summaryrefslogtreecommitdiff
path: root/drivers/iommu/dmar.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-01-02 02:55:29 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-01-02 02:55:29 +0300
commit8e143b90e4d45cca3dc53760d3cfab988bc74571 (patch)
treecd924b3abd58786ce1f3f7a41f5f32ff9f3e6af7 /drivers/iommu/dmar.c
parent78e8696c234ab637c4dd516cabeac344d84ec10b (diff)
parent03ebe48e235f17d70f34890d34d8153b8a84c02e (diff)
downloadlinux-8e143b90e4d45cca3dc53760d3cfab988bc74571.tar.xz
Merge tag 'iommu-updates-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull IOMMU updates from Joerg Roedel: - Page table code for AMD IOMMU now supports large pages where smaller page-sizes were mapped before. VFIO had to work around that in the past and I included a patch to remove it (acked by Alex Williamson) - Patches to unmodularize a couple of IOMMU drivers that would never work as modules anyway. - Work to unify the the iommu-related pointers in 'struct device' into one pointer. This work is not finished yet, but will probably be in the next cycle. - NUMA aware allocation in iommu-dma code - Support for r8a774a1 and r8a774c0 in the Renesas IOMMU driver - Scalable mode support for the Intel VT-d driver - PM runtime improvements for the ARM-SMMU driver - Support for the QCOM-SMMUv2 IOMMU hardware from Qualcom - Various smaller fixes and improvements * tag 'iommu-updates-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (78 commits) iommu: Check for iommu_ops == NULL in iommu_probe_device() ACPI/IORT: Don't call iommu_ops->add_device directly iommu/of: Don't call iommu_ops->add_device directly iommu: Consolitate ->add/remove_device() calls iommu/sysfs: Rename iommu_release_device() dmaengine: sh: rcar-dmac: Use device_iommu_mapped() xhci: Use device_iommu_mapped() powerpc/iommu: Use device_iommu_mapped() ACPI/IORT: Use device_iommu_mapped() iommu/of: Use device_iommu_mapped() driver core: Introduce device_iommu_mapped() function iommu/tegra: Use helper functions to access dev->iommu_fwspec iommu/qcom: Use helper functions to access dev->iommu_fwspec iommu/of: Use helper functions to access dev->iommu_fwspec iommu/mediatek: Use helper functions to access dev->iommu_fwspec iommu/ipmmu-vmsa: Use helper functions to access dev->iommu_fwspec iommu/dma: Use helper functions to access dev->iommu_fwspec iommu/arm-smmu: Use helper functions to access dev->iommu_fwspec ACPI/IORT: Use helper functions to access dev->iommu_fwspec iommu: Introduce wrappers around dev->iommu_fwspec ...
Diffstat (limited to 'drivers/iommu/dmar.c')
-rw-r--r--drivers/iommu/dmar.c91
1 files changed, 61 insertions, 30 deletions
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 1edf2a251336..dc9f14811e0f 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1160,6 +1160,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
int head, tail;
struct q_inval *qi = iommu->qi;
int wait_index = (index + 1) % QI_LENGTH;
+ int shift = qi_shift(iommu);
if (qi->desc_status[wait_index] == QI_ABORT)
return -EAGAIN;
@@ -1173,13 +1174,19 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
*/
if (fault & DMA_FSTS_IQE) {
head = readl(iommu->reg + DMAR_IQH_REG);
- if ((head >> DMAR_IQ_SHIFT) == index) {
- pr_err("VT-d detected invalid descriptor: "
- "low=%llx, high=%llx\n",
- (unsigned long long)qi->desc[index].low,
- (unsigned long long)qi->desc[index].high);
- memcpy(&qi->desc[index], &qi->desc[wait_index],
- sizeof(struct qi_desc));
+ if ((head >> shift) == index) {
+ struct qi_desc *desc = qi->desc + head;
+
+ /*
+ * desc->qw2 and desc->qw3 are either reserved or
+ * used by software as private data. We won't print
+ * out these two qw's for security consideration.
+ */
+ pr_err("VT-d detected invalid descriptor: qw0 = %llx, qw1 = %llx\n",
+ (unsigned long long)desc->qw0,
+ (unsigned long long)desc->qw1);
+ memcpy(desc, qi->desc + (wait_index << shift),
+ 1 << shift);
writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
return -EINVAL;
}
@@ -1191,10 +1198,10 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
*/
if (fault & DMA_FSTS_ITE) {
head = readl(iommu->reg + DMAR_IQH_REG);
- head = ((head >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+ head = ((head >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
head |= 1;
tail = readl(iommu->reg + DMAR_IQT_REG);
- tail = ((tail >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+ tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
@@ -1222,15 +1229,14 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
{
int rc;
struct q_inval *qi = iommu->qi;
- struct qi_desc *hw, wait_desc;
+ int offset, shift, length;
+ struct qi_desc wait_desc;
int wait_index, index;
unsigned long flags;
if (!qi)
return 0;
- hw = qi->desc;
-
restart:
rc = 0;
@@ -1243,16 +1249,21 @@ restart:
index = qi->free_head;
wait_index = (index + 1) % QI_LENGTH;
+ shift = qi_shift(iommu);
+ length = 1 << shift;
qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;
- hw[index] = *desc;
-
- wait_desc.low = QI_IWD_STATUS_DATA(QI_DONE) |
+ offset = index << shift;
+ memcpy(qi->desc + offset, desc, length);
+ wait_desc.qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
- wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);
+ wait_desc.qw1 = virt_to_phys(&qi->desc_status[wait_index]);
+ wait_desc.qw2 = 0;
+ wait_desc.qw3 = 0;
- hw[wait_index] = wait_desc;
+ offset = wait_index << shift;
+ memcpy(qi->desc + offset, &wait_desc, length);
qi->free_head = (qi->free_head + 2) % QI_LENGTH;
qi->free_cnt -= 2;
@@ -1261,7 +1272,7 @@ restart:
* update the HW tail register indicating the presence of
* new descriptors.
*/
- writel(qi->free_head << DMAR_IQ_SHIFT, iommu->reg + DMAR_IQT_REG);
+ writel(qi->free_head << shift, iommu->reg + DMAR_IQT_REG);
while (qi->desc_status[wait_index] != QI_DONE) {
/*
@@ -1298,8 +1309,10 @@ void qi_global_iec(struct intel_iommu *iommu)
{
struct qi_desc desc;
- desc.low = QI_IEC_TYPE;
- desc.high = 0;
+ desc.qw0 = QI_IEC_TYPE;
+ desc.qw1 = 0;
+ desc.qw2 = 0;
+ desc.qw3 = 0;
/* should never fail */
qi_submit_sync(&desc, iommu);
@@ -1310,9 +1323,11 @@ void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
{
struct qi_desc desc;
- desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
+ desc.qw0 = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
| QI_CC_GRAN(type) | QI_CC_TYPE;
- desc.high = 0;
+ desc.qw1 = 0;
+ desc.qw2 = 0;
+ desc.qw3 = 0;
qi_submit_sync(&desc, iommu);
}
@@ -1331,10 +1346,12 @@ void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
if (cap_read_drain(iommu->cap))
dr = 1;
- desc.low = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
+ desc.qw0 = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
- desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
+ desc.qw1 = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
| QI_IOTLB_AM(size_order);
+ desc.qw2 = 0;
+ desc.qw3 = 0;
qi_submit_sync(&desc, iommu);
}
@@ -1347,15 +1364,17 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
if (mask) {
WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
- desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
+ desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
} else
- desc.high = QI_DEV_IOTLB_ADDR(addr);
+ desc.qw1 = QI_DEV_IOTLB_ADDR(addr);
if (qdep >= QI_DEV_IOTLB_MAX_INVS)
qdep = 0;
- desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
+ desc.qw0 = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
QI_DIOTLB_TYPE | QI_DEV_IOTLB_PFSID(pfsid);
+ desc.qw2 = 0;
+ desc.qw3 = 0;
qi_submit_sync(&desc, iommu);
}
@@ -1403,16 +1422,24 @@ static void __dmar_enable_qi(struct intel_iommu *iommu)
u32 sts;
unsigned long flags;
struct q_inval *qi = iommu->qi;
+ u64 val = virt_to_phys(qi->desc);
qi->free_head = qi->free_tail = 0;
qi->free_cnt = QI_LENGTH;
+ /*
+ * Set DW=1 and QS=1 in IQA_REG when Scalable Mode capability
+ * is present.
+ */
+ if (ecap_smts(iommu->ecap))
+ val |= (1 << 11) | 1;
+
raw_spin_lock_irqsave(&iommu->register_lock, flags);
/* write zero to the tail reg */
writel(0, iommu->reg + DMAR_IQT_REG);
- dmar_writeq(iommu->reg + DMAR_IQA_REG, virt_to_phys(qi->desc));
+ dmar_writeq(iommu->reg + DMAR_IQA_REG, val);
iommu->gcmd |= DMA_GCMD_QIE;
writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
@@ -1448,8 +1475,12 @@ int dmar_enable_qi(struct intel_iommu *iommu)
qi = iommu->qi;
-
- desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, 0);
+ /*
+ * Need two pages to accommodate 256 descriptors of 256 bits each
+ * if the remapping hardware supports scalable mode translation.
+ */
+ desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
+ !!ecap_smts(iommu->ecap));
if (!desc_page) {
kfree(qi);
iommu->qi = NULL;