[PATCH v5 03/23] PCI: hotplug: Add a flag for the movable BARs feature

Sergey Miroshnichenko s.miroshnichenko at yadro.com
Sat Aug 17 02:50:41 AEST 2019


When hot-adding a device, the bridge may have windows not big enough (or
fragmented too much) for newly requested BARs to fit in. And expanding
these bridge windows may be impossible because blocked by "neighboring"
BARs and bridge windows.

Still, it may be possible to allocate a memory region for new BARs with the
following procedure:

1) notify all the drivers which support movable BARs to pause and release
   the BARs; the rest of the drivers are guaranteed that their devices will
   not get BARs moved;

2) release all the bridge windows except of root bridges;

3) try to recalculate new bridge windows that will fit all the BAR types:
   - fixed;
   - immovable;
   - movable;
   - newly requested by hot-added devices;

4) if the previous step fails, disable BARs for one of the hot-added
   devices and retry from step 3;

5) notify the drivers, so they remap BARs and resume.

This makes the prior reservation of memory by BIOS/bootloader/firmware not
required anymore for the PCI hotplug.

Drivers indicate their support of movable BARs by implementing the new
.rescan_prepare() and .rescan_done() hooks in the struct pci_driver. All
device's activity must be paused during a rescan, and iounmap()+ioremap()
must be applied to every used BAR.

The platform also may need to prepare to BAR movement, so new hooks added:
pcibios_rescan_prepare(pci_dev) and pcibios_rescan_prepare(pci_dev).

This patch is a preparation for future patches with actual implementation,
and for now it just does the following:
 - declares the feature;
 - defines pci_movable_bars_enabled(), pci_dev_movable_bars_supported(dev);
 - invokes the .rescan_prepare() and .rescan_done() driver notifiers;
 - declares and invokes the pcibios_rescan_prepare()/_done() hooks;
 - adds the PCI_IMMOVABLE_BARS flag.

The feature is disabled by default (via PCI_IMMOVABLE_BARS) until the final
patch of the series. It can be overridden per-arch using this flag or by
the following command line option:

    pcie_movable_bars={ off | force }

CC: Sam Bobroff <sbobroff at linux.ibm.com>
CC: Rajat Jain <rajatja at google.com>
CC: Lukas Wunner <lukas at wunner.de>
CC: Oliver O'Halloran <oohall at gmail.com>
CC: David Laight <David.Laight at ACULAB.COM>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko at yadro.com>
---
 .../admin-guide/kernel-parameters.txt         |  7 ++
 drivers/pci/pci-driver.c                      |  2 +
 drivers/pci/pci.c                             | 24 ++++++
 drivers/pci/pci.h                             |  2 +
 drivers/pci/probe.c                           | 86 ++++++++++++++++++-
 include/linux/pci.h                           |  7 ++
 6 files changed, 126 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 47d981a86e2f..e2274ee87a35 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3526,6 +3526,13 @@
 		nomsi	Do not use MSI for native PCIe PME signaling (this makes
 			all PCIe root ports use INTx for all services).
 
+	pcie_movable_bars=[PCIE]
+			Override the movable BARs support detection:
+		off
+			Disable even if supported by the platform
+		force
+			Enable even if not explicitly declared as supported
+
 	pcmv=		[HW,PCMCIA] BadgePAD 4
 
 	pd_ignore_unused
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index a8124e47bf6e..d11909e79263 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1688,6 +1688,8 @@ static int __init pci_driver_init(void)
 {
 	int ret;
 
+	pci_add_flags(PCI_IMMOVABLE_BARS);
+
 	ret = bus_register(&pci_bus_type);
 	if (ret)
 		return ret;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 61d951766087..3a504f58ac60 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -139,6 +139,30 @@ static int __init pcie_port_pm_setup(char *str)
 }
 __setup("pcie_port_pm=", pcie_port_pm_setup);
 
+static bool pcie_movable_bars_off;
+static bool pcie_movable_bars_force;
+static int __init pcie_movable_bars_setup(char *str)
+{
+	if (!strcmp(str, "off"))
+		pcie_movable_bars_off = true;
+	else if (!strcmp(str, "force"))
+		pcie_movable_bars_force = true;
+	return 1;
+}
+__setup("pcie_movable_bars=", pcie_movable_bars_setup);
+
+bool pci_movable_bars_enabled(void)
+{
+	if (pcie_movable_bars_off)
+		return false;
+
+	if (pcie_movable_bars_force)
+		return true;
+
+	return !pci_has_flag(PCI_IMMOVABLE_BARS);
+}
+EXPORT_SYMBOL(pci_movable_bars_enabled);
+
 /* Time to wait after a reset for device to become responsive */
 #define PCIE_RESET_READY_POLL_MS 60000
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index d22d1b807701..be7acc477c64 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -257,6 +257,8 @@ bool pci_bus_clip_resource(struct pci_dev *dev, int idx);
 void pci_reassigndev_resource_alignment(struct pci_dev *dev);
 void pci_disable_bridge_window(struct pci_dev *dev);
 
+bool pci_dev_movable_bars_supported(struct pci_dev *dev);
+
 /* PCIe link information */
 #define PCIE_SPEED2STR(speed) \
 	((speed) == PCIE_SPEED_16_0GT ? "16 GT/s" : \
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 2e58ece820e8..60e3b48d2251 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3406,6 +3406,74 @@ unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge)
 	return max;
 }
 
+bool pci_dev_movable_bars_supported(struct pci_dev *dev)
+{
+	if (!dev)
+		return false;
+
+	if (dev->driver && dev->driver->rescan_prepare)
+		return true;
+
+	if ((dev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+		return false;
+
+	return !dev->driver;
+}
+
+void __weak pcibios_rescan_prepare(struct pci_dev *dev)
+{
+}
+
+void __weak pcibios_rescan_done(struct pci_dev *dev)
+{
+}
+
+static void pci_bus_rescan_prepare(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	if (bus->self)
+		pci_config_pm_runtime_get(bus->self);
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		struct pci_bus *child = dev->subordinate;
+
+		if (child)
+			pci_bus_rescan_prepare(child);
+
+		if (dev->driver &&
+		    dev->driver->rescan_prepare) {
+			dev->driver->rescan_prepare(dev);
+			pcibios_rescan_prepare(dev);
+		} else if (pci_dev_movable_bars_supported(dev)) {
+			pcibios_rescan_prepare(dev);
+		}
+	}
+}
+
+static void pci_bus_rescan_done(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		struct pci_bus *child = dev->subordinate;
+
+		if (dev->driver &&
+		    dev->driver->rescan_done) {
+			pcibios_rescan_done(dev);
+			dev->driver->rescan_done(dev);
+		} else if (pci_dev_movable_bars_supported(dev)) {
+			pcibios_rescan_done(dev);
+		}
+
+		if (child)
+			pci_bus_rescan_done(child);
+	}
+
+	if (bus->self)
+		pci_config_pm_runtime_put(bus->self);
+}
+
 /**
  * pci_rescan_bus - Scan a PCI bus for devices
  * @bus: PCI bus to scan
@@ -3418,9 +3486,23 @@ unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge)
 unsigned int pci_rescan_bus(struct pci_bus *bus)
 {
 	unsigned int max;
+	struct pci_bus *root = bus;
+
+	while (!pci_is_root_bus(root))
+		root = root->parent;
+
+	if (pci_movable_bars_enabled()) {
+		pci_bus_rescan_prepare(root);
+
+		max = pci_scan_child_bus(root);
+		pci_assign_unassigned_root_bus_resources(root);
+
+		pci_bus_rescan_done(root);
+	} else {
+		max = pci_scan_child_bus(bus);
+		pci_assign_unassigned_bus_resources(bus);
+	}
 
-	max = pci_scan_child_bus(bus);
-	pci_assign_unassigned_bus_resources(bus);
 	pci_bus_add_devices(bus);
 
 	return max;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d3a72159722d..e5b5eff05744 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -838,6 +838,8 @@ struct pci_driver {
 	int  (*resume)(struct pci_dev *dev);	/* Device woken up */
 	void (*shutdown)(struct pci_dev *dev);
 	int  (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */
+	void (*rescan_prepare)(struct pci_dev *dev);
+	void (*rescan_done)(struct pci_dev *dev);
 	const struct pci_error_handlers *err_handler;
 	const struct attribute_group **groups;
 	struct device_driver	driver;
@@ -924,6 +926,7 @@ enum {
 	PCI_ENABLE_PROC_DOMAINS	= 0x00000010,	/* Enable domains in /proc */
 	PCI_COMPAT_DOMAIN_0	= 0x00000020,	/* ... except domain 0 */
 	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,	/* Scan all, not just dev 0 */
+	PCI_IMMOVABLE_BARS	= 0x00000080,	/* Disable runtime BAR reassign */
 };
 
 /* These external functions are only available when PCI support is enabled */
@@ -1266,6 +1269,9 @@ unsigned int pci_rescan_bus(struct pci_bus *bus);
 void pci_lock_rescan_remove(void);
 void pci_unlock_rescan_remove(void);
 
+void pcibios_rescan_prepare(struct pci_dev *dev);
+void pcibios_rescan_done(struct pci_dev *dev);
+
 /* Vital Product Data routines */
 ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
 ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
@@ -1402,6 +1408,7 @@ unsigned char pci_bus_max_busnr(struct pci_bus *bus);
 void pci_setup_bridge(struct pci_bus *bus);
 resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 					 unsigned long type);
+bool pci_movable_bars_enabled(void);
 
 #define PCI_VGA_STATE_CHANGE_BRIDGE (1 << 0)
 #define PCI_VGA_STATE_CHANGE_DECODES (1 << 1)
-- 
2.21.0



More information about the Linuxppc-dev mailing list