Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH 11/13] dma-direct: handle the memory encryption bit in
 common code
To:     Christoph Hellwig <hch@lst.de>, x86@kernel.org
Cc:     Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
        David Woodhouse <dwmw2@infradead.org>,
        Muli Ben-Yehuda <mulix@mulix.org>,
        Jon Mason <jdmason@kudzu.us>, Joerg Roedel <joro@8bytes.org>,
        iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org
References: <20180305174655.9878-1-hch@lst.de>
 <20180305174655.9878-12-hch@lst.de>
From:   Tom Lendacky <thomas.lendacky@amd.com>
Message-ID: <114e27be-5814-4258-4985-af08763c8a74@amd.com>
Date:   Mon, 12 Mar 2018 13:29:25 -0500
User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101
 Thunderbird/52.6.0
MIME-Version: 1.0
In-Reply-To: <20180305174655.9878-12-hch@lst.de>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Received-SPF: None (protection.outlook.com: amd.com does not designate
 permitted sender hosts)
SpamDiagnosticOutput: 1:99
SpamDiagnosticMetadata: NSPM
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 12 Mar 2018 18:29:33.0365 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 092fce6d-9ba0-4a43-5a94-08d5884733fb
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MWHPR12MB1150
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On 3/5/2018 11:46 AM, Christoph Hellwig wrote:
> Give the basic phys_to_dma and dma_to_phys helpers a __-prefix and add
> the memory encryption mask to the non-prefixed versions.  Use the
> __-prefixed versions directly instead of clearing the mask again in
> various places.
> 
> With that in place the generic dma-direct routines can be used to
> allocate non-encrypted bounce buffers, and the x86 SEV case can use
> the generic swiotlb ops.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

So this patch results in my system failing to boot when SME is active.
I'm investigating further to see why.  I'll follow up with more details
as I find them.

Additionally, when running with SME (not SEV), this is forcing all DMA
coherent allocations to be decrypted, when that isn't required with SME
(as long as the device can perform 48-bit or greater DMA).  So it may
be worth looking at only doing the decrypted allocations for SEV.

Thanks,
Tom

> ---
>  arch/arm/include/asm/dma-direct.h                  |  4 +-
>  arch/mips/cavium-octeon/dma-octeon.c               | 10 +--
>  .../include/asm/mach-cavium-octeon/dma-coherence.h |  4 +-
>  .../include/asm/mach-loongson64/dma-coherence.h    | 10 +--
>  arch/mips/loongson64/common/dma-swiotlb.c          |  4 +-
>  arch/powerpc/include/asm/dma-direct.h              |  4 +-
>  arch/x86/Kconfig                                   |  2 +-
>  arch/x86/include/asm/dma-direct.h                  | 25 +-------
>  arch/x86/mm/mem_encrypt.c                          | 73 +---------------------
>  arch/x86/pci/sta2x11-fixup.c                       |  6 +-
>  include/linux/dma-direct.h                         | 21 ++++++-
>  lib/dma-direct.c                                   | 21 +++++--
>  lib/swiotlb.c                                      | 25 +++-----
>  13 files changed, 70 insertions(+), 139 deletions(-)
> 
> diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
> index 5b0a8a421894..b67e5fc1fe43 100644
> --- a/arch/arm/include/asm/dma-direct.h
> +++ b/arch/arm/include/asm/dma-direct.h
> @@ -2,13 +2,13 @@
>  #ifndef ASM_ARM_DMA_DIRECT_H
>  #define ASM_ARM_DMA_DIRECT_H 1
>  
> -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> +static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
>  {
>  	unsigned int offset = paddr & ~PAGE_MASK;
>  	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
>  }
>  
> -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
> +static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
>  {
>  	unsigned int offset = dev_addr & ~PAGE_MASK;
>  	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
> diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
> index c7bb8a407041..7b335ab21697 100644
> --- a/arch/mips/cavium-octeon/dma-octeon.c
> +++ b/arch/mips/cavium-octeon/dma-octeon.c
> @@ -10,7 +10,7 @@
>   * IP32 changes by Ilya.
>   * Copyright (C) 2010 Cavium Networks, Inc.
>   */
> -#include <linux/dma-mapping.h>
> +#include <linux/dma-direct.h>
>  #include <linux/scatterlist.h>
>  #include <linux/bootmem.h>
>  #include <linux/export.h>
> @@ -182,7 +182,7 @@ struct octeon_dma_map_ops {
>  	phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
>  };
>  
> -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
>  {
>  	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
>  						      struct octeon_dma_map_ops,
> @@ -190,9 +190,9 @@ dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
>  
>  	return ops->phys_to_dma(dev, paddr);
>  }
> -EXPORT_SYMBOL(phys_to_dma);
> +EXPORT_SYMBOL(__phys_to_dma);
>  
> -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
> +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
>  {
>  	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
>  						      struct octeon_dma_map_ops,
> @@ -200,7 +200,7 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
>  
>  	return ops->dma_to_phys(dev, daddr);
>  }
> -EXPORT_SYMBOL(dma_to_phys);
> +EXPORT_SYMBOL(__dma_to_phys);
>  
>  static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
>  	.dma_map_ops = {
> diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
> index 138edf6b5b48..6eb1ee548b11 100644
> --- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
> +++ b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
> @@ -69,8 +69,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
>  	return addr + size - 1 <= *dev->dma_mask;
>  }
>  
> -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
> -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
> +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
> +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
>  
>  struct dma_map_ops;
>  extern const struct dma_map_ops *octeon_pci_dma_map_ops;
> diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
> index b1b575f5c6c1..64fc44dec0a8 100644
> --- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h
> +++ b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
> @@ -25,13 +25,13 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
>  	return addr + size - 1 <= *dev->dma_mask;
>  }
>  
> -extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
> -extern phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
> +extern dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
> +extern phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
>  static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
>  					  size_t size)
>  {
>  #ifdef CONFIG_CPU_LOONGSON3
> -	return phys_to_dma(dev, virt_to_phys(addr));
> +	return __phys_to_dma(dev, virt_to_phys(addr));
>  #else
>  	return virt_to_phys(addr) | 0x80000000;
>  #endif
> @@ -41,7 +41,7 @@ static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
>  					       struct page *page)
>  {
>  #ifdef CONFIG_CPU_LOONGSON3
> -	return phys_to_dma(dev, page_to_phys(page));
> +	return __phys_to_dma(dev, page_to_phys(page));
>  #else
>  	return page_to_phys(page) | 0x80000000;
>  #endif
> @@ -51,7 +51,7 @@ static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
>  	dma_addr_t dma_addr)
>  {
>  #if defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_64BIT)
> -	return dma_to_phys(dev, dma_addr);
> +	return __dma_to_phys(dev, dma_addr);
>  #elif defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
>  	return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff);
>  #else
> diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
> index 7bbcf89475f3..6a739f8ae110 100644
> --- a/arch/mips/loongson64/common/dma-swiotlb.c
> +++ b/arch/mips/loongson64/common/dma-swiotlb.c
> @@ -63,7 +63,7 @@ static int loongson_dma_supported(struct device *dev, u64 mask)
>  	return swiotlb_dma_supported(dev, mask);
>  }
>  
> -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
>  {
>  	long nid;
>  #ifdef CONFIG_PHYS48_TO_HT40
> @@ -75,7 +75,7 @@ dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
>  	return paddr;
>  }
>  
> -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
> +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
>  {
>  	long nid;
>  #ifdef CONFIG_PHYS48_TO_HT40
> diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
> index a5b59c765426..7702875aabb7 100644
> --- a/arch/powerpc/include/asm/dma-direct.h
> +++ b/arch/powerpc/include/asm/dma-direct.h
> @@ -17,12 +17,12 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
>  	return addr + size - 1 <= *dev->dma_mask;
>  }
>  
> -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> +static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
>  {
>  	return paddr + get_dma_offset(dev);
>  }
>  
> -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
> +static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
>  {
>  	return daddr - get_dma_offset(dev);
>  }
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 7272bb3768d7..6e25ca4c86ee 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -54,7 +54,6 @@ config X86
>  	select ARCH_HAS_FORTIFY_SOURCE
>  	select ARCH_HAS_GCOV_PROFILE_ALL
>  	select ARCH_HAS_KCOV			if X86_64
> -	select ARCH_HAS_PHYS_TO_DMA
>  	select ARCH_HAS_MEMBARRIER_SYNC_CORE
>  	select ARCH_HAS_PMEM_API		if X86_64
>  	select ARCH_HAS_REFCOUNT
> @@ -691,6 +690,7 @@ config X86_SUPPORTS_MEMORY_FAILURE
>  config STA2X11
>  	bool "STA2X11 Companion Chip Support"
>  	depends on X86_32_NON_STANDARD && PCI
> +	select ARCH_HAS_PHYS_TO_DMA
>  	select X86_DEV_DMA_OPS
>  	select X86_DMA_REMAP
>  	select SWIOTLB
> diff --git a/arch/x86/include/asm/dma-direct.h b/arch/x86/include/asm/dma-direct.h
> index 1295bc622ebe..1a19251eaac9 100644
> --- a/arch/x86/include/asm/dma-direct.h
> +++ b/arch/x86/include/asm/dma-direct.h
> @@ -2,29 +2,8 @@
>  #ifndef ASM_X86_DMA_DIRECT_H
>  #define ASM_X86_DMA_DIRECT_H 1
>  
> -#include <linux/mem_encrypt.h>
> -
> -#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
>  bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
> -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
> -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
> -#else
> -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
> -{
> -	if (!dev->dma_mask)
> -		return 0;
> -
> -	return addr + size - 1 <= *dev->dma_mask;
> -}
> -
> -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> -{
> -	return __sme_set(paddr);
> -}
> +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
> +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
>  
> -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
> -{
> -	return __sme_clr(daddr);
> -}
> -#endif /* CONFIG_X86_DMA_REMAP */
>  #endif /* ASM_X86_DMA_DIRECT_H */
> diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
> index 66beedc8fe3d..8bfc735bbdd7 100644
> --- a/arch/x86/mm/mem_encrypt.c
> +++ b/arch/x86/mm/mem_encrypt.c
> @@ -200,58 +200,6 @@ void __init sme_early_init(void)
>  		swiotlb_force = SWIOTLB_FORCE;
>  }
>  
> -static void *sev_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
> -		       gfp_t gfp, unsigned long attrs)
> -{
> -	unsigned int order;
> -	struct page *page;
> -	void *vaddr = NULL;
> -
> -	order = get_order(size);
> -	page = alloc_pages_node(dev_to_node(dev), gfp, order);
> -	if (page) {
> -		dma_addr_t addr;
> -
> -		/*
> -		 * Since we will be clearing the encryption bit, check the
> -		 * mask with it already cleared.
> -		 */
> -		addr = __sme_clr(phys_to_dma(dev, page_to_phys(page)));
> -		if ((addr + size) > dev->coherent_dma_mask) {
> -			__free_pages(page, get_order(size));
> -		} else {
> -			vaddr = page_address(page);
> -			*dma_handle = addr;
> -		}
> -	}
> -
> -	if (!vaddr)
> -		vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
> -
> -	if (!vaddr)
> -		return NULL;
> -
> -	/* Clear the SME encryption bit for DMA use if not swiotlb area */
> -	if (!is_swiotlb_buffer(dma_to_phys(dev, *dma_handle))) {
> -		set_memory_decrypted((unsigned long)vaddr, 1 << order);
> -		memset(vaddr, 0, PAGE_SIZE << order);
> -		*dma_handle = __sme_clr(*dma_handle);
> -	}
> -
> -	return vaddr;
> -}
> -
> -static void sev_free(struct device *dev, size_t size, void *vaddr,
> -		     dma_addr_t dma_handle, unsigned long attrs)
> -{
> -	/* Set the SME encryption bit for re-use if not swiotlb area */
> -	if (!is_swiotlb_buffer(dma_to_phys(dev, dma_handle)))
> -		set_memory_encrypted((unsigned long)vaddr,
> -				     1 << get_order(size));
> -
> -	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
> -}
> -
>  static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
>  {
>  	pgprot_t old_prot, new_prot;
> @@ -404,20 +352,6 @@ bool sev_active(void)
>  }
>  EXPORT_SYMBOL(sev_active);
>  
> -static const struct dma_map_ops sev_dma_ops = {
> -	.alloc                  = sev_alloc,
> -	.free                   = sev_free,
> -	.map_page               = swiotlb_map_page,
> -	.unmap_page             = swiotlb_unmap_page,
> -	.map_sg                 = swiotlb_map_sg_attrs,
> -	.unmap_sg               = swiotlb_unmap_sg_attrs,
> -	.sync_single_for_cpu    = swiotlb_sync_single_for_cpu,
> -	.sync_single_for_device = swiotlb_sync_single_for_device,
> -	.sync_sg_for_cpu        = swiotlb_sync_sg_for_cpu,
> -	.sync_sg_for_device     = swiotlb_sync_sg_for_device,
> -	.mapping_error          = swiotlb_dma_mapping_error,
> -};
> -
>  /* Architecture __weak replacement functions */
>  void __init mem_encrypt_init(void)
>  {
> @@ -428,12 +362,11 @@ void __init mem_encrypt_init(void)
>  	swiotlb_update_mem_attributes();
>  
>  	/*
> -	 * With SEV, DMA operations cannot use encryption. New DMA ops
> -	 * are required in order to mark the DMA areas as decrypted or
> -	 * to use bounce buffers.
> +	 * With SEV, DMA operations cannot use encryption, we need to use
> +	 * SWIOTLB to bounce buffer DMA operation.
>  	 */
>  	if (sev_active())
> -		dma_ops = &sev_dma_ops;
> +		dma_ops = &swiotlb_dma_ops;
>  
>  	/*
>  	 * With SEV, we need to unroll the rep string I/O instructions.
> diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
> index eac58e03f43c..7a5bafb76d77 100644
> --- a/arch/x86/pci/sta2x11-fixup.c
> +++ b/arch/x86/pci/sta2x11-fixup.c
> @@ -207,11 +207,11 @@ bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
>  }
>  
>  /**
> - * phys_to_dma - Return the DMA AMBA address used for this STA2x11 device
> + * __phys_to_dma - Return the DMA AMBA address used for this STA2x11 device
>   * @dev: device for a PCI device
>   * @paddr: Physical address
>   */
> -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
>  {
>  	if (!dev->archdata.is_sta2x11)
>  		return paddr;
> @@ -223,7 +223,7 @@ dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
>   * @dev: device for a PCI device
>   * @daddr: STA2x11 AMBA DMA address
>   */
> -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
> +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
>  {
>  	if (!dev->archdata.is_sta2x11)
>  		return daddr;
> diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
> index bcdb1a3e4b1f..53ad6a47f513 100644
> --- a/include/linux/dma-direct.h
> +++ b/include/linux/dma-direct.h
> @@ -3,18 +3,19 @@
>  #define _LINUX_DMA_DIRECT_H 1
>  
>  #include <linux/dma-mapping.h>
> +#include <linux/mem_encrypt.h>
>  
>  #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
>  #include <asm/dma-direct.h>
>  #else
> -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> +static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
>  {
>  	dma_addr_t dev_addr = (dma_addr_t)paddr;
>  
>  	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
>  }
>  
> -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
> +static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
>  {
>  	phys_addr_t paddr = (phys_addr_t)dev_addr;
>  
> @@ -30,6 +31,22 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
>  }
>  #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
>  
> +/*
> + * If memory encryption is supported, phys_to_dma will set the memory encryption
> + * bit in the DMA address, and dma_to_phys will clear it.  The raw __phys_to_dma
> + * and __dma_to_phys versions should only be used on non-encrypted memory for
> + * special occasions like DMA coherent buffers.
> + */
> +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
> +{
> +	return __sme_set(__phys_to_dma(dev, paddr));
> +}
> +
> +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
> diff --git a/lib/dma-direct.c b/lib/dma-direct.c
> index c9e8e21cb334..84f50b5982fc 100644
> --- a/lib/dma-direct.c
> +++ b/lib/dma-direct.c
> @@ -9,6 +9,7 @@
>  #include <linux/scatterlist.h>
>  #include <linux/dma-contiguous.h>
>  #include <linux/pfn.h>
> +#include <linux/set_memory.h>
>  
>  #define DIRECT_MAPPING_ERROR		0
>  
> @@ -35,9 +36,13 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
>  	return true;
>  }
>  
> +/*
> + * Since we will be clearing the encryption bit, check the mask with it already
> + * cleared.
> + */
>  static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  {
> -	return phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask;
> +	return __phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask;
>  }
>  
>  void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
> @@ -46,6 +51,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
>  	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
>  	int page_order = get_order(size);
>  	struct page *page = NULL;
> +	void *ret;
>  
>  	/* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
>  	if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
> @@ -78,10 +84,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
>  
>  	if (!page)
>  		return NULL;
> -
> -	*dma_handle = phys_to_dma(dev, page_to_phys(page));
> -	memset(page_address(page), 0, size);
> -	return page_address(page);
> +	*dma_handle = __phys_to_dma(dev, page_to_phys(page));
> +	ret = page_address(page);
> +	set_memory_decrypted((unsigned long)ret, page_order);
> +	memset(ret, 0, size);
> +	return ret;
>  }
>  
>  /*
> @@ -92,9 +99,11 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
>  		dma_addr_t dma_addr, unsigned long attrs)
>  {
>  	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
> +	unsigned int page_order = get_order(size);
>  
> +	set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
>  	if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
> -		free_pages((unsigned long)cpu_addr, get_order(size));
> +		free_pages((unsigned long)cpu_addr, page_order);
>  }
>  
>  static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
> diff --git a/lib/swiotlb.c b/lib/swiotlb.c
> index c43ec2271469..ca8eeaead925 100644
> --- a/lib/swiotlb.c
> +++ b/lib/swiotlb.c
> @@ -158,13 +158,6 @@ unsigned long swiotlb_size_or_default(void)
>  
>  void __weak swiotlb_set_mem_attributes(void *vaddr, unsigned long size) { }
>  
> -/* For swiotlb, clear memory encryption mask from dma addresses */
> -static dma_addr_t swiotlb_phys_to_dma(struct device *hwdev,
> -				      phys_addr_t address)
> -{
> -	return __sme_clr(phys_to_dma(hwdev, address));
> -}
> -
>  /* Note that this doesn't work with highmem page */
>  static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
>  				      volatile void *address)
> @@ -622,7 +615,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size,
>  		return SWIOTLB_MAP_ERROR;
>  	}
>  
> -	start_dma_addr = swiotlb_phys_to_dma(hwdev, io_tlb_start);
> +	start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
>  	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
>  				      dir, attrs);
>  }
> @@ -726,12 +719,12 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
>  		goto out_warn;
>  
>  	phys_addr = swiotlb_tbl_map_single(dev,
> -			swiotlb_phys_to_dma(dev, io_tlb_start),
> +			__phys_to_dma(dev, io_tlb_start),
>  			0, size, DMA_FROM_DEVICE, 0);
>  	if (phys_addr == SWIOTLB_MAP_ERROR)
>  		goto out_warn;
>  
> -	*dma_handle = swiotlb_phys_to_dma(dev, phys_addr);
> +	*dma_handle = __phys_to_dma(dev, phys_addr);
>  	if (dma_coherent_ok(dev, *dma_handle, size))
>  		goto out_unmap;
>  
> @@ -867,10 +860,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
>  	map = map_single(dev, phys, size, dir, attrs);
>  	if (map == SWIOTLB_MAP_ERROR) {
>  		swiotlb_full(dev, size, dir, 1);
> -		return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
> +		return __phys_to_dma(dev, io_tlb_overflow_buffer);
>  	}
>  
> -	dev_addr = swiotlb_phys_to_dma(dev, map);
> +	dev_addr = __phys_to_dma(dev, map);
>  
>  	/* Ensure that the address returned is DMA'ble */
>  	if (dma_capable(dev, dev_addr, size))
> @@ -879,7 +872,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
>  	attrs |= DMA_ATTR_SKIP_CPU_SYNC;
>  	swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
>  
> -	return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
> +	return __phys_to_dma(dev, io_tlb_overflow_buffer);
>  }
>  
>  /*
> @@ -1009,7 +1002,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
>  				sg_dma_len(sgl) = 0;
>  				return 0;
>  			}
> -			sg->dma_address = swiotlb_phys_to_dma(hwdev, map);
> +			sg->dma_address = __phys_to_dma(hwdev, map);
>  		} else
>  			sg->dma_address = dev_addr;
>  		sg_dma_len(sg) = sg->length;
> @@ -1073,7 +1066,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
>  int
>  swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
>  {
> -	return (dma_addr == swiotlb_phys_to_dma(hwdev, io_tlb_overflow_buffer));
> +	return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
>  }
>  
>  /*
> @@ -1085,7 +1078,7 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
>  int
>  swiotlb_dma_supported(struct device *hwdev, u64 mask)
>  {
> -	return swiotlb_phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
> +	return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
>  }
>  
>  #ifdef CONFIG_DMA_DIRECT_OPS
>