[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5ad35536-4993-13f1-5199-ddd99f7009e5@redhat.com>
Date: Sat, 27 Apr 2019 11:04:04 +0200
From: Auger Eric <eric.auger@...hat.com>
To: Jacob Pan <jacob.jun.pan@...ux.intel.com>,
iommu@...ts.linux-foundation.org,
LKML <linux-kernel@...r.kernel.org>,
Joerg Roedel <joro@...tes.org>,
David Woodhouse <dwmw2@...radead.org>,
Alex Williamson <alex.williamson@...hat.com>,
Jean-Philippe Brucker <jean-philippe.brucker@....com>
Cc: Yi Liu <yi.l.liu@...el.com>, "Tian, Kevin" <kevin.tian@...el.com>,
Raj Ashok <ashok.raj@...el.com>,
Christoph Hellwig <hch@...radead.org>,
Lu Baolu <baolu.lu@...ux.intel.com>,
Andriy Shevchenko <andriy.shevchenko@...ux.intel.com>
Subject: Re: [PATCH v2 18/19] iommu/vt-d: Support flushing more translation
cache types
Hi Jacob,
On 4/24/19 1:31 AM, Jacob Pan wrote:
> When Shared Virtual Memory is exposed to a guest via vIOMMU, extended
> IOTLB invalidation may be passed down from outside IOMMU subsystems.
> This patch adds invalidation functions that can be used for additional
> translation cache types.
>
> Signed-off-by: Jacob Pan <jacob.jun.pan@...ux.intel.com>
> ---
> drivers/iommu/dmar.c | 48 +++++++++++++++++++++++++++++++++++++++++++++
> include/linux/intel-iommu.h | 21 ++++++++++++++++----
> 2 files changed, 65 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
> index 9c49300..680894e 100644
> --- a/drivers/iommu/dmar.c
> +++ b/drivers/iommu/dmar.c
> @@ -1357,6 +1357,20 @@ void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
> qi_submit_sync(&desc, iommu);
> }
>
/* PASID-based IOTLB Invalidate */
> +void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u64 addr, u32 pasid,
> + unsigned int size_order, u64 granu)
> +{
> + struct qi_desc desc;
> +
> + desc.qw0 = QI_EIOTLB_PASID(pasid) | QI_EIOTLB_DID(did) |
> + QI_EIOTLB_GRAN(granu) | QI_EIOTLB_TYPE;
> + desc.qw1 = QI_EIOTLB_ADDR(addr) | QI_EIOTLB_IH(0) |
> + QI_EIOTLB_AM(size_order);
I see IH it hardcoded to 0. Don't you envision to cascade the IH. On ARM
this was needed for perf sake.
> + desc.qw2 = 0;
> + desc.qw3 = 0;
> + qi_submit_sync(&desc, iommu);
> +}
> +
> void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
> u16 qdep, u64 addr, unsigned mask)
> {
> @@ -1380,6 +1394,40 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
> qi_submit_sync(&desc, iommu);
> }
>
/* Pasid-based Device-TLB Invalidation */
> +void qi_flush_dev_piotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
> + u32 pasid, u16 qdep, u64 addr, unsigned size, u64 granu)
> +{
> + struct qi_desc desc;
> +
> + desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
> + QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
> + QI_DEV_IOTLB_PFSID(pfsid);
> + desc.qw1 |= QI_DEV_EIOTLB_GLOB(granu);
> +
> + /* If S bit is 0, we only flush a single page. If S bit is set,
> + * The least significant zero bit indicates the size. VT-d spec
> + * 6.5.2.6
> + */
> + if (!size)
> + desc.qw0 = QI_DEV_EIOTLB_ADDR(addr) & ~QI_DEV_EIOTLB_SIZE;
desc.q1 |= ?
> + else {
> + unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size);
> +
> + desc.qw1 = QI_DEV_EIOTLB_ADDR(addr & ~mask) | QI_DEV_EIOTLB_SIZE;
desc.q1 |=
> + }
> + qi_submit_sync(&desc, iommu);
> +}
> +
/* PASID-cache invalidation */
> +void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, int pasid)
> +{
> + struct qi_desc desc;
> +
> + desc.qw0 = QI_PC_TYPE | QI_PC_DID(did) | QI_PC_GRAN(granu) | QI_PC_PASID(pasid);
> + desc.qw1 = 0;
> + desc.qw2 = 0;
> + desc.qw3 = 0;
> + qi_submit_sync(&desc, iommu);
> +}
> /*
> * Disable Queued Invalidation interface.
> */
> diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
> index 5d67d0d4..38e5efb 100644
> --- a/include/linux/intel-iommu.h
> +++ b/include/linux/intel-iommu.h
> @@ -339,7 +339,7 @@ enum {
> #define QI_IOTLB_GRAN(gran) (((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4))
> #define QI_IOTLB_ADDR(addr) (((u64)addr) & VTD_PAGE_MASK)
> #define QI_IOTLB_IH(ih) (((u64)ih) << 6)
> -#define QI_IOTLB_AM(am) (((u8)am))
> +#define QI_IOTLB_AM(am) (((u8)am) & 0x3f)
>
> #define QI_CC_FM(fm) (((u64)fm) << 48)
> #define QI_CC_SID(sid) (((u64)sid) << 32)
> @@ -357,17 +357,22 @@ enum {
> #define QI_PC_DID(did) (((u64)did) << 16)
> #define QI_PC_GRAN(gran) (((u64)gran) << 4)
>
> -#define QI_PC_ALL_PASIDS (QI_PC_TYPE | QI_PC_GRAN(0))
> -#define QI_PC_PASID_SEL (QI_PC_TYPE | QI_PC_GRAN(1))
> +/* PASID cache invalidation granu */
> +#define QI_PC_ALL_PASIDS 0
> +#define QI_PC_PASID_SEL 1
>
> #define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK)
> #define QI_EIOTLB_GL(gl) (((u64)gl) << 7)
> #define QI_EIOTLB_IH(ih) (((u64)ih) << 6)
> -#define QI_EIOTLB_AM(am) (((u64)am))
> +#define QI_EIOTLB_AM(am) (((u64)am) & 0x3f)
> #define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32)
> #define QI_EIOTLB_DID(did) (((u64)did) << 16)
> #define QI_EIOTLB_GRAN(gran) (((u64)gran) << 4)
>
> +/* QI Dev-IOTLB inv granu */
> +#define QI_DEV_IOTLB_GRAN_ALL 1
> +#define QI_DEV_IOTLB_GRAN_PASID_SEL 0
> +
> #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK)
> #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11)
> #define QI_DEV_EIOTLB_GLOB(g) ((u64)g)
> @@ -658,8 +663,16 @@ 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_piotlb(struct intel_iommu *iommu, u16 did, u64 addr,
> + u32 pasid, unsigned int size_order, u64 type);
> extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
> u16 qdep, u64 addr, unsigned mask);
> +
> +extern void qi_flush_dev_piotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
> + u32 pasid, u16 qdep, u64 addr, unsigned size, u64 granu);
> +
> +extern void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, int pasid);
> +
> extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
>
> extern int dmar_ir_support(void);
>
Thanks
Eric
Powered by blists - more mailing lists