Merge branch 'pci/hotplug'

  - Differentiate between pciehp surprise and safe removal (Lukas Wunner)

  - Remove unnecessary pciehp includes (Lukas Wunner)

  - Drop pciehp hotplug_slot_ops wrappers (Lukas Wunner)

  - Tolerate PCIe Slot Presence Detect being hardwired to zero to
    workaround broken hardware, e.g., the Wilocity switch/wireless device
    (Lukas Wunner)

  - Unify pciehp controller & slot structs (Lukas Wunner)

  - Constify hotplug_slot_ops (Lukas Wunner)

  - Drop hotplug_slot_info (Lukas Wunner)

  - Embed hotplug_slot struct into users instead of allocating it
    separately (Lukas Wunner)

  - Initialize PCIe port service drivers directly instead of relying on
    initcall ordering (Keith Busch)

  - Restore PCI config state after a slot reset (Keith Busch)

  - Save/restore DPC config state along with other PCI config state (Keith
    Busch)

  - Reference count devices during AER handling to avoid race issue with
    concurrent hot removal (Keith Busch)

  - If an Upstream Port reports ERR_FATAL, don't try to read the Port's
    config space because it is probably unreachable (Keith Busch)

  - During error handling, use slot-specific reset instead of secondary
    bus reset to avoid link up/down issues on hotplug ports (Keith Busch)

  - Restore previous AER/DPC handling that does not remove and re-enumerate
    devices on ERR_FATAL (Keith Busch)

  - Notify all drivers that may be affected by error recovery resets (Keith
    Busch)

  - Always generate error recovery uevents, even if a driver doesn't have
    error callbacks (Keith Busch)

  - Make PCIe link active reporting detection generic (Keith Busch)

  - Support D3cold in PCIe hierarchies during system sleep and runtime,
    including hotplug and Thunderbolt ports (Mika Westerberg)

  - Handle hpmemsize/hpiosize kernel parameters uniformly, whether slots
    are empty or occupied (Jon Derrick)

  - Remove duplicated include from pci/pcie/err.c and unused variable from
    cpqphp (YueHaibing)

  - Remove driver pci_cleanup_aer_uncorrect_error_status() calls (Oza
    Pawandeep)

  - Uninline PCI bus accessors for better ftracing (Keith Busch)

  - Remove unused AER Root Port .error_resume method (Keith Busch)

  - Use kfifo in AER instead of a local version (Keith Busch)

  - Use threaded IRQ in AER bottom half (Keith Busch)

  - Use managed resources in AER core (Keith Busch)

  - Reuse pcie_port_find_device() for AER injection (Keith Busch)

  - Abstract AER interrupt handling to disconnect error injection (Keith
    Busch)

  - Refactor AER injection callbacks to simplify future improvments (Keith
    Busch)

* pci/hotplug:
  PCI/AER: Refactor error injection fallbacks
  PCI/AER: Abstract AER interrupt handling
  PCI/AER: Reuse existing pcie_port_find_device() interface
  PCI/AER: Use managed resource allocations
  PCI/AER: Use threaded IRQ for bottom half
  PCI/AER: Use kfifo_in_spinlocked() to insert locked elements
  PCI/AER: Use kfifo for tracking events instead of reimplementing it
  PCI/AER: Remove error source from AER struct aer_rpc
  PCI/AER: Remove unused aer_error_resume()
  PCI: Uninline PCI bus accessors for better ftracing
  PCI/AER: Remove pci_cleanup_aer_uncorrect_error_status() calls
  PCI: pnv_php: Use kmemdup()
  PCI: cpqphp: Remove set but not used variable 'physical_slot'
  PCI/ERR: Remove duplicated include from err.c
  PCI: Equalize hotplug memory and io for occupied and empty slots
  PCI / ACPI: Whitelist D3 for more PCIe hotplug ports
  ACPI / property: Allow multiple property compatible _DSD entries
  PCI/PME: Implement runtime PM callbacks
  PCI: pciehp: Implement runtime PM callbacks
  PCI/portdrv: Add runtime PM hooks for port service drivers
  PCI/portdrv: Resume upon exit from system suspend if left runtime suspended
  PCI: pciehp: Do not handle events if interrupts are masked
  PCI: pciehp: Disable hotplug interrupt during suspend
  PCI / ACPI: Enable wake automatically for power managed bridges
  PCI: Do not skip power-managed bridges in pci_enable_wake()
  PCI: Make link active reporting detection generic
  PCI: Unify device inaccessible
  PCI/ERR: Always report current recovery status for udev
  PCI/ERR: Simplify broadcast callouts
  PCI/ERR: Run error recovery callbacks for all affected devices
  PCI/ERR: Handle fatal error recovery
  PCI/ERR: Use slot reset if available
  PCI/AER: Don't read upstream ports below fatal errors
  PCI/AER: Take reference on error devices
  PCI/DPC: Save and restore config state
  PCI: portdrv: Restore PCI config state on slot reset
  PCI: portdrv: Initialize service drivers directly
  PCI: hotplug: Document TODOs
  PCI: hotplug: Embed hotplug_slot
  PCI: hotplug: Drop hotplug_slot_info
  PCI: hotplug: Constify hotplug_slot_ops
  PCI: pciehp: Reshuffle controller struct for clarity
  PCI: pciehp: Rename controller struct members for clarity
  PCI: pciehp: Unify controller and slot structs
  PCI: pciehp: Tolerate Presence Detect hardwired to zero
  PCI: pciehp: Drop hotplug_slot_ops wrappers
  PCI: pciehp: Drop unnecessary includes
  PCI: pciehp: Differentiate between surprise and safe removal
  PCI: Simplify disconnected marking

8 files changed, 335 insertions, 467 deletions

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 83180edd6ed4..a90a9194ac4a 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -30,7 +30,7 @@
 #include "../pci.h"
 #include "portdrv.h"
 
-#define AER_ERROR_SOURCES_MAX		100
+#define AER_ERROR_SOURCES_MAX		128
 
 #define AER_MAX_TYPEOF_COR_ERRS		16	/* as per PCI_ERR_COR_STATUS */
 #define AER_MAX_TYPEOF_UNCOR_ERRS	26	/* as per PCI_ERR_UNCOR_STATUS*/
@@ -42,21 +42,7 @@ struct aer_err_source {
 
 struct aer_rpc {
 	struct pci_dev *rpd;		/* Root Port device */
-	struct work_struct dpc_handler;
-	struct aer_err_source e_sources[AER_ERROR_SOURCES_MAX];
-	struct aer_err_info e_info;
-	unsigned short prod_idx;	/* Error Producer Index */
-	unsigned short cons_idx;	/* Error Consumer Index */
-	int isr;
-	spinlock_t e_lock;		/*
-					 * Lock access to Error Status/ID Regs
-					 * and error producer/consumer index
-					 */
-	struct mutex rpc_mutex;		/*
-					 * only one thread could do
-					 * recovery on the same
-					 * root port hierarchy
-					 */
+	DECLARE_KFIFO(aer_fifo, struct aer_err_source, AER_ERROR_SOURCES_MAX);
 };
 
 /* AER stats for the device */
@@ -866,7 +852,7 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity,
 static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
 {
 	if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
-		e_info->dev[e_info->error_dev_num] = dev;
+		e_info->dev[e_info->error_dev_num] = pci_dev_get(dev);
 		e_info->error_dev_num++;
 		return 0;
 	}
@@ -1010,9 +996,12 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
 					info->status);
 		pci_aer_clear_device_status(dev);
 	} else if (info->severity == AER_NONFATAL)
-		pcie_do_nonfatal_recovery(dev);
+		pcie_do_recovery(dev, pci_channel_io_normal,
+				 PCIE_PORT_SERVICE_AER);
 	else if (info->severity == AER_FATAL)
-		pcie_do_fatal_recovery(dev, PCIE_PORT_SERVICE_AER);
+		pcie_do_recovery(dev, pci_channel_io_frozen,
+				 PCIE_PORT_SERVICE_AER);
+	pci_dev_put(dev);
 }
 
 #ifdef CONFIG_ACPI_APEI_PCIEAER
@@ -1047,9 +1036,11 @@ static void aer_recover_work_func(struct work_struct *work)
 		}
 		cper_print_aer(pdev, entry.severity, entry.regs);
 		if (entry.severity == AER_NONFATAL)
-			pcie_do_nonfatal_recovery(pdev);
+			pcie_do_recovery(pdev, pci_channel_io_normal,
+					 PCIE_PORT_SERVICE_AER);
 		else if (entry.severity == AER_FATAL)
-			pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_AER);
+			pcie_do_recovery(pdev, pci_channel_io_frozen,
+					 PCIE_PORT_SERVICE_AER);
 		pci_dev_put(pdev);
 	}
 }
@@ -1065,7 +1056,6 @@ static DECLARE_WORK(aer_recover_work, aer_recover_work_func);
 void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 		       int severity, struct aer_capability_regs *aer_regs)
 {
-	unsigned long flags;
 	struct aer_recover_entry entry = {
 		.bus		= bus,
 		.devfn		= devfn,
@@ -1074,13 +1064,12 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 		.regs		= aer_regs,
 	};
 
-	spin_lock_irqsave(&aer_recover_ring_lock, flags);
-	if (kfifo_put(&aer_recover_ring, entry))
+	if (kfifo_in_spinlocked(&aer_recover_ring, &entry, sizeof(entry),
+				 &aer_recover_ring_lock))
 		schedule_work(&aer_recover_work);
 	else
 		pr_err("AER recover: Buffer overflow when recovering AER for %04x:%02x:%02x:%x\n",
 		       domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
-	spin_unlock_irqrestore(&aer_recover_ring_lock, flags);
 }
 EXPORT_SYMBOL_GPL(aer_recover_queue);
 #endif
@@ -1115,8 +1104,9 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 			&info->mask);
 		if (!(info->status & ~info->mask))
 			return 0;
-	} else if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
-		info->severity == AER_NONFATAL) {
+	} else if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT ||
+	           pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM ||
+		   info->severity == AER_NONFATAL) {
 
 		/* Link is still healthy for IO reads */
 		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS,
@@ -1170,7 +1160,7 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 		struct aer_err_source *e_src)
 {
 	struct pci_dev *pdev = rpc->rpd;
-	struct aer_err_info *e_info = &rpc->e_info;
+	struct aer_err_info e_info;
 
 	pci_rootport_aer_stats_incr(pdev, e_src);
 
@@ -1179,83 +1169,57 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 	 * uncorrectable error being logged. Report correctable error first.
 	 */
 	if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
-		e_info->id = ERR_COR_ID(e_src->id);
-		e_info->severity = AER_CORRECTABLE;
+		e_info.id = ERR_COR_ID(e_src->id);
+		e_info.severity = AER_CORRECTABLE;
 
 		if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
-			e_info->multi_error_valid = 1;
+			e_info.multi_error_valid = 1;
 		else
-			e_info->multi_error_valid = 0;
-		aer_print_port_info(pdev, e_info);
+			e_info.multi_error_valid = 0;
+		aer_print_port_info(pdev, &e_info);
 
-		if (find_source_device(pdev, e_info))
-			aer_process_err_devices(e_info);
+		if (find_source_device(pdev, &e_info))
+			aer_process_err_devices(&e_info);
 	}
 
 	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
-		e_info->id = ERR_UNCOR_ID(e_src->id);
+		e_info.id = ERR_UNCOR_ID(e_src->id);
 
 		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
-			e_info->severity = AER_FATAL;
+			e_info.severity = AER_FATAL;
 		else
-			e_info->severity = AER_NONFATAL;
+			e_info.severity = AER_NONFATAL;
 
 		if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)
-			e_info->multi_error_valid = 1;
+			e_info.multi_error_valid = 1;
 		else
-			e_info->multi_error_valid = 0;
+			e_info.multi_error_valid = 0;
 
-		aer_print_port_info(pdev, e_info);
+		aer_print_port_info(pdev, &e_info);
 
-		if (find_source_device(pdev, e_info))
-			aer_process_err_devices(e_info);
+		if (find_source_device(pdev, &e_info))
+			aer_process_err_devices(&e_info);
 	}
 }
 
 /**
- * get_e_source - retrieve an error source
- * @rpc: pointer to the root port which holds an error
- * @e_src: pointer to store retrieved error source
- *
- * Return 1 if an error source is retrieved, otherwise 0.
- *
- * Invoked by DPC handler to consume an error.
- */
-static int get_e_source(struct aer_rpc *rpc, struct aer_err_source *e_src)
-{
-	unsigned long flags;
-
-	/* Lock access to Root error producer/consumer index */
-	spin_lock_irqsave(&rpc->e_lock, flags);
-	if (rpc->prod_idx == rpc->cons_idx) {
-		spin_unlock_irqrestore(&rpc->e_lock, flags);
-		return 0;
-	}
-
-	*e_src = rpc->e_sources[rpc->cons_idx];
-	rpc->cons_idx++;
-	if (rpc->cons_idx == AER_ERROR_SOURCES_MAX)
-		rpc->cons_idx = 0;
-	spin_unlock_irqrestore(&rpc->e_lock, flags);
-
-	return 1;
-}
-
-/**
  * aer_isr - consume errors detected by root port
  * @work: definition of this work item
  *
  * Invoked, as DPC, when root port records new detected error
  */
-static void aer_isr(struct work_struct *work)
+static irqreturn_t aer_isr(int irq, void *context)
 {
-	struct aer_rpc *rpc = container_of(work, struct aer_rpc, dpc_handler);
+	struct pcie_device *dev = (struct pcie_device *)context;
+	struct aer_rpc *rpc = get_service_data(dev);
 	struct aer_err_source uninitialized_var(e_src);
 
-	mutex_lock(&rpc->rpc_mutex);
-	while (get_e_source(rpc, &e_src))
+	if (kfifo_is_empty(&rpc->aer_fifo))
+		return IRQ_NONE;
+
+	while (kfifo_get(&rpc->aer_fifo, &e_src))
 		aer_isr_one_error(rpc, &e_src);
-	mutex_unlock(&rpc->rpc_mutex);
+	return IRQ_HANDLED;
 }
 
 /**
@@ -1265,56 +1229,26 @@ static void aer_isr(struct work_struct *work)
  *
  * Invoked when Root Port detects AER messages.
  */
-irqreturn_t aer_irq(int irq, void *context)
+static irqreturn_t aer_irq(int irq, void *context)
 {
-	unsigned int status, id;
 	struct pcie_device *pdev = (struct pcie_device *)context;
 	struct aer_rpc *rpc = get_service_data(pdev);
-	int next_prod_idx;
-	unsigned long flags;
-	int pos;
-
-	pos = pdev->port->aer_cap;
-	/*
-	 * Must lock access to Root Error Status Reg, Root Error ID Reg,
-	 * and Root error producer/consumer index
-	 */
-	spin_lock_irqsave(&rpc->e_lock, flags);
+	struct pci_dev *rp = rpc->rpd;
+	struct aer_err_source e_src = {};
+	int pos = rp->aer_cap;
 
-	/* Read error status */
-	pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);
-	if (!(status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV))) {
-		spin_unlock_irqrestore(&rpc->e_lock, flags);
+	pci_read_config_dword(rp, pos + PCI_ERR_ROOT_STATUS, &e_src.status);
+	if (!(e_src.status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV)))
 		return IRQ_NONE;
-	}
 
-	/* Read error source and clear error status */
-	pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_ERR_SRC, &id);
-	pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status);
+	pci_read_config_dword(rp, pos + PCI_ERR_ROOT_ERR_SRC, &e_src.id);
+	pci_write_config_dword(rp, pos + PCI_ERR_ROOT_STATUS, e_src.status);
 
-	/* Store error source for later DPC handler */
-	next_prod_idx = rpc->prod_idx + 1;
-	if (next_prod_idx == AER_ERROR_SOURCES_MAX)
-		next_prod_idx = 0;
-	if (next_prod_idx == rpc->cons_idx) {
-		/*
-		 * Error Storm Condition - possibly the same error occurred.
-		 * Drop the error.
-		 */
-		spin_unlock_irqrestore(&rpc->e_lock, flags);
+	if (!kfifo_put(&rpc->aer_fifo, e_src))
 		return IRQ_HANDLED;
-	}
-	rpc->e_sources[rpc->prod_idx].status =  status;
-	rpc->e_sources[rpc->prod_idx].id = id;
-	rpc->prod_idx = next_prod_idx;
-	spin_unlock_irqrestore(&rpc->e_lock, flags);
-
-	/*  Invoke DPC handler */
-	schedule_work(&rpc->dpc_handler);
 
-	return IRQ_HANDLED;
+	return IRQ_WAKE_THREAD;
 }
-EXPORT_SYMBOL_GPL(aer_irq);
 
 static int set_device_error_reporting(struct pci_dev *dev, void *data)
 {
@@ -1423,33 +1357,6 @@ static void aer_disable_rootport(struct aer_rpc *rpc)
 }
 
 /**
- * aer_alloc_rpc - allocate Root Port data structure
- * @dev: pointer to the pcie_dev data structure
- *
- * Invoked when Root Port's AER service is loaded.
- */
-static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
-{
-	struct aer_rpc *rpc;
-
-	rpc = kzalloc(sizeof(struct aer_rpc), GFP_KERNEL);
-	if (!rpc)
-		return NULL;
-
-	/* Initialize Root lock access, e_lock, to Root Error Status Reg */
-	spin_lock_init(&rpc->e_lock);
-
-	rpc->rpd = dev->port;
-	INIT_WORK(&rpc->dpc_handler, aer_isr);
-	mutex_init(&rpc->rpc_mutex);
-
-	/* Use PCIe bus function to store rpc into PCIe device */
-	set_service_data(dev, rpc);
-
-	return rpc;
-}
-
-/**
  * aer_remove - clean up resources
  * @dev: pointer to the pcie_dev data structure
  *
@@ -1459,16 +1366,7 @@ static void aer_remove(struct pcie_device *dev)
 {
 	struct aer_rpc *rpc = get_service_data(dev);
 
-	if (rpc) {
-		/* If register interrupt service, it must be free. */
-		if (rpc->isr)
-			free_irq(dev->irq, dev);
-
-		flush_work(&rpc->dpc_handler);
-		aer_disable_rootport(rpc);
-		kfree(rpc);
-		set_service_data(dev, NULL);
-	}
+	aer_disable_rootport(rpc);
 }
 
 /**
@@ -1481,27 +1379,24 @@ static int aer_probe(struct pcie_device *dev)
 {
 	int status;
 	struct aer_rpc *rpc;
-	struct device *device = &dev->port->dev;
+	struct device *device = &dev->device;
 
-	/* Alloc rpc data structure */
-	rpc = aer_alloc_rpc(dev);
+	rpc = devm_kzalloc(device, sizeof(struct aer_rpc), GFP_KERNEL);
 	if (!rpc) {
 		dev_printk(KERN_DEBUG, device, "alloc AER rpc failed\n");
-		aer_remove(dev);
 		return -ENOMEM;
 	}
+	rpc->rpd = dev->port;
+	set_service_data(dev, rpc);
 
-	/* Request IRQ ISR */
-	status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev);
+	status = devm_request_threaded_irq(device, dev->irq, aer_irq, aer_isr,
+					   IRQF_SHARED, "aerdrv", dev);
 	if (status) {
 		dev_printk(KERN_DEBUG, device, "request AER IRQ %d failed\n",
 			   dev->irq);
-		aer_remove(dev);
 		return status;
 	}
 
-	rpc->isr = 1;
-
 	aer_enable_rootport(rpc);
 	dev_info(device, "AER enabled with IRQ %d\n", dev->irq);
 	return 0;
@@ -1526,7 +1421,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	rc = pci_bridge_secondary_bus_reset(dev);
+	rc = pci_bus_error_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
 
 	/* Clear Root Error Status */
@@ -1541,18 +1436,6 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
-/**
- * aer_error_resume - clean up corresponding error status bits
- * @dev: pointer to Root Port's pci_dev data structure
- *
- * Invoked by Port Bus driver during nonfatal recovery.
- */
-static void aer_error_resume(struct pci_dev *dev)
-{
-	pci_aer_clear_device_status(dev);
-	pci_cleanup_aer_uncorrect_error_status(dev);
-}
-
 static struct pcie_port_service_driver aerdriver = {
 	.name		= "aer",
 	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
@@ -1560,7 +1443,6 @@ static struct pcie_port_service_driver aerdriver = {
 
 	.probe		= aer_probe,
 	.remove		= aer_remove,
-	.error_resume	= aer_error_resume,
 	.reset_link	= aer_root_reset,
 };
 
@@ -1569,10 +1451,9 @@ static struct pcie_port_service_driver aerdriver = {
  *
  * Invoked when AER root service driver is loaded.
  */
-static int __init aer_service_init(void)
+int __init pcie_aer_init(void)
 {
 	if (!pci_aer_available() || aer_acpi_firmware_first())
 		return -ENXIO;
 	return pcie_port_service_register(&aerdriver);
 }
-device_initcall(aer_service_init);
diff --git a/drivers/pci/pcie/aer_inject.c b/drivers/pci/pcie/aer_inject.c
index 0eb24346cad3..95d4759664b3 100644
--- a/drivers/pci/pcie/aer_inject.c
+++ b/drivers/pci/pcie/aer_inject.c
@@ -14,6 +14,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/irq.h>
 #include <linux/miscdevice.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
@@ -175,14 +176,48 @@ static u32 *find_pci_config_dword(struct aer_error *err, int where,
 	return target;
 }
 
+static int aer_inj_read(struct pci_bus *bus, unsigned int devfn, int where,
+			int size, u32 *val)
+{
+	struct pci_ops *ops, *my_ops;
+	int rv;
+
+	ops = __find_pci_bus_ops(bus);
+	if (!ops)
+		return -1;
+
+	my_ops = bus->ops;
+	bus->ops = ops;
+	rv = ops->read(bus, devfn, where, size, val);
+	bus->ops = my_ops;
+
+	return rv;
+}
+
+static int aer_inj_write(struct pci_bus *bus, unsigned int devfn, int where,
+			 int size, u32 val)
+{
+	struct pci_ops *ops, *my_ops;
+	int rv;
+
+	ops = __find_pci_bus_ops(bus);
+	if (!ops)
+		return -1;
+
+	my_ops = bus->ops;
+	bus->ops = ops;
+	rv = ops->write(bus, devfn, where, size, val);
+	bus->ops = my_ops;
+
+	return rv;
+}
+
 static int aer_inj_read_config(struct pci_bus *bus, unsigned int devfn,
 			       int where, int size, u32 *val)
 {
 	u32 *sim;
 	struct aer_error *err;
 	unsigned long flags;
-	struct pci_ops *ops;
-	struct pci_ops *my_ops;
 	int domain;
 	int rv;
 
@@ -203,18 +238,7 @@ static int aer_inj_read_config(struct pci_bus *bus, unsigned int devfn,
 		return 0;
 	}
 out:
-	ops = __find_pci_bus_ops(bus);
-	/*
-	 * pci_lock must already be held, so we can directly
-	 * manipulate bus->ops.  Many config access functions,
-	 * including pci_generic_config_read() require the original
-	 * bus->ops be installed to function, so temporarily put them
-	 * back.
-	 */
-	my_ops = bus->ops;
-	bus->ops = ops;
-	rv = ops->read(bus, devfn, where, size, val);
-	bus->ops = my_ops;
+	rv = aer_inj_read(bus, devfn, where, size, val);
 	spin_unlock_irqrestore(&inject_lock, flags);
 	return rv;
 }
@@ -226,8 +250,6 @@ static int aer_inj_write_config(struct pci_bus *bus, unsigned int devfn,
 	struct aer_error *err;
 	unsigned long flags;
 	int rw1cs;
-	struct pci_ops *ops;
-	struct pci_ops *my_ops;
 	int domain;
 	int rv;
 
@@ -251,18 +273,7 @@ static int aer_inj_write_config(struct pci_bus *bus, unsigned int devfn,
 		return 0;
 	}
 out:
-	ops = __find_pci_bus_ops(bus);
-	/*
-	 * pci_lock must already be held, so we can directly
-	 * manipulate bus->ops.  Many config access functions,
-	 * including pci_generic_config_write() require the original
-	 * bus->ops be installed to function, so temporarily put them
-	 * back.
-	 */
-	my_ops = bus->ops;
-	bus->ops = ops;
-	rv = ops->write(bus, devfn, where, size, val);
-	bus->ops = my_ops;
+	rv = aer_inj_write(bus, devfn, where, size, val);
 	spin_unlock_irqrestore(&inject_lock, flags);
 	return rv;
 }
@@ -303,32 +314,13 @@ out:
 	return 0;
 }
 
-static int find_aer_device_iter(struct device *device, void *data)
-{
-	struct pcie_device **result = data;
-	struct pcie_device *pcie_dev;
-
-	if (device->bus == &pcie_port_bus_type) {
-		pcie_dev = to_pcie_device(device);
-		if (pcie_dev->service & PCIE_PORT_SERVICE_AER) {
-			*result = pcie_dev;
-			return 1;
-		}
-	}
-	return 0;
-}
-
-static int find_aer_device(struct pci_dev *dev, struct pcie_device **result)
-{
-	return device_for_each_child(&dev->dev, result, find_aer_device_iter);
-}
-
 static int aer_inject(struct aer_error_inj *einj)
 {
 	struct aer_error *err, *rperr;
 	struct aer_error *err_alloc = NULL, *rperr_alloc = NULL;
 	struct pci_dev *dev, *rpdev;
 	struct pcie_device *edev;
+	struct device *device;
 	unsigned long flags;
 	unsigned int devfn = PCI_DEVFN(einj->dev, einj->fn);
 	int pos_cap_err, rp_pos_cap_err;
@@ -464,7 +456,9 @@ static int aer_inject(struct aer_error_inj *einj)
 	if (ret)
 		goto out_put;
 
-	if (find_aer_device(rpdev, &edev)) {
+	device = pcie_port_find_device(rpdev, PCIE_PORT_SERVICE_AER);
+	if (device) {
+		edev = to_pcie_device(device);
 		if (!get_service_data(edev)) {
 			dev_warn(&edev->device,
 				 "aer_inject: AER service is not initialized\n");
@@ -474,7 +468,9 @@ static int aer_inject(struct aer_error_inj *einj)
 		dev_info(&edev->device,
 			 "aer_inject: Injecting errors %08x/%08x into device %s\n",
 			 einj->cor_status, einj->uncor_status, pci_name(dev));
-		aer_irq(-1, edev);
+		local_irq_disable();
+		generic_handle_irq(edev->irq);
+		local_irq_enable();
 	} else {
 		pci_err(rpdev, "aer_inject: AER device not found\n");
 		ret = -ENODEV;
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index f03279fc87cd..e435d12e61a0 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -44,6 +44,58 @@ static const char * const rp_pio_error_string[] = {
 	"Memory Request Completion Timeout",		 /* Bit Position 18 */
 };
 
+static struct dpc_dev *to_dpc_dev(struct pci_dev *dev)
+{
+	struct device *device;
+
+	device = pcie_port_find_device(dev, PCIE_PORT_SERVICE_DPC);
+	if (!device)
+		return NULL;
+	return get_service_data(to_pcie_device(device));
+}
+
+void pci_save_dpc_state(struct pci_dev *dev)
+{
+	struct dpc_dev *dpc;
+	struct pci_cap_saved_state *save_state;
+	u16 *cap;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	dpc = to_dpc_dev(dev);
+	if (!dpc)
+		return;
+
+	save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_DPC);
+	if (!save_state)
+		return;
+
+	cap = (u16 *)&save_state->cap.data[0];
+	pci_read_config_word(dev, dpc->cap_pos + PCI_EXP_DPC_CTL, cap);
+}
+
+void pci_restore_dpc_state(struct pci_dev *dev)
+{
+	struct dpc_dev *dpc;
+	struct pci_cap_saved_state *save_state;
+	u16 *cap;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	dpc = to_dpc_dev(dev);
+	if (!dpc)
+		return;
+
+	save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_DPC);
+	if (!save_state)
+		return;
+
+	cap = (u16 *)&save_state->cap.data[0];
+	pci_write_config_word(dev, dpc->cap_pos + PCI_EXP_DPC_CTL, *cap);
+}
+
 static int dpc_wait_rp_inactive(struct dpc_dev *dpc)
 {
 	unsigned long timeout = jiffies + HZ;
@@ -67,18 +119,13 @@ static int dpc_wait_rp_inactive(struct dpc_dev *dpc)
 static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 {
 	struct dpc_dev *dpc;
-	struct pcie_device *pciedev;
-	struct device *devdpc;
-
 	u16 cap;
 
 	/*
 	 * DPC disables the Link automatically in hardware, so it has
 	 * already been reset by the time we get here.
 	 */
-	devdpc = pcie_port_find_device(pdev, PCIE_PORT_SERVICE_DPC);
-	pciedev = to_pcie_device(devdpc);
-	dpc = get_service_data(pciedev);
+	dpc = to_dpc_dev(pdev);
 	cap = dpc->cap_pos;
 
 	/*
@@ -93,10 +140,12 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_TRIGGER);
 
+	if (!pcie_wait_for_link(pdev, true))
+		return PCI_ERS_RESULT_DISCONNECT;
+
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-
 static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 {
 	struct device *dev = &dpc->dev->device;
@@ -169,7 +218,7 @@ static irqreturn_t dpc_handler(int irq, void *context)
 
 	reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN) >> 1;
 	ext_reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT) >> 5;
-	dev_warn(dev, "DPC %s detected, remove downstream devices\n",
+	dev_warn(dev, "DPC %s detected\n",
 		 (reason == 0) ? "unmasked uncorrectable error" :
 		 (reason == 1) ? "ERR_NONFATAL" :
 		 (reason == 2) ? "ERR_FATAL" :
@@ -186,7 +235,7 @@ static irqreturn_t dpc_handler(int irq, void *context)
 	}
 
 	/* We configure DPC so it only triggers on ERR_FATAL */
-	pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
+	pcie_do_recovery(pdev, pci_channel_io_frozen, PCIE_PORT_SERVICE_DPC);
 
 	return IRQ_HANDLED;
 }
@@ -259,6 +308,8 @@ static int dpc_probe(struct pcie_device *dev)
 		FLAG(cap, PCI_EXP_DPC_CAP_POISONED_TLP),
 		FLAG(cap, PCI_EXP_DPC_CAP_SW_TRIGGER), dpc->rp_log_size,
 		FLAG(cap, PCI_EXP_DPC_CAP_DL_ACTIVE));
+
+	pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_DPC, sizeof(u16));
 	return status;
 }
 
@@ -282,8 +333,7 @@ static struct pcie_port_service_driver dpcdriver = {
 	.reset_link	= dpc_reset_link,
 };
 
-static int __init dpc_service_init(void)
+int __init pcie_dpc_init(void)
 {
 	return pcie_port_service_register(&dpcdriver);
 }
-device_initcall(dpc_service_init);
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 708fd3a0d646..773197a12568 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -12,18 +12,12 @@
 
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <linux/pci.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/aer.h>
 #include "portdrv.h"
 #include "../pci.h"
 
-struct aer_broadcast_data {
-	enum pci_channel_state state;
-	enum pci_ers_result result;
-};
-
 static pci_ers_result_t merge_result(enum pci_ers_result orig,
 				  enum pci_ers_result new)
 {
@@ -49,66 +43,52 @@ static pci_ers_result_t merge_result(enum pci_ers_result orig,
 	return orig;
 }
 
-static int report_error_detected(struct pci_dev *dev, void *data)
+static int report_error_detected(struct pci_dev *dev,
+				 enum pci_channel_state state,
+				 enum pci_ers_result *result)
 {
 	pci_ers_result_t vote;
 	const struct pci_error_handlers *err_handler;
-	struct aer_broadcast_data *result_data;
-
-	result_data = (struct aer_broadcast_data *) data;
 
 	device_lock(&dev->dev);
-	dev->error_state = result_data->state;
-
-	if (!dev->driver ||
+	if (!pci_dev_set_io_state(dev, state) ||
+		!dev->driver ||
 		!dev->driver->err_handler ||
 		!dev->driver->err_handler->error_detected) {
-		if (result_data->state == pci_channel_io_frozen &&
-			dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
-			/*
-			 * In case of fatal recovery, if one of down-
-			 * stream device has no driver. We might be
-			 * unable to recover because a later insmod
-			 * of a driver for this device is unaware of
-			 * its hw state.
-			 */
-			pci_printk(KERN_DEBUG, dev, "device has %s\n",
-				   dev->driver ?
-				   "no AER-aware driver" : "no driver");
-		}
-
 		/*
-		 * If there's any device in the subtree that does not
-		 * have an error_detected callback, returning
-		 * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of
-		 * the subsequent mmio_enabled/slot_reset/resume
-		 * callbacks of "any" device in the subtree. All the
-		 * devices in the subtree are left in the error state
-		 * without recovery.
+		 * If any device in the subtree does not have an error_detected
+		 * callback, PCI_ERS_RESULT_NO_AER_DRIVER prevents subsequent
+		 * error callbacks of "any" device in the subtree, and will
+		 * exit in the disconnected error state.
 		 */
-
 		if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
 			vote = PCI_ERS_RESULT_NO_AER_DRIVER;
 		else
 			vote = PCI_ERS_RESULT_NONE;
 	} else {
 		err_handler = dev->driver->err_handler;
-		vote = err_handler->error_detected(dev, result_data->state);
-		pci_uevent_ers(dev, PCI_ERS_RESULT_NONE);
+		vote = err_handler->error_detected(dev, state);
 	}
-
-	result_data->result = merge_result(result_data->result, vote);
+	pci_uevent_ers(dev, vote);
+	*result = merge_result(*result, vote);
 	device_unlock(&dev->dev);
 	return 0;
 }
 
+static int report_frozen_detected(struct pci_dev *dev, void *data)
+{
+	return report_error_detected(dev, pci_channel_io_frozen, data);
+}
+
+static int report_normal_detected(struct pci_dev *dev, void *data)
+{
+	return report_error_detected(dev, pci_channel_io_normal, data);
+}
+
 static int report_mmio_enabled(struct pci_dev *dev, void *data)
 {
-	pci_ers_result_t vote;
+	pci_ers_result_t vote, *result = data;
 	const struct pci_error_handlers *err_handler;
-	struct aer_broadcast_data *result_data;
-
-	result_data = (struct aer_broadcast_data *) data;
 
 	device_lock(&dev->dev);
 	if (!dev->driver ||
@@ -118,7 +98,7 @@ static int report_mmio_enabled(struct pci_dev *dev, void *data)
 
 	err_handler = dev->driver->err_handler;
 	vote = err_handler->mmio_enabled(dev);
-	result_data->result = merge_result(result_data->result, vote);
+	*result = merge_result(*result, vote);
 out:
 	device_unlock(&dev->dev);
 	return 0;
@@ -126,11 +106,8 @@ out:
 
 static int report_slot_reset(struct pci_dev *dev, void *data)
 {
-	pci_ers_result_t vote;
+	pci_ers_result_t vote, *result = data;
 	const struct pci_error_handlers *err_handler;
-	struct aer_broadcast_data *result_data;
-
-	result_data = (struct aer_broadcast_data *) data;
 
 	device_lock(&dev->dev);
 	if (!dev->driver ||
@@ -140,7 +117,7 @@ static int report_slot_reset(struct pci_dev *dev, void *data)
 
 	err_handler = dev->driver->err_handler;
 	vote = err_handler->slot_reset(dev);
-	result_data->result = merge_result(result_data->result, vote);
+	*result = merge_result(*result, vote);
 out:
 	device_unlock(&dev->dev);
 	return 0;
@@ -151,17 +128,16 @@ static int report_resume(struct pci_dev *dev, void *data)
 	const struct pci_error_handlers *err_handler;
 
 	device_lock(&dev->dev);
-	dev->error_state = pci_channel_io_normal;
-
-	if (!dev->driver ||
+	if (!pci_dev_set_io_state(dev, pci_channel_io_normal) ||
+		!dev->driver ||
 		!dev->driver->err_handler ||
 		!dev->driver->err_handler->resume)
 		goto out;
 
 	err_handler = dev->driver->err_handler;
 	err_handler->resume(dev);
-	pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
 out:
+	pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
 	device_unlock(&dev->dev);
 	return 0;
 }
@@ -177,207 +153,86 @@ static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 {
 	int rc;
 
-	rc = pci_bridge_secondary_bus_reset(dev);
+	rc = pci_bus_error_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n");
 	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
 static pci_ers_result_t reset_link(struct pci_dev *dev, u32 service)
 {
-	struct pci_dev *udev;
 	pci_ers_result_t status;
 	struct pcie_port_service_driver *driver = NULL;
 
-	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		/* Reset this port for all subordinates */
-		udev = dev;
-	} else {
-		/* Reset the upstream component (likely downstream port) */
-		udev = dev->bus->self;
-	}
-
-	/* Use the aer driver of the component firstly */
-	driver = pcie_port_find_service(udev, service);
-
+	driver = pcie_port_find_service(dev, service);
 	if (driver && driver->reset_link) {
-		status = driver->reset_link(udev);
-	} else if (udev->has_secondary_link) {
-		status = default_reset_link(udev);
+		status = driver->reset_link(dev);
+	} else if (dev->has_secondary_link) {
+		status = default_reset_link(dev);
 	} else {
 		pci_printk(KERN_DEBUG, dev, "no link-reset support at upstream device %s\n",
-			pci_name(udev));
+			pci_name(dev));
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
 	if (status != PCI_ERS_RESULT_RECOVERED) {
 		pci_printk(KERN_DEBUG, dev, "link reset at upstream device %s failed\n",
-			pci_name(udev));
+			pci_name(dev));
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
 	return status;
 }
 
-/**
- * broadcast_error_message - handle message broadca