* [PATCH v7 07/22] dma-direct: swiotlb: handle swiotlb alloc/free outside __dma_direct_alloc_pages
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Move swiotlb allocation out of __dma_direct_alloc_pages() and handle it in
dma_direct_alloc() / dma_direct_alloc_pages().
This is needed for follow-up changes that simplify the handling of
memory encryption/decryption based on the DMA attribute flags.
swiotlb backing pages are already mapped decrypted by
swiotlb_update_mem_attributes() and rmem_swiotlb_device_init(), so
dma-direct should not call dma_set_decrypted() on allocation nor
dma_set_encrypted() on free for swiotlb-backed memory.
Update alloc/free paths to detect swiotlb-backed pages and skip
encrypt/decrypt transitions for those paths. Keep the existing highmem
rejection in dma_direct_alloc_pages() for swiotlb allocations.
Only for "restricted-dma-pool", we currently set `for_alloc = true`, while
rmem_swiotlb_device_init() decrypts the whole pool up front. This pool is
typically used together with "shared-dma-pool", where the shared region is
accessed after remap/ioremap and the returned address is suitable for
decrypted memory access. So existing code paths remain valid.
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
include/linux/swiotlb.h | 6 ++++
kernel/dma/direct.c | 71 ++++++++++++++++++++++++++++++-----------
kernel/dma/swiotlb.c | 6 ++++
3 files changed, 65 insertions(+), 18 deletions(-)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 3dae0f592063..c92ff6791595 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -284,6 +284,8 @@ extern void swiotlb_print_info(void);
#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);
+void swiotlb_free_from_pool(struct device *dev,
+ phys_addr_t tlb_addr, struct io_tlb_pool *pool);
static inline bool is_swiotlb_for_alloc(struct device *dev)
{
@@ -299,6 +301,10 @@ static inline bool swiotlb_free(struct device *dev, struct page *page,
{
return false;
}
+static inline void swiotlb_free_from_pool(struct device *dev,
+ phys_addr_t tlb_addr, struct io_tlb_pool *pool)
+{
+}
static inline bool is_swiotlb_for_alloc(struct device *dev)
{
return false;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 17f1e097499e..0cbf2b0835c4 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -96,14 +96,6 @@ static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
return ret;
}
-static void __dma_direct_free_pages(struct device *dev, struct page *page,
- size_t size)
-{
- if (swiotlb_free(dev, page, size))
- return;
- dma_free_contiguous(dev, page, size);
-}
-
static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size)
{
struct page *page = swiotlb_alloc(dev, size);
@@ -125,9 +117,6 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
WARN_ON_ONCE(!PAGE_ALIGNED(size));
- if (is_swiotlb_for_alloc(dev))
- return dma_direct_alloc_swiotlb(dev, size);
-
gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit);
page = dma_alloc_contiguous(dev, size, gfp);
if (page) {
@@ -203,6 +192,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
bool remap = false, set_uncached = false;
+ bool mark_mem_decrypt = true;
struct page *page;
void *ret;
@@ -252,11 +242,21 @@ void *dma_direct_alloc(struct device *dev, size_t size,
return page ? ret : NULL;
}
+ if (is_swiotlb_for_alloc(dev)) {
+ page = dma_direct_alloc_swiotlb(dev, size);
+ if (page) {
+ mark_mem_decrypt = false;
+ goto setup_page;
+ }
+ return NULL;
+ }
+
/* we always manually zero the memory once we are done */
page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true);
if (!page)
return NULL;
+setup_page:
/*
* dma_alloc_contiguous can return highmem pages depending on a
* combination the cma= arguments and per-arch setup. These need to be
@@ -283,7 +283,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
goto out_free_pages;
} else {
ret = page_address(page);
- if (dma_set_decrypted(dev, ret, size))
+ if (mark_mem_decrypt && dma_set_decrypted(dev, ret, size))
goto out_leak_pages;
}
@@ -300,10 +300,11 @@ void *dma_direct_alloc(struct device *dev, size_t size,
return ret;
out_encrypt_pages:
- if (dma_set_encrypted(dev, page_address(page), size))
+ if (mark_mem_decrypt && dma_set_encrypted(dev, page_address(page), size))
return NULL;
out_free_pages:
- __dma_direct_free_pages(dev, page, size);
+ if (!swiotlb_free(dev, page, size))
+ dma_free_contiguous(dev, page, size);
return NULL;
out_leak_pages:
return NULL;
@@ -312,6 +313,9 @@ void *dma_direct_alloc(struct device *dev, size_t size,
void dma_direct_free(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
{
+ phys_addr_t phys;
+ bool mark_mem_encrypted = true;
+ struct io_tlb_pool *swiotlb_pool;
unsigned int page_order = get_order(size);
if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
@@ -340,16 +344,25 @@ void dma_direct_free(struct device *dev, size_t size,
dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
return;
+ phys = dma_to_phys(dev, dma_addr);
+ swiotlb_pool = swiotlb_find_pool(dev, phys);
+ if (swiotlb_pool)
+ /* Swiotlb doesn't need a page attribute update on free */
+ mark_mem_encrypted = false;
+
if (is_vmalloc_addr(cpu_addr)) {
vunmap(cpu_addr);
} else {
if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
arch_dma_clear_uncached(cpu_addr, size);
- if (dma_set_encrypted(dev, cpu_addr, size))
+ if (mark_mem_encrypted && dma_set_encrypted(dev, cpu_addr, size))
return;
}
- __dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size);
+ if (swiotlb_pool)
+ swiotlb_free_from_pool(dev, phys, swiotlb_pool);
+ else
+ dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
}
struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
@@ -361,6 +374,15 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
return dma_direct_alloc_from_pool(dev, size, dma_handle, &ret, gfp);
+ if (is_swiotlb_for_alloc(dev)) {
+ page = dma_direct_alloc_swiotlb(dev, size);
+ if (!page)
+ return NULL;
+
+ ret = page_address(page);
+ goto setup_page;
+ }
+
page = __dma_direct_alloc_pages(dev, size, gfp, false);
if (!page)
return NULL;
@@ -368,6 +390,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
ret = page_address(page);
if (dma_set_decrypted(dev, ret, size))
goto out_leak_pages;
+setup_page:
memset(ret, 0, size);
*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
return page;
@@ -379,16 +402,28 @@ void dma_direct_free_pages(struct device *dev, size_t size,
struct page *page, dma_addr_t dma_addr,
enum dma_data_direction dir)
{
+ phys_addr_t phys;
void *vaddr = page_address(page);
+ struct io_tlb_pool *swiotlb_pool;
+ bool mark_mem_encrypted = true;
/* If page is not from an atomic pool, dma_free_from_pool_page() fails */
if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
dma_free_from_pool_page(dev, page, size))
return;
- if (dma_set_encrypted(dev, vaddr, size))
+ phys = page_to_phys(page);
+ swiotlb_pool = swiotlb_find_pool(dev, phys);
+ if (swiotlb_pool)
+ mark_mem_encrypted = false;
+
+ if (mark_mem_encrypted && dma_set_encrypted(dev, vaddr, size))
return;
- __dma_direct_free_pages(dev, page, size);
+
+ if (swiotlb_pool)
+ swiotlb_free_from_pool(dev, phys, swiotlb_pool);
+ else
+ dma_free_contiguous(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 6e8db52866bf..d54154c165e5 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1815,6 +1815,12 @@ bool swiotlb_free(struct device *dev, struct page *page, size_t size)
return true;
}
+void swiotlb_free_from_pool(struct device *dev,
+ phys_addr_t tlb_addr, struct io_tlb_pool *pool)
+{
+ swiotlb_release_slots(dev, tlb_addr, pool);
+}
+
static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
struct device *dev)
{
--
2.43.0
^ permalink raw reply related
* [PATCH v7 08/22] coco: arm64: s390: powerpc: Mark secure guests with CC_ATTR_GUEST_MEM_ENCRYPT
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
arm64 Realms, powerpc secure guests and s390 protected virtualization
guests currently report CC_ATTR_MEM_ENCRYPT, but not
CC_ATTR_GUEST_MEM_ENCRYPT.
These environments are all secure guest configurations. Their
force_dma_unencrypted() implementations also treat the same secure guest
state as requiring unencrypted DMA. Report CC_ATTR_GUEST_MEM_ENCRYPT for
the same condition so generic confidential-computing code can distinguish
guest memory encryption from host memory encryption instead of relying only
on CC_ATTR_MEM_ENCRYPT.
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
arch/arm64/kernel/rsi.c | 1 +
arch/powerpc/platforms/pseries/cc_platform.c | 1 +
arch/s390/mm/init.c | 1 +
3 files changed, 3 insertions(+)
diff --git a/arch/arm64/kernel/rsi.c b/arch/arm64/kernel/rsi.c
index 92160f2e57ff..207e36db1e7a 100644
--- a/arch/arm64/kernel/rsi.c
+++ b/arch/arm64/kernel/rsi.c
@@ -27,6 +27,7 @@ bool cc_platform_has(enum cc_attr attr)
{
switch (attr) {
case CC_ATTR_MEM_ENCRYPT:
+ case CC_ATTR_GUEST_MEM_ENCRYPT:
return is_realm_world();
default:
return false;
diff --git a/arch/powerpc/platforms/pseries/cc_platform.c b/arch/powerpc/platforms/pseries/cc_platform.c
index e8021af83a19..46e110a5a717 100644
--- a/arch/powerpc/platforms/pseries/cc_platform.c
+++ b/arch/powerpc/platforms/pseries/cc_platform.c
@@ -17,6 +17,7 @@ bool cc_platform_has(enum cc_attr attr)
{
switch (attr) {
case CC_ATTR_MEM_ENCRYPT:
+ case CC_ATTR_GUEST_MEM_ENCRYPT:
return is_secure_guest();
default:
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index c29326c44af0..6b1c5a4fa9ce 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -148,6 +148,7 @@ bool cc_platform_has(enum cc_attr attr)
{
switch (attr) {
case CC_ATTR_MEM_ENCRYPT:
+ case CC_ATTR_GUEST_MEM_ENCRYPT:
return is_prot_virt_guest();
default:
--
2.43.0
^ permalink raw reply related
* [PATCH v7 09/22] dma-mapping: Add internal shared allocation attribute
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
DMA_ATTR_CC_SHARED describes an existing DMA mapping whose backing memory
is already shared, or decrypted, for confidential computing. It is a
mapping attribute: callers use it to request a shared DMA address encoding
for memory that has already been prepared for shared DMA.
Allocation paths need a related but different state. Once the DMA core
decides that an allocation must use shared backing pages, the lower-level
allocation helpers need to select shared pools, decrypt newly allocated
pages, derive the DMA address with the shared-memory translation and
restore encryption on free. That state is internal to the DMA-mapping
implementation and should not be passed by drivers to dma_alloc_attrs().
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
Documentation/core-api/dma-attributes.rst | 29 +++++++++++++++++++++++
include/linux/dma-mapping.h | 8 +++++++
include/trace/events/dma.h | 3 ++-
3 files changed, 39 insertions(+), 1 deletion(-)
diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 123c8468d58f..eee743184acd 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -179,3 +179,32 @@ interface when building their uAPIs, when possible.
It must never be used in an in-kernel driver that only works with
kernel memory.
+
+DMA_ATTR_CC_SHARED
+------------------
+
+This attribute indicates that a DMA mapping is shared, or decrypted, for
+confidential computing guests. For normal system memory, the caller must
+already have marked the memory decrypted with set_memory_decrypted(). CPU
+PTEs for the mapping must use pgprot_decrypted(), and the same shared
+semantic may be passed to a vIOMMU when it sets up the IOPTE.
+
+This attribute describes an existing mapping. It does not allocate shared
+backing pages and must not be passed to dma_alloc_attrs(). For MMIO, use
+this together with DMA_ATTR_MMIO to indicate shared MMIO. Unless
+DMA_ATTR_MMIO is provided, the mapping requires a struct page.
+
+__DMA_ATTR_ALLOC_CC_SHARED
+--------------------------
+
+This is an internal DMA-mapping attribute for confidential computing guests.
+It is used by allocation paths after the DMA core has determined that the
+backing pages must be shared, or decrypted. For example, the direct DMA and
+SWIOTLB allocation paths use it to select shared DMA pools, decrypt newly
+allocated pages, derive DMA addresses using the shared-memory translation, and
+restore encryption on free.
+
+__DMA_ATTR_ALLOC_CC_SHARED differs from DMA_ATTR_CC_SHARED in that it is not
+a caller-visible DMA API attribute. DMA_ATTR_CC_SHARED describes an
+already-shared mapping and requires the caller to have prepared normal
+system memory before mapping it.
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index cc0823a99cfd..a3e880649fa4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -103,6 +103,14 @@
*/
#define DMA_ATTR_CC_SHARED (1UL << 13)
+/*
+ * __DMA_ATTR_ALLOC_CC_SHARED: Internal DMA-mapping attribute used by
+ * allocation paths that create shared (decrypted) backing pages for
+ * confidential computing guests. Drivers must not pass this attribute to
+ * dma_alloc_attrs().
+ */
+#define __DMA_ATTR_ALLOC_CC_SHARED (1UL << 14)
+
/*
* A dma_addr_t can hold any valid DMA or bus address for the platform. It can
* be given to a device to use as a DMA source or target. It is specific to a
diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index 31c9ddf72c9d..9df02c1511de 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -35,7 +35,8 @@ TRACE_DEFINE_ENUM(DMA_NONE);
{ DMA_ATTR_MMIO, "MMIO" }, \
{ DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" }, \
{ DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" }, \
- { DMA_ATTR_CC_SHARED, "CC_SHARED" })
+ { DMA_ATTR_CC_SHARED, "CC_SHARED" }, \
+ { __DMA_ATTR_ALLOC_CC_SHARED, "ALLOC_CC_SHARED" })
DECLARE_EVENT_CLASS(dma_map,
TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,
--
2.43.0
^ permalink raw reply related
* [PATCH v7 10/22] dma-direct: use __DMA_ATTR_ALLOC_CC_SHARED in alloc/free paths
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Propagate force_dma_unencrypted() into __DMA_ATTR_ALLOC_CC_SHARED in the
dma-direct allocation path and use the attribute to drive the related
decisions.
This updates dma_direct_alloc(), dma_direct_free(), and
dma_direct_alloc_pages() to fold the forced unencrypted case into attrs.
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
kernel/dma/direct.c | 42 +++++++++++++++++++++++++++++++++---------
kernel/dma/mapping.c | 9 +++++++++
2 files changed, 42 insertions(+), 9 deletions(-)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 0cbf2b0835c4..98e47e0b332d 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -192,16 +192,22 @@ void *dma_direct_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
bool remap = false, set_uncached = false;
- bool mark_mem_decrypt = true;
+ bool mark_mem_decrypt = false;
struct page *page;
void *ret;
+ if (force_dma_unencrypted(dev))
+ attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
+
+ if (attrs & __DMA_ATTR_ALLOC_CC_SHARED)
+ mark_mem_decrypt = true;
+
size = PAGE_ALIGN(size);
if (attrs & DMA_ATTR_NO_WARN)
gfp |= __GFP_NOWARN;
- if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
- !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev))
+ if (((attrs & (DMA_ATTR_NO_KERNEL_MAPPING | __DMA_ATTR_ALLOC_CC_SHARED)) ==
+ DMA_ATTR_NO_KERNEL_MAPPING) && !is_swiotlb_for_alloc(dev))
return dma_direct_alloc_no_mapping(dev, size, dma_handle, gfp);
if (!dev_is_dma_coherent(dev)) {
@@ -235,7 +241,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
* Remapping or decrypting memory may block, allocate the memory from
* the atomic pools instead if we aren't allowed block.
*/
- if ((remap || force_dma_unencrypted(dev)) &&
+ if ((remap || (attrs & __DMA_ATTR_ALLOC_CC_SHARED)) &&
dma_direct_use_pool(dev, gfp)) {
page = dma_direct_alloc_from_pool(dev, size, dma_handle,
&ret, gfp);
@@ -314,12 +320,22 @@ void dma_direct_free(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
{
phys_addr_t phys;
- bool mark_mem_encrypted = true;
+ bool mark_mem_encrypted = false;
struct io_tlb_pool *swiotlb_pool;
unsigned int page_order = get_order(size);
- if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
- !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
+ /*
+ * If the allocation used decrypted/shared backing pages, restore
+ * the encryption state on free.
+ */
+ if (force_dma_unencrypted(dev))
+ attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
+
+ if (attrs & __DMA_ATTR_ALLOC_CC_SHARED)
+ mark_mem_encrypted = true;
+
+ if (((attrs & (DMA_ATTR_NO_KERNEL_MAPPING | __DMA_ATTR_ALLOC_CC_SHARED)) ==
+ DMA_ATTR_NO_KERNEL_MAPPING) && !is_swiotlb_for_alloc(dev)) {
/* cpu_addr is a struct page cookie, not a kernel address */
dma_free_contiguous(dev, cpu_addr, size);
return;
@@ -368,10 +384,14 @@ void dma_direct_free(struct device *dev, size_t size,
struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
{
+ unsigned long attrs = 0;
struct page *page;
void *ret;
- if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
+ if (force_dma_unencrypted(dev))
+ attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
+
+ if ((attrs & __DMA_ATTR_ALLOC_CC_SHARED) && dma_direct_use_pool(dev, gfp))
return dma_direct_alloc_from_pool(dev, size, dma_handle, &ret, gfp);
if (is_swiotlb_for_alloc(dev)) {
@@ -405,7 +425,11 @@ void dma_direct_free_pages(struct device *dev, size_t size,
phys_addr_t phys;
void *vaddr = page_address(page);
struct io_tlb_pool *swiotlb_pool;
- bool mark_mem_encrypted = true;
+ /*
+ * if the device had requested for an unencrypted buffer,
+ * convert it to encrypted on free
+ */
+ bool mark_mem_encrypted = force_dma_unencrypted(dev);
/* If page is not from an atomic pool, dma_free_from_pool_page() fails */
if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 4fe04669e5e6..d2f70b6ccd0f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -638,6 +638,15 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
if (WARN_ON_ONCE(flag & __GFP_COMP))
return NULL;
+ if (attrs & (DMA_ATTR_CC_SHARED | __DMA_ATTR_ALLOC_CC_SHARED)) {
+ trace_dma_alloc(dev, NULL, 0, size, DMA_BIDIRECTIONAL, flag,
+ attrs);
+ return NULL;
+ }
+
+ if (force_dma_unencrypted(dev))
+ attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
+
if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) {
trace_dma_alloc(dev, cpu_addr, *dma_handle, size,
DMA_BIDIRECTIONAL, flag, attrs);
--
2.43.0
^ permalink raw reply related
* [PATCH v7 11/22] dma-pool: track decrypted atomic pools and select them via attrs
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Teach the atomic DMA pool code to distinguish between encrypted and
unencrypted pools, and make pool allocation select the matching pool based
on DMA attributes.
Introduce a dma_gen_pool wrapper that records whether a pool is
unencrypted, initialize that state when the atomic pools are created, and
use it when expanding and resizing the pools. Update dma_alloc_from_pool()
to take attrs and skip pools whose encrypted state does not match
__DMA_ATTR_ALLOC_CC_SHARED. Update dma_free_from_pool() accordingly.
Also pass __DMA_ATTR_ALLOC_CC_SHARED from the swiotlb atomic allocation
path so decrypted swiotlb allocations are taken from the correct atomic
pool.
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
drivers/iommu/dma-iommu.c | 7 +-
include/linux/dma-map-ops.h | 2 +-
kernel/dma/direct.c | 11 ++-
kernel/dma/pool.c | 173 +++++++++++++++++++++++-------------
kernel/dma/swiotlb.c | 8 +-
5 files changed, 129 insertions(+), 72 deletions(-)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 68c686c1e81a..a7b1da5e06e6 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1660,9 +1660,14 @@ void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
{
bool coherent = dev_is_dma_coherent(dev);
int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
+ bool is_alloc_cc_shared = attrs & __DMA_ATTR_ALLOC_CC_SHARED;
struct page *page = NULL;
void *cpu_addr;
+ /* Not yet supported */
+ if (is_alloc_cc_shared)
+ return NULL;
+
gfp |= __GFP_ZERO;
if (gfpflags_allow_blocking(gfp) &&
@@ -1673,7 +1678,7 @@ void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
!gfpflags_allow_blocking(gfp) && !coherent) {
page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr,
- gfp, NULL);
+ gfp, attrs, NULL);
if (!page)
return NULL;
} else {
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 137e015c1750..8fae2b7deb20 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -212,7 +212,7 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot,
void dma_common_free_remap(void *cpu_addr, size_t size);
struct page *dma_alloc_from_pool(struct device *dev, size_t size,
- void **cpu_addr, gfp_t flags,
+ void **cpu_addr, gfp_t flags, unsigned long attrs,
bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
bool dma_free_from_pool(struct device *dev, void *start, size_t size);
bool dma_free_from_pool_page(struct device *dev, struct page *page, size_t size);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 98e47e0b332d..c50d6987438e 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -154,7 +154,8 @@ static bool dma_direct_use_pool(struct device *dev, gfp_t gfp)
}
static struct page *dma_direct_alloc_from_pool(struct device *dev, size_t size,
- dma_addr_t *dma_handle, void **cpu_addr, gfp_t gfp)
+ dma_addr_t *dma_handle, void **cpu_addr, gfp_t gfp,
+ unsigned long attrs)
{
struct page *page;
u64 phys_limit;
@@ -163,7 +164,8 @@ static struct page *dma_direct_alloc_from_pool(struct device *dev, size_t size,
return NULL;
gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit);
- page = dma_alloc_from_pool(dev, size, cpu_addr, gfp, dma_coherent_ok);
+ page = dma_alloc_from_pool(dev, size, cpu_addr, gfp, attrs,
+ dma_coherent_ok);
if (!page)
return NULL;
*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
@@ -244,7 +246,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
if ((remap || (attrs & __DMA_ATTR_ALLOC_CC_SHARED)) &&
dma_direct_use_pool(dev, gfp)) {
page = dma_direct_alloc_from_pool(dev, size, dma_handle,
- &ret, gfp);
+ &ret, gfp, attrs);
return page ? ret : NULL;
}
@@ -392,7 +394,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
if ((attrs & __DMA_ATTR_ALLOC_CC_SHARED) && dma_direct_use_pool(dev, gfp))
- return dma_direct_alloc_from_pool(dev, size, dma_handle, &ret, gfp);
+ return dma_direct_alloc_from_pool(dev, size, dma_handle,
+ &ret, gfp, attrs);
if (is_swiotlb_for_alloc(dev)) {
page = dma_direct_alloc_swiotlb(dev, size);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 76bcafe03e44..5115a3e8c722 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -12,12 +12,18 @@
#include <linux/set_memory.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
+#include <linux/cc_platform.h>
-static struct gen_pool *atomic_pool_dma __ro_after_init;
+struct dma_gen_pool {
+ bool cc_shared;
+ struct gen_pool *pool;
+};
+
+static struct dma_gen_pool atomic_pool_dma __ro_after_init;
static unsigned long pool_size_dma;
-static struct gen_pool *atomic_pool_dma32 __ro_after_init;
+static struct dma_gen_pool atomic_pool_dma32 __ro_after_init;
static unsigned long pool_size_dma32;
-static struct gen_pool *atomic_pool_kernel __ro_after_init;
+static struct dma_gen_pool atomic_pool_kernel __ro_after_init;
static unsigned long pool_size_kernel;
/* Size can be defined by the coherent_pool command line */
@@ -76,7 +82,7 @@ static bool cma_in_zone(gfp_t gfp)
return true;
}
-static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
+static int atomic_pool_expand(struct dma_gen_pool *dma_pool, size_t pool_size,
gfp_t gfp)
{
unsigned int order;
@@ -114,14 +120,17 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
* Memory in the atomic DMA pools must be unencrypted, the pools do not
* shrink so no re-encryption occurs in dma_direct_free().
*/
- ret = set_memory_decrypted((unsigned long)page_to_virt(page),
- 1 << order);
- if (ret) {
- leak_pages = true;
- goto remove_mapping;
+ if (dma_pool->cc_shared) {
+ ret = set_memory_decrypted((unsigned long)page_to_virt(page),
+ 1 << order);
+ if (ret) {
+ leak_pages = true;
+ goto remove_mapping;
+ }
}
- ret = gen_pool_add_virt(pool, (unsigned long)addr, page_to_phys(page),
- pool_size, NUMA_NO_NODE);
+
+ ret = gen_pool_add_virt(dma_pool->pool, (unsigned long)addr,
+ page_to_phys(page), pool_size, NUMA_NO_NODE);
if (ret)
goto encrypt_mapping;
@@ -129,12 +138,10 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
return 0;
encrypt_mapping:
- ret = set_memory_encrypted((unsigned long)page_to_virt(page),
- 1 << order);
- if (WARN_ON_ONCE(ret)) {
- /* Decrypt succeeded but encrypt failed, purposely leak */
+ if (dma_pool->cc_shared &&
+ set_memory_encrypted((unsigned long)page_to_virt(page), 1 << order))
leak_pages = true;
- }
+
remove_mapping:
#ifdef CONFIG_DMA_DIRECT_REMAP
dma_common_free_remap(addr, pool_size);
@@ -146,46 +153,52 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
return ret;
}
-static void atomic_pool_resize(struct gen_pool *pool, gfp_t gfp)
+static void atomic_pool_resize(struct dma_gen_pool *dma_pool, gfp_t gfp)
{
- if (pool && gen_pool_avail(pool) < atomic_pool_size)
- atomic_pool_expand(pool, gen_pool_size(pool), gfp);
+ if (dma_pool->pool && gen_pool_avail(dma_pool->pool) < atomic_pool_size)
+ atomic_pool_expand(dma_pool, gen_pool_size(dma_pool->pool), gfp);
}
static void atomic_pool_work_fn(struct work_struct *work)
{
if (IS_ENABLED(CONFIG_ZONE_DMA))
- atomic_pool_resize(atomic_pool_dma,
+ atomic_pool_resize(&atomic_pool_dma,
GFP_KERNEL | GFP_DMA);
if (IS_ENABLED(CONFIG_ZONE_DMA32))
- atomic_pool_resize(atomic_pool_dma32,
+ atomic_pool_resize(&atomic_pool_dma32,
GFP_KERNEL | GFP_DMA32);
- atomic_pool_resize(atomic_pool_kernel, GFP_KERNEL);
+ atomic_pool_resize(&atomic_pool_kernel, GFP_KERNEL);
}
-static __init struct gen_pool *__dma_atomic_pool_init(size_t pool_size,
- gfp_t gfp)
+static __init struct dma_gen_pool *__dma_atomic_pool_init(struct dma_gen_pool *dma_pool,
+ size_t pool_size, gfp_t gfp)
{
- struct gen_pool *pool;
int ret;
- pool = gen_pool_create(PAGE_SHIFT, NUMA_NO_NODE);
- if (!pool)
+ dma_pool->pool = gen_pool_create(PAGE_SHIFT, NUMA_NO_NODE);
+ if (!dma_pool->pool)
return NULL;
- gen_pool_set_algo(pool, gen_pool_first_fit_order_align, NULL);
+ gen_pool_set_algo(dma_pool->pool, gen_pool_first_fit_order_align, NULL);
+
+ /* if platform is using memory encryption atomic pools are by default shared. */
+ if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+ dma_pool->cc_shared = true;
+ else
+ dma_pool->cc_shared = false;
- ret = atomic_pool_expand(pool, pool_size, gfp);
+ ret = atomic_pool_expand(dma_pool, pool_size, gfp);
if (ret) {
- gen_pool_destroy(pool);
+ gen_pool_destroy(dma_pool->pool);
+ dma_pool->pool = NULL;
pr_err("DMA: failed to allocate %zu KiB %pGg pool for atomic allocation\n",
pool_size >> 10, &gfp);
return NULL;
}
pr_info("DMA: preallocated %zu KiB %pGg pool for atomic allocations\n",
- gen_pool_size(pool) >> 10, &gfp);
- return pool;
+ gen_pool_size(dma_pool->pool) >> 10, &gfp);
+ return dma_pool;
}
#ifdef CONFIG_ZONE_DMA32
@@ -211,21 +224,22 @@ static int __init dma_atomic_pool_init(void)
/* All memory might be in the DMA zone(s) to begin with */
if (has_managed_zone(ZONE_NORMAL)) {
- atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size,
- GFP_KERNEL);
- if (!atomic_pool_kernel)
+ __dma_atomic_pool_init(&atomic_pool_kernel, atomic_pool_size, GFP_KERNEL);
+ if (!atomic_pool_kernel.pool)
ret = -ENOMEM;
}
+
if (has_managed_dma()) {
- atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size,
- GFP_KERNEL | GFP_DMA);
- if (!atomic_pool_dma)
+ __dma_atomic_pool_init(&atomic_pool_dma, atomic_pool_size,
+ GFP_KERNEL | GFP_DMA);
+ if (!atomic_pool_dma.pool)
ret = -ENOMEM;
}
+
if (has_managed_dma32) {
- atomic_pool_dma32 = __dma_atomic_pool_init(atomic_pool_size,
- GFP_KERNEL | GFP_DMA32);
- if (!atomic_pool_dma32)
+ __dma_atomic_pool_init(&atomic_pool_dma32, atomic_pool_size,
+ GFP_KERNEL | GFP_DMA32);
+ if (!atomic_pool_dma32.pool)
ret = -ENOMEM;
}
@@ -234,19 +248,44 @@ static int __init dma_atomic_pool_init(void)
}
postcore_initcall(dma_atomic_pool_init);
-static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp)
+static inline struct dma_gen_pool *__dma_guess_pool(struct dma_gen_pool *first,
+ struct dma_gen_pool *second, struct dma_gen_pool *third)
{
- if (prev == NULL) {
+ if (first->pool)
+ return first;
+ if (second && second->pool)
+ return second;
+ if (third && third->pool)
+ return third;
+ return NULL;
+}
+
+static inline struct dma_gen_pool *dma_guess_pool(struct dma_gen_pool *prev,
+ gfp_t gfp)
+{
+ if (!prev) {
if (gfp & GFP_DMA)
- return atomic_pool_dma ?: atomic_pool_dma32 ?: atomic_pool_kernel;
+ return __dma_guess_pool(&atomic_pool_dma,
+ &atomic_pool_dma32,
+ &atomic_pool_kernel);
+
if (gfp & GFP_DMA32)
- return atomic_pool_dma32 ?: atomic_pool_dma ?: atomic_pool_kernel;
- return atomic_pool_kernel ?: atomic_pool_dma32 ?: atomic_pool_dma;
+ return __dma_guess_pool(&atomic_pool_dma32,
+ &atomic_pool_dma,
+ &atomic_pool_kernel);
+
+ return __dma_guess_pool(&atomic_pool_kernel,
+ &atomic_pool_dma32,
+ &atomic_pool_dma);
}
- if (prev == atomic_pool_kernel)
- return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma;
- if (prev == atomic_pool_dma32)
- return atomic_pool_dma;
+
+ if (prev == &atomic_pool_kernel)
+ return __dma_guess_pool(&atomic_pool_dma32,
+ &atomic_pool_dma, NULL);
+
+ if (prev == &atomic_pool_dma32)
+ return __dma_guess_pool(&atomic_pool_dma, NULL, NULL);
+
return NULL;
}
@@ -276,16 +315,20 @@ static struct page *__dma_alloc_from_pool(struct device *dev, size_t size,
}
struct page *dma_alloc_from_pool(struct device *dev, size_t size,
- void **cpu_addr, gfp_t gfp,
+ void **cpu_addr, gfp_t gfp, unsigned long attrs,
bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
{
- struct gen_pool *pool = NULL;
+ struct dma_gen_pool *dma_pool = NULL;
struct page *page;
bool pool_found = false;
- while ((pool = dma_guess_pool(pool, gfp))) {
+ while ((dma_pool = dma_guess_pool(dma_pool, gfp))) {
+
+ if (dma_pool->cc_shared != !!(attrs & __DMA_ATTR_ALLOC_CC_SHARED))
+ continue;
+
pool_found = true;
- page = __dma_alloc_from_pool(dev, size, pool, cpu_addr,
+ page = __dma_alloc_from_pool(dev, size, dma_pool->pool, cpu_addr,
phys_addr_ok);
if (page)
return page;
@@ -300,12 +343,14 @@ struct page *dma_alloc_from_pool(struct device *dev, size_t size,
bool dma_free_from_pool(struct device *dev, void *start, size_t size)
{
- struct gen_pool *pool = NULL;
+ struct dma_gen_pool *dma_pool = NULL;
+
+ while ((dma_pool = dma_guess_pool(dma_pool, 0))) {
- while ((pool = dma_guess_pool(pool, 0))) {
- if (!gen_pool_has_addr(pool, (unsigned long)start, size))
+ if (!gen_pool_has_addr(dma_pool->pool, (unsigned long)start, size))
continue;
- gen_pool_free(pool, (unsigned long)start, size);
+
+ gen_pool_free(dma_pool->pool, (unsigned long)start, size);
return true;
}
@@ -337,7 +382,7 @@ static void dma_pool_find_phys(struct gen_pool *pool, struct gen_pool_chunk *chu
match->found = true;
}
-static bool dma_free_from_pool_phys(struct gen_pool *pool, phys_addr_t phys,
+static bool dma_free_from_pool_phys(struct dma_gen_pool *dma_pool, phys_addr_t phys,
size_t size)
{
struct dma_pool_phys_match match = {
@@ -345,21 +390,21 @@ static bool dma_free_from_pool_phys(struct gen_pool *pool, phys_addr_t phys,
.size = size,
};
- gen_pool_for_each_chunk(pool, dma_pool_find_phys, &match);
+ gen_pool_for_each_chunk(dma_pool->pool, dma_pool_find_phys, &match);
if (!match.found)
return false;
- gen_pool_free(pool, match.addr, size);
+ gen_pool_free(dma_pool->pool, match.addr, size);
return true;
}
bool dma_free_from_pool_page(struct device *dev, struct page *page, size_t size)
{
- struct gen_pool *pool = NULL;
+ struct dma_gen_pool *dma_pool = NULL;
phys_addr_t phys = page_to_phys(page);
- while ((pool = dma_guess_pool(pool, 0))) {
- if (dma_free_from_pool_phys(pool, phys, size))
+ while ((dma_pool = dma_guess_pool(dma_pool, 0))) {
+ if (dma_free_from_pool_phys(dma_pool, phys, size))
return true;
}
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index d54154c165e5..908de28aceb2 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -613,9 +613,9 @@ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
u64 phys_limit, gfp_t gfp, void **vaddr)
{
struct page *page;
+ unsigned long attrs = 0;
*vaddr = NULL;
-
/*
* Allocate from the atomic pools if memory is encrypted and
* the allocation is atomic, because decrypting may block.
@@ -624,8 +624,12 @@ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
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_ALLOC_CC_SHARED;
+
return dma_alloc_from_pool(dev, bytes, vaddr, gfp,
- dma_coherent_ok);
+ attrs, dma_coherent_ok);
}
gfp &= ~GFP_ZONEMASK;
--
2.43.0
^ permalink raw reply related
* [PATCH v7 12/22] dma: swiotlb: pass mapping attributes by reference
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Change swiotlb_tbl_map_single() to take the DMA mapping attributes by
reference and update the direct callers accordingly.
This is a preparatory change for a follow-up patch which updates the
attributes based on the selected swiotlb pool. Keeping the signature change
separate makes the follow-up patch easier to review.
No functional change in this patch.
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
drivers/iommu/dma-iommu.c | 2 +-
drivers/xen/swiotlb-xen.c | 2 +-
include/linux/swiotlb.h | 2 +-
kernel/dma/swiotlb.c | 6 +++---
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index a7b1da5e06e6..fe387829ee92 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1180,7 +1180,7 @@ static phys_addr_t iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
trace_swiotlb_bounced(dev, phys, size);
phys = swiotlb_tbl_map_single(dev, phys, size, iova_mask(iovad), dir,
- attrs);
+ &attrs);
/*
* Untrusted devices should not see padding areas with random leftover
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 2cbf2b588f5b..8c4abe65cd49 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -243,7 +243,7 @@ static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys,
*/
trace_swiotlb_bounced(dev, dev_addr, size);
- map = swiotlb_tbl_map_single(dev, phys, size, 0, dir, attrs);
+ map = swiotlb_tbl_map_single(dev, phys, size, 0, dir, &attrs);
if (map == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index c92ff6791595..ea4c0a292dea 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -238,7 +238,7 @@ static inline phys_addr_t default_swiotlb_limit(void)
phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
size_t mapping_size, unsigned int alloc_aligned_mask,
- enum dma_data_direction dir, unsigned long attrs);
+ enum dma_data_direction dir, unsigned long *attrs);
dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
size_t size, enum dma_data_direction dir, unsigned long attrs);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 908de28aceb2..046ae92c4832 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1396,7 +1396,7 @@ static unsigned long mem_used(struct io_tlb_mem *mem)
*/
phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
size_t mapping_size, unsigned int alloc_align_mask,
- enum dma_data_direction dir, unsigned long attrs)
+ enum dma_data_direction dir, unsigned long *attrs)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
unsigned int offset;
@@ -1430,7 +1430,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
size = ALIGN(mapping_size + offset, alloc_align_mask + 1);
index = swiotlb_find_slots(dev, orig_addr, size, alloc_align_mask, &pool);
if (index == -1) {
- if (!(attrs & DMA_ATTR_NO_WARN))
+ if (!(*attrs & DMA_ATTR_NO_WARN))
dev_warn_ratelimited(dev,
"swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
size, mem->nslabs, mem_used(mem));
@@ -1609,7 +1609,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size);
- swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, 0, dir, attrs);
+ swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, 0, dir, &attrs);
if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
--
2.43.0
^ permalink raw reply related
* [PATCH v7 13/22] dma: swiotlb: track pool encryption state and honor DMA_ATTR_CC_SHARED
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
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 cc_shared flag to io_tlb_mem, initialize it for the default and
restricted pools, and propagate __DMA_ATTR_ALLOC_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.
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
include/linux/dma-direct.h | 10 +++
include/linux/swiotlb.h | 10 ++-
kernel/dma/direct.c | 13 ++-
kernel/dma/swiotlb.c | 177 ++++++++++++++++++++++++++++---------
4 files changed, 162 insertions(+), 48 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 ea4c0a292dea..ee42f7588847 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -66,6 +66,7 @@ extern void __init swiotlb_update_mem_attributes(void);
* @node: Member of the IO TLB memory pool list.
* @rcu: RCU head for swiotlb_dyn_free().
* @transient: %true if transient memory pool.
+ * @cc_shared: %true if the pool memory is shared for confidential computing.
*/
struct io_tlb_pool {
phys_addr_t start;
@@ -81,6 +82,7 @@ struct io_tlb_pool {
struct list_head node;
struct rcu_head rcu;
bool transient;
+ bool cc_shared;
#endif
};
@@ -92,6 +94,7 @@ struct io_tlb_pool {
* @debugfs: The dentry to debugfs.
* @force_bounce: %true if swiotlb bouncing is forced
* @for_alloc: %true if the pool is used for memory allocation
+ * @cc_shared: %true if the pool memory is shared for confidential computing.
* @can_grow: %true if more pools can be allocated dynamically.
* @phys_limit: Maximum allowed physical address.
* @lock: Lock to synchronize changes to the list.
@@ -111,6 +114,7 @@ struct io_tlb_mem {
struct dentry *debugfs;
bool force_bounce;
bool for_alloc;
+ bool cc_shared;
#ifdef CONFIG_SWIOTLB_DYNAMIC
bool can_grow;
u64 phys_limit;
@@ -282,7 +286,8 @@ 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);
void swiotlb_free_from_pool(struct device *dev,
phys_addr_t tlb_addr, struct io_tlb_pool *pool);
@@ -292,7 +297,8 @@ 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 c50d6987438e..64cb9f13ef03 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -96,9 +96,10 @@ static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
return ret;
}
-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);
@@ -251,8 +252,12 @@ void *dma_direct_alloc(struct device *dev, size_t size,
}
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;
}
@@ -398,7 +403,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
&ret, 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 046ae92c4832..335e27bc1e1f 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
+ * shared by default.
+ */
+ if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+ io_tlb_default_mem.cc_shared = true;
+ else
+ io_tlb_default_mem.cc_shared = 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.cc_shared)
+ 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.cc_shared)
+ set_memory_decrypted((unsigned long)vstart,
+ (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
+
swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), 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.cc_shared)
+ 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.
+ * @attrs: DMA attributes for the allocation.
*
* Allocate pages from the buddy allocator. If successful, make the allocated
* pages decrypted that they can be used for DMA.
@@ -570,9 +586,11 @@ 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, unsigned long attrs)
{
unsigned int order = get_order(bytes);
+ bool cc_shared = attrs & __DMA_ATTR_ALLOC_CC_SHARED;
struct page *page;
phys_addr_t paddr;
void *vaddr;
@@ -588,13 +606,13 @@ 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 (cc_shared && 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 (cc_shared && !set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
__free_pages(page, order);
return NULL;
}
@@ -602,6 +620,7 @@ static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit)
/**
* swiotlb_alloc_tlb() - allocate a dynamic IO TLB buffer
* @dev: Device for which a memory pool is allocated.
+ * @mem: SWIOTLB allocator for the pool.
* @bytes: Size of the buffer.
* @phys_limit: Maximum allowed physical address of the buffer.
* @gfp: GFP flags for the allocation.
@@ -609,25 +628,23 @@ static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit)
*
* Return: Allocated pages, or %NULL on allocation failure.
*/
-static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
+static struct page *swiotlb_alloc_tlb(struct device *dev,
+ struct io_tlb_mem *mem, size_t bytes,
u64 phys_limit, gfp_t gfp, void **vaddr)
{
struct page *page;
- unsigned long attrs = 0;
+ unsigned long attrs = mem->cc_shared ? __DMA_ATTR_ALLOC_CC_SHARED : 0;
*vaddr = NULL;
/*
* 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) && dev && mem->cc_shared) {
+
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_ALLOC_CC_SHARED;
-
return dma_alloc_from_pool(dev, bytes, vaddr, gfp,
attrs, dma_coherent_ok);
}
@@ -638,7 +655,7 @@ 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))) {
if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
phys_limit < DMA_BIT_MASK(64) &&
!(gfp & (__GFP_DMA32 | __GFP_DMA)))
@@ -659,21 +676,25 @@ 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.
+ * @cc_shared: 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 cc_shared)
{
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 (!cc_shared ||
+ !set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
__free_pages(virt_to_page(vaddr), get_order(bytes));
}
/**
* swiotlb_alloc_pool() - allocate a new IO TLB memory pool
* @dev: Device for which a memory pool is allocated.
+ * @mem: SWIOTLB allocator for the pool.
* @minslabs: Minimum number of slabs.
* @nslabs: Desired (maximum) number of slabs.
* @nareas: Number of areas.
@@ -687,8 +708,9 @@ static void swiotlb_free_tlb(void *vaddr, size_t bytes)
* Return: New memory pool, or %NULL on allocation failure.
*/
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)
+ struct io_tlb_mem *mem, unsigned long minslabs,
+ unsigned long nslabs, unsigned int nareas, u64 phys_limit,
+ gfp_t gfp)
{
struct io_tlb_pool *pool;
unsigned int slot_order;
@@ -707,10 +729,11 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
if (!pool)
goto error;
pool->areas = (void *)pool + sizeof(*pool);
+ pool->cc_shared = mem->cc_shared;
tlb_size = nslabs << IO_TLB_SHIFT;
- while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, gfp,
- &tlb_vaddr))) {
+ while (!(tlb = swiotlb_alloc_tlb(dev, mem, tlb_size,
+ phys_limit, gfp, &tlb_vaddr))) {
if (nslabs <= minslabs)
goto error_tlb;
nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
@@ -729,7 +752,7 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
return pool;
error_slots:
- swiotlb_free_tlb(tlb_vaddr, tlb_size);
+ swiotlb_free_tlb(tlb_vaddr, tlb_size, mem->cc_shared);
error_tlb:
kfree(pool);
error:
@@ -746,7 +769,7 @@ static void swiotlb_dyn_alloc(struct work_struct *work)
container_of(work, struct io_tlb_mem, dyn_alloc);
struct io_tlb_pool *pool;
- pool = swiotlb_alloc_pool(NULL, IO_TLB_MIN_SLABS, default_nslabs,
+ pool = swiotlb_alloc_pool(NULL, mem, IO_TLB_MIN_SLABS, default_nslabs,
default_nareas, mem->phys_limit, GFP_KERNEL);
if (!pool) {
pr_warn_ratelimited("Failed to allocate new pool");
@@ -767,7 +790,7 @@ 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->cc_shared);
kfree(pool);
}
@@ -1031,6 +1054,7 @@ static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots)
* @pool: Memory pool to be searched.
* @area_index: Index of the IO TLB memory area to be searched.
* @orig_addr: Original (non-bounced) IO buffer address.
+ * @tbl_dma_addr: DMA address of the bounce buffer.
* @alloc_size: Total requested size of the bounce buffer,
* including initial alignment padding.
* @alloc_align_mask: Required alignment of the allocated buffer.
@@ -1042,13 +1066,11 @@ static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots)
* Return: Index of the first allocated slot, or -1 on error.
*/
static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool,
- int area_index, phys_addr_t orig_addr, size_t alloc_size,
- unsigned int alloc_align_mask)
+ int area_index, phys_addr_t orig_addr, dma_addr_t tbl_dma_addr,
+ size_t alloc_size, unsigned int alloc_align_mask)
{
struct io_tlb_area *area = pool->areas + area_index;
unsigned long boundary_mask = dma_get_seg_boundary(dev);
- dma_addr_t tbl_dma_addr =
- phys_to_dma_unencrypted(dev, pool->start) & boundary_mask;
unsigned long max_slots = get_max_slots(boundary_mask);
unsigned int iotlb_align_mask = dma_get_min_align_mask(dev);
unsigned int nslots = nr_slots(alloc_size), stride;
@@ -1061,6 +1083,8 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
BUG_ON(!nslots);
BUG_ON(area_index >= pool->nareas);
+ tbl_dma_addr &= boundary_mask;
+
/*
* Historically, swiotlb allocations >= PAGE_SIZE were guaranteed to be
* page-aligned in the absence of any other alignment requirements.
@@ -1172,6 +1196,7 @@ static int swiotlb_search_area(struct device *dev, int start_cpu,
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
struct io_tlb_pool *pool;
+ dma_addr_t tbl_dma_addr;
int area_index;
int index = -1;
@@ -1180,9 +1205,15 @@ static int swiotlb_search_area(struct device *dev, int start_cpu,
if (cpu_offset >= pool->nareas)
continue;
area_index = (start_cpu + cpu_offset) & (pool->nareas - 1);
+
+ if (mem->cc_shared)
+ tbl_dma_addr = phys_to_dma_unencrypted(dev, pool->start);
+ else
+ tbl_dma_addr = phys_to_dma_encrypted(dev, pool->start);
+
index = swiotlb_search_pool_area(dev, pool, area_index,
- orig_addr, alloc_size,
- alloc_align_mask);
+ orig_addr, tbl_dma_addr,
+ alloc_size, alloc_align_mask);
if (index >= 0) {
*retpool = pool;
break;
@@ -1212,6 +1243,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
struct io_tlb_pool *pool;
+ dma_addr_t tbl_dma_addr;
unsigned long nslabs;
unsigned long flags;
u64 phys_limit;
@@ -1236,12 +1268,17 @@ 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,
+ pool = swiotlb_alloc_pool(dev, mem, nslabs, nslabs, 1, phys_limit,
GFP_NOWAIT);
if (!pool)
return -1;
- index = swiotlb_search_pool_area(dev, pool, 0, orig_addr,
+ if (mem->cc_shared)
+ tbl_dma_addr = phys_to_dma_unencrypted(dev, pool->start);
+ else
+ tbl_dma_addr = phys_to_dma_encrypted(dev, pool->start);
+
+ index = swiotlb_search_pool_area(dev, pool, 0, orig_addr, tbl_dma_addr,
alloc_size, alloc_align_mask);
if (index < 0) {
swiotlb_dyn_free(&pool->rcu);
@@ -1286,15 +1323,23 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
size_t alloc_size, unsigned int alloc_align_mask,
struct io_tlb_pool **retpool)
{
+ struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
struct io_tlb_pool *pool;
+ dma_addr_t tbl_dma_addr;
int start, i;
int index;
- *retpool = pool = &dev->dma_io_tlb_mem->defpool;
+ *retpool = pool = &mem->defpool;
+ if (mem->cc_shared)
+ tbl_dma_addr = phys_to_dma_unencrypted(dev, pool->start);
+ else
+ tbl_dma_addr = phys_to_dma_encrypted(dev, pool->start);
+
i = start = raw_smp_processor_id() & (pool->nareas - 1);
do {
index = swiotlb_search_pool_area(dev, pool, i, orig_addr,
- alloc_size, alloc_align_mask);
+ tbl_dma_addr, alloc_size,
+ alloc_align_mask);
if (index >= 0)
return index;
if (++i >= pool->nareas)
@@ -1377,9 +1422,19 @@ static unsigned long mem_used(struct io_tlb_mem *mem)
* any pre- or post-padding for alignment
* @alloc_align_mask: Required start and end alignment of the allocated buffer
* @dir: DMA direction
- * @attrs: Optional DMA attributes for the map operation
+ * @attrs: Optional DMA attributes for the map operation, updated
+ * to match the selected SWIOTLB pool
*
* Find and allocate a suitable sequence of IO TLB slots for the request.
+ * The device's SWIOTLB pool must match the device's current DMA encryption
+ * requirements. If the device requires decrypted DMA, bouncing is done through
+ * an unencrypted pool and the mapping is marked shared. If the device can DMA
+ * to encrypted memory, bouncing is done through an encrypted pool even when the
+ * original DMA address was unencrypted. Enabling encrypted DMA for a device is
+ * therefore expected to update its default io_tlb_mem to an encrypted pool, so
+ * later bounce mappings for both encrypted and decrypted original memory use
+ * that encrypted pool.
+ *
* The allocated space starts at an alignment specified by alloc_align_mask,
* and the size of the allocated space is rounded up so that the total amount
* of allocated space is a multiple of (alloc_align_mask + 1). If
@@ -1416,6 +1471,30 @@ 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 (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
+
+ /* swiotlb pool is incorrect for this device */
+ if (unlikely(mem->cc_shared != force_dma_unencrypted(dev)))
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+
+ } else if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
+ /*
+ * On hosts with memory encryption, SWIOTLB-backed memory is
+ * unencrypted. DMA addresses returned for bounce buffers must
+ * therefore be marked unencrypted, even for devices that can
+ * address encrypted memory. This also preserves swiotlb=force
+ * behavior for those devices.
+ */
+ if (unlikely(!mem->cc_shared))
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
+
+ /* Force attrs to match the kind of memory in the pool */
+ if (mem->cc_shared)
+ *attrs |= DMA_ATTR_CC_SHARED;
+ else
+ *attrs &= ~DMA_ATTR_CC_SHARED;
+
/*
* The default swiotlb memory pool is allocated with PAGE_SIZE
* alignment. If a mapping is requested with larger alignment,
@@ -1613,8 +1692,11 @@ 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);
+ if (attrs & DMA_ATTR_CC_SHARED)
+ 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,
@@ -1778,7 +1860,7 @@ 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;
@@ -1789,6 +1871,9 @@ struct page *swiotlb_alloc(struct device *dev, size_t size)
if (!mem)
return NULL;
+ if (mem->cc_shared != !!(attrs & __DMA_ATTR_ALLOC_CC_SHARED))
+ return NULL;
+
align = (1 << (get_order(size) + PAGE_SHIFT)) - 1;
index = swiotlb_find_slots(dev, 0, size, align, &pool);
if (index == -1)
@@ -1864,12 +1949,20 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
kfree(mem);
return -ENOMEM;
}
+ /*
+ * if platform supports memory encryption,
+ * restricted mem pool is shared by default
+ */
+ if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+ mem->cc_shared = true;
+ set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
+ rmem->size >> PAGE_SHIFT);
+ } else {
+ mem->cc_shared = false;
+ }
- set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
- rmem->size >> PAGE_SHIFT);
swiotlb_init_io_tlb_pool(pool, rmem->base, phys_to_virt(rmem->base),
- nslabs,
- false, nareas);
+ nslabs, false, nareas);
mem->force_bounce = true;
mem->for_alloc = true;
#ifdef CONFIG_SWIOTLB_DYNAMIC
--
2.43.0
^ permalink raw reply related
* [PATCH v7 14/22] dma-mapping: make dma_pgprot() honor __DMA_ATTR_ALLOC_CC_SHARED
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Fold encrypted/decrypted pgprot selection into dma_pgprot() so callers
do not need to adjust the page protection separately.
Update dma_pgprot() to apply pgprot_decrypted() when DMA_ATTR_CC_SHARED or
__DMA_ATTR_ALLOC_CC_SHARED is set and pgprot_encrypted() otherwise Convert
the dma-direct mmap paths to pass DMA_ATTR_CC_SHARED instead of open-coding
force_dma_unencrypted() handling around dma_pgprot().
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
kernel/dma/direct.c | 8 +++-----
kernel/dma/mapping.c | 16 ++++++++++++----
2 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 64cb9f13ef03..9935f7caa459 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -283,9 +283,6 @@ void *dma_direct_alloc(struct device *dev, size_t size,
if (remap) {
pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
- if (force_dma_unencrypted(dev))
- prot = pgprot_decrypted(prot);
-
/* remove any dirty cache lines on the kernel alias */
arch_dma_prep_coherent(page, size);
@@ -605,9 +602,10 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr));
int ret = -ENXIO;
- vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
if (force_dma_unencrypted(dev))
- vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+ attrs |= DMA_ATTR_CC_SHARED;
+
+ vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index d2f70b6ccd0f..a628820fd10e 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -537,13 +537,21 @@ EXPORT_SYMBOL(dma_get_sgtable_attrs);
*/
pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
{
+ pgprot_t dma_prot;
+
if (dev_is_dma_coherent(dev))
- return prot;
+ dma_prot = prot;
#ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE
- if (attrs & DMA_ATTR_WRITE_COMBINE)
- return pgprot_writecombine(prot);
+ else if (attrs & DMA_ATTR_WRITE_COMBINE)
+ dma_prot = pgprot_writecombine(prot);
#endif
- return pgprot_dmacoherent(prot);
+ else
+ dma_prot = pgprot_dmacoherent(prot);
+
+ if (attrs & (DMA_ATTR_CC_SHARED | __DMA_ATTR_ALLOC_CC_SHARED))
+ return pgprot_decrypted(dma_prot);
+ else
+ return pgprot_encrypted(dma_prot);
}
#endif /* CONFIG_MMU */
--
2.43.0
^ permalink raw reply related
* [PATCH v7 15/22] dma-direct: pass attrs to dma_capable() for DMA_ATTR_CC_SHARED checks
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Teach dma_capable() about DMA_ATTR_CC_SHARED so the capability
check can reject encrypted DMA addresses for devices that require
unencrypted/shared DMA.
Also propagate DMA_ATTR_CC_SHARED in swiotlb_map() when the selected
SWIOTLB pool is decrypted so the capability check sees the correct DMA
address attribute.
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
arch/x86/kernel/amd_gart_64.c | 30 ++++++++++++++++--------------
drivers/xen/swiotlb-xen.c | 6 +++---
include/linux/dma-direct.h | 10 +++++++++-
kernel/dma/direct.h | 6 +++---
kernel/dma/swiotlb.c | 2 +-
5 files changed, 32 insertions(+), 22 deletions(-)
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index e8000a56732e..b5f1f031d45b 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -180,22 +180,23 @@ static void iommu_full(struct device *dev, size_t size, int dir)
}
static inline int
-need_iommu(struct device *dev, unsigned long addr, size_t size)
+need_iommu(struct device *dev, unsigned long addr, size_t size, unsigned long attrs)
{
- return force_iommu || !dma_capable(dev, addr, size, true);
+ return force_iommu || !dma_capable(dev, addr, size, true, attrs);
}
static inline int
-nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
+nonforced_iommu(struct device *dev, unsigned long addr, size_t size,
+ unsigned long attrs)
{
- return !dma_capable(dev, addr, size, true);
+ return !dma_capable(dev, addr, size, true, attrs);
}
/* Map a single continuous physical area into the IOMMU.
* Caller needs to check if the iommu is needed and flush.
*/
static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
- size_t size, int dir, unsigned long align_mask)
+ size_t size, int dir, unsigned long align_mask, unsigned long attrs)
{
unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
unsigned long iommu_page;
@@ -206,7 +207,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
iommu_page = alloc_iommu(dev, npages, align_mask);
if (iommu_page == -1) {
- if (!nonforced_iommu(dev, phys_mem, size))
+ if (!nonforced_iommu(dev, phys_mem, size, attrs))
return phys_mem;
if (panic_on_overflow)
panic("dma_map_area overflow %lu bytes\n", size);
@@ -231,10 +232,10 @@ static dma_addr_t gart_map_phys(struct device *dev, phys_addr_t paddr,
if (unlikely(attrs & DMA_ATTR_MMIO))
return DMA_MAPPING_ERROR;
- if (!need_iommu(dev, paddr, size))
+ if (!need_iommu(dev, paddr, size, attrs))
return paddr;
- bus = dma_map_area(dev, paddr, size, dir, 0);
+ bus = dma_map_area(dev, paddr, size, dir, 0, attrs);
flush_gart();
return bus;
@@ -289,7 +290,7 @@ static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
/* Fallback for dma_map_sg in case of overflow */
static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
- int nents, int dir)
+ int nents, int dir, unsigned long attrs)
{
struct scatterlist *s;
int i;
@@ -301,8 +302,8 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
for_each_sg(sg, s, nents, i) {
unsigned long addr = sg_phys(s);
- if (nonforced_iommu(dev, addr, s->length)) {
- addr = dma_map_area(dev, addr, s->length, dir, 0);
+ if (nonforced_iommu(dev, addr, s->length, attrs)) {
+ addr = dma_map_area(dev, addr, s->length, dir, 0, attrs);
if (addr == DMA_MAPPING_ERROR) {
if (i > 0)
gart_unmap_sg(dev, sg, i, dir, 0);
@@ -401,7 +402,7 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
s->dma_address = addr;
BUG_ON(s->length == 0);
- nextneed = need_iommu(dev, addr, s->length);
+ nextneed = need_iommu(dev, addr, s->length, attrs);
/* Handle the previous not yet processed entries */
if (i > start) {
@@ -449,7 +450,7 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
/* When it was forced or merged try again in a dumb way */
if (force_iommu || iommu_merge) {
- out = dma_map_sg_nonforce(dev, sg, nents, dir);
+ out = dma_map_sg_nonforce(dev, sg, nents, dir, attrs);
if (out > 0)
return out;
}
@@ -473,7 +474,8 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
return vaddr;
*dma_addr = dma_map_area(dev, virt_to_phys(vaddr), size,
- DMA_BIDIRECTIONAL, (1UL << get_order(size)) - 1);
+ DMA_BIDIRECTIONAL,
+ (1UL << get_order(size)) - 1, attrs);
flush_gart();
if (unlikely(*dma_addr == DMA_MAPPING_ERROR))
goto out_free;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 8c4abe65cd49..e2538824ef52 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -212,7 +212,7 @@ static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys,
BUG_ON(dir == DMA_NONE);
if (attrs & DMA_ATTR_MMIO) {
- if (unlikely(!dma_capable(dev, phys, size, false))) {
+ if (unlikely(!dma_capable(dev, phys, size, false, attrs))) {
dev_err_once(
dev,
"DMA addr %pa+%zu overflow (mask %llx, bus limit %llx).\n",
@@ -231,7 +231,7 @@ static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
- if (dma_capable(dev, dev_addr, size, true) &&
+ if (dma_capable(dev, dev_addr, size, true, attrs) &&
!dma_kmalloc_needs_bounce(dev, size, dir) &&
!range_straddles_page_boundary(phys, size) &&
!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
@@ -253,7 +253,7 @@ static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys,
/*
* Ensure that the address returned is DMA'ble
*/
- if (unlikely(!dma_capable(dev, dev_addr, size, true))) {
+ if (unlikely(!dma_capable(dev, dev_addr, size, true, attrs))) {
__swiotlb_tbl_unmap_single(dev, map, size, dir,
attrs | DMA_ATTR_SKIP_CPU_SYNC,
swiotlb_find_pool(dev, map));
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 94fad4e7c11e..daa31a1adf7b 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -135,12 +135,20 @@ static inline bool force_dma_unencrypted(struct device *dev)
#endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */
static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
- bool is_ram)
+ bool is_ram, unsigned long attrs)
{
dma_addr_t end = addr + size - 1;
if (addr == DMA_MAPPING_ERROR)
return false;
+ /*
+ * The DMA address was derived from encrypted RAM, but this device
+ * requires unencrypted DMA addresses. Treat it as not DMA-capable
+ * so the caller can fall back to a suitable SWIOTLB pool.
+ */
+ if (!(attrs & DMA_ATTR_CC_SHARED) && force_dma_unencrypted(dev))
+ return false;
+
if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
return false;
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index 7140c208c123..e05dc7649366 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -101,15 +101,15 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
if (attrs & DMA_ATTR_MMIO) {
dma_addr = phys;
- if (unlikely(!dma_capable(dev, dma_addr, size, false)))
+ if (unlikely(!dma_capable(dev, dma_addr, size, false, attrs)))
goto err_overflow;
} else if (attrs & DMA_ATTR_CC_SHARED) {
dma_addr = phys_to_dma_unencrypted(dev, phys);
- if (unlikely(!dma_capable(dev, dma_addr, size, false)))
+ if (unlikely(!dma_capable(dev, dma_addr, size, false, attrs)))
goto err_overflow;
} else {
dma_addr = phys_to_dma(dev, phys);
- if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
+ if (unlikely(!dma_capable(dev, dma_addr, size, true, attrs)) ||
dma_kmalloc_needs_bounce(dev, size, dir)) {
if (is_swiotlb_active(dev) &&
!(attrs & DMA_ATTR_REQUIRE_COHERENT))
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 335e27bc1e1f..b5960c2e98d8 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1697,7 +1697,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
else
dma_addr = phys_to_dma_encrypted(dev, swiotlb_addr);
- if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+ if (unlikely(!dma_capable(dev, dma_addr, size, true, attrs))) {
__swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir,
attrs | DMA_ATTR_SKIP_CPU_SYNC,
swiotlb_find_pool(dev, swiotlb_addr));
--
2.43.0
^ permalink raw reply related
* [PATCH v7 16/22] dma-direct: make dma_direct_map_phys() honor DMA_ATTR_CC_SHARED
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Teach dma_direct_map_phys() to select the DMA address encoding based on
DMA_ATTR_CC_SHARED.
Use phys_to_dma_unencrypted() for decrypted mappings and
phys_to_dma_encrypted() otherwise. If a device requires unencrypted DMA
but the source physical address is still encrypted, force the mapping
through swiotlb so the DMA address and backing memory attributes remain
consistent.
Update the arm64, x86, s390 and powerpc secure-guest setup to not use
swiotlb force option
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
Changes from v3:
* Handle DMA_ATTR_MMIO
---
arch/arm64/mm/init.c | 4 +--
arch/powerpc/platforms/pseries/svm.c | 2 +-
arch/s390/mm/init.c | 2 +-
arch/x86/kernel/pci-dma.c | 4 +--
kernel/dma/direct.c | 4 ++-
kernel/dma/direct.h | 45 +++++++++++++++-------------
6 files changed, 31 insertions(+), 30 deletions(-)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 97987f850a33..acf67c7064db 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -338,10 +338,8 @@ void __init arch_mm_preinit(void)
unsigned int flags = SWIOTLB_VERBOSE;
bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
- if (is_realm_world()) {
+ if (is_realm_world())
swiotlb = true;
- flags |= SWIOTLB_FORCE;
- }
if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) {
/*
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 384c9dc1899a..7a403dbd35ee 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -29,7 +29,7 @@ static int __init init_svm(void)
* need to use the SWIOTLB buffer for DMA even if dma_capable() says
* otherwise.
*/
- ppc_swiotlb_flags |= SWIOTLB_ANY | SWIOTLB_FORCE;
+ ppc_swiotlb_flags |= SWIOTLB_ANY;
/* Share the SWIOTLB buffer with the host. */
swiotlb_update_mem_attributes();
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 6b1c5a4fa9ce..8d1de5a2e554 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -166,7 +166,7 @@ static void __init pv_init(void)
virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
/* make sure bounce buffers are shared */
- swiotlb_init(true, SWIOTLB_FORCE | SWIOTLB_VERBOSE);
+ swiotlb_init(true, SWIOTLB_VERBOSE);
swiotlb_update_mem_attributes();
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 6267363e0189..75cf8f6ae8cd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -59,10 +59,8 @@ static void __init pci_swiotlb_detect(void)
* bounce buffers as the hypervisor can't access arbitrary VM memory
* that is not explicitly shared with it.
*/
- if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
+ if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
x86_swiotlb_enable = true;
- x86_swiotlb_flags |= SWIOTLB_FORCE;
- }
}
#else
static inline void __init pci_swiotlb_detect(void)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 9935f7caa459..edf40746a775 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -693,8 +693,10 @@ size_t dma_direct_max_mapping_size(struct device *dev)
{
/* If SWIOTLB is active, use its maximum mapping size */
if (is_swiotlb_active(dev) &&
- (dma_addressing_limited(dev) || is_swiotlb_force_bounce(dev)))
+ (dma_addressing_limited(dev) || is_swiotlb_force_bounce(dev) ||
+ force_dma_unencrypted(dev)))
return swiotlb_max_mapping_size(dev);
+
return SIZE_MAX;
}
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index e05dc7649366..f3fc28f352ba 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -88,37 +88,40 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
{
dma_addr_t dma_addr;
+ /*
+ * For a device requiring unencrypted DMA, MMIO memory is treated
+ * as shared by default.
+ */
+ if (force_dma_unencrypted(dev) && (attrs & DMA_ATTR_MMIO))
+ attrs |= DMA_ATTR_CC_SHARED;
+
if (is_swiotlb_force_bounce(dev)) {
- if (!(attrs & DMA_ATTR_CC_SHARED)) {
- if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
- return DMA_MAPPING_ERROR;
+ if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
+ return DMA_MAPPING_ERROR;
- return swiotlb_map(dev, phys, size, dir, attrs);
- }
- } else if (attrs & DMA_ATTR_CC_SHARED) {
- return DMA_MAPPING_ERROR;
+ return swiotlb_map(dev, phys, size, dir, attrs);
}
- if (attrs & DMA_ATTR_MMIO) {
- dma_addr = phys;
- if (unlikely(!dma_capable(dev, dma_addr, size, false, attrs)))
- goto err_overflow;
- } else if (attrs & DMA_ATTR_CC_SHARED) {
+ if (attrs & DMA_ATTR_CC_SHARED)
dma_addr = phys_to_dma_unencrypted(dev, phys);
+ else
+ dma_addr = phys_to_dma_encrypted(dev, phys);
+
+ if (attrs & DMA_ATTR_MMIO) {
if (unlikely(!dma_capable(dev, dma_addr, size, false, attrs)))
goto err_overflow;
- } else {
- dma_addr = phys_to_dma(dev, phys);
- if (unlikely(!dma_capable(dev, dma_addr, size, true, attrs)) ||
- dma_kmalloc_needs_bounce(dev, size, dir)) {
- if (is_swiotlb_active(dev) &&
- !(attrs & DMA_ATTR_REQUIRE_COHERENT))
- return swiotlb_map(dev, phys, size, dir, attrs);
+ goto dma_mapped;
+ }
- goto err_overflow;
- }
+ if (unlikely(!dma_capable(dev, dma_addr, size, true, attrs)) ||
+ dma_kmalloc_needs_bounce(dev, size, dir)) {
+ if (is_swiotlb_active(dev) &&
+ !(attrs & DMA_ATTR_REQUIRE_COHERENT))
+ return swiotlb_map(dev, phys, size, dir, attrs);
+ goto err_overflow;
}
+dma_mapped:
if (!dev_is_dma_coherent(dev) &&
!(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) {
arch_sync_dma_for_device(phys, size, dir);
--
2.43.0
^ permalink raw reply related
* [PATCH v7 17/22] dma-direct: set decrypted flag for remapped DMA allocations
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Devices that are DMA non-coherent and require a remap were skipping
dma_set_decrypted(), leaving DMA buffers encrypted even when the device
requires unencrypted access. Move the call after the if (remap) branch
so that both the direct and remapped allocation paths correctly mark the
allocation as decrypted (or fail cleanly) before use.
Fix dma_direct_alloc() and dma_direct_free() to apply set_memory_*() to the
linear-map alias of the backing pages instead of the remapped CPU address.
Also disallow highmem pages for __DMA_ATTR_ALLOC_CC_SHARED, because highmem
buffers do not provide a usable linear-map address.
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
kernel/dma/direct.c | 56 +++++++++++++++++++++++++++++++++++----------
1 file changed, 44 insertions(+), 12 deletions(-)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index edf40746a775..964e8b0d8709 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -196,14 +196,23 @@ void *dma_direct_alloc(struct device *dev, size_t size,
{
bool remap = false, set_uncached = false;
bool mark_mem_decrypt = false;
+ bool allow_highmem = true;
struct page *page;
void *ret;
if (force_dma_unencrypted(dev))
attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
- if (attrs & __DMA_ATTR_ALLOC_CC_SHARED)
+ if (attrs & __DMA_ATTR_ALLOC_CC_SHARED) {
+ /*
+ * Unencrypted/shared DMA requires a linear-mapped buffer
+ * address to look up the PFN and set architecture-required PFN
+ * attributes. This is not possible with HighMem. Avoid HighMem
+ * allocation.
+ */
+ allow_highmem = false;
mark_mem_decrypt = true;
+ }
size = PAGE_ALIGN(size);
if (attrs & DMA_ATTR_NO_WARN)
@@ -265,7 +274,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
}
/* we always manually zero the memory once we are done */
- page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true);
+ page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, allow_highmem);
if (!page)
return NULL;
@@ -280,6 +289,14 @@ void *dma_direct_alloc(struct device *dev, size_t size,
set_uncached = false;
}
+ if (mark_mem_decrypt) {
+ void *lm_addr;
+
+ lm_addr = page_address(page);
+ if (set_memory_decrypted((unsigned long)lm_addr, PFN_UP(size)))
+ goto out_leak_pages;
+ }
+
if (remap) {
pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
@@ -290,29 +307,36 @@ void *dma_direct_alloc(struct device *dev, size_t size,
ret = dma_common_contiguous_remap(page, size, prot,
__builtin_return_address(0));
if (!ret)
- goto out_free_pages;
+ goto out_encrypt_pages;
} else {
ret = page_address(page);
- if (mark_mem_decrypt && dma_set_decrypted(dev, ret, size))
- goto out_leak_pages;
}
memset(ret, 0, size);
if (set_uncached) {
+ void *uncached_cpu_addr;
+
arch_dma_prep_coherent(page, size);
- ret = arch_dma_set_uncached(ret, size);
- if (IS_ERR(ret))
- goto out_encrypt_pages;
+ uncached_cpu_addr = arch_dma_set_uncached(ret, size);
+ if (IS_ERR(uncached_cpu_addr))
+ goto out_free_remap_pages;
+ ret = uncached_cpu_addr;
}
*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
return ret;
+
+out_free_remap_pages:
+ if (remap)
+ dma_common_free_remap(ret, size);
+
out_encrypt_pages:
- if (mark_mem_decrypt && dma_set_encrypted(dev, page_address(page), size))
- return NULL;
-out_free_pages:
+ if (mark_mem_decrypt &&
+ dma_set_encrypted(dev, page_address(page), size))
+ goto out_leak_pages;
+
if (!swiotlb_free(dev, page, size))
dma_free_contiguous(dev, page, size);
return NULL;
@@ -375,8 +399,16 @@ 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);
- if (mark_mem_encrypted && dma_set_encrypted(dev, cpu_addr, size))
+ }
+
+ if (mark_mem_encrypted) {
+ void *lm_addr;
+
+ lm_addr = phys_to_virt(phys);
+ if (set_memory_encrypted((unsigned long)lm_addr, PFN_UP(size))) {
+ pr_warn_ratelimited("leaking DMA memory that can't be re-encrypted\n");
return;
+ }
}
if (swiotlb_pool)
--
2.43.0
^ permalink raw reply related
* [PATCH v7 18/22] dma-direct: select DMA address encoding from __DMA_ATTR_ALLOC_CC_SHARED
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Jiri Pirko,
Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Make the dma-direct helpers derive the DMA address encoding from
__DMA_ATTR_ALLOC_CC_SHARED instead of implicitly relying on
force_dma_unencrypted() inside phys_to_dma_direct()
Pass an explicit unencrypted/decrypted state into phys_to_dma_direct(),
make the alloc paths return DMA addresses that match the requested buffer
encryption state. Also only call dma_set_decrypted() when
__DMA_ATTR_ALLOC_CC_SHARED is actually set.
Tested-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
kernel/dma/direct.c | 43 ++++++++++++++++++++++++++-----------------
1 file changed, 26 insertions(+), 17 deletions(-)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 964e8b0d8709..23138519cf22 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -24,11 +24,11 @@
u64 zone_dma_limit __ro_after_init = DMA_BIT_MASK(24);
static inline dma_addr_t phys_to_dma_direct(struct device *dev,
- phys_addr_t phys)
+ phys_addr_t phys, bool unencrypted)
{
- if (force_dma_unencrypted(dev))
+ if (unencrypted)
return phys_to_dma_unencrypted(dev, phys);
- return phys_to_dma(dev, phys);
+ return phys_to_dma_encrypted(dev, phys);
}
static inline struct page *dma_direct_to_page(struct device *dev,
@@ -39,8 +39,9 @@ static inline struct page *dma_direct_to_page(struct device *dev,
u64 dma_direct_get_required_mask(struct device *dev)
{
+ bool require_decrypted = force_dma_unencrypted(dev);
phys_addr_t phys = ((phys_addr_t)max_pfn << PAGE_SHIFT) - 1;
- u64 max_dma = phys_to_dma_direct(dev, phys);
+ u64 max_dma = phys_to_dma_direct(dev, phys, require_decrypted);
return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
}
@@ -69,7 +70,8 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 *phys_limit)
bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
{
- dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
+ bool require_decrypted = force_dma_unencrypted(dev);
+ dma_addr_t dma_addr = phys_to_dma_direct(dev, phys, require_decrypted);
if (dma_addr == DMA_MAPPING_ERROR)
return false;
@@ -79,17 +81,18 @@ bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
static int dma_set_decrypted(struct device *dev, void *vaddr, size_t size)
{
- if (!force_dma_unencrypted(dev))
- return 0;
- return set_memory_decrypted((unsigned long)vaddr, PFN_UP(size));
+ int ret;
+
+ ret = set_memory_decrypted((unsigned long)vaddr, PFN_UP(size));
+ if (ret)
+ pr_warn_ratelimited("leaking DMA memory that can't be decrypted\n");
+ return ret;
}
static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
{
int ret;
- if (!force_dma_unencrypted(dev))
- return 0;
ret = set_memory_encrypted((unsigned long)vaddr, PFN_UP(size));
if (ret)
pr_warn_ratelimited("leaking DMA memory that can't be re-encrypted\n");
@@ -169,7 +172,8 @@ static struct page *dma_direct_alloc_from_pool(struct device *dev, size_t size,
dma_coherent_ok);
if (!page)
return NULL;
- *dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+ *dma_handle = phys_to_dma_direct(dev, page_to_phys(page),
+ !!(attrs & __DMA_ATTR_ALLOC_CC_SHARED));
return page;
}
@@ -185,9 +189,11 @@ static void *dma_direct_alloc_no_mapping(struct device *dev, size_t size,
/* remove any dirty cache lines on the kernel alias */
if (!PageHighMem(page))
arch_dma_prep_coherent(page, size);
-
- /* return the page pointer as the opaque cookie */
- *dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+ /*
+ * return the page pointer as the opaque cookie.
+ * Never used for unencrypted allocation
+ */
+ *dma_handle = phys_to_dma_encrypted(dev, page_to_phys(page));
return page;
}
@@ -324,7 +330,8 @@ void *dma_direct_alloc(struct device *dev, size_t size,
ret = uncached_cpu_addr;
}
- *dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+ *dma_handle = phys_to_dma_direct(dev, page_to_phys(page),
+ !!(attrs & __DMA_ATTR_ALLOC_CC_SHARED));
return ret;
@@ -445,11 +452,13 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
return NULL;
ret = page_address(page);
- if (dma_set_decrypted(dev, ret, size))
+ if ((attrs & __DMA_ATTR_ALLOC_CC_SHARED) &&
+ dma_set_decrypted(dev, ret, size))
goto out_leak_pages;
setup_page:
memset(ret, 0, size);
- *dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+ *dma_handle = phys_to_dma_direct(dev, page_to_phys(page),
+ !!(attrs & __DMA_ATTR_ALLOC_CC_SHARED));
return page;
out_leak_pages:
return NULL;
--
2.43.0
^ permalink raw reply related
* [PATCH v7 19/22] dma-direct: rename ret to cpu_addr in alloc helpers
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
ret in dma_direct_alloc() and dma_direct_alloc_pages() holds the returned
CPU mapping, not a generic return value. Rename it to cpu_addr and update
the remaining uses to match.
This makes the allocation paths easier to follow and keeps the local naming
consistent with what the variable actually represents.
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
kernel/dma/direct.c | 40 ++++++++++++++++++++--------------------
1 file changed, 20 insertions(+), 20 deletions(-)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 23138519cf22..9575d68571bf 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -204,7 +204,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
bool mark_mem_decrypt = false;
bool allow_highmem = true;
struct page *page;
- void *ret;
+ void *cpu_addr;
if (force_dma_unencrypted(dev))
attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
@@ -261,9 +261,10 @@ void *dma_direct_alloc(struct device *dev, size_t size,
*/
if ((remap || (attrs & __DMA_ATTR_ALLOC_CC_SHARED)) &&
dma_direct_use_pool(dev, gfp)) {
- page = dma_direct_alloc_from_pool(dev, size, dma_handle,
- &ret, gfp, attrs);
- return page ? ret : NULL;
+ page = dma_direct_alloc_from_pool(dev, size,
+ dma_handle, &cpu_addr,
+ gfp, attrs);
+ return page ? cpu_addr : NULL;
}
if (is_swiotlb_for_alloc(dev)) {
@@ -310,34 +311,33 @@ void *dma_direct_alloc(struct device *dev, size_t size,
arch_dma_prep_coherent(page, size);
/* create a coherent mapping */
- ret = dma_common_contiguous_remap(page, size, prot,
- __builtin_return_address(0));
- if (!ret)
+ cpu_addr = dma_common_contiguous_remap(page, size, prot,
+ __builtin_return_address(0));
+ if (!cpu_addr)
goto out_encrypt_pages;
} else {
- ret = page_address(page);
+ cpu_addr = page_address(page);
}
- memset(ret, 0, size);
+ memset(cpu_addr, 0, size);
if (set_uncached) {
void *uncached_cpu_addr;
arch_dma_prep_coherent(page, size);
- uncached_cpu_addr = arch_dma_set_uncached(ret, size);
+ uncached_cpu_addr = arch_dma_set_uncached(cpu_addr, size);
if (IS_ERR(uncached_cpu_addr))
goto out_free_remap_pages;
- ret = uncached_cpu_addr;
+ cpu_addr = uncached_cpu_addr;
}
*dma_handle = phys_to_dma_direct(dev, page_to_phys(page),
!!(attrs & __DMA_ATTR_ALLOC_CC_SHARED));
- return ret;
-
+ return cpu_addr;
out_free_remap_pages:
if (remap)
- dma_common_free_remap(ret, size);
+ dma_common_free_remap(cpu_addr, size);
out_encrypt_pages:
if (mark_mem_decrypt &&
@@ -429,21 +429,21 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
{
unsigned long attrs = 0;
struct page *page;
- void *ret;
+ void *cpu_addr;
if (force_dma_unencrypted(dev))
attrs |= __DMA_ATTR_ALLOC_CC_SHARED;
if ((attrs & __DMA_ATTR_ALLOC_CC_SHARED) && dma_direct_use_pool(dev, gfp))
return dma_direct_alloc_from_pool(dev, size, dma_handle,
- &ret, gfp, attrs);
+ &cpu_addr, gfp, attrs);
if (is_swiotlb_for_alloc(dev)) {
page = dma_direct_alloc_swiotlb(dev, size, attrs);
if (!page)
return NULL;
- ret = page_address(page);
+ cpu_addr = page_address(page);
goto setup_page;
}
@@ -451,12 +451,12 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
if (!page)
return NULL;
- ret = page_address(page);
+ cpu_addr = page_address(page);
if ((attrs & __DMA_ATTR_ALLOC_CC_SHARED) &&
- dma_set_decrypted(dev, ret, size))
+ dma_set_decrypted(dev, cpu_addr, size))
goto out_leak_pages;
setup_page:
- memset(ret, 0, size);
+ memset(cpu_addr, 0, size);
*dma_handle = phys_to_dma_direct(dev, page_to_phys(page),
!!(attrs & __DMA_ATTR_ALLOC_CC_SHARED));
return page;
--
2.43.0
^ permalink raw reply related
* [PATCH v7 20/22] dma: swiotlb: free dynamic pools from process context
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
swiotlb_dyn_free() is used after removing a dynamic swiotlb pool from
RCU-protected lists. It can call swiotlb_free_tlb(), which may need to
restore the encryption state of an unencrypted pool with
set_memory_encrypted() before freeing the pages.
RCU callbacks run in atomic context, but set_memory_encrypted() is not
guaranteed to be atomic-safe on all architectures. For example, page
attribute updates may allocate page tables or take sleeping locks.
Use queue_rcu_work() for dynamic pool freeing instead. This keeps the RCU
grace period before freeing a published pool, while running the actual pool
teardown from workqueue context. Use the same helper for the transient-pool
error path, since that path may also be reached from atomic DMA mapping
context.
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
include/linux/swiotlb.h | 4 ++--
kernel/dma/swiotlb.c | 19 +++++++++++--------
2 files changed, 13 insertions(+), 10 deletions(-)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ee42f7588847..c3bf7ed6f7a6 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -64,7 +64,7 @@ extern void __init swiotlb_update_mem_attributes(void);
* @areas: Array of memory area descriptors.
* @slots: Array of slot descriptors.
* @node: Member of the IO TLB memory pool list.
- * @rcu: RCU head for swiotlb_dyn_free().
+ * @dyn_free: RCU work item used to free the pool from process context.
* @transient: %true if transient memory pool.
* @cc_shared: %true if the pool memory is shared for confidential computing.
*/
@@ -80,7 +80,7 @@ struct io_tlb_pool {
struct io_tlb_slot *slots;
#ifdef CONFIG_SWIOTLB_DYNAMIC
struct list_head node;
- struct rcu_head rcu;
+ struct rcu_work dyn_free;
bool transient;
bool cc_shared;
#endif
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index b5960c2e98d8..4d0f2c04d891 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -779,13 +779,10 @@ static void swiotlb_dyn_alloc(struct work_struct *work)
add_mem_pool(mem, pool);
}
-/**
- * swiotlb_dyn_free() - RCU callback to free a memory pool
- * @rcu: RCU head in the corresponding struct io_tlb_pool.
- */
-static void swiotlb_dyn_free(struct rcu_head *rcu)
+static void swiotlb_dyn_free_work(struct work_struct *work)
{
- struct io_tlb_pool *pool = container_of(rcu, struct io_tlb_pool, rcu);
+ struct io_tlb_pool *pool =
+ container_of(to_rcu_work(work), struct io_tlb_pool, dyn_free);
size_t slots_size = array_size(sizeof(*pool->slots), pool->nslabs);
size_t tlb_size = pool->end - pool->start;
@@ -794,6 +791,12 @@ static void swiotlb_dyn_free(struct rcu_head *rcu)
kfree(pool);
}
+static void swiotlb_schedule_dyn_free(struct io_tlb_pool *pool)
+{
+ INIT_RCU_WORK(&pool->dyn_free, swiotlb_dyn_free_work);
+ queue_rcu_work(system_wq, &pool->dyn_free);
+}
+
/**
* __swiotlb_find_pool() - find the IO TLB pool for a physical address
* @dev: Device which has mapped the DMA buffer.
@@ -840,7 +843,7 @@ static void swiotlb_del_pool(struct device *dev, struct io_tlb_pool *pool)
list_del_rcu(&pool->node);
spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
- call_rcu(&pool->rcu, swiotlb_dyn_free);
+ swiotlb_schedule_dyn_free(pool);
}
#endif /* CONFIG_SWIOTLB_DYNAMIC */
@@ -1281,7 +1284,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
index = swiotlb_search_pool_area(dev, pool, 0, orig_addr, tbl_dma_addr,
alloc_size, alloc_align_mask);
if (index < 0) {
- swiotlb_dyn_free(&pool->rcu);
+ swiotlb_schedule_dyn_free(pool);
return -1;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v7 21/22] dma: swiotlb: handle set_memory_decrypted() failures
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86, Michael Kelley
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
Check the return value when converting swiotlb pools between encrypted and
decrypted mappings. If the default pool cannot be decrypted after early
initialization, mark the pool fully used so it cannot satisfy future bounce
allocations.
For late initialization, return the `set_memory_decrypted()` failure. For
restricted DMA pools, fail device initialization if the reserved pool
cannot be decrypted.
This prevents swiotlb from using pools whose encryption attributes do not
match their metadata, and avoids returning pages with uncertain encryption
state back to the allocator.
Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
kernel/dma/swiotlb.c | 80 +++++++++++++++++++++++++++++++++++---------
1 file changed, 65 insertions(+), 15 deletions(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 4d0f2c04d891..8b7e47504304 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -248,6 +248,23 @@ static inline unsigned long nr_slots(u64 val)
return DIV_ROUND_UP(val, IO_TLB_SIZE);
}
+static void swiotlb_mark_pool_used(struct io_tlb_pool *pool)
+{
+ unsigned long i;
+
+ for (i = 0; i < pool->nareas; i++) {
+ pool->areas[i].index = 0;
+ pool->areas[i].used = pool->area_nslabs;
+ }
+
+ for (i = 0; i < pool->nslabs; i++) {
+ pool->slots[i].list = 0;
+ pool->slots[i].orig_addr = INVALID_PHYS_ADDR;
+ pool->slots[i].alloc_size = 0;
+ pool->slots[i].pad_slots = 0;
+ }
+}
+
/*
* Early SWIOTLB allocation may be too early to allow an architecture to
* perform the desired operations. This function allows the architecture to
@@ -272,8 +289,16 @@ void __init swiotlb_update_mem_attributes(void)
return;
bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
- if (io_tlb_default_mem.cc_shared)
- set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT);
+ if (io_tlb_default_mem.cc_shared) {
+ int ret;
+
+ ret = set_memory_decrypted((unsigned long)mem->vaddr,
+ bytes >> PAGE_SHIFT);
+ if (ret) {
+ pr_warn("Failed to decrypt default memory pool, disabling it\n");
+ swiotlb_mark_pool_used(mem);
+ }
+ }
}
static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
@@ -442,9 +467,10 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
{
struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+ unsigned int order, area_order, slot_order;
+ bool leak_pages = false;
unsigned int nareas;
unsigned char *vstart = NULL;
- unsigned int order, area_order;
bool retried = false;
int rc = 0;
@@ -504,6 +530,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
(PAGE_SIZE << order) >> 20);
}
+ rc = -ENOMEM;
nareas = limit_nareas(default_nareas, nslabs);
area_order = get_order(array_size(sizeof(*mem->areas), nareas));
mem->areas = (struct io_tlb_area *)
@@ -511,14 +538,20 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
if (!mem->areas)
goto error_area;
+ slot_order = get_order(array_size(sizeof(*mem->slots), nslabs));
mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(array_size(sizeof(*mem->slots), nslabs)));
+ slot_order);
if (!mem->slots)
goto error_slots;
- if (io_tlb_default_mem.cc_shared)
- set_memory_decrypted((unsigned long)vstart,
- (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
+ if (io_tlb_default_mem.cc_shared) {
+ rc = set_memory_decrypted((unsigned long)vstart,
+ (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
+ if (rc) {
+ leak_pages = true;
+ goto error_decrypt;
+ }
+ }
swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), vstart, nslabs, true,
nareas);
@@ -527,16 +560,20 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
swiotlb_print_info();
return 0;
+error_decrypt:
+ free_pages((unsigned long)mem->slots, slot_order);
error_slots:
free_pages((unsigned long)mem->areas, area_order);
error_area:
- free_pages((unsigned long)vstart, order);
- return -ENOMEM;
+ if (!leak_pages)
+ free_pages((unsigned long)vstart, order);
+ return rc;
}
void __init swiotlb_exit(void)
{
struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
+ bool leak_pages = false;
unsigned long tbl_vaddr;
size_t tbl_size, slots_size;
unsigned int area_order;
@@ -552,19 +589,23 @@ void __init swiotlb_exit(void)
tbl_size = PAGE_ALIGN(mem->end - mem->start);
slots_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), mem->nslabs));
- if (io_tlb_default_mem.cc_shared)
- set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT);
+ if (io_tlb_default_mem.cc_shared) {
+ if (set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT))
+ leak_pages = true;
+ }
if (mem->late_alloc) {
area_order = get_order(array_size(sizeof(*mem->areas),
mem->nareas));
free_pages((unsigned long)mem->areas, area_order);
- free_pages(tbl_vaddr, get_order(tbl_size));
+ if (!leak_pages)
+ free_pages(tbl_vaddr, get_order(tbl_size));
free_pages((unsigned long)mem->slots, get_order(slots_size));
} else {
memblock_free(mem->areas,
array_size(sizeof(*mem->areas), mem->nareas));
- memblock_phys_free(mem->start, tbl_size);
+ if (!leak_pages)
+ memblock_phys_free(mem->start, tbl_size);
memblock_free(mem->slots, slots_size);
}
@@ -1957,9 +1998,18 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
* restricted mem pool is shared by default
*/
if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+ int ret;
+
mem->cc_shared = true;
- set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
- rmem->size >> PAGE_SHIFT);
+ ret = set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
+ rmem->size >> PAGE_SHIFT);
+ if (ret) {
+ dev_err(dev, "Failed to decrypt restricted DMA pool\n");
+ kfree(pool->areas);
+ kfree(pool->slots);
+ kfree(mem);
+ return ret;
+ }
} else {
mem->cc_shared = false;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v7 22/22] swiotlb: remove unused SWIOTLB_FORCE flag
From: Aneesh Kumar K.V (Arm) @ 2026-07-01 5:49 UTC (permalink / raw)
To: iommu, linux-arm-kernel, linux-kernel, linux-coco
Cc: Aneesh Kumar K.V (Arm), Robin Murphy, Marek Szyprowski,
Will Deacon, Marc Zyngier, Steven Price, Suzuki K Poulose,
Catalin Marinas, Jiri Pirko, Jason Gunthorpe, Mostafa Saleh,
Petr Tesarik, Alexey Kardashevskiy, Dan Williams, Xu Yilun,
linuxppc-dev, linux-s390, Madhavan Srinivasan, Michael Ellerman,
Nicholas Piggin, Christophe Leroy (CS GROUP), Alexander Gordeev,
Gerald Schaefer, Heiko Carstens, Vasily Gorbik,
Christian Borntraeger, Sven Schnelle, x86
In-Reply-To: <20260701054926.825925-1-aneesh.kumar@kernel.org>
SWIOTLB_FORCE has no remaining in-tree users. Forced bouncing is now
controlled through the swiotlb=force command line option via
swiotlb_force_bounce.
Remove the unused flag and simplify the force_bounce initialization.
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
include/linux/swiotlb.h | 3 +--
kernel/dma/swiotlb.c | 3 +--
2 files changed, 2 insertions(+), 4 deletions(-)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index c3bf7ed6f7a6..9caca923c380 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -15,8 +15,7 @@ struct page;
struct scatterlist;
#define SWIOTLB_VERBOSE (1 << 0) /* verbose initialization */
-#define SWIOTLB_FORCE (1 << 1) /* force bounce buffering */
-#define SWIOTLB_ANY (1 << 2) /* allow any memory for the buffer */
+#define SWIOTLB_ANY (1 << 1) /* allow any memory for the buffer */
/*
* Maximum allowable number of contiguous slabs to map,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 8b7e47504304..897aba538c5b 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -400,8 +400,7 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
if (swiotlb_force_disable)
return;
- io_tlb_default_mem.force_bounce =
- swiotlb_force_bounce || (flags & SWIOTLB_FORCE);
+ io_tlb_default_mem.force_bounce = swiotlb_force_bounce;
#ifdef CONFIG_SWIOTLB_DYNAMIC
if (!remap)
--
2.43.0
^ permalink raw reply related
* Re: [PATCH v8 23/46] KVM: TDX: Make source page optional for KVM_TDX_INIT_MEM_REGION
From: Yan Zhao @ 2026-07-01 6:21 UTC (permalink / raw)
To: Sean Christopherson
Cc: Ackerley Tng, aik@amd.com, andrew.jones@linux.dev,
binbin.wu@linux.intel.com, brauner@kernel.org,
chao.p.peng@linux.intel.com, david@kernel.org,
jmattson@google.com, jthoughton@google.com, michael.roth@amd.com,
oupton@kernel.org, pankaj.gupta@amd.com, qperret@google.com,
Edgecombe, Rick P, rientjes@google.com, shivankg@amd.com,
steven.price@arm.com, tabba@google.com, willy@infradead.org,
wyihan@google.com, forkloop@google.com, pratyush@kernel.org,
suzuki.poulose@arm.com, aneesh.kumar@kernel.org,
liam@infradead.org, Paolo Bonzini, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86@kernel.org, H. Peter Anvin,
Steven Rostedt, Masami Hiramatsu, Mathieu Desnoyers,
Jonathan Corbet, Shuah Khan, Shuah Khan, Annapurve, Vishal,
Andrew Morton, Chris Li, Kairui Song, Kemeng Shi, Nhat Pham,
Barry Song, Axel Rasmussen, Yuanchu Xie, Wei Xu, Youngjun Park,
Qi Zheng, Shakeel Butt, Kiryl Shutsemau, Baoquan He,
Jason Gunthorpe, Vlastimil Babka, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org,
linux-mm@kvack.org, linux-coco@lists.linux.dev
In-Reply-To: <akPEKslqAhygyjhg@google.com>
On Tue, Jun 30, 2026 at 09:27:06PM +0800, Sean Christopherson wrote:
> On Tue, Jun 30, 2026, Yan Zhao wrote:
> > On Tue, Jun 30, 2026 at 08:35:49AM +0800, Sean Christopherson wrote:
> > > Gah, I thought I had sent this out this morning, long before Ackerley's response.
> > > But I got distracted by a meeting and forgot to get back to this... *sigh*
> > >
> > > Sending what I already wrote, even though there's a lot of overlap with Ackerley's
> > > mail.
> > >
> > > On Mon, Jun 29, 2026, Yan Zhao wrote:
> > > > On Fri, Jun 26, 2026 at 08:28:32AM -0700, Ackerley Tng wrote:
> > > > > Yan Zhao <yan.y.zhao@intel.com> writes:
> > > > > > But if a user configures 0 uaddr as valid, writes to it, and then passes 0 as
> > > > > > source_addr(not from gmem), I'm not sure if it's good for the kernel to silently
> > > > > > treat 0 uaddr as an identifier for in-place copy from the private PFN in gmem.
> > > > > >
> > > > >
> > > > > I'd say the original uAPI perhaps just didn't document 0 as an
> > > > > unsupported uaddr. Given that commit 2a62345b3052 already merged, uAPI
> > > > > was perhaps accidentally changed and no customer complained, I think we
> > > > > can move forward with 0 as an invalid src_address? I wouldn't think
> > > > > anyone relies on 0 intentionally being a valid address.
> > > > >
> > > > > I could document that, if it helps?
> > > > What about just documenting that 0 is an unsupported uaddr which will be
> > > > re-purposed as an indicator to use the target pfn as the source, regardless of
> > > > whether gmem_in_place_conversion is true? i.e.,
> > > >
> > > > if (!src_page)
> > > > src_page = pfn_to_page(pfn);
> > >
> > > Because KVM can't generally use the target page as the source without in-place
> > > conversion, it's not supported today, and out-of-place conversion is being
> > > deprecated.
> > By "out-of-place conversion", do you mean using per-VM memory attribute
> > conversion?
>
> Yep, I couldn't come up with a better description.
>
> > > > I don't get why the two scenarios should be treated differently:
> > > > 1. gmem_in_place_conversion==true, shared memory is not from gmem
> > > > 2. gmem_in_place_conversion==false, shared memory is not from gmem
> > > >
> > > > In both case, a 0 uaddr could be mapped to a valid page not from gmem.
> > >
> > > That's immaterial. KVM's ABI (that we're solidifying) is that an address of '0'
> > > for the source means NULL. The fact that userspace could have a valid mapping
> > > at virtual address '0' is irrelevant.
> > So, I'm wondering if we can document that 0 uaddr could always mean using target
> > PFN.
>
> I would document it as saying "no source page", and then state that a source page
> is required if in-place conversion isn't enabled/supported/allowed.
Ok.
> > i.e., for both scenarios 1 and 2, al long as 0 uaddr is specified, we always
> > use target PFN as source for in-place add.
> >
> > > Again, just because something is technically possible doesn't mean it needs to
> > > be supported by every piece of KVM's uAPI.
> > >
> > > > So why not update the uAPI to handle both cases consistently? :)
> > >
> > > Because retroactively adding support for out-of-place conversion is pointless
> > > (requires a userspace update for a feature that's being deprecated), KVM can't
> > > generally support using the source for out-of-place conversion (it's effectively
> > > an obscure zero-page optimization), and IMO rejecting the out-of-place conversion
> > > scenario is valuable for KVM developers, e.g. to help newcomers understand what
> > > exactly is and isn't possible.
> > Ok. You mean per-VM memory attribute is deprecating, and source page from !gmem
> > backend is also deprecating, so we don't want to change uAPI for scenarios under
> > gmem_in_place_conversion==false. Right?
>
> Right.
>
> >
> > > Side topic, isn't TDX broken if target page has already been added to the TD?
> > > IIUC, kvm_tdp_mmu_map_private_pfn() will be a glorified nop due to the page
> > > already having a valid S-EPT mapping, and so KVM will incorrectly allow a double
> > Not sure if my understand out-of-place conversion correctly.
> > Given target PFNs and GFNs are not duplicated, what would cause double add? :)
>
> I was working through what would happen if userspace did KVM_TDX_INIT_MEM_REGION
> on the same target page multiple times.
Oh. To have KVM_TDX_INIT_MEM_REGION on the same target page multiple times, the
user needs to invoke KVM_TDX_INIT_MEM_REGION on the same GPA multiple times.
In that case, yes, kvm_tdp_mmu_map_private_pfn() will return -EIO.
> >
> > > add. Ahhh, no, because KVM will return RET_PF_SPURIOUS and
> > > kvm_tdp_mmu_map_private_pfn() will then return -EIO.
> > My asking was if we could document uaddr always means using target PFN, since
> > TDX's in-place add does not rely on gmem in-place conversion.
>
> Yeah, I was on a tangent, ignore everything from "Side topic" on.
>
^ permalink raw reply
* Re: [PATCH v8 07/46] KVM: Rename memory attribute APIs to prepare for in-place gmem conversion
From: Xiaoyao Li @ 2026-07-01 7:01 UTC (permalink / raw)
To: Sean Christopherson
Cc: ackerleytng, aik, andrew.jones, binbin.wu, brauner, chao.p.peng,
david, jmattson, jthoughton, michael.roth, oupton, pankaj.gupta,
qperret, rick.p.edgecombe, rientjes, shivankg, steven.price,
tabba, willy, wyihan, yan.y.zhao, forkloop, pratyush,
suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H. Peter Anvin, Steven Rostedt, Masami Hiramatsu,
Mathieu Desnoyers, Jonathan Corbet, Shuah Khan, Shuah Khan,
Vishal Annapurve, Andrew Morton, Chris Li, Kairui Song,
Kemeng Shi, Nhat Pham, Barry Song, Axel Rasmussen, Yuanchu Xie,
Wei Xu, Youngjun Park, Qi Zheng, Shakeel Butt, Kiryl Shutsemau,
Baoquan He, Jason Gunthorpe, Vlastimil Babka, kvm, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest, linux-mm,
linux-coco
In-Reply-To: <akP9Qv_IPVEh7GAB@google.com>
On 7/1/2026 1:30 AM, Sean Christopherson wrote:
> On Tue, Jun 30, 2026, Xiaoyao Li wrote:
>> On 6/19/2026 8:31 AM, Ackerley Tng via B4 Relay wrote:
>>> -bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
>>> - unsigned long mask, unsigned long attrs);
>>> +bool kvm_range_has_vm_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
>>> + unsigned long mask, unsigned long attrs);
>>> bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
>>> struct kvm_gfn_range *range);
>>> bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
>>
>> We have
>>
>> - kvm_pre_set_memory_attributes()
>> - kvm_arch_pre_set_memory_attributes()
>> - kvm_arch_post_set_memory_attributes()
>
> Yeah, that's probably for the best.
>
>> left, do they need to be renamed as well?
>>
>> then the interesting one is kvm_vm_set_mem_attributes(), which contains "vm"
>> already while it means "vm ioctl". Do we need to rename it to
>> kvm_vm_set_vm_mem_attributes()?
>
> I say "no" on this last one, the fact that the function is scoped to a VM ioctl
> is enough to communicate that it applies to per-VM attributes.
>
> Actually, since it's a local helper, we could go with kvm_set_vm_mem_attributes()
> to be consistent with the other functions. That just leaves
> kvm_vm_ioctl_set_mem_attributes(), which I think it appropriately scoped.
If we finally choose to rename kvm_vm_set_mem_attributes() to
kvm_set_vm_mem_attributes(), I think the trace
trace_kvm_vm_set_mem_attributes() needs to be renamed to keep it consistent?
^ permalink raw reply
* Re: [PATCH v8 08/46] KVM: Provide generic interface for checking memory private/shared status
From: Xiaoyao Li @ 2026-07-01 7:22 UTC (permalink / raw)
To: ackerleytng, aik, andrew.jones, binbin.wu, brauner, chao.p.peng,
david, jmattson, jthoughton, michael.roth, oupton, pankaj.gupta,
qperret, rick.p.edgecombe, rientjes, shivankg, steven.price,
tabba, willy, wyihan, yan.y.zhao, forkloop, pratyush,
suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Barry Song, Axel Rasmussen,
Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng, Shakeel Butt,
Kiryl Shutsemau, Baoquan He, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <20260618-gmem-inplace-conversion-v8-8-9d2959357853@google.com>
On 6/19/2026 8:31 AM, Ackerley Tng via B4 Relay wrote:
> From: Sean Christopherson <seanjc@google.com>
>
> Introduce a generic kvm_mem_is_private() interface using a static call to
> determine if a GFN is private. This allows the implementation for checking
> a GFN's private/shared status to be set at runtime.
>
> In preparation for choosing implementations between a guest_memfd lookup
> and the existing VM attribute lookup, rename the existing
> VM-attribute-based check to kvm_vm_mem_is_private to emphasize that it
> looks up VM attributes.
>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
One nit below.
> ---
> include/linux/kvm_host.h | 12 +++++++++++-
> virt/kvm/kvm_main.c | 15 +++++++++++++++
> 2 files changed, 26 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index eb26d4ea8945a..3915da2a61778 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -2546,7 +2546,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
> bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
> struct kvm_gfn_range *range);
>
> -static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
> +static inline bool kvm_vm_mem_is_private(struct kvm *kvm, gfn_t gfn)
> {
> return kvm_get_vm_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
> }
> @@ -2557,6 +2557,16 @@ static inline bool kvm_mem_range_is_private(struct kvm *kvm, gfn_t start,
> KVM_MEMORY_ATTRIBUTE_PRIVATE,
> KVM_MEMORY_ATTRIBUTE_PRIVATE);
> }
> +#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
Since it stops the original #define scope of
CONFIG_KVM_VM_MEMORY_ATTRIBUTES here, ...
> +#ifdef kvm_arch_has_private_mem
> +typedef bool (kvm_mem_is_private_t)(struct kvm *kvm, gfn_t gfn);
> +DECLARE_STATIC_CALL(__kvm_mem_is_private, kvm_mem_is_private_t);
> +
> +static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
> +{
> + return static_call(__kvm_mem_is_private)(kvm, gfn);
> +}
> #else
> static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
> {
... we need to update the comment of #endif to match with the new scope
kvm_arch_has_private_mem as below. Or just delete the comment.
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2572,7 +2572,7 @@ static inline bool kvm_mem_is_private(struct kvm
*kvm, gfn_t gfn)
{
return false;
}
-#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */
+#endif /* kvm_arch_has_private_mem */
#ifdef CONFIG_KVM_GUEST_MEMFD
int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
^ permalink raw reply
* Re: [PATCH v2 2/2] KVM: TDX: Return EINVAL, not EOPNOTSUPP, for NULL INIT_MEM_REGION source
From: Yan Zhao @ 2026-07-01 7:27 UTC (permalink / raw)
To: Sean Christopherson
Cc: Paolo Bonzini, Kiryl Shutsemau, Dave Hansen, Rick Edgecombe, kvm,
x86, linux-coco, linux-kernel, Sashiko Bot, Joerg Roedel,
Ackerley Tng
In-Reply-To: <20260630213711.479692-3-seanjc@google.com>
On Tue, Jun 30, 2026 at 02:37:11PM -0700, Sean Christopherson wrote:
> Return EINVAL instead of EOPNOTSUPP if userspace attempts to pass a NULL
> pointer for the source page of INIT_MEM_REGION, so that KVM's ABI is
> consistent between TDX and SNP (for LAUNCH_UPDATE). EOPNOTSUPP was chosen
> to be a forward-looking error code for when guest_memfd supports in-place
> conversion, but even when in-place conversion comes along, it's an awkward
> error code as KVM is deliberately choosing to disallow virtual address '0',
> which is technically a legal userspace address. I.e. it's not so much a
> lack of support as it is that KVM reserves address '0' to simplify KVM's
> internal implementation.
>
> Opportunistically move the check so that it's co-located with the other
> checks on the userspace address, and so that it's more obvious that a NULL
> source address is explicitly disallowed.
>
> Fixes: 2a62345b3052 ("KVM: guest_memfd: GUP source pages prior to populating guest memory")
> Cc: Yan Zhao <yan.y.zhao@intel.com>
> Cc: Ackerley Tng <ackerleytng@google.com>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yan Zhao <yan.y.zhao@intel.com>
> ---
> arch/x86/kvm/vmx/tdx.c | 7 ++-----
> 1 file changed, 2 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index ffe9d0db58c5..b0ec054732b9 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -3198,9 +3198,6 @@ static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
> if (KVM_BUG_ON(kvm_tdx->page_add_src, kvm))
> return -EIO;
>
> - if (!src_page)
> - return -EOPNOTSUPP;
> -
> kvm_tdx->page_add_src = src_page;
> ret = kvm_tdp_mmu_map_private_pfn(arg->vcpu, gfn, pfn);
> kvm_tdx->page_add_src = NULL;
> @@ -3247,8 +3244,8 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c
> if (copy_from_user(®ion, u64_to_user_ptr(cmd->data), sizeof(region)))
> return -EFAULT;
>
> - if (!PAGE_ALIGNED(region.source_addr) || !PAGE_ALIGNED(region.gpa) ||
> - !region.nr_pages ||
> + if (!PAGE_ALIGNED(region.source_addr) || !region.source_addr ||
> + !PAGE_ALIGNED(region.gpa) || !region.nr_pages ||
> region.gpa + (region.nr_pages << PAGE_SHIFT) <= region.gpa ||
> !vt_is_tdx_private_gpa(kvm, region.gpa) ||
> !vt_is_tdx_private_gpa(kvm, region.gpa + (region.nr_pages << PAGE_SHIFT) - 1))
> --
> 2.55.0.rc0.799.gd6f94ed593-goog
>
^ permalink raw reply
* Re: [PATCH v2 2/2] KVM: TDX: Return EINVAL, not EOPNOTSUPP, for NULL INIT_MEM_REGION source
From: Binbin Wu @ 2026-07-01 8:02 UTC (permalink / raw)
To: Sean Christopherson
Cc: Paolo Bonzini, Kiryl Shutsemau, Dave Hansen, Rick Edgecombe, kvm,
x86, linux-coco, linux-kernel, Sashiko Bot, Joerg Roedel,
Yan Zhao, Ackerley Tng
In-Reply-To: <20260630213711.479692-3-seanjc@google.com>
On 7/1/2026 5:37 AM, Sean Christopherson wrote:
> Return EINVAL instead of EOPNOTSUPP if userspace attempts to pass a NULL
> pointer for the source page of INIT_MEM_REGION, so that KVM's ABI is
> consistent between TDX and SNP (for LAUNCH_UPDATE). EOPNOTSUPP was chosen
> to be a forward-looking error code for when guest_memfd supports in-place
> conversion, but even when in-place conversion comes along, it's an awkward
> error code as KVM is deliberately choosing to disallow virtual address '0',
> which is technically a legal userspace address. I.e. it's not so much a
> lack of support as it is that KVM reserves address '0' to simplify KVM's
> internal implementation.
Nit:
Do you think it's worth calling this out in the documentation?
>
> Opportunistically move the check so that it's co-located with the other
> checks on the userspace address, and so that it's more obvious that a NULL
> source address is explicitly disallowed.
>
> Fixes: 2a62345b3052 ("KVM: guest_memfd: GUP source pages prior to populating guest memory")
> Cc: Yan Zhao <yan.y.zhao@intel.com>
> Cc: Ackerley Tng <ackerleytng@google.com>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Binbin Wu <binbin.wu@linxu.intel.com>
^ permalink raw reply
* Re: [PATCH v8 12/46] KVM: guest_memfd: Only prepare folios for private pages
From: Xiaoyao Li @ 2026-07-01 8:05 UTC (permalink / raw)
To: ackerleytng, aik, andrew.jones, binbin.wu, brauner, chao.p.peng,
david, jmattson, jthoughton, michael.roth, oupton, pankaj.gupta,
qperret, rick.p.edgecombe, rientjes, shivankg, steven.price,
tabba, willy, wyihan, yan.y.zhao, forkloop, pratyush,
suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Barry Song, Axel Rasmussen,
Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng, Shakeel Butt,
Kiryl Shutsemau, Baoquan He, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <20260618-gmem-inplace-conversion-v8-12-9d2959357853@google.com>
On 6/19/2026 8:31 AM, Ackerley Tng via B4 Relay wrote:
> From: Ackerley Tng <ackerleytng@google.com>
>
> All-shared guest_memfd used to be only supported for non-CoCo VMs where
> preparation doesn't apply. INIT_SHARED is about to be supported for CoCo
> VMs in a later patch in this series.
>
> In addition, KVM_SET_MEMORY_ATTRIBUTES2 is about to be supported in
> guest_memfd in a later patch in this series.
>
> This means that the kvm fault handler may now call kvm_gmem_get_pfn() on a
> shared folio for a CoCo VM where preparation applies.
I don't get it clear why preparation isn't needed or should not be
performed for shared folio.
Before this patch, userspace VMM can create the gmem with FLAG_MMAP and
FLAG_INIT_SHARED. And KVM always faultin the pfn from gmem. In this
case, the gmem is always shared, and kvm_gmem_prepare_folio() is always
called when faultin from gmem. So it's OK to call preparation for shared
folio, right? Then what is the actual reason we cannot do it now?
^ permalink raw reply
* Re: [PATCH 00/32] x86/msr: Drop 32-bit MSR interfaces
From: Jürgen Groß @ 2026-07-01 8:33 UTC (permalink / raw)
To: Sean Christopherson, Ingo Molnar
Cc: Arnd Bergmann, linux-kernel, linux-pm, linux-edac@vger.kernel.org,
x86, linux-acpi, kvm, linux-coco, linux-pci, virtualization,
linux-ide, dri-devel, linux-fbdev, linux-crypto,
open list:GPIO SUBSYSTEM, linux-hyperv, linux-hwmon,
linux-perf-users, linux-mtd, platform-driver-x86,
Rafael J . Wysocki, Daniel Lezcano, Zhang Rui,
lukasz.luba@arm.com, Jason Baron, Borislav Petkov, Tony Luck,
Yazen Ghannam, Len Brown, Pavel Machek, Thomas Gleixner,
Ingo Molnar, Dave Hansen, H. Peter Anvin, Paolo Bonzini,
Kirill A. Shutemov, Rick Edgecombe, Pu Wen, Bjorn Helgaas,
Ajay Kaher, Alexey Makhalov, Broadcom internal kernel review list,
Viresh Kumar, Reinette Chatre, Dave Martin, James Morse,
Babu Moger, Tony W Wang-oc, Damien Le Moal, Niklas Cassel,
Dave Airlie, Helge Deller, linux-geode, Olivia Mackall,
Herbert Xu, Linus Walleij, Bartosz Golaszewski,
Greg Kroah-Hartman, K. Y. Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Long Li, Guenter Roeck, Peter Zijlstra,
Arnaldo Carvalho de Melo, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Jiri Olsa, Ian Rogers, Adrian Hunter,
James Clark, Josh Poimboeuf, Pawan Gupta, Vitaly Kuznetsov,
Andy Lutomirski, Boris Ostrovsky, Huang Rui, Mario Limonciello,
Perry Yuan, K Prateek Nayak, srinivas.pandruvada@linux.intel.com,
Artem Bityutskiy, Artem Bityutskiy, Miquel Raynal,
Richard Weinberger, Vignesh Raghavendra, Ashok Raj, Hans de Goede,
Ilpo Järvinen, Rajneesh Bhardwaj, David E Box, xen-devel
In-Reply-To: <akQR9YMtMHReJTfB@google.com>
[-- Attachment #1.1.1: Type: text/plain, Size: 1484 bytes --]
On 30.06.26 20:59, Sean Christopherson wrote:
> On Mon, Jun 29, 2026, Ingo Molnar wrote:
>> * Arnd Bergmann <arnd@arndb.de> wrote:
>>
>>>>>> Note that most patches of this series are independent from each other.
>>>>>> Only the patches removing a specific interface (patches 7, 15, 26 and
>>>>>> 30) and the last two patches of the series depend on all previous
>>>>>> patches.
>>>>>
>>>>> It looks like you are touching most files twice or more here, to
>>>>> first convert from rdmsr to rdmsrq and then to change the
>>>>> two-argument rdmsrq() macro to a single-argument inline. If you
>>>>> introduce the inline version of rdmsrq() first, you should be
>>>>> able to skip the second step (patch 31) as they could be able
>>>>> to coexist.
>>>>
>>>> I've discussed how to structure the series with Ingo Molnar before [1]. The
>>>> current approach was his preference.
>>>
>>> Ok.
>>
>> Note that the individual patches are IMO significantly easier to review
>> through the actual 32-bit => 64-bit variable assignment changes done
>> in isolation (which sometimes include minor cleanups), while
>> the Coccinelle semantic patch:
>>
>> { a(b,c) => c = a(b) }
>>
>> which changes both the function signature and the order of terms as
>> well, is just a single add-on treewide patch.
>
> Is the plan for subsystem maintainers to pick up the relevant patches, and then
> do the treewide change one release cycle later?
Yes, please.
Juergen
[-- Attachment #1.1.2: OpenPGP public key --]
[-- Type: application/pgp-keys, Size: 3743 bytes --]
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 495 bytes --]
^ permalink raw reply
* Re: [PATCH v8 17/46] KVM: guest_memfd: Advertise KVM_SET_MEMORY_ATTRIBUTES2 ioctl
From: Xiaoyao Li @ 2026-07-01 9:03 UTC (permalink / raw)
To: ackerleytng, aik, andrew.jones, binbin.wu, brauner, chao.p.peng,
david, jmattson, jthoughton, michael.roth, oupton, pankaj.gupta,
qperret, rick.p.edgecombe, rientjes, shivankg, steven.price,
tabba, willy, wyihan, yan.y.zhao, forkloop, pratyush,
suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Barry Song, Axel Rasmussen,
Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng, Shakeel Butt,
Kiryl Shutsemau, Baoquan He, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <20260618-gmem-inplace-conversion-v8-17-9d2959357853@google.com>
On 6/19/2026 8:31 AM, Ackerley Tng via B4 Relay wrote:
> @@ -4969,6 +4973,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
> return 1;
> case KVM_CAP_GUEST_MEMFD_FLAGS:
> return kvm_gmem_get_supported_flags(kvm);
> + case KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES:
> + if (!gmem_in_place_conversion || !kvm_supports_private_mem(kvm))
> + return 0;
> +
> + return KVM_MEMORY_ATTRIBUTE_PRIVATE;
> #endif
> default:
> break;
this looks inconsistent with the
case KVM_SET_MEMORY_ATTRIBUTES2:
if (!gmem_in_place_conversion)
return -ENOTTY;
Well, the check of
if (!kvm_arch_has_private_mem(f->kvm))
return -EINVAL;
is buried in the following kvm_gmem_set_attributes(). How about moving
of kvm_arch_has_private_mem() check to put it along with
gmem_in_place_conversion check in kvm_gmem_ioctl() in Patch 13?
^ permalink raw reply
* Re: [PATCH v8 06/46] KVM: Enumerate support for PRIVATE memory iff kvm_arch_has_private_mem is defined
From: Xiaoyao Li @ 2026-07-01 9:19 UTC (permalink / raw)
To: ackerleytng, aik, andrew.jones, binbin.wu, brauner, chao.p.peng,
david, jmattson, jthoughton, michael.roth, oupton, pankaj.gupta,
qperret, rick.p.edgecombe, rientjes, shivankg, steven.price,
tabba, willy, wyihan, yan.y.zhao, forkloop, pratyush,
suzuki.poulose, aneesh.kumar, liam, Paolo Bonzini,
Sean Christopherson, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, x86, H. Peter Anvin, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Jonathan Corbet, Shuah Khan,
Shuah Khan, Vishal Annapurve, Andrew Morton, Chris Li,
Kairui Song, Kemeng Shi, Nhat Pham, Barry Song, Axel Rasmussen,
Yuanchu Xie, Wei Xu, Youngjun Park, Qi Zheng, Shakeel Butt,
Kiryl Shutsemau, Baoquan He, Jason Gunthorpe, Vlastimil Babka
Cc: kvm, linux-kernel, linux-trace-kernel, linux-doc, linux-kselftest,
linux-mm, linux-coco
In-Reply-To: <20260618-gmem-inplace-conversion-v8-6-9d2959357853@google.com>
On 6/19/2026 8:31 AM, Ackerley Tng via B4 Relay wrote:
> From: Ackerley Tng <ackerleytng@google.com>
>
> Explicitly guard reporting support for KVM_MEMORY_ATTRIBUTE_PRIVATE based
> on kvm_arch_has_private_mem being #defined in anticipation of decoupling
> kvm_supported_mem_attributes() from CONFIG_KVM_VM_MEMORY_ATTRIBUTES.
Well, after this series, kvm_supported_mem_attributes() is renamed to
kvm_supported_vm_mem_attributes(), and it's still under
CONFIG_KVM_VM_MEMORY_ATTRIBUTES.
> guest_memfd support for memory attributes will be unconditional to avoid
> yet more macros (all architectures that support guest_memfd are expected to
> use per-gmem attributes at some point), at which point enumerating support
> KVM_MEMORY_ATTRIBUTE_PRIVATE based solely on memory attributes being
> supported _somewhere_ would result in KVM over-reporting support on arm64.
I don't understand it. This patch only changes the behavior of
kvm_supported_mem_attributes(), the usage of which is guarded by
CONFIG_KVM_VM_MEMORY_ATTRIBUTES. This is config is only visible to x86
due to patch 03. How does it affect arm64?
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> Reviewed-by: Fuad Tabba <tabba@google.com>
> Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> ---
> virt/kvm/kvm_main.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 1ccc4895a4c26..7b989b659cf82 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -2421,8 +2421,10 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
> #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES
> static u64 kvm_supported_mem_attributes(struct kvm *kvm)
> {
> +#ifdef kvm_arch_has_private_mem
> if (!kvm || kvm_arch_has_private_mem(kvm))
> return KVM_MEMORY_ATTRIBUTE_PRIVATE;
> +#endif
>
> return 0;
> }
>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox