Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Leonardo Bras <leobras.c@gmail.com>
To:     Michael Ellerman <mpe@ellerman.id.au>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        Leonardo Bras <leobras.c@gmail.com>,
        Joel Stanley <joel@jms.id.au>,
        Christophe Leroy <christophe.leroy@c-s.fr>,
        Alexey Kardashevskiy <aik@ozlabs.ru>,
        Nicolin Chen <nicoleotsuka@gmail.com>,
        Niklas Schnelle <schnelle@linux.ibm.com>
Cc:     linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Subject: [PATCH v3 05/11] powerpc/pseries/iommu: Allow DDW windows starting at 0x00
Date:   Thu, 22 Apr 2021 04:07:17 -0300
Message-Id: <20210422070721.463912-6-leobras.c@gmail.com>
In-Reply-To: <20210422070721.463912-1-leobras.c@gmail.com>
References: <20210422070721.463912-1-leobras.c@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

enable_ddw() currently returns the address of the DMA window, which is
considered invalid if has the value 0x00.

Also, it only considers valid an address returned from find_existing_ddw
if it's not 0x00.

Changing this behavior makes sense, given the users of enable_ddw() only
need to know if direct mapping is possible. It can also allow a DMA window
starting at 0x00 to be used.

This will be helpful for using a DDW with indirect mapping, as the window
address will be different than 0x00, but it will not map the whole
partition.

Signed-off-by: Leonardo Bras <leobras.c@gmail.com>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/platforms/pseries/iommu.c | 35 ++++++++++++--------------
 1 file changed, 16 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 6f14894d2d04..955cf095416c 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -849,25 +849,26 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 			np, ret);
 }
 
-static u64 find_existing_ddw(struct device_node *pdn, int *window_shift)
+static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift)
 {
 	struct direct_window *window;
 	const struct dynamic_dma_window_prop *direct64;
-	u64 dma_addr = 0;
+	bool found = false;
 
 	spin_lock(&direct_window_list_lock);
 	/* check if we already created a window and dupe that config if so */
 	list_for_each_entry(window, &direct_window_list, list) {
 		if (window->device == pdn) {
 			direct64 = window->prop;
-			dma_addr = be64_to_cpu(direct64->dma_base);
+			*dma_addr = be64_to_cpu(direct64->dma_base);
 			*window_shift = be32_to_cpu(direct64->window_shift);
+			found = true;
 			break;
 		}
 	}
 	spin_unlock(&direct_window_list_lock);
 
-	return dma_addr;
+	return found;
 }
 
 static struct direct_window *ddw_list_new_entry(struct device_node *pdn,
@@ -1157,20 +1158,19 @@ static int iommu_get_page_shift(u32 query_page_size)
  * pdn: the parent pe node with the ibm,dma_window property
  * Future: also check if we can remap the base window for our base page size
  *
- * returns the dma offset for use by the direct mapped DMA code.
+ * returns true if can map all pages (direct mapping), false otherwise..
  */
-static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
+static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
 	int len = 0, ret;
 	int max_ram_len = order_base_2(ddw_memory_hotplug_max());
 	struct ddw_query_response query;
 	struct ddw_create_response create;
 	int page_shift;
-	u64 dma_addr;
 	struct device_node *dn;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	struct direct_window *window;
-	struct property *win64;
+	struct property *win64 = NULL;
 	struct dynamic_dma_window_prop *ddwprop;
 	struct failed_ddw_pdn *fpdn;
 	bool default_win_removed = false;
@@ -1182,8 +1182,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 	mutex_lock(&direct_window_init_mutex);
 
-	dma_addr = find_existing_ddw(pdn, &len);
-	if (dma_addr != 0)
+	if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len))
 		goto out_unlock;
 
 	/*
@@ -1338,7 +1337,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	list_add(&window->list, &direct_window_list);
 	spin_unlock(&direct_window_list_lock);
 
-	dma_addr = be64_to_cpu(ddwprop->dma_base);
+	dev->dev.archdata.dma_offset = be64_to_cpu(ddwprop->dma_base);
 	goto out_unlock;
 
 out_free_window:
@@ -1351,6 +1350,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	kfree(win64->name);
 	kfree(win64->value);
 	kfree(win64);
+	win64 = NULL;
 
 out_failed:
 	if (default_win_removed)
@@ -1370,10 +1370,10 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * as RAM, then we failed to create a window to cover persistent
 	 * memory and need to set the DMA limit.
 	 */
-	if (pmem_present && dma_addr && (len == max_ram_len))
-		dev->dev.bus_dma_limit = dma_addr + (1ULL << len);
+	if (pmem_present && win64 && (len == max_ram_len))
+		dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len);
 
-	return dma_addr;
+	return win64;
 }
 
 static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
@@ -1452,11 +1452,8 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 			break;
 	}
 
-	if (pdn && PCI_DN(pdn)) {
-		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
-		if (pdev->dev.archdata.dma_offset)
-			return true;
-	}
+	if (pdn && PCI_DN(pdn))
+		return enable_ddw(pdev, pdn);
 
 	return false;
 }
-- 
2.30.2