linux_dsm_epyc7002/drivers/pci/bus.c
Lukas Wunner 9a2a5a638f PCI: Do not treat EPROBE_DEFER as device attach failure
Linux 4.5 introduced a behavioral change in device probing during the
suspend process with commit 013c074f86 ("PM / sleep: prohibit devices
probing during suspend/hibernation"): It defers device probing during the
entire suspend process, starting from the prepare phase and ending with the
complete phase.  A rule existed before that "we rely on subsystems not to
do any probing once a device is suspended" but it is enforced only now
(Alan Stern, https://lkml.org/lkml/2015/9/15/908).

This resulted in a WARN splat if a PCI device (e.g., Thunderbolt) is
plugged in while the system is asleep: Upon waking up, pciehp_resume()
discovers new devices in the resume phase and immediately tries to bind
them to a driver.  Since probing is now deferred, device_attach() returns
-EPROBE_DEFER, which provoked a WARN in pci_bus_add_device().

Linux 4.6-rc1 aggravates the situation with commit ab1a187bba ("PCI:
Check device_attach() return value always"): If device_attach() returns a
negative value, pci_bus_add_device() now removes the sysfs and procfs
entries for the device and pci_bus_add_devices() subsequently locks up with
a BUG.  Even with the BUG fixed we're still in trouble because the device
remains on the deferred probing list even though its sysfs and procfs
entries are gone and its children won't be added.

Fix by not interpreting -EPROBE_DEFER as failure.  The device will be
probed eventually (through device_unblock_probing() in dpm_complete()) and
there is proper locking in place to avoid races (e.g., if devices are
unplugged again und thus deleted from the system before deferred probing
happens, I have tested this).  Also, those functions which dereference
dev->driver (e.g. pci_pm_*()) do contain proper NULL pointer checks.  So it
seems safe to ignore -EPROBE_DEFER.

Fixes: ab1a187bba ("PCI: Check device_attach() return value always")
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
2016-05-02 13:49:11 -05:00

401 lines
9.7 KiB
C

/*
* drivers/pci/bus.c
*
* From setup-res.c, by:
* Dave Rusling (david.rusling@reo.mts.dec.com)
* David Mosberger (davidm@cs.arizona.edu)
* David Miller (davem@redhat.com)
* Ivan Kokshaysky (ink@jurassic.park.msu.ru)
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/proc_fs.h>
#include <linux/slab.h>
#include "pci.h"
void pci_add_resource_offset(struct list_head *resources, struct resource *res,
resource_size_t offset)
{
struct resource_entry *entry;
entry = resource_list_create_entry(res, 0);
if (!entry) {
printk(KERN_ERR "PCI: can't add host bridge window %pR\n", res);
return;
}
entry->offset = offset;
resource_list_add_tail(entry, resources);
}
EXPORT_SYMBOL(pci_add_resource_offset);
void pci_add_resource(struct list_head *resources, struct resource *res)
{
pci_add_resource_offset(resources, res, 0);
}
EXPORT_SYMBOL(pci_add_resource);
void pci_free_resource_list(struct list_head *resources)
{
resource_list_free(resources);
}
EXPORT_SYMBOL(pci_free_resource_list);
void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
unsigned int flags)
{
struct pci_bus_resource *bus_res;
bus_res = kzalloc(sizeof(struct pci_bus_resource), GFP_KERNEL);
if (!bus_res) {
dev_err(&bus->dev, "can't add %pR resource\n", res);
return;
}
bus_res->res = res;
bus_res->flags = flags;
list_add_tail(&bus_res->list, &bus->resources);
}
struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n)
{
struct pci_bus_resource *bus_res;
if (n < PCI_BRIDGE_RESOURCE_NUM)
return bus->resource[n];
n -= PCI_BRIDGE_RESOURCE_NUM;
list_for_each_entry(bus_res, &bus->resources, list) {
if (n-- == 0)
return bus_res->res;
}
return NULL;
}
EXPORT_SYMBOL_GPL(pci_bus_resource_n);
void pci_bus_remove_resources(struct pci_bus *bus)
{
int i;
struct pci_bus_resource *bus_res, *tmp;
for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++)
bus->resource[i] = NULL;
list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) {
list_del(&bus_res->list);
kfree(bus_res);
}
}
static struct pci_bus_region pci_32_bit = {0, 0xffffffffULL};
#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
static struct pci_bus_region pci_64_bit = {0,
(pci_bus_addr_t) 0xffffffffffffffffULL};
static struct pci_bus_region pci_high = {(pci_bus_addr_t) 0x100000000ULL,
(pci_bus_addr_t) 0xffffffffffffffffULL};
#endif
/*
* @res contains CPU addresses. Clip it so the corresponding bus addresses
* on @bus are entirely within @region. This is used to control the bus
* addresses of resources we allocate, e.g., we may need a resource that
* can be mapped by a 32-bit BAR.
*/
static void pci_clip_resource_to_region(struct pci_bus *bus,
struct resource *res,
struct pci_bus_region *region)
{
struct pci_bus_region r;
pcibios_resource_to_bus(bus, &r, res);
if (r.start < region->start)
r.start = region->start;
if (r.end > region->end)
r.end = region->end;
if (r.end < r.start)
res->end = res->start - 1;
else
pcibios_bus_to_resource(bus, res, &r);
}
static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res,
resource_size_t size, resource_size_t align,
resource_size_t min, unsigned long type_mask,
resource_size_t (*alignf)(void *,
const struct resource *,
resource_size_t,
resource_size_t),
void *alignf_data,
struct pci_bus_region *region)
{
int i, ret;
struct resource *r, avail;
resource_size_t max;
type_mask |= IORESOURCE_TYPE_BITS;
pci_bus_for_each_resource(bus, r, i) {
resource_size_t min_used = min;
if (!r)
continue;
/* type_mask must match */
if ((res->flags ^ r->flags) & type_mask)
continue;
/* We cannot allocate a non-prefetching resource
from a pre-fetching area */
if ((r->flags & IORESOURCE_PREFETCH) &&
!(res->flags & IORESOURCE_PREFETCH))
continue;
avail = *r;
pci_clip_resource_to_region(bus, &avail, region);
/*
* "min" is typically PCIBIOS_MIN_IO or PCIBIOS_MIN_MEM to
* protect badly documented motherboard resources, but if
* this is an already-configured bridge window, its start
* overrides "min".
*/
if (avail.start)
min_used = avail.start;
max = avail.end;
/* Ok, try it out.. */
ret = allocate_resource(r, res, size, min_used, max,
align, alignf, alignf_data);
if (ret == 0)
return 0;
}
return -ENOMEM;
}
/**
* pci_bus_alloc_resource - allocate a resource from a parent bus
* @bus: PCI bus
* @res: resource to allocate
* @size: size of resource to allocate
* @align: alignment of resource to allocate
* @min: minimum /proc/iomem address to allocate
* @type_mask: IORESOURCE_* type flags
* @alignf: resource alignment function
* @alignf_data: data argument for resource alignment function
*
* Given the PCI bus a device resides on, the size, minimum address,
* alignment and type, try to find an acceptable resource allocation
* for a specific device resource.
*/
int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
resource_size_t size, resource_size_t align,
resource_size_t min, unsigned long type_mask,
resource_size_t (*alignf)(void *,
const struct resource *,
resource_size_t,
resource_size_t),
void *alignf_data)
{
#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
int rc;
if (res->flags & IORESOURCE_MEM_64) {
rc = pci_bus_alloc_from_region(bus, res, size, align, min,
type_mask, alignf, alignf_data,
&pci_high);
if (rc == 0)
return 0;
return pci_bus_alloc_from_region(bus, res, size, align, min,
type_mask, alignf, alignf_data,
&pci_64_bit);
}
#endif
return pci_bus_alloc_from_region(bus, res, size, align, min,
type_mask, alignf, alignf_data,
&pci_32_bit);
}
EXPORT_SYMBOL(pci_bus_alloc_resource);
/*
* The @idx resource of @dev should be a PCI-PCI bridge window. If this
* resource fits inside a window of an upstream bridge, do nothing. If it
* overlaps an upstream window but extends outside it, clip the resource so
* it fits completely inside.
*/
bool pci_bus_clip_resource(struct pci_dev *dev, int idx)
{
struct pci_bus *bus = dev->bus;
struct resource *res = &dev->resource[idx];
struct resource orig_res = *res;
struct resource *r;
int i;
pci_bus_for_each_resource(bus, r, i) {
resource_size_t start, end;
if (!r)
continue;
if (resource_type(res) != resource_type(r))
continue;
start = max(r->start, res->start);
end = min(r->end, res->end);
if (start > end)
continue; /* no overlap */
if (res->start == start && res->end == end)
return false; /* no change */
res->start = start;
res->end = end;
res->flags &= ~IORESOURCE_UNSET;
orig_res.flags &= ~IORESOURCE_UNSET;
dev_printk(KERN_DEBUG, &dev->dev, "%pR clipped to %pR\n",
&orig_res, res);
return true;
}
return false;
}
void __weak pcibios_resource_survey_bus(struct pci_bus *bus) { }
void __weak pcibios_bus_add_device(struct pci_dev *pdev) { }
/**
* pci_bus_add_device - start driver for a single device
* @dev: device to add
*
* This adds add sysfs entries and start device drivers
*/
void pci_bus_add_device(struct pci_dev *dev)
{
int retval;
/*
* Can not put in pci_device_add yet because resources
* are not assigned yet for some devices.
*/
pcibios_bus_add_device(dev);
pci_fixup_device(pci_fixup_final, dev);
pci_create_sysfs_dev_files(dev);
pci_proc_attach_device(dev);
dev->match_driver = true;
retval = device_attach(&dev->dev);
if (retval < 0 && retval != -EPROBE_DEFER) {
dev_warn(&dev->dev, "device attach failed (%d)\n", retval);
pci_proc_detach_device(dev);
pci_remove_sysfs_dev_files(dev);
return;
}
dev->is_added = 1;
}
EXPORT_SYMBOL_GPL(pci_bus_add_device);
/**
* pci_bus_add_devices - start driver for PCI devices
* @bus: bus to check for new devices
*
* Start driver for PCI devices and add some sysfs entries.
*/
void pci_bus_add_devices(const struct pci_bus *bus)
{
struct pci_dev *dev;
struct pci_bus *child;
list_for_each_entry(dev, &bus->devices, bus_list) {
/* Skip already-added devices */
if (dev->is_added)
continue;
pci_bus_add_device(dev);
}
list_for_each_entry(dev, &bus->devices, bus_list) {
/* Skip if device attach failed */
if (!dev->is_added)
continue;
child = dev->subordinate;
if (child)
pci_bus_add_devices(child);
}
}
EXPORT_SYMBOL(pci_bus_add_devices);
/** pci_walk_bus - walk devices on/under bus, calling callback.
* @top bus whose devices should be walked
* @cb callback to be called for each device found
* @userdata arbitrary pointer to be passed to callback.
*
* Walk the given bus, including any bridged devices
* on buses under this bus. Call the provided callback
* on each device found.
*
* We check the return of @cb each time. If it returns anything
* other than 0, we break out.
*
*/
void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
void *userdata)
{
struct pci_dev *dev;
struct pci_bus *bus;
struct list_head *next;
int retval;
bus = top;
down_read(&pci_bus_sem);
next = top->devices.next;
for (;;) {
if (next == &bus->devices) {
/* end of this bus, go up or finish */
if (bus == top)
break;
next = bus->self->bus_list.next;
bus = bus->self->bus;
continue;
}
dev = list_entry(next, struct pci_dev, bus_list);
if (dev->subordinate) {
/* this is a pci-pci bridge, do its devices next */
next = dev->subordinate->devices.next;
bus = dev->subordinate;
} else
next = dev->bus_list.next;
retval = cb(dev, userdata);
if (retval)
break;
}
up_read(&pci_bus_sem);
}
EXPORT_SYMBOL_GPL(pci_walk_bus);
struct pci_bus *pci_bus_get(struct pci_bus *bus)
{
if (bus)
get_device(&bus->dev);
return bus;
}
EXPORT_SYMBOL(pci_bus_get);
void pci_bus_put(struct pci_bus *bus)
{
if (bus)
put_device(&bus->dev);
}
EXPORT_SYMBOL(pci_bus_put);