OpenCloudOS-Kernel/drivers/pci/msi.c

1565 lines
39 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* PCI Message Signaled Interrupt (MSI)
*
* Copyright (C) 2003-2004 Intel
* Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
* Copyright (C) 2016 Christoph Hellwig.
*/
#include <linux/err.h>
#include <linux/mm.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/ioport.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/msi.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/io.h>
#include <linux/acpi_iort.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/irqdomain.h>
#include <linux/of_irq.h>
#include "pci.h"
static int pci_msi_enable = 1;
int pci_msi_ignore_mask;
#define msix_table_size(flags) ((flags & PCI_MSIX_FLAGS_QSIZE) + 1)
#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
struct irq_domain *domain;
domain = dev_get_msi_domain(&dev->dev);
if (domain && irq_domain_is_hierarchy(domain))
return msi_domain_alloc_irqs(domain, &dev->dev, nvec);
return arch_setup_msi_irqs(dev, nvec, type);
}
static void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
{
struct irq_domain *domain;
domain = dev_get_msi_domain(&dev->dev);
if (domain && irq_domain_is_hierarchy(domain))
msi_domain_free_irqs(domain, &dev->dev);
else
arch_teardown_msi_irqs(dev);
}
#else
#define pci_msi_setup_msi_irqs arch_setup_msi_irqs
#define pci_msi_teardown_msi_irqs arch_teardown_msi_irqs
#endif
/* Arch hooks */
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
{
struct msi_controller *chip = dev->bus->msi;
int err;
if (!chip || !chip->setup_irq)
return -EINVAL;
err = chip->setup_irq(chip, dev, desc);
if (err < 0)
return err;
irq_set_chip_data(desc->irq, chip);
return 0;
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
}
void __weak arch_teardown_msi_irq(unsigned int irq)
{
struct msi_controller *chip = irq_get_chip_data(irq);
if (!chip || !chip->teardown_irq)
return;
chip->teardown_irq(chip, irq);
}
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
struct msi_controller *chip = dev->bus->msi;
struct msi_desc *entry;
int ret;
if (chip && chip->setup_irqs)
return chip->setup_irqs(chip, dev, nvec, type);
/*
* If an architecture wants to support multiple MSI, it needs to
* override arch_setup_msi_irqs()
*/
if (type == PCI_CAP_ID_MSI && nvec > 1)
return 1;
for_each_pci_msi_entry(entry, dev) {
ret = arch_setup_msi_irq(dev, entry);
if (ret < 0)
return ret;
if (ret > 0)
return -ENOSPC;
}
return 0;
}
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
/*
* We have a default implementation available as a separate non-weak
* function, as it is used by the Xen x86 PCI code
*/
void default_teardown_msi_irqs(struct pci_dev *dev)
{
int i;
struct msi_desc *entry;
for_each_pci_msi_entry(entry, dev)
if (entry->irq)
for (i = 0; i < entry->nvec_used; i++)
arch_teardown_msi_irq(entry->irq + i);
}
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
void __weak arch_teardown_msi_irqs(struct pci_dev *dev)
{
return default_teardown_msi_irqs(dev);
}
static void default_restore_msi_irq(struct pci_dev *dev, int irq)
{
struct msi_desc *entry;
entry = NULL;
if (dev->msix_enabled) {
for_each_pci_msi_entry(entry, dev) {
if (irq == entry->irq)
break;
}
} else if (dev->msi_enabled) {
entry = irq_get_msi_desc(irq);
}
if (entry)
__pci_write_msi_msg(entry, &entry->msg);
}
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
void __weak arch_restore_msi_irqs(struct pci_dev *dev)
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
{
return default_restore_msi_irqs(dev);
PCI: use weak functions for MSI arch-specific functions Until now, the MSI architecture-specific functions could be overloaded using a fairly complex set of #define and compile-time conditionals. In order to prepare for the introduction of the msi_chip infrastructure, it is desirable to switch all those functions to use the 'weak' mechanism. This commit converts all the architectures that were overidding those MSI functions to use the new strategy. Note that we keep two separate, non-weak, functions default_teardown_msi_irqs() and default_restore_msi_irqs() for the default behavior of the arch_teardown_msi_irqs() and arch_restore_msi_irqs(), as the default behavior is needed by x86 PCI code. Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Tested-by: Daniel Price <daniel.price@gmail.com> Tested-by: Thierry Reding <thierry.reding@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: x86@kernel.org Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64@vger.kernel.org Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: David S. Miller <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Cc: Chris Metcalf <cmetcalf@tilera.com> Signed-off-by: Jason Cooper <jason@lakedaemon.net>
2013-08-10 04:27:06 +08:00
}
static inline __attribute_const__ u32 msi_mask(unsigned x)
{
/* Don't shift by >= width of type */
if (x >= 5)
return 0xffffffff;
return (1 << (1 << x)) - 1;
}
/*
* PCI 2.3 does not specify mask bits for each MSI interrupt. Attempting to
* mask all MSI interrupts by clearing the MSI enable bit does not work
* reliably as devices without an INTx disable bit will then generate a
* level IRQ which will never be cleared.
*/
u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
{
u32 mask_bits = desc->masked;
if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit)
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
return 0;
mask_bits &= ~mask;
mask_bits |= flag;
pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos,
mask_bits);
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
return mask_bits;
}
static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
{
desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag);
}
static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
{
if (desc->msi_attrib.is_virtual)
return NULL;
return desc->mask_base +
desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
}
/*
* This internal function does not flush PCI writes to the device.
* All users must ensure that they read from the device before either
* assuming that the device state is up to date, or returning out of this
* file. This saves a few milliseconds when initialising devices with lots
* of MSI-X interrupts.
*/
u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
{
u32 mask_bits = desc->masked;
void __iomem *desc_addr;
if (pci_msi_ignore_mask)
return 0;
PCI/MSI: Fix incorrect MSI-X masking on resume When a driver enables MSI-X, msix_program_entries() reads the MSI-X Vector Control register for each vector and saves it in desc->masked. Each register is 32 bits and bit 0 is the actual Mask bit. When we restored these registers during resume, we previously set the Mask bit if *any* bit in desc->masked was set instead of when the Mask bit itself was set: pci_restore_state pci_restore_msi_state __pci_restore_msix_state for_each_pci_msi_entry msix_mask_irq(entry, entry->masked) <-- entire u32 word __pci_msix_desc_mask_irq(desc, flag) mask_bits = desc->masked & ~PCI_MSIX_ENTRY_CTRL_MASKBIT if (flag) <-- testing entire u32, not just bit 0 mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL) This means that after resume, MSI-X vectors were masked when they shouldn't be, which leads to timeouts like this: nvme nvme0: I/O 978 QID 3 timeout, completion polled On resume, set the Mask bit only when the saved Mask bit from suspend was set. This should remove the need for 19ea025e1d28 ("nvme: Add quirk for Kingston NVME SSD running FW E8FK11.T"). [bhelgaas: commit log, move fix to __pci_msix_desc_mask_irq()] Link: https://bugzilla.kernel.org/show_bug.cgi?id=204887 Link: https://lore.kernel.org/r/20191008034238.2503-1-jian-hong@endlessm.com Fixes: f2440d9acbe8 ("PCI MSI: Refactor interrupt masking code") Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Cc: stable@vger.kernel.org
2019-10-08 11:42:39 +08:00
desc_addr = pci_msix_desc_addr(desc);
if (!desc_addr)
return 0;
mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
PCI/MSI: Fix incorrect MSI-X masking on resume When a driver enables MSI-X, msix_program_entries() reads the MSI-X Vector Control register for each vector and saves it in desc->masked. Each register is 32 bits and bit 0 is the actual Mask bit. When we restored these registers during resume, we previously set the Mask bit if *any* bit in desc->masked was set instead of when the Mask bit itself was set: pci_restore_state pci_restore_msi_state __pci_restore_msix_state for_each_pci_msi_entry msix_mask_irq(entry, entry->masked) <-- entire u32 word __pci_msix_desc_mask_irq(desc, flag) mask_bits = desc->masked & ~PCI_MSIX_ENTRY_CTRL_MASKBIT if (flag) <-- testing entire u32, not just bit 0 mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL) This means that after resume, MSI-X vectors were masked when they shouldn't be, which leads to timeouts like this: nvme nvme0: I/O 978 QID 3 timeout, completion polled On resume, set the Mask bit only when the saved Mask bit from suspend was set. This should remove the need for 19ea025e1d28 ("nvme: Add quirk for Kingston NVME SSD running FW E8FK11.T"). [bhelgaas: commit log, move fix to __pci_msix_desc_mask_irq()] Link: https://bugzilla.kernel.org/show_bug.cgi?id=204887 Link: https://lore.kernel.org/r/20191008034238.2503-1-jian-hong@endlessm.com Fixes: f2440d9acbe8 ("PCI MSI: Refactor interrupt masking code") Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Cc: stable@vger.kernel.org
2019-10-08 11:42:39 +08:00
if (flag & PCI_MSIX_ENTRY_CTRL_MASKBIT)
mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
return mask_bits;
}
static void msix_mask_irq(struct msi_desc *desc, u32 flag)
{
desc->masked = __pci_msix_desc_mask_irq(desc, flag);
}
static void msi_set_mask_bit(struct irq_data *data, u32 flag)
{
struct msi_desc *desc = irq_data_get_msi_desc(data);
if (desc->msi_attrib.is_msix) {
msix_mask_irq(desc, flag);
readl(desc->mask_base); /* Flush write to device */
} else {
unsigned offset = data->irq - desc->irq;
msi_mask_irq(desc, 1 << offset, flag << offset);
}
}
/**
* pci_msi_mask_irq - Generic IRQ chip callback to mask PCI/MSI interrupts
* @data: pointer to irqdata associated to that interrupt
*/
void pci_msi_mask_irq(struct irq_data *data)
{
msi_set_mask_bit(data, 1);
}
EXPORT_SYMBOL_GPL(pci_msi_mask_irq);
/**
* pci_msi_unmask_irq - Generic IRQ chip callback to unmask PCI/MSI interrupts
* @data: pointer to irqdata associated to that interrupt
*/
void pci_msi_unmask_irq(struct irq_data *data)
{
msi_set_mask_bit(data, 0);
}
EXPORT_SYMBOL_GPL(pci_msi_unmask_irq);
void default_restore_msi_irqs(struct pci_dev *dev)
{
struct msi_desc *entry;
for_each_pci_msi_entry(entry, dev)
default_restore_msi_irq(dev, entry->irq);
}
void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
struct pci_dev *dev = msi_desc_to_pci_dev(entry);
BUG_ON(dev->current_state != PCI_D0);
if (entry->msi_attrib.is_msix) {
void __iomem *base = pci_msix_desc_addr(entry);
if (!base) {
WARN_ON(1);
return;
}
msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
} else {
int pos = dev->msi_cap;
u16 data;
pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO,
&msg->address_lo);
if (entry->msi_attrib.is_64) {
pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI,
&msg->address_hi);
pci_read_config_word(dev, pos + PCI_MSI_DATA_64, &data);
} else {
msg->address_hi = 0;
pci_read_config_word(dev, pos + PCI_MSI_DATA_32, &data);
}
msg->data = data;
}
}
void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
struct pci_dev *dev = msi_desc_to_pci_dev(entry);
if (dev->current_state != PCI_D0 || pci_dev_is_disconnected(dev)) {
/* Don't touch the hardware now */
} else if (entry->msi_attrib.is_msix) {
void __iomem *base = pci_msix_desc_addr(entry);
if (!base)
goto skip;
writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
} else {
int pos = dev->msi_cap;
u16 msgctl;
pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
msgctl &= ~PCI_MSI_FLAGS_QSIZE;
msgctl |= entry->msi_attrib.multiple << 4;
pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl);
pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO,
msg->address_lo);
if (entry->msi_attrib.is_64) {
pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI,
msg->address_hi);
pci_write_config_word(dev, pos + PCI_MSI_DATA_64,
msg->data);
} else {
pci_write_config_word(dev, pos + PCI_MSI_DATA_32,
msg->data);
}
}
skip:
[PATCH] msi: Safer state caching. There are two ways pci_save_state and pci_restore_state are used. As helper functions during suspend/resume, and as helper functions around a hardware reset event. When used as helper functions around a hardware reset event there is no reason to believe the calls will be paired, nor is there a good reason to believe that if we restore the msi state from before the reset that it will match the current msi state. Since arch code may change the msi message without going through the driver, drivers currently do not have enough information to even know when to call pci_save_state to ensure they will have msi state in sync with the other kernel irq reception data structures. It turns out the solution is straight forward, cache the state in the existing msi data structures (not the magic pci saved things) and have the msi code update the cached state each time we write to the hardware. This means we never need to read the hardware to figure out what the hardware state should be. By modifying the caching in this manner we get to remove our save_state routines and only need to provide restore_state routines. The only fields that were at all tricky to regenerate were the msi and msi-x control registers and the way we regenerate them currently is a bit dependent upon assumptions on how we use the allow msi registers to be configured and used making the code a little bit brittle. If we ever change what cases we allow or how we configure the msi bits we can address the fragility then. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: Auke Kok <auke-jan.h.kok@intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-09 04:04:57 +08:00
entry->msg = *msg;
if (entry->write_msi_msg)
entry->write_msi_msg(entry, entry->write_msi_msg_data);
}
void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
{
struct msi_desc *entry = irq_get_msi_desc(irq);
__pci_write_msi_msg(entry, msg);
}
EXPORT_SYMBOL_GPL(pci_write_msi_msg);
static void free_msi_irqs(struct pci_dev *dev)
{
struct list_head *msi_list = dev_to_msi_list(&dev->dev);
struct msi_desc *entry, *tmp;
struct attribute **msi_attrs;
struct device_attribute *dev_attr;
int i, count = 0;
for_each_pci_msi_entry(entry, dev)
if (entry->irq)
for (i = 0; i < entry->nvec_used; i++)
BUG_ON(irq_has_action(entry->irq + i));
pci_msi_teardown_msi_irqs(dev);
list_for_each_entry_safe(entry, tmp, msi_list, list) {
if (entry->msi_attrib.is_msix) {
if (list_is_last(&entry->list, msi_list))
iounmap(entry->mask_base);
}
PCI: msi: fix imbalanced refcount of msi irq sysfs objects This warning was recently reported to me: ------------[ cut here ]------------ WARNING: at lib/kobject.c:595 kobject_put+0x50/0x60() Hardware name: VMware Virtual Platform kobject: '(null)' (ffff880027b0df40): is not initialized, yet kobject_put() is being called. Modules linked in: vmxnet3(+) vmw_balloon i2c_piix4 i2c_core shpchp raid10 vmw_pvscsi Pid: 630, comm: modprobe Tainted: G W 3.1.6-1.fc16.x86_64 #1 Call Trace: [<ffffffff8106b73f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff8106b836>] warn_slowpath_fmt+0x46/0x50 [<ffffffff810da293>] ? free_desc+0x63/0x70 [<ffffffff812a9aa0>] kobject_put+0x50/0x60 [<ffffffff812e4c25>] free_msi_irqs+0xd5/0x120 [<ffffffff812e524c>] pci_enable_msi_block+0x24c/0x2c0 [<ffffffffa017c273>] vmxnet3_alloc_intr_resources+0x173/0x240 [vmxnet3] [<ffffffffa0182e94>] vmxnet3_probe_device+0x615/0x834 [vmxnet3] [<ffffffff812d141c>] local_pci_probe+0x5c/0xd0 [<ffffffff812d2cb9>] pci_device_probe+0x109/0x130 [<ffffffff8138ba2c>] driver_probe_device+0x9c/0x2b0 [<ffffffff8138bceb>] __driver_attach+0xab/0xb0 [<ffffffff8138bc40>] ? driver_probe_device+0x2b0/0x2b0 [<ffffffff8138bc40>] ? driver_probe_device+0x2b0/0x2b0 [<ffffffff8138a8ac>] bus_for_each_dev+0x5c/0x90 [<ffffffff8138b63e>] driver_attach+0x1e/0x20 [<ffffffff8138b240>] bus_add_driver+0x1b0/0x2a0 [<ffffffffa0188000>] ? 0xffffffffa0187fff [<ffffffff8138c246>] driver_register+0x76/0x140 [<ffffffff815ca414>] ? printk+0x51/0x53 [<ffffffffa0188000>] ? 0xffffffffa0187fff [<ffffffff812d2996>] __pci_register_driver+0x56/0xd0 [<ffffffffa018803a>] vmxnet3_init_module+0x3a/0x3c [vmxnet3] [<ffffffff81002042>] do_one_initcall+0x42/0x180 [<ffffffff810aad71>] sys_init_module+0x91/0x200 [<ffffffff815dccc2>] system_call_fastpath+0x16/0x1b ---[ end trace 44593438a59a9558 ]--- Using INTx interrupt, #Rx queues: 1. It occurs when populate_msi_sysfs fails, which in turn causes free_msi_irqs to be called. Because populate_msi_sysfs fails, we never registered any of the msi irq sysfs objects, but free_msi_irqs still calls kobject_del and kobject_put on each of them, which gets flagged in the above stack trace. The fix is pretty straightforward. We can key of the parent pointer in the kobject. It is only set if the kobject_init_and_add succededs in populate_msi_sysfs. If anything fails there, each kobject has its parent reset to NULL Signed-off-by: Neil Horman <nhorman@tuxdriver.com> CC: Bjorn Helgaas <bhelgaas@google.com> CC: Greg Kroah-Hartman <gregkh@suse.de> CC: linux-pci@vger.kernel.org Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2012-01-03 23:29:54 +08:00
list_del(&entry->list);
free_msi_entry(entry);
}
if (dev->msi_irq_groups) {
sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups);
msi_attrs = dev->msi_irq_groups[0]->attrs;
while (msi_attrs[count]) {
dev_attr = container_of(msi_attrs[count],
struct device_attribute, attr);
kfree(dev_attr->attr.name);
kfree(dev_attr);
++count;
}
kfree(msi_attrs);
kfree(dev->msi_irq_groups[0]);
kfree(dev->msi_irq_groups);
dev->msi_irq_groups = NULL;
}
}
static void pci_intx_for_msi(struct pci_dev *dev, int enable)
{
if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
pci_intx(dev, enable);
}
static void __pci_restore_msi_state(struct pci_dev *dev)
{
u16 control;
[PATCH] msi: Safer state caching. There are two ways pci_save_state and pci_restore_state are used. As helper functions during suspend/resume, and as helper functions around a hardware reset event. When used as helper functions around a hardware reset event there is no reason to believe the calls will be paired, nor is there a good reason to believe that if we restore the msi state from before the reset that it will match the current msi state. Since arch code may change the msi message without going through the driver, drivers currently do not have enough information to even know when to call pci_save_state to ensure they will have msi state in sync with the other kernel irq reception data structures. It turns out the solution is straight forward, cache the state in the existing msi data structures (not the magic pci saved things) and have the msi code update the cached state each time we write to the hardware. This means we never need to read the hardware to figure out what the hardware state should be. By modifying the caching in this manner we get to remove our save_state routines and only need to provide restore_state routines. The only fields that were at all tricky to regenerate were the msi and msi-x control registers and the way we regenerate them currently is a bit dependent upon assumptions on how we use the allow msi registers to be configured and used making the code a little bit brittle. If we ever change what cases we allow or how we configure the msi bits we can address the fragility then. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: Auke Kok <auke-jan.h.kok@intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-09 04:04:57 +08:00
struct msi_desc *entry;
if (!dev->msi_enabled)
return;
entry = irq_get_msi_desc(dev->irq);
pci_intx_for_msi(dev, 0);
pci_msi_set_enable(dev, 0);
arch_restore_msi_irqs(dev);
[PATCH] msi: Safer state caching. There are two ways pci_save_state and pci_restore_state are used. As helper functions during suspend/resume, and as helper functions around a hardware reset event. When used as helper functions around a hardware reset event there is no reason to believe the calls will be paired, nor is there a good reason to believe that if we restore the msi state from before the reset that it will match the current msi state. Since arch code may change the msi message without going through the driver, drivers currently do not have enough information to even know when to call pci_save_state to ensure they will have msi state in sync with the other kernel irq reception data structures. It turns out the solution is straight forward, cache the state in the existing msi data structures (not the magic pci saved things) and have the msi code update the cached state each time we write to the hardware. This means we never need to read the hardware to figure out what the hardware state should be. By modifying the caching in this manner we get to remove our save_state routines and only need to provide restore_state routines. The only fields that were at all tricky to regenerate were the msi and msi-x control registers and the way we regenerate them currently is a bit dependent upon assumptions on how we use the allow msi registers to be configured and used making the code a little bit brittle. If we ever change what cases we allow or how we configure the msi bits we can address the fragility then. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Acked-by: Auke Kok <auke-jan.h.kok@intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-09 04:04:57 +08:00
pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
msi_mask_irq(entry, msi_mask(entry->msi_attrib.multi_cap),
entry->masked);
control &= ~PCI_MSI_FLAGS_QSIZE;
control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
}
static void __pci_restore_msix_state(struct pci_dev *dev)
{
struct msi_desc *entry;
if (!dev->msix_enabled)
return;
BUG_ON(list_empty(dev_to_msi_list(&dev->dev)));
/* route the table */
pci_intx_for_msi(dev, 0);
pci_msix_clear_and_set_ctrl(dev, 0,
PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
arch_restore_msi_irqs(dev);
for_each_pci_msi_entry(entry, dev)
msix_mask_irq(entry, entry->masked);
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
}
void pci_restore_msi_state(struct pci_dev *dev)
{
__pci_restore_msi_state(dev);
__pci_restore_msix_state(dev);
}
EXPORT_SYMBOL_GPL(pci_restore_msi_state);
static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct msi_desc *entry;
unsigned long irq;
int retval;
retval = kstrtoul(attr->attr.name, 10, &irq);
if (retval)
return retval;
entry = irq_get_msi_desc(irq);
if (entry)
return sprintf(buf, "%s\n",
entry->msi_attrib.is_msix ? "msix" : "msi");
return -ENODEV;
}
static int populate_msi_sysfs(struct pci_dev *pdev)
{
struct attribute **msi_attrs;
struct attribute *msi_attr;
struct device_attribute *msi_dev_attr;
struct attribute_group *msi_irq_group;
const struct attribute_group **msi_irq_groups;
struct msi_desc *entry;
int ret = -ENOMEM;
int num_msi = 0;
int count = 0;
int i;
/* Determine how many msi entries we have */
for_each_pci_msi_entry(entry, pdev)
num_msi += entry->nvec_used;
if (!num_msi)
return 0;
/* Dynamically create the MSI attributes for the PCI device */
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
msi_attrs = kcalloc(num_msi + 1, sizeof(void *), GFP_KERNEL);
if (!msi_attrs)
return -ENOMEM;
for_each_pci_msi_entry(entry, pdev) {
for (i = 0; i < entry->nvec_used; i++) {
msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
if (!msi_dev_attr)
goto error_attrs;
msi_attrs[count] = &msi_dev_attr->attr;
sysfs_attr_init(&msi_dev_attr->attr);
msi_dev_attr->attr.name = kasprintf(GFP_KERNEL, "%d",
entry->irq + i);
if (!msi_dev_attr->attr.name)
goto error_attrs;
msi_dev_attr->attr.mode = S_IRUGO;
msi_dev_attr->show = msi_mode_show;
++count;
}
}
msi_irq_group = kzalloc(sizeof(*msi_irq_group), GFP_KERNEL);
if (!msi_irq_group)
goto error_attrs;
msi_irq_group->name = "msi_irqs";
msi_irq_group->attrs = msi_attrs;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
msi_irq_groups = kcalloc(2, sizeof(void *), GFP_KERNEL);
if (!msi_irq_groups)
goto error_irq_group;
msi_irq_groups[0] = msi_irq_group;
ret = sysfs_create_groups(&pdev->dev.kobj, msi_irq_groups);
if (ret)
goto error_irq_groups;
pdev->msi_irq_groups = msi_irq_groups;
return 0;
error_irq_groups:
kfree(msi_irq_groups);
error_irq_group:
kfree(msi_irq_group);
error_attrs:
count = 0;
msi_attr = msi_attrs[count];
while (msi_attr) {
msi_dev_attr = container_of(msi_attr, struct device_attribute, attr);
kfree(msi_attr->name);
kfree(msi_dev_attr);
++count;
msi_attr = msi_attrs[count];
}
kfree(msi_attrs);
return ret;
}
static struct msi_desc *
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd)
{
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 irq_affinity_desc *masks = NULL;
struct msi_desc *entry;
u16 control;
if (affd)
masks = irq_create_affinity_masks(nvec, affd);
/* MSI Entry Initialization */
entry = alloc_msi_entry(&dev->dev, nvec, masks);
if (!entry)
goto out;
pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
entry->msi_attrib.is_msix = 0;
entry->msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT);
entry->msi_attrib.is_virtual = 0;
entry->msi_attrib.entry_nr = 0;
entry->msi_attrib.maskbit = !!(control & PCI_MSI_FLAGS_MASKBIT);
entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */
entry->msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1;
entry->msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec));
if (control & PCI_MSI_FLAGS_64BIT)
entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
else
entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
/* Save the initial mask status */
if (entry->msi_attrib.maskbit)
pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
out:
kfree(masks);
return entry;
}
static int msi_verify_entries(struct pci_dev *dev)
{
struct msi_desc *entry;
for_each_pci_msi_entry(entry, dev) {
if (!dev->no_64bit_msi || !entry->msg.address_hi)
continue;
pci_err(dev, "Device has broken 64-bit MSI but arch"
" tried to assign one above 4G\n");
return -EIO;
}
return 0;
}
/**
* msi_capability_init - configure device's MSI capability structure
* @dev: pointer to the pci_dev data structure of MSI device function
* @nvec: number of interrupts to allocate
* @affd: description of automatic IRQ affinity assignments (may be %NULL)
*
* Setup the MSI capability structure of the device with the requested
* number of interrupts. A return value of zero indicates the successful
* setup of an entry with the new MSI IRQ. A negative return value indicates
* an error, and a positive return value indicates the number of interrupts
* which could have been allocated.
*/
static int msi_capability_init(struct pci_dev *dev, int nvec,
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
struct irq_affinity *affd)
{
struct msi_desc *entry;
int ret;
unsigned mask;
pci_msi_set_enable(dev, 0); /* Disable MSI during set up */
entry = msi_setup_entry(dev, nvec, affd);
if (!entry)
return -ENOMEM;
/* All MSIs are unmasked by default; mask them all */
mask = msi_mask(entry->msi_attrib.multi_cap);
msi_mask_irq(entry, mask, mask);
list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
/* Configure MSI capability structure */
ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
if (ret) {
msi_mask_irq(entry, mask, ~mask);
free_msi_irqs(dev);
return ret;
}
ret = msi_verify_entries(dev);
if (ret) {
msi_mask_irq(entry, mask, ~mask);
free_msi_irqs(dev);
return ret;
}
ret = populate_msi_sysfs(dev);
if (ret) {
msi_mask_irq(entry, mask, ~mask);
free_msi_irqs(dev);
return ret;
}
/* Set MSI enabled bits */
pci_intx_for_msi(dev, 0);
pci_msi_set_enable(dev, 1);
dev->msi_enabled = 1;
pcibios_free_irq(dev);
dev->irq = entry->irq;
return 0;
}
static void __iomem *msix_map_region(struct pci_dev *dev, unsigned nr_entries)
{
resource_size_t phys_addr;
u32 table_offset;
unsigned long flags;
u8 bir;
pci_read_config_dword(dev, dev->msix_cap + PCI_MSIX_TABLE,
&table_offset);
bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR);
flags = pci_resource_flags(dev, bir);
if (!flags || (flags & IORESOURCE_UNSET))
return NULL;
table_offset &= PCI_MSIX_TABLE_OFFSET;
phys_addr = pci_resource_start(dev, bir) + table_offset;
return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
}
static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
struct msix_entry *entries, int nvec,
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
struct irq_affinity *affd)
{
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 irq_affinity_desc *curmsk, *masks = NULL;
struct msi_desc *entry;
int ret, i;
int vec_count = pci_msix_vec_count(dev);
if (affd)
masks = irq_create_affinity_masks(nvec, affd);
for (i = 0, curmsk = masks; i < nvec; i++) {
entry = alloc_msi_entry(&dev->dev, 1, curmsk);
if (!entry) {
if (!i)
iounmap(base);
else
free_msi_irqs(dev);
/* No enough memory. Don't try again */
ret = -ENOMEM;
goto out;
}
entry->msi_attrib.is_msix = 1;
entry->msi_attrib.is_64 = 1;
if (entries)
entry->msi_attrib.entry_nr = entries[i].entry;
else
entry->msi_attrib.entry_nr = i;
entry->msi_attrib.is_virtual =
entry->msi_attrib.entry_nr >= vec_count;
entry->msi_attrib.default_irq = dev->irq;
entry->mask_base = base;
list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
if (masks)
curmsk++;
}
ret = 0;
out:
kfree(masks);
return ret;
}
static void msix_program_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;
desc_addr = pci_msix_desc_addr(entry);
if (desc_addr)
entry->masked = readl(desc_addr +
PCI_MSIX_ENTRY_VECTOR_CTRL);
else
entry->masked = 0;
msix_mask_irq(entry, 1);
}
}
/**
* msix_capability_init - configure device's MSI-X capability
* @dev: pointer to the pci_dev data structure of MSI-X device function
* @entries: pointer to an array of struct msix_entry entries
* @nvec: number of @entries
* @affd: Optional pointer to enable automatic affinity assignment
*
* Setup the MSI-X capability structure of device function with a
* single MSI-X IRQ. A return of zero indicates the successful setup of
* requested MSI-X entries with allocated IRQs or non-zero for otherwise.
**/
static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
int nvec, struct irq_affinity *affd)
{
int ret;
u16 control;
void __iomem *base;
/* Ensure MSI-X is disabled while it is set up */
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
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));
if (!base)
return -ENOMEM;
ret = msix_setup_entries(dev, base, entries, nvec, affd);
if (ret)
return ret;
ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
if (ret)
goto out_avail;
/* Check if all MSI entries honor device restrictions */
ret = msi_verify_entries(dev);
if (ret)
goto out_free;
/*
* Some devices require MSI-X to be enabled before we can touch the
* MSI-X registers. We need to mask all the vectors to prevent
* interrupts coming in before they're fully set up.
*/
pci_msix_clear_and_set_ctrl(dev, 0,
PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE);
msix_program_entries(dev, entries);
ret = populate_msi_sysfs(dev);
if (ret)
goto out_free;
/* Set MSI-X enabled bits and unmask the function */
pci_intx_for_msi(dev, 0);
dev->msix_enabled = 1;
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
pcibios_free_irq(dev);
return 0;
out_avail:
if (ret < 0) {
/*
* If we had some success, report the number of IRQs
* we succeeded in setting up.
*/
struct msi_desc *entry;
int avail = 0;
for_each_pci_msi_entry(entry, dev) {
if (entry->irq != 0)
avail++;
}
if (avail != 0)
ret = avail;
}
out_free:
free_msi_irqs(dev);
return ret;
}
/**
* pci_msi_supported - check whether MSI may be enabled on a device
* @dev: pointer to the pci_dev data structure of MSI device function
* @nvec: how many MSIs have been requested?
*
* Look at global flags, the device itself, and its parent buses
* to determine if MSI/-X are supported for the device. If MSI/-X is
* supported return 1, else return 0.
**/
static int pci_msi_supported(struct pci_dev *dev, int nvec)
{
struct pci_bus *bus;
/* MSI must be globally enabled and supported by the device */
if (!pci_msi_enable)
return 0;
if (!dev || dev->no_msi)
return 0;
/*
* You can't ask to have 0 or less MSIs configured.
* a) it's stupid ..
* b) the list manipulation code assumes nvec >= 1.
*/
if (nvec < 1)
return 0;
/*
* Any bridge which does NOT route MSI transactions from its
* secondary bus to its primary bus must set NO_MSI flag on
* the secondary pci_bus.
* We expect only arch-specific PCI host bus controller driver
* or quirks for specific PCI bridges to be setting NO_MSI.
*/
for (bus = dev->bus; bus; bus = bus->parent)
if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
return 0;
return 1;
}
/**
* pci_msi_vec_count - Return the number of MSI vectors a device can send
* @dev: device to report about
*
* This function returns the number of MSI vectors a device requested via
* Multiple Message Capable register. It returns a negative errno if the
* device is not capable sending MSI interrupts. Otherwise, the call succeeds
* and returns a power of two, up to a maximum of 2^5 (32), according to the
* MSI specification.
**/
int pci_msi_vec_count(struct pci_dev *dev)
{
int ret;
u16 msgctl;
if (!dev->msi_cap)
return -EINVAL;
pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl);
ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
return ret;
}
EXPORT_SYMBOL(pci_msi_vec_count);
static void pci_msi_shutdown(struct pci_dev *dev)
{
struct msi_desc *desc;
u32 mask;
if (!pci_msi_enable || !dev || !dev->msi_enabled)
return;
BUG_ON(list_empty(dev_to_msi_list(&dev->dev)));
desc = first_pci_msi_entry(dev);
pci_msi_set_enable(dev, 0);
pci_intx_for_msi(dev, 1);
dev->msi_enabled = 0;
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
/* Return the device with MSI unmasked as initial states */
mask = msi_mask(desc->msi_attrib.multi_cap);
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
/* Keep cached state to be restored */
__pci_msi_desc_mask_irq(desc, mask, ~mask);
/* Restore dev->irq to its default pin-assertion IRQ */
dev->irq = desc->msi_attrib.default_irq;
pcibios_alloc_irq(dev);
}
void pci_disable_msi(struct pci_dev *dev)
{
if (!pci_msi_enable || !dev || !dev->msi_enabled)
return;
pci_msi_shutdown(dev);
free_msi_irqs(dev);
}
EXPORT_SYMBOL(pci_disable_msi);
/**
* pci_msix_vec_count - return the number of device's MSI-X table entries
* @dev: pointer to the pci_dev data structure of MSI-X device function
* This function returns the number of device's MSI-X table entries and
* therefore the number of MSI-X vectors device is capable of sending.
* It returns a negative errno if the device is not capable of sending MSI-X
* interrupts.
**/
int pci_msix_vec_count(struct pci_dev *dev)
{
u16 control;
if (!dev->msix_cap)
return -EINVAL;
pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
return msix_table_size(control);
}
EXPORT_SYMBOL(pci_msix_vec_count);
static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
int nvec, struct irq_affinity *affd, int flags)
{
int nr_entries;
int i, j;
if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0)
return -EINVAL;
nr_entries = pci_msix_vec_count(dev);
if (nr_entries < 0)
return nr_entries;
if (nvec > nr_entries && !(flags & PCI_IRQ_VIRTUAL))
return nr_entries;
if (entries) {
/* Check for any invalid entries */
for (i = 0; i < nvec; i++) {
if (entries[i].entry >= nr_entries)
return -EINVAL; /* invalid entry */
for (j = i + 1; j < nvec; j++) {
if (entries[i].entry == entries[j].entry)
return -EINVAL; /* duplicate entry */
}
}
}
/* Check whether driver already requested for MSI IRQ */
if (dev->msi_enabled) {
pci_info(dev, "can't enable MSI-X (MSI IRQ already assigned)\n");
return -EINVAL;
}
return msix_capability_init(dev, entries, nvec, affd);
}
static void pci_msix_shutdown(struct pci_dev *dev)
{
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
struct msi_desc *entry;
if (!pci_msi_enable || !dev || !dev->msix_enabled)
return;
if (pci_dev_is_disconnected(dev)) {
dev->msix_enabled = 0;
return;
}
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
/* Return the device with MSI-X masked as initial states */
for_each_pci_msi_entry(entry, dev) {
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
/* Keep cached states to be restored */
__pci_msix_desc_mask_irq(entry, 1);
PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-06-24 11:08:09 +08:00
}
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
pci_intx_for_msi(dev, 1);
dev->msix_enabled = 0;
pcibios_alloc_irq(dev);
}
void pci_disable_msix(struct pci_dev *dev)
{
if (!pci_msi_enable || !dev || !dev->msix_enabled)
return;
pci_msix_shutdown(dev);
free_msi_irqs(dev);
}
EXPORT_SYMBOL(pci_disable_msix);
void pci_no_msi(void)
{
pci_msi_enable = 0;
}
/**
* pci_msi_enabled - is MSI enabled?
*
* Returns true if MSI has not been disabled by the command-line option
* pci=nomsi.
**/
int pci_msi_enabled(void)
{
return pci_msi_enable;
}
EXPORT_SYMBOL(pci_msi_enabled);
static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
struct irq_affinity *affd)
{
int nvec;
int rc;
if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0)
return -EINVAL;
/* Check whether driver already requested MSI-X IRQs */
if (dev->msix_enabled) {
pci_info(dev, "can't enable MSI (MSI-X already enabled)\n");
return -EINVAL;
}
if (maxvec < minvec)
return -ERANGE;
if (WARN_ON_ONCE(dev->msi_enabled))
return -EINVAL;
nvec = pci_msi_vec_count(dev);
if (nvec < 0)
return nvec;
if (nvec < minvec)
return -ENOSPC;
if (nvec > maxvec)
nvec = maxvec;
for (;;) {
if (affd) {
nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
if (nvec < minvec)
return -ENOSPC;
}
rc = msi_capability_init(dev, nvec, affd);
if (rc == 0)
return nvec;
if (rc < 0)
return rc;
if (rc < minvec)
return -ENOSPC;
nvec = rc;
}
}
/* deprecated, don't use */
int pci_enable_msi(struct pci_dev *dev)
{
int rc = __pci_enable_msi_range(dev, 1, 1, NULL);
if (rc < 0)
return rc;
return 0;
}
EXPORT_SYMBOL(pci_enable_msi);
static int __pci_enable_msix_range(struct pci_dev *dev,
struct msix_entry *entries, int minvec,
int maxvec, struct irq_affinity *affd,
int flags)
{
int rc, nvec = maxvec;
if (maxvec < minvec)
return -ERANGE;
if (WARN_ON_ONCE(dev->msix_enabled))
return -EINVAL;
for (;;) {
if (affd) {
nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
if (nvec < minvec)
return -ENOSPC;
}
rc = __pci_enable_msix(dev, entries, nvec, affd, flags);
if (rc == 0)
return nvec;
if (rc < 0)
return rc;
if (rc < minvec)
return -ENOSPC;
nvec = rc;
}
}
/**
* pci_enable_msix_range - configure device's MSI-X capability structure
* @dev: pointer to the pci_dev data structure of MSI-X device function
* @entries: pointer to an array of MSI-X entries
* @minvec: minimum number of MSI-X IRQs requested
* @maxvec: maximum number of MSI-X IRQs requested
*
* Setup the MSI-X capability structure of device function with a maximum
* possible number of interrupts in the range between @minvec and @maxvec
* upon its software driver call to request for MSI-X mode enabled on its
* hardware device function. It returns a negative errno if an error occurs.
* If it succeeds, it returns the actual number of interrupts allocated and
* indicates the successful configuration of MSI-X capability structure
* with new allocated MSI-X interrupts.
**/
int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
int minvec, int maxvec)
{
return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0);
}
EXPORT_SYMBOL(pci_enable_msix_range);
/**
* pci_alloc_irq_vectors_affinity - allocate multiple IRQs for a device
* @dev: PCI device to operate on
* @min_vecs: minimum number of vectors required (must be >= 1)
* @max_vecs: maximum (desired) number of vectors
* @flags: flags or quirks for the allocation
* @affd: optional description of the affinity requirements
*
* Allocate up to @max_vecs interrupt vectors for @dev, using MSI-X or MSI
* vectors if available, and fall back to a single legacy vector
* if neither is available. Return the number of vectors allocated,
* (which might be smaller than @max_vecs) if successful, or a negative
* error code on error. If less than @min_vecs interrupt vectors are
* available for @dev the function will fail with -ENOSPC.
*
* To get the Linux IRQ number used for a vector that can be passed to
* request_irq() use the pci_irq_vector() helper.
*/
int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
unsigned int max_vecs, unsigned int flags,
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
struct irq_affinity *affd)
{
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
struct irq_affinity msi_default_affd = {0};
PCI/MSI: Return -ENOSPC from pci_alloc_irq_vectors_affinity() The API of pci_alloc_irq_vectors_affinity() says it returns -ENOSPC if fewer than @min_vecs interrupt vectors are available for @dev. However, if a device supports MSI-X but not MSI and a caller requests @min_vecs that can't be satisfied by MSI-X, we previously returned -EINVAL (from the failed attempt to enable MSI), not -ENOSPC. When -ENOSPC is returned, callers may reduce the number IRQs they request and try again. Most callers can use the @min_vecs and @max_vecs parameters to avoid this retry loop, but that doesn't work when using IRQ affinity "nr_sets" because rebalancing the sets is driver-specific. This return value bug has been present since pci_alloc_irq_vectors() was added in v4.10 by aff171641d18 ("PCI: Provide sensible IRQ vector alloc/free routines"), but it wasn't an issue because @min_vecs/@max_vecs removed the need for callers to iteratively reduce the number of IRQs requested and retry the allocation, so they didn't need to distinguish -ENOSPC from -EINVAL. In v5.0, 6da4b3ab9a6e ("genirq/affinity: Add support for allocating interrupt sets") added IRQ sets to the interface, which reintroduced the need to check for -ENOSPC and possibly reduce the number of IRQs requested and retry the allocation. Signed-off-by: Ming Lei <ming.lei@redhat.com> [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Christoph Hellwig <hch@lst.de>
2019-01-16 07:31:29 +08:00
int msix_vecs = -ENOSPC;
int msi_vecs = -ENOSPC;
if (flags & PCI_IRQ_AFFINITY) {
if (!affd)
affd = &msi_default_affd;
} else {
if (WARN_ON(affd))
affd = NULL;
}
if (flags & PCI_IRQ_MSIX) {
PCI/MSI: Return -ENOSPC from pci_alloc_irq_vectors_affinity() The API of pci_alloc_irq_vectors_affinity() says it returns -ENOSPC if fewer than @min_vecs interrupt vectors are available for @dev. However, if a device supports MSI-X but not MSI and a caller requests @min_vecs that can't be satisfied by MSI-X, we previously returned -EINVAL (from the failed attempt to enable MSI), not -ENOSPC. When -ENOSPC is returned, callers may reduce the number IRQs they request and try again. Most callers can use the @min_vecs and @max_vecs parameters to avoid this retry loop, but that doesn't work when using IRQ affinity "nr_sets" because rebalancing the sets is driver-specific. This return value bug has been present since pci_alloc_irq_vectors() was added in v4.10 by aff171641d18 ("PCI: Provide sensible IRQ vector alloc/free routines"), but it wasn't an issue because @min_vecs/@max_vecs removed the need for callers to iteratively reduce the number of IRQs requested and retry the allocation, so they didn't need to distinguish -ENOSPC from -EINVAL. In v5.0, 6da4b3ab9a6e ("genirq/affinity: Add support for allocating interrupt sets") added IRQ sets to the interface, which reintroduced the need to check for -ENOSPC and possibly reduce the number of IRQs requested and retry the allocation. Signed-off-by: Ming Lei <ming.lei@redhat.com> [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Christoph Hellwig <hch@lst.de>
2019-01-16 07:31:29 +08:00
msix_vecs = __pci_enable_msix_range(dev, NULL, min_vecs,
max_vecs, affd, flags);
PCI/MSI: Return -ENOSPC from pci_alloc_irq_vectors_affinity() The API of pci_alloc_irq_vectors_affinity() says it returns -ENOSPC if fewer than @min_vecs interrupt vectors are available for @dev. However, if a device supports MSI-X but not MSI and a caller requests @min_vecs that can't be satisfied by MSI-X, we previously returned -EINVAL (from the failed attempt to enable MSI), not -ENOSPC. When -ENOSPC is returned, callers may reduce the number IRQs they request and try again. Most callers can use the @min_vecs and @max_vecs parameters to avoid this retry loop, but that doesn't work when using IRQ affinity "nr_sets" because rebalancing the sets is driver-specific. This return value bug has been present since pci_alloc_irq_vectors() was added in v4.10 by aff171641d18 ("PCI: Provide sensible IRQ vector alloc/free routines"), but it wasn't an issue because @min_vecs/@max_vecs removed the need for callers to iteratively reduce the number of IRQs requested and retry the allocation, so they didn't need to distinguish -ENOSPC from -EINVAL. In v5.0, 6da4b3ab9a6e ("genirq/affinity: Add support for allocating interrupt sets") added IRQ sets to the interface, which reintroduced the need to check for -ENOSPC and possibly reduce the number of IRQs requested and retry the allocation. Signed-off-by: Ming Lei <ming.lei@redhat.com> [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Christoph Hellwig <hch@lst.de>
2019-01-16 07:31:29 +08:00
if (msix_vecs > 0)
return msix_vecs;
}
if (flags & PCI_IRQ_MSI) {
PCI/MSI: Return -ENOSPC from pci_alloc_irq_vectors_affinity() The API of pci_alloc_irq_vectors_affinity() says it returns -ENOSPC if fewer than @min_vecs interrupt vectors are available for @dev. However, if a device supports MSI-X but not MSI and a caller requests @min_vecs that can't be satisfied by MSI-X, we previously returned -EINVAL (from the failed attempt to enable MSI), not -ENOSPC. When -ENOSPC is returned, callers may reduce the number IRQs they request and try again. Most callers can use the @min_vecs and @max_vecs parameters to avoid this retry loop, but that doesn't work when using IRQ affinity "nr_sets" because rebalancing the sets is driver-specific. This return value bug has been present since pci_alloc_irq_vectors() was added in v4.10 by aff171641d18 ("PCI: Provide sensible IRQ vector alloc/free routines"), but it wasn't an issue because @min_vecs/@max_vecs removed the need for callers to iteratively reduce the number of IRQs requested and retry the allocation, so they didn't need to distinguish -ENOSPC from -EINVAL. In v5.0, 6da4b3ab9a6e ("genirq/affinity: Add support for allocating interrupt sets") added IRQ sets to the interface, which reintroduced the need to check for -ENOSPC and possibly reduce the number of IRQs requested and retry the allocation. Signed-off-by: Ming Lei <ming.lei@redhat.com> [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Christoph Hellwig <hch@lst.de>
2019-01-16 07:31:29 +08:00
msi_vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs,
affd);
if (msi_vecs > 0)
return msi_vecs;
}
/* use legacy IRQ if allowed */
if (flags & PCI_IRQ_LEGACY) {
if (min_vecs == 1 && dev->irq) {
genirq/affinity: Add new callback for (re)calculating interrupt sets The interrupt affinity spreading mechanism supports to spread out affinities for one or more interrupt sets. A interrupt set contains one or more interrupts. Each set is mapped to a specific functionality of a device, e.g. general I/O queues and read I/O queus of multiqueue block devices. The number of interrupts per set is defined by the driver. It depends on the total number of available interrupts for the device, which is determined by the PCI capabilites and the availability of underlying CPU resources, and the number of queues which the device provides and the driver wants to instantiate. The driver passes initial configuration for the interrupt allocation via a pointer to struct irq_affinity. Right now the allocation mechanism is complex as it requires to have a loop in the driver to determine the maximum number of interrupts which are provided by the PCI capabilities and the underlying CPU resources. This loop would have to be replicated in every driver which wants to utilize this mechanism. That's unwanted code duplication and error prone. In order to move this into generic facilities it is required to have a mechanism, which allows the recalculation of the interrupt sets and their size, in the core code. As the core code does not have any knowledge about the underlying device, a driver specific callback is required in struct irq_affinity, which can be invoked by the core code. The callback gets the number of available interupts as an argument, so the driver can calculate the corresponding number and size of interrupt sets. At the moment the struct irq_affinity pointer which is handed in from the driver and passed through to several core functions is marked 'const', but for the callback to be able to modify the data in the struct it's required to remove the 'const' qualifier. Add the optional callback to struct irq_affinity, which allows drivers to recalculate the number and size of interrupt sets and remove the 'const' qualifier. For simple invocations, which do not supply a callback, a default callback is installed, which just sets nr_sets to 1 and transfers the number of spreadable vectors to the set_size array at index 0. This is for now guarded by a check for nr_sets != 0 to keep the NVME driver working until it is converted to the callback mechanism. To make sure that the driver configuration is correct under all circumstances the callback is invoked even when there are no interrupts for queues left, i.e. the pre/post requirements already exhaust the numner of available interrupts. At the PCI layer irq_create_affinity_masks() has to be invoked even for the case where the legacy interrupt is used. That ensures that the callback is invoked and the device driver can adjust to that situation. [ tglx: Fixed the simple case (no sets required). Moved the sanity check for nr_sets after the invocation of the callback so it catches broken drivers. Fixed the kernel doc comments for struct irq_affinity and de-'This patch'-ed the changelog ] Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Bjorn Helgaas <helgaas@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: linux-block@vger.kernel.org Cc: Sagi Grimberg <sagi@grimberg.me> Cc: linux-nvme@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: Keith Busch <keith.busch@intel.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com> Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
2019-02-17 01:13:09 +08:00
/*
* Invoke the affinity spreading logic to ensure that
* the device driver can adjust queue configuration
* for the single interrupt case.
*/
if (affd)
irq_create_affinity_masks(1, affd);
pci_intx(dev, 1);
return 1;
}
}
PCI/MSI: Return -ENOSPC from pci_alloc_irq_vectors_affinity() The API of pci_alloc_irq_vectors_affinity() says it returns -ENOSPC if fewer than @min_vecs interrupt vectors are available for @dev. However, if a device supports MSI-X but not MSI and a caller requests @min_vecs that can't be satisfied by MSI-X, we previously returned -EINVAL (from the failed attempt to enable MSI), not -ENOSPC. When -ENOSPC is returned, callers may reduce the number IRQs they request and try again. Most callers can use the @min_vecs and @max_vecs parameters to avoid this retry loop, but that doesn't work when using IRQ affinity "nr_sets" because rebalancing the sets is driver-specific. This return value bug has been present since pci_alloc_irq_vectors() was added in v4.10 by aff171641d18 ("PCI: Provide sensible IRQ vector alloc/free routines"), but it wasn't an issue because @min_vecs/@max_vecs removed the need for callers to iteratively reduce the number of IRQs requested and retry the allocation, so they didn't need to distinguish -ENOSPC from -EINVAL. In v5.0, 6da4b3ab9a6e ("genirq/affinity: Add support for allocating interrupt sets") added IRQ sets to the interface, which reintroduced the need to check for -ENOSPC and possibly reduce the number of IRQs requested and retry the allocation. Signed-off-by: Ming Lei <ming.lei@redhat.com> [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Jens Axboe <axboe@fb.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Christoph Hellwig <hch@lst.de>
2019-01-16 07:31:29 +08:00
if (msix_vecs == -ENOSPC)
return -ENOSPC;
return msi_vecs;
}
EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity);
/**
* pci_free_irq_vectors - free previously allocated IRQs for a device
* @dev: PCI device to operate on
*
* Undoes the allocations and enabling in pci_alloc_irq_vectors().
*/
void pci_free_irq_vectors(struct pci_dev *dev)
{
pci_disable_msix(dev);
pci_disable_msi(dev);
}
EXPORT_SYMBOL(pci_free_irq_vectors);
/**
* pci_irq_vector - return Linux IRQ number of a device vector
* @dev: PCI device to operate on
* @nr: device-relative interrupt vector index (0-based).
*/
int pci_irq_vector(struct pci_dev *dev, unsigned int nr)
{
if (dev->msix_enabled) {
struct msi_desc *entry;
int i = 0;
for_each_pci_msi_entry(entry, dev) {
if (i == nr)
return entry->irq;
i++;
}
WARN_ON_ONCE(1);
return -EINVAL;
}
if (dev->msi_enabled) {
struct msi_desc *entry = first_pci_msi_entry(dev);
if (WARN_ON_ONCE(nr >= entry->nvec_used))
return -EINVAL;
} else {
if (WARN_ON_ONCE(nr > 0))
return -EINVAL;
}
return dev->irq + nr;
}
EXPORT_SYMBOL(pci_irq_vector);
/**
* pci_irq_get_affinity - return the affinity of a particular MSI vector
* @dev: PCI device to operate on
* @nr: device-relative interrupt vector index (0-based).
*/
const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr)
{
if (dev->msix_enabled) {
struct msi_desc *entry;
int i = 0;
for_each_pci_msi_entry(entry, dev) {
if (i == nr)
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
return &entry->affinity->mask;
i++;
}
WARN_ON_ONCE(1);
return NULL;
} else if (dev->msi_enabled) {
struct msi_desc *entry = first_pci_msi_entry(dev);
if (WARN_ON_ONCE(!entry || !entry->affinity ||
nr >= entry->nvec_used))
return NULL;
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
return &entry->affinity[nr].mask;
} else {
return cpu_possible_mask;
}
}
EXPORT_SYMBOL(pci_irq_get_affinity);
struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
{
return to_pci_dev(desc->dev);
}
EXPORT_SYMBOL(msi_desc_to_pci_dev);
void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
{
struct pci_dev *dev = msi_desc_to_pci_dev(desc);
return dev->bus->sysdata;
}
EXPORT_SYMBOL_GPL(msi_desc_to_pci_sysdata);
#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
/**
* pci_msi_domain_write_msg - Helper to write MSI message to PCI config space
* @irq_data: Pointer to interrupt data of the MSI interrupt
* @msg: Pointer to the message
*/
void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
{
struct msi_desc *desc = irq_data_get_msi_desc(irq_data);
/*
* For MSI-X desc->irq is always equal to irq_data->irq. For
* MSI only the first interrupt of MULTI MSI passes the test.
*/
if (desc->irq == irq_data->irq)
__pci_write_msi_msg(desc, msg);
}
/**
* pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source
* @dev: Pointer to the PCI device
* @desc: Pointer to the MSI descriptor
*
* The ID number is only used within the irqdomain.
*/
irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
struct msi_desc *desc)
{
return (irq_hw_number_t)desc->msi_attrib.entry_nr |
pci_dev_id(dev) << 11 |
(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
}
static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc)
{
return !desc->msi_attrib.is_msix && desc->nvec_used > 1;
}
/**
* pci_msi_domain_check_cap - Verify that @domain supports the capabilities
* for @dev
* @domain: The interrupt domain to check
* @info: The domain info for verification
* @dev: The device to check
*
* Returns:
* 0 if the functionality is supported
* 1 if Multi MSI is requested, but the domain does not support it
* -ENOTSUPP otherwise
*/
int pci_msi_domain_check_cap(struct irq_domain *domain,
struct msi_domain_info *info, struct device *dev)
{
struct msi_desc *desc = first_pci_msi_entry(to_pci_dev(dev));
/* Special handling to support __pci_enable_msi_range() */
if (pci_msi_desc_is_multi_msi(desc) &&
!(info->flags & MSI_FLAG_MULTI_PCI_MSI))
return 1;
else if (desc->msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX))
return -ENOTSUPP;
return 0;
}
static int pci_msi_domain_handle_error(struct irq_domain *domain,
struct msi_desc *desc, int error)
{
/* Special handling to support __pci_enable_msi_range() */
if (pci_msi_desc_is_multi_msi(desc) && error == -ENOSPC)
return 1;
return error;
}
#ifdef GENERIC_MSI_DOMAIN_OPS
static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
struct msi_desc *desc)
{
arg->desc = desc;
arg->hwirq = pci_msi_domain_calc_hwirq(msi_desc_to_pci_dev(desc),
desc);
}
#else
#define pci_msi_domain_set_desc NULL
#endif
static struct msi_domain_ops pci_msi_domain_ops_default = {
.set_desc = pci_msi_domain_set_desc,
.msi_check = pci_msi_domain_check_cap,
.handle_error = pci_msi_domain_handle_error,
};
static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info)
{
struct msi_domain_ops *ops = info->ops;
if (ops == NULL) {
info->ops = &pci_msi_domain_ops_default;
} else {
if (ops->set_desc == NULL)
ops->set_desc = pci_msi_domain_set_desc;
if (ops->msi_check == NULL)
ops->msi_check = pci_msi_domain_check_cap;
if (ops->handle_error == NULL)
ops->handle_error = pci_msi_domain_handle_error;
}
}
static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info)
{
struct irq_chip *chip = info->chip;
BUG_ON(!chip);
if (!chip->irq_write_msi_msg)
chip->irq_write_msi_msg = pci_msi_domain_write_msg;
if (!chip->irq_mask)
chip->irq_mask = pci_msi_mask_irq;
if (!chip->irq_unmask)
chip->irq_unmask = pci_msi_unmask_irq;
}
/**
* pci_msi_create_irq_domain - Create a MSI interrupt domain
* @fwnode: Optional fwnode of the interrupt controller
* @info: MSI domain info
* @parent: Parent irq domain
*
* Updates the domain and chip ops and creates a MSI interrupt domain.
*
* Returns:
* A domain pointer or NULL in case of failure.
*/
struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
struct msi_domain_info *info,
struct irq_domain *parent)
{
struct irq_domain *domain;
if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE))
info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
pci_msi_domain_update_dom_ops(info);
if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
pci_msi_domain_update_chip_ops(info);
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
info->flags |= MSI_FLAG_ACTIVATE_EARLY;
if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
info->flags |= MSI_FLAG_MUST_REACTIVATE;
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
2018-08-06 04:31:03 +08:00
/* PCI-MSI is oneshot-safe */
info->chip->flags |= IRQCHIP_ONESHOT_SAFE;
domain = msi_create_irq_domain(fwnode, info, parent);
if (!domain)
return NULL;
irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI);
return domain;
}
EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain);
/*
* Users of the generic MSI infrastructure expect a device to have a single ID,
* so with DMA aliases we have to pick the least-worst compromise. Devices with
* DMA phantom functions tend to still emit MSIs from the real function number,
* so we ignore those and only consider topological aliases where either the
* alias device or RID appears on a different bus number. We also make the
* reasonable assumption that bridges are walked in an upstream direction (so
* the last one seen wins), and the much braver assumption that the most likely
* case is that of PCI->PCIe so we should always use the alias RID. This echoes
* the logic from intel_irq_remapping's set_msi_sid(), which presumably works
* well enough in practice; in the face of the horrible PCIe<->PCI-X conditions
* for taking ownership all we can really do is close our eyes and hope...
*/
static int get_msi_id_cb(struct pci_dev *pdev, u16 alias, void *data)
{
u32 *pa = data;
u8 bus = PCI_BUS_NUM(*pa);
if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus)
*pa = alias;
return 0;
}
/**
* pci_msi_domain_get_msi_rid - Get the MSI requester id (RID)
* @domain: The interrupt domain
* @pdev: The PCI device.
*
* The RID for a device is formed from the alias, with a firmware
* supplied mapping applied
*
* Returns: The RID.
*/
u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
{
struct device_node *of_node;
u32 rid = pci_dev_id(pdev);
pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
of_node = irq_domain_get_of_node(domain);
rid = of_node ? of_msi_map_rid(&pdev->dev, of_node, rid) :
iort_msi_map_rid(&pdev->dev, rid);
return rid;
}
/**
* pci_msi_get_device_domain - Get the MSI domain for a given PCI device
* @pdev: The PCI device
*
* Use the firmware data to find a device-specific MSI domain
* (i.e. not one that is set as a default).
*
* Returns: The corresponding MSI domain or NULL if none has been found.
*/
struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
{
struct irq_domain *dom;
u32 rid = pci_dev_id(pdev);
pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
dom = of_msi_map_get_device_domain(&pdev->dev, rid);
if (!dom)
dom = iort_get_device_domain(&pdev->dev, rid);
return dom;
}
#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */