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

@@ -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);

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;

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;

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]);

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;