PCI: Dynamically map ECAM regions

Attempting to boot 32-bit ARM kernels under QEMU's 3.x virt models fails
when we have more than 512M of RAM in the model as we run out of vmalloc
space for the PCI ECAM regions. This failure will be silent when running
libvirt, as the console in that situation is a PCI device.

In this configuration, the kernel maps the whole ECAM, which QEMU sets up
for 256 buses, even when maybe only seven buses are in use. Each bus uses
1M of ECAM space, and ioremap() adds an additional guard page between
allocations. The kernel vmap allocator will align these regions to 512K,
resulting in each mapping eating 1.5M of vmalloc space. This means we need
384M of vmalloc space just to map all of these, which is very wasteful of
resources.

Fix this by only mapping the ECAM for buses we are going to be using. In
my setups, this is around seven buses in most guests, which is 10.5M of
vmalloc space - way smaller than the 384M that would otherwise be required.
This also means that the kernel can boot without forcing extra RAM into
highmem with the vmalloc= argument, or decreasing the virtual RAM available
to the guest.

Suggested-by: Arnd Bergmann <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Russell King <[e-mail]>
Signed-off-by: Bjorn Helgaas <[e-mail]>
Reviewed-by: Arnd Bergmann <[e-mail]>

drivers/pci/ecam.c

···
 	struct pci_config_window *cfg;
 	unsigned int bus_range, bus_range_max, bsz;
 	struct resource *conflict;
-	int i, err;
+	int err;
 
 	if (busr->start > busr->end)
 		return ERR_PTR(-EINVAL);
···
 	cfg->busr.start = busr->start;
 	cfg->busr.end = busr->end;
 	cfg->busr.flags = IORESOURCE_BUS;
+	cfg->bus_shift = bus_shift;
 	bus_range = resource_size(&cfg->busr);
 	bus_range_max = resource_size(cfgres) >> bus_shift;
 	if (bus_range > bus_range_max) {
···
 		cfg->winp = kcalloc(bus_range, sizeof(*cfg->winp), GFP_KERNEL);
 		if (!cfg->winp)
 			goto err_exit_malloc;
-		for (i = 0; i < bus_range; i++) {
-			cfg->winp[i] =
-				pci_remap_cfgspace(cfgres->start + i * bsz,
-						   bsz);
-			if (!cfg->winp[i])
-				goto err_exit_iomap;
-		}
 	} else {
 		cfg->win = pci_remap_cfgspace(cfgres->start, bus_range * bsz);
 		if (!cfg->win)
···
 }
 EXPORT_SYMBOL_GPL(pci_ecam_free);
 
+static int pci_ecam_add_bus(struct pci_bus *bus)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+	unsigned int bsz = 1 << cfg->bus_shift;
+	unsigned int busn = bus->number;
+	phys_addr_t start;
+
+	if (!per_bus_mapping)
+		return 0;
+
+	if (busn < cfg->busr.start || busn > cfg->busr.end)
+		return -EINVAL;
+
+	busn -= cfg->busr.start;
+	start = cfg->res.start + busn * bsz;
+
+	cfg->winp[busn] = pci_remap_cfgspace(start, bsz);
+	if (!cfg->winp[busn])
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void pci_ecam_remove_bus(struct pci_bus *bus)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+	unsigned int busn = bus->number;
+
+	if (!per_bus_mapping || busn < cfg->busr.start || busn > cfg->busr.end)
+		return;
+
+	busn -= cfg->busr.start;
+	if (cfg->winp[busn]) {
+		iounmap(cfg->winp[busn]);
+		cfg->winp[busn] = NULL;
+	}
+}
+
 /*
  * Function to implement the pci_ops ->map_bus method
  */
···
 /* ECAM ops */
 const struct pci_ecam_ops pci_generic_ecam_ops = {
 	.pci_ops	= {
+		.add_bus	= pci_ecam_add_bus,
+		.remove_bus	= pci_ecam_remove_bus,
 		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read,
 		.write		= pci_generic_config_write,
···
 /* ECAM ops for 32-bit access only (non-compliant) */
 const struct pci_ecam_ops pci_32b_ops = {
 	.pci_ops	= {
+		.add_bus	= pci_ecam_add_bus,
+		.remove_bus	= pci_ecam_remove_bus,
 		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read32,
 		.write		= pci_generic_config_write32,
···
 /* ECAM ops for 32-bit read only (non-compliant) */
 const struct pci_ecam_ops pci_32b_read_ops = {
 	.pci_ops	= {
+		.add_bus	= pci_ecam_add_bus,
+		.remove_bus	= pci_ecam_remove_bus,
 		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read32,
 		.write		= pci_generic_config_write,

include/linux/pci-ecam.h

···
 struct pci_config_window {
 	struct resource			res;
 	struct resource			busr;
+	unsigned int			bus_shift;
 	void				*priv;
 	const struct pci_ecam_ops	*ops;
 	union {