| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 3 Oct 2014 14:31:33 -0700
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Shawn Starr <shawn.starr@...ers.com>,
"Jose P." <lbdkmjdf@...rklasers.com>,
Bjorn Helgaas <bhelgaas@...gle.com>,
Alex Deucher <alexander.deucher@....com>,
Rajat Jain <rajatxjain@...il.com>,
"Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
Dave Airlie <airlied@...hat.com>
Subject: [PATCH 3.16 307/357] PCI: Add pci_ignore_hotplug() to ignore hotplug events for a device
3.16-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bjorn Helgaas <bhelgaas@...gle.com>
commit b440bde74f043c8ec31081cb59c9a53ade954701 upstream.
Powering off a hot-pluggable device, e.g., with pci_set_power_state(D3cold),
normally generates a hot-remove event that unbinds the driver.
Some drivers expect to remain bound to a device even while they power it
off and back on again. This can be dangerous, because if the device is
removed or replaced while it is powered off, the driver doesn't know that
anything changed. But some drivers accept that risk.
Add pci_ignore_hotplug() for use by drivers that know their device cannot
be removed. Using pci_ignore_hotplug() tells the PCI core that hot-plug
events for the device should be ignored.
The radeon and nouveau drivers use this to switch between a low-power,
integrated GPU and a higher-power, higher-performance discrete GPU. They
power off the unused GPU, but they want to remain bound to it.
This is a reimplementation of f244d8b623da ("ACPIPHP / radeon / nouveau:
Fix VGA switcheroo problem related to hotplug") but extends it to work with
both acpiphp and pciehp.
This fixes a problem where systems with dual GPUs using the radeon drivers
become unusable, freezing every few seconds (see bugzillas below). The
resume of the radeon device may also fail, e.g.,
This fixes problems on dual GPU systems where the radeon driver becomes
unusable because of problems while suspending the device, as in bug 79701:
[drm] radeon: finishing device.
radeon 0000:01:00.0: Userspace still has active objects !
radeon 0000:01:00.0: ffff8800cb4ec288 ffff8800cb4ec000 16384 4294967297 force free
...
WARNING: CPU: 0 PID: 67 at /home/apw/COD/linux/drivers/gpu/drm/radeon/radeon_gart.c:234 radeon_gart_unbind+0xd2/0xe0 [radeon]()
trying to unbind memory from uninitialized GART !
or while resuming it, as in bug 77261:
radeon 0000:01:00.0: ring 0 stalled for more than 10158msec
radeon 0000:01:00.0: GPU lockup ...
radeon 0000:01:00.0: GPU pci config reset
pciehp 0000:00:01.0:pcie04: Card not present on Slot(1-1)
radeon 0000:01:00.0: GPU reset succeeded, trying to resume
*ERROR* radeon: dpm resume failed
radeon 0000:01:00.0: Wait for MC idle timedout !
Link: https://bugzilla.kernel.org/show_bug.cgi?id=77261
Link: https://bugzilla.kernel.org/show_bug.cgi?id=79701
Reported-by: Shawn Starr <shawn.starr@...ers.com>
Reported-by: Jose P. <lbdkmjdf@...rklasers.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@...gle.com>
Acked-by: Alex Deucher <alexander.deucher@....com>
Acked-by: Rajat Jain <rajatxjain@...il.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
Acked-by: Dave Airlie <airlied@...hat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
drivers/gpu/drm/nouveau/nouveau_drm.c | 1 +
drivers/gpu/drm/radeon/radeon_drv.c | 1 +
drivers/pci/hotplug/acpiphp_glue.c | 16 ++++++----------
drivers/pci/hotplug/pciehp_hpc.c | 12 ++++++++++++
include/linux/pci.h | 6 ++++++
5 files changed, 26 insertions(+), 10 deletions(-)
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -596,6 +596,7 @@ int nouveau_pmops_suspend(struct device
pci_save_state(pdev);
pci_disable_device(pdev);
+ pci_ignore_hotplug(pdev);
pci_set_power_state(pdev, PCI_D3hot);
return 0;
}
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -429,6 +429,7 @@ static int radeon_pmops_runtime_suspend(
ret = radeon_suspend_kms(drm_dev, false, false);
pci_save_state(pdev);
pci_disable_device(pdev);
+ pci_ignore_hotplug(pdev);
pci_set_power_state(pdev, PCI_D3cold);
drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -573,19 +573,15 @@ static void disable_slot(struct acpiphp_
slot->flags &= (~SLOT_ENABLED);
}
-static bool acpiphp_no_hotplug(struct acpi_device *adev)
-{
- return adev && adev->flags.no_hotplug;
-}
-
static bool slot_no_hotplug(struct acpiphp_slot *slot)
{
- struct acpiphp_func *func;
+ struct pci_bus *bus = slot->bus;
+ struct pci_dev *dev;
- list_for_each_entry(func, &slot->funcs, sibling)
- if (acpiphp_no_hotplug(func_to_acpi_device(func)))
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ if (PCI_SLOT(dev->devfn) == slot->device && dev->ignore_hotplug)
return true;
-
+ }
return false;
}
@@ -658,7 +654,7 @@ static void trim_stale_devices(struct pc
status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta);
alive = (ACPI_SUCCESS(status) && device_status_valid(sta))
- || acpiphp_no_hotplug(adev);
+ || dev->ignore_hotplug;
}
if (!alive)
alive = pci_device_is_present(dev);
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -508,6 +508,8 @@ static irqreturn_t pcie_isr(int irq, voi
{
struct controller *ctrl = (struct controller *)dev_id;
struct pci_dev *pdev = ctrl_dev(ctrl);
+ struct pci_bus *subordinate = pdev->subordinate;
+ struct pci_dev *dev;
struct slot *slot = ctrl->slot;
u16 detected, intr_loc;
@@ -541,6 +543,16 @@ static irqreturn_t pcie_isr(int irq, voi
wake_up(&ctrl->queue);
}
+ if (subordinate) {
+ list_for_each_entry(dev, &subordinate->devices, bus_list) {
+ if (dev->ignore_hotplug) {
+ ctrl_dbg(ctrl, "ignoring hotplug event %#06x (%s requested no hotplug)\n",
+ intr_loc, pci_name(dev));
+ return IRQ_HANDLED;
+ }
+ }
+ }
+
if (!(intr_loc & ~PCI_EXP_SLTSTA_CC))
return IRQ_HANDLED;
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -303,6 +303,7 @@ struct pci_dev {
D3cold, not set for devices
powered on/off by the
corresponding bridge */
+ unsigned int ignore_hotplug:1; /* Ignore hotplug events */
unsigned int d3_delay; /* D3->D0 transition time in ms */
unsigned int d3cold_delay; /* D3cold->D0 transition time in ms */
@@ -1019,6 +1020,11 @@ bool pci_dev_run_wake(struct pci_dev *de
bool pci_check_pme_status(struct pci_dev *dev);
void pci_pme_wakeup_bus(struct pci_bus *bus);
+static inline void pci_ignore_hotplug(struct pci_dev *dev)
+{
+ dev->ignore_hotplug = 1;
+}
+
static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
bool enable)
{
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists