diff mbox series

[v4,10/14] iommu: remove the share_p2m operation

Message ID 20200804134209.8717-11-paul@xen.org
State Superseded
Headers show
Series IOMMU cleanup | expand

Commit Message

Paul Durrant Aug. 4, 2020, 1:42 p.m. UTC
From: Paul Durrant <pdurrant@amazon.com>

Sharing of HAP tables is now VT-d specific so the operation is never defined
for AMD IOMMU any more. There's also no need to pro-actively set vtd.pgd_maddr
when using shared EPT as it is straightforward to simply define a helper
function to return the appropriate value in the shared and non-shared cases.

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: George Dunlap <george.dunlap@citrix.com>
Cc: Wei Liu <wl@xen.org>
Cc: "Roger Pau Monné" <roger.pau@citrix.com>
Cc: Kevin Tian <kevin.tian@intel.com>

v2:
  - Put the PGD level adjust into the helper function too, since it is
    irrelevant in the shared EPT case
---
 xen/arch/x86/mm/p2m.c               |  3 -
 xen/drivers/passthrough/iommu.c     |  8 ---
 xen/drivers/passthrough/vtd/iommu.c | 90 ++++++++++++++++-------------
 xen/include/xen/iommu.h             |  3 -
 4 files changed, 50 insertions(+), 54 deletions(-)

Comments

Jan Beulich Aug. 6, 2020, 12:18 p.m. UTC | #1
On 04.08.2020 15:42, Paul Durrant wrote:
> --- a/xen/drivers/passthrough/vtd/iommu.c
> +++ b/xen/drivers/passthrough/vtd/iommu.c
> @@ -318,6 +318,48 @@ static u64 addr_to_dma_page_maddr(struct domain *domain, u64 addr, int alloc)
>      return pte_maddr;
>  }
>  
> +static uint64_t domain_pgd_maddr(struct domain *d, struct vtd_iommu *iommu)

The 2nd param can be const, and I wonder whether it wouldn't better be
named e.g. "vtd". Then again all you're after is iommu->nr_pt_levels,
so maybe the caller would better pass in that value (removing the
appearance of there being some further dependency about the specific
IOMMU's properties)?

> +{
> +    struct domain_iommu *hd = dom_iommu(d);
> +    uint64_t pgd_maddr;
> +    unsigned int agaw;
> +
> +    ASSERT(spin_is_locked(&hd->arch.mapping_lock));
> +
> +    if ( iommu_use_hap_pt(d) )
> +    {
> +        mfn_t pgd_mfn =
> +            pagetable_get_mfn(p2m_get_pagetable(p2m_get_hostp2m(d)));
> +
> +        return pagetable_get_paddr(pagetable_from_mfn(pgd_mfn));

Why the pagetable -> MFN -> pagetable -> paddr transformation? I.e. just

        return pagetable_get_paddr(p2m_get_pagetable(p2m_get_hostp2m(d)));

? Oh, I've now realized that's how the old code was written.

> +    }
> +
> +    if ( !hd->arch.vtd.pgd_maddr )
> +    {
> +        addr_to_dma_page_maddr(d, 0, 1);
> +
> +        if ( !hd->arch.vtd.pgd_maddr )
> +            return 0;
> +    }
> +
> +    pgd_maddr = hd->arch.vtd.pgd_maddr;
> +
> +    /* Skip top levels of page tables for 2- and 3-level DRHDs. */
> +    for ( agaw = level_to_agaw(4);
> +          agaw != level_to_agaw(iommu->nr_pt_levels);
> +          agaw-- )
> +    {
> +        struct dma_pte *p = map_vtd_domain_page(pgd_maddr);

const?

> +
> +        pgd_maddr = dma_pte_addr(*p);
> +        unmap_vtd_domain_page(p);
> +        if ( !pgd_maddr )
> +            return 0;
> +    }
> +
> +    return pgd_maddr;
> +}

Jan
Tian, Kevin Aug. 14, 2020, 7:04 a.m. UTC | #2
> From: Paul Durrant <paul@xen.org>
> Sent: Tuesday, August 4, 2020 9:42 PM
> 
> From: Paul Durrant <pdurrant@amazon.com>
> 
> Sharing of HAP tables is now VT-d specific so the operation is never defined
> for AMD IOMMU any more. There's also no need to pro-actively set
> vtd.pgd_maddr
> when using shared EPT as it is straightforward to simply define a helper
> function to return the appropriate value in the shared and non-shared cases.
> 
> Signed-off-by: Paul Durrant <pdurrant@amazon.com>

Reviewed-by: Kevin Tian <kevin.tian@intel.com>

> ---
> Cc: Jan Beulich <jbeulich@suse.com>
> Cc: Andrew Cooper <andrew.cooper3@citrix.com>
> Cc: George Dunlap <george.dunlap@citrix.com>
> Cc: Wei Liu <wl@xen.org>
> Cc: "Roger Pau Monné" <roger.pau@citrix.com>
> Cc: Kevin Tian <kevin.tian@intel.com>
> 
> v2:
>   - Put the PGD level adjust into the helper function too, since it is
>     irrelevant in the shared EPT case
> ---
>  xen/arch/x86/mm/p2m.c               |  3 -
>  xen/drivers/passthrough/iommu.c     |  8 ---
>  xen/drivers/passthrough/vtd/iommu.c | 90 ++++++++++++++++-------------
>  xen/include/xen/iommu.h             |  3 -
>  4 files changed, 50 insertions(+), 54 deletions(-)
> 
> diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
> index 9f8b9bc5fd..3bd8d83d23 100644
> --- a/xen/arch/x86/mm/p2m.c
> +++ b/xen/arch/x86/mm/p2m.c
> @@ -726,9 +726,6 @@ int p2m_alloc_table(struct p2m_domain *p2m)
> 
>      p2m->phys_table = pagetable_from_mfn(top_mfn);
> 
> -    if ( hap_enabled(d) )
> -        iommu_share_p2m_table(d);
> -
>      p2m_unlock(p2m);
>      return 0;
>  }
> diff --git a/xen/drivers/passthrough/iommu.c
> b/xen/drivers/passthrough/iommu.c
> index ab44c332bb..7464f10d1c 100644
> --- a/xen/drivers/passthrough/iommu.c
> +++ b/xen/drivers/passthrough/iommu.c
> @@ -498,14 +498,6 @@ int iommu_do_domctl(
>      return ret;
>  }
> 
> -void iommu_share_p2m_table(struct domain* d)
> -{
> -    ASSERT(hap_enabled(d));
> -
> -    if ( iommu_use_hap_pt(d) )
> -        iommu_get_ops()->share_p2m(d);
> -}
> -
>  void iommu_crash_shutdown(void)
>  {
>      if ( !iommu_crash_disable )
> diff --git a/xen/drivers/passthrough/vtd/iommu.c
> b/xen/drivers/passthrough/vtd/iommu.c
> index 68cf0e535a..a532d9e88c 100644
> --- a/xen/drivers/passthrough/vtd/iommu.c
> +++ b/xen/drivers/passthrough/vtd/iommu.c
> @@ -318,6 +318,48 @@ static u64 addr_to_dma_page_maddr(struct
> domain *domain, u64 addr, int alloc)
>      return pte_maddr;
>  }
> 
> +static uint64_t domain_pgd_maddr(struct domain *d, struct vtd_iommu
> *iommu)
> +{
> +    struct domain_iommu *hd = dom_iommu(d);
> +    uint64_t pgd_maddr;
> +    unsigned int agaw;
> +
> +    ASSERT(spin_is_locked(&hd->arch.mapping_lock));
> +
> +    if ( iommu_use_hap_pt(d) )
> +    {
> +        mfn_t pgd_mfn =
> +            pagetable_get_mfn(p2m_get_pagetable(p2m_get_hostp2m(d)));
> +
> +        return pagetable_get_paddr(pagetable_from_mfn(pgd_mfn));
> +    }
> +
> +    if ( !hd->arch.vtd.pgd_maddr )
> +    {
> +        addr_to_dma_page_maddr(d, 0, 1);
> +
> +        if ( !hd->arch.vtd.pgd_maddr )
> +            return 0;
> +    }
> +
> +    pgd_maddr = hd->arch.vtd.pgd_maddr;
> +
> +    /* Skip top levels of page tables for 2- and 3-level DRHDs. */
> +    for ( agaw = level_to_agaw(4);
> +          agaw != level_to_agaw(iommu->nr_pt_levels);
> +          agaw-- )
> +    {
> +        struct dma_pte *p = map_vtd_domain_page(pgd_maddr);
> +
> +        pgd_maddr = dma_pte_addr(*p);
> +        unmap_vtd_domain_page(p);
> +        if ( !pgd_maddr )
> +            return 0;
> +    }
> +
> +    return pgd_maddr;
> +}
> +
>  static void iommu_flush_write_buffer(struct vtd_iommu *iommu)
>  {
>      u32 val;
> @@ -1286,7 +1328,7 @@ int domain_context_mapping_one(
>      struct context_entry *context, *context_entries;
>      u64 maddr, pgd_maddr;
>      u16 seg = iommu->drhd->segment;
> -    int agaw, rc, ret;
> +    int rc, ret;
>      bool_t flush_dev_iotlb;
> 
>      ASSERT(pcidevs_locked());
> @@ -1340,37 +1382,18 @@ int domain_context_mapping_one(
>      if ( iommu_hwdom_passthrough && is_hardware_domain(domain) )
>      {
>          context_set_translation_type(*context, CONTEXT_TT_PASS_THRU);
> -        agaw = level_to_agaw(iommu->nr_pt_levels);
>      }
>      else
>      {
>          spin_lock(&hd->arch.mapping_lock);
> 
> -        /* Ensure we have pagetables allocated down to leaf PTE. */
> -        if ( hd->arch.vtd.pgd_maddr == 0 )
> +        pgd_maddr = domain_pgd_maddr(domain, iommu);
> +        if ( !pgd_maddr )
>          {
> -            addr_to_dma_page_maddr(domain, 0, 1);
> -            if ( hd->arch.vtd.pgd_maddr == 0 )
> -            {
> -            nomem:
> -                spin_unlock(&hd->arch.mapping_lock);
> -                spin_unlock(&iommu->lock);
> -                unmap_vtd_domain_page(context_entries);
> -                return -ENOMEM;
> -            }
> -        }
> -
> -        /* Skip top levels of page tables for 2- and 3-level DRHDs. */
> -        pgd_maddr = hd->arch.vtd.pgd_maddr;
> -        for ( agaw = level_to_agaw(4);
> -              agaw != level_to_agaw(iommu->nr_pt_levels);
> -              agaw-- )
> -        {
> -            struct dma_pte *p = map_vtd_domain_page(pgd_maddr);
> -            pgd_maddr = dma_pte_addr(*p);
> -            unmap_vtd_domain_page(p);
> -            if ( pgd_maddr == 0 )
> -                goto nomem;
> +            spin_unlock(&hd->arch.mapping_lock);
> +            spin_unlock(&iommu->lock);
> +            unmap_vtd_domain_page(context_entries);
> +            return -ENOMEM;
>          }
> 
>          context_set_address_root(*context, pgd_maddr);
> @@ -1389,7 +1412,7 @@ int domain_context_mapping_one(
>          return -EFAULT;
>      }
> 
> -    context_set_address_width(*context, agaw);
> +    context_set_address_width(*context, level_to_agaw(iommu-
> >nr_pt_levels));
>      context_set_fault_enable(*context);
>      context_set_present(*context);
>      iommu_sync_cache(context, sizeof(struct context_entry));
> @@ -1848,18 +1871,6 @@ static int __init vtd_ept_page_compatible(struct
> vtd_iommu *iommu)
>             (ept_has_1gb(ept_cap) && opt_hap_1gb) <= cap_sps_1gb(vtd_cap);
>  }
> 
> -/*
> - * set VT-d page table directory to EPT table if allowed
> - */
> -static void iommu_set_pgd(struct domain *d)
> -{
> -    mfn_t pgd_mfn;
> -
> -    pgd_mfn =
> pagetable_get_mfn(p2m_get_pagetable(p2m_get_hostp2m(d)));
> -    dom_iommu(d)->arch.vtd.pgd_maddr =
> -        pagetable_get_paddr(pagetable_from_mfn(pgd_mfn));
> -}
> -
>  static int rmrr_identity_mapping(struct domain *d, bool_t map,
>                                   const struct acpi_rmrr_unit *rmrr,
>                                   u32 flag)
> @@ -2719,7 +2730,6 @@ static struct iommu_ops __initdata vtd_ops = {
>      .adjust_irq_affinities = adjust_vtd_irq_affinities,
>      .suspend = vtd_suspend,
>      .resume = vtd_resume,
> -    .share_p2m = iommu_set_pgd,
>      .crash_shutdown = vtd_crash_shutdown,
>      .iotlb_flush = iommu_flush_iotlb_pages,
>      .iotlb_flush_all = iommu_flush_iotlb_all,
> diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
> index b7e5d3da09..1f25d2082f 100644
> --- a/xen/include/xen/iommu.h
> +++ b/xen/include/xen/iommu.h
> @@ -271,7 +271,6 @@ struct iommu_ops {
> 
>      int __must_check (*suspend)(void);
>      void (*resume)(void);
> -    void (*share_p2m)(struct domain *d);
>      void (*crash_shutdown)(void);
>      int __must_check (*iotlb_flush)(struct domain *d, dfn_t dfn,
>                                      unsigned long page_count,
> @@ -348,8 +347,6 @@ void iommu_resume(void);
>  void iommu_crash_shutdown(void);
>  int iommu_get_reserved_device_memory(iommu_grdm_t *, void *);
> 
> -void iommu_share_p2m_table(struct domain *d);
> -
>  #ifdef CONFIG_HAS_PCI
>  int iommu_do_pci_domctl(struct xen_domctl *, struct domain *d,
>                          XEN_GUEST_HANDLE_PARAM(xen_domctl_t));
> --
> 2.20.1
diff mbox series

Patch

diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 9f8b9bc5fd..3bd8d83d23 100644
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -726,9 +726,6 @@  int p2m_alloc_table(struct p2m_domain *p2m)
 
     p2m->phys_table = pagetable_from_mfn(top_mfn);
 
-    if ( hap_enabled(d) )
-        iommu_share_p2m_table(d);
-
     p2m_unlock(p2m);
     return 0;
 }
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index ab44c332bb..7464f10d1c 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -498,14 +498,6 @@  int iommu_do_domctl(
     return ret;
 }
 
-void iommu_share_p2m_table(struct domain* d)
-{
-    ASSERT(hap_enabled(d));
-
-    if ( iommu_use_hap_pt(d) )
-        iommu_get_ops()->share_p2m(d);
-}
-
 void iommu_crash_shutdown(void)
 {
     if ( !iommu_crash_disable )
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 68cf0e535a..a532d9e88c 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -318,6 +318,48 @@  static u64 addr_to_dma_page_maddr(struct domain *domain, u64 addr, int alloc)
     return pte_maddr;
 }
 
+static uint64_t domain_pgd_maddr(struct domain *d, struct vtd_iommu *iommu)
+{
+    struct domain_iommu *hd = dom_iommu(d);
+    uint64_t pgd_maddr;
+    unsigned int agaw;
+
+    ASSERT(spin_is_locked(&hd->arch.mapping_lock));
+
+    if ( iommu_use_hap_pt(d) )
+    {
+        mfn_t pgd_mfn =
+            pagetable_get_mfn(p2m_get_pagetable(p2m_get_hostp2m(d)));
+
+        return pagetable_get_paddr(pagetable_from_mfn(pgd_mfn));
+    }
+
+    if ( !hd->arch.vtd.pgd_maddr )
+    {
+        addr_to_dma_page_maddr(d, 0, 1);
+
+        if ( !hd->arch.vtd.pgd_maddr )
+            return 0;
+    }
+
+    pgd_maddr = hd->arch.vtd.pgd_maddr;
+
+    /* Skip top levels of page tables for 2- and 3-level DRHDs. */
+    for ( agaw = level_to_agaw(4);
+          agaw != level_to_agaw(iommu->nr_pt_levels);
+          agaw-- )
+    {
+        struct dma_pte *p = map_vtd_domain_page(pgd_maddr);
+
+        pgd_maddr = dma_pte_addr(*p);
+        unmap_vtd_domain_page(p);
+        if ( !pgd_maddr )
+            return 0;
+    }
+
+    return pgd_maddr;
+}
+
 static void iommu_flush_write_buffer(struct vtd_iommu *iommu)
 {
     u32 val;
@@ -1286,7 +1328,7 @@  int domain_context_mapping_one(
     struct context_entry *context, *context_entries;
     u64 maddr, pgd_maddr;
     u16 seg = iommu->drhd->segment;
-    int agaw, rc, ret;
+    int rc, ret;
     bool_t flush_dev_iotlb;
 
     ASSERT(pcidevs_locked());
@@ -1340,37 +1382,18 @@  int domain_context_mapping_one(
     if ( iommu_hwdom_passthrough && is_hardware_domain(domain) )
     {
         context_set_translation_type(*context, CONTEXT_TT_PASS_THRU);
-        agaw = level_to_agaw(iommu->nr_pt_levels);
     }
     else
     {
         spin_lock(&hd->arch.mapping_lock);
 
-        /* Ensure we have pagetables allocated down to leaf PTE. */
-        if ( hd->arch.vtd.pgd_maddr == 0 )
+        pgd_maddr = domain_pgd_maddr(domain, iommu);
+        if ( !pgd_maddr )
         {
-            addr_to_dma_page_maddr(domain, 0, 1);
-            if ( hd->arch.vtd.pgd_maddr == 0 )
-            {
-            nomem:
-                spin_unlock(&hd->arch.mapping_lock);
-                spin_unlock(&iommu->lock);
-                unmap_vtd_domain_page(context_entries);
-                return -ENOMEM;
-            }
-        }
-
-        /* Skip top levels of page tables for 2- and 3-level DRHDs. */
-        pgd_maddr = hd->arch.vtd.pgd_maddr;
-        for ( agaw = level_to_agaw(4);
-              agaw != level_to_agaw(iommu->nr_pt_levels);
-              agaw-- )
-        {
-            struct dma_pte *p = map_vtd_domain_page(pgd_maddr);
-            pgd_maddr = dma_pte_addr(*p);
-            unmap_vtd_domain_page(p);
-            if ( pgd_maddr == 0 )
-                goto nomem;
+            spin_unlock(&hd->arch.mapping_lock);
+            spin_unlock(&iommu->lock);
+            unmap_vtd_domain_page(context_entries);
+            return -ENOMEM;
         }
 
         context_set_address_root(*context, pgd_maddr);
@@ -1389,7 +1412,7 @@  int domain_context_mapping_one(
         return -EFAULT;
     }
 
-    context_set_address_width(*context, agaw);
+    context_set_address_width(*context, level_to_agaw(iommu->nr_pt_levels));
     context_set_fault_enable(*context);
     context_set_present(*context);
     iommu_sync_cache(context, sizeof(struct context_entry));
@@ -1848,18 +1871,6 @@  static int __init vtd_ept_page_compatible(struct vtd_iommu *iommu)
            (ept_has_1gb(ept_cap) && opt_hap_1gb) <= cap_sps_1gb(vtd_cap);
 }
 
-/*
- * set VT-d page table directory to EPT table if allowed
- */
-static void iommu_set_pgd(struct domain *d)
-{
-    mfn_t pgd_mfn;
-
-    pgd_mfn = pagetable_get_mfn(p2m_get_pagetable(p2m_get_hostp2m(d)));
-    dom_iommu(d)->arch.vtd.pgd_maddr =
-        pagetable_get_paddr(pagetable_from_mfn(pgd_mfn));
-}
-
 static int rmrr_identity_mapping(struct domain *d, bool_t map,
                                  const struct acpi_rmrr_unit *rmrr,
                                  u32 flag)
@@ -2719,7 +2730,6 @@  static struct iommu_ops __initdata vtd_ops = {
     .adjust_irq_affinities = adjust_vtd_irq_affinities,
     .suspend = vtd_suspend,
     .resume = vtd_resume,
-    .share_p2m = iommu_set_pgd,
     .crash_shutdown = vtd_crash_shutdown,
     .iotlb_flush = iommu_flush_iotlb_pages,
     .iotlb_flush_all = iommu_flush_iotlb_all,
diff --git a/xen/include/xen/iommu.h b/xen/include/xen/iommu.h
index b7e5d3da09..1f25d2082f 100644
--- a/xen/include/xen/iommu.h
+++ b/xen/include/xen/iommu.h
@@ -271,7 +271,6 @@  struct iommu_ops {
 
     int __must_check (*suspend)(void);
     void (*resume)(void);
-    void (*share_p2m)(struct domain *d);
     void (*crash_shutdown)(void);
     int __must_check (*iotlb_flush)(struct domain *d, dfn_t dfn,
                                     unsigned long page_count,
@@ -348,8 +347,6 @@  void iommu_resume(void);
 void iommu_crash_shutdown(void);
 int iommu_get_reserved_device_memory(iommu_grdm_t *, void *);
 
-void iommu_share_p2m_table(struct domain *d);
-
 #ifdef CONFIG_HAS_PCI
 int iommu_do_pci_domctl(struct xen_domctl *, struct domain *d,
                         XEN_GUEST_HANDLE_PARAM(xen_domctl_t));