On Wed, 16 Jun 2021, Claire Chang wrote:
Propagate the swiotlb_force into io_tlb_default_mem->force_bounce and use it to determine whether to bounce the data or not. This will be useful later to allow for different pools.
Signed-off-by: Claire Chang tientzu@chromium.org
include/linux/swiotlb.h | 11 +++++++++++ kernel/dma/direct.c | 2 +- kernel/dma/direct.h | 2 +- kernel/dma/swiotlb.c | 4 ++++ 4 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index dd1c30a83058..8d8855c77d9a 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -84,6 +84,7 @@ extern enum swiotlb_force swiotlb_force;
unmap calls.- @debugfs: The dentry to debugfs.
- @late_alloc: %true if allocated using the page allocator
*/
- @force_bounce: %true if swiotlb bouncing is forced
struct io_tlb_mem { phys_addr_t start; @@ -94,6 +95,7 @@ struct io_tlb_mem { spinlock_t lock; struct dentry *debugfs; bool late_alloc;
- bool force_bounce; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size;
@@ -109,6 +111,11 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) return mem && paddr >= mem->start && paddr < mem->end; }
+static inline bool is_swiotlb_force_bounce(struct device *dev) +{
- return dev->dma_io_tlb_mem->force_bounce;
+} void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -120,6 +127,10 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } +static inline bool is_swiotlb_force_bounce(struct device *dev) +{
- return false;
+} static inline void swiotlb_exit(void) { } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 7a88c34d0867..a92465b4eb12 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -496,7 +496,7 @@ size_t dma_direct_max_mapping_size(struct device *dev) { /* If SWIOTLB is active, use its maximum mapping size */ if (is_swiotlb_active(dev) &&
(dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE))
(dma_addressing_limited(dev) || is_swiotlb_force_bounce(dev)))} diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 13e9e7158d94..4632b0f4f72e 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -87,7 +87,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys);
- if (unlikely(swiotlb_force == SWIOTLB_FORCE))
if (is_swiotlb_force_bounce(dev)) return swiotlb_map(dev, phys, size, dir, attrs);
if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
Should we also make the same change in drivers/xen/swiotlb-xen.c:xen_swiotlb_map_page ?
If I make that change, I can see that everything is working as expected for a restricted-dma device with Linux running as dom0 on Xen. However, is_swiotlb_force_bounce returns non-zero even for normal non-restricted-dma devices. That shouldn't happen, right?
It looks like struct io_tlb_slot is not zeroed on allocation. Adding memset(mem, 0x0, struct_size) in swiotlb_late_init_with_tbl solves the issue.
With those two changes, the series passes my tests and you can add my tested-by.