Re: [Xen-devel] [PATCH 2/2] IOMMU/MMU: Adjust low level functions for VT-d Device-TLB flush error.

["Jan Beulich" <JBeulich@xxxxxxxx>]

>>> On 17.03.16 at 07:54, <quan.xu@xxxxxxxxx> wrote:
> --- a/xen/drivers/passthrough/amd/iommu_init.c
> +++ b/xen/drivers/passthrough/amd/iommu_init.c
> @@ -1339,12 +1339,14 @@ static void invalidate_all_devices(void)
>      iterate_ivrs_mappings(_invalidate_all_devices);
>  }
>  
> -void amd_iommu_suspend(void)
> +int amd_iommu_suspend(void)
>  {
>      struct amd_iommu *iommu;
>  
>      for_each_amd_iommu ( iommu )
>          disable_iommu(iommu);
> +
> +    return 0;
>  }
>  
>  void amd_iommu_resume(void)
> @@ -1368,3 +1370,11 @@ void amd_iommu_resume(void)
>          invalidate_all_domain_pages();
>      }
>  }
> +
> +void amd_iommu_crash_shutdown(void)
> +{
> +    struct amd_iommu *iommu;
> +
> +    for_each_amd_iommu ( iommu )
> +        disable_iommu(iommu);
> +}

One of the two should clearly call the other - no need to have the
same code twice.

> --- a/xen/drivers/passthrough/iommu.c
> +++ b/xen/drivers/passthrough/iommu.c
> @@ -182,7 +182,11 @@ void __hwdom_init iommu_hwdom_init(struct domain *d)
>                   ((page->u.inuse.type_info & PGT_type_mask)
>                    == PGT_writable_page) )
>                  mapping |= IOMMUF_writable;
> -            hd->platform_ops->map_page(d, gfn, mfn, mapping);
> +            if ( hd->platform_ops->map_page(d, gfn, mfn, mapping) )
> +                printk(XENLOG_G_ERR
> +                       "IOMMU: Map page gfn: 0x%lx(mfn: 0x%lx) failed.\n",
> +                       gfn, mfn);
> +

Printing one message here is certainly necessary, but what if the
failure repeats for very many pages? Also %#lx instead of 0x%lx
please, and a blank before the opening parenthesis.

> @@ -554,11 +555,24 @@ static void iommu_flush_all(void)
>          iommu = drhd->iommu;
>          iommu_flush_context_global(iommu, 0);
>          flush_dev_iotlb = find_ats_dev_drhd(iommu) ? 1 : 0;
> -        iommu_flush_iotlb_global(iommu, 0, flush_dev_iotlb);
> +        rc = iommu_flush_iotlb_global(iommu, 0, flush_dev_iotlb);
> +
> +        if ( rc > 0 )
> +        {
> +            iommu_flush_write_buffer(iommu);

Why is this needed all of the sudden? (Note that if you did a
more fine grained split, it might also be easier for you to note/
explain all the not directly related changes in the respective
commit messages. Unless of course they fix actual bugs, in
which case they should be split out anyway; such individual
fixes would also likely have a much faster route to commit,
relieving you earlier from the burden of at least some of the
changes you have to carry and re-base.)

> +            rc = 0;
> +        }
> +        else if ( rc < 0 )
> +        {
> +            printk(XENLOG_G_ERR "IOMMU: IOMMU flush all failed.\n");
> +            break;
> +        }

Is a log message really advisable here?

> -static void __intel_iommu_iotlb_flush(struct domain *d, unsigned long gfn,
> +static int __intel_iommu_iotlb_flush(struct domain *d, unsigned long gfn,

While I'm not VT-d maintainer, I think changes like this would be a
good opportunity to also drop the stray double underscores: You
need to touch all callers anyway.

> @@ -584,37 +599,40 @@ static void __intel_iommu_iotlb_flush(struct domain *d, 
> unsigned long gfn,
>              continue;
>  
>          if ( page_count != 1 || gfn == INVALID_GFN )
> -        {
> -            if ( iommu_flush_iotlb_dsi(iommu, iommu_domid,
> -                        0, flush_dev_iotlb) )
> -                iommu_flush_write_buffer(iommu);
> -        }
> +            rc = iommu_flush_iotlb_dsi(iommu, iommu_domid,
> +                                       0, flush_dev_iotlb);
>          else
> +            rc = iommu_flush_iotlb_psi(iommu, iommu_domid,
> +                                       (paddr_t)gfn << PAGE_SHIFT_4K, 0,
> +                                       !dma_old_pte_present,
> +                                       flush_dev_iotlb);
> +        if ( rc > 0 )
>          {
> -            if ( iommu_flush_iotlb_psi(iommu, iommu_domid,
> -                        (paddr_t)gfn << PAGE_SHIFT_4K, PAGE_ORDER_4K,

Note how this used PAGE_ORDER_4K so far?

> -                        !dma_old_pte_present, flush_dev_iotlb) )
> -                iommu_flush_write_buffer(iommu);
> +            iommu_flush_write_buffer(iommu);

Same question again: Why is this all of the sudden needed on
both paths?

> @@ -622,7 +640,7 @@ static void dma_pte_clear_one(struct domain *domain, u64 
> addr)
>      if ( pg_maddr == 0 )
>      {
>          spin_unlock(&hd->arch.mapping_lock);
> -        return;
> +        return -ENOMEM;
>      }

addr_to_dma_page_maddr() gets called with "alloc" being false, so
there can't be any memory allocation failure here. There simply is
nothing to do in this case.

> -void me_wifi_quirk(struct domain *domain, u8 bus, u8 devfn, int map)
> +int me_wifi_quirk(struct domain *domain, u8 bus, u8 devfn, int map)
>  {
>      u32 id;
> +    int rc = 0;
>  
>      id = pci_conf_read32(0, 0, 0, 0, 0);
>      if ( IS_CTG(id) )
>      {
>          /* quit if ME does not exist */
>          if ( pci_conf_read32(0, 0, 3, 0, 0) == 0xffffffff )
> -            return;
> +            return -ENOENT;

Is this really an error? IOW, do all systems which satisfy IS_CTG()
have such a device?

Jan

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel