Commit 687d6809 authored by Linus Torvalds's avatar Linus Torvalds

Merge git://git.infradead.org/~dwmw2/iommu-2.6.31

* git://git.infradead.org/~dwmw2/iommu-2.6.31:
  intel-iommu: Fix one last ia64 build problem in Pass Through Support
  VT-d: support the device IOTLB
  VT-d: cleanup iommu_flush_iotlb_psi and flush_unmaps
  VT-d: add device IOTLB invalidation support
  VT-d: parse ATSR in DMA Remapping Reporting Structure
  PCI: handle Virtual Function ATS enabling
  PCI: support the ATS capability
  intel-iommu: dmar_set_interrupt return error value
  intel-iommu: Tidy up iommu->gcmd handling
  intel-iommu: Fix tiny theoretical race in write-buffer flush.
  intel-iommu: Clean up handling of "caching mode" vs. IOTLB flushing.
  intel-iommu: Clean up handling of "caching mode" vs. context flushing.
  VT-d: fix invalid domain id for KVM context flush
  Fix !CONFIG_DMAR build failure introduced by Intel IOMMU Pass Through Support
  Intel IOMMU Pass Through Support

Fix up trivial conflicts in drivers/pci/{intel-iommu.c,intr_remapping.c}
parents 10534140 008fe148
......@@ -1006,6 +1006,7 @@ and is between 256 and 4096 characters. It is defined in the file
nomerge
forcesac
soft
pt [x86, IA64]
io7= [HW] IO7 for Marvel based alpha systems
See comment before marvel_specify_io7 in
......
......@@ -9,6 +9,11 @@ extern void pci_iommu_shutdown(void);
extern void no_iommu_init(void);
extern int force_iommu, no_iommu;
extern int iommu_detected;
#ifdef CONFIG_DMAR
extern int iommu_pass_through;
#else
#define iommu_pass_through (0)
#endif
extern void iommu_dma_init(void);
extern void machvec_init(const char *name);
......
......@@ -32,6 +32,8 @@ int force_iommu __read_mostly = 1;
int force_iommu __read_mostly;
#endif
int iommu_pass_through;
/* Dummy device used for NULL arguments (normally ISA). Better would
be probably a smaller DMA mask, but this is bug-to-bug compatible
to i386. */
......
......@@ -46,7 +46,7 @@ void __init swiotlb_dma_init(void)
void __init pci_swiotlb_init(void)
{
if (!iommu_detected) {
if (!iommu_detected || iommu_pass_through) {
#ifdef CONFIG_IA64_GENERIC
swiotlb = 1;
printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n");
......
......@@ -6,6 +6,7 @@ extern void no_iommu_init(void);
extern struct dma_map_ops nommu_dma_ops;
extern int force_iommu, no_iommu;
extern int iommu_detected;
extern int iommu_pass_through;
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
......
......@@ -32,6 +32,8 @@ int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
int iommu_pass_through;
dma_addr_t bad_dma_address __read_mostly = 0;
EXPORT_SYMBOL(bad_dma_address);
......@@ -209,6 +211,10 @@ static __init int iommu_setup(char *p)
#ifdef CONFIG_SWIOTLB
if (!strncmp(p, "soft", 4))
swiotlb = 1;
if (!strncmp(p, "pt", 2)) {
iommu_pass_through = 1;
return 1;
}
#endif
gart_parse_options(p);
......
......@@ -71,7 +71,8 @@ void __init pci_swiotlb_init(void)
{
/* don't initialize swiotlb if iommu=off (no_iommu=1) */
#ifdef CONFIG_X86_64
if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN)
if ((!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN) ||
iommu_pass_through)
swiotlb = 1;
#endif
if (swiotlb_force)
......
This diff is collapsed.
This diff is collapsed.
......@@ -409,7 +409,7 @@ int free_irte(int irq)
static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
{
u64 addr;
u32 cmd, sts;
u32 sts;
unsigned long flags;
addr = virt_to_phys((void *)iommu->ir_table->base);
......@@ -420,9 +420,8 @@ static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
(addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
/* Set interrupt-remapping table pointer */
cmd = iommu->gcmd | DMA_GCMD_SIRTP;
iommu->gcmd |= DMA_GCMD_SIRTP;
writel(cmd, iommu->reg + DMAR_GCMD_REG);
writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
readl, (sts & DMA_GSTS_IRTPS), sts);
......@@ -437,9 +436,8 @@ static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
spin_lock_irqsave(&iommu->register_lock, flags);
/* Enable interrupt-remapping */
cmd = iommu->gcmd | DMA_GCMD_IRE;
iommu->gcmd |= DMA_GCMD_IRE;
writel(cmd, iommu->reg + DMAR_GCMD_REG);
writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
readl, (sts & DMA_GSTS_IRES), sts);
......
......@@ -5,6 +5,7 @@
*
* PCI Express I/O Virtualization (IOV) support.
* Single Root IOV 1.0
* Address Translation Service 1.0
*/
#include <linux/pci.h>
......@@ -492,10 +493,10 @@ static int sriov_init(struct pci_dev *dev, int pos)
if (pdev)
iov->dev = pci_dev_get(pdev);
else {
else
iov->dev = dev;
mutex_init(&iov->lock);
}
dev->sriov = iov;
dev->is_physfn = 1;
......@@ -515,11 +516,11 @@ static void sriov_release(struct pci_dev *dev)
{
BUG_ON(dev->sriov->nr_virtfn);
if (dev == dev->sriov->dev)
mutex_destroy(&dev->sriov->lock);
else
if (dev != dev->sriov->dev)
pci_dev_put(dev->sriov->dev);
mutex_destroy(&dev->sriov->lock);
kfree(dev->sriov);
dev->sriov = NULL;
}
......@@ -681,3 +682,145 @@ irqreturn_t pci_sriov_migration(struct pci_dev *dev)
return sriov_migration(dev) ? IRQ_HANDLED : IRQ_NONE;
}
EXPORT_SYMBOL_GPL(pci_sriov_migration);
static int ats_alloc_one(struct pci_dev *dev, int ps)
{
int pos;
u16 cap;
struct pci_ats *ats;
pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
if (!pos)
return -ENODEV;
ats = kzalloc(sizeof(*ats), GFP_KERNEL);
if (!ats)
return -ENOMEM;
ats->pos = pos;
ats->stu = ps;
pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
ats->qdep = PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
PCI_ATS_MAX_QDEP;
dev->ats = ats;
return 0;
}
static void ats_free_one(struct pci_dev *dev)
{
kfree(dev->ats);
dev->ats = NULL;
}
/**
* pci_enable_ats - enable the ATS capability
* @dev: the PCI device
* @ps: the IOMMU page shift
*
* Returns 0 on success, or negative on failure.
*/
int pci_enable_ats(struct pci_dev *dev, int ps)
{
int rc;
u16 ctrl;
BUG_ON(dev->ats && dev->ats->is_enabled);
if (ps < PCI_ATS_MIN_STU)
return -EINVAL;
if (dev->is_physfn || dev->is_virtfn) {
struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
mutex_lock(&pdev->sriov->lock);
if (pdev->ats)
rc = pdev->ats->stu == ps ? 0 : -EINVAL;
else
rc = ats_alloc_one(pdev, ps);
if (!rc)
pdev->ats->ref_cnt++;
mutex_unlock(&pdev->sriov->lock);
if (rc)
return rc;
}
if (!dev->is_physfn) {
rc = ats_alloc_one(dev, ps);
if (rc)
return rc;
}
ctrl = PCI_ATS_CTRL_ENABLE;
if (!dev->is_virtfn)
ctrl |= PCI_ATS_CTRL_STU(ps - PCI_ATS_MIN_STU);
pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
dev->ats->is_enabled = 1;
return 0;
}
/**
* pci_disable_ats - disable the ATS capability
* @dev: the PCI device
*/
void pci_disable_ats(struct pci_dev *dev)
{
u16 ctrl;
BUG_ON(!dev->ats || !dev->ats->is_enabled);
pci_read_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, &ctrl);
ctrl &= ~PCI_ATS_CTRL_ENABLE;
pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
dev->ats->is_enabled = 0;
if (dev->is_physfn || dev->is_virtfn) {
struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
mutex_lock(&pdev->sriov->lock);
pdev->ats->ref_cnt--;
if (!pdev->ats->ref_cnt)
ats_free_one(pdev);
mutex_unlock(&pdev->sriov->lock);
}
if (!dev->is_physfn)
ats_free_one(dev);
}
/**
* pci_ats_queue_depth - query the ATS Invalidate Queue Depth
* @dev: the PCI device
*
* Returns the queue depth on success, or negative on failure.
*
* The ATS spec uses 0 in the Invalidate Queue Depth field to
* indicate that the function can accept 32 Invalidate Request.
* But here we use the `real' values (i.e. 1~32) for the Queue
* Depth; and 0 indicates the function shares the Queue with
* other functions (doesn't exclusively own a Queue).
*/
int pci_ats_queue_depth(struct pci_dev *dev)
{
int pos;
u16 cap;
if (dev->is_virtfn)
return 0;
if (dev->ats)
return dev->ats->qdep;
pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
if (!pos)
return -ENODEV;
pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
return PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
PCI_ATS_MAX_QDEP;
}
......@@ -229,6 +229,15 @@ struct pci_sriov {
u8 __iomem *mstate; /* VF Migration State Array */
};
/* Address Translation Service */
struct pci_ats {
int pos; /* capability position */
int stu; /* Smallest Translation Unit */
int qdep; /* Invalidate Queue Depth */
int ref_cnt; /* Physical Function reference count */
int is_enabled:1; /* Enable bit is set */
};
#ifdef CONFIG_PCI_IOV
extern int pci_iov_init(struct pci_dev *dev);
extern void pci_iov_release(struct pci_dev *dev);
......@@ -236,6 +245,20 @@ extern int pci_iov_resource_bar(struct pci_dev *dev, int resno,
enum pci_bar_type *type);
extern void pci_restore_iov_state(struct pci_dev *dev);
extern int pci_iov_bus_range(struct pci_bus *bus);
extern int pci_enable_ats(struct pci_dev *dev, int ps);
extern void pci_disable_ats(struct pci_dev *dev);
extern int pci_ats_queue_depth(struct pci_dev *dev);
/**
* pci_ats_enabled - query the ATS status
* @dev: the PCI device
*
* Returns 1 if ATS capability is enabled, or 0 if not.
*/
static inline int pci_ats_enabled(struct pci_dev *dev)
{
return dev->ats && dev->ats->is_enabled;
}
#else
static inline int pci_iov_init(struct pci_dev *dev)
{
......@@ -257,6 +280,22 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)
{
return 0;
}
static inline int pci_enable_ats(struct pci_dev *dev, int ps)
{
return -ENODEV;
}
static inline void pci_disable_ats(struct pci_dev *dev)
{
}
static inline int pci_ats_queue_depth(struct pci_dev *dev)
{
return -ENODEV;
}
static inline int pci_ats_enabled(struct pci_dev *dev)
{
return 0;
}
#endif /* CONFIG_PCI_IOV */
#endif /* DRIVERS_PCI_H */
......@@ -13,6 +13,10 @@
#define DMA_PTE_WRITE (2)
#define DMA_PTE_SNP (1 << 11)
#define CONTEXT_TT_MULTI_LEVEL 0
#define CONTEXT_TT_DEV_IOTLB 1
#define CONTEXT_TT_PASS_THROUGH 2
struct intel_iommu;
struct dmar_domain;
struct root_entry;
......@@ -21,11 +25,16 @@ extern void free_dmar_iommu(struct intel_iommu *iommu);
#ifdef CONFIG_DMAR
extern int iommu_calculate_agaw(struct intel_iommu *iommu);
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
{
return 0;
}
static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
{
return 0;
}
#endif
extern int dmar_disabled;
......
......@@ -188,6 +188,15 @@ struct dmar_rmrr_unit {
#define for_each_rmrr_units(rmrr) \
list_for_each_entry(rmrr, &dmar_rmrr_units, list)
struct dmar_atsr_unit {
struct list_head list; /* list of ATSR units */
struct acpi_dmar_header *hdr; /* ACPI header */
struct pci_dev **devices; /* target devices */
int devices_cnt; /* target device count */
u8 include_all:1; /* include all ports */
};
/* Intel DMAR initialization functions */
extern int intel_iommu_init(void);
#else
......
......@@ -53,6 +53,7 @@
#define DMAR_PHMLIMIT_REG 0x78 /* pmrr high limit */
#define DMAR_IQH_REG 0x80 /* Invalidation queue head register */
#define DMAR_IQT_REG 0x88 /* Invalidation queue tail register */
#define DMAR_IQ_SHIFT 4 /* Invalidation queue head/tail shift */
#define DMAR_IQA_REG 0x90 /* Invalidation queue addr register */
#define DMAR_ICS_REG 0x98 /* Invalidation complete status register */
#define DMAR_IRTA_REG 0xb8 /* Interrupt remapping table addr register */
......@@ -120,8 +121,10 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
(ecap_iotlb_offset(e) + ecap_niotlb_iunits(e) * 16)
#define ecap_coherent(e) ((e) & 0x1)
#define ecap_qis(e) ((e) & 0x2)
#define ecap_pass_through(e) ((e >> 6) & 0x1)
#define ecap_eim_support(e) ((e >> 4) & 0x1)
#define ecap_ir_support(e) ((e >> 3) & 0x1)
#define ecap_dev_iotlb_support(e) (((e) >> 2) & 0x1)
#define ecap_max_handle_mask(e) ((e >> 20) & 0xf)
#define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */
......@@ -197,6 +200,8 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
#define DMA_FSTS_PPF ((u32)2)
#define DMA_FSTS_PFO ((u32)1)
#define DMA_FSTS_IQE (1 << 4)
#define DMA_FSTS_ICE (1 << 5)
#define DMA_FSTS_ITE (1 << 6)
#define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff)
/* FRCD_REG, 32 bits access */
......@@ -225,7 +230,8 @@ do { \
enum {
QI_FREE,
QI_IN_USE,
QI_DONE
QI_DONE,
QI_ABORT
};
#define QI_CC_TYPE 0x1
......@@ -254,6 +260,12 @@ enum {
#define QI_CC_DID(did) (((u64)did) << 16)
#define QI_CC_GRAN(gran) (((u64)gran) >> (DMA_CCMD_INVL_GRANU_OFFSET-4))
#define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32)
#define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16)
#define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK)
#define QI_DEV_IOTLB_SIZE 1
#define QI_DEV_IOTLB_MAX_INVS 32
struct qi_desc {
u64 low, high;
};
......@@ -280,10 +292,10 @@ struct ir_table {
#endif
struct iommu_flush {
int (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
u64 type, int non_present_entry_flush);
int (*flush_iotlb)(struct intel_iommu *iommu, u16 did, u64 addr,
unsigned int size_order, u64 type, int non_present_entry_flush);
void (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid,
u8 fm, u64 type);
void (*flush_iotlb)(struct intel_iommu *iommu, u16 did, u64 addr,
unsigned int size_order, u64 type);
};
enum {
......@@ -302,6 +314,7 @@ struct intel_iommu {
spinlock_t register_lock; /* protect register handling */
int seq_id; /* sequence id of the iommu */
int agaw; /* agaw of this iommu */
int msagaw; /* max sagaw of this iommu */
unsigned int irq;
unsigned char name[13]; /* Device Name */
......@@ -329,6 +342,7 @@ static inline void __iommu_flush_cache(
}
extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
extern int dmar_find_matched_atsr_unit(struct pci_dev *dev);
extern int alloc_iommu(struct dmar_drhd_unit *drhd);
extern void free_iommu(struct intel_iommu *iommu);
......@@ -337,11 +351,12 @@ extern void dmar_disable_qi(struct intel_iommu *iommu);
extern int dmar_reenable_qi(struct intel_iommu *iommu);
extern void qi_global_iec(struct intel_iommu *iommu);
extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
u8 fm, u64 type, int non_present_entry_flush);
extern int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
unsigned int size_order, u64 type,
int non_present_entry_flush);
extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
u8 fm, u64 type);
extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
unsigned int size_order, u64 type);
extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
u64 addr, unsigned mask);
extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
......
......@@ -196,6 +196,7 @@ struct pci_cap_saved_state {
struct pcie_link_state;
struct pci_vpd;
struct pci_sriov;
struct pci_ats;
/*
* The pci_dev structure is used to describe PCI devices.
......@@ -293,6 +294,7 @@ struct pci_dev {
struct pci_sriov *sriov; /* SR-IOV capability related */
struct pci_dev *physfn; /* the PF this VF is associated with */
};
struct pci_ats *ats; /* Address Translation Service */
#endif
};
......
......@@ -502,6 +502,7 @@
#define PCI_EXT_CAP_ID_DSN 3
#define PCI_EXT_CAP_ID_PWR 4
#define PCI_EXT_CAP_ID_ARI 14
#define PCI_EXT_CAP_ID_ATS 15
#define PCI_EXT_CAP_ID_SRIOV 16
/* Advanced Error Reporting */
......@@ -620,6 +621,15 @@
#define PCI_ARI_CTRL_ACS 0x0002 /* ACS Function Groups Enable */
#define PCI_ARI_CTRL_FG(x) (((x) >> 4) & 7) /* Function Group */
/* Address Translation Service */
#define PCI_ATS_CAP 0x04 /* ATS Capability Register */
#define PCI_ATS_CAP_QDEP(x) ((x) & 0x1f) /* Invalidate Queue Depth */
#define PCI_ATS_MAX_QDEP 32 /* Max Invalidate Queue Depth */
#define PCI_ATS_CTRL 0x06 /* ATS Control Register */
#define PCI_ATS_CTRL_ENABLE 0x8000 /* ATS Enable */
#define PCI_ATS_CTRL_STU(x) ((x) & 0x1f) /* Smallest Translation Unit */
#define PCI_ATS_MIN_STU 12 /* shift of minimum STU block */
/* Single Root I/O Virtualization */
#define PCI_SRIOV_CAP 0x04 /* SR-IOV Capabilities */
#define PCI_SRIOV_CAP_VFM 0x01 /* VF Migration Capable */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment