2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-28 15:13:55 +08:00
linux-next/kernel/irq/msi.c

554 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2014 Intel Corp.
* Author: Jiang Liu <jiang.liu@linux.intel.com>
*
* This file is licensed under GPLv2.
*
* This file contains common code to support Message Signalled Interrupt for
* PCI compatible and non PCI compatible devices.
*/
#include <linux/types.h>
#include <linux/device.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/msi.h>
#include <linux/slab.h>
#include "internals.h"
/**
* alloc_msi_entry - Allocate an initialize msi_entry
* @dev: Pointer to the device for which this is allocated
* @nvec: The number of vectors used in this entry
* @affinity: Optional pointer to an affinity mask array size of @nvec
*
genirq/core: Introduce struct irq_affinity_desc The interrupt affinity management uses straight cpumask pointers to convey the automatically assigned affinity masks for managed interrupts. The core interrupt descriptor allocation also decides based on the pointer being non NULL whether an interrupt is managed or not. Devices which use managed interrupts usually have two classes of interrupts: - Interrupts for multiple device queues - Interrupts for general device management Currently both classes are treated the same way, i.e. as managed interrupts. The general interrupts get the default affinity mask assigned while the device queue interrupts are spread out over the possible CPUs. Treating the general interrupts as managed is both a limitation and under certain circumstances a bug. Assume the following situation: default_irq_affinity = 4..7 So if CPUs 4-7 are offlined, then the core code will shut down the device management interrupts because the last CPU in their affinity mask went offline. It's also a limitation because it's desired to allow manual placement of the general device interrupts for various reasons. If they are marked managed then the interrupt affinity setting from both user and kernel space is disabled. To remedy that situation it's required to convey more information than the cpumasks through various interfaces related to interrupt descriptor allocation. Instead of adding yet another argument, create a new data structure 'irq_affinity_desc' which for now just contains the cpumask. This struct can be expanded to convey auxilliary information in the next step. No functional change, just preparatory work. [ tglx: Simplified logic and clarified changelog ] Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Dou Liyang <douliyangs@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-pci@vger.kernel.org Cc: kashyap.desai@broadcom.com Cc: shivasharan.srikanteshwara@broadcom.com Cc: sumit.saxena@broadcom.com Cc: ming.lei@redhat.com Cc: hch@lst.de Cc: douliyang1@huawei.com Link: https://lkml.kernel.org/r/20181204155122.6327-2-douliyangs@gmail.com
2018-12-04 23:51:20 +08:00
* If @affinity is not NULL then an affinity array[@nvec] is allocated
* and the affinity masks and flags from @affinity are copied.
*/
genirq/core: Introduce struct irq_affinity_desc The interrupt affinity management uses straight cpumask pointers to convey the automatically assigned affinity masks for managed interrupts. The core interrupt descriptor allocation also decides based on the pointer being non NULL whether an interrupt is managed or not. Devices which use managed interrupts usually have two classes of interrupts: - Interrupts for multiple device queues - Interrupts for general device management Currently both classes are treated the same way, i.e. as managed interrupts. The general interrupts get the default affinity mask assigned while the device queue interrupts are spread out over the possible CPUs. Treating the general interrupts as managed is both a limitation and under certain circumstances a bug. Assume the following situation: default_irq_affinity = 4..7 So if CPUs 4-7 are offlined, then the core code will shut down the device management interrupts because the last CPU in their affinity mask went offline. It's also a limitation because it's desired to allow manual placement of the general device interrupts for various reasons. If they are marked managed then the interrupt affinity setting from both user and kernel space is disabled. To remedy that situation it's required to convey more information than the cpumasks through various interfaces related to interrupt descriptor allocation. Instead of adding yet another argument, create a new data structure 'irq_affinity_desc' which for now just contains the cpumask. This struct can be expanded to convey auxilliary information in the next step. No functional change, just preparatory work. [ tglx: Simplified logic and clarified changelog ] Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Dou Liyang <douliyangs@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-pci@vger.kernel.org Cc: kashyap.desai@broadcom.com Cc: shivasharan.srikanteshwara@broadcom.com Cc: sumit.saxena@broadcom.com Cc: ming.lei@redhat.com Cc: hch@lst.de Cc: douliyang1@huawei.com Link: https://lkml.kernel.org/r/20181204155122.6327-2-douliyangs@gmail.com
2018-12-04 23:51:20 +08:00
struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
const struct irq_affinity_desc *affinity)
{
struct msi_desc *desc;
desc = kzalloc(sizeof(*desc), GFP_KERNEL);
if (!desc)
return NULL;
INIT_LIST_HEAD(&desc->list);
desc->dev = dev;
desc->nvec_used = nvec;
if (affinity) {
desc->affinity = kmemdup(affinity,
nvec * sizeof(*desc->affinity), GFP_KERNEL);
if (!desc->affinity) {
kfree(desc);
return NULL;
}
}
return desc;
}
void free_msi_entry(struct msi_desc *entry)
{
kfree(entry->affinity);
kfree(entry);
}
void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
*msg = entry->msg;
}
void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
{
struct msi_desc *entry = irq_get_msi_desc(irq);
__get_cached_msi_msg(entry, msg);
}
EXPORT_SYMBOL_GPL(get_cached_msi_msg);
#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
static inline void irq_chip_write_msi_msg(struct irq_data *data,
struct msi_msg *msg)
{
data->chip->irq_write_msi_msg(data, msg);
}
static void msi_check_level(struct irq_domain *domain, struct msi_msg *msg)
{
struct msi_domain_info *info = domain->host_data;
/*
* If the MSI provider has messed with the second message and
* not advertized that it is level-capable, signal the breakage.
*/
WARN_ON(!((info->flags & MSI_FLAG_LEVEL_CAPABLE) &&
(info->chip->flags & IRQCHIP_SUPPORTS_LEVEL_MSI)) &&
(msg[1].address_lo || msg[1].address_hi || msg[1].data));
}
/**
* msi_domain_set_affinity - Generic affinity setter function for MSI domains
* @irq_data: The irq data associated to the interrupt
* @mask: The affinity mask to set
* @force: Flag to enforce setting (disable online checks)
*
* Intended to be used by MSI interrupt controllers which are
* implemented with hierarchical domains.
*/
int msi_domain_set_affinity(struct irq_data *irq_data,
const struct cpumask *mask, bool force)
{
struct irq_data *parent = irq_data->parent_data;
struct msi_msg msg[2] = { [1] = { }, };
int ret;
ret = parent->chip->irq_set_affinity(parent, mask, force);
if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
msi_check_level(irq_data->domain, msg);
irq_chip_write_msi_msg(irq_data, msg);
}
return ret;
}
static int msi_domain_activate(struct irq_domain *domain,
struct irq_data *irq_data, bool early)
{
struct msi_msg msg[2] = { [1] = { }, };
BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
msi_check_level(irq_data->domain, msg);
irq_chip_write_msi_msg(irq_data, msg);
return 0;
}
static void msi_domain_deactivate(struct irq_domain *domain,
struct irq_data *irq_data)
{
struct msi_msg msg[2];
memset(msg, 0, sizeof(msg));
irq_chip_write_msi_msg(irq_data, msg);
}
static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
irq_hw_number_t hwirq = ops->get_hwirq(info, arg);
int i, ret;
if (irq_find_mapping(domain, hwirq) > 0)
return -EEXIST;
if (domain->parent) {
ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
if (ret < 0)
return ret;
}
for (i = 0; i < nr_irqs; i++) {
ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg);
if (ret < 0) {
if (ops->msi_free) {
for (i--; i > 0; i--)
ops->msi_free(domain, info, virq + i);
}
irq_domain_free_irqs_top(domain, virq, nr_irqs);
return ret;
}
}
return 0;
}
static void msi_domain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs)
{
struct msi_domain_info *info = domain->host_data;
int i;
if (info->ops->msi_free) {
for (i = 0; i < nr_irqs; i++)
info->ops->msi_free(domain, info, virq + i);
}
irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
static const struct irq_domain_ops msi_domain_ops = {
.alloc = msi_domain_alloc,
.free = msi_domain_free,
.activate = msi_domain_activate,
.deactivate = msi_domain_deactivate,
};
static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,
msi_alloc_info_t *arg)
{
return arg->hwirq;
}
static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev,
int nvec, msi_alloc_info_t *arg)
{
memset(arg, 0, sizeof(*arg));
return 0;
}
static void msi_domain_ops_set_desc(msi_alloc_info_t *arg,
struct msi_desc *desc)
{
arg->desc = desc;
}
static int msi_domain_ops_init(struct irq_domain *domain,
struct msi_domain_info *info,
unsigned int virq, irq_hw_number_t hwirq,
msi_alloc_info_t *arg)
{
irq_domain_set_hwirq_and_chip(domain, virq, hwirq, info->chip,
info->chip_data);
if (info->handler && info->handler_name) {
__irq_set_handler(virq, info->handler, 0, info->handler_name);
if (info->handler_data)
irq_set_handler_data(virq, info->handler_data);
}
return 0;
}
static int msi_domain_ops_check(struct irq_domain *domain,
struct msi_domain_info *info,
struct device *dev)
{
return 0;
}
static struct msi_domain_ops msi_domain_ops_default = {
.get_hwirq = msi_domain_ops_get_hwirq,
.msi_init = msi_domain_ops_init,
.msi_check = msi_domain_ops_check,
.msi_prepare = msi_domain_ops_prepare,
.set_desc = msi_domain_ops_set_desc,
.domain_alloc_irqs = __msi_domain_alloc_irqs,
.domain_free_irqs = __msi_domain_free_irqs,
};
static void msi_domain_update_dom_ops(struct msi_domain_info *info)
{
struct msi_domain_ops *ops = info->ops;
if (ops == NULL) {
info->ops = &msi_domain_ops_default;
return;
}
if (ops->domain_alloc_irqs == NULL)
ops->domain_alloc_irqs = msi_domain_ops_default.domain_alloc_irqs;
if (ops->domain_free_irqs == NULL)
ops->domain_free_irqs = msi_domain_ops_default.domain_free_irqs;
if (!(info->flags & MSI_FLAG_USE_DEF_DOM_OPS))
return;
if (ops->get_hwirq == NULL)
ops->get_hwirq = msi_domain_ops_default.get_hwirq;
if (ops->msi_init == NULL)
ops->msi_init = msi_domain_ops_default.msi_init;
if (ops->msi_check == NULL)
ops->msi_check = msi_domain_ops_default.msi_check;
if (ops->msi_prepare == NULL)
ops->msi_prepare = msi_domain_ops_default.msi_prepare;
if (ops->set_desc == NULL)
ops->set_desc = msi_domain_ops_default.set_desc;
}
static void msi_domain_update_chip_ops(struct msi_domain_info *info)
{
struct irq_chip *chip = info->chip;
BUG_ON(!chip || !chip->irq_mask || !chip->irq_unmask);
if (!chip->irq_set_affinity)
chip->irq_set_affinity = msi_domain_set_affinity;
}
/**
* msi_create_irq_domain - Create a MSI interrupt domain
* @fwnode: Optional fwnode of the interrupt controller
* @info: MSI domain info
* @parent: Parent irq domain
*/
struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
struct msi_domain_info *info,
struct irq_domain *parent)
{
struct irq_domain *domain;
msi_domain_update_dom_ops(info);
if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
msi_domain_update_chip_ops(info);
domain = irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0,
fwnode, &msi_domain_ops, info);
if (domain && !domain->name && info->chip)
domain->name = info->chip->name;
return domain;
}
int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
int nvec, msi_alloc_info_t *arg)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
int ret;
ret = ops->msi_check(domain, info, dev);
if (ret == 0)
ret = ops->msi_prepare(domain, dev, nvec, arg);
return ret;
}
int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
int virq, int nvec, msi_alloc_info_t *arg)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
struct msi_desc *desc;
int ret = 0;
for_each_msi_entry(desc, dev) {
/* Don't even try the multi-MSI brain damage. */
if (WARN_ON(!desc->irq || desc->nvec_used != 1)) {
ret = -EINVAL;
break;
}
if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
continue;
ops->set_desc(arg, desc);
/* Assumes the domain mutex is held! */
ret = irq_domain_alloc_irqs_hierarchy(domain, desc->irq, 1,
arg);
if (ret)
break;
irq_set_msi_desc_off(desc->irq, 0, desc);
}
if (ret) {
/* Mop up the damage */
for_each_msi_entry(desc, dev) {
if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
continue;
irq_domain_free_irqs_common(domain, desc->irq, 1);
}
}
return ret;
}
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
/*
* Carefully check whether the device can use reservation mode. If
* reservation mode is enabled then the early activation will assign a
* dummy vector to the device. If the PCI/MSI device does not support
* masking of the entry then this can result in spurious interrupts when
* the device driver is not absolutely careful. But even then a malfunction
* of the hardware could result in a spurious interrupt on the dummy vector
* and render the device unusable. If the entry can be masked then the core
* logic will prevent the spurious interrupt and reservation mode can be
* used. For now reservation mode is restricted to PCI/MSI.
*/
static bool msi_check_reservation_mode(struct irq_domain *domain,
struct msi_domain_info *info,
struct device *dev)
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
{
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
struct msi_desc *desc;
switch(domain->bus_token) {
case DOMAIN_BUS_PCI_MSI:
case DOMAIN_BUS_VMD_MSI:
break;
default:
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
return false;
}
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
if (!(info->flags & MSI_FLAG_MUST_REACTIVATE))
return false;
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
if (IS_ENABLED(CONFIG_PCI_MSI) && pci_msi_ignore_mask)
return false;
/*
* Checking the first MSI descriptor is sufficient. MSIX supports
* masking and MSI does so when the maskbit is set.
*/
desc = first_msi_entry(dev);
return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit;
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
}
int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
int nvec)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
struct irq_data *irq_data;
struct msi_desc *desc;
msi_alloc_info_t arg = { };
int i, ret, virq;
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
bool can_reserve;
ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
if (ret)
return ret;
for_each_msi_entry(desc, dev) {
ops->set_desc(&arg, desc);
virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
dev_to_node(dev), &arg, false,
desc->affinity);
if (virq < 0) {
ret = -ENOSPC;
if (ops->handle_error)
ret = ops->handle_error(domain, desc, ret);
if (ops->msi_finish)
ops->msi_finish(&arg, ret);
return ret;
}
for (i = 0; i < desc->nvec_used; i++) {
irq_set_msi_desc_off(virq, i, desc);
irq_debugfs_copy_devname(virq + i, dev);
}
}
if (ops->msi_finish)
ops->msi_finish(&arg, 0);
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
can_reserve = msi_check_reservation_mode(domain, info, dev);
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
for_each_msi_entry(desc, dev) {
virq = desc->irq;
if (desc->nvec_used == 1)
dev_dbg(dev, "irq %d for MSI\n", virq);
else
dev_dbg(dev, "irq [%d-%d] for MSI\n",
virq, virq + desc->nvec_used - 1);
genirq/msi: Make sure PCI MSIs are activated early Bharat Kumar Gogada reported issues with the generic MSI code, where the end-point ended up with garbage in its MSI configuration (both for the vector and the message). It turns out that the two MSI paths in the kernel are doing slightly different things: generic MSI: disable MSI -> allocate MSI -> enable MSI -> setup EP PCI MSI: disable MSI -> allocate MSI -> setup EP -> enable MSI And it turns out that end-points are allowed to latch the content of the MSI configuration registers as soon as MSIs are enabled. In Bharat's case, the end-point ends up using whatever was there already, which is not what you want. In order to make things converge, we introduce a new MSI domain flag (MSI_FLAG_ACTIVATE_EARLY) that is unconditionally set for PCI/MSI. When set, this flag forces the programming of the end-point as soon as the MSIs are allocated. A consequence of this is that we have an extra activate in irq_startup, but that should be without much consequence. tglx: - Several people reported a VMWare regression with PCI/MSI-X passthrough. It turns out that the patch also cures that issue. - We need to have a look at the MSI disable interrupt path, where we write the msg to all zeros without disabling MSI in the PCI device. Is that correct? Fixes: 52f518a3a7c2 "x86/MSI: Use hierarchical irqdomains to manage MSI interrupts" Reported-and-tested-by: Bharat Kumar Gogada <bharat.kumar.gogada@xilinx.com> Reported-and-tested-by: Foster Snowhill <forst@forstwoof.ru> Reported-by: Matthias Prager <linux@matthiasprager.de> Reported-by: Jason Taylor <jason.taylor@simplivity.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: linux-pci@vger.kernel.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1468426713-31431-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-07-14 00:18:33 +08:00
/*
* This flag is set by the PCI layer as we need to activate
* the MSI entries before the PCI layer enables MSI in the
* card. Otherwise the card latches a random msi message.
*/
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
continue;
genirq/msi: Make sure PCI MSIs are activated early Bharat Kumar Gogada reported issues with the generic MSI code, where the end-point ended up with garbage in its MSI configuration (both for the vector and the message). It turns out that the two MSI paths in the kernel are doing slightly different things: generic MSI: disable MSI -> allocate MSI -> enable MSI -> setup EP PCI MSI: disable MSI -> allocate MSI -> setup EP -> enable MSI And it turns out that end-points are allowed to latch the content of the MSI configuration registers as soon as MSIs are enabled. In Bharat's case, the end-point ends up using whatever was there already, which is not what you want. In order to make things converge, we introduce a new MSI domain flag (MSI_FLAG_ACTIVATE_EARLY) that is unconditionally set for PCI/MSI. When set, this flag forces the programming of the end-point as soon as the MSIs are allocated. A consequence of this is that we have an extra activate in irq_startup, but that should be without much consequence. tglx: - Several people reported a VMWare regression with PCI/MSI-X passthrough. It turns out that the patch also cures that issue. - We need to have a look at the MSI disable interrupt path, where we write the msg to all zeros without disabling MSI in the PCI device. Is that correct? Fixes: 52f518a3a7c2 "x86/MSI: Use hierarchical irqdomains to manage MSI interrupts" Reported-and-tested-by: Bharat Kumar Gogada <bharat.kumar.gogada@xilinx.com> Reported-and-tested-by: Foster Snowhill <forst@forstwoof.ru> Reported-by: Matthias Prager <linux@matthiasprager.de> Reported-by: Jason Taylor <jason.taylor@simplivity.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: linux-pci@vger.kernel.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1468426713-31431-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-07-14 00:18:33 +08:00
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
irq_data = irq_domain_get_irq_data(domain, desc->irq);
x86/apic/msi: Plug non-maskable MSI affinity race Evan tracked down a subtle race between the update of the MSI message and the device raising an interrupt internally on PCI devices which do not support MSI masking. The update of the MSI message is non-atomic and consists of either 2 or 3 sequential 32bit wide writes to the PCI config space. - Write address low 32bits - Write address high 32bits (If supported by device) - Write data When an interrupt is migrated then both address and data might change, so the kernel attempts to mask the MSI interrupt first. But for MSI masking is optional, so there exist devices which do not provide it. That means that if the device raises an interrupt internally between the writes then a MSI message is sent built from half updated state. On x86 this can lead to spurious interrupts on the wrong interrupt vector when the affinity setting changes both address and data. As a consequence the device interrupt can be lost causing the device to become stuck or malfunctioning. Evan tried to handle that by disabling MSI accross an MSI message update. That's not feasible because disabling MSI has issues on its own: If MSI is disabled the PCI device is routing an interrupt to the legacy INTx mechanism. The INTx delivery can be disabled, but the disablement is not working on all devices. Some devices lose interrupts when both MSI and INTx delivery are disabled. Another way to solve this would be to enforce the allocation of the same vector on all CPUs in the system for this kind of screwed devices. That could be done, but it would bring back the vector space exhaustion problems which got solved a few years ago. Fortunately the high address (if supported by the device) is only relevant when X2APIC is enabled which implies interrupt remapping. In the interrupt remapping case the affinity setting is happening at the interrupt remapping unit and the PCI MSI message is programmed only once when the PCI device is initialized. That makes it possible to solve it with a two step update: 1) Target the MSI msg to the new vector on the current target CPU 2) Target the MSI msg to the new vector on the new target CPU In both cases writing the MSI message is only changing a single 32bit word which prevents the issue of inconsistency. After writing the final destination it is necessary to check whether the device issued an interrupt while the intermediate state #1 (new vector, current CPU) was in effect. This is possible because the affinity change is always happening on the current target CPU. The code runs with interrupts disabled, so the interrupt can be detected by checking the IRR of the local APIC. If the vector is pending in the IRR then the interrupt is retriggered on the new target CPU by sending an IPI for the associated vector on the target CPU. This can cause spurious interrupts on both the local and the new target CPU. 1) If the new vector is not in use on the local CPU and the device affected by the affinity change raised an interrupt during the transitional state (step #1 above) then interrupt entry code will ignore that spurious interrupt. The vector is marked so that the 'No irq handler for vector' warning is supressed once. 2) If the new vector is in use already on the local CPU then the IRR check might see an pending interrupt from the device which is using this vector. The IPI to the new target CPU will then invoke the handler of the device, which got the affinity change, even if that device did not issue an interrupt 3) If the new vector is in use already on the local CPU and the device affected by the affinity change raised an interrupt during the transitional state (step #1 above) then the handler of the device which uses that vector on the local CPU will be invoked. expose issues in device driver interrupt handlers which are not prepared to handle a spurious interrupt correctly. This not a regression, it's just exposing something which was already broken as spurious interrupts can happen for a lot of reasons and all driver handlers need to be able to deal with them. Reported-by: Evan Green <evgreen@chromium.org> Debugged-by: Evan Green <evgreen@chromium.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Evan Green <evgreen@chromium.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87imkr4s7n.fsf@nanos.tec.linutronix.de
2020-01-31 22:26:52 +08:00
if (!can_reserve) {
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
irqd_clr_can_reserve(irq_data);
x86/apic/msi: Plug non-maskable MSI affinity race Evan tracked down a subtle race between the update of the MSI message and the device raising an interrupt internally on PCI devices which do not support MSI masking. The update of the MSI message is non-atomic and consists of either 2 or 3 sequential 32bit wide writes to the PCI config space. - Write address low 32bits - Write address high 32bits (If supported by device) - Write data When an interrupt is migrated then both address and data might change, so the kernel attempts to mask the MSI interrupt first. But for MSI masking is optional, so there exist devices which do not provide it. That means that if the device raises an interrupt internally between the writes then a MSI message is sent built from half updated state. On x86 this can lead to spurious interrupts on the wrong interrupt vector when the affinity setting changes both address and data. As a consequence the device interrupt can be lost causing the device to become stuck or malfunctioning. Evan tried to handle that by disabling MSI accross an MSI message update. That's not feasible because disabling MSI has issues on its own: If MSI is disabled the PCI device is routing an interrupt to the legacy INTx mechanism. The INTx delivery can be disabled, but the disablement is not working on all devices. Some devices lose interrupts when both MSI and INTx delivery are disabled. Another way to solve this would be to enforce the allocation of the same vector on all CPUs in the system for this kind of screwed devices. That could be done, but it would bring back the vector space exhaustion problems which got solved a few years ago. Fortunately the high address (if supported by the device) is only relevant when X2APIC is enabled which implies interrupt remapping. In the interrupt remapping case the affinity setting is happening at the interrupt remapping unit and the PCI MSI message is programmed only once when the PCI device is initialized. That makes it possible to solve it with a two step update: 1) Target the MSI msg to the new vector on the current target CPU 2) Target the MSI msg to the new vector on the new target CPU In both cases writing the MSI message is only changing a single 32bit word which prevents the issue of inconsistency. After writing the final destination it is necessary to check whether the device issued an interrupt while the intermediate state #1 (new vector, current CPU) was in effect. This is possible because the affinity change is always happening on the current target CPU. The code runs with interrupts disabled, so the interrupt can be detected by checking the IRR of the local APIC. If the vector is pending in the IRR then the interrupt is retriggered on the new target CPU by sending an IPI for the associated vector on the target CPU. This can cause spurious interrupts on both the local and the new target CPU. 1) If the new vector is not in use on the local CPU and the device affected by the affinity change raised an interrupt during the transitional state (step #1 above) then interrupt entry code will ignore that spurious interrupt. The vector is marked so that the 'No irq handler for vector' warning is supressed once. 2) If the new vector is in use already on the local CPU then the IRR check might see an pending interrupt from the device which is using this vector. The IPI to the new target CPU will then invoke the handler of the device, which got the affinity change, even if that device did not issue an interrupt 3) If the new vector is in use already on the local CPU and the device affected by the affinity change raised an interrupt during the transitional state (step #1 above) then the handler of the device which uses that vector on the local CPU will be invoked. expose issues in device driver interrupt handlers which are not prepared to handle a spurious interrupt correctly. This not a regression, it's just exposing something which was already broken as spurious interrupts can happen for a lot of reasons and all driver handlers need to be able to deal with them. Reported-by: Evan Green <evgreen@chromium.org> Debugged-by: Evan Green <evgreen@chromium.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Evan Green <evgreen@chromium.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87imkr4s7n.fsf@nanos.tec.linutronix.de
2020-01-31 22:26:52 +08:00
if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
irqd_set_msi_nomask_quirk(irq_data);
}
genirq/msi, x86/vector: Prevent reservation mode for non maskable MSI The new reservation mode for interrupts assigns a dummy vector when the interrupt is allocated and assigns a real vector when the interrupt is requested. The reservation mode prevents vector pressure when devices with a large amount of queues/interrupts are initialized, but only a minimal subset of those queues/interrupts is actually used. This mode has an issue with MSI interrupts which cannot be masked. If the driver is not careful or the hardware emits an interrupt before the device irq is requestd by the driver then the interrupt ends up on the dummy vector as a spurious interrupt which can cause malfunction of the device or in the worst case a lockup of the machine. Change the logic for the reservation mode so that the early activation of MSI interrupts checks whether: - the device is a PCI/MSI device - the reservation mode of the underlying irqdomain is activated - PCI/MSI masking is globally enabled - the PCI/MSI device uses either MSI-X, which supports masking, or MSI with the maskbit supported. If one of those conditions is false, then clear the reservation mode flag in the irq data of the interrupt and invoke irq_domain_activate_irq() with the reserve argument cleared. In the x86 vector code, clear the can_reserve flag in the vector allocation data so a subsequent free_irq() won't create the same situation again. The interrupt stays assigned to a real vector until pci_disable_msi() is invoked and all allocations are undone. Fixes: 4900be83602b ("x86/vector/msi: Switch to global reservation mode") Reported-by: Alexandru Chirvasitu <achirvasub@gmail.com> Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291406420.1899@nanos Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712291409460.1899@nanos
2017-12-29 17:47:22 +08:00
ret = irq_domain_activate_irq(irq_data, can_reserve);
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
if (ret)
goto cleanup;
}
/*
* If these interrupts use reservation mode, clear the activated bit
* so request_irq() will assign the final vector.
*/
if (can_reserve) {
for_each_msi_entry(desc, dev) {
genirq/msi: Make sure PCI MSIs are activated early Bharat Kumar Gogada reported issues with the generic MSI code, where the end-point ended up with garbage in its MSI configuration (both for the vector and the message). It turns out that the two MSI paths in the kernel are doing slightly different things: generic MSI: disable MSI -> allocate MSI -> enable MSI -> setup EP PCI MSI: disable MSI -> allocate MSI -> setup EP -> enable MSI And it turns out that end-points are allowed to latch the content of the MSI configuration registers as soon as MSIs are enabled. In Bharat's case, the end-point ends up using whatever was there already, which is not what you want. In order to make things converge, we introduce a new MSI domain flag (MSI_FLAG_ACTIVATE_EARLY) that is unconditionally set for PCI/MSI. When set, this flag forces the programming of the end-point as soon as the MSIs are allocated. A consequence of this is that we have an extra activate in irq_startup, but that should be without much consequence. tglx: - Several people reported a VMWare regression with PCI/MSI-X passthrough. It turns out that the patch also cures that issue. - We need to have a look at the MSI disable interrupt path, where we write the msg to all zeros without disabling MSI in the PCI device. Is that correct? Fixes: 52f518a3a7c2 "x86/MSI: Use hierarchical irqdomains to manage MSI interrupts" Reported-and-tested-by: Bharat Kumar Gogada <bharat.kumar.gogada@xilinx.com> Reported-and-tested-by: Foster Snowhill <forst@forstwoof.ru> Reported-by: Matthias Prager <linux@matthiasprager.de> Reported-by: Jason Taylor <jason.taylor@simplivity.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: linux-pci@vger.kernel.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1468426713-31431-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-07-14 00:18:33 +08:00
irq_data = irq_domain_get_irq_data(domain, desc->irq);
genirq/msi: Handle reactivation only on success When analyzing the fallout of the x86 vector allocation rework it turned out that the error handling in msi_domain_alloc_irqs() is broken. If MSI_FLAG_MUST_REACTIVATE is set for a MSI domain then it clears the activation flag for a successfully initialized msi descriptor. If a subsequent initialization fails then the error handling code path does not deactivate the interrupt because the activation flag got cleared. Move the clearing of the activation flag outside of the initialization loop so that an eventual failure can be cleaned up correctly. Fixes: 22d0b12f3560 ("genirq/irqdomain: Add force reactivation flag to irq domains") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Alexandru Chirvasitu <achirvasub@gmail.com> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Dou Liyang <douly.fnst@cn.fujitsu.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Maciej W. Rozycki <macro@linux-mips.org> Cc: Mikael Pettersson <mikpelinux@gmail.com> Cc: Josh Poulson <jopoulso@microsoft.com> Cc: Mihai Costache <v-micos@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Marc Zyngier <marc.zyngier@arm.com> Cc: linux-pci@vger.kernel.org Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Dexuan Cui <decui@microsoft.com> Cc: Simon Xiao <sixiao@microsoft.com> Cc: Saeed Mahameed <saeedm@mellanox.com> Cc: Jork Loeser <Jork.Loeser@microsoft.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: devel@linuxdriverproject.org Cc: KY Srinivasan <kys@microsoft.com> Cc: Alan Cox <alan@linux.intel.com> Cc: Sakari Ailus <sakari.ailus@intel.com>, Cc: linux-media@vger.kernel.org
2017-12-29 17:42:10 +08:00
irqd_clr_activated(irq_data);
genirq/msi: Make sure PCI MSIs are activated early Bharat Kumar Gogada reported issues with the generic MSI code, where the end-point ended up with garbage in its MSI configuration (both for the vector and the message). It turns out that the two MSI paths in the kernel are doing slightly different things: generic MSI: disable MSI -> allocate MSI -> enable MSI -> setup EP PCI MSI: disable MSI -> allocate MSI -> setup EP -> enable MSI And it turns out that end-points are allowed to latch the content of the MSI configuration registers as soon as MSIs are enabled. In Bharat's case, the end-point ends up using whatever was there already, which is not what you want. In order to make things converge, we introduce a new MSI domain flag (MSI_FLAG_ACTIVATE_EARLY) that is unconditionally set for PCI/MSI. When set, this flag forces the programming of the end-point as soon as the MSIs are allocated. A consequence of this is that we have an extra activate in irq_startup, but that should be without much consequence. tglx: - Several people reported a VMWare regression with PCI/MSI-X passthrough. It turns out that the patch also cures that issue. - We need to have a look at the MSI disable interrupt path, where we write the msg to all zeros without disabling MSI in the PCI device. Is that correct? Fixes: 52f518a3a7c2 "x86/MSI: Use hierarchical irqdomains to manage MSI interrupts" Reported-and-tested-by: Bharat Kumar Gogada <bharat.kumar.gogada@xilinx.com> Reported-and-tested-by: Foster Snowhill <forst@forstwoof.ru> Reported-by: Matthias Prager <linux@matthiasprager.de> Reported-by: Jason Taylor <jason.taylor@simplivity.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: linux-pci@vger.kernel.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1468426713-31431-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-07-14 00:18:33 +08:00
}
}
return 0;
cleanup:
for_each_msi_entry(desc, dev) {
struct irq_data *irqd;
if (desc->irq == virq)
break;
irqd = irq_domain_get_irq_data(domain, desc->irq);
if (irqd_is_activated(irqd))
irq_domain_deactivate_irq(irqd);
}
msi_domain_free_irqs(domain, dev);
return ret;
}
/**
* msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
* @domain: The domain to allocate from
* @dev: Pointer to device struct of the device for which the interrupts
* are allocated
* @nvec: The number of interrupts to allocate
*
* Returns 0 on success or an error code.
*/
int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
int nvec)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
return ops->domain_alloc_irqs(domain, dev, nvec);
}
void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
{
struct msi_desc *desc;
for_each_msi_entry(desc, dev) {
genirq: MSI: Fix freeing of unallocated MSI While debugging an unrelated issue with the GICv3 ITS driver, the following trace triggered: WARNING: CPU: 1 PID: 1 at kernel/irq/irqdomain.c:1121 irq_domain_free_irqs+0x160/0x17c() NULL pointer, cannot free irq Modules linked in: CPU: 1 PID: 1 Comm: swapper/0 Tainted: G W 3.19.0-rc6+ #3690 Hardware name: FVP Base (DT) Call trace: [<ffffffc000089398>] dump_backtrace+0x0/0x13c [<ffffffc0000894e4>] show_stack+0x10/0x1c [<ffffffc00066d134>] dump_stack+0x74/0x94 [<ffffffc0000a92f8>] warn_slowpath_common+0x9c/0xd4 [<ffffffc0000a938c>] warn_slowpath_fmt+0x5c/0x80 [<ffffffc0000ee04c>] irq_domain_free_irqs+0x15c/0x17c [<ffffffc0000ef918>] msi_domain_free_irqs+0x58/0x74 [<ffffffc000386f58>] free_msi_irqs+0xb4/0x1c0 // The msi_prepare callback fails here [<ffffffc0003872c0>] pci_enable_msix+0x25c/0x3d4 [<ffffffc00038746c>] pci_enable_msix_range+0x34/0x80 [<ffffffc0003924ac>] vp_try_to_find_vqs+0xec/0x528 [<ffffffc000392954>] vp_find_vqs+0x6c/0xa8 [<ffffffc0003ee2a8>] init_vq+0x120/0x248 [<ffffffc0003eefb0>] virtblk_probe+0xb0/0x6bc [<ffffffc00038fc34>] virtio_dev_probe+0x17c/0x214 [<ffffffc0003d4a04>] driver_probe_device+0x7c/0x23c [<ffffffc0003d4cb0>] __driver_attach+0x98/0xa0 [<ffffffc0003d2c60>] bus_for_each_dev+0x60/0xb4 [<ffffffc0003d455c>] driver_attach+0x1c/0x28 [<ffffffc0003d41b0>] bus_add_driver+0x150/0x208 [<ffffffc0003d54c0>] driver_register+0x64/0x130 [<ffffffc00038f9e8>] register_virtio_driver+0x24/0x68 [<ffffffc00091320c>] init+0x70/0xac [<ffffffc0000828f0>] do_one_initcall+0x94/0x1d0 [<ffffffc0008e9b00>] kernel_init_freeable+0x144/0x1e4 [<ffffffc00066a434>] kernel_init+0xc/0xd8 ---[ end trace f9ee562a77cc7bae ]--- The ITS msi_prepare callback having failed, we end-up trying to free MSIs that have never been allocated. Oddly enough, the kernel is pretty upset about it. It turns out that this behaviour was expected before the MSI domain was introduced (and dealt with in arch_teardown_msi_irqs). The obvious fix is to detect this early enough and bail out. Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Reviewed-by: Jiang Liu <jiang.liu@linux.intel.com> Link: http://lkml.kernel.org/r/1422299419-6051-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-01-27 03:10:19 +08:00
/*
* We might have failed to allocate an MSI early
* enough that there is no IRQ associated to this
* entry. If that's the case, don't do anything.
*/
if (desc->irq) {
irq_domain_free_irqs(desc->irq, desc->nvec_used);
desc->irq = 0;
}
}
}
/**
* __msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev
* @domain: The domain to managing the interrupts
* @dev: Pointer to device struct of the device for which the interrupts
* are free
*/
void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
return ops->domain_free_irqs(domain, dev);
}
/**
* msi_get_domain_info - Get the MSI interrupt domain info for @domain
* @domain: The interrupt domain to retrieve data from
*
* Returns the pointer to the msi_domain_info stored in
* @domain->host_data.
*/
struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain)
{
return (struct msi_domain_info *)domain->host_data;
}
#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */