[PATCH V5 00/10] VF EEH on Power8

[PATCH V5 00/10] VF EEH on Power8

[Wei Yang]

This patchset enables EEH on SRIOV VFs. The general idea is to create proper
VF edev and VF PE and handle them properly.

Different from the Bus PE, VF PE just contain one VF. This introduces the
difference of EEH error handling on a VF PE. Generally, it has several
differences.

First, the VF's removal and re-enumerate rely on its PF. VF has a tight
relationship between its PF. This is not proper to enumerate a VF by usual
scan procedure. That's why virtfn_add/virtfn_remove are exported in this patch
set.

Second, the reset/restore of a VF is done in kernel space. FW is not aware of
the VF, this means the usual reset function done in FW will not work. One of
the patch will imitate the reset/restore function in kernel space.

Third, the VF may be removed during the PF's error_detected function. In this
case, the original error_detected->slot_reset->resume sequence is not proper
to those removed VFs, since they are re-created by PF in a fresh state. A flag
in eeh_dev is introduce to mark the eeh_dev is in error state. By doing so, we
track whether this device needs to be reset or not.

This has been tested both on host and in guest on Power8 with latest kernel
version.

v5:
   * remove the compound field, iterate on Master VF PE instead
   * some code refine on PCI config restore and reset on VF
     the wait time for assert and deassert
     PCI device address format
     check on edev->pcie_cap and edev->aer_cap before access them
v4:
   * refine the change logs, comment and code style
   * change pnv_pci_fixup_vf_eeh() to pnv_eeh_vf_final_fixup() and remove the
     CONFIG_PCI_IOV macro
   * reorder patch 5/6 to make the logic more reasonable
   * remove remove_dev_pci_data()
   * remove the EEH_DEV_VF flag, use edev->physfn to identify a VF EEH DEV and
     remove related CONFIG_PCI_IOV macro
   * add the option for VF reset
   * fix the pnv_eeh_cfg_blocked() logic
   * replace pnv_pci_cfg_{read,write} with eeh_ops->{read,write}_config in
     pnv_eeh_vf_restore_config()
   * rename pnv_eeh_vf_restore_config() to pnv_eeh_restore_vf_config()
   * rename pnv_pci_fixup_vf_caps() to pnv_pci_vf_header_fixup() and move it
     to arch/powerpc/platforms/powernv/pci.c
   * add a field compound in pnv_ioda_pe to link compound PEs
   * handle compound PE for VF PEs
v3:
   * add back vf_index in pci_dn to track the VF's index
   * rename ppdev in eeh_dev to physfn for consistency
   * move edev->physfn assignment before dev->dev.archdata.edev is set
   * move pnv_pci_fixup_vf_eeh() and pnv_pci_fixup_vf_caps() to eeh-powernv.c
   * more clear and detail in commit log and comment in code
   * merge eeh_rmv_virt_device() with eeh_rmv_device()
   * move the cfg_blocked check logic from pnv_eeh_read/write_config() to
     pnv_eeh_cfg_blocked()
   * move the vf reset/restore logic into its own patch, two patches are
     created.
     powerpc/powernv: Support PCI config restore for VFs
     powerpc/powernv: Support EEH reset for VFs
   * simplify the vf reset logic
v2:
   * add prefix pci_iov_ to virtfn_add/virtfn_remove
   * use EEH_DEV_VF as a flag for a VF's eeh_dev
   * use eeh_dev instead of edev in change log
   * remove vf_index in eeh_dev, calculate it from pdn->busno and devfn
   * do eeh_add_device_late() and eeh_sysfs_add_device() both after pci_dev is
     well initialized
   * do FLR to reset a VF PE
   * imitate the restore function in FW for VF
   * remove the reverse order patch, since it is still under discussion

Wei Yang (10):
  pci/iov: rename and export virtfn_add/virtfn_remove
  powerpc/pci_dn: cache vf_index in pci_dn
  powerpc/pci: remove PCI devices in reverse order
  powerpc/eeh: cache address range just for normal device
  powerpc/powernv: create/release eeh_dev for VF
  powerpc/eeh: create EEH_PE_VF for VF PE
  powerpc/powernv: Support EEH reset for VFs
  powerpc/powernv: Support PCI config restore for VFs
  powerpc/eeh: handle VF PE properly
  powerpc/powernv: compound PE for VFs

 arch/powerpc/include/asm/eeh.h               |    4 +
 arch/powerpc/include/asm/pci-bridge.h        |    2 +
 arch/powerpc/kernel/eeh.c                    |   13 ++
 arch/powerpc/kernel/eeh_cache.c              |    2 +-
 arch/powerpc/kernel/eeh_driver.c             |  105 ++++++++++---
 arch/powerpc/kernel/eeh_pe.c                 |   13 +-
 arch/powerpc/kernel/pci-hotplug.c            |    2 +-
 arch/powerpc/kernel/pci_dn.c                 |   13 +-
 arch/powerpc/platforms/powernv/eeh-powernv.c |  216 +++++++++++++++++++++++++-
 arch/powerpc/platforms/powernv/pci-ioda.c    |   50 +++++-
 arch/powerpc/platforms/powernv/pci.c         |   33 +++-
 drivers/pci/iov.c                            |   10 +-
 include/linux/pci.h                          |    2 +
 13 files changed, 424 insertions(+), 41 deletions(-)

-- 
1.7.9.5

[PATCH V5 01/10] pci/iov: rename and export virtfn_add/virtfn_remove

[Wei Yang]

During the EEH recovery, when a device's driver is not EEH aware or no
driver is bound with a device, EEH core would do hotplug on this device.
While it isn't feasible for a VF with usual hotplug procedure. During
removal of a VF, virtual bus should be removed if necessary. During the
re-creation, the pci_scan_slot() doesn't work on a VF.

This patch exports two functions to handle the hotplug case for VF
properly. They will be invoked when the EEH core does the hotplug case for
VFs.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 drivers/pci/iov.c   |   10 +++++-----
 include/linux/pci.h |    2 ++
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 47daf2f..f353e6f 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -106,7 +106,7 @@ resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno)
 	return dev->sriov->barsz[resno - PCI_IOV_RESOURCES];
 }
 
-static int virtfn_add(struct pci_dev *dev, int id, int reset)
+int pci_iov_virtfn_add(struct pci_dev *dev, int id, int reset)
 {
 	int i;
 	int rc = -ENOMEM;
@@ -181,7 +181,7 @@ failed:
 	return rc;
 }
 
-static void virtfn_remove(struct pci_dev *dev, int id, int reset)
+void pci_iov_virtfn_remove(struct pci_dev *dev, int id, int reset)
 {
 	struct pci_dev *virtfn;
 
@@ -302,7 +302,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	}
 
 	for (i = 0; i < initial; i++) {
-		rc = virtfn_add(dev, i, 0);
+		rc = pci_iov_virtfn_add(dev, i, 0);
 		if (rc)
 			goto failed;
 	}
@@ -314,7 +314,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 
 failed:
 	for (j = 0; j < i; j++)
-		virtfn_remove(dev, j, 0);
+		pci_iov_virtfn_remove(dev, j, 0);
 
 	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
 	pci_cfg_access_lock(dev);
@@ -343,7 +343,7 @@ static void sriov_disable(struct pci_dev *dev)
 		return;
 
 	for (i = 0; i < iov->num_VFs; i++)
-		virtfn_remove(dev, i, 0);
+		pci_iov_virtfn_remove(dev, i, 0);
 
 	pcibios_sriov_disable(dev);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 353db8d..94bacfa 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1679,6 +1679,8 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int id);
 
 int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 void pci_disable_sriov(struct pci_dev *dev);
+int pci_iov_virtfn_add(struct pci_dev *dev, int id, int reset);
+void pci_iov_virtfn_remove(struct pci_dev *dev, int id, int reset);
 int pci_num_vf(struct pci_dev *dev);
 int pci_vfs_assigned(struct pci_dev *dev);
 int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs);
-- 
1.7.9.5

[PATCH V5 02/10] powerpc/pci_dn: cache vf_index in pci_dn

[Wei Yang]

The patch caches the VF index in pci_dn, which can be used to calculate
VF's bus, device and function number. Those information helps to locate
the VF's PCI device instance when doing hotplug during EEH recovery if
necessary.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pci-bridge.h |    1 +
 arch/powerpc/kernel/pci_dn.c          |    4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 1811c44..d78afe4 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -199,6 +199,7 @@ struct pci_dn {
 #ifdef CONFIG_PCI_IOV
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
 	u16     num_vfs;		/* number of VFs enabled*/
+	int     vf_index;		/* VF index in the PF */
 	int     offset;			/* PE# for the first VF PE */
 #define M64_PER_IOV 4
 	int     m64_per_iov;
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index b3b4df9..f771130 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -139,6 +139,7 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 #ifdef CONFIG_PCI_IOV
 static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
 					   struct pci_dev *pdev,
+					   int vf_index,
 					   int busno, int devfn)
 {
 	struct pci_dn *pdn;
@@ -157,6 +158,7 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
 	pdn->parent = parent;
 	pdn->busno = busno;
 	pdn->devfn = devfn;
+	pdn->vf_index = vf_index;
 #ifdef CONFIG_PPC_POWERNV
 	pdn->pe_number = IODA_INVALID_PE;
 #endif
@@ -196,7 +198,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 		return NULL;
 
 	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
-		pdn = add_one_dev_pci_data(parent, NULL,
+		pdn = add_one_dev_pci_data(parent, NULL, i,
 					   pci_iov_virtfn_bus(pdev, i),
 					   pci_iov_virtfn_devfn(pdev, i));
 		if (!pdn) {
-- 
1.7.9.5

[PATCH V5 03/10] powerpc/pci: remove PCI devices in reverse order

[Wei Yang]

As commit ac205b7b ("PCI: make sriov work with hotplug remove") indicates,
when removing PCI devices on a bus which has VFs, we need to remove them
in the reverse order.

This patch applies this pattern to the hotplug removal code for the powerpc
arch.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/pci-hotplug.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 7ed85a6..98f84ed 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -50,7 +50,7 @@ void pcibios_remove_pci_devices(struct pci_bus *bus)
 
 	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
 		 pci_domain_nr(bus),  bus->number);
-	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
+	list_for_each_entry_safe_reverse(dev, tmp, &bus->devices, bus_list) {
 		pr_debug("   Removing %s...\n", pci_name(dev));
 		pci_stop_and_remove_bus_device(dev);
 	}
-- 
1.7.9.5

[PATCH V5 04/10] powerpc/eeh: cache address range just for normal device

[Wei Yang]

The address cache is used to find the related eeh_dev for a given MMIO
address.  From the definition of pci_dev.resource[], it keeps MMIO address
in following order: 6 normal BAR, ROM BAR, 6 IOV BAR, 4 Bridge window.

In the address cache, first it doesn't cache bridge device, second the IOV
BAR range should map to their own VFs separately. This means it just need
to cache the first 7 BARs for a normal device.

This patch restricts the address cache to save the first 7 BARs for a pci
device.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/eeh_cache.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index a1e86e1..f0ce2a3 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -196,7 +196,7 @@ static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
 	}
 
 	/* Walk resources on this device, poke them into the tree */
-	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
 		resource_size_t start = pci_resource_start(dev,i);
 		resource_size_t end = pci_resource_end(dev,i);
 		unsigned long flags = pci_resource_flags(dev,i);
-- 
1.7.9.5

[PATCH V5 05/10] powerpc/powernv: create/release eeh_dev for VF

[Wei Yang]

EEH on powerpc platform needs eeh_dev structure to track the PCI device
status. Since VFs are created/released dynamically, VF's eeh_dev is also
dynamically created/released in system.

This patch creates/removes eeh_dev when pci_dn is created/removed for VFs,
and marks it with EEH_DEV_VF type.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/eeh.h |    1 +
 arch/powerpc/kernel/eeh.c      |    4 ++++
 arch/powerpc/kernel/pci_dn.c   |    9 +++++++++
 3 files changed, 14 insertions(+)

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index a52db28..1b3614d 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -138,6 +138,7 @@ struct eeh_dev {
 	struct pci_controller *phb;	/* Associated PHB		*/
 	struct pci_dn *pdn;		/* Associated PCI device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
+	struct pci_dev *physfn;		/* Associated PF PORT		*/
 	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
 
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 6c7ce1b..221e280 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1135,6 +1135,10 @@ void eeh_add_device_late(struct pci_dev *dev)
 	}
 
 	edev->pdev = dev;
+#ifdef CONFIG_PCI_IOV
+	if (dev->is_virtfn)
+		edev->physfn = dev->physfn;
+#endif
 	dev->dev.archdata.edev = edev;
 
 	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index f771130..0469247 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -180,6 +180,7 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
 struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 {
 #ifdef CONFIG_PCI_IOV
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pci_dn *parent, *pdn;
 	int i;
 
@@ -206,6 +207,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 				 __func__, i);
 			return NULL;
 		}
+		eeh_dev_init(pdn, hose);
 	}
 #endif /* CONFIG_PCI_IOV */
 
@@ -254,10 +256,17 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
 		list_for_each_entry_safe(pdn, tmp,
 			&parent->child_list, list) {
+			struct eeh_dev *edev;
 			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
 			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
 				continue;
 
+			edev = pdn_to_eeh_dev(pdn);
+			if (edev) {
+				pdn->edev = NULL;
+				kfree(edev);
+			}
+
 			if (!list_empty(&pdn->list))
 				list_del(&pdn->list);
 
-- 
1.7.9.5

[PATCH V5 06/10] powerpc/eeh: create EEH_PE_VF for VF PE

[Wei Yang]

On powernv platform, VF PE is a special PE which is different from the Bus
PE.  On the EEH side, it needs a corresponding concept to handle the VF PE
properly. For example, we need to create VF PE when VF's pci_dev is
initialized in kernel. And add a flag to mark it is a VF PE.

This patch introduces the EEH_PE_VF type for VF PE and creates it for a VF.
At the mean time, it creates the sysfs and address cache for VF PE at PCI
device final fixup time.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/eeh.h               |    1 +
 arch/powerpc/kernel/eeh_pe.c                 |   10 ++++++++--
 arch/powerpc/platforms/powernv/eeh-powernv.c |   16 ++++++++++++++++
 3 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 1b3614d..c1fde48 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -70,6 +70,7 @@ struct pci_dn;
 #define EEH_PE_PHB	(1 << 1)	/* PHB PE    */
 #define EEH_PE_DEVICE 	(1 << 2)	/* Device PE */
 #define EEH_PE_BUS	(1 << 3)	/* Bus PE    */
+#define EEH_PE_VF	(1 << 4)	/* VF PE     */
 
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 35f0b62..260a701 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -299,7 +299,10 @@ static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
 	 * EEH device already having associated PE, but
 	 * the direct parent EEH device doesn't have yet.
 	 */
-	pdn = pdn ? pdn->parent : NULL;
+	if (edev->physfn)
+		pdn = pci_get_pdn(edev->physfn);
+	else
+		pdn = pdn ? pdn->parent : NULL;
 	while (pdn) {
 		/* We're poking out of PCI territory */
 		parent = pdn_to_eeh_dev(pdn);
@@ -382,7 +385,10 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 	}
 
 	/* Create a new EEH PE */
-	pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE);
+	if (edev->physfn)
+		pe = eeh_pe_alloc(edev->phb, EEH_PE_VF);
+	else
+		pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE);
 	if (!pe) {
 		pr_err("%s: out of memory!\n", __func__);
 		return -ENOMEM;
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 622f08c..c4ea2ad 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1540,3 +1540,19 @@ static int __init eeh_powernv_init(void)
 	return ret;
 }
 machine_early_initcall(powernv, eeh_powernv_init);
+
+static void pnv_eeh_vf_final_fixup(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	/*
+	 * The following operations will fail if VF's sysfs files aren't
+	 * created or its resources aren't finalized.
+	 */
+	if (!pdev->is_virtfn)
+		return;
+
+	eeh_add_device_early(pdn);
+	eeh_add_device_late(pdev);
+	eeh_sysfs_add_device(pdev);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pnv_eeh_vf_final_fixup);
-- 
1.7.9.5

[PATCH V5 07/10] powerpc/powernv: Support EEH reset for VFs

[Wei Yang]

Before VF PE is introduced, there isn't a method to reset an individual PCI
function. And since skiboot firmware is not aware of the VF, the VF's reset
should be done in kernel.

This patch introduces a function pnv_eeh_vf_pe_reset() to do the FLR or AF
FLR to a VF.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/eeh.h               |    1 +
 arch/powerpc/platforms/powernv/eeh-powernv.c |  129 +++++++++++++++++++++++++-
 2 files changed, 129 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index c1fde48..3d64cf3 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -134,6 +134,7 @@ struct eeh_dev {
 	int pcix_cap;			/* Saved PCIx capability	*/
 	int pcie_cap;			/* Saved PCIe capability	*/
 	int aer_cap;			/* Saved AER capability		*/
+	int af_cap;			/* Saved AF 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/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index c4ea2ad..2a224b2 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -402,6 +402,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX);
 	edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP);
 	edev->aer_cap  = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR);
+	edev->af_cap   = pnv_eeh_find_cap(pdn, PCI_CAP_ID_AF);
 	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
 		if (edev->pcie_cap) {
@@ -891,6 +892,123 @@ static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
 	return 0;
 }
 
+static bool pnv_eeh_wait_for_pending(struct pci_dn *pdn, int pos, u16 mask)
+{
+	int i;
+	u32 status;
+
+	/* Wait for Transaction Pending bit clean */
+	for (i = 0; i < 4; i++) {
+		if (i)
+			msleep((1 << (i - 1)) * 100);
+
+		eeh_ops->read_config(pdn, pos, 2, &status);
+		if (!(status & mask))
+			return true;
+	}
+
+	return false;
+}
+
+static int pnv_eeh_do_flr(struct pci_dn *pdn, int option)
+{
+	u32 cap;
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+
+	if (!edev->pcie_cap)
+		return -ENOTTY;
+
+	eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP, 4, &cap);
+	if (!(cap & PCI_EXP_DEVCAP_FLR))
+		return -ENOTTY;
+
+	if (!pnv_eeh_wait_for_pending(pdn, edev->pcie_cap + PCI_EXP_DEVSTA,
+			PCI_EXP_DEVSTA_TRPND))
+		pr_warn("%s: Pending transaction while issuing FLR to "
+			"%04x:%02x:%02x.%01x\n",
+			__func__, edev->phb->global_number, pdn->busno,
+			PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+
+	eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, 4, &cap);
+	if (option == EEH_RESET_DEACTIVATE)
+		cap &= ~PCI_EXP_DEVCTL_BCR_FLR;
+	else
+		cap |= PCI_EXP_DEVCTL_BCR_FLR;
+	eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, 4, cap);
+	if (option == EEH_RESET_DEACTIVATE)
+		msleep(EEH_PE_RST_SETTLE_TIME);
+	else
+		msleep(EEH_PE_RST_HOLD_TIME);
+	return 0;
+}
+
+static int pnv_eeh_do_af_flr(struct pci_dn *pdn, int option)
+{
+	u32 cap;
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+
+	if (!edev->af_cap)
+		return -ENOTTY;
+
+	eeh_ops->read_config(pdn, edev->af_cap + PCI_AF_CAP, 1, &cap);
+	if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR))
+		return -ENOTTY;
+
+	/*
+	 * Wait for Transaction Pending bit to clear.  A word-aligned test
+	 * is used, so we use the conrol offset rather than status and shift
+	 * the test bit to match.
+	 */
+	if (!pnv_eeh_wait_for_pending(pdn, edev->af_cap + PCI_AF_CTRL,
+				 PCI_AF_STATUS_TP << 8))
+		pr_warn("%s: Pending transaction while issuing AF FLR to "
+			"%04x:%02x:%02x.%01x\n",
+			__func__, edev->phb->global_number, pdn->busno,
+			PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+
+	if (option == EEH_RESET_DEACTIVATE)
+		eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, 1, 0);
+	else
+		eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, 1,
+				PCI_AF_CTRL_FLR);
+	if (option == EEH_RESET_DEACTIVATE)
+		msleep(EEH_PE_RST_SETTLE_TIME);
+	else
+		msleep(EEH_PE_RST_HOLD_TIME);
+	return 0;
+}
+
+static int pnv_eeh_reset_vf(struct pci_dn *pdn, int option)
+{
+	int rc;
+
+	rc = pnv_eeh_do_flr(pdn, option);
+	if (rc != -ENOTTY)
+		return rc;
+
+	rc = pnv_eeh_do_af_flr(pdn, option);
+	if (rc != -ENOTTY)
+		return rc;
+
+	return -ENOTTY;
+}
+
+static int pnv_eeh_vf_pe_reset(struct eeh_pe *pe, int option)
+{
+	struct eeh_dev *edev, *tmp;
+	struct pci_dn *pdn;
+	int ret = 0;
+
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdn = eeh_dev_to_pdn(edev);
+		ret |= pnv_eeh_reset_vf(pdn, option);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
 void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
 {
 	struct pci_controller *hose;
@@ -966,7 +1084,9 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
 		}
 
 		bus = eeh_pe_bus_get(pe);
-		if (pci_is_root_bus(bus) ||
+		if (pe->type & EEH_PE_VF)
+			ret = pnv_eeh_vf_pe_reset(pe, option);
+		else if (pci_is_root_bus(bus) ||
 			pci_is_root_bus(bus->parent))
 			ret = pnv_eeh_root_reset(hose, option);
 		else
@@ -1106,6 +1226,13 @@ static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn)
 	if (!edev || !edev->pe)
 		return false;
 
+	/*
+	 * For VF's reset operation, we need to rely on the kernel to
+	 * do those PCI config operations since firmware isn't aware of VFs.
+	 */
+	if ((edev->physfn) && (edev->pe->state & EEH_PE_RESET))
+		return false;
+
 	if (edev->pe->state & EEH_PE_CFG_BLOCKED)
 		return true;
 
-- 
1.7.9.5

[PATCH V5 08/10] powerpc/powernv: Support PCI config restore for VFs

[Wei Yang]

Since skiboot firmware is not aware of VFs, the restore action for VF
should be done in kernel.

The patch introduces function pnv_eeh_restore_vf_config() to restore PCI
config space for VFs after reset.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pci-bridge.h        |    1 +
 arch/powerpc/platforms/powernv/eeh-powernv.c |   71 +++++++++++++++++++++++++-
 arch/powerpc/platforms/powernv/pci.c         |   16 ++++++
 3 files changed, 87 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index d78afe4..168b991 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -205,6 +205,7 @@ struct pci_dn {
 	int     m64_per_iov;
 #define IODA_INVALID_M64        (-1)
 	int     m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV];
+	int	mps;
 #endif /* CONFIG_PCI_IOV */
 #endif
 	struct list_head child_list;
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 2a224b2..1393283 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1607,6 +1607,68 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	return ret;
 }
 
+#ifdef CONFIG_PCI_IOV
+static int pnv_eeh_restore_vf_config(struct pci_dn *pdn)
+{
+	int old_mps;
+	u32 devctl, cmd, cap2, aer_capctl;
+	struct eeh_dev *edev;
+
+	/* Restore MPS */
+	edev = pdn_to_eeh_dev(pdn);
+	if (edev->pcie_cap) {
+		old_mps = (ffs(pdn->mps) - 8) << 5;
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				2, &devctl);
+		devctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
+		devctl |= old_mps;
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				2, devctl);
+	}
+
+	/* Disable Completion Timeout */
+	if (edev->pcie_cap) {
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2,
+				4, &cap2);
+		if (cap2 & 0x10) {
+			eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL2,
+					4, &cap2);
+			cap2 |= 0x10;
+			eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL2,
+					4, cap2);
+		}
+	}
+
+	/* Enable SERR and parity checking */
+	eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd);
+	cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd);
+
+	/* Enable report various errors */
+	if (edev->pcie_cap) {
+		eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				2, &devctl);
+		devctl &= ~PCI_EXP_DEVCTL_CERE;
+		devctl |= (PCI_EXP_DEVCTL_NFERE |
+			   PCI_EXP_DEVCTL_FERE |
+			   PCI_EXP_DEVCTL_URRE);
+		eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL,
+				2, devctl);
+	}
+
+	/* Enable ECRC generation and check */
+	if (edev->pcie_cap && edev->aer_cap) {
+		eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP,
+				4, &aer_capctl);
+		aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
+		eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP,
+				4, aer_capctl);
+	}
+
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static int pnv_eeh_restore_config(struct pci_dn *pdn)
 {
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
@@ -1617,7 +1679,14 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 		return -EEXIST;
 
 	phb = edev->phb->private_data;
-	ret = opal_pci_reinit(phb->opal_id,
+	/*
+	 * We have to restore the PCI config space after reset since the
+	 * firmware can't see SRIOV VFs.
+	 */
+	if (edev->physfn)
+		ret = pnv_eeh_restore_vf_config(pdn);
+	else
+		ret = opal_pci_reinit(phb->opal_id,
 			      OPAL_REINIT_PCI_DEV, edev->config_addr);
 	if (ret) {
 		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index bca2aeb..31d0258 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -781,3 +781,19 @@ machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init);
 struct pci_controller_ops pnv_pci_controller_ops = {
 	.dma_dev_setup = pnv_pci_dma_dev_setup,
 };
+
+static void pnv_pci_fixup_vf_caps(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	int parent_mps;
+
+	if (!pdev->is_virtfn)
+		return;
+
+	/* Synchronize MPS for VF and PF */
+	parent_mps = pcie_get_mps(pdev->physfn);
+	if ((128 << pdev->pcie_mpss) >= parent_mps)
+		pcie_set_mps(pdev, parent_mps);
+	pdn->mps = pcie_get_mps(pdev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_pci_fixup_vf_caps);
-- 
1.7.9.5

[PATCH V5 09/10] powerpc/eeh: handle VF PE properly

[Wei Yang]

Compared with Bus PE, VF PE just has one single pci function. This
introduces the difference of error handling on a VF PE.

For example in the hotplug case, EEH needs to remove and re-create the VF
properly. In the case when PF's error_detected() disable SRIOV, this patch
introduces a flag to mark the eeh_dev of a VF to avoid the slot_reset() and
resume(). Since the FW is not ware of the VF, this patch handles the VF
restore/reset in kernel directly.

This patch is to handle the VF PE properly in these cases.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/eeh.h   |    1 +
 arch/powerpc/kernel/eeh.c        |    9 ++++
 arch/powerpc/kernel/eeh_driver.c |  105 ++++++++++++++++++++++++++++++--------
 arch/powerpc/kernel/eeh_pe.c     |    3 +-
 4 files changed, 96 insertions(+), 22 deletions(-)

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 3d64cf3..d24382c 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -140,6 +140,7 @@ struct eeh_dev {
 	struct pci_controller *phb;	/* Associated PHB		*/
 	struct pci_dn *pdn;		/* Associated PCI device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
+	int    in_error;		/* Error flag for eeh_dev	*/
 	struct pci_dev *physfn;		/* Associated PF PORT		*/
 	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 221e280..fac0a72 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1226,6 +1226,15 @@ void eeh_remove_device(struct pci_dev *dev)
 	 * from the parent PE during the BAR resotre.
 	 */
 	edev->pdev = NULL;
+	/*
+	 * in_error is used to mark a eeh_dev is in error state.
+	 * It is set to 1, in eeh_report_error().
+	 * Then checked in eeh_report_reset() and eeh_report_resume(), if this
+	 * flag is not set, those eeh handlers are not invoked.
+	 * At last it is cleared in eeh_report_resume() or when the PCI device
+	 * is removed to mark the error state is cleared.
+	 * */
+	edev->in_error = 0;
 	dev->dev.archdata.edev = NULL;
 	if (!(edev->pe->state & EEH_PE_KEEP))
 		eeh_rmv_from_parent_pe(edev);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 89eb4bc..5b81283 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -211,6 +211,7 @@ static void *eeh_report_error(void *data, void *userdata)
 	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
 	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
 
+	edev->in_error = 1;
 	eeh_pcid_put(dev);
 	return NULL;
 }
@@ -282,7 +283,8 @@ static void *eeh_report_reset(void *data, void *userdata)
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->slot_reset ||
-	    (edev->mode & EEH_DEV_NO_HANDLER)) {
+	    (edev->mode & EEH_DEV_NO_HANDLER) ||
+	    (!edev->in_error)) {
 		eeh_pcid_put(dev);
 		return NULL;
 	}
@@ -339,14 +341,16 @@ static void *eeh_report_resume(void *data, void *userdata)
 
 	if (!driver->err_handler ||
 	    !driver->err_handler->resume ||
-	    (edev->mode & EEH_DEV_NO_HANDLER)) {
+	    (edev->mode & EEH_DEV_NO_HANDLER) ||
+	    (!edev->in_error)) {
 		edev->mode &= ~EEH_DEV_NO_HANDLER;
-		eeh_pcid_put(dev);
-		return NULL;
+		goto out;
 	}
 
 	driver->err_handler->resume(dev);
 
+out:
+	edev->in_error = 0;
 	eeh_pcid_put(dev);
 	return NULL;
 }
@@ -386,12 +390,40 @@ static void *eeh_report_failure(void *data, void *userdata)
 	return NULL;
 }
 
+#ifdef CONFIG_PCI_IOV
+static void *eeh_add_virt_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);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
+
+	if (!(edev->physfn)) {
+		pr_warn("%s: EEH dev %04x:%02x:%02x.%01x not for VF\n",
+			__func__, edev->phb->global_number, pdn->busno,
+			PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+		return NULL;
+	}
+
+	driver = eeh_pcid_get(dev);
+	if (driver) {
+		eeh_pcid_put(dev);
+		if (driver->err_handler)
+			return NULL;
+	}
+
+	pci_iov_virtfn_add(edev->physfn, pdn->vf_index, 0);
+	return NULL;
+}
+#endif /* CONFIG_PCI_IOV */
+
 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;
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	/*
 	 * Actually, we should remove the PCI bridges as well.
@@ -416,7 +448,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	driver = eeh_pcid_get(dev);
 	if (driver) {
 		eeh_pcid_put(dev);
-		if (driver->err_handler)
+		if (removed && driver->err_handler)
 			return NULL;
 	}
 
@@ -425,11 +457,22 @@ static void *eeh_rmv_device(void *data, void *userdata)
 		 pci_name(dev));
 	edev->bus = dev->bus;
 	edev->mode |= EEH_DEV_DISCONNECTED;
-	(*removed)++;
+	if (removed)
+		(*removed)++;
 
-	pci_lock_rescan_remove();
-	pci_stop_and_remove_bus_device(dev);
-	pci_unlock_rescan_remove();
+	if (edev->physfn) {
+		pci_iov_virtfn_remove(edev->physfn, pdn->vf_index, 0);
+		edev->pdev = NULL;
+		/*
+		 * We have to set the VF PE number to invalid one, which is
+		 * required to plug the VF successfully.
+		 */
+		pdn->pe_number = IODA_INVALID_PE;
+	} else {
+		pci_lock_rescan_remove();
+		pci_stop_and_remove_bus_device(dev);
+		pci_unlock_rescan_remove();
+	}
 
 	return NULL;
 }
@@ -548,6 +591,7 @@ 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, removed = 0;
+	struct eeh_dev *edev;
 
 	/* pcibios will clear the counter; save the value */
 	cnt = pe->freeze_count;
@@ -561,12 +605,15 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
 	if (bus) {
-		pci_lock_rescan_remove();
-		pcibios_remove_pci_devices(bus);
-		pci_unlock_rescan_remove();
-	} else if (frozen_bus) {
+		if (pe->type & EEH_PE_VF)
+			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
+		else {
+			pci_lock_rescan_remove();
+			pcibios_remove_pci_devices(bus);
+			pci_unlock_rescan_remove();
+		}
+	} else if (frozen_bus)
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
-	}
 
 	/*
 	 * Reset the pci controller. (Asserts RST#; resets config space).
@@ -607,14 +654,26 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 		 * PE. We should disconnect it so the binding can be
 		 * rebuilt when adding PCI devices.
 		 */
+		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
 		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
-		pcibios_add_pci_devices(bus);
+#ifdef CONFIG_PCI_IOV
+		if (pe->type & EEH_PE_VF)
+			eeh_add_virt_device(edev, NULL);
+		else
+#endif
+			pcibios_add_pci_devices(bus);
 	} else if (frozen_bus && removed) {
 		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
 		ssleep(5);
 
+		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
 		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
-		pcibios_add_pci_devices(frozen_bus);
+#ifdef CONFIG_PCI_IOV
+		if (pe->type & EEH_PE_VF)
+			eeh_add_virt_device(edev, NULL);
+		else
+#endif
+			pcibios_add_pci_devices(frozen_bus);
 	}
 	eeh_pe_state_clear(pe, EEH_PE_KEEP);
 
@@ -792,11 +851,15 @@ perm_error:
 	 * the their PCI config any more.
 	 */
 	if (frozen_bus) {
-		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
-
-		pci_lock_rescan_remove();
-		pcibios_remove_pci_devices(frozen_bus);
-		pci_unlock_rescan_remove();
+		if (pe->type & EEH_PE_VF) {
+			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
+			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+		} else {
+			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+			pci_lock_rescan_remove();
+			pcibios_remove_pci_devices(frozen_bus);
+			pci_unlock_rescan_remove();
+		}
 	}
 }
 
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 260a701..5cde950 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -914,7 +914,8 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 	if (pe->type & EEH_PE_PHB) {
 		bus = pe->phb->bus;
 	} else if (pe->type & EEH_PE_BUS ||
-		   pe->type & EEH_PE_DEVICE) {
+		   pe->type & EEH_PE_DEVICE ||
+		   pe->type & EEH_PE_VF) {
 		if (pe->bus) {
 			bus = pe->bus;
 			goto out;
-- 
1.7.9.5

[PATCH V5 10/10] powerpc/powernv: compound PE for VFs

[Wei Yang]

When VF BAR size is larger than 64MB, we group VFs in terms of M64 BAR,
which means those VFs in a group should form a compound PE.

This patch links those VF PEs into compound PE in this case.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/pci-ioda.c |   50 ++++++++++++++++++++++++++---
 arch/powerpc/platforms/powernv/pci.c      |   17 ++++++++--
 2 files changed, 60 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 920c252..23fe8aa 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1345,6 +1345,7 @@ static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 				vf_index < (vf_group + 1) * vf_per_group &&
 				vf_index < num_vfs;
 				vf_index++)
+
 				for (vf_index1 = vf_group * vf_per_group;
 					vf_index1 < (vf_group + 1) * vf_per_group &&
 					vf_index1 < num_vfs;
@@ -1363,9 +1364,20 @@ static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 	}
 
 	list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
+		struct pnv_ioda_pe *s, *sn;
 		if (pe->parent_dev != pdev)
 			continue;
 
+		if ((pe->flags & PNV_IODA_PE_MASTER) &&
+		    (pe->flags & PNV_IODA_PE_VF)) {
+			list_for_each_entry_safe(s, sn, &pe->slaves, list) {
+				pnv_pci_ioda2_release_dma_pe(pdev, s);
+				list_del(&s->list);
+				pnv_ioda_deconfigure_pe(phb, s);
+				pnv_ioda_free_pe(phb, s->pe_number);
+			}
+		}
+
 		pnv_pci_ioda2_release_dma_pe(pdev, pe);
 
 		/* Remove from list */
@@ -1418,7 +1430,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 	struct pci_bus        *bus;
 	struct pci_controller *hose;
 	struct pnv_phb        *phb;
-	struct pnv_ioda_pe    *pe;
+	struct pnv_ioda_pe    *pe, *master_pe;
 	int                    pe_num;
 	u16                    vf_index;
 	struct pci_dn         *pdn;
@@ -1464,10 +1476,16 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 				GFP_KERNEL, hose->node);
 		pe->tce32_table->data = pe;
 
-		/* Put PE to the list */
-		mutex_lock(&phb->ioda.pe_list_mutex);
-		list_add_tail(&pe->list, &phb->ioda.pe_list);
-		mutex_unlock(&phb->ioda.pe_list_mutex);
+		/*
+		 * Put PE to the list,
+		 * or postpone this if we have Compound PE
+		 */
+		if ((pdn->m64_per_iov != M64_PER_IOV) ||
+		    (num_vfs <= M64_PER_IOV)) {
+			mutex_lock(&phb->ioda.pe_list_mutex);
+			list_add_tail(&pe->list, &phb->ioda.pe_list);
+			mutex_unlock(&phb->ioda.pe_list_mutex);
+		}
 
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
 	}
@@ -1480,10 +1498,32 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
 
 		for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) {
+			master_pe = NULL;
+
 			for (vf_index = vf_group * vf_per_group;
 			     vf_index < (vf_group + 1) * vf_per_group &&
 			     vf_index < num_vfs;
 			     vf_index++) {
+
+				/*
+				 * Figure out the master PE and put all slave
+				 * PEs to master PE's list.
+				 */
+				pe = &phb->ioda.pe_array[pdn->offset + vf_index];
+				if (!master_pe) {
+					pe->flags |= PNV_IODA_PE_MASTER;
+					INIT_LIST_HEAD(&pe->slaves);
+					master_pe = pe;
+					mutex_lock(&phb->ioda.pe_list_mutex);
+					list_add_tail(&pe->list, &phb->ioda.pe_list);
+					mutex_unlock(&phb->ioda.pe_list_mutex);
+				} else {
+					pe->flags |= PNV_IODA_PE_SLAVE;
+					pe->master = master_pe;
+					list_add_tail(&pe->list,
+						&master_pe->slaves);
+				}
+
 				for (vf_index1 = vf_group * vf_per_group;
 				     vf_index1 < (vf_group + 1) * vf_per_group &&
 				     vf_index1 < num_vfs;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 31d0258..073caec 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -667,7 +667,7 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 #ifdef CONFIG_PCI_IOV
-	struct pnv_ioda_pe *pe;
+	struct pnv_ioda_pe *pe, *slave;
 	struct pci_dn *pdn;
 
 	/* Fix the VF pdn PE number */
@@ -679,10 +679,23 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 			    (pdev->devfn & 0xff))) {
 				pdn->pe_number = pe->pe_number;
 				pe->pdev = pdev;
-				break;
+				goto found;
+			}
+
+			if ((pe->flags & PNV_IODA_PE_MASTER) &&
+			    (pe->flags & PNV_IODA_PE_VF)) {
+				list_for_each_entry(slave, &pe->slaves, list) {
+					if (slave->rid == ((pdev->bus->number << 8)
+					   | (pdev->devfn & 0xff))) {
+						pdn->pe_number = slave->pe_number;
+						slave->pdev = pdev;
+						goto found;
+					}
+				}
 			}
 		}
 	}
+found:
 #endif /* CONFIG_PCI_IOV */
 
 	if (phb && phb->dma_dev_setup)
-- 
1.7.9.5