提交 ba395927 编写于 作者: K Keshavamurthy, Anil S 提交者: Linus Torvalds

Intel IOMMU: Intel IOMMU driver

Actual intel IOMMU driver.  Hardware spec can be found at:
http://www.intel.com/technology/virtualization

This driver sets X86_64 'dma_ops', so hook into standard DMA APIs.  In this
way, PCI driver will get virtual DMA address.  This change is transparent to
PCI drivers.

[akpm@linux-foundation.org: remove unneeded cast]
[akpm@linux-foundation.org: build fix]
[bunk@stusta.de: fix duplicate CONFIG_DMAR Makefile line]
Signed-off-by: NAnil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 f8de50eb
Linux IOMMU Support
===================
The architecture spec can be obtained from the below location.
http://www.intel.com/technology/virtualization/
This guide gives a quick cheat sheet for some basic understanding.
Some Keywords
DMAR - DMA remapping
DRHD - DMA Engine Reporting Structure
RMRR - Reserved memory Region Reporting Structure
ZLR - Zero length reads from PCI devices
IOVA - IO Virtual address.
Basic stuff
-----------
ACPI enumerates and lists the different DMA engines in the platform, and
device scope relationships between PCI devices and which DMA engine controls
them.
What is RMRR?
-------------
There are some devices the BIOS controls, for e.g USB devices to perform
PS2 emulation. The regions of memory used for these devices are marked
reserved in the e820 map. When we turn on DMA translation, DMA to those
regions will fail. Hence BIOS uses RMRR to specify these regions along with
devices that need to access these regions. OS is expected to setup
unity mappings for these regions for these devices to access these regions.
How is IOVA generated?
---------------------
Well behaved drivers call pci_map_*() calls before sending command to device
that needs to perform DMA. Once DMA is completed and mapping is no longer
required, device performs a pci_unmap_*() calls to unmap the region.
The Intel IOMMU driver allocates a virtual address per domain. Each PCIE
device has its own domain (hence protection). Devices under p2p bridges
share the virtual address with all devices under the p2p bridge due to
transaction id aliasing for p2p bridges.
IOVA generation is pretty generic. We used the same technique as vmalloc()
but these are not global address spaces, but separate for each domain.
Different DMA engines may support different number of domains.
We also allocate gaurd pages with each mapping, so we can attempt to catch
any overflow that might happen.
Graphics Problems?
------------------
If you encounter issues with graphics devices, you can try adding
option intel_iommu=igfx_off to turn off the integrated graphics engine.
Some exceptions to IOVA
-----------------------
Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff).
The same is true for peer to peer transactions. Hence we reserve the
address from PCI MMIO ranges so they are not allocated for IOVA addresses.
Boot Message Sample
-------------------
Something like this gets printed indicating presence of DMAR tables
in ACPI.
ACPI: DMAR (v001 A M I OEMDMAR 0x00000001 MSFT 0x00000097) @ 0x000000007f5b5ef0
When DMAR is being processed and initialized by ACPI, prints DMAR locations
and any RMRR's processed.
ACPI DMAR:Host address width 36
ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff
ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff
When DMAR is enabled for use, you will notice..
PCI-DMA: Using DMAR IOMMU
TBD
----
- For compatibility testing, could use unity map domain for all devices, just
provide a 1-1 for all useful memory under a single domain for all devices.
- API for paravirt ops for abstracting functionlity for VMM folks.
......@@ -772,6 +772,16 @@ and is between 256 and 4096 characters. It is defined in the file
inttest= [IA64]
intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option
off
Disable intel iommu driver.
igfx_off [Default Off]
By default, gfx is mapped as normal device. If a gfx
device has a dedicated DMAR unit, the DMAR unit is
bypassed by not enabling DMAR with this option. In
this case, gfx device will use physical address for
DMA.
io7= [HW] IO7 for Marvel based alpha systems
See comment before marvel_specify_io7 in
arch/alpha/kernel/core_marvel.c.
......
......@@ -7,6 +7,7 @@
#include <linux/string.h>
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/dmar.h>
#include <asm/io.h>
#include <asm/iommu.h>
#include <asm/calgary.h>
......@@ -305,6 +306,8 @@ void __init pci_iommu_alloc(void)
detect_calgary();
#endif
detect_intel_iommu();
#ifdef CONFIG_SWIOTLB
pci_swiotlb_init();
#endif
......@@ -316,6 +319,8 @@ static int __init pci_iommu_init(void)
calgary_iommu_init();
#endif
intel_iommu_init();
#ifdef CONFIG_IOMMU
gart_iommu_init();
#endif
......
......@@ -21,7 +21,7 @@ obj-$(CONFIG_PCI_MSI) += msi.o
obj-$(CONFIG_HT_IRQ) += htirq.o
# Build Intel IOMMU support
obj-$(CONFIG_DMAR) += dmar.o
obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
#
# Some architectures use the generic PCI setup functions
......
此差异已折叠。
/*
* Copyright (c) 2006, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, write to the Free Software Foundation, Inc., 59 Temple
* Place - Suite 330, Boston, MA 02111-1307 USA.
*
* Copyright (C) Ashok Raj <ashok.raj@intel.com>
* Copyright (C) Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
*/
#ifndef _INTEL_IOMMU_H_
#define _INTEL_IOMMU_H_
#include <linux/types.h>
#include <linux/msi.h>
#include "iova.h"
#include <linux/io.h>
/*
* Intel IOMMU register specification per version 1.0 public spec.
*/
#define DMAR_VER_REG 0x0 /* Arch version supported by this IOMMU */
#define DMAR_CAP_REG 0x8 /* Hardware supported capabilities */
#define DMAR_ECAP_REG 0x10 /* Extended capabilities supported */
#define DMAR_GCMD_REG 0x18 /* Global command register */
#define DMAR_GSTS_REG 0x1c /* Global status register */
#define DMAR_RTADDR_REG 0x20 /* Root entry table */
#define DMAR_CCMD_REG 0x28 /* Context command reg */
#define DMAR_FSTS_REG 0x34 /* Fault Status register */
#define DMAR_FECTL_REG 0x38 /* Fault control register */
#define DMAR_FEDATA_REG 0x3c /* Fault event interrupt data register */
#define DMAR_FEADDR_REG 0x40 /* Fault event interrupt addr register */
#define DMAR_FEUADDR_REG 0x44 /* Upper address register */
#define DMAR_AFLOG_REG 0x58 /* Advanced Fault control */
#define DMAR_PMEN_REG 0x64 /* Enable Protected Memory Region */
#define DMAR_PLMBASE_REG 0x68 /* PMRR Low addr */
#define DMAR_PLMLIMIT_REG 0x6c /* PMRR low limit */
#define DMAR_PHMBASE_REG 0x70 /* pmrr high base addr */
#define DMAR_PHMLIMIT_REG 0x78 /* pmrr high limit */
#define OFFSET_STRIDE (9)
/*
#define dmar_readl(dmar, reg) readl(dmar + reg)
#define dmar_readq(dmar, reg) ({ \
u32 lo, hi; \
lo = readl(dmar + reg); \
hi = readl(dmar + reg + 4); \
(((u64) hi) << 32) + lo; })
*/
static inline u64 dmar_readq(void *addr)
{
u32 lo, hi;
lo = readl(addr);
hi = readl(addr + 4);
return (((u64) hi) << 32) + lo;
}
static inline void dmar_writeq(void __iomem *addr, u64 val)
{
writel((u32)val, addr);
writel((u32)(val >> 32), addr + 4);
}
#define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4)
#define DMAR_VER_MINOR(v) ((v) & 0x0f)
/*
* Decoding Capability Register
*/
#define cap_read_drain(c) (((c) >> 55) & 1)
#define cap_write_drain(c) (((c) >> 54) & 1)
#define cap_max_amask_val(c) (((c) >> 48) & 0x3f)
#define cap_num_fault_regs(c) ((((c) >> 40) & 0xff) + 1)
#define cap_pgsel_inv(c) (((c) >> 39) & 1)
#define cap_super_page_val(c) (((c) >> 34) & 0xf)
#define cap_super_offset(c) (((find_first_bit(&cap_super_page_val(c), 4)) \
* OFFSET_STRIDE) + 21)
#define cap_fault_reg_offset(c) ((((c) >> 24) & 0x3ff) * 16)
#define cap_max_fault_reg_offset(c) \
(cap_fault_reg_offset(c) + cap_num_fault_regs(c) * 16)
#define cap_zlr(c) (((c) >> 22) & 1)
#define cap_isoch(c) (((c) >> 23) & 1)
#define cap_mgaw(c) ((((c) >> 16) & 0x3f) + 1)
#define cap_sagaw(c) (((c) >> 8) & 0x1f)
#define cap_caching_mode(c) (((c) >> 7) & 1)
#define cap_phmr(c) (((c) >> 6) & 1)
#define cap_plmr(c) (((c) >> 5) & 1)
#define cap_rwbf(c) (((c) >> 4) & 1)
#define cap_afl(c) (((c) >> 3) & 1)
#define cap_ndoms(c) (((unsigned long)1) << (4 + 2 * ((c) & 0x7)))
/*
* Extended Capability Register
*/
#define ecap_niotlb_iunits(e) ((((e) >> 24) & 0xff) + 1)
#define ecap_iotlb_offset(e) ((((e) >> 8) & 0x3ff) * 16)
#define ecap_max_iotlb_offset(e) \
(ecap_iotlb_offset(e) + ecap_niotlb_iunits(e) * 16)
#define ecap_coherent(e) ((e) & 0x1)
/* IOTLB_REG */
#define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60)
#define DMA_TLB_DSI_FLUSH (((u64)2) << 60)
#define DMA_TLB_PSI_FLUSH (((u64)3) << 60)
#define DMA_TLB_IIRG(type) ((type >> 60) & 7)
#define DMA_TLB_IAIG(val) (((val) >> 57) & 7)
#define DMA_TLB_READ_DRAIN (((u64)1) << 49)
#define DMA_TLB_WRITE_DRAIN (((u64)1) << 48)
#define DMA_TLB_DID(id) (((u64)((id) & 0xffff)) << 32)
#define DMA_TLB_IVT (((u64)1) << 63)
#define DMA_TLB_IH_NONLEAF (((u64)1) << 6)
#define DMA_TLB_MAX_SIZE (0x3f)
/* GCMD_REG */
#define DMA_GCMD_TE (((u32)1) << 31)
#define DMA_GCMD_SRTP (((u32)1) << 30)
#define DMA_GCMD_SFL (((u32)1) << 29)
#define DMA_GCMD_EAFL (((u32)1) << 28)
#define DMA_GCMD_WBF (((u32)1) << 27)
/* GSTS_REG */
#define DMA_GSTS_TES (((u32)1) << 31)
#define DMA_GSTS_RTPS (((u32)1) << 30)
#define DMA_GSTS_FLS (((u32)1) << 29)
#define DMA_GSTS_AFLS (((u32)1) << 28)
#define DMA_GSTS_WBFS (((u32)1) << 27)
/* CCMD_REG */
#define DMA_CCMD_ICC (((u64)1) << 63)
#define DMA_CCMD_GLOBAL_INVL (((u64)1) << 61)
#define DMA_CCMD_DOMAIN_INVL (((u64)2) << 61)
#define DMA_CCMD_DEVICE_INVL (((u64)3) << 61)
#define DMA_CCMD_FM(m) (((u64)((m) & 0x3)) << 32)
#define DMA_CCMD_MASK_NOBIT 0
#define DMA_CCMD_MASK_1BIT 1
#define DMA_CCMD_MASK_2BIT 2
#define DMA_CCMD_MASK_3BIT 3
#define DMA_CCMD_SID(s) (((u64)((s) & 0xffff)) << 16)
#define DMA_CCMD_DID(d) ((u64)((d) & 0xffff))
/* FECTL_REG */
#define DMA_FECTL_IM (((u32)1) << 31)
/* FSTS_REG */
#define DMA_FSTS_PPF ((u32)2)
#define DMA_FSTS_PFO ((u32)1)
#define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff)
/* FRCD_REG, 32 bits access */
#define DMA_FRCD_F (((u32)1) << 31)
#define dma_frcd_type(d) ((d >> 30) & 1)
#define dma_frcd_fault_reason(c) (c & 0xff)
#define dma_frcd_source_id(c) (c & 0xffff)
#define dma_frcd_page_addr(d) (d & (((u64)-1) << 12)) /* low 64 bit */
/*
* 0: Present
* 1-11: Reserved
* 12-63: Context Ptr (12 - (haw-1))
* 64-127: Reserved
*/
struct root_entry {
u64 val;
u64 rsvd1;
};
#define ROOT_ENTRY_NR (PAGE_SIZE_4K/sizeof(struct root_entry))
static inline bool root_present(struct root_entry *root)
{
return (root->val & 1);
}
static inline void set_root_present(struct root_entry *root)
{
root->val |= 1;
}
static inline void set_root_value(struct root_entry *root, unsigned long value)
{
root->val |= value & PAGE_MASK_4K;
}
struct context_entry;
static inline struct context_entry *
get_context_addr_from_root(struct root_entry *root)
{
return (struct context_entry *)
(root_present(root)?phys_to_virt(
root->val & PAGE_MASK_4K):
NULL);
}
/*
* low 64 bits:
* 0: present
* 1: fault processing disable
* 2-3: translation type
* 12-63: address space root
* high 64 bits:
* 0-2: address width
* 3-6: aval
* 8-23: domain id
*/
struct context_entry {
u64 lo;
u64 hi;
};
#define context_present(c) ((c).lo & 1)
#define context_fault_disable(c) (((c).lo >> 1) & 1)
#define context_translation_type(c) (((c).lo >> 2) & 3)
#define context_address_root(c) ((c).lo & PAGE_MASK_4K)
#define context_address_width(c) ((c).hi & 7)
#define context_domain_id(c) (((c).hi >> 8) & ((1 << 16) - 1))
#define context_set_present(c) do {(c).lo |= 1;} while (0)
#define context_set_fault_enable(c) \
do {(c).lo &= (((u64)-1) << 2) | 1;} while (0)
#define context_set_translation_type(c, val) \
do { \
(c).lo &= (((u64)-1) << 4) | 3; \
(c).lo |= ((val) & 3) << 2; \
} while (0)
#define CONTEXT_TT_MULTI_LEVEL 0
#define context_set_address_root(c, val) \
do {(c).lo |= (val) & PAGE_MASK_4K;} while (0)
#define context_set_address_width(c, val) do {(c).hi |= (val) & 7;} while (0)
#define context_set_domain_id(c, val) \
do {(c).hi |= ((val) & ((1 << 16) - 1)) << 8;} while (0)
#define context_clear_entry(c) do {(c).lo = 0; (c).hi = 0;} while (0)
/*
* 0: readable
* 1: writable
* 2-6: reserved
* 7: super page
* 8-11: available
* 12-63: Host physcial address
*/
struct dma_pte {
u64 val;
};
#define dma_clear_pte(p) do {(p).val = 0;} while (0)
#define DMA_PTE_READ (1)
#define DMA_PTE_WRITE (2)
#define dma_set_pte_readable(p) do {(p).val |= DMA_PTE_READ;} while (0)
#define dma_set_pte_writable(p) do {(p).val |= DMA_PTE_WRITE;} while (0)
#define dma_set_pte_prot(p, prot) \
do {(p).val = ((p).val & ~3) | ((prot) & 3); } while (0)
#define dma_pte_addr(p) ((p).val & PAGE_MASK_4K)
#define dma_set_pte_addr(p, addr) do {\
(p).val |= ((addr) & PAGE_MASK_4K); } while (0)
#define dma_pte_present(p) (((p).val & 3) != 0)
struct intel_iommu;
struct dmar_domain {
int id; /* domain id */
struct intel_iommu *iommu; /* back pointer to owning iommu */
struct list_head devices; /* all devices' list */
struct iova_domain iovad; /* iova's that belong to this domain */
struct dma_pte *pgd; /* virtual address */
spinlock_t mapping_lock; /* page table lock */
int gaw; /* max guest address width */
/* adjusted guest address width, 0 is level 2 30-bit */
int agaw;
#define DOMAIN_FLAG_MULTIPLE_DEVICES 1
int flags;
};
/* PCI domain-device relationship */
struct device_domain_info {
struct list_head link; /* link to domain siblings */
struct list_head global; /* link to global list */
u8 bus; /* PCI bus numer */
u8 devfn; /* PCI devfn number */
struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
struct dmar_domain *domain; /* pointer to domain */
};
extern int init_dmars(void);
struct intel_iommu {
void __iomem *reg; /* Pointer to hardware regs, virtual addr */
u64 cap;
u64 ecap;
unsigned long *domain_ids; /* bitmap of domains */
struct dmar_domain **domains; /* ptr to domains */
int seg;
u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */
spinlock_t lock; /* protect context, domain ids */
spinlock_t register_lock; /* protect register handling */
struct root_entry *root_entry; /* virtual address */
unsigned int irq;
unsigned char name[7]; /* Device Name */
struct msi_msg saved_msg;
struct sys_device sysdev;
};
#endif
......@@ -23,7 +23,14 @@
#include <linux/acpi.h>
#include <linux/types.h>
#include <linux/msi.h>
#ifdef CONFIG_DMAR
struct intel_iommu;
/* Intel IOMMU detection and initialization functions */
extern void detect_intel_iommu(void);
extern int intel_iommu_init(void);
extern int dmar_table_init(void);
extern int early_dmar_detect(void);
......@@ -49,4 +56,19 @@ struct dmar_rmrr_unit {
int devices_cnt; /* target device count */
};
#define for_each_drhd_unit(drhd) \
list_for_each_entry(drhd, &dmar_drhd_units, list)
#define for_each_rmrr_units(rmrr) \
list_for_each_entry(rmrr, &dmar_rmrr_units, list)
#else
static inline void detect_intel_iommu(void)
{
return;
}
static inline int intel_iommu_init(void)
{
return -ENODEV;
}
#endif /* !CONFIG_DMAR */
#endif /* __DMAR_H__ */
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册