[GIT PULL] core/iommu changes for v3.2
From: Ingo Molnar
Date: Wed Oct 26 2011 - 09:17:00 EST
Linus,
Please pull the latest core-iommu-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-iommu-for-linus
Thanks,
Ingo
------------------>
Suresh Siddha (11):
x86, x2apic: Enable the bios request for x2apic optout
intr_remap: Call dmar_dev_scope_init() explicitly
iommu: Move IOMMU specific code to intel-iommu.c
iommu: No need to set dmar_disabled in check_zero_address()
iommu: Cleanup ifdefs in detect_intel_iommu()
x86, msi, intr-remap: Use the ioapic set affinity routine
x86, ioapic: Define irq_remap_modify_chip_defaults()
iommu: Rename the DMAR and INTR_REMAP config options
x86, kdump, ioapic: Reset remote-IRR in clear_IO_APIC
x86, ioapic: Restore the mask bit correctly in eoi_ioapic_irq()
x86, ioapic: Consolidate the explicit EOI code
Documentation/kernel-parameters.txt | 3 +-
arch/ia64/configs/generic_defconfig | 2 +-
arch/ia64/dig/Makefile | 2 +-
arch/ia64/include/asm/device.h | 2 +-
arch/ia64/include/asm/iommu.h | 6 +-
arch/ia64/include/asm/pci.h | 2 +-
arch/ia64/kernel/Makefile | 2 +-
arch/ia64/kernel/acpi.c | 4 +-
arch/ia64/kernel/msi_ia64.c | 4 +-
arch/ia64/kernel/pci-dma.c | 2 +-
arch/x86/Kconfig | 6 +-
arch/x86/configs/x86_64_defconfig | 4 +-
arch/x86/include/asm/device.h | 2 +-
arch/x86/include/asm/hw_irq.h | 2 +-
arch/x86/include/asm/irq_remapping.h | 6 +-
arch/x86/kernel/apic/apic.c | 33 ++--
arch/x86/kernel/apic/io_apic.c | 284 ++++++++++++++++-----------------
drivers/char/agp/intel-gtt.c | 4 +-
drivers/iommu/Kconfig | 25 ++--
drivers/iommu/Makefile | 5 +-
drivers/iommu/dmar.c | 198 +++---------------------
drivers/iommu/intel-iommu.c | 167 +++++++++++++++++++--
drivers/iommu/intr_remapping.c | 53 ++++++-
drivers/pci/quirks.c | 2 +-
include/linux/dma_remapping.h | 10 +-
include/linux/dmar.h | 43 ++++-
include/linux/intel-iommu.h | 6 +-
27 files changed, 474 insertions(+), 405 deletions(-)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 854ed5ca..1386556 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1014,10 +1014,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
has the capability. With this option, super page will
not be supported.
intremap= [X86-64, Intel-IOMMU]
- Format: { on (default) | off | nosid }
on enable Interrupt Remapping (default)
off disable Interrupt Remapping
nosid disable Source ID checking
+ no_x2apic_optout
+ BIOS x2APIC opt-out request will be ignored
inttest= [IA-64]
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index 0e5cd14..43ab1cd 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -234,4 +234,4 @@ CONFIG_CRYPTO_MD5=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
CONFIG_CRC_T10DIF=y
CONFIG_MISC_DEVICES=y
-CONFIG_DMAR=y
+CONFIG_INTEL_IOMMU=y
diff --git a/arch/ia64/dig/Makefile b/arch/ia64/dig/Makefile
index 2f7cadd..ae16ec4 100644
--- a/arch/ia64/dig/Makefile
+++ b/arch/ia64/dig/Makefile
@@ -6,7 +6,7 @@
#
obj-y := setup.o
-ifeq ($(CONFIG_DMAR), y)
+ifeq ($(CONFIG_INTEL_IOMMU), y)
obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o
else
obj-$(CONFIG_IA64_GENERIC) += machvec.o
diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h
index d66d446..d05e78f 100644
--- a/arch/ia64/include/asm/device.h
+++ b/arch/ia64/include/asm/device.h
@@ -10,7 +10,7 @@ struct dev_archdata {
#ifdef CONFIG_ACPI
void *acpi_handle;
#endif
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
void *iommu; /* hook for IOMMU specific extension */
#endif
};
diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h
index 745e095..105c93b 100644
--- a/arch/ia64/include/asm/iommu.h
+++ b/arch/ia64/include/asm/iommu.h
@@ -7,12 +7,14 @@
extern void pci_iommu_shutdown(void);
extern void no_iommu_init(void);
+#ifdef CONFIG_INTEL_IOMMU
extern int force_iommu, no_iommu;
-extern int iommu_detected;
-#ifdef CONFIG_DMAR
extern int iommu_pass_through;
+extern int iommu_detected;
#else
#define iommu_pass_through (0)
+#define no_iommu (1)
+#define iommu_detected (0)
#endif
extern void iommu_dma_init(void);
extern void machvec_init(const char *name);
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index 73b5f78..127dd7b 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -139,7 +139,7 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
return channel ? isa_irq_to_vector(15) : isa_irq_to_vector(14);
}
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
extern void pci_iommu_alloc(void);
#endif
#endif /* _ASM_IA64_PCI_H */
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 395c2f2..d959c84 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -43,7 +43,7 @@ obj-$(CONFIG_IA64_ESI) += esi.o
ifneq ($(CONFIG_IA64_ESI),)
obj-y += esi_stub.o # must be in kernel proper
endif
-obj-$(CONFIG_DMAR) += pci-dma.o
+obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o
obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
obj-$(CONFIG_BINFMT_ELF) += elfcore.o
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 3be485a..bfb4d01 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -88,7 +88,7 @@ acpi_get_sysname(void)
struct acpi_table_rsdp *rsdp;
struct acpi_table_xsdt *xsdt;
struct acpi_table_header *hdr;
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
u64 i, nentries;
#endif
@@ -125,7 +125,7 @@ acpi_get_sysname(void)
return "xen";
}
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
/* Look for Intel IOMMU */
nentries = (hdr->length - sizeof(*hdr)) /
sizeof(xsdt->table_offset_entry[0]);
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 009df54..94e0db7 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -131,7 +131,7 @@ void arch_teardown_msi_irq(unsigned int irq)
return ia64_teardown_msi_irq(irq);
}
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
#ifdef CONFIG_SMP
static int dmar_msi_set_affinity(struct irq_data *data,
const struct cpumask *mask, bool force)
@@ -210,5 +210,5 @@ int arch_setup_dmar_msi(unsigned int irq)
"edge");
return 0;
}
-#endif /* CONFIG_DMAR */
+#endif /* CONFIG_INTEL_IOMMU */
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index f6b1ff0..c16162c 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -14,7 +14,7 @@
#include <asm/system.h>
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
#include <linux/kernel.h>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a47bb2..b8cd544 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -130,7 +130,7 @@ config SBUS
bool
config NEED_DMA_MAP_STATE
- def_bool (X86_64 || DMAR || DMA_API_DEBUG)
+ def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG)
config NEED_SG_DMA_LENGTH
def_bool y
@@ -220,7 +220,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
config HAVE_INTEL_TXT
def_bool y
- depends on EXPERIMENTAL && DMAR && ACPI
+ depends on EXPERIMENTAL && INTEL_IOMMU && ACPI
config X86_32_SMP
def_bool y
@@ -287,7 +287,7 @@ config SMP
config X86_X2APIC
bool "Support x2apic"
- depends on X86_LOCAL_APIC && X86_64 && INTR_REMAP
+ depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
---help---
This enables x2apic support on CPUs that have this feature.
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 22a0dc8..058a35b 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -67,8 +67,8 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
CONFIG_CPU_FREQ_GOV_ONDEMAND=y
CONFIG_X86_ACPI_CPUFREQ=y
CONFIG_PCI_MMCONFIG=y
-CONFIG_DMAR=y
-# CONFIG_DMAR_DEFAULT_ON is not set
+CONFIG_INTEL_IOMMU=y
+# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
CONFIG_PCIEPORTBUS=y
CONFIG_PCCARD=y
CONFIG_YENTA=y
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 029f230..63a2a03 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,7 +8,7 @@ struct dev_archdata {
#ifdef CONFIG_X86_64
struct dma_map_ops *dma_ops;
#endif
-#if defined(CONFIG_DMAR) || defined(CONFIG_AMD_IOMMU)
+#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU)
void *iommu; /* hook for IOMMU specific extension */
#endif
};
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 0919905..eb92a6e 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -119,7 +119,7 @@ struct irq_cfg {
cpumask_var_t old_domain;
u8 vector;
u8 move_in_progress : 1;
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
struct irq_2_iommu irq_2_iommu;
#endif
};
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 1c23360..47d9993 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -3,7 +3,8 @@
#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
+static void irq_remap_modify_chip_defaults(struct irq_chip *chip);
static inline void prepare_irte(struct irte *irte, int vector,
unsigned int dest)
{
@@ -36,6 +37,9 @@ static inline bool irq_remapped(struct irq_cfg *cfg)
{
return false;
}
+static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+}
#endif
#endif /* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 52fa563..a2fd72e 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1437,27 +1437,21 @@ void enable_x2apic(void)
int __init enable_IR(void)
{
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
if (!intr_remapping_supported()) {
pr_debug("intr-remapping not supported\n");
- return 0;
+ return -1;
}
if (!x2apic_preenabled && skip_ioapic_setup) {
pr_info("Skipped enabling intr-remap because of skipping "
"io-apic setup\n");
- return 0;
+ return -1;
}
- if (enable_intr_remapping(x2apic_supported()))
- return 0;
-
- pr_info("Enabled Interrupt-remapping\n");
-
- return 1;
-
+ return enable_intr_remapping();
#endif
- return 0;
+ return -1;
}
void __init enable_IR_x2apic(void)
@@ -1481,11 +1475,11 @@ void __init enable_IR_x2apic(void)
mask_ioapic_entries();
if (dmar_table_init_ret)
- ret = 0;
+ ret = -1;
else
ret = enable_IR();
- if (!ret) {
+ if (ret < 0) {
/* IR is required if there is APIC ID > 255 even when running
* under KVM
*/
@@ -1499,6 +1493,9 @@ void __init enable_IR_x2apic(void)
x2apic_force_phys();
}
+ if (ret == IRQ_REMAP_XAPIC_MODE)
+ goto nox2apic;
+
x2apic_enabled = 1;
if (x2apic_supported() && !x2apic_mode) {
@@ -1508,19 +1505,21 @@ void __init enable_IR_x2apic(void)
}
nox2apic:
- if (!ret) /* IR enabling failed */
+ if (ret < 0) /* IR enabling failed */
restore_ioapic_entries();
legacy_pic->restore_mask();
local_irq_restore(flags);
out:
- if (x2apic_enabled)
+ if (x2apic_enabled || !x2apic_supported())
return;
if (x2apic_preenabled)
panic("x2apic: enabled by BIOS but kernel init failed.");
- else if (cpu_has_x2apic)
- pr_info("Not enabling x2apic, Intr-remapping init failed.\n");
+ else if (ret == IRQ_REMAP_XAPIC_MODE)
+ pr_info("x2apic not enabled, IRQ remapping is in xapic mode\n");
+ else if (ret < 0)
+ pr_info("x2apic not enabled, IRQ remapping init failed\n");
}
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8eb863e..229e19f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -394,13 +394,21 @@ union entry_union {
struct IO_APIC_route_entry entry;
};
+static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin)
+{
+ union entry_union eu;
+
+ eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
+ eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
+ return eu.entry;
+}
+
static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
{
union entry_union eu;
unsigned long flags;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
- eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
+ eu.entry = __ioapic_read_entry(apic, pin);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return eu.entry;
}
@@ -529,18 +537,6 @@ static void io_apic_modify_irq(struct irq_cfg *cfg,
__io_apic_modify_irq(entry, mask_and, mask_or, final);
}
-static void __mask_and_edge_IO_APIC_irq(struct irq_pin_list *entry)
-{
- __io_apic_modify_irq(entry, ~IO_APIC_REDIR_LEVEL_TRIGGER,
- IO_APIC_REDIR_MASKED, NULL);
-}
-
-static void __unmask_and_level_IO_APIC_irq(struct irq_pin_list *entry)
-{
- __io_apic_modify_irq(entry, ~IO_APIC_REDIR_MASKED,
- IO_APIC_REDIR_LEVEL_TRIGGER, NULL);
-}
-
static void io_apic_sync(struct irq_pin_list *entry)
{
/*
@@ -585,6 +581,66 @@ static void unmask_ioapic_irq(struct irq_data *data)
unmask_ioapic(data->chip_data);
}
+/*
+ * IO-APIC versions below 0x20 don't support EOI register.
+ * For the record, here is the information about various versions:
+ * 0Xh 82489DX
+ * 1Xh I/OAPIC or I/O(x)APIC which are not PCI 2.2 Compliant
+ * 2Xh I/O(x)APIC which is PCI 2.2 Compliant
+ * 30h-FFh Reserved
+ *
+ * Some of the Intel ICH Specs (ICH2 to ICH5) documents the io-apic
+ * version as 0x2. This is an error with documentation and these ICH chips
+ * use io-apic's of version 0x20.
+ *
+ * For IO-APIC's with EOI register, we use that to do an explicit EOI.
+ * Otherwise, we simulate the EOI message manually by changing the trigger
+ * mode to edge and then back to level, with RTE being masked during this.
+ */
+static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg)
+{
+ if (mpc_ioapic_ver(apic) >= 0x20) {
+ /*
+ * Intr-remapping uses pin number as the virtual vector
+ * in the RTE. Actual vector is programmed in
+ * intr-remapping table entry. Hence for the io-apic
+ * EOI we use the pin number.
+ */
+ if (cfg && irq_remapped(cfg))
+ io_apic_eoi(apic, pin);
+ else
+ io_apic_eoi(apic, vector);
+ } else {
+ struct IO_APIC_route_entry entry, entry1;
+
+ entry = entry1 = __ioapic_read_entry(apic, pin);
+
+ /*
+ * Mask the entry and change the trigger mode to edge.
+ */
+ entry1.mask = 1;
+ entry1.trigger = IOAPIC_EDGE;
+
+ __ioapic_write_entry(apic, pin, entry1);
+
+ /*
+ * Restore the previous level triggered entry.
+ */
+ __ioapic_write_entry(apic, pin, entry);
+ }
+}
+
+static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+{
+ struct irq_pin_list *entry;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ for_each_irq_pin(entry, cfg->irq_2_pin)
+ __eoi_ioapic_pin(entry->apic, entry->pin, cfg->vector, cfg);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
{
struct IO_APIC_route_entry entry;
@@ -593,10 +649,44 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
entry = ioapic_read_entry(apic, pin);
if (entry.delivery_mode == dest_SMI)
return;
+
+ /*
+ * Make sure the entry is masked and re-read the contents to check
+ * if it is a level triggered pin and if the remote-IRR is set.
+ */
+ if (!entry.mask) {
+ entry.mask = 1;
+ ioapic_write_entry(apic, pin, entry);
+ entry = ioapic_read_entry(apic, pin);
+ }
+
+ if (entry.irr) {
+ unsigned long flags;
+
+ /*
+ * Make sure the trigger mode is set to level. Explicit EOI
+ * doesn't clear the remote-IRR if the trigger mode is not
+ * set to level.
+ */
+ if (!entry.trigger) {
+ entry.trigger = IOAPIC_LEVEL;
+ ioapic_write_entry(apic, pin, entry);
+ }
+
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ __eoi_ioapic_pin(apic, pin, entry.vector, NULL);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+ }
+
/*
- * Disable it in the IO-APIC irq-routing table:
+ * Clear the rest of the bits in the IO-APIC RTE except for the mask
+ * bit.
*/
ioapic_mask_entry(apic, pin);
+ entry = ioapic_read_entry(apic, pin);
+ if (entry.irr)
+ printk(KERN_ERR "Unable to reset IRR for apic: %d, pin :%d\n",
+ mpc_ioapic_id(apic), pin);
}
static void clear_IO_APIC (void)
@@ -1202,7 +1292,6 @@ void __setup_vector_irq(int cpu)
}
static struct irq_chip ioapic_chip;
-static struct irq_chip ir_ioapic_chip;
#ifdef CONFIG_X86_32
static inline int IO_APIC_irq_trigger(int irq)
@@ -1246,7 +1335,7 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
if (irq_remapped(cfg)) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- chip = &ir_ioapic_chip;
+ irq_remap_modify_chip_defaults(chip);
fasteoi = trigger != 0;
}
@@ -2255,7 +2344,7 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
return ret;
}
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
/*
* Migrate the IO-APIC irq in the presence of intr-remapping.
@@ -2267,6 +2356,9 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
* updated vector information), by using a virtual vector (io-apic pin number).
* Real vector that is used for interrupting cpu will be coming from
* the interrupt-remapping table entry.
+ *
+ * As the migration is a simple atomic update of IRTE, the same mechanism
+ * is used to migrate MSI irq's in the presence of interrupt-remapping.
*/
static int
ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
@@ -2291,10 +2383,16 @@ ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
irte.dest_id = IRTE_DEST(dest);
/*
- * Modified the IRTE and flushes the Interrupt entry cache.
+ * Atomically updates the IRTE with the new destination, vector
+ * and flushes the interrupt entry cache.
*/
modify_irte(irq, &irte);
+ /*
+ * After this point, all the interrupts will start arriving
+ * at the new destination. So, time to cleanup the previous
+ * vector allocation.
+ */
if (cfg->move_in_progress)
send_cleanup_vector(cfg);
@@ -2407,48 +2505,6 @@ static void ack_apic_edge(struct irq_data *data)
atomic_t irq_mis_count;
-/*
- * IO-APIC versions below 0x20 don't support EOI register.
- * For the record, here is the information about various versions:
- * 0Xh 82489DX
- * 1Xh I/OAPIC or I/O(x)APIC which are not PCI 2.2 Compliant
- * 2Xh I/O(x)APIC which is PCI 2.2 Compliant
- * 30h-FFh Reserved
- *
- * Some of the Intel ICH Specs (ICH2 to ICH5) documents the io-apic
- * version as 0x2. This is an error with documentation and these ICH chips
- * use io-apic's of version 0x20.
- *
- * For IO-APIC's with EOI register, we use that to do an explicit EOI.
- * Otherwise, we simulate the EOI message manually by changing the trigger
- * mode to edge and then back to level, with RTE being masked during this.
-*/
-static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
-{
- struct irq_pin_list *entry;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&ioapic_lock, flags);
- for_each_irq_pin(entry, cfg->irq_2_pin) {
- if (mpc_ioapic_ver(entry->apic) >= 0x20) {
- /*
- * Intr-remapping uses pin number as the virtual vector
- * in the RTE. Actual vector is programmed in
- * intr-remapping table entry. Hence for the io-apic
- * EOI we use the pin number.
- */
- if (irq_remapped(cfg))
- io_apic_eoi(entry->apic, entry->pin);
- else
- io_apic_eoi(entry->apic, cfg->vector);
- } else {
- __mask_and_edge_IO_APIC_irq(entry);
- __unmask_and_level_IO_APIC_irq(entry);
- }
- }
- raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
static void ack_apic_level(struct irq_data *data)
{
struct irq_cfg *cfg = data->chip_data;
@@ -2552,7 +2608,7 @@ static void ack_apic_level(struct irq_data *data)
}
}
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
static void ir_ack_apic_edge(struct irq_data *data)
{
ack_APIC_irq();
@@ -2563,7 +2619,23 @@ static void ir_ack_apic_level(struct irq_data *data)
ack_APIC_irq();
eoi_ioapic_irq(data->irq, data->chip_data);
}
-#endif /* CONFIG_INTR_REMAP */
+
+static void ir_print_prefix(struct irq_data *data, struct seq_file *p)
+{
+ seq_printf(p, " IR-%s", data->chip->name);
+}
+
+static void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+ chip->irq_print_chip = ir_print_prefix;
+ chip->irq_ack = ir_ack_apic_edge;
+ chip->irq_eoi = ir_ack_apic_level;
+
+#ifdef CONFIG_SMP
+ chip->irq_set_affinity = ir_ioapic_set_affinity;
+#endif
+}
+#endif /* CONFIG_IRQ_REMAP */
static struct irq_chip ioapic_chip __read_mostly = {
.name = "IO-APIC",
@@ -2578,21 +2650,6 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_retrigger = ioapic_retrigger_irq,
};
-static struct irq_chip ir_ioapic_chip __read_mostly = {
- .name = "IR-IO-APIC",
- .irq_startup = startup_ioapic_irq,
- .irq_mask = mask_ioapic_irq,
- .irq_unmask = unmask_ioapic_irq,
-#ifdef CONFIG_INTR_REMAP
- .irq_ack = ir_ack_apic_edge,
- .irq_eoi = ir_ack_apic_level,
-#ifdef CONFIG_SMP
- .irq_set_affinity = ir_ioapic_set_affinity,
-#endif
-#endif
- .irq_retrigger = ioapic_retrigger_irq,
-};
-
static inline void init_IO_APIC_traps(void)
{
struct irq_cfg *cfg;
@@ -3144,45 +3201,6 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
return 0;
}
-#ifdef CONFIG_INTR_REMAP
-/*
- * Migrate the MSI irq to another cpumask. This migration is
- * done in the process context using interrupt-remapping hardware.
- */
-static int
-ir_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- struct irq_cfg *cfg = data->chip_data;
- unsigned int dest, irq = data->irq;
- struct irte irte;
-
- if (get_irte(irq, &irte))
- return -1;
-
- if (__ioapic_set_affinity(data, mask, &dest))
- return -1;
-
- irte.vector = cfg->vector;
- irte.dest_id = IRTE_DEST(dest);
-
- /*
- * atomically update the IRTE with the new destination and vector.
- */
- modify_irte(irq, &irte);
-
- /*
- * After this point, all the interrupts will start arriving
- * at the new destination. So, time to cleanup the previous
- * vector allocation.
- */
- if (cfg->move_in_progress)
- send_cleanup_vector(cfg);
-
- return 0;
-}
-
-#endif
#endif /* CONFIG_SMP */
/*
@@ -3200,19 +3218,6 @@ static struct irq_chip msi_chip = {
.irq_retrigger = ioapic_retrigger_irq,
};
-static struct irq_chip msi_ir_chip = {
- .name = "IR-PCI-MSI",
- .irq_unmask = unmask_msi_irq,
- .irq_mask = mask_msi_irq,
-#ifdef CONFIG_INTR_REMAP
- .irq_ack = ir_ack_apic_edge,
-#ifdef CONFIG_SMP
- .irq_set_affinity = ir_msi_set_affinity,
-#endif
-#endif
- .irq_retrigger = ioapic_retrigger_irq,
-};
-
/*
* Map the PCI dev to the corresponding remapping hardware unit
* and allocate 'nvec' consecutive interrupt-remapping table entries
@@ -3255,7 +3260,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
if (irq_remapped(irq_get_chip_data(irq))) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- chip = &msi_ir_chip;
+ irq_remap_modify_chip_defaults(chip);
}
irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
@@ -3328,7 +3333,7 @@ void native_teardown_msi_irq(unsigned int irq)
destroy_irq(irq);
}
-#if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
+#ifdef CONFIG_DMAR_TABLE
#ifdef CONFIG_SMP
static int
dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
@@ -3409,19 +3414,6 @@ static int hpet_msi_set_affinity(struct irq_data *data,
#endif /* CONFIG_SMP */
-static struct irq_chip ir_hpet_msi_type = {
- .name = "IR-HPET_MSI",
- .irq_unmask = hpet_msi_unmask,
- .irq_mask = hpet_msi_mask,
-#ifdef CONFIG_INTR_REMAP
- .irq_ack = ir_ack_apic_edge,
-#ifdef CONFIG_SMP
- .irq_set_affinity = ir_msi_set_affinity,
-#endif
-#endif
- .irq_retrigger = ioapic_retrigger_irq,
-};
-
static struct irq_chip hpet_msi_type = {
.name = "HPET_MSI",
.irq_unmask = hpet_msi_unmask,
@@ -3458,7 +3450,7 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
hpet_msi_write(irq_get_handler_data(irq), &msg);
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
if (irq_remapped(irq_get_chip_data(irq)))
- chip = &ir_hpet_msi_type;
+ irq_remap_modify_chip_defaults(chip);
irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
return 0;
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 8515101..2774ac1 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -30,10 +30,10 @@
/*
* If we have Intel graphics, we're not going to have anything other than
* an Intel IOMMU. So make the correct use of the PCI DMA API contingent
- * on the Intel IOMMU support (CONFIG_DMAR).
+ * on the Intel IOMMU support (CONFIG_INTEL_IOMMU).
* Only newer chipsets need to bother with this, of course.
*/
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
#define USE_PCI_DMA_API 1
#else
#define USE_PCI_DMA_API 0
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index b57b3fa..7d7eaa1 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -59,10 +59,14 @@ config AMD_IOMMU_STATS
If unsure, say N.
# Intel IOMMU support
-config DMAR
- bool "Support for DMA Remapping Devices"
+config DMAR_TABLE
+ bool
+
+config INTEL_IOMMU
+ bool "Support for Intel IOMMU using DMA Remapping Devices"
depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
select IOMMU_API
+ select DMAR_TABLE
help
DMA remapping (DMAR) devices support enables independent address
translations for Direct Memory Access (DMA) from devices.
@@ -70,18 +74,18 @@ config DMAR
and include PCI device scope covered by these DMA
remapping devices.
-config DMAR_DEFAULT_ON
+config INTEL_IOMMU_DEFAULT_ON
def_bool y
- prompt "Enable DMA Remapping Devices by default"
- depends on DMAR
+ prompt "Enable Intel DMA Remapping Devices by default"
+ depends on INTEL_IOMMU
help
Selecting this option will enable a DMAR device at boot time if
one is found. If this option is not selected, DMAR support can
be enabled by passing intel_iommu=on to the kernel.
-config DMAR_BROKEN_GFX_WA
+config INTEL_IOMMU_BROKEN_GFX_WA
bool "Workaround broken graphics drivers (going away soon)"
- depends on DMAR && BROKEN && X86
+ depends on INTEL_IOMMU && BROKEN && X86
---help---
Current Graphics drivers tend to use physical address
for DMA and avoid using DMA APIs. Setting this config
@@ -90,18 +94,19 @@ config DMAR_BROKEN_GFX_WA
to use physical addresses for DMA, at least until this
option is removed in the 2.6.32 kernel.
-config DMAR_FLOPPY_WA
+config INTEL_IOMMU_FLOPPY_WA
def_bool y
- depends on DMAR && X86
+ depends on INTEL_IOMMU && X86
---help---
Floppy disk drivers are known to bypass DMA API calls
thereby failing to work when IOMMU is enabled. This
workaround will setup a 1:1 mapping for the first
16MiB to make floppy (an ISA device) work.
-config INTR_REMAP
+config IRQ_REMAP
bool "Support for Interrupt Remapping (EXPERIMENTAL)"
depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
+ select DMAR_TABLE
---help---
Supports Interrupt remapping for IO-APIC and MSI devices.
To use x2apic mode in the CPU's which support x2APIC enhancements or
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 4d4d77d..6394994 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -1,5 +1,6 @@
obj-$(CONFIG_IOMMU_API) += iommu.o
obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
-obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
-obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o
+obj-$(CONFIG_DMAR_TABLE) += dmar.o
+obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o
+obj-$(CONFIG_IRQ_REMAP) += intr_remapping.o
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 6dcc7e2..587e8f2 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -46,7 +46,7 @@
*/
LIST_HEAD(dmar_drhd_units);
-static struct acpi_table_header * __initdata dmar_tbl;
+struct acpi_table_header * __initdata dmar_tbl;
static acpi_size dmar_tbl_size;
static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
@@ -118,8 +118,8 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
return 0;
}
-static int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
- struct pci_dev ***devices, u16 segment)
+int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
+ struct pci_dev ***devices, u16 segment)
{
struct acpi_dmar_device_scope *scope;
void * tmp = start;
@@ -217,133 +217,6 @@ static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
return ret;
}
-#ifdef CONFIG_DMAR
-LIST_HEAD(dmar_rmrr_units);
-
-static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
-{
- list_add(&rmrr->list, &dmar_rmrr_units);
-}
-
-
-static int __init
-dmar_parse_one_rmrr(struct acpi_dmar_header *header)
-{
- struct acpi_dmar_reserved_memory *rmrr;
- struct dmar_rmrr_unit *rmrru;
-
- rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
- if (!rmrru)
- return -ENOMEM;
-
- rmrru->hdr = header;
- rmrr = (struct acpi_dmar_reserved_memory *)header;
- rmrru->base_address = rmrr->base_address;
- rmrru->end_address = rmrr->end_address;
-
- dmar_register_rmrr_unit(rmrru);
- return 0;
-}
-
-static int __init
-rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
-{
- struct acpi_dmar_reserved_memory *rmrr;
- int ret;
-
- rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
- ret = dmar_parse_dev_scope((void *)(rmrr + 1),
- ((void *)rmrr) + rmrr->header.length,
- &rmrru->devices_cnt, &rmrru->devices, rmrr->segment);
-
- if (ret || (rmrru->devices_cnt == 0)) {
- list_del(&rmrru->list);
- kfree(rmrru);
- }
- return ret;
-}
-
-static LIST_HEAD(dmar_atsr_units);
-
-static int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
-{
- struct acpi_dmar_atsr *atsr;
- struct dmar_atsr_unit *atsru;
-
- atsr = container_of(hdr, struct acpi_dmar_atsr, header);
- atsru = kzalloc(sizeof(*atsru), GFP_KERNEL);
- if (!atsru)
- return -ENOMEM;
-
- atsru->hdr = hdr;
- atsru->include_all = atsr->flags & 0x1;
-
- list_add(&atsru->list, &dmar_atsr_units);
-
- return 0;
-}
-
-static int __init atsr_parse_dev(struct dmar_atsr_unit *atsru)
-{
- int rc;
- struct acpi_dmar_atsr *atsr;
-
- if (atsru->include_all)
- return 0;
-
- atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
- rc = dmar_parse_dev_scope((void *)(atsr + 1),
- (void *)atsr + atsr->header.length,
- &atsru->devices_cnt, &atsru->devices,
- atsr->segment);
- if (rc || !atsru->devices_cnt) {
- list_del(&atsru->list);
- kfree(atsru);
- }
-
- return rc;
-}
-
-int dmar_find_matched_atsr_unit(struct pci_dev *dev)
-{
- int i;
- struct pci_bus *bus;
- struct acpi_dmar_atsr *atsr;
- struct dmar_atsr_unit *atsru;
-
- dev = pci_physfn(dev);
-
- list_for_each_entry(atsru, &dmar_atsr_units, list) {
- atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
- if (atsr->segment == pci_domain_nr(dev->bus))
- goto found;
- }
-
- return 0;
-
-found:
- for (bus = dev->bus; bus; bus = bus->parent) {
- struct pci_dev *bridge = bus->self;
-
- if (!bridge || !pci_is_pcie(bridge) ||
- bridge->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE)
- return 0;
-
- if (bridge->pcie_type == PCI_EXP_TYPE_ROOT_PORT) {
- for (i = 0; i < atsru->devices_cnt; i++)
- if (atsru->devices[i] == bridge)
- return 1;
- break;
- }
- }
-
- if (atsru->include_all)
- return 1;
-
- return 0;
-}
-#endif
-
#ifdef CONFIG_ACPI_NUMA
static int __init
dmar_parse_one_rhsa(struct acpi_dmar_header *header)
@@ -484,14 +357,10 @@ parse_dmar_table(void)
ret = dmar_parse_one_drhd(entry_header);
break;
case ACPI_DMAR_TYPE_RESERVED_MEMORY:
-#ifdef CONFIG_DMAR
ret = dmar_parse_one_rmrr(entry_header);
-#endif
break;
case ACPI_DMAR_TYPE_ATSR:
-#ifdef CONFIG_DMAR
ret = dmar_parse_one_atsr(entry_header);
-#endif
break;
case ACPI_DMAR_HARDWARE_AFFINITY:
#ifdef CONFIG_ACPI_NUMA
@@ -557,34 +426,31 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev)
int __init dmar_dev_scope_init(void)
{
+ static int dmar_dev_scope_initialized;
struct dmar_drhd_unit *drhd, *drhd_n;
int ret = -ENODEV;
+ if (dmar_dev_scope_initialized)
+ return dmar_dev_scope_initialized;
+
+ if (list_empty(&dmar_drhd_units))
+ goto fail;
+
list_for_each_entry_safe(drhd, drhd_n, &dmar_drhd_units, list) {
ret = dmar_parse_dev(drhd);
if (ret)
- return ret;
+ goto fail;
}
-#ifdef CONFIG_DMAR
- {
- struct dmar_rmrr_unit *rmrr, *rmrr_n;
- struct dmar_atsr_unit *atsr, *atsr_n;
-
- list_for_each_entry_safe(rmrr, rmrr_n, &dmar_rmrr_units, list) {
- ret = rmrr_parse_dev(rmrr);
- if (ret)
- return ret;
- }
+ ret = dmar_parse_rmrr_atsr_dev();
+ if (ret)
+ goto fail;
- list_for_each_entry_safe(atsr, atsr_n, &dmar_atsr_units, list) {
- ret = atsr_parse_dev(atsr);
- if (ret)
- return ret;
- }
- }
-#endif
+ dmar_dev_scope_initialized = 1;
+ return 0;
+fail:
+ dmar_dev_scope_initialized = ret;
return ret;
}
@@ -611,14 +477,6 @@ int __init dmar_table_init(void)
return -ENODEV;
}
-#ifdef CONFIG_DMAR
- if (list_empty(&dmar_rmrr_units))
- printk(KERN_INFO PREFIX "No RMRR found\n");
-
- if (list_empty(&dmar_atsr_units))
- printk(KERN_INFO PREFIX "No ATSR found\n");
-#endif
-
return 0;
}
@@ -682,9 +540,6 @@ int __init check_zero_address(void)
return 1;
failed:
-#ifdef CONFIG_DMAR
- dmar_disabled = 1;
-#endif
return 0;
}
@@ -696,22 +551,21 @@ int __init detect_intel_iommu(void)
if (ret)
ret = check_zero_address();
{
-#ifdef CONFIG_INTR_REMAP
struct acpi_table_dmar *dmar;
dmar = (struct acpi_table_dmar *) dmar_tbl;
- if (ret && cpu_has_x2apic && dmar->flags & 0x1)
+
+ if (ret && intr_remapping_enabled && cpu_has_x2apic &&
+ dmar->flags & 0x1)
printk(KERN_INFO
- "Queued invalidation will be enabled to support "
- "x2apic and Intr-remapping.\n");
-#endif
-#ifdef CONFIG_DMAR
+ "Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");
+
if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
iommu_detected = 1;
/* Make sure ACS will be enabled */
pci_request_acs();
}
-#endif
+
#ifdef CONFIG_X86
if (ret)
x86_init.iommu.iommu_init = intel_iommu_init;
@@ -758,7 +612,6 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
goto err_unmap;
}
-#ifdef CONFIG_DMAR
agaw = iommu_calculate_agaw(iommu);
if (agaw < 0) {
printk(KERN_ERR
@@ -773,7 +626,6 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
iommu->seq_id);
goto err_unmap;
}
-#endif
iommu->agaw = agaw;
iommu->msagaw = msagaw;
@@ -817,9 +669,7 @@ void free_iommu(struct intel_iommu *iommu)
if (!iommu)
return;
-#ifdef CONFIG_DMAR
free_dmar_iommu(iommu);
-#endif
if (iommu->reg)
iounmap(iommu->reg);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index c621c98..4e249ed 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -393,11 +393,11 @@ static long list_size;
static void domain_remove_dev_info(struct dmar_domain *domain);
-#ifdef CONFIG_DMAR_DEFAULT_ON
+#ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
int dmar_disabled = 0;
#else
int dmar_disabled = 1;
-#endif /*CONFIG_DMAR_DEFAULT_ON*/
+#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
static int dmar_map_gfx = 1;
static int dmar_forcedac;
@@ -2150,7 +2150,7 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
rmrr->end_address);
}
-#ifdef CONFIG_DMAR_FLOPPY_WA
+#ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
static inline void iommu_prepare_isa(void)
{
struct pci_dev *pdev;
@@ -2173,7 +2173,7 @@ static inline void iommu_prepare_isa(void)
{
return;
}
-#endif /* !CONFIG_DMAR_FLPY_WA */
+#endif /* !CONFIG_INTEL_IOMMU_FLPY_WA */
static int md_domain_init(struct dmar_domain *domain, int guest_width);
@@ -2484,7 +2484,7 @@ static int __init init_dmars(void)
if (iommu_pass_through)
iommu_identity_mapping |= IDENTMAP_ALL;
-#ifdef CONFIG_DMAR_BROKEN_GFX_WA
+#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
iommu_identity_mapping |= IDENTMAP_GFX;
#endif
@@ -3390,6 +3390,151 @@ static void __init init_iommu_pm_ops(void)
static inline void init_iommu_pm_ops(void) {}
#endif /* CONFIG_PM */
+LIST_HEAD(dmar_rmrr_units);
+
+static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
+{
+ list_add(&rmrr->list, &dmar_rmrr_units);
+}
+
+
+int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
+{
+ struct acpi_dmar_reserved_memory *rmrr;
+ struct dmar_rmrr_unit *rmrru;
+
+ rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
+ if (!rmrru)
+ return -ENOMEM;
+
+ rmrru->hdr = header;
+ rmrr = (struct acpi_dmar_reserved_memory *)header;
+ rmrru->base_address = rmrr->base_address;
+ rmrru->end_address = rmrr->end_address;
+
+ dmar_register_rmrr_unit(rmrru);
+ return 0;
+}
+
+static int __init
+rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
+{
+ struct acpi_dmar_reserved_memory *rmrr;
+ int ret;
+
+ rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
+ ret = dmar_parse_dev_scope((void *)(rmrr + 1),
+ ((void *)rmrr) + rmrr->header.length,
+ &rmrru->devices_cnt, &rmrru->devices, rmrr->segment);
+
+ if (ret || (rmrru->devices_cnt == 0)) {
+ list_del(&rmrru->list);
+ kfree(rmrru);
+ }
+ return ret;
+}
+
+static LIST_HEAD(dmar_atsr_units);
+
+int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
+{
+ struct acpi_dmar_atsr *atsr;
+ struct dmar_atsr_unit *atsru;
+
+ atsr = container_of(hdr, struct acpi_dmar_atsr, header);
+ atsru = kzalloc(sizeof(*atsru), GFP_KERNEL);
+ if (!atsru)
+ return -ENOMEM;
+
+ atsru->hdr = hdr;
+ atsru->include_all = atsr->flags & 0x1;
+
+ list_add(&atsru->list, &dmar_atsr_units);
+
+ return 0;
+}
+
+static int __init atsr_parse_dev(struct dmar_atsr_unit *atsru)
+{
+ int rc;
+ struct acpi_dmar_atsr *atsr;
+
+ if (atsru->include_all)
+ return 0;
+
+ atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+ rc = dmar_parse_dev_scope((void *)(atsr + 1),
+ (void *)atsr + atsr->header.length,
+ &atsru->devices_cnt, &atsru->devices,
+ atsr->segment);
+ if (rc || !atsru->devices_cnt) {
+ list_del(&atsru->list);
+ kfree(atsru);
+ }
+
+ return rc;
+}
+
+int dmar_find_matched_atsr_unit(struct pci_dev *dev)
+{
+ int i;
+ struct pci_bus *bus;
+ struct acpi_dmar_atsr *atsr;
+ struct dmar_atsr_unit *atsru;
+
+ dev = pci_physfn(dev);
+
+ list_for_each_entry(atsru, &dmar_atsr_units, list) {
+ atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+ if (atsr->segment == pci_domain_nr(dev->bus))
+ goto found;
+ }
+
+ return 0;
+
+found:
+ for (bus = dev->bus; bus; bus = bus->parent) {
+ struct pci_dev *bridge = bus->self;
+
+ if (!bridge || !pci_is_pcie(bridge) ||
+ bridge->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE)
+ return 0;
+
+ if (bridge->pcie_type == PCI_EXP_TYPE_ROOT_PORT) {
+ for (i = 0; i < atsru->devices_cnt; i++)
+ if (atsru->devices[i] == bridge)
+ return 1;
+ break;
+ }
+ }
+
+ if (atsru->include_all)
+ return 1;
+
+ return 0;
+}
+
+int dmar_parse_rmrr_atsr_dev(void)
+{
+ struct dmar_rmrr_unit *rmrr, *rmrr_n;
+ struct dmar_atsr_unit *atsr, *atsr_n;
+ int ret = 0;
+
+ list_for_each_entry_safe(rmrr, rmrr_n, &dmar_rmrr_units, list) {
+ ret = rmrr_parse_dev(rmrr);
+ if (ret)
+ return ret;
+ }
+
+ list_for_each_entry_safe(atsr, atsr_n, &dmar_atsr_units, list) {
+ ret = atsr_parse_dev(atsr);
+ if (ret)
+ return ret;
+ }
+
+ return ret;
+}
+
/*
* Here we only respond to action of unbound device from driver.
*
@@ -3439,16 +3584,12 @@ int __init intel_iommu_init(void)
return -ENODEV;
}
- if (dmar_dev_scope_init()) {
+ if (dmar_dev_scope_init() < 0) {
if (force_on)
panic("tboot: Failed to initialize DMAR device scope\n");
return -ENODEV;
}
- /*
- * Check the need for DMA-remapping initialization now.
- * Above initialization will also be used by Interrupt-remapping.
- */
if (no_iommu || dmar_disabled)
return -ENODEV;
@@ -3458,6 +3599,12 @@ int __init intel_iommu_init(void)
return -ENODEV;
}
+ if (list_empty(&dmar_rmrr_units))
+ printk(KERN_INFO "DMAR: No RMRR found\n");
+
+ if (list_empty(&dmar_atsr_units))
+ printk(KERN_INFO "DMAR: No ATSR found\n");
+
if (dmar_init_reserved_ranges()) {
if (force_on)
panic("tboot: Failed to reserve iommu ranges\n");
diff --git a/drivers/iommu/intr_remapping.c b/drivers/iommu/intr_remapping.c
index 1a89d4a..cfb0dd4 100644
--- a/drivers/iommu/intr_remapping.c
+++ b/drivers/iommu/intr_remapping.c
@@ -21,6 +21,7 @@ int intr_remapping_enabled;
static int disable_intremap;
static int disable_sourceid_checking;
+static int no_x2apic_optout;
static __init int setup_nointremap(char *str)
{
@@ -34,12 +35,20 @@ static __init int setup_intremap(char *str)
if (!str)
return -EINVAL;
- 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;
+ 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;
}
@@ -501,6 +510,15 @@ end:
spin_unlock_irqrestore(&iommu->register_lock, flags);
}
+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;
@@ -521,16 +539,25 @@ int __init intr_remapping_supported(void)
return 1;
}
-int __init enable_intr_remapping(int eim)
+int __init enable_intr_remapping(void)
{
struct dmar_drhd_unit *drhd;
int setup = 0;
+ int eim = 0;
if (parse_ioapics_under_ir() != 1) {
printk(KERN_INFO "Not enable interrupt remapping\n");
return -1;
}
+ 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;
@@ -606,8 +633,9 @@ int __init enable_intr_remapping(int eim)
goto error;
intr_remapping_enabled = 1;
+ pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic");
- return 0;
+ return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;
error:
/*
@@ -745,6 +773,15 @@ int __init parse_ioapics_under_ir(void)
return ir_supported;
}
+int 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;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 1196f61..b23856a 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2788,7 +2788,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832);
#endif /*CONFIG_MMC_RICOH_MMC*/
-#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
+#ifdef CONFIG_DMAR_TABLE
#define VTUNCERRMSK_REG 0x1ac
#define VTD_MSK_SPEC_ERRORS (1 << 31)
/*
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index bbd8661..ef90cbd 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -25,11 +25,12 @@ struct intel_iommu;
struct dmar_domain;
struct root_entry;
-extern void free_dmar_iommu(struct intel_iommu *iommu);
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
+extern void free_dmar_iommu(struct intel_iommu *iommu);
extern int iommu_calculate_agaw(struct intel_iommu *iommu);
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
+extern int dmar_disabled;
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
{
@@ -39,8 +40,11 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
{
return 0;
}
+static inline void free_dmar_iommu(struct intel_iommu *iommu)
+{
+}
+#define dmar_disabled (1)
#endif
-extern int dmar_disabled;
#endif
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 7b776d7..a8b1a84 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -26,8 +26,13 @@
#include <linux/msi.h>
#include <linux/irqreturn.h>
+/* DMAR Flags */
+#define DMAR_INTR_REMAP 0x1
+#define DMAR_X2APIC_OPT_OUT 0x2
+
struct intel_iommu;
-#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
+#ifdef CONFIG_DMAR_TABLE
+extern struct acpi_table_header *dmar_tbl;
struct dmar_drhd_unit {
struct list_head list; /* list of drhd units */
struct acpi_dmar_header *hdr; /* ACPI header */
@@ -76,7 +81,7 @@ static inline int enable_drhd_fault_handling(void)
{
return -1;
}
-#endif /* !CONFIG_DMAR && !CONFIG_INTR_REMAP */
+#endif /* !CONFIG_DMAR_TABLE */
struct irte {
union {
@@ -107,10 +112,10 @@ struct irte {
};
};
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
extern int intr_remapping_enabled;
extern int intr_remapping_supported(void);
-extern int enable_intr_remapping(int);
+extern int enable_intr_remapping(void);
extern void disable_intr_remapping(void);
extern int reenable_intr_remapping(int);
@@ -177,7 +182,7 @@ static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev)
#define intr_remapping_enabled (0)
-static inline int enable_intr_remapping(int eim)
+static inline int enable_intr_remapping(void)
{
return -1;
}
@@ -192,6 +197,11 @@ static inline int reenable_intr_remapping(int eim)
}
#endif
+enum {
+ IRQ_REMAP_XAPIC_MODE,
+ IRQ_REMAP_X2APIC_MODE,
+};
+
/* Can't use the common MSI interrupt functions
* since DMAR is not a pci device
*/
@@ -204,7 +214,7 @@ extern int dmar_set_interrupt(struct intel_iommu *iommu);
extern irqreturn_t dmar_fault(int irq, void *dev_id);
extern int arch_setup_dmar_msi(unsigned int irq);
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
extern int iommu_detected, no_iommu;
extern struct list_head dmar_rmrr_units;
struct dmar_rmrr_unit {
@@ -227,9 +237,26 @@ struct dmar_atsr_unit {
u8 include_all:1; /* include all ports */
};
+int dmar_parse_rmrr_atsr_dev(void);
+extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
+extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
+extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
+ struct pci_dev ***devices, u16 segment);
extern int intel_iommu_init(void);
-#else /* !CONFIG_DMAR: */
+#else /* !CONFIG_INTEL_IOMMU: */
static inline int intel_iommu_init(void) { return -ENODEV; }
-#endif /* CONFIG_DMAR */
+static inline int dmar_parse_one_rmrr(struct acpi_dmar_header *header)
+{
+ return 0;
+}
+static inline int dmar_parse_one_atsr(struct acpi_dmar_header *header)
+{
+ return 0;
+}
+static inline int dmar_parse_rmrr_atsr_dev(void)
+{
+ return 0;
+}
+#endif /* CONFIG_INTEL_IOMMU */
#endif /* __DMAR_H__ */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 9310c69..235b887 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -279,7 +279,7 @@ struct q_inval {
int free_cnt;
};
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
/* 1MB - maximum possible interrupt remapping table size */
#define INTR_REMAP_PAGE_ORDER 8
#define INTR_REMAP_TABLE_REG_SIZE 0xf
@@ -318,7 +318,7 @@ struct intel_iommu {
unsigned int irq;
unsigned char name[13]; /* Device Name */
-#ifdef CONFIG_DMAR
+#ifdef CONFIG_INTEL_IOMMU
unsigned long *domain_ids; /* bitmap of domains */
struct dmar_domain **domains; /* ptr to domains */
spinlock_t lock; /* protect context, domain ids */
@@ -329,7 +329,7 @@ struct intel_iommu {
struct q_inval *qi; /* Queued invalidation info */
u32 *iommu_state; /* Store iommu states between suspend and resume.*/
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
struct ir_table *ir_table; /* Interrupt remapping info */
#endif
int node;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/