Merge branch 'pci/peer-to-peer'

- Add "pci=disable_acs_redir=" parameter to disable ACS redirection for
    peer-to-peer DMA support (we don't have the peer-to-peer support yet;
    this is just one piece) (Logan Gunthorpe)

* pci/peer-to-peer:
  PCI: Add ACS Redirect disable quirk for Intel Sunrise Point
  PCI: Add device-specific ACS Redirect disable infrastructure
  PCI: Convert device-specific ACS quirks from NULL termination to ARRAY_SIZE
  PCI: Add "pci=disable_acs_redir=" parameter for peer-to-peer support
  PCI: Allow specifying devices using a base bus and path of devfns
  PCI: Make specifying PCI devices in kernel parameters reusable
  PCI: Hide ACS quirk declarations inside PCI core

Documentation/admin-guide/kernel-parameters.txt

@@ -2994,7 +2994,30 @@
 			See header of drivers/block/paride/pcd.c.
 			See also Documentation/blockdev/paride.txt.
 
-	pci=option[,option...]	[PCI] various PCI subsystem options:
+	pci=option[,option...]	[PCI] various PCI subsystem options.
+
+				Some options herein operate on a specific device
+				or a set of devices (<pci_dev>). These are
+				specified in one of the following formats:
+
+				[<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]*
+				pci:<vendor>:<device>[:<subvendor>:<subdevice>]
+
+				Note: the first format specifies a PCI
+				bus/device/function address which may change
+				if new hardware is inserted, if motherboard
+				firmware changes, or due to changes caused
+				by other kernel parameters. If the
+				domain is left unspecified, it is
+				taken to be zero. Optionally, a path
+				to a device through multiple device/function
+				addresses can be specified after the base
+				address (this is more robust against
+				renumbering issues).  The second format
+				selects devices using IDs from the
+				configuration space which may match multiple
+				devices in the system.
+
 		earlydump	[X86] dump PCI config space before the kernel
 				changes anything
 		off		[X86] don't probe for the PCI bus
@@ -3123,11 +3146,10 @@
 				window. The default value is 64 megabytes.
 		resource_alignment=
 				Format:
-				[<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...]
+				[<order of align>@]<pci_dev>[; ...]
-				[<order of align>@]pci:<vendor>:<device>\
-						[:<subvendor>:<subdevice>][; ...]
 				Specifies alignment and device to reassign
-				aligned memory resources.
+				aligned memory resources. How to
+				specify the device is described above.
 				If <order of align> is not specified,
 				PAGE_SIZE is used as alignment.
 				PCI-PCI bridge can be specified, if resource
@@ -3170,6 +3192,15 @@
 				Adding the window is slightly risky (it may
 				conflict with unreported devices), so this
 				taints the kernel.
+		disable_acs_redir=<pci_dev>[; ...]
+				Specify one or more PCI devices (in the format
+				specified above) separated by semicolons.
+				Each device specified will have the PCI ACS
+				redirect capabilities forced off which will
+				allow P2P traffic between devices through
+				bridges without forcing it upstream. Note:
+				this removes isolation between devices and
+				may put more devices in an IOMMU group.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.

drivers/pci/pci.c

@@ -190,6 +190,168 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
 EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
 #endif
 
+/**
+ * pci_dev_str_match_path - test if a path string matches a device
+ * @dev:    the PCI device to test
+ * @p:      string to match the device against
+ * @endptr: pointer to the string after the match
+ *
+ * Test if a string (typically from a kernel parameter) formatted as a
+ * path of device/function addresses matches a PCI device. The string must
+ * be of the form:
+ *
+ *   [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
+ *
+ * A path for a device can be obtained using 'lspci -t'.  Using a path
+ * is more robust against bus renumbering than using only a single bus,
+ * device and function address.
+ *
+ * Returns 1 if the string matches the device, 0 if it does not and
+ * a negative error code if it fails to parse the string.
+ */
+static int pci_dev_str_match_path(struct pci_dev *dev, const char *path,
+				  const char **endptr)
+{
+	int ret;
+	int seg, bus, slot, func;
+	char *wpath, *p;
+	char end;
+
+	*endptr = strchrnul(path, ';');
+
+	wpath = kmemdup_nul(path, *endptr - path, GFP_KERNEL);
+	if (!wpath)
+		return -ENOMEM;
+
+	while (1) {
+		p = strrchr(wpath, '/');
+		if (!p)
+			break;
+		ret = sscanf(p, "/%x.%x%c", &slot, &func, &end);
+		if (ret != 2) {
+			ret = -EINVAL;
+			goto free_and_exit;
+		}
+
+		if (dev->devfn != PCI_DEVFN(slot, func)) {
+			ret = 0;
+			goto free_and_exit;
+		}
+
+		/*
+		 * Note: we don't need to get a reference to the upstream
+		 * bridge because we hold a reference to the top level
+		 * device which should hold a reference to the bridge,
+		 * and so on.
+		 */
+		dev = pci_upstream_bridge(dev);
+		if (!dev) {
+			ret = 0;
+			goto free_and_exit;
+		}
+
+		*p = 0;
+	}
+
+	ret = sscanf(wpath, "%x:%x:%x.%x%c", &seg, &bus, &slot,
+		     &func, &end);
+	if (ret != 4) {
+		seg = 0;
+		ret = sscanf(wpath, "%x:%x.%x%c", &bus, &slot, &func, &end);
+		if (ret != 3) {
+			ret = -EINVAL;
+			goto free_and_exit;
+		}
+	}
+
+	ret = (seg == pci_domain_nr(dev->bus) &&
+	       bus == dev->bus->number &&
+	       dev->devfn == PCI_DEVFN(slot, func));
+
+free_and_exit:
+	kfree(wpath);
+	return ret;
+}
+
+/**
+ * pci_dev_str_match - test if a string matches a device
+ * @dev:    the PCI device to test
+ * @p:      string to match the device against
+ * @endptr: pointer to the string after the match
+ *
+ * Test if a string (typically from a kernel parameter) matches a specified
+ * PCI device. The string may be of one of the following formats:
+ *
+ *   [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
+ *   pci:<vendor>:<device>[:<subvendor>:<subdevice>]
+ *
+ * The first format specifies a PCI bus/device/function address which
+ * may change if new hardware is inserted, if motherboard firmware changes,
+ * or due to changes caused in kernel parameters. If the domain is
+ * left unspecified, it is taken to be 0.  In order to be robust against
+ * bus renumbering issues, a path of PCI device/function numbers may be used
+ * to address the specific device.  The path for a device can be determined
+ * through the use of 'lspci -t'.
+ *
+ * The second format matches devices using IDs in the configuration
+ * space which may match multiple devices in the system. A value of 0
+ * for any field will match all devices. (Note: this differs from
+ * in-kernel code that uses PCI_ANY_ID which is ~0; this is for
+ * legacy reasons and convenience so users don't have to specify
+ * FFFFFFFFs on the command line.)
+ *
+ * Returns 1 if the string matches the device, 0 if it does not and
+ * a negative error code if the string cannot be parsed.
+ */
+static int pci_dev_str_match(struct pci_dev *dev, const char *p,
+			     const char **endptr)
+{
+	int ret;
+	int count;
+	unsigned short vendor, device, subsystem_vendor, subsystem_device;
+
+	if (strncmp(p, "pci:", 4) == 0) {
+		/* PCI vendor/device (subvendor/subdevice) IDs are specified */
+		p += 4;
+		ret = sscanf(p, "%hx:%hx:%hx:%hx%n", &vendor, &device,
+			     &subsystem_vendor, &subsystem_device, &count);
+		if (ret != 4) {
+			ret = sscanf(p, "%hx:%hx%n", &vendor, &device, &count);
+			if (ret != 2)
+				return -EINVAL;
+
+			subsystem_vendor = 0;
+			subsystem_device = 0;
+		}
+
+		p += count;
+
+		if ((!vendor || vendor == dev->vendor) &&
+		    (!device || device == dev->device) &&
+		    (!subsystem_vendor ||
+			    subsystem_vendor == dev->subsystem_vendor) &&
+		    (!subsystem_device ||
+			    subsystem_device == dev->subsystem_device))
+			goto found;
+	} else {
+		/*
+		 * PCI Bus, Device, Function IDs are specified
+		 *  (optionally, may include a path of devfns following it)
+		 */
+		ret = pci_dev_str_match_path(dev, p, &p);
+		if (ret < 0)
+			return ret;
+		else if (ret)
+			goto found;
+	}
+
+	*endptr = p;
+	return 0;
+
+found:
+	*endptr = p;
+	return 1;
+}
 
 static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
 				   u8 pos, int cap, int *ttl)
@@ -2829,6 +2991,66 @@ void pci_request_acs(void)
 	pci_acs_enable = 1;
 }
 
+static const char *disable_acs_redir_param;
+
+/**
+ * pci_disable_acs_redir - disable ACS redirect capabilities
+ * @dev: the PCI device
+ *
+ * For only devices specified in the disable_acs_redir parameter.
+ */
+static void pci_disable_acs_redir(struct pci_dev *dev)
+{
+	int ret = 0;
+	const char *p;
+	int pos;
+	u16 ctrl;
+
+	if (!disable_acs_redir_param)
+		return;
+
+	p = disable_acs_redir_param;
+	while (*p) {
+		ret = pci_dev_str_match(dev, p, &p);
+		if (ret < 0) {
+			pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n",
+				     disable_acs_redir_param);
+
+			break;
+		} else if (ret == 1) {
+			/* Found a match */
+			break;
+		}
+
+		if (*p != ';' && *p != ',') {
+			/* End of param or invalid format */
+			break;
+		}
+		p++;
+	}
+
+	if (ret != 1)
+		return;
+
+	if (!pci_dev_specific_disable_acs_redir(dev))
+		return;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos) {
+		pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n");
+		return;
+	}
+
+	pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
+
+	/* P2P Request & Completion Redirect */
+	ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+	pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+
+	pci_info(dev, "disabled ACS redirect\n");
+}
+
 /**
  * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites
  * @dev: the PCI device
@@ -2868,12 +3090,22 @@ static void pci_std_enable_acs(struct pci_dev *dev)
 void pci_enable_acs(struct pci_dev *dev)
 {
 	if (!pci_acs_enable)
-		return;
+		goto disable_acs_redir;
 
 	if (!pci_dev_specific_enable_acs(dev))
-		return;
+		goto disable_acs_redir;
 
 	pci_std_enable_acs(dev);
+
+disable_acs_redir:
+	/*
+	 * Note: pci_disable_acs_redir() must be called even if ACS was not
+	 * enabled by the kernel because it may have been enabled by
+	 * platform firmware.  So if we are told to disable it, we should
+	 * always disable it after setting the kernel's default
+	 * preferences.
+	 */
+	pci_disable_acs_redir(dev);
 }
 
 static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
@@ -5514,10 +5746,10 @@ static DEFINE_SPINLOCK(resource_alignment_lock);
 static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
 							bool *resize)
 {
-	int seg, bus, slot, func, align_order, count;
+	int align_order, count;
-	unsigned short vendor, device, subsystem_vendor, subsystem_device;
 	resource_size_t align = pcibios_default_alignment();
-	char *p;
+	const char *p;
+	int ret;
 
 	spin_lock(&resource_alignment_lock);
 	p = resource_alignment_param;
@@ -5537,58 +5769,21 @@ static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
 		} else {
 			align_order = -1;
 		}
-		if (strncmp(p, "pci:", 4) == 0) {
+
-			/* PCI vendor/device (subvendor/subdevice) ids are specified */
+		ret = pci_dev_str_match(dev, p, &p);
-			p += 4;
+		if (ret == 1) {
-			if (sscanf(p, "%hx:%hx:%hx:%hx%n",
-				&vendor, &device, &subsystem_vendor, &subsystem_device, &count) != 4) {
-				if (sscanf(p, "%hx:%hx%n", &vendor, &device, &count) != 2) {
-					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: pci:%s\n",
-						p);
-					break;
-				}
-				subsystem_vendor = subsystem_device = 0;
-			}
-			p += count;
-			if ((!vendor || (vendor == dev->vendor)) &&
-				(!device || (device == dev->device)) &&
-				(!subsystem_vendor || (subsystem_vendor == dev->subsystem_vendor)) &&
-				(!subsystem_device || (subsystem_device == dev->subsystem_device))) {
 			*resize = true;
 			if (align_order == -1)
 				align = PAGE_SIZE;
 			else
 				align = 1 << align_order;
-				/* Found */
 			break;
-			}
+		} else if (ret < 0) {
-		}
+			pr_err("PCI: Can't parse resource_alignment parameter: %s\n",
-		else {
-			if (sscanf(p, "%x:%x:%x.%x%n",
-				&seg, &bus, &slot, &func, &count) != 4) {
-				seg = 0;
-				if (sscanf(p, "%x:%x.%x%n",
-						&bus, &slot, &func, &count) != 3) {
-					/* Invalid format */
-					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n",
 			       p);
 			break;
 		}
-			}
+
-			p += count;
-			if (seg == pci_domain_nr(dev->bus) &&
-				bus == dev->bus->number &&
-				slot == PCI_SLOT(dev->devfn) &&
-				func == PCI_FUNC(dev->devfn)) {
-				*resize = true;
-				if (align_order == -1)
-					align = PAGE_SIZE;
-				else
-					align = 1 << align_order;
-				/* Found */
-				break;
-			}
-		}
 		if (*p != ';' && *p != ',') {
 			/* End of param or invalid format */
 			break;
@@ -5901,6 +6096,8 @@ static int __init pci_setup(char *str)
 				pcie_bus_config = PCIE_BUS_PEER2PEER;
 			} else if (!strncmp(str, "pcie_scan_all", 13)) {
 				pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
+			} else if (!strncmp(str, "disable_acs_redir=", 18)) {
+				disable_acs_redir_param = str + 18;
 			} else {
 				printk(KERN_ERR "PCI: Unknown option `%s'\n",
 						str);

drivers/pci/pci.h

@@ -400,6 +400,25 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 }
 
 void pci_enable_acs(struct pci_dev *dev);
+#ifdef CONFIG_PCI_QUIRKS
+int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
+int pci_dev_specific_enable_acs(struct pci_dev *dev);
+int pci_dev_specific_disable_acs_redir(struct pci_dev *dev);
+#else
+static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
+					       u16 acs_flags)
+{
+	return -ENOTTY;
+}
+static inline int pci_dev_specific_enable_acs(struct pci_dev *dev)
+{
+	return -ENOTTY;
+}
+static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
+{
+	return -ENOTTY;
+}
+#endif
 
 /* PCI error reporting and recovery */
 void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service);

drivers/pci/quirks.c

@@ -4555,27 +4555,79 @@ static int pci_quirk_enable_intel_spt_pch_acs(struct pci_dev *dev)
 	return 0;
 }
 
-static const struct pci_dev_enable_acs {
+static int pci_quirk_disable_intel_spt_pch_acs_redir(struct pci_dev *dev)
+{
+	int pos;
+	u32 cap, ctrl;
+
+	if (!pci_quirk_intel_spt_pch_acs_match(dev))
+		return -ENOTTY;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos)
+		return -ENOTTY;
+
+	pci_read_config_dword(dev, pos + PCI_ACS_CAP, &cap);
+	pci_read_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, &ctrl);
+
+	ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+	pci_write_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, ctrl);
+
+	pci_info(dev, "Intel SPT PCH root port workaround: disabled ACS redirect\n");
+
+	return 0;
+}
+
+static const struct pci_dev_acs_ops {
 	u16 vendor;
 	u16 device;
 	int (*enable_acs)(struct pci_dev *dev);
-} pci_dev_enable_acs[] = {
+	int (*disable_acs_redir)(struct pci_dev *dev);
-	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_pch_acs },
+} pci_dev_acs_ops[] = {
-	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_spt_pch_acs },
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
-	{ 0 }
+	    .enable_acs = pci_quirk_enable_intel_pch_acs,
+	},
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+	    .enable_acs = pci_quirk_enable_intel_spt_pch_acs,
+	    .disable_acs_redir = pci_quirk_disable_intel_spt_pch_acs_redir,
+	},
 };
 
 int pci_dev_specific_enable_acs(struct pci_dev *dev)
 {
-	const struct pci_dev_enable_acs *i;
+	const struct pci_dev_acs_ops *p;
-	int ret;
+	int i, ret;
 
-	for (i = pci_dev_enable_acs; i->enable_acs; i++) {
+	for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) {
-		if ((i->vendor == dev->vendor ||
+		p = &pci_dev_acs_ops[i];
-		     i->vendor == (u16)PCI_ANY_ID) &&
+		if ((p->vendor == dev->vendor ||
-		    (i->device == dev->device ||
+		     p->vendor == (u16)PCI_ANY_ID) &&
-		     i->device == (u16)PCI_ANY_ID)) {
+		    (p->device == dev->device ||
-			ret = i->enable_acs(dev);
+		     p->device == (u16)PCI_ANY_ID) &&
+		    p->enable_acs) {
+			ret = p->enable_acs(dev);
+			if (ret >= 0)
+				return ret;
+		}
+	}
+
+	return -ENOTTY;
+}
+
+int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
+{
+	const struct pci_dev_acs_ops *p;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) {
+		p = &pci_dev_acs_ops[i];
+		if ((p->vendor == dev->vendor ||
+		     p->vendor == (u16)PCI_ANY_ID) &&
+		    (p->device == dev->device ||
+		     p->device == (u16)PCI_ANY_ID) &&
+		    p->disable_acs_redir) {
+			ret = p->disable_acs_redir(dev);
 			if (ret >= 0)
 				return ret;
 		}

include/linux/pci.h

@@ -1890,20 +1890,9 @@ enum pci_fixup_pass {
 
 #ifdef CONFIG_PCI_QUIRKS
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
-int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
-int pci_dev_specific_enable_acs(struct pci_dev *dev);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) { }
-static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
-					       u16 acs_flags)
-{
-	return -ENOTTY;
-}
-static inline int pci_dev_specific_enable_acs(struct pci_dev *dev)
-{
-	return -ENOTTY;
-}
 #endif
 
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);