From 97645154a9056106a957905c7836a016e5c89b3b Mon Sep 17 00:00:00 2001
From: Paul Bolle <pebolle@tiscali.nl>
Date: Sun, 14 Jul 2013 13:02:15 +0200
Subject: powerpc/pseries: Drop "select HOTPLUG"

The Kconfig symbol HOTPLUG was removed with commit 40b313608a ("Finally
eradicate CONFIG_HOTPLUG"). But there's still one select statement for
that symbol. It seems that select statement was added after the patch to
remove CONFIG_HOTPLUG was submitted. Anyhow, it is useless and can be
dropped.

Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/Kconfig | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 1bd3399146ed..62b4f8025de0 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -19,7 +19,6 @@ config PPC_PSERIES
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
-	select HOTPLUG if SMP
 	select HOTPLUG_CPU if SMP
 	default y
 
-- 
cgit v1.2.3


From ee1dd1e3dc774cf257012215d996e8e7e370c162 Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Wed, 10 Jul 2013 18:32:56 +0530
Subject: powerpc: Fix the corrupt r3 error during MCE handling.

During Machine Check interrupt on pseries platform, R3 generally points to
memory region inside RTAS (FWNMI) area. We see r3 corruption because when RTAS
delivers the machine check exception it passes the address inside FWNMI area
with the top most bit set. This patch fixes this issue by masking top two bit
in machine check exception handler.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/ras.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 7b3cbde8c783..721c0586b284 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -287,6 +287,9 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 	unsigned long *savep;
 	struct rtas_error_log *h, *errhdr = NULL;
 
+	/* Mask top two bits */
+	regs->gpr[3] &= ~(0x3UL << 62);
+
 	if (!VALID_FWNMI_BUFFER(regs->gpr[3])) {
 		printk(KERN_ERR "FWNMI: corrupt r3 0x%016lx\n", regs->gpr[3]);
 		return NULL;
-- 
cgit v1.2.3


From f5c57710dd62dd06f176934a8b4b8accbf00f9f8 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 24 Jul 2013 10:24:58 +0800
Subject: powerpc/eeh: Use partial hotplug for EEH unaware drivers

When EEH error happens to one specific PE, some devices with drivers
supporting EEH won't except hotplug on the device. However, there
might have other deivces without driver, or with driver without EEH
support. For the case, we need do partial hotplug in order to make
sure that the PE becomes absolutely quite during reset. Otherise,
the PE reset might fail and leads to failure of error recovery.

The current code doesn't handle that 'mixed' case properly, it either
uses the error callbacks to the drivers, or tries hotplug, but doesn't
handle a PE (EEH domain) composed of a combination of the two.

The patch intends to support so-called "partial" hotplug for EEH:
Before we do reset, we stop and remove those PCI devices without
EEH sensitive driver. The corresponding EEH devices are not detached
from its PE, but with special flag. After the reset is done, those
EEH devices with the special flag will be scanned one by one.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h               |  6 ++-
 arch/powerpc/kernel/eeh.c                    | 30 +++++++++--
 arch/powerpc/kernel/eeh_driver.c             | 74 ++++++++++++++++++++++++++--
 arch/powerpc/kernel/eeh_pe.c                 | 20 +++-----
 arch/powerpc/kernel/eeh_sysfs.c              |  7 +++
 arch/powerpc/platforms/powernv/eeh-powernv.c |  2 +-
 arch/powerpc/platforms/pseries/eeh_pseries.c |  2 +-
 7 files changed, 117 insertions(+), 24 deletions(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index e8c411b63caf..f54a60131de5 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -84,7 +84,8 @@ struct eeh_pe {
  * another tree except the currently existing tree of PCI
  * buses and PCI devices
  */
-#define EEH_DEV_IRQ_DISABLED	(1<<0)	/* Interrupt disabled		*/
+#define EEH_DEV_IRQ_DISABLED	(1 << 0)	/* Interrupt disabled	*/
+#define EEH_DEV_DISCONNECTED	(1 << 1)	/* Removing from PE	*/
 
 struct eeh_dev {
 	int mode;			/* EEH mode			*/
@@ -97,6 +98,7 @@ struct eeh_dev {
 	struct pci_controller *phb;	/* Associated PHB		*/
 	struct device_node *dn;		/* Associated device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
+	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
 
 static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
@@ -197,6 +199,8 @@ struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
 int eeh_add_to_parent_pe(struct eeh_dev *edev);
 int eeh_rmv_from_parent_pe(struct eeh_dev *edev);
 void eeh_pe_update_time_stamp(struct eeh_pe *pe);
+void *eeh_pe_traverse(struct eeh_pe *root,
+		eeh_traverse_func fn, void *flag);
 void *eeh_pe_dev_traverse(struct eeh_pe *root,
 		eeh_traverse_func fn, void *flag);
 void eeh_pe_restore_bars(struct eeh_pe *pe);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 56bd4584f61f..a5783f1a7a96 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -900,7 +900,21 @@ void eeh_add_device_late(struct pci_dev *dev)
 		pr_debug("EEH: Already referenced !\n");
 		return;
 	}
-	WARN_ON(edev->pdev);
+
+	/*
+	 * The EEH cache might not be removed correctly because of
+	 * unbalanced kref to the device during unplug time, which
+	 * relies on pcibios_release_device(). So we have to remove
+	 * that here explicitly.
+	 */
+	if (edev->pdev) {
+		eeh_rmv_from_parent_pe(edev);
+		eeh_addr_cache_rmv_dev(edev->pdev);
+		eeh_sysfs_remove_device(edev->pdev);
+
+		edev->pdev = NULL;
+		dev->dev.archdata.edev = NULL;
+	}
 
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
@@ -982,14 +996,24 @@ void eeh_remove_device(struct pci_dev *dev)
 	/* Unregister the device with the EEH/PCI address search system */
 	pr_debug("EEH: Removing device %s\n", pci_name(dev));
 
-	if (!edev || !edev->pdev) {
+	if (!edev || !edev->pdev || !edev->pe) {
 		pr_debug("EEH: Not referenced !\n");
 		return;
 	}
+
+	/*
+	 * During the hotplug for EEH error recovery, we need the EEH
+	 * device attached to the parent PE in order for BAR restore
+	 * a bit later. So we keep it for BAR restore and remove it
+	 * from the parent PE during the BAR resotre.
+	 */
 	edev->pdev = NULL;
 	dev->dev.archdata.edev = NULL;
+	if (!(edev->pe->state & EEH_PE_KEEP))
+		eeh_rmv_from_parent_pe(edev);
+	else
+		edev->mode |= EEH_DEV_DISCONNECTED;
 
-	eeh_rmv_from_parent_pe(edev);
 	eeh_addr_cache_rmv_dev(dev);
 	eeh_sysfs_remove_device(dev);
 }
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 9ef3bbb8580a..9fda75d1f5aa 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -338,6 +338,54 @@ static void *eeh_report_failure(void *data, void *userdata)
 	return NULL;
 }
 
+static void *eeh_rmv_device(void *data, void *userdata)
+{
+	struct pci_driver *driver;
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	int *removed = (int *)userdata;
+
+	/*
+	 * Actually, we should remove the PCI bridges as well.
+	 * However, that's lots of complexity to do that,
+	 * particularly some of devices under the bridge might
+	 * support EEH. So we just care about PCI devices for
+	 * simplicity here.
+	 */
+	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
+		return NULL;
+	driver = eeh_pcid_get(dev);
+	if (driver && driver->err_handler)
+		return NULL;
+
+	/* Remove it from PCI subsystem */
+	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
+		 pci_name(dev));
+	edev->bus = dev->bus;
+	edev->mode |= EEH_DEV_DISCONNECTED;
+	(*removed)++;
+
+	pci_stop_and_remove_bus_device(dev);
+
+	return NULL;
+}
+
+static void *eeh_pe_detach_dev(void *data, void *userdata)
+{
+	struct eeh_pe *pe = (struct eeh_pe *)data;
+	struct eeh_dev *edev, *tmp;
+
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		if (!(edev->mode & EEH_DEV_DISCONNECTED))
+			continue;
+
+		edev->mode &= ~(EEH_DEV_DISCONNECTED | EEH_DEV_IRQ_DISABLED);
+		eeh_rmv_from_parent_pe(edev);
+	}
+
+	return NULL;
+}
+
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
  * @pe: EEH PE
@@ -349,8 +397,9 @@ static void *eeh_report_failure(void *data, void *userdata)
  */
 static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 {
+	struct pci_bus *frozen_bus = eeh_pe_bus_get(pe);
 	struct timeval tstamp;
-	int cnt, rc;
+	int cnt, rc, removed = 0;
 
 	/* pcibios will clear the counter; save the value */
 	cnt = pe->freeze_count;
@@ -362,10 +411,11 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * devices are expected to be attached soon when calling
 	 * into pcibios_add_pci_devices().
 	 */
-	if (bus) {
-		eeh_pe_state_mark(pe, EEH_PE_KEEP);
+	eeh_pe_state_mark(pe, EEH_PE_KEEP);
+	if (bus)
 		pcibios_remove_pci_devices(bus);
-	}
+	else if (frozen_bus)
+		eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
 
 	/* Reset the pci controller. (Asserts RST#; resets config space).
 	 * Reconfigure bridges and devices. Don't try to bring the system
@@ -386,10 +436,24 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * potentially weird things happen.
 	 */
 	if (bus) {
+		pr_info("EEH: Sleep 5s ahead of complete hotplug\n");
 		ssleep(5);
+
+		/*
+		 * The EEH device is still connected with its parent
+		 * PE. We should disconnect it so the binding can be
+		 * rebuilt when adding PCI devices.
+		 */
+		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
 		pcibios_add_pci_devices(bus);
-		eeh_pe_state_clear(pe, EEH_PE_KEEP);
+	} else if (frozen_bus && removed) {
+		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
+		ssleep(5);
+
+		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
+		pcibios_add_pci_devices(frozen_bus);
 	}
+	eeh_pe_state_clear(pe, EEH_PE_KEEP);
 
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index c8b815e45c8f..2aa955ae01a1 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -149,8 +149,8 @@ static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
  * callback returns something other than NULL, or no more PEs
  * to be traversed.
  */
-static void *eeh_pe_traverse(struct eeh_pe *root,
-			eeh_traverse_func fn, void *flag)
+void *eeh_pe_traverse(struct eeh_pe *root,
+		      eeh_traverse_func fn, void *flag)
 {
 	struct eeh_pe *pe;
 	void *ret;
@@ -409,8 +409,8 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 	int cnt;
 
 	if (!edev->pe) {
-		pr_warning("%s: No PE found for EEH device %s\n",
-			__func__, edev->dn->full_name);
+		pr_debug("%s: No PE found for EEH device %s\n",
+			 __func__, edev->dn->full_name);
 		return -EEXIST;
 	}
 
@@ -728,18 +728,12 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
  */
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
-	struct pci_dev *pdev = NULL;
 	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
 	struct device_node *dn = eeh_dev_to_of_node(edev);
 
-	/* Trace the PCI bridge */
-	if (eeh_probe_mode_dev()) {
-		pdev = eeh_dev_to_pci_dev(edev);
-		if (pdev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
-                        pdev = NULL;
-        }
-
-	if (pdev)
+	/* Do special restore for bridges */
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
 		eeh_restore_bridge_bars(pdev, edev, dn);
 	else
 		eeh_restore_device_bars(edev, dn);
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index e7ae3484918c..61e2a1452131 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -68,6 +68,13 @@ void eeh_sysfs_add_device(struct pci_dev *pdev)
 
 void eeh_sysfs_remove_device(struct pci_dev *pdev)
 {
+	/*
+	 * The parent directory might have been removed. We needn't
+	 * continue for that case.
+	 */
+	if (!pdev->dev.kobj.sd)
+		return;
+
 	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 969cce73055a..a380428cf9ce 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -114,7 +114,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	 * the root bridge. So it's not reasonable to continue
 	 * the probing.
 	 */
-	if (!dn || !edev)
+	if (!dn || !edev || edev->pe)
 		return 0;
 
 	/* Skip for PCI-ISA bridge */
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b456b157d33d..0f44f9fe49ac 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -153,7 +153,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 
 	/* Retrieve OF node and eeh device */
 	edev = of_node_to_eeh_dev(dn);
-	if (!of_device_is_available(dn))
+	if (edev->pe || !of_device_is_available(dn))
 		return NULL;
 
 	/* Retrieve class/vendor/device IDs */
-- 
cgit v1.2.3


From 4b83bd452f17582c8d1c916568fd28a237a2eb46 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 24 Jul 2013 10:24:59 +0800
Subject: powerpc/eeh: Don't use pci_dev during BAR restore

While restoring BARs for one specific PCI device, the pci_dev
instance should have been released. So it's not reliable to use
the pci_dev instance on restoring BARs. However, we still need
some information (e.g. PCIe capability position, header type) from
the pci_dev instance. So we have to store those information to
EEH device in advance.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h               |  8 +++-
 arch/powerpc/kernel/eeh_pe.c                 | 25 ++++++-----
 arch/powerpc/platforms/powernv/eeh-powernv.c | 11 +++++
 arch/powerpc/platforms/pseries/eeh_pseries.c | 63 +++++++++++++++++++++++++++-
 4 files changed, 91 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index f54a60131de5..4199d9943277 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -84,8 +84,11 @@ struct eeh_pe {
  * another tree except the currently existing tree of PCI
  * buses and PCI devices
  */
-#define EEH_DEV_IRQ_DISABLED	(1 << 0)	/* Interrupt disabled	*/
-#define EEH_DEV_DISCONNECTED	(1 << 1)	/* Removing from PE	*/
+#define EEH_DEV_BRIDGE		(1 << 0)	/* PCI bridge		*/
+#define EEH_DEV_ROOT_PORT	(1 << 1)	/* PCIe root port	*/
+#define EEH_DEV_DS_PORT		(1 << 2)	/* Downstream port	*/
+#define EEH_DEV_IRQ_DISABLED	(1 << 3)	/* Interrupt disabled	*/
+#define EEH_DEV_DISCONNECTED	(1 << 4)	/* Removing from PE	*/
 
 struct eeh_dev {
 	int mode;			/* EEH mode			*/
@@ -93,6 +96,7 @@ struct eeh_dev {
 	int config_addr;		/* Config address		*/
 	int pe_config_addr;		/* PE config address		*/
 	u32 config_space[16];		/* Saved PCI config space	*/
+	u8 pcie_cap;			/* Saved PCIe capability	*/
 	struct eeh_pe *pe;		/* Associated PE		*/
 	struct list_head list;		/* Form link list in the PE	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 2aa955ae01a1..f9450537e335 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -578,7 +578,7 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state)
  * blocked on normal path during the stage. So we need utilize
  * eeh operations, which is always permitted.
  */
-static void eeh_bridge_check_link(struct pci_dev *pdev,
+static void eeh_bridge_check_link(struct eeh_dev *edev,
 				  struct device_node *dn)
 {
 	int cap;
@@ -589,16 +589,17 @@ static void eeh_bridge_check_link(struct pci_dev *pdev,
 	 * We only check root port and downstream ports of
 	 * PCIe switches
 	 */
-	if (!pci_is_pcie(pdev) ||
-	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
-	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
+	if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT)))
 		return;
 
-	pr_debug("%s: Check PCIe link for %s ...\n",
-		 __func__, pci_name(pdev));
+	pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n",
+		 __func__, edev->phb->global_number,
+		 edev->config_addr >> 8,
+		 PCI_SLOT(edev->config_addr & 0xFF),
+		 PCI_FUNC(edev->config_addr & 0xFF));
 
 	/* Check slot status */
-	cap = pdev->pcie_cap;
+	cap = edev->pcie_cap;
 	eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
 	if (!(val & PCI_EXP_SLTSTA_PDS)) {
 		pr_debug("  No card in the slot (0x%04x) !\n", val);
@@ -652,8 +653,7 @@ static void eeh_bridge_check_link(struct pci_dev *pdev,
 #define BYTE_SWAP(OFF)	(8*((OFF)/4)+3-(OFF))
 #define SAVED_BYTE(OFF)	(((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
 
-static void eeh_restore_bridge_bars(struct pci_dev *pdev,
-				    struct eeh_dev *edev,
+static void eeh_restore_bridge_bars(struct eeh_dev *edev,
 				    struct device_node *dn)
 {
 	int i;
@@ -679,7 +679,7 @@ static void eeh_restore_bridge_bars(struct pci_dev *pdev,
 	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
 
 	/* Check the PCIe link is ready */
-	eeh_bridge_check_link(pdev, dn);
+	eeh_bridge_check_link(edev, dn);
 }
 
 static void eeh_restore_device_bars(struct eeh_dev *edev,
@@ -729,12 +729,11 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
 	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
 	struct device_node *dn = eeh_dev_to_of_node(edev);
 
 	/* Do special restore for bridges */
-	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-		eeh_restore_bridge_bars(pdev, edev, dn);
+	if (edev->mode & EEH_DEV_BRIDGE)
+		eeh_restore_bridge_bars(edev, dn);
 	else
 		eeh_restore_device_bars(edev, dn);
 
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a380428cf9ce..4361a5c7f3ab 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -124,6 +124,17 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	/* Initialize eeh device */
 	edev->class_code	= dev->class;
 	edev->mode		= 0;
+	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		edev->mode |= EEH_DEV_BRIDGE;
+	if (pci_is_pcie(dev)) {
+		edev->pcie_cap = pci_pcie_cap(dev);
+
+		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+			edev->mode |= EEH_DEV_ROOT_PORT;
+		else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
+			edev->mode |= EEH_DEV_DS_PORT;
+	}
+
 	edev->config_addr	= ((dev->bus->number << 8) | dev->devfn);
 	edev->pe_config_addr	= phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff);
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 0f44f9fe49ac..9e80f0af311f 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -133,6 +133,48 @@ static int pseries_eeh_init(void)
 	return 0;
 }
 
+static int pseries_eeh_cap_start(struct device_node *dn)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	u32 status;
+
+	if (!pdn)
+		return 0;
+
+	rtas_read_config(pdn, PCI_STATUS, 2, &status);
+	if (!(status & PCI_STATUS_CAP_LIST))
+		return 0;
+
+	return PCI_CAPABILITY_LIST;
+}
+
+
+static int pseries_eeh_find_cap(struct device_node *dn, int cap)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	int pos = pseries_eeh_cap_start(dn);
+	int cnt = 48;	/* Maximal number of capabilities */
+	u32 id;
+
+	if (!pos)
+		return 0;
+
+        while (cnt--) {
+		rtas_read_config(pdn, pos, 1, &pos);
+		if (pos < 0x40)
+			break;
+		pos &= ~3;
+		rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+		if (id == 0xff)
+			break;
+		if (id == cap)
+			return pos;
+		pos += PCI_CAP_LIST_NEXT;
+	}
+
+	return 0;
+}
+
 /**
  * pseries_eeh_of_probe - EEH probe on the given device
  * @dn: OF node
@@ -146,8 +188,10 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 {
 	struct eeh_dev *edev;
 	struct eeh_pe pe;
+	struct pci_dn *pdn = PCI_DN(dn);
 	const u32 *class_code, *vendor_id, *device_id;
 	const u32 *regs;
+	u32 pcie_flags;
 	int enable = 0;
 	int ret;
 
@@ -167,9 +211,26 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 	if (dn->type && !strcmp(dn->type, "isa"))
 		return NULL;
 
-	/* Update class code and mode of eeh device */
+	/*
+	 * Update class code and mode of eeh device. We need
+	 * correctly reflects that current device is root port
+	 * or PCIe switch downstream port.
+	 */
 	edev->class_code = *class_code;
+	edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP);
 	edev->mode = 0;
+	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		edev->mode |= EEH_DEV_BRIDGE;
+		if (edev->pcie_cap) {
+			rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+					 2, &pcie_flags);
+			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
+			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
+				edev->mode |= EEH_DEV_ROOT_PORT;
+			else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM)
+				edev->mode |= EEH_DEV_DS_PORT;
+		}
+	}
 
 	/* Retrieve the device address */
 	regs = of_get_property(dn, "reg", NULL);
-- 
cgit v1.2.3


From ab55d2187da27414f78056810713c92f9a4350c2 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 24 Jul 2013 10:25:01 +0800
Subject: powerpc/eeh: Introdce flag to protect sysfs

The patch introduces flag EEH_DEV_SYSFS to keep track that the sysfs
entries for the corresponding EEH device (then PCI device) has been
added or removed, in order to avoid race condition.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h               |  2 ++
 arch/powerpc/kernel/eeh.c                    |  2 ++
 arch/powerpc/kernel/eeh_sysfs.c              | 16 +++++++++++++++-
 arch/powerpc/platforms/powernv/eeh-powernv.c |  4 ++--
 arch/powerpc/platforms/pseries/eeh_pseries.c |  2 +-
 5 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 4199d9943277..d3e5e9bc8f94 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -90,6 +90,8 @@ struct eeh_pe {
 #define EEH_DEV_IRQ_DISABLED	(1 << 3)	/* Interrupt disabled	*/
 #define EEH_DEV_DISCONNECTED	(1 << 4)	/* Removing from PE	*/
 
+#define EEH_DEV_SYSFS		(1 << 8)	/* Sysfs created        */
+
 struct eeh_dev {
 	int mode;			/* EEH mode			*/
 	int class_code;			/* Class code of the device	*/
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index a5783f1a7a96..ea9414c8088d 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -911,6 +911,7 @@ void eeh_add_device_late(struct pci_dev *dev)
 		eeh_rmv_from_parent_pe(edev);
 		eeh_addr_cache_rmv_dev(edev->pdev);
 		eeh_sysfs_remove_device(edev->pdev);
+		edev->mode &= ~EEH_DEV_SYSFS;
 
 		edev->pdev = NULL;
 		dev->dev.archdata.edev = NULL;
@@ -1016,6 +1017,7 @@ void eeh_remove_device(struct pci_dev *dev)
 
 	eeh_addr_cache_rmv_dev(dev);
 	eeh_sysfs_remove_device(dev);
+	edev->mode &= ~EEH_DEV_SYSFS;
 }
 
 static int proc_eeh_show(struct seq_file *m, void *v)
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index 61e2a1452131..5d753d4f2c75 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -56,26 +56,40 @@ EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
 
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
 	int rc=0;
 
+	if (edev && (edev->mode & EEH_DEV_SYSFS))
+		return;
+
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 
 	if (rc)
 		printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
+	else if (edev)
+		edev->mode |= EEH_DEV_SYSFS;
 }
 
 void eeh_sysfs_remove_device(struct pci_dev *pdev)
 {
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
 	/*
 	 * The parent directory might have been removed. We needn't
 	 * continue for that case.
 	 */
-	if (!pdev->dev.kobj.sd)
+	if (!pdev->dev.kobj.sd) {
+		if (edev)
+			edev->mode &= ~EEH_DEV_SYSFS;
 		return;
+	}
 
 	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+
+	if (edev)
+		edev->mode &= ~EEH_DEV_SYSFS;
 }
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 4361a5c7f3ab..79663d26e6ea 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -122,8 +122,8 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 		return 0;
 
 	/* Initialize eeh device */
-	edev->class_code	= dev->class;
-	edev->mode		= 0;
+	edev->class_code = dev->class;
+	edev->mode	&= 0xFFFFFF00;
 	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
 		edev->mode |= EEH_DEV_BRIDGE;
 	if (pci_is_pcie(dev)) {
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 9e80f0af311f..7fbc25b1813f 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -218,7 +218,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 	 */
 	edev->class_code = *class_code;
 	edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP);
-	edev->mode = 0;
+	edev->mode &= 0xFFFFFF00;
 	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
 		if (edev->pcie_cap) {
-- 
cgit v1.2.3


From ad92c615975a57c4b206c5c99f77a0bf22b373c4 Mon Sep 17 00:00:00 2001
From: Denis Kirjanov <kda@linux-powerpc.org>
Date: Tue, 23 Jul 2013 15:28:03 +0400
Subject: powerpc/pseries: Fix a typo in pSeries_lpar_hpte_insert()

Commit 801eb73f45371accc78ca9d6d22d647eeb722c11 introduced
a bug while checking PTE flags. We have to drop the _PAGE_COHERENT flag
when __PAGE_NO_CACHE is set and the cache update policy is not write-through
(i.e. _PAGE_WRITETHRU is not set)

Signed-off-by: Denis Kirjanov <kda@linux-powerpc.org>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
CC:  Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/lpar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 02d6e21619bb..8bad880bd177 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -146,7 +146,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	flags = 0;
 
 	/* Make pHyp happy */
-	if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU))
+	if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU))
 		hpte_r &= ~_PAGE_COHERENT;
 	if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N))
 		flags |= H_COALESCE_CAND;
-- 
cgit v1.2.3


From 679750054ae8129a536734bccf526ff6da35376a Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 2 Jul 2013 12:20:03 -0600
Subject: powerpc/powernv: Mark pnv_pci_init_ioda2_phb() as __init

Mark pnv_pci_init_ioda2_phb() as __init.  It is called only from an
init function (pnv_pci_init()), and it calls an init function
(pnv_pci_init_ioda_phb()):

    pnv_pci_init                # init
      pnv_pci_init_ioda2_phb    # non-init
	pnv_pci_init_ioda_phb   # init

This should fix a section mismatch warning.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/pci-ioda.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 49b57b9f835d..d8140b125e62 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1266,7 +1266,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE);
 }
 
-void pnv_pci_init_ioda2_phb(struct device_node *np)
+void __init pnv_pci_init_ioda2_phb(struct device_node *np)
 {
 	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
 }
-- 
cgit v1.2.3


From 7e76f34fa103677a27d96a7cfef8ce61389a32de Mon Sep 17 00:00:00 2001
From: Aruna Balakrishnaiah <aruna@linux.vnet.ibm.com>
Date: Thu, 8 Aug 2013 22:33:49 +0530
Subject: powerpc/pseries: Fix buffer overflow when reading from pstore

When reading from pstore there is a buffer overflow during decompression
due to the header added in unzip_oops. Remove unzip_oops and call
pstore_decompress directly in nvram_pstore_read. Allocate buffer of size
report_length of the oops header as header will not be deallocated in pstore.
Since we have 'openssl' command line tool to decompress the compressed data,
dump the compressed data in case decompression fails instead of not dumping
anything.

Signed-off-by: Aruna Balakrishnaiah <aruna@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/nvram.c | 70 ++++++++++++----------------------
 1 file changed, 24 insertions(+), 46 deletions(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 9f8671a44551..893f36053c97 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -569,35 +569,6 @@ error:
 	return ret;
 }
 
-static int unzip_oops(char *oops_buf, char *big_buf)
-{
-	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
-	u64 timestamp = oops_hdr->timestamp;
-	char *big_oops_data = NULL;
-	char *oops_data_buf = NULL;
-	size_t big_oops_data_sz;
-	int unzipped_len;
-
-	big_oops_data = big_buf + sizeof(struct oops_log_info);
-	big_oops_data_sz = big_oops_buf_sz - sizeof(struct oops_log_info);
-	oops_data_buf = oops_buf + sizeof(struct oops_log_info);
-
-	unzipped_len = nvram_decompress(oops_data_buf, big_oops_data,
-					oops_hdr->report_length,
-					big_oops_data_sz);
-
-	if (unzipped_len < 0) {
-		pr_err("nvram: decompression failed; returned %d\n",
-								unzipped_len);
-		return -1;
-	}
-	oops_hdr = (struct oops_log_info *)big_buf;
-	oops_hdr->version = OOPS_HDR_VERSION;
-	oops_hdr->report_length = (u16) unzipped_len;
-	oops_hdr->timestamp = timestamp;
-	return 0;
-}
-
 static int nvram_pstore_open(struct pstore_info *psi)
 {
 	/* Reset the iterator to start reading partitions again */
@@ -685,10 +656,9 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 	unsigned int err_type, id_no, size = 0;
 	struct nvram_os_partition *part = NULL;
 	char *buff = NULL, *big_buff = NULL;
-	int rc, sig = 0;
+	int sig = 0;
 	loff_t p;
 
-read_partition:
 	read_type++;
 
 	switch (nvram_type_ids[read_type]) {
@@ -749,30 +719,36 @@ read_partition:
 		*id = id_no;
 
 	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
+		int length, unzipped_len;
+
 		oops_hdr = (struct oops_log_info *)buff;
-		*buf = buff + sizeof(*oops_hdr);
+		length = oops_hdr->report_length;
+		*buf = kmalloc(length, GFP_KERNEL);
+		if (*buf == NULL)
+			return -ENOMEM;
+		memcpy(*buf, buff + sizeof(*oops_hdr), length);
+		time->tv_sec = oops_hdr->timestamp;
+		time->tv_nsec = 0;
+		kfree(buff);
 
 		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) {
 			big_buff = kmalloc(big_oops_buf_sz, GFP_KERNEL);
 			if (!big_buff)
 				return -ENOMEM;
 
-			rc = unzip_oops(buff, big_buff);
+			unzipped_len = nvram_decompress(*buf, big_buff,
+						length, big_oops_buf_sz);
 
-			if (rc != 0) {
-				kfree(buff);
+			if (unzipped_len < 0) {
+				pr_err("nvram: decompression failed, returned "
+					"rc %d\n", unzipped_len);
 				kfree(big_buff);
-				goto read_partition;
+			} else {
+				*buf = big_buff;
+				length = unzipped_len;
 			}
-
-			oops_hdr = (struct oops_log_info *)big_buff;
-			*buf = big_buff + sizeof(*oops_hdr);
-			kfree(buff);
 		}
-
-		time->tv_sec = oops_hdr->timestamp;
-		time->tv_nsec = 0;
-		return oops_hdr->report_length;
+		return length;
 	}
 
 	*buf = buff;
@@ -816,6 +792,7 @@ static int nvram_pstore_init(void)
 static void __init nvram_init_oops_partition(int rtas_partition_exists)
 {
 	int rc;
+	size_t size;
 
 	rc = pseries_nvram_init_os_partition(&oops_log_partition);
 	if (rc != 0) {
@@ -844,8 +821,9 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
 	big_oops_buf_sz = (oops_data_sz * 100) / 45;
 	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
 	if (big_oops_buf) {
-		stream.workspace = kmalloc(zlib_deflate_workspacesize(
-				WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+		size = max(zlib_deflate_workspacesize(WINDOW_BITS, MEM_LEVEL),
+			zlib_inflate_workspacesize());
+		stream.workspace = kmalloc(size, GFP_KERNEL);
 		if (!stream.workspace) {
 			pr_err("nvram: No memory for compression workspace; "
 				"skipping compression of %s partition data\n",
-- 
cgit v1.2.3


From 156c9ebdaca20d9ce428dc189f2b24d2a0ec8eaf Mon Sep 17 00:00:00 2001
From: Aruna Balakrishnaiah <aruna@linux.vnet.ibm.com>
Date: Thu, 8 Aug 2013 22:34:00 +0530
Subject: powerpc/pseries: Add backward compatibilty to read old kernel
 oops-log

Older kernels has just length information in their header. Handle it
while reading old kernel oops log from pstore.

Applies on top of powerpc/pseries: Fix buffer overflow when reading from pstore

Signed-off-by: Aruna Balakrishnaiah <aruna@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/nvram.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/platforms')

diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 893f36053c97..6a5f2b1f32ca 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -720,15 +720,25 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 
 	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
 		int length, unzipped_len;
+		size_t hdr_size;
 
 		oops_hdr = (struct oops_log_info *)buff;
-		length = oops_hdr->report_length;
+		if (oops_hdr->version < OOPS_HDR_VERSION) {
+			/* Old format oops header had 2-byte record size */
+			hdr_size = sizeof(u16);
+			length = oops_hdr->version;
+			time->tv_sec = 0;
+			time->tv_nsec = 0;
+		} else {
+			hdr_size = sizeof(*oops_hdr);
+			length = oops_hdr->report_length;
+			time->tv_sec = oops_hdr->timestamp;
+			time->tv_nsec = 0;
+		}
 		*buf = kmalloc(length, GFP_KERNEL);
 		if (*buf == NULL)
 			return -ENOMEM;
-		memcpy(*buf, buff + sizeof(*oops_hdr), length);
-		time->tv_sec = oops_hdr->timestamp;
-		time->tv_nsec = 0;
+		memcpy(*buf, buff + hdr_size, length);
 		kfree(buff);
 
 		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) {
-- 
cgit v1.2.3