linux/drivers/iommu/intr_remapping.c

835 lines
18 KiB
C
Raw Normal View History

#include <linux/interrupt.h>
#include <linux/dmar.h>
#include <linux/spinlock.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/jiffies.h>
#include <linux/hpet.h>
#include <linux/pci.h>
#include <linux/irq.h>
#include <asm/io_apic.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#include <linux/intel-iommu.h>
#include "intr_remapping.h"
#include <acpi/acpi.h>
#include <asm/pci-direct.h>
static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
static struct hpet_scope ir_hpet[MAX_HPET_TBS];
static int ir_ioapic_num, ir_hpet_num;
int intr_remapping_enabled;
static int disable_intremap;
static int disable_sourceid_checking;
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
static int no_x2apic_optout;
static __init int setup_nointremap(char *str)
{
disable_intremap = 1;
return 0;
}
early_param("nointremap", setup_nointremap);
static __init int setup_intremap(char *str)
{
if (!str)
return -EINVAL;
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
while (*str) {
if (!strncmp(str, "on", 2))
disable_intremap = 0;
else if (!strncmp(str, "off", 3))
disable_intremap = 1;
else if (!strncmp(str, "nosid", 5))
disable_sourceid_checking = 1;
else if (!strncmp(str, "no_x2apic_optout", 16))
no_x2apic_optout = 1;
str += strcspn(str, ",");
while (*str == ',')
str++;
}
return 0;
}
early_param("intremap", setup_intremap);
static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
{
struct irq_cfg *cfg = irq_get_chip_data(irq);
return cfg ? &cfg->irq_2_iommu : NULL;
}
int get_irte(int irq, struct irte *entry)
{
struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
x86, x2apic: fix lock ordering during IRQ migration Impact: fix potential deadlock on x2apic fix "hard-safe -> hard-unsafe lock order detected" with irq_2_ir_lock On x2apic enabled system: [ INFO: hard-safe -> hard-unsafe lock order detected ] 2.6.27-03151-g4480f15b #1 ------------------------------------------------------ swapper/1 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: (irq_2_ir_lock){--..}, at: [<ffffffff8038ebc0>] get_irte+0x2f/0x95 and this task is already holding: (&irq_desc_lock_class){+...}, at: [<ffffffff802649ed>] setup_irq+0x67/0x281 which would create a new lock dependency: (&irq_desc_lock_class){+...} -> (irq_2_ir_lock){--..} but this new dependency connects a hard-irq-safe lock: (&irq_desc_lock_class){+...} ... which became hard-irq-safe at: [<ffffffffffffffff>] 0xffffffffffffffff to a hard-irq-unsafe lock: (irq_2_ir_lock){--..} ... which became hard-irq-unsafe at: ... [<ffffffff802547b5>] __lock_acquire+0x571/0x706 [<ffffffff8025499f>] lock_acquire+0x55/0x71 [<ffffffff8062f2c4>] _spin_lock+0x2c/0x38 [<ffffffff8038ee50>] alloc_irte+0x8a/0x14b [<ffffffff8021f733>] setup_IO_APIC_irq+0x119/0x30e [<ffffffff8090860e>] setup_IO_APIC+0x146/0x6e5 [<ffffffff809058fc>] native_smp_prepare_cpus+0x24e/0x2e9 [<ffffffff808f982c>] kernel_init+0x5a/0x176 [<ffffffff8020c289>] child_rip+0xa/0x11 [<ffffffffffffffff>] 0xffffffffffffffff Fix this theoretical lock order issue by using spin_lock_irqsave() instead of spin_lock() Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-03-17 08:04:53 +08:00
unsigned long flags;
int index;
if (!entry || !irq_iommu)
return -1;
raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
index = irq_iommu->irte_index + irq_iommu->sub_handle;
*entry = *(irq_iommu->iommu->ir_table->base + index);
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return 0;
}
int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
{
struct ir_table *table = iommu->ir_table;
struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
u16 index, start_index;
unsigned int mask = 0;
x86, x2apic: fix lock ordering during IRQ migration Impact: fix potential deadlock on x2apic fix "hard-safe -> hard-unsafe lock order detected" with irq_2_ir_lock On x2apic enabled system: [ INFO: hard-safe -> hard-unsafe lock order detected ] 2.6.27-03151-g4480f15b #1 ------------------------------------------------------ swapper/1 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: (irq_2_ir_lock){--..}, at: [<ffffffff8038ebc0>] get_irte+0x2f/0x95 and this task is already holding: (&irq_desc_lock_class){+...}, at: [<ffffffff802649ed>] setup_irq+0x67/0x281 which would create a new lock dependency: (&irq_desc_lock_class){+...} -> (irq_2_ir_lock){--..} but this new dependency connects a hard-irq-safe lock: (&irq_desc_lock_class){+...} ... which became hard-irq-safe at: [<ffffffffffffffff>] 0xffffffffffffffff to a hard-irq-unsafe lock: (irq_2_ir_lock){--..} ... which became hard-irq-unsafe at: ... [<ffffffff802547b5>] __lock_acquire+0x571/0x706 [<ffffffff8025499f>] lock_acquire+0x55/0x71 [<ffffffff8062f2c4>] _spin_lock+0x2c/0x38 [<ffffffff8038ee50>] alloc_irte+0x8a/0x14b [<ffffffff8021f733>] setup_IO_APIC_irq+0x119/0x30e [<ffffffff8090860e>] setup_IO_APIC+0x146/0x6e5 [<ffffffff809058fc>] native_smp_prepare_cpus+0x24e/0x2e9 [<ffffffff808f982c>] kernel_init+0x5a/0x176 [<ffffffff8020c289>] child_rip+0xa/0x11 [<ffffffffffffffff>] 0xffffffffffffffff Fix this theoretical lock order issue by using spin_lock_irqsave() instead of spin_lock() Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-03-17 08:04:53 +08:00
unsigned long flags;
int i;
if (!count || !irq_iommu)
return -1;
/*
* start the IRTE search from index 0.
*/
index = start_index = 0;
if (count > 1) {
count = __roundup_pow_of_two(count);
mask = ilog2(count);
}
if (mask > ecap_max_handle_mask(iommu->ecap)) {
printk(KERN_ERR
"Requested mask %x exceeds the max invalidation handle"
" mask value %Lx\n", mask,
ecap_max_handle_mask(iommu->ecap));
return -1;
}
raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
do {
for (i = index; i < index + count; i++)
if (table->base[i].present)
break;
/* empty index found */
if (i == index + count)
break;
index = (index + count) % INTR_REMAP_TABLE_ENTRIES;
if (index == start_index) {
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
printk(KERN_ERR "can't allocate an IRTE\n");
return -1;
}
} while (1);
for (i = index; i < index + count; i++)
table->base[i].present = 1;
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = 0;
irq_iommu->irte_mask = mask;
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return index;
}
static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
{
struct qi_desc desc;
desc.low = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
| QI_IEC_SELECTIVE;
desc.high = 0;
return qi_submit_sync(&desc, iommu);
}
int map_irq_to_irte_handle(int irq, u16 *sub_handle)
{
struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
x86, x2apic: fix lock ordering during IRQ migration Impact: fix potential deadlock on x2apic fix "hard-safe -> hard-unsafe lock order detected" with irq_2_ir_lock On x2apic enabled system: [ INFO: hard-safe -> hard-unsafe lock order detected ] 2.6.27-03151-g4480f15b #1 ------------------------------------------------------ swapper/1 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: (irq_2_ir_lock){--..}, at: [<ffffffff8038ebc0>] get_irte+0x2f/0x95 and this task is already holding: (&irq_desc_lock_class){+...}, at: [<ffffffff802649ed>] setup_irq+0x67/0x281 which would create a new lock dependency: (&irq_desc_lock_class){+...} -> (irq_2_ir_lock){--..} but this new dependency connects a hard-irq-safe lock: (&irq_desc_lock_class){+...} ... which became hard-irq-safe at: [<ffffffffffffffff>] 0xffffffffffffffff to a hard-irq-unsafe lock: (irq_2_ir_lock){--..} ... which became hard-irq-unsafe at: ... [<ffffffff802547b5>] __lock_acquire+0x571/0x706 [<ffffffff8025499f>] lock_acquire+0x55/0x71 [<ffffffff8062f2c4>] _spin_lock+0x2c/0x38 [<ffffffff8038ee50>] alloc_irte+0x8a/0x14b [<ffffffff8021f733>] setup_IO_APIC_irq+0x119/0x30e [<ffffffff8090860e>] setup_IO_APIC+0x146/0x6e5 [<ffffffff809058fc>] native_smp_prepare_cpus+0x24e/0x2e9 [<ffffffff808f982c>] kernel_init+0x5a/0x176 [<ffffffff8020c289>] child_rip+0xa/0x11 [<ffffffffffffffff>] 0xffffffffffffffff Fix this theoretical lock order issue by using spin_lock_irqsave() instead of spin_lock() Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-03-17 08:04:53 +08:00
unsigned long flags;
int index;
if (!irq_iommu)
return -1;
raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
*sub_handle = irq_iommu->sub_handle;
index = irq_iommu->irte_index;
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return index;
}
int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
{
struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
x86, x2apic: fix lock ordering during IRQ migration Impact: fix potential deadlock on x2apic fix "hard-safe -> hard-unsafe lock order detected" with irq_2_ir_lock On x2apic enabled system: [ INFO: hard-safe -> hard-unsafe lock order detected ] 2.6.27-03151-g4480f15b #1 ------------------------------------------------------ swapper/1 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: (irq_2_ir_lock){--..}, at: [<ffffffff8038ebc0>] get_irte+0x2f/0x95 and this task is already holding: (&irq_desc_lock_class){+...}, at: [<ffffffff802649ed>] setup_irq+0x67/0x281 which would create a new lock dependency: (&irq_desc_lock_class){+...} -> (irq_2_ir_lock){--..} but this new dependency connects a hard-irq-safe lock: (&irq_desc_lock_class){+...} ... which became hard-irq-safe at: [<ffffffffffffffff>] 0xffffffffffffffff to a hard-irq-unsafe lock: (irq_2_ir_lock){--..} ... which became hard-irq-unsafe at: ... [<ffffffff802547b5>] __lock_acquire+0x571/0x706 [<ffffffff8025499f>] lock_acquire+0x55/0x71 [<ffffffff8062f2c4>] _spin_lock+0x2c/0x38 [<ffffffff8038ee50>] alloc_irte+0x8a/0x14b [<ffffffff8021f733>] setup_IO_APIC_irq+0x119/0x30e [<ffffffff8090860e>] setup_IO_APIC+0x146/0x6e5 [<ffffffff809058fc>] native_smp_prepare_cpus+0x24e/0x2e9 [<ffffffff808f982c>] kernel_init+0x5a/0x176 [<ffffffff8020c289>] child_rip+0xa/0x11 [<ffffffffffffffff>] 0xffffffffffffffff Fix this theoretical lock order issue by using spin_lock_irqsave() instead of spin_lock() Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-03-17 08:04:53 +08:00
unsigned long flags;
if (!irq_iommu)
return -1;
raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = subhandle;
irq_iommu->irte_mask = 0;
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return 0;
}
int modify_irte(int irq, struct irte *irte_modified)
{
struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
struct intel_iommu *iommu;
x86, x2apic: fix lock ordering during IRQ migration Impact: fix potential deadlock on x2apic fix "hard-safe -> hard-unsafe lock order detected" with irq_2_ir_lock On x2apic enabled system: [ INFO: hard-safe -> hard-unsafe lock order detected ] 2.6.27-03151-g4480f15b #1 ------------------------------------------------------ swapper/1 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: (irq_2_ir_lock){--..}, at: [<ffffffff8038ebc0>] get_irte+0x2f/0x95 and this task is already holding: (&irq_desc_lock_class){+...}, at: [<ffffffff802649ed>] setup_irq+0x67/0x281 which would create a new lock dependency: (&irq_desc_lock_class){+...} -> (irq_2_ir_lock){--..} but this new dependency connects a hard-irq-safe lock: (&irq_desc_lock_class){+...} ... which became hard-irq-safe at: [<ffffffffffffffff>] 0xffffffffffffffff to a hard-irq-unsafe lock: (irq_2_ir_lock){--..} ... which became hard-irq-unsafe at: ... [<ffffffff802547b5>] __lock_acquire+0x571/0x706 [<ffffffff8025499f>] lock_acquire+0x55/0x71 [<ffffffff8062f2c4>] _spin_lock+0x2c/0x38 [<ffffffff8038ee50>] alloc_irte+0x8a/0x14b [<ffffffff8021f733>] setup_IO_APIC_irq+0x119/0x30e [<ffffffff8090860e>] setup_IO_APIC+0x146/0x6e5 [<ffffffff809058fc>] native_smp_prepare_cpus+0x24e/0x2e9 [<ffffffff808f982c>] kernel_init+0x5a/0x176 [<ffffffff8020c289>] child_rip+0xa/0x11 [<ffffffffffffffff>] 0xffffffffffffffff Fix this theoretical lock order issue by using spin_lock_irqsave() instead of spin_lock() Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-03-17 08:04:53 +08:00
unsigned long flags;
struct irte *irte;
int rc, index;
if (!irq_iommu)
return -1;
raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
iommu = irq_iommu->iommu;
index = irq_iommu->irte_index + irq_iommu->sub_handle;
irte = &iommu->ir_table->base[index];
set_64bit(&irte->low, irte_modified->low);
set_64bit(&irte->high, irte_modified->high);
__iommu_flush_cache(iommu, irte, sizeof(*irte));
rc = qi_flush_iec(iommu, index, 0);
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return rc;
}
struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
{
int i;
for (i = 0; i < MAX_HPET_TBS; i++)
if (ir_hpet[i].id == hpet_id)
return ir_hpet[i].iommu;
return NULL;
}
x64, x2apic/intr-remap: IO-APIC support for interrupt-remapping IO-APIC support in the presence of interrupt-remapping infrastructure. IO-APIC RTE will be programmed with interrupt-remapping table entry(IRTE) index and the IRTE will contain information about the vector, cpu destination, trigger mode etc, which traditionally was present in the IO-APIC RTE. Introduce a new irq_chip for cleaner irq migration (in the process context as opposed to the current irq migration in the context of an interrupt. interrupt-remapping infrastructure will help us achieve this cleanly). For edge triggered, irq migration is a simple atomic update(of vector and cpu destination) of IRTE and flush the hardware cache. For level triggered, we need to modify the io-apic RTE aswell with the update vector information, along with modifying IRTE with vector and cpu destination. So irq migration for level triggered is little bit more complex compared to edge triggered migration. But the good news is, we use the same algorithm for level triggered migration as we have today, only difference being, we now initiate the irq migration from process context instead of the interrupt context. In future, when we do a directed EOI (combined with cpu EOI broadcast suppression) to the IO-APIC, level triggered irq migration will also be as simple as edge triggered migration and we can do the irq migration with a simple atomic update to IO-APIC RTE. TBD: some tests/changes needed in the presence of fixup_irqs() for level triggered irq migration. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: akpm@linux-foundation.org Cc: arjan@linux.intel.com Cc: andi@firstfloor.org Cc: ebiederm@xmission.com Cc: jbarnes@virtuousgeek.org Cc: steiner@sgi.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-11 02:16:56 +08:00
struct intel_iommu *map_ioapic_to_ir(int apic)
{
int i;
for (i = 0; i < MAX_IO_APICS; i++)
if (ir_ioapic[i].id == apic)
return ir_ioapic[i].iommu;
return NULL;
}
struct intel_iommu *map_dev_to_ir(struct pci_dev *dev)
{
struct dmar_drhd_unit *drhd;
drhd = dmar_find_matched_drhd_unit(dev);
if (!drhd)
return NULL;
return drhd->iommu;
}
static int clear_entries(struct irq_2_iommu *irq_iommu)
{
struct irte *start, *entry, *end;
struct intel_iommu *iommu;
int index;
if (irq_iommu->sub_handle)
return 0;
iommu = irq_iommu->iommu;
index = irq_iommu->irte_index + irq_iommu->sub_handle;
start = iommu->ir_table->base + index;
end = start + (1 << irq_iommu->irte_mask);
for (entry = start; entry < end; entry++) {
set_64bit(&entry->low, 0);
set_64bit(&entry->high, 0);
}
return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
}
int free_irte(int irq)
{
struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
x86, x2apic: fix lock ordering during IRQ migration Impact: fix potential deadlock on x2apic fix "hard-safe -> hard-unsafe lock order detected" with irq_2_ir_lock On x2apic enabled system: [ INFO: hard-safe -> hard-unsafe lock order detected ] 2.6.27-03151-g4480f15b #1 ------------------------------------------------------ swapper/1 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: (irq_2_ir_lock){--..}, at: [<ffffffff8038ebc0>] get_irte+0x2f/0x95 and this task is already holding: (&irq_desc_lock_class){+...}, at: [<ffffffff802649ed>] setup_irq+0x67/0x281 which would create a new lock dependency: (&irq_desc_lock_class){+...} -> (irq_2_ir_lock){--..} but this new dependency connects a hard-irq-safe lock: (&irq_desc_lock_class){+...} ... which became hard-irq-safe at: [<ffffffffffffffff>] 0xffffffffffffffff to a hard-irq-unsafe lock: (irq_2_ir_lock){--..} ... which became hard-irq-unsafe at: ... [<ffffffff802547b5>] __lock_acquire+0x571/0x706 [<ffffffff8025499f>] lock_acquire+0x55/0x71 [<ffffffff8062f2c4>] _spin_lock+0x2c/0x38 [<ffffffff8038ee50>] alloc_irte+0x8a/0x14b [<ffffffff8021f733>] setup_IO_APIC_irq+0x119/0x30e [<ffffffff8090860e>] setup_IO_APIC+0x146/0x6e5 [<ffffffff809058fc>] native_smp_prepare_cpus+0x24e/0x2e9 [<ffffffff808f982c>] kernel_init+0x5a/0x176 [<ffffffff8020c289>] child_rip+0xa/0x11 [<ffffffffffffffff>] 0xffffffffffffffff Fix this theoretical lock order issue by using spin_lock_irqsave() instead of spin_lock() Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2009-03-17 08:04:53 +08:00
unsigned long flags;
int rc;
if (!irq_iommu)
return -1;
raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
rc = clear_entries(irq_iommu);
irq_iommu->iommu = NULL;
irq_iommu->irte_index = 0;
irq_iommu->sub_handle = 0;
irq_iommu->irte_mask = 0;
raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return rc;
}
/*
* source validation type
*/
#define SVT_NO_VERIFY 0x0 /* no verification is required */
#define SVT_VERIFY_SID_SQ 0x1 /* verify using SID and SQ fields */
#define SVT_VERIFY_BUS 0x2 /* verify bus of request-id */
/*
* source-id qualifier
*/
#define SQ_ALL_16 0x0 /* verify all 16 bits of request-id */
#define SQ_13_IGNORE_1 0x1 /* verify most significant 13 bits, ignore
* the third least significant bit
*/
#define SQ_13_IGNORE_2 0x2 /* verify most significant 13 bits, ignore
* the second and third least significant bits
*/
#define SQ_13_IGNORE_3 0x3 /* verify most significant 13 bits, ignore
* the least three significant bits
*/
/*
* set SVT, SQ and SID fields of irte to verify
* source ids of interrupt requests
*/
static void set_irte_sid(struct irte *irte, unsigned int svt,
unsigned int sq, unsigned int sid)
{
if (disable_sourceid_checking)
svt = SVT_NO_VERIFY;
irte->svt = svt;
irte->sq = sq;
irte->sid = sid;
}
int set_ioapic_sid(struct irte *irte, int apic)
{
int i;
u16 sid = 0;
if (!irte)
return -1;
for (i = 0; i < MAX_IO_APICS; i++) {
if (ir_ioapic[i].id == apic) {
sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
break;
}
}
if (sid == 0) {
pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic);
return -1;
}
set_irte_sid(irte, 1, 0, sid);
return 0;
}
int set_hpet_sid(struct irte *irte, u8 id)
{
int i;
u16 sid = 0;
if (!irte)
return -1;
for (i = 0; i < MAX_HPET_TBS; i++) {
if (ir_hpet[i].id == id) {
sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
break;
}
}
if (sid == 0) {
pr_warning("Failed to set source-id of HPET block (%d)\n", id);
return -1;
}
/*
* Should really use SQ_ALL_16. Some platforms are broken.
* While we figure out the right quirks for these broken platforms, use
* SQ_13_IGNORE_3 for now.
*/
set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_13_IGNORE_3, sid);
return 0;
}
int set_msi_sid(struct irte *irte, struct pci_dev *dev)
{
struct pci_dev *bridge;
if (!irte || !dev)
return -1;
/* PCIe device or Root Complex integrated PCI device */
if (pci_is_pcie(dev) || !dev->bus->parent) {
set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
(dev->bus->number << 8) | dev->devfn);
return 0;
}
bridge = pci_find_upstream_pcie_bridge(dev);
if (bridge) {
if (pci_is_pcie(bridge))/* this is a PCIe-to-PCI/PCIX bridge */
set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16,
(bridge->bus->number << 8) | dev->bus->number);
else /* this is a legacy PCI bridge */
set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
(bridge->bus->number << 8) | bridge->devfn);
}
return 0;
}
static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
{
u64 addr;
u32 sts;
unsigned long flags;
addr = virt_to_phys((void *)iommu->ir_table->base);
raw_spin_lock_irqsave(&iommu->register_lock, flags);
dmar_writeq(iommu->reg + DMAR_IRTA_REG,
(addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
/* Set interrupt-remapping table pointer */
iommu->gcmd |= DMA_GCMD_SIRTP;
writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
readl, (sts & DMA_GSTS_IRTPS), sts);
raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
/*
* global invalidation of interrupt entry cache before enabling
* interrupt-remapping.
*/
qi_global_iec(iommu);
raw_spin_lock_irqsave(&iommu->register_lock, flags);
/* Enable interrupt-remapping */
iommu->gcmd |= DMA_GCMD_IRE;
writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
readl, (sts & DMA_GSTS_IRES), sts);
raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}
static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
{
struct ir_table *ir_table;
struct page *pages;
ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
GFP_ATOMIC);
if (!iommu->ir_table)
return -ENOMEM;
pages = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
INTR_REMAP_PAGE_ORDER);
if (!pages) {
printk(KERN_ERR "failed to allocate pages of order %d\n",
INTR_REMAP_PAGE_ORDER);
kfree(iommu->ir_table);
return -ENOMEM;
}
ir_table->base = page_address(pages);
iommu_set_intr_remapping(iommu, mode);
return 0;
}
/*
* Disable Interrupt Remapping.
*/
static void iommu_disable_intr_remapping(struct intel_iommu *iommu)
{
unsigned long flags;
u32 sts;
if (!ecap_ir_support(iommu->ecap))
return;
/*
* global invalidation of interrupt entry cache before disabling
* interrupt-remapping.
*/
qi_global_iec(iommu);
raw_spin_lock_irqsave(&iommu->register_lock, flags);
sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
if (!(sts & DMA_GSTS_IRES))
goto end;
iommu->gcmd &= ~DMA_GCMD_IRE;
writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
readl, !(sts & DMA_GSTS_IRES), sts);
end:
raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
static int __init dmar_x2apic_optout(void)
{
struct acpi_table_dmar *dmar;
dmar = (struct acpi_table_dmar *)dmar_tbl;
if (!dmar || no_x2apic_optout)
return 0;
return dmar->flags & DMAR_X2APIC_OPT_OUT;
}
int __init intr_remapping_supported(void)
{
struct dmar_drhd_unit *drhd;
if (disable_intremap)
return 0;
if (!dmar_ir_support())
return 0;
for_each_drhd_unit(drhd) {
struct intel_iommu *iommu = drhd->iommu;
if (!ecap_ir_support(iommu->ecap))
return 0;
}
return 1;
}
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
int __init enable_intr_remapping(void)
{
struct dmar_drhd_unit *drhd;
int setup = 0;
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
int eim = 0;
if (parse_ioapics_under_ir() != 1) {
printk(KERN_INFO "Not enable interrupt remapping\n");
return -1;
}
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
if (x2apic_supported()) {
eim = !dmar_x2apic_optout();
WARN(!eim, KERN_WARNING
"Your BIOS is broken and requested that x2apic be disabled\n"
"This will leave your machine vulnerable to irq-injection attacks\n"
"Use 'intremap=no_x2apic_optout' to override BIOS request\n");
}
for_each_drhd_unit(drhd) {
struct intel_iommu *iommu = drhd->iommu;
/*
* If the queued invalidation is already initialized,
* shouldn't disable it.
*/
if (iommu->qi)
continue;
/*
* Clear previous faults.
*/
dmar_fault(-1, iommu);
/*
* Disable intr remapping and queued invalidation, if already
* enabled prior to OS handover.
*/
iommu_disable_intr_remapping(iommu);
dmar_disable_qi(iommu);
}
/*
* check for the Interrupt-remapping support
*/
for_each_drhd_unit(drhd) {
struct intel_iommu *iommu = drhd->iommu;
if (!ecap_ir_support(iommu->ecap))
continue;
if (eim && !ecap_eim_support(iommu->ecap)) {
printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, "
" ecap %Lx\n", drhd->reg_base_addr, iommu->ecap);
return -1;
}
}
/*
* Enable queued invalidation for all the DRHD's.
*/
for_each_drhd_unit(drhd) {
int ret;
struct intel_iommu *iommu = drhd->iommu;
ret = dmar_enable_qi(iommu);
if (ret) {
printk(KERN_ERR "DRHD %Lx: failed to enable queued, "
" invalidation, ecap %Lx, ret %d\n",
drhd->reg_base_addr, iommu->ecap, ret);
return -1;
}
}
/*
* Setup Interrupt-remapping for all the DRHD's now.
*/
for_each_drhd_unit(drhd) {
struct intel_iommu *iommu = drhd->iommu;
if (!ecap_ir_support(iommu->ecap))
continue;
if (setup_intr_remapping(iommu, eim))
goto error;
setup = 1;
}
if (!setup)
goto error;
intr_remapping_enabled = 1;
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic");
x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song <youquan.song@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-08-24 08:05:18 +08:00
return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;
error:
/*
* handle error condition gracefully here!
*/
return -1;
}
static void ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
struct intel_iommu *iommu)
{
struct acpi_dmar_pci_path *path;
u8 bus;
int count;
bus = scope->bus;
path = (struct acpi_dmar_pci_path *)(scope + 1);
count = (scope->length - sizeof(struct acpi_dmar_device_scope))
/ sizeof(struct acpi_dmar_pci_path);
while (--count > 0) {
/*
* Access PCI directly due to the PCI
* subsystem isn't initialized yet.
*/
bus = read_pci_config_byte(bus, path->dev, path->fn,
PCI_SECONDARY_BUS);
path++;
}
ir_hpet[ir_hpet_num].bus = bus;
ir_hpet[ir_hpet_num].devfn = PCI_DEVFN(path->dev, path->fn);
ir_hpet[ir_hpet_num].iommu = iommu;
ir_hpet[ir_hpet_num].id = scope->enumeration_id;
ir_hpet_num++;
}
static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
struct intel_iommu *iommu)
{
struct acpi_dmar_pci_path *path;
u8 bus;
int count;
bus = scope->bus;
path = (struct acpi_dmar_pci_path *)(scope + 1);
count = (scope->length - sizeof(struct acpi_dmar_device_scope))
/ sizeof(struct acpi_dmar_pci_path);
while (--count > 0) {
/*
* Access PCI directly due to the PCI
* subsystem isn't initialized yet.
*/
bus = read_pci_config_byte(bus, path->dev, path->fn,
PCI_SECONDARY_BUS);
path++;
}
ir_ioapic[ir_ioapic_num].bus = bus;
ir_ioapic[ir_ioapic_num].devfn = PCI_DEVFN(path->dev, path->fn);
ir_ioapic[ir_ioapic_num].iommu = iommu;
ir_ioapic[ir_ioapic_num].id = scope->enumeration_id;
ir_ioapic_num++;
}
static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
struct intel_iommu *iommu)
{
struct acpi_dmar_hardware_unit *drhd;
struct acpi_dmar_device_scope *scope;
void *start, *end;
drhd = (struct acpi_dmar_hardware_unit *)header;
start = (void *)(drhd + 1);
end = ((void *)drhd) + header->length;
while (start < end) {
scope = start;
if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
if (ir_ioapic_num == MAX_IO_APICS) {
printk(KERN_WARNING "Exceeded Max IO APICS\n");
return -1;
}
printk(KERN_INFO "IOAPIC id %d under DRHD base "
" 0x%Lx IOMMU %d\n", scope->enumeration_id,
drhd->address, iommu->seq_id);
ir_parse_one_ioapic_scope(scope, iommu);
} else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET) {
if (ir_hpet_num == MAX_HPET_TBS) {
printk(KERN_WARNING "Exceeded Max HPET blocks\n");
return -1;
}
printk(KERN_INFO "HPET id %d under DRHD base"
" 0x%Lx\n", scope->enumeration_id,
drhd->address);
ir_parse_one_hpet_scope(scope, iommu);
}
start += scope->length;
}
return 0;
}
/*
* Finds the assocaition between IOAPIC's and its Interrupt-remapping
* hardware unit.
*/
int __init parse_ioapics_under_ir(void)
{
struct dmar_drhd_unit *drhd;
int ir_supported = 0;
for_each_drhd_unit(drhd) {
struct intel_iommu *iommu = drhd->iommu;
if (ecap_ir_support(iommu->ecap)) {
if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu))
return -1;
ir_supported = 1;
}
}
if (ir_supported && ir_ioapic_num != nr_ioapics) {
printk(KERN_WARNING
"Not all IO-APIC's listed under remapping hardware\n");
return -1;
}
return ir_supported;
}
int __init ir_dev_scope_init(void)
{
if (!intr_remapping_enabled)
return 0;
return dmar_dev_scope_init();
}
rootfs_initcall(ir_dev_scope_init);
void disable_intr_remapping(void)
{
struct dmar_drhd_unit *drhd;
struct intel_iommu *iommu = NULL;
/*
* Disable Interrupt-remapping for all the DRHD's now.
*/
for_each_iommu(iommu, drhd) {
if (!ecap_ir_support(iommu->ecap))
continue;
iommu_disable_intr_remapping(iommu);
}
}
int reenable_intr_remapping(int eim)
{
struct dmar_drhd_unit *drhd;
int setup = 0;
struct intel_iommu *iommu = NULL;
for_each_iommu(iommu, drhd)
if (iommu->qi)
dmar_reenable_qi(iommu);
/*
* Setup Interrupt-remapping for all the DRHD's now.
*/
for_each_iommu(iommu, drhd) {
if (!ecap_ir_support(iommu->ecap))
continue;
/* Set up interrupt remapping for iommu.*/
iommu_set_intr_remapping(iommu, eim);
setup = 1;
}
if (!setup)
goto error;
return 0;
error:
/*
* handle error condition gracefully here!
*/
return -1;
}