6.6.157-rc1 review

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maxime Ripard <[email protected]>

[ Upstream commit 30ac1d403438a6c6039f0af5bb2df3d021f96036 ]

The drm_bridge_funcs.atomic_reset documentation states that the hook must return either a valid drm_bridge_state object or an ERR_PTR().

The cdns_mhdp_bridge_atomic_reset() callback returns NULL when the allocation of its state fails, violating this contract.

Return ERR_PTR(-ENOMEM) instead.

---
 drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 44955601a9dfc..eeefb0fa70d88 100644
@@ -2161,7 +2161,7 @@ cdns_mhdp_bridge_atomic_reset(struct drm_bridge *bridge)
 
 	cdns_mhdp_state = kzalloc(sizeof(*cdns_mhdp_state), GFP_KERNEL);
 	if (!cdns_mhdp_state)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	__drm_atomic_helper_bridge_reset(bridge, &cdns_mhdp_state->base);
 

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konstantin Andreev <[email protected]>

[ Upstream commit fba3d32825f4bbc8e20f0cdc3b14df57965b8fe5 ]

The smack_msg_queue_msgrcv() function incorrectly checks the permissions of the 'current' task instead of the 'target' task.

In the msgsnd() syscall path, if a receiver is already waiting, the pipelined_send() optimization is used to push the message directly to the receiver task:

    ipc/msg.c`pipelined_send():
    ` smp_store_release(&msr->r_msg, msg)

In this case, the 'sender' (current) task performs the check on behalf of the 'receiver' task (msr->r_tsk, passed as the 'target' parameter):

ipc/msg.c`pipelined_send():
` security_msg_queue_msgrcv(,, target := msr->r_tsk,,)

However, smack_msg_queue_msgrcv() ignores the 'target' and checks 'current':

smack_msg_queue_msgrcv(…)
` smk_curacc_msq(isp, MAY_READWRITE); // current task

'current' MAY satisfy smack_msg_queue_msgrcv r/w requirement, but 'target' (the receiver task) might NOT;
as a result, an unauthorized receiver gets the message, violating MAC policy.

Test:
1) create a sysv message queue with label “foo”
2) echo "bar foo r" >/smack/load2
3) msgrcv(,,,0,MSG_NOERROR) in "bar"-labeled task. The task is waiting for the messages ...
4) msgsnd() from a "foo"-labeled task:
"bar"-labeled task gets the message.

This patch fixes the issue by checking permission on the 'target' task instead of 'current'.

(2008-02-04, Casey Schaufler)

---
 security/smack/smack_lsm.c | 65 +++++++++++++++++++++++++++-----------
 1 file changed, 47 insertions(+), 18 deletions(-)

index 2d5e9cae5606e..cda7099d8286e 100644
@@ -145,12 +145,13 @@ static int smk_bu_note(char *note, struct smack_known *sskp,
 #define smk_bu_note(note, sskp, oskp, mode, RC) (RC)
 #endif
 
-#ifdef CONFIG_SECURITY_SMACK_BRINGUP
-static int smk_bu_current(char *note, struct smack_known *oskp,
-			  int mode, int rc)
+static int
+smk_bu_tsk_to_obj(struct task_struct *tsk, const struct task_smack *tsp,
+		  char *note, struct smack_known *oskp, int mode, int rc)
 {
-	struct task_smack *tsp = smack_cred(current_cred());
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
 	char acc[SMK_NUM_ACCESS_TYPE + 1];
+	char comm[TASK_COMM_LEN];
 
 	if (rc <= 0)
 		return rc;

@@ -158,14 +159,22 @@ static int smk_bu_current(char *note, struct smack_known *oskp,
 		rc = 0;
 
 	smk_bu_mode(mode, acc);
+
 	pr_info("Smack %s: (%s %s %s) %s %s\n", smk_bu_mess[rc],
-		tsp->smk_task->smk_known, oskp->smk_known,
-		acc, current->comm, note);
+		smk_of_task(tsp)->smk_known, oskp->smk_known,
+		acc, get_task_comm(comm, tsk), note);
 	return 0;
-}
 #else
-#define smk_bu_current(note, oskp, mode, RC) (RC)
+	return rc;
 #endif
+}
+
+static int smk_bu_current(char *note, struct smack_known *oskp,
+			  int mode, int rc)
+{
+	return smk_bu_tsk_to_obj(current, smack_cred(current_cred()),
+				 note, oskp, mode, rc);
+}
 
 #ifdef CONFIG_SECURITY_SMACK_BRINGUP
 static int smk_bu_task(struct task_struct *otp, int mode, int rc)

@@ -3283,14 +3292,20 @@ static int smack_sem_semop(struct kern_ipc_perm *isp, struct sembuf *sops,
 }
 
 /**
- * smk_curacc_msq : helper to check if current has access on msq
- * @isp : the msq
+ * smk_tskacc_msq : helper to check if tsk has access on msq
+ * @tsk: the task that requests access
+ * @isp : the sysv msg queue permissions
  * @access : access requested
  *
- * return 0 if current has access, error otherwise
+ * return 0 if tsk has access, error otherwise
  */
-static int smk_curacc_msq(struct kern_ipc_perm *isp, int access)
+static int
+smk_tskacc_msq(struct task_struct *tsk, struct kern_ipc_perm *isp, int access)
 {
+	const bool tsk_is_current = (tsk == current);
+	const struct cred * const tsk_cred =
+			(tsk_is_current ? current_cred() : get_task_cred(tsk));
+	struct task_smack * const tsp = smack_cred(tsk_cred);
 	struct smack_known *msp = smack_of_ipc(isp);
 	struct smk_audit_info ad;
 	int rc;

@@ -3299,11 +3314,25 @@ static int smk_curacc_msq(struct kern_ipc_perm *isp, int access)
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
 	ad.a.u.ipc_id = isp->id;
 #endif
-	rc = smk_curacc(msp, access, &ad);
-	rc = smk_bu_current("msq", msp, access, rc);
+	rc = smk_tskacc(tsp, msp, access, &ad);
+	rc = smk_bu_tsk_to_obj(tsk, tsp, "msq", msp, access, rc);
+	if (!tsk_is_current)
+		put_cred(tsk_cred);
 	return rc;
 }
 
+/**
+ * smk_curacc_msq : helper to check if current has access on msq
+ * @isp : the sysv msg queue permissions
+ * @access : access requested
+ *
+ * return 0 if current has access, error otherwise
+ */
+static int smk_curacc_msq(struct kern_ipc_perm *isp, int access)
+{
+	return smk_tskacc_msq(current, isp, access);
+}
+
 /**
  * smack_msg_queue_associate - Smack access check for msg_queue
  * @isp: the object

@@ -3371,21 +3400,21 @@ static int smack_msg_queue_msgsnd(struct kern_ipc_perm *isp, struct msg_msg *msg
 }
 
 /**
- * smack_msg_queue_msgrcv - Smack access check for msg_queue
+ * smack_msg_queue_msgrcv - check it target has r/w access to msg_queue
  * @isp: the object
  * @msg: unused
- * @target: unused
+ * @target: the task that msgrcv() from the queue
  * @type: unused
  * @mode: unused
  *
- * Returns 0 if current has read and write access, error code otherwise
+ * Returns 0 if target has read and write access, error code otherwise
  */
 static int smack_msg_queue_msgrcv(struct kern_ipc_perm *isp,
 				  struct msg_msg *msg,
 				  struct task_struct *target, long type,
 				  int mode)
 {
-	return smk_curacc_msq(isp, MAY_READWRITE);
+	return smk_tskacc_msq(target, isp, MAY_READWRITE);
 }
 
 /**

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dmitry Antipov <[email protected]>

[ Upstream commit b78fede1c69a090d377bf80417ce1f7f7f314534 ]

Use the convenient 'kstrto{u,s}32_from_user()' to simplify write handlers of /smack/{doi,direct,mapped,logging,ptrace} sysfs entries.

Stable-dep-of: 577dc3b6a8cf ("smack: deduplicate smackfs/{direct,mapped} file_operations")

---
 security/smack/smackfs.c | 81 +++++++++++-----------------------------
 1 file changed, 22 insertions(+), 59 deletions(-)

index 109ad155ffc2a..dd44d254c300c 100644
@@ -1616,24 +1616,17 @@ static ssize_t smk_read_doi(struct file *filp, char __user *buf,
 static ssize_t smk_write_doi(struct file *file, const char __user *buf,
 			     size_t count, loff_t *ppos)
 {
-	char temp[80];
-	unsigned long u;
+	int ret;
+	u32 u;
 
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	if (count >= sizeof(temp) || count == 0)
-		return -EINVAL;
-
-	if (copy_from_user(temp, buf, count) != 0)
-		return -EFAULT;
-
-	temp[count] = '\0';
+	ret = kstrtou32_from_user(buf, count, 10, &u);
+	if (unlikely(ret))
+		return ret;
 
-	if (kstrtoul(temp, 10, &u))
-		return -EINVAL;
-
-	if (u == CIPSO_V4_DOI_UNKNOWN || u > U32_MAX)
+	if (u == CIPSO_V4_DOI_UNKNOWN)
 		return -EINVAL;
 
 	return smk_cipso_doi(u, GFP_KERNEL) ? : count;

@@ -1682,22 +1675,14 @@ static ssize_t smk_write_direct(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
 	struct smack_known *skp;
-	char temp[80];
-	int i;
+	int i, ret;
 
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	if (count >= sizeof(temp) || count == 0)
-		return -EINVAL;
-
-	if (copy_from_user(temp, buf, count) != 0)
-		return -EFAULT;
-
-	temp[count] = '\0';
-
-	if (sscanf(temp, "%d", &i) != 1)
-		return -EINVAL;
+	ret = kstrtos32_from_user(buf, count, 10, &i);
+	if (unlikely(ret))
+		return ret;
 
 	/*
 	 * Don't do anything if the value hasn't actually changed.

@@ -1760,22 +1745,14 @@ static ssize_t smk_write_mapped(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
 	struct smack_known *skp;
-	char temp[80];
-	int i;
+	int i, ret;
 
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	if (count >= sizeof(temp) || count == 0)
-		return -EINVAL;
-
-	if (copy_from_user(temp, buf, count) != 0)
-		return -EFAULT;
-
-	temp[count] = '\0';
-
-	if (sscanf(temp, "%d", &i) != 1)
-		return -EINVAL;
+	ret = kstrtos32_from_user(buf, count, 10, &i);
+	if (unlikely(ret))
+		return ret;
 
 	/*
 	 * Don't do anything if the value hasn't actually changed.

@@ -2196,22 +2173,15 @@ static ssize_t smk_read_logging(struct file *filp, char __user *buf,
 static ssize_t smk_write_logging(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	char temp[32];
-	int i;
+	int i, ret;
 
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	if (count >= sizeof(temp) || count == 0)
-		return -EINVAL;
-
-	if (copy_from_user(temp, buf, count) != 0)
-		return -EFAULT;
+	ret = kstrtos32_from_user(buf, count, 10, &i);
+	if (unlikely(ret))
+		return ret;
 
-	temp[count] = '\0';
-
-	if (sscanf(temp, "%d", &i) != 1)
-		return -EINVAL;
 	if (i < 0 || i > 3)
 		return -EINVAL;
 	log_policy = i;

@@ -2854,22 +2824,15 @@ static ssize_t smk_read_ptrace(struct file *filp, char __user *buf,
 static ssize_t smk_write_ptrace(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	char temp[32];
-	int i;
+	int i, ret;
 
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	if (*ppos != 0 || count >= sizeof(temp) || count == 0)
-		return -EINVAL;
-
-	if (copy_from_user(temp, buf, count) != 0)
-		return -EFAULT;
+	ret = kstrtos32_from_user(buf, count, 10, &i);
+	if (unlikely(ret))
+		return ret;
 
-	temp[count] = '\0';
-
-	if (sscanf(temp, "%d", &i) != 1)
-		return -EINVAL;
 	if (i < SMACK_PTRACE_DEFAULT || i > SMACK_PTRACE_MAX)
 		return -EINVAL;
 	smack_ptrace_rule = i;

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konstantin Andreev <[email protected]>

[ Upstream commit 577dc3b6a8cf200e6e27b2d9967cac14a1fed2f3 ]

The file_operations for smackfs/direct and smackfs/mapped are identical up to a textual replacement of "direct" with "mapped"

This patch combines two instances of file_operations into one, handling both files.

---
 security/smack/smack.h   |   5 +-
 security/smack/smackfs.c | 133 ++++++++++++---------------------------
 2 files changed, 42 insertions(+), 96 deletions(-)

index aac0574cdfad3..96a4a92ac0932 100644
@@ -299,8 +299,9 @@ int smack_populate_secattr(struct smack_known *skp);
  * Shared data.
  */
 extern int smack_enabled __initdata;
-extern int smack_cipso_direct;
-extern int smack_cipso_mapped;
+extern int smack_cipso_auto_level[2];
+#define smack_cipso_direct (+smack_cipso_auto_level[0])
+#define smack_cipso_mapped (+smack_cipso_auto_level[1])
 extern struct smack_known *smack_net_ambient;
 extern struct smack_known *smack_syslog_label;
 #ifdef CONFIG_SECURITY_SMACK_BRINGUP

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konstantin Andreev <[email protected]>

[ Upstream commit a7c44fd9f80e37763acf9cd3c87a58058d206427 ]

Both smackfs/direct and smackfs/mapped incorrectly accept the full range of integer values. For example:

    # cd /sys/fs/smackfs/
    # cat direct ; echo
    250

    # cat cipso2
    @ 250/2
    _ 250/2,4,5,6,7,8
    * 250/3,5,7
    ^ 250/2,4,5,6,7
    ? 250/3,4,5,6,7,8

    # echo -1234 >direct ; cat direct ; echo
    -1234
    # cat cipso2
    @ -1234/2
    _ -1234/2,4,5,6,7,8
    * -1234/3,5,7
    ^ -1234/2,4,5,6,7
    ? -1234/3,4,5,6,7,8
    #

I noticed two things regarding this:

1) sensitivity levels are truncated to 8 bits when labeling outgoing packets (0x2e = 46 for the -1234 example above)

2) the reverse process fails: incoming packets with sensitivity level 46 do not match these smackfs/cipso2 entries.

Even observation (1) on its own warrants a fix.

This patch restricts smackfs/direct and smackfs/mapped accepted values to the 0-255 range.

---
 security/smack/smack.h   |  2 +-
 security/smack/smackfs.c | 26 ++++++++++++++------------
 2 files changed, 15 insertions(+), 13 deletions(-)

index 96a4a92ac0932..e44f4e9f5d2be 100644
@@ -299,7 +299,7 @@ int smack_populate_secattr(struct smack_known *skp);
  * Shared data.
  */
 extern int smack_enabled __initdata;
-extern int smack_cipso_auto_level[2];
+extern u8  smack_cipso_auto_level[2];
 #define smack_cipso_direct (+smack_cipso_auto_level[0])
 #define smack_cipso_mapped (+smack_cipso_auto_level[1])
 extern struct smack_known *smack_net_ambient;

index ab472058d2e43..0f304667d8578 100644
@@ -92,7 +92,7 @@ struct smack_known *smack_net_ambient;
  * secid is contained directly in the category set.
  * It can be reset via smackfs/mapped
  */
-int smack_cipso_auto_level[2] = {
+u8 smack_cipso_auto_level[2] = {
 	SMACK_CIPSO_DIRECT_DEFAULT,
 	SMACK_CIPSO_MAPPED_DEFAULT,
 };

@@ -1659,17 +1659,15 @@ static const struct file_operations smk_doi_ops = {
 static ssize_t smk_read_cipso_auto_level(struct file *filp, char __user *buf,
 			       size_t count, loff_t *ppos)
 {
-	char temp[80];
-	ssize_t rc;
+	char temp[sizeof "255"];
+	int n;
 
 	if (*ppos != 0)
 		return 0;
 
-	sprintf(temp, "%d", smack_cipso_auto_level[
-			      smk_cipso_auto_level_idx(filp)]);
-	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
-
-	return rc;
+	n = sprintf(temp, "%u", (unsigned int)smack_cipso_auto_level[
+		smk_cipso_auto_level_idx(filp)]);
+	return simple_read_from_buffer(buf, count, ppos, temp, n);
 }
 
 /**

@@ -1685,13 +1683,16 @@ static ssize_t
 smk_write_cipso_auto_level(struct file *filp, const char __user *buf,
 			   size_t count, loff_t *ppos)
 {
-	struct smack_known *skp;
-	int i, ret, idx, old_lvl;
+	int ret, idx;
+	u8  i, old_lvl;
 
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
-
-	ret = kstrtos32_from_user(buf, count, 10, &i);
+	/*
+	 * draft-ietf-cipso-ipsecurity-01 (CIPSO 2.2), 3.4.2.4:
+	 * "Sensitivity Level is 1 octet in length. Its value is from 0 to 255"
+	 */
+	ret = kstrtou8_from_user(buf, count, 10, &i);
 	if (unlikely(ret))
 		return ret;
 

@@ -1704,6 +1705,7 @@ smk_write_cipso_auto_level(struct file *filp, const char __user *buf,
 	old_lvl = smack_cipso_auto_level[idx];
 
 	if (old_lvl != i) {
+		struct smack_known *skp;
 		mutex_lock(&smack_known_lock);
 		list_for_each_entry_rcu(skp, &smack_known_list, list)
 			if (skp->smk_netlabel.attr.mls.lvl ==

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jens Remus <[email protected]>

[ Upstream commit 0cfdf974f133e0ff17ed80e7895adbe7889d9522 ]

Commit

ccace936eec7 ("x86: Add types to indirectly called assembly functions")

introduced a x86-specific implementation of __CFI_TYPE() using an asymmetric combination of SYM_START() and SYM_FUNC_END() to add a symbol to the KCFI type identifier that precedes a function.

This asymmetric combination is an issue if SYM_FUNC_END() ever gets extended in a way that requires it to be used symmetrically with SYM_FUNC_START*(). For instance to emit DWARF CFI directives that denote the start/end of a function. [1]

Use SYM_END() with SYM_T_FUNC instead. No functional change, as the generic implementation of SYM_FUNC_END(name) expands into SYM_END(name, SYM_T_FUNC).

---
 arch/x86/include/asm/linkage.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 571fe4d2d2328..6cea7b15785a3 100644
@@ -103,7 +103,7 @@
 	.byte 0xb8 ASM_NL					\
 	.long __kcfi_typeid_##name ASM_NL			\
 	CFI_POST_PADDING					\
-	SYM_FUNC_END(__cfi_##name)
+	SYM_END(__cfi_##name, SYM_T_FUNC)
 
 /* UML needs to be able to override memcpy() and friends for KASAN. */
 #ifdef CONFIG_UML

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maoyi Xie <[email protected]>

[ Upstream commit a0a8cd9fc9c48b95095bcec4b146f7a99486f58e ]

cros_typec_register_partner_pdos() copies the partner PDOs from the EC TYPEC_STATUS response into the fixed caps_desc.pdo[PDO_MAX_OBJECTS] array.

	memcpy(caps_desc.pdo, resp->source_cap_pdos,
	       sizeof(u32) * resp->source_cap_count);
	...
	memcpy(caps_desc.pdo, resp->sink_cap_pdos,
	       sizeof(u32) * resp->sink_cap_count);

PDO_MAX_OBJECTS is 7. source_cap_count and sink_cap_count are u8 fields from the EC. The only check is that they are not both zero. If either is larger than 7, the memcpy writes past the end of the array on the stack. A count of 255 overflows it by about 1 KB. The EC source arrays are only seven entries wide. A larger count reads past them too.

The ChromeOS EC firmware caps these counts today, so a compliant setup does not hit this. The kernel should still validate these values rather than trust them.

Validate the counts in cros_typec_register_partner_pdos() next to the memcpy. Skip the PDO registration if either count is above PDO_MAX_OBJECTS. The rest of cros_typec_handle_status() still runs so events are handled and cleared.

---
 drivers/platform/chrome/cros_ec_typec.c | 6 ++++++
 1 file changed, 6 insertions(+)

index 76807ceb313a9..65549c3a67486 100644
@@ -942,6 +942,12 @@ static void cros_typec_register_partner_pdos(struct cros_typec_data *typec,
 	if (!resp->source_cap_count && !resp->sink_cap_count)
 		return;
 
+	if (resp->source_cap_count > PDO_MAX_OBJECTS ||
+	    resp->sink_cap_count > PDO_MAX_OBJECTS) {
+		dev_warn(typec->dev, "Invalid PDO count from EC, port: %d\n", port_num);
+		return;
+	}
+
 	port->partner_pd = typec_partner_usb_power_delivery_register(port->partner, &desc);
 	if (IS_ERR(port->partner_pd)) {
 		dev_warn(typec->dev, "Failed to register partner PD device, port: %d\n", port_num);

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Philipp Weber <[email protected]>

[ Upstream commit a4bc41504690b7d7064931909874f5b98cd148b6 ]

A driver's probe calls hid_device_io_start() to enable input delivery, then fails at a later initialization step and unwinds via hid_hw_stop(). The unwind frees struct hidraw via hidraw_disconnect() while in-flight HID reports may still be running on another CPU, dereferencing the freed object through hidraw_report_event(). syzbot reports the resulting use-after-free for the corsair-psu HID driver.

Edward Adam Davis posted a per-driver fix for corsair-psu that adds an explicit hid_device_io_stop() before hid_hw_stop() in the probe error path ("hwmon: prevent packets from going to driver for probe", 2026-04-28). Auditing the tree shows 15 drivers call hid_device_io_start(); 7 also call hid_device_io_stop() and 8 do not:

drivers calling hid_device_io_start() without a matching hid_device_io_stop() before hid_hw_stop():
drivers/hwmon/corsair-psu.c (fix posted by Edward)
drivers/hwmon/corsair-cpro.c drivers/hwmon/nzxt-kraken3.c drivers/hwmon/nzxt-smart2.c drivers/hwmon/gigabyte_waterforce.c drivers/hid/hid-logitech-dj.c drivers/hid/hid-nintendo.c drivers/hid/hid-mcp2221.c

Roughly half of all callers of the API are exposed. Centralize the quiesce in hid_hw_stop() so callers do not have to remember the matching stop: if a driver has left hdev->io_started true on entry, call hid_device_io_stop() before hid_disconnect().

For the 7 drivers that already call hid_device_io_stop() correctly, hdev->io_started is false on entry, the guard short-circuits, and behavior is unchanged.

No Fixes: tag because the affected drivers gained their hid_device_io_start() calls independently over years; the bug is a class-wide API misuse rather than a regression from one commit.

---
 drivers/hid/hid-core.c | 7 +++++++
 1 file changed, 7 insertions(+)

index b924980b5783e..241dfec35d1c0 100644
@@ -2370,9 +2370,16 @@ EXPORT_SYMBOL_GPL(hid_hw_start);
  *
  * This is usually called from remove function or from probe when something
  * failed and hid_hw_start was called already.
+ *
+ * If the caller enabled HID input via hid_device_io_start() and is unwinding
+ * without an explicit hid_device_io_stop(), quiesce input first so that
+ * in-flight reports cannot reach handlers (e.g. hidraw_report_event) whose
+ * backing objects hid_disconnect() is about to free.
  */
 void hid_hw_stop(struct hid_device *hdev)
 {
+	if (hdev->io_started)
+		hid_device_io_stop(hdev);
 	hid_disconnect(hdev);
 	hdev->ll_driver->stop(hdev);
 }

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christos Maragkos <[email protected]>

[ Upstream commit 1f9b25d3fb65b9384dec16d9db13a3e71abd9145 ]

Previously, the imu_timestamp_us variable was incremented twice per report, causing it to advance by two times the desired amount.

This resulted in incorrect jumps in IMU timestamps reported using MSC_TIMESTAMP, so userspace applications saw corrupted timing on functions such as gyroscope-based aim and motion controls.

This is fixed by removing the redundant increment at the start of the report handling so the remaining can account for the full report interval.

---
 drivers/hid/hid-nintendo.c | 1 -
 1 file changed, 1 deletion(-)

index a69b04ffbb2be..115f496368e58 100644
@@ -1164,7 +1164,6 @@ static void joycon_parse_imu_report(struct joycon_ctlr *ctlr,
 		dropped_threshold = ctlr->imu_avg_delta_ms * 3 / 2;
 		dropped_pkts = (delta - min(delta, dropped_threshold)) /
 				ctlr->imu_avg_delta_ms;
-		ctlr->imu_timestamp_us += 1000 * ctlr->imu_avg_delta_ms;
 		if (dropped_pkts > JC_IMU_DROPPED_PKT_WARNING) {
 			hid_warn(ctlr->hdev,
 				 "compensating for %u dropped IMU reports\n",

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Bommarito <[email protected]>

[ Upstream commit 43fae42628a8c10fa8981773d7ec9f1a367821a7 ]

kone_keep_values_up_to_date() and kone_profile_activated() use an 8-bit, device-supplied profile value as an index into the 5-element kone->profiles[] array without a range check. A malicious USB device claiming the Roccat Kone id can send a switch-profile event (or a startup_profile read at probe) with an out-of-range value and make the driver read out of bounds; the result is exposed via the actual_dpi sysfs attribute.

Reject out-of-range indices in both paths.

This was found with static analysis and confirmed with the KUnit test added in the following patch (KASAN: slab-out-of-bounds).

---
 drivers/hid/hid-roccat-kone.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

index 00a1abc7e8390..ab17179afb3cb 100644
@@ -36,6 +36,8 @@ static uint profile_numbers[5] = {0, 1, 2, 3, 4};
 
 static void kone_profile_activated(struct kone_device *kone, uint new_profile)
 {
+	if (new_profile < 1 || new_profile > ARRAY_SIZE(kone->profiles))
+		new_profile = 1;
 	kone->actual_profile = new_profile;
 	kone->actual_dpi = kone->profiles[new_profile - 1].startup_dpi;
 }

@@ -793,8 +795,10 @@ static void kone_keep_values_up_to_date(struct kone_device *kone,
 {
 	switch (event->event) {
 	case kone_mouse_event_switch_profile:
-		kone->actual_dpi = kone->profiles[event->value - 1].
-				startup_dpi;
+		if (event->value >= 1 &&
+		    event->value <= ARRAY_SIZE(kone->profiles))
+			kone->actual_dpi =
+				kone->profiles[event->value - 1].startup_dpi;
 		fallthrough;
 	case kone_mouse_event_osd_profile:
 		kone->actual_profile = event->value;

2.53.0

# Librecast Test Results

020/020 [ OK ] liblcrq
010/010 [ OK ] libmld
120/120 [ OK ] liblibrecast

CPU/kernel: Linux auntie 6.6.157-rc1-gfcb8c41a77e1 #1 SMP PREEMPT_DYNAMIC Sat Sep 12 13:50:15 -00 2026 x86_64 AMD Ryzen 9 9950X 16-Core Processor AuthenticAMD GNU/Linux

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Weigang He <[email protected]>

[ Upstream commit fa476d53edd24e8105faace04e881b9c4179738f ]

exynos_get_pmu_regmap() obtains a device_node via of_find_matching_node() and passes it to exynos_get_pmu_regmap_by_phandle(np, NULL). With propname == NULL the callee uses np directly and does not drop a reference, so the reference taken by of_find_matching_node() is leaked on every call -- including on each -EPROBE_DEFER retry of the only in-tree caller, exynos_retention_init() in the Exynos pinctrl driver.

Annotate np with the __free(device_node) cleanup attribute so the reference is released when the function returns.

Found by static analysis tool CodeQL.

---
 drivers/soc/samsung/exynos-pmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 250537d7cfd64..aea4afefb3454 100644
@@ -115,8 +115,8 @@ static const struct mfd_cell exynos_pmu_devs[] = {
 
 struct regmap *exynos_get_pmu_regmap(void)
 {
-	struct device_node *np = of_find_matching_node(NULL,
-						      exynos_pmu_of_device_ids);
+	struct device_node *np __free(device_node) =
+		of_find_matching_node(NULL, exynos_pmu_of_device_ids);
 	if (np)
 		return syscon_node_to_regmap(np);
 	return ERR_PTR(-ENODEV);

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gui-Dong Han <[email protected]>

[ Upstream commit a1d83d1b810665bd53ce8a7b7867e054d68676c7 ]

cec_pin_update() fills work_pin_events[] and work_pin_ts[], then increments work_pin_num_events. cec_pin_thread_func() uses that counter to decide when to read the FIFO entries.

Do not let the counter update be observed without the event update. Also do not let a freed slot be reused before the thread has finished reading it. Use release operations when publishing an entry and releasing a slot, and acquire operations when consuming those counter updates.

Leave the other work_pin_num_events users as they do not participate in this FIFO publication path.

---
 drivers/media/cec/core/cec-pin.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

index 330d5d5d86aba..4c91f96351cad 100644
@@ -114,7 +114,7 @@ static void cec_pin_update(struct cec_pin *pin, bool v, bool force)
 		return;
 
 	pin->adap->cec_pin_is_high = v;
-	if (atomic_read(&pin->work_pin_num_events) < CEC_NUM_PIN_EVENTS) {
+	if (atomic_read_acquire(&pin->work_pin_num_events) < CEC_NUM_PIN_EVENTS) {
 		u8 ev = v;
 
 		if (pin->work_pin_events_dropped) {

@@ -125,7 +125,7 @@ static void cec_pin_update(struct cec_pin *pin, bool v, bool force)
 		pin->work_pin_ts[pin->work_pin_events_wr] = ktime_get();
 		pin->work_pin_events_wr =
 			(pin->work_pin_events_wr + 1) % CEC_NUM_PIN_EVENTS;
-		atomic_inc(&pin->work_pin_num_events);
+		atomic_inc_return_release(&pin->work_pin_num_events);
 	} else {
 		pin->work_pin_events_dropped = true;
 		pin->work_pin_events_dropped_cnt++;

@@ -1074,7 +1074,7 @@ static int cec_pin_thread_func(void *_adap)
 						     pin->work_tx_ts);
 		}
 
-		while (atomic_read(&pin->work_pin_num_events)) {
+		while (atomic_read_acquire(&pin->work_pin_num_events)) {
 			unsigned int idx = pin->work_pin_events_rd;
 			u8 v = pin->work_pin_events[idx];
 

@@ -1083,7 +1083,7 @@ static int cec_pin_thread_func(void *_adap)
 						v & CEC_PIN_EVENT_FL_DROPPED,
 						pin->work_pin_ts[idx]);
 			pin->work_pin_events_rd = (idx + 1) % CEC_NUM_PIN_EVENTS;
-			atomic_dec(&pin->work_pin_num_events);
+			atomic_dec_return_release(&pin->work_pin_num_events);
 		}
 
 		switch (atomic_xchg(&pin->work_irq_change,

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Myeonghun Pak <[email protected]>

[ Upstream commit e25d8d35e8cbc1a4c04a8b86eed6aa7229f6449e ]

vc7_probe() registers the APLL with clk_register_fixed_rate(), which is not devm-managed and must be explicitly unregistered on probe failure.

Most later errors already unwind through err_clk, but a failure from vc7_get_bank_clk() in the output registration loop returned directly. That skipped clk_unregister_fixed_rate() and leaked the APLL clock.

Route that error through the existing err_clk label so the fixed-rate clock is released consistently with the other probe failure paths.

This issue was identified during our ongoing static-analysis research while reviewing kernel code.

---
 drivers/clk/clk-versaclock7.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 9ab35c1af0ff9..7db12918b84d4 100644
@@ -1191,7 +1191,7 @@ static int vc7_probe(struct i2c_client *client)
 		if (ret) {
 			dev_err_probe(&client->dev, ret,
 				      "unable to register output %d\n", i);
-			return ret;
+			goto err_clk;
 		}
 
 		switch (bank_src_map.type) {

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander A. Klimov <[email protected]>

[ Upstream commit 9f275f2ee9ca60ea4c092bdc0195987945ad8ad8 ]

Not only these error checks are redundand,
those of_clk_get() return values weren't cleaned up via clk_put().

---
 drivers/clk/clk-moxart.c | 14 --------------
 1 file changed, 14 deletions(-)

index 3786a0153ad17..40663ef3ef0ae 100644
@@ -17,7 +17,6 @@ static void __init moxart_of_pll_clk_init(struct device_node *node)
 {
 	void __iomem *base;
 	struct clk_hw *hw;
-	struct clk *ref_clk;
 	unsigned int mul;
 	const char *name = node->name;
 	const char *parent_name;

@@ -34,12 +33,6 @@ static void __init moxart_of_pll_clk_init(struct device_node *node)
 	mul = readl(base + 0x30) >> 3 & 0x3f;
 	iounmap(base);
 
-	ref_clk = of_clk_get(node, 0);
-	if (IS_ERR(ref_clk)) {
-		pr_err("%pOF: of_clk_get failed\n", node);
-		return;
-	}
-
 	hw = clk_hw_register_fixed_factor(NULL, name, parent_name, 0, mul, 1);
 	if (IS_ERR(hw)) {
 		pr_err("%pOF: failed to register clock\n", node);

@@ -56,7 +49,6 @@ static void __init moxart_of_apb_clk_init(struct device_node *node)
 {
 	void __iomem *base;
 	struct clk_hw *hw;
-	struct clk *pll_clk;
 	unsigned int div, val;
 	unsigned int div_idx[] = { 2, 3, 4, 6, 8};
 	const char *name = node->name;

@@ -78,12 +70,6 @@ static void __init moxart_of_apb_clk_init(struct device_node *node)
 		val = 0;
 	div = div_idx[val] * 2;
 
-	pll_clk = of_clk_get(node, 0);
-	if (IS_ERR(pll_clk)) {
-		pr_err("%pOF: of_clk_get failed\n", node);
-		return;
-	}
-
 	hw = clk_hw_register_fixed_factor(NULL, name, parent_name, 0, 1, div);
 	if (IS_ERR(hw)) {
 		pr_err("%pOF: failed to register clock\n", node);

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joey Lu <[email protected]>

[ Upstream commit b3a2223a7805c7e6759a32a5d6ca574ad07e2710 ]

div_u64() does not modify its argument in place; the return value must be assigned. Both ma35d1_calc_smic_pll_freq() and ma35d1_calc_pll_freq() called div_u64() and discarded the result, leaving pll_freq holding the undivided product and thus returning a frequency orders of magnitude too high.

---
 drivers/clk/nuvoton/clk-ma35d1-pll.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index ff3fb8b87c24b..9bb18fc371d17 100644
@@ -92,7 +92,7 @@ static unsigned long ma35d1_calc_smic_pll_freq(u32 pll0_ctl0,
 	p = FIELD_GET(SPLL0_CTL0_OUTDIV, pll0_ctl0);
 	outdiv = 1 << p;
 	pll_freq = (u64)parent_rate * n;
-	div_u64(pll_freq, m * outdiv);
+	pll_freq = div_u64(pll_freq, m * outdiv);
 	return pll_freq;
 }
 

@@ -110,7 +110,7 @@ static unsigned long ma35d1_calc_pll_freq(u8 mode, u32 *reg_ctl, unsigned long p
 
 	if (mode == PLL_MODE_INT) {
 		pll_freq = (u64)parent_rate * n;
-		div_u64(pll_freq, m * p);
+		pll_freq = div_u64(pll_freq, m * p);
 	} else {
 		x = FIELD_GET(PLL_CTL1_FRAC, reg_ctl[1]);
 		/* 2 decimal places floating to integer (ex. 1.23 to 123) */

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joey Lu <[email protected]>

[ Upstream commit 26de5aed72d80bd8aec2583134aca3597c64fda9 ]

PLL_CTL1_FRAC was defined as GENMASK(31, 24), covering only 8 bits. The hardware fractional field occupies bits [31:8] (24 bits), so the mask must be GENMASK(31, 8).

The previous fractional-mode calculation used FIELD_MAX(PLL_CTL1_FRAC) as the denominator to obtain 2 decimal places. With the corrected 24-bit mask the old divisor is wrong; replace the arithmetic with a proper 24-bit fixed-point rounding to 3 decimal places using the kernel's DIV_ROUND_CLOSEST_ULL helper:

n_frac = n * 1000 + DIV_ROUND_CLOSEST_ULL(x * 1000, 1 << 24)

---
 drivers/clk/nuvoton/clk-ma35d1-pll.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

index 9bb18fc371d17..64f473fd770bc 100644
@@ -48,7 +48,7 @@
 #define PLL_CTL1_PD		BIT(0)
 #define PLL_CTL1_BP		BIT(1)
 #define PLL_CTL1_OUTDIV		GENMASK(6, 4)
-#define PLL_CTL1_FRAC		GENMASK(31, 24)
+#define PLL_CTL1_FRAC		GENMASK(31, 8)
 #define PLL_CTL2_SLOPE		GENMASK(23, 0)
 
 #define INDIV_MIN		1

@@ -113,9 +113,9 @@ static unsigned long ma35d1_calc_pll_freq(u8 mode, u32 *reg_ctl, unsigned long p
 		pll_freq = div_u64(pll_freq, m * p);
 	} else {
 		x = FIELD_GET(PLL_CTL1_FRAC, reg_ctl[1]);
-		/* 2 decimal places floating to integer (ex. 1.23 to 123) */
-		n = n * 100 + ((x * 100) / FIELD_MAX(PLL_CTL1_FRAC));
-		pll_freq = div_u64(parent_rate * n, 100 * m * p);
+		/* convert 24-bit fraction to 3 decimal digits, rounding to closest */
+		n = n * 1000 + DIV_ROUND_CLOSEST_ULL((u64)x * 1000, 1ULL << 24);
+		pll_freq = div_u64((u64)parent_rate * n, 1000 * m * p);
 	}
 	return pll_freq;
 }

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Masney <[email protected]>

[ Upstream commit cd9e9bbfd93be277e316ee854614e2c4cd502fa8 ]

The round_rate() clk ops is deprecated, so migrate this driver from round_rate() to determine_rate() using the Coccinelle semantic patch on the cover letter of this series.

Stable-dep-of: e1311954cb60 ("clk: nuvoton: ma35d1: fix ma35d1_clk_pll_determine_rate logic")

---
 drivers/clk/nuvoton/clk-ma35d1-pll.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

index 64f473fd770bc..eb9d69d2077b1 100644
@@ -244,35 +244,43 @@ static unsigned long ma35d1_clk_pll_recalc_rate(struct clk_hw *hw, unsigned long
 	return 0;
 }
 
-static long ma35d1_clk_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-				      unsigned long *parent_rate)
+static int ma35d1_clk_pll_determine_rate(struct clk_hw *hw,
+					 struct clk_rate_request *req)
 {
 	struct ma35d1_clk_pll *pll = to_ma35d1_clk_pll(hw);
 	u32 reg_ctl[3] = { 0 };
 	unsigned long pll_freq;
 	long ret;
 
-	if (*parent_rate < PLL_FREF_MIN_FREQ || *parent_rate > PLL_FREF_MAX_FREQ)
+	if (req->best_parent_rate < PLL_FREF_MIN_FREQ || req->best_parent_rate > PLL_FREF_MAX_FREQ)
 		return -EINVAL;
 
-	ret = ma35d1_pll_find_closest(pll, rate, *parent_rate, reg_ctl, &pll_freq);
+	ret = ma35d1_pll_find_closest(pll, req->rate, req->best_parent_rate,
+				      reg_ctl, &pll_freq);
 	if (ret < 0)
 		return ret;
 
 	switch (pll->id) {
 	case CAPLL:
 		reg_ctl[0] = readl_relaxed(pll->ctl0_base);
-		pll_freq = ma35d1_calc_smic_pll_freq(reg_ctl[0], *parent_rate);
-		return pll_freq;
+		pll_freq = ma35d1_calc_smic_pll_freq(reg_ctl[0], req->best_parent_rate);
+		req->rate = pll_freq;
+
+		return 0;
 	case DDRPLL:
 	case APLL:
 	case EPLL:
 	case VPLL:
 		reg_ctl[0] = readl_relaxed(pll->ctl0_base);
 		reg_ctl[1] = readl_relaxed(pll->ctl1_base);
-		pll_freq = ma35d1_calc_pll_freq(pll->mode, reg_ctl, *parent_rate);
-		return pll_freq;
+		pll_freq = ma35d1_calc_pll_freq(pll->mode, reg_ctl, req->best_parent_rate);
+		req->rate = pll_freq;
+
+		return 0;
 	}
+
+	req->rate = 0;
+
 	return 0;
 }
 

@@ -311,12 +319,12 @@ static const struct clk_ops ma35d1_clk_pll_ops = {
 	.unprepare = ma35d1_clk_pll_unprepare,
 	.set_rate = ma35d1_clk_pll_set_rate,
 	.recalc_rate = ma35d1_clk_pll_recalc_rate,
-	.round_rate = ma35d1_clk_pll_round_rate,
+	.determine_rate = ma35d1_clk_pll_determine_rate,
 };
 
 static const struct clk_ops ma35d1_clk_fixed_pll_ops = {
 	.recalc_rate = ma35d1_clk_pll_recalc_rate,
-	.round_rate = ma35d1_clk_pll_round_rate,
+	.determine_rate = ma35d1_clk_pll_determine_rate,
 };
 
 struct clk_hw *ma35d1_reg_clk_pll(struct device *dev, u32 id, u8 u8mode, const char *name,

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joey Lu <[email protected]>

[ Upstream commit e1311954cb600d5f95cd9e2fe9a7376edc2ac3c5 ]

ma35d1_clk_pll_determine_rate() called ma35d1_pll_find_closest() unconditionally before the switch statement, and then every case branch overwrote pll_freq by reading the current hardware registers. For CAPLL and DDRPLL this means find_closest() ran unnecessarily (and incorrectly, since those PLLs are read-only) and its result was silently discarded.

Fix by moving the find_closest() call inside the APLL/EPLL/VPLL branch where it belongs. Group CAPLL and DDRPLL together as read-only PLLs that simply report their current rate; handle them with an explicit if/else to keep the CAPLL (SMIC design) and DDRPLL (standard design) paths distinct.

---
 drivers/clk/nuvoton/clk-ma35d1-pll.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

index eb9d69d2077b1..c7c0dc91a012c 100644
@@ -255,32 +255,32 @@ static int ma35d1_clk_pll_determine_rate(struct clk_hw *hw,
 	if (req->best_parent_rate < PLL_FREF_MIN_FREQ || req->best_parent_rate > PLL_FREF_MAX_FREQ)
 		return -EINVAL;
 
-	ret = ma35d1_pll_find_closest(pll, req->rate, req->best_parent_rate,
-				      reg_ctl, &pll_freq);
-	if (ret < 0)
-		return ret;
-
 	switch (pll->id) {
 	case CAPLL:
+	case DDRPLL:
+		/* Read-only PLLs: return current rate */
 		reg_ctl[0] = readl_relaxed(pll->ctl0_base);
-		pll_freq = ma35d1_calc_smic_pll_freq(reg_ctl[0], req->best_parent_rate);
+		if (pll->id == CAPLL) {
+			pll_freq = ma35d1_calc_smic_pll_freq(reg_ctl[0], req->best_parent_rate);
+		} else {
+			reg_ctl[1] = readl_relaxed(pll->ctl1_base);
+			pll_freq = ma35d1_calc_pll_freq(pll->mode, reg_ctl, req->best_parent_rate);
+		}
 		req->rate = pll_freq;
-
 		return 0;
-	case DDRPLL:
 	case APLL:
 	case EPLL:
 	case VPLL:
-		reg_ctl[0] = readl_relaxed(pll->ctl0_base);
-		reg_ctl[1] = readl_relaxed(pll->ctl1_base);
-		pll_freq = ma35d1_calc_pll_freq(pll->mode, reg_ctl, req->best_parent_rate);
+		/* Configurable PLLs: find closest achievable rate */
+		ret = ma35d1_pll_find_closest(pll, req->rate, req->best_parent_rate,
+					      reg_ctl, &pll_freq);
+		if (ret < 0)
+			return ret;
 		req->rate = pll_freq;
-
 		return 0;
 	}
 
 	req->rate = 0;
-
 	return 0;
 }
 

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Runyu Xiao <[email protected]>

[ Upstream commit 612ccf42acd14bb2685fa60c3495ca13e63e8989 ]

rt700_sdw_remove() drains jack_detect_work and jack_btn_check_work only when rt700->hw_init is true. That state bit is cleared by rt700_update_status() when the SoundWire slave becomes UNATTACHED, but a jack work item can already have been queued by rt700_interrupt_callback() or rt700_jack_init() while the device was initialized.

Do not use hw_init as the remove-time guard for draining these work objects. The delayed works are initialized during rt700_init(), so remove can cancel them unconditionally and pair the object lifetime with the codec-private data lifetime instead of a mutable hardware state bit.

This issue was found by our static analysis tool and then confirmed by manual review of the SoundWire status, interrupt and remove paths. The remove path should drain work based on whether the work object exists, not on a runtime hardware state bit that can change after the work was queued.

A QEMU PoC queued jack_detect_work, simulated SDW_SLAVE_UNATTACHED, and then entered remove. DEBUG_OBJECTS reported an active timer/work object associated with the rt700 jack work path after remove skipped the cancel.

This is sent as an RFC because the practical trigger depends on SoundWire core remove ordering after an UNATTACHED status update. If remove cannot run after hw_init has been cleared while jack work is still pending, this is a defensive lifecycle cleanup rather than a reachable race on current systems.

---
 sound/soc/codecs/rt700-sdw.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

index 52c33d56b143a..033b686ad0d45 100644
@@ -459,10 +459,8 @@ static int rt700_sdw_remove(struct sdw_slave *slave)
 {
 	struct rt700_priv *rt700 = dev_get_drvdata(&slave->dev);
 
-	if (rt700->hw_init) {
-		cancel_delayed_work_sync(&rt700->jack_detect_work);
-		cancel_delayed_work_sync(&rt700->jack_btn_check_work);
-	}
+	cancel_delayed_work_sync(&rt700->jack_detect_work);
+	cancel_delayed_work_sync(&rt700->jack_btn_check_work);
 
 	pm_runtime_disable(&slave->dev);
 

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shengjiu Wang <[email protected]>

[ Upstream commit 3359ba93d01a23b2e4249e9e44ccfe48eb9c5d71 ]

After pm_runtime_enable() the AUDMIX block is powered off and stays suspended until the first runtime resume. Register writes issued between probe() and the first resume (e.g. from DAPM or ALSA control paths) target unpowered hardware and cause a system hang.

Fix this by calling pm_runtime_resume_and_get() immediately after pm_runtime_enable() to power the hardware up and enable its clocks. Release the reference afterwards with pm_runtime_put() to allow the runtime PM framework to suspend the device and switch the regmap to cache-only mode when idle.

When CONFIG_PM is disabled or runtime PM is not enabled, pm_runtime_* calls are stubs that do not power up the hardware. Handle this case explicitly by calling fsl_audmix_runtime_resume() directly so the hardware is always initialised and its clocks are enabled, ensuring register accesses succeed regardless of PM configuration.

---
 sound/soc/fsl/fsl_audmix.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

index 8bc02ceda13c2..d5c5a2117013c 100644
@@ -458,6 +458,9 @@ static const struct of_device_id fsl_audmix_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, fsl_audmix_ids);
 
+static int fsl_audmix_runtime_resume(struct device *dev);
+static int fsl_audmix_runtime_suspend(struct device *dev);
+
 static int fsl_audmix_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;

@@ -489,13 +492,25 @@ static int fsl_audmix_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->lock);
 	platform_set_drvdata(pdev, priv);
 	pm_runtime_enable(dev);
+	if (!pm_runtime_enabled(dev)) {
+		ret = fsl_audmix_runtime_resume(dev);
+		if (ret)
+			goto err_disable_pm;
+	}
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret < 0)
+		goto err_pm_get_sync;
+
+	/* To enable regmap cache only when runtime PM enabled */
+	pm_runtime_put(dev);
 
 	ret = devm_snd_soc_register_component(dev, &fsl_audmix_component,
 					      fsl_audmix_dai,
 					      ARRAY_SIZE(fsl_audmix_dai));
 	if (ret) {
 		dev_err(dev, "failed to register ASoC DAI\n");
-		goto err_disable_pm;
+		goto err_pm_get_sync;
 	}
 
 	/*

@@ -507,12 +522,15 @@ static int fsl_audmix_probe(struct platform_device *pdev)
 		if (IS_ERR(priv->pdev)) {
 			ret = PTR_ERR(priv->pdev);
 			dev_err(dev, "failed to register platform: %d\n", ret);
-			goto err_disable_pm;
+			goto err_pm_get_sync;
 		}
 	}
 
 	return 0;
 
+err_pm_get_sync:
+	if (!pm_runtime_status_suspended(dev))
+		fsl_audmix_runtime_suspend(dev);
 err_disable_pm:
 	pm_runtime_disable(dev);
 	return ret;

@@ -523,6 +541,8 @@ static void fsl_audmix_remove(struct platform_device *pdev)
 	struct fsl_audmix *priv = dev_get_drvdata(&pdev->dev);
 
 	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		fsl_audmix_runtime_suspend(&pdev->dev);
 
 	if (priv->pdev)
 		platform_device_unregister(priv->pdev);

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Min zhang <[email protected]>

[ Upstream commit a8036f4591542de4b38ec81d3e2ba47bc0b2652b ]

Using devm_kmalloc() does not zero-initialize the allocated structure. Uninitialized members in struct hisi_reset_controller may contain garbage data, which can cause reset_controller_register() to fail unexpectedly.

Replace devm_kmalloc() with devm_kzalloc() to ensure all structure fields are properly zero-initialized.

---
 drivers/clk/hisilicon/reset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 93cee17db8b16..c3b7daac93132 100644
@@ -91,7 +91,7 @@ struct hisi_reset_controller *hisi_reset_init(struct platform_device *pdev)
 {
 	struct hisi_reset_controller *rstc;
 
-	rstc = devm_kmalloc(&pdev->dev, sizeof(*rstc), GFP_KERNEL);
+	rstc = devm_kzalloc(&pdev->dev, sizeof(*rstc), GFP_KERNEL);
 	if (!rstc)
 		return NULL;
 

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Weigang He <[email protected]>

[ Upstream commit 936407c3563ac745cbbb9953c0cf2472128a22f4 ]

imx_src_init() obtains a device_node reference via of_find_compatible_node() matching "fsl,imx51-src" and uses it only to call of_iomap(). It never releases that reference: on the success path the function returns at the end without of_node_put(np), leaking one device_node refcount on every boot of an i.MX5/6 platform.

Release the reference right after of_iomap(). of_iomap() maps the node's registers but does not retain a reference to the device_node, so the node can be put once the mapping is done. The early return on a NULL np needs no put.

Found by static analysis tool CodeQL.

---
 arch/arm/mach-imx/src.c | 1 +
 1 file changed, 1 insertion(+)

index 59a8e8cc44693..f28bfb653a88f 100644
@@ -171,6 +171,7 @@ void __init imx_src_init(void)
 	if (!np)
 		return;
 	src_base = of_iomap(np, 0);
+	of_node_put(np);
 	WARN_ON(!src_base);
 
 	/*

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Weigang He <[email protected]>

[ Upstream commit 3de939b2ac843d56d88e2ab1e1b1f667cba9e1d4 ]

imx7_src_init() obtains two device_node references via of_find_compatible_node() - one for "fsl,imx7d-src" and one for "fsl,imx7d-gpc" - reusing the same np variable, but never calls of_node_put() on either. On every i.MX7D boot up to two device_node refcounts are leaked:

- The "fsl,imx7d-src" node is leaked both when of_iomap() fails (the early return after the mapping) and when it succeeds, because np is then overwritten by the second of_find_compatible_node() call without releasing the prior reference.
- The "fsl,imx7d-gpc" node is leaked on every path leaving the function after it is acquired.

Release each reference immediately after of_iomap() consumes the node. of_iomap() maps the node's registers but does not retain a reference to the device_node, so it is safe to put the node once mapped; this also drops the first reference before np is reused for the second lookup.

Found by static analysis tool CodeQL.

---
 arch/arm/mach-imx/src.c | 2 ++
 1 file changed, 2 insertions(+)

index f28bfb653a88f..c3c80b4c3d53b 100644
@@ -196,6 +196,7 @@ void __init imx7_src_init(void)
 		return;
 
 	src_base = of_iomap(np, 0);
+	of_node_put(np);
 	if (!src_base)
 		return;
 

@@ -204,6 +205,7 @@ void __init imx7_src_init(void)
 		return;
 
 	gpc_base = of_iomap(np, 0);
+	of_node_put(np);
 	if (!gpc_base)
 		return;
 }

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Masney <[email protected]>

[ Upstream commit 5f2db1ce201216e81333ecc2ab51494410b2fe0d ]

The init.ops is assigned a default value, however right below it is an if, else if, and else where all of them also assign a value to init.ops. Drop the redundant init.ops assignment at the top.

---
 drivers/clk/imx/clk-scu.c | 1 -
 1 file changed, 1 deletion(-)

index 3a68576cdae76..0156cd38b6fbd 100644
@@ -481,7 +481,6 @@ struct clk_hw *__imx_clk_scu(struct device *dev, const char *name,
 	clk->clk_type = clk_type;
 
 	init.name = name;
-	init.ops = &clk_scu_ops;
 	if (rsrc_id == IMX_SC_R_A35 || rsrc_id == IMX_SC_R_A53 || rsrc_id == IMX_SC_R_A72)
 		init.ops = &clk_scu_cpu_ops;
 	else if (rsrc_id == IMX_SC_R_PI_0_PLL)

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Henrik Grimler <[email protected]>

[ Upstream commit 3b3bce4a692ac60d9f4a341e6b597dd1fd0a28f9 ]

lima_vm_create() is currently run before va_start and va_end are set up, meaning they are both 0. lima_vm_create() runs drm_mm_init() with them as arguments for the allocator, and if DRM_DEBUG_MM is enabled the DRM_MM_BUG_ON check in drm_mm_init then fires, as seen here on exynos4412-odroid-u2:

[    1.736297] ------------[ cut here ]------------
[    1.740370] kernel BUG at drivers/gpu/drm/drm_mm.c:931!
[    1.745574] Internal error: Oops - BUG: 0 [#1] SMP ARM
[    1.750697] Modules linked in:
[    1.753734] CPU: 0 UID: 0 PID: 41 Comm: kworker/u16:1 Not tainted 7.0.10-postmarketos-exynos4 #11 PREEMPT
[    1.763372] Hardware name: Samsung Exynos (Flattened Device Tree)
[    1.769446] Workqueue: events_unbound deferred_probe_work_func
[    1.775261] PC is at drm_mm_init+0x9c/0xa4
[    1.779339] LR is at lima_vm_create+0x144/0x17c

[ ... ]

Fix the issue by moving the lima_vm_create() call after va_start and va_end are set up.

---
 drivers/gpu/drm/lima/lima_device.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

index 02cef0cea6572..3843797d376b3 100644
@@ -368,12 +368,6 @@ int lima_device_init(struct lima_device *ldev)
 	if (err)
 		goto err_out0;
 
-	ldev->empty_vm = lima_vm_create(ldev);
-	if (!ldev->empty_vm) {
-		err = -ENOMEM;
-		goto err_out1;
-	}
-
 	ldev->va_start = 0;
 	if (ldev->id == lima_gpu_mali450) {
 		ldev->va_end = LIMA_VA_RESERVE_START;

@@ -387,6 +381,12 @@ int lima_device_init(struct lima_device *ldev)
 	} else
 		ldev->va_end = LIMA_VA_RESERVE_END;
 
+	ldev->empty_vm = lima_vm_create(ldev);
+	if (!ldev->empty_vm) {
+		err = -ENOMEM;
+		goto err_out1;
+	}
+
 	ldev->iomem = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ldev->iomem)) {
 		dev_err(ldev->dev, "fail to ioremap iomem\n");

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wei Yang <[email protected]>

[ Upstream commit 7783dcd79ae9c4aa48bc47bd4275772445dc4b2a ]

Current node_spanned_pages is got as a summation of all zone's spanned page in calculate_node_totalpages(). Generally this is good, but if we use kernelcore=mirror, it is would be wrong.

Without kernelcore=mirror:

    The test machine has below memory layout:

      memory[0x0]     [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0
      memory[0x1]     [0x0000000000100000-0x00000000bffdefff], 0x00000000bfedf000 bytes on node 0 flags: 0x0
      memory[0x2]     [0x0000000100000000-0x00000001bfffffff], 0x00000000c0000000 bytes on node 0 flags: 0x0

    And the Zone range is:

      DMA      [mem 0x0000000000001000-0x0000000000ffffff]
      DMA32    [mem 0x0000000001000000-0x00000000ffffffff]
      Normal   [mem 0x0000000100000000-0x00000001bfffffff]

    Then we see, with spanned_pages printed:

      On node 0 spanned_pages: 1835007 totalpages: 1572733

With kernelcore=mirror:

    The test machine has below memory layout:

      memory[0x0]     [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x2
      memory[0x1]     [0x0000000000100000-0x00000000bffdefff], 0x00000000bfedf000 bytes on node 0 flags: 0x2
      memory[0x2]     [0x0000000100000000-0x000000013fffffff], 0x0000000040000000 bytes on node 0 flags: 0x2
      memory[0x3]     [0x0000000140000000-0x00000001bfffffff], 0x0000000080000000 bytes on node 0 flags: 0x0

    And the Zone range is:

      DMA      [mem 0x0000000000001000-0x0000000000ffffff]
      DMA32    [mem 0x0000000001000000-0x00000000ffffffff]
      Normal   [mem 0x0000000100000000-0x00000001bfffffff]
      Device   empty
    Movable zone start for each node
      Node 0: 0x0000000140000000

    Then we see, with spanned_pages printed:

      On node 0 spanned_pages: 2359295 totalpages: 1572733

The total range of memory on node 0 doesn't change, but the spanned_pages becomes much larger.

The reason is when kernelcore=mirror is specified, the range of Zone Normal and Zone Movable would overlap. So the overlapped range would be calculated twice.

A wrong node_spanned_pages would effect defer_init(), since each zone_end_pfn is less than pgdat_end_pfn().

As we already passed in node_start_pfn and node_end_pfn, fix this by get it from (node_start_pfn - node_end_pfn) directly.

---
 mm/mm_init.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

index 1aba3e8737d88..45c5a7ca96097 100644
@@ -1279,7 +1279,7 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat,
 						unsigned long node_start_pfn,
 						unsigned long node_end_pfn)
 {
-	unsigned long realtotalpages = 0, totalpages = 0;
+	unsigned long realtotalpages = 0;
 	enum zone_type i;
 
 	for (i = 0; i < MAX_NR_ZONES; i++) {

@@ -1309,11 +1309,10 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat,
 		zone->present_early_pages = real_size;
 #endif
 
-		totalpages += spanned;
 		realtotalpages += real_size;
 	}
 
-	pgdat->node_spanned_pages = totalpages;
+	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
 	pgdat->node_present_pages = realtotalpages;
 	pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
 }

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chen, Yu C <[email protected]>

[ Upstream commit 4f166adb5cb0525d9e32d45729fd8f28c80acbee ]

A divide-by-zero crash is observed when running hackbench:

   [14697.488452] CPU: 112 UID: 0 PID: 124791 Comm: hackbench Not tainted 7.1.0-rc2+
   [14697.492627] RIP: 0010:propagate_entity_load_avg+0x35f/0x3e0
   [14697.506799]  <TASK>
   [14697.507411]  __dequeue_task+0x2b4/0xc70
   [14697.508677]  dequeue_task_fair+0x36/0x370
   [14697.509047]  dequeue_task+0x101/0x2f0
   [14697.509426]  __schedule+0x1b1/0x1a00
   [14697.510868]  anon_pipe_read+0x3da/0x450
   [14697.511400]  vfs_read+0x361/0x390
   [14697.512053]  __x64_sys_read+0x19/0x30

The divide-by-zero happens here:

  if (scale_load_down(gcfs_rq->load.weight)) {
           load_sum = div_u64(gcfs_rq->avg.load_sum,
                              scale_load_down(gcfs_rq->load.weight));
  }

gcfs_rq->load.weight is an insane large value and is truncated to the lower 32 bits by div_u64, which happen to be 0.

Using AI for investigation, the cause is a u32 overflow in update_tg_cfs_runnable(), and flat pickup became a victim when using tg_tasks():

u32 new_sum, divider;
...
new_sum = se->avg.runnable_avg * divider; <-- boom

The following sequence shows how this triggers the crash:

propagate_entity_load_avg()
update_tg_cfs_runnable() # u32 overflow corrupts runnable_sum

__update_load_avg_cfs_rq()
___update_load_avg() # computes insane runnable_avg
update_tg_load_avg() # propagates to tg->runnable_avg

update_cfs_group()

     calc_concur_shares()
       tg_tasks()                 # long-to-int truncation, negative nr
     reweight_entity()            # corrupted se->load.weight
       update_load_add()          # corrupted cfs_rq->load.weight

propagate_entity_load_avg()
update_tg_cfs_load()
div_u64() # divide-by-zero

Fix by widening new_sum from u32 to u64 (no need to force tg_tasks() to return unsigned long after this fix)

---
 kernel/sched/fair.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index c3a6b66b836c0..a36ee92e3075a 100644
@@ -4312,7 +4312,8 @@ static inline void
 update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
 	long delta_sum, delta_avg = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg;
-	u32 new_sum, divider;
+	u64 new_sum;
+	u32 divider;
 
 	/* Nothing to update */
 	if (!delta_avg)

@@ -4326,7 +4327,7 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf
 
 	/* Set new sched_entity's runnable */
 	se->avg.runnable_avg = gcfs_rq->avg.runnable_avg;
-	new_sum = se->avg.runnable_avg * divider;
+	new_sum = (u64)se->avg.runnable_avg * divider;
 	delta_sum = (long)new_sum - (long)se->avg.runnable_sum;
 	se->avg.runnable_sum = new_sum;
 

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zide Chen <[email protected]>

[ Upstream commit 3012af7df3430788eddd30b3c6654d0a0a5f06c6 ]

uncore_event_cpu_online() returns -ENOMEM early when both the MSR and MMIO box allocations fail. This also aborts PCI uncore setup, even though PCI PMUs are independent of the MSR/MMIO paths.

Remove the early return so PCI uncore setup always runs regardless of whether MSR or MMIO box allocation succeeds.

---
 arch/x86/events/intel/uncore.c | 2 --
 1 file changed, 2 deletions(-)

index 42dba09461dae..6769820a007b7 100644
@@ -1607,8 +1607,6 @@ static int uncore_event_cpu_online(unsigned int cpu)
 	die = topology_logical_die_id(cpu);
 	msr_ret = uncore_box_ref(uncore_msr_uncores, die, cpu);
 	mmio_ret = uncore_box_ref(uncore_mmio_uncores, die, cpu);
-	if (msr_ret && mmio_ret)
-		return -ENOMEM;
 
 	/*
 	 * Check if there is an online cpu in the package

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniel McCarthy <[email protected]>

[ Upstream commit 32711f77db0641e57fd96fdc013bf1286b9f2514 ]

If the devm_pinctrl_register() function fails, bcm2835_pinctrl_probe() calls gpiochip_remove() before gpiochip_add_data() has registered the GPIO chip.

This means that upon failure the gpio_chip.gpiodev
is NULL resulting in a null pointer dereference
inside the gpiochip_remove() function.

Remove the unnecessary function call to gpiochip_remove(). No GPIO cleanup is required because the GPIO chip has not yet been registered. Without this change there is potential for a kernel panic upon registration failure

---
 drivers/pinctrl/bcm/pinctrl-bcm2835.c | 1 -
 1 file changed, 1 deletion(-)

index 1489191a213fe..8f3470d576e43 100644
@@ -1280,7 +1280,6 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev)
 	pc->pctl_desc = *pdata->pctl_desc;
 	pc->pctl_dev = devm_pinctrl_register(dev, &pc->pctl_desc, pc);
 	if (IS_ERR(pc->pctl_dev)) {
-		gpiochip_remove(&pc->gpio_chip);
 		return PTR_ERR(pc->pctl_dev);
 	}
 

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Young <[email protected]>

[ Upstream commit 5370facb7b4461166a4610d456fefeb92ef50a82 ]

Since commit 206241069ecf ("[media] rc/keymaps: Remove the obsolete rc-rc5-tv keymap"), the rc-rc5-tv keymap is no longer in the tree.

---
 include/media/rc-map.h | 1 -
 1 file changed, 1 deletion(-)

index 4676545ffd8fa..e26e3577d11d1 100644
@@ -308,7 +308,6 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_PROTEUS_2309              "rc-proteus-2309"
 #define RC_MAP_PURPLETV                  "rc-purpletv"
 #define RC_MAP_PV951                     "rc-pv951"
-#define RC_MAP_RC5_TV                    "rc-rc5-tv"
 #define RC_MAP_RC6_MCE                   "rc-rc6-mce"
 #define RC_MAP_REAL_AUDIO_220_32_KEYS    "rc-real-audio-220-32-keys"
 #define RC_MAP_REDDO                     "rc-reddo"

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Young <[email protected]>

[ Upstream commit 6e5deb2923b0d1b73c77a1a77c30b0da43d9e022 ]

Since commit af86ce79f020 ("[media] remove the old RC_MAP_HAUPPAUGE_NEW RC map"), the RC_MAP_HAUPPAUGE_NEW define is no longer used.

---
 include/media/rc-map.h | 1 -
 1 file changed, 1 deletion(-)

index e26e3577d11d1..b7805ecce62b5 100644
@@ -262,7 +262,6 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_GENIUS_TVGO_A11MCE        "rc-genius-tvgo-a11mce"
 #define RC_MAP_GOTVIEW7135               "rc-gotview7135"
 #define RC_MAP_HAUPPAUGE                 "rc-hauppauge"
-#define RC_MAP_HAUPPAUGE_NEW             "rc-hauppauge"
 #define RC_MAP_HISI_POPLAR               "rc-hisi-poplar"
 #define RC_MAP_HISI_TV_DEMO              "rc-hisi-tv-demo"
 #define RC_MAP_IMON_MCE                  "rc-imon-mce"

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Weilin Wang <[email protected]>

[ Upstream commit 8f95b29c73e181274759c3f9483ba7f875447e3c ]

The original test report was too complicated to read with information that not really useful. This new update simplify the report which should largely improve the readibility.

Stable-dep-of: 8953bfd8820b ("perf tests: Skip metrics validation if system-wide recording lacks permission")

---
 .../tests/shell/lib/perf_metric_validation.py | 231 ++++++++++--------
 tools/perf/tests/shell/stat_metrics_values.sh |   4 +-
 2 files changed, 127 insertions(+), 108 deletions(-)

index 50a34a9cc0400..a2d235252183b 100644
@@ -1,4 +1,4 @@
-#SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: GPL-2.0
 import re
 import csv
 import json

@@ -6,36 +6,61 @@ import argparse
 from pathlib import Path
 import subprocess
 
+
+class TestError:
+    def __init__(self, metric: list[str], wl: str, value: list[float], low: float, up=float('nan'), description=str()):
+        self.metric: list = metric  # multiple metrics in relationship type tests
+        self.workloads = [wl]  # multiple workloads possible
+        self.collectedValue: list = value
+        self.valueLowBound = low
+        self.valueUpBound = up
+        self.description = description
+
+    def __repr__(self) -> str:
+        if len(self.metric) > 1:
+            return "\nMetric Relationship Error: \tThe collected value of metric {0}\n\
+                \tis {1} in workload(s): {2} \n\
+                \tbut expected value range is [{3}, {4}]\n\
+                \tRelationship rule description: \'{5}\'".format(self.metric, self.collectedValue, self.workloads,
+                                                                 self.valueLowBound, self.valueUpBound, self.description)
+        elif len(self.collectedValue) == 0:
+            return "\nNo Metric Value Error: \tMetric {0} returns with no value \n\
+                    \tworkload(s): {1}".format(self.metric, self.workloads)
+        else:
+            return "\nWrong Metric Value Error: \tThe collected value of metric {0}\n\
+                    \tis {1} in workload(s): {2}\n\
+                    \tbut expected value range is [{3}, {4}]"\
+                        .format(self.metric, self.collectedValue, self.workloads,
+                                self.valueLowBound, self.valueUpBound)
+
+
 class Validator:
     def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', workload='true', metrics=''):
         self.rulefname = rulefname
         self.reportfname = reportfname
         self.rules = None
-        self.collectlist:str = metrics
+        self.collectlist: str = metrics
         self.metrics = self.__set_metrics(metrics)
         self.skiplist = set()
         self.tolerance = t
 
         self.workloads = [x for x in workload.split(",") if x]
-        self.wlidx = 0 # idx of current workloads
-        self.allresults = dict() # metric results of all workload
-        self.allignoremetrics = dict() # metrics with no results or negative results
-        self.allfailtests = dict()
+        self.wlidx = 0  # idx of current workloads
+        self.allresults = dict()  # metric results of all workload
         self.alltotalcnt = dict()
         self.allpassedcnt = dict()
-        self.allerrlist = dict()
 
-        self.results = dict() # metric results of current workload
+        self.results = dict()  # metric results of current workload
         # vars for test pass/failure statistics
-        self.ignoremetrics= set() # metrics with no results or negative results, neg result counts as a failed test
-        self.failtests = dict()
+        # metrics with no results or negative results, neg result counts failed tests
+        self.ignoremetrics = set()
         self.totalcnt = 0
         self.passedcnt = 0
         # vars for errors
         self.errlist = list()
 
         # vars for Rule Generator
-        self.pctgmetrics = set() # Percentage rule
+        self.pctgmetrics = set()  # Percentage rule
 
         # vars for debug
         self.datafname = datafname

@@ -69,10 +94,10 @@ class Validator:
                       ensure_ascii=True,
                       indent=4)
 
-    def get_results(self, idx:int = 0):
+    def get_results(self, idx: int = 0):
         return self.results[idx]
 
-    def get_bounds(self, lb, ub, error, alias={}, ridx:int = 0) -> list:
+    def get_bounds(self, lb, ub, error, alias={}, ridx: int = 0) -> list:
         """
         Get bounds and tolerance from lb, ub, and error.
         If missing lb, use 0.0; missing ub, use float('inf); missing error, use self.tolerance.

@@ -85,7 +110,7 @@ class Validator:
                   tolerance, denormalized base on upper bound value
         """
         # init ubv and lbv to invalid values
-        def get_bound_value (bound, initval, ridx):
+        def get_bound_value(bound, initval, ridx):
             val = initval
             if isinstance(bound, int) or isinstance(bound, float):
                 val = bound

@@ -113,10 +138,10 @@ class Validator:
 
         return lbv, ubv, denormerr
 
-    def get_value(self, name:str, ridx:int = 0) -> list:
+    def get_value(self, name: str, ridx: int = 0) -> list:
         """
         Get value of the metric from self.results.
-        If result of this metric is not provided, the metric name will be added into self.ignoremetics and self.errlist.
+        If result of this metric is not provided, the metric name will be added into self.ignoremetics.
         All future test(s) on this metric will fail.
 
         @param name: name of the metric

@@ -142,7 +167,7 @@ class Validator:
         Check if metrics value are non-negative.
         One metric is counted as one test.
         Failure: when metric value is negative or not provided.
-        Metrics with negative value will be added into the self.failtests['PositiveValueTest'] and self.ignoremetrics.
+        Metrics with negative value will be added into self.ignoremetrics.
         """
         negmetric = dict()
         pcnt = 0

@@ -155,25 +180,27 @@ class Validator:
             else:
                 pcnt += 1
             tcnt += 1
+        # The first round collect_perf() run these metrics with simple workload
+        # "true". We give metrics a second chance with a longer workload if less
+        # than 20 metrics failed positive test.
         if len(rerun) > 0 and len(rerun) < 20:
             second_results = dict()
             self.second_test(rerun, second_results)
             for name, val in second_results.items():
-                if name not in negmetric: continue
+                if name not in negmetric:
+                    continue
                 if val >= 0:
                     del negmetric[name]
                     pcnt += 1
 
-        self.failtests['PositiveValueTest']['Total Tests'] = tcnt
-        self.failtests['PositiveValueTest']['Passed Tests'] = pcnt
         if len(negmetric.keys()):
             self.ignoremetrics.update(negmetric.keys())
-            negmessage = ["{0}(={1:.4f})".format(name, val) for name, val in negmetric.items()]
-            self.failtests['PositiveValueTest']['Failed Tests'].append({'NegativeValue': negmessage})
+            self.errlist.extend(
+                [TestError([m], self.workloads[self.wlidx], negmetric[m], 0) for m in negmetric.keys()])
 
         return
 
-    def evaluate_formula(self, formula:str, alias:dict, ridx:int = 0):
+    def evaluate_formula(self, formula: str, alias: dict, ridx: int = 0):
         """
         Evaluate the value of formula.
 

@@ -187,10 +214,11 @@ class Validator:
         sign = "+"
         f = str()
 
-        #TODO: support parenthesis?
+        # TODO: support parenthesis?
         for i in range(len(formula)):
             if i+1 == len(formula) or formula[i] in ('+', '-', '*', '/'):
-                s = alias[formula[b:i]] if i+1 < len(formula) else alias[formula[b:]]
+                s = alias[formula[b:i]] if i + \
+                    1 < len(formula) else alias[formula[b:]]
                 v = self.get_value(s, ridx)
                 if not v:
                     errs.append(s)

@@ -228,49 +256,49 @@ class Validator:
         alias = dict()
         for m in rule['Metrics']:
             alias[m['Alias']] = m['Name']
-        lbv, ubv, t = self.get_bounds(rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold'], alias, ridx=rule['RuleIndex'])
-        val, f = self.evaluate_formula(rule['Formula'], alias, ridx=rule['RuleIndex'])
+        lbv, ubv, t = self.get_bounds(
+            rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold'], alias, ridx=rule['RuleIndex'])
+        val, f = self.evaluate_formula(
+            rule['Formula'], alias, ridx=rule['RuleIndex'])
+
+        lb = rule['RangeLower']
+        ub = rule['RangeUpper']
+        if isinstance(lb, str):
+            if lb in alias:
+                lb = alias[lb]
+        if isinstance(ub, str):
+            if ub in alias:
+                ub = alias[ub]
+
         if val == -1:
-            self.failtests['RelationshipTest']['Failed Tests'].append({'RuleIndex': rule['RuleIndex'], 'Description':f})
+            self.errlist.append(TestError([m['Name'] for m in rule['Metrics']], self.workloads[self.wlidx], [],
+                                lb, ub, rule['Description']))
         elif not self.check_bound(val, lbv, ubv, t):
-            lb = rule['RangeLower']
-            ub = rule['RangeUpper']
-            if isinstance(lb, str):
-                if lb in alias:
-                    lb = alias[lb]
-            if isinstance(ub, str):
-                if ub in alias:
-                    ub = alias[ub]
-            self.failtests['RelationshipTest']['Failed Tests'].append({'RuleIndex': rule['RuleIndex'], 'Formula':f,
-                                                                       'RangeLower': lb, 'LowerBoundValue': self.get_value(lb),
-                                                                       'RangeUpper': ub, 'UpperBoundValue':self.get_value(ub),
-                                                                       'ErrorThreshold': t, 'CollectedValue': val})
+            self.errlist.append(TestError([m['Name'] for m in rule['Metrics']], self.workloads[self.wlidx], [val],
+                                lb, ub, rule['Description']))
         else:
             self.passedcnt += 1
-            self.failtests['RelationshipTest']['Passed Tests'] += 1
         self.totalcnt += 1
-        self.failtests['RelationshipTest']['Total Tests'] += 1
 
         return
 
-
     # Single Metric Test
-    def single_test(self, rule:dict):
+    def single_test(self, rule: dict):
         """
         Validate if the metrics are in the required value range.
         eg. lower_bound <= metrics_value <= upper_bound
         One metric is counted as one test in this type of test.
         One rule may include one or more metrics.
         Failure: when the metric value not provided or the value is outside the bounds.
-        This test updates self.total_cnt and records failed tests in self.failtest['SingleMetricTest'].
+        This test updates self.total_cnt.
 
         @param rule: dict with metrics to validate and the value range requirement
         """
-        lbv, ubv, t = self.get_bounds(rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold'])
+        lbv, ubv, t = self.get_bounds(
+            rule['RangeLower'], rule['RangeUpper'], rule['ErrorThreshold'])
         metrics = rule['Metrics']
         passcnt = 0
         totalcnt = 0
-        faillist = list()
         failures = dict()
         rerun = list()
         for m in metrics:

@@ -286,25 +314,20 @@ class Validator:
             second_results = dict()
             self.second_test(rerun, second_results)
             for name, val in second_results.items():
-                if name not in failures: continue
+                if name not in failures:
+                    continue
                 if self.check_bound(val, lbv, ubv, t):
                     passcnt += 1
                     del failures[name]
                 else:
-                    failures[name] = val
+                    failures[name] = [val]
                     self.results[0][name] = val
 
         self.totalcnt += totalcnt
         self.passedcnt += passcnt
-        self.failtests['SingleMetricTest']['Total Tests'] += totalcnt
-        self.failtests['SingleMetricTest']['Passed Tests'] += passcnt
         if len(failures.keys()) != 0:
-            faillist = [{'MetricName':name, 'CollectedValue':val} for name, val in failures.items()]
-            self.failtests['SingleMetricTest']['Failed Tests'].append({'RuleIndex':rule['RuleIndex'],
-                                                                       'RangeLower': rule['RangeLower'],
-                                                                       'RangeUpper': rule['RangeUpper'],
-                                                                       'ErrorThreshold':rule['ErrorThreshold'],
-                                                                       'Failure':faillist})
+            self.errlist.extend([TestError([name], self.workloads[self.wlidx], val,
+                                rule['RangeLower'], rule['RangeUpper']) for name, val in failures.items()])
 
         return
 

@@ -312,19 +335,11 @@ class Validator:
         """
         Create final report and write into a JSON file.
         """
-        alldata = list()
-        for i in range(0, len(self.workloads)):
-            reportstas = {"Total Rule Count": self.alltotalcnt[i], "Passed Rule Count": self.allpassedcnt[i]}
-            data = {"Metric Validation Statistics": reportstas, "Tests in Category": self.allfailtests[i],
-                    "Errors":self.allerrlist[i]}
-            alldata.append({"Workload": self.workloads[i], "Report": data})
-
-        json_str = json.dumps(alldata, indent=4)
-        print("Test validation finished. Final report: ")
-        print(json_str)
+        print(self.errlist)
 
         if self.debug:
-            allres = [{"Workload": self.workloads[i], "Results": self.allresults[i]} for i in range(0, len(self.workloads))]
+            allres = [{"Workload": self.workloads[i], "Results": self.allresults[i]}
+                      for i in range(0, len(self.workloads))]
             self.json_dump(allres, self.datafname)
 
     def check_rule(self, testtype, metric_list):

@@ -342,13 +357,13 @@ class Validator:
         return True
 
     # Start of Collector and Converter
-    def convert(self, data: list, metricvalues:dict):
+    def convert(self, data: list, metricvalues: dict):
         """
         Convert collected metric data from the -j output to dict of {metric_name:value}.
         """
         for json_string in data:
             try:
-                result =json.loads(json_string)
+                result = json.loads(json_string)
                 if "metric-unit" in result and result["metric-unit"] != "(null)" and result["metric-unit"] != "":
                     name = result["metric-unit"].split("  ")[1] if len(result["metric-unit"].split("  ")) > 1 \
                         else result["metric-unit"]

@@ -365,9 +380,10 @@ class Validator:
         print(" ".join(command))
         cmd = subprocess.run(command, stderr=subprocess.PIPE, encoding='utf-8')
         data = [x+'}' for x in cmd.stderr.split('}\n') if x]
+        if data[0][0] != '{':
+            data[0] = data[0][data[0].find('{'):]
         return data
 
-
     def collect_perf(self, workload: str):
         """
         Collect metric data with "perf stat -M" on given workload with -a and -j.

@@ -385,14 +401,18 @@ class Validator:
             if rule["TestType"] == "RelationshipTest":
                 metrics = [m["Name"] for m in rule["Metrics"]]
                 if not any(m not in collectlist[0] for m in metrics):
-                    collectlist[rule["RuleIndex"]] = [",".join(list(set(metrics)))]
+                    collectlist[rule["RuleIndex"]] = [
+                        ",".join(list(set(metrics)))]
 
         for idx, metrics in collectlist.items():
-            if idx == 0: wl = "true"
-            else: wl = workload
+            if idx == 0:
+                wl = "true"
+            else:
+                wl = workload
             for metric in metrics:
                 data = self._run_perf(metric, wl)
-                if idx not in self.results: self.results[idx] = dict()
+                if idx not in self.results:
+                    self.results[idx] = dict()
                 self.convert(data, self.results[idx])
         return
 

@@ -412,7 +432,8 @@ class Validator:
         2) create metric name list
         """
         command = ['perf', 'list', '-j', '--details', 'metrics']
-        cmd = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, encoding='utf-8')
+        cmd = subprocess.run(command, stdout=subprocess.PIPE,
+                             stderr=subprocess.PIPE, encoding='utf-8')
         try:
             data = json.loads(cmd.stdout)
             for m in data:

@@ -453,12 +474,12 @@ class Validator:
         rules = data['RelationshipRules']
         self.skiplist = set([name.lower() for name in data['SkipList']])
         self.rules = self.remove_unsupported_rules(rules)
-        pctgrule = {'RuleIndex':0,
-                    'TestType':'SingleMetricTest',
-                    'RangeLower':'0',
+        pctgrule = {'RuleIndex': 0,
+                    'TestType': 'SingleMetricTest',
+                    'RangeLower': '0',
                     'RangeUpper': '100',
                     'ErrorThreshold': self.tolerance,
-                    'Description':'Metrics in percent unit have value with in [0, 100]',
+                    'Description': 'Metrics in percent unit have value with in [0, 100]',
                     'Metrics': [{'Name': m.lower()} for m in self.pctgmetrics]}
         self.rules.append(pctgrule)
 

@@ -469,8 +490,9 @@ class Validator:
             idx += 1
 
         if self.debug:
-            #TODO: need to test and generate file name correctly
-            data = {'RelationshipRules':self.rules, 'SupportedMetrics': [{"MetricName": name} for name in self.metrics]}
+            # TODO: need to test and generate file name correctly
+            data = {'RelationshipRules': self.rules, 'SupportedMetrics': [
+                {"MetricName": name} for name in self.metrics]}
             self.json_dump(data, self.fullrulefname)
 
         return

@@ -482,20 +504,17 @@ class Validator:
         @param key: key to the dictionaries (index of self.workloads).
         '''
         self.allresults[key] = self.results
-        self.allignoremetrics[key] = self.ignoremetrics
-        self.allfailtests[key] = self.failtests
         self.alltotalcnt[key] = self.totalcnt
         self.allpassedcnt[key] = self.passedcnt
-        self.allerrlist[key] = self.errlist
 
-    #Initialize data structures before data validation of each workload
+    # Initialize data structures before data validation of each workload
     def _init_data(self):
 
-        testtypes = ['PositiveValueTest', 'RelationshipTest', 'SingleMetricTest']
+        testtypes = ['PositiveValueTest',
+                     'RelationshipTest', 'SingleMetricTest']
         self.results = dict()
-        self.ignoremetrics= set()
+        self.ignoremetrics = set()
         self.errlist = list()
-        self.failtests = {k:{'Total Tests':0, 'Passed Tests':0, 'Failed Tests':[]} for k in testtypes}
         self.totalcnt = 0
         self.passedcnt = 0
 

@@ -525,32 +544,33 @@ class Validator:
                 testtype = r['TestType']
                 if not self.check_rule(testtype, r['Metrics']):
                     continue
-                if  testtype == 'RelationshipTest':
+                if testtype == 'RelationshipTest':
                     self.relationship_test(r)
                 elif testtype == 'SingleMetricTest':
                     self.single_test(r)
                 else:
                     print("Unsupported Test Type: ", testtype)
-                    self.errlist.append("Unsupported Test Type from rule: " + r['RuleIndex'])
-            self._storewldata(i)
             print("Workload: ", self.workloads[i])
-            print("Total metrics collected: ", self.failtests['PositiveValueTest']['Total Tests'])
-            print("Non-negative metric count: ", self.failtests['PositiveValueTest']['Passed Tests'])
             print("Total Test Count: ", self.totalcnt)
             print("Passed Test Count: ", self.passedcnt)
-
+            self._storewldata(i)
         self.create_report()
-        return sum(self.alltotalcnt.values()) != sum(self.allpassedcnt.values())
+        return len(self.errlist) > 0
 # End of Class Validator
 
 
 def main() -> None:
-    parser = argparse.ArgumentParser(description="Launch metric value validation")
-
-    parser.add_argument("-rule", help="Base validation rule file", required=True)
-    parser.add_argument("-output_dir", help="Path for validator output file, report file", required=True)
-    parser.add_argument("-debug", help="Debug run, save intermediate data to files", action="store_true", default=False)
-    parser.add_argument("-wl", help="Workload to run while data collection", default="true")
+    parser = argparse.ArgumentParser(
+        description="Launch metric value validation")
+
+    parser.add_argument(
+        "-rule", help="Base validation rule file", required=True)
+    parser.add_argument(
+        "-output_dir", help="Path for validator output file, report file", required=True)
+    parser.add_argument("-debug", help="Debug run, save intermediate data to files",
+                        action="store_true", default=False)
+    parser.add_argument(
+        "-wl", help="Workload to run while data collection", default="true")
     parser.add_argument("-m", help="Metric list to validate", default="")
     args = parser.parse_args()
     outpath = Path(args.output_dir)

@@ -559,8 +579,8 @@ def main() -> None:
     datafile = Path.joinpath(outpath, 'perf_data.json')
 
     validator = Validator(args.rule, reportf, debug=args.debug,
-                        datafname=datafile, fullrulefname=fullrule, workload=args.wl,
-                        metrics=args.m)
+                          datafname=datafile, fullrulefname=fullrule, workload=args.wl,
+                          metrics=args.m)
     ret = validator.test()
 
     return ret

@@ -569,6 +589,3 @@ def main() -> None:
 if __name__ == "__main__":
     import sys
     sys.exit(main())
-
-
-

index ad94c936de7e8..dc93f03a90e63 100755
@@ -25,6 +25,8 @@ echo "Output will be stored in: $tmpdir"
 $PYTHON $pythonvalidator -rule $rulefile -output_dir $tmpdir -wl "${workload}"
 ret=$?
 rm -rf $tmpdir
-
+if [ $ret -ne 0 ]; then
+	echo "Metric validation return with erros. Please check metrics reported with errors."
+fi
 exit $ret
 

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

[ Upstream commit e2cb1db7daf8b7863aeec07bb574d3fae54518e6 ]

Like in the metricgroup tests, it should check the permission first and then skip relevant failures accordingly.

Also it needs to try again with the system wide flag properly. On the second round, check if the result has the metric name because other failure cases are checked in the first round already.

Stable-dep-of: 8953bfd8820b ("perf tests: Skip metrics validation if system-wide recording lacks permission")

---
 tools/perf/tests/shell/stat_all_metrics.sh | 87 ++++++++++++++++------
 1 file changed, 66 insertions(+), 21 deletions(-)

index 54774525e18a7..73e9347e88a96 100755
@@ -2,42 +2,87 @@
 # perf all metrics test
 # SPDX-License-Identifier: GPL-2.0
 
+ParanoidAndNotRoot()
+{
+  [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
+}
+
+system_wide_flag="-a"
+if ParanoidAndNotRoot 0
+then
+  system_wide_flag=""
+fi
+
 err=0
 for m in $(perf list --raw-dump metrics); do
   echo "Testing $m"
-  result=$(perf stat -M "$m" true 2>&1)
-  if [[ "$result" =~ ${m:0:50} ]] || [[ "$result" =~ "<not supported>" ]]
+  result=$(perf stat -M "$m" $system_wide_flag -- sleep 0.01 2>&1)
+  result_err=$?
+  if [[ $result_err -gt 0 ]]
   then
-    continue
+    if [[ "$result" =~ \
+          "Access to performance monitoring and observability operations is limited" ]]
+    then
+      echo "Permission failure"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
+    then
+      echo "Permissions - need system wide mode"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "<not supported>" ]]
+    then
+      echo "Not supported events"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
+    then
+      echo "FP issues"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    elif [[ "$result" =~ "PMM" ]]
+    then
+      echo "Optane memory issues"
+      echo $result
+      if [[ $err -eq 0 ]]
+      then
+        err=2 # Skip
+      fi
+      continue
+    fi
   fi
-  # Failed so try system wide.
-  result=$(perf stat -M "$m" -a sleep 0.01 2>&1)
+
   if [[ "$result" =~ ${m:0:50} ]]
   then
     continue
   fi
-  # Failed again, possibly the workload was too small so retry with something
-  # longer.
-  result=$(perf stat -M "$m" perf bench internals synthesize 2>&1)
+
+  # Failed, possibly the workload was too small so retry with something longer.
+  result=$(perf stat -M "$m" $system_wide_flag -- perf bench internals synthesize 2>&1)
   if [[ "$result" =~ ${m:0:50} ]]
   then
     continue
   fi
   echo "Metric '$m' not printed in:"
   echo "$result"
-  if [[ "$err" != "1" ]]
-  then
-    err=2
-    if [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
-    then
-      echo "Skip, not fail, for FP issues"
-    elif [[ "$result" =~ "PMM" ]]
-    then
-      echo "Skip, not fail, for Optane memory issues"
-    else
-      err=1
-    fi
-  fi
+  err=1
 done
 
 exit "$err"

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 08d9e883481b2c38326ed37314b1f6a1284c03d8 ]

Issue reported by Thomas Falcon and diagnosed by Kan Liang here:
https://lore.kernel.org/lkml/[email protected]/
Metrics with missing events can be erroneously skipped if they contain FP, AMX or PMM events.

Stable-dep-of: 8953bfd8820b ("perf tests: Skip metrics validation if system-wide recording lacks permission")

---
 tools/perf/tests/shell/stat_all_metrics.sh | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

index 73e9347e88a96..ee817c66da061 100755
@@ -20,7 +20,13 @@ for m in $(perf list --raw-dump metrics); do
   result_err=$?
   if [[ $result_err -gt 0 ]]
   then
-    if [[ "$result" =~ \
+    if [[ "$result" =~ "Cannot resolve IDs for" ]]
+    then
+      echo "Metric contains missing events"
+      echo $result
+      err=1 # Fail
+      continue
+    elif [[ "$result" =~ \
           "Access to performance monitoring and observability operations is limited" ]]
     then
       echo "Permission failure"

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 365e02ddb65d443f1ba16af5a4ddcd638f1e7823 ]

When permissions are limited running sleep without system wide isn't a good benchmark to run to achieve samples, switch to running noploop.

Remove indent for non-success cases.

Allow skip for the not counted case.

Minor debug changes.

Stable-dep-of: 8953bfd8820b ("perf tests: Skip metrics validation if system-wide recording lacks permission")

---
 tools/perf/tests/shell/stat_all_metrics.sh | 118 +++++++++++----------
 1 file changed, 64 insertions(+), 54 deletions(-)

index ee817c66da061..6fa585a1e34c9 100755
@@ -7,86 +7,96 @@ ParanoidAndNotRoot()
   [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
 }
 
+test_prog="sleep 0.01"
 system_wide_flag="-a"
 if ParanoidAndNotRoot 0
 then
   system_wide_flag=""
+  test_prog="perf test -w noploop"
 fi
 
 err=0
 for m in $(perf list --raw-dump metrics); do
   echo "Testing $m"
-  result=$(perf stat -M "$m" $system_wide_flag -- sleep 0.01 2>&1)
+  result=$(perf stat -M "$m" $system_wide_flag -- $test_prog 2>&1)
   result_err=$?
-  if [[ $result_err -gt 0 ]]
+  if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
-    if [[ "$result" =~ "Cannot resolve IDs for" ]]
-    then
-      echo "Metric contains missing events"
-      echo $result
-      err=1 # Fail
-      continue
-    elif [[ "$result" =~ \
-          "Access to performance monitoring and observability operations is limited" ]]
+    # No error result and metric shown.
+    continue
+  fi
+  if [[ "$result" =~ "Cannot resolve IDs for" ]]
+  then
+    echo "Metric contains missing events"
+    echo $result
+    err=1 # Fail
+    continue
+  elif [[ "$result" =~ \
+        "Access to performance monitoring and observability operations is limited" ]]
+  then
+    echo "Permission failure"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Permission failure"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
+  then
+    echo "Permissions - need system wide mode"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Permissions - need system wide mode"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "<not supported>" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "<not supported>" ]]
+  then
+    echo "Not supported events"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Not supported events"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "<not counted>" ]]
+  then
+    echo "Not counted events"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "FP issues"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
-    elif [[ "$result" =~ "PMM" ]]
+      err=2 # Skip
+    fi
+    continue
+  elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
+  then
+    echo "FP issues"
+    echo $result
+    if [[ $err -eq 0 ]]
     then
-      echo "Optane memory issues"
-      echo $result
-      if [[ $err -eq 0 ]]
-      then
-        err=2 # Skip
-      fi
-      continue
+      err=2 # Skip
     fi
-  fi
-
-  if [[ "$result" =~ ${m:0:50} ]]
+    continue
+  elif [[ "$result" =~ "PMM" ]]
   then
+    echo "Optane memory issues"
+    echo $result
+    if [[ $err -eq 0 ]]
+    then
+      err=2 # Skip
+    fi
     continue
   fi
 
   # Failed, possibly the workload was too small so retry with something longer.
   result=$(perf stat -M "$m" $system_wide_flag -- perf bench internals synthesize 2>&1)
-  if [[ "$result" =~ ${m:0:50} ]]
+  result_err=$?
+  if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
+    # No error result and metric shown.
     continue
   fi
-  echo "Metric '$m' not printed in:"
+  echo "Metric '$m' has non-zero error '$result_err' or not printed in:"
   echo "$result"
   err=1
 done

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 91c1949d768520d9befa7761eb97c3826997da25 ]

Default metrics may use unsupported events and be ignored. These metrics shouldn't cause metric testing to fail.

Stable-dep-of: 8953bfd8820b ("perf tests: Skip metrics validation if system-wide recording lacks permission")

---
 tools/perf/tests/shell/stat_all_metrics.sh | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

index 6fa585a1e34c9..a7edf01b39433 100755
@@ -25,8 +25,13 @@ for m in $(perf list --raw-dump metrics); do
     # No error result and metric shown.
     continue
   fi
-  if [[ "$result" =~ "Cannot resolve IDs for" ]]
+  if [[ "$result" =~ "Cannot resolve IDs for" || "$result" =~ "No supported events found" ]]
   then
+    if [[ "$m" == @(l1_prefetch_miss_rate|stalled_cycles_per_instruction) ]]
+    then
+      # Default metrics that may use unsupported events.
+      continue
+    fi
     echo "Metric contains missing events"
     echo $result
     err=1 # Fail

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 41b67ab3d2f5be9d0b6e5ba9cbec97c820fc50e8 ]

Determine if a metric is default from perf list --raw-dump $m eg:

```
$ perf list --raw-dump l1_prefetch_miss_rate
Default4 l1_prefetch_miss_rate
```

If a metric has "not supported" or "no supported events" then ignore these failures for default metrics. Tidy up the skip/fail messages in the output to make them easier to spot/read.

```
$ perf list -vv "all metrics"
...
Testing llc_miss_rate
[Ignored llc_miss_rate] failed but as a Default metric this can be expected
Error: No supported events found. The LLC-loads event is not supported.
...
```

Stable-dep-of: 8953bfd8820b ("perf tests: Skip metrics validation if system-wide recording lacks permission")

---
 tools/perf/tests/shell/stat_all_metrics.sh | 27 ++++++++++++++--------
 1 file changed, 17 insertions(+), 10 deletions(-)

index a7edf01b39433..3dabb39c7cc8c 100755
@@ -27,19 +27,20 @@ for m in $(perf list --raw-dump metrics); do
   fi
   if [[ "$result" =~ "Cannot resolve IDs for" || "$result" =~ "No supported events found" ]]
   then
-    if [[ "$m" == @(l1_prefetch_miss_rate|stalled_cycles_per_instruction) ]]
+    if [[ $(perf list --raw-dump $m) == "Default"* ]]
     then
-      # Default metrics that may use unsupported events.
+      echo "[Ignored $m] failed but as a Default metric this can be expected"
+      echo $result
       continue
     fi
-    echo "Metric contains missing events"
+    echo "[Failed $m] Metric contains missing events"
     echo $result
     err=1 # Fail
     continue
   elif [[ "$result" =~ \
         "Access to performance monitoring and observability operations is limited" ]]
   then
-    echo "Permission failure"
+    echo "[Skipped $m] Permission failure"
     echo $result
     if [[ $err -eq 0 ]]
     then

@@ -48,7 +49,7 @@ for m in $(perf list --raw-dump metrics); do
     continue
   elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]
   then
-    echo "Permissions - need system wide mode"
+    echo "[Skipped $m] Permissions - need system wide mode"
     echo $result
     if [[ $err -eq 0 ]]
     then

@@ -57,7 +58,13 @@ for m in $(perf list --raw-dump metrics); do
     continue
   elif [[ "$result" =~ "<not supported>" ]]
   then
-    echo "Not supported events"
+    if [[ $(perf list --raw-dump $m) == "Default"* ]]
+    then
+      echo "[Ignored $m] failed but as a Default metric this can be expected"
+      echo $result
+      continue
+    fi
+    echo "[Skipped $m] Not supported events"
     echo $result
     if [[ $err -eq 0 ]]
     then

@@ -66,7 +73,7 @@ for m in $(perf list --raw-dump metrics); do
     continue
   elif [[ "$result" =~ "<not counted>" ]]
   then
-    echo "Not counted events"
+    echo "[Skipped $m] Not counted events"
     echo $result
     if [[ $err -eq 0 ]]
     then

@@ -75,7 +82,7 @@ for m in $(perf list --raw-dump metrics); do
     continue
   elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]
   then
-    echo "FP issues"
+    echo "[Skipped $m] FP issues"
     echo $result
     if [[ $err -eq 0 ]]
     then

@@ -84,7 +91,7 @@ for m in $(perf list --raw-dump metrics); do
     continue
   elif [[ "$result" =~ "PMM" ]]
   then
-    echo "Optane memory issues"
+    echo "[Skipped $m] Optane memory issues"
     echo $result
     if [[ $err -eq 0 ]]
     then

@@ -101,7 +108,7 @@ for m in $(perf list --raw-dump metrics); do
     # No error result and metric shown.
     continue
   fi
-  echo "Metric '$m' has non-zero error '$result_err' or not printed in:"
+  echo "[Failed $m] has non-zero error '$result_err' or not printed in:"
   echo "$result"
   err=1
 done

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

[ Upstream commit 1c89bc1b95fa9058f3e7cd37f1142939261417d5 ]

I think the return value of SKIP (2) should be used when it skipped the entire test suite rather than a few of them. While the FAIL should be reserved if any of test failed.

  $ perf test -vv 110
  110: perf all metrics test:
  --- start ---
  test child forked, pid 2496399
  Testing tma_core_bound
  Testing tma_info_core_ilp
  Testing tma_info_memory_l2mpki
  Testing tma_memory_bound
  Testing tma_bottleneck_irregular_overhead
  Testing tma_bottleneck_mispredictions
  Testing tma_info_bad_spec_branch_misprediction_cost
  Testing tma_info_bad_spec_ipmisp_cond_ntaken
  Testing tma_info_bad_spec_ipmisp_cond_taken
  Testing tma_info_bad_spec_ipmisp_indirect
  Testing tma_info_bad_spec_ipmisp_ret
  Testing tma_info_bad_spec_ipmispredict
  Testing tma_info_branches_callret
  Testing tma_info_branches_cond_nt
  Testing tma_info_branches_cond_tk
  Testing tma_info_branches_jump
  Testing tma_info_branches_other_branches
  Testing tma_branch_mispredicts
  Testing tma_clears_resteers
  Testing tma_machine_clears
  Testing tma_mispredicts_resteers
  Testing tma_bottleneck_big_code
  Testing tma_icache_misses
  Testing tma_itlb_misses
  Testing tma_unknown_branches
  Testing tma_info_bad_spec_spec_clears_ratio
  Testing tma_other_mispredicts
  Testing tma_branch_instructions
  Testing tma_info_frontend_tbpc
  Testing tma_info_inst_mix_bptkbranch
  Testing tma_info_inst_mix_ipbranch
  Testing tma_info_inst_mix_ipcall
  Testing tma_info_inst_mix_iptb
  Testing tma_info_system_ipfarbranch
  Testing tma_info_thread_uptb
  Testing tma_bottleneck_branching_overhead
  Testing tma_nop_instructions
  Testing tma_bottleneck_compute_bound_est
  Testing tma_divider
  Testing tma_ports_utilized_3m
  Testing tma_bottleneck_instruction_fetch_bw
  Testing tma_frontend_bound
  Testing tma_assists
  Testing tma_other_nukes
  Testing tma_serializing_operation
  Testing tma_bottleneck_data_cache_memory_bandwidth
  Testing tma_fb_full
  Testing tma_mem_bandwidth
  Testing tma_sq_full
  Testing tma_bottleneck_data_cache_memory_latency
  Testing tma_l1_latency_dependency
  Testing tma_l2_bound
  Testing tma_l3_hit_latency
  Testing tma_mem_latency
  Testing tma_store_latency
  Testing tma_bottleneck_memory_synchronization
  Testing tma_contested_accesses
  Testing tma_data_sharing
  Testing tma_false_sharing
  Testing tma_bottleneck_memory_data_tlbs
  Testing tma_dtlb_load
  Testing tma_dtlb_store
  Testing tma_backend_bound
  Testing tma_bottleneck_other_bottlenecks
  Testing tma_bottleneck_useful_work
  Testing tma_retiring
  Testing tma_info_memory_fb_hpki
  Testing tma_info_memory_l1mpki
  Testing tma_info_memory_l1mpki_load
  Testing tma_info_memory_l2hpki_all
  Testing tma_info_memory_l2hpki_load
  Testing tma_info_memory_l2mpki_all
  Testing tma_info_memory_l2mpki_load
  Testing tma_l1_bound
  Testing tma_l3_bound
  Testing tma_info_memory_l2mpki_rfo
  Testing tma_fp_scalar
  Testing tma_fp_vector
  Testing tma_fp_vector_128b
  Testing tma_fp_vector_256b
  Testing tma_fp_vector_512b
  Testing tma_port_0
  Testing tma_x87_use
  Testing tma_info_botlnk_l0_core_bound_likely
  Testing tma_info_core_fp_arith_utilization
  Testing tma_info_pipeline_execute
  Testing tma_info_system_gflops
  Testing tma_info_thread_execute_per_issue
  Testing tma_dsb
  Testing tma_info_botlnk_l2_dsb_bandwidth
  Testing tma_info_frontend_dsb_coverage
  Testing tma_decoder0_alone
  Testing tma_dsb_switches
  Testing tma_info_botlnk_l2_dsb_misses
  Testing tma_info_frontend_dsb_switch_cost
  Testing tma_info_frontend_ipdsb_miss_ret
  Testing tma_mite
  Testing tma_mite_4wide
  Testing CPUs_utilized
  Testing backend_cycles_idle
  [Ignored backend_cycles_idle] failed but as a Default metric this can be expected
  Performance counter stats for 'perf test -w noploop': <not counted> cpu-cycles:u <not supported> stalled-cycles-backend:u 1.014051473 seconds time elapsed 1.005718000 seconds user 0.008013000 seconds sys
  Testing branch_frequency
  Testing branch_miss_rate
  Testing cs_per_second
  Testing cycles_frequency
  Testing frontend_cycles_idle
  [Ignored frontend_cycles_idle] failed but as a Default metric this can be expected
  Performance counter stats for 'perf test -w noploop': <not counted> cpu-cycles:u <not supported> stalled-cycles-frontend:u 1.012813656 seconds time elapsed 1.004603000 seconds user 0.008004000 seconds sys
  Testing insn_per_cycle
  Testing migrations_per_second
  Testing page_faults_per_second
  Testing stalled_cycles_per_instruction
  [Ignored stalled_cycles_per_instruction] failed but as a Default metric this can be expected
  Error: No supported events found. The stalled-cycles-backend:u event is not supported.
  Testing tma_bad_speculation
  Testing l1d_miss_rate
  Testing llc_miss_rate
  Testing dtlb_miss_rate
  Testing itlb_miss_rate
  [Ignored itlb_miss_rate] failed but as a Default metric this can be expected
  Performance counter stats for 'perf test -w noploop': <not supported> iTLB-loads:u 3,097 iTLB-load-misses:u 1.012766732 seconds time elapsed 1.004318000 seconds user 0.008002000 seconds sys
  Testing l1i_miss_rate
  [Ignored l1i_miss_rate] failed but as a Default metric this can be expected
  Performance counter stats for 'perf test -w noploop': <not counted> L1-icache-load-misses:u <not supported> L1-icache-loads:u 1.013606395 seconds time elapsed 1.001371000 seconds user 0.011968000 seconds sys
  Testing l1_prefetch_miss_rate
  [Ignored l1_prefetch_miss_rate] failed but as a Default metric this can be expected
  Error: No supported events found. The L1-dcache-prefetches:u event is not supported.
  Testing tma_info_botlnk_l2_ic_misses
  Testing tma_info_frontend_fetch_upc
  Testing tma_info_frontend_icache_miss_latency
  Testing tma_info_frontend_ipunknown_branch
  Testing tma_info_frontend_lsd_coverage
  Testing tma_info_memory_tlb_code_stlb_mpki
  Testing tma_info_pipeline_fetch_dsb
  Testing tma_info_pipeline_fetch_lsd
  Testing tma_info_pipeline_fetch_mite
  Testing tma_info_pipeline_fetch_ms
  Testing tma_fetch_bandwidth
  Testing tma_lsd
  Testing tma_branch_resteers
  Testing tma_code_l2_hit
  Testing tma_code_l2_miss
  Testing tma_code_stlb_hit
  Testing tma_code_stlb_miss
  Testing tma_code_stlb_miss_2m
  Testing tma_code_stlb_miss_4k
  Testing tma_lcp
  Testing tma_ms_switches
  Testing tma_info_core_flopc
  Testing tma_info_inst_mix_iparith
  Testing tma_info_inst_mix_iparith_avx128
  Testing tma_info_inst_mix_iparith_avx256
  Testing tma_info_inst_mix_iparith_avx512
  Testing tma_info_inst_mix_iparith_scalar_dp
  Testing tma_info_inst_mix_iparith_scalar_sp
  Testing tma_info_inst_mix_ipflop
  Testing tma_info_inst_mix_ippause
  Testing tma_fetch_latency
  Testing tma_fp_arith
  Testing tma_fp_assists
  Testing tma_info_system_cpu_utilization
  Testing tma_info_system_dram_bw_use
  [Skipped tma_info_system_dram_bw_use] Not supported events
  Performance counter stats for 'perf test -w noploop': <not supported> UNC_ARB_TRK_REQUESTS.ALL:u <not supported> UNC_ARB_COH_TRK_REQUESTS.ALL:u 1,013,554,749 duration_time 1.013527265 seconds time elapsed 1.005417000 seconds user 0.008011000 seconds sys
  Testing tma_info_frontend_l2mpki_code
  Testing tma_info_frontend_l2mpki_code_all
  Testing tma_info_inst_mix_ipload
  Testing tma_info_inst_mix_ipstore
  Testing tma_info_memory_latency_load_l2_miss_latency
  Testing tma_lock_latency
  Testing tma_info_memory_core_l1d_cache_fill_bw_2t
  Testing tma_info_memory_core_l2_cache_fill_bw_2t
  Testing tma_info_memory_core_l3_cache_access_bw_2t
  Testing tma_info_memory_core_l3_cache_fill_bw_2t
  Testing tma_info_memory_l1d_cache_fill_bw
  Testing tma_info_memory_l2_cache_fill_bw
  Testing tma_info_memory_l3_cache_access_bw
  Testing tma_info_memory_l3_cache_fill_bw
  Testing tma_info_memory_l3mpki
  Testing tma_info_memory_load_miss_real_latency
  Testing tma_info_memory_mix_bus_lock_pki
  Testing tma_info_memory_mix_uc_load_pki
  Testing tma_info_memory_mlp
  Testing tma_info_memory_tlb_load_stlb_mpki
  Testing tma_info_memory_tlb_page_walks_utilization
  Testing tma_info_memory_tlb_store_stlb_mpki
  Testing tma_info_system_mem_parallel_reads
  [Skipped tma_info_system_mem_parallel_reads] Not supported events
  Performance counter stats for 'perf test -w noploop': <not supported> UNC_ARB_DAT_OCCUPANCY.RD:u <not counted> UNC_ARB_DAT_OCCUPANCY.RD/cmask=1/ 1.013354884 seconds time elapsed 1.009239000 seconds user 0.004004000 seconds sys
  Testing tma_info_system_mem_read_latency
  [Skipped tma_info_system_mem_read_latency] Not supported events
  Performance counter stats for 'perf test -w noploop': <not supported> UNC_ARB_DAT_OCCUPANCY.RD:u <not counted> UNC_ARB_TRK_OCCUPANCY.RD <not counted> UNC_ARB_TRK_REQUESTS.RD 1.012882143 seconds time elapsed 1.004600000 seconds user 0.008036000 seconds sys
  Testing tma_info_thread_cpi
  Testing tma_streaming_stores
  Testing tma_dram_bound
  Testing tma_store_bound
  Testing tma_l2_hit_latency
  Testing tma_load_stlb_hit
  Testing tma_load_stlb_miss
  Testing tma_load_stlb_miss_1g
  Testing tma_load_stlb_miss_2m
  Testing tma_load_stlb_miss_4k
  Testing tma_store_stlb_hit
  Testing tma_store_stlb_miss
  Testing tma_store_stlb_miss_1g
  Testing tma_store_stlb_miss_2m
  Testing tma_store_stlb_miss_4k
  Testing tma_info_memory_latency_data_l2_mlp
  Testing tma_info_memory_latency_load_l2_mlp
  Testing tma_info_pipeline_ipassist
  Testing tma_microcode_sequencer
  Testing tma_ms
  Testing tma_info_system_kernel_cpi
  [Failed tma_info_system_kernel_cpi] Metric contains missing events
  Error: No supported events found. Access to performance monitoring and observability operations is limited. Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open access to performance monitoring and observability operations for processes without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability. More information can be found at 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html perf_event_paranoid setting is 2: -1: Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK >= 0: Disallow raw and ftrace function tracepoint access >= 1: Disallow CPU event access >= 2: Disallow kernel profiling To make the adjusted perf_event_paranoid setting permanent preserve it in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = <setting>)
  Testing tma_info_system_kernel_utilization
  [Failed tma_info_system_kernel_utilization] Metric contains missing events
  Error: No supported events found. Access to performance monitoring and observability operations is limited. Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open access to performance monitoring and observability operations for processes without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability. More information can be found at 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html perf_event_paranoid setting is 2: -1: Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK >= 0: Disallow raw and ftrace function tracepoint access >= 1: Disallow CPU event access >= 2: Disallow kernel profiling To make the adjusted perf_event_paranoid setting permanent preserve it in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = <setting>)
  Testing tma_info_pipeline_retire
  Testing tma_info_thread_clks
  Testing tma_info_thread_uoppi
  Testing tma_memory_operations
  Testing tma_other_light_ops
  Testing tma_ports_utilization
  Testing tma_ports_utilized_0
  Testing tma_ports_utilized_1
  Testing tma_ports_utilized_2
  Testing C10_Pkg_Residency
  [Failed C10_Pkg_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_pkg/c10-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_pkg/c10-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing C2_Pkg_Residency
  [Failed C2_Pkg_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_pkg/c2-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_pkg/c2-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing C3_Pkg_Residency
  [Failed C3_Pkg_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { msr/tsc/, cstate_pkg/c3-residency/ } Error: No supported events found. Invalid event (msr/tsc/u) in per-thread mode, enable system wide with '-a'.
  Testing C6_Core_Residency
  [Failed C6_Core_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_core/c6-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_core/c6-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing C6_Pkg_Residency
  [Failed C6_Pkg_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_pkg/c6-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_pkg/c6-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing C7_Core_Residency
  [Failed C7_Core_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_core/c7-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_core/c7-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing C7_Pkg_Residency
  [Failed C7_Pkg_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_pkg/c7-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_pkg/c7-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing C8_Pkg_Residency
  [Failed C8_Pkg_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_pkg/c8-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_pkg/c8-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing C9_Pkg_Residency
  [Failed C9_Pkg_Residency] Metric contains missing events
  WARNING: grouped events cpus do not match. Events with CPUs not matching the leader will be removed from the group. anon group { cstate_pkg/c9-residency/, msr/tsc/ } Error: No supported events found. Invalid event (cstate_pkg/c9-residency/u) in per-thread mode, enable system wide with '-a'.
  Testing tma_info_core_epc
  Testing tma_info_system_core_frequency
  Testing tma_info_system_power
  [Skipped tma_info_system_power] Not supported events
  Performance counter stats for 'perf test -w noploop': <not supported> Joules power/energy-pkg/u 1,013,238,256 duration_time 1.013223072 seconds time elapsed 0.995924000 seconds user 0.011903000 seconds sys
  Testing tma_info_system_power_license0_utilization
  Testing tma_info_system_power_license1_utilization
  Testing tma_info_system_power_license2_utilization
  Testing tma_info_system_turbo_utilization
  Testing tma_info_inst_mix_ipswpf
  Testing tma_info_memory_prefetches_useless_hwpf
  Testing tma_info_core_coreipc
  Testing tma_info_thread_ipc
  Testing tma_heavy_operations
  Testing tma_light_operations
  Testing tma_info_core_core_clks
  Testing tma_info_system_smt_2t_utilization
  Testing tma_info_thread_slots_utilization
  Testing UNCORE_FREQ
  [Skipped UNCORE_FREQ] Not supported events
  Performance counter stats for 'perf test -w noploop': <not supported> UNC_CLOCK.SOCKET:u 1,015,993,466 duration_time 1.015949387 seconds time elapsed 1.007676000 seconds user 0.008029000 seconds sys
  Testing tma_info_system_socket_clks
  [Failed tma_info_system_socket_clks] Metric contains missing events
  Error: No supported events found. Invalid event (UNC_CLOCK.SOCKET:u) in per-thread mode, enable system wide with '-a'.
  Testing tma_info_inst_mix_instructions
  Testing tma_info_system_cpus_utilized
  Testing tma_info_system_mux
  Testing tma_info_system_time
  Testing tma_info_thread_slots
  Testing tma_few_uops_instructions
  Testing tma_4k_aliasing
  Testing tma_cisc
  Testing tma_fp_divider
  Testing tma_int_divider
  Testing tma_slow_pause
  Testing tma_split_loads
  Testing tma_split_stores
  Testing tma_store_fwd_blk
  Testing tma_alu_op_utilization
  Testing tma_load_op_utilization
  Testing tma_mixing_vectors
  Testing tma_store_op_utilization
  Testing tma_port_1
  Testing tma_port_5
  Testing tma_port_6
  Testing smi_cycles
  [Skipped smi_cycles] Not supported events
  Performance counter stats for 'perf test -w noploop': <not supported> msr/smi/u <not supported> msr/aperf/u 3,965,789,327 cycles:u 1.012779591 seconds time elapsed 1.004579000 seconds user 0.007972000 seconds sys
  Testing smi_num
  [Failed smi_num] Metric contains missing events
  Error: No supported events found. Invalid event (msr/smi/u) in per-thread mode, enable system wide with '-a'.
  Testing tsx_aborted_cycles
  Testing tsx_cycles_per_elision
  Testing tsx_cycles_per_transaction
  Testing tsx_transactional_cycles
  ---- end(-1) ----
  110: perf all metrics test                                           : FAILED!

Stable-dep-of: 8953bfd8820b ("perf tests: Skip metrics validation if system-wide recording lacks permission")

---
 tools/perf/tests/shell/stat_all_metrics.sh | 29 ++++++++++++++++------
 1 file changed, 22 insertions(+), 7 deletions(-)

index 3dabb39c7cc8c..b582d23f28c9e 100755
@@ -15,7 +15,8 @@ then
   test_prog="perf test -w noploop"
 fi
 
-err=0
+skip=0
+err=3
 for m in $(perf list --raw-dump metrics); do
   echo "Testing $m"
   result=$(perf stat -M "$m" $system_wide_flag -- $test_prog 2>&1)

@@ -23,6 +24,10 @@ for m in $(perf list --raw-dump metrics); do
   if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
     # No error result and metric shown.
+    if [[ "$err" -ne 1 ]]
+    then
+      err=0
+    fi
     continue
   fi
   if [[ "$result" =~ "Cannot resolve IDs for" || "$result" =~ "No supported events found" ]]

@@ -44,7 +49,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "in per-thread mode, enable system wide" ]]

@@ -53,7 +58,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "<not supported>" ]]

@@ -68,7 +73,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "<not counted>" ]]

@@ -77,7 +82,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "FP_ARITH" || "$result" =~ "AMX" ]]

@@ -86,7 +91,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   elif [[ "$result" =~ "PMM" ]]

@@ -95,7 +100,7 @@ for m in $(perf list --raw-dump metrics); do
     echo $result
     if [[ $err -eq 0 ]]
     then
-      err=2 # Skip
+      skip=1
     fi
     continue
   fi

@@ -106,6 +111,10 @@ for m in $(perf list --raw-dump metrics); do
   if [[ $result_err -eq 0 && "$result" =~ ${m:0:50} ]]
   then
     # No error result and metric shown.
+    if [[ "$err" -ne 1 ]]
+    then
+      err=0
+    fi
     continue
   fi
   echo "[Failed $m] has non-zero error '$result_err' or not printed in:"

@@ -113,4 +122,10 @@ for m in $(perf list --raw-dump metrics); do
   err=1
 done
 
+# return SKIP only if no success returned
+if [[ "$err" -eq 3 && "$skip" -eq 1 ]]
+then
+  err=2
+fi
+
 exit "$err"

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 8953bfd8820b6525032023fda3a420098c1823ae ]

The metrics value validation test requires system-wide recording (-a), which can fail on systems without root permissions or where paranoid levels restrict tracing. Add a check to skip the test if -a is not supported.

Also fix false negatives during validation by updating parse error string patterns and resolving issues in metric list generation.

---
 .../tests/shell/lib/perf_metric_validation.py | 11 ++-
 tools/perf/tests/shell/stat_all_metrics.sh    | 75 ++++++++++++-------
 tools/perf/tests/shell/stat_metrics_values.sh |  7 ++
 3 files changed, 60 insertions(+), 33 deletions(-)

index a2d235252183b..5f32340b224d1 100644
@@ -378,10 +378,13 @@ class Validator:
         wl = workload.split()
         command.extend(wl)
         print(" ".join(command))
-        cmd = subprocess.run(command, stderr=subprocess.PIPE, encoding='utf-8')
-        data = [x+'}' for x in cmd.stderr.split('}\n') if x]
-        if data[0][0] != '{':
-            data[0] = data[0][data[0].find('{'):]
+        cmd = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, encoding='utf-8')
+        lines = cmd.stderr.splitlines() + cmd.stdout.splitlines()
+        data = []
+        for line in lines:
+            line = line.strip()
+            if line.startswith('{') and line.endswith('}'):
+                data.append(line)
         return data
 
     def collect_perf(self, workload: str):

index dc93f03a90e63..f3c77b1dd826e 100755
@@ -14,6 +14,13 @@ fi
 
 grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; }
 
+# Skip if no permission to record system-wide events
+if ! perf stat -a -e instructions sleep 0.01 >/dev/null 2>&1; then
+  echo "Skipping: no permission to record system-wide events (-a)"
+  exit 2
+fi
+
+
 pythonvalidator=$(dirname $0)/lib/perf_metric_validation.py
 rulefile=$(dirname $0)/lib/perf_metric_validation_rules.json
 tmpdir=$(mktemp -d /tmp/__perf_test.program.XXXXX)

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Richter <[email protected]>

[ Upstream commit 999eea92e8d7a1ffa83f7dc89c83d8ed1e746fa9 ]

This test case often fails on s390 (about 2 out of 10) because the 10% percent limit on the difference between --bpf-counters event counting and s390 hardware counting is more than 10% in all failure cases. Raise the limit to 20% on s390 and the test case succeeds.

Stable-dep-of: b02027776ac5 ("perf tests: Fix flakiness in BPF counters test on hybrid systems")

---
 tools/perf/tests/shell/stat_bpf_counters.sh | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

index a87bb2814b4c6..2d92098747746 100755
@@ -4,19 +4,19 @@
 
 set -e
 
-# check whether $2 is within +/- 10% of $1
+# check whether $2 is within +/- 20% of $1
 compare_number()
 {
        first_num=$1
        second_num=$2
 
-       # upper bound is first_num * 110%
-       upper=$(expr $first_num + $first_num / 10 )
-       # lower bound is first_num * 90%
-       lower=$(expr $first_num - $first_num / 10 )
+       # upper bound is first_num * 120%
+       upper=$(expr $first_num + $first_num / 5 )
+       # lower bound is first_num * 80%
+       lower=$(expr $first_num - $first_num / 5 )
 
        if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
-               echo "The difference between $first_num and $second_num are greater than 10%."
+               echo "The difference between $first_num and $second_num are greater than 20%."
                exit 1
        fi
 }

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit d9bd1d4264baddf7ab8baae86e91674d369f22de ]

Refactor test to better enable sharing of logic, to give an idea of progress and introduce test functions. Add test of measuring both cycles and cycles:b simultaneously.

Stable-dep-of: b02027776ac5 ("perf tests: Fix flakiness in BPF counters test on hybrid systems")

---
 tools/perf/tests/shell/stat_bpf_counters.sh | 75 ++++++++++++++-------
 1 file changed, 52 insertions(+), 23 deletions(-)

index 2d92098747746..61f8149d854e1 100755
@@ -4,21 +4,59 @@
 
 set -e
 
+workload="perf bench sched messaging -g 1 -l 100 -t"
+
 # check whether $2 is within +/- 20% of $1
 compare_number()
 {
-       first_num=$1
-       second_num=$2
-
-       # upper bound is first_num * 120%
-       upper=$(expr $first_num + $first_num / 5 )
-       # lower bound is first_num * 80%
-       lower=$(expr $first_num - $first_num / 5 )
-
-       if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
-               echo "The difference between $first_num and $second_num are greater than 20%."
-               exit 1
-       fi
+	first_num=$1
+	second_num=$2
+
+	# upper bound is first_num * 120%
+	upper=$(expr $first_num + $first_num / 5 )
+	# lower bound is first_num * 80%
+	lower=$(expr $first_num - $first_num / 5 )
+
+	if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
+		echo "The difference between $first_num and $second_num are greater than 20%."
+		exit 1
+	fi
+}
+
+check_counts()
+{
+	base_cycles=$1
+	bpf_cycles=$2
+
+	if [ "$base_cycles" = "<not" ]; then
+		echo "Skipping: cycles event not counted"
+		exit 2
+	fi
+	if [ "$bpf_cycles" = "<not" ]; then
+		echo "Failed: cycles not counted with --bpf-counters"
+		exit 1
+	fi
+}
+
+test_bpf_counters()
+{
+	printf "Testing --bpf-counters "
+	base_cycles=$(perf stat --no-big-num -e cycles -- $workload 2>&1 | awk '/cycles/ {print $1}')
+	bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- $workload  2>&1 | awk '/cycles/ {print $1}')
+	check_counts $base_cycles $bpf_cycles
+	compare_number $base_cycles $bpf_cycles
+	echo "[Success]"
+}
+
+test_bpf_modifier()
+{
+	printf "Testing bpf event modifier "
+	stat_output=$(perf stat --no-big-num -e cycles/name=base_cycles/,cycles/name=bpf_cycles/b -- $workload 2>&1)
+	base_cycles=$(echo "$stat_output"| awk '/base_cycles/ {print $1}')
+	bpf_cycles=$(echo "$stat_output"| awk '/bpf_cycles/ {print $1}')
+	check_counts $base_cycles $bpf_cycles
+	compare_number $base_cycles $bpf_cycles
+	echo "[Success]"
 }
 
 # skip if --bpf-counters is not supported

@@ -30,16 +68,7 @@ if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then
 	exit 2
 fi
 
-base_cycles=$(perf stat --no-big-num -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
-if [ "$base_cycles" = "<not" ]; then
-	echo "Skipping: cycles event not counted"
-	exit 2
-fi
-bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
-if [ "$bpf_cycles" = "<not" ]; then
-	echo "Failed: cycles not counted with --bpf-counters"
-	exit 1
-fi
+test_bpf_counters
+test_bpf_modifier
 
-compare_number $base_cycles $bpf_cycles
 exit 0

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Veronika Molnarova <[email protected]>

[ Upstream commit e8b86f0311a4b721663df8105a680e5968f21d4c ]

The test has been failing for some time when two separate runs of perf benchmarks are recorded for cycles events and their counts are compared, while once the recording was done with option --bpf-counters and once without it. It is expected that the count of the samples should be within a certain range, firstly the difference was set to be within 10%, which was then later raised to 20%. However, the test case keeps failing on certain architectures as recording the provided benchmark can produce completely different counts based on the current load of the system.

Sampling two separate runs on intel-eaglestream-spr-13 of "perf stat --no-big-num -e cycles -- perf bench sched messaging -g 1 -l 100 -t":

Performance counter stats for 'perf bench sched messaging -g 1 -l 100 -t':

         396782898      cycles

       0.010051983 seconds time elapsed

       0.008664000 seconds user
       0.097058000 seconds sys

Performance counter stats for 'perf bench sched messaging -g 1 -l 100 -t':

        1431133032      cycles

       0.021803714 seconds time elapsed

       0.023377000 seconds user
       0.349918000 seconds sys

, which is ranging from 400mil to 1400mil samples.

Instead of recording the cycles use instructions event, which provides more stable values. At the same time change the tested workload to one of the provided testing workloads by perf that is not based on a scheduler, which can provide another dependency on the current load.

Sampling instructions event with the new workload provide much more stable results on intel-eaglestream-spr-13 of "perf stat --no-big-num -e instructions -- perf test -w brstack":

Performance counter stats for 'perf test -w brstack':

          64584494      instructions

       0.009173945 seconds time elapsed

       0.007262000 seconds user
       0.002071000 seconds sys

Performance counter stats for 'perf test -w brstack':

          64672669      instructions

       0.008888135 seconds time elapsed

       0.005018000 seconds user
       0.004018000 seconds sys

Stable-dep-of: b02027776ac5 ("perf tests: Fix flakiness in BPF counters test on hybrid systems")

---
 tools/perf/tests/shell/stat_bpf_counters.sh | 36 ++++++++++-----------
 1 file changed, 18 insertions(+), 18 deletions(-)

index 61f8149d854e1..f250b7d6f773f 100755
@@ -4,7 +4,7 @@
 
 set -e
 
-workload="perf bench sched messaging -g 1 -l 100 -t"
+workload="perf test -w brstack"
 
 # check whether $2 is within +/- 20% of $1
 compare_number()

@@ -25,15 +25,15 @@ compare_number()
 
 check_counts()
 {
-	base_cycles=$1
-	bpf_cycles=$2
+	base_instructions=$1
+	bpf_instructions=$2
 
-	if [ "$base_cycles" = "<not" ]; then
-		echo "Skipping: cycles event not counted"
+	if [ "$base_instructions" = "<not" ]; then
+		echo "Skipping: instructions event not counted"
 		exit 2
 	fi
-	if [ "$bpf_cycles" = "<not" ]; then
-		echo "Failed: cycles not counted with --bpf-counters"
+	if [ "$bpf_instructions" = "<not" ]; then
+		echo "Failed: instructions not counted with --bpf-counters"
 		exit 1
 	fi
 }

@@ -41,29 +41,29 @@ check_counts()
 test_bpf_counters()
 {
 	printf "Testing --bpf-counters "
-	base_cycles=$(perf stat --no-big-num -e cycles -- $workload 2>&1 | awk '/cycles/ {print $1}')
-	bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- $workload  2>&1 | awk '/cycles/ {print $1}')
-	check_counts $base_cycles $bpf_cycles
-	compare_number $base_cycles $bpf_cycles
+	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
+	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
+	check_counts $base_instructions $bpf_instructions
+	compare_number $base_instructions $bpf_instructions
 	echo "[Success]"
 }
 
 test_bpf_modifier()
 {
 	printf "Testing bpf event modifier "
-	stat_output=$(perf stat --no-big-num -e cycles/name=base_cycles/,cycles/name=bpf_cycles/b -- $workload 2>&1)
-	base_cycles=$(echo "$stat_output"| awk '/base_cycles/ {print $1}')
-	bpf_cycles=$(echo "$stat_output"| awk '/bpf_cycles/ {print $1}')
-	check_counts $base_cycles $bpf_cycles
-	compare_number $base_cycles $bpf_cycles
+	stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
+	base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
+	bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
+	check_counts $base_instructions $bpf_instructions
+	compare_number $base_instructions $bpf_instructions
 	echo "[Success]"
 }
 
 # skip if --bpf-counters is not supported
-if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then
+if ! perf stat -e instructions --bpf-counters true > /dev/null 2>&1; then
 	if [ "$1" = "-v" ]; then
 		echo "Skipping: --bpf-counters not supported"
-		perf --no-pager stat -e cycles --bpf-counters true || true
+		perf --no-pager stat -e instructions --bpf-counters true || true
 	fi
 	exit 2
 fi

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tengda Wu <[email protected]>

[ Upstream commit d36e5b36a2928b30e09ff59ce5ce2d5df935176e ]

Replace brstack workload with sqrtloop workload, because sqrtloop workload contains fork(), which is suitable for testing the bperf event inheritance feature.

Stable-dep-of: b02027776ac5 ("perf tests: Fix flakiness in BPF counters test on hybrid systems")

---
 tools/perf/tests/shell/stat_bpf_counters.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index f250b7d6f773f..831f02add75e5 100755
@@ -4,7 +4,7 @@
 
 set -e
 
-workload="perf test -w brstack"
+workload="perf test -w sqrtloop"
 
 # check whether $2 is within +/- 20% of $1
 compare_number()

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

[ Upstream commit d9db9c8db56c3e378aa5c91637664f77ca5a6f72 ]

The test constantly fails on my Intel hybrid machine. The issue was it has two events in the output even if I only gave it one event.

  $ perf stat -e instructions -- perf test -w sqrtloop

Performance counter stats for 'perf test -w sqrtloop':

         910,856,421      cpu_atom/instructions/                (28.05%)
      14,852,865,997      cpu_core/instructions/                (96.79%)

         1.014313341 seconds time elapsed

         1.004114000 seconds user
         0.008174000 seconds sys

Let's modify the awk script to add the values for each line and print the total. The variable 'i' has a number of input lines that have valid output and variable 'c' has the sum of actual counter values. That way it should work on any platforms.

Stable-dep-of: b02027776ac5 ("perf tests: Fix flakiness in BPF counters test on hybrid systems")

---
 tools/perf/tests/shell/stat_bpf_counters.sh | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

index 831f02add75e5..b776ee2e445a6 100755
@@ -41,8 +41,14 @@ check_counts()
 test_bpf_counters()
 {
 	printf "Testing --bpf-counters "
-	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | awk '/instructions/ {print $1}')
-	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | awk '/instructions/ {print $1}')
+	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | \
+				awk -v i=0 -v c=0 '/instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
+	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | \
+				awk -v i=0 -v c=0 '/instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
 	check_counts $base_instructions $bpf_instructions
 	compare_number $base_instructions $bpf_instructions
 	echo "[Success]"

@@ -52,8 +58,14 @@ test_bpf_modifier()
 {
 	printf "Testing bpf event modifier "
 	stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
-	base_instructions=$(echo "$stat_output"| awk '/base_instructions/ {print $1}')
-	bpf_instructions=$(echo "$stat_output"| awk '/bpf_instructions/ {print $1}')
+	base_instructions=$(echo "$stat_output"| \
+				awk -v i=0 -v c=0 '/base_instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
+	bpf_instructions=$(echo "$stat_output"| \
+				awk -v i=0 -v c=0 '/bpf_instructions/ { \
+					if ($1 != "<not") { i++; c += $1 } \
+				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
 	check_counts $base_instructions $bpf_instructions
 	compare_number $base_instructions $bpf_instructions
 	echo "[Success]"

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit b02027776ac5bf737f1b76f3759f405e376097e5 ]

The perf stat --bpf-counters test fails intermittently on hybrid architectures or systems with dynamic frequency scaling (DVFS). This happens because the test workload (sqrtloop) runs for a fixed 1-second duration, and the CPU frequency can scale dynamically between idle and maximum frequency. As the first run runs on a cold CPU and the second run runs on a warmed-up CPU (or vice versa), the number of instructions executed in 1 second differs by up to 2.2x, violating the comparison tolerance.

Also, when running as root, BPF tracepoints and scheduling programs trigger frequently. Since standard perf stat -e instructions measures both user and kernel space instructions, it counts BPF helper and program execution overheads, whereas the BPF counters themselves do not self- measure. This introduces a large kernel-space instruction count discrepancy between standard and BPF counters.

Fix these issues by:
1. Switching the workload to a strictly deterministic, iteration-based
workload: awk 'BEGIN { for (i=0; i<10000000; i++) sum+=i }'. We pin
the
workload to a single random allowed CPU using taskset -c $CPU via a
bash array.
2. Restricting the counted event to user-space only (instructions:u or /u).
3. Tightening the comparison tolerance from 20% to 15%.

These modifications isolate the measurements to user-space instructions of the deterministic loop, which executes a virtually identical number of instructions on both runs (with less than 0.001% variation), eliminating Dynamic Frequency Scaling (DVFS), kernel scheduling noise, and BPF helper self-measurement overheads.

---
 tools/perf/tests/shell/stat_bpf_counters.sh | 28 +++++++++++++--------
 1 file changed, 18 insertions(+), 10 deletions(-)

index b776ee2e445a6..76d4a7f15a43d 100755
@@ -4,21 +4,26 @@
 
 set -e
 
-workload="perf test -w sqrtloop"
+# Get the first allowed CPU
+CPU=$(taskset -c -p $$ | awk -F': ' '{print $2}' | awk -F'[,-]' '{print $1}')
+if [ -z "$CPU" ]; then
+	CPU=0
+fi
+workload=(taskset -c "$CPU" awk 'BEGIN { for (i=0; i<10000000; i++) sum+=i }')
 
-# check whether $2 is within +/- 20% of $1
+# check whether $2 is within +/- 15% of $1
 compare_number()
 {
 	first_num=$1
 	second_num=$2
 
-	# upper bound is first_num * 120%
-	upper=$(expr $first_num + $first_num / 5 )
-	# lower bound is first_num * 80%
-	lower=$(expr $first_num - $first_num / 5 )
+	# upper bound is first_num * 115%
+	upper=$(expr $first_num + $first_num / 20 \* 3 )
+	# lower bound is first_num * 85%
+	lower=$(expr $first_num - $first_num / 20 \* 3 )
 
 	if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
-		echo "The difference between $first_num and $second_num are greater than 20%."
+		echo "The difference between $first_num and $second_num are greater than 15%."
 		exit 1
 	fi
 }

@@ -41,11 +46,12 @@ check_counts()
 test_bpf_counters()
 {
 	printf "Testing --bpf-counters "
-	base_instructions=$(perf stat --no-big-num -e instructions -- $workload 2>&1 | \
+	base_instructions=$(perf stat --no-big-num -e instructions:u -- "${workload[@]}" 2>&1 | \
 				awk -v i=0 -v c=0 '/instructions/ { \
 					if ($1 != "<not") { i++; c += $1 } \
 				} END { if (i > 0) printf "%.0f", c; else print "<not" }')
-	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions -- $workload  2>&1 | \
+	bpf_instructions=$(perf stat --no-big-num --bpf-counters -e instructions:u \
+				-- "${workload[@]}"  2>&1 | \
 				awk -v i=0 -v c=0 '/instructions/ { \
 					if ($1 != "<not") { i++; c += $1 } \
 				} END { if (i > 0) printf "%.0f", c; else print "<not" }')

@@ -57,7 +63,9 @@ test_bpf_counters()
 test_bpf_modifier()
 {
 	printf "Testing bpf event modifier "
-	stat_output=$(perf stat --no-big-num -e instructions/name=base_instructions/,instructions/name=bpf_instructions/b -- $workload 2>&1)
+	stat_output=$(perf stat --no-big-num \
+		-e instructions/name=base_instructions/u,instructions/name=bpf_instructions/bu \
+		-- "${workload[@]}" 2>&1)
 	base_instructions=$(echo "$stat_output"| \
 				awk -v i=0 -v c=0 '/base_instructions/ { \
 					if ($1 != "<not") { i++; c += $1 } \

2.53.0

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nirmala Devi Mal Nadar <[email protected]>

[ Upstream commit 84ccfaee29fe46e305244a69c4471e83629ad5d1 ]

Extend TPS6594 PMIC register and field definitions to support TPS65224 power management IC.

TPS65224 is software compatible to TPS6594 and can re-use many of the same definitions, new definitions are added to support additional controls available on TPS65224.

Stable-dep-of: 7fd28093b3ef ("regulator: tps6594: Fix device node reference leaks in multiphase loop")

---
 include/linux/mfd/tps6594.h | 347 ++++++++++++++++++++++++++++++++++--
 1 file changed, 335 insertions(+), 12 deletions(-)

index 3f7c5e23cd4cd..e754c01acc643 100644
@@ -18,12 +18,13 @@ enum pmic_id {
 	TPS6594,
 	TPS6593,
 	LP8764,
+	TPS65224,
 };
 
 /* Macro to get page index from register address */
 #define TPS6594_REG_TO_PAGE(reg)	((reg) >> 8)
 
-/* Registers for page 0 of TPS6594 */
+/* Registers for page 0 */
 #define TPS6594_REG_DEV_REV				0x01
 
 #define TPS6594_REG_NVM_CODE_1				0x02

@@ -56,9 +57,6 @@ enum pmic_id {
 #define TPS6594_REG_GPIOX_OUT(gpio_inst)		(TPS6594_REG_GPIO_OUT_1 + (gpio_inst) / 8)
 #define TPS6594_REG_GPIOX_IN(gpio_inst)			(TPS6594_REG_GPIO_IN_1 + (gpio_inst) / 8)
 
-#define TPS6594_REG_GPIO_IN_1				0x3f
-#define TPS6594_REG_GPIO_IN_2				0x40
-
 #define TPS6594_REG_RAIL_SEL_1				0x41
 #define TPS6594_REG_RAIL_SEL_2				0x42
 #define TPS6594_REG_RAIL_SEL_3				0x43

@@ -70,13 +68,15 @@ enum pmic_id {
 #define TPS6594_REG_FSM_TRIG_MASK_3			0x48
 
 #define TPS6594_REG_MASK_BUCK1_2			0x49
+#define TPS65224_REG_MASK_BUCKS				0x49
 #define TPS6594_REG_MASK_BUCK3_4			0x4a
 #define TPS6594_REG_MASK_BUCK5				0x4b
 #define TPS6594_REG_MASK_LDO1_2				0x4c
+#define TPS65224_REG_MASK_LDOS				0x4c
 #define TPS6594_REG_MASK_LDO3_4				0x4d
 #define TPS6594_REG_MASK_VMON				0x4e
-#define TPS6594_REG_MASK_GPIO1_8_FALL			0x4f
-#define TPS6594_REG_MASK_GPIO1_8_RISE			0x50
+#define TPS6594_REG_MASK_GPIO_FALL			0x4f
+#define TPS6594_REG_MASK_GPIO_RISE			0x50
 #define TPS6594_REG_MASK_GPIO9_11			0x51
 #define TPS6594_REG_MASK_STARTUP			0x52
 #define TPS6594_REG_MASK_MISC				0x53

@@ -174,6 +174,10 @@ enum pmic_id {
 
 #define TPS6594_REG_REGISTER_LOCK			0xa1
 
+#define TPS65224_REG_SRAM_ACCESS_1			0xa2
+#define TPS65224_REG_SRAM_ACCESS_2			0xa3
+#define TPS65224_REG_SRAM_ADDR_CTRL			0xa4
+#define TPS65224_REG_RECOV_CNT_PFSM_INCR		0xa5
 #define TPS6594_REG_MANUFACTURING_VER			0xa6
 
 #define TPS6594_REG_CUSTOMER_NVM_ID_REG			0xa7

@@ -182,6 +186,9 @@ enum pmic_id {
 
 #define TPS6594_REG_SOFT_REBOOT_REG			0xab
 
+#define TPS65224_REG_ADC_CTRL				0xac
+#define TPS65224_REG_ADC_RESULT_REG_1			0xad
+#define TPS65224_REG_ADC_RESULT_REG_2			0xae
 #define TPS6594_REG_RTC_SECONDS				0xb5
 #define TPS6594_REG_RTC_MINUTES				0xb6
 #define TPS6594_REG_RTC_HOURS				0xb7

@@ -199,6 +206,7 @@ enum pmic_id {
 
 #define TPS6594_REG_RTC_CTRL_1				0xc2
 #define TPS6594_REG_RTC_CTRL_2				0xc3
+#define TPS65224_REG_STARTUP_CTRL			0xc3
 #define TPS6594_REG_RTC_STATUS				0xc4
 #define TPS6594_REG_RTC_INTERRUPTS			0xc5
 #define TPS6594_REG_RTC_COMP_LSB			0xc6

@@ -214,13 +222,17 @@ enum pmic_id {
 #define TPS6594_REG_PFSM_DELAY_REG_2			0xce
 #define TPS6594_REG_PFSM_DELAY_REG_3			0xcf
 #define TPS6594_REG_PFSM_DELAY_REG_4			0xd0
+#define TPS65224_REG_ADC_GAIN_COMP_REG			0xd0
+#define TPS65224_REG_CRC_CALC_CONTROL			0xef
+#define TPS65224_REG_REGMAP_USER_CRC_LOW		0xf0
+#define TPS65224_REG_REGMAP_USER_CRC_HIGH		0xf1
 
-/* Registers for page 1 of TPS6594 */
+/* Registers for page 1 */
 #define TPS6594_REG_SERIAL_IF_CONFIG			0x11a
 #define TPS6594_REG_I2C1_ID				0x122
 #define TPS6594_REG_I2C2_ID				0x123
 
-/* Registers for page 4 of TPS6594 */
+/* Registers for page 4 */
 #define TPS6594_REG_WD_ANSWER_REG			0x401
 #define TPS6594_REG_WD_QUESTION_ANSW_CNT		0x402
 #define TPS6594_REG_WD_WIN1_CFG				0x403

@@ -241,16 +253,26 @@ enum pmic_id {
 #define TPS6594_BIT_BUCK_PLDN				BIT(5)
 #define TPS6594_BIT_BUCK_RV_SEL				BIT(7)
 
-/* BUCKX_CONF register field definition */
+/* TPS6594 BUCKX_CONF register field definition */
 #define TPS6594_MASK_BUCK_SLEW_RATE			GENMASK(2, 0)
 #define TPS6594_MASK_BUCK_ILIM				GENMASK(5, 3)
 
-/* BUCKX_PG_WINDOW register field definition */
+/* TPS65224 BUCKX_CONF register field definition */
+#define TPS65224_MASK_BUCK_SLEW_RATE			GENMASK(1, 0)
+
+/* TPS6594 BUCKX_PG_WINDOW register field definition */
 #define TPS6594_MASK_BUCK_OV_THR			GENMASK(2, 0)
 #define TPS6594_MASK_BUCK_UV_THR			GENMASK(5, 3)
 
-/* BUCKX VSET */
-#define TPS6594_MASK_BUCKS_VSET GENMASK(7, 0)
+/* TPS65224 BUCKX_PG_WINDOW register field definition */
+#define TPS65224_MASK_BUCK_VMON_THR			GENMASK(1, 0)
+
+/* TPS6594 BUCKX_VOUT register field definition */
+#define TPS6594_MASK_BUCKS_VSET				GENMASK(7, 0)
+
+/* TPS65224 BUCKX_VOUT register field definition */
+#define TPS65224_MASK_BUCK1_VSET			GENMASK(7, 0)
+#define TPS65224_MASK_BUCKS_VSET			GENMASK(6, 0)
 
 /* LDOX_CTRL register field definition */
 #define TPS6594_BIT_LDO_EN				BIT(0)

@@ -258,6 +280,7 @@ enum pmic_id {
 #define TPS6594_BIT_LDO_VMON_EN				BIT(4)
 #define TPS6594_MASK_LDO_PLDN				GENMASK(6, 5)
 #define TPS6594_BIT_LDO_RV_SEL				BIT(7)
+#define TPS65224_BIT_LDO_DISCHARGE_EN			BIT(5)
 
 /* LDORTC_CTRL register field definition */
 #define TPS6594_BIT_LDORTC_DIS				BIT(0)

@@ -271,6 +294,9 @@ enum pmic_id {
 #define TPS6594_MASK_LDO_OV_THR				GENMASK(2, 0)
 #define TPS6594_MASK_LDO_UV_THR				GENMASK(5, 3)
 
+/* LDOX_PG_WINDOW register field definition */
+#define TPS65224_MASK_LDO_VMON_THR			GENMASK(1, 0)
+
 /* VCCA_VMON_CTRL register field definition */
 #define TPS6594_BIT_VMON_EN				BIT(0)
 #define TPS6594_BIT_VMON1_EN				BIT(1)

@@ -278,10 +304,12 @@ enum pmic_id {
 #define TPS6594_BIT_VMON2_EN				BIT(3)
 #define TPS6594_BIT_VMON2_RV_SEL			BIT(4)
 #define TPS6594_BIT_VMON_DEGLITCH_SEL			BIT(5)
+#define TPS65224_BIT_VMON_DEGLITCH_SEL			GENMASK(7, 5)
 
 /* VCCA_PG_WINDOW register field definition */
 #define TPS6594_MASK_VCCA_OV_THR			GENMASK(2, 0)
 #define TPS6594_MASK_VCCA_UV_THR			GENMASK(5, 3)
+#define TPS65224_MASK_VCCA_VMON_THR			GENMASK(1, 0)
 #define TPS6594_BIT_VCCA_PG_SET				BIT(6)
 
 /* VMONX_PG_WINDOW register field definition */

@@ -289,6 +317,9 @@ enum pmic_id {
 #define TPS6594_MASK_VMONX_UV_THR			GENMASK(5, 3)
 #define TPS6594_BIT_VMONX_RANGE				BIT(6)
 
+/* VMONX_PG_WINDOW register field definition */
+#define TPS65224_MASK_VMONX_THR				GENMASK(1, 0)
+
 /* GPIOX_CONF register field definition */
 #define TPS6594_BIT_GPIO_DIR				BIT(0)
 #define TPS6594_BIT_GPIO_OD				BIT(1)

@@ -296,6 +327,8 @@ enum pmic_id {
 #define TPS6594_BIT_GPIO_PU_PD_EN			BIT(3)
 #define TPS6594_BIT_GPIO_DEGLITCH_EN			BIT(4)
 #define TPS6594_MASK_GPIO_SEL				GENMASK(7, 5)
+#define TPS65224_MASK_GPIO_SEL				GENMASK(6, 5)
+#define TPS65224_MASK_GPIO_SEL_GPIO6			GENMASK(7, 5)
 
 /* NPWRON_CONF register field definition */
 #define TPS6594_BIT_NRSTOUT_OD				BIT(0)

@@ -305,6 +338,12 @@ enum pmic_id {
 #define TPS6594_BIT_ENABLE_POL				BIT(5)
 #define TPS6594_MASK_NPWRON_SEL				GENMASK(7, 6)
 
+/* POWER_ON_CONFIG register field definition */
+#define TPS65224_BIT_NINT_ENDRV_PU_SEL			BIT(0)
+#define TPS65224_BIT_NINT_ENDRV_SEL			BIT(1)
+#define TPS65224_BIT_EN_PB_DEGL				BIT(5)
+#define TPS65224_MASK_EN_PB_VSENSE_CONFIG		GENMASK(7, 6)
+
 /* GPIO_OUT_X register field definition */
 #define TPS6594_BIT_GPIOX_OUT(gpio_inst)		BIT((gpio_inst) % 8)
 

@@ -312,6 +351,12 @@ enum pmic_id {
 #define TPS6594_BIT_GPIOX_IN(gpio_inst)			BIT((gpio_inst) % 8)
 #define TPS6594_BIT_NPWRON_IN				BIT(3)
 
+/* GPIO_OUT_X register field definition */
+#define TPS65224_BIT_GPIOX_OUT(gpio_inst)		BIT((gpio_inst))
+
+/* GPIO_IN_X register field definition */
+#define TPS65224_BIT_GPIOX_IN(gpio_inst)		BIT((gpio_inst))
+
 /* RAIL_SEL_1 register field definition */
 #define TPS6594_MASK_BUCK1_GRP_SEL			GENMASK(1, 0)
 #define TPS6594_MASK_BUCK2_GRP_SEL			GENMASK(3, 2)

@@ -343,6 +388,9 @@ enum pmic_id {
 #define TPS6594_BIT_GPIOX_FSM_MASK(gpio_inst)		BIT(((gpio_inst) << 1) % 8)
 #define TPS6594_BIT_GPIOX_FSM_MASK_POL(gpio_inst)	BIT(((gpio_inst) << 1) % 8 + 1)
 
+#define TPS65224_BIT_GPIOX_FSM_MASK(gpio_inst)		BIT(((gpio_inst) << 1) % 6)
+#define TPS65224_BIT_GPIOX_FSM_MASK_POL(gpio_inst)	BIT(((gpio_inst) << 1) % 6 + 1)
+
 /* MASK_BUCKX register field definition */
 #define TPS6594_BIT_BUCKX_OV_MASK(buck_inst)		BIT(((buck_inst) << 2) % 8)
 #define TPS6594_BIT_BUCKX_UV_MASK(buck_inst)		BIT(((buck_inst) << 2) % 8 + 1)

@@ -361,22 +409,46 @@ enum pmic_id {
 #define TPS6594_BIT_VMON2_OV_MASK			BIT(5)
 #define TPS6594_BIT_VMON2_UV_MASK			BIT(6)
 
+/* MASK_BUCK Register field definition */
+#define TPS65224_BIT_BUCK1_UVOV_MASK			BIT(0)
+#define TPS65224_BIT_BUCK2_UVOV_MASK			BIT(1)
+#define TPS65224_BIT_BUCK3_UVOV_MASK			BIT(2)
+#define TPS65224_BIT_BUCK4_UVOV_MASK			BIT(4)
+
+/* MASK_LDO_VMON register field definition */
+#define TPS65224_BIT_LDO1_UVOV_MASK			BIT(0)
+#define TPS65224_BIT_LDO2_UVOV_MASK			BIT(1)
+#define TPS65224_BIT_LDO3_UVOV_MASK			BIT(2)
+#define TPS65224_BIT_VCCA_UVOV_MASK			BIT(4)
+#define TPS65224_BIT_VMON1_UVOV_MASK			BIT(5)
+#define TPS65224_BIT_VMON2_UVOV_MASK			BIT(6)
+
 /* MASK_GPIOX register field definition */
 #define TPS6594_BIT_GPIOX_FALL_MASK(gpio_inst)		BIT((gpio_inst) < 8 ? \
 							    (gpio_inst) : (gpio_inst) % 8)
 #define TPS6594_BIT_GPIOX_RISE_MASK(gpio_inst)		BIT((gpio_inst) < 8 ? \
 							    (gpio_inst) : (gpio_inst) % 8 + 3)
+/* MASK_GPIOX register field definition */
+#define TPS65224_BIT_GPIOX_FALL_MASK(gpio_inst)		BIT((gpio_inst))
+#define TPS65224_BIT_GPIOX_RISE_MASK(gpio_inst)		BIT((gpio_inst))
 
 /* MASK_STARTUP register field definition */
 #define TPS6594_BIT_NPWRON_START_MASK			BIT(0)
 #define TPS6594_BIT_ENABLE_MASK				BIT(1)
 #define TPS6594_BIT_FSD_MASK				BIT(4)
 #define TPS6594_BIT_SOFT_REBOOT_MASK			BIT(5)
+#define TPS65224_BIT_VSENSE_MASK			BIT(0)
+#define TPS65224_BIT_PB_SHORT_MASK			BIT(2)
 
 /* MASK_MISC register field definition */
 #define TPS6594_BIT_BIST_PASS_MASK			BIT(0)
 #define TPS6594_BIT_EXT_CLK_MASK			BIT(1)
+#define TPS65224_BIT_REG_UNLOCK_MASK			BIT(2)
 #define TPS6594_BIT_TWARN_MASK				BIT(3)
+#define TPS65224_BIT_PB_LONG_MASK			BIT(4)
+#define TPS65224_BIT_PB_FALL_MASK			BIT(5)
+#define TPS65224_BIT_PB_RISE_MASK			BIT(6)
+#define TPS65224_BIT_ADC_CONV_READY_MASK		BIT(7)
 
 /* MASK_MODERATE_ERR register field definition */
 #define TPS6594_BIT_BIST_FAIL_MASK			BIT(1)

@@ -391,6 +463,8 @@ enum pmic_id {
 #define TPS6594_BIT_ORD_SHUTDOWN_MASK			BIT(1)
 #define TPS6594_BIT_MCU_PWR_ERR_MASK			BIT(2)
 #define TPS6594_BIT_SOC_PWR_ERR_MASK			BIT(3)
+#define TPS65224_BIT_COMM_ERR_MASK			BIT(4)
+#define TPS65224_BIT_I2C2_ERR_MASK			BIT(5)
 
 /* MASK_COMM_ERR register field definition */
 #define TPS6594_BIT_COMM_FRM_ERR_MASK			BIT(0)

@@ -426,6 +500,12 @@ enum pmic_id {
 #define TPS6594_BIT_BUCK3_4_INT				BIT(1)
 #define TPS6594_BIT_BUCK5_INT				BIT(2)
 
+/* INT_BUCK register field definition */
+#define TPS65224_BIT_BUCK1_UVOV_INT			BIT(0)
+#define TPS65224_BIT_BUCK2_UVOV_INT			BIT(1)
+#define TPS65224_BIT_BUCK3_UVOV_INT			BIT(2)
+#define TPS65224_BIT_BUCK4_UVOV_INT			BIT(3)
+
 /* INT_BUCKX register field definition */
 #define TPS6594_BIT_BUCKX_OV_INT(buck_inst)		BIT(((buck_inst) << 2) % 8)
 #define TPS6594_BIT_BUCKX_UV_INT(buck_inst)		BIT(((buck_inst) << 2) % 8 + 1)

@@ -437,6 +517,14 @@ enum pmic_id {
 #define TPS6594_BIT_LDO3_4_INT				BIT(1)
 #define TPS6594_BIT_VCCA_INT				BIT(4)
 
+/* INT_LDO_VMON register field definition */
+#define TPS65224_BIT_LDO1_UVOV_INT			BIT(0)
+#define TPS65224_BIT_LDO2_UVOV_INT			BIT(1)
+#define TPS65224_BIT_LDO3_UVOV_INT			BIT(2)
+#define TPS65224_BIT_VCCA_UVOV_INT			BIT(4)
+#define TPS65224_BIT_VMON1_UVOV_INT			BIT(5)
+#define TPS65224_BIT_VMON2_UVOV_INT			BIT(6)
+
 /* INT_LDOX register field definition */
 #define TPS6594_BIT_LDOX_OV_INT(ldo_inst)		BIT(((ldo_inst) << 2) % 8)
 #define TPS6594_BIT_LDOX_UV_INT(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 1)

@@ -462,17 +550,32 @@ enum pmic_id {
 /* INT_GPIOX register field definition */
 #define TPS6594_BIT_GPIOX_INT(gpio_inst)		BIT(gpio_inst)
 
+/* INT_GPIO register field definition */
+#define TPS65224_BIT_GPIO1_INT				BIT(0)
+#define TPS65224_BIT_GPIO2_INT				BIT(1)
+#define TPS65224_BIT_GPIO3_INT				BIT(2)
+#define TPS65224_BIT_GPIO4_INT				BIT(3)
+#define TPS65224_BIT_GPIO5_INT				BIT(4)
+#define TPS65224_BIT_GPIO6_INT				BIT(5)
+
 /* INT_STARTUP register field definition */
 #define TPS6594_BIT_NPWRON_START_INT			BIT(0)
+#define TPS65224_BIT_VSENSE_INT				BIT(0)
 #define TPS6594_BIT_ENABLE_INT				BIT(1)
 #define TPS6594_BIT_RTC_INT				BIT(2)
+#define TPS65224_BIT_PB_SHORT_INT			BIT(2)
 #define TPS6594_BIT_FSD_INT				BIT(4)
 #define TPS6594_BIT_SOFT_REBOOT_INT			BIT(5)
 
 /* INT_MISC register field definition */
 #define TPS6594_BIT_BIST_PASS_INT			BIT(0)
 #define TPS6594_BIT_EXT_CLK_INT				BIT(1)
+#define TPS65224_BIT_REG_UNLOCK_INT			BIT(2)
 #define TPS6594_BIT_TWARN_INT				BIT(3)
+#define TPS65224_BIT_PB_LONG_INT			BIT(4)
+#define TPS65224_BIT_PB_FALL_INT			BIT(5)
+#define TPS65224_BIT_PB_RISE_INT			BIT(6)
+#define TPS65224_BIT_ADC_CONV_READY_INT			BIT(7)
 
 /* INT_MODERATE_ERR register field definition */
 #define TPS6594_BIT_TSD_ORD_INT				BIT(0)

@@ -488,6 +591,7 @@ enum pmic_id {
 #define TPS6594_BIT_TSD_IMM_INT				BIT(0)
 #define TPS6594_BIT_VCCA_OVP_INT			BIT(1)
 #define TPS6594_BIT_PFSM_ERR_INT			BIT(2)
+#define TPS65224_BIT_BG_XMON_INT			BIT(3)
 
 /* INT_FSM_ERR register field definition */
 #define TPS6594_BIT_IMM_SHUTDOWN_INT			BIT(0)

@@ -496,6 +600,7 @@ enum pmic_id {
 #define TPS6594_BIT_SOC_PWR_ERR_INT			BIT(3)
 #define TPS6594_BIT_COMM_ERR_INT			BIT(4)
 #define TPS6594_BIT_READBACK_ERR_INT			BIT(5)
+#define TPS65224_BIT_I2C2_ERR_INT			BIT(5)
 #define TPS6594_BIT_ESM_INT				BIT(6)
 #define TPS6594_BIT_WD_INT				BIT(7)
 

@@ -536,8 +641,18 @@ enum pmic_id {
 #define TPS6594_BIT_VMON2_OV_STAT			BIT(5)
 #define TPS6594_BIT_VMON2_UV_STAT			BIT(6)
 
+/* STAT_LDO_VMON register field definition */
+#define TPS65224_BIT_LDO1_UVOV_STAT			BIT(0)
+#define TPS65224_BIT_LDO2_UVOV_STAT			BIT(1)
+#define TPS65224_BIT_LDO3_UVOV_STAT			BIT(2)
+#define TPS65224_BIT_VCCA_UVOV_STAT			BIT(4)
+#define TPS65224_BIT_VMON1_UVOV_STAT			BIT(5)
+#define TPS65224_BIT_VMON2_UVOV_STAT			BIT(6)
+
 /* STAT_STARTUP register field definition */
+#define TPS65224_BIT_VSENSE_STAT			BIT(0)
 #define TPS6594_BIT_ENABLE_STAT				BIT(1)
+#define TPS65224_BIT_PB_LEVEL_STAT			BIT(2)
 
 /* STAT_MISC register field definition */
 #define TPS6594_BIT_EXT_CLK_STAT			BIT(1)

@@ -549,6 +664,7 @@ enum pmic_id {
 /* STAT_SEVERE_ERR register field definition */
 #define TPS6594_BIT_TSD_IMM_STAT			BIT(0)
 #define TPS6594_BIT_VCCA_OVP_STAT			BIT(1)
+#define TPS65224_BIT_BG_XMON_STAT			BIT(3)
 
 /* STAT_READBACK_ERR register field definition */
 #define TPS6594_BIT_EN_DRV_READBACK_STAT		BIT(0)

@@ -597,6 +713,8 @@ enum pmic_id {
 #define TPS6594_BIT_BB_CHARGER_EN			BIT(0)
 #define TPS6594_BIT_BB_ICHR				BIT(1)
 #define TPS6594_MASK_BB_VEOC				GENMASK(3, 2)
+#define TPS65224_BIT_I2C1_SPI_CRC_EN			BIT(4)
+#define TPS65224_BIT_I2C2_CRC_EN			BIT(5)
 #define TPS6594_BB_EOC_RDY				BIT(7)
 
 /* ENABLE_DRV_REG register field definition */

@@ -617,6 +735,7 @@ enum pmic_id {
 #define TPS6594_BIT_NRSTOUT_SOC_IN			BIT(2)
 #define TPS6594_BIT_FORCE_EN_DRV_LOW			BIT(3)
 #define TPS6594_BIT_SPMI_LPM_EN				BIT(4)
+#define TPS65224_BIT_TSD_DISABLE			BIT(5)
 
 /* RECOV_CNT_REG_1 register field definition */
 #define TPS6594_MASK_RECOV_CNT				GENMASK(3, 0)

@@ -671,15 +790,27 @@ enum pmic_id {
 /* ESM_SOC_START_REG register field definition */
 #define TPS6594_BIT_ESM_SOC_START			BIT(0)
 
+/* ESM_MCU_START_REG register field definition */
+#define TPS65224_BIT_ESM_MCU_START			BIT(0)
+
 /* ESM_SOC_MODE_CFG register field definition */
 #define TPS6594_MASK_ESM_SOC_ERR_CNT_TH			GENMASK(3, 0)
 #define TPS6594_BIT_ESM_SOC_ENDRV			BIT(5)
 #define TPS6594_BIT_ESM_SOC_EN				BIT(6)
 #define TPS6594_BIT_ESM_SOC_MODE			BIT(7)
 
+/* ESM_MCU_MODE_CFG register field definition */
+#define TPS65224_MASK_ESM_MCU_ERR_CNT_TH		GENMASK(3, 0)
+#define TPS65224_BIT_ESM_MCU_ENDRV			BIT(5)
+#define TPS65224_BIT_ESM_MCU_EN				BIT(6)
+#define TPS65224_BIT_ESM_MCU_MODE			BIT(7)
+
 /* ESM_SOC_ERR_CNT_REG register field definition */
 #define TPS6594_MASK_ESM_SOC_ERR_CNT			GENMASK(4, 0)
 
+/* ESM_MCU_ERR_CNT_REG register field definition */
+#define TPS6594_MASK_ESM_MCU_ERR_CNT			GENMASK(4, 0)
+
 /* REGISTER_LOCK register field definition */
 #define TPS6594_BIT_REGISTER_LOCK_STATUS		BIT(0)
 

@@ -687,6 +818,29 @@ enum pmic_id {
 #define TPS6594_MASK_VMON1_SLEW_RATE			GENMASK(2, 0)
 #define TPS6594_MASK_VMON2_SLEW_RATE			GENMASK(5, 3)
 
+/* SRAM_ACCESS_1 Register field definition */
+#define TPS65224_MASk_SRAM_UNLOCK_SEQ			GENMASK(7, 0)
+
+/* SRAM_ACCESS_2 Register field definition */
+#define TPS65224_BIT_SRAM_WRITE_MODE			BIT(0)
+#define TPS65224_BIT_OTP_PROG_USER			BIT(1)
+#define TPS65224_BIT_OTP_PROG_PFSM			BIT(2)
+#define TPS65224_BIT_OTP_PROG_STATUS			BIT(3)
+#define TPS65224_BIT_SRAM_UNLOCKED			BIT(6)
+#define TPS65224_USER_PROG_ALLOWED			BIT(7)
+
+/* SRAM_ADDR_CTRL Register field definition */
+#define TPS65224_MASk_SRAM_SEL				GENMASK(1, 0)
+
+/* RECOV_CNT_PFSM_INCR Register field definition */
+#define TPS65224_BIT_INCREMENT_RECOV_CNT		BIT(0)
+
+/* MANUFACTURING_VER Register field definition */
+#define TPS65224_MASK_SILICON_REV			GENMASK(7, 0)
+
+/* CUSTOMER_NVM_ID_REG Register field definition */
+#define TPS65224_MASK_CUSTOMER_NVM_ID			GENMASK(7, 0)
+
 /* SOFT_REBOOT_REG register field definition */
 #define TPS6594_BIT_SOFT_REBOOT				BIT(0)
 

@@ -755,14 +909,83 @@ enum pmic_id {
 #define TPS6594_BIT_I2C2_CRC_EN				BIT(2)
 #define TPS6594_MASK_T_CRC				GENMASK(7, 3)
 
+/* ADC_CTRL Register field definition */
+#define TPS65224_BIT_ADC_START				BIT(0)
+#define TPS65224_BIT_ADC_CONT_CONV			BIT(1)
+#define TPS65224_BIT_ADC_THERMAL_SEL			BIT(2)
+#define TPS65224_BIT_ADC_RDIV_EN			BIT(3)
+#define TPS65224_BIT_ADC_STATUS				BIT(7)
+
+/* ADC_RESULT_REG_1 Register field definition */
+#define TPS65224_MASK_ADC_RESULT_11_4			GENMASK(7, 0)
+
+/* ADC_RESULT_REG_2 Register field definition */
+#define TPS65224_MASK_ADC_RESULT_3_0			GENMASK(7, 4)
+
+/* STARTUP_CTRL Register field definition */
+#define TPS65224_MASK_STARTUP_DEST			GENMASK(6, 5)
+#define TPS65224_BIT_FIRST_STARTUP_DONE			BIT(7)
+
+/* SCRATCH_PAD_REG_1 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_1			GENMASK(7, 0)
+
+/* SCRATCH_PAD_REG_2 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_2			GENMASK(7, 0)
+
+/* SCRATCH_PAD_REG_3 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_3			GENMASK(7, 0)
+
+/* SCRATCH_PAD_REG_4 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_4			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_1 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY1			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_2 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY2			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_3 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY3			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_4 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY4			GENMASK(7, 0)
+
+/* CRC_CALC_CONTROL Register field definition */
+#define TPS65224_BIT_RUN_CRC_BIST			BIT(0)
+#define TPS65224_BIT_RUN_CRC_UPDATE			BIT(1)
+
+/* ADC_GAIN_COMP_REG Register field definition */
+#define TPS65224_MASK_ADC_GAIN_COMP			GENMASK(7, 0)
+
+/* REGMAP_USER_CRC_LOW Register field definition */
+#define TPS65224_MASK_REGMAP_USER_CRC16_LOW		GENMASK(7, 0)
+
+/* REGMAP_USER_CRC_HIGH Register field definition */
+#define TPS65224_MASK_REGMAP_USER_CRC16_HIGH		GENMASK(7, 0)
+
+/* WD_ANSWER_REG Register field definition */
+#define TPS6594_MASK_WD_ANSWER				GENMASK(7, 0)
+
 /* WD_QUESTION_ANSW_CNT register field definition */
 #define TPS6594_MASK_WD_QUESTION			GENMASK(3, 0)
 #define TPS6594_MASK_WD_ANSW_CNT			GENMASK(5, 4)
+#define TPS65224_BIT_INT_TOP_STATUS			BIT(7)
+
+/* WD WIN1_CFG register field definition */
+#define TPS6594_MASK_WD_WIN1_CFG			GENMASK(6, 0)
+
+/* WD WIN2_CFG register field definition */
+#define TPS6594_MASK_WD_WIN2_CFG			GENMASK(6, 0)
+
+/* WD LongWin register field definition */
+#define TPS6594_MASK_WD_LONGWIN_CFG			GENMASK(7, 0)
 
 /* WD_MODE_REG register field definition */
 #define TPS6594_BIT_WD_RETURN_LONGWIN			BIT(0)
 #define TPS6594_BIT_WD_MODE_SELECT			BIT(1)
 #define TPS6594_BIT_WD_PWRHOLD				BIT(2)
+#define TPS65224_BIT_WD_ENDRV_SEL			BIT(6)
+#define TPS65224_BIT_WD_CNT_SEL				BIT(7)
 
 /* WD_QA_CFG register field definition */
 #define TPS6594_MASK_WD_QUESTION_SEED			GENMASK(3, 0)