For a while we've been having issues with seemingly random interrupts
coming from nvidia cards when resuming them. Originally the fix for this
was thought to be just re-arming the MSI interrupt registers right after
re-allocating our IRQs, however it seems a lot of what we do is both
wrong and not even nessecary.
This was made apparent by what appeared to be a regression in the
mainline kernel that started introducing suspend/resume issues for
nouveau:
a0c9259dc4
(irq/matrix: Spread interrupts on allocation)
After this commit was introduced, we started getting interrupts from the
GPU before we actually re-allocated our own IRQ (see references below)
and assigned the IRQ handler. Investigating this turned out that the
problem was not with the commit, but the fact that nouveau even
free/allocates it's irqs before and after suspend/resume.
For starters: drivers in the linux kernel haven't had to handle
freeing/re-allocating their IRQs during suspend/resume cycles for quite
a while now. Nouveau seems to be one of the few drivers left that still
does this, despite the fact there's no reason we actually need to since
disabling interrupts from the device side should be enough, as the
kernel is already smart enough to know to disable host-side interrupts
for us before going into suspend. Since we were tearing down our IRQs by
hand however, that means there was a short period during resume where
interrupts could be received before we re-allocated our IRQ which would
lead to us getting an unhandled IRQ. Since we never handle said IRQ and
re-arm the interrupt registers, this would cause us to miss all of the
interrupts from the GPU and cause our init process to start timing out
on anything requiring interrupts.
So, since this whole setup/teardown every suspend/resume cycle is
useless anyway, move irq setup/teardown into the pci subdev's ctor/dtor
functions instead so they're only called at driver load and driver
unload. This should fix most of the issues with pending interrupts on
resume, along with getting suspend/resume for nouveau to work again.
As well, this probably means we can also just remove the msi rearm call
inside nvkm_pci_init(). But since our main focus here is to fix
suspend/resume before 4.15, we'll save that for a later patch.
Signed-off-by: Lyude Paul <lyude@redhat.com>
Cc: Karol Herbst <kherbst@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Mike Galbraith <efault@gmx.de>
Cc: stable@vger.kernel.org
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
232 lines
5.1 KiB
C
232 lines
5.1 KiB
C
/*
|
|
* Copyright 2015 Red Hat Inc.
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a
|
|
* copy of this software and associated documentation files (the "Software"),
|
|
* to deal in the Software without restriction, including without limitation
|
|
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
|
|
* and/or sell copies of the Software, and to permit persons to whom the
|
|
* Software is furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice shall be included in
|
|
* all copies or substantial portions of the Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
|
|
* THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
|
|
* OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
|
|
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
|
|
* OTHER DEALINGS IN THE SOFTWARE.
|
|
*
|
|
* Authors: Ben Skeggs <bskeggs@redhat.com>
|
|
*/
|
|
#include "priv.h"
|
|
#include "agp.h"
|
|
|
|
#include <core/option.h>
|
|
#include <core/pci.h>
|
|
#include <subdev/mc.h>
|
|
|
|
u32
|
|
nvkm_pci_rd32(struct nvkm_pci *pci, u16 addr)
|
|
{
|
|
return pci->func->rd32(pci, addr);
|
|
}
|
|
|
|
void
|
|
nvkm_pci_wr08(struct nvkm_pci *pci, u16 addr, u8 data)
|
|
{
|
|
pci->func->wr08(pci, addr, data);
|
|
}
|
|
|
|
void
|
|
nvkm_pci_wr32(struct nvkm_pci *pci, u16 addr, u32 data)
|
|
{
|
|
pci->func->wr32(pci, addr, data);
|
|
}
|
|
|
|
u32
|
|
nvkm_pci_mask(struct nvkm_pci *pci, u16 addr, u32 mask, u32 value)
|
|
{
|
|
u32 data = pci->func->rd32(pci, addr);
|
|
pci->func->wr32(pci, addr, (data & ~mask) | value);
|
|
return data;
|
|
}
|
|
|
|
void
|
|
nvkm_pci_rom_shadow(struct nvkm_pci *pci, bool shadow)
|
|
{
|
|
u32 data = nvkm_pci_rd32(pci, 0x0050);
|
|
if (shadow)
|
|
data |= 0x00000001;
|
|
else
|
|
data &= ~0x00000001;
|
|
nvkm_pci_wr32(pci, 0x0050, data);
|
|
}
|
|
|
|
static irqreturn_t
|
|
nvkm_pci_intr(int irq, void *arg)
|
|
{
|
|
struct nvkm_pci *pci = arg;
|
|
struct nvkm_device *device = pci->subdev.device;
|
|
bool handled = false;
|
|
|
|
if (pci->irq < 0)
|
|
return IRQ_HANDLED;
|
|
|
|
nvkm_mc_intr_unarm(device);
|
|
if (pci->msi)
|
|
pci->func->msi_rearm(pci);
|
|
nvkm_mc_intr(device, &handled);
|
|
nvkm_mc_intr_rearm(device);
|
|
return handled ? IRQ_HANDLED : IRQ_NONE;
|
|
}
|
|
|
|
static int
|
|
nvkm_pci_fini(struct nvkm_subdev *subdev, bool suspend)
|
|
{
|
|
struct nvkm_pci *pci = nvkm_pci(subdev);
|
|
|
|
if (pci->agp.bridge)
|
|
nvkm_agp_fini(pci);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
nvkm_pci_preinit(struct nvkm_subdev *subdev)
|
|
{
|
|
struct nvkm_pci *pci = nvkm_pci(subdev);
|
|
if (pci->agp.bridge)
|
|
nvkm_agp_preinit(pci);
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
nvkm_pci_oneinit(struct nvkm_subdev *subdev)
|
|
{
|
|
struct nvkm_pci *pci = nvkm_pci(subdev);
|
|
struct pci_dev *pdev = pci->pdev;
|
|
int ret;
|
|
|
|
if (pci_is_pcie(pci->pdev)) {
|
|
ret = nvkm_pcie_oneinit(pci);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
ret = request_irq(pdev->irq, nvkm_pci_intr, IRQF_SHARED, "nvkm", pci);
|
|
if (ret)
|
|
return ret;
|
|
|
|
pci->irq = pdev->irq;
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
nvkm_pci_init(struct nvkm_subdev *subdev)
|
|
{
|
|
struct nvkm_pci *pci = nvkm_pci(subdev);
|
|
int ret;
|
|
|
|
if (pci->agp.bridge) {
|
|
ret = nvkm_agp_init(pci);
|
|
if (ret)
|
|
return ret;
|
|
} else if (pci_is_pcie(pci->pdev)) {
|
|
nvkm_pcie_init(pci);
|
|
}
|
|
|
|
if (pci->func->init)
|
|
pci->func->init(pci);
|
|
|
|
/* Ensure MSI interrupts are armed, for the case where there are
|
|
* already interrupts pending (for whatever reason) at load time.
|
|
*/
|
|
if (pci->msi)
|
|
pci->func->msi_rearm(pci);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void *
|
|
nvkm_pci_dtor(struct nvkm_subdev *subdev)
|
|
{
|
|
struct nvkm_pci *pci = nvkm_pci(subdev);
|
|
|
|
nvkm_agp_dtor(pci);
|
|
|
|
if (pci->irq >= 0) {
|
|
/* freq_irq() will call the handler, we use pci->irq == -1
|
|
* to signal that it's been torn down and should be a noop.
|
|
*/
|
|
int irq = pci->irq;
|
|
pci->irq = -1;
|
|
free_irq(irq, pci);
|
|
}
|
|
|
|
if (pci->msi)
|
|
pci_disable_msi(pci->pdev);
|
|
|
|
return nvkm_pci(subdev);
|
|
}
|
|
|
|
static const struct nvkm_subdev_func
|
|
nvkm_pci_func = {
|
|
.dtor = nvkm_pci_dtor,
|
|
.oneinit = nvkm_pci_oneinit,
|
|
.preinit = nvkm_pci_preinit,
|
|
.init = nvkm_pci_init,
|
|
.fini = nvkm_pci_fini,
|
|
};
|
|
|
|
int
|
|
nvkm_pci_new_(const struct nvkm_pci_func *func, struct nvkm_device *device,
|
|
int index, struct nvkm_pci **ppci)
|
|
{
|
|
struct nvkm_pci *pci;
|
|
|
|
if (!(pci = *ppci = kzalloc(sizeof(**ppci), GFP_KERNEL)))
|
|
return -ENOMEM;
|
|
nvkm_subdev_ctor(&nvkm_pci_func, device, index, &pci->subdev);
|
|
pci->func = func;
|
|
pci->pdev = device->func->pci(device)->pdev;
|
|
pci->irq = -1;
|
|
pci->pcie.speed = -1;
|
|
pci->pcie.width = -1;
|
|
|
|
if (device->type == NVKM_DEVICE_AGP)
|
|
nvkm_agp_ctor(pci);
|
|
|
|
switch (pci->pdev->device & 0x0ff0) {
|
|
case 0x00f0:
|
|
case 0x02e0:
|
|
/* BR02? NFI how these would be handled yet exactly */
|
|
break;
|
|
default:
|
|
switch (device->chipset) {
|
|
case 0xaa:
|
|
/* reported broken, nv also disable it */
|
|
break;
|
|
default:
|
|
pci->msi = true;
|
|
break;
|
|
}
|
|
}
|
|
|
|
#ifdef __BIG_ENDIAN
|
|
pci->msi = false;
|
|
#endif
|
|
|
|
pci->msi = nvkm_boolopt(device->cfgopt, "NvMSI", pci->msi);
|
|
if (pci->msi && func->msi_rearm) {
|
|
pci->msi = pci_enable_msi(pci->pdev) == 0;
|
|
if (pci->msi)
|
|
nvkm_debug(&pci->subdev, "MSI enabled\n");
|
|
} else {
|
|
pci->msi = false;
|
|
}
|
|
|
|
return 0;
|
|
}
|