Calculate the required operation in the caller, and pass it directly
instead of recalculating it for each page, and use simple arithmetics
to get from the physical address to Xen page size aligned chunks.
Signed-off-by: Christoph Hellwig <[email protected]>
---
arch/arm/xen/mm.c | 62 +++++++++++++++++------------------------------
1 file changed, 22 insertions(+), 40 deletions(-)
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 90574d89d0d4..14210ebdea1a 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -35,64 +35,46 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
return __get_free_pages(flags, order);
}
-enum dma_cache_op {
- DMA_UNMAP,
- DMA_MAP,
-};
static bool hypercall_cflush = false;
-/* functions called by SWIOTLB */
-
-static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
- size_t size, enum dma_data_direction dir, enum dma_cache_op op)
+/* buffers in highmem or foreign pages cannot cross page boundaries */
+static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
{
struct gnttab_cache_flush cflush;
- unsigned long xen_pfn;
- size_t left = size;
- xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
- offset %= XEN_PAGE_SIZE;
+ cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
+ cflush.offset = xen_offset_in_page(handle);
+ cflush.op = op;
do {
- size_t len = left;
-
- /* buffers in highmem or foreign pages cannot cross page
- * boundaries */
- if (len + offset > XEN_PAGE_SIZE)
- len = XEN_PAGE_SIZE - offset;
-
- cflush.op = 0;
- cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
- cflush.offset = offset;
- cflush.length = len;
-
- if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
- cflush.op = GNTTAB_CACHE_INVAL;
- if (op == DMA_MAP) {
- if (dir == DMA_FROM_DEVICE)
- cflush.op = GNTTAB_CACHE_INVAL;
- else
- cflush.op = GNTTAB_CACHE_CLEAN;
- }
- if (cflush.op)
- HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
+ if (size + cflush.offset > XEN_PAGE_SIZE)
+ cflush.length = XEN_PAGE_SIZE - cflush.offset;
+ else
+ cflush.length = size;
+
+ HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
+
+ handle += cflush.length;
+ size -= cflush.length;
- offset = 0;
- xen_pfn++;
- left -= len;
- } while (left);
+ cflush.offset = 0;
+ } while (size);
}
static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir)
{
- dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
+ if (dir != DMA_TO_DEVICE)
+ dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
}
static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir)
{
- dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
+ if (dir == DMA_FROM_DEVICE)
+ dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
+ else
+ dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
}
void __xen_dma_map_page(struct device *hwdev, struct page *page,
--
2.20.1
And this was still buggy I think, it really needs some real Xen/Arm
testing which I can't do. Hopefully better version below:
--
From 5ad4b6e291dbb49f65480c9b769414931cbd485a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <[email protected]>
Date: Wed, 24 Jul 2019 15:26:08 +0200
Subject: xen/arm: simplify dma_cache_maint
Calculate the required operation in the caller, and pass it directly
instead of recalculating it for each page, and use simple arithmetics
to get from the physical address to Xen page size aligned chunks.
Signed-off-by: Christoph Hellwig <[email protected]>
---
arch/arm/xen/mm.c | 61 ++++++++++++++++-------------------------------
1 file changed, 21 insertions(+), 40 deletions(-)
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 90574d89d0d4..2fde161733b0 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -35,64 +35,45 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
return __get_free_pages(flags, order);
}
-enum dma_cache_op {
- DMA_UNMAP,
- DMA_MAP,
-};
static bool hypercall_cflush = false;
-/* functions called by SWIOTLB */
-
-static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
- size_t size, enum dma_data_direction dir, enum dma_cache_op op)
+/* buffers in highmem or foreign pages cannot cross page boundaries */
+static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
{
struct gnttab_cache_flush cflush;
- unsigned long xen_pfn;
- size_t left = size;
- xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
- offset %= XEN_PAGE_SIZE;
+ cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
+ cflush.offset = xen_offset_in_page(handle);
+ cflush.op = op;
do {
- size_t len = left;
-
- /* buffers in highmem or foreign pages cannot cross page
- * boundaries */
- if (len + offset > XEN_PAGE_SIZE)
- len = XEN_PAGE_SIZE - offset;
-
- cflush.op = 0;
- cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
- cflush.offset = offset;
- cflush.length = len;
-
- if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
- cflush.op = GNTTAB_CACHE_INVAL;
- if (op == DMA_MAP) {
- if (dir == DMA_FROM_DEVICE)
- cflush.op = GNTTAB_CACHE_INVAL;
- else
- cflush.op = GNTTAB_CACHE_CLEAN;
- }
- if (cflush.op)
- HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
+ if (size + cflush.offset > XEN_PAGE_SIZE)
+ cflush.length = XEN_PAGE_SIZE - cflush.offset;
+ else
+ cflush.length = size;
+
+ HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
- offset = 0;
- xen_pfn++;
- left -= len;
- } while (left);
+ cflush.offset = 0;
+ cflush.a.dev_bus_addr += cflush.length;
+ size -= cflush.length;
+ } while (size);
}
static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir)
{
- dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
+ if (dir != DMA_TO_DEVICE)
+ dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
}
static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir)
{
- dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
+ if (dir == DMA_FROM_DEVICE)
+ dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
+ else
+ dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
}
void __xen_dma_map_page(struct device *hwdev, struct page *page,
--
2.20.1
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> Calculate the required operation in the caller, and pass it directly
> instead of recalculating it for each page, and use simple arithmetics
> to get from the physical address to Xen page size aligned chunks.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> arch/arm/xen/mm.c | 62 +++++++++++++++++------------------------------
> 1 file changed, 22 insertions(+), 40 deletions(-)
>
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index 90574d89d0d4..14210ebdea1a 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -35,64 +35,46 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
> return __get_free_pages(flags, order);
> }
>
> -enum dma_cache_op {
> - DMA_UNMAP,
> - DMA_MAP,
> -};
> static bool hypercall_cflush = false;
>
> -/* functions called by SWIOTLB */
> -
> -static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
> - size_t size, enum dma_data_direction dir, enum dma_cache_op op)
> +/* buffers in highmem or foreign pages cannot cross page boundaries */
> +static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
> {
> struct gnttab_cache_flush cflush;
> - unsigned long xen_pfn;
> - size_t left = size;
>
> - xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
> - offset %= XEN_PAGE_SIZE;
> + cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
> + cflush.offset = xen_offset_in_page(handle);
> + cflush.op = op;
>
> do {
> - size_t len = left;
> -
> - /* buffers in highmem or foreign pages cannot cross page
> - * boundaries */
> - if (len + offset > XEN_PAGE_SIZE)
> - len = XEN_PAGE_SIZE - offset;
> -
> - cflush.op = 0;
> - cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
> - cflush.offset = offset;
> - cflush.length = len;
> -
> - if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - if (op == DMA_MAP) {
> - if (dir == DMA_FROM_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - else
> - cflush.op = GNTTAB_CACHE_CLEAN;
> - }
> - if (cflush.op)
> - HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
> + if (size + cflush.offset > XEN_PAGE_SIZE)
> + cflush.length = XEN_PAGE_SIZE - cflush.offset;
> + else
> + cflush.length = size;
isn't it missing a:
cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
here?
> + HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
> +
> + handle += cflush.length;
> + size -= cflush.length;
>
> - offset = 0;
> - xen_pfn++;
> - left -= len;
> - } while (left);
> + cflush.offset = 0;
> + } while (size);
> }
>
> static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
> + if (dir != DMA_TO_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> }
>
> static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
> + if (dir == DMA_FROM_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> + else
> + dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
> }
>
> void __xen_dma_map_page(struct device *hwdev, struct page *page,
> --
> 2.20.1
>
On Tue, 27 Aug 2019, Christoph Hellwig wrote:
> And this was still buggy I think, it really needs some real Xen/Arm
> testing which I can't do. Hopefully better version below:
>
> --
> >From 5ad4b6e291dbb49f65480c9b769414931cbd485a Mon Sep 17 00:00:00 2001
> From: Christoph Hellwig <[email protected]>
> Date: Wed, 24 Jul 2019 15:26:08 +0200
> Subject: xen/arm: simplify dma_cache_maint
>
> Calculate the required operation in the caller, and pass it directly
> instead of recalculating it for each page, and use simple arithmetics
> to get from the physical address to Xen page size aligned chunks.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> arch/arm/xen/mm.c | 61 ++++++++++++++++-------------------------------
> 1 file changed, 21 insertions(+), 40 deletions(-)
>
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index 90574d89d0d4..2fde161733b0 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -35,64 +35,45 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
> return __get_free_pages(flags, order);
> }
>
> -enum dma_cache_op {
> - DMA_UNMAP,
> - DMA_MAP,
> -};
> static bool hypercall_cflush = false;
>
> -/* functions called by SWIOTLB */
> -
> -static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
> - size_t size, enum dma_data_direction dir, enum dma_cache_op op)
> +/* buffers in highmem or foreign pages cannot cross page boundaries */
> +static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
> {
> struct gnttab_cache_flush cflush;
> - unsigned long xen_pfn;
> - size_t left = size;
>
> - xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
> - offset %= XEN_PAGE_SIZE;
> + cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
> + cflush.offset = xen_offset_in_page(handle);
> + cflush.op = op;
>
> do {
> - size_t len = left;
> -
> - /* buffers in highmem or foreign pages cannot cross page
> - * boundaries */
> - if (len + offset > XEN_PAGE_SIZE)
> - len = XEN_PAGE_SIZE - offset;
> -
> - cflush.op = 0;
> - cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
> - cflush.offset = offset;
> - cflush.length = len;
> -
> - if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - if (op == DMA_MAP) {
> - if (dir == DMA_FROM_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - else
> - cflush.op = GNTTAB_CACHE_CLEAN;
> - }
> - if (cflush.op)
> - HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
> + if (size + cflush.offset > XEN_PAGE_SIZE)
> + cflush.length = XEN_PAGE_SIZE - cflush.offset;
> + else
> + cflush.length = size;
> +
> + HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
>
> - offset = 0;
> - xen_pfn++;
> - left -= len;
> - } while (left);
> + cflush.offset = 0;
> + cflush.a.dev_bus_addr += cflush.length;
> + size -= cflush.length;
Yes that's better
Reviewed-by: Stefano Stabellini <[email protected]>
> + } while (size);
> }
>
> static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
> + if (dir != DMA_TO_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> }
>
> static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
> + if (dir == DMA_FROM_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> + else
> + dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
> }
>
> void __xen_dma_map_page(struct device *hwdev, struct page *page,
> --
> 2.20.1
>