@@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
unsigned long ua, unsigned long entries);
extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa);
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa);
extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa);
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa);
extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
#endif
@@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
return H_TOO_HARD;
- if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+ if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
return H_HARDWARE;
if (mm_iommu_mapped_inc(mem))
@@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
if (!mem)
return H_TOO_HARD;
- if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+ if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+ &hpa)))
return H_HARDWARE;
pua = (void *) vmalloc_to_phys(pua);
@@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
if (mem)
- prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+ prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+ IOMMU_PAGE_SHIFT_4K, &tces) == 0;
}
if (!prereg) {
@@ -27,6 +27,7 @@ struct mm_iommu_table_group_mem_t {
struct rcu_head rcu;
unsigned long used;
atomic64_t mapped;
+ unsigned int pageshift;
u64 ua; /* userspace address */
u64 entries; /* number of entries in hpas[] */
u64 *hpas; /* vmalloc'ed */
@@ -166,6 +167,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
goto unlock_exit;
}
+ mem->pageshift = 30; /* start from 1G pages - the biggest we have */
+
for (i = 0; i < entries; ++i) {
if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
1/* pages */, 1/* iswrite */, &page)) {
@@ -199,6 +202,9 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
}
}
populate:
+ mem->pageshift = min_t(unsigned int, mem->pageshift,
+ PAGE_SHIFT +
+ compound_order(compound_head(page)));
mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
}
@@ -349,7 +355,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
EXPORT_SYMBOL_GPL(mm_iommu_find);
long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa)
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa)
{
const long entry = (ua - mem->ua) >> PAGE_SHIFT;
u64 *va = &mem->hpas[entry];
@@ -357,6 +363,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
if (entry >= mem->entries)
return -EFAULT;
+ if (pageshift > mem->pageshift)
+ return -EFAULT;
+
*hpa = *va | (ua & ~PAGE_MASK);
return 0;
@@ -364,7 +373,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
- unsigned long ua, unsigned long *hpa)
+ unsigned long ua, unsigned int pageshift, unsigned long *hpa)
{
const long entry = (ua - mem->ua) >> PAGE_SHIFT;
void *va = &mem->hpas[entry];
@@ -373,6 +382,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
if (entry >= mem->entries)
return -EFAULT;
+ if (pageshift > mem->pageshift)
+ return -EFAULT;
+
pa = (void *) vmalloc_to_phys(va);
if (!pa)
return -EFAULT;
@@ -467,7 +467,7 @@ static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
if (!mem)
return -EINVAL;
- ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+ ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
if (ret)
return -EINVAL;
We already have a check in drivers/vfio/vfio_iommu_spapr_tce.c that an IOMMU page is contained in the physical page so the PCI hardware won't get access to unassigned host memory. However we do not have this check in KVM fastpath (H_PUT_TCE accelerated code) so the user space can pin memory backed with 64k pages and create a hardware TCE table with a bigger page size. We were lucky so far and did not hit this yet as the very first time the mapping happens we do not have tbl::it_userspace allocated yet and fall back to the userspace which in turn calls VFIO IOMMU driver and that fails because of the check in vfio_iommu_spapr_tce.c which is really sustainable solution. This stores the smallest preregistered page size in the preregistered region descriptor and changes the mm_iommu_xxx API to check this against the IOMMU page size. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> --- The bug is: run QEMU _without_ hugepages (no -mempath) and tell it to advertise 16MB pages to the guest; a typical pseries guest will use 16MB for IOMMU pages without checking the mmu pagesize and this will fail at https://git.qemu.org/?p=qemu.git;a=blob;f=hw/vfio/common.c;h=fb396cf00ac40eb35967a04c9cc798ca896eed57;hb=refs/heads/master#l256 With the change, mapping will fail in KVM and the guest will print: mlx5_core 0000:00:00.0: ibm,create-pe-dma-window(2027) 0 8000000 20000000 18 1f returned 0 (liobn = 0x80000001 starting addr = 8000000 0) mlx5_core 0000:00:00.0: created tce table LIOBN 0x80000001 for /pci@800000020000000/ethernet@0 mlx5_core 0000:00:00.0: failed to map direct window for /pci@800000020000000/ethernet@0: -1 --- arch/powerpc/include/asm/mmu_context.h | 4 ++-- arch/powerpc/kvm/book3s_64_vio.c | 2 +- arch/powerpc/kvm/book3s_64_vio_hv.c | 6 ++++-- arch/powerpc/mm/mmu_context_iommu.c | 16 ++++++++++++++-- drivers/vfio/vfio_iommu_spapr_tce.c | 2 +- 5 files changed, 22 insertions(+), 8 deletions(-)