PCI: Add Virtual Channel to save/restore support

While we don't really have any infrastructure for making use of VC
support, the system BIOS can configure the topology to non-default
VC values prior to boot.  This may be due to silicon bugs, desire to
reserve traffic classes, or perhaps just BIOS bugs.  When we reset
devices, the VC configuration may return to default values, which can
be incompatible with devices upstream.  For instance, Nvidia GRID
cards provide a PCIe switch and some number of GPUs, all supporting
VC.  The power-on default for VC is to support TC0-7 across VC0,
however some platforms will only enable TC0/VC0 mapping across the
topology.  When we do a secondary bus reset on the downstream switch
port, the GPU is reset to a TC0-7/VC0 mapping while the opposite end
of the link only enables TC0/VC0.  If the GPU attempts to use TC1-7,
it fails.

This patch attempts to provide complete support for VC save/restore,
even beyond the minimally required use case above.  This includes
save/restore and reload of the arbitration table, save/restore and
reload of the port arbitration tables, and re-enabling of the
channels for VC, VC9, and MFVC capabilities.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

5 files changed, 466 insertions, 5 deletions

diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 6ebf5bf8e7a7..17d2b07ee67c 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -4,7 +4,7 @@
 
 obj-y		+= access.o bus.o probe.o host-bridge.o remove.o pci.o \
 			pci-driver.o search.o pci-sysfs.o rom.o setup-res.o \
-			irq.o vpd.o setup-bus.o
+			irq.o vpd.o setup-bus.o vc.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_SYSFS) += slot.o
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8f2be7ec705c..508e560b7d2a 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -984,6 +984,8 @@ pci_save_state(struct pci_dev *dev)
 		return i;
 	if ((i = pci_save_pcix_state(dev)) != 0)
 		return i;
+	if ((i = pci_save_vc_state(dev)) != 0)
+		return i;
 	return 0;
 }
 
@@ -1046,6 +1048,7 @@ void pci_restore_state(struct pci_dev *dev)
 	/* PCI Express register must be restored first */
 	pci_restore_pcie_state(dev);
 	pci_restore_ats_state(dev);
+	pci_restore_vc_state(dev);
 
 	pci_restore_config_space(dev);
 
@@ -2118,6 +2121,8 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev)
 	if (error)
 		dev_err(&dev->dev,
 			"unable to preallocate PCI-X save buffer\n");
+
+	pci_allocate_vc_save_buffers(dev);
 }
 
 void pci_free_cap_save_buffers(struct pci_dev *dev)
diff --git a/drivers/pci/vc.c b/drivers/pci/vc.c
new file mode 100644
index 000000000000..c10567e4f14f
--- /dev/null
+++ b/drivers/pci/vc.c
@@ -0,0 +1,434 @@
+/*
+ * PCI Virtual Channel support
+ *
+ * Copyright (C) 2013 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+#include <linux/types.h>
+
+/**
+ * pci_vc_save_restore_dwords - Save or restore a series of dwords
+ * @dev: device
+ * @pos: starting config space position
+ * @buf: buffer to save to or restore from
+ * @dwords: number of dwords to save/restore
+ * @save: whether to save or restore
+ */
+static void pci_vc_save_restore_dwords(struct pci_dev *dev, int pos,
+				       u32 *buf, int dwords, bool save)
+{
+	int i;
+
+	for (i = 0; i < dwords; i++, buf++) {
+		if (save)
+			pci_read_config_dword(dev, pos + (i * 4), buf);
+		else
+			pci_write_config_dword(dev, pos + (i * 4), *buf);
+	}
+}
+
+/**
+ * pci_vc_load_arb_table - load and wait for VC arbitration table
+ * @dev: device
+ * @pos: starting position of VC capability (VC/VC9/MFVC)
+ *
+ * Set Load VC Arbitration Table bit requesting hardware to apply the VC
+ * Arbitration Table (previously loaded).  When the VC Arbitration Table
+ * Status clears, hardware has latched the table into VC arbitration logic.
+ */
+static void pci_vc_load_arb_table(struct pci_dev *dev, int pos)
+{
+	u16 ctrl;
+
+	pci_read_config_word(dev, pos + PCI_VC_PORT_CTRL, &ctrl);
+	pci_write_config_word(dev, pos + PCI_VC_PORT_CTRL,
+			      ctrl | PCI_VC_PORT_CTRL_LOAD_TABLE);
+	if (pci_wait_for_pending(dev, pos + PCI_VC_PORT_STATUS,
+				 PCI_VC_PORT_STATUS_TABLE))
+		return;
+
+	dev_err(&dev->dev, "VC arbitration table failed to load\n");
+}
+
+/**
+ * pci_vc_load_port_arb_table - Load and wait for VC port arbitration table
+ * @dev: device
+ * @pos: starting position of VC capability (VC/VC9/MFVC)
+ * @res: VC resource number, ie. VCn (0-7)
+ *
+ * Set Load Port Arbitration Table bit requesting hardware to apply the Port
+ * Arbitration Table (previously loaded).  When the Port Arbitration Table
+ * Status clears, hardware has latched the table into port arbitration logic.
+ */
+static void pci_vc_load_port_arb_table(struct pci_dev *dev, int pos, int res)
+{
+	int ctrl_pos, status_pos;
+	u32 ctrl;
+
+	ctrl_pos = pos + PCI_VC_RES_CTRL + (res * PCI_CAP_VC_PER_VC_SIZEOF);
+	status_pos = pos + PCI_VC_RES_STATUS + (res * PCI_CAP_VC_PER_VC_SIZEOF);
+
+	pci_read_config_dword(dev, ctrl_pos, &ctrl);
+	pci_write_config_dword(dev, ctrl_pos,
+			       ctrl | PCI_VC_RES_CTRL_LOAD_TABLE);
+
+	if (pci_wait_for_pending(dev, status_pos, PCI_VC_RES_STATUS_TABLE))
+		return;
+
+	dev_err(&dev->dev, "VC%d port arbitration table failed to load\n", res);
+}
+
+/**
+ * pci_vc_enable - Enable virtual channel
+ * @dev: device
+ * @pos: starting position of VC capability (VC/VC9/MFVC)
+ * @res: VC res number, ie. VCn (0-7)
+ *
+ * A VC is enabled by setting the enable bit in matching resource control
+ * registers on both sides of a link.  We therefore need to find the opposite
+ * end of the link.  To keep this simple we enable from the downstream device.
+ * RC devices do not have an upstream device, nor does it seem that VC9 do
+ * (spec is unclear).  Once we find the upstream device, match the VC ID to
+ * get the correct resource, disable and enable on both ends.
+ */
+static void pci_vc_enable(struct pci_dev *dev, int pos, int res)
+{
+	int ctrl_pos, status_pos, id, pos2, evcc, i, ctrl_pos2, status_pos2;
+	u32 ctrl, header, reg1, ctrl2;
+	struct pci_dev *link = NULL;
+
+	/* Enable VCs from the downstream device */
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT ||
+	    pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+
+	ctrl_pos = pos + PCI_VC_RES_CTRL + (res * PCI_CAP_VC_PER_VC_SIZEOF);
+	status_pos = pos + PCI_VC_RES_STATUS + (res * PCI_CAP_VC_PER_VC_SIZEOF);
+
+	pci_read_config_dword(dev, ctrl_pos, &ctrl);
+	id = ctrl & PCI_VC_RES_CTRL_ID;
+
+	pci_read_config_dword(dev, pos, &header);
+
+	/* If there is no opposite end of the link, skip to enable */
+	if (PCI_EXT_CAP_ID(header) == PCI_EXT_CAP_ID_VC9 ||
+	    pci_is_root_bus(dev->bus))
+		goto enable;
+
+	pos2 = pci_find_ext_capability(dev->bus->self, PCI_EXT_CAP_ID_VC);
+	if (!pos2)
+		goto enable;
+
+	pci_read_config_dword(dev->bus->self, pos2 + PCI_VC_PORT_REG1, &reg1);
+	evcc = reg1 & PCI_VC_REG1_EVCC;
+
+	/* VC0 is hardwired enabled, so we can start with 1 */
+	for (i = 1; i < evcc + 1; i++) {
+		ctrl_pos2 = pos2 + PCI_VC_RES_CTRL +
+				(i * PCI_CAP_VC_PER_VC_SIZEOF);
+		status_pos2 = pos2 + PCI_VC_RES_STATUS +
+				(i * PCI_CAP_VC_PER_VC_SIZEOF);
+		pci_read_config_dword(dev->bus->self, ctrl_pos2, &ctrl2);
+		if ((ctrl2 & PCI_VC_RES_CTRL_ID) == id) {
+			link = dev->bus->self;
+			break;
+		}
+	}
+
+	if (!link)
+		goto enable;
+
+	/* Disable if enabled */
+	if (ctrl2 & PCI_VC_RES_CTRL_ENABLE) {
+		ctrl2 &= ~PCI_VC_RES_CTRL_ENABLE;
+		pci_write_config_dword(link, ctrl_pos2, ctrl2);
+	}
+
+	/* Enable on both ends */
+	ctrl2 |= PCI_VC_RES_CTRL_ENABLE;
+	pci_write_config_dword(link, ctrl_pos2, ctrl2);
+enable:
+	ctrl |= PCI_VC_RES_CTRL_ENABLE;
+	pci_write_config_dword(dev, ctrl_pos, ctrl);
+
+	if (!pci_wait_for_pending(dev, status_pos, PCI_VC_RES_STATUS_NEGO))
+		dev_err(&dev->dev, "VC%d negotiation stuck pending\n", id);
+
+	if (link && !pci_wait_for_pending(link, status_pos2,
+					  PCI_VC_RES_STATUS_NEGO))
+		dev_err(&link->dev, "VC%d negotiation stuck pending\n", id);
+}
+
+/**
+ * pci_vc_do_save_buffer - Size, save, or restore VC state
+ * @dev: device
+ * @pos: starting position of VC capability (VC/VC9/MFVC)
+ * @save_state: buffer for save/restore
+ * @name: for error message
+ * @save: if provided a buffer, this indicates what to do with it
+ *
+ * Walking Virtual Channel config space to size, save, or restore it
+ * is complicated, so we do it all from one function to reduce code and
+ * guarantee ordering matches in the buffer.  When called with NULL
+ * @save_state, return the size of the necessary save buffer.  When called
+ * with a non-NULL @save_state, @save determines whether we save to the
+ * buffer or restore from it.
+ */
+static int pci_vc_do_save_buffer(struct pci_dev *dev, int pos,
+				 struct pci_cap_saved_state *save_state,
+				 bool save)
+{
+	u32 reg1;
+	char evcc, lpevcc, parb_size;
+	int i, len = 0;
+	u8 *buf = save_state ? (u8 *)save_state->cap.data : NULL;
+
+	/* Sanity check buffer size for save/restore */
+	if (buf && save_state->cap.size !=
+	    pci_vc_do_save_buffer(dev, pos, NULL, save)) {
+		dev_err(&dev->dev,
+			"VC save buffer size does not match @0x%x\n", pos);
+		return -ENOMEM;
+	}
+
+	pci_read_config_dword(dev, pos + PCI_VC_PORT_REG1, &reg1);
+	/* Extended VC Count (not counting VC0) */
+	evcc = reg1 & PCI_VC_REG1_EVCC;
+	/* Low Priority Extended VC Count (not counting VC0) */
+	lpevcc = (reg1 & PCI_VC_REG1_LPEVCC) >> 4;
+	/* Port Arbitration Table Entry Size (bits) */
+	parb_size = 1 << ((reg1 & PCI_VC_REG1_ARB_SIZE) >> 10);
+
+	/*
+	 * Port VC Control Register contains VC Arbitration Select, which
+	 * cannot be modified when more than one LPVC is in operation.  We
+	 * therefore save/restore it first, as only VC0 should be enabled
+	 * after device reset.
+	 */
+	if (buf) {
+		if (save)
+			pci_read_config_word(dev, pos + PCI_VC_PORT_CTRL,
+					     (u16 *)buf);
+		else
+			pci_write_config_word(dev, pos + PCI_VC_PORT_CTRL,
+					      *(u16 *)buf);
+		buf += 2;
+	}
+	len += 2;
+
+	/*
+	 * If we have any Low Priority VCs and a VC Arbitration Table Offset
+	 * in Port VC Capability Register 2 then save/restore it next.
+	 */
+	if (lpevcc) {
+		u32 reg2;
+		int vcarb_offset;
+
+		pci_read_config_dword(dev, pos + PCI_VC_PORT_REG2, &reg2);
+		vcarb_offset = ((reg2 & PCI_VC_REG2_ARB_OFF) >> 24) * 16;
+
+		if (vcarb_offset) {
+			int size, vcarb_phases = 0;
+
+			if (reg2 & PCI_VC_REG2_128_PHASE)
+				vcarb_phases = 128;
+			else if (reg2 & PCI_VC_REG2_64_PHASE)
+				vcarb_phases = 64;
+			else if (reg2 & PCI_VC_REG2_32_PHASE)
+				vcarb_phases = 32;
+
+			/* Fixed 4 bits per phase per lpevcc (plus VC0) */
+			size = ((lpevcc + 1) * vcarb_phases * 4) / 8;
+
+			if (size && buf) {
+				pci_vc_save_restore_dwords(dev,
+							   pos + vcarb_offset,
+							   (u32 *)buf,
+							   size / 4, save);
+				/*
+				 * On restore, we need to signal hardware to
+				 * re-load the VC Arbitration Table.
+				 */
+				if (!save)
+					pci_vc_load_arb_table(dev, pos);
+
+				buf += size;
+			}
+			len += size;
+		}
+	}
+
+	/*
+	 * In addition to each VC Resource Control Register, we may have a
+	 * Port Arbitration Table attached to each VC.  The Port Arbitration
+	 * Table Offset in each VC Resource Capability Register tells us if
+	 * it exists.  The entry size is global from the Port VC Capability
+	 * Register1 above.  The number of phases is determined per VC.
+	 */
+	for (i = 0; i < evcc + 1; i++) {
+		u32 cap;
+		int parb_offset;
+
+		pci_read_config_dword(dev, pos + PCI_VC_RES_CAP +
+				      (i * PCI_CAP_VC_PER_VC_SIZEOF), &cap);
+		parb_offset = ((cap & PCI_VC_RES_CAP_ARB_OFF) >> 24) * 16;
+		if (parb_offset) {
+			int size, parb_phases = 0;
+
+			if (cap & PCI_VC_RES_CAP_256_PHASE)
+				parb_phases = 256;
+			else if (cap & (PCI_VC_RES_CAP_128_PHASE |
+					PCI_VC_RES_CAP_128_PHASE_TB))
+				parb_phases = 128;
+			else if (cap & PCI_VC_RES_CAP_64_PHASE)
+				parb_phases = 64;
+			else if (cap & PCI_VC_RES_CAP_32_PHASE)
+				parb_phases = 32;
+
+			size = (parb_size * parb_phases) / 8;
+
+			if (size && buf) {
+				pci_vc_save_restore_dwords(dev,
+							   pos + parb_offset,
+							   (u32 *)buf,
+							   size / 4, save);
+				buf += size;
+			}
+			len += size;
+		}
+
+		/* VC Resource Control Register */
+		if (buf) {
+			int ctrl_pos = pos + PCI_VC_RES_CTRL +
+						(i * PCI_CAP_VC_PER_VC_SIZEOF);
+			if (save)
+				pci_read_config_dword(dev, ctrl_pos,
+						      (u32 *)buf);
+			else {
+				u32 tmp, ctrl = *(u32 *)buf;
+				/*
+				 * For an FLR case, the VC config may remain.
+				 * Preserve enable bit, restore the rest.
+				 */
+				pci_read_config_dword(dev, ctrl_pos, &tmp);
+				tmp &= PCI_VC_RES_CTRL_ENABLE;
+				tmp |= ctrl & ~PCI_VC_RES_CTRL_ENABLE;
+				pci_write_config_dword(dev, ctrl_pos, tmp);
+				/* Load port arbitration table if used */
+				if (ctrl & PCI_VC_RES_CTRL_ARB_SELECT)
+					pci_vc_load_port_arb_table(dev, pos, i);
+				/* Re-enable if needed */
+				if ((ctrl ^ tmp) & PCI_VC_RES_CTRL_ENABLE)
+					pci_vc_enable(dev, pos, i);
+			}
+			buf += 4;
+		}
+		len += 4;
+	}
+
+	return buf ? 0 : len;
+}
+
+static struct {
+	u16 id;
+	const char *name;
+} vc_caps[] = { { PCI_EXT_CAP_ID_MFVC, "MFVC" },
+		{ PCI_EXT_CAP_ID_VC, "VC" },
+		{ PCI_EXT_CAP_ID_VC9, "VC9" } };
+
+/**
+ * pci_save_vc_state - Save VC state to pre-allocate save buffer
+ * @dev: device
+ *
+ * For each type of VC capability, VC/VC9/MFVC, find the capability and
+ * save it to the pre-allocated save buffer.
+ */
+int pci_save_vc_state(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vc_caps); i++) {
+		int pos, ret;
+		struct pci_cap_saved_state *save_state;
+
+		pos = pci_find_ext_capability(dev, vc_caps[i].id);
+		if (!pos)
+			continue;
+
+		save_state = pci_find_saved_ext_cap(dev, vc_caps[i].id);
+		if (!save_state) {
+			dev_err(&dev->dev, "%s buffer not found in %s\n",
+				vc_caps[i].name, __func__);
+			return -ENOMEM;
+		}
+
+		ret = pci_vc_do_save_buffer(dev, pos, save_state, true);
+		if (ret) {
+			dev_err(&dev->dev, "%s save unsuccessful %s\n",
+				vc_caps[i].name, __func__);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * pci_restore_vc_state - Restore VC state from save buffer
+ * @dev: device
+ *
+ * For each type of VC capability, VC/VC9/MFVC, find the capability and
+ * restore it from the previously saved buffer.
+ */
+void pci_restore_vc_state(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vc_caps); i++) {
+		int pos;
+		struct pci_cap_saved_state *save_state;
+
+		pos = pci_find_ext_capability(dev, vc_caps[i].id);
+		save_state = pci_find_saved_ext_cap(dev, vc_caps[i].id);
+		if (!save_state || !pos)
+			continue;
+
+		pci_vc_do_save_buffer(dev, pos, save_state, false);
+	}
+}
+
+/**
+ * pci_allocate_vc_save_buffers - Allocate save buffers for VC caps
+ * @dev: device
+ *
+ * For each type of VC capability, VC/VC9/MFVC, find the capability, size
+ * it, and allocate a buffer for save/restore.
+ */
+
+void pci_allocate_vc_save_buffers(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vc_caps); i++) {
+		int len, pos = pci_find_ext_capability(dev, vc_caps[i].id);
+
+		if (!pos)
+			continue;
+
+		len = pci_vc_do_save_buffer(dev, pos, NULL, false);
+		if (pci_add_ext_cap_save_buffer(dev, vc_caps[i].id, len))
+			dev_err(&dev->dev,
+				"unable to preallocate %s save buffer\n",
+				vc_caps[i].name);
+	}
+}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 1bb75b0c4c6f..ef34ad76532c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1005,6 +1005,11 @@ static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
 	return __pci_enable_wake(dev, state, false, enable);
 }
 
+/* PCI Virtual Channel */
+int pci_save_vc_state(struct pci_dev *dev);
+void pci_restore_vc_state(struct pci_dev *dev);
+void pci_allocate_vc_save_buffers(struct pci_dev *dev);
+
 #define PCI_EXP_IDO_REQUEST	(1<<0)
 #define PCI_EXP_IDO_COMPLETION	(1<<1)
 void pci_enable_ido(struct pci_dev *dev, unsigned long type);
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 4a98e85438a7..5eefacd93e18 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -678,16 +678,33 @@
 
 /* Virtual Channel */
 #define PCI_VC_PORT_REG1	4
-#define  PCI_VC_REG1_EVCC	0x7	/* extended VC count */
+#define  PCI_VC_REG1_EVCC	0x00000007	/* extended VC count */
+#define  PCI_VC_REG1_LPEVCC	0x00000070	/* low prio extended VC count */
+#define  PCI_VC_REG1_ARB_SIZE	0x00000c00
 #define PCI_VC_PORT_REG2	8
-#define  PCI_VC_REG2_32_PHASE	0x2
-#define  PCI_VC_REG2_64_PHASE	0x4
-#define  PCI_VC_REG2_128_PHASE	0x8
+#define  PCI_VC_REG2_32_PHASE		0x00000002
+#define  PCI_VC_REG2_64_PHASE		0x00000004
+#define  PCI_VC_REG2_128_PHASE		0x00000008
+#define  PCI_VC_REG2_ARB_OFF		0xff000000
 #define PCI_VC_PORT_CTRL	12
+#define  PCI_VC_PORT_CTRL_LOAD_TABLE	0x00000001
 #define PCI_VC_PORT_STATUS	14
+#define  PCI_VC_PORT_STATUS_TABLE	0x00000001
 #define PCI_VC_RES_CAP		16
+#define  PCI_VC_RES_CAP_32_PHASE	0x00000002
+#define  PCI_VC_RES_CAP_64_PHASE	0x00000004
+#define  PCI_VC_RES_CAP_128_PHASE	0x00000008
+#define  PCI_VC_RES_CAP_128_PHASE_TB	0x00000010
+#define  PCI_VC_RES_CAP_256_PHASE	0x00000020
+#define  PCI_VC_RES_CAP_ARB_OFF		0xff000000
 #define PCI_VC_RES_CTRL		20
+#define  PCI_VC_RES_CTRL_LOAD_TABLE	0x00010000
+#define  PCI_VC_RES_CTRL_ARB_SELECT	0x000e0000
+#define  PCI_VC_RES_CTRL_ID		0x07000000
+#define  PCI_VC_RES_CTRL_ENABLE		0x80000000
 #define PCI_VC_RES_STATUS	26
+#define  PCI_VC_RES_STATUS_TABLE	0x00000001
+#define  PCI_VC_RES_STATUS_NEGO		0x00000002
 #define PCI_CAP_VC_BASE_SIZEOF		0x10
 #define PCI_CAP_VC_PER_VC_SIZEOF	0x0C