diff mbox series

[v4,02/14] x86/iommu: add common page-table allocator

Message ID 20200804134209.8717-3-paul@xen.org (mailing list archive)
State Superseded
Headers show
Series IOMMU cleanup | expand

Commit Message

Paul Durrant Aug. 4, 2020, 1:41 p.m. UTC
From: Paul Durrant <pdurrant@amazon.com>

Instead of having separate page table allocation functions in VT-d and AMD
IOMMU code, we could use a common allocation function in the general x86 code.

This patch adds a new allocation function, iommu_alloc_pgtable(), for this
purpose. The function adds the page table pages to a list. The pages in this
list are then freed by iommu_free_pgtables(), which is called by
domain_relinquish_resources() after PCI devices have been de-assigned.

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Wei Liu <wl@xen.org>
Cc: "Roger Pau Monné" <roger.pau@citrix.com>

v4:
 - Remove space between '*' and '__must_check'
 - Reduce frequency of pre-empt check during table freeing
 - Fix parentheses formatting

v2:
 - This is split out from a larger patch of the same name in v1
---
 xen/arch/x86/domain.c               |  9 ++++-
 xen/drivers/passthrough/x86/iommu.c | 51 +++++++++++++++++++++++++++++
 xen/include/asm-x86/iommu.h         |  7 ++++
 3 files changed, 66 insertions(+), 1 deletion(-)

Comments

Jan Beulich Aug. 5, 2020, 3:39 p.m. UTC | #1
On 04.08.2020 15:41, Paul Durrant wrote:
> From: Paul Durrant <pdurrant@amazon.com>
> 
> Instead of having separate page table allocation functions in VT-d and AMD
> IOMMU code, we could use a common allocation function in the general x86 code.
> 
> This patch adds a new allocation function, iommu_alloc_pgtable(), for this
> purpose. The function adds the page table pages to a list. The pages in this
> list are then freed by iommu_free_pgtables(), which is called by
> domain_relinquish_resources() after PCI devices have been de-assigned.
> 
> Signed-off-by: Paul Durrant <pdurrant@amazon.com>

Reviewed-by: Jan Beulich <jbeulich@suse.com>
diff mbox series

Patch

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index f8084dc9e3..d1ecc7b83b 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -2153,7 +2153,8 @@  int domain_relinquish_resources(struct domain *d)
         d->arch.rel_priv = PROG_ ## x; /* Fallthrough */ case PROG_ ## x
 
         enum {
-            PROG_paging = 1,
+            PROG_iommu_pagetables = 1,
+            PROG_paging,
             PROG_vcpu_pagetables,
             PROG_shared,
             PROG_xen,
@@ -2168,6 +2169,12 @@  int domain_relinquish_resources(struct domain *d)
         if ( ret )
             return ret;
 
+    PROGRESS(iommu_pagetables):
+
+        ret = iommu_free_pgtables(d);
+        if ( ret )
+            return ret;
+
     PROGRESS(paging):
 
         /* Tear down paging-assistance stuff. */
diff --git a/xen/drivers/passthrough/x86/iommu.c b/xen/drivers/passthrough/x86/iommu.c
index a12109a1de..aea07e47c4 100644
--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -140,6 +140,9 @@  int arch_iommu_domain_init(struct domain *d)
 
     spin_lock_init(&hd->arch.mapping_lock);
 
+    INIT_PAGE_LIST_HEAD(&hd->arch.pgtables.list);
+    spin_lock_init(&hd->arch.pgtables.lock);
+
     return 0;
 }
 
@@ -257,6 +260,54 @@  void __hwdom_init arch_iommu_hwdom_init(struct domain *d)
         return;
 }
 
+int iommu_free_pgtables(struct domain *d)
+{
+    struct domain_iommu *hd = dom_iommu(d);
+    struct page_info *pg;
+    unsigned int done = 0;
+
+    while ( (pg = page_list_remove_head(&hd->arch.pgtables.list)) )
+    {
+        free_domheap_page(pg);
+
+        if ( !(++done & 0xff) && general_preempt_check() )
+            return -ERESTART;
+    }
+
+    return 0;
+}
+
+struct page_info *iommu_alloc_pgtable(struct domain *d)
+{
+    struct domain_iommu *hd = dom_iommu(d);
+    unsigned int memflags = 0;
+    struct page_info *pg;
+    void *p;
+
+#ifdef CONFIG_NUMA
+    if ( hd->node != NUMA_NO_NODE )
+        memflags = MEMF_node(hd->node);
+#endif
+
+    pg = alloc_domheap_page(NULL, memflags);
+    if ( !pg )
+        return NULL;
+
+    p = __map_domain_page(pg);
+    clear_page(p);
+
+    if ( hd->platform_ops->sync_cache )
+        iommu_vcall(hd->platform_ops, sync_cache, p, PAGE_SIZE);
+
+    unmap_domain_page(p);
+
+    spin_lock(&hd->arch.pgtables.lock);
+    page_list_add(pg, &hd->arch.pgtables.list);
+    spin_unlock(&hd->arch.pgtables.lock);
+
+    return pg;
+}
+
 /*
  * Local variables:
  * mode: C
diff --git a/xen/include/asm-x86/iommu.h b/xen/include/asm-x86/iommu.h
index 8ce97c981f..970eb06ffa 100644
--- a/xen/include/asm-x86/iommu.h
+++ b/xen/include/asm-x86/iommu.h
@@ -46,6 +46,10 @@  typedef uint64_t daddr_t;
 struct arch_iommu
 {
     spinlock_t mapping_lock; /* io page table lock */
+    struct {
+        struct page_list_head list;
+        spinlock_t lock;
+    } pgtables;
 
     union {
         /* Intel VT-d */
@@ -131,6 +135,9 @@  int pi_update_irte(const struct pi_desc *pi_desc, const struct pirq *pirq,
         iommu_vcall(ops, sync_cache, addr, size);       \
 })
 
+int __must_check iommu_free_pgtables(struct domain *d);
+struct page_info *__must_check iommu_alloc_pgtable(struct domain *d);
+
 #endif /* !__ARCH_X86_IOMMU_H__ */
 /*
  * Local variables: