From b5dfbeacf74865a8d62a4f70f501cdc61510f8e0 Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Fri, 27 Mar 2020 17:33:24 -0500
Subject: PCI/ERR: Combine pci_channel_io_frozen cases

pcie_do_recovery() had two "if (state == pci_channel_io_frozen)" cases
right after each other.  Combine them to make this easier to read.  No
functional change intended.

Link: https://lore.kernel.org/r/20200317170654.GA23125@infradead.org
[bhelgaas: split from https://lore.kernel.org/r/a255fcb3a3fdebcd90f84e08b555f1786eb8eba2.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com]
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/err.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 01dfc8bb7ca0..cf97e068e12a 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -203,14 +203,13 @@ void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
 	bus = dev->subordinate;
 
 	pci_dbg(dev, "broadcast error_detected message\n");
-	if (state == pci_channel_io_frozen)
+	if (state == pci_channel_io_frozen) {
 		pci_walk_bus(bus, report_frozen_detected, &status);
-	else
+		if (reset_link(dev, service) != PCI_ERS_RESULT_RECOVERED)
+			goto failed;
+	} else {
 		pci_walk_bus(bus, report_normal_detected, &status);
-
-	if (state == pci_channel_io_frozen &&
-	    reset_link(dev, service) != PCI_ERS_RESULT_RECOVERED)
-		goto failed;
+	}
 
 	if (status == PCI_ERS_RESULT_CAN_RECOVER) {
 		status = PCI_ERS_RESULT_RECOVERED;
-- 
cgit v1.2.3


From 6d2c89441571ea534d6240f7724f518936c44f8d Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:25:58 -0700
Subject: PCI/ERR: Update error status after reset_link()

Commit bdb5ac85777d ("PCI/ERR: Handle fatal error recovery") uses
reset_link() to recover from fatal errors.  But during fatal error
recovery, if the initial value of error status is PCI_ERS_RESULT_DISCONNECT
or PCI_ERS_RESULT_NO_AER_DRIVER then even after successful recovery (using
reset_link()) pcie_do_recovery() will report the recovery result as
failure.  Update the status of error after reset_link().

You can reproduce this issue by triggering a SW DPC using "DPC Software
Trigger" bit in "DPC Control Register".  You should see recovery failed
dmesg log as below:

  pcieport 0000:00:16.0: DPC: containment event, status:0x1f27 source:0x0000
  pcieport 0000:00:16.0: DPC: software trigger detected
  pci 0000:04:00.0: AER: can't recover (no error_detected callback)
  pcieport 0000:00:16.0: AER: device recovery failed

Fixes: bdb5ac85777d ("PCI/ERR: Handle fatal error recovery")
Link: https://lore.kernel.org/r/a255fcb3a3fdebcd90f84e08b555f1786eb8eba2.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
[bhelgaas: split pci_channel_io_frozen simplification to separate patch]
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Keith Busch <keith.busch@intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
---
 drivers/pci/pcie/err.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index cf97e068e12a..1ac57e9e1e71 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -205,7 +205,8 @@ void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
 	pci_dbg(dev, "broadcast error_detected message\n");
 	if (state == pci_channel_io_frozen) {
 		pci_walk_bus(bus, report_frozen_detected, &status);
-		if (reset_link(dev, service) != PCI_ERS_RESULT_RECOVERED)
+		status = reset_link(dev, service);
+		if (status != PCI_ERS_RESULT_RECOVERED)
 			goto failed;
 	} else {
 		pci_walk_bus(bus, report_normal_detected, &status);
-- 
cgit v1.2.3


From be06c1b42eea749547d2f0248dc0a7c1153f67b9 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 23 Mar 2020 17:26:01 -0700
Subject: PCI/DPC: Move DPC data into struct pci_dev

We only need 25 bits of data for DPC, so I don't think it's worth the
complexity of allocating and keeping track of the struct dpc_dev separately
from the pci_dev.  Move that data into the struct pci_dev.

Link: https://lore.kernel.org/r/98323eaa18080adbe5bb30846862f09f8722d4b3.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/dpc.c | 103 +++++++++++++++----------------------------------
 1 file changed, 31 insertions(+), 72 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index e06f42f58d3d..6b116d7fdb89 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -17,13 +17,6 @@
 #include "portdrv.h"
 #include "../pci.h"
 
-struct dpc_dev {
-	struct pcie_device	*dev;
-	u16			cap_pos;
-	bool			rp_extensions;
-	u8			rp_log_size;
-};
-
 static const char * const rp_pio_error_string[] = {
 	"Configuration Request received UR Completion",	 /* Bit Position 0  */
 	"Configuration Request received CA Completion",	 /* Bit Position 1  */
@@ -46,63 +39,42 @@ 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);
+	pci_read_config_word(dev, dev->dpc_cap + 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);
+	pci_write_config_word(dev, dev->dpc_cap + PCI_EXP_DPC_CTL, *cap);
 }
 
-static int dpc_wait_rp_inactive(struct dpc_dev *dpc)
+static int dpc_wait_rp_inactive(struct pci_dev *pdev)
 {
 	unsigned long timeout = jiffies + HZ;
-	struct pci_dev *pdev = dpc->dev->port;
-	u16 cap = dpc->cap_pos, status;
+	u16 cap = pdev->dpc_cap, status;
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
 	while (status & PCI_EXP_DPC_RP_BUSY &&
@@ -119,15 +91,13 @@ 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;
 	u16 cap;
 
 	/*
 	 * DPC disables the Link automatically in hardware, so it has
 	 * already been reset by the time we get here.
 	 */
-	dpc = to_dpc_dev(pdev);
-	cap = dpc->cap_pos;
+	cap = pdev->dpc_cap;
 
 	/*
 	 * Wait until the Link is inactive, then clear DPC Trigger Status
@@ -135,7 +105,7 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	 */
 	pcie_wait_for_link(pdev, false);
 
-	if (dpc->rp_extensions && dpc_wait_rp_inactive(dpc))
+	if (pdev->dpc_rp_extensions && dpc_wait_rp_inactive(pdev))
 		return PCI_ERS_RESULT_DISCONNECT;
 
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
@@ -147,10 +117,9 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
+static void dpc_process_rp_pio_error(struct pci_dev *pdev)
 {
-	struct pci_dev *pdev = dpc->dev->port;
-	u16 cap = dpc->cap_pos, dpc_status, first_error;
+	u16 cap = pdev->dpc_cap, dpc_status, first_error;
 	u32 status, mask, sev, syserr, exc, dw0, dw1, dw2, dw3, log, prefix;
 	int i;
 
@@ -175,7 +144,7 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 				first_error == i ? " (First)" : "");
 	}
 
-	if (dpc->rp_log_size < 4)
+	if (pdev->dpc_rp_log_size < 4)
 		goto clear_status;
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG,
 			      &dw0);
@@ -188,12 +157,12 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 	pci_err(pdev, "TLP Header: %#010x %#010x %#010x %#010x\n",
 		dw0, dw1, dw2, dw3);
 
-	if (dpc->rp_log_size < 5)
+	if (pdev->dpc_rp_log_size < 5)
 		goto clear_status;
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG, &log);
 	pci_err(pdev, "RP PIO ImpSpec Log %#010x\n", log);
 
-	for (i = 0; i < dpc->rp_log_size - 5; i++) {
+	for (i = 0; i < pdev->dpc_rp_log_size - 5; i++) {
 		pci_read_config_dword(pdev,
 			cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix);
 		pci_err(pdev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix);
@@ -226,10 +195,9 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
 
 static irqreturn_t dpc_handler(int irq, void *context)
 {
+	struct pci_dev *pdev = context;
+	u16 cap = pdev->dpc_cap, status, source, reason, ext_reason;
 	struct aer_err_info info;
-	struct dpc_dev *dpc = context;
-	struct pci_dev *pdev = dpc->dev->port;
-	u16 cap = dpc->cap_pos, status, source, reason, ext_reason;
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
@@ -248,8 +216,8 @@ static irqreturn_t dpc_handler(int irq, void *context)
 				     "reserved error");
 
 	/* show RP PIO error detail information */
-	if (dpc->rp_extensions && reason == 3 && ext_reason == 0)
-		dpc_process_rp_pio_error(dpc);
+	if (pdev->dpc_rp_extensions && reason == 3 && ext_reason == 0)
+		dpc_process_rp_pio_error(pdev);
 	else if (reason == 0 &&
 		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
 		 aer_get_device_error_info(pdev, &info)) {
@@ -266,9 +234,8 @@ static irqreturn_t dpc_handler(int irq, void *context)
 
 static irqreturn_t dpc_irq(int irq, void *context)
 {
-	struct dpc_dev *dpc = (struct dpc_dev *)context;
-	struct pci_dev *pdev = dpc->dev->port;
-	u16 cap = dpc->cap_pos, status;
+	struct pci_dev *pdev = context;
+	u16 cap = pdev->dpc_cap, status;
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
 
@@ -285,7 +252,6 @@ static irqreturn_t dpc_irq(int irq, void *context)
 #define FLAG(x, y) (((x) & (y)) ? '+' : '-')
 static int dpc_probe(struct pcie_device *dev)
 {
-	struct dpc_dev *dpc;
 	struct pci_dev *pdev = dev->port;
 	struct device *device = &dev->device;
 	int status;
@@ -294,43 +260,37 @@ static int dpc_probe(struct pcie_device *dev)
 	if (pcie_aer_get_firmware_first(pdev) && !pcie_ports_dpc_native)
 		return -ENOTSUPP;
 
-	dpc = devm_kzalloc(device, sizeof(*dpc), GFP_KERNEL);
-	if (!dpc)
-		return -ENOMEM;
-
-	dpc->cap_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC);
-	dpc->dev = dev;
-	set_service_data(dev, dpc);
+	pdev->dpc_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC);
 
 	status = devm_request_threaded_irq(device, dev->irq, dpc_irq,
 					   dpc_handler, IRQF_SHARED,
-					   "pcie-dpc", dpc);
+					   "pcie-dpc", pdev);
 	if (status) {
 		pci_warn(pdev, "request IRQ%d failed: %d\n", dev->irq,
 			 status);
 		return status;
 	}
 
-	pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CAP, &cap);
-	pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, &ctl);
+	pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CAP, &cap);
+	pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl);
 
-	dpc->rp_extensions = (cap & PCI_EXP_DPC_CAP_RP_EXT);
-	if (dpc->rp_extensions) {
-		dpc->rp_log_size = (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8;
-		if (dpc->rp_log_size < 4 || dpc->rp_log_size > 9) {
+	pdev->dpc_rp_extensions = (cap & PCI_EXP_DPC_CAP_RP_EXT) ? 1 : 0;
+	if (pdev->dpc_rp_extensions) {
+		pdev->dpc_rp_log_size = (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8;
+		if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) {
 			pci_err(pdev, "RP PIO log size %u is invalid\n",
-				dpc->rp_log_size);
-			dpc->rp_log_size = 0;
+				pdev->dpc_rp_log_size);
+			pdev->dpc_rp_log_size = 0;
 		}
 	}
 
 	ctl = (ctl & 0xfff4) | PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN;
-	pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, ctl);
+	pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl);
 
 	pci_info(pdev, "error containment capabilities: Int Msg #%d, RPExt%c PoisonedTLP%c SwTrigger%c RP PIO Log %d, DL_ActiveErr%c\n",
 		 cap & PCI_EXP_DPC_IRQ, FLAG(cap, PCI_EXP_DPC_CAP_RP_EXT),
 		 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_SW_TRIGGER), pdev->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));
@@ -339,13 +299,12 @@ static int dpc_probe(struct pcie_device *dev)
 
 static void dpc_remove(struct pcie_device *dev)
 {
-	struct dpc_dev *dpc = get_service_data(dev);
 	struct pci_dev *pdev = dev->port;
 	u16 ctl;
 
-	pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, &ctl);
+	pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl);
 	ctl &= ~(PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN);
-	pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, ctl);
+	pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl);
 }
 
 static struct pcie_port_service_driver dpcdriver = {
-- 
cgit v1.2.3


From b6cf1a42f916af0b056079c37fc5fa7bf8e4b2e2 Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:26:02 -0700
Subject: PCI/ERR: Remove service dependency in pcie_do_recovery()

Previously we passed the PCIe service type parameter to pcie_do_recovery(),
where reset_link() looked up the underlying pci_port_service_driver and its
.reset_link() function pointer. Instead of using this roundabout way, we
can just pass the driver-specific .reset_link() callback function when
calling pcie_do_recovery() function.

This allows us to call pcie_do_recovery() from code that is not a PCIe port
service driver, e.g., Error Disconnect Recover (EDR) support.

Remove pcie_port_find_service() and pcie_port_service_driver.reset_link
since they are now unused.

Link: https://lore.kernel.org/r/60e02b87b526cdf2930400059d98704bf0a147d1.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h               |  2 +-
 drivers/pci/pcie/aer.c          | 12 ++++------
 drivers/pci/pcie/dpc.c          |  3 +--
 drivers/pci/pcie/err.c          | 52 ++++++-----------------------------------
 drivers/pci/pcie/portdrv.h      |  5 ----
 drivers/pci/pcie/portdrv_core.c | 21 -----------------
 6 files changed, 14 insertions(+), 81 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 6394e7746fb5..3e5efb83e9a2 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -548,7 +548,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
 
 /* PCI error reporting and recovery */
 void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
-		      u32 service);
+		      pci_ers_result_t (*reset_link)(struct pci_dev *pdev));
 
 bool pcie_wait_for_link(struct pci_dev *pdev, bool active);
 #ifdef CONFIG_PCIEASPM
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 4a818b07a1af..c0540c3761dc 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -102,6 +102,7 @@ struct aer_stats {
 #define ERR_UNCOR_ID(d)			(d >> 16)
 
 static int pcie_aer_disable;
+static pci_ers_result_t aer_root_reset(struct pci_dev *dev);
 
 void pci_no_aer(void)
 {
@@ -1053,11 +1054,9 @@ 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_recovery(dev, pci_channel_io_normal,
-				 PCIE_PORT_SERVICE_AER);
+		pcie_do_recovery(dev, pci_channel_io_normal, aer_root_reset);
 	else if (info->severity == AER_FATAL)
-		pcie_do_recovery(dev, pci_channel_io_frozen,
-				 PCIE_PORT_SERVICE_AER);
+		pcie_do_recovery(dev, pci_channel_io_frozen, aer_root_reset);
 	pci_dev_put(dev);
 }
 
@@ -1094,10 +1093,10 @@ 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_recovery(pdev, pci_channel_io_normal,
-					 PCIE_PORT_SERVICE_AER);
+					 aer_root_reset);
 		else if (entry.severity == AER_FATAL)
 			pcie_do_recovery(pdev, pci_channel_io_frozen,
-					 PCIE_PORT_SERVICE_AER);
+					 aer_root_reset);
 		pci_dev_put(pdev);
 	}
 }
@@ -1501,7 +1500,6 @@ static struct pcie_port_service_driver aerdriver = {
 
 	.probe		= aer_probe,
 	.remove		= aer_remove,
-	.reset_link	= aer_root_reset,
 };
 
 /**
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 6b116d7fdb89..1ae5d94944eb 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -227,7 +227,7 @@ static irqreturn_t dpc_handler(int irq, void *context)
 	}
 
 	/* We configure DPC so it only triggers on ERR_FATAL */
-	pcie_do_recovery(pdev, pci_channel_io_frozen, PCIE_PORT_SERVICE_DPC);
+	pcie_do_recovery(pdev, pci_channel_io_frozen, dpc_reset_link);
 
 	return IRQ_HANDLED;
 }
@@ -313,7 +313,6 @@ static struct pcie_port_service_driver dpcdriver = {
 	.service	= PCIE_PORT_SERVICE_DPC,
 	.probe		= dpc_probe,
 	.remove		= dpc_remove,
-	.reset_link	= dpc_reset_link,
 };
 
 int __init pcie_dpc_init(void)
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 1ac57e9e1e71..9d5b71a7f837 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -146,49 +146,9 @@ out:
 	return 0;
 }
 
-/**
- * default_reset_link - default reset function
- * @dev: pointer to pci_dev data structure
- *
- * Invoked when performing link reset on a Downstream Port or a
- * Root Port with no aer driver.
- */
-static pci_ers_result_t default_reset_link(struct pci_dev *dev)
-{
-	int rc;
-
-	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)
-{
-	pci_ers_result_t status;
-	struct pcie_port_service_driver *driver = NULL;
-
-	driver = pcie_port_find_service(dev, service);
-	if (driver && driver->reset_link) {
-		status = driver->reset_link(dev);
-	} else if (pcie_downstream_port(dev)) {
-		status = default_reset_link(dev);
-	} else {
-		pci_printk(KERN_DEBUG, dev, "no link-reset support at upstream device %s\n",
-			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(dev));
-		return PCI_ERS_RESULT_DISCONNECT;
-	}
-
-	return status;
-}
-
-void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
-		      u32 service)
+void pcie_do_recovery(struct pci_dev *dev,
+		      enum pci_channel_state state,
+		      pci_ers_result_t (*reset_link)(struct pci_dev *pdev))
 {
 	pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
 	struct pci_bus *bus;
@@ -205,9 +165,11 @@ void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
 	pci_dbg(dev, "broadcast error_detected message\n");
 	if (state == pci_channel_io_frozen) {
 		pci_walk_bus(bus, report_frozen_detected, &status);
-		status = reset_link(dev, service);
-		if (status != PCI_ERS_RESULT_RECOVERED)
+		status = reset_link(dev);
+		if (status != PCI_ERS_RESULT_RECOVERED) {
+			pci_warn(dev, "link reset failed\n");
 			goto failed;
+		}
 	} else {
 		pci_walk_bus(bus, report_normal_detected, &status);
 	}
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 1e673619b101..64b5e081cdb2 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -92,9 +92,6 @@ struct pcie_port_service_driver {
 	/* Device driver may resume normal operations */
 	void (*error_resume)(struct pci_dev *dev);
 
-	/* Link Reset Capability - AER service driver specific */
-	pci_ers_result_t (*reset_link)(struct pci_dev *dev);
-
 	int port_type;  /* Type of the port this driver can handle */
 	u32 service;    /* Port service this device represents */
 
@@ -161,7 +158,5 @@ static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
 }
 #endif
 
-struct pcie_port_service_driver *pcie_port_find_service(struct pci_dev *dev,
-							u32 service);
 struct device *pcie_port_find_device(struct pci_dev *dev, u32 service);
 #endif /* _PORTDRV_H_ */
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 5075cb9e850c..50a9522ab07d 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -458,27 +458,6 @@ static int find_service_iter(struct device *device, void *data)
 	return 0;
 }
 
-/**
- * pcie_port_find_service - find the service driver
- * @dev: PCI Express port the service is associated with
- * @service: Service to find
- *
- * Find PCI Express port service driver associated with given service
- */
-struct pcie_port_service_driver *pcie_port_find_service(struct pci_dev *dev,
-							u32 service)
-{
-	struct pcie_port_service_driver *drv;
-	struct portdrv_service_data pdrvs;
-
-	pdrvs.drv = NULL;
-	pdrvs.service = service;
-	device_for_each_child(&dev->dev, &pdrvs, find_service_iter);
-
-	drv = pdrvs.drv;
-	return drv;
-}
-
 /**
  * pcie_port_find_device - find the struct device
  * @dev: PCI Express port the service is associated with
-- 
cgit v1.2.3


From e8e5ff2aeec19ade42f0535f4b554a3f6e1a58f7 Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:26:03 -0700
Subject: PCI/ERR: Return status of pcie_do_recovery()

As per the DPC Enhancements ECN [1], sec 4.5.1, table 4-4, if the OS
supports Error Disconnect Recover (EDR), it must invalidate the software
state associated with child devices of the port without attempting to
access the child device hardware. In addition, if the OS supports DPC, it
must attempt to recover the child devices if the port implements the DPC
Capability. If the OS continues operation, the OS must inform the firmware
of the status of the recovery operation via the _OST method.

Return the result of pcie_do_recovery() so we can report it to firmware via
_OST.

[1] Downstream Port Containment Related Enhancements ECN, Jan 28, 2019,
    affecting PCI Firmware Specification, Rev. 3.2
    https://members.pcisig.com/wg/PCI-SIG/document/12888

Link: https://lore.kernel.org/r/eb60ec89448769349c6722954ffbf2de163155b5.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      |  5 +++--
 drivers/pci/pcie/err.c | 10 ++++++----
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 3e5efb83e9a2..efbe94096050 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -547,8 +547,9 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
 #endif
 
 /* PCI error reporting and recovery */
-void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
-		      pci_ers_result_t (*reset_link)(struct pci_dev *pdev));
+pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
+			enum pci_channel_state state,
+			pci_ers_result_t (*reset_link)(struct pci_dev *pdev));
 
 bool pcie_wait_for_link(struct pci_dev *pdev, bool active);
 #ifdef CONFIG_PCIEASPM
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 9d5b71a7f837..0c40488da651 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -146,9 +146,9 @@ out:
 	return 0;
 }
 
-void pcie_do_recovery(struct pci_dev *dev,
-		      enum pci_channel_state state,
-		      pci_ers_result_t (*reset_link)(struct pci_dev *pdev))
+pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
+			enum pci_channel_state state,
+			pci_ers_result_t (*reset_link)(struct pci_dev *pdev))
 {
 	pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER;
 	struct pci_bus *bus;
@@ -200,11 +200,13 @@ void pcie_do_recovery(struct pci_dev *dev,
 	pci_aer_clear_device_status(dev);
 	pci_cleanup_aer_uncorrect_error_status(dev);
 	pci_info(dev, "device recovery successful\n");
-	return;
+	return status;
 
 failed:
 	pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
 
 	/* TODO: Should kernel panic here? */
 	pci_info(dev, "device recovery failed\n");
+
+	return status;
 }
-- 
cgit v1.2.3


From 27005618178ef9e9bf9c42fd91101771c92e9308 Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:26:04 -0700
Subject: PCI/DPC: Cache DPC capabilities in pci_init_capabilities()

Since Error Disconnect Recover needs to use DPC error handling routines
even if the OS doesn't have control of DPC, move the initalization and
caching of DPC capabilities from the DPC driver to pci_init_capabilities().

Link: https://lore.kernel.org/r/5888380657c8b9551675b5dbd48e370e4fd2703d.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      |  2 ++
 drivers/pci/pcie/dpc.c | 33 +++++++++++++++++++++------------
 drivers/pci/probe.c    |  1 +
 3 files changed, 24 insertions(+), 12 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index efbe94096050..e48677a0ba42 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -448,9 +448,11 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
 #ifdef CONFIG_PCIE_DPC
 void pci_save_dpc_state(struct pci_dev *dev);
 void pci_restore_dpc_state(struct pci_dev *dev);
+void pci_dpc_init(struct pci_dev *pdev);
 #else
 static inline void pci_save_dpc_state(struct pci_dev *dev) {}
 static inline void pci_restore_dpc_state(struct pci_dev *dev) {}
+static inline void pci_dpc_init(struct pci_dev *pdev) {}
 #endif
 
 #ifdef CONFIG_PCI_ATS
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 1ae5d94944eb..a1c9d45876bd 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -249,6 +249,27 @@ static irqreturn_t dpc_irq(int irq, void *context)
 	return IRQ_HANDLED;
 }
 
+void pci_dpc_init(struct pci_dev *pdev)
+{
+	u16 cap;
+
+	pdev->dpc_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC);
+	if (!pdev->dpc_cap)
+		return;
+
+	pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CAP, &cap);
+	if (!(cap & PCI_EXP_DPC_CAP_RP_EXT))
+		return;
+
+	pdev->dpc_rp_extensions = true;
+	pdev->dpc_rp_log_size = (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8;
+	if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) {
+		pci_err(pdev, "RP PIO log size %u is invalid\n",
+			pdev->dpc_rp_log_size);
+		pdev->dpc_rp_log_size = 0;
+	}
+}
+
 #define FLAG(x, y) (((x) & (y)) ? '+' : '-')
 static int dpc_probe(struct pcie_device *dev)
 {
@@ -260,8 +281,6 @@ static int dpc_probe(struct pcie_device *dev)
 	if (pcie_aer_get_firmware_first(pdev) && !pcie_ports_dpc_native)
 		return -ENOTSUPP;
 
-	pdev->dpc_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC);
-
 	status = devm_request_threaded_irq(device, dev->irq, dpc_irq,
 					   dpc_handler, IRQF_SHARED,
 					   "pcie-dpc", pdev);
@@ -274,16 +293,6 @@ static int dpc_probe(struct pcie_device *dev)
 	pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CAP, &cap);
 	pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl);
 
-	pdev->dpc_rp_extensions = (cap & PCI_EXP_DPC_CAP_RP_EXT) ? 1 : 0;
-	if (pdev->dpc_rp_extensions) {
-		pdev->dpc_rp_log_size = (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8;
-		if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) {
-			pci_err(pdev, "RP PIO log size %u is invalid\n",
-				pdev->dpc_rp_log_size);
-			pdev->dpc_rp_log_size = 0;
-		}
-	}
-
 	ctl = (ctl & 0xfff4) | PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN;
 	pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl);
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 512cb4312ddd..c6f91f886818 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2329,6 +2329,7 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	pci_enable_acs(dev);		/* Enable ACS P2P upstream forwarding */
 	pci_ptm_init(dev);		/* Precision Time Measurement */
 	pci_aer_init(dev);		/* Advanced Error Reporting */
+	pci_dpc_init(dev);		/* Downstream Port Containment */
 
 	pcie_report_downtraining(dev);
 
-- 
cgit v1.2.3


From 20e15e673b05a045fdbe534d40edf948e1b0b1af Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:26:05 -0700
Subject: PCI/AER: Add pci_aer_raw_clear_status() to unconditionally clear
 Error Status

Per the SFI _OSC and DPC Updates ECN [1] implementation note flowchart, the
OS seems to be expected to clear AER status even if it doesn't have
ownership of the AER capability.  Unlike the DPC capability, where a DPC
ECN [2] specifies a window when the OS is allowed to access DPC registers
even if it doesn't have ownership, there is no clear model for AER.

Add pci_aer_raw_clear_status() to clear the AER error status registers
unconditionally.  This is intended for use only by the EDR path (see [2]).

[1] System Firmware Intermediary (SFI) _OSC and DPC Updates ECN, Feb 24,
    2020, affecting PCI Firmware Specification, Rev. 3.2
    https://members.pcisig.com/wg/PCI-SIG/document/14076
[2] Downstream Port Containment Related Enhancements ECN, Jan 28, 2019,
    affecting PCI Firmware Specification, Rev. 3.2
    https://members.pcisig.com/wg/PCI-SIG/document/12888

[bhelgaas: changelog]
Link: https://lore.kernel.org/r/c19ad28f3633cce67448609e89a75635da0da07d.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      |  2 ++
 drivers/pci/pcie/aer.c | 22 ++++++++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index e48677a0ba42..6d09bb22b73d 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -654,12 +654,14 @@ void pci_aer_exit(struct pci_dev *dev);
 extern const struct attribute_group aer_stats_attr_group;
 void pci_aer_clear_fatal_status(struct pci_dev *dev);
 void pci_aer_clear_device_status(struct pci_dev *dev);
+int pci_aer_raw_clear_status(struct pci_dev *dev);
 #else
 static inline void pci_no_aer(void) { }
 static inline void pci_aer_init(struct pci_dev *d) { }
 static inline void pci_aer_exit(struct pci_dev *d) { }
 static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { }
 static inline void pci_aer_clear_device_status(struct pci_dev *dev) { }
+static inline int pci_aer_raw_clear_status(struct pci_dev *dev) { return -EINVAL; }
 #endif
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index c0540c3761dc..bd9f122165e0 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -420,7 +420,16 @@ void pci_aer_clear_fatal_status(struct pci_dev *dev)
 		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
 }
 
-int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
+/**
+ * pci_aer_raw_clear_status - Clear AER error registers.
+ * @dev: the PCI device
+ *
+ * Clearing AER error status registers unconditionally, regardless of
+ * whether they're owned by firmware or the OS.
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_aer_raw_clear_status(struct pci_dev *dev)
 {
 	int pos;
 	u32 status;
@@ -433,9 +442,6 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 	if (!pos)
 		return -EIO;
 
-	if (pcie_aer_get_firmware_first(dev))
-		return -EIO;
-
 	port_type = pci_pcie_type(dev);
 	if (port_type == PCI_EXP_TYPE_ROOT_PORT) {
 		pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status);
@@ -451,6 +457,14 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 	return 0;
 }
 
+int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
+{
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
+	return pci_aer_raw_clear_status(dev);
+}
+
 void pci_save_aer_state(struct pci_dev *dev)
 {
 	struct pci_cap_saved_state *save_state;
-- 
cgit v1.2.3


From aea47413e7ceec6024f5a2b743cb1a4b2176bf3f Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:26:06 -0700
Subject: PCI/DPC: Expose dpc_process_error(), dpc_reset_link() for use by EDR

If firmware controls DPC, it is generally responsible for managing the DPC
capability and events, and the OS should not access the DPC capability.

However, if firmware controls DPC and both the OS and the platform support
Error Disconnect Recover (EDR) notifications, the OS EDR notify handler is
responsible for recovery, and the notify handler may read/write the DPC
capability until it clears the DPC Trigger Status bit.  See [1], sec 4.5.1,
table 4-6.

Expose some DPC error handling functions so they can be used by the EDR
notify handler.

[1] Downstream Port Containment Related Enhancements ECN, Jan 28, 2019,
    affecting PCI Firmware Specification, Rev. 3.2
    https://members.pcisig.com/wg/PCI-SIG/document/12888

Link: https://lore.kernel.org/r/e9000bb15b3a4293e81d98bb29ead7c84a6393c9.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      |  2 ++
 drivers/pci/pcie/dpc.c | 12 +++++++++---
 2 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 6d09bb22b73d..25265bf80a83 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -449,6 +449,8 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
 void pci_save_dpc_state(struct pci_dev *dev);
 void pci_restore_dpc_state(struct pci_dev *dev);
 void pci_dpc_init(struct pci_dev *pdev);
+void dpc_process_error(struct pci_dev *pdev);
+pci_ers_result_t dpc_reset_link(struct pci_dev *pdev);
 #else
 static inline void pci_save_dpc_state(struct pci_dev *dev) {}
 static inline void pci_restore_dpc_state(struct pci_dev *dev) {}
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index a1c9d45876bd..22998ee2f7ea 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -89,7 +89,7 @@ static int dpc_wait_rp_inactive(struct pci_dev *pdev)
 	return 0;
 }
 
-static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
+pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 {
 	u16 cap;
 
@@ -193,9 +193,8 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
 	return 1;
 }
 
-static irqreturn_t dpc_handler(int irq, void *context)
+void dpc_process_error(struct pci_dev *pdev)
 {
-	struct pci_dev *pdev = context;
 	u16 cap = pdev->dpc_cap, status, source, reason, ext_reason;
 	struct aer_err_info info;
 
@@ -225,6 +224,13 @@ static irqreturn_t dpc_handler(int irq, void *context)
 		pci_cleanup_aer_uncorrect_error_status(pdev);
 		pci_aer_clear_fatal_status(pdev);
 	}
+}
+
+static irqreturn_t dpc_handler(int irq, void *context)
+{
+	struct pci_dev *pdev = context;
+
+	dpc_process_error(pdev);
 
 	/* We configure DPC so it only triggers on ERR_FATAL */
 	pcie_do_recovery(pdev, pci_channel_io_frozen, dpc_reset_link);
-- 
cgit v1.2.3


From ac1c8e35a3262d04cc81b07fac6480a3539e3b0f Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:26:07 -0700
Subject: PCI/DPC: Add Error Disconnect Recover (EDR) support

Error Disconnect Recover (EDR) is a feature that allows ACPI firmware to
notify OSPM that a device has been disconnected due to an error condition
(ACPI v6.3, sec 5.6.6).  OSPM advertises its support for EDR on PCI devices
via _OSC (see [1], sec 4.5.1, table 4-4).  The OSPM EDR notify handler
should invalidate software state associated with disconnected devices and
may attempt to recover them.  OSPM communicates the status of recovery to
the firmware via _OST (sec 6.3.5.2).

For PCIe, firmware may use Downstream Port Containment (DPC) to support
EDR.  Per [1], sec 4.5.1, table 4-6, even if firmware has retained control
of DPC, OSPM may read/write DPC control and status registers during the EDR
notification processing window, i.e., from the time it receives an EDR
notification until it clears the DPC Trigger Status.

Note that per [1], sec 4.5.1 and 4.5.2.4,

  1. If the OS supports EDR, it should advertise that to firmware by
     setting OSC_PCI_EDR_SUPPORT in _OSC Support.

  2. If the OS sets OSC_PCI_EXPRESS_DPC_CONTROL in _OSC Control to request
     control of the DPC capability, it must also set OSC_PCI_EDR_SUPPORT in
     _OSC Support.

Add an EDR notify handler to attempt recovery.

[1] Downstream Port Containment Related Enhancements ECN, Jan 28, 2019,
    affecting PCI Firmware Specification, Rev. 3.2
    https://members.pcisig.com/wg/PCI-SIG/document/12888

[bhelgaas: squash add/enable patches into one]
Link: https://lore.kernel.org/r/90f91fe6d25c13f9d2255d2ce97ca15be307e1bb.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
---
 drivers/pci/pci-acpi.c    |   2 +
 drivers/pci/pcie/Kconfig  |  10 ++
 drivers/pci/pcie/Makefile |   1 +
 drivers/pci/pcie/edr.c    | 239 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/probe.c       |   1 +
 5 files changed, 253 insertions(+)
 create mode 100644 drivers/pci/pcie/edr.c

(limited to 'drivers/pci')

diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 0c02d500158f..1a6d2062cf8d 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -1241,6 +1241,7 @@ static void pci_acpi_setup(struct device *dev)
 
 	pci_acpi_optimize_delay(pci_dev, adev->handle);
 	pci_acpi_set_untrusted(pci_dev);
+	pci_acpi_add_edr_notifier(pci_dev);
 
 	pci_acpi_add_pm_notifier(adev, pci_dev);
 	if (!adev->wakeup.flags.valid)
@@ -1268,6 +1269,7 @@ static void pci_acpi_cleanup(struct device *dev)
 	if (!adev)
 		return;
 
+	pci_acpi_remove_edr_notifier(pci_dev);
 	pci_acpi_remove_pm_notifier(adev);
 	if (adev->wakeup.flags.valid) {
 		acpi_device_power_remove_dependent(adev, dev);
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index 6e3c04b46fb1..772b1f4cb19e 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -140,3 +140,13 @@ config PCIE_BW
 	  This enables PCI Express Bandwidth Change Notification.  If
 	  you know link width or rate changes occur only to correct
 	  unreliable links, you may answer Y.
+
+config PCIE_EDR
+	bool "PCI Express Error Disconnect Recover support"
+	depends on PCIE_DPC && ACPI
+	help
+	  This option adds Error Disconnect Recover support as specified
+	  in the Downstream Port Containment Related Enhancements ECN to
+	  the PCI Firmware Specification r3.2.  Enable this if you want to
+	  support hybrid DPC model which uses both firmware and OS to
+	  implement DPC.
diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
index efb9d2e71e9e..68da9280ff11 100644
--- a/drivers/pci/pcie/Makefile
+++ b/drivers/pci/pcie/Makefile
@@ -13,3 +13,4 @@ obj-$(CONFIG_PCIE_PME)		+= pme.o
 obj-$(CONFIG_PCIE_DPC)		+= dpc.o
 obj-$(CONFIG_PCIE_PTM)		+= ptm.o
 obj-$(CONFIG_PCIE_BW)		+= bw_notification.o
+obj-$(CONFIG_PCIE_EDR)		+= edr.o
diff --git a/drivers/pci/pcie/edr.c b/drivers/pci/pcie/edr.c
new file mode 100644
index 000000000000..594622a6cb16
--- /dev/null
+++ b/drivers/pci/pcie/edr.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Error Disconnect Recover support
+ * Author: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
+ *
+ * Copyright (C) 2020 Intel Corp.
+ */
+
+#define dev_fmt(fmt) "EDR: " fmt
+
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+
+#include "portdrv.h"
+#include "../pci.h"
+
+#define EDR_PORT_DPC_ENABLE_DSM		0x0C
+#define EDR_PORT_LOCATE_DSM		0x0D
+#define EDR_OST_SUCCESS			0x80
+#define EDR_OST_FAILED			0x81
+
+/*
+ * _DSM wrapper function to enable/disable DPC
+ * @pdev   : PCI device structure
+ *
+ * returns 0 on success or errno on failure.
+ */
+static int acpi_enable_dpc(struct pci_dev *pdev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	union acpi_object *obj, argv4, req;
+	int status = 0;
+
+	/*
+	 * Behavior when calling unsupported _DSM functions is undefined,
+	 * so check whether EDR_PORT_DPC_ENABLE_DSM is supported.
+	 */
+	if (!acpi_check_dsm(adev->handle, &pci_acpi_dsm_guid, 5,
+			    1ULL << EDR_PORT_DPC_ENABLE_DSM))
+		return 0;
+
+	req.type = ACPI_TYPE_INTEGER;
+	req.integer.value = 1;
+
+	argv4.type = ACPI_TYPE_PACKAGE;
+	argv4.package.count = 1;
+	argv4.package.elements = &req;
+
+	/*
+	 * Per Downstream Port Containment Related Enhancements ECN to PCI
+	 * Firmware Specification r3.2, sec 4.6.12, EDR_PORT_DPC_ENABLE_DSM is
+	 * optional.  Return success if it's not implemented.
+	 */
+	obj = acpi_evaluate_dsm(adev->handle, &pci_acpi_dsm_guid, 5,
+				EDR_PORT_DPC_ENABLE_DSM, &argv4);
+	if (!obj)
+		return 0;
+
+	if (obj->type != ACPI_TYPE_INTEGER) {
+		pci_err(pdev, FW_BUG "Enable DPC _DSM returned non integer\n");
+		status = -EIO;
+	}
+
+	if (obj->integer.value != 1) {
+		pci_err(pdev, "Enable DPC _DSM failed to enable DPC\n");
+		status = -EIO;
+	}
+
+	ACPI_FREE(obj);
+
+	return status;
+}
+
+/*
+ * _DSM wrapper function to locate DPC port
+ * @pdev   : Device which received EDR event
+ *
+ * Returns pci_dev or NULL.  Caller is responsible for dropping a reference
+ * on the returned pci_dev with pci_dev_put().
+ */
+static struct pci_dev *acpi_dpc_port_get(struct pci_dev *pdev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	union acpi_object *obj;
+	u16 port;
+
+	/*
+	 * Behavior when calling unsupported _DSM functions is undefined,
+	 * so check whether EDR_PORT_DPC_ENABLE_DSM is supported.
+	 */
+	if (!acpi_check_dsm(adev->handle, &pci_acpi_dsm_guid, 5,
+			    1ULL << EDR_PORT_LOCATE_DSM))
+		return pci_dev_get(pdev);
+
+	obj = acpi_evaluate_dsm(adev->handle, &pci_acpi_dsm_guid, 5,
+				EDR_PORT_LOCATE_DSM, NULL);
+	if (!obj)
+		return pci_dev_get(pdev);
+
+	if (obj->type != ACPI_TYPE_INTEGER) {
+		ACPI_FREE(obj);
+		pci_err(pdev, FW_BUG "Locate Port _DSM returned non integer\n");
+		return NULL;
+	}
+
+	/*
+	 * Firmware returns DPC port BDF details in following format:
+	 *	15:8 = bus
+	 *	 7:3 = device
+	 *	 2:0 = function
+	 */
+	port = obj->integer.value;
+
+	ACPI_FREE(obj);
+
+	return pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus),
+					   PCI_BUS_NUM(port), port & 0xff);
+}
+
+/*
+ * _OST wrapper function to let firmware know the status of EDR event
+ * @pdev   : Device used to send _OST
+ * @edev   : Device which experienced EDR event
+ * @status : Status of EDR event
+ */
+static int acpi_send_edr_status(struct pci_dev *pdev, struct pci_dev *edev,
+				u16 status)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	u32 ost_status;
+
+	pci_dbg(pdev, "Status for %s: %#x\n", pci_name(edev), status);
+
+	ost_status = PCI_DEVID(edev->bus->number, edev->devfn) << 16;
+	ost_status |= status;
+
+	status = acpi_evaluate_ost(adev->handle, ACPI_NOTIFY_DISCONNECT_RECOVER,
+				   ost_status, NULL);
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void edr_handle_event(acpi_handle handle, u32 event, void *data)
+{
+	struct pci_dev *pdev = data, *edev;
+	pci_ers_result_t estate = PCI_ERS_RESULT_DISCONNECT;
+	u16 status;
+
+	pci_info(pdev, "ACPI event %#x received\n", event);
+
+	if (event != ACPI_NOTIFY_DISCONNECT_RECOVER)
+		return;
+
+	/* Locate the port which issued EDR event */
+	edev = acpi_dpc_port_get(pdev);
+	if (!edev) {
+		pci_err(pdev, "Firmware failed to locate DPC port\n");
+		return;
+	}
+
+	pci_dbg(pdev, "Reported EDR dev: %s\n", pci_name(edev));
+
+	/* If port does not support DPC, just send the OST */
+	if (!edev->dpc_cap) {
+		pci_err(edev, FW_BUG "This device doesn't support DPC\n");
+		goto send_ost;
+	}
+
+	/* Check if there is a valid DPC trigger */
+	pci_read_config_word(edev, edev->dpc_cap + PCI_EXP_DPC_STATUS, &status);
+	if (!(status & PCI_EXP_DPC_STATUS_TRIGGER)) {
+		pci_err(edev, "Invalid DPC trigger %#010x\n", status);
+		goto send_ost;
+	}
+
+	dpc_process_error(edev);
+	pci_aer_raw_clear_status(edev);
+
+	/*
+	 * Irrespective of whether the DPC event is triggered by ERR_FATAL
+	 * or ERR_NONFATAL, since the link is already down, use the FATAL
+	 * error recovery path for both cases.
+	 */
+	estate = pcie_do_recovery(edev, pci_channel_io_frozen, dpc_reset_link);
+
+send_ost:
+
+	/*
+	 * If recovery is successful, send _OST(0xF, BDF << 16 | 0x80)
+	 * to firmware. If not successful, send _OST(0xF, BDF << 16 | 0x81).
+	 */
+	if (estate == PCI_ERS_RESULT_RECOVERED) {
+		pci_dbg(edev, "DPC port successfully recovered\n");
+		acpi_send_edr_status(pdev, edev, EDR_OST_SUCCESS);
+	} else {
+		pci_dbg(edev, "DPC port recovery failed\n");
+		acpi_send_edr_status(pdev, edev, EDR_OST_FAILED);
+	}
+
+	pci_dev_put(edev);
+}
+
+void pci_acpi_add_edr_notifier(struct pci_dev *pdev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	acpi_status status;
+
+	if (!adev) {
+		pci_dbg(pdev, "No valid ACPI node, skipping EDR init\n");
+		return;
+	}
+
+	status = acpi_install_notify_handler(adev->handle, ACPI_SYSTEM_NOTIFY,
+					     edr_handle_event, pdev);
+	if (ACPI_FAILURE(status)) {
+		pci_err(pdev, "Failed to install notify handler\n");
+		return;
+	}
+
+	if (acpi_enable_dpc(pdev))
+		acpi_remove_notify_handler(adev->handle, ACPI_SYSTEM_NOTIFY,
+					   edr_handle_event);
+	else
+		pci_dbg(pdev, "Notify handler installed\n");
+}
+
+void pci_acpi_remove_edr_notifier(struct pci_dev *pdev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+
+	if (!adev)
+		return;
+
+	acpi_remove_notify_handler(adev->handle, ACPI_SYSTEM_NOTIFY,
+				   edr_handle_event);
+	pci_dbg(pdev, "Notify handler removed\n");
+}
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index c6f91f886818..f67c007edcae 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -598,6 +598,7 @@ static void pci_init_host_bridge(struct pci_host_bridge *bridge)
 	bridge->native_shpc_hotplug = 1;
 	bridge->native_pme = 1;
 	bridge->native_ltr = 1;
+	bridge->native_dpc = 1;
 }
 
 struct pci_host_bridge *pci_alloc_host_bridge(size_t priv)
-- 
cgit v1.2.3


From 894020fdd88c1e9a74c60b67c0f19f1c7696ba2f Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 23 Mar 2020 17:26:08 -0700
Subject: PCI/AER: Rationalize error status register clearing

The AER interfaces to clear error status registers were a confusing mess:

  - pci_cleanup_aer_uncorrect_error_status() cleared non-fatal errors
    from the Uncorrectable Error Status register.

  - pci_aer_clear_fatal_status() cleared fatal errors from the
    Uncorrectable Error Status register.

  - pci_cleanup_aer_error_status_regs() cleared the Root Error Status
    register (for Root Ports), the Uncorrectable Error Status register,
    and the Correctable Error Status register.

Rename them to make them consistent:

  From                                     To
  ---------------------------------------- -------------------------------
  pci_cleanup_aer_uncorrect_error_status() pci_aer_clear_nonfatal_status()
  pci_aer_clear_fatal_status()             pci_aer_clear_fatal_status()
  pci_cleanup_aer_error_status_regs()      pci_aer_clear_status()

Since pci_cleanup_aer_error_status_regs() (renamed to
pci_aer_clear_status()) is only used within drivers/pci/, move the
declaration from <linux/aer.h> to drivers/pci/pci.h.

[bhelgaas: commit log, add renames]
Link: https://lore.kernel.org/r/d1310a75dc3d28f7e8da4e99c45fbd3e60fe238e.1585000084.git.sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c      | 2 +-
 drivers/pci/pci.h      | 2 ++
 drivers/pci/pcie/aer.c | 8 ++++----
 drivers/pci/pcie/dpc.c | 2 +-
 drivers/pci/pcie/err.c | 2 +-
 5 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'drivers/pci')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d828ca835a98..6c6e8c73fd8f 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1503,7 +1503,7 @@ void pci_restore_state(struct pci_dev *dev)
 	pci_restore_rebar_state(dev);
 	pci_restore_dpc_state(dev);
 
-	pci_cleanup_aer_error_status_regs(dev);
+	pci_aer_clear_status(dev);
 	pci_restore_aer_state(dev);
 
 	pci_restore_config_space(dev);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 25265bf80a83..bd46f23e3db1 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -656,6 +656,7 @@ void pci_aer_exit(struct pci_dev *dev);
 extern const struct attribute_group aer_stats_attr_group;
 void pci_aer_clear_fatal_status(struct pci_dev *dev);
 void pci_aer_clear_device_status(struct pci_dev *dev);
+int pci_aer_clear_status(struct pci_dev *dev);
 int pci_aer_raw_clear_status(struct pci_dev *dev);
 #else
 static inline void pci_no_aer(void) { }
@@ -663,6 +664,7 @@ static inline void pci_aer_init(struct pci_dev *d) { }
 static inline void pci_aer_exit(struct pci_dev *d) { }
 static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { }
 static inline void pci_aer_clear_device_status(struct pci_dev *dev) { }
+static inline int pci_aer_clear_status(struct pci_dev *dev) { return -EINVAL; }
 static inline int pci_aer_raw_clear_status(struct pci_dev *dev) { return -EINVAL; }
 #endif
 
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index bd9f122165e0..f4274d301235 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -377,7 +377,7 @@ void pci_aer_clear_device_status(struct pci_dev *dev)
 	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta);
 }
 
-int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
+int pci_aer_clear_nonfatal_status(struct pci_dev *dev)
 {
 	int pos;
 	u32 status, sev;
@@ -398,7 +398,7 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
+EXPORT_SYMBOL_GPL(pci_aer_clear_nonfatal_status);
 
 void pci_aer_clear_fatal_status(struct pci_dev *dev)
 {
@@ -457,7 +457,7 @@ int pci_aer_raw_clear_status(struct pci_dev *dev)
 	return 0;
 }
 
-int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
+int pci_aer_clear_status(struct pci_dev *dev)
 {
 	if (pcie_aer_get_firmware_first(dev))
 		return -EIO;
@@ -530,7 +530,7 @@ void pci_aer_init(struct pci_dev *dev)
 	n = pcie_cap_has_rtctl(dev) ? 5 : 4;
 	pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_ERR, sizeof(u32) * n);
 
-	pci_cleanup_aer_error_status_regs(dev);
+	pci_aer_clear_status(dev);
 }
 
 void pci_aer_exit(struct pci_dev *dev)
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 22998ee2f7ea..762170423fdd 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -221,7 +221,7 @@ void dpc_process_error(struct pci_dev *pdev)
 		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
 		 aer_get_device_error_info(pdev, &info)) {
 		aer_print_error(pdev, &info);
-		pci_cleanup_aer_uncorrect_error_status(pdev);
+		pci_aer_clear_nonfatal_status(pdev);
 		pci_aer_clear_fatal_status(pdev);
 	}
 }
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 0c40488da651..14bb8f54723e 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -198,7 +198,7 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev,
 	pci_walk_bus(bus, report_resume, &status);
 
 	pci_aer_clear_device_status(dev);
-	pci_cleanup_aer_uncorrect_error_status(dev);
+	pci_aer_clear_nonfatal_status(dev);
 	pci_info(dev, "device recovery successful\n");
 	return status;
 
-- 
cgit v1.2.3