Re: [PATCH v4 4/6] VT-d: add device IOTLB invalidation support

[Grant Grundler]

On Mon, Mar 23, 2009 at 03:59:00PM +0800, Yu Zhao wrote:
> Support device IOTLB invalidation to flush the translation cached
> in the Endpoint.
> 
> Signed-off-by: Yu Zhao <yu.zhao@xxxxxxxxx>
> ---
>  drivers/pci/dmar.c          |   77 ++++++++++++++++++++++++++++++++++++++----
>  include/linux/intel-iommu.h |   14 +++++++-
>  2 files changed, 82 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
> index 106bc45..494b167 100644
> --- a/drivers/pci/dmar.c
> +++ b/drivers/pci/dmar.c
> @@ -674,7 +674,8 @@ 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++;
> @@ -684,10 +685,13 @@ 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);
>  
>  	/*
> @@ -697,7 +701,11 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
>  	 */
>  	if (fault & DMA_FSTS_IQE) {
>  		head = readl(iommu->reg + DMAR_IQH_REG);
> -		if ((head >> 4) == index) {
> +		if ((head >> DMAR_IQ_OFFSET) == index) {

Yu,
DMAR_IQ_OFFSET should probably be called DMAR_IQ_SHIFT since it's used the
same way that "PAGE_SHIFT" is used.

I've looked through the rest of the code and don't see any problems.
But I also don't have a clue what "ITE" (in IOMMU context) is. I'm assuming
it has something to do with translation errors but have no idea about
where/when those are generated and what the outcome is.

thanks,
grant

> +			printk(KERN_ERR "VT-d detected invalid descriptor: "
> +				"low=%llx, high=%llx\n",
> +				(unsigned long long)qi->desc[index].low,
> +				(unsigned long long)qi->desc[index].high);
>  			memcpy(&qi->desc[index], &qi->desc[wait_index],
>  					sizeof(struct qi_desc));
>  			__iommu_flush_cache(iommu, &qi->desc[index],
> @@ -707,6 +715,32 @@ 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;
>  }
>  
> @@ -716,7 +750,7 @@ 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;
> @@ -727,6 +761,9 @@ 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);
> @@ -757,7 +794,7 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
>  	 * update the HW tail register indicating the presence of
>  	 * new descriptors.
>  	 */
> -	writel(qi->free_head << 4, iommu->reg + DMAR_IQT_REG);
> +	writel(qi->free_head << DMAR_IQ_OFFSET, iommu->reg + DMAR_IQT_REG);
>  
>  	while (qi->desc_status[wait_index] != QI_DONE) {
>  		/*
> @@ -769,18 +806,21 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
>  		 */
>  		rc = qi_check_fault(iommu, index);
>  		if (rc)
> -			goto out;
> +			break;
>  
>  		spin_unlock(&qi->q_lock);
>  		cpu_relax();
>  		spin_lock(&qi->q_lock);
>  	}
> -out:
> -	qi->desc_status[index] = qi->desc_status[wait_index] = QI_DONE;
> +
> +	qi->desc_status[index] = QI_DONE;
>  
>  	reclaim_free_desc(qi);
>  	spin_unlock_irqrestore(&qi->q_lock, flags);
>  
> +	if (rc == -EAGAIN)
> +		goto restart;
> +
>  	return rc;
>  }
>  
> @@ -847,6 +887,27 @@ 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 660a7f4..a32b3db 100644
> --- a/include/linux/intel-iommu.h
> +++ b/include/linux/intel-iommu.h
> @@ -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_OFFSET	4	/* Invalidation queue head/tail offset */
>  #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 */
> @@ -195,6 +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 */
> @@ -223,7 +226,8 @@ do {									\
>  enum {
>  	QI_FREE,
>  	QI_IN_USE,
> -	QI_DONE
> +	QI_DONE,
> +	QI_ABORT
>  };
>  
>  #define QI_CC_TYPE		0x1
> @@ -252,6 +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;
>  };
> @@ -329,6 +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);
>  
> -- 
> 1.5.6.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pci" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
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/