linux/drivers/pci/msi.c

1120 lines
28 KiB
C
Raw Normal View History

/*
* File: msi.c
* Purpose: PCI Message Signaled Interrupt (MSI)
*
* Copyright (C) 2003-2004 Intel
* Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
*/
#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 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 08:04:11 +00:00
#include <linux/slab.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)
/* 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>
2013-08-09 20:27:06 +00:00
int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
{
struct msi_chip *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>
2013-08-09 20:27:06 +00:00
}
void __weak arch_teardown_msi_irq(unsigned int irq)
{
struct msi_chip *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>
2013-08-09 20:27:06 +00:00
int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
struct msi_desc *entry;
int ret;
/*
* 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;
list_for_each_entry(entry, &dev->msi_list, list) {
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>
2013-08-09 20:27:06 +00:00
/*
* 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)
{
struct msi_desc *entry;
list_for_each_entry(entry, &dev->msi_list, list) {
int i, nvec;
if (entry->irq == 0)
continue;
if (entry->nvec_used)
nvec = entry->nvec_used;
else
nvec = 1 << entry->msi_attrib.multiple;
for (i = 0; i < nvec; 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>
2013-08-09 20:27:06 +00:00
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) {
list_for_each_entry(entry, &dev->msi_list, list) {
if (irq == entry->irq)
break;
}
} else if (dev->msi_enabled) {
entry = irq_get_msi_desc(irq);
}
if (entry)
__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>
2013-08-09 20:27:06 +00:00
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>
2013-08-09 20:27:06 +00:00
{
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>
2013-08-09 20:27:06 +00:00
}
static void msi_set_enable(struct pci_dev *dev, int enable)
{
u16 control;
pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
control &= ~PCI_MSI_FLAGS_ENABLE;
if (enable)
control |= PCI_MSI_FLAGS_ENABLE;
pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
}
static void msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
{
u16 ctrl;
pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
ctrl &= ~clear;
ctrl |= set;
pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl);
}
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 default_msi_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 03:08:09 +00:00
return 0;
mask_bits &= ~mask;
mask_bits |= flag;
pci_write_config_dword(desc->dev, 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 03:08:09 +00:00
return mask_bits;
}
__weak u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
{
return default_msi_mask_irq(desc, mask, flag);
}
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 03:08:09 +00:00
static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
{
desc->masked = arch_msi_mask_irq(desc, mask, flag);
}
/*
* 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 default_msix_mask_irq(struct msi_desc *desc, u32 flag)
{
u32 mask_bits = desc->masked;
unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_VECTOR_CTRL;
if (pci_msi_ignore_mask)
return 0;
mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
if (flag)
mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
writel(mask_bits, desc->mask_base + offset);
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 03:08:09 +00:00
return mask_bits;
}
__weak u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag)
{
return default_msix_mask_irq(desc, flag);
}
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 03:08:09 +00:00
static void msix_mask_irq(struct msi_desc *desc, u32 flag)
{
desc->masked = arch_msix_mask_irq(desc, flag);
}
static void msi_set_mask_bit(struct irq_data *data, u32 flag)
{
struct msi_desc *desc = irq_data_get_msi(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);
}
}
void mask_msi_irq(struct irq_data *data)
{
msi_set_mask_bit(data, 1);
}
void unmask_msi_irq(struct irq_data *data)
{
msi_set_mask_bit(data, 0);
}
void default_restore_msi_irqs(struct pci_dev *dev)
{
struct msi_desc *entry;
list_for_each_entry(entry, &dev->msi_list, list) {
default_restore_msi_irq(dev, entry->irq);
}
}
void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
BUG_ON(entry->dev->current_state != PCI_D0);
if (entry->msi_attrib.is_msix) {
void __iomem *base = entry->mask_base +
entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
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 {
struct pci_dev *dev = entry->dev;
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 read_msi_msg(unsigned int irq, struct msi_msg *msg)
{
struct msi_desc *entry = irq_get_msi_desc(irq);
__read_msi_msg(entry, msg);
}
void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
/* Assert that the cache is valid, assuming that
* valid messages are not all-zeroes. */
BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo |
entry->msg.data));
*msg = entry->msg;
}
void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
{
struct msi_desc *entry = irq_get_msi_desc(irq);
__get_cached_msi_msg(entry, msg);
}
EXPORT_SYMBOL_GPL(get_cached_msi_msg);
void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
if (entry->dev->current_state != PCI_D0) {
/* Don't touch the hardware now */
} else if (entry->msi_attrib.is_msix) {
void __iomem *base;
base = entry->mask_base +
entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
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 {
struct pci_dev *dev = entry->dev;
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);
}
}
[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>
2007-03-08 20:04:57 +00:00
entry->msg = *msg;
}
void write_msi_msg(unsigned int irq, struct msi_msg *msg)
{
struct msi_desc *entry = irq_get_msi_desc(irq);
__write_msi_msg(entry, msg);
}
EXPORT_SYMBOL_GPL(write_msi_msg);
static void free_msi_irqs(struct pci_dev *dev)
{
struct msi_desc *entry, *tmp;
struct attribute **msi_attrs;
struct device_attribute *dev_attr;
int count = 0;
list_for_each_entry(entry, &dev->msi_list, list) {
int i, nvec;
if (!entry->irq)
continue;
if (entry->nvec_used)
nvec = entry->nvec_used;
else
nvec = 1 << entry->msi_attrib.multiple;
for (i = 0; i < nvec; i++)
BUG_ON(irq_has_action(entry->irq + i));
}
arch_teardown_msi_irqs(dev);
list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) {
if (entry->msi_attrib.is_msix) {
if (list_is_last(&entry->list, &dev->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 15:29:54 +00:00
list_del(&entry->list);
kfree(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 struct msi_desc *alloc_msi_entry(struct pci_dev *dev)
{
struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
if (!desc)
return NULL;
INIT_LIST_HEAD(&desc->list);
desc->dev = dev;
return desc;
}
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>
2007-03-08 20:04:57 +00:00
struct msi_desc *entry;
if (!dev->msi_enabled)
return;
entry = irq_get_msi_desc(dev->irq);
pci_intx_for_msi(dev, 0);
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>
2007-03-08 20:04:57 +00:00
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->msi_list));
/* route the table */
pci_intx_for_msi(dev, 0);
msix_clear_and_set_ctrl(dev, 0,
PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
arch_restore_msi_irqs(dev);
list_for_each_entry(entry, &dev->msi_list, list) {
msix_mask_irq(entry, entry->masked);
}
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;
/* Determine how many msi entries we have */
list_for_each_entry(entry, &pdev->msi_list, list) {
++num_msi;
}
if (!num_msi)
return 0;
/* Dynamically create the MSI attributes for the PCI device */
msi_attrs = kzalloc(sizeof(void *) * (num_msi + 1), GFP_KERNEL);
if (!msi_attrs)
return -ENOMEM;
list_for_each_entry(entry, &pdev->msi_list, list) {
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);
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;
msi_irq_groups = kzalloc(sizeof(void *) * 2, 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 *msi_setup_entry(struct pci_dev *dev)
{
u16 control;
struct msi_desc *entry;
/* MSI Entry Initialization */
entry = alloc_msi_entry(dev);
if (!entry)
return NULL;
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.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;
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);
return entry;
}
/**
* 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
*
* 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)
{
struct msi_desc *entry;
int ret;
unsigned mask;
msi_set_enable(dev, 0); /* Disable MSI during set up */
entry = msi_setup_entry(dev);
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->msi_list);
/* Configure MSI capability structure */
ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
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);
msi_set_enable(dev, 1);
dev->msi_enabled = 1;
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;
u8 bir;
pci_read_config_dword(dev, dev->msix_cap + PCI_MSIX_TABLE,
&table_offset);
bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR);
table_offset &= PCI_MSIX_TABLE_OFFSET;
phys_addr = pci_resource_start(dev, bir) + table_offset;
return ioremap_nocache(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)
{
struct msi_desc *entry;
int i;
for (i = 0; i < nvec; i++) {
entry = alloc_msi_entry(dev);
if (!entry) {
if (!i)
iounmap(base);
else
free_msi_irqs(dev);
/* No enough memory. Don't try again */
return -ENOMEM;
}
entry->msi_attrib.is_msix = 1;
entry->msi_attrib.is_64 = 1;
entry->msi_attrib.entry_nr = entries[i].entry;
entry->msi_attrib.default_irq = dev->irq;
entry->mask_base = base;
list_add_tail(&entry->list, &dev->msi_list);
}
return 0;
}
static void msix_program_entries(struct pci_dev *dev,
struct msix_entry *entries)
{
struct msi_desc *entry;
int i = 0;
list_for_each_entry(entry, &dev->msi_list, list) {
int offset = entries[i].entry * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_VECTOR_CTRL;
entries[i].vector = entry->irq;
irq_set_msi_desc(entry->irq, entry);
entry->masked = readl(entry->mask_base + offset);
msix_mask_irq(entry, 1);
i++;
}
}
/**
* 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
*
* 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, int nvec)
{
int ret;
u16 control;
void __iomem *base;
/* Ensure MSI-X is disabled while it is set up */
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);
if (ret)
return ret;
ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
if (ret)
goto out_avail;
/*
* 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.
*/
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;
msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
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;
list_for_each_entry(entry, &dev->msi_list, list) {
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 || dev->current_state != PCI_D0)
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);
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->msi_list));
desc = list_first_entry(&dev->msi_list, struct msi_desc, list);
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 03:08:09 +00:00
/* 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 03:08:09 +00:00
/* Keep cached state to be restored */
arch_msi_mask_irq(desc, mask, ~mask);
/* Restore dev->irq to its default pin-assertion irq */
dev->irq = desc->msi_attrib.default_irq;
}
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);
/**
* pci_enable_msix - 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
* @nvec: number of MSI-X irqs requested for allocation by device driver
*
* Setup the MSI-X capability structure of device function with the number
* of requested irqs upon its software driver call to request for
* MSI-X mode enabled on its hardware device function. A return of zero
* indicates the successful configuration of MSI-X capability structure
* with new allocated MSI-X irqs. A return of < 0 indicates a failure.
* Or a return of > 0 indicates that driver request is exceeding the number
* of irqs or MSI-X vectors available. Driver should use the returned value to
* re-send its request.
**/
int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
{
int nr_entries;
int i, j;
if (!pci_msi_supported(dev, nvec))
return -EINVAL;
if (!entries)
return -EINVAL;
nr_entries = pci_msix_vec_count(dev);
if (nr_entries < 0)
return nr_entries;
if (nvec > nr_entries)
return nr_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 */
}
}
WARN_ON(!!dev->msix_enabled);
/* Check whether driver already requested for MSI irq */
if (dev->msi_enabled) {
dev_info(&dev->dev, "can't enable MSI-X (MSI IRQ already assigned)\n");
return -EINVAL;
}
return msix_capability_init(dev, entries, nvec);
}
EXPORT_SYMBOL(pci_enable_msix);
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 03:08:09 +00:00
struct msi_desc *entry;
if (!pci_msi_enable || !dev || !dev->msix_enabled)
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 03:08:09 +00:00
/* Return the device with MSI-X masked as initial states */
list_for_each_entry(entry, &dev->msi_list, list) {
/* Keep cached states to be restored */
arch_msix_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 03:08:09 +00:00
}
msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
pci_intx_for_msi(dev, 1);
dev->msix_enabled = 0;
}
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);
void pci_msi_init_pci_dev(struct pci_dev *dev)
{
INIT_LIST_HEAD(&dev->msi_list);
/* Disable the msi hardware to avoid screaming interrupts
* during boot. This is the power on reset default so
* usually this should be a noop.
*/
dev->msi_cap = pci_find_capability(dev, PCI_CAP_ID_MSI);
if (dev->msi_cap)
msi_set_enable(dev, 0);
dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
if (dev->msix_cap)
msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
}
/**
* pci_enable_msi_range - configure device's MSI capability structure
* @dev: device to configure
* @minvec: minimal number of interrupts to configure
* @maxvec: maximum number of interrupts to configure
*
* This function tries to allocate a maximum possible number of interrupts in a
* range between @minvec and @maxvec. It returns a negative errno if an error
* occurs. If it succeeds, it returns the actual number of interrupts allocated
* and updates the @dev's irq member to the lowest new interrupt number;
* the other interrupt numbers allocated to this device are consecutive.
**/
int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
{
int nvec;
int rc;
if (!pci_msi_supported(dev, minvec))
return -EINVAL;
WARN_ON(!!dev->msi_enabled);
/* Check whether driver already requested MSI-X irqs */
if (dev->msix_enabled) {
dev_info(&dev->dev,
"can't enable MSI (MSI-X already enabled)\n");
return -EINVAL;
}
if (maxvec < minvec)
return -ERANGE;
nvec = pci_msi_vec_count(dev);
if (nvec < 0)
return nvec;
else if (nvec < minvec)
return -EINVAL;
else if (nvec > maxvec)
nvec = maxvec;
do {
rc = msi_capability_init(dev, nvec);
if (rc < 0) {
return rc;
} else if (rc > 0) {
if (rc < minvec)
return -ENOSPC;
nvec = rc;
}
} while (rc);
return nvec;
}
EXPORT_SYMBOL(pci_enable_msi_range);
/**
* 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)
{
int nvec = maxvec;
int rc;
if (maxvec < minvec)
return -ERANGE;
do {
rc = pci_enable_msix(dev, entries, nvec);
if (rc < 0) {
return rc;
} else if (rc > 0) {
if (rc < minvec)
return -ENOSPC;
nvec = rc;
}
} while (rc);
return nvec;
}
EXPORT_SYMBOL(pci_enable_msix_range);