[PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Christoph Hellwig
Factor out a new swiotlb_alloc_buffer helper that allocates DMA coherent
memory from the swiotlb bounce buffer.

This allows to simplify the swiotlb_alloc implemenation that uses
dma_direct_alloc to try to allocate a reachable buffer first.

Signed-off-by: Christoph Hellwig 
---
 lib/swiotlb.c | 122 +++---
 1 file changed, 65 insertions(+), 57 deletions(-)

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 1a147f1354a1..bf2d19ee91c1 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -709,75 +709,79 @@ void swiotlb_tbl_sync_single(struct device *hwdev, 
phys_addr_t tlb_addr,
 }
 EXPORT_SYMBOL_GPL(swiotlb_tbl_sync_single);
 
-void *
-swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-  dma_addr_t *dma_handle, gfp_t flags)
+static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
+   size_t size)
 {
-   bool warn = !(flags & __GFP_NOWARN);
-   dma_addr_t dev_addr;
-   void *ret;
-   int order = get_order(size);
-   u64 dma_mask = DMA_BIT_MASK(32);
+   u64 mask = DMA_BIT_MASK(32);
 
-   if (hwdev && hwdev->coherent_dma_mask)
-   dma_mask = hwdev->coherent_dma_mask;
+   if (dev && dev->coherent_dma_mask)
+   mask = dev->coherent_dma_mask;
+   return addr + size - 1 <= mask;
+}
 
-   ret = (void *)__get_free_pages(flags, order);
-   if (ret) {
-   dev_addr = swiotlb_virt_to_bus(hwdev, ret);
-   if (dev_addr + size - 1 > dma_mask) {
-   /*
-* The allocated memory isn't reachable by the device.
-*/
-   free_pages((unsigned long) ret, order);
-   ret = NULL;
-   }
-   }
-   if (!ret) {
-   /*
-* We are either out of memory or the device can't DMA to
-* GFP_DMA memory; fall back on map_single(), which
-* will grab memory from the lowest available address range.
-*/
-   phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE,
-  warn ? 0 : DMA_ATTR_NO_WARN);
-   if (paddr == SWIOTLB_MAP_ERROR)
-   goto err_warn;
+static void *
+swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
+   unsigned long attrs)
+{
+   phys_addr_t phys_addr;
+
+   if (swiotlb_force == SWIOTLB_NO_FORCE)
+   goto out_warn;
 
-   ret = phys_to_virt(paddr);
-   dev_addr = swiotlb_phys_to_dma(hwdev, paddr);
+   phys_addr = swiotlb_tbl_map_single(dev,
+   swiotlb_phys_to_dma(dev, io_tlb_start),
+   0, size, DMA_FROM_DEVICE, 0);
+   if (phys_addr == SWIOTLB_MAP_ERROR)
+   goto out_warn;
 
-   /* Confirm address can be DMA'd by device */
-   if (dev_addr + size - 1 > dma_mask) {
-   printk("hwdev DMA mask = 0x%016Lx, dev_addr = 
0x%016Lx\n",
-  (unsigned long long)dma_mask,
-  (unsigned long long)dev_addr);
+   *dma_handle = swiotlb_phys_to_dma(dev, phys_addr);
 
-   /*
-* DMA_TO_DEVICE to avoid memcpy in unmap_single.
-* The DMA_ATTR_SKIP_CPU_SYNC is optional.
-*/
-   swiotlb_tbl_unmap_single(hwdev, paddr,
-size, DMA_TO_DEVICE,
-DMA_ATTR_SKIP_CPU_SYNC);
-   goto err_warn;
-   }
-   }
+   if (dma_coherent_ok(dev, *dma_handle, size))
+   goto out_unmap;
 
-   *dma_handle = dev_addr;
-   memset(ret, 0, size);
+   memset(phys_to_virt(phys_addr), 0, size);
+   return phys_to_virt(phys_addr);
 
-   return ret;
+out_unmap:
+   dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
+   (unsigned long long)(dev ? dev->coherent_dma_mask : 0),
+   (unsigned long long)*dma_handle);
 
-err_warn:
-   if (warn && printk_ratelimit()) {
-   pr_warn("swiotlb: coherent allocation failed for device %s 
size=%zu\n",
-   dev_name(hwdev), size);
+   /*
+* DMA_TO_DEVICE to avoid memcpy in unmap_single.
+* DMA_ATTR_SKIP_CPU_SYNC is optional.
+*/
+   swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
+   DMA_ATTR_SKIP_CPU_SYNC);
+out_warn:
+   if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+   dev_warn(dev,
+   "swiotlb: coherent allocation failed, size=%zu\n",
+   size);
dump_stack();
}
-
return NULL;
 }
+
+void *
+swiotlb_alloc_coherent(str

Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Robin Murphy

On 10/01/18 08:09, Christoph Hellwig wrote:

Factor out a new swiotlb_alloc_buffer helper that allocates DMA coherent
memory from the swiotlb bounce buffer.

This allows to simplify the swiotlb_alloc implemenation that uses
dma_direct_alloc to try to allocate a reachable buffer first.

Signed-off-by: Christoph Hellwig 
---
  lib/swiotlb.c | 122 +++---
  1 file changed, 65 insertions(+), 57 deletions(-)

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 1a147f1354a1..bf2d19ee91c1 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -709,75 +709,79 @@ void swiotlb_tbl_sync_single(struct device *hwdev, 
phys_addr_t tlb_addr,
  }
  EXPORT_SYMBOL_GPL(swiotlb_tbl_sync_single);
  
-void *

-swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-  dma_addr_t *dma_handle, gfp_t flags)
+static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
+   size_t size)
  {
-   bool warn = !(flags & __GFP_NOWARN);
-   dma_addr_t dev_addr;
-   void *ret;
-   int order = get_order(size);
-   u64 dma_mask = DMA_BIT_MASK(32);
+   u64 mask = DMA_BIT_MASK(32);
  
-	if (hwdev && hwdev->coherent_dma_mask)

-   dma_mask = hwdev->coherent_dma_mask;
+   if (dev && dev->coherent_dma_mask)
+   mask = dev->coherent_dma_mask;
+   return addr + size - 1 <= mask;
+}
  
-	ret = (void *)__get_free_pages(flags, order);

-   if (ret) {
-   dev_addr = swiotlb_virt_to_bus(hwdev, ret);
-   if (dev_addr + size - 1 > dma_mask) {
-   /*
-* The allocated memory isn't reachable by the device.
-*/
-   free_pages((unsigned long) ret, order);
-   ret = NULL;
-   }
-   }
-   if (!ret) {
-   /*
-* We are either out of memory or the device can't DMA to
-* GFP_DMA memory; fall back on map_single(), which
-* will grab memory from the lowest available address range.
-*/
-   phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE,
-  warn ? 0 : DMA_ATTR_NO_WARN);
-   if (paddr == SWIOTLB_MAP_ERROR)
-   goto err_warn;
+static void *
+swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
+   unsigned long attrs)
+{
+   phys_addr_t phys_addr;
+
+   if (swiotlb_force == SWIOTLB_NO_FORCE)
+   goto out_warn;
  
-		ret = phys_to_virt(paddr);

-   dev_addr = swiotlb_phys_to_dma(hwdev, paddr);
+   phys_addr = swiotlb_tbl_map_single(dev,
+   swiotlb_phys_to_dma(dev, io_tlb_start),
+   0, size, DMA_FROM_DEVICE, 0);
+   if (phys_addr == SWIOTLB_MAP_ERROR)
+   goto out_warn;
  
-		/* Confirm address can be DMA'd by device */

-   if (dev_addr + size - 1 > dma_mask) {
-   printk("hwdev DMA mask = 0x%016Lx, dev_addr = 
0x%016Lx\n",
-  (unsigned long long)dma_mask,
-  (unsigned long long)dev_addr);
+   *dma_handle = swiotlb_phys_to_dma(dev, phys_addr);


nit: this should probably go after the dma_coherent_ok() check (as with 
the original logic).


  
-			/*

-* DMA_TO_DEVICE to avoid memcpy in unmap_single.
-* The DMA_ATTR_SKIP_CPU_SYNC is optional.
-*/
-   swiotlb_tbl_unmap_single(hwdev, paddr,
-size, DMA_TO_DEVICE,
-DMA_ATTR_SKIP_CPU_SYNC);
-   goto err_warn;
-   }
-   }
+   if (dma_coherent_ok(dev, *dma_handle, size))
+   goto out_unmap;
  
-	*dma_handle = dev_addr;

-   memset(ret, 0, size);
+   memset(phys_to_virt(phys_addr), 0, size);
+   return phys_to_virt(phys_addr);
  
-	return ret;

+out_unmap:
+   dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
+   (unsigned long long)(dev ? dev->coherent_dma_mask : 0),
+   (unsigned long long)*dma_handle);
  
-err_warn:

-   if (warn && printk_ratelimit()) {
-   pr_warn("swiotlb: coherent allocation failed for device %s 
size=%zu\n",
-   dev_name(hwdev), size);
+   /*
+* DMA_TO_DEVICE to avoid memcpy in unmap_single.
+* DMA_ATTR_SKIP_CPU_SYNC is optional.
+*/
+   swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
+   DMA_ATTR_SKIP_CPU_SYNC);
+out_warn:
+   if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+   dev_warn(dev,
+   "swiotlb: coherent allocation failed, size=%zu\n",
+   size);
  

Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Christoph Hellwig
On Wed, Jan 10, 2018 at 12:22:18PM +, Robin Murphy wrote:
>> +if (phys_addr == SWIOTLB_MAP_ERROR)
>> +goto out_warn;
>>   -  /* Confirm address can be DMA'd by device */
>> -if (dev_addr + size - 1 > dma_mask) {
>> -printk("hwdev DMA mask = 0x%016Lx, dev_addr = 
>> 0x%016Lx\n",
>> -   (unsigned long long)dma_mask,
>> -   (unsigned long long)dev_addr);
>> +*dma_handle = swiotlb_phys_to_dma(dev, phys_addr);
>
> nit: this should probably go after the dma_coherent_ok() check (as with the 
> original logic).

But the originall logic also needs the dma_addr_t for the
dma_coherent_ok check:

dev_addr = swiotlb_phys_to_dma(hwdev, paddr);
/* Confirm address can be DMA'd by device */
if (dev_addr + size - 1 > dma_mask) {
...
goto err_warn;
}

or do you mean assining to *dma_handle?  The dma_handle is not
valid for a failure return, so I don't think this should matter.

>> +if (ret) {
>> +*dma_handle = swiotlb_virt_to_bus(hwdev, ret);
>> +if (dma_coherent_ok(hwdev, *dma_handle, size)) {
>> +memset(ret, 0, size);
>> +return ret;
>> +}
>
> Aren't we leaking the pages here?

Yes, that free_pages got lost somewhere in the rebases, I've added
it back.


Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-10 Thread Robin Murphy

On 10/01/18 15:46, Christoph Hellwig wrote:

On Wed, Jan 10, 2018 at 12:22:18PM +, Robin Murphy wrote:

+   if (phys_addr == SWIOTLB_MAP_ERROR)
+   goto out_warn;
   -/* Confirm address can be DMA'd by device */
-   if (dev_addr + size - 1 > dma_mask) {
-   printk("hwdev DMA mask = 0x%016Lx, dev_addr = 
0x%016Lx\n",
-  (unsigned long long)dma_mask,
-  (unsigned long long)dev_addr);
+   *dma_handle = swiotlb_phys_to_dma(dev, phys_addr);


nit: this should probably go after the dma_coherent_ok() check (as with the
original logic).


But the originall logic also needs the dma_addr_t for the
dma_coherent_ok check:

dev_addr = swiotlb_phys_to_dma(hwdev, paddr);
/* Confirm address can be DMA'd by device */
if (dev_addr + size - 1 > dma_mask) {
...
goto err_warn;
}

or do you mean assining to *dma_handle?  The dma_handle is not
valid for a failure return, so I don't think this should matter.


Yeah, only the assignment - as I said, it's just a stylistic nit; no big 
deal either way.



+   if (ret) {
+   *dma_handle = swiotlb_virt_to_bus(hwdev, ret);
+   if (dma_coherent_ok(hwdev, *dma_handle, size)) {
+   memset(ret, 0, size);
+   return ret;
+   }


Aren't we leaking the pages here?


Yes, that free_pages got lost somewhere in the rebases, I've added
it back.


Cool.

Robin.


Re: [PATCH 10/22] swiotlb: refactor coherent buffer allocation

2018-01-15 Thread Christoph Hellwig
On Wed, Jan 10, 2018 at 05:02:30PM +, Robin Murphy wrote:
>>>
>>> Aren't we leaking the pages here?
>>
>> Yes, that free_pages got lost somewhere in the rebases, I've added
>> it back.
>
> Cool.

FYI, here is the fixed version, I don't want to re-send the whole
series for this fix:

http://git.infradead.org/users/hch/misc.git/commitdiff/0176adb004065d6815a8e67946752df4cd947c5b