swiotlb: remove dma_mark_clean

Instead of providing a special dma_mark_clean hook just for ia64, switch
ia64 to use the normal arch_sync_dma_for_cpu hooks instead.

This means that we now also set the PG_arch_1 bit for pages in the
swiotlb buffer, which isn't stricly needed as we will never execute code
out of the swiotlb buffer, but otherwise harmless.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Tony Luck <tony.luck@intel.com>

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index d6f203658994bb8411835d1ef237cea995ae349c..c587e3316c385d42fe06c03cfc37e10207094aab 100644 (file)
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -28,7 +28,8 @@ config IA64
        select HAVE_ARCH_TRACEHOOK
        select HAVE_MEMBLOCK_NODE_MAP
        select HAVE_VIRT_CPU_ACCOUNTING
-       select ARCH_HAS_DMA_MARK_CLEAN
+       select ARCH_HAS_DMA_COHERENT_TO_PFN
+       select ARCH_HAS_SYNC_DMA_FOR_CPU
        select VIRT_TO_BUS
        select ARCH_DISCARD_MEMBLOCK
        select GENERIC_IRQ_PROBE

diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 7a471d8d67d4eea7cffcad2feb00adaed91fae85..36dd6aa6d7597757220796188ace680f657421f3 100644 (file)
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/swiotlb.h>
 #include <linux/export.h>
 
@@ -16,6 +16,24 @@ const struct dma_map_ops *dma_get_ops(struct device *dev)
 EXPORT_SYMBOL(dma_get_ops);
 
 #ifdef CONFIG_SWIOTLB
+void *arch_dma_alloc(struct device *dev, size_t size,
+               dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+       return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+               dma_addr_t dma_addr, unsigned long attrs)
+{
+       dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+               dma_addr_t dma_addr)
+{
+       return page_to_pfn(virt_to_page(cpu_addr));
+}
+
 void __init swiotlb_dma_init(void)
 {
        dma_ops = &swiotlb_dma_ops;

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index d5e12ff1d73cf69f1350577d61f311b5081e8075..0cf43bb13d6e561d4c22e46dd5a1bf4a07b08522 100644 (file)
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
+#include <linux/dma-noncoherent.h>
 #include <linux/efi.h>
 #include <linux/elf.h>
 #include <linux/memblock.h>
@@ -71,18 +72,14 @@ __ia64_sync_icache_dcache (pte_t pte)
  * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
  * flush them when they get mapped into an executable vm-area.
  */
-void
-dma_mark_clean(void *addr, size_t size)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+               size_t size, enum dma_data_direction dir)
 {
-       unsigned long pg_addr, end;
-
-       pg_addr = PAGE_ALIGN((unsigned long) addr);
-       end = (unsigned long) addr + size;
-       while (pg_addr + PAGE_SIZE <= end) {
-               struct page *page = virt_to_page(pg_addr);
-               set_bit(PG_arch_1, &page->flags);
-               pg_addr += PAGE_SIZE;
-       }
+       unsigned long pfn = PHYS_PFN(paddr);
+
+       do {
+               set_bit(PG_arch_1, &pfn_to_page(pfn)->flags);
+       } while (++pfn <= PHYS_PFN(paddr + size - 1));
 }
 
 inline void

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 833e80b46eb27acbccd457465436c9996115b58e..989cf872b98c60398e9394528721de1811151e9a 100644 (file)
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -441,21 +441,8 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
        xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
 
        /* NOTE: We use dev_addr here, not paddr! */
-       if (is_xen_swiotlb_buffer(dev_addr)) {
+       if (is_xen_swiotlb_buffer(dev_addr))
                swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
-               return;
-       }
-
-       if (dir != DMA_FROM_DEVICE)
-               return;
-
-       /*
-        * phys_to_virt doesn't work with hihgmem page but we could
-        * call dma_mark_clean() with hihgmem page here. However, we
-        * are fine since dma_mark_clean() is null on POWERPC. We can
-        * make dma_mark_clean() take a physical address if necessary.
-        */
-       dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
@@ -493,11 +480,6 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 
        if (target == SYNC_FOR_DEVICE)
                xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir);
-
-       if (dir != DMA_FROM_DEVICE)
-               return;
-
-       dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 6e5a47ae7d64b8216d3c30a0404b95c43d7d3eaf..1aa73f4907ae5406fb287bd6a8a1fa31718fbfa9 100644 (file)
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -48,14 +48,6 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
        return __sme_clr(__dma_to_phys(dev, daddr));
 }
 
-#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
-void dma_mark_clean(void *addr, size_t size);
-#else
-static inline void dma_mark_clean(void *addr, size_t size)
-{
-}
-#endif /* CONFIG_ARCH_HAS_DMA_MARK_CLEAN */
-
 u64 dma_direct_get_required_mask(struct device *dev);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
                gfp_t gfp, unsigned long attrs);

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 19ba8e473d71c53869bcffe6f40d65d2f4f9a1d6..2e126bac5d7d83ebaf54bba2158d8673749ca9aa 100644 (file)
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -706,21 +706,8 @@ void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
            (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
                arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
 
-       if (is_swiotlb_buffer(paddr)) {
+       if (is_swiotlb_buffer(paddr))
                swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
-               return;
-       }
-
-       if (dir != DMA_FROM_DEVICE)
-               return;
-
-       /*
-        * phys_to_virt doesn't work with hihgmem page but we could
-        * call dma_mark_clean() with hihgmem page here. However, we
-        * are fine since dma_mark_clean() is null on POWERPC. We can
-        * make dma_mark_clean() take a physical address if necessary.
-        */
-       dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 /*
@@ -750,9 +737,6 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 
        if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE)
                arch_sync_dma_for_device(hwdev, paddr, size, dir);
-
-       if (!is_swiotlb_buffer(paddr) && dir == DMA_FROM_DEVICE)
-               dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void