Merge: PCI/ASPM: Disable L1 before disabling L1 PM Substates

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7278

JIRA: https://issues.redhat.com/browse/RHEL-102694

## Summary of Changes

The following series updates PCI/ASPM code.

Signed-off-by: Marcin Juszkiewicz <mjuszkiewicz@redhat.com>

Approved-by: John W. Linville <linville@redhat.com>
Approved-by: Myron Stowe <mstowe@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

drivers/pci/pcie/aspm.c

@@ -81,24 +81,44 @@ void pci_configure_aspm_l1ss(struct pci_dev *pdev)
 
 void pci_save_aspm_l1ss_state(struct pci_dev *pdev)
 {
+	struct pci_dev *parent = pdev->bus->self;
 	struct pci_cap_saved_state *save_state;
-	u16 l1ss = pdev->l1ss;
 	u32 *cap;
 
+	/*
+	 * If this is a Downstream Port, we never restore the L1SS state
+	 * directly; we only restore it when we restore the state of the
+	 * Upstream Port below it.
+	 */
+	if (pcie_downstream_port(pdev) || !parent)
+		return;
+
+	if (!pdev->l1ss || !parent->l1ss)
+		return;
+
 	/*
 	 * Save L1 substate configuration. The ASPM L0s/L1 configuration
 	 * in PCI_EXP_LNKCTL_ASPMC is saved by pci_save_pcie_state().
 	 */
-	if (!l1ss)
+	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS);
+	if (!save_state)
 		return;
 
-	save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS);
+	cap = &save_state->cap.data[0];
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2, cap++);
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, cap++);
+
+	/*
+	 * Save parent's L1 substate configuration so we have it for
+	 * pci_restore_aspm_l1ss_state(pdev) to restore.
+	 */
+	save_state = pci_find_saved_ext_cap(parent, PCI_EXT_CAP_ID_L1SS);
 	if (!save_state)
 		return;
 
 	cap = &save_state->cap.data[0];
-	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL2, cap++);
-	pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, cap++);
+	pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, cap++);
+	pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, cap++);
 }
 
 void pci_restore_aspm_l1ss_state(struct pci_dev *pdev)
@@ -805,6 +825,15 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &parent_lnkctl);
 	pcie_capability_read_word(child, PCI_EXP_LNKCTL, &child_lnkctl);
 
+	/* Disable L0s/L1 before updating L1SS config */
+	if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) ||
+	    FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) {
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL,
+					   child_lnkctl & ~PCI_EXP_LNKCTL_ASPMC);
+		pcie_capability_write_word(parent, PCI_EXP_LNKCTL,
+					   parent_lnkctl & ~PCI_EXP_LNKCTL_ASPMC);
+	}
+
 	/*
 	 * Setup L0s state
 	 *
@@ -829,6 +858,13 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 
 	aspm_l1ss_init(link);
 
+	/* Restore L0s/L1 if they were enabled */
+	if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, child_lnkctl) ||
+	    FIELD_GET(PCI_EXP_LNKCTL_ASPMC, parent_lnkctl)) {
+		pcie_capability_write_word(parent, PCI_EXP_LNKCTL, parent_lnkctl);
+		pcie_capability_write_word(child, PCI_EXP_LNKCTL, child_lnkctl);
+	}
+
 	/* Save default state */
 	link->aspm_default = link->aspm_enabled;
 
@@ -845,52 +881,35 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	}
 }
 
-/* Configure the ASPM L1 substates */
+/* Configure the ASPM L1 substates. Caller must disable L1 first. */
 static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 {
-	u32 val, enable_req;
+	u32 val;
 	struct pci_dev *child = link->downstream, *parent = link->pdev;
 
-	enable_req = (link->aspm_enabled ^ state) & state;
+	val = 0;
+	if (state & PCIE_LINK_STATE_L1_1)
+		val |= PCI_L1SS_CTL1_ASPM_L1_1;
+	if (state & PCIE_LINK_STATE_L1_2)
+		val |= PCI_L1SS_CTL1_ASPM_L1_2;
+	if (state & PCIE_LINK_STATE_L1_1_PCIPM)
+		val |= PCI_L1SS_CTL1_PCIPM_L1_1;
+	if (state & PCIE_LINK_STATE_L1_2_PCIPM)
+		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/*
-	 * Here are the rules specified in the PCIe spec for enabling L1SS:
-	 * - When enabling L1.x, enable bit at parent first, then at child
-	 * - When disabling L1.x, disable bit at child first, then at parent
-	 * - When enabling ASPM L1.x, need to disable L1
-	 *   (at child followed by parent).
-	 * - The ASPM/PCIPM L1.2 must be disabled while programming timing
+	 * PCIe r6.2, sec 5.5.4, rules for enabling L1 PM Substates:
+	 * - Clear L1.x enable bits at child first, then at parent
+	 * - Set L1.x enable bits at parent first, then at child
+	 * - ASPM/PCIPM L1.2 must be disabled while programming timing
 	 *   parameters
-	 *
-	 * To keep it simple, disable all L1SS bits first, and later enable
-	 * what is needed.
 	 */
 
 	/* Disable all L1 substates */
 	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
 				       PCI_L1SS_CTL1_L1SS_MASK, 0);
 	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 				       PCI_L1SS_CTL1_L1SS_MASK, 0);
-	/*
-	 * If needed, disable L1, and it gets enabled later
-	 * in pcie_config_aspm_link().
-	 */
-	if (enable_req & (PCIE_LINK_STATE_L1_1 | PCIE_LINK_STATE_L1_2)) {
-		pcie_capability_clear_word(child, PCI_EXP_LNKCTL,
-					   PCI_EXP_LNKCTL_ASPM_L1);
-		pcie_capability_clear_word(parent, PCI_EXP_LNKCTL,
-					   PCI_EXP_LNKCTL_ASPM_L1);
-	}
-
-	val = 0;
-	if (state & PCIE_LINK_STATE_L1_1)
-		val |= PCI_L1SS_CTL1_ASPM_L1_1;
-	if (state & PCIE_LINK_STATE_L1_2)
-		val |= PCI_L1SS_CTL1_ASPM_L1_2;
-	if (state & PCIE_LINK_STATE_L1_1_PCIPM)
-		val |= PCI_L1SS_CTL1_PCIPM_L1_1;
-	if (state & PCIE_LINK_STATE_L1_2_PCIPM)
-		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
 	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
@@ -937,21 +956,30 @@ static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state)
 		dwstream |= PCI_EXP_LNKCTL_ASPM_L1;
 	}
 
+	/*
+	 * Per PCIe r6.2, sec 5.5.4, setting either or both of the enable
+	 * bits for ASPM L1 PM Substates must be done while ASPM L1 is
+	 * disabled. Disable L1 here and apply new configuration after L1SS
+	 * configuration has been completed.
+	 *
+	 * Per sec 7.5.3.7, when disabling ASPM L1, software must disable
+	 * it in the Downstream component prior to disabling it in the
+	 * Upstream component, and ASPM L1 must be enabled in the Upstream
+	 * component prior to enabling it in the Downstream component.
+	 *
+	 * Sec 7.5.3.7 also recommends programming the same ASPM Control
+	 * value for all functions of a multi-function device.
+	 */
+	list_for_each_entry(child, &linkbus->devices, bus_list)
+		pcie_config_aspm_dev(child, 0);
+	pcie_config_aspm_dev(parent, 0);
+
 	if (link->aspm_capable & PCIE_LINK_STATE_L1SS)
 		pcie_config_aspm_l1ss(link, state);
 
-	/*
-	 * Spec 2.0 suggests all functions should be configured the
-	 * same setting for ASPM. Enabling ASPM L1 should be done in
-	 * upstream component first and then downstream, and vice
-	 * versa for disabling ASPM L1. Spec doesn't mention L0S.
-	 */
-	if (state & PCIE_LINK_STATE_L1)
-		pcie_config_aspm_dev(parent, upstream);
+	pcie_config_aspm_dev(parent, upstream);
 	list_for_each_entry(child, &linkbus->devices, bus_list)
 		pcie_config_aspm_dev(child, dwstream);
-	if (!(state & PCIE_LINK_STATE_L1))
-		pcie_config_aspm_dev(parent, upstream);
 
 	link->aspm_enabled = state;
 
@@ -1242,16 +1270,16 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 	parent_link = link->parent;
 
 	/*
-	 * link->downstream is a pointer to the pci_dev of function 0.  If
-	 * we remove that function, the pci_dev is about to be deallocated,
-	 * so we can't use link->downstream again.  Free the link state to
-	 * avoid this.
+	 * Free the parent link state, no later than function 0 (i.e.
+	 * link->downstream) being removed.
 	 *
-	 * If we're removing a non-0 function, it's possible we could
-	 * retain the link state, but PCIe r6.0, sec 7.5.3.7, recommends
-	 * programming the same ASPM Control value for all functions of
-	 * multi-function devices, so disable ASPM for all of them.
+	 * Do not free the link state any earlier. If function 0 is a
+	 * switch upstream port, this link state is parent_link to all
+	 * subordinate ones.
 	 */
+	if (pdev != link->downstream)
+		goto out;
+
 	pcie_config_aspm_link(link, 0);
 	list_del(&link->sibling);
 	free_link_state(link);
@@ -1262,6 +1290,7 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 		pcie_config_aspm_path(parent_link);
 	}
 
+ out:
 	mutex_unlock(&aspm_lock);
 	up_read(&pci_bus_sem);
 }
@@ -1442,6 +1471,9 @@ static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked)
  * touch the LNKCTL register. Also note that this does not enable states
  * disabled by pci_disable_link_state(). Return 0 or a negative errno.
  *
+ * Note: Ensure devices are in D0 before enabling PCI-PM L1 PM Substates, per
+ * PCIe r6.0, sec 5.5.4.
+ *
  * @pdev: PCI device
  * @state: Mask of ASPM link states to enable
  */
@@ -1458,6 +1490,9 @@ EXPORT_SYMBOL(pci_enable_link_state);
  * can't touch the LNKCTL register. Also note that this does not enable states
  * disabled by pci_disable_link_state(). Return 0 or a negative errno.
  *
+ * Note: Ensure devices are in D0 before enabling PCI-PM L1 PM Substates, per
+ * PCIe r6.0, sec 5.5.4.
+ *
  * @pdev: PCI device
  * @state: Mask of ASPM link states to enable
  *