iommu/vt-d: Fix PASID table allocation

commit 910170442944e1f8674fd5ddbeeb8ccd1877ea98 upstream.

Somehow I ended up with an off-by-three error in calculating the size of
the PASID and PASID State tables, which triggers allocations failures as
those tables unfortunately have to be physically contiguous.

In fact, even the *correct* maximum size of 8MiB is problematic and is
wont to lead to allocation failures. Since I have extracted a promise
that this *will* be fixed in hardware, I'm happy to limit it on the
current hardware to a maximum of 0x20000 PASIDs, which gives us 1MiB
tables — still not ideal, but better than before.

Reported by Mika Kuoppala <mika.kuoppala@linux.intel.com> and also by
Xunlei Pang <xlpang@redhat.com> who submitted a simpler patch to fix
only the allocation (and not the free) to the "correct" limit... which
was still problematic.

Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index d9939fa9b58887567d1fe8a7a94c7e5f1452cdf0..f929879ecae60ce8c266e9f21719e2b49783c7ab 100644 (file)
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -39,10 +39,18 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
        struct page *pages;
        int order;
 
        struct page *pages;
        int order;
 

-       order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-       if (order < 0)
-               order = 0;
-
+       /* Start at 2 because it's defined as 2^(1+PSS) */
+       iommu->pasid_max = 2 << ecap_pss(iommu->ecap);
+
+       /* Eventually I'm promised we will get a multi-level PASID table
+        * and it won't have to be physically contiguous. Until then,
+        * limit the size because 8MiB contiguous allocations can be hard
+        * to come by. The limit of 0x20000, which is 1MiB for each of
+        * the PASID and PASID-state tables, is somewhat arbitrary. */
+       if (iommu->pasid_max > 0x20000)
+               iommu->pasid_max = 0x20000;
+
+       order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);

        pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
        if (!pages) {
                pr_warn("IOMMU: %s: Failed to allocate PASID table\n",
        pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
        if (!pages) {
                pr_warn("IOMMU: %s: Failed to allocate PASID table\n",


@@ -53,6 +61,8 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
        pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order);
 
        if (ecap_dis(iommu->ecap)) {
        pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order);
 
        if (ecap_dis(iommu->ecap)) {

+               /* Just making it explicit... */
+               BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry));

                pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
                if (pages)
                        iommu->pasid_state_table = page_address(pages);
                pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
                if (pages)
                        iommu->pasid_state_table = page_address(pages);


@@ -68,11 +78,7 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 
 int intel_svm_free_pasid_tables(struct intel_iommu *iommu)
 {
 
 int intel_svm_free_pasid_tables(struct intel_iommu *iommu)
 {

-       int order;
-
-       order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT;
-       if (order < 0)
-               order = 0;
+       int order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);

 
        if (iommu->pasid_table) {
                free_pages((unsigned long)iommu->pasid_table, order);
 
        if (iommu->pasid_table) {
                free_pages((unsigned long)iommu->pasid_table, order);


@@ -371,8 +377,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
                }
                svm->iommu = iommu;
 
                }
                svm->iommu = iommu;
 

-               if (pasid_max > 2 << ecap_pss(iommu->ecap))
-                       pasid_max = 2 << ecap_pss(iommu->ecap);
+               if (pasid_max > iommu->pasid_max)
+                       pasid_max = iommu->pasid_max;

 
                /* Do not use PASID 0 in caching mode (virtualised IOMMU) */
                ret = idr_alloc(&iommu->pasid_idr, svm,
 
                /* Do not use PASID 0 in caching mode (virtualised IOMMU) */
                ret = idr_alloc(&iommu->pasid_idr, svm,

diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2d9b650047a5b96582f66dff2b2581cce97c2b65..d49e26c6cdc7b5e48e41591f7c73e74d200441a8 100644 (file)
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -429,6 +429,7 @@ struct intel_iommu {
        struct page_req_dsc *prq;
        unsigned char prq_name[16];    /* Name for PRQ interrupt */
        struct idr pasid_idr;
        struct page_req_dsc *prq;
        unsigned char prq_name[16];    /* Name for PRQ interrupt */
        struct idr pasid_idr;

+       u32 pasid_max;

 #endif
        struct q_inval  *qi;            /* Queued invalidation info */
        u32 *iommu_state; /* Store iommu states between suspend and resume.*/
 #endif
        struct q_inval  *qi;            /* Queued invalidation info */
        u32 *iommu_state; /* Store iommu states between suspend and resume.*/