IB/hfi1: Fixes for RC

index b2ed4b9..1c810d6 100644
@@ -1066,6 +1066,8 @@ static int do_8051_command(struct hfi1_devdata *dd, u32 type, u64 in_data,
 static int thermal_init(struct hfi1_devdata *dd);
 
 static void update_statusp(struct hfi1_pportdata *ppd, u32 state);
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs);
 static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 				  int msecs);
 static void log_state_transition(struct hfi1_pportdata *ppd, u32 state);

@@ -10305,6 +10307,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	u32 previous_state;
+	int offline_state_ret;
 	int ret;
 
 	update_lcb_cache(dd);

@@ -10326,28 +10329,11 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 		ppd->offline_disabled_reason =
 		HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT);
 
-	/*
-	 * Wait for offline transition. It can take a while for
-	 * the link to go down.
-	 */
-	ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * Now in charge of LCB - must be after the physical state is
-	 * offline.quiet and before host_link_state is changed.
-	 */
-	set_host_lcb_access(dd);
-	write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
-
-	/* make sure the logical state is also down */
-	ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
-	if (ret)
-		force_logical_link_state_down(ppd);
-
-	ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
+	offline_state_ret = wait_phys_link_offline_substates(ppd, 10000);
+	if (offline_state_ret < 0)
+		return offline_state_ret;
 
+	/* Disabling AOC transmitters */
 	if (ppd->port_type == PORT_TYPE_QSFP &&
 	    ppd->qsfp_info.limiting_active &&
 	    qsfp_mod_present(ppd)) {

@@ -10365,6 +10351,30 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 	}
 
 	/*
+	 * Wait for the offline.Quiet transition if it hasn't happened yet. It
+	 * can take a while for the link to go down.
+	 */
+	if (offline_state_ret != PLS_OFFLINE_QUIET) {
+		ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * Now in charge of LCB - must be after the physical state is
+	 * offline.quiet and before host_link_state is changed.
+	 */
+	set_host_lcb_access(dd);
+	write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
+
+	/* make sure the logical state is also down */
+	ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
+	if (ret)
+		force_logical_link_state_down(ppd);
+
+	ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
+
+	/*
 	 * The LNI has a mandatory wait time after the physical state
 	 * moves to Offline.Quiet.  The wait time may be different
 	 * depending on how the link went down.  The 8051 firmware

@@ -12804,6 +12814,39 @@ static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state,
 	return 0;
 }
 
+/*
+ * wait_phys_link_offline_quiet_substates - wait for any offline substate
+ * @ppd: port device
+ * @msecs: the number of milliseconds to wait
+ *
+ * Wait up to msecs milliseconds for any offline physical link
+ * state change to occur.
+ * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT.
+ */
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+					    int msecs)
+{
+	u32 read_state;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(msecs);
+	while (1) {
+		read_state = read_physical_state(ppd->dd);
+		if ((read_state & 0xF0) == PLS_OFFLINE)
+			break;
+		if (time_after(jiffies, timeout)) {
+			dd_dev_err(ppd->dd,
+				   "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n",
+				   read_state, msecs);
+			return -ETIMEDOUT;
+		}
+		usleep_range(1950, 2050); /* sleep 2ms-ish */
+	}
+
+	log_state_transition(ppd, read_state);
+	return read_state;
+}
+
 #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
 (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)
 

index b8345a6..461f937 100644
@@ -204,6 +204,7 @@
 #define PLS_OFFLINE_READY_TO_QUIET_LT	   0x92
 #define PLS_OFFLINE_REPORT_FAILURE		   0x93
 #define PLS_OFFLINE_READY_TO_QUIET_BCC	   0x94
+#define PLS_OFFLINE_QUIET_DURATION	   0x95
 #define PLS_POLLING				   0x20
 #define PLS_POLLING_QUIET			   0x20
 #define PLS_POLLING_ACTIVE			   0x21

index 1c810d6..27b75a8 100644
@@ -9415,7 +9415,7 @@ static void set_qsfp_int_n(struct hfi1_pportdata *ppd, u8 enable)
 	write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask);
 }
 
-void reset_qsfp(struct hfi1_pportdata *ppd)
+int reset_qsfp(struct hfi1_pportdata *ppd)
 {
 	struct hfi1_devdata *dd = ppd->dd;
 	u64 mask, qsfp_mask;

@@ -9445,6 +9445,13 @@ void reset_qsfp(struct hfi1_pportdata *ppd)
 	 * for alarms and warnings
 	 */
 	set_qsfp_int_n(ppd, 1);
+
+	/*
+	 * After the reset, AOC transmitters are enabled by default. They need
+	 * to be turned off to complete the QSFP setup before they can be
+	 * enabled again.
+	 */
+	return set_qsfp_tx(ppd, 0);
 }
 
 static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,

@@ -10406,6 +10413,9 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason)
 			& (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) {
 		/* went down while attempting link up */
 		check_lni_states(ppd);
+
+		/* The QSFP doesn't need to be reset on LNI failure */
+		ppd->qsfp_info.reset_needed = 0;
 	}
 
 	/* the active link width (downgrade) is 0 on link down */

index 461f937..50b8645 100644
@@ -723,7 +723,7 @@ void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason,
 void handle_link_bounce(struct work_struct *work);
 void handle_start_link(struct work_struct *work);
 void handle_sma_message(struct work_struct *work);
-void reset_qsfp(struct hfi1_pportdata *ppd);
+int reset_qsfp(struct hfi1_pportdata *ppd);
 void qsfp_event(struct work_struct *work);
 void start_freeze_handling(struct hfi1_pportdata *ppd, int flags);
 int send_idle_sma(struct hfi1_devdata *dd, u64 message);

index a8af96d..d486355 100644
@@ -790,7 +790,9 @@ static int tune_active_qsfp(struct hfi1_pportdata *ppd, u32 *ptr_tx_preset,
 	 * reuse of stale settings established in our previous pass through.
 	 */
 	if (ppd->qsfp_info.reset_needed) {
-		reset_qsfp(ppd);
+		ret = reset_qsfp(ppd);
+		if (ret)
+			return ret;
 		refresh_qsfp_cache(ppd, &ppd->qsfp_info);
 	} else {
 		ppd->qsfp_info.reset_needed = 1;

index d46b171..1613af1 100644
@@ -204,7 +204,10 @@ int eprom_init(struct hfi1_devdata *dd)
 	return ret;
 }
 
-/* magic character sequence that trails an image */
+/* magic character sequence that begins an image */
+#define IMAGE_START_MAGIC "APO="
+
+/* magic character sequence that might trail an image */
 #define IMAGE_TRAIL_MAGIC "egamiAPO"
 
 /* EPROM file types */

@@ -250,6 +253,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
 {
 	void *buffer;
 	void *p;
+	u32 length;
 	int ret;
 
 	buffer = kmalloc(P1_SIZE, GFP_KERNEL);

@@ -262,15 +266,21 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data,
 		return ret;
 	}
 
-	/* scan for image magic that may trail the actual data */
-	p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
-	if (!p) {
+	/* config partition is valid only if it starts with IMAGE_START_MAGIC */
+	if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) {
 		kfree(buffer);
 		return -ENOENT;
 	}
 
+	/* scan for image magic that may trail the actual data */
+	p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
+	if (p)
+		length = p - buffer;
+	else
+		length = P1_SIZE;
+
 	*data = buffer;
-	*size = p - buffer;
+	*size = length;
 	return 0;
 }
 

index 27b75a8..0be4278 100644
@@ -8240,6 +8240,7 @@ static irqreturn_t general_interrupt(int irq, void *data)
 	u64 regs[CCE_NUM_INT_CSRS];
 	u32 bit;
 	int i;
+	irqreturn_t handled = IRQ_NONE;
 
 	this_cpu_inc(*dd->int_counter);
 

@@ -8260,9 +8261,10 @@ static irqreturn_t general_interrupt(int irq, void *data)
 	for_each_set_bit(bit, (unsigned long *)&regs[0],
 			 CCE_NUM_INT_CSRS * 64) {
 		is_interrupt(dd, bit);
+		handled = IRQ_HANDLED;
 	}
 
-	return IRQ_HANDLED;
+	return handled;
 }
 
 static irqreturn_t sdma_interrupt(int irq, void *data)

index 2bc8926..d9a1e98 100644
@@ -930,15 +930,8 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo)
 	switch (ret) {
 	case 0:
 		ret = setup_base_ctxt(fd, uctxt);
-		if (uctxt->subctxt_cnt) {
-			/*
-			 * Base context is done (successfully or not), notify
-			 * anybody using a sub-context that is waiting for
-			 * this completion.
-			 */
-			clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
-			wake_up(&uctxt->wait);
-		}
+		if (ret)
+			deallocate_ctxt(uctxt);
 		break;
 	case 1:
 		ret = complete_subctxt(fd);

@@ -1305,25 +1298,25 @@ static int setup_base_ctxt(struct hfi1_filedata *fd,
 	/* Now allocate the RcvHdr queue and eager buffers. */
 	ret = hfi1_create_rcvhdrq(dd, uctxt);
 	if (ret)
-		return ret;
+		goto done;
 
 	ret = hfi1_setup_eagerbufs(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	/* If sub-contexts are enabled, do the appropriate setup */
 	if (uctxt->subctxt_cnt)
 		ret = setup_subctxt(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	ret = hfi1_alloc_ctxt_rcv_groups(uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	ret = init_user_ctxt(fd, uctxt);
 	if (ret)
-		goto setup_failed;
+		goto done;
 
 	user_init(uctxt);
 

@@ -1331,12 +1324,22 @@ static int setup_base_ctxt(struct hfi1_filedata *fd,
 	fd->uctxt = uctxt;
 	hfi1_rcd_get(uctxt);
 
-	return 0;
+done:
+	if (uctxt->subctxt_cnt) {
+		/*
+		 * On error, set the failed bit so sub-contexts will clean up
+		 * correctly.
+		 */
+		if (ret)
+			set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
 
-setup_failed:
-	/* Set the failed bit so sub-context init can do the right thing */
-	set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
-	deallocate_ctxt(uctxt);
+		/*
+		 * Base context is done (successfully or not), notify anybody
+		 * using a sub-context that is waiting for this completion.
+		 */
+		clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
+		wake_up(&uctxt->wait);
+	}
 
 	return ret;
 }

index 82447b7..09e50fd 100644
@@ -68,7 +68,7 @@
 /*
  * Code to adjust PCIe capabilities.
  */
-static int tune_pcie_caps(struct hfi1_devdata *);
+static void tune_pcie_caps(struct hfi1_devdata *);
 
 /*
  * Do all the common PCIe setup and initialization.

@@ -351,7 +351,7 @@ int pcie_speeds(struct hfi1_devdata *dd)
  */
 int request_msix(struct hfi1_devdata *dd, u32 msireq)
 {
-	int nvec, ret;
+	int nvec;
 
 	nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq,
 				     PCI_IRQ_MSIX | PCI_IRQ_LEGACY);

@@ -360,12 +360,7 @@ int request_msix(struct hfi1_devdata *dd, u32 msireq)
 		return nvec;
 	}
 
-	ret = tune_pcie_caps(dd);
-	if (ret) {
-		dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret);
-		pci_free_irq_vectors(dd->pcidev);
-		return ret;
-	}
+	tune_pcie_caps(dd);
 
 	/* check for legacy IRQ */
 	if (nvec == 1 && !dd->pcidev->msix_enabled)

@@ -502,7 +497,7 @@ int save_pci_variables(struct hfi1_devdata *dd)
 module_param_named(aspm, aspm_mode, uint, S_IRUGO);
 MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic");
 
-static int tune_pcie_caps(struct hfi1_devdata *dd)
+static void tune_pcie_caps(struct hfi1_devdata *dd)
 {
 	struct pci_dev *parent;
 	u16 rc_mpss, rc_mps, ep_mpss, ep_mps;

@@ -513,22 +508,14 @@ static int tune_pcie_caps(struct hfi1_devdata *dd)
 	 * Turn on extended tags in DevCtl in case the BIOS has turned it off
 	 * to improve WFR SDMA bandwidth
 	 */
-	ret = pcie_capability_read_word(dd->pcidev,
-					PCI_EXP_DEVCTL, &ectl);
-	if (ret) {
-		dd_dev_err(dd, "Unable to read from PCI config\n");
-		return ret;
-	}
-
-	if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
+	ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl);
+	if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
 		dd_dev_info(dd, "Enabling PCIe extended tags\n");
 		ectl |= PCI_EXP_DEVCTL_EXT_TAG;
 		ret = pcie_capability_write_word(dd->pcidev,
 						 PCI_EXP_DEVCTL, ectl);
-		if (ret) {
-			dd_dev_err(dd, "Unable to write to PCI config\n");
-			return ret;
-		}
+		if (ret)
+			dd_dev_info(dd, "Unable to write to PCI config\n");
 	}
 	/* Find out supported and configured values for parent (root) */
 	parent = dd->pcidev->bus->self;

@@ -536,15 +523,22 @@ static int tune_pcie_caps(struct hfi1_devdata *dd)
 	 * The driver cannot perform the tuning if it does not have
 	 * access to the upstream component.
 	 */
-	if (!parent)
-		return -EINVAL;
+	if (!parent) {
+		dd_dev_info(dd, "Parent not found\n");
+		return;
+	}
 	if (!pci_is_root_bus(parent->bus)) {
 		dd_dev_info(dd, "Parent not root\n");
-		return -EINVAL;
+		return;
+	}
+	if (!pci_is_pcie(parent)) {
+		dd_dev_info(dd, "Parent is not PCI Express capable\n");
+		return;
+	}
+	if (!pci_is_pcie(dd->pcidev)) {
+		dd_dev_info(dd, "PCI device is not PCI Express capable\n");
+		return;
 	}
-
-	if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
-		return -EINVAL;
 	rc_mpss = parent->pcie_mpss;
 	rc_mps = ffs(pcie_get_mps(parent)) - 8;
 	/* Find out supported and configured values for endpoint (us) */

@@ -590,8 +584,6 @@ static int tune_pcie_caps(struct hfi1_devdata *dd)
 		ep_mrrs = max_mrrs;
 		pcie_set_readrq(dd->pcidev, ep_mrrs);
 	}
-
-	return 0;
 }
 
 /* End of PCIe capability tuning */

index 2e07537..6cd6163 100644
@@ -1000,19 +1000,6 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv)
 		 */
 		priv->dev->broadcast[8] = priv->pkey >> 8;
 		priv->dev->broadcast[9] = priv->pkey & 0xff;
-
-		/*
-		 * Update the broadcast address in the priv->broadcast object,
-		 * in case it already exists, otherwise no one will do that.
-		 */
-		if (priv->broadcast) {
-			spin_lock_irq(&priv->lock);
-			memcpy(priv->broadcast->mcmember.mgid.raw,
-			       priv->dev->broadcast + 4,
-			sizeof(union ib_gid));
-			spin_unlock_irq(&priv->lock);
-		}
-
 		return 0;
 	}