The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 7d5ec3d3612396dc6d4b76366d20ab9fc06f399f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:41 +0200
Subject: [PATCH] PCI/MSI: Mask all unused MSI-X entries
When MSI-X is enabled the ordering of calls is:
msix_map_region();
msix_setup_entries();
pci_msi_setup_msi_irqs();
msix_program_entries();
This has a few interesting issues:
1) msix_setup_entries() allocates the MSI descriptors and initializes them
except for the msi_desc:masked member which is left zero initialized.
2) pci_msi_setup_msi_irqs() allocates the interrupt descriptors and sets
up the MSI interrupts which ends up in pci_write_msi_msg() unless the
interrupt chip provides its own irq_write_msi_msg() function.
3) msix_program_entries() does not do what the name suggests. It solely
updates the entries array (if not NULL) and initializes the masked
member for each MSI descriptor by reading the hardware state and then
masks the entry.
Obviously this has some issues:
1) The uninitialized masked member of msi_desc prevents the enforcement
of masking the entry in pci_write_msi_msg() depending on the cached
masked bit. Aside of that half initialized data is a NONO in general
2) msix_program_entries() only ensures that the actually allocated entries
are masked. This is wrong as experimentation with crash testing and
crash kernel kexec has shown.
This limited testing unearthed that when the production kernel had more
entries in use and unmasked when it crashed and the crash kernel
allocated a smaller amount of entries, then a full scan of all entries
found unmasked entries which were in use in the production kernel.
This is obviously a device or emulation issue as the device reset
should mask all MSI-X table entries, but obviously that's just part
of the paper specification.
Cure this by:
1) Masking all table entries in hardware
2) Initializing msi_desc::masked in msix_setup_entries()
3) Removing the mask dance in msix_program_entries()
4) Renaming msix_program_entries() to msix_update_entries() to
reflect the purpose of that function.
As the masking of unused entries has never been done the Fixes tag refers
to a commit in:
git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.403833459@linutronix.de
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5d39ed828085..57c9ec9b976b 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -691,6 +691,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
{
struct irq_affinity_desc *curmsk, *masks = NULL;
struct msi_desc *entry;
+ void __iomem *addr;
int ret, i;
int vec_count = pci_msix_vec_count(dev);
@@ -711,6 +712,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
entry->msi_attrib.is_msix = 1;
entry->msi_attrib.is_64 = 1;
+
if (entries)
entry->msi_attrib.entry_nr = entries[i].entry;
else
@@ -722,6 +724,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
entry->msi_attrib.default_irq = dev->irq;
entry->mask_base = base;
+ addr = pci_msix_desc_addr(entry);
+ if (addr)
+ entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
if (masks)
curmsk++;
@@ -732,26 +738,25 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
return ret;
}
-static void msix_program_entries(struct pci_dev *dev,
- struct msix_entry *entries)
+static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
{
struct msi_desc *entry;
- int i = 0;
- void __iomem *desc_addr;
for_each_pci_msi_entry(entry, dev) {
- if (entries)
- entries[i++].vector = entry->irq;
+ if (entries) {
+ entries->vector = entry->irq;
+ entries++;
+ }
+ }
+}
- desc_addr = pci_msix_desc_addr(entry);
- if (desc_addr)
- entry->masked = readl(desc_addr +
- PCI_MSIX_ENTRY_VECTOR_CTRL);
- else
- entry->masked = 0;
+static void msix_mask_all(void __iomem *base, int tsize)
+{
+ u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
+ int i;
- msix_mask_irq(entry, 1);
- }
+ for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
+ writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
}
/**
@@ -768,9 +773,9 @@ static void msix_program_entries(struct pci_dev *dev,
static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
int nvec, struct irq_affinity *affd)
{
- int ret;
- u16 control;
void __iomem *base;
+ int ret, tsize;
+ u16 control;
/*
* Some devices require MSI-X to be enabled before the MSI-X
@@ -782,12 +787,16 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
/* Request & Map MSI-X table region */
- base = msix_map_region(dev, msix_table_size(control));
+ tsize = msix_table_size(control);
+ base = msix_map_region(dev, tsize);
if (!base) {
ret = -ENOMEM;
goto out_disable;
}
+ /* Ensure that all table entries are masked. */
+ msix_mask_all(base, tsize);
+
ret = msix_setup_entries(dev, base, entries, nvec, affd);
if (ret)
goto out_disable;
@@ -801,7 +810,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
if (ret)
goto out_free;
- msix_program_entries(dev, entries);
+ msix_update_entries(dev, entries);
ret = populate_msi_sysfs(dev);
if (ret)
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 7d5ec3d3612396dc6d4b76366d20ab9fc06f399f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:41 +0200
Subject: [PATCH] PCI/MSI: Mask all unused MSI-X entries
When MSI-X is enabled the ordering of calls is:
msix_map_region();
msix_setup_entries();
pci_msi_setup_msi_irqs();
msix_program_entries();
This has a few interesting issues:
1) msix_setup_entries() allocates the MSI descriptors and initializes them
except for the msi_desc:masked member which is left zero initialized.
2) pci_msi_setup_msi_irqs() allocates the interrupt descriptors and sets
up the MSI interrupts which ends up in pci_write_msi_msg() unless the
interrupt chip provides its own irq_write_msi_msg() function.
3) msix_program_entries() does not do what the name suggests. It solely
updates the entries array (if not NULL) and initializes the masked
member for each MSI descriptor by reading the hardware state and then
masks the entry.
Obviously this has some issues:
1) The uninitialized masked member of msi_desc prevents the enforcement
of masking the entry in pci_write_msi_msg() depending on the cached
masked bit. Aside of that half initialized data is a NONO in general
2) msix_program_entries() only ensures that the actually allocated entries
are masked. This is wrong as experimentation with crash testing and
crash kernel kexec has shown.
This limited testing unearthed that when the production kernel had more
entries in use and unmasked when it crashed and the crash kernel
allocated a smaller amount of entries, then a full scan of all entries
found unmasked entries which were in use in the production kernel.
This is obviously a device or emulation issue as the device reset
should mask all MSI-X table entries, but obviously that's just part
of the paper specification.
Cure this by:
1) Masking all table entries in hardware
2) Initializing msi_desc::masked in msix_setup_entries()
3) Removing the mask dance in msix_program_entries()
4) Renaming msix_program_entries() to msix_update_entries() to
reflect the purpose of that function.
As the masking of unused entries has never been done the Fixes tag refers
to a commit in:
git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.403833459@linutronix.de
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5d39ed828085..57c9ec9b976b 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -691,6 +691,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
{
struct irq_affinity_desc *curmsk, *masks = NULL;
struct msi_desc *entry;
+ void __iomem *addr;
int ret, i;
int vec_count = pci_msix_vec_count(dev);
@@ -711,6 +712,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
entry->msi_attrib.is_msix = 1;
entry->msi_attrib.is_64 = 1;
+
if (entries)
entry->msi_attrib.entry_nr = entries[i].entry;
else
@@ -722,6 +724,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
entry->msi_attrib.default_irq = dev->irq;
entry->mask_base = base;
+ addr = pci_msix_desc_addr(entry);
+ if (addr)
+ entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
if (masks)
curmsk++;
@@ -732,26 +738,25 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
return ret;
}
-static void msix_program_entries(struct pci_dev *dev,
- struct msix_entry *entries)
+static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
{
struct msi_desc *entry;
- int i = 0;
- void __iomem *desc_addr;
for_each_pci_msi_entry(entry, dev) {
- if (entries)
- entries[i++].vector = entry->irq;
+ if (entries) {
+ entries->vector = entry->irq;
+ entries++;
+ }
+ }
+}
- desc_addr = pci_msix_desc_addr(entry);
- if (desc_addr)
- entry->masked = readl(desc_addr +
- PCI_MSIX_ENTRY_VECTOR_CTRL);
- else
- entry->masked = 0;
+static void msix_mask_all(void __iomem *base, int tsize)
+{
+ u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
+ int i;
- msix_mask_irq(entry, 1);
- }
+ for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
+ writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
}
/**
@@ -768,9 +773,9 @@ static void msix_program_entries(struct pci_dev *dev,
static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
int nvec, struct irq_affinity *affd)
{
- int ret;
- u16 control;
void __iomem *base;
+ int ret, tsize;
+ u16 control;
/*
* Some devices require MSI-X to be enabled before the MSI-X
@@ -782,12 +787,16 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
/* Request & Map MSI-X table region */
- base = msix_map_region(dev, msix_table_size(control));
+ tsize = msix_table_size(control);
+ base = msix_map_region(dev, tsize);
if (!base) {
ret = -ENOMEM;
goto out_disable;
}
+ /* Ensure that all table entries are masked. */
+ msix_mask_all(base, tsize);
+
ret = msix_setup_entries(dev, base, entries, nvec, affd);
if (ret)
goto out_disable;
@@ -801,7 +810,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
if (ret)
goto out_free;
- msix_program_entries(dev, entries);
+ msix_update_entries(dev, entries);
ret = populate_msi_sysfs(dev);
if (ret)
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 7d5ec3d3612396dc6d4b76366d20ab9fc06f399f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:41 +0200
Subject: [PATCH] PCI/MSI: Mask all unused MSI-X entries
When MSI-X is enabled the ordering of calls is:
msix_map_region();
msix_setup_entries();
pci_msi_setup_msi_irqs();
msix_program_entries();
This has a few interesting issues:
1) msix_setup_entries() allocates the MSI descriptors and initializes them
except for the msi_desc:masked member which is left zero initialized.
2) pci_msi_setup_msi_irqs() allocates the interrupt descriptors and sets
up the MSI interrupts which ends up in pci_write_msi_msg() unless the
interrupt chip provides its own irq_write_msi_msg() function.
3) msix_program_entries() does not do what the name suggests. It solely
updates the entries array (if not NULL) and initializes the masked
member for each MSI descriptor by reading the hardware state and then
masks the entry.
Obviously this has some issues:
1) The uninitialized masked member of msi_desc prevents the enforcement
of masking the entry in pci_write_msi_msg() depending on the cached
masked bit. Aside of that half initialized data is a NONO in general
2) msix_program_entries() only ensures that the actually allocated entries
are masked. This is wrong as experimentation with crash testing and
crash kernel kexec has shown.
This limited testing unearthed that when the production kernel had more
entries in use and unmasked when it crashed and the crash kernel
allocated a smaller amount of entries, then a full scan of all entries
found unmasked entries which were in use in the production kernel.
This is obviously a device or emulation issue as the device reset
should mask all MSI-X table entries, but obviously that's just part
of the paper specification.
Cure this by:
1) Masking all table entries in hardware
2) Initializing msi_desc::masked in msix_setup_entries()
3) Removing the mask dance in msix_program_entries()
4) Renaming msix_program_entries() to msix_update_entries() to
reflect the purpose of that function.
As the masking of unused entries has never been done the Fixes tag refers
to a commit in:
git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Fixes: f036d4ea5fa7 ("[PATCH] ia32 Message Signalled Interrupt support")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas(a)google.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.403833459@linutronix.de
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5d39ed828085..57c9ec9b976b 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -691,6 +691,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
{
struct irq_affinity_desc *curmsk, *masks = NULL;
struct msi_desc *entry;
+ void __iomem *addr;
int ret, i;
int vec_count = pci_msix_vec_count(dev);
@@ -711,6 +712,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
entry->msi_attrib.is_msix = 1;
entry->msi_attrib.is_64 = 1;
+
if (entries)
entry->msi_attrib.entry_nr = entries[i].entry;
else
@@ -722,6 +724,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
entry->msi_attrib.default_irq = dev->irq;
entry->mask_base = base;
+ addr = pci_msix_desc_addr(entry);
+ if (addr)
+ entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
if (masks)
curmsk++;
@@ -732,26 +738,25 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
return ret;
}
-static void msix_program_entries(struct pci_dev *dev,
- struct msix_entry *entries)
+static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
{
struct msi_desc *entry;
- int i = 0;
- void __iomem *desc_addr;
for_each_pci_msi_entry(entry, dev) {
- if (entries)
- entries[i++].vector = entry->irq;
+ if (entries) {
+ entries->vector = entry->irq;
+ entries++;
+ }
+ }
+}
- desc_addr = pci_msix_desc_addr(entry);
- if (desc_addr)
- entry->masked = readl(desc_addr +
- PCI_MSIX_ENTRY_VECTOR_CTRL);
- else
- entry->masked = 0;
+static void msix_mask_all(void __iomem *base, int tsize)
+{
+ u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
+ int i;
- msix_mask_irq(entry, 1);
- }
+ for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
+ writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
}
/**
@@ -768,9 +773,9 @@ static void msix_program_entries(struct pci_dev *dev,
static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
int nvec, struct irq_affinity *affd)
{
- int ret;
- u16 control;
void __iomem *base;
+ int ret, tsize;
+ u16 control;
/*
* Some devices require MSI-X to be enabled before the MSI-X
@@ -782,12 +787,16 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
/* Request & Map MSI-X table region */
- base = msix_map_region(dev, msix_table_size(control));
+ tsize = msix_table_size(control);
+ base = msix_map_region(dev, tsize);
if (!base) {
ret = -ENOMEM;
goto out_disable;
}
+ /* Ensure that all table entries are masked. */
+ msix_mask_all(base, tsize);
+
ret = msix_setup_entries(dev, base, entries, nvec, affd);
if (ret)
goto out_disable;
@@ -801,7 +810,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
if (ret)
goto out_free;
- msix_program_entries(dev, entries);
+ msix_update_entries(dev, entries);
ret = populate_msi_sysfs(dev);
if (ret)
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From dbbc93576e03fbe24b365fab0e901eb442237a8a Mon Sep 17 00:00:00 2001
From: Bixuan Cui <cuibixuan(a)huawei.com>
Date: Tue, 18 May 2021 11:31:17 +0800
Subject: [PATCH] genirq/msi: Ensure deactivation on teardown
msi_domain_alloc_irqs() invokes irq_domain_activate_irq(), but
msi_domain_free_irqs() does not enforce deactivation before tearing down
the interrupts.
This happens when PCI/MSI interrupts are set up and never used before being
torn down again, e.g. in error handling pathes. The only place which cleans
that up is the error handling path in msi_domain_alloc_irqs().
Move the cleanup from msi_domain_alloc_irqs() into msi_domain_free_irqs()
to cure that.
Fixes: f3b0946d629c ("genirq/msi: Make sure PCI MSIs are activated early")
Signed-off-by: Bixuan Cui <cuibixuan(a)huawei.com>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210518033117.78104-1-cuibixuan@huawei.com
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index c41965e348b5..85df3ca03efe 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -476,11 +476,6 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
return 0;
cleanup:
- for_each_msi_vector(desc, i, dev) {
- irq_data = irq_domain_get_irq_data(domain, i);
- if (irqd_is_activated(irq_data))
- irq_domain_deactivate_irq(irq_data);
- }
msi_domain_free_irqs(domain, dev);
return ret;
}
@@ -505,7 +500,15 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
{
+ struct irq_data *irq_data;
struct msi_desc *desc;
+ int i;
+
+ for_each_msi_vector(desc, i, dev) {
+ irq_data = irq_domain_get_irq_data(domain, i);
+ if (irqd_is_activated(irq_data))
+ irq_domain_deactivate_irq(irq_data);
+ }
for_each_msi_entry(desc, dev) {
/*
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From dbbc93576e03fbe24b365fab0e901eb442237a8a Mon Sep 17 00:00:00 2001
From: Bixuan Cui <cuibixuan(a)huawei.com>
Date: Tue, 18 May 2021 11:31:17 +0800
Subject: [PATCH] genirq/msi: Ensure deactivation on teardown
msi_domain_alloc_irqs() invokes irq_domain_activate_irq(), but
msi_domain_free_irqs() does not enforce deactivation before tearing down
the interrupts.
This happens when PCI/MSI interrupts are set up and never used before being
torn down again, e.g. in error handling pathes. The only place which cleans
that up is the error handling path in msi_domain_alloc_irqs().
Move the cleanup from msi_domain_alloc_irqs() into msi_domain_free_irqs()
to cure that.
Fixes: f3b0946d629c ("genirq/msi: Make sure PCI MSIs are activated early")
Signed-off-by: Bixuan Cui <cuibixuan(a)huawei.com>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210518033117.78104-1-cuibixuan@huawei.com
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index c41965e348b5..85df3ca03efe 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -476,11 +476,6 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
return 0;
cleanup:
- for_each_msi_vector(desc, i, dev) {
- irq_data = irq_domain_get_irq_data(domain, i);
- if (irqd_is_activated(irq_data))
- irq_domain_deactivate_irq(irq_data);
- }
msi_domain_free_irqs(domain, dev);
return ret;
}
@@ -505,7 +500,15 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
{
+ struct irq_data *irq_data;
struct msi_desc *desc;
+ int i;
+
+ for_each_msi_vector(desc, i, dev) {
+ irq_data = irq_domain_get_irq_data(domain, i);
+ if (irqd_is_activated(irq_data))
+ irq_domain_deactivate_irq(irq_data);
+ }
for_each_msi_entry(desc, dev) {
/*
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 826da771291fc25a428e871f9e7fb465e390f852 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:48 +0200
Subject: [PATCH] genirq: Provide IRQCHIP_AFFINITY_PRE_STARTUP
X86 IO/APIC and MSI interrupts (when used without interrupts remapping)
require that the affinity setup on startup is done before the interrupt is
enabled for the first time as the non-remapped operation mode cannot safely
migrate enabled interrupts from arbitrary contexts. Provide a new irq chip
flag which allows affected hardware to request this.
This has to be opt-in because there have been reports in the past that some
interrupt chips cannot handle affinity setting before startup.
Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.779791738@linutronix.de
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8e9a9ae471a6..c8293c817646 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -569,6 +569,7 @@ struct irq_chip {
* IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips
* IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs
* in the suspend path if they are in disabled state
+ * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup
*/
enum {
IRQCHIP_SET_TYPE_MASKED = (1 << 0),
@@ -581,6 +582,7 @@ enum {
IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7),
IRQCHIP_SUPPORTS_NMI = (1 << 8),
IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9),
+ IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10),
};
#include <linux/irqdesc.h>
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 7f04c7d8296e..a98bcfc4be7b 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -265,8 +265,11 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
} else {
switch (__irq_startup_managed(desc, aff, force)) {
case IRQ_STARTUP_NORMAL:
+ if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)
+ irq_setup_affinity(desc);
ret = __irq_startup(desc);
- irq_setup_affinity(desc);
+ if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP))
+ irq_setup_affinity(desc);
break;
case IRQ_STARTUP_MANAGED:
irq_do_set_affinity(d, aff, false);
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 826da771291fc25a428e871f9e7fb465e390f852 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:48 +0200
Subject: [PATCH] genirq: Provide IRQCHIP_AFFINITY_PRE_STARTUP
X86 IO/APIC and MSI interrupts (when used without interrupts remapping)
require that the affinity setup on startup is done before the interrupt is
enabled for the first time as the non-remapped operation mode cannot safely
migrate enabled interrupts from arbitrary contexts. Provide a new irq chip
flag which allows affected hardware to request this.
This has to be opt-in because there have been reports in the past that some
interrupt chips cannot handle affinity setting before startup.
Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.779791738@linutronix.de
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8e9a9ae471a6..c8293c817646 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -569,6 +569,7 @@ struct irq_chip {
* IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips
* IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs
* in the suspend path if they are in disabled state
+ * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup
*/
enum {
IRQCHIP_SET_TYPE_MASKED = (1 << 0),
@@ -581,6 +582,7 @@ enum {
IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7),
IRQCHIP_SUPPORTS_NMI = (1 << 8),
IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9),
+ IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10),
};
#include <linux/irqdesc.h>
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 7f04c7d8296e..a98bcfc4be7b 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -265,8 +265,11 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
} else {
switch (__irq_startup_managed(desc, aff, force)) {
case IRQ_STARTUP_NORMAL:
+ if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)
+ irq_setup_affinity(desc);
ret = __irq_startup(desc);
- irq_setup_affinity(desc);
+ if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP))
+ irq_setup_affinity(desc);
break;
case IRQ_STARTUP_MANAGED:
irq_do_set_affinity(d, aff, false);
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 0c0e37dc11671384e53ba6ede53a4d91162a2cc5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:49 +0200
Subject: [PATCH] x86/ioapic: Force affinity setup before startup
The IO/APIC cannot handle interrupt affinity changes safely after startup
other than from an interrupt handler. The startup sequence in the generic
interrupt code violates that assumption.
Mark the irq chip with the new IRQCHIP_AFFINITY_PRE_STARTUP flag so that
the default interrupt setting happens before the interrupt is started up
for the first time.
Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.832143400@linutronix.de
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d5c691a3208b..39224e035e47 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static struct irq_chip ioapic_ir_chip __read_mostly = {
@@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static inline void init_IO_APIC_traps(void)
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 0c0e37dc11671384e53ba6ede53a4d91162a2cc5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:49 +0200
Subject: [PATCH] x86/ioapic: Force affinity setup before startup
The IO/APIC cannot handle interrupt affinity changes safely after startup
other than from an interrupt handler. The startup sequence in the generic
interrupt code violates that assumption.
Mark the irq chip with the new IRQCHIP_AFFINITY_PRE_STARTUP flag so that
the default interrupt setting happens before the interrupt is started up
for the first time.
Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.832143400@linutronix.de
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d5c691a3208b..39224e035e47 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static struct irq_chip ioapic_ir_chip __read_mostly = {
@@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static inline void init_IO_APIC_traps(void)
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 0c0e37dc11671384e53ba6ede53a4d91162a2cc5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Thu, 29 Jul 2021 23:51:49 +0200
Subject: [PATCH] x86/ioapic: Force affinity setup before startup
The IO/APIC cannot handle interrupt affinity changes safely after startup
other than from an interrupt handler. The startup sequence in the generic
interrupt code violates that assumption.
Mark the irq chip with the new IRQCHIP_AFFINITY_PRE_STARTUP flag so that
the default interrupt setting happens before the interrupt is started up
for the first time.
Fixes: 18404756765c ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Tested-by: Marc Zyngier <maz(a)kernel.org>
Reviewed-by: Marc Zyngier <maz(a)kernel.org>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.832143400@linutronix.de
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d5c691a3208b..39224e035e47 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static struct irq_chip ioapic_ir_chip __read_mostly = {
@@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static inline void init_IO_APIC_traps(void)