From 109cdbc223f6e2d6c80f8371f22415b50c18a366 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 18 May 2012 16:52:19 -0600
Subject: PCI: remove pci_bus_find_ext_capability() (unused)

pci_bus_find_ext_capability() is unused, and this patch removes it.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux/pci.h')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..2618ad99653 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -714,8 +714,6 @@ enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *dev);
 int pci_find_capability(struct pci_dev *dev, int cap);
 int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap);
 int pci_find_ext_capability(struct pci_dev *dev, int cap);
-int pci_bus_find_ext_capability(struct pci_bus *bus, unsigned int devfn,
-				int cap);
 int pci_find_ht_capability(struct pci_dev *dev, int ht_cap);
 int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap);
 struct pci_bus *pci_find_next_bus(const struct pci_bus *from);
-- 
cgit v1.2.3-70-g09d2


From 12ea6cad1c7d046e21decc18b0e2170c6794dc51 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 11 Jun 2012 05:26:55 +0000
Subject: PCI: add PCI DMA source ID quirk

DMA transactions are tagged with the source ID of the device making
the request.  Occasionally hardware screws this up and uses the
source ID of a different device (often the wrong function number of
a multifunction device).  A specific Ricoh multifunction device is
a prime example of this problem and included in this patch.

Given a pci_dev, this function returns the pci_dev to use as the
source ID for DMA.  When hardware works correctly, this returns
the input device.  For the components of the Ricoh multifunction
device, it returns the pci_dev for function 0.

This will be used by IOMMU drivers for determining the boundaries
of IOMMU groups as multiple devices using the same source ID must
be contained within the same group.  This can also be used by
existing streaming DMA paths for the same purpose.

[bhelgaas: fold in pci_dev_get() for !CONFIG_PCI]
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h  |  8 ++++++++
 2 files changed, 59 insertions(+)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 2a752167754..acd3956b44b 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3179,3 +3179,54 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 
 	return -ENOTTY;
 }
+
+static struct pci_dev *pci_func_0_dma_source(struct pci_dev *dev)
+{
+	if (!PCI_FUNC(dev->devfn))
+		return pci_dev_get(dev);
+
+	return pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+}
+
+static const struct pci_dev_dma_source {
+	u16 vendor;
+	u16 device;
+	struct pci_dev *(*dma_source)(struct pci_dev *dev);
+} pci_dev_dma_source[] = {
+	/*
+	 * https://bugzilla.redhat.com/show_bug.cgi?id=605888
+	 *
+	 * Some Ricoh devices use the function 0 source ID for DMA on
+	 * other functions of a multifunction device.  The DMA devices
+	 * is therefore function 0, which will have implications of the
+	 * iommu grouping of these devices.
+	 */
+	{ PCI_VENDOR_ID_RICOH, 0xe822, pci_func_0_dma_source },
+	{ PCI_VENDOR_ID_RICOH, 0xe230, pci_func_0_dma_source },
+	{ PCI_VENDOR_ID_RICOH, 0xe832, pci_func_0_dma_source },
+	{ PCI_VENDOR_ID_RICOH, 0xe476, pci_func_0_dma_source },
+	{ 0 }
+};
+
+/*
+ * IOMMUs with isolation capabilities need to be programmed with the
+ * correct source ID of a device.  In most cases, the source ID matches
+ * the device doing the DMA, but sometimes hardware is broken and will
+ * tag the DMA as being sourced from a different device.  This function
+ * allows that translation.  Note that the reference count of the
+ * returned device is incremented on all paths.
+ */
+struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
+{
+	const struct pci_dev_dma_source *i;
+
+	for (i = pci_dev_dma_source; i->dma_source; i++) {
+		if ((i->vendor == dev->vendor ||
+		     i->vendor == (u16)PCI_ANY_ID) &&
+		    (i->device == dev->device ||
+		     i->device == (u16)PCI_ANY_ID))
+			return i->dma_source(dev);
+	}
+
+	return pci_dev_get(dev);
+}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..39983be7b25 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1332,6 +1332,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
 static inline int pci_domain_nr(struct pci_bus *bus)
 { return 0; }
 
+static inline struct pci_dev *pci_dev_get(struct pci_dev *dev)
+{ return NULL; }
+
 #define dev_is_pci(d) (false)
 #define dev_is_pf(d) (false)
 #define dev_num_vf(d) (0)
@@ -1486,9 +1489,14 @@ enum pci_fixup_pass {
 
 #ifdef CONFIG_PCI_QUIRKS
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
+struct pci_dev *pci_get_dma_source(struct pci_dev *dev);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) {}
+static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
+{
+	return pci_dev_get(dev);
+}
 #endif
 
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
-- 
cgit v1.2.3-70-g09d2


From c32823f82b42abc1f08b365085862fd1d57c0b61 Mon Sep 17 00:00:00 2001
From: Myron Stowe <myron.stowe@redhat.com>
Date: Fri, 1 Jun 2012 15:16:25 -0600
Subject: PCI: make pci_ltr_supported() static

The PCI Express Latency Tolerance Reporting (LTR) feature's
pci_ltr_supported() routine is currently only used within
drivers/pci/pci.c so make it static.

Acked-by: Donald Dutile <ddutile@redhat.com>
Signed-off-by: Myron Stowe <myron.stowe@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 3 +--
 include/linux/pci.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 447e83472c0..847e0c35cdb 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2169,7 +2169,7 @@ EXPORT_SYMBOL(pci_disable_obff);
  * RETURNS:
  * True if @dev supports latency tolerance reporting, false otherwise.
  */
-bool pci_ltr_supported(struct pci_dev *dev)
+static bool pci_ltr_supported(struct pci_dev *dev)
 {
 	int pos;
 	u32 cap;
@@ -2185,7 +2185,6 @@ bool pci_ltr_supported(struct pci_dev *dev)
 
 	return cap & PCI_EXP_DEVCAP2_LTR;
 }
-EXPORT_SYMBOL(pci_ltr_supported);
 
 /**
  * pci_enable_ltr - enable latency tolerance reporting
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..b2bec26b7f0 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -875,7 +875,6 @@ enum pci_obff_signal_type {
 int pci_enable_obff(struct pci_dev *dev, enum pci_obff_signal_type);
 void pci_disable_obff(struct pci_dev *dev);
 
-bool pci_ltr_supported(struct pci_dev *dev);
 int pci_enable_ltr(struct pci_dev *dev);
 void pci_disable_ltr(struct pci_dev *dev);
 int pci_set_ltr(struct pci_dev *dev, int snoop_lat_ns, int nosnoop_lat_ns);
-- 
cgit v1.2.3-70-g09d2


From ad805758c0eb25bce7b2e3b298d63dc62a1bc71c Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 11 Jun 2012 05:27:07 +0000
Subject: PCI: add ACS validation utility

In a PCI environment, transactions aren't always required to reach
the root bus before being re-routed.  Intermediate switches between
an endpoint and the root bus can redirect DMA back downstream before
things like IOMMUs have a chance to intervene.  Legacy PCI is always
susceptible to this as it operates on a shared bus.  PCIe added a
new capability to describe and control this behavior, Access Control
Services, or ACS.

The utility function pci_acs_enabled() allows us to test the ACS
capabilities of an individual devices against a set of flags while
pci_acs_path_enabled() tests a complete path from a given downstream
device up to the specified upstream device.  We also include the
ability to add device specific tests as it's likely we'll see
devices that do not implement ACS, but want to indicate support
for various capabilities in this space.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c    | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/quirks.c | 33 +++++++++++++++++++++++++
 include/linux/pci.h  | 10 +++++++-
 3 files changed, 111 insertions(+), 1 deletion(-)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 447e83472c0..1ccf7d49f52 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2359,6 +2359,75 @@ void pci_enable_acs(struct pci_dev *dev)
 	pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
 }
 
+/**
+ * pci_acs_enabled - test ACS against required flags for a given device
+ * @pdev: device to test
+ * @acs_flags: required PCI ACS flags
+ *
+ * Return true if the device supports the provided flags.  Automatically
+ * filters out flags that are not implemented on multifunction devices.
+ */
+bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
+{
+	int pos, ret;
+	u16 ctrl;
+
+	ret = pci_dev_specific_acs_enabled(pdev, acs_flags);
+	if (ret >= 0)
+		return ret > 0;
+
+	if (!pci_is_pcie(pdev))
+		return false;
+
+	/* Filter out flags not applicable to multifunction */
+	if (pdev->multifunction)
+		acs_flags &= (PCI_ACS_RR | PCI_ACS_CR |
+			      PCI_ACS_EC | PCI_ACS_DT);
+
+	if (pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM ||
+	    pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT ||
+	    pdev->multifunction) {
+		pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS);
+		if (!pos)
+			return false;
+
+		pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl);
+		if ((ctrl & acs_flags) != acs_flags)
+			return false;
+	}
+
+	return true;
+}
+
+/**
+ * pci_acs_path_enable - test ACS flags from start to end in a hierarchy
+ * @start: starting downstream device
+ * @end: ending upstream device or NULL to search to the root bus
+ * @acs_flags: required flags
+ *
+ * Walk up a device tree from start to end testing PCI ACS support.  If
+ * any step along the way does not support the required flags, return false.
+ */
+bool pci_acs_path_enabled(struct pci_dev *start,
+			  struct pci_dev *end, u16 acs_flags)
+{
+	struct pci_dev *pdev, *parent = start;
+
+	do {
+		pdev = parent;
+
+		if (!pci_acs_enabled(pdev, acs_flags))
+			return false;
+
+		if (pci_is_root_bus(pdev->bus))
+			return (end == NULL);
+
+		parent = pdev->bus->self;
+	} while (pdev != end);
+
+	return true;
+}
+
 /**
  * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge
  * @dev: the PCI device
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index acd3956b44b..27e2c8f4ec7 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3230,3 +3230,36 @@ struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
 
 	return pci_dev_get(dev);
 }
+
+static const struct pci_dev_acs_enabled {
+	u16 vendor;
+	u16 device;
+	int (*acs_enabled)(struct pci_dev *dev, u16 acs_flags);
+} pci_dev_acs_enabled[] = {
+	{ 0 }
+};
+
+int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags)
+{
+	const struct pci_dev_acs_enabled *i;
+	int ret;
+
+	/*
+	 * Allow devices that do not expose standard PCIe ACS capabilities
+	 * or control to indicate their support here.  Multi-function express
+	 * devices which do not allow internal peer-to-peer between functions,
+	 * but do not implement PCIe ACS may wish to return true here.
+	 */
+	for (i = pci_dev_acs_enabled; i->acs_enabled; i++) {
+		if ((i->vendor == dev->vendor ||
+		     i->vendor == (u16)PCI_ANY_ID) &&
+		    (i->device == dev->device ||
+		     i->device == (u16)PCI_ANY_ID)) {
+			ret = i->acs_enabled(dev, acs_flags);
+			if (ret >= 0)
+				return ret;
+		}
+	}
+
+	return -ENOTTY;
+}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 39983be7b25..dd7af0f37b3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1490,6 +1490,7 @@ enum pci_fixup_pass {
 #ifdef CONFIG_PCI_QUIRKS
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
 struct pci_dev *pci_get_dma_source(struct pci_dev *dev);
+int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) {}
@@ -1497,6 +1498,11 @@ static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
 {
 	return pci_dev_get(dev);
 }
+static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
+					       u16 acs_flags)
+{
+	return -ENOTTY;
+}
 #endif
 
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
@@ -1599,7 +1605,9 @@ static inline bool pci_is_pcie(struct pci_dev *dev)
 }
 
 void pci_request_acs(void);
-
+bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags);
+bool pci_acs_path_enabled(struct pci_dev *start,
+			  struct pci_dev *end, u16 acs_flags);
 
 #define PCI_VPD_LRDT			0x80	/* Large Resource Data Type */
 #define PCI_VPD_LRDT_ID(x)		(x | PCI_VPD_LRDT)
-- 
cgit v1.2.3-70-g09d2


From c63587d7f5b9db84e71daf5962dc0394eb657da2 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 11 Jun 2012 05:27:19 +0000
Subject: PCI: export pci_user functions for use by other drivers

VFIO PCI support will make use of these for user-initiated
PCI config accesses.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/access.c | 6 ++++--
 drivers/pci/pci.h    | 7 -------
 include/linux/pci.h  | 8 ++++++++
 3 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 2a581642c23..ba91a7e1751 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -162,7 +162,8 @@ int pci_user_read_config_##size						\
 	if (ret > 0)							\
 		ret = -EINVAL;						\
 	return ret;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(pci_user_read_config_##size);
 
 /* Returns 0 on success, negative values indicate error. */
 #define PCI_USER_WRITE_CONFIG(size,type)				\
@@ -181,7 +182,8 @@ int pci_user_write_config_##size					\
 	if (ret > 0)							\
 		ret = -EINVAL;						\
 	return ret;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(pci_user_write_config_##size);
 
 PCI_USER_READ_CONFIG(byte, u8)
 PCI_USER_READ_CONFIG(word, u16)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index e4943479b23..f2dcc46bdec 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -86,13 +86,6 @@ static inline bool pci_is_bridge(struct pci_dev *pci_dev)
 	return !!(pci_dev->subordinate);
 }
 
-extern int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val);
-extern int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val);
-extern int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val);
-extern int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val);
-extern int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val);
-extern int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val);
-
 struct pci_vpd_ops {
 	ssize_t (*read)(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
 	ssize_t (*write)(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index dd7af0f37b3..9d04599c6bd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -777,6 +777,14 @@ static inline int pci_write_config_dword(const struct pci_dev *dev, int where,
 	return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
 }
 
+/* user-space driven config access */
+int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val);
+int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val);
+int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val);
+int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val);
+int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val);
+int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val);
+
 int __must_check pci_enable_device(struct pci_dev *dev);
 int __must_check pci_enable_device_io(struct pci_dev *dev);
 int __must_check pci_enable_device_mem(struct pci_dev *dev);
-- 
cgit v1.2.3-70-g09d2


From a6961651408afa9387d6df43c4a1dc4fd35dcb1b Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 11 Jun 2012 05:27:33 +0000
Subject: PCI: create common pcibios_err_to_errno

For returning errors out to non-PCI code.  Re-name xen's version.

Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/xen/xen-pciback/conf_space.c |  6 +++---
 include/linux/pci.h                  | 26 ++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 3 deletions(-)

(limited to 'include/linux/pci.h')

diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 30d7be026c1..46ae0f9f02a 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -124,7 +124,7 @@ static inline u32 merge_value(u32 val, u32 new_val, u32 new_val_mask,
 	return val;
 }
 
-static int pcibios_err_to_errno(int err)
+static int xen_pcibios_err_to_errno(int err)
 {
 	switch (err) {
 	case PCIBIOS_SUCCESSFUL:
@@ -202,7 +202,7 @@ out:
 		       pci_name(dev), size, offset, value);
 
 	*ret_val = value;
-	return pcibios_err_to_errno(err);
+	return xen_pcibios_err_to_errno(err);
 }
 
 int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
@@ -290,7 +290,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 		}
 	}
 
-	return pcibios_err_to_errno(err);
+	return xen_pcibios_err_to_errno(err);
 }
 
 void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 9d04599c6bd..a691f62bcf8 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -474,6 +474,32 @@ static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false;
 #define PCIBIOS_SET_FAILED		0x88
 #define PCIBIOS_BUFFER_TOO_SMALL	0x89
 
+/*
+ * Translate above to generic errno for passing back through non-pci.
+ */
+static inline int pcibios_err_to_errno(int err)
+{
+	if (err <= PCIBIOS_SUCCESSFUL)
+		return err; /* Assume already errno */
+
+	switch (err) {
+	case PCIBIOS_FUNC_NOT_SUPPORTED:
+		return -ENOENT;
+	case PCIBIOS_BAD_VENDOR_ID:
+		return -EINVAL;
+	case PCIBIOS_DEVICE_NOT_FOUND:
+		return -ENODEV;
+	case PCIBIOS_BAD_REGISTER_NUMBER:
+		return -EFAULT;
+	case PCIBIOS_SET_FAILED:
+		return -EIO;
+	case PCIBIOS_BUFFER_TOO_SMALL:
+		return -ENOSPC;
+	}
+
+	return -ENOTTY;
+}
+
 /* Low-level architecture-dependent routines */
 
 struct pci_ops {
-- 
cgit v1.2.3-70-g09d2


From 92f02430934ca1c1e991a1ab3541880575042697 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Thu, 17 May 2012 18:51:11 -0700
Subject: PCI: add busn_res in struct pci_bus

This adds a busn_res resource in struct pci_bus.  This will replace the
secondary/subordinate members and will be used to build a bus number
resource tree to help with bus number allocation.

[bhelgaas: changelog]
CC: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux/pci.h')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..ba7c5cd314b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -419,6 +419,7 @@ struct pci_bus {
 	struct list_head slots;		/* list of slots on this bus */
 	struct resource *resource[PCI_BRIDGE_RESOURCE_NUM];
 	struct list_head resources;	/* address space routed to this bus */
+	struct resource busn_res;	/* bus numbers routed to this bus */
 
 	struct pci_ops	*ops;		/* configuration access functions */
 	void		*sysdata;	/* hook for sys-specific extension */
-- 
cgit v1.2.3-70-g09d2


From 3527ed81ca01bbaf09df952e68528377a9cd092f Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Thu, 17 May 2012 18:51:11 -0700
Subject: PCI: remove secondary/subordinate in struct pci_bus

The pci_bus secondary/subordinate members are now unused, so remove them.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux/pci.h')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index ba7c5cd314b..6b10966cd1b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -427,8 +427,6 @@ struct pci_bus {
 
 	unsigned char	number;		/* bus number */
 	unsigned char	primary;	/* number of primary bridge */
-	unsigned char	secondary;	/* number of secondary bridge */
-	unsigned char	subordinate;	/* max number of subordinate buses */
 	unsigned char	max_bus_speed;	/* enum pci_bus_speed */
 	unsigned char	cur_bus_speed;	/* enum pci_bus_speed */
 
-- 
cgit v1.2.3-70-g09d2


From 98a3583107ed587ed3cfe2a1d8e5347421de5a80 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Fri, 18 May 2012 11:35:50 -0600
Subject: PCI: add busn_res operation functions

Will use them insert/update busn res in pci_bus struct.

[bhelgaas: print conflicting entry if insertion fails]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h |  3 +++
 2 files changed, 71 insertions(+)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 674a477a648..7662ab7b264 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1714,6 +1714,74 @@ err_out:
 	return NULL;
 }
 
+int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int bus_max)
+{
+	struct resource *res = &b->busn_res;
+	struct resource *parent_res, *conflict;
+
+	res->start = bus;
+	res->end = bus_max;
+	res->flags = IORESOURCE_BUS;
+
+	if (!pci_is_root_bus(b))
+		parent_res = &b->parent->busn_res;
+	else {
+		parent_res = get_pci_domain_busn_res(pci_domain_nr(b));
+		res->flags |= IORESOURCE_PCI_FIXED;
+	}
+
+	conflict = insert_resource_conflict(parent_res, res);
+
+	if (conflict)
+		dev_printk(KERN_DEBUG, &b->dev,
+			   "busn_res: can not insert %pR under %s%pR (conflicts with %s %pR)\n",
+			    res, pci_is_root_bus(b) ? "domain " : "",
+			    parent_res, conflict->name, conflict);
+	else
+		dev_printk(KERN_DEBUG, &b->dev,
+			   "busn_res: %pR is inserted under %s%pR\n",
+			   res, pci_is_root_bus(b) ? "domain " : "",
+			   parent_res);
+
+	return conflict == NULL;
+}
+
+int pci_bus_update_busn_res_end(struct pci_bus *b, int bus_max)
+{
+	struct resource *res = &b->busn_res;
+	struct resource old_res = *res;
+	resource_size_t size;
+	int ret;
+
+	if (res->start > bus_max)
+		return -EINVAL;
+
+	size = bus_max - res->start + 1;
+	ret = adjust_resource(res, res->start, size);
+	dev_printk(KERN_DEBUG, &b->dev,
+			"busn_res: %pR end %s updated to %02x\n",
+			&old_res, ret ? "can not be" : "is", bus_max);
+
+	if (!ret && !res->parent)
+		pci_bus_insert_busn_res(b, res->start, res->end);
+
+	return ret;
+}
+
+void pci_bus_release_busn_res(struct pci_bus *b)
+{
+	struct resource *res = &b->busn_res;
+	int ret;
+
+	if (!res->flags || !res->parent)
+		return;
+
+	ret = release_resource(res);
+	dev_printk(KERN_DEBUG, &b->dev,
+			"busn_res: %pR %s released\n",
+			res, ret ? "can not be" : "is");
+}
+
 struct pci_bus * __devinit pci_scan_root_bus(struct device *parent, int bus,
 		struct pci_ops *ops, void *sysdata, struct list_head *resources)
 {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 6b10966cd1b..c4df570f3bb 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -667,6 +667,9 @@ struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops, void *sysdata);
 struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 				    struct pci_ops *ops, void *sysdata,
 				    struct list_head *resources);
+int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int busmax);
+int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax);
+void pci_bus_release_busn_res(struct pci_bus *b);
 struct pci_bus * __devinit pci_scan_root_bus(struct device *parent, int bus,
 					     struct pci_ops *ops, void *sysdata,
 					     struct list_head *resources);
-- 
cgit v1.2.3-70-g09d2


From 67cdc827286366acb6c60c821013c1185ee00b36 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Thu, 17 May 2012 18:51:12 -0700
Subject: PCI: add default busn_resource

We need to put into the resources list for legacy system.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 7 +++++++
 include/linux/pci.h | 2 ++
 2 files changed, 9 insertions(+)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 6258f6f2498..68e75cb0831 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -16,6 +16,13 @@
 #define CARDBUS_LATENCY_TIMER	176	/* secondary latency timer */
 #define CARDBUS_RESERVE_BUSNR	3
 
+struct resource busn_resource = {
+	.name	= "PCI busn",
+	.start	= 0,
+	.end	= 255,
+	.flags	= IORESOURCE_BUS,
+};
+
 /* Ugh.  Need to stop exporting this to modules. */
 LIST_HEAD(pci_root_buses);
 EXPORT_SYMBOL(pci_root_buses);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c4df570f3bb..8c8b44d6210 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -368,6 +368,8 @@ static inline int pci_channel_offline(struct pci_dev *pdev)
 	return (pdev->error_state != pci_channel_io_normal);
 }
 
+extern struct resource busn_resource;
+
 struct pci_host_bridge_window {
 	struct list_head list;
 	struct resource *res;		/* host bridge aperture (CPU address) */
-- 
cgit v1.2.3-70-g09d2


From fbebb9fd22581b6422d60669c4ff86ce99d6cdba Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Sat, 16 Jun 2012 14:40:22 -0600
Subject: PCI: add infrastructure for devices with broken INTx masking

pci_intx_mask_supported() assumes INTx masking is supported if the
PCI_COMMAND_INTX_DISABLE bit is writable.  But when that bit is set,
some devices don't actually mask INTx or update PCI_STATUS_INTERRUPT
as we expect.

This patch adds a way for quirks to identify these broken devices.

[bhelgaas: split out from Chelsio quirk addition]
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c    |  3 +++
 drivers/pci/quirks.c | 10 ++++++++++
 include/linux/pci.h  |  1 +
 3 files changed, 14 insertions(+)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 447e83472c0..9ae517a6836 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2876,6 +2876,9 @@ bool pci_intx_mask_supported(struct pci_dev *dev)
 	bool mask_supported = false;
 	u16 orig, new;
 
+	if (dev->broken_intx_masking)
+		return false;
+
 	pci_cfg_access_lock(dev);
 
 	pci_read_config_word(dev, PCI_COMMAND, &orig);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 2a752167754..cc13415416d 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2929,6 +2929,16 @@ static void __devinit disable_igfx_irq(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq);
 
+/*
+ * Some devices may pass our check in pci_intx_mask_supported if
+ * PCI_COMMAND_INTX_DISABLE works though they actually do not properly
+ * support this feature.
+ */
+static void __devinit quirk_broken_intx_masking(struct pci_dev *dev)
+{
+	dev->broken_intx_masking = 1;
+}
+
 static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f,
 			  struct pci_fixup *end)
 {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..40a039f1dff 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -324,6 +324,7 @@ struct pci_dev {
 	unsigned int    is_hotplug_bridge:1;
 	unsigned int    __aer_firmware_first_valid:1;
 	unsigned int	__aer_firmware_first:1;
+	unsigned int	broken_intx_masking:1;
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
-- 
cgit v1.2.3-70-g09d2


From 448bd857d48e69b33ef323739dc6d8ca20d4cda7 Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Sat, 23 Jun 2012 10:23:51 +0800
Subject: PCI/PM: add PCIe runtime D3cold support

This patch adds runtime D3cold support and corresponding ACPI platform
support.  This patch only enables runtime D3cold support; it does not
enable D3cold support during system suspend/hibernate.

D3cold is the deepest power saving state for a PCIe device, where its main
power is removed.  While it is in D3cold, you can't access the device at
all, not even its configuration space (which is still accessible in D3hot).
Therefore the PCI PM registers can not be used to transition into/out of
the D3cold state; that must be done by platform logic such as ACPI _PR3.

To support wakeup from D3cold, a system may provide auxiliary power, which
allows a device to request wakeup using a Beacon or the sideband WAKE#
signal.  WAKE# is usually connected to platform logic such as ACPI GPE.
This is quite different from other power saving states, where devices
request wakeup via a PME message on the PCIe link.

Some devices, such as those in plug-in slots, have no direct platform
logic.  For example, there is usually no ACPI _PR3 for them.  D3cold
support for these devices can be done via the PCIe Downstream Port leading
to the device.  When the PCIe port is powered on/off, the device is powered
on/off too.  Wakeup events from the device will be notified to the
corresponding PCIe port.

For more information about PCIe D3cold and corresponding ACPI support,
please refer to:

- PCI Express Base Specification Revision 2.0
- Advanced Configuration and Power Interface Specification Revision 5.0

[bhelgaas: changelog]
Reviewed-by: Rafael J. Wysocki <rjw@sisk.pl>
Originally-by: Zheng Yan <zheng.z.yan@intel.com>
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci-acpi.c         |  23 +++++++--
 drivers/pci/pci-driver.c       |  10 +++-
 drivers/pci/pci-sysfs.c        |  29 +++++++++++
 drivers/pci/pci.c              | 114 +++++++++++++++++++++++++++++++++++++----
 drivers/pci/pci.h              |   1 +
 drivers/pci/pcie/portdrv_pci.c |  44 ++++++++++++++--
 include/linux/pci.h            |  16 ++++--
 7 files changed, 215 insertions(+), 22 deletions(-)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index a9efebc586b..e1658afef87 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -48,6 +48,12 @@ static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context)
 	if (event != ACPI_NOTIFY_DEVICE_WAKE || !pci_dev)
 		return;
 
+	if (pci_dev->current_state == PCI_D3cold) {
+		pci_wakeup_event(pci_dev);
+		pm_runtime_resume(&pci_dev->dev);
+		return;
+	}
+
 	if (!pci_dev->pm_cap || !pci_dev->pme_support
 	     || pci_check_pme_status(pci_dev)) {
 		if (pci_dev->pme_poll)
@@ -187,10 +193,13 @@ acpi_status pci_acpi_remove_pm_notifier(struct acpi_device *dev)
 
 static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
 {
-	int acpi_state;
+	int acpi_state, d_max;
 
-	acpi_state = acpi_pm_device_sleep_state(&pdev->dev, NULL,
-						ACPI_STATE_D3);
+	if (pdev->no_d3cold)
+		d_max = ACPI_STATE_D3_HOT;
+	else
+		d_max = ACPI_STATE_D3_COLD;
+	acpi_state = acpi_pm_device_sleep_state(&pdev->dev, NULL, d_max);
 	if (acpi_state < 0)
 		return PCI_POWER_ERROR;
 
@@ -297,7 +306,13 @@ static void acpi_pci_propagate_run_wake(struct pci_bus *bus, bool enable)
 
 static int acpi_pci_run_wake(struct pci_dev *dev, bool enable)
 {
-	if (dev->pme_interrupt)
+	/*
+	 * Per PCI Express Base Specification Revision 2.0 section
+	 * 5.3.3.2 Link Wakeup, platform support is needed for D3cold
+	 * waking up to power on the main link even if there is PME
+	 * support for D3cold
+	 */
+	if (dev->pme_interrupt && !dev->runtime_d3cold)
 		return 0;
 
 	if (!acpi_pm_device_run_wake(&dev->dev, enable))
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index bf0cee629b6..ca2e4c79a58 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1019,10 +1019,13 @@ static int pci_pm_runtime_suspend(struct device *dev)
 	if (!pm || !pm->runtime_suspend)
 		return -ENOSYS;
 
+	pci_dev->no_d3cold = false;
 	error = pm->runtime_suspend(dev);
 	suspend_report_result(pm->runtime_suspend, error);
 	if (error)
 		return error;
+	if (!pci_dev->d3cold_allowed)
+		pci_dev->no_d3cold = true;
 
 	pci_fixup_device(pci_fixup_suspend, pci_dev);
 
@@ -1044,6 +1047,7 @@ static int pci_pm_runtime_suspend(struct device *dev)
 
 static int pci_pm_runtime_resume(struct device *dev)
 {
+	int rc;
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 
@@ -1054,7 +1058,11 @@ static int pci_pm_runtime_resume(struct device *dev)
 	__pci_enable_wake(pci_dev, PCI_D0, true, false);
 	pci_fixup_device(pci_fixup_resume, pci_dev);
 
-	return pm->runtime_resume(dev);
+	rc = pm->runtime_resume(dev);
+
+	pci_dev->runtime_d3cold = false;
+
+	return rc;
 }
 
 static int pci_pm_runtime_idle(struct device *dev)
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 86c63fe45d1..1426db0c060 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -28,6 +28,7 @@
 #include <linux/pci-aspm.h>
 #include <linux/slab.h>
 #include <linux/vgaarb.h>
+#include <linux/pm_runtime.h>
 #include "pci.h"
 
 static int sysfs_initialized;	/* = 0 */
@@ -378,6 +379,31 @@ dev_bus_rescan_store(struct device *dev, struct device_attribute *attr,
 
 #endif
 
+#if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI)
+static ssize_t d3cold_allowed_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	unsigned long val;
+
+	if (strict_strtoul(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	pdev->d3cold_allowed = !!val;
+	pm_runtime_resume(dev);
+
+	return count;
+}
+
+static ssize_t d3cold_allowed_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	return sprintf (buf, "%u\n", pdev->d3cold_allowed);
+}
+#endif
+
 struct device_attribute pci_dev_attrs[] = {
 	__ATTR_RO(resource),
 	__ATTR_RO(vendor),
@@ -401,6 +427,9 @@ struct device_attribute pci_dev_attrs[] = {
 #ifdef CONFIG_HOTPLUG
 	__ATTR(remove, (S_IWUSR|S_IWGRP), NULL, remove_store),
 	__ATTR(rescan, (S_IWUSR|S_IWGRP), NULL, dev_rescan_store),
+#endif
+#if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI)
+	__ATTR(d3cold_allowed, 0644, d3cold_allowed_show, d3cold_allowed_store),
 #endif
 	__ATTR_NULL,
 };
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 9eae64b1795..8effb9b23ee 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -622,7 +622,8 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
 		dev_info(&dev->dev, "Refused to change power state, "
 			"currently in D%d\n", dev->current_state);
 
-	/* According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT
+	/*
+	 * According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT
 	 * INTERFACE SPECIFICATION, REV. 1.2", a device transitioning
 	 * from D3hot to D0 _may_ perform an internal reset, thereby
 	 * going to "D0 Uninitialized" rather than "D0 Initialized".
@@ -654,6 +655,16 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
 	if (dev->pm_cap) {
 		u16 pmcsr;
 
+		/*
+		 * Configuration space is not accessible for device in
+		 * D3cold, so just keep or set D3cold for safety
+		 */
+		if (dev->current_state == PCI_D3cold)
+			return;
+		if (state == PCI_D3cold) {
+			dev->current_state = PCI_D3cold;
+			return;
+		}
 		pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
 		dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
 	} else {
@@ -694,8 +705,50 @@ static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
  */
 static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
 {
-	if (state == PCI_D0)
+	if (state == PCI_D0) {
 		pci_platform_power_transition(dev, PCI_D0);
+		/*
+		 * Mandatory power management transition delays, see
+		 * PCI Express Base Specification Revision 2.0 Section
+		 * 6.6.1: Conventional Reset.  Do not delay for
+		 * devices powered on/off by corresponding bridge,
+		 * because have already delayed for the bridge.
+		 */
+		if (dev->runtime_d3cold) {
+			msleep(dev->d3cold_delay);
+			/*
+			 * When powering on a bridge from D3cold, the
+			 * whole hierarchy may be powered on into
+			 * D0uninitialized state, resume them to give
+			 * them a chance to suspend again
+			 */
+			pci_wakeup_bus(dev->subordinate);
+		}
+	}
+}
+
+/**
+ * __pci_dev_set_current_state - Set current state of a PCI device
+ * @dev: Device to handle
+ * @data: pointer to state to be set
+ */
+static int __pci_dev_set_current_state(struct pci_dev *dev, void *data)
+{
+	pci_power_t state = *(pci_power_t *)data;
+
+	dev->current_state = state;
+	return 0;
+}
+
+/**
+ * __pci_bus_set_current_state - Walk given bus and set current state of devices
+ * @bus: Top bus of the subtree to walk.
+ * @state: state to be set
+ */
+static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
+{
+	if (bus)
+		pci_walk_bus(bus, __pci_dev_set_current_state, &state);
 }
 
 /**
@@ -707,8 +760,15 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
  */
 int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state)
 {
-	return state >= PCI_D0 ?
-			pci_platform_power_transition(dev, state) : -EINVAL;
+	int ret;
+
+	if (state < PCI_D0)
+		return -EINVAL;
+	ret = pci_platform_power_transition(dev, state);
+	/* Power off the bridge may power off the whole hierarchy */
+	if (!ret && state == PCI_D3cold)
+		__pci_bus_set_current_state(dev->subordinate, PCI_D3cold);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
 
@@ -732,8 +792,8 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 	int error;
 
 	/* bound the state we're entering */
-	if (state > PCI_D3hot)
-		state = PCI_D3hot;
+	if (state > PCI_D3cold)
+		state = PCI_D3cold;
 	else if (state < PCI_D0)
 		state = PCI_D0;
 	else if ((state == PCI_D1 || state == PCI_D2) && pci_no_d1d2(dev))
@@ -748,10 +808,15 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 	/* This device is quirked not to be put into D3, so
 	   don't put it in D3 */
-	if (state == PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
+	if (state >= PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
 		return 0;
 
-	error = pci_raw_set_power_state(dev, state);
+	/*
+	 * To put device in D3cold, we put device into D3hot in native
+	 * way, then put device into D3cold with platform ops
+	 */
+	error = pci_raw_set_power_state(dev, state > PCI_D3hot ?
+					PCI_D3hot : state);
 
 	if (!__pci_complete_power_transition(dev, state))
 		error = 0;
@@ -1497,6 +1562,28 @@ void pci_pme_wakeup_bus(struct pci_bus *bus)
 		pci_walk_bus(bus, pci_pme_wakeup, (void *)true);
 }
 
+/**
+ * pci_wakeup - Wake up a PCI device
+ * @dev: Device to handle.
+ * @ign: ignored parameter
+ */
+static int pci_wakeup(struct pci_dev *pci_dev, void *ign)
+{
+	pci_wakeup_event(pci_dev);
+	pm_request_resume(&pci_dev->dev);
+	return 0;
+}
+
+/**
+ * pci_wakeup_bus - Walk given bus and wake up devices on it
+ * @bus: Top bus of the subtree to walk.
+ */
+void pci_wakeup_bus(struct pci_bus *bus)
+{
+	if (bus)
+		pci_walk_bus(bus, pci_wakeup, NULL);
+}
+
 /**
  * pci_pme_capable - check the capability of PCI device to generate PME#
  * @dev: PCI device to handle.
@@ -1754,6 +1841,10 @@ int pci_prepare_to_sleep(struct pci_dev *dev)
 	if (target_state == PCI_POWER_ERROR)
 		return -EIO;
 
+	/* D3cold during system suspend/hibernate is not supported */
+	if (target_state > PCI_D3hot)
+		target_state = PCI_D3hot;
+
 	pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev));
 
 	error = pci_set_power_state(dev, target_state);
@@ -1791,12 +1882,16 @@ int pci_finish_runtime_suspend(struct pci_dev *dev)
 	if (target_state == PCI_POWER_ERROR)
 		return -EIO;
 
+	dev->runtime_d3cold = target_state == PCI_D3cold;
+
 	__pci_enable_wake(dev, target_state, true, pci_dev_run_wake(dev));
 
 	error = pci_set_power_state(dev, target_state);
 
-	if (error)
+	if (error) {
 		__pci_enable_wake(dev, target_state, true, false);
+		dev->runtime_d3cold = false;
+	}
 
 	return error;
 }
@@ -1866,6 +1961,7 @@ void pci_pm_init(struct pci_dev *dev)
 
 	dev->pm_cap = pm;
 	dev->d3_delay = PCI_PM_D3_WAIT;
+	dev->d3cold_delay = PCI_PM_D3COLD_WAIT;
 
 	dev->d1_support = false;
 	dev->d2_support = false;
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index e4943479b23..5cd3dce7a24 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -70,6 +70,7 @@ extern void pci_update_current_state(struct pci_dev *dev, pci_power_t state);
 extern void pci_disable_enabled_device(struct pci_dev *dev);
 extern int pci_finish_runtime_suspend(struct pci_dev *dev);
 extern int __pci_pme_wakeup(struct pci_dev *dev, void *ign);
+extern void pci_wakeup_bus(struct pci_bus *bus);
 extern void pci_pm_init(struct pci_dev *dev);
 extern void platform_pci_wakeup_init(struct pci_dev *dev);
 extern void pci_allocate_cap_save_buffers(struct pci_dev *dev);
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 7c576b9aa01..3a7eefcb270 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -101,12 +101,48 @@ static int pcie_port_resume_noirq(struct device *dev)
 }
 
 #ifdef CONFIG_PM_RUNTIME
-static int pcie_port_runtime_pm(struct device *dev)
+struct d3cold_info {
+	bool no_d3cold;
+	unsigned int d3cold_delay;
+};
+
+static int pci_dev_d3cold_info(struct pci_dev *pdev, void *data)
+{
+	struct d3cold_info *info = data;
+
+	info->d3cold_delay = max_t(unsigned int, pdev->d3cold_delay,
+				   info->d3cold_delay);
+	if (pdev->no_d3cold)
+		info->no_d3cold = true;
+	return 0;
+}
+
+static int pcie_port_runtime_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct d3cold_info d3cold_info = {
+		.no_d3cold	= false,
+		.d3cold_delay	= PCI_PM_D3_WAIT,
+	};
+
+	/*
+	 * If any subordinate device disable D3cold, we should not put
+	 * the port into D3cold.  The D3cold delay of port should be
+	 * the max of that of all subordinate devices.
+	 */
+	pci_walk_bus(pdev->subordinate, pci_dev_d3cold_info, &d3cold_info);
+	pdev->no_d3cold = d3cold_info.no_d3cold;
+	pdev->d3cold_delay = d3cold_info.d3cold_delay;
+	return 0;
+}
+
+static int pcie_port_runtime_resume(struct device *dev)
 {
 	return 0;
 }
 #else
-#define pcie_port_runtime_pm	NULL
+#define pcie_port_runtime_suspend	NULL
+#define pcie_port_runtime_resume	NULL
 #endif
 
 static const struct dev_pm_ops pcie_portdrv_pm_ops = {
@@ -117,8 +153,8 @@ static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.poweroff	= pcie_port_device_suspend,
 	.restore	= pcie_port_device_resume,
 	.resume_noirq	= pcie_port_resume_noirq,
-	.runtime_suspend = pcie_port_runtime_pm,
-	.runtime_resume = pcie_port_runtime_pm,
+	.runtime_suspend = pcie_port_runtime_suspend,
+	.runtime_resume = pcie_port_runtime_resume,
 };
 
 #define PCIE_PORTDRV_PM_OPS	(&pcie_portdrv_pm_ops)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..002cfd3e33c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -132,9 +132,10 @@ static inline const char *pci_power_name(pci_power_t state)
 	return pci_power_names[1 + (int) state];
 }
 
-#define PCI_PM_D2_DELAY	200
-#define PCI_PM_D3_WAIT	10
-#define PCI_PM_BUS_WAIT	50
+#define PCI_PM_D2_DELAY		200
+#define PCI_PM_D3_WAIT		10
+#define PCI_PM_D3COLD_WAIT	100
+#define PCI_PM_BUS_WAIT		50
 
 /** The pci_channel state describes connectivity between the CPU and
  *  the pci device.  If some PCI bus between here and the pci device
@@ -278,11 +279,18 @@ struct pci_dev {
 	unsigned int	pme_poll:1;	/* Poll device's PME status bit */
 	unsigned int	d1_support:1;	/* Low power state D1 is supported */
 	unsigned int	d2_support:1;	/* Low power state D2 is supported */
-	unsigned int	no_d1d2:1;	/* Only allow D0 and D3 */
+	unsigned int	no_d1d2:1;	/* D1 and D2 are forbidden */
+	unsigned int	no_d3cold:1;	/* D3cold is forbidden */
+	unsigned int	d3cold_allowed:1;	/* D3cold is allowed by user */
 	unsigned int	mmio_always_on:1;	/* disallow turning off io/mem
 						   decoding during bar sizing */
 	unsigned int	wakeup_prepared:1;
+	unsigned int	runtime_d3cold:1;	/* whether go through runtime
+						   D3cold, not set for devices
+						   powered on/off by the
+						   corresponding bridge */
 	unsigned int	d3_delay;	/* D3->D0 transition time in ms */
+	unsigned int	d3cold_delay;	/* D3cold->D0 transition time in ms */
 
 #ifdef CONFIG_PCIEASPM
 	struct pcie_link_state	*link_state;	/* ASPM link state. */
-- 
cgit v1.2.3-70-g09d2


From 2b6f2c3520124e8bad4bffa71f5b98e602b9cf03 Mon Sep 17 00:00:00 2001
From: Myron Stowe <myron.stowe@redhat.com>
Date: Mon, 25 Jun 2012 21:30:57 -0600
Subject: PCI: pull pcibios_setup() up into core

Currently, all of the architectures implement their own pcibios_setup()
routine.  Most of the implementations do nothing so this patch introduces
a generic (__weak) routine in the core that can be used by all
architectures as a default.  If necessary, it can be overridden by
architecture-specific code.

Signed-off-by: Myron Stowe <myron.stowe@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 12 ++++++++++++
 include/linux/pci.h |  1 +
 2 files changed, 13 insertions(+)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 447e83472c0..c87d518acac 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2665,6 +2665,18 @@ static void __pci_set_master(struct pci_dev *dev, bool enable)
 	dev->is_busmaster = enable;
 }
 
+/**
+ * pcibios_setup - process "pci=" kernel boot arguments
+ * @str: string used to pass in "pci=" kernel boot arguments
+ *
+ * Process kernel boot arguments.  This is the default implementation.
+ * Architecture specific implementations can override this as necessary.
+ */
+char * __weak __init pcibios_setup(char *str)
+{
+	return str;
+}
+
 /**
  * pcibios_set_master - enable PCI bus-mastering for device dev
  * @dev: the PCI device to enable
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..f91143e86f8 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -642,6 +642,7 @@ extern int no_pci_devices(void);
 
 void pcibios_fixup_bus(struct pci_bus *);
 int __must_check pcibios_enable_device(struct pci_dev *, int mask);
+/* Architecture specific versions may override this (weak) */
 char *pcibios_setup(char *str);
 
 /* Used only when drivers/pci/setup.c is used */
-- 
cgit v1.2.3-70-g09d2


From 2b28ae1912e5ce5bb0527e352ae6ff04e76183d1 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 9 Jul 2012 13:38:57 -0600
Subject: PCI: reimplement P2P bridge 1K I/O windows (Intel P64H2)

9d265124d051 and 15a260d53f7c added quirks for P2P bridges that support
I/O windows that start/end at 1K boundaries, not just the 4K boundaries
defined by the PCI spec.  For details, see the IOBL_ADR register and the
EN1K bit in the CNF register in the Intel 82870P2 (P64H2).

These quirks complicate the code that reads P2P bridge windows
(pci_read_bridge_io() and pci_cfg_fake_ranges()) because the bridge
I/O resource is updated in the HEADER quirk, in pci_read_bridge_io(),
in pci_setup_bridge(), and again in the FINAL quirk.  This is confusing
and makes it impossible to reassign the bridge windows after FINAL
quirks are run.

This patch adds support for 1K windows in the generic paths, so the
HEADER quirk only has to enable this support.  The FINAL quirk, which
used to undo damage done by pci_setup_bridge(), is no longer needed.

This removes "if (!res->start) res->start = ..." from pci_read_bridge_io();
that was part of 9d265124d051 to avoid overwriting the resource filled in
by the quirk.  Since pci_read_bridge_io() itself now knows about
granularity, the quirk no longer updates the resource and this test is no
longer needed.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c      | 25 ++++++++++++++-----------
 drivers/pci/quirks.c     | 39 +--------------------------------------
 drivers/pci/setup-bus.c  | 11 +++++++++--
 include/linux/pci.h      |  1 +
 include/linux/pci_regs.h |  3 ++-
 5 files changed, 27 insertions(+), 52 deletions(-)

(limited to 'include/linux/pci.h')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 9c5d2a99299..ef24cf765b2 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -269,15 +269,23 @@ static void __devinit pci_read_bridge_io(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
 	u8 io_base_lo, io_limit_lo;
-	unsigned long base, limit;
+	unsigned long io_mask, io_granularity, base, limit;
 	struct pci_bus_region region;
-	struct resource *res, res2;
+	struct resource *res;
+
+	io_mask = PCI_IO_RANGE_MASK;
+	io_granularity = 0x1000;
+	if (dev->io_window_1k) {
+		/* Support 1K I/O space granularity */
+		io_mask = PCI_IO_1K_RANGE_MASK;
+		io_granularity = 0x400;
+	}
 
 	res = child->resource[0];
 	pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
 	pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
-	base = (io_base_lo & PCI_IO_RANGE_MASK) << 8;
-	limit = (io_limit_lo & PCI_IO_RANGE_MASK) << 8;
+	base = (io_base_lo & io_mask) << 8;
+	limit = (io_limit_lo & io_mask) << 8;
 
 	if ((io_base_lo & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32) {
 		u16 io_base_hi, io_limit_hi;
@@ -289,14 +297,9 @@ static void __devinit pci_read_bridge_io(struct pci_bus *child)
 
 	if (base <= limit) {
 		res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO;
-		res2.flags = res->flags;
 		region.start = base;
-		region.end = limit + 0xfff;
-		pcibios_bus_to_resource(dev, &res2, &region);
-		if (!res->start)
-			res->start = res2.start;
-		if (!res->end)
-			res->end = res2.end;
+		region.end = limit + io_granularity - 1;
+		pcibios_bus_to_resource(dev, res, &region);
 		dev_printk(KERN_DEBUG, &dev->dev, "  bridge window %pR\n", res);
 	}
 }
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 2a752167754..356846bd7ff 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1938,53 +1938,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, fixup_rev1
 static void __devinit quirk_p64h2_1k_io(struct pci_dev *dev)
 {
 	u16 en1k;
-	u8 io_base_lo, io_limit_lo;
-	unsigned long base, limit;
-	struct resource *res = dev->resource + PCI_BRIDGE_RESOURCES;
 
 	pci_read_config_word(dev, 0x40, &en1k);
 
 	if (en1k & 0x200) {
 		dev_info(&dev->dev, "Enable I/O Space to 1KB granularity\n");
-
-		pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo);
-		pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo);
-		base = (io_base_lo & (PCI_IO_RANGE_MASK | 0x0c)) << 8;
-		limit = (io_limit_lo & (PCI_IO_RANGE_MASK | 0x0c)) << 8;
-
-		if (base <= limit) {
-			res->start = base;
-			res->end = limit + 0x3ff;
-		}
+		dev->io_window_1k = 1;
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	0x1460,		quirk_p64h2_1k_io);
 
-/* Fix the IOBL_ADR for 1k I/O space granularity on the Intel P64H2
- * The IOBL_ADR gets re-written to 4k boundaries in pci_setup_bridge()
- * in drivers/pci/setup-bus.c
- */
-static void __devinit quirk_p64h2_1k_io_fix_iobl(struct pci_dev *dev)
-{
-	u16 en1k, iobl_adr, iobl_adr_1k;
-	struct resource *res = dev->resource + PCI_BRIDGE_RESOURCES;
-
-	pci_read_config_word(dev, 0x40, &en1k);
-
-	if (en1k & 0x200) {
-		pci_read_config_word(dev, PCI_IO_BASE, &iobl_adr);
-
-		iobl_adr_1k = iobl_adr | (res->start >> 8) | (res->end & 0xfc00);
-
-		if (iobl_adr != iobl_adr_1k) {
-			dev_info(&dev->dev, "Fixing P64H2 IOBL_ADR from 0x%x to 0x%x for 1KB granularity\n",
-				iobl_adr,iobl_adr_1k);
-			pci_write_config_word(dev, PCI_IO_BASE, iobl_adr_1k);
-		}
-	}
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x1460,		quirk_p64h2_1k_io_fix_iobl);
-
 /* Under some circumstances, AER is not linked with extended capabilities.
  * Force it to be linked by setting the corresponding control bit in the
  * config space.
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 8fa2d4be88d..dad5425f1f0 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -469,16 +469,23 @@ static void pci_setup_bridge_io(struct pci_bus *bus)
 	struct pci_dev *bridge = bus->self;
 	struct resource *res;
 	struct pci_bus_region region;
+	unsigned long io_mask;
+	u8 io_base_lo, io_limit_lo;
 	u32 l, io_upper16;
 
+	io_mask = PCI_IO_RANGE_MASK;
+	if (bridge->io_window_1k)
+		io_mask = PCI_IO_1K_RANGE_MASK;
+
 	/* Set up the top and bottom of the PCI I/O segment for this bus. */
 	res = bus->resource[0];
 	pcibios_resource_to_bus(bridge, &region, res);
 	if (res->flags & IORESOURCE_IO) {
 		pci_read_config_dword(bridge, PCI_IO_BASE, &l);
 		l &= 0xffff0000;
-		l |= (region.start >> 8) & 0x00f0;
-		l |= region.end & 0xf000;
+		io_base_lo = (region.start >> 8) & io_mask;
+		io_limit_lo = (region.end >> 8) & io_mask;
+		l |= ((u32) io_limit_lo << 8) | io_base_lo;
 		/* Set up upper 16 bits of I/O base/limit. */
 		io_upper16 = (region.end & 0xffff0000) | (region.start >> 16);
 		dev_info(&bridge->dev, "  bridge window %pR\n", res);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d8c379dba6a..89b46fd245c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -324,6 +324,7 @@ struct pci_dev {
 	unsigned int    is_hotplug_bridge:1;
 	unsigned int    __aer_firmware_first_valid:1;
 	unsigned int	__aer_firmware_first:1;
+	unsigned int	io_window_1k:1;	/* Intel P2P bridge 1K I/O windows */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index 4b608f54341..88c9ea56e25 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -125,7 +125,8 @@
 #define  PCI_IO_RANGE_TYPE_MASK	0x0fUL	/* I/O bridging type */
 #define  PCI_IO_RANGE_TYPE_16	0x00
 #define  PCI_IO_RANGE_TYPE_32	0x01
-#define  PCI_IO_RANGE_MASK	(~0x0fUL)
+#define  PCI_IO_RANGE_MASK	(~0x0fUL) /* Standard 4K I/O windows */
+#define  PCI_IO_1K_RANGE_MASK	(~0x03UL) /* Intel 1K I/O windows */
 #define PCI_SEC_STATUS		0x1e	/* Secondary status register, only bit 14 used */
 #define PCI_MEMORY_BASE		0x20	/* Memory range behind */
 #define PCI_MEMORY_LIMIT	0x22
-- 
cgit v1.2.3-70-g09d2