From 9087c37584fb7d8315877bb55f85e4268cc0b4f4 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Wed, 10 Jul 2019 19:01:19 +0000 Subject: dma-direct: Force unencrypted DMA under SME for certain DMA masks If a device doesn't support DMA to a physical address that includes the encryption bit (currently bit 47, so 48-bit DMA), then the DMA must occur to unencrypted memory. SWIOTLB is used to satisfy that requirement if an IOMMU is not active (enabled or configured in passthrough mode). However, commit fafadcd16595 ("swiotlb: don't dip into swiotlb pool for coherent allocations") modified the coherent allocation support in SWIOTLB to use the DMA direct coherent allocation support. When an IOMMU is not active, this resulted in dma_alloc_coherent() failing for devices that didn't support DMA addresses that included the encryption bit. Addressing this requires changes to the force_dma_unencrypted() function in kernel/dma/direct.c. Since the function is now non-trivial and SME/SEV specific, update the DMA direct support to add an arch override for the force_dma_unencrypted() function. The arch override is selected when CONFIG_AMD_MEM_ENCRYPT is set. The arch override function resides in the arch/x86/mm/mem_encrypt.c file and forces unencrypted DMA when either SEV is active or SME is active and the device does not support DMA to physical addresses that include the encryption bit. Fixes: fafadcd16595 ("swiotlb: don't dip into swiotlb pool for coherent allocations") Suggested-by: Christoph Hellwig Signed-off-by: Tom Lendacky Acked-by: Thomas Gleixner [hch: moved the force_dma_unencrypted declaration to dma-mapping.h, fold the s390 fix from Halil Pasic] Signed-off-by: Christoph Hellwig --- kernel/dma/Kconfig | 3 +++ kernel/dma/direct.c | 16 ++++------------ 2 files changed, 7 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 70f8f8d9200e..9decbba255fc 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -48,6 +48,9 @@ config ARCH_HAS_DMA_COHERENT_TO_PFN config ARCH_HAS_DMA_MMAP_PGPROT bool +config ARCH_HAS_FORCE_DMA_UNENCRYPTED + bool + config DMA_NONCOHERENT_CACHE_SYNC bool diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index b90e1aede743..d7cec866d16b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -23,14 +23,6 @@ #define ARCH_ZONE_DMA_BITS 24 #endif -/* - * For AMD SEV all DMA must be to unencrypted addresses. - */ -static inline bool force_dma_unencrypted(void) -{ - return sev_active(); -} - static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) { if (!dev->dma_mask) { @@ -46,7 +38,7 @@ static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) static inline dma_addr_t phys_to_dma_direct(struct device *dev, phys_addr_t phys) { - if (force_dma_unencrypted()) + if (force_dma_unencrypted(dev)) return __phys_to_dma(dev, phys); return phys_to_dma(dev, phys); } @@ -67,7 +59,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask) dma_mask = dev->bus_dma_mask; - if (force_dma_unencrypted()) + if (force_dma_unencrypted(dev)) *phys_mask = __dma_to_phys(dev, dma_mask); else *phys_mask = dma_to_phys(dev, dma_mask); @@ -159,7 +151,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, } ret = page_address(page); - if (force_dma_unencrypted()) { + if (force_dma_unencrypted(dev)) { set_memory_decrypted((unsigned long)ret, 1 << get_order(size)); *dma_handle = __phys_to_dma(dev, page_to_phys(page)); } else { @@ -192,7 +184,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, return; } - if (force_dma_unencrypted()) + if (force_dma_unencrypted(dev)) set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order); if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && -- cgit v1.2.3 From a5008b59cd9d8de12ab623cb5052bb4735330e5c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 16 Jul 2019 22:00:54 +0200 Subject: dma-direct: only limit the mapping size if swiotlb could be used Don't just check for a swiotlb buffer, but also if buffering might be required for this particular device. Fixes: 133d624b1cee ("dma: Introduce dma_max_mapping_size()") Reported-by: Benjamin Herrenschmidt Signed-off-by: Christoph Hellwig Tested-by: Benjamin Herrenschmidt --- kernel/dma/direct.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index d7cec866d16b..e269b6f9b444 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -399,11 +399,9 @@ int dma_direct_supported(struct device *dev, u64 mask) size_t dma_direct_max_mapping_size(struct device *dev) { - size_t size = SIZE_MAX; - /* If SWIOTLB is active, use its maximum mapping size */ - if (is_swiotlb_active()) - size = swiotlb_max_mapping_size(dev); - - return size; + if (is_swiotlb_active() && + (dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE)) + return swiotlb_max_mapping_size(dev); + return SIZE_MAX; } -- cgit v1.2.3 From 449fa54d6815be8c2c1f68fa9dbbae9384a7c03e Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Fri, 19 Jul 2019 17:26:48 +0800 Subject: dma-direct: correct the physical addr in dma_direct_sync_sg_for_cpu/device dma_map_sg() may use swiotlb buffer when the kernel command line includes "swiotlb=force" or the dma_addr is out of dev->dma_mask range. After DMA complete the memory moving from device to memory, then user call dma_sync_sg_for_cpu() to sync with DMA buffer, and copy the original virtual buffer to other space. So dma_direct_sync_sg_for_cpu() should use swiotlb physical addr, not the original physical addr from sg_phys(sg). dma_direct_sync_sg_for_device() also has the same issue, correct it as well. Fixes: 55897af63091("dma-direct: merge swiotlb_dma_ops into the dma_direct code") Signed-off-by: Fugang Duan Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- kernel/dma/direct.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index e269b6f9b444..59bdceea3737 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -234,12 +234,14 @@ void dma_direct_sync_sg_for_device(struct device *dev, int i; for_each_sg(sgl, sg, nents, i) { - if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) - swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, + phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, sg->length, dir, SYNC_FOR_DEVICE); if (!dev_is_dma_coherent(dev)) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, + arch_sync_dma_for_device(dev, paddr, sg->length, dir); } } @@ -271,11 +273,13 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, int i; for_each_sg(sgl, sg, nents, i) { + phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); + if (!dev_is_dma_coherent(dev)) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); - - if (unlikely(is_swiotlb_buffer(sg_phys(sg)))) - swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, dir, + arch_sync_dma_for_cpu(dev, paddr, sg->length, dir); + + if (unlikely(is_swiotlb_buffer(paddr))) + swiotlb_tbl_sync_single(dev, paddr, sg->length, dir, SYNC_FOR_CPU); } -- cgit v1.2.3