From 4316ba4a50331a963a8c76c7716cd7a4646aa385 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 8 Apr 2025 13:53:53 -0300
Subject: iommu/pages: Remove the order argument to iommu_free_pages()

Now that we have a folio under the allocation iommu_free_pages() can know
the order of the original allocation and do the correct thing to free it.

The next patch will rename iommu_free_page() to iommu_free_pages() so we
have naming consistency with iommu_alloc_pages_node().

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Mostafa Saleh <smostafa@google.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/5-v4-c8663abbb606+3f7-iommu_pages_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/init.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

(limited to 'drivers/iommu/amd/init.c')

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index dd9e26b7b718..69aad383f97e 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -644,8 +644,7 @@ static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg)
 
 static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->dev_table,
-			 get_order(pci_seg->dev_table_size));
+	iommu_free_pages(pci_seg->dev_table);
 	pci_seg->dev_table = NULL;
 }
 
@@ -662,8 +661,7 @@ static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 
 static inline void free_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->rlookup_table,
-			 get_order(pci_seg->rlookup_table_size));
+	iommu_free_pages(pci_seg->rlookup_table);
 	pci_seg->rlookup_table = NULL;
 }
 
@@ -682,8 +680,7 @@ static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_se
 static inline void free_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
 	kmemleak_free(pci_seg->irq_lookup_table);
-	iommu_free_pages(pci_seg->irq_lookup_table,
-			 get_order(pci_seg->rlookup_table_size));
+	iommu_free_pages(pci_seg->irq_lookup_table);
 	pci_seg->irq_lookup_table = NULL;
 }
 
@@ -707,8 +704,7 @@ static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg)
 
 static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->alias_table,
-			 get_order(pci_seg->alias_table_size));
+	iommu_free_pages(pci_seg->alias_table);
 	pci_seg->alias_table = NULL;
 }
 
@@ -817,7 +813,7 @@ static void iommu_disable_command_buffer(struct amd_iommu *iommu)
 
 static void __init free_command_buffer(struct amd_iommu *iommu)
 {
-	iommu_free_pages(iommu->cmd_buf, get_order(CMD_BUFFER_SIZE));
+	iommu_free_pages(iommu->cmd_buf);
 }
 
 void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp,
@@ -829,7 +825,7 @@ void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp,
 	if (buf &&
 	    check_feature(FEATURE_SNP) &&
 	    set_memory_4k((unsigned long)buf, (1 << order))) {
-		iommu_free_pages(buf, order);
+		iommu_free_pages(buf);
 		buf = NULL;
 	}
 
@@ -873,14 +869,14 @@ static void iommu_disable_event_buffer(struct amd_iommu *iommu)
 
 static void __init free_event_buffer(struct amd_iommu *iommu)
 {
-	iommu_free_pages(iommu->evt_buf, get_order(EVT_BUFFER_SIZE));
+	iommu_free_pages(iommu->evt_buf);
 }
 
 static void free_ga_log(struct amd_iommu *iommu)
 {
 #ifdef CONFIG_IRQ_REMAP
-	iommu_free_pages(iommu->ga_log, get_order(GA_LOG_SIZE));
-	iommu_free_pages(iommu->ga_log_tail, get_order(8));
+	iommu_free_pages(iommu->ga_log);
+	iommu_free_pages(iommu->ga_log_tail);
 #endif
 }
 
@@ -2789,8 +2785,7 @@ static void early_enable_iommus(void)
 
 		for_each_pci_segment(pci_seg) {
 			if (pci_seg->old_dev_tbl_cpy != NULL) {
-				iommu_free_pages(pci_seg->old_dev_tbl_cpy,
-						 get_order(pci_seg->dev_table_size));
+				iommu_free_pages(pci_seg->old_dev_tbl_cpy);
 				pci_seg->old_dev_tbl_cpy = NULL;
 			}
 		}
@@ -2803,8 +2798,7 @@ static void early_enable_iommus(void)
 		pr_info("Copied DEV table from previous kernel.\n");
 
 		for_each_pci_segment(pci_seg) {
-			iommu_free_pages(pci_seg->dev_table,
-					 get_order(pci_seg->dev_table_size));
+			iommu_free_pages(pci_seg->dev_table);
 			pci_seg->dev_table = pci_seg->old_dev_tbl_cpy;
 		}
 
-- 
cgit v1.2.3


From 3e8e986ce8a0d5fcf5479212d0c1ece4626c4a27 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 8 Apr 2025 13:53:54 -0300
Subject: iommu/pages: Remove iommu_free_page()

Use iommu_free_pages() instead.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Mostafa Saleh <smostafa@google.com>
Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/6-v4-c8663abbb606+3f7-iommu_pages_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/init.c          |  2 +-
 drivers/iommu/amd/io_pgtable.c    |  4 ++--
 drivers/iommu/amd/io_pgtable_v2.c |  8 ++++----
 drivers/iommu/amd/iommu.c         |  4 ++--
 drivers/iommu/intel/dmar.c        |  4 ++--
 drivers/iommu/intel/iommu.c       | 12 ++++++------
 drivers/iommu/intel/pasid.c       |  4 ++--
 drivers/iommu/iommu-pages.h       |  9 ---------
 drivers/iommu/riscv/iommu.c       |  6 +++---
 drivers/iommu/rockchip-iommu.c    |  8 ++++----
 drivers/iommu/tegra-smmu.c        | 12 ++++++------
 11 files changed, 32 insertions(+), 41 deletions(-)

(limited to 'drivers/iommu/amd/init.c')

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 69aad383f97e..b5415dd19426 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -946,7 +946,7 @@ static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
 static void __init free_cwwb_sem(struct amd_iommu *iommu)
 {
 	if (iommu->cmd_sem)
-		iommu_free_page((void *)iommu->cmd_sem);
+		iommu_free_pages((void *)iommu->cmd_sem);
 }
 
 static void iommu_enable_xt(struct amd_iommu *iommu)
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 26cf562dde11..42d9e6746dee 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -146,7 +146,7 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable,
 
 out:
 	spin_unlock_irqrestore(&domain->lock, flags);
-	iommu_free_page(pte);
+	iommu_free_pages(pte);
 
 	return ret;
 }
@@ -222,7 +222,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable,
 
 			/* pte could have been changed somewhere. */
 			if (!try_cmpxchg64(pte, &__pte, __npte))
-				iommu_free_page(page);
+				iommu_free_pages(page);
 			else if (IOMMU_PTE_PRESENT(__pte))
 				*updated = true;
 
diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c
index a56a27396305..f5f2f5327378 100644
--- a/drivers/iommu/amd/io_pgtable_v2.c
+++ b/drivers/iommu/amd/io_pgtable_v2.c
@@ -121,10 +121,10 @@ static void free_pgtable(u64 *pt, int level)
 		if (level > 2)
 			free_pgtable(p, level - 1);
 		else
-			iommu_free_page(p);
+			iommu_free_pages(p);
 	}
 
-	iommu_free_page(pt);
+	iommu_free_pages(pt);
 }
 
 /* Allocate page table */
@@ -159,7 +159,7 @@ static u64 *v2_alloc_pte(int nid, u64 *pgd, unsigned long iova,
 			__npte = set_pgtable_attr(page);
 			/* pte could have been changed somewhere. */
 			if (!try_cmpxchg64(pte, &__pte, __npte))
-				iommu_free_page(page);
+				iommu_free_pages(page);
 			else if (IOMMU_PTE_PRESENT(__pte))
 				*updated = true;
 
@@ -181,7 +181,7 @@ static u64 *v2_alloc_pte(int nid, u64 *pgd, unsigned long iova,
 		if (pg_size == IOMMU_PAGE_SIZE_1G)
 			free_pgtable(__pte, end_level - 1);
 		else if (pg_size == IOMMU_PAGE_SIZE_2M)
-			iommu_free_page(__pte);
+			iommu_free_pages(__pte);
 	}
 
 	return pte;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b503d01e3b80..fe31166ced94 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1812,7 +1812,7 @@ static void free_gcr3_tbl_level1(u64 *tbl)
 
 		ptr = iommu_phys_to_virt(tbl[i] & PAGE_MASK);
 
-		iommu_free_page(ptr);
+		iommu_free_pages(ptr);
 	}
 }
 
@@ -1845,7 +1845,7 @@ static void free_gcr3_table(struct gcr3_tbl_info *gcr3_info)
 	/* Free per device domain ID */
 	pdom_id_free(gcr3_info->domid);
 
-	iommu_free_page(gcr3_info->gcr3_tbl);
+	iommu_free_pages(gcr3_info->gcr3_tbl);
 	gcr3_info->gcr3_tbl = NULL;
 }
 
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index e540092d664d..14bc39b2cdd5 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1187,7 +1187,7 @@ static void free_iommu(struct intel_iommu *iommu)
 	}
 
 	if (iommu->qi) {
-		iommu_free_page(iommu->qi->desc);
+		iommu_free_pages(iommu->qi->desc);
 		kfree(iommu->qi->desc_status);
 		kfree(iommu->qi);
 	}
@@ -1714,7 +1714,7 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 
 	qi->desc_status = kcalloc(QI_LENGTH, sizeof(int), GFP_ATOMIC);
 	if (!qi->desc_status) {
-		iommu_free_page(qi->desc);
+		iommu_free_pages(qi->desc);
 		kfree(qi);
 		iommu->qi = NULL;
 		return -ENOMEM;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index b29da2d96d0b..e66fd919501f 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -571,17 +571,17 @@ static void free_context_table(struct intel_iommu *iommu)
 	for (i = 0; i < ROOT_ENTRY_NR; i++) {
 		context = iommu_context_addr(iommu, i, 0, 0);
 		if (context)
-			iommu_free_page(context);
+			iommu_free_pages(context);
 
 		if (!sm_supported(iommu))
 			continue;
 
 		context = iommu_context_addr(iommu, i, 0x80, 0);
 		if (context)
-			iommu_free_page(context);
+			iommu_free_pages(context);
 	}
 
-	iommu_free_page(iommu->root_entry);
+	iommu_free_pages(iommu->root_entry);
 	iommu->root_entry = NULL;
 }
 
@@ -745,7 +745,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 			tmp = 0ULL;
 			if (!try_cmpxchg64(&pte->val, &tmp, pteval))
 				/* Someone else set it while we were thinking; use theirs. */
-				iommu_free_page(tmp_page);
+				iommu_free_pages(tmp_page);
 			else
 				domain_flush_cache(domain, pte, sizeof(*pte));
 		}
@@ -858,7 +858,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
 		      last_pfn < level_pfn + level_size(level) - 1)) {
 			dma_clear_pte(pte);
 			domain_flush_cache(domain, pte, sizeof(*pte));
-			iommu_free_page(level_pte);
+			iommu_free_pages(level_pte);
 		}
 next:
 		pfn += level_size(level);
@@ -882,7 +882,7 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
 
 	/* free pgd */
 	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
-		iommu_free_page(domain->pgd);
+		iommu_free_pages(domain->pgd);
 		domain->pgd = NULL;
 	}
 }
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 58a13366b41c..b616aaad03ba 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -96,7 +96,7 @@ void intel_pasid_free_table(struct device *dev)
 	max_pde = pasid_table->max_pasid >> PASID_PDE_SHIFT;
 	for (i = 0; i < max_pde; i++) {
 		table = get_pasid_table_from_pde(&dir[i]);
-		iommu_free_page(table);
+		iommu_free_pages(table);
 	}
 
 	iommu_free_pages(pasid_table->table);
@@ -160,7 +160,7 @@ retry:
 		tmp = 0ULL;
 		if (!try_cmpxchg64(&dir[dir_index].val, &tmp,
 				   (u64)virt_to_phys(entries) | PASID_PTE_PRESENT)) {
-			iommu_free_page(entries);
+			iommu_free_pages(entries);
 			goto retry;
 		}
 		if (!ecap_coherent(info->iommu->ecap)) {
diff --git a/drivers/iommu/iommu-pages.h b/drivers/iommu/iommu-pages.h
index 88587da1782b..fcd17b94f7b8 100644
--- a/drivers/iommu/iommu-pages.h
+++ b/drivers/iommu/iommu-pages.h
@@ -122,15 +122,6 @@ static inline void iommu_free_pages(void *virt)
 	put_page(page);
 }
 
-/**
- * iommu_free_page - free page
- * @virt: virtual address of the page to be freed.
- */
-static inline void iommu_free_page(void *virt)
-{
-	iommu_free_pages(virt);
-}
-
 /**
  * iommu_put_pages_list - free a list of pages.
  * @page: the head of the lru list to be freed.
diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c
index 1868468d018a..4fe07343d84e 100644
--- a/drivers/iommu/riscv/iommu.c
+++ b/drivers/iommu/riscv/iommu.c
@@ -1105,7 +1105,7 @@ static void riscv_iommu_pte_free(struct riscv_iommu_domain *domain,
 	if (freelist)
 		list_add_tail(&virt_to_page(ptr)->lru, freelist);
 	else
-		iommu_free_page(ptr);
+		iommu_free_pages(ptr);
 }
 
 static unsigned long *riscv_iommu_pte_alloc(struct riscv_iommu_domain *domain,
@@ -1148,7 +1148,7 @@ pte_retry:
 			old = pte;
 			pte = _io_pte_entry(virt_to_pfn(addr), _PAGE_TABLE);
 			if (cmpxchg_relaxed(ptr, old, pte) != old) {
-				iommu_free_page(addr);
+				iommu_free_pages(addr);
 				goto pte_retry;
 			}
 		}
@@ -1393,7 +1393,7 @@ static struct iommu_domain *riscv_iommu_alloc_paging_domain(struct device *dev)
 	domain->pscid = ida_alloc_range(&riscv_iommu_pscids, 1,
 					RISCV_IOMMU_MAX_PSCID, GFP_KERNEL);
 	if (domain->pscid < 0) {
-		iommu_free_page(domain->pgd_root);
+		iommu_free_pages(domain->pgd_root);
 		kfree(domain);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index af4cc91b2bbf..f1b49370dfa3 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -737,7 +737,7 @@ static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
 	pt_dma = dma_map_single(rk_domain->dma_dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE);
 	if (dma_mapping_error(rk_domain->dma_dev, pt_dma)) {
 		dev_err(rk_domain->dma_dev, "DMA mapping error while allocating page table\n");
-		iommu_free_page(page_table);
+		iommu_free_pages(page_table);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1086,7 +1086,7 @@ static struct iommu_domain *rk_iommu_domain_alloc_paging(struct device *dev)
 	return &rk_domain->domain;
 
 err_free_dt:
-	iommu_free_page(rk_domain->dt);
+	iommu_free_pages(rk_domain->dt);
 err_free_domain:
 	kfree(rk_domain);
 
@@ -1107,13 +1107,13 @@ static void rk_iommu_domain_free(struct iommu_domain *domain)
 			u32 *page_table = phys_to_virt(pt_phys);
 			dma_unmap_single(rk_domain->dma_dev, pt_phys,
 					 SPAGE_SIZE, DMA_TO_DEVICE);
-			iommu_free_page(page_table);
+			iommu_free_pages(page_table);
 		}
 	}
 
 	dma_unmap_single(rk_domain->dma_dev, rk_domain->dt_dma,
 			 SPAGE_SIZE, DMA_TO_DEVICE);
-	iommu_free_page(rk_domain->dt);
+	iommu_free_pages(rk_domain->dt);
 
 	kfree(rk_domain);
 }
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 95e97d1e4004..7ad1b3c7c7fc 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -303,7 +303,7 @@ static struct iommu_domain *tegra_smmu_domain_alloc_paging(struct device *dev)
 
 	as->count = kcalloc(SMMU_NUM_PDE, sizeof(u32), GFP_KERNEL);
 	if (!as->count) {
-		iommu_free_page(as->pd);
+		iommu_free_pages(as->pd);
 		kfree(as);
 		return NULL;
 	}
@@ -311,7 +311,7 @@ static struct iommu_domain *tegra_smmu_domain_alloc_paging(struct device *dev)
 	as->pts = kcalloc(SMMU_NUM_PDE, sizeof(*as->pts), GFP_KERNEL);
 	if (!as->pts) {
 		kfree(as->count);
-		iommu_free_page(as->pd);
+		iommu_free_pages(as->pd);
 		kfree(as);
 		return NULL;
 	}
@@ -608,14 +608,14 @@ static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
 		dma = dma_map_single(smmu->dev, pt, SMMU_SIZE_PT,
 				     DMA_TO_DEVICE);
 		if (dma_mapping_error(smmu->dev, dma)) {
-			iommu_free_page(pt);
+			iommu_free_pages(pt);
 			return NULL;
 		}
 
 		if (!smmu_dma_addr_valid(smmu, dma)) {
 			dma_unmap_single(smmu->dev, dma, SMMU_SIZE_PT,
 					 DMA_TO_DEVICE);
-			iommu_free_page(pt);
+			iommu_free_pages(pt);
 			return NULL;
 		}
 
@@ -656,7 +656,7 @@ static void tegra_smmu_pte_put_use(struct tegra_smmu_as *as, unsigned long iova)
 
 		dma_unmap_single(smmu->dev, pte_dma, SMMU_SIZE_PT,
 				 DMA_TO_DEVICE);
-		iommu_free_page(pt);
+		iommu_free_pages(pt);
 		as->pts[pde] = NULL;
 	}
 }
@@ -707,7 +707,7 @@ static struct tegra_pt *as_get_pde_page(struct tegra_smmu_as *as,
 	 */
 	if (as->pts[pde]) {
 		if (pt)
-			iommu_free_page(pt);
+			iommu_free_pages(pt);
 
 		pt = as->pts[pde];
 	}
-- 
cgit v1.2.3


From e874c666b15bcb6280c4e747d8de3879bb728829 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 8 Apr 2025 13:54:04 -0300
Subject: iommu/amd: Change rlookup, irq_lookup, and alias to use kvalloc()

This is just CPU memory used by the driver to track things, it doesn't
need to use iommu-pages. All of them are indexed by devid and devid is
bounded by pci_seg->last_bdf or we are already out of bounds on the page
allocation.

Switch them to use some version of kvmalloc_array() and drop the now
unused constants and remove the tbl_size() round up to PAGE_SIZE multiples
logic.

Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/16-v4-c8663abbb606+3f7-iommu_pages_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/amd_iommu_types.h |  8 --------
 drivers/iommu/amd/init.c            | 26 ++++++++++++--------------
 2 files changed, 12 insertions(+), 22 deletions(-)

(limited to 'drivers/iommu/amd/init.c')

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 5089b58e528a..5ea73f08b388 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -29,8 +29,6 @@
  * some size calculation constants
  */
 #define DEV_TABLE_ENTRY_SIZE		32
-#define ALIAS_TABLE_ENTRY_SIZE		2
-#define RLOOKUP_TABLE_ENTRY_SIZE	(sizeof(void *))
 
 /* Capability offsets used by the driver */
 #define MMIO_CAP_HDR_OFFSET	0x00
@@ -616,12 +614,6 @@ struct amd_iommu_pci_seg {
 	/* Size of the device table */
 	u32 dev_table_size;
 
-	/* Size of the alias table */
-	u32 alias_table_size;
-
-	/* Size of the rlookup table */
-	u32 rlookup_table_size;
-
 	/*
 	 * device table virtual address
 	 *
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index b5415dd19426..3acdbef8fbbf 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -651,8 +651,9 @@ static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg)
 /* Allocate per PCI segment IOMMU rlookup table. */
 static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	pci_seg->rlookup_table = iommu_alloc_pages(GFP_KERNEL,
-						   get_order(pci_seg->rlookup_table_size));
+	pci_seg->rlookup_table = kvcalloc(pci_seg->last_bdf + 1,
+					  sizeof(*pci_seg->rlookup_table),
+					  GFP_KERNEL);
 	if (pci_seg->rlookup_table == NULL)
 		return -ENOMEM;
 
@@ -661,16 +662,15 @@ static inline int __init alloc_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 
 static inline void free_rlookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->rlookup_table);
+	kvfree(pci_seg->rlookup_table);
 	pci_seg->rlookup_table = NULL;
 }
 
 static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	pci_seg->irq_lookup_table = iommu_alloc_pages(GFP_KERNEL,
-						      get_order(pci_seg->rlookup_table_size));
-	kmemleak_alloc(pci_seg->irq_lookup_table,
-		       pci_seg->rlookup_table_size, 1, GFP_KERNEL);
+	pci_seg->irq_lookup_table = kvcalloc(pci_seg->last_bdf + 1,
+					     sizeof(*pci_seg->irq_lookup_table),
+					     GFP_KERNEL);
 	if (pci_seg->irq_lookup_table == NULL)
 		return -ENOMEM;
 
@@ -679,8 +679,7 @@ static inline int __init alloc_irq_lookup_table(struct amd_iommu_pci_seg *pci_se
 
 static inline void free_irq_lookup_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	kmemleak_free(pci_seg->irq_lookup_table);
-	iommu_free_pages(pci_seg->irq_lookup_table);
+	kvfree(pci_seg->irq_lookup_table);
 	pci_seg->irq_lookup_table = NULL;
 }
 
@@ -688,8 +687,9 @@ static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg)
 {
 	int i;
 
-	pci_seg->alias_table = iommu_alloc_pages(GFP_KERNEL,
-						 get_order(pci_seg->alias_table_size));
+	pci_seg->alias_table = kvmalloc_array(pci_seg->last_bdf + 1,
+					      sizeof(*pci_seg->alias_table),
+					      GFP_KERNEL);
 	if (!pci_seg->alias_table)
 		return -ENOMEM;
 
@@ -704,7 +704,7 @@ static int __init alloc_alias_table(struct amd_iommu_pci_seg *pci_seg)
 
 static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->alias_table);
+	kvfree(pci_seg->alias_table);
 	pci_seg->alias_table = NULL;
 }
 
@@ -1596,8 +1596,6 @@ static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id,
 	pci_seg->last_bdf = last_bdf;
 	DUMP_printk("PCI segment : 0x%0x, last bdf : 0x%04x\n", id, last_bdf);
 	pci_seg->dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE, last_bdf);
-	pci_seg->alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE, last_bdf);
-	pci_seg->rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE, last_bdf);
 
 	pci_seg->id = id;
 	init_llist_head(&pci_seg->dev_data_list);
-- 
cgit v1.2.3


From 5faa04c4edd462cc4ded939cea6f5a995f2ad0ec Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 8 Apr 2025 13:54:05 -0300
Subject: iommu/amd: Use roundup_pow_two() instead of get_order()

If x >= PAGE_SIZE then:

  1 << (get_order(x) + PAGE_SHIFT) == roundup_pow_two()

Inline this into the only caller, compute the size of the HW device table
in terms of 4K pages which matches the HW definition.

Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/17-v4-c8663abbb606+3f7-iommu_pages_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/init.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

(limited to 'drivers/iommu/amd/init.c')

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 3acdbef8fbbf..13b5f83e6423 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -243,14 +243,6 @@ static void init_translation_status(struct amd_iommu *iommu)
 		iommu->flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED;
 }
 
-static inline unsigned long tbl_size(int entry_size, int last_bdf)
-{
-	unsigned shift = PAGE_SHIFT +
-			 get_order((last_bdf + 1) * entry_size);
-
-	return 1UL << shift;
-}
-
 int amd_iommu_get_num_iommus(void)
 {
 	return amd_iommus_present;
@@ -1595,7 +1587,9 @@ static struct amd_iommu_pci_seg *__init alloc_pci_segment(u16 id,
 
 	pci_seg->last_bdf = last_bdf;
 	DUMP_printk("PCI segment : 0x%0x, last bdf : 0x%04x\n", id, last_bdf);
-	pci_seg->dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE, last_bdf);
+	pci_seg->dev_table_size =
+		max(roundup_pow_of_two((last_bdf + 1) * DEV_TABLE_ENTRY_SIZE),
+		    SZ_4K);
 
 	pci_seg->id = id;
 	init_llist_head(&pci_seg->dev_data_list);
-- 
cgit v1.2.3


From d50aaa4a9ffb0149d2187dfe3477300561f06fec Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 8 Apr 2025 13:54:07 -0300
Subject: iommu: Update various drivers to pass in lg2sz instead of order to
 iommu pages

Convert most of the places calling get_order() as an argument to the
iommu-pages allocator into order_base_2() or the _sz flavour
instead. These places already have an exact size, there is no particular
reason to use order here.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/19-v4-c8663abbb606+3f7-iommu_pages_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/init.c        | 29 +++++++++++++++--------------
 drivers/iommu/intel/dmar.c      |  6 +++---
 drivers/iommu/io-pgtable-arm.c  | 12 +++++++++---
 drivers/iommu/io-pgtable-dart.c | 12 +++---------
 drivers/iommu/sun50i-iommu.c    |  4 ++--
 5 files changed, 32 insertions(+), 31 deletions(-)

(limited to 'drivers/iommu/amd/init.c')

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 13b5f83e6423..df1094893eb0 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -626,8 +626,8 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table, u16 pci_
 /* Allocate per PCI segment device table */
 static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	pci_seg->dev_table = iommu_alloc_pages(GFP_KERNEL | GFP_DMA32,
-					       get_order(pci_seg->dev_table_size));
+	pci_seg->dev_table = iommu_alloc_pages_sz(GFP_KERNEL | GFP_DMA32,
+						  pci_seg->dev_table_size);
 	if (!pci_seg->dev_table)
 		return -ENOMEM;
 
@@ -707,8 +707,7 @@ static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
  */
 static int __init alloc_command_buffer(struct amd_iommu *iommu)
 {
-	iommu->cmd_buf = iommu_alloc_pages(GFP_KERNEL,
-					   get_order(CMD_BUFFER_SIZE));
+	iommu->cmd_buf = iommu_alloc_pages_sz(GFP_KERNEL, CMD_BUFFER_SIZE);
 
 	return iommu->cmd_buf ? 0 : -ENOMEM;
 }
@@ -811,14 +810,16 @@ static void __init free_command_buffer(struct amd_iommu *iommu)
 void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu, gfp_t gfp,
 				  size_t size)
 {
-	int order = get_order(size);
-	void *buf = iommu_alloc_pages(gfp, order);
+	void *buf;
 
-	if (buf &&
-	    check_feature(FEATURE_SNP) &&
-	    set_memory_4k((unsigned long)buf, (1 << order))) {
+	size = PAGE_ALIGN(size);
+	buf = iommu_alloc_pages_sz(gfp, size);
+	if (!buf)
+		return NULL;
+	if (check_feature(FEATURE_SNP) &&
+	    set_memory_4k((unsigned long)buf, size / PAGE_SIZE)) {
 		iommu_free_pages(buf);
-		buf = NULL;
+		return NULL;
 	}
 
 	return buf;
@@ -913,11 +914,11 @@ static int iommu_init_ga_log(struct amd_iommu *iommu)
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
 		return 0;
 
-	iommu->ga_log = iommu_alloc_pages(GFP_KERNEL, get_order(GA_LOG_SIZE));
+	iommu->ga_log = iommu_alloc_pages_sz(GFP_KERNEL, GA_LOG_SIZE);
 	if (!iommu->ga_log)
 		goto err_out;
 
-	iommu->ga_log_tail = iommu_alloc_pages(GFP_KERNEL, get_order(8));
+	iommu->ga_log_tail = iommu_alloc_pages_sz(GFP_KERNEL, 8);
 	if (!iommu->ga_log_tail)
 		goto err_out;
 
@@ -1012,8 +1013,8 @@ static bool __copy_device_table(struct amd_iommu *iommu)
 	if (!old_devtb)
 		return false;
 
-	pci_seg->old_dev_tbl_cpy = iommu_alloc_pages(GFP_KERNEL | GFP_DMA32,
-						     get_order(pci_seg->dev_table_size));
+	pci_seg->old_dev_tbl_cpy = iommu_alloc_pages_sz(
+		GFP_KERNEL | GFP_DMA32, pci_seg->dev_table_size);
 	if (pci_seg->old_dev_tbl_cpy == NULL) {
 		pr_err("Failed to allocate memory for copying old device table!\n");
 		memunmap(old_devtb);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 14bc39b2cdd5..10374b684d6d 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1681,7 +1681,6 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 {
 	struct q_inval *qi;
 	void *desc;
-	int order;
 
 	if (!ecap_qis(iommu->ecap))
 		return -ENOENT;
@@ -1702,8 +1701,9 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 	 * Need two pages to accommodate 256 descriptors of 256 bits each
 	 * if the remapping hardware supports scalable mode translation.
 	 */
-	order = ecap_smts(iommu->ecap) ? 1 : 0;
-	desc = iommu_alloc_pages_node(iommu->node, GFP_ATOMIC, order);
+	desc = iommu_alloc_pages_node_sz(iommu->node, GFP_ATOMIC,
+					 ecap_smts(iommu->ecap) ? SZ_8K :
+								  SZ_4K);
 	if (!desc) {
 		kfree(qi);
 		iommu->qi = NULL;
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 08d0f62abe8a..545229cf62d2 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -263,14 +263,20 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 				    void *cookie)
 {
 	struct device *dev = cfg->iommu_dev;
-	int order = get_order(size);
+	size_t alloc_size;
 	dma_addr_t dma;
 	void *pages;
 
+	/*
+	 * For very small starting-level translation tables the HW requires a
+	 * minimum alignment of at least 64 to cover all cases.
+	 */
+	alloc_size = max(size, 64);
 	if (cfg->alloc)
-		pages = cfg->alloc(cookie, size, gfp);
+		pages = cfg->alloc(cookie, alloc_size, gfp);
 	else
-		pages = iommu_alloc_pages_node(dev_to_node(dev), gfp, order);
+		pages = iommu_alloc_pages_node_sz(dev_to_node(dev), gfp,
+						  alloc_size);
 
 	if (!pages)
 		return NULL;
diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
index 8b5403aae8c0..679bda104797 100644
--- a/drivers/iommu/io-pgtable-dart.c
+++ b/drivers/iommu/io-pgtable-dart.c
@@ -107,13 +107,6 @@ static phys_addr_t iopte_to_paddr(dart_iopte pte,
 	return paddr;
 }
 
-static void *__dart_alloc_pages(size_t size, gfp_t gfp)
-{
-	int order = get_order(size);
-
-	return iommu_alloc_pages(gfp, order);
-}
-
 static int dart_init_pte(struct dart_io_pgtable *data,
 			     unsigned long iova, phys_addr_t paddr,
 			     dart_iopte prot, int num_entries,
@@ -255,7 +248,7 @@ static int dart_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 
 	/* no L2 table present */
 	if (!pte) {
-		cptep = __dart_alloc_pages(tblsz, gfp);
+		cptep = iommu_alloc_pages_sz(gfp, tblsz);
 		if (!cptep)
 			return -ENOMEM;
 
@@ -412,7 +405,8 @@ apple_dart_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	cfg->apple_dart_cfg.n_ttbrs = 1 << data->tbl_bits;
 
 	for (i = 0; i < cfg->apple_dart_cfg.n_ttbrs; ++i) {
-		data->pgd[i] = __dart_alloc_pages(DART_GRANULE(data), GFP_KERNEL);
+		data->pgd[i] =
+			iommu_alloc_pages_sz(GFP_KERNEL, DART_GRANULE(data));
 		if (!data->pgd[i])
 			goto out_free_data;
 		cfg->apple_dart_cfg.ttbr[i] = virt_to_phys(data->pgd[i]);
diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c
index 6385560dbc3f..76c9620af4bb 100644
--- a/drivers/iommu/sun50i-iommu.c
+++ b/drivers/iommu/sun50i-iommu.c
@@ -690,8 +690,8 @@ sun50i_iommu_domain_alloc_paging(struct device *dev)
 	if (!sun50i_domain)
 		return NULL;
 
-	sun50i_domain->dt = iommu_alloc_pages(GFP_KERNEL | GFP_DMA32,
-					      get_order(DT_SIZE));
+	sun50i_domain->dt =
+		iommu_alloc_pages_sz(GFP_KERNEL | GFP_DMA32, DT_SIZE);
 	if (!sun50i_domain->dt)
 		goto err_free_domain;
 
-- 
cgit v1.2.3


From 94a9921e2c25eedcf95b00cedbd065579406655a Mon Sep 17 00:00:00 2001
From: Sairaj Kodilkar <sarunkod@amd.com>
Date: Mon, 17 Mar 2025 11:20:20 +0530
Subject: iommu/amd: Add support for HTRangeIgnore feature

AMD IOMMU reserves the address range 0xfd00000000-0xffffffffff for
the hypertransport protocol (HT) and has special meaning. Hence devices
cannot use this address range for the DMA. However on some AMD platforms
this HT range is shifted to the very top of the address space and new
feature bit `HTRangeIgnore` is introduced. When this feature bit is on,
IOMMU treats the GPA access to the legacy HT range as regular GPA access.

Signed-off-by: Sairaj Kodilkar <sarunkod@amd.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20250317055020.25214-1-sarunkod@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/amd_iommu.h       | 2 ++
 drivers/iommu/amd/amd_iommu_types.h | 1 +
 drivers/iommu/amd/init.c            | 5 +++++
 drivers/iommu/amd/iommu.c           | 3 +++
 4 files changed, 11 insertions(+)

(limited to 'drivers/iommu/amd/init.c')

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 220c598b7e14..29a8864381c3 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -147,6 +147,8 @@ static inline int get_pci_sbdf_id(struct pci_dev *pdev)
 	return PCI_SEG_DEVID_TO_SBDF(seg, devid);
 }
 
+bool amd_iommu_ht_range_ignore(void);
+
 /*
  * This must be called after device probe completes. During probe
  * use rlookup_amd_iommu() get the iommu.
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 5089b58e528a..11dd152cfa95 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -111,6 +111,7 @@
 #define FEATURE_SNPAVICSUP	GENMASK_ULL(7, 5)
 #define FEATURE_SNPAVICSUP_GAM(x) \
 	(FIELD_GET(FEATURE_SNPAVICSUP, x) == 0x1)
+#define FEATURE_HT_RANGE_IGNORE		BIT_ULL(11)
 
 #define FEATURE_NUM_INT_REMAP_SUP	GENMASK_ULL(9, 8)
 #define FEATURE_NUM_INT_REMAP_SUP_2K(x) \
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index dd9e26b7b718..acf8941e1ed3 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -256,6 +256,11 @@ int amd_iommu_get_num_iommus(void)
 	return amd_iommus_present;
 }
 
+bool amd_iommu_ht_range_ignore(void)
+{
+	return check_feature2(FEATURE_HT_RANGE_IGNORE);
+}
+
 /*
  * Iterate through all the IOMMUs to get common EFR
  * masks among all IOMMUs and warn if found inconsistency.
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 15e334264881..95520bcf6c0e 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2916,6 +2916,9 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 		return;
 	list_add_tail(&region->list, head);
 
+	if (amd_iommu_ht_range_ignore())
+		return;
+
 	region = iommu_alloc_resv_region(HT_RANGE_START,
 					 HT_RANGE_END - HT_RANGE_START + 1,
 					 0, IOMMU_RESV_RESERVED, GFP_KERNEL);
-- 
cgit v1.2.3