* [PATCH V9 07/18] powerpc/pci: Define pcibios_disable_device() on powerpc
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
When driver remove a pci_dev, it will call pcibios_disable_device() which is
platform dependent. This gives flexibility to platforms.
This patch defines this weak function on powerpc architecture.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/machdep.h | 5 ++++-
arch/powerpc/kernel/pci-common.c | 8 ++++++++
2 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 307347f..8242262 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -240,7 +240,10 @@ struct machdep_calls {
/* Called when pci_enable_device() is called. Returns 0 to
* allow assignment/enabling of the device. */
- int (*pcibios_enable_device_hook)(struct pci_dev *);
+ int (*pcibios_enable_device_hook)(struct pci_dev *);
+
+ /* Called when pci_disable_device() is called. */
+ void (*pcibios_disable_device_hook)(struct pci_dev *);
/* Called after scan and before resource survey */
void (*pcibios_fixup_phb)(struct pci_controller *hose);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 399d813..17acfa7 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1452,6 +1452,14 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
return pci_enable_resources(dev, mask);
}
+void pcibios_disable_device(struct pci_dev *dev)
+{
+ if (ppc_md.pcibios_disable_device_hook)
+ ppc_md.pcibios_disable_device_hook(dev);
+
+ return;
+}
+
resource_size_t pcibios_io_space_offset(struct pci_controller *hose)
{
return (unsigned long) hose->io_base_virt - _IO_BASE;
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 08/18] powrepc/pci: Refactor pci_dn
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
pci_dn is the extension of PCI device node and it's created from
device node. Unfortunately, VFs that are enabled dynamically by
PF's driver and they don't have corresponding device nodes, and
pci_dn. The patch refactors pci_dn to support VFs:
* pci_dn is organized as a hierarchy tree. VF's pci_dn is put
to the child list of pci_dn of PF's bridge. pci_dn of other
device put to the child list of pci_dn of its upstream bridge.
* VF's pci_dn is expected to be created dynamically when applying
final fixup to PF. VF's pci_dn will be destroyed when releasing
PF's pci_dev instance. pci_dn of other device is still created
from device node as before.
* For one particular PCI device (VF or not), its pci_dn can be
found from pdev->dev.archdata.firmware_data, PCI_DN(devnode),
or parent's list. The fast path (fetching pci_dn through PCI
device instance) is populated during early fixup time.
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/device.h | 3 +
arch/powerpc/include/asm/pci-bridge.h | 14 +-
arch/powerpc/kernel/pci-hotplug.c | 3 +
arch/powerpc/kernel/pci_dn.c | 246 ++++++++++++++++++++++++++++++++-
4 files changed, 261 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 38faede..29992cd 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -34,6 +34,9 @@ struct dev_archdata {
#ifdef CONFIG_SWIOTLB
dma_addr_t max_direct_dma_addr;
#endif
+#ifdef CONFIG_PPC64
+ void *firmware_data;
+#endif
#ifdef CONFIG_EEH
struct eeh_dev *edev;
#endif
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 4ca90a3..757d7bb 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -89,6 +89,7 @@ struct pci_controller {
#ifdef CONFIG_PPC64
unsigned long buid;
+ void *firmware_data;
#endif /* CONFIG_PPC64 */
void *private_data;
@@ -150,9 +151,13 @@ static inline int isa_vaddr_is_ioport(void __iomem *address)
struct iommu_table;
struct pci_dn {
+ int flags;
+#define PCI_DN_FLAG_IOV_VF 0x01
+
int busno; /* pci bus number */
int devfn; /* pci device and function number */
+ struct pci_dn *parent;
struct pci_controller *phb; /* for pci devices */
struct iommu_table *iommu_table; /* for phb's or bridges */
struct device_node *node; /* back-pointer to the device_node */
@@ -169,14 +174,19 @@ struct pci_dn {
#ifdef CONFIG_PPC_POWERNV
int pe_number;
#endif
+ struct list_head child_list;
+ struct list_head list;
};
/* Get the pointer to a device_node's pci_dn */
#define PCI_DN(dn) ((struct pci_dn *) (dn)->data)
+extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
+ int devfn);
extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
-
-extern void * update_dn_pci_info(struct device_node *dn, void *data);
+extern struct pci_dn *add_dev_pci_info(struct pci_dev *pdev);
+extern void remove_dev_pci_info(struct pci_dev *pdev);
+extern void *update_dn_pci_info(struct device_node *dn, void *data);
static inline int pci_device_from_OF_node(struct device_node *np,
u8 *bus, u8 *devfn)
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 5b78917..af60efe 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -30,6 +30,9 @@
void pcibios_release_device(struct pci_dev *dev)
{
eeh_remove_device(dev);
+
+ /* Release firmware data */
+ remove_dev_pci_info(dev);
}
/**
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 1f61fab..fa966ae 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -32,12 +32,222 @@
#include <asm/ppc-pci.h>
#include <asm/firmware.h>
+/*
+ * The function is used to find the firmware data of one
+ * specific PCI device, which is attached to the indicated
+ * PCI bus. For VFs, their firmware data is linked to that
+ * one of PF's bridge. For other devices, their firmware
+ * data is linked to that of their bridge.
+ */
+static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
+{
+ struct pci_bus *pbus;
+ struct device_node *dn;
+ struct pci_dn *pdn;
+
+ /*
+ * We probably have virtual bus which doesn't
+ * have associated bridge.
+ */
+ pbus = bus;
+ while (pbus) {
+ if (pci_is_root_bus(pbus) || pbus->self)
+ break;
+
+ pbus = pbus->parent;
+ }
+
+ /*
+ * Except virtual bus, all PCI buses should
+ * have device nodes.
+ */
+ dn = pci_bus_to_OF_node(pbus);
+ pdn = dn ? PCI_DN(dn) : NULL;
+
+ return pdn;
+}
+
+struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
+ int devfn)
+{
+ struct device_node *dn = NULL;
+ struct pci_dn *parent, *pdn;
+ struct pci_dev *pdev = NULL;
+
+ /* Fast path: fetch from PCI device */
+ list_for_each_entry(pdev, &bus->devices, bus_list) {
+ if (pdev->devfn == devfn) {
+ if (pdev->dev.archdata.firmware_data)
+ return pdev->dev.archdata.firmware_data;
+
+ dn = pci_device_to_OF_node(pdev);
+ break;
+ }
+ }
+
+ /* Fast path: fetch from device node */
+ pdn = dn ? PCI_DN(dn) : NULL;
+ if (pdn)
+ return pdn;
+
+ /* Slow path: fetch from firmware data hierarchy */
+ parent = pci_bus_to_pdn(bus);
+ if (!parent)
+ return NULL;
+
+ list_for_each_entry(pdn, &parent->child_list, list) {
+ if (pdn->busno == bus->number &&
+ pdn->devfn == devfn)
+ return pdn;
+ }
+
+ return NULL;
+}
+
struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
{
- struct device_node *dn = pci_device_to_OF_node(pdev);
- if (!dn)
+ struct device_node *dn;
+ struct pci_dn *parent, *pdn;
+
+ /* Search device directly */
+ if (pdev->dev.archdata.firmware_data)
+ return pdev->dev.archdata.firmware_data;
+
+ /* Check device node */
+ dn = pci_device_to_OF_node(pdev);
+ pdn = dn ? PCI_DN(dn) : NULL;
+ if (pdn)
+ return pdn;
+
+ /*
+ * VFs don't have device nodes. We hook their
+ * firmware data to PF's bridge.
+ */
+ parent = pci_bus_to_pdn(pdev->bus);
+ if (!parent)
return NULL;
- return PCI_DN(dn);
+
+ list_for_each_entry(pdn, &parent->child_list, list) {
+ if (pdn->busno == pdev->bus->number &&
+ pdn->devfn == pdev->devfn)
+ return pdn;
+ }
+
+ return NULL;
+}
+
+static struct pci_dn *add_one_dev_pci_info(struct pci_dn *parent,
+ struct pci_dev *pdev,
+ int busno, int devfn)
+{
+ struct pci_dn *pdn;
+
+ /* Except PHB, we always have parent firmware data */
+ if (!parent)
+ return NULL;
+
+ pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+ if (!pdn) {
+ pr_warn("%s: Out of memory !\n", __func__);
+ return NULL;
+ }
+
+ pdn->phb = parent->phb;
+ pdn->parent = parent;
+ pdn->busno = busno;
+ pdn->devfn = devfn;
+#ifdef CONFIG_PPC_POWERNV
+ pdn->pe_number = IODA_INVALID_PE;
+#endif
+ INIT_LIST_HEAD(&pdn->child_list);
+ INIT_LIST_HEAD(&pdn->list);
+ list_add_tail(&pdn->list, &parent->child_list);
+
+ /*
+ * If we already have PCI device instance, lets
+ * bind them.
+ */
+ if (pdev)
+ pdev->dev.archdata.firmware_data = pdn;
+
+ return pdn;
+}
+
+struct pci_dn *add_dev_pci_info(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+ struct pci_dn *parent, *pdn;
+ int i;
+
+ /* Only support IOV for now */
+ if (!pdev->is_physfn)
+ return pci_get_pdn(pdev);
+
+ /* Check if VFs have been populated */
+ pdn = pci_get_pdn(pdev);
+ if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
+ return NULL;
+
+ pdn->flags |= PCI_DN_FLAG_IOV_VF;
+ parent = pci_bus_to_pdn(pdev->bus);
+ if (!parent)
+ return NULL;
+
+ for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+ pdn = add_one_dev_pci_info(parent, NULL,
+ pci_iov_virtfn_bus(pdev, i),
+ pci_iov_virtfn_devfn(pdev, i));
+ if (!pdn) {
+ pr_warn("%s: Cannot create firmware data "
+ "for VF#%d of %s\n",
+ __func__, i, pci_name(pdev));
+ return NULL;
+ }
+ }
+#endif
+
+ return pci_get_pdn(pdev);
+}
+
+void remove_dev_pci_info(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+ struct pci_dn *parent;
+ struct pci_dn *pdn, *tmp;
+ int i;
+
+ /* Only support IOV PF for now */
+ if (!pdev->is_physfn)
+ return;
+
+ /* Check if VFs have been populated */
+ pdn = pci_get_pdn(pdev);
+ if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
+ return;
+
+ pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
+ parent = pci_bus_to_pdn(pdev->bus);
+ if (!parent)
+ return;
+
+ /*
+ * We might introduce flag to pci_dn in future
+ * so that we can release VF's firmware data in
+ * a batch mode.
+ */
+ for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+ list_for_each_entry_safe(pdn, tmp,
+ &parent->child_list, list) {
+ if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
+ pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
+ continue;
+
+ if (!list_empty(&pdn->list))
+ list_del(&pdn->list);
+ kfree(pdn);
+ }
+ }
+#endif
}
/*
@@ -49,6 +259,7 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
struct pci_controller *phb = data;
const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL);
const __be32 *regs;
+ struct device_node *parent;
struct pci_dn *pdn;
pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
@@ -70,6 +281,15 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
}
pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
+
+ /* Attach to parent node */
+ INIT_LIST_HEAD(&pdn->child_list);
+ INIT_LIST_HEAD(&pdn->list);
+ parent = of_get_parent(dn);
+ pdn->parent = parent ? PCI_DN(parent) : NULL;
+ if (pdn->parent)
+ list_add_tail(&pdn->list, &pdn->parent->child_list);
+
return NULL;
}
@@ -150,6 +370,7 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
if (pdn) {
pdn->devfn = pdn->busno = -1;
pdn->phb = phb;
+ phb->firmware_data = pdn;
}
/* Update dn->phb ptrs for new phb and children devices */
@@ -173,3 +394,22 @@ void __init pci_devs_phb_init(void)
list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
pci_devs_phb_init_dynamic(phb);
}
+
+static void pci_dev_pdn_create(struct pci_dev *pdev)
+{
+ add_dev_pci_info(pdev);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_create);
+
+static void pci_dev_pdn_setup(struct pci_dev *pdev)
+{
+ struct pci_dn *pdn;
+
+ if (pdev->dev.archdata.firmware_data)
+ return;
+
+ /* Setup the fast path */
+ pdn = pci_get_pdn(pdev);
+ pdev->dev.archdata.firmware_data = pdn;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup);
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 09/18] powerpc/pci: remove pci_dn->pcidev field
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
The field pci_dn->pcidev is assigned but not used.
This patch removes this field.
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/platforms/powernv/pci-ioda.c | 1 -
2 files changed, 2 deletions(-)
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 757d7bb..063d79d 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -166,7 +166,6 @@ struct pci_dn {
bool force_32bit_msi;
- struct pci_dev *pcidev; /* back-pointer to the pci device */
#ifdef CONFIG_EEH
struct eeh_dev *edev; /* eeh device */
#endif
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 468a0f2..df49dc6 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -727,7 +727,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
pci_name(dev));
continue;
}
- pdn->pcidev = dev;
pdn->pe_number = pe->pe_number;
pe->dma_weight += pnv_ioda_dma_weight(dev);
if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 10/18] powerpc/powernv: Use pci_dn in PCI config accessor
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
The PCI config accessors rely on device node. Unfortunately, VFs
don't have corresponding device nodes. So we have to switch to
pci_dn for PCI config access.
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
---
arch/powerpc/platforms/powernv/eeh-powernv.c | 14 +++++-
arch/powerpc/platforms/powernv/pci.c | 69 ++++++++++----------------
arch/powerpc/platforms/powernv/pci.h | 4 +-
3 files changed, 40 insertions(+), 47 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 1d19e79..c63b6c1 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -419,21 +419,31 @@ static inline bool powernv_eeh_cfg_blocked(struct device_node *dn)
static int powernv_eeh_read_config(struct device_node *dn,
int where, int size, u32 *val)
{
+ struct pci_dn *pdn = PCI_DN(dn);
+
+ if (!pdn)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
if (powernv_eeh_cfg_blocked(dn)) {
*val = 0xFFFFFFFF;
return PCIBIOS_SET_FAILED;
}
- return pnv_pci_cfg_read(dn, where, size, val);
+ return pnv_pci_cfg_read(pdn, where, size, val);
}
static int powernv_eeh_write_config(struct device_node *dn,
int where, int size, u32 val)
{
+ struct pci_dn *pdn = PCI_DN(dn);
+
+ if (!pdn)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
if (powernv_eeh_cfg_blocked(dn))
return PCIBIOS_SET_FAILED;
- return pnv_pci_cfg_write(dn, where, size, val);
+ return pnv_pci_cfg_write(pdn, where, size, val);
}
/**
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b2187d0..f8dbb3f 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -368,9 +368,9 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
spin_unlock_irqrestore(&phb->lock, flags);
}
-static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
- struct device_node *dn)
+static void pnv_pci_config_check_eeh(struct pci_dn *pdn)
{
+ struct pnv_phb *phb = pdn->phb->private_data;
u8 fstate;
__be16 pcierr;
int pe_no;
@@ -381,7 +381,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
* setup that yet. So all ER errors should be mapped to
* reserved PE.
*/
- pe_no = PCI_DN(dn)->pe_number;
+ pe_no = pdn->pe_number;
if (pe_no == IODA_INVALID_PE) {
if (phb->type == PNV_PHB_P5IOC2)
pe_no = 0;
@@ -409,8 +409,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
}
cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n",
- (PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn),
- pe_no, fstate);
+ (pdn->busno << 8) | (pdn->devfn), pe_no, fstate);
/* Clear the frozen state if applicable */
if (fstate == OPAL_EEH_STOPPED_MMIO_FREEZE ||
@@ -427,10 +426,9 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
}
}
-int pnv_pci_cfg_read(struct device_node *dn,
+int pnv_pci_cfg_read(struct pci_dn *pdn,
int where, int size, u32 *val)
{
- struct pci_dn *pdn = PCI_DN(dn);
struct pnv_phb *phb = pdn->phb->private_data;
u32 bdfn = (pdn->busno << 8) | pdn->devfn;
s64 rc;
@@ -464,10 +462,9 @@ int pnv_pci_cfg_read(struct device_node *dn,
return PCIBIOS_SUCCESSFUL;
}
-int pnv_pci_cfg_write(struct device_node *dn,
+int pnv_pci_cfg_write(struct pci_dn *pdn,
int where, int size, u32 val)
{
- struct pci_dn *pdn = PCI_DN(dn);
struct pnv_phb *phb = pdn->phb->private_data;
u32 bdfn = (pdn->busno << 8) | pdn->devfn;
@@ -491,18 +488,17 @@ int pnv_pci_cfg_write(struct device_node *dn,
}
#if CONFIG_EEH
-static bool pnv_pci_cfg_check(struct pci_controller *hose,
- struct device_node *dn)
+static bool pnv_pci_cfg_check(struct pci_dn *pdn)
{
struct eeh_dev *edev = NULL;
- struct pnv_phb *phb = hose->private_data;
+ struct pnv_phb *phb = pdn->phb->private_data;
/* EEH not enabled ? */
if (!(phb->flags & PNV_PHB_FLAG_EEH))
return true;
/* PE reset or device removed ? */
- edev = of_node_to_eeh_dev(dn);
+ edev = pdn->edev;
if (edev) {
if (edev->pe &&
(edev->pe->state & EEH_PE_CFG_BLOCKED))
@@ -515,8 +511,7 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose,
return true;
}
#else
-static inline pnv_pci_cfg_check(struct pci_controller *hose,
- struct device_node *dn)
+static inline pnv_pci_cfg_check(struct pci_dn *pdn)
{
return true;
}
@@ -526,32 +521,26 @@ static int pnv_pci_read_config(struct pci_bus *bus,
unsigned int devfn,
int where, int size, u32 *val)
{
- struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
struct pci_dn *pdn;
struct pnv_phb *phb;
- bool found = false;
int ret;
*val = 0xFFFFFFFF;
- for (dn = busdn->child; dn; dn = dn->sibling) {
- pdn = PCI_DN(dn);
- if (pdn && pdn->devfn == devfn) {
- phb = pdn->phb->private_data;
- found = true;
- break;
- }
- }
+ pdn = pci_get_pdn_by_devfn(bus, devfn);
+ if (!pdn)
+ return PCIBIOS_DEVICE_NOT_FOUND;
- if (!found || !pnv_pci_cfg_check(pdn->phb, dn))
+ if (!pnv_pci_cfg_check(pdn))
return PCIBIOS_DEVICE_NOT_FOUND;
- ret = pnv_pci_cfg_read(dn, where, size, val);
- if (phb->flags & PNV_PHB_FLAG_EEH) {
+ ret = pnv_pci_cfg_read(pdn, where, size, val);
+ phb = pdn->phb->private_data;
+ if (phb->flags & PNV_PHB_FLAG_EEH && pdn->edev) {
if (*val == EEH_IO_ERROR_VALUE(size) &&
- eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+ eeh_dev_check_failure(pdn->edev))
return PCIBIOS_DEVICE_NOT_FOUND;
} else {
- pnv_pci_config_check_eeh(phb, dn);
+ pnv_pci_config_check_eeh(pdn);
}
return ret;
@@ -561,27 +550,21 @@ static int pnv_pci_write_config(struct pci_bus *bus,
unsigned int devfn,
int where, int size, u32 val)
{
- struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
struct pci_dn *pdn;
struct pnv_phb *phb;
- bool found = false;
int ret;
- for (dn = busdn->child; dn; dn = dn->sibling) {
- pdn = PCI_DN(dn);
- if (pdn && pdn->devfn == devfn) {
- phb = pdn->phb->private_data;
- found = true;
- break;
- }
- }
+ pdn = pci_get_pdn_by_devfn(bus, devfn);
+ if (!pdn)
+ return PCIBIOS_DEVICE_NOT_FOUND;
- if (!found || !pnv_pci_cfg_check(pdn->phb, dn))
+ if (!pnv_pci_cfg_check(pdn))
return PCIBIOS_DEVICE_NOT_FOUND;
- ret = pnv_pci_cfg_write(dn, where, size, val);
+ ret = pnv_pci_cfg_write(pdn, where, size, val);
+ phb = pdn->phb->private_data;
if (!(phb->flags & PNV_PHB_FLAG_EEH))
- pnv_pci_config_check_eeh(phb, dn);
+ pnv_pci_config_check_eeh(pdn);
return ret;
}
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 34d29eb..9dc4143 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -219,9 +219,9 @@ extern struct pnv_eeh_ops ioda_eeh_ops;
void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
unsigned char *log_buff);
-int pnv_pci_cfg_read(struct device_node *dn,
+int pnv_pci_cfg_read(struct pci_dn *pdn,
int where, int size, u32 *val);
-int pnv_pci_cfg_write(struct device_node *dn,
+int pnv_pci_cfg_write(struct pci_dn *pdn,
int where, int size, u32 val);
extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
void *tce_mem, u64 tce_size,
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 11/18] powerpc/powernv: Allocate pe->iommu_table dynamically
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
Current iommu_table of a PE is a static field. This will have a problem when
iommu_free_table is called.
This patch allocate iommu_table dynamically.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/iommu.h | 3 +++
arch/powerpc/platforms/powernv/pci-ioda.c | 26 ++++++++++++++------------
arch/powerpc/platforms/powernv/pci.h | 2 +-
3 files changed, 18 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 42632c7..0fedacb 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -78,6 +78,9 @@ struct iommu_table {
struct iommu_group *it_group;
#endif
void (*set_bypass)(struct iommu_table *tbl, bool enable);
+#ifdef CONFIG_PPC_POWERNV
+ void *data;
+#endif
};
/* Pure 2^n version of get_order */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index df49dc6..6d35ed9 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -785,6 +785,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
return;
}
+ pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
+ GFP_KERNEL, hose->node);
+ pe->tce32_table->data = pe;
+
/* Associate it with all child devices */
pnv_ioda_setup_same_PE(bus, pe);
@@ -858,7 +862,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
pe = &phb->ioda.pe_array[pdn->pe_number];
WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
- set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
+ set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table);
}
static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
@@ -885,7 +889,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
} else {
dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
set_dma_ops(&pdev->dev, &dma_iommu_ops);
- set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+ set_iommu_table_base(&pdev->dev, pe->tce32_table);
}
*pdev->dev.dma_mask = dma_mask;
return 0;
@@ -922,9 +926,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
list_for_each_entry(dev, &bus->devices, bus_list) {
if (add_to_iommu_group)
set_iommu_table_base_and_group(&dev->dev,
- &pe->tce32_table);
+ pe->tce32_table);
else
- set_iommu_table_base(&dev->dev, &pe->tce32_table);
+ set_iommu_table_base(&dev->dev, pe->tce32_table);
if (dev->subordinate)
pnv_ioda_setup_bus_dma(pe, dev->subordinate,
@@ -1014,8 +1018,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
__be64 *startp, __be64 *endp, bool rm)
{
- struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
- tce32_table);
+ struct pnv_ioda_pe *pe = tbl->data;
struct pnv_phb *phb = pe->phb;
if (phb->type == PNV_PHB_IODA1)
@@ -1081,7 +1084,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
}
/* Setup linux iommu table */
- tbl = &pe->tce32_table;
+ tbl = pe->tce32_table;
pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
base << 28, IOMMU_PAGE_SHIFT_4K);
@@ -1119,8 +1122,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
{
- struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
- tce32_table);
+ struct pnv_ioda_pe *pe = tbl->data;
uint16_t window_id = (pe->pe_number << 1 ) + 1;
int64_t rc;
@@ -1165,10 +1167,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
pe->tce_bypass_base = 1ull << 59;
/* Install set_bypass callback for VFIO */
- pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+ pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
/* Enable bypass by default */
- pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+ pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
}
static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
@@ -1216,7 +1218,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
}
/* Setup linux iommu table */
- tbl = &pe->tce32_table;
+ tbl = pe->tce32_table;
pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
IOMMU_PAGE_SHIFT_4K);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 9dc4143..0f24a14 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -53,7 +53,7 @@ struct pnv_ioda_pe {
/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
int tce32_seg;
int tce32_segcount;
- struct iommu_table tce32_table;
+ struct iommu_table *tce32_table;
phys_addr_t tce_inval_reg_phys;
/* 64-bit TCE bypass region */
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 12/18] powerpc/powernv: Expand VF resources according to the number of total_pe
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
On PHB3, PF IOV BAR will be covered by M64 BAR to have better PE isolation.
Mostly the total_pe number is different from the total_VFs, which will lead to
a conflict between MMIO space and the PE number.
For example, total_VFs is 128 and total_pe is 256, then the second half of M64
BAR space will be part of other PCI device, which may already belongs to other
PEs.
This patch expands the PF IOV BAR size to reserve total_pe number of VF's BAR
size, which prevents the conflict.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/machdep.h | 4 +++
arch/powerpc/include/asm/pci-bridge.h | 3 ++
arch/powerpc/kernel/pci-common.c | 5 +++
arch/powerpc/platforms/powernv/pci-ioda.c | 56 +++++++++++++++++++++++++++++
4 files changed, 68 insertions(+)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 8242262..86d47ca 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -254,6 +254,10 @@ struct machdep_calls {
/* Reset the secondary bus of bridge */
void (*pcibios_reset_secondary_bus)(struct pci_dev *dev);
+#ifdef CONFIG_PCI_IOV
+ void (*pcibios_fixup_sriov)(struct pci_bus *bus);
+#endif /* CONFIG_PCI_IOV */
+
/* Called to shutdown machine specific hardware not already controlled
* by other drivers.
*/
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 063d79d..ff26045 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -172,6 +172,9 @@ struct pci_dn {
#define IODA_INVALID_PE (-1)
#ifdef CONFIG_PPC_POWERNV
int pe_number;
+#ifdef CONFIG_PCI_IOV
+ u16 max_vfs; /* number of VFs IOV BAR expended */
+#endif /* CONFIG_PCI_IOV */
#endif
struct list_head child_list;
struct list_head list;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 17acfa7..4e3d87d 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1645,6 +1645,11 @@ void pcibios_scan_phb(struct pci_controller *hose)
if (ppc_md.pcibios_fixup_phb)
ppc_md.pcibios_fixup_phb(hose);
+#ifdef CONFIG_PCI_IOV
+ if (ppc_md.pcibios_fixup_sriov)
+ ppc_md.pcibios_fixup_sriov(bus);
+#endif /* CONFIG_PCI_IOV */
+
/* Configure PCI Express settings */
if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
struct pci_bus *child;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 6d35ed9..ef279d3 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1601,6 +1601,59 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
#endif /* CONFIG_PCI_MSI */
+#ifdef CONFIG_PCI_IOV
+static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
+{
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct resource *res;
+ int i;
+ resource_size_t size;
+ struct pci_dn *pdn;
+
+ if (!pdev->is_physfn || pdev->is_added)
+ return;
+
+ hose = pci_bus_to_host(pdev->bus);
+ phb = hose->private_data;
+
+ pdn = pci_get_pdn(pdev);
+ pdn->max_vfs = 0;
+
+ for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++) {
+ res = &pdev->resource[i];
+ if (!res->flags || res->parent)
+ continue;
+ if (!pnv_pci_is_mem_pref_64(res->flags)) {
+ dev_warn(&pdev->dev, " Skipping expanding IOV BAR %pR on %s\n",
+ res, pci_name(pdev));
+ continue;
+ }
+
+ dev_dbg(&pdev->dev, " Fixing VF BAR[%d] %pR to\n", i, res);
+ size = pci_iov_resource_size(pdev, i);
+ res->end = res->start + size * phb->ioda.total_pe - 1;
+ dev_dbg(&pdev->dev, " %pR\n", res);
+ }
+ pdn->max_vfs = phb->ioda.total_pe;
+}
+
+static void pnv_pci_ioda_fixup_sriov(struct pci_bus *bus)
+{
+ struct pci_dev *pdev;
+ struct pci_bus *b;
+
+ list_for_each_entry(pdev, &bus->devices, bus_list) {
+ b = pdev->subordinate;
+
+ if (b)
+ pnv_pci_ioda_fixup_sriov(b);
+
+ pnv_pci_ioda_fixup_iov_resources(pdev);
+ }
+}
+#endif /* CONFIG_PCI_IOV */
+
/*
* This function is supposed to be called on basis of PE from top
* to bottom style. So the the I/O or MMIO segment assigned to
@@ -1983,6 +2036,9 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
+#ifdef CONFIG_PCI_IOV
+ ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_sriov;
+#endif /* CONFIG_PCI_IOV */
pci_add_flags(PCI_REASSIGN_ALL_RSRC);
/* Reset IODA tables to a clean state */
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 14/18] powerpc/powernv: Implement pcibios_iov_resource_size() on powernv
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
On PowerNV platform, the PF's IOV BAR size would be expanded, which is
different from the normal case.
This patch retrieves the VF BAR size by total size dividing the expanded number
of VFs.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/machdep.h | 1 +
arch/powerpc/kernel/pci-common.c | 8 ++++++++
arch/powerpc/platforms/powernv/pci-ioda.c | 15 +++++++++++++++
3 files changed, 24 insertions(+)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 15a13e6..d971874 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -259,6 +259,7 @@ struct machdep_calls {
resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *,
int resno,
resource_size_t align);
+ resource_size_t (*pcibios_iov_resource_size)(struct pci_dev *, int resno);
#endif /* CONFIG_PCI_IOV */
/* Called to shutdown machine specific hardware not already controlled
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 581e67b..a2a96d3 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -143,6 +143,14 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev,
return 0;
}
+
+resource_size_t pcibios_iov_resource_size(struct pci_dev *pdev, int resno)
+{
+ if (ppc_md.pcibios_iov_resource_size)
+ return ppc_md.pcibios_iov_resource_size(pdev, resno);
+
+ return 0;
+}
#endif /* CONFIG_PCI_IOV */
static resource_size_t pcibios_io_size(const struct pci_controller *hose)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 880d76d..f7abba3 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1847,6 +1847,20 @@ static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
return align;
}
+
+static resource_size_t pnv_pci_iov_resource_size(struct pci_dev *pdev, int resno)
+{
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+ resource_size_t size = 0;
+
+ if (!pdn->max_vfs)
+ return size;
+
+ size = resource_size(pdev->resource + resno);
+ do_div(size, pdn->max_vfs);
+
+ return size;
+}
#endif /* CONFIG_PCI_IOV */
/* Prevent enabling devices for which we couldn't properly
@@ -2058,6 +2072,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
#ifdef CONFIG_PCI_IOV
ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_sriov;
ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
+ ppc_md.pcibios_iov_resource_size = pnv_pci_iov_resource_size;
#endif /* CONFIG_PCI_IOV */
pci_add_flags(PCI_REASSIGN_ALL_RSRC);
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 13/18] powerpc/powernv: Implement pcibios_iov_resource_alignment() on powernv
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
This patch implements the pcibios_iov_resource_alignment() on powernv
platform.
On PowerNV platform, there are 3 cases for the IOV BAR:
1. initial state, the IOV BAR size is multiple times of VF BAR size
2. after expanded, the IOV BAR size is expanded to meet the M64 segment size
3. sizing stage, the IOV BAR is truncated to 0
pnv_pci_iov_resource_alignment() handle these three cases respectively.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/machdep.h | 3 +++
arch/powerpc/kernel/pci-common.c | 14 ++++++++++++++
arch/powerpc/platforms/powernv/pci-ioda.c | 20 ++++++++++++++++++++
3 files changed, 37 insertions(+)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 86d47ca..15a13e6 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -256,6 +256,9 @@ struct machdep_calls {
#ifdef CONFIG_PCI_IOV
void (*pcibios_fixup_sriov)(struct pci_bus *bus);
+ resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *,
+ int resno,
+ resource_size_t align);
#endif /* CONFIG_PCI_IOV */
/* Called to shutdown machine specific hardware not already controlled
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 4e3d87d..581e67b 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -131,6 +131,20 @@ void pcibios_reset_secondary_bus(struct pci_dev *dev)
pci_reset_secondary_bus(dev);
}
+#ifdef CONFIG_PCI_IOV
+resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev,
+ int resno,
+ resource_size_t align)
+{
+ if (ppc_md.pcibios_iov_resource_alignment)
+ return ppc_md.pcibios_iov_resource_alignment(pdev,
+ resno,
+ align);
+
+ return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
static resource_size_t pcibios_io_size(const struct pci_controller *hose)
{
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index ef279d3..880d76d 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1830,6 +1830,25 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
return phb->ioda.io_segsize;
}
+#ifdef CONFIG_PCI_IOV
+static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
+ int resno,
+ resource_size_t align)
+{
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+ resource_size_t iov_align;
+
+ iov_align = resource_size(&pdev->resource[resno]);
+ if (iov_align)
+ return iov_align;
+
+ if (pdn->max_vfs)
+ return pdn->max_vfs * align;
+
+ return align;
+}
+#endif /* CONFIG_PCI_IOV */
+
/* Prevent enabling devices for which we couldn't properly
* assign a PE
*/
@@ -2038,6 +2057,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
#ifdef CONFIG_PCI_IOV
ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_sriov;
+ ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
#endif /* CONFIG_PCI_IOV */
pci_add_flags(PCI_REASSIGN_ALL_RSRC);
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 15/18] powerpc/powernv: Shift VF resource with an offset
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
On PowrNV platform, resource position in M64 implies the PE# the resource
belongs to. In some particular case, adjustment of a resource is necessary to
locate it to a correct position in M64.
This patch introduces a function to shift the 'real' PF IOV BAR address
according to an offset.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/platforms/powernv/pci-ioda.c | 31 +++++++++++++++++++++++++++++
1 file changed, 31 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f7abba3..5034a3c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -14,6 +14,7 @@
#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/crash_dump.h>
+#include <linux/pci_regs.h>
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/string.h>
@@ -644,6 +645,36 @@ static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
return 10;
}
+#ifdef CONFIG_PCI_IOV
+static void pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
+{
+ struct pci_dn *pdn = pci_get_pdn(dev);
+ int i;
+ struct resource *res;
+ resource_size_t size;
+
+ if (!dev->is_physfn)
+ return;
+
+ for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++) {
+ res = &dev->resource[i];
+ if (!res->flags || !res->parent)
+ continue;
+
+ if (!pnv_pci_is_mem_pref_64(res->flags))
+ continue;
+
+ dev_info(&dev->dev, " Shifting VF BAR %pR to\n", res);
+ size = pci_iov_resource_size(dev, i);
+ res->start += size*offset;
+
+ dev_info(&dev->dev, " %pR\n", res);
+ pci_update_resource(dev, i);
+ }
+ pdn->max_vfs -= offset;
+}
+#endif /* CONFIG_PCI_IOV */
+
#if 0
static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
{
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 16/18] powerpc/powernv: Allocate VF PE
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
VFs are created, when pci device is enabled.
This patch tries best to assign maximum resources and PEs for VF when pci
device is enabled. Enough M64 assigned to cover the IOV BAR, IOV BAR is
shifted to meet the PE# indicated by M64. VF's pdn->pdev and pdn->pe_number
are fixed.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pci-bridge.h | 4 +
arch/powerpc/kernel/pci_dn.c | 11 +
arch/powerpc/platforms/powernv/pci-ioda.c | 460 ++++++++++++++++++++++++++++-
arch/powerpc/platforms/powernv/pci.c | 18 ++
arch/powerpc/platforms/powernv/pci.h | 7 +
5 files changed, 487 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index ff26045..8d8d40a 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -174,6 +174,10 @@ struct pci_dn {
int pe_number;
#ifdef CONFIG_PCI_IOV
u16 max_vfs; /* number of VFs IOV BAR expended */
+ u16 vf_pes; /* VF PE# under this PF */
+ int offset; /* PE# for the first VF PE */
+#define IODA_INVALID_M64 (-1)
+ int m64_wins[PCI_SRIOV_NUM_BARS];
#endif /* CONFIG_PCI_IOV */
#endif
struct list_head child_list;
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index fa966ae..dbc2f55 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -216,6 +216,17 @@ void remove_dev_pci_info(struct pci_dev *pdev)
struct pci_dn *pdn, *tmp;
int i;
+ /*
+ * VF and VF PE is create/released dynamicly, which we need to
+ * bind/unbind them. Otherwise when re-enable SRIOV, the VF and VF PE
+ * would be mismatched.
+ */
+ if (pdev->is_virtfn) {
+ pdn = pci_get_pdn(pdev);
+ pdn->pe_number = IODA_INVALID_PE;
+ return;
+ }
+
/* Only support IOV PF for now */
if (!pdev->is_physfn)
return;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5034a3c..649f49d4 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -45,6 +45,9 @@
#include "powernv.h"
#include "pci.h"
+/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
+#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8)
+
static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
const char *fmt, ...)
{
@@ -57,11 +60,18 @@ static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
vaf.fmt = fmt;
vaf.va = &args;
- if (pe->pdev)
+ if (pe->flags & PNV_IODA_PE_DEV)
strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix));
- else
+ else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
sprintf(pfix, "%04x:%02x ",
pci_domain_nr(pe->pbus), pe->pbus->number);
+#ifdef CONFIG_PCI_IOV
+ else if (pe->flags & PNV_IODA_PE_VF)
+ sprintf(pfix, "%04x:%02x:%2x.%d",
+ pci_domain_nr(pe->parent_dev->bus),
+ (pe->rid & 0xff00) >> 8,
+ PCI_SLOT(pe->rid), PCI_FUNC(pe->rid));
+#endif /* CONFIG_PCI_IOV*/
printk("%spci %s: [PE# %.3d] %pV",
level, pfix, pe->pe_number, &vaf);
@@ -508,6 +518,89 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
}
#endif /* CONFIG_PCI_MSI */
+#ifdef CONFIG_PCI_IOV
+static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
+{
+ struct pci_dev *parent;
+ uint8_t bcomp, dcomp, fcomp;
+ int64_t rc;
+ long rid_end, rid;
+
+ /* Currently, we just deconfigure VF PE. Bus PE will always there.*/
+ if (pe->pbus) {
+ int count;
+
+ dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
+ fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
+ parent = pe->pbus->self;
+ if (pe->flags & PNV_IODA_PE_BUS_ALL)
+ count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+ else
+ count = 1;
+
+ switch(count) {
+ case 1: bcomp = OpalPciBusAll; break;
+ case 2: bcomp = OpalPciBus7Bits; break;
+ case 4: bcomp = OpalPciBus6Bits; break;
+ case 8: bcomp = OpalPciBus5Bits; break;
+ case 16: bcomp = OpalPciBus4Bits; break;
+ case 32: bcomp = OpalPciBus3Bits; break;
+ default:
+ pr_err("%s: Number of subordinate busses %d"
+ " unsupported\n",
+ pci_is_root_bus(pe->pbus)?"root bus":pci_name(pe->pbus->self),
+ count);
+ /* Do an exact match only */
+ bcomp = OpalPciBusAll;
+ }
+ rid_end = pe->rid + (count << 8);
+ } else {
+ if (pe->flags & PNV_IODA_PE_VF)
+ parent = pe->parent_dev;
+ else
+ parent = pe->pdev->bus->self;
+ bcomp = OpalPciBusAll;
+ dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
+ fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
+ rid_end = pe->rid + 1;
+ }
+
+ /* Clear the reverse map */
+ for (rid = pe->rid; rid < rid_end; rid++)
+ phb->ioda.pe_rmap[rid] = 0;
+
+ /* Release from all parents PELT-V */
+ while (parent) {
+ struct pci_dn *pdn = pci_get_pdn(parent);
+ if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+ rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
+ pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+ /* XXX What to do in case of error ? */
+ }
+ parent = parent->bus->self;
+ }
+
+ opal_pci_eeh_freeze_set(phb->opal_id, pe->pe_number,
+ OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+ /* Dissociate PE in PELT */
+ rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+ pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+ if (rc)
+ pe_warn(pe, "OPAL error %ld remove self from PELTV\n", rc);
+ rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
+ bcomp, dcomp, fcomp, OPAL_UNMAP_PE);
+ if (rc)
+ pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
+
+ pe->pbus = NULL;
+ pe->pdev = NULL;
+ pe->parent_dev = NULL;
+
+ return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
{
struct pci_dev *parent;
@@ -536,13 +629,19 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
default:
pr_err("%s: Number of subordinate busses %d"
" unsupported\n",
- pci_name(pe->pbus->self), count);
+ pci_is_root_bus(pe->pbus)?"root bus":pci_name(pe->pbus->self),
+ count);
/* Do an exact match only */
bcomp = OpalPciBusAll;
}
rid_end = pe->rid + (count << 8);
} else {
- parent = pe->pdev->bus->self;
+#ifdef CONFIG_PCI_IOV
+ if (pe->flags & PNV_IODA_PE_VF)
+ parent = pe->parent_dev;
+ else
+#endif /* CONFIG_PCI_IOV */
+ parent = pe->pdev->bus->self;
bcomp = OpalPciBusAll;
dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
@@ -878,6 +977,314 @@ static void pnv_pci_ioda_setup_PEs(void)
}
}
+#ifdef CONFIG_PCI_IOV
+static int pnv_pci_vf_release_m64(struct pci_dev *pdev)
+{
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pci_dn *pdn;
+ int i;
+
+ bus = pdev->bus;
+ hose = pci_bus_to_host(bus);
+ phb = hose->private_data;
+ pdn = pci_get_pdn(pdev);
+
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+ if (pdn->m64_wins[i] == IODA_INVALID_M64)
+ continue;
+ opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 0);
+ clear_bit(pdn->m64_wins[i], &phb->ioda.m64_bar_alloc);
+ pdn->m64_wins[i] = IODA_INVALID_M64;
+ }
+
+ return 0;
+}
+
+static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
+{
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pci_dn *pdn;
+ unsigned int win;
+ struct resource *res;
+ int i;
+ int64_t rc;
+
+ bus = pdev->bus;
+ hose = pci_bus_to_host(bus);
+ phb = hose->private_data;
+ pdn = pci_get_pdn(pdev);
+
+ /* Initialize the m64_wins to IODA_INVALID_M64 */
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
+ pdn->m64_wins[i] = IODA_INVALID_M64;
+
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+ res = pdev->resource + PCI_IOV_RESOURCES + i;
+ if (!res->flags || !res->parent)
+ continue;
+
+ if (!pnv_pci_is_mem_pref_64(res->flags))
+ continue;
+
+ do {
+ win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
+ phb->ioda.m64_bar_idx + 1, 0);
+
+ if (win >= phb->ioda.m64_bar_idx + 1)
+ goto m64_failed;
+ } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+
+ pdn->m64_wins[i] = win;
+
+ /* Map the M64 here */
+ rc = opal_pci_set_phb_mem_window(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE,
+ pdn->m64_wins[i],
+ res->start,
+ 0, /* unused */
+ resource_size(res));
+ if (rc != OPAL_SUCCESS) {
+ pr_err("Failed to map M64 BAR #%d: %lld\n", win, rc);
+ goto m64_failed;
+ }
+
+ rc = opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 1);
+ if (rc != OPAL_SUCCESS) {
+ pr_err("Failed to enable M64 BAR #%d: %llx\n", win, rc);
+ goto m64_failed;
+ }
+ }
+ return 0;
+
+m64_failed:
+ pnv_pci_vf_release_m64(pdev);
+ return -EBUSY;
+}
+
+static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
+{
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct iommu_table *tbl;
+ unsigned long addr;
+ int64_t rc;
+
+ bus = dev->bus;
+ hose = pci_bus_to_host(bus);
+ phb = hose->private_data;
+ tbl = pe->tce32_table;
+ addr = tbl->it_base;
+
+ opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
+ pe->pe_number << 1, 1, __pa(addr),
+ 0, 0x1000);
+
+ rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+ pe->pe_number,
+ (pe->pe_number << 1) + 1,
+ pe->tce_bypass_base,
+ 0);
+ if (rc)
+ pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
+
+ iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
+ free_pages(addr, get_order(TCE32_TABLE_SIZE));
+ pe->tce32_table = NULL;
+}
+
+static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
+{
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pnv_ioda_pe *pe, *pe_n;
+ struct pci_dn *pdn;
+
+ bus = pdev->bus;
+ hose = pci_bus_to_host(bus);
+ phb = hose->private_data;
+
+ if (!pdev->is_physfn)
+ return;
+
+ pdn = pci_get_pdn(pdev);
+ list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
+ if (pe->parent_dev != pdev)
+ continue;
+
+ pnv_pci_ioda2_release_dma_pe(pdev, pe);
+
+ /* Remove from list */
+ mutex_lock(&phb->ioda.pe_list_mutex);
+ list_del(&pe->list);
+ mutex_unlock(&phb->ioda.pe_list_mutex);
+
+ pnv_ioda_deconfigure_pe(phb, pe);
+
+ pnv_ioda_free_pe(phb, pe->pe_number);
+ }
+}
+
+void pnv_pci_sriov_disable(struct pci_dev *pdev)
+{
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pci_dn *pdn;
+ struct pci_sriov *iov;
+ u16 vf_num;
+
+ bus = pdev->bus;
+ hose = pci_bus_to_host(bus);
+ phb = hose->private_data;
+ pdn = pci_get_pdn(pdev);
+ iov = pdev->sriov;
+ vf_num = pdn->vf_pes;
+
+ /* Release VF PEs */
+ pnv_ioda_release_vf_PE(pdev);
+
+ if (phb->type == PNV_PHB_IODA2) {
+ pnv_pci_vf_resource_shift(pdev, -pdn->offset);
+
+ /* Release M64 BARs */
+ pnv_pci_vf_release_m64(pdev);
+
+ /* Release PE numbers */
+ bitmap_clear(phb->ioda.pe_alloc, pdn->offset, vf_num);
+ pdn->offset = 0;
+ }
+
+ return;
+}
+
+static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe);
+static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 vf_num)
+{
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pnv_ioda_pe *pe;
+ int pe_num;
+ u16 vf_index;
+ struct pci_dn *pdn;
+
+ bus = pdev->bus;
+ hose = pci_bus_to_host(bus);
+ phb = hose->private_data;
+ pdn = pci_get_pdn(pdev);
+
+ if (!pdev->is_physfn)
+ return;
+
+ /* Reserve PE for each VF */
+ for (vf_index = 0; vf_index < vf_num; vf_index++) {
+ pe_num = pdn->offset + vf_index;
+
+ pe = &phb->ioda.pe_array[pe_num];
+ pe->pe_number = pe_num;
+ pe->phb = phb;
+ pe->flags = PNV_IODA_PE_VF;
+ pe->pbus = NULL;
+ pe->parent_dev = pdev;
+ pe->tce32_seg = -1;
+ pe->mve_number = -1;
+ pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
+ pci_iov_virtfn_devfn(pdev, vf_index);
+
+ pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%d\n",
+ hose->global_number, pdev->bus->number,
+ PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
+ PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);
+
+ if (pnv_ioda_configure_pe(phb, pe)) {
+ /* XXX What do we do here ? */
+ if (pe_num)
+ pnv_ioda_free_pe(phb, pe_num);
+ pe->pdev = NULL;
+ continue;
+ }
+
+ pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
+ 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);
+
+ pnv_pci_ioda2_setup_dma_pe(phb, pe);
+
+ }
+}
+
+int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 vf_num)
+{
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ struct pnv_phb *phb;
+ struct pci_dn *pdn;
+ int ret;
+
+ bus = pdev->bus;
+ hose = pci_bus_to_host(bus);
+ phb = hose->private_data;
+ pdn = pci_get_pdn(pdev);
+
+ if (phb->type == PNV_PHB_IODA2) {
+ /* Calculate available PE for required VFs */
+ mutex_lock(&phb->ioda.pe_alloc_mutex);
+try_again:
+ pdn->offset = bitmap_find_next_zero_area(
+ phb->ioda.pe_alloc, phb->ioda.total_pe,
+ 0, vf_num, 0);
+ if (pdn->offset >= phb->ioda.total_pe) {
+ vf_num--;
+ if (vf_num)
+ goto try_again;
+
+ mutex_unlock(&phb->ioda.pe_alloc_mutex);
+ pr_info("Failed to enable VF\n");
+ pdn->offset = 0;
+ return -EBUSY;
+ }
+ bitmap_set(phb->ioda.pe_alloc, pdn->offset, vf_num);
+ pdn->vf_pes = vf_num;
+ mutex_unlock(&phb->ioda.pe_alloc_mutex);
+
+ /* Assign M64 BAR accordingly */
+ ret = pnv_pci_vf_assign_m64(pdev);
+ if (ret) {
+ pr_info("No enough M64 resource\n");
+ goto m64_failed;
+ }
+
+ /* Do some magic shift */
+ pnv_pci_vf_resource_shift(pdev, pdn->offset);
+ }
+
+ /* Setup VF PEs */
+ pnv_ioda_setup_vf_PE(pdev, vf_num);
+
+ return 0;
+
+m64_failed:
+ bitmap_clear(phb->ioda.pe_alloc, pdn->offset, vf_num);
+ pdn->offset = 0;
+
+ return ret;
+}
+#endif /* CONFIG_PCI_IOV */
+
static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
{
struct pci_dn *pdn = pci_get_pdn(pdev);
@@ -1070,9 +1477,6 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
int64_t rc;
void *addr;
- /* 256M DMA window, 4K TCE pages, 8 bytes TCE */
-#define TCE32_TABLE_SIZE ((0x10000000 / 0x1000) * 8)
-
/* XXX FIXME: Handle 64-bit only DMA devices */
/* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
/* XXX FIXME: Allocate multi-level tables on PHB3 */
@@ -1135,12 +1539,19 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
TCE_PCI_SWINV_PAIR);
}
iommu_init_table(tbl, phb->hose->node);
- iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
- if (pe->pdev)
+ if (pe->flags & PNV_IODA_PE_DEV) {
+ iommu_register_group(tbl, phb->hose->global_number,
+ pe->pe_number);
set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
- else
+ } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
+ iommu_register_group(tbl, phb->hose->global_number,
+ pe->pe_number);
pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+ } else if (pe->flags & PNV_IODA_PE_VF) {
+ iommu_register_group(tbl, phb->hose->global_number,
+ pe->pe_number);
+ }
return;
fail:
@@ -1267,12 +1678,19 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
}
iommu_init_table(tbl, phb->hose->node);
- iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
- if (pe->pdev)
+ if (pe->flags & PNV_IODA_PE_DEV) {
+ iommu_register_group(tbl, phb->hose->global_number,
+ pe->pe_number);
set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
- else
+ } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
+ iommu_register_group(tbl, phb->hose->global_number,
+ pe->pe_number);
pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+ } else if (pe->flags & PNV_IODA_PE_VF) {
+ iommu_register_group(tbl, phb->hose->global_number,
+ pe->pe_number);
+ }
/* Also create a bypass window */
pnv_pci_ioda2_setup_bypass_pe(phb, pe);
@@ -1915,9 +2333,22 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev)
if (!pdn || pdn->pe_number == IODA_INVALID_PE)
return -EINVAL;
+#ifdef CONFIG_PCI_IOV
+ if (dev->is_physfn)
+ pnv_pci_sriov_enable(dev, pci_sriov_get_totalvfs(dev));
+#endif
return 0;
}
+static void pnv_pci_disable_device_hook(struct pci_dev *dev)
+{
+#ifdef CONFIG_PCI_IOV
+ if (dev->is_physfn)
+ pnv_pci_sriov_disable(dev);
+#endif
+ return;
+}
+
static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
u32 devfn)
{
@@ -1983,6 +2414,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
phb->hub_id = hub_id;
phb->opal_id = phb_id;
phb->type = ioda_type;
+ mutex_init(&phb->ioda.pe_alloc_mutex);
/* Detect specific models for error handling */
if (of_device_is_compatible(np, "ibm,p7ioc-pciex"))
@@ -2043,6 +2475,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
INIT_LIST_HEAD(&phb->ioda.pe_dma_list);
INIT_LIST_HEAD(&phb->ioda.pe_list);
+ mutex_init(&phb->ioda.pe_list_mutex);
/* Calculate how many 32-bit TCE segments we have */
phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;
@@ -2098,6 +2531,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
*/
ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
+ ppc_md.pcibios_disable_device_hook = pnv_pci_disable_device_hook;
ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
#ifdef CONFIG_PCI_IOV
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index f8dbb3f..580c3d7 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -716,6 +716,24 @@ 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 pci_dn *pdn;
+
+ /* Fix the VF pdn PE number */
+ if (pdev->is_virtfn) {
+ pdn = pci_get_pdn(pdev);
+ WARN_ON(pdn->pe_number != IODA_INVALID_PE);
+ list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+ if (pe->rid == ((pdev->bus->number << 8) |
+ (pdev->devfn & 0xff))) {
+ pdn->pe_number = pe->pe_number;
+ pe->pdev = pdev;
+ break;
+ }
+ }
+ }
+#endif /* CONFIG_PCI_IOV */
/* If we have no phb structure, try to setup a fallback based on
* the device-tree (RTAS PCI for example)
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 0f24a14..3556984 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -23,6 +23,7 @@ enum pnv_phb_model {
#define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */
#define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */
#define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */
+#define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */
/* Data associated with a PE, including IOMMU tracking etc.. */
struct pnv_phb;
@@ -34,6 +35,9 @@ struct pnv_ioda_pe {
* entire bus (& children). In the former case, pdev
* is populated, in the later case, pbus is.
*/
+#ifdef CONFIG_PCI_IOV
+ struct pci_dev *parent_dev;
+#endif
struct pci_dev *pdev;
struct pci_bus *pbus;
@@ -165,6 +169,8 @@ struct pnv_phb {
/* PE allocation bitmap */
unsigned long *pe_alloc;
+ /* PE allocation mutex */
+ struct mutex pe_alloc_mutex;
/* M32 & IO segment maps */
unsigned int *m32_segmap;
@@ -179,6 +185,7 @@ struct pnv_phb {
* on the sequence of creation
*/
struct list_head pe_list;
+ struct mutex pe_list_mutex;
/* Reverse map of PEs, will have to extend if
* we are to support more than 256 PEs, indexed
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 17/18] powerpc/powernv: Expanding IOV BAR, with m64_per_iov supported
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
M64 aperture size is limited on PHB3. When the IOV BAR is too big, this will
exceed the limitation and failed to be assigned.
This patch introduce a different expanding based on the IOV BAR size:
IOV BAR size is smaller than 64M, expand to total_pe.
IOV BAR size is bigger than 64M, roundup power2.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pci-bridge.h | 2 ++
arch/powerpc/platforms/powernv/pci-ioda.c | 31 +++++++++++++++++++++++++++--
2 files changed, 31 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 8d8d40a..a336c7a 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -176,6 +176,8 @@ struct pci_dn {
u16 max_vfs; /* number of VFs IOV BAR expended */
u16 vf_pes; /* VF PE# under this PF */
int offset; /* PE# for the first VF PE */
+#define M64_PER_IOV 4
+ int m64_per_iov;
#define IODA_INVALID_M64 (-1)
int m64_wins[PCI_SRIOV_NUM_BARS];
#endif /* CONFIG_PCI_IOV */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 649f49d4..a4e78ab 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2059,6 +2059,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
int i;
resource_size_t size;
struct pci_dn *pdn;
+ int mul, total_vfs;
if (!pdev->is_physfn || pdev->is_added)
return;
@@ -2069,6 +2070,32 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
pdn = pci_get_pdn(pdev);
pdn->max_vfs = 0;
+ total_vfs = pci_sriov_get_totalvfs(pdev);
+ pdn->m64_per_iov = 1;
+ mul = phb->ioda.total_pe;
+
+ for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++) {
+ res = &pdev->resource[i];
+ if (!res->flags || res->parent)
+ continue;
+ if (!pnv_pci_is_mem_pref_64(res->flags)) {
+ dev_warn(&pdev->dev, " non M64 IOV BAR %pR on %s\n",
+ res, pci_name(pdev));
+ continue;
+ }
+
+ size = pci_iov_resource_size(pdev, i);
+
+ /* bigger than 64M */
+ if (size > (1 << 26)) {
+ dev_info(&pdev->dev, "PowerNV: VF BAR[%d] size "
+ "is bigger than 64M, roundup power2\n", i);
+ pdn->m64_per_iov = M64_PER_IOV;
+ mul = __roundup_pow_of_two(total_vfs);
+ break;
+ }
+ }
+
for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++) {
res = &pdev->resource[i];
if (!res->flags || res->parent)
@@ -2081,10 +2108,10 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
dev_dbg(&pdev->dev, " Fixing VF BAR[%d] %pR to\n", i, res);
size = pci_iov_resource_size(pdev, i);
- res->end = res->start + size * phb->ioda.total_pe - 1;
+ res->end = res->start + size * mul - 1;
dev_dbg(&pdev->dev, " %pR\n", res);
}
- pdn->max_vfs = phb->ioda.total_pe;
+ pdn->max_vfs = mul;
}
static void pnv_pci_ioda_fixup_sriov(struct pci_bus *bus)
--
1.7.9.5
^ permalink raw reply related
* [PATCH V9 18/18] powerpc/powernv: Group VF PE when IOV BAR is big on PHB3
From: Wei Yang @ 2014-11-02 15:41 UTC (permalink / raw)
To: bhelgaas, benh, gwshan, linux-pci, linuxppc-dev; +Cc: Wei Yang
In-Reply-To: <1414942894-17034-1-git-send-email-weiyang@linux.vnet.ibm.com>
When IOV BAR is big, each of it is covered by 4 M64 window. This leads to
several VF PE sits in one PE in terms of M64.
This patch group VF PEs according to the M64 allocation.
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pci-bridge.h | 2 +-
arch/powerpc/platforms/powernv/pci-ioda.c | 188 +++++++++++++++++++++++------
2 files changed, 149 insertions(+), 41 deletions(-)
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index a336c7a..aaf5a31 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -179,7 +179,7 @@ struct pci_dn {
#define M64_PER_IOV 4
int m64_per_iov;
#define IODA_INVALID_M64 (-1)
- int m64_wins[PCI_SRIOV_NUM_BARS];
+ int m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV];
#endif /* CONFIG_PCI_IOV */
#endif
struct list_head child_list;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index a4e78ab..ea02131 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -984,26 +984,27 @@ static int pnv_pci_vf_release_m64(struct pci_dev *pdev)
struct pci_controller *hose;
struct pnv_phb *phb;
struct pci_dn *pdn;
- int i;
+ int i, j;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
phb = hose->private_data;
pdn = pci_get_pdn(pdev);
- for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
- if (pdn->m64_wins[i] == IODA_INVALID_M64)
- continue;
- opal_pci_phb_mmio_enable(phb->opal_id,
- OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 0);
- clear_bit(pdn->m64_wins[i], &phb->ioda.m64_bar_alloc);
- pdn->m64_wins[i] = IODA_INVALID_M64;
- }
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
+ for (j = 0; j < M64_PER_IOV; j++) {
+ if (pdn->m64_wins[i][j] == IODA_INVALID_M64)
+ continue;
+ opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0);
+ clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc);
+ pdn->m64_wins[i][j] = IODA_INVALID_M64;
+ }
return 0;
}
-static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
+static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 vf_num)
{
struct pci_bus *bus;
struct pci_controller *hose;
@@ -1011,17 +1012,33 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
struct pci_dn *pdn;
unsigned int win;
struct resource *res;
- int i;
+ int i, j;
int64_t rc;
+ int total_vfs;
+ resource_size_t size, start;
+ int pe_num;
+ int vf_groups;
+ int vf_per_group;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
phb = hose->private_data;
pdn = pci_get_pdn(pdev);
+ total_vfs = pci_sriov_get_totalvfs(pdev);
/* Initialize the m64_wins to IODA_INVALID_M64 */
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
- pdn->m64_wins[i] = IODA_INVALID_M64;
+ for (j = 0; j < M64_PER_IOV; j++)
+ pdn->m64_wins[i][j] = IODA_INVALID_M64;
+
+ if (pdn->m64_per_iov == M64_PER_IOV) {
+ vf_groups = (vf_num <= M64_PER_IOV) ? vf_num: M64_PER_IOV;
+ vf_per_group = (vf_num <= M64_PER_IOV)? 1:
+ __roundup_pow_of_two(vf_num) / pdn->m64_per_iov;
+ } else {
+ vf_groups = 1;
+ vf_per_group = 1;
+ }
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = pdev->resource + PCI_IOV_RESOURCES + i;
@@ -1031,33 +1048,61 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
if (!pnv_pci_is_mem_pref_64(res->flags))
continue;
- do {
- win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
- phb->ioda.m64_bar_idx + 1, 0);
-
- if (win >= phb->ioda.m64_bar_idx + 1)
- goto m64_failed;
- } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+ for (j = 0; j < vf_groups; j++) {
+ do {
+ win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
+ phb->ioda.m64_bar_idx + 1, 0);
+
+ if (win >= phb->ioda.m64_bar_idx + 1)
+ goto m64_failed;
+ } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+
+ pdn->m64_wins[i][j] = win;
+
+ if (pdn->m64_per_iov == M64_PER_IOV) {
+ size = pci_iov_resource_size(pdev,
+ PCI_IOV_RESOURCES + i);
+ size = size * vf_per_group;
+ start = res->start + size * j;
+ } else {
+ size = resource_size(res);
+ start = res->start;
+ }
- pdn->m64_wins[i] = win;
+ /* Map the M64 here */
+ if (pdn->m64_per_iov == M64_PER_IOV) {
+ pe_num = pdn->offset + j;
+ rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+ pe_num, OPAL_M64_WINDOW_TYPE,
+ pdn->m64_wins[i][j], 0);
+ }
- /* Map the M64 here */
- rc = opal_pci_set_phb_mem_window(phb->opal_id,
+ rc = opal_pci_set_phb_mem_window(phb->opal_id,
OPAL_M64_WINDOW_TYPE,
- pdn->m64_wins[i],
- res->start,
+ pdn->m64_wins[i][j],
+ start,
0, /* unused */
- resource_size(res));
- if (rc != OPAL_SUCCESS) {
- pr_err("Failed to map M64 BAR #%d: %lld\n", win, rc);
- goto m64_failed;
- }
+ size);
- rc = opal_pci_phb_mmio_enable(phb->opal_id,
- OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 1);
- if (rc != OPAL_SUCCESS) {
- pr_err("Failed to enable M64 BAR #%d: %llx\n", win, rc);
- goto m64_failed;
+
+ if (rc != OPAL_SUCCESS) {
+ pr_err("Failed to set M64 BAR #%d: %lld\n",
+ win, rc);
+ goto m64_failed;
+ }
+
+ if (pdn->m64_per_iov == M64_PER_IOV)
+ rc = opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2);
+ else
+ rc = opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1);
+
+ if (rc != OPAL_SUCCESS) {
+ pr_err("Failed to enable M64 BAR #%d: %llx\n",
+ win, rc);
+ goto m64_failed;
+ }
}
}
return 0;
@@ -1099,22 +1144,53 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
pe->tce32_table = NULL;
}
-static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
+static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 vf_num)
{
struct pci_bus *bus;
struct pci_controller *hose;
struct pnv_phb *phb;
struct pnv_ioda_pe *pe, *pe_n;
struct pci_dn *pdn;
+ u16 vf_index;
+ int64_t rc;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
phb = hose->private_data;
+ pdn = pci_get_pdn(pdev);
if (!pdev->is_physfn)
return;
- pdn = pci_get_pdn(pdev);
+ if (pdn->m64_per_iov == M64_PER_IOV && vf_num > M64_PER_IOV) {
+ int vf_group;
+ int vf_per_group;
+ int vf_index1;
+
+ vf_per_group = __roundup_pow_of_two(vf_num) / pdn->m64_per_iov;
+
+ for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++)
+ for (vf_index = vf_group * vf_per_group;
+ vf_index < (vf_group + 1) * vf_per_group &&
+ vf_index < vf_num;
+ vf_index++)
+ for (vf_index1 = vf_group * vf_per_group;
+ vf_index1 < (vf_group + 1) * vf_per_group &&
+ vf_index1 < vf_num;
+ vf_index1++){
+
+ rc = opal_pci_set_peltv(phb->opal_id,
+ pdn->offset + vf_index,
+ pdn->offset + vf_index1,
+ OPAL_REMOVE_PE_FROM_DOMAIN);
+
+ if (rc)
+ pr_warn("%s: Failed to unlink same"
+ " group PE#%d(%lld)\n", __func__,
+ pdn->offset + vf_index1, rc);
+ }
+ }
+
list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
if (pe->parent_dev != pdev)
continue;
@@ -1149,10 +1225,11 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev)
vf_num = pdn->vf_pes;
/* Release VF PEs */
- pnv_ioda_release_vf_PE(pdev);
+ pnv_ioda_release_vf_PE(pdev, vf_num);
if (phb->type == PNV_PHB_IODA2) {
- pnv_pci_vf_resource_shift(pdev, -pdn->offset);
+ if (pdn->m64_per_iov == 1)
+ pnv_pci_vf_resource_shift(pdev, -pdn->offset);
/* Release M64 BARs */
pnv_pci_vf_release_m64(pdev);
@@ -1176,6 +1253,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 vf_num)
int pe_num;
u16 vf_index;
struct pci_dn *pdn;
+ int64_t rc;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
@@ -1223,7 +1301,36 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 vf_num)
mutex_unlock(&phb->ioda.pe_list_mutex);
pnv_pci_ioda2_setup_dma_pe(phb, pe);
+ }
+ if (pdn->m64_per_iov == M64_PER_IOV && vf_num > M64_PER_IOV) {
+ int vf_group;
+ int vf_per_group;
+ int vf_index1;
+
+ vf_per_group = __roundup_pow_of_two(vf_num) / pdn->m64_per_iov;
+
+ for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++)
+ for (vf_index = vf_group * vf_per_group;
+ vf_index < (vf_group + 1) * vf_per_group &&
+ vf_index < vf_num;
+ vf_index++)
+ for (vf_index1 = vf_group * vf_per_group;
+ vf_index1 < (vf_group + 1) * vf_per_group &&
+ vf_index1 < vf_num;
+ vf_index1++) {
+
+ rc = opal_pci_set_peltv(phb->opal_id,
+ pdn->offset + vf_index,
+ pdn->offset + vf_index1,
+ OPAL_ADD_PE_TO_DOMAIN);
+
+ if (rc)
+ pr_warn("%s: Failed to link same "
+ "group PE#%d(%lld)\n",
+ __func__,
+ pdn->offset + vf_index1, rc);
+ }
}
}
@@ -1262,14 +1369,15 @@ try_again:
mutex_unlock(&phb->ioda.pe_alloc_mutex);
/* Assign M64 BAR accordingly */
- ret = pnv_pci_vf_assign_m64(pdev);
+ ret = pnv_pci_vf_assign_m64(pdev, vf_num);
if (ret) {
pr_info("No enough M64 resource\n");
goto m64_failed;
}
/* Do some magic shift */
- pnv_pci_vf_resource_shift(pdev, pdn->offset);
+ if (pdn->m64_per_iov == 1)
+ pnv_pci_vf_resource_shift(pdev, pdn->offset);
}
/* Setup VF PEs */
--
1.7.9.5
^ permalink raw reply related
* [PATCH V3 1/2] powerpc/mm/thp: Remove code duplication
From: Aneesh Kumar K.V @ 2014-11-02 15:45 UTC (permalink / raw)
To: benh, paulus, mpe; +Cc: linuxppc-dev, Aneesh Kumar K.V
Rename invalidate_old_hpte to flush_hash_hugepage and use that in
other places.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
Changes from V2:
* split the patch for easier review
* Rebase to latest linus tree
arch/powerpc/include/asm/tlbflush.h | 3 +-
arch/powerpc/mm/hash_utils_64.c | 52 ++++++++++++++++++++++++++++++
arch/powerpc/mm/hugepage-hash64.c | 54 ++-----------------------------
arch/powerpc/mm/pgtable_64.c | 64 ++++++-------------------------------
4 files changed, 65 insertions(+), 108 deletions(-)
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 2def01ed0cb2..afe57427ef8e 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -127,7 +127,8 @@ static inline void arch_leave_lazy_mmu_mode(void)
extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
int ssize, int local);
extern void flush_hash_range(unsigned long number, int local);
-
+extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+ pmd_t *pmdp, unsigned int psize, int ssize);
static inline void local_flush_tlb_mm(struct mm_struct *mm)
{
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d5339a3b9945..26517ea34970 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1315,6 +1315,58 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
#endif
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+ pmd_t *pmdp, unsigned int psize, int ssize)
+{
+ int i, max_hpte_count, valid;
+ unsigned long s_addr;
+ unsigned char *hpte_slot_array;
+ unsigned long hidx, shift, vpn, hash, slot;
+
+ s_addr = addr & HPAGE_PMD_MASK;
+ hpte_slot_array = get_hpte_slot_array(pmdp);
+ /*
+ * IF we try to do a HUGE PTE update after a withdraw is done.
+ * we will find the below NULL. This happens when we do
+ * split_huge_page_pmd
+ */
+ if (!hpte_slot_array)
+ return;
+
+ if (ppc_md.hugepage_invalidate)
+ return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+ psize, ssize);
+ /*
+ * No bluk hpte removal support, invalidate each entry
+ */
+ shift = mmu_psize_defs[psize].shift;
+ max_hpte_count = HPAGE_PMD_SIZE >> shift;
+ for (i = 0; i < max_hpte_count; i++) {
+ /*
+ * 8 bits per each hpte entries
+ * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+ */
+ valid = hpte_valid(hpte_slot_array, i);
+ if (!valid)
+ continue;
+ hidx = hpte_hash_index(hpte_slot_array, i);
+
+ /* get the vpn */
+ addr = s_addr + (i * (1ul << shift));
+ vpn = hpt_vpn(addr, vsid, ssize);
+ hash = hpt_hash(vpn, shift, ssize);
+ if (hidx & _PTEIDX_SECONDARY)
+ hash = ~hash;
+
+ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot += hidx & _PTEIDX_GROUP_IX;
+ ppc_md.hpte_invalidate(slot, vpn, psize,
+ MMU_PAGE_16M, ssize, 0);
+ }
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
void flush_hash_range(unsigned long number, int local)
{
if (ppc_md.flush_hash_range)
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 5f5e6328c21c..1b3ad46a71b5 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -18,57 +18,6 @@
#include <linux/mm.h>
#include <asm/machdep.h>
-static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
- pmd_t *pmdp, unsigned int psize, int ssize)
-{
- int i, max_hpte_count, valid;
- unsigned long s_addr;
- unsigned char *hpte_slot_array;
- unsigned long hidx, shift, vpn, hash, slot;
-
- s_addr = addr & HPAGE_PMD_MASK;
- hpte_slot_array = get_hpte_slot_array(pmdp);
- /*
- * IF we try to do a HUGE PTE update after a withdraw is done.
- * we will find the below NULL. This happens when we do
- * split_huge_page_pmd
- */
- if (!hpte_slot_array)
- return;
-
- if (ppc_md.hugepage_invalidate)
- return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
- psize, ssize);
- /*
- * No bluk hpte removal support, invalidate each entry
- */
- shift = mmu_psize_defs[psize].shift;
- max_hpte_count = HPAGE_PMD_SIZE >> shift;
- for (i = 0; i < max_hpte_count; i++) {
- /*
- * 8 bits per each hpte entries
- * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
- */
- valid = hpte_valid(hpte_slot_array, i);
- if (!valid)
- continue;
- hidx = hpte_hash_index(hpte_slot_array, i);
-
- /* get the vpn */
- addr = s_addr + (i * (1ul << shift));
- vpn = hpt_vpn(addr, vsid, ssize);
- hash = hpt_hash(vpn, shift, ssize);
- if (hidx & _PTEIDX_SECONDARY)
- hash = ~hash;
-
- slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
- slot += hidx & _PTEIDX_GROUP_IX;
- ppc_md.hpte_invalidate(slot, vpn, psize,
- MMU_PAGE_16M, ssize, 0);
- }
-}
-
-
int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
pmd_t *pmdp, unsigned long trap, int local, int ssize,
unsigned int psize)
@@ -145,7 +94,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
* hash page table entries.
*/
if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
- invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize);
+ flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
+ ssize);
}
valid = hpte_valid(hpte_slot_array, index);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index c8d709ab489d..62e8010a0c49 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -731,29 +731,13 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, unsigned long old_pmd)
{
- int ssize, i;
- unsigned long s_addr;
- int max_hpte_count;
- unsigned int psize, valid;
- unsigned char *hpte_slot_array;
- unsigned long hidx, vpn, vsid, hash, shift, slot;
-
- /*
- * Flush all the hptes mapping this hugepage
- */
- s_addr = addr & HPAGE_PMD_MASK;
- hpte_slot_array = get_hpte_slot_array(pmdp);
- /*
- * IF we try to do a HUGE PTE update after a withdraw is done.
- * we will find the below NULL. This happens when we do
- * split_huge_page_pmd
- */
- if (!hpte_slot_array)
- return;
+ int ssize;
+ unsigned int psize;
+ unsigned long vsid;
/* get the base page size,vsid and segment size */
#ifdef CONFIG_DEBUG_VM
- psize = get_slice_psize(mm, s_addr);
+ psize = get_slice_psize(mm, addr);
BUG_ON(psize == MMU_PAGE_16M);
#endif
if (old_pmd & _PAGE_COMBO)
@@ -761,46 +745,16 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
else
psize = MMU_PAGE_64K;
- if (!is_kernel_addr(s_addr)) {
- ssize = user_segment_size(s_addr);
- vsid = get_vsid(mm->context.id, s_addr, ssize);
+ if (!is_kernel_addr(addr)) {
+ ssize = user_segment_size(addr);
+ vsid = get_vsid(mm->context.id, addr, ssize);
WARN_ON(vsid == 0);
} else {
- vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize);
+ vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
ssize = mmu_kernel_ssize;
}
- if (ppc_md.hugepage_invalidate)
- return ppc_md.hugepage_invalidate(vsid, s_addr,
- hpte_slot_array,
- psize, ssize);
- /*
- * No bluk hpte removal support, invalidate each entry
- */
- shift = mmu_psize_defs[psize].shift;
- max_hpte_count = HPAGE_PMD_SIZE >> shift;
- for (i = 0; i < max_hpte_count; i++) {
- /*
- * 8 bits per each hpte entries
- * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
- */
- valid = hpte_valid(hpte_slot_array, i);
- if (!valid)
- continue;
- hidx = hpte_hash_index(hpte_slot_array, i);
-
- /* get the vpn */
- addr = s_addr + (i * (1ul << shift));
- vpn = hpt_vpn(addr, vsid, ssize);
- hash = hpt_hash(vpn, shift, ssize);
- if (hidx & _PTEIDX_SECONDARY)
- hash = ~hash;
-
- slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
- slot += hidx & _PTEIDX_GROUP_IX;
- ppc_md.hpte_invalidate(slot, vpn, psize,
- MMU_PAGE_16M, ssize, 0);
- }
+ return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize);
}
static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
--
2.1.0
^ permalink raw reply related
* [PATCH V3 2/2] powerpc/mm/thp: Use tlbiel if possible
From: Aneesh Kumar K.V @ 2014-11-02 15:45 UTC (permalink / raw)
To: benh, paulus, mpe; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1414943128-29889-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
If we know that user address space has never executed on other cpus
we could use tlbiel.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/machdep.h | 2 +-
arch/powerpc/include/asm/tlbflush.h | 3 ++-
arch/powerpc/mm/hash_native_64.c | 4 ++--
arch/powerpc/mm/hash_utils_64.c | 28 +++++++++++++++++++++++-----
arch/powerpc/mm/hugepage-hash64.c | 2 +-
arch/powerpc/mm/pgtable_64.c | 9 +++++++--
arch/powerpc/platforms/pseries/lpar.c | 2 +-
7 files changed, 37 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 307347f8ddbd..ccc9f9bd1605 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -60,7 +60,7 @@ struct machdep_calls {
void (*hugepage_invalidate)(unsigned long vsid,
unsigned long addr,
unsigned char *hpte_slot_array,
- int psize, int ssize);
+ int psize, int ssize, int local);
/* special for kexec, to be called in real mode, linear mapping is
* destroyed as well */
void (*hpte_clear_all)(void);
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index afe57427ef8e..6a5c1774b32c 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -128,7 +128,8 @@ extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
int ssize, int local);
extern void flush_hash_range(unsigned long number, int local);
extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
- pmd_t *pmdp, unsigned int psize, int ssize);
+ pmd_t *pmdp, unsigned int psize, int ssize,
+ int local);
static inline void local_flush_tlb_mm(struct mm_struct *mm)
{
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index ae4962a06476..459840d9b7d3 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -419,7 +419,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
static void native_hugepage_invalidate(unsigned long vsid,
unsigned long addr,
unsigned char *hpte_slot_array,
- int psize, int ssize)
+ int psize, int ssize, int local)
{
int i;
struct hash_pte *hptep;
@@ -465,7 +465,7 @@ static void native_hugepage_invalidate(unsigned long vsid,
* instruction compares entry_VA in tlb with the VA specified
* here
*/
- tlbie(vpn, psize, actual_psize, ssize, 0);
+ tlbie(vpn, psize, actual_psize, ssize, local);
}
local_irq_restore(flags);
}
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 26517ea34970..7a6fa267d1f4 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1317,7 +1317,7 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
- pmd_t *pmdp, unsigned int psize, int ssize)
+ pmd_t *pmdp, unsigned int psize, int ssize, int local)
{
int i, max_hpte_count, valid;
unsigned long s_addr;
@@ -1334,9 +1334,11 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
if (!hpte_slot_array)
return;
- if (ppc_md.hugepage_invalidate)
- return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
- psize, ssize);
+ if (ppc_md.hugepage_invalidate) {
+ ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+ psize, ssize, local);
+ goto tm_abort;
+ }
/*
* No bluk hpte removal support, invalidate each entry
*/
@@ -1362,8 +1364,24 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
ppc_md.hpte_invalidate(slot, vpn, psize,
- MMU_PAGE_16M, ssize, 0);
+ MMU_PAGE_16M, ssize, local);
+ }
+tm_abort:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* Transactions are not aborted by tlbiel, only tlbie.
+ * Without, syncing a page back to a block device w/ PIO could pick up
+ * transactional data (bad!) so we force an abort here. Before the
+ * sync the page will be made read-only, which will flush_hash_page.
+ * BIG ISSUE here: if the kernel uses a page from userspace without
+ * unmapping it first, it may see the speculated version.
+ */
+ if (local && cpu_has_feature(CPU_FTR_TM) &&
+ current->thread.regs &&
+ MSR_TM_ACTIVE(current->thread.regs->msr)) {
+ tm_enable();
+ tm_abort(TM_CAUSE_TLBI);
}
+#endif
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 1b3ad46a71b5..3a648cd363ae 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -95,7 +95,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
*/
if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
- ssize);
+ ssize, local);
}
valid = hpte_valid(hpte_slot_array, index);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 62e8010a0c49..f54b0908c55e 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -731,9 +731,10 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, unsigned long old_pmd)
{
- int ssize;
+ int ssize, local = 0;
unsigned int psize;
unsigned long vsid;
+ const struct cpumask *tmp;
/* get the base page size,vsid and segment size */
#ifdef CONFIG_DEBUG_VM
@@ -754,7 +755,11 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
ssize = mmu_kernel_ssize;
}
- return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize);
+ tmp = cpumask_of(smp_processor_id());
+ if (cpumask_equal(mm_cpumask(mm), tmp))
+ local = 1;
+
+ return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, local);
}
static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 8c509d5397c6..0bb4a6461823 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -432,7 +432,7 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
static void pSeries_lpar_hugepage_invalidate(unsigned long vsid,
unsigned long addr,
unsigned char *hpte_slot_array,
- int psize, int ssize)
+ int psize, int ssize, int local)
{
int i, index = 0;
unsigned long s_addr = addr;
--
2.1.0
^ permalink raw reply related
* Re: [PATCH] powerpc: Replace cc constraint in inline assembly with cr0
From: Anton Blanchard @ 2014-11-02 20:17 UTC (permalink / raw)
To: Segher Boessenkool; +Cc: ulrich.weigand, paulus, linuxppc-dev
In-Reply-To: <20141101133317.GA1608@gate.crashing.org>
Hi Segher,
> > Our inline assembly only clobbers the first condition register
> > field, but we mark all of them as being clobbered.
>
> No, we don't. "cc" has been an alias for cr0 for over twenty two and
> a half years now; it has never changed meaning. This is an LLVM bug.
Thanks! I opened http://llvm.org/bugs/show_bug.cgi?id=21451 to track it.
Anton
^ permalink raw reply
* [PATCH] powerpc/pseries: Quieten ibm,pcie-link-speed-stats warning
From: Anton Blanchard @ 2014-11-02 21:18 UTC (permalink / raw)
To: benh, paulus, mpe; +Cc: linuxppc-dev
The ibm,pcie-link-speed-stats isn't mandatory, so we shouldn't print
a high priority error message when missing. One example where we see
this is QEMU.
Reduce it to pr_debug.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
arch/powerpc/platforms/pseries/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 67e4859..fe16a50 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -134,7 +134,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
of_node_put(pdn);
if (rc) {
- pr_err("no ibm,pcie-link-speed-stats property\n");
+ pr_debug("no ibm,pcie-link-speed-stats property\n");
return 0;
}
--
1.9.1
^ permalink raw reply related
* [PATCH] powerpc/pseries: Quieten relocation on exceptions warning
From: Anton Blanchard @ 2014-11-02 21:34 UTC (permalink / raw)
To: benh, paulus, mpe, mikey; +Cc: linuxppc-dev
The H_SET_MODE hcall returns H_P2 if a function is not implemented
and all callers should handle this case.
The call to enable relocation on exceptions currently prints an error
message if the feature is not implemented. While H_SET_MODE was
first introduced on POWER8 (which has relocation on exceptions), it
has been now added on some POWER7 configurations (which does not).
Check for H_P2 and print an informational message instead.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
arch/powerpc/platforms/pseries/setup.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 125c589..fcc9227 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -499,7 +499,11 @@ static void __init pSeries_setup_arch(void)
if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
long rc;
- if ((rc = pSeries_enable_reloc_on_exc()) != H_SUCCESS) {
+
+ rc = pSeries_enable_reloc_on_exc();
+ if (rc == H_P2) {
+ pr_info("Relocation on exceptions not supported\n");
+ } else if (rc != H_SUCCESS) {
pr_warn("Unable to enable relocation on exceptions: "
"%ld\n", rc);
}
--
1.9.1
^ permalink raw reply related
* [PATCH 1/2] powerpc: Save/restore PPR for KVM hypercalls
From: Paul Mackerras @ 2014-11-03 4:46 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Suresh E. Warrier, Paul Mackerras
From: "Suresh E. Warrier" <warrier@linux.vnet.ibm.com>
The system call FLIH (first-level interrupt handler) at 0xc00
unconditionally sets hardware priority to medium. For hypercalls, this
means we lose guest OS priority. The front end (do_kvm_0x**) to the
KVM interrupt handler always assumes that PPR priority is saved in
PACA exception save area, so it copies this to the kvm_hstate
structure. For hypercalls, this would be the saved priority from any
previous exception. Eventually, the guest gets resumed with an
incorrect priority.
The fix is to save the PPR priority in PACA exception save area before
switching HMT priorities in the FLIH so that existing code described above
in the KVM interrupt handler can copy it from there into the VCPU's saved
context.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kernel/exceptions-64s.S | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 72e783e..f67d909 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -292,15 +292,26 @@ decrementer_pSeries:
. = 0xc00
.globl system_call_pSeries
system_call_pSeries:
- HMT_MEDIUM
+ /*
+ * Switch to HMT medium priority on systems where we don't support
+ * saving/restoring PPR or if CONFIG_KVM_BOOK3S_64_HANDLER is not
+ * set. Otherwise, we save PPR in the CONFIG_KVM_BOOK3S_64_HANDLER
+ * path before switching priority.
+ */
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+ HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
GET_PACA(r13)
std r9,PACA_EXGEN+EX_R9(r13)
+ OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);
+ HMT_MEDIUM;
std r10,PACA_EXGEN+EX_R10(r13)
+ OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR);
mfcr r9
KVMTEST(0xc00)
GET_SCRATCH0(r13)
+#else
+ HMT_MEDIUM;
#endif
SYSCALL_PSERIES_1
SYSCALL_PSERIES_2_RFID
--
2.1.1
^ permalink raw reply related
* [PATCH 2/2] powerpc: Fix compilation of emulate_step()
From: Paul Mackerras @ 2014-11-03 4:46 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Paul Mackerras
In-Reply-To: <1414990003-6104-1-git-send-email-paulus@samba.org>
Commit be96f63375a1 ("powerpc: Split out instruction analysis
part of emulate_step()") added some calls to do_fp_load()
and do_fp_store(), which fail to compile on configs with
CONFIG_PPC_FPU=n and CONFIG_PPC_EMULATE_SSTEP=y. This fixes
the compile by adding #ifdef CONFIG_PPC_FPU around the code
that calls these functions.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/lib/sstep.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 54651fc..dc885b3 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1865,6 +1865,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
}
goto ldst_done;
+#ifdef CONFIG_PPC_FPU
case LOAD_FP:
if (regs->msr & MSR_LE)
return 0;
@@ -1873,7 +1874,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
else
err = do_fp_load(op.reg, do_lfd, op.ea, size, regs);
goto ldst_done;
-
+#endif
#ifdef CONFIG_ALTIVEC
case LOAD_VMX:
if (regs->msr & MSR_LE)
@@ -1919,6 +1920,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
err = write_mem(op.val, op.ea, size, regs);
goto ldst_done;
+#ifdef CONFIG_PPC_FPU
case STORE_FP:
if (regs->msr & MSR_LE)
return 0;
@@ -1927,7 +1929,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
else
err = do_fp_store(op.reg, do_stfd, op.ea, size, regs);
goto ldst_done;
-
+#endif
#ifdef CONFIG_ALTIVEC
case STORE_VMX:
if (regs->msr & MSR_LE)
--
2.1.1
^ permalink raw reply related
* [PATCH 1/2] powerpc/mm: Check for matching hpte without taking hpte lock
From: Aneesh Kumar K.V @ 2014-11-03 14:51 UTC (permalink / raw)
To: benh, paulus, mpe; +Cc: linuxppc-dev, Aneesh Kumar K.V
With smaller hash page table config, we would end up in situation
where we would be replacing hash page table slot frequently. In
such config, we will find the hpte to be not matching, and we
can do that check without holding the hpte lock. We need to
recheck the hpte again after holding lock.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/hash_native_64.c | 24 +++++++++++++++---------
1 file changed, 15 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index ae4962a06476..83c6bb12be14 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -294,8 +294,6 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
DBG_LOW(" update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
vpn, want_v & HPTE_V_AVPN, slot, newpp);
- native_lock_hpte(hptep);
-
hpte_v = be64_to_cpu(hptep->v);
/*
* We need to invalidate the TLB always because hpte_remove doesn't do
@@ -308,16 +306,24 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
DBG_LOW(" -> miss\n");
ret = -1;
} else {
- DBG_LOW(" -> hit\n");
- /* Update the HPTE */
- hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & ~(HPTE_R_PP | HPTE_R_N)) |
- (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C)));
+ native_lock_hpte(hptep);
+ /* recheck with locks held */
+ hpte_v = be64_to_cpu(hptep->v);
+ if (unlikely(!HPTE_V_COMPARE(hpte_v, want_v) ||
+ !(hpte_v & HPTE_V_VALID))) {
+ ret = -1;
+ } else {
+ DBG_LOW(" -> hit\n");
+ /* Update the HPTE */
+ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
+ ~(HPTE_R_PP | HPTE_R_N)) |
+ (newpp & (HPTE_R_PP | HPTE_R_N |
+ HPTE_R_C)));
+ }
+ native_unlock_hpte(hptep);
}
- native_unlock_hpte(hptep);
-
/* Ensure it is out of the tlb too. */
tlbie(vpn, bpsize, apsize, ssize, local);
-
return ret;
}
--
2.1.0
^ permalink raw reply related
* [PATCH 2/2] powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault
From: Aneesh Kumar K.V @ 2014-11-03 14:51 UTC (permalink / raw)
To: benh, paulus, mpe; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1415026295-25965-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
upatepp get called for a nohpte fault, when we find from the linux
page table that the translation was hashed before. In that case
we are sure that there is no existing translation, hence we could
avoid doing tlbie.
Performance number:
We use randbox_access_bench written by Anton.
Kernel with THP disabled and smaller hash page table size.
86.60% random_access_b [kernel.kallsyms] [k] .native_hpte_updatepp
2.10% random_access_b random_access_bench [.] doit
1.99% random_access_b [kernel.kallsyms] [k] .do_raw_spin_lock
1.85% random_access_b [kernel.kallsyms] [k] .native_hpte_insert
1.26% random_access_b [kernel.kallsyms] [k] .native_flush_hash_range
1.18% random_access_b [kernel.kallsyms] [k] .__delay
0.69% random_access_b [kernel.kallsyms] [k] .native_hpte_remove
0.37% random_access_b [kernel.kallsyms] [k] .clear_user_page
0.34% random_access_b [kernel.kallsyms] [k] .__hash_page_64K
0.32% random_access_b [kernel.kallsyms] [k] fast_exception_return
0.30% random_access_b [kernel.kallsyms] [k] .hash_page_mm
With Fix:
27.54% random_access_b random_access_bench [.] doit
22.90% random_access_b [kernel.kallsyms] [k] .native_hpte_insert
5.76% random_access_b [kernel.kallsyms] [k] .native_hpte_remove
5.20% random_access_b [kernel.kallsyms] [k] fast_exception_return
5.12% random_access_b [kernel.kallsyms] [k] .__hash_page_64K
4.80% random_access_b [kernel.kallsyms] [k] .hash_page_mm
3.31% random_access_b [kernel.kallsyms] [k] data_access_common
1.84% random_access_b [kernel.kallsyms] [k] .trace_hardirqs_on_caller
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/machdep.h | 2 +-
arch/powerpc/include/asm/mmu-hash64.h | 22 ++++++++++-------
arch/powerpc/include/asm/tlbflush.h | 2 +-
arch/powerpc/kernel/exceptions-64s.S | 2 ++
arch/powerpc/mm/hash_low_64.S | 15 ++++++------
arch/powerpc/mm/hash_native_64.c | 15 ++++++++----
arch/powerpc/mm/hash_utils_64.c | 40 +++++++++++++++++++------------
arch/powerpc/mm/hugepage-hash64.c | 6 ++---
arch/powerpc/mm/hugetlbpage-hash64.c | 6 ++---
arch/powerpc/platforms/cell/beat_htab.c | 4 ++--
arch/powerpc/platforms/cell/spu_base.c | 5 ++--
arch/powerpc/platforms/cell/spufs/fault.c | 2 +-
arch/powerpc/platforms/ps3/htab.c | 2 +-
arch/powerpc/platforms/pseries/lpar.c | 2 +-
drivers/misc/cxl/fault.c | 8 +++++--
15 files changed, 82 insertions(+), 51 deletions(-)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 307347f8ddbd..7b44bdf0c313 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -42,7 +42,7 @@ struct machdep_calls {
unsigned long newpp,
unsigned long vpn,
int bpsize, int apsize,
- int ssize, int local);
+ int ssize, unsigned long flags);
void (*hpte_updateboltedpp)(unsigned long newpp,
unsigned long ea,
int psize, int ssize);
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index aeebc94b2bce..4f13c3ed7acf 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -316,27 +316,33 @@ static inline unsigned long hpt_hash(unsigned long vpn,
return hash & 0x7fffffffffUL;
}
+#define HPTE_LOCAL_UPDATE 0x1
+#define HPTE_NOHPTE_UPDATE 0x2
+
extern int __hash_page_4K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
- unsigned int local, int ssize, int subpage_prot);
+ unsigned long flags, int ssize, int subpage_prot);
extern int __hash_page_64K(unsigned long ea, unsigned long access,
unsigned long vsid, pte_t *ptep, unsigned long trap,
- unsigned int local, int ssize);
+ unsigned long flags, int ssize);
struct mm_struct;
unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
-extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap);
-extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
+extern int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+ unsigned long access, unsigned long trap,
+ unsigned long flags);
+extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+ unsigned long dsisr);
int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
- pte_t *ptep, unsigned long trap, int local, int ssize,
- unsigned int shift, unsigned int mmu_psize);
+ pte_t *ptep, unsigned long trap, unsigned long flags,
+ int ssize, unsigned int shift, unsigned int mmu_psize);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern int __hash_page_thp(unsigned long ea, unsigned long access,
unsigned long vsid, pmd_t *pmdp, unsigned long trap,
- int local, int ssize, unsigned int psize);
+ unsigned long flags, int ssize, unsigned int psize);
#else
static inline int __hash_page_thp(unsigned long ea, unsigned long access,
unsigned long vsid, pmd_t *pmdp,
- unsigned long trap, int local,
+ unsigned long trap, unsigned long flags,
int ssize, unsigned int psize)
{
BUG();
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 2def01ed0cb2..2f9862ac8d0e 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -125,7 +125,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
- int ssize, int local);
+ int ssize, unsigned long flags);
extern void flush_hash_range(unsigned long number, int local);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 72e783ea0681..2366e9d918a2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1571,9 +1571,11 @@ do_hash_page:
* r3 contains the faulting address
* r4 contains the required access permissions
* r5 contains the trap number
+ * r6 contains dsisr
*
* at return r3 = 0 for success, 1 for page fault, negative for error
*/
+ ld r6,_DSISR(r1)
bl hash_page /* build HPTE if possible */
cmpdi r3,0 /* see if hash_page succeeded */
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 057cbbb4c576..fc5ce0926204 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -46,7 +46,8 @@
/*
* _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
- * pte_t *ptep, unsigned long trap, int local, int ssize)
+ * pte_t *ptep, unsigned long trap, unsigned long flags,
+ * int ssize)
*
* Adds a 4K page to the hash table in a segment of 4K pages only
*/
@@ -298,7 +299,7 @@ htab_modify_pte:
li r6,MMU_PAGE_4K /* base page size */
li r7,MMU_PAGE_4K /* actual page size */
ld r8,STK_PARAM(R9)(r1) /* segment size */
- ld r9,STK_PARAM(R8)(r1) /* get "local" param */
+ ld r9,STK_PARAM(R8)(r1) /* get "flags" param */
.globl htab_call_hpte_updatepp
htab_call_hpte_updatepp:
bl . /* Patched by htab_finish_init() */
@@ -338,8 +339,8 @@ htab_pte_insert_failure:
*****************************************************************************/
/* _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
- * pte_t *ptep, unsigned long trap, int local, int ssize,
- * int subpg_prot)
+ * pte_t *ptep, unsigned long trap, unsigned local flags,
+ * int ssize, int subpg_prot)
*/
/*
@@ -594,7 +595,7 @@ htab_inval_old_hpte:
li r5,0 /* PTE.hidx */
li r6,MMU_PAGE_64K /* psize */
ld r7,STK_PARAM(R9)(r1) /* ssize */
- ld r8,STK_PARAM(R8)(r1) /* local */
+ ld r8,STK_PARAM(R8)(r1) /* flags */
bl flush_hash_page
/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
lis r0,_PAGE_HPTE_SUB@h
@@ -666,7 +667,7 @@ htab_modify_pte:
li r6,MMU_PAGE_4K /* base page size */
li r7,MMU_PAGE_4K /* actual page size */
ld r8,STK_PARAM(R9)(r1) /* segment size */
- ld r9,STK_PARAM(R8)(r1) /* get "local" param */
+ ld r9,STK_PARAM(R8)(r1) /* get "flags" param */
.globl htab_call_hpte_updatepp
htab_call_hpte_updatepp:
bl . /* patched by htab_finish_init() */
@@ -962,7 +963,7 @@ ht64_modify_pte:
li r6,MMU_PAGE_64K /* base page size */
li r7,MMU_PAGE_64K /* actual page size */
ld r8,STK_PARAM(R9)(r1) /* segment size */
- ld r9,STK_PARAM(R8)(r1) /* get "local" param */
+ ld r9,STK_PARAM(R8)(r1) /* get "flags" param */
.globl ht64_call_hpte_updatepp
ht64_call_hpte_updatepp:
bl . /* patched by htab_finish_init() */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 83c6bb12be14..216efffdef8d 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -283,11 +283,11 @@ static long native_hpte_remove(unsigned long hpte_group)
static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
unsigned long vpn, int bpsize,
- int apsize, int ssize, int local)
+ int apsize, int ssize, unsigned long flags)
{
struct hash_pte *hptep = htab_address + slot;
unsigned long hpte_v, want_v;
- int ret = 0;
+ int ret = 0, local = 0;
want_v = hpte_encode_avpn(vpn, bpsize, ssize);
@@ -322,8 +322,15 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
}
native_unlock_hpte(hptep);
}
- /* Ensure it is out of the tlb too. */
- tlbie(vpn, bpsize, apsize, ssize, local);
+
+ if (flags & HPTE_LOCAL_UPDATE)
+ local = 1;
+ /*
+ * Ensure it is out of the tlb too if it is not a nohpte fault
+ */
+ if (!(flags & HPTE_NOHPTE_UPDATE))
+ tlbie(vpn, bpsize, apsize, ssize, local);
+
return ret;
}
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 64ee89c0825f..553192a2cede 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1003,7 +1003,9 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
* -1 - critical hash insertion error
* -2 - access not permitted by subpage protection mechanism
*/
-int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+ unsigned long access, unsigned long trap,
+ unsigned long flags)
{
enum ctx_state prev_state = exception_enter();
pgd_t *pgdir;
@@ -1011,7 +1013,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
pte_t *ptep;
unsigned hugeshift;
const struct cpumask *tmp;
- int rc, user_region = 0, local = 0;
+ int rc, user_region = 0;
int psize, ssize;
DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
@@ -1063,7 +1065,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
/* Check CPU locality */
tmp = cpumask_of(smp_processor_id());
if (user_region && cpumask_equal(mm_cpumask(mm), tmp))
- local = 1;
+ flags |= HPTE_LOCAL_UPDATE;
#ifndef CONFIG_PPC_64K_PAGES
/* If we use 4K pages and our psize is not 4K, then we might
@@ -1100,11 +1102,11 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
if (hugeshift) {
if (pmd_trans_huge(*(pmd_t *)ptep))
rc = __hash_page_thp(ea, access, vsid, (pmd_t *)ptep,
- trap, local, ssize, psize);
+ trap, flags, ssize, psize);
#ifdef CONFIG_HUGETLB_PAGE
else
rc = __hash_page_huge(ea, access, vsid, ptep, trap,
- local, ssize, hugeshift, psize);
+ flags, ssize, hugeshift, psize);
#else
else {
/*
@@ -1163,7 +1165,8 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
#ifdef CONFIG_PPC_HAS_HASH_64K
if (psize == MMU_PAGE_64K)
- rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
+ rc = __hash_page_64K(ea, access, vsid, ptep, trap,
+ flags, ssize);
else
#endif /* CONFIG_PPC_HAS_HASH_64K */
{
@@ -1172,7 +1175,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
rc = -2;
else
rc = __hash_page_4K(ea, access, vsid, ptep, trap,
- local, ssize, spp);
+ flags, ssize, spp);
}
/* Dump some info in case of hash insertion failure, they should
@@ -1195,14 +1198,19 @@ bail:
}
EXPORT_SYMBOL_GPL(hash_page_mm);
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+ unsigned long dsisr)
{
+ unsigned long flags = 0;
struct mm_struct *mm = current->mm;
if (REGION_ID(ea) == VMALLOC_REGION_ID)
mm = &init_mm;
- return hash_page_mm(mm, ea, access, trap);
+ if (dsisr & DSISR_NOHPTE)
+ flags |= HPTE_NOHPTE_UPDATE;
+
+ return hash_page_mm(mm, ea, access, trap, flags);
}
EXPORT_SYMBOL_GPL(hash_page);
@@ -1214,7 +1222,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
pgd_t *pgdir;
pte_t *ptep;
unsigned long flags;
- int rc, ssize, local = 0;
+ int rc, ssize, update_flags = 0;
BUG_ON(REGION_ID(ea) != USER_REGION_ID);
@@ -1265,16 +1273,17 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
/* Is that local to this CPU ? */
if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
- local = 1;
+ update_flags = HPTE_LOCAL_UPDATE;
/* Hash it in */
#ifdef CONFIG_PPC_HAS_HASH_64K
if (mm->context.user_psize == MMU_PAGE_64K)
- rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
+ rc = __hash_page_64K(ea, access, vsid, ptep, trap,
+ update_flags, ssize);
else
#endif /* CONFIG_PPC_HAS_HASH_64K */
- rc = __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize,
- subpage_protection(mm, ea));
+ rc = __hash_page_4K(ea, access, vsid, ptep, trap, update_flags,
+ ssize, subpage_protection(mm, ea));
/* Dump some info in case of hash insertion failure, they should
* never happen so it is really useful to know if/when they do
@@ -1292,9 +1301,10 @@ out_exit:
* do not forget to update the assembly call site !
*/
void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
- int local)
+ unsigned long flags)
{
unsigned long hash, index, shift, hidx, slot;
+ int local = flags & HPTE_LOCAL_UPDATE;
DBG_LOW("flush_hash_page(vpn=%016lx)\n", vpn);
pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 5f5e6328c21c..edecf9381aed 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -70,8 +70,8 @@ static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
- pmd_t *pmdp, unsigned long trap, int local, int ssize,
- unsigned int psize)
+ pmd_t *pmdp, unsigned long trap, unsigned long flags,
+ int ssize, unsigned int psize)
{
unsigned int index, valid;
unsigned char *hpte_slot_array;
@@ -158,7 +158,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
slot += hidx & _PTEIDX_GROUP_IX;
ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
- psize, lpsize, ssize, local);
+ psize, lpsize, ssize, flags);
/*
* We failed to update, try to insert a new entry.
*/
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index a5bcf9301196..d94b1af53a93 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -19,8 +19,8 @@ extern long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
unsigned long vflags, int psize, int ssize);
int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
- pte_t *ptep, unsigned long trap, int local, int ssize,
- unsigned int shift, unsigned int mmu_psize)
+ pte_t *ptep, unsigned long trap, unsigned long flags,
+ int ssize, unsigned int shift, unsigned int mmu_psize)
{
unsigned long vpn;
unsigned long old_pte, new_pte;
@@ -81,7 +81,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
slot += (old_pte & _PAGE_F_GIX) >> 12;
if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
- mmu_psize, ssize, local) == -1)
+ mmu_psize, ssize, flags) == -1)
old_pte &= ~_PAGE_HPTEFLAGS;
}
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index d4d245c0d787..bee9232fe619 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -186,7 +186,7 @@ static long beat_lpar_hpte_updatepp(unsigned long slot,
unsigned long newpp,
unsigned long vpn,
int psize, int apsize,
- int ssize, int local)
+ int ssize, unsigned long flags)
{
unsigned long lpar_rc;
u64 dummy0, dummy1;
@@ -369,7 +369,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
unsigned long newpp,
unsigned long vpn,
int psize, int apsize,
- int ssize, int local)
+ int ssize, unsigned long flags)
{
unsigned long lpar_rc;
unsigned long want_v;
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index ffcbd242e669..f7af74f83693 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -181,7 +181,8 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea)
return 0;
}
-extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); //XXX
+extern int hash_page(unsigned long ea, unsigned long access,
+ unsigned long trap, unsigned long dsisr); //XXX
static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
{
int ret;
@@ -196,7 +197,7 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
(REGION_ID(ea) != USER_REGION_ID)) {
spin_unlock(&spu->register_lock);
- ret = hash_page(ea, _PAGE_PRESENT, 0x300);
+ ret = hash_page(ea, _PAGE_PRESENT, 0x300, dsisr);
spin_lock(&spu->register_lock);
if (!ret) {
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index e45894a08118..d98f845ac777 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -144,7 +144,7 @@ int spufs_handle_class1(struct spu_context *ctx)
access = (_PAGE_PRESENT | _PAGE_USER);
access |= (dsisr & MFC_DSISR_ACCESS_PUT) ? _PAGE_RW : 0UL;
local_irq_save(flags);
- ret = hash_page(ea, access, 0x300);
+ ret = hash_page(ea, access, 0x300, dsisr);
local_irq_restore(flags);
/* hashing failed, so try the actual fault handler */
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 3e270e3412ae..2f95d33cf34a 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -110,7 +110,7 @@ static long ps3_hpte_remove(unsigned long hpte_group)
static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
unsigned long vpn, int psize, int apsize,
- int ssize, int local)
+ int ssize, unsigned long inv_flags)
{
int result;
u64 hpte_v, want_v, hpte_rs;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 8c509d5397c6..003d0e88f651 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -274,7 +274,7 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot,
unsigned long newpp,
unsigned long vpn,
int psize, int apsize,
- int ssize, int local)
+ int ssize, unsigned long inv_flags)
{
unsigned long lpar_rc;
unsigned long flags = (newpp & 7) | H_AVPN;
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index c99e896604ee..f8684bca2d79 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -133,7 +133,7 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
{
unsigned flt = 0;
int result;
- unsigned long access, flags;
+ unsigned long access, flags, inv_flags = 0;
if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
pr_devel("copro_handle_mm_fault failed: %#x\n", result);
@@ -149,8 +149,12 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
access |= _PAGE_RW;
if ((!ctx->kernel) || ~(dar & (1ULL << 63)))
access |= _PAGE_USER;
+
+ if (dsisr & DSISR_NOHPTE)
+ inv_flags |= HPTE_NOHPTE_UPDATE;
+
local_irq_save(flags);
- hash_page_mm(mm, dar, access, 0x300);
+ hash_page_mm(mm, dar, access, 0x300, inv_flags);
local_irq_restore(flags);
pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);
--
2.1.0
^ permalink raw reply related
* Re: [PATCH] PPC: bpf_jit_comp: add SKF_AD_PKTTYPE instruction
From: Philippe Bergheaud @ 2014-11-03 15:45 UTC (permalink / raw)
To: Denis Kirjanov; +Cc: linuxppc-dev, Matt Evans, netdev
In-Reply-To: <CAOJe8K0t3G-bHm_24GjrTp9mmKnYZS1_bdGgrwQBLjC_s5is6w@mail.gmail.com>
Denis Kirjanov wrote:
> Any feedback from PPC folks?
I have reviewed the patch and it looks fine to me.
I have tested successfuly on ppc64le.
I could not test it on ppc64.
Philippe
> On 10/26/14, Denis Kirjanov <kda@linux-powerpc.org> wrote:
>
>>Cc: Matt Evans <matt@ozlabs.org>
>>Signed-off-by: Denis Kirjanov <kda@linux-powerpc.org>
>>---
>> arch/powerpc/include/asm/ppc-opcode.h | 1 +
>> arch/powerpc/net/bpf_jit.h | 7 +++++++
>> arch/powerpc/net/bpf_jit_comp.c | 5 +++++
>> 3 files changed, 13 insertions(+)
>>
>>diff --git a/arch/powerpc/include/asm/ppc-opcode.h
>>b/arch/powerpc/include/asm/ppc-opcode.h
>>index 6f85362..1a52877 100644
>>--- a/arch/powerpc/include/asm/ppc-opcode.h
>>+++ b/arch/powerpc/include/asm/ppc-opcode.h
>>@@ -204,6 +204,7 @@
>> #define PPC_INST_ERATSX_DOT 0x7c000127
>>
>> /* Misc instructions for BPF compiler */
>>+#define PPC_INST_LBZ 0x88000000
>> #define PPC_INST_LD 0xe8000000
>> #define PPC_INST_LHZ 0xa0000000
>> #define PPC_INST_LHBRX 0x7c00062c
>>diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
>>index 9aee27c..c406aa9 100644
>>--- a/arch/powerpc/net/bpf_jit.h
>>+++ b/arch/powerpc/net/bpf_jit.h
>>@@ -87,6 +87,9 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
>> #define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \
>> ___PPC_RA(base) | ((i) & 0xfffc))
>>
>>+
>>+#define PPC_LBZ(r, base, i) EMIT(PPC_INST_LBZ | ___PPC_RT(r) | \
>>+ ___PPC_RA(base) | IMM_L(i))
>> #define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \
>> ___PPC_RA(base) | IMM_L(i))
>> #define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \
>>@@ -96,6 +99,10 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
>> #define PPC_LHBRX(r, base, b) EMIT(PPC_INST_LHBRX | ___PPC_RT(r) | \
>> ___PPC_RA(base) | ___PPC_RB(b))
>> /* Convenience helpers for the above with 'far' offsets: */
>>+#define PPC_LBZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LBZ(r, base, i);
>> \
>>+ else { PPC_ADDIS(r, base, IMM_HA(i)); \
>>+ PPC_LBZ(r, r, IMM_L(i)); } } while(0)
>>+
>> #define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i);
>> \
>> else { PPC_ADDIS(r, base, IMM_HA(i)); \
>> PPC_LD(r, r, IMM_L(i)); } } while(0)
>>diff --git a/arch/powerpc/net/bpf_jit_comp.c
>>b/arch/powerpc/net/bpf_jit_comp.c
>>index cbae2df..d110e28 100644
>>--- a/arch/powerpc/net/bpf_jit_comp.c
>>+++ b/arch/powerpc/net/bpf_jit_comp.c
>>@@ -407,6 +407,11 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32
>>*image,
>> PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
>> queue_mapping));
>> break;
>>+ case BPF_ANC | SKF_AD_PKTTYPE:
>>+ PPC_LBZ_OFFS(r_A, r_skb, PKT_TYPE_OFFSET());
>>+ PPC_ANDI(r_A, r_A, PKT_TYPE_MAX);
>>+ PPC_SRWI(r_A, r_A, 5);
>>+ break;
>> case BPF_ANC | SKF_AD_CPU:
>> #ifdef CONFIG_SMP
>> /*
>>--
>>2.1.0
>>
>>
>
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev
^ permalink raw reply
* Re: [PATCH] powerpc: use device_online/offline() instead of cpu_up/down()
From: Nathan Fontenot @ 2014-11-03 15:45 UTC (permalink / raw)
To: Dan Streetman, Benjamin Herrenschmidt, Michael Ellerman,
Tyrel Datwyler
Cc: Thomas Falcon, Greg Kroah-Hartman, Rafael J. Wysocki,
Rafael J. Wysocki, linux-kernel, Paul Mackerras, Daniel Walter,
Bharata B Rao, Grant Likely, Andrew Morton, Neil Zhang,
linuxppc-dev
In-Reply-To: <1414784494-12573-1-git-send-email-ddstreet@ieee.org>
On 10/31/2014 02:41 PM, Dan Streetman wrote:
> In powerpc pseries platform dlpar operations, Use device_online() and
> device_offline() instead of cpu_up() and cpu_down().
>
> Calling cpu_up/down directly does not update the cpu device offline
> field, which is used to online/offline a cpu from sysfs. Calling
> device_online/offline instead keeps the sysfs cpu online value correct.
> The hotplug lock, which is required to be held when calling
> device_online/offline, is already held when dlpar_online/offline_cpu
> are called, since they are called only from cpu_probe|release_store.
>
> This patch fixes errors on PowerVM systems that have cpu(s) added/removed
> using dlpar operations; without this patch, the
> /sys/devices/system/cpu/cpuN/online nodes do not correctly show the
> online state of added/removed cpus.
>
> Signed-off-by: Dan Streetman <ddstreet@ieee.org>
> Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Acked-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
> ---
>
> Previous discussion for this:
> https://lkml.org/lkml/2014/10/29/839
>
> arch/powerpc/platforms/pseries/dlpar.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
> index 6ad83bd..c22bb1b 100644
> --- a/arch/powerpc/platforms/pseries/dlpar.c
> +++ b/arch/powerpc/platforms/pseries/dlpar.c
> @@ -382,7 +382,7 @@ static int dlpar_online_cpu(struct device_node *dn)
> BUG_ON(get_cpu_current_state(cpu)
> != CPU_STATE_OFFLINE);
> cpu_maps_update_done();
> - rc = cpu_up(cpu);
> + rc = device_online(get_cpu_device(cpu));
> if (rc)
> goto out;
> cpu_maps_update_begin();
> @@ -467,7 +467,7 @@ static int dlpar_offline_cpu(struct device_node *dn)
> if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
> set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
> cpu_maps_update_done();
> - rc = cpu_down(cpu);
> + rc = device_offline(get_cpu_device(cpu));
> if (rc)
> goto out;
> cpu_maps_update_begin();
>
^ permalink raw reply
* [PATCH 0/4] powernv: cpuidle: Redesign idle states management
From: Shreyas B. Prabhu @ 2014-11-03 16:08 UTC (permalink / raw)
To: linux-kernel
Cc: linux-pm, Shreyas B. Prabhu, Rafael J. Wysocki, Paul Mackerras,
Preeti U Murthy, linuxppc-dev
Deep idle states like sleep and winkle are per core idle states. A core
enters these states only when all the threads enter either the particular
idle state or a deeper one. There are tasks like fastsleep hardware bug
workaround and hypervisor core state save which have to be done only by
the last thread of the core entering deep idle state and similarly tasks
like timebase resync, hypervisor core register restore that have to be
done only by the first thread waking up from these states.
The current idle state management does not have a way to distinguish the
first/last thread of the core waking/entering idle states. Tasks like
timebase resync are done for all the threads. This is not only is suboptimal,
but can cause functionality issues when subcores are involved.
Winkle is deeper idle state compared to fastsleep. In this state the power
supply to the chiplet, i.e core, private L2 and private L3 is turned off.
This results in a total hypervisor state loss. This patch set adds support
for winkle and provides a way to track the idle states of the threads of the
core and use it for idle state management of idle states sleep and winkle.
TODO:
-----
Handle the case where a thread enters nap and wakes up with supervisor/
hypervisor state loss. This can only happen due to a bug in the
hardware or the kernel. One way to handle this can be restore the state,
switch to the kernel process context and trigger a panic or a warning.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: linux-pm@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Paul Mackerras (1):
powerpc: powernv: Switch off MMU before entering nap/sleep/rvwinkle
mode
Preeti U. Murthy (1):
powerpc/powernv: Enable Offline CPUs to enter deep idle states
Shreyas B. Prabhu (2):
powernv: cpuidle: Redesign idle states management
powernv: powerpc: Add winkle support for offline cpus
arch/powerpc/include/asm/cpuidle.h | 14 ++
arch/powerpc/include/asm/opal.h | 13 +
arch/powerpc/include/asm/paca.h | 6 +
arch/powerpc/include/asm/ppc-opcode.h | 2 +
arch/powerpc/include/asm/processor.h | 1 +
arch/powerpc/include/asm/reg.h | 2 +
arch/powerpc/kernel/asm-offsets.c | 6 +
arch/powerpc/kernel/cpu_setup_power.S | 4 +
arch/powerpc/kernel/exceptions-64s.S | 30 ++-
arch/powerpc/kernel/idle_power7.S | 326 +++++++++++++++++++++----
arch/powerpc/platforms/powernv/opal-wrappers.S | 39 +++
arch/powerpc/platforms/powernv/powernv.h | 2 +
arch/powerpc/platforms/powernv/setup.c | 170 +++++++++++++
arch/powerpc/platforms/powernv/smp.c | 10 +-
arch/powerpc/platforms/powernv/subcore.c | 35 +++
arch/powerpc/platforms/powernv/subcore.h | 1 +
drivers/cpuidle/cpuidle-powernv.c | 10 +-
17 files changed, 611 insertions(+), 60 deletions(-)
create mode 100644 arch/powerpc/include/asm/cpuidle.h
--
1.9.3
^ permalink raw reply
* [PATCH 1/4] powerpc: powernv: Switch off MMU before entering nap/sleep/rvwinkle mode
From: Shreyas B. Prabhu @ 2014-11-03 16:08 UTC (permalink / raw)
To: linux-kernel; +Cc: Shreyas B. Prabhu, linuxppc-dev, Paul Mackerras
In-Reply-To: <1415030910-5799-1-git-send-email-shreyas@linux.vnet.ibm.com>
From: Paul Mackerras <paulus@samba.org>
Currently, when going idle, we set the flag indicating that we are in
nap mode (paca->kvm_hstate.hwthread_state) and then execute the nap
(or sleep or rvwinkle) instruction, all with the MMU on. This is bad
for two reasons: (a) the architecture specifies that those instructions
must be executed with the MMU off, and in fact with only the SF, HV, ME
and possibly RI bits set, and (b) this introduces a race, because as
soon as we set the flag, another thread can switch the MMU to a guest
context. If the race is lost, this thread will typically start looping
on relocation-on ISIs at 0xc...4400.
This fixes it by setting the MSR as required by the architecture before
setting the flag or executing the nap/sleep/rvwinkle instruction.
[ shreyas@linux.vnet.ibm.com: Edited to handle LE ]
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
---
arch/powerpc/include/asm/reg.h | 2 ++
arch/powerpc/kernel/idle_power7.S | 18 +++++++++++++++++-
2 files changed, 19 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c998279..a68ee15 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -118,8 +118,10 @@
#define __MSR (MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
#ifdef __BIG_ENDIAN__
#define MSR_ __MSR
+#define MSR_IDLE (MSR_ME | MSR_SF | MSR_HV)
#else
#define MSR_ (__MSR | MSR_LE)
+#define MSR_IDLE (MSR_ME | MSR_SF | MSR_HV | MSR_LE)
#endif
#define MSR_KERNEL (MSR_ | MSR_64BIT)
#define MSR_USER32 (MSR_ | MSR_PR | MSR_EE)
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index c0754bb..283c603 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -101,7 +101,23 @@ _GLOBAL(power7_powersave_common)
std r9,_MSR(r1)
std r1,PACAR1(r13)
-_GLOBAL(power7_enter_nap_mode)
+ /*
+ * Go to real mode to do the nap, as required by the architecture.
+ * Also, we need to be in real mode before setting hwthread_state,
+ * because as soon as we do that, another thread can switch
+ * the MMU context to the guest.
+ */
+ LOAD_REG_IMMEDIATE(r5, MSR_IDLE)
+ li r6, MSR_RI
+ andc r6, r9, r6
+ LOAD_REG_ADDR(r7, power7_enter_nap_mode)
+ mtmsrd r6, 1 /* clear RI before setting SRR0/1 */
+ mtspr SPRN_SRR0, r7
+ mtspr SPRN_SRR1, r5
+ rfid
+
+ .globl power7_enter_nap_mode
+power7_enter_nap_mode:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/* Tell KVM we're napping */
li r4,KVM_HWTHREAD_IN_NAP
--
1.9.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox