- a
strong indication that there weren't enough grace periods during the
stutter interval.
To address these issues, this patch sets the "stutter end" time to an
absolute point in the future set by the main stutter thread. This is
then used for waiting in stutter_wait(). While the stutter thread still
defines this absolute time, the waiters' waiting logic doesn't rely on
the stutter thread receiving sufficient CPU time to halt the stuttering
as the halting is now self-controlled.
Cc: stable(a)vger.kernel.org
Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org>
Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org>
diff --git a/kernel/torture.c b/kernel/torture.c
index 6ba62e5993e7..fd353f98162f 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -720,7 +720,7 @@ static void torture_shutdown_cleanup(void)
* suddenly applied to or removed from the system.
*/
static struct task_struct *stutter_task;
-static int stutter_pause_test;
+static ktime_t stutter_till_abs_time;
static int stutter;
static int stutter_gap;
@@ -730,30 +730,16 @@ static int stutter_gap;
*/
bool stutter_wait(const char *title)
{
- unsigned int i = 0;
bool ret = false;
- int spt;
+ ktime_t till_ns;
cond_resched_tasks_rcu_qs();
- spt = READ_ONCE(stutter_pause_test);
- for (; spt; spt = READ_ONCE(stutter_pause_test)) {
- if (!ret && !rt_task(current)) {
- sched_set_normal(current, MAX_NICE);
- ret = true;
- }
- if (spt == 1) {
- torture_hrtimeout_jiffies(1, NULL);
- } else if (spt == 2) {
- while (READ_ONCE(stutter_pause_test)) {
- if (!(i++ & 0xffff))
- torture_hrtimeout_us(10, 0, NULL);
- cond_resched();
- }
- } else {
- torture_hrtimeout_jiffies(round_jiffies_relative(HZ), NULL);
- }
- torture_shutdown_absorb(title);
+ till_ns = READ_ONCE(stutter_till_abs_time);
+ if (till_ns && ktime_before(ktime_get(), till_ns)) {
+ torture_hrtimeout_ns(till_ns, 0, HRTIMER_MODE_ABS, NULL);
+ ret = true;
}
+ torture_shutdown_absorb(title);
return ret;
}
EXPORT_SYMBOL_GPL(stutter_wait);
@@ -764,23 +750,16 @@ EXPORT_SYMBOL_GPL(stutter_wait);
*/
static int torture_stutter(void *arg)
{
- DEFINE_TORTURE_RANDOM(rand);
- int wtime;
+ ktime_t till_ns;
VERBOSE_TOROUT_STRING("torture_stutter task started");
do {
if (!torture_must_stop() && stutter > 1) {
- wtime = stutter;
- if (stutter > 2) {
- WRITE_ONCE(stutter_pause_test, 1);
- wtime = stutter - 3;
- torture_hrtimeout_jiffies(wtime, &rand);
- wtime = 2;
- }
- WRITE_ONCE(stutter_pause_test, 2);
- torture_hrtimeout_jiffies(wtime, NULL);
+ till_ns = ktime_add_ns(ktime_get(),
+ jiffies_to_nsecs(stutter));
+ WRITE_ONCE(stutter_till_abs_time, till_ns);
+ torture_hrtimeout_jiffies(stutter - 1, NULL);
}
- WRITE_ONCE(stutter_pause_test, 0);
if (!torture_must_stop())
torture_hrtimeout_jiffies(stutter_gap, NULL);
torture_shutdown_absorb("torture_stutter");
The patch below does not apply to the 6.5-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x cca42bd8eb1b54a4c9bbf48c79d120e66619a3e4
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112201-parakeet-trustless-649e@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
cca42bd8eb1b ("rcutorture: Fix stuttering races and other issues")
10af43671e8b ("torture: Move stutter_wait() timeouts to hrtimers")
5d248bb39fe1 ("torture: Add lock_torture writer_fifo module parameter")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From cca42bd8eb1b54a4c9bbf48c79d120e66619a3e4 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel(a)joelfernandes.org>
Date: Sat, 29 Jul 2023 14:27:31 +0000
Subject: [PATCH] rcutorture: Fix stuttering races and other issues
The stuttering code isn't functioning as expected. Ideally, it should
pause the torture threads for a designated period before resuming. Yet,
it fails to halt the test for the correct duration. Additionally, a race
condition exists, potentially causing the stuttering code to pause for
an extended period if the 'spt' variable is non-zero due to the stutter
orchestration thread's inadequate CPU time.
Moreover, over-stuttering can hinder RCU's progress on TREE07 kernels.
This happens as the stuttering code may run within a softirq due to RCU
callbacks. Consequently, ksoftirqd keeps a CPU busy for several seconds,
thus obstructing RCU's progress. This situation triggers a warning
message in the logs:
[ 2169.481783] rcu_torture_writer: rtort_pipe_count: 9
This warning suggests that an RCU torture object, although invisible to
RCU readers, couldn't make it past the pipe array and be freed -- a
strong indication that there weren't enough grace periods during the
stutter interval.
To address these issues, this patch sets the "stutter end" time to an
absolute point in the future set by the main stutter thread. This is
then used for waiting in stutter_wait(). While the stutter thread still
defines this absolute time, the waiters' waiting logic doesn't rely on
the stutter thread receiving sufficient CPU time to halt the stuttering
as the halting is now self-controlled.
Cc: stable(a)vger.kernel.org
Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org>
Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org>
diff --git a/kernel/torture.c b/kernel/torture.c
index 6ba62e5993e7..fd353f98162f 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -720,7 +720,7 @@ static void torture_shutdown_cleanup(void)
* suddenly applied to or removed from the system.
*/
static struct task_struct *stutter_task;
-static int stutter_pause_test;
+static ktime_t stutter_till_abs_time;
static int stutter;
static int stutter_gap;
@@ -730,30 +730,16 @@ static int stutter_gap;
*/
bool stutter_wait(const char *title)
{
- unsigned int i = 0;
bool ret = false;
- int spt;
+ ktime_t till_ns;
cond_resched_tasks_rcu_qs();
- spt = READ_ONCE(stutter_pause_test);
- for (; spt; spt = READ_ONCE(stutter_pause_test)) {
- if (!ret && !rt_task(current)) {
- sched_set_normal(current, MAX_NICE);
- ret = true;
- }
- if (spt == 1) {
- torture_hrtimeout_jiffies(1, NULL);
- } else if (spt == 2) {
- while (READ_ONCE(stutter_pause_test)) {
- if (!(i++ & 0xffff))
- torture_hrtimeout_us(10, 0, NULL);
- cond_resched();
- }
- } else {
- torture_hrtimeout_jiffies(round_jiffies_relative(HZ), NULL);
- }
- torture_shutdown_absorb(title);
+ till_ns = READ_ONCE(stutter_till_abs_time);
+ if (till_ns && ktime_before(ktime_get(), till_ns)) {
+ torture_hrtimeout_ns(till_ns, 0, HRTIMER_MODE_ABS, NULL);
+ ret = true;
}
+ torture_shutdown_absorb(title);
return ret;
}
EXPORT_SYMBOL_GPL(stutter_wait);
@@ -764,23 +750,16 @@ EXPORT_SYMBOL_GPL(stutter_wait);
*/
static int torture_stutter(void *arg)
{
- DEFINE_TORTURE_RANDOM(rand);
- int wtime;
+ ktime_t till_ns;
VERBOSE_TOROUT_STRING("torture_stutter task started");
do {
if (!torture_must_stop() && stutter > 1) {
- wtime = stutter;
- if (stutter > 2) {
- WRITE_ONCE(stutter_pause_test, 1);
- wtime = stutter - 3;
- torture_hrtimeout_jiffies(wtime, &rand);
- wtime = 2;
- }
- WRITE_ONCE(stutter_pause_test, 2);
- torture_hrtimeout_jiffies(wtime, NULL);
+ till_ns = ktime_add_ns(ktime_get(),
+ jiffies_to_nsecs(stutter));
+ WRITE_ONCE(stutter_till_abs_time, till_ns);
+ torture_hrtimeout_jiffies(stutter - 1, NULL);
}
- WRITE_ONCE(stutter_pause_test, 0);
if (!torture_must_stop())
torture_hrtimeout_jiffies(stutter_gap, NULL);
torture_shutdown_absorb("torture_stutter");
The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x cca42bd8eb1b54a4c9bbf48c79d120e66619a3e4
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112259-concrete-detonator-b0ed@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..
Possible dependencies:
cca42bd8eb1b ("rcutorture: Fix stuttering races and other issues")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From cca42bd8eb1b54a4c9bbf48c79d120e66619a3e4 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel(a)joelfernandes.org>
Date: Sat, 29 Jul 2023 14:27:31 +0000
Subject: [PATCH] rcutorture: Fix stuttering races and other issues
The stuttering code isn't functioning as expected. Ideally, it should
pause the torture threads for a designated period before resuming. Yet,
it fails to halt the test for the correct duration. Additionally, a race
condition exists, potentially causing the stuttering code to pause for
an extended period if the 'spt' variable is non-zero due to the stutter
orchestration thread's inadequate CPU time.
Moreover, over-stuttering can hinder RCU's progress on TREE07 kernels.
This happens as the stuttering code may run within a softirq due to RCU
callbacks. Consequently, ksoftirqd keeps a CPU busy for several seconds,
thus obstructing RCU's progress. This situation triggers a warning
message in the logs:
[ 2169.481783] rcu_torture_writer: rtort_pipe_count: 9
This warning suggests that an RCU torture object, although invisible to
RCU readers, couldn't make it past the pipe array and be freed -- a
strong indication that there weren't enough grace periods during the
stutter interval.
To address these issues, this patch sets the "stutter end" time to an
absolute point in the future set by the main stutter thread. This is
then used for waiting in stutter_wait(). While the stutter thread still
defines this absolute time, the waiters' waiting logic doesn't rely on
the stutter thread receiving sufficient CPU time to halt the stuttering
as the halting is now self-controlled.
Cc: stable(a)vger.kernel.org
Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org>
Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org>
diff --git a/kernel/torture.c b/kernel/torture.c
index 6ba62e5993e7..fd353f98162f 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -720,7 +720,7 @@ static void torture_shutdown_cleanup(void)
* suddenly applied to or removed from the system.
*/
static struct task_struct *stutter_task;
-static int stutter_pause_test;
+static ktime_t stutter_till_abs_time;
static int stutter;
static int stutter_gap;
@@ -730,30 +730,16 @@ static int stutter_gap;
*/
bool stutter_wait(const char *title)
{
- unsigned int i = 0;
bool ret = false;
- int spt;
+ ktime_t till_ns;
cond_resched_tasks_rcu_qs();
- spt = READ_ONCE(stutter_pause_test);
- for (; spt; spt = READ_ONCE(stutter_pause_test)) {
- if (!ret && !rt_task(current)) {
- sched_set_normal(current, MAX_NICE);
- ret = true;
- }
- if (spt == 1) {
- torture_hrtimeout_jiffies(1, NULL);
- } else if (spt == 2) {
- while (READ_ONCE(stutter_pause_test)) {
- if (!(i++ & 0xffff))
- torture_hrtimeout_us(10, 0, NULL);
- cond_resched();
- }
- } else {
- torture_hrtimeout_jiffies(round_jiffies_relative(HZ), NULL);
- }
- torture_shutdown_absorb(title);
+ till_ns = READ_ONCE(stutter_till_abs_time);
+ if (till_ns && ktime_before(ktime_get(), till_ns)) {
+ torture_hrtimeout_ns(till_ns, 0, HRTIMER_MODE_ABS, NULL);
+ ret = true;
}
+ torture_shutdown_absorb(title);
return ret;
}
EXPORT_SYMBOL_GPL(stutter_wait);
@@ -764,23 +750,16 @@ EXPORT_SYMBOL_GPL(stutter_wait);
*/
static int torture_stutter(void *arg)
{
- DEFINE_TORTURE_RANDOM(rand);
- int wtime;
+ ktime_t till_ns;
VERBOSE_TOROUT_STRING("torture_stutter task started");
do {
if (!torture_must_stop() && stutter > 1) {
- wtime = stutter;
- if (stutter > 2) {
- WRITE_ONCE(stutter_pause_test, 1);
- wtime = stutter - 3;
- torture_hrtimeout_jiffies(wtime, &rand);
- wtime = 2;
- }
- WRITE_ONCE(stutter_pause_test, 2);
- torture_hrtimeout_jiffies(wtime, NULL);
+ till_ns = ktime_add_ns(ktime_get(),
+ jiffies_to_nsecs(stutter));
+ WRITE_ONCE(stutter_till_abs_time, till_ns);
+ torture_hrtimeout_jiffies(stutter - 1, NULL);
}
- WRITE_ONCE(stutter_pause_test, 0);
if (!torture_must_stop())
torture_hrtimeout_jiffies(stutter_gap, NULL);
torture_shutdown_absorb("torture_stutter");
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112207-dealmaker-frigidly-e080@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
83a939f0fdc2 ("PCI: exynos: Don't discard .remove() callback")
778f7c194b1d ("PCI: dwc: exynos: Rework the driver to support Exynos5433 variant")
b9ac0f9dc8ea ("PCI: dwc: Move dw_pcie_setup_rc() to DWC common code")
59fbab1ae40e ("PCI: dwc: Move dw_pcie_msi_init() into core")
886a9c134755 ("PCI: dwc: Move link handling into common code")
331e9bcead52 ("PCI: dwc: Drop the .set_num_vectors() host op")
a0fd361db8e5 ("PCI: dwc: Move "dbi", "dbi2", and "addr_space" resource setup into common code")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de>
Date: Sun, 1 Oct 2023 19:02:51 +0200
Subject: [PATCH] PCI: exynos: Don't discard .remove() callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
With CONFIG_PCI_EXYNOS=y and exynos_pcie_remove() marked with __exit, the
function is discarded from the driver. In this case a bound device can
still get unbound, e.g via sysfs. Then no cleanup code is run resulting in
resource leaks or worse.
The right thing to do is do always have the remove callback available.
This fixes the following warning by modpost:
WARNING: modpost: drivers/pci/controller/dwc/pci-exynos: section mismatch in reference: exynos_pcie_driver+0x8 (section: .data) -> exynos_pcie_remove (section: .exit.text)
(with ARCH=x86_64 W=1 allmodconfig).
Fixes: 340cba6092c2 ("pci: Add PCIe driver for Samsung Exynos")
Link: https://lore.kernel.org/r/20231001170254.2506508-2-u.kleine-koenig@pengutro…
Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Reviewed-by: Alim Akhtar <alim.akhtar(a)samsung.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 6319082301d6..c6bede346932 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -375,7 +375,7 @@ static int exynos_pcie_probe(struct platform_device *pdev)
return ret;
}
-static int __exit exynos_pcie_remove(struct platform_device *pdev)
+static int exynos_pcie_remove(struct platform_device *pdev)
{
struct exynos_pcie *ep = platform_get_drvdata(pdev);
@@ -431,7 +431,7 @@ static const struct of_device_id exynos_pcie_of_match[] = {
static struct platform_driver exynos_pcie_driver = {
.probe = exynos_pcie_probe,
- .remove = __exit_p(exynos_pcie_remove),
+ .remove = exynos_pcie_remove,
.driver = {
.name = "exynos-pcie",
.of_match_table = exynos_pcie_of_match,
Hello,
This series contains the backports of two related changes to fix
removal of timed-out catchall elements.
As-is, removed element remains on the list and will be collected
again.
The adjustments are needed because of missing commit
0e1ea651c971 ("netfilter: nf_tables: shrink memory consumption of set elements"),
so we need to pass set_elem container struct instead of "elem_priv".
Pablo Neira Ayuso (2):
netfilter: nf_tables: remove catchall element in GC sync path
netfilter: nf_tables: split async and sync catchall in two functions
net/netfilter/nf_tables_api.c | 53 ++++++++++++++++++++++++-----------
1 file changed, 36 insertions(+), 17 deletions(-)
--
2.41.0
From: Mike Christie <michael.christie(a)oracle.com>
[ Upstream commit 3b83486399a6a9feb9c681b74c21a227d48d7020 ]
If scsi_execute_cmd() returns < 0, it doesn't initialize the sshdr, so we
shouldn't access the sshdr. If it returns 0, then the cmd executed
successfully, so there is no need to check the sshdr. sd_sync_cache() will
only access the sshdr if it's been setup because it calls
scsi_status_is_check_condition() before accessing it. However, the
sd_sync_cache() caller, sd_suspend_common(), does not check.
sd_suspend_common() is only checking for ILLEGAL_REQUEST which it's using
to determine if the command is supported. If it's not it just ignores the
error. So to fix its sshdr use this patch just moves that check to
sd_sync_cache() where it converts ILLEGAL_REQUEST to success/0.
sd_suspend_common() was ignoring that error and sd_shutdown() doesn't check
for errors so there will be no behavior changes.
Signed-off-by: Mike Christie <michael.christie(a)oracle.com>
Link: https://lore.kernel.org/r/20231106231304.5694-2-michael.christie@oracle.com
Reviewed-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: Martin Wilck <mwilck(a)suse.com>
Reviewed-by: Bart Van Assche <bvanassche(a)acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/scsi/sd.c | 53 ++++++++++++++++++++---------------------------
1 file changed, 23 insertions(+), 30 deletions(-)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c4babb16dac73..1b7de2daf64a2 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1681,24 +1681,21 @@ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
return disk_changed ? DISK_EVENT_MEDIA_CHANGE : 0;
}
-static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
+static int sd_sync_cache(struct scsi_disk *sdkp)
{
int retries, res;
struct scsi_device *sdp = sdkp->device;
const int timeout = sdp->request_queue->rq_timeout
* SD_FLUSH_TIMEOUT_MULTIPLIER;
- struct scsi_sense_hdr my_sshdr;
+ struct scsi_sense_hdr sshdr;
const struct scsi_exec_args exec_args = {
.req_flags = BLK_MQ_REQ_PM,
- /* caller might not be interested in sense, but we need it */
- .sshdr = sshdr ? : &my_sshdr,
+ .sshdr = &sshdr,
};
if (!scsi_device_online(sdp))
return -ENODEV;
- sshdr = exec_args.sshdr;
-
for (retries = 3; retries > 0; --retries) {
unsigned char cmd[16] = { 0 };
@@ -1723,15 +1720,23 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
return res;
if (scsi_status_is_check_condition(res) &&
- scsi_sense_valid(sshdr)) {
- sd_print_sense_hdr(sdkp, sshdr);
+ scsi_sense_valid(&sshdr)) {
+ sd_print_sense_hdr(sdkp, &sshdr);
/* we need to evaluate the error return */
- if (sshdr->asc == 0x3a || /* medium not present */
- sshdr->asc == 0x20 || /* invalid command */
- (sshdr->asc == 0x74 && sshdr->ascq == 0x71)) /* drive is password locked */
+ if (sshdr.asc == 0x3a || /* medium not present */
+ sshdr.asc == 0x20 || /* invalid command */
+ (sshdr.asc == 0x74 && sshdr.ascq == 0x71)) /* drive is password locked */
/* this is no error here */
return 0;
+ /*
+ * This drive doesn't support sync and there's not much
+ * we can do because this is called during shutdown
+ * or suspend so just return success so those operations
+ * can proceed.
+ */
+ if (sshdr.sense_key == ILLEGAL_REQUEST)
+ return 0;
}
switch (host_byte(res)) {
@@ -3886,7 +3891,7 @@ static void sd_shutdown(struct device *dev)
if (sdkp->WCE && sdkp->media_present) {
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
- sd_sync_cache(sdkp, NULL);
+ sd_sync_cache(sdkp);
}
if ((system_state != SYSTEM_RESTART &&
@@ -3907,7 +3912,6 @@ static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime)
static int sd_suspend_common(struct device *dev, bool runtime)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
- struct scsi_sense_hdr sshdr;
int ret = 0;
if (!sdkp) /* E.g.: runtime suspend following sd_remove() */
@@ -3916,24 +3920,13 @@ static int sd_suspend_common(struct device *dev, bool runtime)
if (sdkp->WCE && sdkp->media_present) {
if (!sdkp->device->silence_suspend)
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
- ret = sd_sync_cache(sdkp, &sshdr);
-
- if (ret) {
- /* ignore OFFLINE device */
- if (ret == -ENODEV)
- return 0;
-
- if (!scsi_sense_valid(&sshdr) ||
- sshdr.sense_key != ILLEGAL_REQUEST)
- return ret;
+ ret = sd_sync_cache(sdkp);
+ /* ignore OFFLINE device */
+ if (ret == -ENODEV)
+ return 0;
- /*
- * sshdr.sense_key == ILLEGAL_REQUEST means this drive
- * doesn't support sync. There's not much to do and
- * suspend shouldn't fail.
- */
- ret = 0;
- }
+ if (ret)
+ return ret;
}
if (sd_do_start_stop(sdkp->device, runtime)) {
--
2.42.0
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x c9260693aa0c1e029ed23693cfd4d7814eee6624
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112200-barcode-wasp-98d7@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
c9260693aa0c ("PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e card")
26409dd04589 ("of: unittest: Add pci_dt_testdrv pci driver")
ae9813db1dc5 ("PCI: Add quirks to generate device tree node for Xilinx Alveo U50")
74df14cd301a ("of: unittest: add node lifecycle tests")
e87cacadebaf ("of: overlay: rename overlay source files from .dts to .dtso")
5459c0b70467 ("PCI/DPC: Quirk PIO log size for certain Intel Root Ports")
3cc30140dbe2 ("Merge tag 'pci-v5.19-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c9260693aa0c1e029ed23693cfd4d7814eee6624 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas(a)wunner.de>
Date: Thu, 21 Sep 2023 16:23:34 +0200
Subject: [PATCH] PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e
card
Commit ac91e6980563 ("PCI: Unify delay handling for reset and resume")
shortened an unconditional 1 sec delay after a Secondary Bus Reset to 100
msec for PCIe (per PCIe r6.1 sec 6.6.1). The 1 sec delay is only required
for Conventional PCI.
But it turns out that there are PCIe devices which require a longer delay
than prescribed before first config space access after reset recovery or
resume from D3cold:
Chad reports that a "VideoPropulsion Torrent QN16e" MPEG QAM Modulator
"raises a PCI system error (PERR), as reported by the IPMI event log, and
the hardware itself would suffer a catastrophic event, cycling the server"
unless the longer delay is observed.
The card is specified to conform to PCIe r1.0 and indeed only supports Gen1
speed (2.5 GT/s) according to lspci. PCIe r1.0 sec 7.6 prescribes the same
100 msec delay as PCIe r6.1 sec 6.6.1:
To allow components to perform internal initialization, system software
must wait for at least 100 ms from the end of a reset (cold/warm/hot)
before it is permitted to issue Configuration Requests
The behavior of the Torrent QN16e card thus appears to be a quirk. Treat
it as such and lengthen the reset delay for this specific device.
Fixes: ac91e6980563 ("PCI: Unify delay handling for reset and resume")
Link: https://lore.kernel.org/r/47727e792c7f0282dc144e3ec8ce8eb6e713394e.16953045…
Reported-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Closes: https://lore.kernel.org/linux-pci/DM6PR16MB2844903E34CAB910082DF019B1FAA@DM…
Tested-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Signed-off-by: Lukas Wunner <lukas(a)wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org # v5.4+
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index eeec1d6f9023..91a15d79c7c4 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -6188,3 +6188,15 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node);
+
+/*
+ * Devices known to require a longer delay before first config space access
+ * after reset recovery or resume from D3cold:
+ *
+ * VideoPropulsion (aka Genroco) Torrent QN16e MPEG QAM Modulator
+ */
+static void pci_fixup_d3cold_delay_1sec(struct pci_dev *pdev)
+{
+ pdev->d3cold_delay = 1000;
+}
+DECLARE_PCI_FIXUP_FINAL(0x5555, 0x0004, pci_fixup_d3cold_delay_1sec);
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x c9260693aa0c1e029ed23693cfd4d7814eee6624
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112258-saddlebag-vantage-48b3@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
c9260693aa0c ("PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e card")
26409dd04589 ("of: unittest: Add pci_dt_testdrv pci driver")
ae9813db1dc5 ("PCI: Add quirks to generate device tree node for Xilinx Alveo U50")
74df14cd301a ("of: unittest: add node lifecycle tests")
e87cacadebaf ("of: overlay: rename overlay source files from .dts to .dtso")
5459c0b70467 ("PCI/DPC: Quirk PIO log size for certain Intel Root Ports")
3cc30140dbe2 ("Merge tag 'pci-v5.19-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c9260693aa0c1e029ed23693cfd4d7814eee6624 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas(a)wunner.de>
Date: Thu, 21 Sep 2023 16:23:34 +0200
Subject: [PATCH] PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e
card
Commit ac91e6980563 ("PCI: Unify delay handling for reset and resume")
shortened an unconditional 1 sec delay after a Secondary Bus Reset to 100
msec for PCIe (per PCIe r6.1 sec 6.6.1). The 1 sec delay is only required
for Conventional PCI.
But it turns out that there are PCIe devices which require a longer delay
than prescribed before first config space access after reset recovery or
resume from D3cold:
Chad reports that a "VideoPropulsion Torrent QN16e" MPEG QAM Modulator
"raises a PCI system error (PERR), as reported by the IPMI event log, and
the hardware itself would suffer a catastrophic event, cycling the server"
unless the longer delay is observed.
The card is specified to conform to PCIe r1.0 and indeed only supports Gen1
speed (2.5 GT/s) according to lspci. PCIe r1.0 sec 7.6 prescribes the same
100 msec delay as PCIe r6.1 sec 6.6.1:
To allow components to perform internal initialization, system software
must wait for at least 100 ms from the end of a reset (cold/warm/hot)
before it is permitted to issue Configuration Requests
The behavior of the Torrent QN16e card thus appears to be a quirk. Treat
it as such and lengthen the reset delay for this specific device.
Fixes: ac91e6980563 ("PCI: Unify delay handling for reset and resume")
Link: https://lore.kernel.org/r/47727e792c7f0282dc144e3ec8ce8eb6e713394e.16953045…
Reported-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Closes: https://lore.kernel.org/linux-pci/DM6PR16MB2844903E34CAB910082DF019B1FAA@DM…
Tested-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Signed-off-by: Lukas Wunner <lukas(a)wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org # v5.4+
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index eeec1d6f9023..91a15d79c7c4 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -6188,3 +6188,15 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node);
+
+/*
+ * Devices known to require a longer delay before first config space access
+ * after reset recovery or resume from D3cold:
+ *
+ * VideoPropulsion (aka Genroco) Torrent QN16e MPEG QAM Modulator
+ */
+static void pci_fixup_d3cold_delay_1sec(struct pci_dev *pdev)
+{
+ pdev->d3cold_delay = 1000;
+}
+DECLARE_PCI_FIXUP_FINAL(0x5555, 0x0004, pci_fixup_d3cold_delay_1sec);
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x c9260693aa0c1e029ed23693cfd4d7814eee6624
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112256-fancy-quintet-036e@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
c9260693aa0c ("PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e card")
26409dd04589 ("of: unittest: Add pci_dt_testdrv pci driver")
ae9813db1dc5 ("PCI: Add quirks to generate device tree node for Xilinx Alveo U50")
74df14cd301a ("of: unittest: add node lifecycle tests")
e87cacadebaf ("of: overlay: rename overlay source files from .dts to .dtso")
5459c0b70467 ("PCI/DPC: Quirk PIO log size for certain Intel Root Ports")
3cc30140dbe2 ("Merge tag 'pci-v5.19-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c9260693aa0c1e029ed23693cfd4d7814eee6624 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas(a)wunner.de>
Date: Thu, 21 Sep 2023 16:23:34 +0200
Subject: [PATCH] PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e
card
Commit ac91e6980563 ("PCI: Unify delay handling for reset and resume")
shortened an unconditional 1 sec delay after a Secondary Bus Reset to 100
msec for PCIe (per PCIe r6.1 sec 6.6.1). The 1 sec delay is only required
for Conventional PCI.
But it turns out that there are PCIe devices which require a longer delay
than prescribed before first config space access after reset recovery or
resume from D3cold:
Chad reports that a "VideoPropulsion Torrent QN16e" MPEG QAM Modulator
"raises a PCI system error (PERR), as reported by the IPMI event log, and
the hardware itself would suffer a catastrophic event, cycling the server"
unless the longer delay is observed.
The card is specified to conform to PCIe r1.0 and indeed only supports Gen1
speed (2.5 GT/s) according to lspci. PCIe r1.0 sec 7.6 prescribes the same
100 msec delay as PCIe r6.1 sec 6.6.1:
To allow components to perform internal initialization, system software
must wait for at least 100 ms from the end of a reset (cold/warm/hot)
before it is permitted to issue Configuration Requests
The behavior of the Torrent QN16e card thus appears to be a quirk. Treat
it as such and lengthen the reset delay for this specific device.
Fixes: ac91e6980563 ("PCI: Unify delay handling for reset and resume")
Link: https://lore.kernel.org/r/47727e792c7f0282dc144e3ec8ce8eb6e713394e.16953045…
Reported-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Closes: https://lore.kernel.org/linux-pci/DM6PR16MB2844903E34CAB910082DF019B1FAA@DM…
Tested-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Signed-off-by: Lukas Wunner <lukas(a)wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org # v5.4+
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index eeec1d6f9023..91a15d79c7c4 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -6188,3 +6188,15 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node);
+
+/*
+ * Devices known to require a longer delay before first config space access
+ * after reset recovery or resume from D3cold:
+ *
+ * VideoPropulsion (aka Genroco) Torrent QN16e MPEG QAM Modulator
+ */
+static void pci_fixup_d3cold_delay_1sec(struct pci_dev *pdev)
+{
+ pdev->d3cold_delay = 1000;
+}
+DECLARE_PCI_FIXUP_FINAL(0x5555, 0x0004, pci_fixup_d3cold_delay_1sec);
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x c9260693aa0c1e029ed23693cfd4d7814eee6624
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112254-work-demystify-2b7c@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
c9260693aa0c ("PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e card")
26409dd04589 ("of: unittest: Add pci_dt_testdrv pci driver")
ae9813db1dc5 ("PCI: Add quirks to generate device tree node for Xilinx Alveo U50")
74df14cd301a ("of: unittest: add node lifecycle tests")
e87cacadebaf ("of: overlay: rename overlay source files from .dts to .dtso")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c9260693aa0c1e029ed23693cfd4d7814eee6624 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas(a)wunner.de>
Date: Thu, 21 Sep 2023 16:23:34 +0200
Subject: [PATCH] PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e
card
Commit ac91e6980563 ("PCI: Unify delay handling for reset and resume")
shortened an unconditional 1 sec delay after a Secondary Bus Reset to 100
msec for PCIe (per PCIe r6.1 sec 6.6.1). The 1 sec delay is only required
for Conventional PCI.
But it turns out that there are PCIe devices which require a longer delay
than prescribed before first config space access after reset recovery or
resume from D3cold:
Chad reports that a "VideoPropulsion Torrent QN16e" MPEG QAM Modulator
"raises a PCI system error (PERR), as reported by the IPMI event log, and
the hardware itself would suffer a catastrophic event, cycling the server"
unless the longer delay is observed.
The card is specified to conform to PCIe r1.0 and indeed only supports Gen1
speed (2.5 GT/s) according to lspci. PCIe r1.0 sec 7.6 prescribes the same
100 msec delay as PCIe r6.1 sec 6.6.1:
To allow components to perform internal initialization, system software
must wait for at least 100 ms from the end of a reset (cold/warm/hot)
before it is permitted to issue Configuration Requests
The behavior of the Torrent QN16e card thus appears to be a quirk. Treat
it as such and lengthen the reset delay for this specific device.
Fixes: ac91e6980563 ("PCI: Unify delay handling for reset and resume")
Link: https://lore.kernel.org/r/47727e792c7f0282dc144e3ec8ce8eb6e713394e.16953045…
Reported-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Closes: https://lore.kernel.org/linux-pci/DM6PR16MB2844903E34CAB910082DF019B1FAA@DM…
Tested-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Signed-off-by: Lukas Wunner <lukas(a)wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org # v5.4+
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index eeec1d6f9023..91a15d79c7c4 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -6188,3 +6188,15 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node);
+
+/*
+ * Devices known to require a longer delay before first config space access
+ * after reset recovery or resume from D3cold:
+ *
+ * VideoPropulsion (aka Genroco) Torrent QN16e MPEG QAM Modulator
+ */
+static void pci_fixup_d3cold_delay_1sec(struct pci_dev *pdev)
+{
+ pdev->d3cold_delay = 1000;
+}
+DECLARE_PCI_FIXUP_FINAL(0x5555, 0x0004, pci_fixup_d3cold_delay_1sec);
The patch below does not apply to the 6.5-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x c9260693aa0c1e029ed23693cfd4d7814eee6624
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112252-underrate-creative-1a23@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
c9260693aa0c ("PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e card")
26409dd04589 ("of: unittest: Add pci_dt_testdrv pci driver")
ae9813db1dc5 ("PCI: Add quirks to generate device tree node for Xilinx Alveo U50")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c9260693aa0c1e029ed23693cfd4d7814eee6624 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas(a)wunner.de>
Date: Thu, 21 Sep 2023 16:23:34 +0200
Subject: [PATCH] PCI: Lengthen reset delay for VideoPropulsion Torrent QN16e
card
Commit ac91e6980563 ("PCI: Unify delay handling for reset and resume")
shortened an unconditional 1 sec delay after a Secondary Bus Reset to 100
msec for PCIe (per PCIe r6.1 sec 6.6.1). The 1 sec delay is only required
for Conventional PCI.
But it turns out that there are PCIe devices which require a longer delay
than prescribed before first config space access after reset recovery or
resume from D3cold:
Chad reports that a "VideoPropulsion Torrent QN16e" MPEG QAM Modulator
"raises a PCI system error (PERR), as reported by the IPMI event log, and
the hardware itself would suffer a catastrophic event, cycling the server"
unless the longer delay is observed.
The card is specified to conform to PCIe r1.0 and indeed only supports Gen1
speed (2.5 GT/s) according to lspci. PCIe r1.0 sec 7.6 prescribes the same
100 msec delay as PCIe r6.1 sec 6.6.1:
To allow components to perform internal initialization, system software
must wait for at least 100 ms from the end of a reset (cold/warm/hot)
before it is permitted to issue Configuration Requests
The behavior of the Torrent QN16e card thus appears to be a quirk. Treat
it as such and lengthen the reset delay for this specific device.
Fixes: ac91e6980563 ("PCI: Unify delay handling for reset and resume")
Link: https://lore.kernel.org/r/47727e792c7f0282dc144e3ec8ce8eb6e713394e.16953045…
Reported-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Closes: https://lore.kernel.org/linux-pci/DM6PR16MB2844903E34CAB910082DF019B1FAA@DM…
Tested-by: Chad Schroeder <CSchroeder(a)sonifi.com>
Signed-off-by: Lukas Wunner <lukas(a)wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org # v5.4+
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index eeec1d6f9023..91a15d79c7c4 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -6188,3 +6188,15 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node);
+
+/*
+ * Devices known to require a longer delay before first config space access
+ * after reset recovery or resume from D3cold:
+ *
+ * VideoPropulsion (aka Genroco) Torrent QN16e MPEG QAM Modulator
+ */
+static void pci_fixup_d3cold_delay_1sec(struct pci_dev *pdev)
+{
+ pdev->d3cold_delay = 1000;
+}
+DECLARE_PCI_FIXUP_FINAL(0x5555, 0x0004, pci_fixup_d3cold_delay_1sec);
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112211-carded-sake-3ee5@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
83a939f0fdc2 ("PCI: exynos: Don't discard .remove() callback")
778f7c194b1d ("PCI: dwc: exynos: Rework the driver to support Exynos5433 variant")
b9ac0f9dc8ea ("PCI: dwc: Move dw_pcie_setup_rc() to DWC common code")
59fbab1ae40e ("PCI: dwc: Move dw_pcie_msi_init() into core")
886a9c134755 ("PCI: dwc: Move link handling into common code")
331e9bcead52 ("PCI: dwc: Drop the .set_num_vectors() host op")
a0fd361db8e5 ("PCI: dwc: Move "dbi", "dbi2", and "addr_space" resource setup into common code")
1b6a0e43a1a1 ("PCI: layerscape: Add EP mode support for ls1088a and ls2088a")
cc255eb0bfbe ("PCI: layerscape: Modify the way of getting capability with different PEX")
20e458fb92af ("PCI: layerscape: Fix some format issue of the code")
47a062609a30 ("PCI: designware-ep: Modify MSI and MSIX CAP way of finding")
6bfc9c3a2c70 ("PCI: designware-ep: Move the function of getting MSI capability forward")
24ede430fa49 ("PCI: designware-ep: Add multiple PFs support for DWC")
fdd056ff7af4 ("PCI: dwc: Use DBI accessors")
aeaa0bfe8965 ("PCI: dwc: Move N_FTS setup to common setup")
d439e7edd134 ("PCI: dwc/intel-gw: Drop unused max_width")
441e48fdf0b4 ("PCI: dwc: Set PORT_LINK_DLL_LINK_EN in common setup code")
39bc5006501c ("PCI: dwc: Centralize link gen setting")
84667a416d42 ("PCI: dwc/tegra: Use common Designware port logic register definitions")
fb7652327101 ("PCI: dwc: Remove hardcoded PCI_CAP_ID_EXP offset")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de>
Date: Sun, 1 Oct 2023 19:02:51 +0200
Subject: [PATCH] PCI: exynos: Don't discard .remove() callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
With CONFIG_PCI_EXYNOS=y and exynos_pcie_remove() marked with __exit, the
function is discarded from the driver. In this case a bound device can
still get unbound, e.g via sysfs. Then no cleanup code is run resulting in
resource leaks or worse.
The right thing to do is do always have the remove callback available.
This fixes the following warning by modpost:
WARNING: modpost: drivers/pci/controller/dwc/pci-exynos: section mismatch in reference: exynos_pcie_driver+0x8 (section: .data) -> exynos_pcie_remove (section: .exit.text)
(with ARCH=x86_64 W=1 allmodconfig).
Fixes: 340cba6092c2 ("pci: Add PCIe driver for Samsung Exynos")
Link: https://lore.kernel.org/r/20231001170254.2506508-2-u.kleine-koenig@pengutro…
Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Reviewed-by: Alim Akhtar <alim.akhtar(a)samsung.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 6319082301d6..c6bede346932 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -375,7 +375,7 @@ static int exynos_pcie_probe(struct platform_device *pdev)
return ret;
}
-static int __exit exynos_pcie_remove(struct platform_device *pdev)
+static int exynos_pcie_remove(struct platform_device *pdev)
{
struct exynos_pcie *ep = platform_get_drvdata(pdev);
@@ -431,7 +431,7 @@ static const struct of_device_id exynos_pcie_of_match[] = {
static struct platform_driver exynos_pcie_driver = {
.probe = exynos_pcie_probe,
- .remove = __exit_p(exynos_pcie_remove),
+ .remove = exynos_pcie_remove,
.driver = {
.name = "exynos-pcie",
.of_match_table = exynos_pcie_of_match,
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112210-embargo-yen-0719@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
83a939f0fdc2 ("PCI: exynos: Don't discard .remove() callback")
778f7c194b1d ("PCI: dwc: exynos: Rework the driver to support Exynos5433 variant")
b9ac0f9dc8ea ("PCI: dwc: Move dw_pcie_setup_rc() to DWC common code")
59fbab1ae40e ("PCI: dwc: Move dw_pcie_msi_init() into core")
886a9c134755 ("PCI: dwc: Move link handling into common code")
331e9bcead52 ("PCI: dwc: Drop the .set_num_vectors() host op")
a0fd361db8e5 ("PCI: dwc: Move "dbi", "dbi2", and "addr_space" resource setup into common code")
1b6a0e43a1a1 ("PCI: layerscape: Add EP mode support for ls1088a and ls2088a")
cc255eb0bfbe ("PCI: layerscape: Modify the way of getting capability with different PEX")
20e458fb92af ("PCI: layerscape: Fix some format issue of the code")
47a062609a30 ("PCI: designware-ep: Modify MSI and MSIX CAP way of finding")
6bfc9c3a2c70 ("PCI: designware-ep: Move the function of getting MSI capability forward")
24ede430fa49 ("PCI: designware-ep: Add multiple PFs support for DWC")
fdd056ff7af4 ("PCI: dwc: Use DBI accessors")
aeaa0bfe8965 ("PCI: dwc: Move N_FTS setup to common setup")
d439e7edd134 ("PCI: dwc/intel-gw: Drop unused max_width")
441e48fdf0b4 ("PCI: dwc: Set PORT_LINK_DLL_LINK_EN in common setup code")
39bc5006501c ("PCI: dwc: Centralize link gen setting")
84667a416d42 ("PCI: dwc/tegra: Use common Designware port logic register definitions")
fb7652327101 ("PCI: dwc: Remove hardcoded PCI_CAP_ID_EXP offset")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de>
Date: Sun, 1 Oct 2023 19:02:51 +0200
Subject: [PATCH] PCI: exynos: Don't discard .remove() callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
With CONFIG_PCI_EXYNOS=y and exynos_pcie_remove() marked with __exit, the
function is discarded from the driver. In this case a bound device can
still get unbound, e.g via sysfs. Then no cleanup code is run resulting in
resource leaks or worse.
The right thing to do is do always have the remove callback available.
This fixes the following warning by modpost:
WARNING: modpost: drivers/pci/controller/dwc/pci-exynos: section mismatch in reference: exynos_pcie_driver+0x8 (section: .data) -> exynos_pcie_remove (section: .exit.text)
(with ARCH=x86_64 W=1 allmodconfig).
Fixes: 340cba6092c2 ("pci: Add PCIe driver for Samsung Exynos")
Link: https://lore.kernel.org/r/20231001170254.2506508-2-u.kleine-koenig@pengutro…
Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Reviewed-by: Alim Akhtar <alim.akhtar(a)samsung.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 6319082301d6..c6bede346932 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -375,7 +375,7 @@ static int exynos_pcie_probe(struct platform_device *pdev)
return ret;
}
-static int __exit exynos_pcie_remove(struct platform_device *pdev)
+static int exynos_pcie_remove(struct platform_device *pdev)
{
struct exynos_pcie *ep = platform_get_drvdata(pdev);
@@ -431,7 +431,7 @@ static const struct of_device_id exynos_pcie_of_match[] = {
static struct platform_driver exynos_pcie_driver = {
.probe = exynos_pcie_probe,
- .remove = __exit_p(exynos_pcie_remove),
+ .remove = exynos_pcie_remove,
.driver = {
.name = "exynos-pcie",
.of_match_table = exynos_pcie_of_match,
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112209-antics-unreached-451a@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
83a939f0fdc2 ("PCI: exynos: Don't discard .remove() callback")
778f7c194b1d ("PCI: dwc: exynos: Rework the driver to support Exynos5433 variant")
b9ac0f9dc8ea ("PCI: dwc: Move dw_pcie_setup_rc() to DWC common code")
59fbab1ae40e ("PCI: dwc: Move dw_pcie_msi_init() into core")
886a9c134755 ("PCI: dwc: Move link handling into common code")
331e9bcead52 ("PCI: dwc: Drop the .set_num_vectors() host op")
a0fd361db8e5 ("PCI: dwc: Move "dbi", "dbi2", and "addr_space" resource setup into common code")
1b6a0e43a1a1 ("PCI: layerscape: Add EP mode support for ls1088a and ls2088a")
cc255eb0bfbe ("PCI: layerscape: Modify the way of getting capability with different PEX")
20e458fb92af ("PCI: layerscape: Fix some format issue of the code")
47a062609a30 ("PCI: designware-ep: Modify MSI and MSIX CAP way of finding")
6bfc9c3a2c70 ("PCI: designware-ep: Move the function of getting MSI capability forward")
24ede430fa49 ("PCI: designware-ep: Add multiple PFs support for DWC")
fdd056ff7af4 ("PCI: dwc: Use DBI accessors")
aeaa0bfe8965 ("PCI: dwc: Move N_FTS setup to common setup")
d439e7edd134 ("PCI: dwc/intel-gw: Drop unused max_width")
441e48fdf0b4 ("PCI: dwc: Set PORT_LINK_DLL_LINK_EN in common setup code")
39bc5006501c ("PCI: dwc: Centralize link gen setting")
84667a416d42 ("PCI: dwc/tegra: Use common Designware port logic register definitions")
fb7652327101 ("PCI: dwc: Remove hardcoded PCI_CAP_ID_EXP offset")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 83a939f0fdc208ff3639dd3d42ac9b3c35607fd2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de>
Date: Sun, 1 Oct 2023 19:02:51 +0200
Subject: [PATCH] PCI: exynos: Don't discard .remove() callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
With CONFIG_PCI_EXYNOS=y and exynos_pcie_remove() marked with __exit, the
function is discarded from the driver. In this case a bound device can
still get unbound, e.g via sysfs. Then no cleanup code is run resulting in
resource leaks or worse.
The right thing to do is do always have the remove callback available.
This fixes the following warning by modpost:
WARNING: modpost: drivers/pci/controller/dwc/pci-exynos: section mismatch in reference: exynos_pcie_driver+0x8 (section: .data) -> exynos_pcie_remove (section: .exit.text)
(with ARCH=x86_64 W=1 allmodconfig).
Fixes: 340cba6092c2 ("pci: Add PCIe driver for Samsung Exynos")
Link: https://lore.kernel.org/r/20231001170254.2506508-2-u.kleine-koenig@pengutro…
Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Reviewed-by: Alim Akhtar <alim.akhtar(a)samsung.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 6319082301d6..c6bede346932 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -375,7 +375,7 @@ static int exynos_pcie_probe(struct platform_device *pdev)
return ret;
}
-static int __exit exynos_pcie_remove(struct platform_device *pdev)
+static int exynos_pcie_remove(struct platform_device *pdev)
{
struct exynos_pcie *ep = platform_get_drvdata(pdev);
@@ -431,7 +431,7 @@ static const struct of_device_id exynos_pcie_of_match[] = {
static struct platform_driver exynos_pcie_driver = {
.probe = exynos_pcie_probe,
- .remove = __exit_p(exynos_pcie_remove),
+ .remove = exynos_pcie_remove,
.driver = {
.name = "exynos-pcie",
.of_match_table = exynos_pcie_of_match,
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x a07d2497ed657eb2efeb967af47e22f573dcd1d6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112212-decimal-recapture-1786@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
a07d2497ed65 ("PCI: qcom-ep: Add dedicated callback for writing to DBI2 registers")
01794236666a ("PCI: qcom-ep: Add ICC bandwidth voting support")
8f05cd35c73b ("PCI: qcom-ep: Add support for BME notification")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a07d2497ed657eb2efeb967af47e22f573dcd1d6 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <mani(a)kernel.org>
Date: Wed, 25 Oct 2023 18:30:29 +0530
Subject: [PATCH] PCI: qcom-ep: Add dedicated callback for writing to DBI2
registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The DWC core driver exposes the write_dbi2() callback for writing to the
DBI2 registers in a vendor-specific way.
On the Qcom EP platforms, the DBI_CS2 bit in the ELBI region needs to be
asserted before writing to any DBI2 registers and deasserted once done.
So, let's implement the callback for the Qcom PCIe EP driver so that the
DBI2 writes are correctly handled in the hardware.
Without this callback, the DBI2 register writes like BAR size won't go
through and as a result, the default BAR size is set for all BARs.
[kwilczynski: commit log, renamed function to match the DWC convention]
Fixes: f55fee56a631 ("PCI: qcom-ep: Add Qualcomm PCIe Endpoint controller driver")
Suggested-by: Serge Semin <fancer.lancer(a)gmail.com>
Link: https://lore.kernel.org/linux-pci/20231025130029.74693-2-manivannan.sadhasi…
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam(a)linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski(a)kernel.org>
Reviewed-by: Serge Semin <fancer.lancer(a)gmail.com>
Cc: stable(a)vger.kernel.org # 5.16+
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 8bd8107690a6..9b62ee6992f0 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -123,6 +123,7 @@
/* ELBI registers */
#define ELBI_SYS_STTS 0x08
+#define ELBI_CS2_ENABLE 0xa4
/* DBI registers */
#define DBI_CON_STATUS 0x44
@@ -263,6 +264,21 @@ static void qcom_pcie_dw_stop_link(struct dw_pcie *pci)
disable_irq(pcie_ep->perst_irq);
}
+static void qcom_pcie_dw_write_dbi2(struct dw_pcie *pci, void __iomem *base,
+ u32 reg, size_t size, u32 val)
+{
+ struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
+ int ret;
+
+ writel(1, pcie_ep->elbi + ELBI_CS2_ENABLE);
+
+ ret = dw_pcie_write(pci->dbi_base2 + reg, size, val);
+ if (ret)
+ dev_err(pci->dev, "Failed to write DBI2 register (0x%x): %d\n", reg, ret);
+
+ writel(0, pcie_ep->elbi + ELBI_CS2_ENABLE);
+}
+
static void qcom_pcie_ep_icc_update(struct qcom_pcie_ep *pcie_ep)
{
struct dw_pcie *pci = &pcie_ep->pci;
@@ -519,6 +535,7 @@ static const struct dw_pcie_ops pci_ops = {
.link_up = qcom_pcie_dw_link_up,
.start_link = qcom_pcie_dw_start_link,
.stop_link = qcom_pcie_dw_stop_link,
+ .write_dbi2 = qcom_pcie_dw_write_dbi2,
};
static int qcom_pcie_ep_get_io_resources(struct platform_device *pdev,
The patch below does not apply to the 6.5-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x a07d2497ed657eb2efeb967af47e22f573dcd1d6
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112211-rush-provolone-6433@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
a07d2497ed65 ("PCI: qcom-ep: Add dedicated callback for writing to DBI2 registers")
01794236666a ("PCI: qcom-ep: Add ICC bandwidth voting support")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a07d2497ed657eb2efeb967af47e22f573dcd1d6 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <mani(a)kernel.org>
Date: Wed, 25 Oct 2023 18:30:29 +0530
Subject: [PATCH] PCI: qcom-ep: Add dedicated callback for writing to DBI2
registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The DWC core driver exposes the write_dbi2() callback for writing to the
DBI2 registers in a vendor-specific way.
On the Qcom EP platforms, the DBI_CS2 bit in the ELBI region needs to be
asserted before writing to any DBI2 registers and deasserted once done.
So, let's implement the callback for the Qcom PCIe EP driver so that the
DBI2 writes are correctly handled in the hardware.
Without this callback, the DBI2 register writes like BAR size won't go
through and as a result, the default BAR size is set for all BARs.
[kwilczynski: commit log, renamed function to match the DWC convention]
Fixes: f55fee56a631 ("PCI: qcom-ep: Add Qualcomm PCIe Endpoint controller driver")
Suggested-by: Serge Semin <fancer.lancer(a)gmail.com>
Link: https://lore.kernel.org/linux-pci/20231025130029.74693-2-manivannan.sadhasi…
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam(a)linaro.org>
Signed-off-by: Krzysztof Wilczyński <kwilczynski(a)kernel.org>
Reviewed-by: Serge Semin <fancer.lancer(a)gmail.com>
Cc: stable(a)vger.kernel.org # 5.16+
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 8bd8107690a6..9b62ee6992f0 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -123,6 +123,7 @@
/* ELBI registers */
#define ELBI_SYS_STTS 0x08
+#define ELBI_CS2_ENABLE 0xa4
/* DBI registers */
#define DBI_CON_STATUS 0x44
@@ -263,6 +264,21 @@ static void qcom_pcie_dw_stop_link(struct dw_pcie *pci)
disable_irq(pcie_ep->perst_irq);
}
+static void qcom_pcie_dw_write_dbi2(struct dw_pcie *pci, void __iomem *base,
+ u32 reg, size_t size, u32 val)
+{
+ struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
+ int ret;
+
+ writel(1, pcie_ep->elbi + ELBI_CS2_ENABLE);
+
+ ret = dw_pcie_write(pci->dbi_base2 + reg, size, val);
+ if (ret)
+ dev_err(pci->dev, "Failed to write DBI2 register (0x%x): %d\n", reg, ret);
+
+ writel(0, pcie_ep->elbi + ELBI_CS2_ENABLE);
+}
+
static void qcom_pcie_ep_icc_update(struct qcom_pcie_ep *pcie_ep)
{
struct dw_pcie *pci = &pcie_ep->pci;
@@ -519,6 +535,7 @@ static const struct dw_pcie_ops pci_ops = {
.link_up = qcom_pcie_dw_link_up,
.start_link = qcom_pcie_dw_start_link,
.stop_link = qcom_pcie_dw_stop_link,
+ .write_dbi2 = qcom_pcie_dw_write_dbi2,
};
static int qcom_pcie_ep_get_io_resources(struct platform_device *pdev,
This device has a silicon bug that makes it report a timeout interrupt
but no data in the FIFO.
The datasheet states the following in the errata section 18.1.4:
"If the host reads the receive FIFO at the same time as a
time-out interrupt condition happens, the host might read 0xCC
(time-out) in the Interrupt Indication Register (IIR), but bit 0
of the Line Status Register (LSR) is not set (means there is no
data in the receive FIFO)."
The errata doesn't explicitly mention that, but tests have shown
and the vendor has confirmed that the RXLVL register is equally
affected.
This bug has hit us on production units and when it does, sc16is7xx_irq()
would spin forever because sc16is7xx_port_irq() keeps seeing an
interrupt in the IIR register that is not cleared because the driver
does not call into sc16is7xx_handle_rx() unless the RXLVL register
reports at least one byte in the FIFO.
Fix this by always reading one byte when this condition is detected
in order to clear the interrupt. This approach was confirmed to be
correct by NXP through their support channels.
Signed-off-by: Daniel Mack <daniel(a)zonque.org>
Co-Developed-by: Maxim Popov <maxim.snafu(a)gmail.com>
Cc: stable(a)vger.kernel.org
---
Meanwhile, NXP has confirmed this fix to be correct.
v4: NXP has confirmed the fix; update the commit log accordingly
v3: re-added the additional Co-Developed-by and stable@ tags
v2: reworded the commit log a bit for more context.
drivers/tty/serial/sc16is7xx.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 289ca7d4e566..76f76e510ed1 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -765,6 +765,18 @@ static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
case SC16IS7XX_IIR_RTOI_SRC:
case SC16IS7XX_IIR_XOFFI_SRC:
rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
+
+ /*
+ * There is a silicon bug that makes the chip report a
+ * time-out interrupt but no data in the FIFO. This is
+ * described in errata section 18.1.4.
+ *
+ * When this happens, read one byte from the FIFO to
+ * clear the interrupt.
+ */
+ if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
+ rxlen = 1;
+
if (rxlen)
sc16is7xx_handle_rx(port, rxlen, iir);
break;
--
2.41.0
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 5ad1e217a2b23aa046b241183bd9452d259d70d0
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112230-baggage-playback-8fc5@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
5ad1e217a2b2 ("clk: visconti: Fix undefined behavior bug in struct visconti_pll_provider")
7e626a080bb2 ("clk: visconti: remove unused visconti_pll_provider::regmap")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5ad1e217a2b23aa046b241183bd9452d259d70d0 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars(a)kernel.org>
Date: Mon, 16 Oct 2023 16:05:27 -0600
Subject: [PATCH] clk: visconti: Fix undefined behavior bug in struct
visconti_pll_provider
`struct clk_hw_onecell_data` is a flexible structure, which means that
it contains flexible-array member at the bottom, in this case array
`hws`:
include/linux/clk-provider.h:
1380 struct clk_hw_onecell_data {
1381 unsigned int num;
1382 struct clk_hw *hws[] __counted_by(num);
1383 };
This could potentially lead to an overwrite of the objects following
`clk_data` in `struct visconti_pll_provider`, in this case
`struct device_node *node;`, at run-time:
drivers/clk/visconti/pll.h:
16 struct visconti_pll_provider {
17 void __iomem *reg_base;
18 struct clk_hw_onecell_data clk_data;
19 struct device_node *node;
20 };
Notice that a total of 56 bytes are allocated for flexible-array `hws`
at line 328. See below:
include/dt-bindings/clock/toshiba,tmpv770x.h:
14 #define TMPV770X_NR_PLL 7
drivers/clk/visconti/pll-tmpv770x.c:
69 ctx = visconti_init_pll(np, reg_base, TMPV770X_NR_PLL);
drivers/clk/visconti/pll.c:
321 struct visconti_pll_provider * __init visconti_init_pll(struct device_node *np,
322 void __iomem *base,
323 unsigned long nr_plls)
324 {
325 struct visconti_pll_provider *ctx;
...
328 ctx = kzalloc(struct_size(ctx, clk_data.hws, nr_plls), GFP_KERNEL);
`struct_size(ctx, clk_data.hws, nr_plls)` above translates to
sizeof(struct visconti_pll_provider) + sizeof(struct clk_hw *) * 7 ==
24 + 8 * 7 == 24 + 56
^^^^
|
allocated bytes for flex array `hws`
$ pahole -C visconti_pll_provider drivers/clk/visconti/pll.o
struct visconti_pll_provider {
void * reg_base; /* 0 8 */
struct clk_hw_onecell_data clk_data; /* 8 8 */
struct device_node * node; /* 16 8 */
/* size: 24, cachelines: 1, members: 3 */
/* last cacheline: 24 bytes */
};
And then, after the allocation, some data is written into all members
of `struct visconti_pll_provider`:
332 for (i = 0; i < nr_plls; ++i)
333 ctx->clk_data.hws[i] = ERR_PTR(-ENOENT);
334
335 ctx->node = np;
336 ctx->reg_base = base;
337 ctx->clk_data.num = nr_plls;
Fix all these by placing the declaration of object `clk_data` at the
end of `struct visconti_pll_provider`. Also, add a comment to make it
clear that this object must always be last in the structure, and
prevent this bug from being introduced again in the future.
-Wflex-array-member-not-at-end is coming in GCC-14, and we are getting
ready to enable it globally.
Fixes: b4cbe606dc36 ("clk: visconti: Add support common clock driver and reset driver")
Cc: stable(a)vger.kernel.org
Reviewed-by: Kees Cook <keescook(a)chromium.org>
Acked-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu(a)toshiba.co.jp>
Signed-off-by: Gustavo A. R. Silva <gustavoars(a)kernel.org>
Link: https://lore.kernel.org/r/57a831d94ee2b3889b11525d4ad500356f89576f.16974928…
Signed-off-by: Stephen Boyd <sboyd(a)kernel.org>
diff --git a/drivers/clk/visconti/pll.h b/drivers/clk/visconti/pll.h
index 01d07f1bf01b..c4bd40676da4 100644
--- a/drivers/clk/visconti/pll.h
+++ b/drivers/clk/visconti/pll.h
@@ -15,8 +15,10 @@
struct visconti_pll_provider {
void __iomem *reg_base;
- struct clk_hw_onecell_data clk_data;
struct device_node *node;
+
+ /* Must be last */
+ struct clk_hw_onecell_data clk_data;
};
#define VISCONTI_PLL_RATE(_rate, _dacen, _dsmen, \
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x ea167a7fc2426f7685c3735e104921c1a20a6d3f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112200-frenzied-liking-978f@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
ea167a7fc242 ("cpufreq: stats: Fix buffer overflow detection in trans_stats()")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ea167a7fc2426f7685c3735e104921c1a20a6d3f Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth(a)gmail.com>
Date: Tue, 24 Oct 2023 20:30:14 +0200
Subject: [PATCH] cpufreq: stats: Fix buffer overflow detection in
trans_stats()
Commit 3c0897c180c6 ("cpufreq: Use scnprintf() for avoiding potential
buffer overflow") switched from snprintf to the more secure scnprintf
but never updated the exit condition for PAGE_SIZE.
As the commit say and as scnprintf document, what scnprintf returns what
is actually written not counting the '\0' end char. This results in the
case of len exceeding the size, len set to PAGE_SIZE - 1, as it can be
written at max PAGE_SIZE - 1 (as '\0' is not counted)
Because of len is never set to PAGE_SIZE, the function never break early,
never prints the warning and never return -EFBIG.
Fix this by changing the condition to PAGE_SIZE - 1 to correctly trigger
the error.
Cc: 5.10+ <stable(a)vger.kernel.org> # 5.10+
Fixes: 3c0897c180c6 ("cpufreq: Use scnprintf() for avoiding potential buffer overflow")
Signed-off-by: Christian Marangi <ansuelsmth(a)gmail.com>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index a33df3c66c88..40a9ff18da06 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -131,23 +131,23 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
len += sysfs_emit_at(buf, len, " From : To\n");
len += sysfs_emit_at(buf, len, " : ");
for (i = 0; i < stats->state_num; i++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "%9u ", stats->freq_table[i]);
}
- if (len >= PAGE_SIZE)
- return PAGE_SIZE;
+ if (len >= PAGE_SIZE - 1)
+ return PAGE_SIZE - 1;
len += sysfs_emit_at(buf, len, "\n");
for (i = 0; i < stats->state_num; i++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "%9u: ", stats->freq_table[i]);
for (j = 0; j < stats->state_num; j++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
if (pending)
@@ -157,12 +157,12 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
len += sysfs_emit_at(buf, len, "%9u ", count);
}
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "\n");
}
- if (len >= PAGE_SIZE) {
+ if (len >= PAGE_SIZE - 1) {
pr_warn_once("cpufreq transition table exceeds PAGE_SIZE. Disabling\n");
return -EFBIG;
}
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x ea167a7fc2426f7685c3735e104921c1a20a6d3f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112259-willpower-movable-0aa9@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
ea167a7fc242 ("cpufreq: stats: Fix buffer overflow detection in trans_stats()")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ea167a7fc2426f7685c3735e104921c1a20a6d3f Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth(a)gmail.com>
Date: Tue, 24 Oct 2023 20:30:14 +0200
Subject: [PATCH] cpufreq: stats: Fix buffer overflow detection in
trans_stats()
Commit 3c0897c180c6 ("cpufreq: Use scnprintf() for avoiding potential
buffer overflow") switched from snprintf to the more secure scnprintf
but never updated the exit condition for PAGE_SIZE.
As the commit say and as scnprintf document, what scnprintf returns what
is actually written not counting the '\0' end char. This results in the
case of len exceeding the size, len set to PAGE_SIZE - 1, as it can be
written at max PAGE_SIZE - 1 (as '\0' is not counted)
Because of len is never set to PAGE_SIZE, the function never break early,
never prints the warning and never return -EFBIG.
Fix this by changing the condition to PAGE_SIZE - 1 to correctly trigger
the error.
Cc: 5.10+ <stable(a)vger.kernel.org> # 5.10+
Fixes: 3c0897c180c6 ("cpufreq: Use scnprintf() for avoiding potential buffer overflow")
Signed-off-by: Christian Marangi <ansuelsmth(a)gmail.com>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index a33df3c66c88..40a9ff18da06 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -131,23 +131,23 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
len += sysfs_emit_at(buf, len, " From : To\n");
len += sysfs_emit_at(buf, len, " : ");
for (i = 0; i < stats->state_num; i++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "%9u ", stats->freq_table[i]);
}
- if (len >= PAGE_SIZE)
- return PAGE_SIZE;
+ if (len >= PAGE_SIZE - 1)
+ return PAGE_SIZE - 1;
len += sysfs_emit_at(buf, len, "\n");
for (i = 0; i < stats->state_num; i++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "%9u: ", stats->freq_table[i]);
for (j = 0; j < stats->state_num; j++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
if (pending)
@@ -157,12 +157,12 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
len += sysfs_emit_at(buf, len, "%9u ", count);
}
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "\n");
}
- if (len >= PAGE_SIZE) {
+ if (len >= PAGE_SIZE - 1) {
pr_warn_once("cpufreq transition table exceeds PAGE_SIZE. Disabling\n");
return -EFBIG;
}
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x ea167a7fc2426f7685c3735e104921c1a20a6d3f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112257-imaging-antiviral-52c3@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
ea167a7fc242 ("cpufreq: stats: Fix buffer overflow detection in trans_stats()")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ea167a7fc2426f7685c3735e104921c1a20a6d3f Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth(a)gmail.com>
Date: Tue, 24 Oct 2023 20:30:14 +0200
Subject: [PATCH] cpufreq: stats: Fix buffer overflow detection in
trans_stats()
Commit 3c0897c180c6 ("cpufreq: Use scnprintf() for avoiding potential
buffer overflow") switched from snprintf to the more secure scnprintf
but never updated the exit condition for PAGE_SIZE.
As the commit say and as scnprintf document, what scnprintf returns what
is actually written not counting the '\0' end char. This results in the
case of len exceeding the size, len set to PAGE_SIZE - 1, as it can be
written at max PAGE_SIZE - 1 (as '\0' is not counted)
Because of len is never set to PAGE_SIZE, the function never break early,
never prints the warning and never return -EFBIG.
Fix this by changing the condition to PAGE_SIZE - 1 to correctly trigger
the error.
Cc: 5.10+ <stable(a)vger.kernel.org> # 5.10+
Fixes: 3c0897c180c6 ("cpufreq: Use scnprintf() for avoiding potential buffer overflow")
Signed-off-by: Christian Marangi <ansuelsmth(a)gmail.com>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index a33df3c66c88..40a9ff18da06 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -131,23 +131,23 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
len += sysfs_emit_at(buf, len, " From : To\n");
len += sysfs_emit_at(buf, len, " : ");
for (i = 0; i < stats->state_num; i++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "%9u ", stats->freq_table[i]);
}
- if (len >= PAGE_SIZE)
- return PAGE_SIZE;
+ if (len >= PAGE_SIZE - 1)
+ return PAGE_SIZE - 1;
len += sysfs_emit_at(buf, len, "\n");
for (i = 0; i < stats->state_num; i++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "%9u: ", stats->freq_table[i]);
for (j = 0; j < stats->state_num; j++) {
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
if (pending)
@@ -157,12 +157,12 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
len += sysfs_emit_at(buf, len, "%9u ", count);
}
- if (len >= PAGE_SIZE)
+ if (len >= PAGE_SIZE - 1)
break;
len += sysfs_emit_at(buf, len, "\n");
}
- if (len >= PAGE_SIZE) {
+ if (len >= PAGE_SIZE - 1) {
pr_warn_once("cpufreq transition table exceeds PAGE_SIZE. Disabling\n");
return -EFBIG;
}
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 374de39d38f97b0e58cfee88da590b2d056ccf7f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112258-fancied-capsize-64cb@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
374de39d38f9 ("pmdomain: imx: Make imx pgc power domain also set the fwnode")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 374de39d38f97b0e58cfee88da590b2d056ccf7f Mon Sep 17 00:00:00 2001
From: Pengfei Li <pengfei.li_1(a)nxp.com>
Date: Sat, 21 Oct 2023 02:59:49 +0800
Subject: [PATCH] pmdomain: imx: Make imx pgc power domain also set the fwnode
Currently, The imx pgc power domain doesn't set the fwnode
pointer, which results in supply regulator device can't get
consumer imx pgc power domain device from fwnode when creating
a link.
This causes the driver core to instead try to create a link
between the parent gpc device of imx pgc power domain device and
supply regulator device. However, at this point, the gpc device
has already been bound, and the link creation will fail. So adding
the fwnode pointer to the imx pgc power domain device will fix
this issue.
Signed-off-by: Pengfei Li <pengfei.li_1(a)nxp.com>
Tested-by: Emil Kronborg <emil.kronborg(a)protonmail.com>
Fixes: 3fb16866b51d ("driver core: fw_devlink: Make cycle detection more robust")
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020185949.537083-1-pengfei.li_1@nxp.com
Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org>
diff --git a/drivers/pmdomain/imx/gpc.c b/drivers/pmdomain/imx/gpc.c
index 90a8b2c0676f..419ed15cc10c 100644
--- a/drivers/pmdomain/imx/gpc.c
+++ b/drivers/pmdomain/imx/gpc.c
@@ -498,6 +498,7 @@ static int imx_gpc_probe(struct platform_device *pdev)
pd_pdev->dev.parent = &pdev->dev;
pd_pdev->dev.of_node = np;
+ pd_pdev->dev.fwnode = of_fwnode_handle(np);
ret = platform_device_add(pd_pdev);
if (ret) {
The patch below does not apply to the 6.5-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x 374de39d38f97b0e58cfee88da590b2d056ccf7f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112257-armless-stump-64b8@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
374de39d38f9 ("pmdomain: imx: Make imx pgc power domain also set the fwnode")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 374de39d38f97b0e58cfee88da590b2d056ccf7f Mon Sep 17 00:00:00 2001
From: Pengfei Li <pengfei.li_1(a)nxp.com>
Date: Sat, 21 Oct 2023 02:59:49 +0800
Subject: [PATCH] pmdomain: imx: Make imx pgc power domain also set the fwnode
Currently, The imx pgc power domain doesn't set the fwnode
pointer, which results in supply regulator device can't get
consumer imx pgc power domain device from fwnode when creating
a link.
This causes the driver core to instead try to create a link
between the parent gpc device of imx pgc power domain device and
supply regulator device. However, at this point, the gpc device
has already been bound, and the link creation will fail. So adding
the fwnode pointer to the imx pgc power domain device will fix
this issue.
Signed-off-by: Pengfei Li <pengfei.li_1(a)nxp.com>
Tested-by: Emil Kronborg <emil.kronborg(a)protonmail.com>
Fixes: 3fb16866b51d ("driver core: fw_devlink: Make cycle detection more robust")
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020185949.537083-1-pengfei.li_1@nxp.com
Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org>
diff --git a/drivers/pmdomain/imx/gpc.c b/drivers/pmdomain/imx/gpc.c
index 90a8b2c0676f..419ed15cc10c 100644
--- a/drivers/pmdomain/imx/gpc.c
+++ b/drivers/pmdomain/imx/gpc.c
@@ -498,6 +498,7 @@ static int imx_gpc_probe(struct platform_device *pdev)
pd_pdev->dev.parent = &pdev->dev;
pd_pdev->dev.of_node = np;
+ pd_pdev->dev.fwnode = of_fwnode_handle(np);
ret = platform_device_add(pd_pdev);
if (ret) {
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x 0ec7731655de196bc1e4af99e495b38778109d22
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112217-steersman-frosted-7a48@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
0ec7731655de ("regmap: Ensure range selector registers are updated after cache sync")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 0ec7731655de196bc1e4af99e495b38778109d22 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie(a)kernel.org>
Date: Thu, 26 Oct 2023 16:49:19 +0100
Subject: [PATCH] regmap: Ensure range selector registers are updated after
cache sync
When we sync the register cache we do so with the cache bypassed in order
to avoid overhead from writing the synced values back into the cache. If
the regmap has ranges and the selector register for those ranges is in a
register which is cached this has the unfortunate side effect of meaning
that the physical and cached copies of the selector register can be out of
sync after a cache sync. The cache will have whatever the selector was when
the sync started and the hardware will have the selector for the register
that was synced last.
Fix this by rewriting all cached selector registers after every sync,
ensuring that the hardware and cache have the same content. This will
result in extra writes that wouldn't otherwise be needed but is simple
so hopefully robust. We don't read from the hardware since not all
devices have physical read support.
Given that nobody noticed this until now it is likely that we are rarely if
ever hitting this case.
Reported-by: Hector Martin <marcan(a)marcan.st>
Cc: stable(a)vger.kernel.org
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Link: https://lore.kernel.org/r/20231026-regmap-fix-selector-sync-v1-1-633ded8277…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index c5d151e9c481..92592f944a3d 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -334,6 +334,11 @@ static int regcache_default_sync(struct regmap *map, unsigned int min,
return 0;
}
+static int rbtree_all(const void *key, const struct rb_node *node)
+{
+ return 0;
+}
+
/**
* regcache_sync - Sync the register cache with the hardware.
*
@@ -351,6 +356,7 @@ int regcache_sync(struct regmap *map)
unsigned int i;
const char *name;
bool bypass;
+ struct rb_node *node;
if (WARN_ON(map->cache_type == REGCACHE_NONE))
return -EINVAL;
@@ -392,6 +398,30 @@ int regcache_sync(struct regmap *map)
/* Restore the bypass state */
map->cache_bypass = bypass;
map->no_sync_defaults = false;
+
+ /*
+ * If we did any paging with cache bypassed and a cached
+ * paging register then the register and cache state might
+ * have gone out of sync, force writes of all the paging
+ * registers.
+ */
+ rb_for_each(node, 0, &map->range_tree, rbtree_all) {
+ struct regmap_range_node *this =
+ rb_entry(node, struct regmap_range_node, node);
+
+ /* If there's nothing in the cache there's nothing to sync */
+ ret = regcache_read(map, this->selector_reg, &i);
+ if (ret != 0)
+ continue;
+
+ ret = _regmap_write(map, this->selector_reg, i);
+ if (ret != 0) {
+ dev_err(map->dev, "Failed to write %x = %x: %d\n",
+ this->selector_reg, i, ret);
+ break;
+ }
+ }
+
map->unlock(map->lock_arg);
regmap_async_complete(map);
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x 0ec7731655de196bc1e4af99e495b38778109d22
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112257-fracture-enlisted-b500@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
0ec7731655de ("regmap: Ensure range selector registers are updated after cache sync")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 0ec7731655de196bc1e4af99e495b38778109d22 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie(a)kernel.org>
Date: Thu, 26 Oct 2023 16:49:19 +0100
Subject: [PATCH] regmap: Ensure range selector registers are updated after
cache sync
When we sync the register cache we do so with the cache bypassed in order
to avoid overhead from writing the synced values back into the cache. If
the regmap has ranges and the selector register for those ranges is in a
register which is cached this has the unfortunate side effect of meaning
that the physical and cached copies of the selector register can be out of
sync after a cache sync. The cache will have whatever the selector was when
the sync started and the hardware will have the selector for the register
that was synced last.
Fix this by rewriting all cached selector registers after every sync,
ensuring that the hardware and cache have the same content. This will
result in extra writes that wouldn't otherwise be needed but is simple
so hopefully robust. We don't read from the hardware since not all
devices have physical read support.
Given that nobody noticed this until now it is likely that we are rarely if
ever hitting this case.
Reported-by: Hector Martin <marcan(a)marcan.st>
Cc: stable(a)vger.kernel.org
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Link: https://lore.kernel.org/r/20231026-regmap-fix-selector-sync-v1-1-633ded8277…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index c5d151e9c481..92592f944a3d 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -334,6 +334,11 @@ static int regcache_default_sync(struct regmap *map, unsigned int min,
return 0;
}
+static int rbtree_all(const void *key, const struct rb_node *node)
+{
+ return 0;
+}
+
/**
* regcache_sync - Sync the register cache with the hardware.
*
@@ -351,6 +356,7 @@ int regcache_sync(struct regmap *map)
unsigned int i;
const char *name;
bool bypass;
+ struct rb_node *node;
if (WARN_ON(map->cache_type == REGCACHE_NONE))
return -EINVAL;
@@ -392,6 +398,30 @@ int regcache_sync(struct regmap *map)
/* Restore the bypass state */
map->cache_bypass = bypass;
map->no_sync_defaults = false;
+
+ /*
+ * If we did any paging with cache bypassed and a cached
+ * paging register then the register and cache state might
+ * have gone out of sync, force writes of all the paging
+ * registers.
+ */
+ rb_for_each(node, 0, &map->range_tree, rbtree_all) {
+ struct regmap_range_node *this =
+ rb_entry(node, struct regmap_range_node, node);
+
+ /* If there's nothing in the cache there's nothing to sync */
+ ret = regcache_read(map, this->selector_reg, &i);
+ if (ret != 0)
+ continue;
+
+ ret = _regmap_write(map, this->selector_reg, i);
+ if (ret != 0) {
+ dev_err(map->dev, "Failed to write %x = %x: %d\n",
+ this->selector_reg, i, ret);
+ break;
+ }
+ }
+
map->unlock(map->lock_arg);
regmap_async_complete(map);
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 0ec7731655de196bc1e4af99e495b38778109d22
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112236-grumble-repose-10b5@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
0ec7731655de ("regmap: Ensure range selector registers are updated after cache sync")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 0ec7731655de196bc1e4af99e495b38778109d22 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie(a)kernel.org>
Date: Thu, 26 Oct 2023 16:49:19 +0100
Subject: [PATCH] regmap: Ensure range selector registers are updated after
cache sync
When we sync the register cache we do so with the cache bypassed in order
to avoid overhead from writing the synced values back into the cache. If
the regmap has ranges and the selector register for those ranges is in a
register which is cached this has the unfortunate side effect of meaning
that the physical and cached copies of the selector register can be out of
sync after a cache sync. The cache will have whatever the selector was when
the sync started and the hardware will have the selector for the register
that was synced last.
Fix this by rewriting all cached selector registers after every sync,
ensuring that the hardware and cache have the same content. This will
result in extra writes that wouldn't otherwise be needed but is simple
so hopefully robust. We don't read from the hardware since not all
devices have physical read support.
Given that nobody noticed this until now it is likely that we are rarely if
ever hitting this case.
Reported-by: Hector Martin <marcan(a)marcan.st>
Cc: stable(a)vger.kernel.org
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Link: https://lore.kernel.org/r/20231026-regmap-fix-selector-sync-v1-1-633ded8277…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index c5d151e9c481..92592f944a3d 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -334,6 +334,11 @@ static int regcache_default_sync(struct regmap *map, unsigned int min,
return 0;
}
+static int rbtree_all(const void *key, const struct rb_node *node)
+{
+ return 0;
+}
+
/**
* regcache_sync - Sync the register cache with the hardware.
*
@@ -351,6 +356,7 @@ int regcache_sync(struct regmap *map)
unsigned int i;
const char *name;
bool bypass;
+ struct rb_node *node;
if (WARN_ON(map->cache_type == REGCACHE_NONE))
return -EINVAL;
@@ -392,6 +398,30 @@ int regcache_sync(struct regmap *map)
/* Restore the bypass state */
map->cache_bypass = bypass;
map->no_sync_defaults = false;
+
+ /*
+ * If we did any paging with cache bypassed and a cached
+ * paging register then the register and cache state might
+ * have gone out of sync, force writes of all the paging
+ * registers.
+ */
+ rb_for_each(node, 0, &map->range_tree, rbtree_all) {
+ struct regmap_range_node *this =
+ rb_entry(node, struct regmap_range_node, node);
+
+ /* If there's nothing in the cache there's nothing to sync */
+ ret = regcache_read(map, this->selector_reg, &i);
+ if (ret != 0)
+ continue;
+
+ ret = _regmap_write(map, this->selector_reg, i);
+ if (ret != 0) {
+ dev_err(map->dev, "Failed to write %x = %x: %d\n",
+ this->selector_reg, i, ret);
+ break;
+ }
+ }
+
map->unlock(map->lock_arg);
regmap_async_complete(map);
The patch below does not apply to the 4.109-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.109.y
git checkout FETCH_HEAD
git cherry-pick -x 0ec7731655de196bc1e4af99e495b38778109d22
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112233-huddle-harmony-d181@gregkh' --subject-prefix 'PATCH 4.109.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 0ec7731655de196bc1e4af99e495b38778109d22 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie(a)kernel.org>
Date: Thu, 26 Oct 2023 16:49:19 +0100
Subject: [PATCH] regmap: Ensure range selector registers are updated after
cache sync
When we sync the register cache we do so with the cache bypassed in order
to avoid overhead from writing the synced values back into the cache. If
the regmap has ranges and the selector register for those ranges is in a
register which is cached this has the unfortunate side effect of meaning
that the physical and cached copies of the selector register can be out of
sync after a cache sync. The cache will have whatever the selector was when
the sync started and the hardware will have the selector for the register
that was synced last.
Fix this by rewriting all cached selector registers after every sync,
ensuring that the hardware and cache have the same content. This will
result in extra writes that wouldn't otherwise be needed but is simple
so hopefully robust. We don't read from the hardware since not all
devices have physical read support.
Given that nobody noticed this until now it is likely that we are rarely if
ever hitting this case.
Reported-by: Hector Martin <marcan(a)marcan.st>
Cc: stable(a)vger.kernel.org
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Link: https://lore.kernel.org/r/20231026-regmap-fix-selector-sync-v1-1-633ded8277…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index c5d151e9c481..92592f944a3d 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -334,6 +334,11 @@ static int regcache_default_sync(struct regmap *map, unsigned int min,
return 0;
}
+static int rbtree_all(const void *key, const struct rb_node *node)
+{
+ return 0;
+}
+
/**
* regcache_sync - Sync the register cache with the hardware.
*
@@ -351,6 +356,7 @@ int regcache_sync(struct regmap *map)
unsigned int i;
const char *name;
bool bypass;
+ struct rb_node *node;
if (WARN_ON(map->cache_type == REGCACHE_NONE))
return -EINVAL;
@@ -392,6 +398,30 @@ int regcache_sync(struct regmap *map)
/* Restore the bypass state */
map->cache_bypass = bypass;
map->no_sync_defaults = false;
+
+ /*
+ * If we did any paging with cache bypassed and a cached
+ * paging register then the register and cache state might
+ * have gone out of sync, force writes of all the paging
+ * registers.
+ */
+ rb_for_each(node, 0, &map->range_tree, rbtree_all) {
+ struct regmap_range_node *this =
+ rb_entry(node, struct regmap_range_node, node);
+
+ /* If there's nothing in the cache there's nothing to sync */
+ ret = regcache_read(map, this->selector_reg, &i);
+ if (ret != 0)
+ continue;
+
+ ret = _regmap_write(map, this->selector_reg, i);
+ if (ret != 0) {
+ dev_err(map->dev, "Failed to write %x = %x: %d\n",
+ this->selector_reg, i, ret);
+ break;
+ }
+ }
+
map->unlock(map->lock_arg);
regmap_async_complete(map);
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 0ec7731655de196bc1e4af99e495b38778109d22
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112209-procreate-flop-2437@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
0ec7731655de ("regmap: Ensure range selector registers are updated after cache sync")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 0ec7731655de196bc1e4af99e495b38778109d22 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie(a)kernel.org>
Date: Thu, 26 Oct 2023 16:49:19 +0100
Subject: [PATCH] regmap: Ensure range selector registers are updated after
cache sync
When we sync the register cache we do so with the cache bypassed in order
to avoid overhead from writing the synced values back into the cache. If
the regmap has ranges and the selector register for those ranges is in a
register which is cached this has the unfortunate side effect of meaning
that the physical and cached copies of the selector register can be out of
sync after a cache sync. The cache will have whatever the selector was when
the sync started and the hardware will have the selector for the register
that was synced last.
Fix this by rewriting all cached selector registers after every sync,
ensuring that the hardware and cache have the same content. This will
result in extra writes that wouldn't otherwise be needed but is simple
so hopefully robust. We don't read from the hardware since not all
devices have physical read support.
Given that nobody noticed this until now it is likely that we are rarely if
ever hitting this case.
Reported-by: Hector Martin <marcan(a)marcan.st>
Cc: stable(a)vger.kernel.org
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Link: https://lore.kernel.org/r/20231026-regmap-fix-selector-sync-v1-1-633ded8277…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index c5d151e9c481..92592f944a3d 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -334,6 +334,11 @@ static int regcache_default_sync(struct regmap *map, unsigned int min,
return 0;
}
+static int rbtree_all(const void *key, const struct rb_node *node)
+{
+ return 0;
+}
+
/**
* regcache_sync - Sync the register cache with the hardware.
*
@@ -351,6 +356,7 @@ int regcache_sync(struct regmap *map)
unsigned int i;
const char *name;
bool bypass;
+ struct rb_node *node;
if (WARN_ON(map->cache_type == REGCACHE_NONE))
return -EINVAL;
@@ -392,6 +398,30 @@ int regcache_sync(struct regmap *map)
/* Restore the bypass state */
map->cache_bypass = bypass;
map->no_sync_defaults = false;
+
+ /*
+ * If we did any paging with cache bypassed and a cached
+ * paging register then the register and cache state might
+ * have gone out of sync, force writes of all the paging
+ * registers.
+ */
+ rb_for_each(node, 0, &map->range_tree, rbtree_all) {
+ struct regmap_range_node *this =
+ rb_entry(node, struct regmap_range_node, node);
+
+ /* If there's nothing in the cache there's nothing to sync */
+ ret = regcache_read(map, this->selector_reg, &i);
+ if (ret != 0)
+ continue;
+
+ ret = _regmap_write(map, this->selector_reg, i);
+ if (ret != 0) {
+ dev_err(map->dev, "Failed to write %x = %x: %d\n",
+ this->selector_reg, i, ret);
+ break;
+ }
+ }
+
map->unlock(map->lock_arg);
regmap_async_complete(map);
The patch below does not apply to the 6.5-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y
git checkout FETCH_HEAD
git cherry-pick -x b131329b9bfbd1b4c0c5e088cb0c6ec03a12930f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112207-docile-knoll-50f6@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^..
Possible dependencies:
b131329b9bfb ("pmdomain: amlogic: Fix mask for the second NNA mem PD domain")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From b131329b9bfbd1b4c0c5e088cb0c6ec03a12930f Mon Sep 17 00:00:00 2001
From: Tomeu Vizoso <tomeu(a)tomeuvizoso.net>
Date: Mon, 16 Oct 2023 10:02:04 +0200
Subject: [PATCH] pmdomain: amlogic: Fix mask for the second NNA mem PD domain
Without this change, the NPU hangs when the 8th NN core is used.
It matches what the out-of-tree driver does.
Signed-off-by: Tomeu Vizoso <tomeu(a)tomeuvizoso.net>
Fixes: 9a217b7e8953 ("soc: amlogic: meson-pwrc: Add NNA power domain for A311D")
Acked-by: Neil Armstrong <neil.armstrong(a)linaro.org>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231016080205.41982-2-tomeu@tomeuvizoso.net
Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org>
diff --git a/drivers/pmdomain/amlogic/meson-ee-pwrc.c b/drivers/pmdomain/amlogic/meson-ee-pwrc.c
index cfb796d40d9d..0dd71cd814c5 100644
--- a/drivers/pmdomain/amlogic/meson-ee-pwrc.c
+++ b/drivers/pmdomain/amlogic/meson-ee-pwrc.c
@@ -228,7 +228,7 @@ static struct meson_ee_pwrc_mem_domain sm1_pwrc_mem_audio[] = {
static struct meson_ee_pwrc_mem_domain g12a_pwrc_mem_nna[] = {
{ G12A_HHI_NANOQ_MEM_PD_REG0, GENMASK(31, 0) },
- { G12A_HHI_NANOQ_MEM_PD_REG1, GENMASK(23, 0) },
+ { G12A_HHI_NANOQ_MEM_PD_REG1, GENMASK(31, 0) },
};
#define VPU_PD(__name, __top_pd, __mem, __is_pwr_off, __resets, __clks) \
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 7994db905c0fd692cf04c527585f08a91b560144
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112204-jeeringly-remake-6ff6@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
7994db905c0f ("PCI: keystone: Don't discard .probe() callback")
18b0415bc802 ("PCI: keystone: Add support for PCIe RC in AM654x Platforms")
156c6fef75a4 ("PCI: keystone: Explicitly set the PCIe mode")
b1dee41b7692 ("PCI: keystone: Move resources initialization to prepare for EP support")
2341ab4fd5d7 ("PCI: keystone: Use platform_get_resource_byname() to get memory resources")
f3560a9f88ae ("PCI: keystone: Perform host initialization in a single function")
0790eb175ee0 ("PCI: keystone: Cleanup error_irq configuration")
1146c2953dcb ("PCI: keystone: Add separate functions for configuring MSI and legacy interrupt")
1beb55126937 ("PCI: keystone: Cleanup interrupt related macros")
261de72f0169 ("PCI: keystone: Cleanup macros defined in pci-keystone.c")
c0b8558648c2 ("PCI: keystone: Reorder header file in alphabetical order")
daaaa665ca01 ("PCI: keystone: Add debug error message for all errors")
0523cdc6e775 ("PCI: keystone: Use ERR_IRQ_STATUS instead of ERR_IRQ_STATUS_RAW to get interrupt status")
23fe5bd4be90 ("PCI: keystone: Cleanup ks_pcie_link_up()")
f9127db9fbad ("PCI: keystone: Cleanup set_dbi_mode() and get_dbi_mode()")
e75043ad9792 ("PCI: keystone: Cleanup outbound window configuration")
b4f1af8352fd ("PCI: keystone: Get number of outbound windows from DT")
44c747af2be7 ("PCI: keystone: Cleanup configuration space access")
8047eb55129a ("PCI: keystone: Invoke runtime PM APIs to enable clock")
49229238ab47 ("PCI: keystone: Cleanup PHY handling")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7994db905c0fd692cf04c527585f08a91b560144 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de>
Date: Sun, 1 Oct 2023 19:02:54 +0200
Subject: [PATCH] PCI: keystone: Don't discard .probe() callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The __init annotation makes the ks_pcie_probe() function disappear after
booting completes. However a device can also be bound later. In that case,
we try to call ks_pcie_probe(), but the backing memory is likely already
overwritten.
The right thing to do is do always have the probe callback available. Note
that the (wrong) __refdata annotation prevented this issue to be noticed by
modpost.
Fixes: 0c4ffcfe1fbc ("PCI: keystone: Add TI Keystone PCIe driver")
Link: https://lore.kernel.org/r/20231001170254.2506508-5-u.kleine-koenig@pengutro…
Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index eb3fa17b243f..0def919f89fa 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -1100,7 +1100,7 @@ static const struct of_device_id ks_pcie_of_match[] = {
{ },
};
-static int __init ks_pcie_probe(struct platform_device *pdev)
+static int ks_pcie_probe(struct platform_device *pdev)
{
const struct dw_pcie_host_ops *host_ops;
const struct dw_pcie_ep_ops *ep_ops;
@@ -1318,7 +1318,7 @@ static int ks_pcie_remove(struct platform_device *pdev)
return 0;
}
-static struct platform_driver ks_pcie_driver __refdata = {
+static struct platform_driver ks_pcie_driver = {
.probe = ks_pcie_probe,
.remove = ks_pcie_remove,
.driver = {
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 200bddbb3f5202bbce96444fdc416305de14f547
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112236-scone-stinking-706f@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
200bddbb3f52 ("PCI: keystone: Don't discard .remove() callback")
49229238ab47 ("PCI: keystone: Cleanup PHY handling")
b51a625b784a ("PCI: keystone: Use SYSCON APIs to get device ID from control module")
b492aca35c98 ("PCI: keystone: Merge pci-keystone-dw.c and pci-keystone.c")
1f79f98f0575 ("PCI: keystone: Remove unused argument from ks_dw_pcie_host_init()")
00a2c4094f8e ("PCI: keystone: Use quirk to set MRRS for PCI host bridge")
6e0832fa432e ("PCI: Collect all native drivers under drivers/pci/controller/")
e52d38f4abf4 ("Merge branch 'lorenzo/pci/rockchip'")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 200bddbb3f5202bbce96444fdc416305de14f547 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de>
Date: Sun, 1 Oct 2023 19:02:53 +0200
Subject: [PATCH] PCI: keystone: Don't discard .remove() callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
With CONFIG_PCIE_KEYSTONE=y and ks_pcie_remove() marked with __exit, the
function is discarded from the driver. In this case a bound device can
still get unbound, e.g via sysfs. Then no cleanup code is run resulting in
resource leaks or worse.
The right thing to do is do always have the remove callback available.
Note that this driver cannot be compiled as a module, so ks_pcie_remove()
was always discarded before this change and modpost couldn't warn about
this issue. Furthermore the __ref annotation also prevents a warning.
Fixes: 0c4ffcfe1fbc ("PCI: keystone: Add TI Keystone PCIe driver")
Link: https://lore.kernel.org/r/20231001170254.2506508-4-u.kleine-koenig@pengutro…
Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 49aea6ce3e87..eb3fa17b243f 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -1302,7 +1302,7 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
return ret;
}
-static int __exit ks_pcie_remove(struct platform_device *pdev)
+static int ks_pcie_remove(struct platform_device *pdev)
{
struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
struct device_link **link = ks_pcie->link;
@@ -1320,7 +1320,7 @@ static int __exit ks_pcie_remove(struct platform_device *pdev)
static struct platform_driver ks_pcie_driver __refdata = {
.probe = ks_pcie_probe,
- .remove = __exit_p(ks_pcie_remove),
+ .remove = ks_pcie_remove,
.driver = {
.name = "keystone-pcie",
.of_match_table = ks_pcie_of_match,
max_mapnr variable is utilized in the pfn_valid() method in order to
determine the upper PFN space boundary. Having it uninitialized
effectively makes any PFN passed to that method invalid. That in its turn
causes the kernel mm-subsystem occasion malfunctions even after the
max_mapnr variable is actually properly updated. For instance,
pfn_valid() is called in the init_unavailable_range() method in the
framework of the calls-chain on MIPS:
setup_arch()
+-> paging_init()
+-> free_area_init()
+-> memmap_init()
+-> memmap_init_zone_range()
+-> init_unavailable_range()
Since pfn_valid() always returns "false" value before max_mapnr is
initialized in the mem_init() method, any flatmem page-holes will be left
in the poisoned/uninitialized state including the IO-memory pages. Thus
any further attempts to map/remap the IO-memory by using MMU may fail.
In particular it happened in my case on attempt to map the SRAM region.
The kernel bootup procedure just crashed on the unhandled unaligned access
bug raised in the __update_cache() method:
> Unhandled kernel unaligned access[#1]:
> CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.7.0-rc1-00307-g0dff108838c9-dirty #2056
> ...
> Call Trace:
> [<8011ef9c>] __update_cache+0x88/0x1bc
> [<80385944>] ioremap_page_range+0x110/0x2a4
> [<80126948>] ioremap_prot+0x17c/0x1f4
> [<80711b80>] __devm_ioremap+0x8c/0x120
> [<80711e0c>] __devm_ioremap_resource+0xf4/0x218
> [<808bf244>] sram_probe+0x4f4/0x930
> [<80889d20>] platform_probe+0x68/0xec
> ...
Let's fix the problem by initializing the max_mapnr variable as soon as
the required data is available. In particular it can be done right in the
paging_init() method before free_area_init() is called since all the PFN
zone boundaries have already been calculated by that time.
Cc: stable(a)vger.kernel.org
Signed-off-by: Serge Semin <fancer.lancer(a)gmail.com>
---
Note I don't really know since what point that problem actually exists.
Based on the commits log it might had been persistent even before the
boot_mem_map allocator was dropped. On the other hand I hadn't seen it
actually come out before moving my working tree from kernel 6.5-rc4 to
6.7-rc1. So after updating the kernel I got the unhandled unaligned access
BUG() due to the access to compound head pointer the __update_cache()
method (see the commit log). After enabling the DEBUG_VM config I managed
to find out that the IO-memory pages were just left uninitialized and
poisoned:
> page:81367080 is uninitialized and poisoned (pfn 8192)
> page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p))
> Kernel bug detected[#1]:
> CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.7.0-rc1-00298-g88721b1a9ad5-dirty
> $ 0 : 00000000 812d0000 00000034 dced7cdf
> $ 4 : dced7cdf 00594000 10000000 ffff00fe
> $ 8 : 8196bfe0 00000000 00000001 818458c0
> $12 : 00000000 00000000 00000000 00000216
> $16 : 00002800 81227b80 00000000 00000000
> $20 : 00000000 00000000 00000000 00000000
> $24 : 0000022b 818458c0
> $28 : 81968000 8196be68 00000000 803a0920
> Hi : 00000000
> Lo : 00000000
> epc : 8039d2a4 BUG+0x0/0x4
> ra : 803a0920 post_alloc_hook+0x0/0x128
> Status: 10000003 KERNEL EXL IE
> Cause : 00800424 (ExcCode 09)
> PrId : 0001a830 (MIPS P5600)
> Modules linked in:
> Process swapper/0 (pid: 1, threadinfo=81968000, task=819a0000, tls=00000000)
> Stack : 00000000 8101ccb0 00000000 8196bd00 00000000 80359768 818a8300 00000001
> 81139088 8114438c 8042e4f8 81297a2c 81297a2c 81255e90 819a1b50 dced7cdf
> 81297a2c 81297a2c 00000000 81227b80 00000000 81241168 811394b0 00000000
> 81140000 80e2cee0 00000000 00000000 00000000 00000000 00000000 819b0000
> 81140000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
> ...
> Call Trace:
> [<8039d2a4>] BUG+0x0/0x4
> [<803a0920>] post_alloc_hook+0x0/0x128
>
> Code: 01001025 03e00008 24020001 <000c000d> 2403003c 27bdffd0 afb2001c 3c12812f 8e4269e4
Which in its turn made me digging deeper into the way the MMIO-space pages
are initialized. That's how I got into the pfn_valid() and
init_unavailable_range() working improperly on my setup.
Anyway none of the problems above I spotted on kernel 6.5-rc4. So what
actually triggered having them finally popped up isn't that easy to be
foundn seeing the involved code hasn't changed much.
---
arch/mips/mm/init.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 5dcb525a8995..6e368a4658b5 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -422,7 +422,12 @@ void __init paging_init(void)
(highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10));
max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn;
}
+
+ max_mapnr = highend_pfn ? highend_pfn : max_low_pfn;
+#else
+ max_mapnr = max_low_pfn;
#endif
+ high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
free_area_init(max_zone_pfns);
}
@@ -458,13 +463,6 @@ void __init mem_init(void)
*/
BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT));
-#ifdef CONFIG_HIGHMEM
- max_mapnr = highend_pfn ? highend_pfn : max_low_pfn;
-#else
- max_mapnr = max_low_pfn;
-#endif
- high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-
maar_init();
memblock_free_all();
setup_zero_pages(); /* Setup zeroed pages. */
--
2.42.1
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x ef5dd8ec88ac11e8e353164407d55b73c988b369
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112214-slaw-bootlace-8f7a@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
ef5dd8ec88ac ("hvc/xen: fix event channel handling for secondary consoles")
fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
3bd5371a4da6 ("xen/events: Remove unused bind_evtchn_to_irq_lateeoi()")
54c9de89895e ("xen/events: add a new "late EOI" evtchn framework")
0102e4efda76 ("xen: Use evtchn_type_t as a type for event channels")
bce5963bcb4f ("xen/events: fix binding user event channels to cpus")
9f51c05dc41a ("pvcalls-front: Avoid get_free_pages(GFP_KERNEL) under spinlock")
975ef94a0284 ("pvcalls-front: fixes incorrect error handling")
1d3145675538 ("xen/gntdev: Make private routines/structures accessible")
975ef7ff81bb ("xen/gntdev: Allow mappings for DMA buffers")
64d6871827b1 ("pvcalls-front: introduce a per sock_mapping refcount")
a9a08845e9ac ("vfs: do bulk POLL* -> EPOLL* replacement")
68c5735eaa5e ("Merge tag 'media/v4.16-2' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef5dd8ec88ac11e8e353164407d55b73c988b369 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw(a)amazon.co.uk>
Date: Fri, 20 Oct 2023 17:15:27 +0100
Subject: [PATCH] hvc/xen: fix event channel handling for secondary consoles
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The xencons_connect_backend() function allocates a local interdomain
event channel with xenbus_alloc_evtchn(), then calls
bind_interdomain_evtchn_to_irq_lateeoi() to bind to that port# on the
*remote* domain.
That doesn't work very well:
(qemu) device_add xen-console,id=con1,chardev=pty0
[ 44.323872] xenconsole console-1: 2 xenbus_dev_probe on device/console/1
[ 44.323995] xenconsole: probe of console-1 failed with error -2
Fix it to use bind_evtchn_to_irq_lateeoi(), which does the right thing
by just binding that *local* event channel to an irq. The backend will
do the interdomain binding.
This didn't affect the primary console because the setup for that is
special — the toolstack allocates the guest event channel and the guest
discovers it with HVMOP_get_param.
Fixes: fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020161529.355083-2-dwmw2@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 98764e740c07..f24e285b6441 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -433,7 +433,7 @@ static int xencons_connect_backend(struct xenbus_device *dev,
if (ret)
return ret;
info->evtchn = evtchn;
- irq = bind_interdomain_evtchn_to_irq_lateeoi(dev, evtchn);
+ irq = bind_evtchn_to_irq_lateeoi(evtchn);
if (irq < 0)
return irq;
info->irq = irq;
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x ef5dd8ec88ac11e8e353164407d55b73c988b369
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112213-ladybug-starter-d2c2@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
ef5dd8ec88ac ("hvc/xen: fix event channel handling for secondary consoles")
fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
3bd5371a4da6 ("xen/events: Remove unused bind_evtchn_to_irq_lateeoi()")
54c9de89895e ("xen/events: add a new "late EOI" evtchn framework")
0102e4efda76 ("xen: Use evtchn_type_t as a type for event channels")
bce5963bcb4f ("xen/events: fix binding user event channels to cpus")
9f51c05dc41a ("pvcalls-front: Avoid get_free_pages(GFP_KERNEL) under spinlock")
975ef94a0284 ("pvcalls-front: fixes incorrect error handling")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef5dd8ec88ac11e8e353164407d55b73c988b369 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw(a)amazon.co.uk>
Date: Fri, 20 Oct 2023 17:15:27 +0100
Subject: [PATCH] hvc/xen: fix event channel handling for secondary consoles
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The xencons_connect_backend() function allocates a local interdomain
event channel with xenbus_alloc_evtchn(), then calls
bind_interdomain_evtchn_to_irq_lateeoi() to bind to that port# on the
*remote* domain.
That doesn't work very well:
(qemu) device_add xen-console,id=con1,chardev=pty0
[ 44.323872] xenconsole console-1: 2 xenbus_dev_probe on device/console/1
[ 44.323995] xenconsole: probe of console-1 failed with error -2
Fix it to use bind_evtchn_to_irq_lateeoi(), which does the right thing
by just binding that *local* event channel to an irq. The backend will
do the interdomain binding.
This didn't affect the primary console because the setup for that is
special — the toolstack allocates the guest event channel and the guest
discovers it with HVMOP_get_param.
Fixes: fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020161529.355083-2-dwmw2@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 98764e740c07..f24e285b6441 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -433,7 +433,7 @@ static int xencons_connect_backend(struct xenbus_device *dev,
if (ret)
return ret;
info->evtchn = evtchn;
- irq = bind_interdomain_evtchn_to_irq_lateeoi(dev, evtchn);
+ irq = bind_evtchn_to_irq_lateeoi(evtchn);
if (irq < 0)
return irq;
info->irq = irq;
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x ef5dd8ec88ac11e8e353164407d55b73c988b369
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112211-papyrus-december-999f@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
ef5dd8ec88ac ("hvc/xen: fix event channel handling for secondary consoles")
fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
3bd5371a4da6 ("xen/events: Remove unused bind_evtchn_to_irq_lateeoi()")
54c9de89895e ("xen/events: add a new "late EOI" evtchn framework")
0102e4efda76 ("xen: Use evtchn_type_t as a type for event channels")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef5dd8ec88ac11e8e353164407d55b73c988b369 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw(a)amazon.co.uk>
Date: Fri, 20 Oct 2023 17:15:27 +0100
Subject: [PATCH] hvc/xen: fix event channel handling for secondary consoles
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The xencons_connect_backend() function allocates a local interdomain
event channel with xenbus_alloc_evtchn(), then calls
bind_interdomain_evtchn_to_irq_lateeoi() to bind to that port# on the
*remote* domain.
That doesn't work very well:
(qemu) device_add xen-console,id=con1,chardev=pty0
[ 44.323872] xenconsole console-1: 2 xenbus_dev_probe on device/console/1
[ 44.323995] xenconsole: probe of console-1 failed with error -2
Fix it to use bind_evtchn_to_irq_lateeoi(), which does the right thing
by just binding that *local* event channel to an irq. The backend will
do the interdomain binding.
This didn't affect the primary console because the setup for that is
special — the toolstack allocates the guest event channel and the guest
discovers it with HVMOP_get_param.
Fixes: fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020161529.355083-2-dwmw2@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 98764e740c07..f24e285b6441 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -433,7 +433,7 @@ static int xencons_connect_backend(struct xenbus_device *dev,
if (ret)
return ret;
info->evtchn = evtchn;
- irq = bind_interdomain_evtchn_to_irq_lateeoi(dev, evtchn);
+ irq = bind_evtchn_to_irq_lateeoi(evtchn);
if (irq < 0)
return irq;
info->irq = irq;
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x ef5dd8ec88ac11e8e353164407d55b73c988b369
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112210-salt-repossess-a9d7@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
ef5dd8ec88ac ("hvc/xen: fix event channel handling for secondary consoles")
fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
3bd5371a4da6 ("xen/events: Remove unused bind_evtchn_to_irq_lateeoi()")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ef5dd8ec88ac11e8e353164407d55b73c988b369 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw(a)amazon.co.uk>
Date: Fri, 20 Oct 2023 17:15:27 +0100
Subject: [PATCH] hvc/xen: fix event channel handling for secondary consoles
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The xencons_connect_backend() function allocates a local interdomain
event channel with xenbus_alloc_evtchn(), then calls
bind_interdomain_evtchn_to_irq_lateeoi() to bind to that port# on the
*remote* domain.
That doesn't work very well:
(qemu) device_add xen-console,id=con1,chardev=pty0
[ 44.323872] xenconsole console-1: 2 xenbus_dev_probe on device/console/1
[ 44.323995] xenconsole: probe of console-1 failed with error -2
Fix it to use bind_evtchn_to_irq_lateeoi(), which does the right thing
by just binding that *local* event channel to an irq. The backend will
do the interdomain binding.
This didn't affect the primary console because the setup for that is
special — the toolstack allocates the guest event channel and the guest
discovers it with HVMOP_get_param.
Fixes: fe415186b43d ("xen/console: harden hvc_xen against event channel storms")
Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020161529.355083-2-dwmw2@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 98764e740c07..f24e285b6441 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -433,7 +433,7 @@ static int xencons_connect_backend(struct xenbus_device *dev,
if (ret)
return ret;
info->evtchn = evtchn;
- irq = bind_interdomain_evtchn_to_irq_lateeoi(dev, evtchn);
+ irq = bind_evtchn_to_irq_lateeoi(evtchn);
if (irq < 0)
return irq;
info->irq = irq;
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x a30badfd7c13fc8763a9e10c5a12ba7f81515a55
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112233-haggler-coma-5bfd@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
a30badfd7c13 ("hvc/xen: fix console unplug")
df561f6688fe ("treewide: Use fallthrough pseudo-keyword")
37711e5e2325 ("Merge tag 'nfs-for-5.9-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a30badfd7c13fc8763a9e10c5a12ba7f81515a55 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw(a)amazon.co.uk>
Date: Fri, 20 Oct 2023 17:15:29 +0100
Subject: [PATCH] hvc/xen: fix console unplug
On unplug of a Xen console, xencons_disconnect_backend() unconditionally
calls free_irq() via unbind_from_irqhandler(), causing a warning of
freeing an already-free IRQ:
(qemu) device_del con1
[ 32.050919] ------------[ cut here ]------------
[ 32.050942] Trying to free already-free IRQ 33
[ 32.050990] WARNING: CPU: 0 PID: 51 at kernel/irq/manage.c:1895 __free_irq+0x1d4/0x330
It should be using evtchn_put() to tear down the event channel binding,
and let the Linux IRQ side of it be handled by notifier_del_irq() through
the HVC code.
On which topic... xencons_disconnect_backend() should call hvc_remove()
*first*, rather than tearing down the event channel and grant mapping
while they are in use. And then the IRQ is guaranteed to be freed by
the time it's torn down by evtchn_put().
Since evtchn_put() also closes the actual event channel, avoid calling
xenbus_free_evtchn() except in the failure path where the IRQ was not
successfully set up.
However, calling hvc_remove() at the start of xencons_disconnect_backend()
still isn't early enough. An unplug request is indicated by the backend
setting its state to XenbusStateClosing, which triggers a notification
to xencons_backend_changed(), which... does nothing except set its own
frontend state directly to XenbusStateClosed without *actually* tearing
down the HVC device or, you know, making sure it isn't actively in use.
So the backend sees the guest frontend set its state to XenbusStateClosed
and stops servicing the interrupt... and the guest spins for ever in the
domU_write_console() function waiting for the ring to drain.
Fix that one by calling hvc_remove() from xencons_backend_changed() before
signalling to the backend that it's OK to proceed with the removal.
Tested with 'dd if=/dev/zero of=/dev/hvc1' while telling Qemu to remove
the console device.
Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020161529.355083-4-dwmw2@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 4a768b504263..34c01874f45b 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -377,18 +377,21 @@ void xen_console_resume(void)
#ifdef CONFIG_HVC_XEN_FRONTEND
static void xencons_disconnect_backend(struct xencons_info *info)
{
- if (info->irq > 0)
- unbind_from_irqhandler(info->irq, NULL);
- info->irq = 0;
+ if (info->hvc != NULL)
+ hvc_remove(info->hvc);
+ info->hvc = NULL;
+ if (info->irq > 0) {
+ evtchn_put(info->evtchn);
+ info->irq = 0;
+ info->evtchn = 0;
+ }
+ /* evtchn_put() will also close it so this is only an error path */
if (info->evtchn > 0)
xenbus_free_evtchn(info->xbdev, info->evtchn);
info->evtchn = 0;
if (info->gntref > 0)
gnttab_free_grant_references(info->gntref);
info->gntref = 0;
- if (info->hvc != NULL)
- hvc_remove(info->hvc);
- info->hvc = NULL;
}
static void xencons_free(struct xencons_info *info)
@@ -553,10 +556,23 @@ static void xencons_backend_changed(struct xenbus_device *dev,
if (dev->state == XenbusStateClosed)
break;
fallthrough; /* Missed the backend's CLOSING state */
- case XenbusStateClosing:
+ case XenbusStateClosing: {
+ struct xencons_info *info = dev_get_drvdata(&dev->dev);;
+
+ /*
+ * Don't tear down the evtchn and grant ref before the other
+ * end has disconnected, but do stop userspace from trying
+ * to use the device before we allow the backend to close.
+ */
+ if (info->hvc) {
+ hvc_remove(info->hvc);
+ info->hvc = NULL;
+ }
+
xenbus_frontend_closed(dev);
break;
}
+ }
}
static const struct xenbus_device_id xencons_ids[] = {
@@ -616,7 +632,7 @@ static int __init xen_hvc_init(void)
list_del(&info->list);
spin_unlock_irqrestore(&xencons_lock, flags);
if (info->irq)
- unbind_from_irqhandler(info->irq, NULL);
+ evtchn_put(info->evtchn);
kfree(info);
return r;
}
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x a30badfd7c13fc8763a9e10c5a12ba7f81515a55
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112231-graves-congress-59af@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
a30badfd7c13 ("hvc/xen: fix console unplug")
df561f6688fe ("treewide: Use fallthrough pseudo-keyword")
37711e5e2325 ("Merge tag 'nfs-for-5.9-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a30badfd7c13fc8763a9e10c5a12ba7f81515a55 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw(a)amazon.co.uk>
Date: Fri, 20 Oct 2023 17:15:29 +0100
Subject: [PATCH] hvc/xen: fix console unplug
On unplug of a Xen console, xencons_disconnect_backend() unconditionally
calls free_irq() via unbind_from_irqhandler(), causing a warning of
freeing an already-free IRQ:
(qemu) device_del con1
[ 32.050919] ------------[ cut here ]------------
[ 32.050942] Trying to free already-free IRQ 33
[ 32.050990] WARNING: CPU: 0 PID: 51 at kernel/irq/manage.c:1895 __free_irq+0x1d4/0x330
It should be using evtchn_put() to tear down the event channel binding,
and let the Linux IRQ side of it be handled by notifier_del_irq() through
the HVC code.
On which topic... xencons_disconnect_backend() should call hvc_remove()
*first*, rather than tearing down the event channel and grant mapping
while they are in use. And then the IRQ is guaranteed to be freed by
the time it's torn down by evtchn_put().
Since evtchn_put() also closes the actual event channel, avoid calling
xenbus_free_evtchn() except in the failure path where the IRQ was not
successfully set up.
However, calling hvc_remove() at the start of xencons_disconnect_backend()
still isn't early enough. An unplug request is indicated by the backend
setting its state to XenbusStateClosing, which triggers a notification
to xencons_backend_changed(), which... does nothing except set its own
frontend state directly to XenbusStateClosed without *actually* tearing
down the HVC device or, you know, making sure it isn't actively in use.
So the backend sees the guest frontend set its state to XenbusStateClosed
and stops servicing the interrupt... and the guest spins for ever in the
domU_write_console() function waiting for the ring to drain.
Fix that one by calling hvc_remove() from xencons_backend_changed() before
signalling to the backend that it's OK to proceed with the removal.
Tested with 'dd if=/dev/zero of=/dev/hvc1' while telling Qemu to remove
the console device.
Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020161529.355083-4-dwmw2@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 4a768b504263..34c01874f45b 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -377,18 +377,21 @@ void xen_console_resume(void)
#ifdef CONFIG_HVC_XEN_FRONTEND
static void xencons_disconnect_backend(struct xencons_info *info)
{
- if (info->irq > 0)
- unbind_from_irqhandler(info->irq, NULL);
- info->irq = 0;
+ if (info->hvc != NULL)
+ hvc_remove(info->hvc);
+ info->hvc = NULL;
+ if (info->irq > 0) {
+ evtchn_put(info->evtchn);
+ info->irq = 0;
+ info->evtchn = 0;
+ }
+ /* evtchn_put() will also close it so this is only an error path */
if (info->evtchn > 0)
xenbus_free_evtchn(info->xbdev, info->evtchn);
info->evtchn = 0;
if (info->gntref > 0)
gnttab_free_grant_references(info->gntref);
info->gntref = 0;
- if (info->hvc != NULL)
- hvc_remove(info->hvc);
- info->hvc = NULL;
}
static void xencons_free(struct xencons_info *info)
@@ -553,10 +556,23 @@ static void xencons_backend_changed(struct xenbus_device *dev,
if (dev->state == XenbusStateClosed)
break;
fallthrough; /* Missed the backend's CLOSING state */
- case XenbusStateClosing:
+ case XenbusStateClosing: {
+ struct xencons_info *info = dev_get_drvdata(&dev->dev);;
+
+ /*
+ * Don't tear down the evtchn and grant ref before the other
+ * end has disconnected, but do stop userspace from trying
+ * to use the device before we allow the backend to close.
+ */
+ if (info->hvc) {
+ hvc_remove(info->hvc);
+ info->hvc = NULL;
+ }
+
xenbus_frontend_closed(dev);
break;
}
+ }
}
static const struct xenbus_device_id xencons_ids[] = {
@@ -616,7 +632,7 @@ static int __init xen_hvc_init(void)
list_del(&info->list);
spin_unlock_irqrestore(&xencons_lock, flags);
if (info->irq)
- unbind_from_irqhandler(info->irq, NULL);
+ evtchn_put(info->evtchn);
kfree(info);
return r;
}
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x a30badfd7c13fc8763a9e10c5a12ba7f81515a55
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112229-slicing-deceiving-2f7c@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
a30badfd7c13 ("hvc/xen: fix console unplug")
df561f6688fe ("treewide: Use fallthrough pseudo-keyword")
37711e5e2325 ("Merge tag 'nfs-for-5.9-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a30badfd7c13fc8763a9e10c5a12ba7f81515a55 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw(a)amazon.co.uk>
Date: Fri, 20 Oct 2023 17:15:29 +0100
Subject: [PATCH] hvc/xen: fix console unplug
On unplug of a Xen console, xencons_disconnect_backend() unconditionally
calls free_irq() via unbind_from_irqhandler(), causing a warning of
freeing an already-free IRQ:
(qemu) device_del con1
[ 32.050919] ------------[ cut here ]------------
[ 32.050942] Trying to free already-free IRQ 33
[ 32.050990] WARNING: CPU: 0 PID: 51 at kernel/irq/manage.c:1895 __free_irq+0x1d4/0x330
It should be using evtchn_put() to tear down the event channel binding,
and let the Linux IRQ side of it be handled by notifier_del_irq() through
the HVC code.
On which topic... xencons_disconnect_backend() should call hvc_remove()
*first*, rather than tearing down the event channel and grant mapping
while they are in use. And then the IRQ is guaranteed to be freed by
the time it's torn down by evtchn_put().
Since evtchn_put() also closes the actual event channel, avoid calling
xenbus_free_evtchn() except in the failure path where the IRQ was not
successfully set up.
However, calling hvc_remove() at the start of xencons_disconnect_backend()
still isn't early enough. An unplug request is indicated by the backend
setting its state to XenbusStateClosing, which triggers a notification
to xencons_backend_changed(), which... does nothing except set its own
frontend state directly to XenbusStateClosed without *actually* tearing
down the HVC device or, you know, making sure it isn't actively in use.
So the backend sees the guest frontend set its state to XenbusStateClosed
and stops servicing the interrupt... and the guest spins for ever in the
domU_write_console() function waiting for the ring to drain.
Fix that one by calling hvc_remove() from xencons_backend_changed() before
signalling to the backend that it's OK to proceed with the removal.
Tested with 'dd if=/dev/zero of=/dev/hvc1' while telling Qemu to remove
the console device.
Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20231020161529.355083-4-dwmw2@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 4a768b504263..34c01874f45b 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -377,18 +377,21 @@ void xen_console_resume(void)
#ifdef CONFIG_HVC_XEN_FRONTEND
static void xencons_disconnect_backend(struct xencons_info *info)
{
- if (info->irq > 0)
- unbind_from_irqhandler(info->irq, NULL);
- info->irq = 0;
+ if (info->hvc != NULL)
+ hvc_remove(info->hvc);
+ info->hvc = NULL;
+ if (info->irq > 0) {
+ evtchn_put(info->evtchn);
+ info->irq = 0;
+ info->evtchn = 0;
+ }
+ /* evtchn_put() will also close it so this is only an error path */
if (info->evtchn > 0)
xenbus_free_evtchn(info->xbdev, info->evtchn);
info->evtchn = 0;
if (info->gntref > 0)
gnttab_free_grant_references(info->gntref);
info->gntref = 0;
- if (info->hvc != NULL)
- hvc_remove(info->hvc);
- info->hvc = NULL;
}
static void xencons_free(struct xencons_info *info)
@@ -553,10 +556,23 @@ static void xencons_backend_changed(struct xenbus_device *dev,
if (dev->state == XenbusStateClosed)
break;
fallthrough; /* Missed the backend's CLOSING state */
- case XenbusStateClosing:
+ case XenbusStateClosing: {
+ struct xencons_info *info = dev_get_drvdata(&dev->dev);;
+
+ /*
+ * Don't tear down the evtchn and grant ref before the other
+ * end has disconnected, but do stop userspace from trying
+ * to use the device before we allow the backend to close.
+ */
+ if (info->hvc) {
+ hvc_remove(info->hvc);
+ info->hvc = NULL;
+ }
+
xenbus_frontend_closed(dev);
break;
}
+ }
}
static const struct xenbus_device_id xencons_ids[] = {
@@ -616,7 +632,7 @@ static int __init xen_hvc_init(void)
list_del(&info->list);
spin_unlock_irqrestore(&xencons_lock, flags);
if (info->irq)
- unbind_from_irqhandler(info->irq, NULL);
+ evtchn_put(info->evtchn);
kfree(info);
return r;
}
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x bfa993b355d33a438a746523e7129391c8664e8a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112215-letter-postwar-91df@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
bfa993b355d3 ("acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0")
a4a7644c1509 ("x86/xen: move paravirt lazy code")
9bd0c413b90c ("Merge branch 'acpi-processor'")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From bfa993b355d33a438a746523e7129391c8664e8a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau(a)citrix.com>
Date: Wed, 8 Nov 2023 16:25:15 -0500
Subject: [PATCH] acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The Processor capability bits notify ACPI of the OS capabilities, and
so ACPI can adjust the return of other Processor methods taking the OS
capabilities into account.
When Linux is running as a Xen dom0, the hypervisor is the entity
in charge of processor power management, and hence Xen needs to make
sure the capabilities reported by _OSC/_PDC match the capabilities of
the driver in Xen.
Introduce a small helper to sanitize the buffer when running as Xen
dom0.
When Xen supports HWP, this serves as the equivalent of commit
a21211672c9a ("ACPI / processor: Request native thermal interrupt
handling via _OSC") to avoid SMM crashes. Xen will set bit
ACPI_PROC_CAP_COLLAB_PROC_PERF (bit 12) in the capability bits and the
_OSC/_PDC call will apply it.
[ jandryuk: Mention Xen HWP's need. Support _OSC & _PDC ]
Signed-off-by: Roger Pau Monné <roger.pau(a)citrix.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Jason Andryuk <jandryuk(a)gmail.com>
Reviewed-by: Michal Wilczynski <michal.wilczynski(a)intel.com>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Link: https://lore.kernel.org/r/20231108212517.72279-1-jandryuk@gmail.com
Signed-off-by: Juergen Gross <jgross(a)suse.com>
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
#include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
if (!cpu_has(c, X86_FEATURE_MWAIT) ||
boot_option_idle_override == IDLE_NOMWAIT)
*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+ if (xen_initial_domain()) {
+ /*
+ * When Linux is running as Xen dom0, the hypervisor is the
+ * entity in charge of the processor power management, and so
+ * Xen needs to check the OS capabilities reported in the
+ * processor capabilities buffer matches what the hypervisor
+ * driver supports.
+ */
+ xen_sanitize_proc_cap_bits(cap);
+ }
}
static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
enum xen_lazy_mode xen_get_lazy_mode(void);
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+ BUG();
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3..508655273145 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
/*
* @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
return online;
}
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+ int ret;
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+ ret = HYPERVISOR_platform_op(&op);
+ if (ret)
+ pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+ ret);
+ else
+ *cap = buf[2];
+}
#endif
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x bfa993b355d33a438a746523e7129391c8664e8a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112213-control-spent-ad42@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
bfa993b355d3 ("acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0")
a4a7644c1509 ("x86/xen: move paravirt lazy code")
9bd0c413b90c ("Merge branch 'acpi-processor'")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From bfa993b355d33a438a746523e7129391c8664e8a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau(a)citrix.com>
Date: Wed, 8 Nov 2023 16:25:15 -0500
Subject: [PATCH] acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The Processor capability bits notify ACPI of the OS capabilities, and
so ACPI can adjust the return of other Processor methods taking the OS
capabilities into account.
When Linux is running as a Xen dom0, the hypervisor is the entity
in charge of processor power management, and hence Xen needs to make
sure the capabilities reported by _OSC/_PDC match the capabilities of
the driver in Xen.
Introduce a small helper to sanitize the buffer when running as Xen
dom0.
When Xen supports HWP, this serves as the equivalent of commit
a21211672c9a ("ACPI / processor: Request native thermal interrupt
handling via _OSC") to avoid SMM crashes. Xen will set bit
ACPI_PROC_CAP_COLLAB_PROC_PERF (bit 12) in the capability bits and the
_OSC/_PDC call will apply it.
[ jandryuk: Mention Xen HWP's need. Support _OSC & _PDC ]
Signed-off-by: Roger Pau Monné <roger.pau(a)citrix.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Jason Andryuk <jandryuk(a)gmail.com>
Reviewed-by: Michal Wilczynski <michal.wilczynski(a)intel.com>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Link: https://lore.kernel.org/r/20231108212517.72279-1-jandryuk@gmail.com
Signed-off-by: Juergen Gross <jgross(a)suse.com>
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
#include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
if (!cpu_has(c, X86_FEATURE_MWAIT) ||
boot_option_idle_override == IDLE_NOMWAIT)
*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+ if (xen_initial_domain()) {
+ /*
+ * When Linux is running as Xen dom0, the hypervisor is the
+ * entity in charge of the processor power management, and so
+ * Xen needs to check the OS capabilities reported in the
+ * processor capabilities buffer matches what the hypervisor
+ * driver supports.
+ */
+ xen_sanitize_proc_cap_bits(cap);
+ }
}
static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
enum xen_lazy_mode xen_get_lazy_mode(void);
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+ BUG();
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3..508655273145 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
/*
* @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
return online;
}
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+ int ret;
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+ ret = HYPERVISOR_platform_op(&op);
+ if (ret)
+ pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+ ret);
+ else
+ *cap = buf[2];
+}
#endif
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y
git checkout FETCH_HEAD
git cherry-pick -x bfa993b355d33a438a746523e7129391c8664e8a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112212-yoyo-stoplight-03b7@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^..
Possible dependencies:
bfa993b355d3 ("acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0")
a4a7644c1509 ("x86/xen: move paravirt lazy code")
9bd0c413b90c ("Merge branch 'acpi-processor'")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From bfa993b355d33a438a746523e7129391c8664e8a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau(a)citrix.com>
Date: Wed, 8 Nov 2023 16:25:15 -0500
Subject: [PATCH] acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The Processor capability bits notify ACPI of the OS capabilities, and
so ACPI can adjust the return of other Processor methods taking the OS
capabilities into account.
When Linux is running as a Xen dom0, the hypervisor is the entity
in charge of processor power management, and hence Xen needs to make
sure the capabilities reported by _OSC/_PDC match the capabilities of
the driver in Xen.
Introduce a small helper to sanitize the buffer when running as Xen
dom0.
When Xen supports HWP, this serves as the equivalent of commit
a21211672c9a ("ACPI / processor: Request native thermal interrupt
handling via _OSC") to avoid SMM crashes. Xen will set bit
ACPI_PROC_CAP_COLLAB_PROC_PERF (bit 12) in the capability bits and the
_OSC/_PDC call will apply it.
[ jandryuk: Mention Xen HWP's need. Support _OSC & _PDC ]
Signed-off-by: Roger Pau Monné <roger.pau(a)citrix.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Jason Andryuk <jandryuk(a)gmail.com>
Reviewed-by: Michal Wilczynski <michal.wilczynski(a)intel.com>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Link: https://lore.kernel.org/r/20231108212517.72279-1-jandryuk@gmail.com
Signed-off-by: Juergen Gross <jgross(a)suse.com>
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
#include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
if (!cpu_has(c, X86_FEATURE_MWAIT) ||
boot_option_idle_override == IDLE_NOMWAIT)
*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+ if (xen_initial_domain()) {
+ /*
+ * When Linux is running as Xen dom0, the hypervisor is the
+ * entity in charge of the processor power management, and so
+ * Xen needs to check the OS capabilities reported in the
+ * processor capabilities buffer matches what the hypervisor
+ * driver supports.
+ */
+ xen_sanitize_proc_cap_bits(cap);
+ }
}
static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
enum xen_lazy_mode xen_get_lazy_mode(void);
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+ BUG();
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3..508655273145 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
/*
* @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
return online;
}
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+ int ret;
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+ ret = HYPERVISOR_platform_op(&op);
+ if (ret)
+ pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+ ret);
+ else
+ *cap = buf[2];
+}
#endif
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y
git checkout FETCH_HEAD
git cherry-pick -x bfa993b355d33a438a746523e7129391c8664e8a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112211-ludicrous-enviable-d7eb@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^..
Possible dependencies:
bfa993b355d3 ("acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0")
a4a7644c1509 ("x86/xen: move paravirt lazy code")
9bd0c413b90c ("Merge branch 'acpi-processor'")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From bfa993b355d33a438a746523e7129391c8664e8a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau(a)citrix.com>
Date: Wed, 8 Nov 2023 16:25:15 -0500
Subject: [PATCH] acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The Processor capability bits notify ACPI of the OS capabilities, and
so ACPI can adjust the return of other Processor methods taking the OS
capabilities into account.
When Linux is running as a Xen dom0, the hypervisor is the entity
in charge of processor power management, and hence Xen needs to make
sure the capabilities reported by _OSC/_PDC match the capabilities of
the driver in Xen.
Introduce a small helper to sanitize the buffer when running as Xen
dom0.
When Xen supports HWP, this serves as the equivalent of commit
a21211672c9a ("ACPI / processor: Request native thermal interrupt
handling via _OSC") to avoid SMM crashes. Xen will set bit
ACPI_PROC_CAP_COLLAB_PROC_PERF (bit 12) in the capability bits and the
_OSC/_PDC call will apply it.
[ jandryuk: Mention Xen HWP's need. Support _OSC & _PDC ]
Signed-off-by: Roger Pau Monné <roger.pau(a)citrix.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Jason Andryuk <jandryuk(a)gmail.com>
Reviewed-by: Michal Wilczynski <michal.wilczynski(a)intel.com>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Link: https://lore.kernel.org/r/20231108212517.72279-1-jandryuk@gmail.com
Signed-off-by: Juergen Gross <jgross(a)suse.com>
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
#include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
if (!cpu_has(c, X86_FEATURE_MWAIT) ||
boot_option_idle_override == IDLE_NOMWAIT)
*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+ if (xen_initial_domain()) {
+ /*
+ * When Linux is running as Xen dom0, the hypervisor is the
+ * entity in charge of the processor power management, and so
+ * Xen needs to check the OS capabilities reported in the
+ * processor capabilities buffer matches what the hypervisor
+ * driver supports.
+ */
+ xen_sanitize_proc_cap_bits(cap);
+ }
}
static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
enum xen_lazy_mode xen_get_lazy_mode(void);
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+ BUG();
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3..508655273145 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
/*
* @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
return online;
}
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+ int ret;
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+ ret = HYPERVISOR_platform_op(&op);
+ if (ret)
+ pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+ ret);
+ else
+ *cap = buf[2];
+}
#endif
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x bfa993b355d33a438a746523e7129391c8664e8a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112210-impurity-skylight-806c@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
bfa993b355d3 ("acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0")
a4a7644c1509 ("x86/xen: move paravirt lazy code")
9bd0c413b90c ("Merge branch 'acpi-processor'")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From bfa993b355d33a438a746523e7129391c8664e8a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau(a)citrix.com>
Date: Wed, 8 Nov 2023 16:25:15 -0500
Subject: [PATCH] acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The Processor capability bits notify ACPI of the OS capabilities, and
so ACPI can adjust the return of other Processor methods taking the OS
capabilities into account.
When Linux is running as a Xen dom0, the hypervisor is the entity
in charge of processor power management, and hence Xen needs to make
sure the capabilities reported by _OSC/_PDC match the capabilities of
the driver in Xen.
Introduce a small helper to sanitize the buffer when running as Xen
dom0.
When Xen supports HWP, this serves as the equivalent of commit
a21211672c9a ("ACPI / processor: Request native thermal interrupt
handling via _OSC") to avoid SMM crashes. Xen will set bit
ACPI_PROC_CAP_COLLAB_PROC_PERF (bit 12) in the capability bits and the
_OSC/_PDC call will apply it.
[ jandryuk: Mention Xen HWP's need. Support _OSC & _PDC ]
Signed-off-by: Roger Pau Monné <roger.pau(a)citrix.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Jason Andryuk <jandryuk(a)gmail.com>
Reviewed-by: Michal Wilczynski <michal.wilczynski(a)intel.com>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Link: https://lore.kernel.org/r/20231108212517.72279-1-jandryuk@gmail.com
Signed-off-by: Juergen Gross <jgross(a)suse.com>
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
#include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
if (!cpu_has(c, X86_FEATURE_MWAIT) ||
boot_option_idle_override == IDLE_NOMWAIT)
*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+ if (xen_initial_domain()) {
+ /*
+ * When Linux is running as Xen dom0, the hypervisor is the
+ * entity in charge of the processor power management, and so
+ * Xen needs to check the OS capabilities reported in the
+ * processor capabilities buffer matches what the hypervisor
+ * driver supports.
+ */
+ xen_sanitize_proc_cap_bits(cap);
+ }
}
static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
enum xen_lazy_mode xen_get_lazy_mode(void);
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+ BUG();
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3..508655273145 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
/*
* @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
return online;
}
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+ int ret;
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+ ret = HYPERVISOR_platform_op(&op);
+ if (ret)
+ pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+ ret);
+ else
+ *cap = buf[2];
+}
#endif
The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x bfa993b355d33a438a746523e7129391c8664e8a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023112208-buggy-quartered-b19a@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
bfa993b355d3 ("acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0")
a4a7644c1509 ("x86/xen: move paravirt lazy code")
9bd0c413b90c ("Merge branch 'acpi-processor'")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From bfa993b355d33a438a746523e7129391c8664e8a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau(a)citrix.com>
Date: Wed, 8 Nov 2023 16:25:15 -0500
Subject: [PATCH] acpi/processor: sanitize _OSC/_PDC capabilities for Xen dom0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The Processor capability bits notify ACPI of the OS capabilities, and
so ACPI can adjust the return of other Processor methods taking the OS
capabilities into account.
When Linux is running as a Xen dom0, the hypervisor is the entity
in charge of processor power management, and hence Xen needs to make
sure the capabilities reported by _OSC/_PDC match the capabilities of
the driver in Xen.
Introduce a small helper to sanitize the buffer when running as Xen
dom0.
When Xen supports HWP, this serves as the equivalent of commit
a21211672c9a ("ACPI / processor: Request native thermal interrupt
handling via _OSC") to avoid SMM crashes. Xen will set bit
ACPI_PROC_CAP_COLLAB_PROC_PERF (bit 12) in the capability bits and the
_OSC/_PDC call will apply it.
[ jandryuk: Mention Xen HWP's need. Support _OSC & _PDC ]
Signed-off-by: Roger Pau Monné <roger.pau(a)citrix.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Jason Andryuk <jandryuk(a)gmail.com>
Reviewed-by: Michal Wilczynski <michal.wilczynski(a)intel.com>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Link: https://lore.kernel.org/r/20231108212517.72279-1-jandryuk@gmail.com
Signed-off-by: Juergen Gross <jgross(a)suse.com>
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c..f896eed4516c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
#include <asm/x86_init.h>
#include <asm/cpufeature.h>
#include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
if (!cpu_has(c, X86_FEATURE_MWAIT) ||
boot_option_idle_override == IDLE_NOMWAIT)
*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+ if (xen_initial_domain()) {
+ /*
+ * When Linux is running as Xen dom0, the hypervisor is the
+ * entity in charge of the processor power management, and so
+ * Xen needs to check the OS capabilities reported in the
+ * processor capabilities buffer matches what the hypervisor
+ * driver supports.
+ */
+ xen_sanitize_proc_cap_bits(cap);
+ }
}
static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b..a9088250770f 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
enum xen_lazy_mode xen_get_lazy_mode(void);
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+ BUG();
+}
+#endif
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3..508655273145 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
/*
* @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
return online;
}
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+ int ret;
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+ ret = HYPERVISOR_platform_op(&op);
+ if (ret)
+ pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+ ret);
+ else
+ *cap = buf[2];
+}
#endif