All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stefano Stabellini <sstabellini@kernel.org>
To: Claire Chang <tientzu@chromium.org>
Cc: Rob Herring <robh+dt@kernel.org>,
	mpe@ellerman.id.au, Joerg Roedel <joro@8bytes.org>,
	Will Deacon <will@kernel.org>,
	Frank Rowand <frowand.list@gmail.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	boris.ostrovsky@oracle.com, jgross@suse.com,
	Christoph Hellwig <hch@lst.de>,
	Marek Szyprowski <m.szyprowski@samsung.com>,
	benh@kernel.crashing.org, paulus@samba.org,
	"list@263.net:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
	sstabellini@kernel.org, Robin Murphy <robin.murphy@arm.com>,
	grant.likely@arm.com, xypron.glpk@gmx.de,
	Thierry Reding <treding@nvidia.com>,
	mingo@kernel.org, bauerman@linux.ibm.com, peterz@infradead.org,
	Greg KH <gregkh@linuxfoundation.org>,
	Saravana Kannan <saravanak@google.com>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	heikki.krogerus@linux.intel.com,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Dan Williams <dan.j.williams@intel.com>,
	Bartosz Golaszewski <bgolaszewski@baylibre.com>,
	linux-devicetree <devicetree@vger.kernel.org>,
	lkml <linux-kernel@vger.kernel.org>,
	linuxppc-dev@lists.ozlabs.org, xen-devel@lists.xenproject.org,
	Nicolas Boichat <drinkcat@chromium.org>,
	Jim Quinlan <james.quinlan@broadcom.com>,
	tfiga@chromium.org, bskeggs@redhat.com, bhelgaas@google.com,
	chris@chris-wilson.co.uk, daniel@ffwll.ch, airlied@linux.ie,
	dri-devel@lists.freedesktop.org, intel-gfx@lists.freedesktop.org,
	jani.nikula@linux.intel.com, jxgao@google.com,
	joonas.lahtinen@linux.intel.com, linux-pci@vger.kernel.org,
	maarten.lankhorst@linux.intel.com, matthew.auld@intel.com,
	rodrigo.vivi@intel.com, thomas.hellstrom@linux.intel.com
Subject: Re: [PATCH v13 09/12] swiotlb: Add restricted DMA alloc/free support
Date: Thu, 17 Jun 2021 16:31:10 -0700 (PDT)	[thread overview]
Message-ID: <alpine.DEB.2.21.2106171448490.24906@sstabellini-ThinkPad-T480s> (raw)
In-Reply-To: <20210617062635.1660944-10-tientzu@chromium.org>

On Thu, 17 Jun 2021, Claire Chang wrote:
> Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to
> support the memory allocation from restricted DMA pool.
> 
> The restricted DMA pool is preferred if available.
> 
> Note that since coherent allocation needs remapping, one must set up
> another device coherent pool by shared-dma-pool and use
> dma_alloc_from_dev_coherent instead for atomic coherent allocation.
> 
> Signed-off-by: Claire Chang <tientzu@chromium.org>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Stefano Stabellini <sstabellini@kernel.org>
> Tested-by: Will Deacon <will@kernel.org>

Acked-by: Stefano Stabellini <sstabellini@kernel.org>


> ---
>  include/linux/swiotlb.h | 26 ++++++++++++++++++++++
>  kernel/dma/direct.c     | 49 +++++++++++++++++++++++++++++++----------
>  kernel/dma/swiotlb.c    | 38 ++++++++++++++++++++++++++++++--
>  3 files changed, 99 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 8d8855c77d9a..a73fad460162 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force;
>   * @debugfs:	The dentry to debugfs.
>   * @late_alloc:	%true if allocated using the page allocator
>   * @force_bounce: %true if swiotlb bouncing is forced
> + * @for_alloc:  %true if the pool is used for memory allocation
>   */
>  struct io_tlb_mem {
>  	phys_addr_t start;
> @@ -96,6 +97,7 @@ struct io_tlb_mem {
>  	struct dentry *debugfs;
>  	bool late_alloc;
>  	bool force_bounce;
> +	bool for_alloc;
>  	struct io_tlb_slot {
>  		phys_addr_t orig_addr;
>  		size_t alloc_size;
> @@ -156,4 +158,28 @@ static inline void swiotlb_adjust_size(unsigned long size)
>  extern void swiotlb_print_info(void);
>  extern void swiotlb_set_max_segment(unsigned int);
>  
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size);
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size);
> +
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return dev->dma_io_tlb_mem->for_alloc;
> +}
> +#else
> +static inline struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	return NULL;
> +}
> +static inline bool swiotlb_free(struct device *dev, struct page *page,
> +				size_t size)
> +{
> +	return false;
> +}
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return false;
> +}
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> +
>  #endif /* __LINUX_SWIOTLB_H */
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index a92465b4eb12..2de33e5d302b 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -75,6 +75,15 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
>  }
>  
> +static void __dma_direct_free_pages(struct device *dev, struct page *page,
> +				    size_t size)
> +{
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    swiotlb_free(dev, page, size))
> +		return;
> +	dma_free_contiguous(dev, page, size);
> +}
> +
>  static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  		gfp_t gfp)
>  {
> @@ -86,6 +95,16 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  
>  	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
>  					   &phys_limit);
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    is_swiotlb_for_alloc(dev)) {
> +		page = swiotlb_alloc(dev, size);
> +		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
> +			__dma_direct_free_pages(dev, page, size);
> +			return NULL;
> +		}
> +		return page;
> +	}
> +
>  	page = dma_alloc_contiguous(dev, size, gfp);
>  	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
>  		dma_free_contiguous(dev, page, size);
> @@ -142,7 +161,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  		gfp |= __GFP_NOWARN;
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
>  		if (!page)
>  			return NULL;
> @@ -155,18 +174,23 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev))
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
>  
>  	/*
>  	 * Remapping or decrypting memory may block. If either is required and
>  	 * we can't block, allocate the memory from the atomic pools.
> +	 * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must
> +	 * set up another device coherent pool by shared-dma-pool and use
> +	 * dma_alloc_from_dev_coherent instead.
>  	 */
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
>  	    !gfpflags_allow_blocking(gfp) &&
>  	    (force_dma_unencrypted(dev) ||
> -	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
> +	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> +	      !dev_is_dma_coherent(dev))) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	/* we always manually zero the memory once we are done */
> @@ -237,7 +261,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  			return NULL;
>  	}
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -247,15 +271,15 @@ void dma_direct_free(struct device *dev, size_t size,
>  	unsigned int page_order = get_order(size);
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		/* cpu_addr is a struct page cookie, not a kernel address */
>  		dma_free_contiguous(dev, cpu_addr, size);
>  		return;
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev)) {
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev)) {
>  		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
>  		return;
>  	}
> @@ -273,7 +297,7 @@ void dma_direct_free(struct device *dev, size_t size,
>  	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
>  		arch_dma_clear_uncached(cpu_addr, size);
>  
> -	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
> +	__dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size);
>  }
>  
>  struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
> @@ -283,7 +307,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	void *ret;
>  
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
> -	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
> +	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	page = __dma_direct_alloc_pages(dev, size, gfp);
> @@ -310,7 +335,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
>  	return page;
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -329,7 +354,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
>  	if (force_dma_unencrypted(dev))
>  		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
>  
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  }
>  
>  #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index ff09341bb9f5..6499cfbfe95f 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -463,8 +463,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
>  
>  	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
>  	do {
> -		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> -		    (orig_addr & iotlb_align_mask)) {
> +		if (orig_addr &&
> +		    (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> +			    (orig_addr & iotlb_align_mask)) {
>  			index = wrap_index(mem, index + 1);
>  			continue;
>  		}
> @@ -703,3 +704,36 @@ static int __init swiotlb_create_default_debugfs(void)
>  late_initcall(swiotlb_create_default_debugfs);
>  
>  #endif
> +
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
> +	phys_addr_t tlb_addr;
> +	int index;
> +
> +	if (!mem)
> +		return NULL;
> +
> +	index = swiotlb_find_slots(dev, 0, size);
> +	if (index == -1)
> +		return NULL;
> +
> +	tlb_addr = slot_addr(mem->start, index);
> +
> +	return pfn_to_page(PFN_DOWN(tlb_addr));
> +}
> +
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size)
> +{
> +	phys_addr_t tlb_addr = page_to_phys(page);
> +
> +	if (!is_swiotlb_buffer(dev, tlb_addr))
> +		return false;
> +
> +	swiotlb_release_slots(dev, tlb_addr);
> +
> +	return true;
> +}
> +
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> -- 
> 2.32.0.288.g62a8d224e6-goog
> 

WARNING: multiple messages have this Message-ID
From: Stefano Stabellini <sstabellini@kernel.org>
To: Claire Chang <tientzu@chromium.org>
Cc: heikki.krogerus@linux.intel.com,
	thomas.hellstrom@linux.intel.com, peterz@infradead.org,
	joonas.lahtinen@linux.intel.com, dri-devel@lists.freedesktop.org,
	chris@chris-wilson.co.uk, grant.likely@arm.com, paulus@samba.org,
	Frank Rowand <frowand.list@gmail.com>,
	mingo@kernel.org, Marek Szyprowski <m.szyprowski@samsung.com>,
	sstabellini@kernel.org, Saravana Kannan <saravanak@google.com>,
	Joerg Roedel <joro@8bytes.org>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	Christoph Hellwig <hch@lst.de>,
	Bartosz Golaszewski <bgolaszewski@baylibre.com>,
	bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org,
	Thierry Reding <treding@nvidia.com>,
	intel-gfx@lists.freedesktop.org, matthew.auld@intel.com,
	linux-devicetree <devicetree@vger.kernel.org>,
	jxgao@google.com, daniel@ffwll.ch, Will Deacon <will@kernel.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	maarten.lankhorst@linux.intel.com, airlied@linux.ie,
	Dan Williams <dan.j.williams@intel.com>,
	linuxppc-dev@lists.ozlabs.org, jani.nikula@linux.intel.com,
	Rob Herring <robh+dt@kernel.org>,
	rodrigo.vivi@intel.com, bhelgaas@google.com,
	boris.ostrovsky@oracle.com,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	jgross@suse.com, Nicolas Boichat <drinkcat@chromium.org>,
	Greg KH <gregkh@linuxfoundation.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	lkml <linux-kernel@vger.kernel.org>,
	tfiga@chromium.org,
	"list@263.net:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
	Jim Quinlan <james.quinlan@broadcom.com>,
	xypron.glpk@gmx.de, Robin Murphy <robin.murphy@arm.com>,
	bauerman@linux.ibm.com
Subject: Re: [PATCH v13 09/12] swiotlb: Add restricted DMA alloc/free support
Date: Thu, 17 Jun 2021 16:31:10 -0700 (PDT)	[thread overview]
Message-ID: <alpine.DEB.2.21.2106171448490.24906@sstabellini-ThinkPad-T480s> (raw)
In-Reply-To: <20210617062635.1660944-10-tientzu@chromium.org>

On Thu, 17 Jun 2021, Claire Chang wrote:
> Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to
> support the memory allocation from restricted DMA pool.
> 
> The restricted DMA pool is preferred if available.
> 
> Note that since coherent allocation needs remapping, one must set up
> another device coherent pool by shared-dma-pool and use
> dma_alloc_from_dev_coherent instead for atomic coherent allocation.
> 
> Signed-off-by: Claire Chang <tientzu@chromium.org>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Stefano Stabellini <sstabellini@kernel.org>
> Tested-by: Will Deacon <will@kernel.org>

Acked-by: Stefano Stabellini <sstabellini@kernel.org>


> ---
>  include/linux/swiotlb.h | 26 ++++++++++++++++++++++
>  kernel/dma/direct.c     | 49 +++++++++++++++++++++++++++++++----------
>  kernel/dma/swiotlb.c    | 38 ++++++++++++++++++++++++++++++--
>  3 files changed, 99 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 8d8855c77d9a..a73fad460162 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force;
>   * @debugfs:	The dentry to debugfs.
>   * @late_alloc:	%true if allocated using the page allocator
>   * @force_bounce: %true if swiotlb bouncing is forced
> + * @for_alloc:  %true if the pool is used for memory allocation
>   */
>  struct io_tlb_mem {
>  	phys_addr_t start;
> @@ -96,6 +97,7 @@ struct io_tlb_mem {
>  	struct dentry *debugfs;
>  	bool late_alloc;
>  	bool force_bounce;
> +	bool for_alloc;
>  	struct io_tlb_slot {
>  		phys_addr_t orig_addr;
>  		size_t alloc_size;
> @@ -156,4 +158,28 @@ static inline void swiotlb_adjust_size(unsigned long size)
>  extern void swiotlb_print_info(void);
>  extern void swiotlb_set_max_segment(unsigned int);
>  
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size);
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size);
> +
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return dev->dma_io_tlb_mem->for_alloc;
> +}
> +#else
> +static inline struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	return NULL;
> +}
> +static inline bool swiotlb_free(struct device *dev, struct page *page,
> +				size_t size)
> +{
> +	return false;
> +}
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return false;
> +}
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> +
>  #endif /* __LINUX_SWIOTLB_H */
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index a92465b4eb12..2de33e5d302b 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -75,6 +75,15 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
>  }
>  
> +static void __dma_direct_free_pages(struct device *dev, struct page *page,
> +				    size_t size)
> +{
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    swiotlb_free(dev, page, size))
> +		return;
> +	dma_free_contiguous(dev, page, size);
> +}
> +
>  static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  		gfp_t gfp)
>  {
> @@ -86,6 +95,16 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  
>  	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
>  					   &phys_limit);
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    is_swiotlb_for_alloc(dev)) {
> +		page = swiotlb_alloc(dev, size);
> +		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
> +			__dma_direct_free_pages(dev, page, size);
> +			return NULL;
> +		}
> +		return page;
> +	}
> +
>  	page = dma_alloc_contiguous(dev, size, gfp);
>  	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
>  		dma_free_contiguous(dev, page, size);
> @@ -142,7 +161,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  		gfp |= __GFP_NOWARN;
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
>  		if (!page)
>  			return NULL;
> @@ -155,18 +174,23 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev))
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
>  
>  	/*
>  	 * Remapping or decrypting memory may block. If either is required and
>  	 * we can't block, allocate the memory from the atomic pools.
> +	 * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must
> +	 * set up another device coherent pool by shared-dma-pool and use
> +	 * dma_alloc_from_dev_coherent instead.
>  	 */
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
>  	    !gfpflags_allow_blocking(gfp) &&
>  	    (force_dma_unencrypted(dev) ||
> -	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
> +	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> +	      !dev_is_dma_coherent(dev))) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	/* we always manually zero the memory once we are done */
> @@ -237,7 +261,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  			return NULL;
>  	}
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -247,15 +271,15 @@ void dma_direct_free(struct device *dev, size_t size,
>  	unsigned int page_order = get_order(size);
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		/* cpu_addr is a struct page cookie, not a kernel address */
>  		dma_free_contiguous(dev, cpu_addr, size);
>  		return;
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev)) {
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev)) {
>  		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
>  		return;
>  	}
> @@ -273,7 +297,7 @@ void dma_direct_free(struct device *dev, size_t size,
>  	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
>  		arch_dma_clear_uncached(cpu_addr, size);
>  
> -	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
> +	__dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size);
>  }
>  
>  struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
> @@ -283,7 +307,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	void *ret;
>  
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
> -	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
> +	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	page = __dma_direct_alloc_pages(dev, size, gfp);
> @@ -310,7 +335,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
>  	return page;
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -329,7 +354,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
>  	if (force_dma_unencrypted(dev))
>  		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
>  
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  }
>  
>  #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index ff09341bb9f5..6499cfbfe95f 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -463,8 +463,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
>  
>  	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
>  	do {
> -		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> -		    (orig_addr & iotlb_align_mask)) {
> +		if (orig_addr &&
> +		    (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> +			    (orig_addr & iotlb_align_mask)) {
>  			index = wrap_index(mem, index + 1);
>  			continue;
>  		}
> @@ -703,3 +704,36 @@ static int __init swiotlb_create_default_debugfs(void)
>  late_initcall(swiotlb_create_default_debugfs);
>  
>  #endif
> +
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
> +	phys_addr_t tlb_addr;
> +	int index;
> +
> +	if (!mem)
> +		return NULL;
> +
> +	index = swiotlb_find_slots(dev, 0, size);
> +	if (index == -1)
> +		return NULL;
> +
> +	tlb_addr = slot_addr(mem->start, index);
> +
> +	return pfn_to_page(PFN_DOWN(tlb_addr));
> +}
> +
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size)
> +{
> +	phys_addr_t tlb_addr = page_to_phys(page);
> +
> +	if (!is_swiotlb_buffer(dev, tlb_addr))
> +		return false;
> +
> +	swiotlb_release_slots(dev, tlb_addr);
> +
> +	return true;
> +}
> +
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> -- 
> 2.32.0.288.g62a8d224e6-goog
> 

WARNING: multiple messages have this Message-ID
From: Stefano Stabellini <sstabellini@kernel.org>
To: Claire Chang <tientzu@chromium.org>
Cc: heikki.krogerus@linux.intel.com,
	thomas.hellstrom@linux.intel.com, peterz@infradead.org,
	benh@kernel.crashing.org, joonas.lahtinen@linux.intel.com,
	dri-devel@lists.freedesktop.org, chris@chris-wilson.co.uk,
	grant.likely@arm.com, paulus@samba.org,
	Frank Rowand <frowand.list@gmail.com>,
	mingo@kernel.org, sstabellini@kernel.org,
	Saravana Kannan <saravanak@google.com>,
	mpe@ellerman.id.au,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	Christoph Hellwig <hch@lst.de>,
	Bartosz Golaszewski <bgolaszewski@baylibre.com>,
	bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org,
	Thierry Reding <treding@nvidia.com>,
	intel-gfx@lists.freedesktop.org, matthew.auld@intel.com,
	linux-devicetree <devicetree@vger.kernel.org>,
	jxgao@google.com, daniel@ffwll.ch, Will Deacon <will@kernel.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	maarten.lankhorst@linux.intel.com, airlied@linux.ie,
	Dan Williams <dan.j.williams@intel.com>,
	linuxppc-dev@lists.ozlabs.org, jani.nikula@linux.intel.com,
	Rob Herring <robh+dt@kernel.org>,
	rodrigo.vivi@intel.com, bhelgaas@google.com,
	boris.ostrovsky@oracle.com,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	jgross@suse.com, Nicolas Boichat <drinkcat@chromium.org>,
	Greg KH <gregkh@linuxfoundation.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	lkml <linux-kernel@vger.kernel.org>,
	"list@263.net:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
	Jim Quinlan <james.quinlan@broadcom.com>,
	xypron.glpk@gmx.de, Robin Murphy <robin.murphy@arm.com>,
	bauerman@linux.ibm.com
Subject: Re: [PATCH v13 09/12] swiotlb: Add restricted DMA alloc/free support
Date: Thu, 17 Jun 2021 16:31:10 -0700 (PDT)	[thread overview]
Message-ID: <alpine.DEB.2.21.2106171448490.24906@sstabellini-ThinkPad-T480s> (raw)
In-Reply-To: <20210617062635.1660944-10-tientzu@chromium.org>

On Thu, 17 Jun 2021, Claire Chang wrote:
> Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to
> support the memory allocation from restricted DMA pool.
> 
> The restricted DMA pool is preferred if available.
> 
> Note that since coherent allocation needs remapping, one must set up
> another device coherent pool by shared-dma-pool and use
> dma_alloc_from_dev_coherent instead for atomic coherent allocation.
> 
> Signed-off-by: Claire Chang <tientzu@chromium.org>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Stefano Stabellini <sstabellini@kernel.org>
> Tested-by: Will Deacon <will@kernel.org>

Acked-by: Stefano Stabellini <sstabellini@kernel.org>


> ---
>  include/linux/swiotlb.h | 26 ++++++++++++++++++++++
>  kernel/dma/direct.c     | 49 +++++++++++++++++++++++++++++++----------
>  kernel/dma/swiotlb.c    | 38 ++++++++++++++++++++++++++++++--
>  3 files changed, 99 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 8d8855c77d9a..a73fad460162 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force;
>   * @debugfs:	The dentry to debugfs.
>   * @late_alloc:	%true if allocated using the page allocator
>   * @force_bounce: %true if swiotlb bouncing is forced
> + * @for_alloc:  %true if the pool is used for memory allocation
>   */
>  struct io_tlb_mem {
>  	phys_addr_t start;
> @@ -96,6 +97,7 @@ struct io_tlb_mem {
>  	struct dentry *debugfs;
>  	bool late_alloc;
>  	bool force_bounce;
> +	bool for_alloc;
>  	struct io_tlb_slot {
>  		phys_addr_t orig_addr;
>  		size_t alloc_size;
> @@ -156,4 +158,28 @@ static inline void swiotlb_adjust_size(unsigned long size)
>  extern void swiotlb_print_info(void);
>  extern void swiotlb_set_max_segment(unsigned int);
>  
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size);
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size);
> +
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return dev->dma_io_tlb_mem->for_alloc;
> +}
> +#else
> +static inline struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	return NULL;
> +}
> +static inline bool swiotlb_free(struct device *dev, struct page *page,
> +				size_t size)
> +{
> +	return false;
> +}
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return false;
> +}
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> +
>  #endif /* __LINUX_SWIOTLB_H */
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index a92465b4eb12..2de33e5d302b 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -75,6 +75,15 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
>  }
>  
> +static void __dma_direct_free_pages(struct device *dev, struct page *page,
> +				    size_t size)
> +{
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    swiotlb_free(dev, page, size))
> +		return;
> +	dma_free_contiguous(dev, page, size);
> +}
> +
>  static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  		gfp_t gfp)
>  {
> @@ -86,6 +95,16 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  
>  	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
>  					   &phys_limit);
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    is_swiotlb_for_alloc(dev)) {
> +		page = swiotlb_alloc(dev, size);
> +		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
> +			__dma_direct_free_pages(dev, page, size);
> +			return NULL;
> +		}
> +		return page;
> +	}
> +
>  	page = dma_alloc_contiguous(dev, size, gfp);
>  	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
>  		dma_free_contiguous(dev, page, size);
> @@ -142,7 +161,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  		gfp |= __GFP_NOWARN;
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
>  		if (!page)
>  			return NULL;
> @@ -155,18 +174,23 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev))
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
>  
>  	/*
>  	 * Remapping or decrypting memory may block. If either is required and
>  	 * we can't block, allocate the memory from the atomic pools.
> +	 * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must
> +	 * set up another device coherent pool by shared-dma-pool and use
> +	 * dma_alloc_from_dev_coherent instead.
>  	 */
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
>  	    !gfpflags_allow_blocking(gfp) &&
>  	    (force_dma_unencrypted(dev) ||
> -	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
> +	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> +	      !dev_is_dma_coherent(dev))) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	/* we always manually zero the memory once we are done */
> @@ -237,7 +261,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  			return NULL;
>  	}
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -247,15 +271,15 @@ void dma_direct_free(struct device *dev, size_t size,
>  	unsigned int page_order = get_order(size);
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		/* cpu_addr is a struct page cookie, not a kernel address */
>  		dma_free_contiguous(dev, cpu_addr, size);
>  		return;
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev)) {
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev)) {
>  		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
>  		return;
>  	}
> @@ -273,7 +297,7 @@ void dma_direct_free(struct device *dev, size_t size,
>  	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
>  		arch_dma_clear_uncached(cpu_addr, size);
>  
> -	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
> +	__dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size);
>  }
>  
>  struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
> @@ -283,7 +307,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	void *ret;
>  
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
> -	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
> +	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	page = __dma_direct_alloc_pages(dev, size, gfp);
> @@ -310,7 +335,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
>  	return page;
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -329,7 +354,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
>  	if (force_dma_unencrypted(dev))
>  		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
>  
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  }
>  
>  #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index ff09341bb9f5..6499cfbfe95f 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -463,8 +463,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
>  
>  	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
>  	do {
> -		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> -		    (orig_addr & iotlb_align_mask)) {
> +		if (orig_addr &&
> +		    (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> +			    (orig_addr & iotlb_align_mask)) {
>  			index = wrap_index(mem, index + 1);
>  			continue;
>  		}
> @@ -703,3 +704,36 @@ static int __init swiotlb_create_default_debugfs(void)
>  late_initcall(swiotlb_create_default_debugfs);
>  
>  #endif
> +
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
> +	phys_addr_t tlb_addr;
> +	int index;
> +
> +	if (!mem)
> +		return NULL;
> +
> +	index = swiotlb_find_slots(dev, 0, size);
> +	if (index == -1)
> +		return NULL;
> +
> +	tlb_addr = slot_addr(mem->start, index);
> +
> +	return pfn_to_page(PFN_DOWN(tlb_addr));
> +}
> +
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size)
> +{
> +	phys_addr_t tlb_addr = page_to_phys(page);
> +
> +	if (!is_swiotlb_buffer(dev, tlb_addr))
> +		return false;
> +
> +	swiotlb_release_slots(dev, tlb_addr);
> +
> +	return true;
> +}
> +
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> -- 
> 2.32.0.288.g62a8d224e6-goog
> 
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

WARNING: multiple messages have this Message-ID
From: Stefano Stabellini <sstabellini@kernel.org>
To: Claire Chang <tientzu@chromium.org>
Cc: heikki.krogerus@linux.intel.com,
	thomas.hellstrom@linux.intel.com, peterz@infradead.org,
	dri-devel@lists.freedesktop.org, chris@chris-wilson.co.uk,
	grant.likely@arm.com, paulus@samba.org,
	Frank Rowand <frowand.list@gmail.com>,
	mingo@kernel.org, Marek Szyprowski <m.szyprowski@samsung.com>,
	sstabellini@kernel.org, Saravana Kannan <saravanak@google.com>,
	mpe@ellerman.id.au, Joerg Roedel <joro@8bytes.org>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	Christoph Hellwig <hch@lst.de>,
	Bartosz Golaszewski <bgolaszewski@baylibre.com>,
	bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org,
	Thierry Reding <treding@nvidia.com>,
	intel-gfx@lists.freedesktop.org, matthew.auld@intel.com,
	linux-devicetree <devicetree@vger.kernel.org>,
	jxgao@google.com, Will Deacon <will@kernel.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	airlied@linux.ie, Dan Williams <dan.j.williams@intel.com>,
	linuxppc-dev@lists.ozlabs.org, Rob Herring <robh+dt@kernel.org>,
	rodrigo.vivi@intel.com, bhelgaas@google.com,
	boris.ostrovsky@oracle.com,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	jgross@suse.com, Nicolas Boichat <drinkcat@chromium.org>,
	Greg KH <gregkh@linuxfoundation.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	lkml <linux-kernel@vger.kernel.org>,
	tfiga@chromium.org,
	"list@263.net:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
	Jim Quinlan <james.quinlan@broadcom.com>,
	xypron.glpk@gmx.de, Robin Murphy <robin.murphy@arm.com>,
	bauerman@linux.ibm.com
Subject: Re: [PATCH v13 09/12] swiotlb: Add restricted DMA alloc/free support
Date: Thu, 17 Jun 2021 16:31:10 -0700 (PDT)	[thread overview]
Message-ID: <alpine.DEB.2.21.2106171448490.24906@sstabellini-ThinkPad-T480s> (raw)
In-Reply-To: <20210617062635.1660944-10-tientzu@chromium.org>

On Thu, 17 Jun 2021, Claire Chang wrote:
> Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to
> support the memory allocation from restricted DMA pool.
> 
> The restricted DMA pool is preferred if available.
> 
> Note that since coherent allocation needs remapping, one must set up
> another device coherent pool by shared-dma-pool and use
> dma_alloc_from_dev_coherent instead for atomic coherent allocation.
> 
> Signed-off-by: Claire Chang <tientzu@chromium.org>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Stefano Stabellini <sstabellini@kernel.org>
> Tested-by: Will Deacon <will@kernel.org>

Acked-by: Stefano Stabellini <sstabellini@kernel.org>


> ---
>  include/linux/swiotlb.h | 26 ++++++++++++++++++++++
>  kernel/dma/direct.c     | 49 +++++++++++++++++++++++++++++++----------
>  kernel/dma/swiotlb.c    | 38 ++++++++++++++++++++++++++++++--
>  3 files changed, 99 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 8d8855c77d9a..a73fad460162 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force;
>   * @debugfs:	The dentry to debugfs.
>   * @late_alloc:	%true if allocated using the page allocator
>   * @force_bounce: %true if swiotlb bouncing is forced
> + * @for_alloc:  %true if the pool is used for memory allocation
>   */
>  struct io_tlb_mem {
>  	phys_addr_t start;
> @@ -96,6 +97,7 @@ struct io_tlb_mem {
>  	struct dentry *debugfs;
>  	bool late_alloc;
>  	bool force_bounce;
> +	bool for_alloc;
>  	struct io_tlb_slot {
>  		phys_addr_t orig_addr;
>  		size_t alloc_size;
> @@ -156,4 +158,28 @@ static inline void swiotlb_adjust_size(unsigned long size)
>  extern void swiotlb_print_info(void);
>  extern void swiotlb_set_max_segment(unsigned int);
>  
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size);
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size);
> +
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return dev->dma_io_tlb_mem->for_alloc;
> +}
> +#else
> +static inline struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	return NULL;
> +}
> +static inline bool swiotlb_free(struct device *dev, struct page *page,
> +				size_t size)
> +{
> +	return false;
> +}
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return false;
> +}
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> +
>  #endif /* __LINUX_SWIOTLB_H */
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index a92465b4eb12..2de33e5d302b 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -75,6 +75,15 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
>  }
>  
> +static void __dma_direct_free_pages(struct device *dev, struct page *page,
> +				    size_t size)
> +{
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    swiotlb_free(dev, page, size))
> +		return;
> +	dma_free_contiguous(dev, page, size);
> +}
> +
>  static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  		gfp_t gfp)
>  {
> @@ -86,6 +95,16 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  
>  	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
>  					   &phys_limit);
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    is_swiotlb_for_alloc(dev)) {
> +		page = swiotlb_alloc(dev, size);
> +		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
> +			__dma_direct_free_pages(dev, page, size);
> +			return NULL;
> +		}
> +		return page;
> +	}
> +
>  	page = dma_alloc_contiguous(dev, size, gfp);
>  	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
>  		dma_free_contiguous(dev, page, size);
> @@ -142,7 +161,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  		gfp |= __GFP_NOWARN;
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
>  		if (!page)
>  			return NULL;
> @@ -155,18 +174,23 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev))
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
>  
>  	/*
>  	 * Remapping or decrypting memory may block. If either is required and
>  	 * we can't block, allocate the memory from the atomic pools.
> +	 * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must
> +	 * set up another device coherent pool by shared-dma-pool and use
> +	 * dma_alloc_from_dev_coherent instead.
>  	 */
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
>  	    !gfpflags_allow_blocking(gfp) &&
>  	    (force_dma_unencrypted(dev) ||
> -	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
> +	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> +	      !dev_is_dma_coherent(dev))) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	/* we always manually zero the memory once we are done */
> @@ -237,7 +261,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  			return NULL;
>  	}
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -247,15 +271,15 @@ void dma_direct_free(struct device *dev, size_t size,
>  	unsigned int page_order = get_order(size);
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		/* cpu_addr is a struct page cookie, not a kernel address */
>  		dma_free_contiguous(dev, cpu_addr, size);
>  		return;
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev)) {
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev)) {
>  		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
>  		return;
>  	}
> @@ -273,7 +297,7 @@ void dma_direct_free(struct device *dev, size_t size,
>  	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
>  		arch_dma_clear_uncached(cpu_addr, size);
>  
> -	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
> +	__dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size);
>  }
>  
>  struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
> @@ -283,7 +307,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	void *ret;
>  
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
> -	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
> +	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	page = __dma_direct_alloc_pages(dev, size, gfp);
> @@ -310,7 +335,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
>  	return page;
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -329,7 +354,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
>  	if (force_dma_unencrypted(dev))
>  		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
>  
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  }
>  
>  #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index ff09341bb9f5..6499cfbfe95f 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -463,8 +463,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
>  
>  	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
>  	do {
> -		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> -		    (orig_addr & iotlb_align_mask)) {
> +		if (orig_addr &&
> +		    (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> +			    (orig_addr & iotlb_align_mask)) {
>  			index = wrap_index(mem, index + 1);
>  			continue;
>  		}
> @@ -703,3 +704,36 @@ static int __init swiotlb_create_default_debugfs(void)
>  late_initcall(swiotlb_create_default_debugfs);
>  
>  #endif
> +
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
> +	phys_addr_t tlb_addr;
> +	int index;
> +
> +	if (!mem)
> +		return NULL;
> +
> +	index = swiotlb_find_slots(dev, 0, size);
> +	if (index == -1)
> +		return NULL;
> +
> +	tlb_addr = slot_addr(mem->start, index);
> +
> +	return pfn_to_page(PFN_DOWN(tlb_addr));
> +}
> +
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size)
> +{
> +	phys_addr_t tlb_addr = page_to_phys(page);
> +
> +	if (!is_swiotlb_buffer(dev, tlb_addr))
> +		return false;
> +
> +	swiotlb_release_slots(dev, tlb_addr);
> +
> +	return true;
> +}
> +
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> -- 
> 2.32.0.288.g62a8d224e6-goog
> 

WARNING: multiple messages have this Message-ID
From: Stefano Stabellini <sstabellini@kernel.org>
To: Claire Chang <tientzu@chromium.org>
Cc: heikki.krogerus@linux.intel.com,
	thomas.hellstrom@linux.intel.com, peterz@infradead.org,
	benh@kernel.crashing.org, dri-devel@lists.freedesktop.org,
	chris@chris-wilson.co.uk, grant.likely@arm.com, paulus@samba.org,
	Frank Rowand <frowand.list@gmail.com>,
	mingo@kernel.org, Marek Szyprowski <m.szyprowski@samsung.com>,
	sstabellini@kernel.org, Saravana Kannan <saravanak@google.com>,
	mpe@ellerman.id.au, Joerg Roedel <joro@8bytes.org>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	Christoph Hellwig <hch@lst.de>,
	Bartosz Golaszewski <bgolaszewski@baylibre.com>,
	bskeggs@redhat.com, linux-pci@vger.kernel.org,
	xen-devel@lists.xenproject.org,
	Thierry Reding <treding@nvidia.com>,
	intel-gfx@lists.freedesktop.org, matthew.auld@intel.com,
	linux-devicetree <devicetree@vger.kernel.org>,
	jxgao@google.com, Will Deacon <will@kernel.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	airlied@linux.ie, Dan Williams <dan.j.williams@intel.com>,
	linuxppc-dev@lists.ozlabs.org, Rob Herring <robh+dt@kernel.org>,
	bhelgaas@google.com, boris.ostrovsky@oracle.com,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	jgross@suse.com, Nicolas Boichat <drinkcat@chromium.org>,
	Greg KH <gregkh@linuxfoundation.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	lkml <linux-kernel@vger.kernel.org>,
	tfiga@chromium.org,
	"list@263.net:IOMMU DRIVERS" <iommu@lists.linux-foundation.org>,
	Jim Quinlan <james.quinlan@broadcom.com>,
	xypron.glpk@gmx.de, Robin Murphy <robin.murphy@arm.com>,
	bauerman@linux.ibm.com
Subject: Re: [Intel-gfx] [PATCH v13 09/12] swiotlb: Add restricted DMA alloc/free support
Date: Thu, 17 Jun 2021 16:31:10 -0700 (PDT)	[thread overview]
Message-ID: <alpine.DEB.2.21.2106171448490.24906@sstabellini-ThinkPad-T480s> (raw)
In-Reply-To: <20210617062635.1660944-10-tientzu@chromium.org>

On Thu, 17 Jun 2021, Claire Chang wrote:
> Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to
> support the memory allocation from restricted DMA pool.
> 
> The restricted DMA pool is preferred if available.
> 
> Note that since coherent allocation needs remapping, one must set up
> another device coherent pool by shared-dma-pool and use
> dma_alloc_from_dev_coherent instead for atomic coherent allocation.
> 
> Signed-off-by: Claire Chang <tientzu@chromium.org>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Tested-by: Stefano Stabellini <sstabellini@kernel.org>
> Tested-by: Will Deacon <will@kernel.org>

Acked-by: Stefano Stabellini <sstabellini@kernel.org>


> ---
>  include/linux/swiotlb.h | 26 ++++++++++++++++++++++
>  kernel/dma/direct.c     | 49 +++++++++++++++++++++++++++++++----------
>  kernel/dma/swiotlb.c    | 38 ++++++++++++++++++++++++++++++--
>  3 files changed, 99 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 8d8855c77d9a..a73fad460162 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force;
>   * @debugfs:	The dentry to debugfs.
>   * @late_alloc:	%true if allocated using the page allocator
>   * @force_bounce: %true if swiotlb bouncing is forced
> + * @for_alloc:  %true if the pool is used for memory allocation
>   */
>  struct io_tlb_mem {
>  	phys_addr_t start;
> @@ -96,6 +97,7 @@ struct io_tlb_mem {
>  	struct dentry *debugfs;
>  	bool late_alloc;
>  	bool force_bounce;
> +	bool for_alloc;
>  	struct io_tlb_slot {
>  		phys_addr_t orig_addr;
>  		size_t alloc_size;
> @@ -156,4 +158,28 @@ static inline void swiotlb_adjust_size(unsigned long size)
>  extern void swiotlb_print_info(void);
>  extern void swiotlb_set_max_segment(unsigned int);
>  
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size);
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size);
> +
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return dev->dma_io_tlb_mem->for_alloc;
> +}
> +#else
> +static inline struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	return NULL;
> +}
> +static inline bool swiotlb_free(struct device *dev, struct page *page,
> +				size_t size)
> +{
> +	return false;
> +}
> +static inline bool is_swiotlb_for_alloc(struct device *dev)
> +{
> +	return false;
> +}
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> +
>  #endif /* __LINUX_SWIOTLB_H */
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index a92465b4eb12..2de33e5d302b 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -75,6 +75,15 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
>  		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
>  }
>  
> +static void __dma_direct_free_pages(struct device *dev, struct page *page,
> +				    size_t size)
> +{
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    swiotlb_free(dev, page, size))
> +		return;
> +	dma_free_contiguous(dev, page, size);
> +}
> +
>  static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  		gfp_t gfp)
>  {
> @@ -86,6 +95,16 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
>  
>  	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
>  					   &phys_limit);
> +	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
> +	    is_swiotlb_for_alloc(dev)) {
> +		page = swiotlb_alloc(dev, size);
> +		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
> +			__dma_direct_free_pages(dev, page, size);
> +			return NULL;
> +		}
> +		return page;
> +	}
> +
>  	page = dma_alloc_contiguous(dev, size, gfp);
>  	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
>  		dma_free_contiguous(dev, page, size);
> @@ -142,7 +161,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  		gfp |= __GFP_NOWARN;
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
>  		if (!page)
>  			return NULL;
> @@ -155,18 +174,23 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev))
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
>  
>  	/*
>  	 * Remapping or decrypting memory may block. If either is required and
>  	 * we can't block, allocate the memory from the atomic pools.
> +	 * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must
> +	 * set up another device coherent pool by shared-dma-pool and use
> +	 * dma_alloc_from_dev_coherent instead.
>  	 */
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
>  	    !gfpflags_allow_blocking(gfp) &&
>  	    (force_dma_unencrypted(dev) ||
> -	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
> +	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> +	      !dev_is_dma_coherent(dev))) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	/* we always manually zero the memory once we are done */
> @@ -237,7 +261,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>  			return NULL;
>  	}
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -247,15 +271,15 @@ void dma_direct_free(struct device *dev, size_t size,
>  	unsigned int page_order = get_order(size);
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> -	    !force_dma_unencrypted(dev)) {
> +	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
>  		/* cpu_addr is a struct page cookie, not a kernel address */
>  		dma_free_contiguous(dev, cpu_addr, size);
>  		return;
>  	}
>  
>  	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
> -	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
> -	    !dev_is_dma_coherent(dev)) {
> +	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev) &&
> +	    !is_swiotlb_for_alloc(dev)) {
>  		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
>  		return;
>  	}
> @@ -273,7 +297,7 @@ void dma_direct_free(struct device *dev, size_t size,
>  	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
>  		arch_dma_clear_uncached(cpu_addr, size);
>  
> -	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
> +	__dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size);
>  }
>  
>  struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
> @@ -283,7 +307,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	void *ret;
>  
>  	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
> -	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
> +	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) &&
> +	    !is_swiotlb_for_alloc(dev))
>  		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
>  
>  	page = __dma_direct_alloc_pages(dev, size, gfp);
> @@ -310,7 +335,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>  	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
>  	return page;
>  out_free_pages:
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  	return NULL;
>  }
>  
> @@ -329,7 +354,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
>  	if (force_dma_unencrypted(dev))
>  		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
>  
> -	dma_free_contiguous(dev, page, size);
> +	__dma_direct_free_pages(dev, page, size);
>  }
>  
>  #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index ff09341bb9f5..6499cfbfe95f 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -463,8 +463,9 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
>  
>  	index = wrap = wrap_index(mem, ALIGN(mem->index, stride));
>  	do {
> -		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> -		    (orig_addr & iotlb_align_mask)) {
> +		if (orig_addr &&
> +		    (slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
> +			    (orig_addr & iotlb_align_mask)) {
>  			index = wrap_index(mem, index + 1);
>  			continue;
>  		}
> @@ -703,3 +704,36 @@ static int __init swiotlb_create_default_debugfs(void)
>  late_initcall(swiotlb_create_default_debugfs);
>  
>  #endif
> +
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +struct page *swiotlb_alloc(struct device *dev, size_t size)
> +{
> +	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
> +	phys_addr_t tlb_addr;
> +	int index;
> +
> +	if (!mem)
> +		return NULL;
> +
> +	index = swiotlb_find_slots(dev, 0, size);
> +	if (index == -1)
> +		return NULL;
> +
> +	tlb_addr = slot_addr(mem->start, index);
> +
> +	return pfn_to_page(PFN_DOWN(tlb_addr));
> +}
> +
> +bool swiotlb_free(struct device *dev, struct page *page, size_t size)
> +{
> +	phys_addr_t tlb_addr = page_to_phys(page);
> +
> +	if (!is_swiotlb_buffer(dev, tlb_addr))
> +		return false;
> +
> +	swiotlb_release_slots(dev, tlb_addr);
> +
> +	return true;
> +}
> +
> +#endif /* CONFIG_DMA_RESTRICTED_POOL */
> -- 
> 2.32.0.288.g62a8d224e6-goog
> 
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2021-06-17 23:31 UTC|newest]

Thread overview: 139+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-17  6:26 [PATCH v13 00/12] Restricted DMA Claire Chang
2021-06-17  6:26 ` [Intel-gfx] " Claire Chang
2021-06-17  6:26 ` Claire Chang
2021-06-17  6:26 ` Claire Chang
2021-06-17  6:26 ` Claire Chang
2021-06-17  6:26 ` [PATCH v13 01/12] swiotlb: Refactor swiotlb init functions Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17 23:30   ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` [Intel-gfx] " Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-18  6:25     ` Claire Chang
2021-06-18  6:25       ` Claire Chang
2021-06-18  6:25       ` [Intel-gfx] " Claire Chang
2021-06-18  6:25       ` Claire Chang
2021-06-18  6:25       ` Claire Chang
2021-06-18  6:25       ` Claire Chang
2021-06-18 14:09       ` Tom Lendacky
2021-06-18 14:09         ` [Intel-gfx] " Tom Lendacky
2021-06-18 14:09         ` Tom Lendacky
2021-06-18 14:09         ` Tom Lendacky via iommu
2021-06-18 14:09         ` Tom Lendacky
2021-06-18 14:32         ` Christoph Hellwig
2021-06-18 14:32           ` [Intel-gfx] " Christoph Hellwig
2021-06-18 14:32           ` Christoph Hellwig
2021-06-18 14:32           ` Christoph Hellwig
2021-06-21 17:59           ` Stefano Stabellini
2021-06-21 17:59             ` Stefano Stabellini
2021-06-21 17:59             ` [Intel-gfx] " Stefano Stabellini
2021-06-21 17:59             ` Stefano Stabellini
2021-06-21 17:59             ` Stefano Stabellini
2021-06-21 17:59             ` Stefano Stabellini
2021-06-21 20:19             ` Christoph Hellwig
2021-06-21 20:19               ` [Intel-gfx] " Christoph Hellwig
2021-06-21 20:19               ` Christoph Hellwig
2021-06-21 20:19               ` Christoph Hellwig
2021-06-17  6:26 ` [PATCH v13 02/12] swiotlb: Refactor swiotlb_create_debugfs Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26 ` [PATCH v13 03/12] swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17 23:30   ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` [Intel-gfx] " Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17  6:26 ` [PATCH v13 04/12] swiotlb: Update is_swiotlb_buffer to add a struct device argument Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17 23:30   ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` [Intel-gfx] " Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17  6:26 ` [PATCH v13 05/12] swiotlb: Update is_swiotlb_active " Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17 23:30   ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` [Intel-gfx] " Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17 23:30     ` Stefano Stabellini
2021-06-17  6:26 ` [PATCH v13 06/12] swiotlb: Use is_swiotlb_force_bounce for swiotlb data bouncing Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17 23:31   ` Stefano Stabellini
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17 23:31     ` [Intel-gfx] " Stefano Stabellini
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17  6:26 ` [PATCH v13 07/12] swiotlb: Move alloc_size to swiotlb_find_slots Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26 ` [PATCH v13 08/12] swiotlb: Refactor swiotlb_tbl_unmap_single Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26 ` [PATCH v13 09/12] swiotlb: Add restricted DMA alloc/free support Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17 23:31   ` Stefano Stabellini [this message]
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17 23:31     ` [Intel-gfx] " Stefano Stabellini
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17 23:31     ` Stefano Stabellini
2021-06-17  6:26 ` [PATCH v13 10/12] swiotlb: Add restricted DMA pool initialization Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26 ` [PATCH v13 11/12] dt-bindings: of: Add restricted DMA pool Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26 ` [PATCH v13 12/12] of: Add plumbing for " Claire Chang
2021-06-17  6:26   ` [Intel-gfx] " Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:26   ` Claire Chang
2021-06-17  6:32 ` [PATCH v13 00/12] Restricted DMA Claire Chang
2021-06-17  6:32   ` Claire Chang
2021-06-17  6:32   ` [Intel-gfx] " Claire Chang
2021-06-17  6:32   ` Claire Chang
2021-06-17  6:32   ` Claire Chang
2021-06-17  6:32   ` Claire Chang
2021-06-19  3:43   ` Claire Chang
2021-06-19  3:43     ` Claire Chang
2021-06-19  3:43     ` [Intel-gfx] " Claire Chang
2021-06-19  3:43     ` Claire Chang
2021-06-19  3:43     ` Claire Chang
2021-06-19  3:43     ` Claire Chang
2021-06-17  6:33 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=alpine.DEB.2.21.2106171448490.24906@sstabellini-ThinkPad-T480s \
    --to=sstabellini@kernel.org \
    --cc=airlied@linux.ie \
    --cc=andriy.shevchenko@linux.intel.com \
    --cc=bauerman@linux.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=bgolaszewski@baylibre.com \
    --cc=bhelgaas@google.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bskeggs@redhat.com \
    --cc=chris@chris-wilson.co.uk \
    --cc=dan.j.williams@intel.com \
    --cc=daniel@ffwll.ch \
    --cc=devicetree@vger.kernel.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=drinkcat@chromium.org \
    --cc=frowand.list@gmail.com \
    --cc=grant.likely@arm.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hch@lst.de \
    --cc=heikki.krogerus@linux.intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=james.quinlan@broadcom.com \
    --cc=jani.nikula@linux.intel.com \
    --cc=jgross@suse.com \
    --cc=joonas.lahtinen@linux.intel.com \
    --cc=joro@8bytes.org \
    --cc=jxgao@google.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=m.szyprowski@samsung.com \
    --cc=maarten.lankhorst@linux.intel.com \
    --cc=matthew.auld@intel.com \
    --cc=mingo@kernel.org \
    --cc=mpe@ellerman.id.au \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    --cc=rafael.j.wysocki@intel.com \
    --cc=rdunlap@infradead.org \
    --cc=robh+dt@kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=saravanak@google.com \
    --cc=tfiga@chromium.org \
    --cc=thomas.hellstrom@linux.intel.com \
    --cc=tientzu@chromium.org \
    --cc=treding@nvidia.com \
    --cc=will@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    --cc=xypron.glpk@gmx.de \
    --subject='Re: [PATCH v13 09/12] swiotlb: Add restricted DMA alloc/free support' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.