lkml.org 
[lkml]   [2009]   [Feb]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v3 4/6] VT-d: add device IOTLB invalidation support
Date
Support device IOTLB invalidation to flush the translation cached in the
Endpoint.

Signed-off-by: Yu Zhao <yu.zhao@intel.com>
---
drivers/pci/dmar.c | 63 ++++++++++++++++++++++++++++++++++++++++--
include/linux/intel-iommu.h | 13 ++++++++-
2 files changed, 72 insertions(+), 4 deletions(-)
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 66dda07..93b38e7 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -664,7 +664,8 @@ void free_iommu(struct intel_iommu *iommu)
*/
static inline void reclaim_free_desc(struct q_inval *qi)
{
- while (qi->desc_status[qi->free_tail] == QI_DONE) {
+ while (qi->desc_status[qi->free_tail] == QI_DONE ||
+ qi->desc_status[qi->free_tail] == QI_ABORT) {
qi->desc_status[qi->free_tail] = QI_FREE;
qi->free_tail = (qi->free_tail + 1) % QI_LENGTH;
qi->free_cnt++;
@@ -674,10 +675,13 @@ static inline void reclaim_free_desc(struct q_inval *qi)
static int qi_check_fault(struct intel_iommu *iommu, int index)
{
u32 fault;
- int head;
+ int head, tail;
struct q_inval *qi = iommu->qi;
int wait_index = (index + 1) % QI_LENGTH;

+ if (qi->desc_status[wait_index] == QI_ABORT)
+ return -EAGAIN;
+
fault = readl(iommu->reg + DMAR_FSTS_REG);

/*
@@ -701,6 +705,32 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
}
}

+ /*
+ * If ITE happens, all pending wait_desc commands are aborted.
+ * No new descriptors are fetched until the ITE is cleared.
+ */
+ if (fault & DMA_FSTS_ITE) {
+ head = readl(iommu->reg + DMAR_IQH_REG);
+ head = ((head >> DMAR_IQ_OFFSET) - 1 + QI_LENGTH) % QI_LENGTH;
+ head |= 1;
+ tail = readl(iommu->reg + DMAR_IQT_REG);
+ tail = ((tail >> DMAR_IQ_OFFSET) - 1 + QI_LENGTH) % QI_LENGTH;
+
+ writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
+
+ do {
+ if (qi->desc_status[head] == QI_IN_USE)
+ qi->desc_status[head] = QI_ABORT;
+ head = (head - 2 + QI_LENGTH) % QI_LENGTH;
+ } while (head != tail);
+
+ if (qi->desc_status[wait_index] == QI_ABORT)
+ return -EAGAIN;
+ }
+
+ if (fault & DMA_FSTS_ICE)
+ writel(DMA_FSTS_ICE, iommu->reg + DMAR_FSTS_REG);
+
return 0;
}

@@ -710,7 +740,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
*/
int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
{
- int rc = 0;
+ int rc;
struct q_inval *qi = iommu->qi;
struct qi_desc *hw, wait_desc;
int wait_index, index;
@@ -721,6 +751,9 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)

hw = qi->desc;

+restart:
+ rc = 0;
+
spin_lock_irqsave(&qi->q_lock, flags);
while (qi->free_cnt < 3) {
spin_unlock_irqrestore(&qi->q_lock, flags);
@@ -775,6 +808,9 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
reclaim_free_desc(qi);
spin_unlock_irqrestore(&qi->q_lock, flags);

+ if (rc == -EAGAIN)
+ goto restart;
+
return rc;
}

@@ -841,6 +877,27 @@ int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
return qi_submit_sync(&desc, iommu);
}

+int qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
+ u64 addr, unsigned mask)
+{
+ struct qi_desc desc;
+
+ if (mask) {
+ BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
+ addr |= (1 << (VTD_PAGE_SHIFT + mask - 1)) - 1;
+ desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
+ } else
+ desc.high = QI_DEV_IOTLB_ADDR(addr);
+
+ if (qdep >= QI_DEV_IOTLB_MAX_INVS)
+ qdep = 0;
+
+ desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
+ QI_DIOTLB_TYPE;
+
+ return qi_submit_sync(&desc, iommu);
+}
+
/*
* Enable Queued Invalidation interface. This is a must to support
* interrupt-remapping. Also used by DMA-remapping, which replaces
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 0a220c9..d82bdac 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -196,6 +196,8 @@ 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 */
@@ -224,7 +226,8 @@ do { \
enum {
QI_FREE,
QI_IN_USE,
- QI_DONE
+ QI_DONE,
+ QI_ABORT
};

#define QI_CC_TYPE 0x1
@@ -253,6 +256,12 @@ 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;
};
@@ -330,6 +339,8 @@ extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
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 int 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);

--
1.6.1


\
 
 \ /
  Last update: 2009-02-13 03:55    [from the cache]
©2003-2011 Jasper Spaans