From: Lu Baolu <baolu.lu@linux.intel.com>
To: Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
Robin Murphy <robin.murphy@arm.com>,
Kevin Tian <kevin.tian@intel.com>, Jason Gunthorpe <jgg@ziepe.ca>
Cc: Tina Zhang <tina.zhang@intel.com>, Yi Liu <yi.l.liu@intel.com>,
iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
Lu Baolu <baolu.lu@linux.intel.com>
Subject: [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers
Date: Wed, 10 Apr 2024 10:08:34 +0800 [thread overview]
Message-ID: <20240410020844.253535-3-baolu.lu@linux.intel.com> (raw)
In-Reply-To: <20240410020844.253535-1-baolu.lu@linux.intel.com>
Add several helpers to invalidate the caches after mappings in the
affected domain are changed.
- cache_tag_flush_range() invalidates a range of caches after mappings
within this range are changed. It uses the page-selective cache
invalidation methods.
- cache_tag_flush_all() invalidates all caches tagged by a domain ID.
It uses the domain-selective cache invalidation methods.
- cache_tag_flush_range_np() invalidates a range of caches when new
mappings are created in the domain and the corresponding page table
entries change from non-present to present.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
drivers/iommu/intel/iommu.h | 14 +++
drivers/iommu/intel/cache.c | 195 ++++++++++++++++++++++++++++++++++++
drivers/iommu/intel/iommu.c | 12 ---
3 files changed, 209 insertions(+), 12 deletions(-)
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 6f6bffc60852..700574421b51 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -35,6 +35,8 @@
#define VTD_PAGE_MASK (((u64)-1) << VTD_PAGE_SHIFT)
#define VTD_PAGE_ALIGN(addr) (((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
+#define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
+
#define VTD_STRIDE_SHIFT (9)
#define VTD_STRIDE_MASK (((u64)-1) << VTD_STRIDE_SHIFT)
@@ -1041,6 +1043,13 @@ static inline void context_set_sm_pre(struct context_entry *context)
context->lo |= BIT_ULL(4);
}
+/* Returns a number of VTD pages, but aligned to MM page size */
+static inline unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
+{
+ host_addr &= ~PAGE_MASK;
+ return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
+}
+
/* Convert value to context PASID directory size field coding. */
#define context_pdts(pds) (((pds) & 0x7) << 9)
@@ -1116,6 +1125,11 @@ int cache_tag_assign_domain(struct dmar_domain *domain, u16 did,
struct device *dev, ioasid_t pasid);
void cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,
struct device *dev, ioasid_t pasid);
+void cache_tag_flush_range(struct dmar_domain *domain, unsigned long start,
+ unsigned long end, int ih);
+void cache_tag_flush_all(struct dmar_domain *domain);
+void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start,
+ unsigned long end);
#ifdef CONFIG_INTEL_IOMMU_SVM
void intel_svm_check(struct intel_iommu *iommu);
diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c
index debbdaeff1c4..b2270dc8a765 100644
--- a/drivers/iommu/intel/cache.c
+++ b/drivers/iommu/intel/cache.c
@@ -12,6 +12,7 @@
#include <linux/dmar.h>
#include <linux/iommu.h>
#include <linux/memory.h>
+#include <linux/pci.h>
#include <linux/spinlock.h>
#include "iommu.h"
@@ -194,3 +195,197 @@ void cache_tag_unassign_domain(struct dmar_domain *domain, u16 did,
if (domain->domain.type == IOMMU_DOMAIN_NESTED)
__cache_tag_unassign_parent_domain(domain->s2_domain, did, dev, pasid);
}
+
+static unsigned long calculate_psi_aligned_address(unsigned long start,
+ unsigned long end,
+ unsigned long *_pages,
+ unsigned long *_mask)
+{
+ unsigned long pages = aligned_nrpages(start, end - start + 1);
+ unsigned long aligned_pages = __roundup_pow_of_two(pages);
+ unsigned long bitmask = aligned_pages - 1;
+ unsigned long mask = ilog2(aligned_pages);
+ unsigned long pfn = IOVA_PFN(start);
+
+ /*
+ * PSI masks the low order bits of the base address. If the
+ * address isn't aligned to the mask, then compute a mask value
+ * needed to ensure the target range is flushed.
+ */
+ if (unlikely(bitmask & pfn)) {
+ unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+ /*
+ * Since end_pfn <= pfn + bitmask, the only way bits
+ * higher than bitmask can differ in pfn and end_pfn is
+ * by carrying. This means after masking out bitmask,
+ * high bits starting with the first set bit in
+ * shared_bits are all equal in both pfn and end_pfn.
+ */
+ shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+ mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+ }
+
+ *_pages = aligned_pages;
+ *_mask = mask;
+
+ return ALIGN_DOWN(start, VTD_PAGE_SIZE);
+}
+
+/*
+ * Invalidates a range of IOVA from @start (inclusive) to @end (inclusive)
+ * when the memory mappings in the target domain have been modified.
+ */
+void cache_tag_flush_range(struct dmar_domain *domain, unsigned long start,
+ unsigned long end, int ih)
+{
+ unsigned long pages, mask, addr;
+ struct cache_tag *tag;
+ unsigned long flags;
+
+ addr = calculate_psi_aligned_address(start, end, &pages, &mask);
+
+ spin_lock_irqsave(&domain->cache_lock, flags);
+ list_for_each_entry(tag, &domain->cache_tags, node) {
+ struct intel_iommu *iommu = tag->iommu;
+ struct device_domain_info *info;
+ u16 sid;
+
+ switch (tag->type) {
+ case CACHE_TAG_IOTLB:
+ case CACHE_TAG_PARENT_IOTLB:
+ if (domain->use_first_level) {
+ qi_flush_piotlb(iommu, tag->domain_id,
+ tag->pasid, addr, pages, ih);
+ } else {
+ /*
+ * Fallback to domain selective flush if no
+ * PSI support or the size is too big.
+ */
+ if (!cap_pgsel_inv(iommu->cap) ||
+ mask > cap_max_amask_val(iommu->cap))
+ iommu->flush.flush_iotlb(iommu, tag->domain_id,
+ 0, 0, DMA_TLB_DSI_FLUSH);
+ else
+ iommu->flush.flush_iotlb(iommu, tag->domain_id,
+ addr | ih, mask,
+ DMA_TLB_PSI_FLUSH);
+ }
+ break;
+ case CACHE_TAG_PARENT_DEVTLB:
+ /*
+ * Address translation cache in device side caches the
+ * result of nested translation. There is no easy way
+ * to identify the exact set of nested translations
+ * affected by a change in S2. So just flush the entire
+ * device cache.
+ */
+ addr = 0;
+ mask = MAX_AGAW_PFN_WIDTH;
+ fallthrough;
+ case CACHE_TAG_DEVTLB:
+ info = dev_iommu_priv_get(tag->dev);
+ sid = PCI_DEVID(info->bus, info->devfn);
+
+ if (tag->pasid == IOMMU_NO_PASID)
+ qi_flush_dev_iotlb(iommu, sid, info->pfsid,
+ info->ats_qdep, addr, mask);
+ else
+ qi_flush_dev_iotlb_pasid(iommu, sid, info->pfsid,
+ tag->pasid, info->ats_qdep,
+ addr, mask);
+
+ quirk_extra_dev_tlb_flush(info, addr, mask, tag->pasid, info->ats_qdep);
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&domain->cache_lock, flags);
+}
+
+/*
+ * Invalidates all ranges of IOVA when the memory mappings in the target
+ * domain have been modified.
+ */
+void cache_tag_flush_all(struct dmar_domain *domain)
+{
+ struct cache_tag *tag;
+ unsigned long flags;
+
+ spin_lock_irqsave(&domain->cache_lock, flags);
+ list_for_each_entry(tag, &domain->cache_tags, node) {
+ struct intel_iommu *iommu = tag->iommu;
+ struct device_domain_info *info;
+ u16 sid;
+
+ switch (tag->type) {
+ case CACHE_TAG_IOTLB:
+ case CACHE_TAG_PARENT_IOTLB:
+ if (domain->use_first_level)
+ qi_flush_piotlb(iommu, tag->domain_id,
+ tag->pasid, 0, -1, 0);
+ else
+ iommu->flush.flush_iotlb(iommu, tag->domain_id,
+ 0, 0, DMA_TLB_DSI_FLUSH);
+ break;
+ case CACHE_TAG_DEVTLB:
+ case CACHE_TAG_PARENT_DEVTLB:
+ info = dev_iommu_priv_get(tag->dev);
+ sid = PCI_DEVID(info->bus, info->devfn);
+
+ qi_flush_dev_iotlb(iommu, sid, info->pfsid, info->ats_qdep,
+ 0, MAX_AGAW_PFN_WIDTH);
+ quirk_extra_dev_tlb_flush(info, 0, MAX_AGAW_PFN_WIDTH,
+ IOMMU_NO_PASID, info->ats_qdep);
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&domain->cache_lock, flags);
+}
+
+/*
+ * Invalidate a range of IOVA when new mappings are created in the target
+ * domain.
+ *
+ * - VT-d spec, Section 6.1 Caching Mode: When the CM field is reported as
+ * Set, any software updates to remapping structures other than first-
+ * stage mapping requires explicit invalidation of the caches.
+ * - VT-d spec, Section 6.8 Write Buffer Flushing: For hardware that requires
+ * write buffer flushing, software must explicitly perform write-buffer
+ * flushing, if cache invalidation is not required.
+ */
+void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start,
+ unsigned long end)
+{
+ unsigned long pages, mask, addr;
+ struct cache_tag *tag;
+ unsigned long flags;
+
+ addr = calculate_psi_aligned_address(start, end, &pages, &mask);
+
+ spin_lock_irqsave(&domain->cache_lock, flags);
+ list_for_each_entry(tag, &domain->cache_tags, node) {
+ struct intel_iommu *iommu = tag->iommu;
+
+ if (!cap_caching_mode(iommu->cap) || domain->use_first_level) {
+ iommu_flush_write_buffer(iommu);
+ continue;
+ }
+
+ if (tag->type == CACHE_TAG_IOTLB ||
+ tag->type == CACHE_TAG_PARENT_IOTLB) {
+ /*
+ * Fallback to domain selective flush if no
+ * PSI support or the size is too big.
+ */
+ if (!cap_pgsel_inv(iommu->cap) ||
+ mask > cap_max_amask_val(iommu->cap))
+ iommu->flush.flush_iotlb(iommu, tag->domain_id,
+ 0, 0, DMA_TLB_DSI_FLUSH);
+ else
+ iommu->flush.flush_iotlb(iommu, tag->domain_id,
+ addr, mask,
+ DMA_TLB_PSI_FLUSH);
+ }
+ }
+ spin_unlock_irqrestore(&domain->cache_lock, flags);
+}
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 17b8ce4b9154..4572624a275e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -54,11 +54,6 @@
__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
#define DOMAIN_MAX_ADDR(gaw) (((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)
-/* IO virtual address start page frame number */
-#define IOVA_START_PFN (1)
-
-#define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
-
static void __init check_tylersburg_isoch(void);
static int rwbf_quirk;
@@ -1985,13 +1980,6 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
domain_context_mapping_cb, domain);
}
-/* Returns a number of VTD pages, but aligned to MM page size */
-static unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
-{
- host_addr &= ~PAGE_MASK;
- return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
-}
-
/* Return largest possible superpage level for a given mapping */
static int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn,
unsigned long phy_pfn, unsigned long pages)
--
2.34.1
next prev parent reply other threads:[~2024-04-10 2:10 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-10 2:08 [PATCH v2 00/12] Consolidate domain cache invalidation Lu Baolu
2024-04-10 2:08 ` [PATCH v2 01/12] iommu/vt-d: Add cache tag assignment interface Lu Baolu
2024-04-10 2:08 ` Lu Baolu [this message]
2024-04-15 4:15 ` [PATCH v2 02/12] iommu/vt-d: Add cache tag invalidation helpers Zhang, Tina
2024-04-15 5:06 ` Baolu Lu
2024-04-15 6:46 ` Zhang, Tina
2024-04-10 2:08 ` [PATCH v2 03/12] iommu/vt-d: Add trace events for cache tag interface Lu Baolu
2024-04-10 2:08 ` [PATCH v2 04/12] iommu/vt-d: Use cache_tag_flush_all() in flush_iotlb_all Lu Baolu
2024-04-10 2:08 ` [PATCH v2 05/12] iommu/vt-d: Use cache_tag_flush_range() in tlb_sync Lu Baolu
2024-04-10 2:08 ` [PATCH v2 06/12] iommu/vt-d: Use cache_tag_flush_range_np() in iotlb_sync_map Lu Baolu
2024-04-10 2:08 ` [PATCH v2 07/12] iommu/vt-d: Cleanup use of iommu_flush_iotlb_psi() Lu Baolu
2024-04-10 2:08 ` [PATCH v2 08/12] iommu/vt-d: Use cache_tag_flush_range() in cache_invalidate_user Lu Baolu
2024-04-10 2:08 ` [PATCH v2 09/12] iommu/vt-d: Use cache helpers in arch_invalidate_secondary_tlbs Lu Baolu
2024-04-10 15:55 ` Jason Gunthorpe
2024-04-11 8:10 ` Baolu Lu
2024-04-10 2:08 ` [PATCH v2 10/12] iommu/vt-d: Retire intel_svm_dev Lu Baolu
2024-04-10 2:08 ` [PATCH v2 11/12] iommu: Add ops->domain_alloc_sva() Lu Baolu
2024-04-10 2:08 ` [PATCH v2 12/12] iommu/vt-d: Retire struct intel_svm Lu Baolu
2024-04-10 15:49 ` Jason Gunthorpe
2024-04-11 7:55 ` Baolu Lu
2024-04-11 8:32 ` Tian, Kevin
2024-04-11 10:42 ` Baolu Lu
2024-04-11 13:07 ` Jason Gunthorpe
2024-04-11 13:13 ` Baolu Lu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240410020844.253535-3-baolu.lu@linux.intel.com \
--to=baolu.lu@linux.intel.com \
--cc=iommu@lists.linux.dev \
--cc=jgg@ziepe.ca \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=robin.murphy@arm.com \
--cc=tina.zhang@intel.com \
--cc=will@kernel.org \
--cc=yi.l.liu@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.