From: Aneesh Kumar K.V <aneesh.kumar@kernel.org>
To: Mostafa Saleh <smostafa@google.com>
Cc: iommu@lists.linux.dev, linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, linux-coco@lists.linux.dev,
Robin Murphy <robin.murphy@arm.com>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
Steven Price <steven.price@arm.com>,
Suzuki K Poulose <Suzuki.Poulose@arm.com>,
Catalin Marinas <catalin.marinas@arm.com>,
Jiri Pirko <jiri@resnulli.us>, Jason Gunthorpe <jgg@ziepe.ca>,
Petr Tesarik <ptesarik@suse.com>,
Alexey Kardashevskiy <aik@amd.com>,
Dan Williams <dan.j.williams@intel.com>,
Xu Yilun <yilun.xu@linux.intel.com>,
linuxppc-dev@lists.ozlabs.org, linux-s390@vger.kernel.org,
Madhavan Srinivasan <maddy@linux.ibm.com>,
Michael Ellerman <mpe@ellerman.id.au>,
Nicholas Piggin <npiggin@gmail.com>,
"Christophe Leroy (CS GROUP)" <chleroy@kernel.org>,
Alexander Gordeev <agordeev@linux.ibm.com>,
Gerald Schaefer <gerald.schaefer@linux.ibm.com>,
Heiko Carstens <hca@linux.ibm.com>,
Vasily Gorbik <gor@linux.ibm.com>,
Christian Borntraeger <borntraeger@linux.ibm.com>,
Sven Schnelle <svens@linux.ibm.com>,
x86@kernel.org
Subject: Re: [PATCH v4 04/13] dma: swiotlb: track pool encryption state and honor DMA_ATTR_CC_SHARED
Date: Thu, 14 May 2026 18:18:05 +0530 [thread overview]
Message-ID: <yq5apl2y5f96.fsf@kernel.org> (raw)
In-Reply-To: <agW5rhE9n2gDQ0w5@google.com>
Mostafa Saleh <smostafa@google.com> writes:
> On Thu, May 14, 2026 at 11:24:42AM +0530, Aneesh Kumar K.V wrote:
>> Mostafa Saleh <smostafa@google.com> writes:
>>
>> > On Tue, May 12, 2026 at 02:33:59PM +0530, Aneesh Kumar K.V (Arm) wrote:
>> >> Teach swiotlb to distinguish between encrypted and decrypted bounce
>> >> buffer pools, and make allocation and mapping paths select a pool whose
>> >> state matches the requested DMA attributes.
>> >>
>> >> Add a decrypted flag to io_tlb_mem, initialize it for the default and
>> >> restricted pools, and propagate DMA_ATTR_CC_SHARED into swiotlb pool
>> >> allocation. Reject swiotlb alloc/map requests when the selected pool does
>> >> not match the required encrypted/decrypted state.
>> >>
>> >> Also return DMA addresses with the matching phys_to_dma_{encrypted,
>> >> unencrypted} helper so the DMA address encoding stays consistent with the
>> >> chosen pool.
>> >>
>> >> Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
>> >> ---
>> >> include/linux/dma-direct.h | 10 ++++
>> >> include/linux/swiotlb.h | 8 ++-
>> >> kernel/dma/direct.c | 14 +++--
>> >> kernel/dma/swiotlb.c | 108 +++++++++++++++++++++++++++----------
>> >> 4 files changed, 107 insertions(+), 33 deletions(-)
>> >>
>> >> diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
>> >> index c249912456f9..94fad4e7c11e 100644
>> >> --- a/include/linux/dma-direct.h
>> >> +++ b/include/linux/dma-direct.h
>> >> @@ -77,6 +77,10 @@ static inline dma_addr_t dma_range_map_max(const struct bus_dma_region *map)
>> >> #ifndef phys_to_dma_unencrypted
>> >> #define phys_to_dma_unencrypted phys_to_dma
>> >> #endif
>> >> +
>> >> +#ifndef phys_to_dma_encrypted
>> >> +#define phys_to_dma_encrypted phys_to_dma
>> >> +#endif
>> >> #else
>> >> static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
>> >> {
>> >> @@ -90,6 +94,12 @@ static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
>> >> {
>> >> return dma_addr_unencrypted(__phys_to_dma(dev, paddr));
>> >> }
>> >> +
>> >> +static inline dma_addr_t phys_to_dma_encrypted(struct device *dev,
>> >> + phys_addr_t paddr)
>> >> +{
>> >> + return dma_addr_encrypted(__phys_to_dma(dev, paddr));
>> >> +}
>> >> /*
>> >> * 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.
>> >> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
>> >> index 3dae0f592063..b3fa3c6e0169 100644
>> >> --- a/include/linux/swiotlb.h
>> >> +++ b/include/linux/swiotlb.h
>> >> @@ -81,6 +81,7 @@ struct io_tlb_pool {
>> >> struct list_head node;
>> >> struct rcu_head rcu;
>> >> bool transient;
>> >> + bool unencrypted;
>> >> #endif
>> >> };
>> >>
>> >> @@ -111,6 +112,7 @@ struct io_tlb_mem {
>> >> struct dentry *debugfs;
>> >> bool force_bounce;
>> >> bool for_alloc;
>> >> + bool unencrypted;
>> >> #ifdef CONFIG_SWIOTLB_DYNAMIC
>> >> bool can_grow;
>> >> u64 phys_limit;
>> >> @@ -282,7 +284,8 @@ static inline void swiotlb_sync_single_for_cpu(struct device *dev,
>> >> extern void swiotlb_print_info(void);
>> >>
>> >> #ifdef CONFIG_DMA_RESTRICTED_POOL
>> >> -struct page *swiotlb_alloc(struct device *dev, size_t size);
>> >> +struct page *swiotlb_alloc(struct device *dev, size_t size,
>> >> + unsigned long attrs);
>> >> bool swiotlb_free(struct device *dev, struct page *page, size_t size);
>> >>
>> >> static inline bool is_swiotlb_for_alloc(struct device *dev)
>> >> @@ -290,7 +293,8 @@ 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)
>> >> +static inline struct page *swiotlb_alloc(struct device *dev, size_t size,
>> >> + unsigned long attrs)
>> >> {
>> >> return NULL;
>> >> }
>> >> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
>> >> index dc2907439b3d..97ae4fa10521 100644
>> >> --- a/kernel/dma/direct.c
>> >> +++ b/kernel/dma/direct.c
>> >> @@ -104,9 +104,10 @@ static void __dma_direct_free_pages(struct device *dev, struct page *page,
>> >> dma_free_contiguous(dev, page, size);
>> >> }
>> >>
>> >> -static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size)
>> >> +static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size,
>> >> + unsigned long attrs)
>> >> {
>> >> - struct page *page = swiotlb_alloc(dev, size);
>> >> + struct page *page = swiotlb_alloc(dev, size, attrs);
>> >>
>> >> if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
>> >> swiotlb_free(dev, page, size);
>> >> @@ -266,8 +267,12 @@ void *dma_direct_alloc(struct device *dev, size_t size,
>> >> gfp, attrs);
>> >>
>> >> if (is_swiotlb_for_alloc(dev)) {
>> >> - page = dma_direct_alloc_swiotlb(dev, size);
>> >> + page = dma_direct_alloc_swiotlb(dev, size, attrs);
>> >> if (page) {
>> >> + /*
>> >> + * swiotlb allocations comes from pool already marked
>> >> + * decrypted
>> >> + */
>> >> mark_mem_decrypt = false;
>> >> goto setup_page;
>> >> }
>> >> @@ -374,6 +379,7 @@ void dma_direct_free(struct device *dev, size_t size,
>> >> return;
>> >>
>> >> if (swiotlb_find_pool(dev, dma_to_phys(dev, dma_addr)))
>> >> + /* Swiotlb doesn't need a page attribute update on free */
>> >> mark_mem_encrypted = false;
>> >>
>> >> if (is_vmalloc_addr(cpu_addr)) {
>> >> @@ -403,7 +409,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
>> >> gfp, attrs);
>> >>
>> >> if (is_swiotlb_for_alloc(dev)) {
>> >> - page = dma_direct_alloc_swiotlb(dev, size);
>> >> + page = dma_direct_alloc_swiotlb(dev, size, attrs);
>> >> if (!page)
>> >> return NULL;
>> >>
>> >> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
>> >> index ab4eccbaa076..065663be282c 100644
>> >> --- a/kernel/dma/swiotlb.c
>> >> +++ b/kernel/dma/swiotlb.c
>> >> @@ -259,10 +259,21 @@ void __init swiotlb_update_mem_attributes(void)
>> >> struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
>> >> unsigned long bytes;
>> >>
>> >> + /*
>> >> + * if platform support memory encryption, swiotlb buffers are
>> >> + * decrypted by default.
>> >> + */
>> >> + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
>> >> + io_tlb_default_mem.unencrypted = true;
>> >> + else
>> >> + io_tlb_default_mem.unencrypted = false;
>> >> +
>> >> if (!mem->nslabs || mem->late_alloc)
>> >> return;
>> >> bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
>> >> - set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT);
>> >> +
>> >> + if (io_tlb_default_mem.unencrypted)
>> >> + set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT);
>> >> }
>> >>
>> >> static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
>> >> @@ -505,8 +516,10 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
>> >> if (!mem->slots)
>> >> goto error_slots;
>> >>
>> >> - set_memory_decrypted((unsigned long)vstart,
>> >> - (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
>> >> + if (io_tlb_default_mem.unencrypted)
>> >> + set_memory_decrypted((unsigned long)vstart,
>> >> + (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
>> >> +
>> >> swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), nslabs, true,
>> >> nareas);
>> >> add_mem_pool(&io_tlb_default_mem, mem);
>> >> @@ -539,7 +552,9 @@ void __init swiotlb_exit(void)
>> >> tbl_size = PAGE_ALIGN(mem->end - mem->start);
>> >> slots_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), mem->nslabs));
>> >>
>> >> - set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT);
>> >> + if (io_tlb_default_mem.unencrypted)
>> >> + set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT);
>> >> +
>> >> if (mem->late_alloc) {
>> >> area_order = get_order(array_size(sizeof(*mem->areas),
>> >> mem->nareas));
>> >> @@ -563,6 +578,7 @@ void __init swiotlb_exit(void)
>> >> * @gfp: GFP flags for the allocation.
>> >> * @bytes: Size of the buffer.
>> >> * @phys_limit: Maximum allowed physical address of the buffer.
>> >> + * @unencrypted: true to allocate unencrypted memory, false for encrypted memory
>> >> *
>> >> * Allocate pages from the buddy allocator. If successful, make the allocated
>> >> * pages decrypted that they can be used for DMA.
>> >> @@ -570,7 +586,8 @@ void __init swiotlb_exit(void)
>> >> * Return: Decrypted pages, %NULL on allocation failure, or ERR_PTR(-EAGAIN)
>> >> * if the allocated physical address was above @phys_limit.
>> >> */
>> >> -static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit)
>> >> +static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes,
>> >> + u64 phys_limit, bool unencrypted)
>> >> {
>> >> unsigned int order = get_order(bytes);
>> >> struct page *page;
>> >> @@ -588,13 +605,13 @@ static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit)
>> >> }
>> >>
>> >> vaddr = phys_to_virt(paddr);
>> >> - if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes)))
>> >> + if (unencrypted && set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes)))
>> >> goto error;
>> >> return page;
>> >>
>> >> error:
>> >> /* Intentional leak if pages cannot be encrypted again. */
>> >> - if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
>> >> + if (unencrypted && !set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
>> >> __free_pages(page, order);
>> >> return NULL;
>> >> }
>> >> @@ -604,30 +621,26 @@ static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit)
>> >> * @dev: Device for which a memory pool is allocated.
>> >> * @bytes: Size of the buffer.
>> >> * @phys_limit: Maximum allowed physical address of the buffer.
>> >> + * @attrs: DMA attributes for the allocation.
>> >> * @gfp: GFP flags for the allocation.
>> >> *
>> >> * Return: Allocated pages, or %NULL on allocation failure.
>> >> */
>> >> static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
>> >> - u64 phys_limit, gfp_t gfp)
>> >> + u64 phys_limit, unsigned long attrs, gfp_t gfp)
>> >> {
>> >> struct page *page;
>> >> - unsigned long attrs = 0;
>> >>
>> >> /*
>> >> * Allocate from the atomic pools if memory is encrypted and
>> >> * the allocation is atomic, because decrypting may block.
>> >> */
>> >> - if (!gfpflags_allow_blocking(gfp) && dev && force_dma_unencrypted(dev)) {
>> >> + if (!gfpflags_allow_blocking(gfp) && (attrs & DMA_ATTR_CC_SHARED)) {
>> >> void *vaddr;
>> >>
>> >> if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
>> >> return NULL;
>> >>
>> >> - /* swiotlb considered decrypted by default */
>> >> - if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
>> >> - attrs = DMA_ATTR_CC_SHARED;
>> >> -
>> >> return dma_alloc_from_pool(dev, bytes, &vaddr, gfp,
>> >> attrs, dma_coherent_ok);
>> >> }
>> >> @@ -638,7 +651,8 @@ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
>> >> else if (phys_limit <= DMA_BIT_MASK(32))
>> >> gfp |= __GFP_DMA32;
>> >>
>> >> - while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit))) {
>> >> + while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit,
>> >> + !!(attrs & DMA_ATTR_CC_SHARED)))) {
>> >> if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
>> >> phys_limit < DMA_BIT_MASK(64) &&
>> >> !(gfp & (__GFP_DMA32 | __GFP_DMA)))
>> >> @@ -657,15 +671,18 @@ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
>> >> * swiotlb_free_tlb() - free a dynamically allocated IO TLB buffer
>> >> * @vaddr: Virtual address of the buffer.
>> >> * @bytes: Size of the buffer.
>> >> + * @unencrypted: true if @vaddr was allocated decrypted and must be
>> >> + * re-encrypted before being freed
>> >> */
>> >> -static void swiotlb_free_tlb(void *vaddr, size_t bytes)
>> >> +static void swiotlb_free_tlb(void *vaddr, size_t bytes, bool unencrypted)
>> >> {
>> >> if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
>> >> dma_free_from_pool(NULL, vaddr, bytes))
>> >> return;
>> >>
>> >> /* Intentional leak if pages cannot be encrypted again. */
>> >> - if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
>> >> + if (!unencrypted ||
>> >> + !set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
>> >> __free_pages(virt_to_page(vaddr), get_order(bytes));
>> >> }
>> >>
>> >> @@ -676,6 +693,7 @@ static void swiotlb_free_tlb(void *vaddr, size_t bytes)
>> >> * @nslabs: Desired (maximum) number of slabs.
>> >> * @nareas: Number of areas.
>> >> * @phys_limit: Maximum DMA buffer physical address.
>> >> + * @attrs: DMA attributes for the allocation.
>> >> * @gfp: GFP flags for the allocations.
>> >> *
>> >> * Allocate and initialize a new IO TLB memory pool. The actual number of
>> >> @@ -686,7 +704,8 @@ static void swiotlb_free_tlb(void *vaddr, size_t bytes)
>> >> */
>> >> static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
>> >> unsigned long minslabs, unsigned long nslabs,
>> >> - unsigned int nareas, u64 phys_limit, gfp_t gfp)
>> >> + unsigned int nareas, u64 phys_limit, unsigned long attrs,
>> >> + gfp_t gfp)
>> >> {
>> >> struct io_tlb_pool *pool;
>> >> unsigned int slot_order;
>> >> @@ -704,9 +723,10 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
>> >> if (!pool)
>> >> goto error;
>> >> pool->areas = (void *)pool + sizeof(*pool);
>> >> + pool->unencrypted = !!(attrs & DMA_ATTR_CC_SHARED);
>> >>
>> >> tlb_size = nslabs << IO_TLB_SHIFT;
>> >> - while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, gfp))) {
>> >> + while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, attrs, gfp))) {
>> >> if (nslabs <= minslabs)
>> >> goto error_tlb;
>> >> nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
>> >> @@ -724,7 +744,8 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
>> >> return pool;
>> >>
>> >> error_slots:
>> >> - swiotlb_free_tlb(page_address(tlb), tlb_size);
>> >> + swiotlb_free_tlb(page_address(tlb), tlb_size,
>> >> + !!(attrs & DMA_ATTR_CC_SHARED));
>> >> error_tlb:
>> >> kfree(pool);
>> >> error:
>> >> @@ -742,7 +763,9 @@ static void swiotlb_dyn_alloc(struct work_struct *work)
>> >> struct io_tlb_pool *pool;
>> >>
>> >> pool = swiotlb_alloc_pool(NULL, IO_TLB_MIN_SLABS, default_nslabs,
>> >> - default_nareas, mem->phys_limit, GFP_KERNEL);
>> >> + default_nareas, mem->phys_limit,
>> >> + mem->unencrypted ? DMA_ATTR_CC_SHARED : 0,
>> >> + GFP_KERNEL);
>> >> if (!pool) {
>> >> pr_warn_ratelimited("Failed to allocate new pool");
>> >> return;
>> >> @@ -762,7 +785,7 @@ static void swiotlb_dyn_free(struct rcu_head *rcu)
>> >> size_t tlb_size = pool->end - pool->start;
>> >>
>> >> free_pages((unsigned long)pool->slots, get_order(slots_size));
>> >> - swiotlb_free_tlb(pool->vaddr, tlb_size);
>> >> + swiotlb_free_tlb(pool->vaddr, tlb_size, pool->unencrypted);
>> >> kfree(pool);
>> >> }
>> >>
>> >> @@ -1232,6 +1255,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
>> >> nslabs = nr_slots(alloc_size);
>> >> phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit);
>> >> pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit,
>> >> + mem->unencrypted ? DMA_ATTR_CC_SHARED : 0,
>> >> GFP_NOWAIT);
>> >> if (!pool)
>> >> return -1;
>> >> @@ -1394,6 +1418,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
>> >> enum dma_data_direction dir, unsigned long attrs)
>> >> {
>> >> struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
>> >> + bool require_decrypted = false;
>> >> unsigned int offset;
>> >> struct io_tlb_pool *pool;
>> >> unsigned int i;
>> >> @@ -1411,6 +1436,16 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
>> >> if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
>> >> pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
>> >>
>> >> + /*
>> >> + * if we are trying to swiotlb map a decrypted paddr or the paddr is encrypted
>> >> + * but the device is forcing decryption, use decrypted io_tlb_mem
>> >> + */
>> >> + if ((attrs & DMA_ATTR_CC_SHARED) || force_dma_unencrypted(dev))
>> >> + require_decrypted = true;
>> >> +
>> >> + if (require_decrypted != mem->unencrypted)
>> >> + return (phys_addr_t)DMA_MAPPING_ERROR;
>> >> +
>> >> /*
>> >> * The default swiotlb memory pool is allocated with PAGE_SIZE
>> >> * alignment. If a mapping is requested with larger alignment,
>> >> @@ -1608,8 +1643,14 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
>> >> if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
>> >> return DMA_MAPPING_ERROR;
>> >>
>> >> - /* Ensure that the address returned is DMA'ble */
>> >> - dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
>> >> + /*
>> >> + * Use the allocated io_tlb_mem encryption type to determine dma addr.
>> >> + */
>> >> + if (dev->dma_io_tlb_mem->unencrypted)
>> >> + dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
>> >> + else
>> >> + dma_addr = phys_to_dma_encrypted(dev, swiotlb_addr);
>> >> +
>> >> if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
>> >> __swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir,
>> >> attrs | DMA_ATTR_SKIP_CPU_SYNC,
>> >> @@ -1773,7 +1814,8 @@ static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
>> >>
>> >> #ifdef CONFIG_DMA_RESTRICTED_POOL
>> >>
>> >> -struct page *swiotlb_alloc(struct device *dev, size_t size)
>> >> +struct page *swiotlb_alloc(struct device *dev, size_t size,
>> >> + unsigned long attrs)
>> >> {
>> >> struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
>> >> struct io_tlb_pool *pool;
>> >> @@ -1784,6 +1826,9 @@ struct page *swiotlb_alloc(struct device *dev, size_t size)
>> >> if (!mem)
>> >> return NULL;
>> >>
>> >> + if (mem->unencrypted != !!(attrs & DMA_ATTR_CC_SHARED))
>> >> + return NULL;
>> >> +
>> >> align = (1 << (get_order(size) + PAGE_SHIFT)) - 1;
>> >> index = swiotlb_find_slots(dev, 0, size, align, &pool);
>> >> if (index == -1)
>> >> @@ -1853,9 +1898,18 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
>> >> kfree(mem);
>> >> return -ENOMEM;
>> >> }
>> >> + /*
>> >> + * if platform supports memory encryption,
>> >> + * restricted mem pool is decrypted by default
>> >> + */
>> >> + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
>> >> + mem->unencrypted = true;
>> >> + set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
>> >> + rmem->size >> PAGE_SHIFT);
>> >> + } else {
>> >> + mem->unencrypted = false;
>> >> + }
>> >
>> > This breaks pKVM as it doesn’t set CC_ATTR_MEM_ENCRYPT, so all virtio
>> > traffic now fails.
>> >
>> > Also, by design, some drivers are clueless about bouncing, so
>> > I believe that the pool should have a way to control it’s property
>> > (encrypted or decrypted) and that takes priority over whatever
>> > attributes comes from allocation.
>> > And that brings us to the same point whether it’s better to return
>> > the memory along with it’s state or we pass the requested state.
>> > I think for other cases it’s fine for the device/DMA-API to dictate
>> > the attrs, but not in restricted-dma case, the firmware just knows better.
>> >
>>
>> Is it that the pKVM guest kernel does not have awareness of
>> encrypted/decrypted DMA allocations? Instead, the firmware attaches
>> hypervisor-shared pages to the device via restricted-dma-pool? The
>> kernel then has swiotlb->for_alloc = true, and hence all DMA allocations
>> go through the restricted-dma-pool?
>
> Yes.
>
>>
>> Given that pKVM supports pkvm_set_memory_encrypted() and
>> pkvm_set_memory_decrypted(), can we consider adding CC_ATTR_MEM_ENCRYPT
>> support to pKVM? It would also be good to investigate whether we can set
>> force_dma_unencrypted(dev) to true where needed.
>
> I was looking in to that, but it didn't work because
> force_dma_unencrypted() is broken with restricted-dma due to the
> double decryption issue, that's when I sent my first series [1]
>
> May be we should land some basic fixes for that path so we can
> convert pKVM, then we do the full rework.
>
> I will revive my old work and see if I can send a RFC.
>
> [1] https://lore.kernel.org/all/20260305170335.963568-1-smostafa@google.com/
>
With this series, can you check whether the only change needed is
something like the following?
modified kernel/dma/swiotlb.c
@@ -1905,7 +1905,8 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
* if platform supports memory encryption,
* restricted mem pool is decrypted by default
*/
- if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+ //if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+ if (true) {
mem->unencrypted = true;
set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
rmem->size >> PAGE_SHIFT);
>
>>
>> I agree that this patch, as it stands, can break pKVM because we are now
>> missing the set_memory_decrypted() call required for pKVM to work.
>>
>> We now mark the swiotlb io_tlb_mem as unencrypted/encrypted in the guest
>> using struct io_tlb_mem->unencrypted. I am not clear what we can use for
>> pKVM to conditionalize this so that it works for both protected and
>> unprotected guests.
>
> There is no problem with non-protected guests as they don't use memory
> encryption, my initial thought was that th encrpyted/decrypted is
> per-pool property which is decided by FW (device-tree).
>
What I meant was that we need a generic way to identify a pKVM guest, so
that we can use it in the conditional above.
-aneesh
next prev parent reply other threads:[~2026-05-14 12:48 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-12 9:03 [PATCH v4 00/13] dma-mapping: Use DMA_ATTR_CC_SHARED through direct, pool and swiotlb paths Aneesh Kumar K.V (Arm)
2026-05-12 9:03 ` [PATCH v4 01/13] dma-direct: swiotlb: handle swiotlb alloc/free outside __dma_direct_alloc_pages Aneesh Kumar K.V (Arm)
2026-05-13 13:57 ` Mostafa Saleh
2026-05-14 4:54 ` Aneesh Kumar K.V
2026-05-12 9:03 ` [PATCH v4 02/13] dma-direct: use DMA_ATTR_CC_SHARED in alloc/free paths Aneesh Kumar K.V (Arm)
2026-05-13 13:58 ` Mostafa Saleh
2026-05-14 5:01 ` Aneesh Kumar K.V
2026-05-12 9:03 ` [PATCH v4 03/13] dma-pool: track decrypted atomic pools and select them via attrs Aneesh Kumar K.V (Arm)
2026-05-13 14:00 ` Mostafa Saleh
2026-05-14 7:00 ` Aneesh Kumar K.V
2026-05-14 8:06 ` Mostafa Saleh
2026-05-12 9:03 ` [PATCH v4 04/13] dma: swiotlb: track pool encryption state and honor DMA_ATTR_CC_SHARED Aneesh Kumar K.V (Arm)
2026-05-13 14:27 ` Mostafa Saleh
2026-05-13 17:24 ` Jason Gunthorpe
2026-05-14 6:24 ` Aneesh Kumar K.V
2026-05-14 11:48 ` Mostafa Saleh
2026-05-14 12:35 ` Jason Gunthorpe
2026-05-14 14:43 ` Mostafa Saleh
2026-05-14 5:54 ` Aneesh Kumar K.V
2026-05-14 12:02 ` Mostafa Saleh
2026-05-14 12:48 ` Aneesh Kumar K.V [this message]
2026-05-14 14:21 ` Mostafa Saleh
2026-05-14 14:43 ` Aneesh Kumar K.V
2026-05-14 14:37 ` Jason Gunthorpe
2026-05-14 15:43 ` Mostafa Saleh
2026-05-12 9:04 ` [PATCH v4 05/13] dma-mapping: make dma_pgprot() " Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 06/13] dma-direct: pass attrs to dma_capable() for DMA_ATTR_CC_SHARED checks Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 07/13] dma-direct: make dma_direct_map_phys() honor DMA_ATTR_CC_SHARED Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 08/13] dma-direct: set decrypted flag for remapped DMA allocations Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 09/13] dma-direct: select DMA address encoding from DMA_ATTR_CC_SHARED Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 10/13] dma-pool: fix page leak in atomic_pool_expand() cleanup Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 11/13] dma-direct: rename ret to cpu_addr in alloc helpers Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 12/13] dma-direct: return struct page from dma_direct_alloc_from_pool() Aneesh Kumar K.V (Arm)
2026-05-12 9:04 ` [PATCH v4 13/13] x86/amd-gart: preserve the direct DMA address until GART mapping succeeds Aneesh Kumar K.V (Arm)
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=yq5apl2y5f96.fsf@kernel.org \
--to=aneesh.kumar@kernel.org \
--cc=Suzuki.Poulose@arm.com \
--cc=agordeev@linux.ibm.com \
--cc=aik@amd.com \
--cc=borntraeger@linux.ibm.com \
--cc=catalin.marinas@arm.com \
--cc=chleroy@kernel.org \
--cc=dan.j.williams@intel.com \
--cc=gerald.schaefer@linux.ibm.com \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=iommu@lists.linux.dev \
--cc=jgg@ziepe.ca \
--cc=jiri@resnulli.us \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-coco@lists.linux.dev \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=m.szyprowski@samsung.com \
--cc=maddy@linux.ibm.com \
--cc=maz@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=ptesarik@suse.com \
--cc=robin.murphy@arm.com \
--cc=smostafa@google.com \
--cc=steven.price@arm.com \
--cc=svens@linux.ibm.com \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--cc=yilun.xu@linux.intel.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox