diff options
author | Jason Gunthorpe <jgg@nvidia.com> | 2020-09-17 15:12:22 -0300 |
---|---|---|
committer | Jason Gunthorpe <jgg@nvidia.com> | 2020-09-18 10:31:45 -0300 |
commit | 5dee5872f87552cfb173c899d35fc1413c2aa77f (patch) | |
tree | 273a8551247785dbec22d1e7c55e2b636e1c9e8e /drivers/iommu/amd/iommu.c | |
parent | c0a6b5ecc5b7dd028c2921415ea036074a8f8b00 (diff) | |
parent | 376ceb31ff879c2ee6b48eef841d6fa7720f6f43 (diff) |
Merge branch 'mlx5_active_speed' into rdma.git for-next
Leon Romanovsky says:
====================
IBTA declares speed as 16 bits, but kernel stores it in u8. This series
fixes in-kernel declaration while keeping external interface intact.
====================
Based on the mlx5-next branch at
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
due to dependencies.
* branch 'mlx5_active_speed':
RDMA: Fix link active_speed size
RDMA/mlx5: Delete duplicated mlx5_ptys_width enum
net/mlx5: Refactor query port speed functions
Diffstat (limited to 'drivers/iommu/amd/iommu.c')
-rw-r--r-- | drivers/iommu/amd/iommu.c | 26 |
1 files changed, 21 insertions, 5 deletions
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index ba9f3dbc5b94..07ae8b93887e 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2659,7 +2659,12 @@ static int amd_iommu_def_domain_type(struct device *dev) if (!dev_data) return 0; - if (dev_data->iommu_v2) + /* + * Do not identity map IOMMUv2 capable devices when memory encryption is + * active, because some of those devices (AMD GPUs) don't have the + * encryption bit in their DMA-mask and require remapping. + */ + if (!mem_encrypt_active() && dev_data->iommu_v2) return IOMMU_DOMAIN_IDENTITY; return 0; @@ -3292,6 +3297,7 @@ out: static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte, struct amd_ir_data *data) { + bool ret; struct irq_remap_table *table; struct amd_iommu *iommu; unsigned long flags; @@ -3309,10 +3315,18 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte, entry = (struct irte_ga *)table->table; entry = &entry[index]; - entry->lo.fields_remap.valid = 0; - entry->hi.val = irte->hi.val; - entry->lo.val = irte->lo.val; - entry->lo.fields_remap.valid = 1; + + ret = cmpxchg_double(&entry->lo.val, &entry->hi.val, + entry->lo.val, entry->hi.val, + irte->lo.val, irte->hi.val); + /* + * We use cmpxchg16 to atomically update the 128-bit IRTE, + * and it cannot be updated by the hardware or other processors + * behind us, so the return value of cmpxchg16 should be the + * same as the old value. + */ + WARN_ON(!ret); + if (data) data->ref = entry; @@ -3850,6 +3864,7 @@ int amd_iommu_deactivate_guest_mode(void *data) struct amd_ir_data *ir_data = (struct amd_ir_data *)data; struct irte_ga *entry = (struct irte_ga *) ir_data->entry; struct irq_cfg *cfg = ir_data->cfg; + u64 valid = entry->lo.fields_remap.valid; if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry || !entry->lo.fields_vapic.guest_mode) @@ -3858,6 +3873,7 @@ int amd_iommu_deactivate_guest_mode(void *data) entry->lo.val = 0; entry->hi.val = 0; + entry->lo.fields_remap.valid = valid; entry->lo.fields_remap.dm = apic->irq_dest_mode; entry->lo.fields_remap.int_type = apic->irq_delivery_mode; entry->hi.fields.vector = cfg->vector; |