usbcore.blinkenlights=1
+Hyphens (dashes) and underscores are equivalent in parameter names, so
+ log_buf_len=1M print-fatal-signals=1
+can also be entered as
+ log-buf-len=1M print_fatal_signals=1
+
+
This document may not be entirely up to date and comprehensive. The command
"modinfo -p ${modulename}" shows a current list of all parameters of a loadable
module. Loadable modules, after being loaded into the running kernel, also
EFI EFI Partitioning (GPT) is enabled
EIDE EIDE/ATAPI support is enabled.
FB The frame buffer device is enabled.
+ GCOV GCOV profiling is enabled.
HW Appropriate hardware is enabled.
IA-64 IA-64 architecture is enabled.
IMA Integrity measurement architecture is enabled.
ISAPNP ISA PnP code is enabled.
ISDN Appropriate ISDN support is enabled.
JOY Appropriate joystick support is enabled.
- KMEMTRACE kmemtrace is enabled.
LIBATA Libata driver is enabled
LP Printer support is enabled.
LOOP Loopback device support is enabled.
flushed before they will be reused, which
is a lot of faster
- amd_iommu_size= [HW,X86-64]
- Define the size of the aperture for the AMD IOMMU
- driver. Possible values are:
- '32M', '64M' (default), '128M', '256M', '512M', '1G'
-
amijoy.map= [HW,JOY] Amiga joystick support
Map of devices attached to JOY0DAT and JOY1DAT
Format: <a>,<b>
not play well with APC CPU idle - disable it if you have
APC and your system crashes randomly.
- apic= [APIC,i386] Advanced Programmable Interrupt Controller
+ apic= [APIC,X86-32] Advanced Programmable Interrupt Controller
Change the output verbosity whilst booting
Format: { quiet (default) | verbose | debug }
Change the amount of debugging information output
Also note the kernel might malfunction if you disable
some critical bits.
+ cmo_free_hint= [PPC] Format: { yes | no }
+ Specify whether pages are marked as being inactive
+ when they are freed. This is used in CMO environments
+ to determine OS memory pressure for page stealing by
+ a hypervisor.
+ Default: yes
+
code_bytes [X86] How many bytes of object code to print
in an oops report.
Range: 0 - 8192
console=brl,ttyS0
For now, only VisioBraille is supported.
+ consoleblank= [KNL] The console blank (screen saver) timeout in
+ seconds. Defaults to 10*60 = 10mins. A value of 0
+ disables the blank timer.
+
coredump_filter=
[KNL] Change the default value for
/proc/<pid>/coredump_filter.
DMA-API debugging code disables itself because the
architectural default is too low.
+ dma_debug_driver=<driver_name>
+ With this option the DMA-API debugging driver
+ filter feature can be enabled at boot time. Just
+ pass the driver to filter for as the parameter.
+ The filter can be disabled or changed to another
+ driver later using sysfs.
+
dscc4.setup= [NET]
dtc3181e= [HW,SCSI]
to discrete, to make X server driver able to add WB
entry later. This parameter enables that.
- enable_timer_pin_1 [i386,x86-64]
+ enable_timer_pin_1 [X86]
Enable PIN 1 of APIC timer
Can be useful to work around chipset bugs
(in particular on some ATI chipsets).
ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
ftrace=[tracer]
- [ftrace] will set and start the specified tracer
+ [FTRACE] will set and start the specified tracer
as early as possible in order to facilitate early
boot debugging.
ftrace_dump_on_oops
- [ftrace] will dump the trace buffers on oops.
+ [FTRACE] will dump the trace buffers on oops.
+
+ ftrace_filter=[function-list]
+ [FTRACE] Limit the functions traced by the function
+ tracer at boot up. function-list is a comma separated
+ list of functions. This list can be changed at run
+ time by the set_ftrace_filter file in the debugfs
+ tracing directory.
+
+ ftrace_notrace=[function-list]
+ [FTRACE] Do not trace the functions specified in
+ function-list. This list can be changed at run time
+ by the set_ftrace_notrace file in the debugfs
+ tracing directory.
gamecon.map[2|3]=
[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
Format: off | on
default: on
+ gcov_persist= [GCOV] When non-zero (default), profiling data for
+ kernel modules is saved and remains accessible via
+ debugfs, even when the module is unloaded/reloaded.
+ When zero, profiling data is discarded and associated
+ debugfs files are removed at module unload time.
+
gdth= [HW,SCSI]
See header of drivers/scsi/gdth.c.
hashdist= [KNL,NUMA] Large hashes allocated during boot
are distributed across NUMA nodes. Defaults on
- for IA-64, off otherwise.
+ for 64bit NUMA, off otherwise.
Format: 0 | 1 (for off | on)
hcl= [IA-64] SGI's Hardware Graph compatibility layer
ide-core.nodma= [HW] (E)IDE subsystem
Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc
- .vlb_clock .pci_clock .noflush .noprobe .nowerr .cdrom
- .chs .ignore_cable are additional options
- See Documentation/ide/ide.txt.
-
- idebus= [HW] (E)IDE subsystem - VLB/PCI bus speed
+ .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr
+ .cdrom .chs .ignore_cable are additional options
See Documentation/ide/ide.txt.
ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
Formt: { "sha1" | "md5" }
default: "sha1"
+ ima_tcb [IMA]
+ Load a policy which meets the needs of the Trusted
+ Computing Base. This means IMA will measure all
+ programs exec'd, files mmap'd for exec, and all files
+ opened for read by uid=0.
+
in2000= [HW,SCSI]
See header of drivers/scsi/in2000.c.
nomerge
forcesac
soft
+ pt [x86, IA64]
io7= [HW] IO7 for Marvel based alpha systems
See comment before marvel_specify_io7 in
use the HighMem zone if it exists, and the Normal
zone if it does not.
- kmemtrace.enable= [KNL,KMEMTRACE] Format: { yes | no }
- Controls whether kmemtrace is enabled
- at boot-time.
-
- kmemtrace.subbufs=n [KNL,KMEMTRACE] Overrides the number of
- subbufs kmemtrace's relay channel has. Set this
- higher than default (KMEMTRACE_N_SUBBUFS in code) if
- you experience buffer overruns.
-
kgdboc= [HW] kgdb over consoles.
Requires a tty driver that supports console polling.
- (only serial suported for now)
+ (only serial supported for now)
Format: <serial_device>[,baud]
kmac= [MIPS] korina ethernet MAC address.
Configure the RouterBoard 532 series on-chip
Ethernet adapter MAC address.
+ kmemleak= [KNL] Boot-time kmemleak enable/disable
+ Valid arguments: on, off
+ Default: on
+
kstack=N [X86] Print N words from the kernel stack
in oops dumps.
min_addr=nn[KMG] [KNL,BOOT,ia64] All physical memory below this
physical address is ignored.
+ mini2440= [ARM,HW,KNL]
+ Format:[0..2][b][c][t]
+ Default: "0tb"
+ MINI2440 configuration specification:
+ 0 - The attached screen is the 3.5" TFT
+ 1 - The attached screen is the 7" TFT
+ 2 - The VGA Shield is attached (1024x768)
+ Leaving out the screen size parameter will not load
+ the TFT driver, and the framebuffer will be left
+ unconfigured.
+ b - Enable backlight. The TFT backlight pin will be
+ linked to the kernel VESA blanking code and a GPIO
+ LED. This parameter is not necessary when using the
+ VGA shield.
+ c - Enable the s3c camera interface.
+ t - Reserved for enabling touchscreen support. The
+ touchscreen support is not enabled in the mainstream
+ kernel as of 2.6.30, a preliminary port can be found
+ in the "bleeding edge" mini2440 support kernel at
+ http://repo.or.cz/w/linux-2.6/mini2440.git
+
mminit_loglevel=
[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
parameter allows control of the logging verbosity for
mtdparts= [MTD]
See drivers/mtd/cmdlinepart.c.
+ onenand.bdry= [HW,MTD] Flex-OneNAND Boundary Configuration
+
+ Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]
+
+ boundary - index of last SLC block on Flex-OneNAND.
+ The remaining blocks are configured as MLC blocks.
+ lock - Configure if Flex-OneNAND boundary should be locked.
+ Once locked, the boundary cannot be changed.
+ 1 indicates lock status, 0 indicates unlock status.
+
mtdset= [ARM]
ARM/S3C2412 JIVE boot control
('y', default) or cooked coordinates ('n')
mtrr_chunk_size=nn[KMG] [X86]
- used for mtrr cleanup. It is largest continous chunk
+ used for mtrr cleanup. It is largest continuous chunk
that could hold holes aka. UC entries.
mtrr_gran_size=nn[KMG] [X86]
register save and restore. The kernel will only save
legacy floating-point registers on task switch.
+ noxsave [BUGS=X86] Disables x86 extended register state save
+ and restore using xsave. The kernel will fallback to
+ enabling legacy floating-point and sse state.
+
nohlt [BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
wfi(ARM) instruction doesn't work correctly and not to
use it. This is also useful when using JTAG debugger.
noinitrd [RAM] Tells the kernel not to load any configured
initial RAM disk.
+ nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
+ remapping.
+
nointroute [IA-64]
nojitter [IA64] Disables jitter checking for ITC timers.
nowb [ARM]
+ nox2apic [X86-64,APIC] Do not enable x2APIC mode.
+
nptcg= [IA64] Override max number of concurrent global TLB
purges which is reported from either PAL_VM_SUMMARY or
SAL PALO.
oprofile.timer= [HW]
Use timer interrupt instead of performance counters
+ oprofile.cpu_type= Force an oprofile cpu type
+ This might be useful if you have an older oprofile
+ userland or if you want common events.
+ Format: { archperfmon }
+ archperfmon: [X86] Force use of architectural
+ perfmon on Intel CPUs instead of the
+ CPU specific event set.
+
osst= [HW,SCSI] SCSI Tape Driver
Format: <buffer_size>,<write_threshold>
See also Documentation/scsi/st.txt.
root domains (aka PCI segments, in ACPI-speak).
nommconf [X86] Disable use of MMCONFIG for PCI
Configuration
+ check_enable_amd_mmconf [X86] check for and enable
+ properly configured MMIO access to PCI
+ config space on AMD family 10h CPU
nomsi [MSI] If the PCI_MSI kernel config parameter is
enabled, this kernel boot option can be used to
disable the use of MSI interrupts system-wide.
IRQ routing is enabled.
noacpi [X86] Do not use ACPI for IRQ routing
or for PCI scanning.
- use_crs [X86] Use _CRS for PCI resource
+ nocrs [X86] Don't use _CRS for PCI resource
allocation.
routeirq Do IRQ routing for all PCI devices.
This is normally done in pci_enable_device(),
PAGE_SIZE is used as alignment.
PCI-PCI bridge can be specified, if resource
windows need to be expanded.
+ ecrc= Enable/disable PCIe ECRC (transaction layer
+ end-to-end CRC checking).
+ bios: Use BIOS/firmware settings. This is the
+ the default.
+ off: Turn ECRC off
+ on: Turn ECRC on.
pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
Management.
#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
+ #define MAX_AGAW_WIDTH 64
+
#define DOMAIN_MAX_ADDR(gaw) ((((u64)1) << gaw) - 1)
#define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
#define DMA_32BIT_PFN IOVA_PFN(DMA_BIT_MASK(32))
#define DMA_64BIT_PFN IOVA_PFN(DMA_BIT_MASK(64))
+#ifndef PHYSICAL_PAGE_MASK
+#define PHYSICAL_PAGE_MASK PAGE_MASK
+#endif
+
/* global iommu list, set NULL for ignored DMAR units */
static struct intel_iommu **g_iommus;
context->lo &= (((u64)-1) << 2) | 1;
}
- #define CONTEXT_TT_MULTI_LEVEL 0
-
static inline void context_set_translation_type(struct context_entry *context,
unsigned long value)
{
u8 bus; /* PCI bus number */
u8 devfn; /* PCI devfn number */
struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
+ struct intel_iommu *iommu; /* IOMMU used by this device */
struct dmar_domain *domain; /* pointer to domain */
};
static inline int width_to_agaw(int width);
- /* calculate agaw for each iommu.
- * "SAGAW" may be different across iommus, use a default agaw, and
- * get a supported less agaw for iommus that don't support the default agaw.
- */
- int iommu_calculate_agaw(struct intel_iommu *iommu)
+ static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
{
unsigned long sagaw;
int agaw = -1;
sagaw = cap_sagaw(iommu->cap);
- for (agaw = width_to_agaw(DEFAULT_DOMAIN_ADDRESS_WIDTH);
+ for (agaw = width_to_agaw(max_gaw);
agaw >= 0; agaw--) {
if (test_bit(agaw, &sagaw))
break;
return agaw;
}
+ /*
+ * Calculate max SAGAW for each iommu.
+ */
+ int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
+ {
+ return __iommu_calculate_agaw(iommu, MAX_AGAW_WIDTH);
+ }
+
+ /*
+ * calculate agaw for each iommu.
+ * "SAGAW" may be different across iommus, use a default agaw, and
+ * get a supported less agaw for iommus that don't support the default agaw.
+ */
+ int iommu_calculate_agaw(struct intel_iommu *iommu)
+ {
+ return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+ }
+
/* in native case, each domain is related to only one iommu */
static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
{
static void iommu_set_root_entry(struct intel_iommu *iommu)
{
void *addr;
- u32 cmd, sts;
+ u32 sts;
unsigned long flag;
addr = iommu->root_entry;
spin_lock_irqsave(&iommu->register_lock, flag);
dmar_writeq(iommu->reg + DMAR_RTADDR_REG, virt_to_phys(addr));
- cmd = iommu->gcmd | DMA_GCMD_SRTP;
- writel(cmd, iommu->reg + DMAR_GCMD_REG);
+ writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG);
/* Make sure hardware complete it */
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
- readl, (sts & DMA_GSTS_RTPS), sts);
+ readl, (sts & DMA_GSTS_RTPS), sts);
spin_unlock_irqrestore(&iommu->register_lock, flag);
}
if (!rwbf_quirk && !cap_rwbf(iommu->cap))
return;
- val = iommu->gcmd | DMA_GCMD_WBF;
spin_lock_irqsave(&iommu->register_lock, flag);
- writel(val, iommu->reg + DMAR_GCMD_REG);
+ writel(iommu->gcmd | DMA_GCMD_WBF, iommu->reg + DMAR_GCMD_REG);
/* Make sure hardware complete it */
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
- readl, (!(val & DMA_GSTS_WBFS)), val);
+ readl, (!(val & DMA_GSTS_WBFS)), val);
spin_unlock_irqrestore(&iommu->register_lock, flag);
}
/* return value determine if we need a write buffer flush */
- static int __iommu_flush_context(struct intel_iommu *iommu,
- u16 did, u16 source_id, u8 function_mask, u64 type,
- int non_present_entry_flush)
+ static void __iommu_flush_context(struct intel_iommu *iommu,
+ u16 did, u16 source_id, u8 function_mask,
+ u64 type)
{
u64 val = 0;
unsigned long flag;
- /*
- * In the non-present entry flush case, if hardware doesn't cache
- * non-present entry we do nothing and if hardware cache non-present
- * entry, we flush entries of domain 0 (the domain id is used to cache
- * any non-present entries)
- */
- if (non_present_entry_flush) {
- if (!cap_caching_mode(iommu->cap))
- return 1;
- else
- did = 0;
- }
-
switch (type) {
case DMA_CCMD_GLOBAL_INVL:
val = DMA_CCMD_GLOBAL_INVL;
dmar_readq, (!(val & DMA_CCMD_ICC)), val);
spin_unlock_irqrestore(&iommu->register_lock, flag);
-
- /* flush context entry will implicitly flush write buffer */
- return 0;
}
/* return value determine if we need a write buffer flush */
- static int __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
- u64 addr, unsigned int size_order, u64 type,
- int non_present_entry_flush)
+ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
+ u64 addr, unsigned int size_order, u64 type)
{
int tlb_offset = ecap_iotlb_offset(iommu->ecap);
u64 val = 0, val_iva = 0;
unsigned long flag;
- /*
- * In the non-present entry flush case, if hardware doesn't cache
- * non-present entry we do nothing and if hardware cache non-present
- * entry, we flush entries of domain 0 (the domain id is used to cache
- * any non-present entries)
- */
- if (non_present_entry_flush) {
- if (!cap_caching_mode(iommu->cap))
- return 1;
- else
- did = 0;
- }
-
switch (type) {
case DMA_TLB_GLOBAL_FLUSH:
/* global flush doesn't need set IVA_REG */
pr_debug("IOMMU: tlb flush request %Lx, actual %Lx\n",
(unsigned long long)DMA_TLB_IIRG(type),
(unsigned long long)DMA_TLB_IAIG(val));
- /* flush iotlb entry will implicitly flush write buffer */
- return 0;
}
- static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
- u64 addr, unsigned int pages, int non_present_entry_flush)
+ static struct device_domain_info *iommu_support_dev_iotlb(
+ struct dmar_domain *domain, int segment, u8 bus, u8 devfn)
+ {
+ int found = 0;
+ unsigned long flags;
+ struct device_domain_info *info;
+ struct intel_iommu *iommu = device_to_iommu(segment, bus, devfn);
+
+ if (!ecap_dev_iotlb_support(iommu->ecap))
+ return NULL;
+
+ if (!iommu->qi)
+ return NULL;
+
+ spin_lock_irqsave(&device_domain_lock, flags);
+ list_for_each_entry(info, &domain->devices, link)
+ if (info->bus == bus && info->devfn == devfn) {
+ found = 1;
+ break;
+ }
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+
+ if (!found || !info->dev)
+ return NULL;
+
+ if (!pci_find_ext_capability(info->dev, PCI_EXT_CAP_ID_ATS))
+ return NULL;
+
+ if (!dmar_find_matched_atsr_unit(info->dev))
+ return NULL;
+
+ info->iommu = iommu;
+
+ return info;
+ }
+
+ static void iommu_enable_dev_iotlb(struct device_domain_info *info)
{
- unsigned int mask;
+ if (!info)
+ return;
+
+ pci_enable_ats(info->dev, VTD_PAGE_SHIFT);
+ }
+
+ static void iommu_disable_dev_iotlb(struct device_domain_info *info)
+ {
+ if (!info->dev || !pci_ats_enabled(info->dev))
+ return;
+
+ pci_disable_ats(info->dev);
+ }
+
+ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
+ u64 addr, unsigned mask)
+ {
+ u16 sid, qdep;
+ unsigned long flags;
+ struct device_domain_info *info;
+
+ spin_lock_irqsave(&device_domain_lock, flags);
+ list_for_each_entry(info, &domain->devices, link) {
+ if (!info->dev || !pci_ats_enabled(info->dev))
+ continue;
+
+ sid = info->bus << 8 | info->devfn;
+ qdep = pci_ats_queue_depth(info->dev);
+ qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask);
+ }
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+ }
+
+ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
+ u64 addr, unsigned int pages)
+ {
+ unsigned int mask = ilog2(__roundup_pow_of_two(pages));
BUG_ON(addr & (~VTD_PAGE_MASK));
BUG_ON(pages == 0);
- /* Fallback to domain selective flush if no PSI support */
- if (!cap_pgsel_inv(iommu->cap))
- return iommu->flush.flush_iotlb(iommu, did, 0, 0,
- DMA_TLB_DSI_FLUSH,
- non_present_entry_flush);
-
/*
+ * Fallback to domain selective flush if no PSI support or the size is
+ * too big.
* PSI requires page size to be 2 ^ x, and the base address is naturally
* aligned to the size
*/
- mask = ilog2(__roundup_pow_of_two(pages));
- /* Fallback to domain selective flush if size is too big */
- if (mask > cap_max_amask_val(iommu->cap))
- return iommu->flush.flush_iotlb(iommu, did, 0, 0,
- DMA_TLB_DSI_FLUSH, non_present_entry_flush);
-
- return iommu->flush.flush_iotlb(iommu, did, addr, mask,
- DMA_TLB_PSI_FLUSH,
- non_present_entry_flush);
+ if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
+ iommu->flush.flush_iotlb(iommu, did, 0, 0,
+ DMA_TLB_DSI_FLUSH);
+ else
+ iommu->flush.flush_iotlb(iommu, did, addr, mask,
+ DMA_TLB_PSI_FLUSH);
+ if (did)
+ iommu_flush_dev_iotlb(iommu->domains[did], addr, mask);
}
static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
unsigned long flags;
spin_lock_irqsave(&iommu->register_lock, flags);
- writel(iommu->gcmd|DMA_GCMD_TE, iommu->reg + DMAR_GCMD_REG);
+ iommu->gcmd |= DMA_GCMD_TE;
+ writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
/* Make sure hardware complete it */
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
- readl, (sts & DMA_GSTS_TES), sts);
+ readl, (sts & DMA_GSTS_TES), sts);
- iommu->gcmd |= DMA_GCMD_TE;
spin_unlock_irqrestore(&iommu->register_lock, flags);
return 0;
}
/* Make sure hardware complete it */
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
- readl, (!(sts & DMA_GSTS_TES)), sts);
+ readl, (!(sts & DMA_GSTS_TES)), sts);
spin_unlock_irqrestore(&iommu->register_lock, flag);
return 0;
if (!r->flags || !(r->flags & IORESOURCE_MEM))
continue;
addr = r->start;
- addr &= PAGE_MASK;
+ addr &= PHYSICAL_PAGE_MASK;
size = r->end - addr;
size = PAGE_ALIGN(size);
iova = reserve_iova(&reserved_iova_list, IOVA_PFN(addr),
free_domain_mem(domain);
}
- static int domain_context_mapping_one(struct dmar_domain *domain,
- int segment, u8 bus, u8 devfn)
+ static int domain_context_mapping_one(struct dmar_domain *domain, int segment,
+ u8 bus, u8 devfn, int translation)
{
struct context_entry *context;
unsigned long flags;
unsigned long ndomains;
int id;
int agaw;
+ struct device_domain_info *info = NULL;
pr_debug("Set context mapping for %02x:%02x.%d\n",
bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+
BUG_ON(!domain->pgd);
+ BUG_ON(translation != CONTEXT_TT_PASS_THROUGH &&
+ translation != CONTEXT_TT_MULTI_LEVEL);
iommu = device_to_iommu(segment, bus, devfn);
if (!iommu)
}
context_set_domain_id(context, id);
- context_set_address_width(context, iommu->agaw);
- context_set_address_root(context, virt_to_phys(pgd));
- context_set_translation_type(context, CONTEXT_TT_MULTI_LEVEL);
+
+ if (translation != CONTEXT_TT_PASS_THROUGH) {
+ info = iommu_support_dev_iotlb(domain, segment, bus, devfn);
+ translation = info ? CONTEXT_TT_DEV_IOTLB :
+ CONTEXT_TT_MULTI_LEVEL;
+ }
+ /*
+ * In pass through mode, AW must be programmed to indicate the largest
+ * AGAW value supported by hardware. And ASR is ignored by hardware.
+ */
+ if (unlikely(translation == CONTEXT_TT_PASS_THROUGH))
+ context_set_address_width(context, iommu->msagaw);
+ else {
+ context_set_address_root(context, virt_to_phys(pgd));
+ context_set_address_width(context, iommu->agaw);
+ }
+
+ context_set_translation_type(context, translation);
context_set_fault_enable(context);
context_set_present(context);
domain_flush_cache(domain, context, sizeof(*context));
- /* it's a non-present to present mapping */
- if (iommu->flush.flush_context(iommu, domain->id,
- (((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT,
- DMA_CCMD_DEVICE_INVL, 1))
+ /*
+ * It's a non-present to present mapping. If hardware doesn't cache
+ * non-present entry we only need to flush the write-buffer. If the
+ * _does_ cache non-present entries, then it does so in the special
+ * domain #0, which we have to flush:
+ */
+ if (cap_caching_mode(iommu->cap)) {
+ iommu->flush.flush_context(iommu, 0,
+ (((u16)bus) << 8) | devfn,
+ DMA_CCMD_MASK_NOBIT,
+ DMA_CCMD_DEVICE_INVL);
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH);
+ } else {
iommu_flush_write_buffer(iommu);
- else
- iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH, 0);
-
+ }
+ iommu_enable_dev_iotlb(info);
spin_unlock_irqrestore(&iommu->lock, flags);
spin_lock_irqsave(&domain->iommu_lock, flags);
}
static int
- domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev)
+ domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev,
+ int translation)
{
int ret;
struct pci_dev *tmp, *parent;
ret = domain_context_mapping_one(domain, pci_domain_nr(pdev->bus),
- pdev->bus->number, pdev->devfn);
+ pdev->bus->number, pdev->devfn,
+ translation);
if (ret)
return ret;
ret = domain_context_mapping_one(domain,
pci_domain_nr(parent->bus),
parent->bus->number,
- parent->devfn);
+ parent->devfn, translation);
if (ret)
return ret;
parent = parent->bus->self;
if (tmp->is_pcie) /* this is a PCIE-to-PCI bridge */
return domain_context_mapping_one(domain,
pci_domain_nr(tmp->subordinate),
- tmp->subordinate->number, 0);
+ tmp->subordinate->number, 0,
+ translation);
else /* this is a legacy PCI bridge */
return domain_context_mapping_one(domain,
pci_domain_nr(tmp->bus),
tmp->bus->number,
- tmp->devfn);
+ tmp->devfn,
+ translation);
}
static int domain_context_mapped(struct pci_dev *pdev)
clear_context_table(iommu, bus, devfn);
iommu->flush.flush_context(iommu, 0, 0, 0,
- DMA_CCMD_GLOBAL_INVL, 0);
- iommu->flush.flush_iotlb(iommu, 0, 0, 0,
- DMA_TLB_GLOBAL_FLUSH, 0);
+ DMA_CCMD_GLOBAL_INVL);
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
}
static void domain_remove_dev_info(struct dmar_domain *domain)
info->dev->dev.archdata.iommu = NULL;
spin_unlock_irqrestore(&device_domain_lock, flags);
+ iommu_disable_dev_iotlb(info);
iommu = device_to_iommu(info->segment, info->bus, info->devfn);
iommu_detach_dev(iommu, info->bus, info->devfn);
free_devinfo_mem(info);
goto error;
/* context entry init */
- ret = domain_context_mapping(domain, pdev);
+ ret = domain_context_mapping(domain, pdev, CONTEXT_TT_MULTI_LEVEL);
if (!ret)
return 0;
error:
}
#endif /* !CONFIG_DMAR_FLPY_WA */
+ /* Initialize each context entry as pass through.*/
+ static int __init init_context_pass_through(void)
+ {
+ struct pci_dev *pdev = NULL;
+ struct dmar_domain *domain;
+ int ret;
+
+ for_each_pci_dev(pdev) {
+ domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
+ ret = domain_context_mapping(domain, pdev,
+ CONTEXT_TT_PASS_THROUGH);
+ if (ret)
+ return ret;
+ }
+ return 0;
+ }
+
static int __init init_dmars(void)
{
struct dmar_drhd_unit *drhd;
struct pci_dev *pdev;
struct intel_iommu *iommu;
int i, ret;
+ int pass_through = 1;
/*
* for each drhd
printk(KERN_ERR "IOMMU: allocate root entry failed\n");
goto error;
}
+ if (!ecap_pass_through(iommu->ecap))
+ pass_through = 0;
}
+ if (iommu_pass_through)
+ if (!pass_through) {
+ printk(KERN_INFO
+ "Pass Through is not supported by hardware.\n");
+ iommu_pass_through = 0;
+ }
/*
* Start from the sane iommu hardware state.
}
}
-#ifdef CONFIG_INTR_REMAP
- if (!intr_remapping_enabled) {
- ret = enable_intr_remapping(0);
- if (ret)
- printk(KERN_ERR
- "IOMMU: enable interrupt remapping failed\n");
- }
-#endif
/*
- * For each rmrr
- * for each dev attached to rmrr
- * do
- * locate drhd for dev, alloc domain for dev
- * allocate free domain
- * allocate page table entries for rmrr
- * if context not allocated for bus
- * allocate and init context
- * set present in root table for this bus
- * init context with domain, translation etc
- * endfor
- * endfor
+ * If pass through is set and enabled, context entries of all pci
+ * devices are intialized by pass through translation type.
*/
- for_each_rmrr_units(rmrr) {
- for (i = 0; i < rmrr->devices_cnt; i++) {
- pdev = rmrr->devices[i];
- /* some BIOS lists non-exist devices in DMAR table */
- if (!pdev)
- continue;
- ret = iommu_prepare_rmrr_dev(rmrr, pdev);
- if (ret)
- printk(KERN_ERR
- "IOMMU: mapping reserved region failed\n");
+ if (iommu_pass_through) {
+ ret = init_context_pass_through();
+ if (ret) {
+ printk(KERN_ERR "IOMMU: Pass through init failed.\n");
+ iommu_pass_through = 0;
}
}
- iommu_prepare_gfx_mapping();
+ /*
+ * If pass through is not set or not enabled, setup context entries for
+ * identity mappings for rmrr, gfx, and isa.
+ */
+ if (!iommu_pass_through) {
+ /*
+ * For each rmrr
+ * for each dev attached to rmrr
+ * do
+ * locate drhd for dev, alloc domain for dev
+ * allocate free domain
+ * allocate page table entries for rmrr
+ * if context not allocated for bus
+ * allocate and init context
+ * set present in root table for this bus
+ * init context with domain, translation etc
+ * endfor
+ * endfor
+ */
+ for_each_rmrr_units(rmrr) {
+ for (i = 0; i < rmrr->devices_cnt; i++) {
+ pdev = rmrr->devices[i];
+ /*
+ * some BIOS lists non-exist devices in DMAR
+ * table.
+ */
+ if (!pdev)
+ continue;
+ ret = iommu_prepare_rmrr_dev(rmrr, pdev);
+ if (ret)
+ printk(KERN_ERR
+ "IOMMU: mapping reserved region failed\n");
+ }
+ }
+
+ iommu_prepare_gfx_mapping();
- iommu_prepare_isa();
+ iommu_prepare_isa();
+ }
/*
* for each drhd
iommu_set_root_entry(iommu);
- iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL,
- 0);
- iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH,
- 0);
+ iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
iommu_disable_protect_mem_regions(iommu);
ret = iommu_enable_translation(iommu);
/* make sure context mapping is ok */
if (unlikely(!domain_context_mapped(pdev))) {
- ret = domain_context_mapping(domain, pdev);
+ ret = domain_context_mapping(domain, pdev,
+ CONTEXT_TT_MULTI_LEVEL);
if (ret) {
printk(KERN_ERR
"Domain context map for %s failed",
* is not a big problem
*/
ret = domain_page_mapping(domain, start_paddr,
- ((u64)paddr) & PAGE_MASK, size, prot);
+ ((u64)paddr) & PHYSICAL_PAGE_MASK,
+ size, prot);
if (ret)
goto error;
- /* it's a non-present to present mapping */
- ret = iommu_flush_iotlb_psi(iommu, domain->id,
- start_paddr, size >> VTD_PAGE_SHIFT, 1);
- if (ret)
+ /* it's a non-present to present mapping. Only flush if caching mode */
+ if (cap_caching_mode(iommu->cap))
+ iommu_flush_iotlb_psi(iommu, 0, start_paddr,
+ size >> VTD_PAGE_SHIFT);
+ else
iommu_flush_write_buffer(iommu);
return start_paddr + ((u64)paddr & (~PAGE_MASK));
if (!iommu)
continue;
- if (deferred_flush[i].next) {
- iommu->flush.flush_iotlb(iommu, 0, 0, 0,
- DMA_TLB_GLOBAL_FLUSH, 0);
- for (j = 0; j < deferred_flush[i].next; j++) {
- __free_iova(&deferred_flush[i].domain[j]->iovad,
- deferred_flush[i].iova[j]);
- }
- deferred_flush[i].next = 0;
+ if (!deferred_flush[i].next)
+ continue;
+
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+ DMA_TLB_GLOBAL_FLUSH);
+ for (j = 0; j < deferred_flush[i].next; j++) {
+ unsigned long mask;
+ struct iova *iova = deferred_flush[i].iova[j];
+
+ mask = (iova->pfn_hi - iova->pfn_lo + 1) << PAGE_SHIFT;
+ mask = ilog2(mask >> VTD_PAGE_SHIFT);
+ iommu_flush_dev_iotlb(deferred_flush[i].domain[j],
+ iova->pfn_lo << PAGE_SHIFT, mask);
+ __free_iova(&deferred_flush[i].domain[j]->iovad, iova);
}
+ deferred_flush[i].next = 0;
}
list_size = 0;
/* free page tables */
dma_pte_free_pagetable(domain, start_addr, start_addr + size);
if (intel_iommu_strict) {
- if (iommu_flush_iotlb_psi(iommu,
- domain->id, start_addr, size >> VTD_PAGE_SHIFT, 0))
- iommu_flush_write_buffer(iommu);
+ iommu_flush_iotlb_psi(iommu, domain->id, start_addr,
+ size >> VTD_PAGE_SHIFT);
/* free iova */
__free_iova(&domain->iovad, iova);
} else {
/* free page tables */
dma_pte_free_pagetable(domain, start_addr, start_addr + size);
- if (iommu_flush_iotlb_psi(iommu, domain->id, start_addr,
- size >> VTD_PAGE_SHIFT, 0))
- iommu_flush_write_buffer(iommu);
+ iommu_flush_iotlb_psi(iommu, domain->id, start_addr,
+ size >> VTD_PAGE_SHIFT);
/* free iova */
__free_iova(&domain->iovad, iova);
addr = page_to_phys(sg_page(sg)) + sg->offset;
size = aligned_size((u64)addr, sg->length);
ret = domain_page_mapping(domain, start_addr + offset,
- ((u64)addr) & PAGE_MASK,
- size, prot);
+ ((u64)addr) & PHYSICAL_PAGE_MASK,
+ size, prot);
if (ret) {
/* clear the page */
dma_pte_clear_range(domain, start_addr,
offset += size;
}
- /* it's a non-present to present mapping */
- if (iommu_flush_iotlb_psi(iommu, domain->id,
- start_addr, offset >> VTD_PAGE_SHIFT, 1))
+ /* it's a non-present to present mapping. Only flush if caching mode */
+ if (cap_caching_mode(iommu->cap))
+ iommu_flush_iotlb_psi(iommu, 0, start_addr,
+ offset >> VTD_PAGE_SHIFT);
+ else
iommu_flush_write_buffer(iommu);
+
return nelems;
}
iommu_set_root_entry(iommu);
iommu->flush.flush_context(iommu, 0, 0, 0,
- DMA_CCMD_GLOBAL_INVL, 0);
+ DMA_CCMD_GLOBAL_INVL);
iommu->flush.flush_iotlb(iommu, 0, 0, 0,
- DMA_TLB_GLOBAL_FLUSH, 0);
+ DMA_TLB_GLOBAL_FLUSH);
iommu_disable_protect_mem_regions(iommu);
iommu_enable_translation(iommu);
}
for_each_active_iommu(iommu, drhd) {
iommu->flush.flush_context(iommu, 0, 0, 0,
- DMA_CCMD_GLOBAL_INVL, 0);
+ DMA_CCMD_GLOBAL_INVL);
iommu->flush.flush_iotlb(iommu, 0, 0, 0,
- DMA_TLB_GLOBAL_FLUSH, 0);
+ DMA_TLB_GLOBAL_FLUSH);
}
}
* Check the need for DMA-remapping initialization now.
* Above initialization will also be used by Interrupt-remapping.
*/
- if (no_iommu || swiotlb || dmar_disabled)
+ if (no_iommu || (swiotlb && !iommu_pass_through) || dmar_disabled)
return -ENODEV;
iommu_init_mempool();
init_timer(&unmap_timer);
force_iommu = 1;
- dma_ops = &intel_dma_ops;
+
+ if (!iommu_pass_through) {
+ printk(KERN_INFO
+ "Multi-level page-table translation for DMAR.\n");
+ dma_ops = &intel_dma_ops;
+ } else
+ printk(KERN_INFO
+ "DMAR: Pass through translation for DMAR.\n");
+
init_iommu_sysfs();
register_iommu(&intel_iommu_ops);
info->dev->dev.archdata.iommu = NULL;
spin_unlock_irqrestore(&device_domain_lock, flags);
+ iommu_disable_dev_iotlb(info);
iommu_detach_dev(iommu, info->bus, info->devfn);
iommu_detach_dependent_devices(iommu, pdev);
free_devinfo_mem(info);
spin_unlock_irqrestore(&device_domain_lock, flags1);
+ iommu_disable_dev_iotlb(info);
iommu = device_to_iommu(info->segment, info->bus, info->devfn);
iommu_detach_dev(iommu, info->bus, info->devfn);
iommu_detach_dependent_devices(iommu, info->dev);
return -EFAULT;
}
- ret = domain_context_mapping(dmar_domain, pdev);
+ ret = vm_domain_add_dev_info(dmar_domain, pdev);
if (ret)
return ret;
- ret = vm_domain_add_dev_info(dmar_domain, pdev);
+ ret = domain_context_mapping(dmar_domain, pdev, CONTEXT_TT_MULTI_LEVEL);
return ret;
}