summaryrefslogtreecommitdiffstats
path: root/drivers/pci
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/pci')
-rw-r--r--drivers/pci/Kconfig37
-rw-r--r--drivers/pci/Makefile1
-rw-r--r--drivers/pci/ats.c439
-rw-r--r--drivers/pci/hotplug-pci.c1
-rw-r--r--drivers/pci/hotplug/acpiphp_glue.c109
-rw-r--r--drivers/pci/hotplug/pciehp_acpi.c1
-rw-r--r--drivers/pci/hotplug/pcihp_slot.c48
-rw-r--r--drivers/pci/hotplug/rpadlpar_core.c1
-rw-r--r--drivers/pci/htirq.c1
-rw-r--r--drivers/pci/ioapic.c1
-rw-r--r--drivers/pci/iov.c143
-rw-r--r--drivers/pci/irq.c1
-rw-r--r--drivers/pci/msi.c1
-rw-r--r--drivers/pci/of.c2
-rw-r--r--drivers/pci/pci-acpi.c6
-rw-r--r--drivers/pci/pci-sysfs.c1
-rw-r--r--drivers/pci/pci.c130
-rw-r--r--drivers/pci/pci.h4
-rw-r--r--drivers/pci/pcie/pme.c9
-rw-r--r--drivers/pci/probe.c153
-rw-r--r--drivers/pci/quirks.c114
-rw-r--r--drivers/pci/rom.c1
-rw-r--r--drivers/pci/setup-bus.c168
-rw-r--r--drivers/pci/setup-res.c153
-rw-r--r--drivers/pci/slot.c1
-rw-r--r--drivers/pci/vpd.c1
-rw-r--r--drivers/pci/xen-pcifront.c5
27 files changed, 1168 insertions, 364 deletions
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 0fa466a91bf..b6f9749b4fa 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -51,17 +51,6 @@ config XEN_PCIDEV_FRONTEND
The PCI device frontend driver allows the kernel to import arbitrary
PCI devices from a PCI backend to support PCI driver domains.
-config XEN_PCIDEV_FE_DEBUG
- bool "Xen PCI Frontend debugging"
- depends on XEN_PCIDEV_FRONTEND && PCI_DEBUG
- help
- Say Y here if you want the Xen PCI frontend to produce a bunch of debug
- messages to the system log. Select this if you are having a
- problem with Xen PCI frontend support and want to see more of what is
- going on.
-
- When in doubt, say N.
-
config HT_IRQ
bool "Interrupts on hypertransport devices"
default y
@@ -71,9 +60,13 @@ config HT_IRQ
If unsure say Y.
+config PCI_ATS
+ bool
+
config PCI_IOV
bool "PCI IOV support"
depends on PCI
+ select PCI_ATS
help
I/O Virtualization is a PCI feature supported by some devices
which allows them to create virtual devices which share their
@@ -81,6 +74,28 @@ config PCI_IOV
If unsure, say N.
+config PCI_PRI
+ bool "PCI PRI support"
+ select PCI_ATS
+ help
+ PRI is the PCI Page Request Interface. It allows PCI devices that are
+ behind an IOMMU to recover from page faults.
+
+ If unsure, say N.
+
+config PCI_PASID
+ bool "PCI PASID support"
+ depends on PCI
+ select PCI_ATS
+ help
+ Process Address Space Identifiers (PASIDs) can be used by PCI devices
+ to access more than one IO address space at the same time. To make
+ use of this feature an IOMMU is required which also supports PASIDs.
+ Select this option if you have such an IOMMU and want to compile the
+ driver for it into your kernel.
+
+ If unsure, say N.
+
config PCI_IOAPIC
bool
depends on PCI
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 6fadae3ad13..083a49fee56 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_PCI_MSI) += msi.o
# Build the Hypertransport interrupt support
obj-$(CONFIG_HT_IRQ) += htirq.o
+obj-$(CONFIG_PCI_ATS) += ats.o
obj-$(CONFIG_PCI_IOV) += iov.o
#
diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
new file mode 100644
index 00000000000..7ec56fb0bd7
--- /dev/null
+++ b/drivers/pci/ats.c
@@ -0,0 +1,439 @@
+/*
+ * drivers/pci/ats.c
+ *
+ * Copyright (C) 2009 Intel Corporation, Yu Zhao <yu.zhao@intel.com>
+ * Copyright (C) 2011 Advanced Micro Devices,
+ *
+ * PCI Express I/O Virtualization (IOV) support.
+ * Address Translation Service 1.0
+ * Page Request Interface added by Joerg Roedel <joerg.roedel@amd.com>
+ * PASID support added by Joerg Roedel <joerg.roedel@amd.com>
+ */
+
+#include <linux/export.h>
+#include <linux/pci-ats.h>
+#include <linux/pci.h>
+
+#include "pci.h"
+
+static int ats_alloc_one(struct pci_dev *dev, int ps)
+{
+ int pos;
+ u16 cap;
+ struct pci_ats *ats;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
+ if (!pos)
+ return -ENODEV;
+
+ ats = kzalloc(sizeof(*ats), GFP_KERNEL);
+ if (!ats)
+ return -ENOMEM;
+
+ ats->pos = pos;
+ ats->stu = ps;
+ pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
+ ats->qdep = PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
+ PCI_ATS_MAX_QDEP;
+ dev->ats = ats;
+
+ return 0;
+}
+
+static void ats_free_one(struct pci_dev *dev)
+{
+ kfree(dev->ats);
+ dev->ats = NULL;
+}
+
+/**
+ * pci_enable_ats - enable the ATS capability
+ * @dev: the PCI device
+ * @ps: the IOMMU page shift
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_enable_ats(struct pci_dev *dev, int ps)
+{
+ int rc;
+ u16 ctrl;
+
+ BUG_ON(dev->ats && dev->ats->is_enabled);
+
+ if (ps < PCI_ATS_MIN_STU)
+ return -EINVAL;
+
+ if (dev->is_physfn || dev->is_virtfn) {
+ struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
+
+ mutex_lock(&pdev->sriov->lock);
+ if (pdev->ats)
+ rc = pdev->ats->stu == ps ? 0 : -EINVAL;
+ else
+ rc = ats_alloc_one(pdev, ps);
+
+ if (!rc)
+ pdev->ats->ref_cnt++;
+ mutex_unlock(&pdev->sriov->lock);
+ if (rc)
+ return rc;
+ }
+
+ if (!dev->is_physfn) {
+ rc = ats_alloc_one(dev, ps);
+ if (rc)
+ return rc;
+ }
+
+ ctrl = PCI_ATS_CTRL_ENABLE;
+ if (!dev->is_virtfn)
+ ctrl |= PCI_ATS_CTRL_STU(ps - PCI_ATS_MIN_STU);
+ pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
+
+ dev->ats->is_enabled = 1;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_enable_ats);
+
+/**
+ * pci_disable_ats - disable the ATS capability
+ * @dev: the PCI device
+ */
+void pci_disable_ats(struct pci_dev *dev)
+{
+ u16 ctrl;
+
+ BUG_ON(!dev->ats || !dev->ats->is_enabled);
+
+ pci_read_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, &ctrl);
+ ctrl &= ~PCI_ATS_CTRL_ENABLE;
+ pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
+
+ dev->ats->is_enabled = 0;
+
+ if (dev->is_physfn || dev->is_virtfn) {
+ struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
+
+ mutex_lock(&pdev->sriov->lock);
+ pdev->ats->ref_cnt--;
+ if (!pdev->ats->ref_cnt)
+ ats_free_one(pdev);
+ mutex_unlock(&pdev->sriov->lock);
+ }
+
+ if (!dev->is_physfn)
+ ats_free_one(dev);
+}
+EXPORT_SYMBOL_GPL(pci_disable_ats);
+
+/**
+ * pci_ats_queue_depth - query the ATS Invalidate Queue Depth
+ * @dev: the PCI device
+ *
+ * Returns the queue depth on success, or negative on failure.
+ *
+ * The ATS spec uses 0 in the Invalidate Queue Depth field to
+ * indicate that the function can accept 32 Invalidate Request.
+ * But here we use the `real' values (i.e. 1~32) for the Queue
+ * Depth; and 0 indicates the function shares the Queue with
+ * other functions (doesn't exclusively own a Queue).
+ */
+int pci_ats_queue_depth(struct pci_dev *dev)
+{
+ int pos;
+ u16 cap;
+
+ if (dev->is_virtfn)
+ return 0;
+
+ if (dev->ats)
+ return dev->ats->qdep;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
+ if (!pos)
+ return -ENODEV;
+
+ pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
+
+ return PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
+ PCI_ATS_MAX_QDEP;
+}
+EXPORT_SYMBOL_GPL(pci_ats_queue_depth);
+
+#ifdef CONFIG_PCI_PRI
+/**
+ * pci_enable_pri - Enable PRI capability
+ * @ pdev: PCI device structure
+ *
+ * Returns 0 on success, negative value on error
+ */
+int pci_enable_pri(struct pci_dev *pdev, u32 reqs)
+{
+ u16 control, status;
+ u32 max_requests;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+ if (!pos)
+ return -EINVAL;
+
+ pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
+ pci_read_config_word(pdev, pos + PCI_PRI_STATUS_OFF, &status);
+ if ((control & PCI_PRI_ENABLE) || !(status & PCI_PRI_STATUS_STOPPED))
+ return -EBUSY;
+
+ pci_read_config_dword(pdev, pos + PCI_PRI_MAX_REQ_OFF, &max_requests);
+ reqs = min(max_requests, reqs);
+ pci_write_config_dword(pdev, pos + PCI_PRI_ALLOC_REQ_OFF, reqs);
+
+ control |= PCI_PRI_ENABLE;
+ pci_write_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, control);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_enable_pri);
+
+/**
+ * pci_disable_pri - Disable PRI capability
+ * @pdev: PCI device structure
+ *
+ * Only clears the enabled-bit, regardless of its former value
+ */
+void pci_disable_pri(struct pci_dev *pdev)
+{
+ u16 control;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+ if (!pos)
+ return;
+
+ pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
+ control &= ~PCI_PRI_ENABLE;
+ pci_write_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, control);
+}
+EXPORT_SYMBOL_GPL(pci_disable_pri);
+
+/**
+ * pci_pri_enabled - Checks if PRI capability is enabled
+ * @pdev: PCI device structure
+ *
+ * Returns true if PRI is enabled on the device, false otherwise
+ */
+bool pci_pri_enabled(struct pci_dev *pdev)
+{
+ u16 control;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+ if (!pos)
+ return false;
+
+ pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
+
+ return (control & PCI_PRI_ENABLE) ? true : false;
+}
+EXPORT_SYMBOL_GPL(pci_pri_enabled);
+
+/**
+ * pci_reset_pri - Resets device's PRI state
+ * @pdev: PCI device structure
+ *
+ * The PRI capability must be disabled before this function is called.
+ * Returns 0 on success, negative value on error.
+ */
+int pci_reset_pri(struct pci_dev *pdev)
+{
+ u16 control;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+ if (!pos)
+ return -EINVAL;
+
+ pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
+ if (control & PCI_PRI_ENABLE)
+ return -EBUSY;
+
+ control |= PCI_PRI_RESET;
+
+ pci_write_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, control);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_reset_pri);
+
+/**
+ * pci_pri_stopped - Checks whether the PRI capability is stopped
+ * @pdev: PCI device structure
+ *
+ * Returns true if the PRI capability on the device is disabled and the
+ * device has no outstanding PRI requests, false otherwise. The device
+ * indicates this via the STOPPED bit in the status register of the
+ * capability.
+ * The device internal state can be cleared by resetting the PRI state
+ * with pci_reset_pri(). This can force the capability into the STOPPED
+ * state.
+ */
+bool pci_pri_stopped(struct pci_dev *pdev)
+{
+ u16 control, status;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+ if (!pos)
+ return true;
+
+ pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
+ pci_read_config_word(pdev, pos + PCI_PRI_STATUS_OFF, &status);
+
+ if (control & PCI_PRI_ENABLE)
+ return false;
+
+ return (status & PCI_PRI_STATUS_STOPPED) ? true : false;
+}
+EXPORT_SYMBOL_GPL(pci_pri_stopped);
+
+/**
+ * pci_pri_status - Request PRI status of a device
+ * @pdev: PCI device structure
+ *
+ * Returns negative value on failure, status on success. The status can
+ * be checked against status-bits. Supported bits are currently:
+ * PCI_PRI_STATUS_RF: Response failure
+ * PCI_PRI_STATUS_UPRGI: Unexpected Page Request Group Index
+ * PCI_PRI_STATUS_STOPPED: PRI has stopped
+ */
+int pci_pri_status(struct pci_dev *pdev)
+{
+ u16 status, control;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+ if (!pos)
+ return -EINVAL;
+
+ pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
+ pci_read_config_word(pdev, pos + PCI_PRI_STATUS_OFF, &status);
+
+ /* Stopped bit is undefined when enable == 1, so clear it */
+ if (control & PCI_PRI_ENABLE)
+ status &= ~PCI_PRI_STATUS_STOPPED;
+
+ return status;
+}
+EXPORT_SYMBOL_GPL(pci_pri_status);
+#endif /* CONFIG_PCI_PRI */
+
+#ifdef CONFIG_PCI_PASID
+/**
+ * pci_enable_pasid - Enable the PASID capability
+ * @pdev: PCI device structure
+ * @features: Features to enable
+ *
+ * Returns 0 on success, negative value on error. This function checks
+ * whether the features are actually supported by the device and returns
+ * an error if not.
+ */
+int pci_enable_pasid(struct pci_dev *pdev, int features)
+{
+ u16 control, supported;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+ if (!pos)
+ return -EINVAL;
+
+ pci_read_config_word(pdev, pos + PCI_PASID_CONTROL_OFF, &control);
+ pci_read_config_word(pdev, pos + PCI_PASID_CAP_OFF, &supported);
+
+ if (!(supported & PCI_PASID_ENABLE))
+ return -EINVAL;
+
+ supported &= PCI_PASID_EXEC | PCI_PASID_PRIV;
+
+ /* User wants to enable anything unsupported? */
+ if ((supported & features) != features)
+ return -EINVAL;
+
+ control = PCI_PASID_ENABLE | features;
+
+ pci_write_config_word(pdev, pos + PCI_PASID_CONTROL_OFF, control);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_enable_pasid);
+
+/**
+ * pci_disable_pasid - Disable the PASID capability
+ * @pdev: PCI device structure
+ *
+ */
+void pci_disable_pasid(struct pci_dev *pdev)
+{
+ u16 control = 0;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+ if (!pos)
+ return;
+
+ pci_write_config_word(pdev, pos + PCI_PASID_CONTROL_OFF, control);
+}
+EXPORT_SYMBOL_GPL(pci_disable_pasid);
+
+/**
+ * pci_pasid_features - Check which PASID features are supported
+ * @pdev: PCI device structure
+ *
+ * Returns a negative value when no PASI capability is present.
+ * Otherwise is returns a bitmask with supported features. Current
+ * features reported are:
+ * PCI_PASID_ENABLE - PASID capability can be enabled
+ * PCI_PASID_EXEC - Execute permission supported
+ * PCI_PASID_PRIV - Priviledged mode supported
+ */
+int pci_pasid_features(struct pci_dev *pdev)
+{
+ u16 supported;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+ if (!pos)
+ return -EINVAL;
+
+ pci_read_config_word(pdev, pos + PCI_PASID_CAP_OFF, &supported);
+
+ supported &= PCI_PASID_ENABLE | PCI_PASID_EXEC | PCI_PASID_PRIV;
+
+ return supported;
+}
+EXPORT_SYMBOL_GPL(pci_pasid_features);
+
+#define PASID_NUMBER_SHIFT 8
+#define PASID_NUMBER_MASK (0x1f << PASID_NUMBER_SHIFT)
+/**
+ * pci_max_pasid - Get maximum number of PASIDs supported by device
+ * @pdev: PCI device structure
+ *
+ * Returns negative value when PASID capability is not present.
+ * Otherwise it returns the numer of supported PASIDs.
+ */
+int pci_max_pasids(struct pci_dev *pdev)
+{
+ u16 supported;
+ int pos;
+
+ pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+ if (!pos)
+ return -EINVAL;
+
+ pci_read_config_word(pdev, pos + PCI_PASID_CAP_OFF, &supported);
+
+ supported = (supported & PASID_NUMBER_MASK) >> PASID_NUMBER_SHIFT;
+
+ return (1 << supported);
+}
+EXPORT_SYMBOL_GPL(pci_max_pasids);
+#endif /* CONFIG_PCI_PASID */
diff --git a/drivers/pci/hotplug-pci.c b/drivers/pci/hotplug-pci.c
index 4d4a6447840..d3509cdeb55 100644
--- a/drivers/pci/hotplug-pci.c
+++ b/drivers/pci/hotplug-pci.c
@@ -1,6 +1,7 @@
/* Core PCI functionality used only by PCI hotplug */
#include <linux/pci.h>
+#include <linux/export.h>
#include "pci.h"
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 220285760b6..596172b4ae9 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -48,6 +48,7 @@
#include <linux/pci-acpi.h>
#include <linux/mutex.h>
#include <linux/slab.h>
+#include <linux/acpi.h>
#include "../pci.h"
#include "acpiphp.h"
@@ -1149,15 +1150,35 @@ check_sub_bridges(acpi_handle handle, u32 lvl, void *context, void **rv)
return AE_OK ;
}
-/**
- * handle_hotplug_event_bridge - handle ACPI event on bridges
- * @handle: Notify()'ed acpi_handle
- * @type: Notify code
- * @context: pointer to acpiphp_bridge structure
- *
- * Handles ACPI event notification on {host,p2p} bridges.
- */
-static void handle_hotplug_event_bridge(acpi_handle handle, u32 type, void *context)
+struct acpiphp_hp_work {
+ struct work_struct work;
+ acpi_handle handle;
+ u32 type;
+ void *context;
+};
+
+static void alloc_acpiphp_hp_work(acpi_handle handle, u32 type,
+ void *context,
+ void (*func)(struct work_struct *work))
+{
+ struct acpiphp_hp_work *hp_work;
+ int ret;
+
+ hp_work = kmalloc(sizeof(*hp_work), GFP_KERNEL);
+ if (!hp_work)
+ return;
+
+ hp_work->handle = handle;
+ hp_work->type = type;
+ hp_work->context = context;
+
+ INIT_WORK(&hp_work->work, func);
+ ret = queue_work(kacpi_hotplug_wq, &hp_work->work);
+ if (!ret)
+ kfree(hp_work);
+}
+
+static void _handle_hotplug_event_bridge(struct work_struct *work)
{
struct acpiphp_bridge *bridge;
char objname[64];
@@ -1165,11 +1186,18 @@ static void handle_hotplug_event_bridge(acpi_handle handle, u32 type, void *cont
.pointer = objname };
struct acpi_device *device;
int num_sub_bridges = 0;
+ struct acpiphp_hp_work *hp_work;
+ acpi_handle handle;
+ u32 type;
+
+ hp_work = container_of(work, struct acpiphp_hp_work, work);
+ handle = hp_work->handle;
+ type = hp_work->type;
if (acpi_bus_get_device(handle, &device)) {
/* This bridge must have just been physically inserted */
handle_bridge_insertion(handle, type);
- return;
+ goto out;
}
bridge = acpiphp_handle_to_bridge(handle);
@@ -1180,7 +1208,7 @@ static void handle_hotplug_event_bridge(acpi_handle handle, u32 type, void *cont
if (!bridge && !num_sub_bridges) {
err("cannot get bridge info\n");
- return;
+ goto out;
}
acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
@@ -1241,22 +1269,49 @@ static void handle_hotplug_event_bridge(acpi_handle handle, u32 type, void *cont
warn("notify_handler: unknown event type 0x%x for %s\n", type, objname);
break;
}
+
+out:
+ kfree(hp_work); /* allocated in handle_hotplug_event_bridge */
}
/**
- * handle_hotplug_event_func - handle ACPI event on functions (i.e. slots)
+ * handle_hotplug_event_bridge - handle ACPI event on bridges
* @handle: Notify()'ed acpi_handle
* @type: Notify code
- * @context: pointer to acpiphp_func structure
+ * @context: pointer to acpiphp_bridge structure
*
- * Handles ACPI event notification on slots.
+ * Handles ACPI event notification on {host,p2p} bridges.
*/
-static void handle_hotplug_event_func(acpi_handle handle, u32 type, void *context)
+static void handle_hotplug_event_bridge(acpi_handle handle, u32 type,
+ void *context)
+{
+ /*
+ * Currently the code adds all hotplug events to the kacpid_wq
+ * queue when it should add hotplug events to the kacpi_hotplug_wq.
+ * The proper way to fix this is to reorganize the code so that
+ * drivers (dock, etc.) do not call acpi_os_execute(), etc.
+ * For now just re-add this work to the kacpi_hotplug_wq so we
+ * don't deadlock on hotplug actions.
+ */
+ alloc_acpiphp_hp_work(handle, type, context,
+ _handle_hotplug_event_bridge);
+}
+
+static void _handle_hotplug_event_func(struct work_struct *work)
{
struct acpiphp_func *func;
char objname[64];
struct acpi_buffer buffer = { .length = sizeof(objname),
.pointer = objname };
+ struct acpiphp_hp_work *hp_work;
+ acpi_handle handle;
+ u32 type;
+ void *context;
+
+ hp_work = container_of(work, struct acpiphp_hp_work, work);
+ handle = hp_work->handle;
+ type = hp_work->type;
+ context = hp_work->context;
acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
@@ -1291,8 +1346,32 @@ static void handle_hotplug_event_func(acpi_handle handle, u32 type, void *contex
warn("notify_handler: unknown event type 0x%x for %s\n", type, objname);
break;
}
+
+ kfree(hp_work); /* allocated in handle_hotplug_event_func */
}
+/**
+ * handle_hotplug_event_func - handle ACPI event on functions (i.e. slots)
+ * @handle: Notify()'ed acpi_handle
+ * @type: Notify code
+ * @context: pointer to acpiphp_func structure
+ *
+ * Handles ACPI event notification on slots.
+ */
+static void handle_hotplug_event_func(acpi_handle handle, u32 type,
+ void *context)
+{
+ /*
+ * Currently the code adds all hotplug events to the kacpid_wq
+ * queue when it should add hotplug events to the kacpi_hotplug_wq.
+ * The proper way to fix this is to reorganize the code so that
+ * drivers (dock, etc.) do not call acpi_os_execute(), etc.
+ * For now just re-add this work to the kacpi_hotplug_wq so we
+ * don't deadlock on hotplug actions.
+ */
+ alloc_acpiphp_hp_work(handle, type, context,
+ _handle_hotplug_event_func);
+}
static acpi_status
find_root_bridges(acpi_handle handle, u32 lvl, void *context, void **rv)
diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c
index 5f7226223a6..376d70d1717 100644
--- a/drivers/pci/hotplug/pciehp_acpi.c
+++ b/drivers/pci/hotplug/pciehp_acpi.c
@@ -27,6 +27,7 @@
#include <linux/pci.h>
#include <linux/pci_hotplug.h>
#include <linux/slab.h>
+#include <linux/module.h>
#include "pciehp.h"
#define PCIEHP_DETECT_PCIE (0)
diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c
index 749fdf07031..8c05a18c977 100644
--- a/drivers/pci/hotplug/pcihp_slot.c
+++ b/drivers/pci/hotplug/pcihp_slot.c
@@ -24,6 +24,7 @@
*/
#include <linux/pci.h>
+#include <linux/export.h>
#include <linux/pci_hotplug.h>
static struct hpp_type0 pci_default_type0 = {
@@ -158,47 +159,6 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
*/
}
-/* Program PCIE MaxPayload setting on device: ensure parent maxpayload <= device */
-static int pci_set_payload(struct pci_dev *dev)
-{
- int pos, ppos;
- u16 pctl, psz;
- u16 dctl, dsz, dcap, dmax;
- struct pci_dev *parent;
-
- parent = dev->bus->self;
- pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
- if (!pos)
- return 0;
-
- /* Read Device MaxPayload capability and setting */
- pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &dctl);
- pci_read_config_word(dev, pos + PCI_EXP_DEVCAP, &dcap);
- dsz = (dctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5;
- dmax = (dcap & PCI_EXP_DEVCAP_PAYLOAD);
-
- /* Read Parent MaxPayload setting */
- ppos = pci_find_capability(parent, PCI_CAP_ID_EXP);
- if (!ppos)
- return 0;
- pci_read_config_word(parent, ppos + PCI_EXP_DEVCTL, &pctl);
- psz = (pctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5;
-
- /* If parent payload > device max payload -> error
- * If parent payload > device payload -> set speed
- * If parent payload <= device payload -> do nothing
- */
- if (psz > dmax)
- return -1;
- else if (psz > dsz) {
- dev_info(&dev->dev, "Setting MaxPayload to %d\n", 128 << psz);
- pci_write_config_word(dev, pos + PCI_EXP_DEVCTL,
- (dctl & ~PCI_EXP_DEVCTL_PAYLOAD) +
- (psz << 5));
- }
- return 0;
-}
-
void pci_configure_slot(struct pci_dev *dev)
{
struct pci_dev *cdev;
@@ -210,9 +170,9 @@ void pci_configure_slot(struct pci_dev *dev)
(dev->class >> 8) == PCI_CLASS_BRIDGE_PCI)))
return;
- ret = pci_set_payload(dev);
- if (ret)
- dev_warn(&dev->dev, "could not set device max payload\n");
+ if (dev->bus && dev->bus->self)
+ pcie_bus_configure_settings(dev->bus,
+ dev->bus->self->pcie_mpss);
memset(&hpp, 0, sizeof(hpp));
ret = pci_get_hp_params(dev, &hpp);
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index 1d002b1c2bf..c56a9413e1a 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -18,6 +18,7 @@
#undef DEBUG
#include <linux/init.h>
+#include <linux/module.h>
#include <linux/pci.h>
#include <linux/string.h>
#include <linux/vmalloc.h>
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index db057b6fe0c..6e373ea57b3 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -9,6 +9,7 @@
#include <linux/irq.h>
#include <linux/pci.h>
#include <linux/spinlock.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/htirq.h>
diff --git a/drivers/pci/ioapic.c b/drivers/pci/ioapic.c
index 203508b227b..5775638ac01 100644
--- a/drivers/pci/ioapic.c
+++ b/drivers/pci/ioapic.c
@@ -17,6 +17,7 @@
*/
#include <linux/pci.h>
+#include <linux/export.h>
#include <linux/acpi.h>
#include <linux/slab.h>
#include <acpi/acpi_bus.h>
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 42fae477651..b82c155d7b3 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -11,6 +11,7 @@
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/mutex.h>
+#include <linux/export.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/pci-ats.h>
@@ -722,145 +723,3 @@ int pci_num_vf(struct pci_dev *dev)
return dev->sriov->nr_virtfn;
}
EXPORT_SYMBOL_GPL(pci_num_vf);
-
-static int ats_alloc_one(struct pci_dev *dev, int ps)
-{
- int pos;
- u16 cap;
- struct pci_ats *ats;
-
- pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
- if (!pos)
- return -ENODEV;
-
- ats = kzalloc(sizeof(*ats), GFP_KERNEL);
- if (!ats)
- return -ENOMEM;
-
- ats->pos = pos;
- ats->stu = ps;
- pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
- ats->qdep = PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
- PCI_ATS_MAX_QDEP;
- dev->ats = ats;
-
- return 0;
-}
-
-static void ats_free_one(struct pci_dev *dev)
-{
- kfree(dev->ats);
- dev->ats = NULL;
-}
-
-/**
- * pci_enable_ats - enable the ATS capability
- * @dev: the PCI device
- * @ps: the IOMMU page shift
- *
- * Returns 0 on success, or negative on failure.
- */
-int pci_enable_ats(struct pci_dev *dev, int ps)
-{
- int rc;
- u16 ctrl;
-
- BUG_ON(dev->ats && dev->ats->is_enabled);
-
- if (ps < PCI_ATS_MIN_STU)
- return -EINVAL;
-
- if (dev->is_physfn || dev->is_virtfn) {
- struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
-
- mutex_lock(&pdev->sriov->lock);
- if (pdev->ats)
- rc = pdev->ats->stu == ps ? 0 : -EINVAL;
- else
- rc = ats_alloc_one(pdev, ps);
-
- if (!rc)
- pdev->ats->ref_cnt++;
- mutex_unlock(&pdev->sriov->lock);
- if (rc)
- return rc;
- }
-
- if (!dev->is_physfn) {
- rc = ats_alloc_one(dev, ps);
- if (rc)
- return rc;
- }
-
- ctrl = PCI_ATS_CTRL_ENABLE;
- if (!dev->is_virtfn)
- ctrl |= PCI_ATS_CTRL_STU(ps - PCI_ATS_MIN_STU);
- pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
-
- dev->ats->is_enabled = 1;
-
- return 0;
-}
-
-/**
- * pci_disable_ats - disable the ATS capability
- * @dev: the PCI device
- */
-void pci_disable_ats(struct pci_dev *dev)
-{
- u16 ctrl;
-
- BUG_ON(!dev->ats || !dev->ats->is_enabled);
-
- pci_read_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, &ctrl);
- ctrl &= ~PCI_ATS_CTRL_ENABLE;
- pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
-
- dev->ats->is_enabled = 0;
-
- if (dev->is_physfn || dev->is_virtfn) {
- struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
-
- mutex_lock(&pdev->sriov->lock);
- pdev->ats->ref_cnt--;
- if (!pdev->ats->ref_cnt)
- ats_free_one(pdev);
- mutex_unlock(&pdev->sriov->lock);
- }
-
- if (!dev->is_physfn)
- ats_free_one(dev);
-}
-
-/**
- * pci_ats_queue_depth - query the ATS Invalidate Queue Depth
- * @dev: the PCI device
- *
- * Returns the queue depth on success, or negative on failure.
- *
- * The ATS spec uses 0 in the Invalidate Queue Depth field to
- * indicate that the function can accept 32 Invalidate Request.
- * But here we use the `real' values (i.e. 1~32) for the Queue
- * Depth; and 0 indicates the function shares the Queue with
- * other functions (doesn't exclusively own a Queue).
- */
-int pci_ats_queue_depth(struct pci_dev *dev)
-{
- int pos;
- u16 cap;
-
- if (dev->is_virtfn)
- return 0;
-
- if (dev->ats)
- return dev->ats->qdep;
-
- pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
- if (!pos)
- return -ENODEV;
-
- pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
-
- return PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
- PCI_ATS_MAX_QDEP;
-}
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index de01174aff0..e5f69a43b1b 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -7,6 +7,7 @@
#include <linux/acpi.h>
#include <linux/device.h>
#include <linux/kernel.h>
+#include <linux/export.h>
#include <linux/pci.h>
static void pci_note_irq_problem(struct pci_dev *pdev, const char *reason)
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 2f10328bf66..0e6d04d7ba4 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -11,6 +11,7 @@
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/export.h>
#include <linux/ioport.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index c94d37ec55c..f0929934bb7 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -55,7 +55,7 @@ struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus)
*/
if (bus->bridge->of_node)
return of_node_get(bus->bridge->of_node);
- if (bus->bridge->parent->of_node)
+ if (bus->bridge->parent && bus->bridge->parent->of_node)
return of_node_get(bus->bridge->parent->of_node);
return NULL;
}
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index d36f41ea8cb..4ecb6408b0d 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -46,6 +46,9 @@ static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context)
struct pci_dev *pci_dev = context;
if (event == ACPI_NOTIFY_DEVICE_WAKE && pci_dev) {
+ if (pci_dev->pme_poll)
+ pci_dev->pme_poll = false;
+
pci_wakeup_event(pci_dev);
pci_check_pme_status(pci_dev);
pm_runtime_resume(&pci_dev->dev);
@@ -282,7 +285,6 @@ static int acpi_dev_run_wake(struct device *phys_dev, bool enable)
{
struct acpi_device *dev;
acpi_handle handle;
- int error = -ENODEV;
if (!device_run_wake(phys_dev))
return -EINVAL;
@@ -302,7 +304,7 @@ static int acpi_dev_run_wake(struct device *phys_dev, bool enable)
acpi_disable_wakeup_device_power(dev);
}
- return error;
+ return 0;
}
static void acpi_pci_propagate_run_wake(struct pci_bus *bus, bool enable)
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 7bcf12adced..106be0d08f8 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -19,6 +19,7 @@
#include <linux/sched.h>
#include <linux/pci.h>
#include <linux/stat.h>
+#include <linux/export.h>
#include <linux/topology.h>
#include <linux/mm.h>
#include <linux/fs.h>
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 08a95b369d8..6f45a73c6e9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -77,6 +77,8 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE;
unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE;
unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE;
+enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF;
+
/*
* The default CLS is used if arch didn't set CLS explicitly and not
* all pci devices agree on the same value. Arch can override either
@@ -1405,13 +1407,16 @@ bool pci_check_pme_status(struct pci_dev *dev)
/**
* pci_pme_wakeup - Wake up a PCI device if its PME Status bit is set.
* @dev: Device to handle.
- * @ign: Ignored.
+ * @pme_poll_reset: Whether or not to reset the device's pme_poll flag.
*
* Check if @dev has generated PME and queue a resume request for it in that
* case.
*/
-static int pci_pme_wakeup(struct pci_dev *dev, void *ign)
+static int pci_pme_wakeup(struct pci_dev *dev, void *pme_poll_reset)
{
+ if (pme_poll_reset && dev->pme_poll)
+ dev->pme_poll = false;
+
if (pci_check_pme_status(dev)) {
pci_wakeup_event(dev);
pm_request_resume(&dev->dev);
@@ -1426,7 +1431,7 @@ static int pci_pme_wakeup(struct pci_dev *dev, void *ign)
void pci_pme_wakeup_bus(struct pci_bus *bus)
{
if (bus)
- pci_walk_bus(bus, pci_pme_wakeup, NULL);
+ pci_walk_bus(bus, pci_pme_wakeup, (void *)true);
}
/**
@@ -1444,31 +1449,26 @@ bool pci_pme_capable(struct pci_dev *dev, pci_power_t state)
static void pci_pme_list_scan(struct work_struct *work)
{
- struct pci_pme_device *pme_dev;
+ struct pci_pme_device *pme_dev, *n;
mutex_lock(&pci_pme_list_mutex);
if (!list_empty(&pci_pme_list)) {
- list_for_each_entry(pme_dev, &pci_pme_list, list)
- pci_pme_wakeup(pme_dev->dev, NULL);
- schedule_delayed_work(&pci_pme_work, msecs_to_jiffies(PME_TIMEOUT));
+ list_for_each_entry_safe(pme_dev, n, &pci_pme_list, list) {
+ if (pme_dev->dev->pme_poll) {
+ pci_pme_wakeup(pme_dev->dev, NULL);
+ } else {
+ list_del(&pme_dev->list);
+ kfree(pme_dev);
+ }
+ }
+ if (!list_empty(&pci_pme_list))
+ schedule_delayed_work(&pci_pme_work,
+ msecs_to_jiffies(PME_TIMEOUT));
}
mutex_unlock(&pci_pme_list_mutex);
}
/**
- * pci_external_pme - is a device an external PCI PME source?
- * @dev: PCI device to check
- *
- */
-
-static bool pci_external_pme(struct pci_dev *dev)
-{
- if (pci_is_pcie(dev) || dev->bus->number == 0)
- return false;
- return true;
-}
-
-/**
* pci_pme_active - enable or disable PCI device's PME# function
* @dev: PCI device to handle.
* @enable: 'true' to enable PME# generation; 'false' to disable it.
@@ -1501,7 +1501,7 @@ void pci_pme_active(struct pci_dev *dev, bool enable)
hit, and the power savings from the devices will still be a
win. */
- if (pci_external_pme(dev)) {
+ if (dev->pme_poll) {
struct pci_pme_device *pme_dev;
if (enable) {
pme_dev = kmalloc(sizeof(struct pci_pme_device),
@@ -1819,6 +1819,7 @@ void pci_pm_init(struct pci_dev *dev)
(pmc & PCI_PM_CAP_PME_D3) ? " D3hot" : "",
(pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : "");
dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT;
+ dev->pme_poll = true;
/*
* Make device's PM flags reflect the wake-up capability, but
* let the user space enable it to wake up the system as needed.
@@ -3201,8 +3202,6 @@ int pcie_set_readrq(struct pci_dev *dev, int rq)
if (rq < 128 || rq > 4096 || !is_power_of_2(rq))
goto out;
- v = (ffs(rq) - 8) << 12;
-
cap = pci_pcie_cap(dev);
if (!cap)
goto out;
@@ -3210,6 +3209,22 @@ int pcie_set_readrq(struct pci_dev *dev, int rq)
err = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
if (err)
goto out;
+ /*
+ * If using the "performance" PCIe config, we clamp the
+ * read rq size to the max packet size to prevent the
+ * host bridge generating requests larger than we can
+ * cope with
+ */
+ if (pcie_bus_config == PCIE_BUS_PERFORMANCE) {
+ int mps = pcie_get_mps(dev);
+
+ if (mps < 0)
+ return mps;
+ if (mps < rq)
+ rq = mps;
+ }
+
+ v = (ffs(rq) - 8) << 12;
if ((ctl & PCI_EXP_DEVCTL_READRQ) != v) {
ctl &= ~PCI_EXP_DEVCTL_READRQ;
@@ -3223,6 +3238,67 @@ out:
EXPORT_SYMBOL(pcie_set_readrq);
/**
+ * pcie_get_mps - get PCI Express maximum payload size
+ * @dev: PCI device to query
+ *
+ * Returns maximum payload size in bytes
+ * or appropriate error value.
+ */
+int pcie_get_mps(struct pci_dev *dev)
+{
+ int ret, cap;
+ u16 ctl;
+
+ cap = pci_pcie_cap(dev);
+ if (!cap)
+ return -EINVAL;
+
+ ret = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
+ if (!ret)
+ ret = 128 << ((ctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5);
+
+ return ret;
+}
+
+/**
+ * pcie_set_mps - set PCI Express maximum payload size
+ * @dev: PCI device to query
+ * @mps: maximum payload size in bytes
+ * valid values are 128, 256, 512, 1024, 2048, 4096
+ *
+ * If possible sets maximum payload size
+ */
+int pcie_set_mps(struct pci_dev *dev, int mps)
+{
+ int cap, err = -EINVAL;
+ u16 ctl, v;
+
+ if (mps < 128 || mps > 4096 || !is_power_of_2(mps))
+ goto out;
+
+ v = ffs(mps) - 8;
+ if (v > dev->pcie_mpss)
+ goto out;
+ v <<= 5;
+
+ cap = pci_pcie_cap(dev);
+ if (!cap)
+ goto out;
+
+ err = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
+ if (err)
+ goto out;
+
+ if ((ctl & PCI_EXP_DEVCTL_PAYLOAD) != v) {
+ ctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
+ ctl |= v;
+ err = pci_write_config_word(dev, cap + PCI_EXP_DEVCTL, ctl);
+ }
+out:
+ return err;
+}
+
+/**
* pci_select_bars - Make BAR mask from the type of resource
* @dev: the PCI device for which BAR mask is made
* @flags: resource type mask to be selected
@@ -3505,6 +3581,14 @@ static int __init pci_setup(char *str)
pci_hotplug_io_size = memparse(str + 9, &str);
} else if (!strncmp(str, "hpmemsize=", 10)) {
pci_hotplug_mem_size = memparse(str + 10, &str);
+ } else if (!strncmp(str, "pcie_bus_tune_off", 17)) {
+ pcie_bus_config = PCIE_BUS_TUNE_OFF;
+ } else if (!strncmp(str, "pcie_bus_safe", 13)) {
+ pcie_bus_config = PCIE_BUS_SAFE;
+ } else if (!strncmp(str, "pcie_bus_perf", 13)) {
+ pcie_bus_config = PCIE_BUS_PERFORMANCE;
+ } else if (!strncmp(str, "pcie_bus_peer2peer", 18)) {
+ pcie_bus_config = PCIE_BUS_PEER2PEER;
} else {
printk(KERN_ERR "PCI: Unknown option `%s'\n",
str);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c8cee764b0d..b74084e9ca1 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -283,6 +283,8 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)
#endif /* CONFIG_PCI_IOV */
+extern unsigned long pci_cardbus_resource_alignment(struct resource *);
+
static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
struct resource *res)
{
@@ -292,6 +294,8 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END)
return pci_sriov_resource_alignment(dev, resno);
#endif
+ if (dev->class >> 8 == PCI_CLASS_BRIDGE_CARDBUS)
+ return pci_cardbus_resource_alignment(res);
return resource_alignment(res);
}
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 0057344a3fc..001f1b78f39 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -84,6 +84,9 @@ static bool pcie_pme_walk_bus(struct pci_bus *bus)
list_for_each_entry(dev, &bus->devices, bus_list) {
/* Skip PCIe devices in case we started from a root port. */
if (!pci_is_pcie(dev) && pci_check_pme_status(dev)) {
+ if (dev->pme_poll)
+ dev->pme_poll = false;
+
pci_wakeup_event(dev);
pm_request_resume(&dev->dev);
ret = true;
@@ -142,6 +145,9 @@ static void pcie_pme_handle_request(struct pci_dev *port, u16 req_id)
/* First, check if the PME is from the root port itself. */
if (port->devfn == devfn && port->bus->number == busnr) {
+ if (port->pme_poll)
+ port->pme_poll = false;
+
if (pci_check_pme_status(port)) {
pm_request_resume(&port->dev);
found = true;
@@ -187,6 +193,9 @@ static void pcie_pme_handle_request(struct pci_dev *port, u16 req_id)
/* The device is there, but we have to check its PME status. */
found = pci_check_pme_status(dev);
if (found) {
+ if (dev->pme_poll)
+ dev->pme_poll = false;
+
pci_wakeup_event(dev);
pm_request_resume(&dev->dev);
}
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 795c9026d55..04e74f48571 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -856,6 +856,8 @@ void set_pcie_port_type(struct pci_dev *pdev)
pdev->pcie_cap = pos;
pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4;
+ pci_read_config_word(pdev, pos + PCI_EXP_DEVCAP, &reg16);
+ pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD;
}
void set_pcie_hotplug_bridge(struct pci_dev *pdev)
@@ -1326,6 +1328,157 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
return nr;
}
+static int pcie_find_smpss(struct pci_dev *dev, void *data)
+{
+ u8 *smpss = data;
+
+ if (!pci_is_pcie(dev))
+ return 0;
+
+ /* For PCIE hotplug enabled slots not connected directly to a
+ * PCI-E root port, there can be problems when hotplugging
+ * devices. This is due to the possibility of hotplugging a
+ * device into the fabric with a smaller MPS that the devices
+ * currently running have configured. Modifying the MPS on the
+ * running devices could cause a fatal bus error due to an
+ * incoming frame being larger than the newly configured MPS.
+ * To work around this, the MPS for the entire fabric must be
+ * set to the minimum size. Any devices hotplugged into this
+ * fabric will have the minimum MPS set. If the PCI hotplug
+ * slot is directly connected to the root port and there are not
+ * other devices on the fabric (which seems to be the most
+ * common case), then this is not an issue and MPS discovery
+ * will occur as normal.
+ */
+ if (dev->is_hotplug_bridge && (!list_is_singular(&dev->bus->devices) ||
+ (dev->bus->self &&
+ dev->bus->self->pcie_type != PCI_EXP_TYPE_ROOT_PORT)))
+ *smpss = 0;
+
+ if (*smpss > dev->pcie_mpss)
+ *smpss = dev->pcie_mpss;
+
+ return 0;
+}
+
+static void pcie_write_mps(struct pci_dev *dev, int mps)
+{
+ int rc;
+
+ if (pcie_bus_config == PCIE_BUS_PERFORMANCE) {
+ mps = 128 << dev->pcie_mpss;
+
+ if (dev->pcie_type != PCI_EXP_TYPE_ROOT_PORT && dev->bus->self)
+ /* For "Performance", the assumption is made that
+ * downstream communication will never be larger than
+ * the MRRS. So, the MPS only needs to be configured
+ * for the upstream communication. This being the case,
+ * walk from the top down and set the MPS of the child
+ * to that of the parent bus.
+ *
+ * Configure the device MPS with the smaller of the
+ * device MPSS or the bridge MPS (which is assumed to be
+ * properly configured at this point to the largest
+ * allowable MPS based on its parent bus).
+ */
+ mps = min(mps, pcie_get_mps(dev->bus->self));
+ }
+
+ rc = pcie_set_mps(dev, mps);
+ if (rc)
+ dev_err(&dev->dev, "Failed attempting to set the MPS\n");
+}
+
+static void pcie_write_mrrs(struct pci_dev *dev)
+{
+ int rc, mrrs;
+
+ /* In the "safe" case, do not configure the MRRS. There appear to be
+ * issues with setting MRRS to 0 on a number of devices.
+ */
+ if (pcie_bus_config != PCIE_BUS_PERFORMANCE)
+ return;
+
+ /* For Max performance, the MRRS must be set to the largest supported
+ * value. However, it cannot be configured larger than the MPS the
+ * device or the bus can support. This should already be properly
+ * configured by a prior call to pcie_write_mps.
+ */
+ mrrs = pcie_get_mps(dev);
+
+ /* MRRS is a R/W register. Invalid values can be written, but a
+ * subsequent read will verify if the value is acceptable or not.
+ * If the MRRS value provided is not acceptable (e.g., too large),
+ * shrink the value until it is acceptable to the HW.
+ */
+ while (mrrs != pcie_get_readrq(dev) && mrrs >= 128) {
+ rc = pcie_set_readrq(dev, mrrs);
+ if (!rc)
+ break;
+
+ dev_warn(&dev->dev, "Failed attempting to set the MRRS\n");
+ mrrs /= 2;
+ }
+
+ if (mrrs < 128)
+ dev_err(&dev->dev, "MRRS was unable to be configured with a "
+ "safe value. If problems are experienced, try running "
+ "with pci=pcie_bus_safe.\n");
+}
+
+static int pcie_bus_configure_set(struct pci_dev *dev, void *data)
+{
+ int mps, orig_mps;
+
+ if (!pci_is_pcie(dev))
+ return 0;
+
+ mps = 128 << *(u8 *)data;
+ orig_mps = pcie_get_mps(dev);
+
+ pcie_write_mps(dev, mps);
+ pcie_write_mrrs(dev);
+
+ dev_info(&dev->dev, "PCI-E Max Payload Size set to %4d/%4d (was %4d), "
+ "Max Read Rq %4d\n", pcie_get_mps(dev), 128 << dev->pcie_mpss,
+ orig_mps, pcie_get_readrq(dev));
+
+ return 0;
+}
+
+/* pcie_bus_configure_settings requires that pci_walk_bus work in a top-down,
+ * parents then children fashion. If this changes, then this code will not
+ * work as designed.
+ */
+void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss)
+{
+ u8 smpss;
+
+ if (!pci_is_pcie(bus->self))
+ return;
+
+ if (pcie_bus_config == PCIE_BUS_TUNE_OFF)
+ return;
+
+ /* FIXME - Peer to peer DMA is possible, though the endpoint would need
+ * to be aware to the MPS of the destination. To work around this,
+ * simply force the MPS of the entire system to the smallest possible.
+ */
+ if (pcie_bus_config == PCIE_BUS_PEER2PEER)
+ smpss = 0;
+
+ if (pcie_bus_config == PCIE_BUS_SAFE) {
+ smpss = mpss;
+
+ pcie_find_smpss(bus->self, &smpss);
+ pci_walk_bus(bus, pcie_find_smpss, &smpss);
+ }
+
+ pcie_bus_configure_set(bus->self, &smpss);
+ pci_walk_bus(bus, pcie_bus_configure_set, &smpss);
+}
+EXPORT_SYMBOL_GPL(pcie_bus_configure_settings);
+
unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus)
{
unsigned int devfn, pass, max = bus->secondary;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 1196f61a4ab..64765474676 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -17,6 +17,7 @@
#include <linux/types.h>
#include <linux/kernel.h>
+#include <linux/export.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/delay.h>
@@ -2745,20 +2746,6 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
/* disable must be done via function #0 */
if (PCI_FUNC(dev->devfn))
return;
-
- pci_read_config_byte(dev, 0xCB, &disable);
-
- if (disable & 0x02)
- return;
-
- pci_read_config_byte(dev, 0xCA, &write_enable);
- pci_write_config_byte(dev, 0xCA, 0x57);
- pci_write_config_byte(dev, 0xCB, disable | 0x02);
- pci_write_config_byte(dev, 0xCA, write_enable);
-
- dev_notice(&dev->dev, "proprietary Ricoh MMC controller disabled (via firewire function)\n");
- dev_notice(&dev->dev, "MMC cards are now supported by standard SDHCI controller\n");
-
/*
* RICOH 0xe823 SD/MMC card reader fails to recognize
* certain types of SD/MMC cards. Lowering the SD base
@@ -2781,6 +2768,20 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev)
dev_notice(&dev->dev, "MMC controller base frequency changed to 50Mhz.\n");
}
+
+ pci_read_config_byte(dev, 0xCB, &disable);
+
+ if (disable & 0x02)
+ return;
+
+ pci_read_config_byte(dev, 0xCA, &write_enable);
+ pci_write_config_byte(dev, 0xCA, 0x57);
+ pci_write_config_byte(dev, 0xCB, disable | 0x02);
+ pci_write_config_byte(dev, 0xCA, write_enable);
+
+ dev_notice(&dev->dev, "proprietary Ricoh MMC controller disabled (via firewire function)\n");
+ dev_notice(&dev->dev, "MMC cards are now supported by standard SDHCI controller\n");
+
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
@@ -2788,7 +2789,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
#endif /*CONFIG_MMC_RICOH_MMC*/
-#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
+#ifdef CONFIG_DMAR_TABLE
#define VTUNCERRMSK_REG 0x1ac
#define VTD_MSK_SPEC_ERRORS (1 << 31)
/*
@@ -2822,6 +2823,89 @@ static void __devinit fixup_ti816x_class(struct pci_dev* dev)
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_TI, 0xb800, fixup_ti816x_class);
+/* Some PCIe devices do not work reliably with the claimed maximum
+ * payload size supported.
+ */
+static void __devinit fixup_mpss_256(struct pci_dev *dev)
+{
+ dev->pcie_mpss = 1; /* 256 bytes */
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
+ PCI_DEVICE_ID_SOLARFLARE_SFC4000A_0, fixup_mpss_256);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
+ PCI_DEVICE_ID_SOLARFLARE_SFC4000A_1, fixup_mpss_256);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
+ PCI_DEVICE_ID_SOLARFLARE_SFC4000B, fixup_mpss_256);
+
+/* Intel 5000 and 5100 Memory controllers have an errata with read completion
+ * coalescing (which is enabled by default on some BIOSes) and MPS of 256B.
+ * Since there is no way of knowing what the PCIE MPS on each fabric will be
+ * until all of the devices are discovered and buses walked, read completion
+ * coalescing must be disabled. Unfortunately, it cannot be re-enabled because
+ * it is possible to hotplug a device with MPS of 256B.
+ */
+static void __devinit quirk_intel_mc_errata(struct pci_dev *dev)
+{
+ int err;
+ u16 rcc;
+
+ if (pcie_bus_config == PCIE_BUS_TUNE_OFF)
+ return;
+
+ /* Intel errata specifies bits to change but does not say what they are.
+ * Keeping them magical until such time as the registers and values can
+ * be explained.
+ */
+ err = pci_read_config_word(dev, 0x48, &rcc);
+ if (err) {
+ dev_err(&dev->dev, "Error attempting to read the read "
+ "completion coalescing register.\n");
+ return;
+ }
+
+ if (!(rcc & (1 << 10)))
+ return;
+
+ rcc &= ~(1 << 10);
+
+ err = pci_write_config_word(dev, 0x48, rcc);
+ if (err) {
+ dev_err(&dev->dev, "Error attempting to write the read "
+ "completion coalescing register.\n");
+ return;
+ }
+
+ pr_info_once("Read completion coalescing disabled due to hardware "
+ "errata relating to 256B MPS.\n");
+}
+/* Intel 5000 series memory controllers and ports 2-7 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25c0, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25d0, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25d4, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25d8, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e2, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e3, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e4, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e5, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e6, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25e7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25f7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25f8, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25f9, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25fa, quirk_intel_mc_errata);
+/* Intel 5100 series memory controllers and ports 2-7 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65c0, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e2, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e3, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e4, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e5, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e6, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65e7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f7, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f8, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65f9, quirk_intel_mc_errata);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x65fa, quirk_intel_mc_errata);
+
static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f,
struct pci_fixup *end)
{
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 36864a935d6..48ebdb237f3 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -7,6 +7,7 @@
* PCI ROM access routines
*/
#include <linux/kernel.h>
+#include <linux/export.h>
#include <linux/pci.h>
#include <linux/slab.h>
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 8a1d3c7863a..86b69f85f90 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -34,6 +34,7 @@ struct resource_list_x {
resource_size_t start;
resource_size_t end;
resource_size_t add_size;
+ resource_size_t min_align;
unsigned long flags;
};
@@ -65,7 +66,7 @@ void pci_realloc(void)
*/
static void add_to_list(struct resource_list_x *head,
struct pci_dev *dev, struct resource *res,
- resource_size_t add_size)
+ resource_size_t add_size, resource_size_t min_align)
{
struct resource_list_x *list = head;
struct resource_list_x *ln = list->next;
@@ -84,13 +85,16 @@ static void add_to_list(struct resource_list_x *head,
tmp->end = res->end;
tmp->flags = res->flags;
tmp->add_size = add_size;
+ tmp->min_align = min_align;
list->next = tmp;
}
static void add_to_failed_list(struct resource_list_x *head,
struct pci_dev *dev, struct resource *res)
{
- add_to_list(head, dev, res, 0);
+ add_to_list(head, dev, res,
+ 0 /* dont care */,
+ 0 /* dont care */);
}
static void __dev_sort_resources(struct pci_dev *dev,
@@ -121,18 +125,18 @@ static inline void reset_resource(struct resource *res)
}
/**
- * adjust_resources_sorted() - satisfy any additional resource requests
+ * reassign_resources_sorted() - satisfy any additional resource requests
*
- * @add_head : head of the list tracking requests requiring additional
+ * @realloc_head : head of the list tracking requests requiring additional
* resources
* @head : head of the list tracking requests with allocated
* resources
*
- * Walk through each element of the add_head and try to procure
+ * Walk through each element of the realloc_head and try to procure
* additional resources for the element, provided the element
* is in the head list.
*/
-static void adjust_resources_sorted(struct resource_list_x *add_head,
+static void reassign_resources_sorted(struct resource_list_x *realloc_head,
struct resource_list *head)
{
struct resource *res;
@@ -141,8 +145,8 @@ static void adjust_resources_sorted(struct resource_list_x *add_head,
resource_size_t add_size;
int idx;
- prev = add_head;
- for (list = add_head->next; list;) {
+ prev = realloc_head;
+ for (list = realloc_head->next; list;) {
res = list->res;
/* skip resource that has been reset */
if (!res->flags)
@@ -159,13 +163,17 @@ static void adjust_resources_sorted(struct resource_list_x *add_head,
idx = res - &list->dev->resource[0];
add_size=list->add_size;
- if (!resource_size(res) && add_size) {
- res->end = res->start + add_size - 1;
- if(pci_assign_resource(list->dev, idx))
+ if (!resource_size(res)) {
+ res->start = list->start;
+ res->end = res->start + add_size - 1;
+ if(pci_assign_resource(list->dev, idx))
reset_resource(res);
- } else if (add_size) {
- adjust_resource(res, res->start,
- resource_size(res) + add_size);
+ } else {
+ resource_size_t align = list->min_align;
+ res->flags |= list->flags & (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN);
+ if (pci_reassign_resource(list->dev, idx, add_size, align))
+ dev_printk(KERN_DEBUG, &list->dev->dev, "failed to add optional resources res=%pR\n",
+ res);
}
out:
tmp = list;
@@ -210,16 +218,16 @@ static void assign_requested_resources_sorted(struct resource_list *head,
}
static void __assign_resources_sorted(struct resource_list *head,
- struct resource_list_x *add_head,
+ struct resource_list_x *realloc_head,
struct resource_list_x *fail_head)
{
/* Satisfy the must-have resource requests */
assign_requested_resources_sorted(head, fail_head);
- /* Try to satisfy any additional nice-to-have resource
+ /* Try to satisfy any additional optional resource
requests */
- if (add_head)
- adjust_resources_sorted(add_head, head);
+ if (realloc_head)
+ reassign_resources_sorted(realloc_head, head);
free_list(resource_list, head);
}
@@ -235,7 +243,7 @@ static void pdev_assign_resources_sorted(struct pci_dev *dev,
}
static void pbus_assign_resources_sorted(const struct pci_bus *bus,
- struct resource_list_x *add_head,
+ struct resource_list_x *realloc_head,
struct resource_list_x *fail_head)
{
struct pci_dev *dev;
@@ -245,7 +253,7 @@ static void pbus_assign_resources_sorted(const struct pci_bus *bus,
list_for_each_entry(dev, &bus->devices, bus_list)
__dev_sort_resources(dev, &head);
- __assign_resources_sorted(&head, add_head, fail_head);
+ __assign_resources_sorted(&head, realloc_head, fail_head);
}
void pci_setup_cardbus(struct pci_bus *bus)
@@ -418,7 +426,7 @@ static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type)
pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, bus->bridge_ctl);
}
-static void pci_setup_bridge(struct pci_bus *bus)
+void pci_setup_bridge(struct pci_bus *bus)
{
unsigned long type = IORESOURCE_IO | IORESOURCE_MEM |
IORESOURCE_PREFETCH;
@@ -540,13 +548,27 @@ static resource_size_t calculate_memsize(resource_size_t size,
return size;
}
+static resource_size_t get_res_add_size(struct resource_list_x *realloc_head,
+ struct resource *res)
+{
+ struct resource_list_x *list;
+
+ /* check if it is in realloc_head list */
+ for (list = realloc_head->next; list && list->res != res;
+ list = list->next);
+ if (list)
+ return list->add_size;
+
+ return 0;
+}
+
/**
* pbus_size_io() - size the io window of a given bus
*
* @bus : the bus
* @min_size : the minimum io window that must to be allocated
* @add_size : additional optional io window
- * @add_head : track the additional io window on this list
+ * @realloc_head : track the additional io window on this list
*
* Sizing the IO windows of the PCI-PCI bridge is trivial,
* since these windows have 4K granularity and the IO ranges
@@ -554,11 +576,12 @@ static resource_size_t calculate_memsize(resource_size_t size,
* We must be careful with the ISA aliasing though.
*/
static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
- resource_size_t add_size, struct resource_list_x *add_head)
+ resource_size_t add_size, struct resource_list_x *realloc_head)
{
struct pci_dev *dev;
struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO);
unsigned long size = 0, size0 = 0, size1 = 0;
+ resource_size_t children_add_size = 0;
if (!b_res)
return;
@@ -579,11 +602,16 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
size += r_size;
else
size1 += r_size;
+
+ if (realloc_head)
+ children_add_size += get_res_add_size(realloc_head, r);
}
}
size0 = calculate_iosize(size, min_size, size1,
resource_size(b_res), 4096);
- size1 = (!add_head || (add_head && !add_size)) ? size0 :
+ if (children_add_size > add_size)
+ add_size = children_add_size;
+ size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 :
calculate_iosize(size, min_size+add_size, size1,
resource_size(b_res), 4096);
if (!size0 && !size1) {
@@ -598,8 +626,8 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
b_res->start = 4096;
b_res->end = b_res->start + size0 - 1;
b_res->flags |= IORESOURCE_STARTALIGN;
- if (size1 > size0 && add_head)
- add_to_list(add_head, bus->self, b_res, size1-size0);
+ if (size1 > size0 && realloc_head)
+ add_to_list(realloc_head, bus->self, b_res, size1-size0, 4096);
}
/**
@@ -608,7 +636,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
* @bus : the bus
* @min_size : the minimum memory window that must to be allocated
* @add_size : additional optional memory window
- * @add_head : track the additional memory window on this list
+ * @realloc_head : track the additional memory window on this list
*
* Calculate the size of the bus and minimal alignment which
* guarantees that all child resources fit in this size.
@@ -616,7 +644,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
unsigned long type, resource_size_t min_size,
resource_size_t add_size,
- struct resource_list_x *add_head)
+ struct resource_list_x *realloc_head)
{
struct pci_dev *dev;
resource_size_t min_align, align, size, size0, size1;
@@ -624,6 +652,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
int order, max_order;
struct resource *b_res = find_free_bus_resource(bus, type);
unsigned int mem64_mask = 0;
+ resource_size_t children_add_size = 0;
if (!b_res)
return 0;
@@ -645,6 +674,16 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
if (r->parent || (r->flags & mask) != type)
continue;
r_size = resource_size(r);
+#ifdef CONFIG_PCI_IOV
+ /* put SRIOV requested res to the optional list */
+ if (realloc_head && i >= PCI_IOV_RESOURCES &&
+ i <= PCI_IOV_RESOURCE_END) {
+ r->end = r->start - 1;
+ add_to_list(realloc_head, dev, r, r_size, 0/* dont' care */);
+ children_add_size += r_size;
+ continue;
+ }
+#endif
/* For bridges size != alignment */
align = pci_resource_alignment(dev, r);
order = __ffs(align) - 20;
@@ -665,6 +704,9 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
if (order > max_order)
max_order = order;
mem64_mask &= r->flags & IORESOURCE_MEM_64;
+
+ if (realloc_head)
+ children_add_size += get_res_add_size(realloc_head, r);
}
}
align = 0;
@@ -681,7 +723,9 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
align += aligns[order];
}
size0 = calculate_memsize(size, min_size, 0, resource_size(b_res), min_align);
- size1 = (!add_head || (add_head && !add_size)) ? size0 :
+ if (children_add_size > add_size)
+ add_size = children_add_size;
+ size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 :
calculate_memsize(size, min_size+add_size, 0,
resource_size(b_res), min_align);
if (!size0 && !size1) {
@@ -695,12 +739,22 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
b_res->start = min_align;
b_res->end = size0 + min_align - 1;
b_res->flags |= IORESOURCE_STARTALIGN | mem64_mask;
- if (size1 > size0 && add_head)
- add_to_list(add_head, bus->self, b_res, size1-size0);
+ if (size1 > size0 && realloc_head)
+ add_to_list(realloc_head, bus->self, b_res, size1-size0, min_align);
return 1;
}
-static void pci_bus_size_cardbus(struct pci_bus *bus)
+unsigned long pci_cardbus_resource_alignment(struct resource *res)
+{
+ if (res->flags & IORESOURCE_IO)
+ return pci_cardbus_io_size;
+ if (res->flags & IORESOURCE_MEM)
+ return pci_cardbus_mem_size;
+ return 0;
+}
+
+static void pci_bus_size_cardbus(struct pci_bus *bus,
+ struct resource_list_x *realloc_head)
{
struct pci_dev *bridge = bus->self;
struct resource *b_res = &bridge->resource[PCI_BRIDGE_RESOURCES];
@@ -711,12 +765,14 @@ static void pci_bus_size_cardbus(struct pci_bus *bus)
* a fixed amount of bus space for CardBus bridges.
*/
b_res[0].start = 0;
- b_res[0].end = pci_cardbus_io_size - 1;
b_res[0].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN;
+ if (realloc_head)
+ add_to_list(realloc_head, bridge, b_res, pci_cardbus_io_size, 0 /* dont care */);
b_res[1].start = 0;
- b_res[1].end = pci_cardbus_io_size - 1;
b_res[1].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN;
+ if (realloc_head)
+ add_to_list(realloc_head, bridge, b_res+1, pci_cardbus_io_size, 0 /* dont care */);
/*
* Check whether prefetchable memory is supported
@@ -736,21 +792,31 @@ static void pci_bus_size_cardbus(struct pci_bus *bus)
*/
if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0) {
b_res[2].start = 0;
- b_res[2].end = pci_cardbus_mem_size - 1;
b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH | IORESOURCE_SIZEALIGN;
+ if (realloc_head)
+ add_to_list(realloc_head, bridge, b_res+2, pci_cardbus_mem_size, 0 /* dont care */);
b_res[3].start = 0;
- b_res[3].end = pci_cardbus_mem_size - 1;
b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN;
+ if (realloc_head)
+ add_to_list(realloc_head, bridge, b_res+3, pci_cardbus_mem_size, 0 /* dont care */);
} else {
b_res[3].start = 0;
- b_res[3].end = pci_cardbus_mem_size * 2 - 1;
b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN;
+ if (realloc_head)
+ add_to_list(realloc_head, bridge, b_res+3, pci_cardbus_mem_size * 2, 0 /* dont care */);
}
+
+ /* set the size of the resource to zero, so that the resource does not
+ * get assigned during required-resource allocation cycle but gets assigned
+ * during the optional-resource allocation cycle.
+ */
+ b_res[0].start = b_res[1].start = b_res[2].start = b_res[3].start = 1;
+ b_res[0].end = b_res[1].end = b_res[2].end = b_res[3].end = 0;
}
void __ref __pci_bus_size_bridges(struct pci_bus *bus,
- struct resource_list_x *add_head)
+ struct resource_list_x *realloc_head)
{
struct pci_dev *dev;
unsigned long mask, prefmask;
@@ -763,12 +829,12 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus,
switch (dev->class >> 8) {
case PCI_CLASS_BRIDGE_CARDBUS:
- pci_bus_size_cardbus(b);
+ pci_bus_size_cardbus(b, realloc_head);
break;
case PCI_CLASS_BRIDGE_PCI:
default:
- __pci_bus_size_bridges(b, add_head);
+ __pci_bus_size_bridges(b, realloc_head);
break;
}
}
@@ -792,7 +858,7 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus,
* Follow thru
*/
default:
- pbus_size_io(bus, 0, additional_io_size, add_head);
+ pbus_size_io(bus, 0, additional_io_size, realloc_head);
/* If the bridge supports prefetchable range, size it
separately. If it doesn't, or its prefetchable window
has already been allocated by arch code, try
@@ -800,11 +866,11 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus,
resources. */
mask = IORESOURCE_MEM;
prefmask = IORESOURCE_MEM | IORESOURCE_PREFETCH;
- if (pbus_size_mem(bus, prefmask, prefmask, 0, additional_mem_size, add_head))
+ if (pbus_size_mem(bus, prefmask, prefmask, 0, additional_mem_size, realloc_head))
mask = prefmask; /* Success, size non-prefetch only. */
else
additional_mem_size += additional_mem_size;
- pbus_size_mem(bus, mask, IORESOURCE_MEM, 0, additional_mem_size, add_head);
+ pbus_size_mem(bus, mask, IORESOURCE_MEM, 0, additional_mem_size, realloc_head);
break;
}
}
@@ -816,20 +882,20 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus)
EXPORT_SYMBOL(pci_bus_size_bridges);
static void __ref __pci_bus_assign_resources(const struct pci_bus *bus,
- struct resource_list_x *add_head,
+ struct resource_list_x *realloc_head,
struct resource_list_x *fail_head)
{
struct pci_bus *b;
struct pci_dev *dev;
- pbus_assign_resources_sorted(bus, add_head, fail_head);
+ pbus_assign_resources_sorted(bus, realloc_head, fail_head);
list_for_each_entry(dev, &bus->devices, bus_list) {
b = dev->subordinate;
if (!b)
continue;
- __pci_bus_assign_resources(b, add_head, fail_head);
+ __pci_bus_assign_resources(b, realloc_head, fail_head);
switch (dev->class >> 8) {
case PCI_CLASS_BRIDGE_PCI:
@@ -1039,7 +1105,7 @@ void __init
pci_assign_unassigned_resources(void)
{
struct pci_bus *bus;
- struct resource_list_x add_list; /* list of resources that
+ struct resource_list_x realloc_list; /* list of resources that
want additional resources */
int tried_times = 0;
enum release_type rel_type = leaf_only;
@@ -1052,7 +1118,7 @@ pci_assign_unassigned_resources(void)
head.next = NULL;
- add_list.next = NULL;
+ realloc_list.next = NULL;
pci_try_num = max_depth + 1;
printk(KERN_DEBUG "PCI: max bus depth: %d pci_try_num: %d\n",
@@ -1062,12 +1128,12 @@ again:
/* Depth first, calculate sizes and alignments of all
subordinate buses. */
list_for_each_entry(bus, &pci_root_buses, node)
- __pci_bus_size_bridges(bus, &add_list);
+ __pci_bus_size_bridges(bus, &realloc_list);
/* Depth last, allocate resources and update the hardware. */
list_for_each_entry(bus, &pci_root_buses, node)
- __pci_bus_assign_resources(bus, &add_list, &head);
- BUG_ON(add_list.next);
+ __pci_bus_assign_resources(bus, &realloc_list, &head);
+ BUG_ON(realloc_list.next);
tried_times++;
/* any device complain? */
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 319f359906e..5717509becb 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -18,6 +18,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
+#include <linux/export.h>
#include <linux/pci.h>
#include <linux/errno.h>
#include <linux/ioport.h>
@@ -128,16 +129,16 @@ void pci_disable_bridge_window(struct pci_dev *dev)
}
#endif /* CONFIG_PCI_QUIRKS */
+
+
static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
- int resno)
+ int resno, resource_size_t size, resource_size_t align)
{
struct resource *res = dev->resource + resno;
- resource_size_t size, min, align;
+ resource_size_t min;
int ret;
- size = resource_size(res);
min = (res->flags & IORESOURCE_IO) ? PCIBIOS_MIN_IO : PCIBIOS_MIN_MEM;
- align = pci_resource_alignment(dev, res);
/* First, try exact prefetching match.. */
ret = pci_bus_alloc_resource(bus, res, size, align, min,
@@ -154,56 +155,101 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
ret = pci_bus_alloc_resource(bus, res, size, align, min, 0,
pcibios_align_resource, dev);
}
+ return ret;
+}
- if (ret < 0 && dev->fw_addr[resno]) {
- struct resource *root, *conflict;
- resource_size_t start, end;
+static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
+ int resno, resource_size_t size)
+{
+ struct resource *root, *conflict;
+ resource_size_t start, end;
+ int ret = 0;
- /*
- * If we failed to assign anything, let's try the address
- * where firmware left it. That at least has a chance of
- * working, which is better than just leaving it disabled.
- */
+ if (res->flags & IORESOURCE_IO)
+ root = &ioport_resource;
+ else
+ root = &iomem_resource;
+
+ start = res->start;
+ end = res->end;
+ res->start = dev->fw_addr[resno];
+ res->end = res->start + size - 1;
+ dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n",
+ resno, res);
+ conflict = request_resource_conflict(root, res);
+ if (conflict) {
+ dev_info(&dev->dev,
+ "BAR %d: %pR conflicts with %s %pR\n", resno,
+ res, conflict->name, conflict);
+ res->start = start;
+ res->end = end;
+ ret = 1;
+ }
+ return ret;
+}
+
+static int _pci_assign_resource(struct pci_dev *dev, int resno, int size, resource_size_t min_align)
+{
+ struct resource *res = dev->resource + resno;
+ struct pci_bus *bus;
+ int ret;
+ char *type;
- if (res->flags & IORESOURCE_IO)
- root = &ioport_resource;
+ bus = dev->bus;
+ while ((ret = __pci_assign_resource(bus, dev, resno, size, min_align))) {
+ if (!bus->parent || !bus->self->transparent)
+ break;
+ bus = bus->parent;
+ }
+
+ if (ret) {
+ if (res->flags & IORESOURCE_MEM)
+ if (res->flags & IORESOURCE_PREFETCH)
+ type = "mem pref";
+ else
+ type = "mem";
+ else if (res->flags & IORESOURCE_IO)
+ type = "io";
else
- root = &iomem_resource;
-
- start = res->start;
- end = res->end;
- res->start = dev->fw_addr[resno];
- res->end = res->start + size - 1;
- dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n",
- resno, res);
- conflict = request_resource_conflict(root, res);
- if (conflict) {
- dev_info(&dev->dev,
- "BAR %d: %pR conflicts with %s %pR\n", resno,
- res, conflict->name, conflict);
- res->start = start;
- res->end = end;
- } else
- ret = 0;
+ type = "unknown";
+ dev_info(&dev->dev,
+ "BAR %d: can't assign %s (size %#llx)\n",
+ resno, type, (unsigned long long) resource_size(res));
}
+ return ret;
+}
+
+int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsize,
+ resource_size_t min_align)
+{
+ struct resource *res = dev->resource + resno;
+ resource_size_t new_size;
+ int ret;
+
+ if (!res->parent) {
+ dev_info(&dev->dev, "BAR %d: can't reassign an unassigned resouce %pR "
+ "\n", resno, res);
+ return -EINVAL;
+ }
+
+ new_size = resource_size(res) + addsize + min_align;
+ ret = _pci_assign_resource(dev, resno, new_size, min_align);
if (!ret) {
res->flags &= ~IORESOURCE_STARTALIGN;
dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res);
if (resno < PCI_BRIDGE_RESOURCES)
pci_update_resource(dev, resno);
}
-
return ret;
}
int pci_assign_resource(struct pci_dev *dev, int resno)
{
struct resource *res = dev->resource + resno;
- resource_size_t align;
+ resource_size_t align, size;
struct pci_bus *bus;
int ret;
- char *type;
align = pci_resource_alignment(dev, res);
if (!align) {
@@ -213,34 +259,27 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
}
bus = dev->bus;
- while ((ret = __pci_assign_resource(bus, dev, resno))) {
- if (bus->parent && bus->self->transparent)
- bus = bus->parent;
- else
- bus = NULL;
- if (bus)
- continue;
- break;
- }
+ size = resource_size(res);
+ ret = _pci_assign_resource(dev, resno, size, align);
- if (ret) {
- if (res->flags & IORESOURCE_MEM)
- if (res->flags & IORESOURCE_PREFETCH)
- type = "mem pref";
- else
- type = "mem";
- else if (res->flags & IORESOURCE_IO)
- type = "io";
- else
- type = "unknown";
- dev_info(&dev->dev,
- "BAR %d: can't assign %s (size %#llx)\n",
- resno, type, (unsigned long long) resource_size(res));
- }
+ /*
+ * If we failed to assign anything, let's try the address
+ * where firmware left it. That at least has a chance of
+ * working, which is better than just leaving it disabled.
+ */
+ if (ret < 0 && dev->fw_addr[resno])
+ ret = pci_revert_fw_address(res, dev, resno, size);
+ if (!ret) {
+ res->flags &= ~IORESOURCE_STARTALIGN;
+ dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res);
+ if (resno < PCI_BRIDGE_RESOURCES)
+ pci_update_resource(dev, resno);
+ }
return ret;
}
+
/* Sort resources by alignment */
void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head)
{
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 968cfea04f7..ac6412fb8d6 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -7,6 +7,7 @@
#include <linux/kobject.h>
#include <linux/slab.h>
+#include <linux/module.h>
#include <linux/pci.h>
#include <linux/err.h>
#include "pci.h"
diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c
index a5a5ca17cfe..39b79070335 100644
--- a/drivers/pci/vpd.c
+++ b/drivers/pci/vpd.c
@@ -6,6 +6,7 @@
*/
#include <linux/pci.h>
+#include <linux/export.h>
int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt)
{
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 6fa215a3861..90832a95599 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -400,9 +400,8 @@ static int pcifront_claim_resource(struct pci_dev *dev, void *data)
dev_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
pci_name(dev), i);
if (pci_claim_resource(dev, i)) {
- dev_err(&pdev->xdev->dev, "Could not claim "
- "resource %s/%d! Device offline. Try "
- "giving less than 4GB to domain.\n",
+ dev_err(&pdev->xdev->dev, "Could not claim resource %s/%d! "
+ "Device offline. Try using e820_host=1 in the guest config.\n",
pci_name(dev), i);
}
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-10-17 08:19:58 +0000