Re: [PATCH v5 05/11] powerpc/pseries/iommu: Allow DDW windows starting at 0x00

2021-07-20 Thread Frederic Barrat




On 16/07/2021 10:27, Leonardo Bras wrote:

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 
Reviewed-by: Alexey Kardashevskiy 
---



Looks good to me
Reviewed-by: Frederic Barrat 




  arch/powerpc/platforms/pseries/iommu.c | 36 +-
  1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/iommu.c 
b/arch/powerpc/platforms/pseries/iommu.c
index 712d1667144a..b34b473bbdc1 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -853,25 +853,26 @@ 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(_window_list_lock);

/* check if we already created a window and dupe that config if so */
list_for_each_entry(window, _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(_window_list_lock);
  
-	return dma_addr;

+   return found;
  }
  
  static struct direct_window *ddw_list_new_entry(struct device_node *pdn,

@@ -1161,20 +1162,20 @@ 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;
+   bool ddw_enabled = false;
struct dynamic_dma_window_prop *ddwprop;
struct failed_ddw_pdn *fpdn;
bool default_win_removed = false;
@@ -1186,9 +1187,10 @@ static u64 enable_ddw(struct pci_dev *dev, struct 
device_node *pdn)
  
  	mutex_lock(_window_init_mutex);
  
-	dma_addr = find_existing_ddw(pdn, );

-   if (dma_addr != 0)
+   if (find_existing_ddw(pdn, >dev.archdata.dma_offset, )) {
+   ddw_enabled = true;
goto out_unlock;
+   }
  
  	/*

 * If we already went through this for a previous function of
@@ -1342,7 +1344,8 @@ static u64 enable_ddw(struct pci_dev *dev, struct 
device_node *pdn)
list_add(>list, _window_list);
spin_unlock(_window_list_lock);
  
-	dma_addr = be64_to_cpu(ddwprop->dma_base);

+   dev->dev.archdata.dma_offset = be64_to_cpu(ddwprop->dma_base);
+   ddw_enabled = true;
goto out_unlock;
  
  out_free_window:

@@ -1374,10 +1377,10 @@ 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 && ddw_enabled && (len == max_ram_len))
+   dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL 
<< len);
  
-	return dma_addr;

+   return ddw_enabled;
  }
  
  static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)

@@ -1456,11 +1459,8 @@ 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 

[PATCH v5 05/11] powerpc/pseries/iommu: Allow DDW windows starting at 0x00

2021-07-16 Thread Leonardo Bras
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 
Reviewed-by: Alexey Kardashevskiy 
---
 arch/powerpc/platforms/pseries/iommu.c | 36 +-
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/iommu.c 
b/arch/powerpc/platforms/pseries/iommu.c
index 712d1667144a..b34b473bbdc1 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -853,25 +853,26 @@ 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(_window_list_lock);
/* check if we already created a window and dupe that config if so */
list_for_each_entry(window, _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(_window_list_lock);
 
-   return dma_addr;
+   return found;
 }
 
 static struct direct_window *ddw_list_new_entry(struct device_node *pdn,
@@ -1161,20 +1162,20 @@ 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;
+   bool ddw_enabled = false;
struct dynamic_dma_window_prop *ddwprop;
struct failed_ddw_pdn *fpdn;
bool default_win_removed = false;
@@ -1186,9 +1187,10 @@ static u64 enable_ddw(struct pci_dev *dev, struct 
device_node *pdn)
 
mutex_lock(_window_init_mutex);
 
-   dma_addr = find_existing_ddw(pdn, );
-   if (dma_addr != 0)
+   if (find_existing_ddw(pdn, >dev.archdata.dma_offset, )) {
+   ddw_enabled = true;
goto out_unlock;
+   }
 
/*
 * If we already went through this for a previous function of
@@ -1342,7 +1344,8 @@ static u64 enable_ddw(struct pci_dev *dev, struct 
device_node *pdn)
list_add(>list, _window_list);
spin_unlock(_window_list_lock);
 
-   dma_addr = be64_to_cpu(ddwprop->dma_base);
+   dev->dev.archdata.dma_offset = be64_to_cpu(ddwprop->dma_base);
+   ddw_enabled = true;
goto out_unlock;
 
 out_free_window:
@@ -1374,10 +1377,10 @@ 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 && ddw_enabled && (len == max_ram_len))
+   dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL 
<< len);
 
-   return dma_addr;
+   return ddw_enabled;
 }
 
 static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
@@ -1456,11 +1459,8 @@ 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 &&