Re: [PATCH v8 00/14] Convert powerpc to default topdown mmap layout (v8)
Hi Andrew, Le 11/03/2022 à 05:49, Andrew Morton a écrit : > On Fri, 11 Mar 2022 15:26:42 +1100 Michael Ellerman > wrote: > >>> What will be the merge strategy ? I guess it's a bit late to get it >>> through powerpc tree, so I was just wondering whether we could get >>> patches 2 to 5 in mm this cycle, and the powerpc ones next cycle ? >> >> Yeah I didn't pick it up because the mm changes don't have many acks and >> I'm always nervous about carrying generic mm changes. >> >> It would be my preference if Andrew could take 2-5 through mm for v5.18, >> but it is quite late, so I'm not sure how he will feel about that. > > 5.18 isn't a problem. Perhaps you meant 5.17, which would be real tough. > > Can we take a look after 5.18-rc1? 5.18-rc1 was released last night. Can you take patchs 2-5 as they are, or do you prefer I resend them to yourself as a standalone series ? Thanks Christophe
[PATCH 15/15] x86: remove cruft from
gets pulled in by all drivers using the DMA API. Remove x86 internal variables and unnecessary includes from it. Signed-off-by: Christoph Hellwig --- arch/x86/include/asm/dma-mapping.h | 11 --- arch/x86/include/asm/iommu.h | 2 ++ 2 files changed, 2 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 256fd8115223d..1c66708e30623 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -2,17 +2,6 @@ #ifndef _ASM_X86_DMA_MAPPING_H #define _ASM_X86_DMA_MAPPING_H -/* - * IOMMU interface. See Documentation/core-api/dma-api-howto.rst and - * Documentation/core-api/dma-api.rst for documentation. - */ - -#include -#include - -extern int iommu_merge; -extern int panic_on_overflow; - extern const struct dma_map_ops *dma_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index dba89ed40d38d..0bef44d30a278 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -8,6 +8,8 @@ extern int force_iommu, no_iommu; extern int iommu_detected; +extern int iommu_merge; +extern int panic_on_overflow; #ifdef CONFIG_SWIOTLB extern bool x86_swiotlb_enable; -- 2.30.2
[PATCH 14/15] swiotlb: remove swiotlb_init_with_tbl and swiotlb_init_late_with_tbl
No users left.
Signed-off-by: Christoph Hellwig
---
include/linux/swiotlb.h | 2 --
kernel/dma/swiotlb.c| 77 +++--
2 files changed, 20 insertions(+), 59 deletions(-)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 7b50c82f84ce9..7ed35dd3de6e7 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -34,13 +34,11 @@ struct scatterlist;
/* default to 64MB */
#define IO_TLB_DEFAULT_SIZE (64UL<<20)
-int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags);
unsigned long swiotlb_size_or_default(void);
void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
int (*remap)(void *tlb, unsigned long nslabs));
int swiotlb_init_late(size_t size, gfp_t gfp_mask,
int (*remap)(void *tlb, unsigned long nslabs));
-extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
extern void __init swiotlb_update_mem_attributes(void);
phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index d5fe8f5e08300..c54fc40ebb493 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -225,33 +225,6 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem
*mem, phys_addr_t start,
return;
}
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs,
- unsigned int flags)
-{
- struct io_tlb_mem *mem = _tlb_default_mem;
- size_t alloc_size;
-
- if (swiotlb_force_disable)
- return 0;
-
- /* protect against double initialization */
- if (WARN_ON_ONCE(mem->nslabs))
- return -ENOMEM;
-
- alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
- mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
- if (!mem->slots)
- panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
- __func__, alloc_size, PAGE_SIZE);
-
- swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false);
- mem->force_bounce = flags & SWIOTLB_FORCE;
-
- if (flags & SWIOTLB_VERBOSE)
- swiotlb_print_info();
- return 0;
-}
-
/*
* Statically reserve bounce buffer space and initialize bounce buffer data
* structures for the software IO TLB used to implement the DMA API.
@@ -259,7 +232,9 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long
nslabs,
void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
int (*remap)(void *tlb, unsigned long nslabs))
{
+ struct io_tlb_mem *mem = _tlb_default_mem;
unsigned long nslabs = default_nslabs;
+ size_t alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
size_t bytes;
void *tlb;
@@ -280,7 +255,8 @@ void __init swiotlb_init_remap(bool addressing_limit,
unsigned int flags,
else
tlb = memblock_alloc_low(bytes, PAGE_SIZE);
if (!tlb)
- goto fail;
+ panic("%s: failed to allocate tlb structure\n", __func__);
+
if (remap && remap(tlb, nslabs) < 0) {
memblock_free(tlb, PAGE_ALIGN(bytes));
@@ -290,14 +266,17 @@ void __init swiotlb_init_remap(bool addressing_limit,
unsigned int flags,
__func__, bytes);
goto retry;
}
- if (swiotlb_init_with_tbl(tlb, default_nslabs, flags))
- goto fail_free_mem;
- return;
-fail_free_mem:
- memblock_free(tlb, bytes);
-fail:
- pr_warn("Cannot allocate buffer");
+ mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
+ if (!mem->slots)
+ panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
+ __func__, alloc_size, PAGE_SIZE);
+
+ swiotlb_init_io_tlb_mem(mem, __pa(tlb), default_nslabs, false);
+ mem->force_bounce = flags & SWIOTLB_FORCE;
+
+ if (flags & SWIOTLB_VERBOSE)
+ swiotlb_print_info();
}
void __init swiotlb_init(bool addressing_limit, unsigned int flags)
@@ -313,6 +292,7 @@ void __init swiotlb_init(bool addressing_limit, unsigned
int flags)
int swiotlb_init_late(size_t size, gfp_t gfp_mask,
int (*remap)(void *tlb, unsigned long nslabs))
{
+ struct io_tlb_mem *mem = _tlb_default_mem;
unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
unsigned long bytes;
unsigned char *vstart = NULL;
@@ -353,33 +333,16 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
return rc;
goto retry;
}
- rc = swiotlb_late_init_with_tbl(vstart, nslabs);
- if (rc)
- free_pages((unsigned long)vstart, order);
-
- return rc;
-}
-
-int
-swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
-{
- struct io_tlb_mem *mem = _tlb_default_mem;
- unsigned long bytes = nslabs << IO_TLB_SHIFT;
-
- if
[PATCH 13/15] swiotlb: merge swiotlb-xen initialization into swiotlb
Reuse the generic swiotlb initialization for xen-swiotlb. For ARM/ARM64
this works trivially, while for x86 xen_swiotlb_fixup needs to be passed
as the remap argument to swiotlb_init_remap/swiotlb_init_late.
Note that the lower bound of the swiotlb size is changed to the smaller
IO_TLB_MIN_SLABS based value with this patch, but that is fine as the
2MB value used in Xen before was just an optimization and is not the
hard lower bound.
Signed-off-by: Christoph Hellwig
Reviewed-by: Stefano Stabellini
---
arch/arm/xen/mm.c | 21 +++---
arch/x86/include/asm/xen/page.h | 5 --
arch/x86/kernel/pci-dma.c | 20 ++---
drivers/xen/swiotlb-xen.c | 128 +---
include/xen/arm/page.h | 1 -
include/xen/swiotlb-xen.h | 8 +-
6 files changed, 28 insertions(+), 155 deletions(-)
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 28c2070602535..ff05a7899cb86 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -23,22 +23,20 @@
#include
#include
-unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+static gfp_t xen_swiotlb_gfp(void)
{
phys_addr_t base;
- gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM;
u64 i;
for_each_mem_range(i, , NULL) {
if (base < (phys_addr_t)0x) {
if (IS_ENABLED(CONFIG_ZONE_DMA32))
- flags |= __GFP_DMA32;
- else
- flags |= __GFP_DMA;
- break;
+ return __GFP_DMA32;
+ return __GFP_DMA;
}
}
- return __get_free_pages(flags, order);
+
+ return GFP_KERNEL;
}
static bool hypercall_cflush = false;
@@ -140,10 +138,13 @@ static int __init xen_mm_init(void)
if (!xen_swiotlb_detect())
return 0;
- rc = xen_swiotlb_init();
/* we can work with the default swiotlb */
- if (rc < 0 && rc != -EEXIST)
- return rc;
+ if (!io_tlb_default_mem.nslabs) {
+ rc = swiotlb_init_late(swiotlb_size_or_default(),
+ xen_swiotlb_gfp(), NULL);
+ if (rc < 0)
+ return rc;
+ }
cflush.op = 0;
cflush.a.dev_bus_addr = 0;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index e989bc2269f54..1fc67df500145 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -357,9 +357,4 @@ static inline bool xen_arch_need_swiotlb(struct device *dev,
return false;
}
-static inline unsigned long xen_get_swiotlb_free_pages(unsigned int order)
-{
- return __get_free_pages(__GFP_NOWARN, order);
-}
-
#endif /* _ASM_X86_XEN_PAGE_H */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a705a199bf8a3..30bbe4abb5d61 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -72,15 +72,13 @@ static inline void __init pci_swiotlb_detect(void)
#endif /* CONFIG_SWIOTLB */
#ifdef CONFIG_SWIOTLB_XEN
-static bool xen_swiotlb;
-
static void __init pci_xen_swiotlb_init(void)
{
if (!xen_initial_domain() && !x86_swiotlb_enable)
return;
x86_swiotlb_enable = true;
- xen_swiotlb = true;
- xen_swiotlb_init_early();
+ x86_swiotlb_flags |= SWIOTLB_ANY;
+ swiotlb_init_remap(true, x86_swiotlb_flags, xen_swiotlb_fixup);
dma_ops = _swiotlb_dma_ops;
if (IS_ENABLED(CONFIG_PCI))
pci_request_acs();
@@ -88,14 +86,16 @@ static void __init pci_xen_swiotlb_init(void)
int pci_xen_swiotlb_init_late(void)
{
- int rc;
-
- if (xen_swiotlb)
+ if (dma_ops == _swiotlb_dma_ops)
return 0;
- rc = xen_swiotlb_init();
- if (rc)
- return rc;
+ /* we can work with the default swiotlb */
+ if (!io_tlb_default_mem.nslabs) {
+ int rc = swiotlb_init_late(swiotlb_size_or_default(),
+ GFP_KERNEL, xen_swiotlb_fixup);
+ if (rc < 0)
+ return rc;
+ }
/* XXX: this switches the dma ops under live devices! */
dma_ops = _swiotlb_dma_ops;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index c2da3eb4826e8..df8085b50df10 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -104,7 +104,7 @@ static int is_xen_swiotlb_buffer(struct device *dev,
dma_addr_t dma_addr)
return 0;
}
-static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
+int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
{
int rc;
unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT);
@@ -130,132 +130,6 @@ static int xen_swiotlb_fixup(void *buf, unsigned long
nslabs)
return 0;
}
-enum xen_swiotlb_err {
-
[PATCH 12/15] swiotlb: provide swiotlb_init variants that remap the buffer
To shared more code between swiotlb and xen-swiotlb, offer a
swiotlb_init_remap interface and add a remap callback to
swiotlb_init_late that will allow Xen to remap the buffer the
buffer without duplicating much of the logic.
Signed-off-by: Christoph Hellwig
---
arch/x86/pci/sta2x11-fixup.c | 2 +-
include/linux/swiotlb.h | 5 -
kernel/dma/swiotlb.c | 36 +---
3 files changed, 38 insertions(+), 5 deletions(-)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c7e6faf59a861..7368afc039987 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -57,7 +57,7 @@ static void sta2x11_new_instance(struct pci_dev *pdev)
int size = STA2X11_SWIOTLB_SIZE;
/* First instance: register your own swiotlb area */
dev_info(>dev, "Using SWIOTLB (size %i)\n", size);
- if (swiotlb_init_late(size, GFP_DMA))
+ if (swiotlb_init_late(size, GFP_DMA, NULL))
dev_emerg(>dev, "init swiotlb failed\n");
}
list_add(>list, _instance_list);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ee655f2e4d28b..7b50c82f84ce9 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -36,8 +36,11 @@ struct scatterlist;
int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags);
unsigned long swiotlb_size_or_default(void);
+void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
+ int (*remap)(void *tlb, unsigned long nslabs));
+int swiotlb_init_late(size_t size, gfp_t gfp_mask,
+ int (*remap)(void *tlb, unsigned long nslabs));
extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
-int swiotlb_init_late(size_t size, gfp_t gfp_mask);
extern void __init swiotlb_update_mem_attributes(void);
phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 119187afc65ec..d5fe8f5e08300 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -256,9 +256,11 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long
nslabs,
* Statically reserve bounce buffer space and initialize bounce buffer data
* structures for the software IO TLB used to implement the DMA API.
*/
-void __init swiotlb_init(bool addressing_limit, unsigned int flags)
+void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
+ int (*remap)(void *tlb, unsigned long nslabs))
{
- size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
+ unsigned long nslabs = default_nslabs;
+ size_t bytes;
void *tlb;
if (!addressing_limit && !swiotlb_force_bounce)
@@ -271,12 +273,23 @@ void __init swiotlb_init(bool addressing_limit, unsigned
int flags)
* allow to pick a location everywhere for hypervisors with guest
* memory encryption.
*/
+retry:
+ bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
if (flags & SWIOTLB_ANY)
tlb = memblock_alloc(bytes, PAGE_SIZE);
else
tlb = memblock_alloc_low(bytes, PAGE_SIZE);
if (!tlb)
goto fail;
+ if (remap && remap(tlb, nslabs) < 0) {
+ memblock_free(tlb, PAGE_ALIGN(bytes));
+
+ nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+ if (nslabs < IO_TLB_MIN_SLABS)
+ panic("%s: Failed to remap %zu bytes\n",
+ __func__, bytes);
+ goto retry;
+ }
if (swiotlb_init_with_tbl(tlb, default_nslabs, flags))
goto fail_free_mem;
return;
@@ -287,12 +300,18 @@ void __init swiotlb_init(bool addressing_limit, unsigned
int flags)
pr_warn("Cannot allocate buffer");
}
+void __init swiotlb_init(bool addressing_limit, unsigned int flags)
+{
+ return swiotlb_init_remap(addressing_limit, flags, NULL);
+}
+
/*
* Systems with larger DMA zones (those that don't support ISA) can
* initialize the swiotlb later using the slab allocator if needed.
* This should be just like above, but with some error catching.
*/
-int swiotlb_init_late(size_t size, gfp_t gfp_mask)
+int swiotlb_init_late(size_t size, gfp_t gfp_mask,
+ int (*remap)(void *tlb, unsigned long nslabs))
{
unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
unsigned long bytes;
@@ -303,6 +322,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask)
if (swiotlb_force_disable)
return 0;
+retry:
order = get_order(nslabs << IO_TLB_SHIFT);
nslabs = SLABS_PER_PAGE << order;
bytes = nslabs << IO_TLB_SHIFT;
@@ -323,6 +343,16 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask)
(PAGE_SIZE << order) >> 20);
nslabs = SLABS_PER_PAGE << order;
}
+ if
[PATCH 11/15] swiotlb: pass a gfp_mask argument to swiotlb_init_late
Let the caller chose a zone to allocate from. This will be used
later on by the xen-swiotlb initialization on arm.
Signed-off-by: Christoph Hellwig
Reviewed-by: Anshuman Khandual
---
arch/x86/pci/sta2x11-fixup.c | 2 +-
include/linux/swiotlb.h | 2 +-
kernel/dma/swiotlb.c | 7 ++-
3 files changed, 4 insertions(+), 7 deletions(-)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index e0c039a75b2db..c7e6faf59a861 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -57,7 +57,7 @@ static void sta2x11_new_instance(struct pci_dev *pdev)
int size = STA2X11_SWIOTLB_SIZE;
/* First instance: register your own swiotlb area */
dev_info(>dev, "Using SWIOTLB (size %i)\n", size);
- if (swiotlb_init_late(size))
+ if (swiotlb_init_late(size, GFP_DMA))
dev_emerg(>dev, "init swiotlb failed\n");
}
list_add(>list, _instance_list);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index eabdd89987027..ee655f2e4d28b 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -37,7 +37,7 @@ struct scatterlist;
int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags);
unsigned long swiotlb_size_or_default(void);
extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
-int swiotlb_init_late(size_t size);
+int swiotlb_init_late(size_t size, gfp_t gfp_mask);
extern void __init swiotlb_update_mem_attributes(void);
phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index f6e091424af3d..119187afc65ec 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -292,7 +292,7 @@ void __init swiotlb_init(bool addressing_limit, unsigned
int flags)
* initialize the swiotlb later using the slab allocator if needed.
* This should be just like above, but with some error catching.
*/
-int swiotlb_init_late(size_t size)
+int swiotlb_init_late(size_t size, gfp_t gfp_mask)
{
unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
unsigned long bytes;
@@ -303,15 +303,12 @@ int swiotlb_init_late(size_t size)
if (swiotlb_force_disable)
return 0;
- /*
-* Get IO TLB memory from the low pages
-*/
order = get_order(nslabs << IO_TLB_SHIFT);
nslabs = SLABS_PER_PAGE << order;
bytes = nslabs << IO_TLB_SHIFT;
while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
- vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+ vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
order);
if (vstart)
break;
--
2.30.2
[PATCH 09/15] swiotlb: make the swiotlb_init interface more useful
Pass a bool to pass if swiotlb needs to be enabled based on the
addressing needs and replace the verbose argument with a set of
flags, including one to force enable bounce buffering.
Note that this patch removes the possibility to force xen-swiotlb
use using swiotlb=force on the command line on x86 (arm and arm64
never supported that), but this interface will be restored shortly.
Signed-off-by: Christoph Hellwig
---
arch/arm/mm/init.c | 6 +
arch/arm64/mm/init.c | 6 +
arch/ia64/mm/init.c| 4 +--
arch/mips/cavium-octeon/dma-octeon.c | 2 +-
arch/mips/loongson64/dma.c | 2 +-
arch/mips/sibyte/common/dma.c | 2 +-
arch/powerpc/mm/mem.c | 3 ++-
arch/powerpc/platforms/pseries/setup.c | 3 ---
arch/riscv/mm/init.c | 8 +-
arch/s390/mm/init.c| 3 +--
arch/x86/kernel/pci-dma.c | 15 ++-
drivers/xen/swiotlb-xen.c | 4 +--
include/linux/swiotlb.h| 15 ++-
include/trace/events/swiotlb.h | 29 -
kernel/dma/swiotlb.c | 35 ++
15 files changed, 55 insertions(+), 82 deletions(-)
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index fe249ea919083..ce64bdb55a16b 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -271,11 +271,7 @@ static void __init free_highpages(void)
void __init mem_init(void)
{
#ifdef CONFIG_ARM_LPAE
- if (swiotlb_force == SWIOTLB_FORCE ||
- max_pfn > arm_dma_pfn_limit)
- swiotlb_init(1);
- else
- swiotlb_force = SWIOTLB_NO_FORCE;
+ swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE);
#endif
set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 8ac25f19084e8..7b6ea4d6733d6 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -398,11 +398,7 @@ void __init bootmem_init(void)
*/
void __init mem_init(void)
{
- if (swiotlb_force == SWIOTLB_FORCE ||
- max_pfn > PFN_DOWN(arm64_dma_phys_limit))
- swiotlb_init(1);
- else if (!xen_swiotlb_detect())
- swiotlb_force = SWIOTLB_NO_FORCE;
+ swiotlb_init(max_pfn > PFN_DOWN(arm64_dma_phys_limit), SWIOTLB_VERBOSE);
/* this will put all unused low memory onto the freelists */
memblock_free_all();
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 5d165607bf354..3c3e15b22608f 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -437,9 +437,7 @@ mem_init (void)
if (iommu_detected)
break;
#endif
-#ifdef CONFIG_SWIOTLB
- swiotlb_init(1);
-#endif
+ swiotlb_init(true, SWIOTLB_VERBOSE);
} while (0);
#ifdef CONFIG_FLATMEM
diff --git a/arch/mips/cavium-octeon/dma-octeon.c
b/arch/mips/cavium-octeon/dma-octeon.c
index fb7547e217263..9fbba6a8fa4c5 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -235,5 +235,5 @@ void __init plat_swiotlb_setup(void)
#endif
swiotlb_adjust_size(swiotlbsize);
- swiotlb_init(1);
+ swiotlb_init(true, SWIOTLB_VERBOSE);
}
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index 364f2f27c8723..8220a1bc0db64 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -24,5 +24,5 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
void __init plat_swiotlb_setup(void)
{
- swiotlb_init(1);
+ swiotlb_init(true, SWIOTLB_VERBOSE);
}
diff --git a/arch/mips/sibyte/common/dma.c b/arch/mips/sibyte/common/dma.c
index eb47a94f3583e..c5c2c782aff68 100644
--- a/arch/mips/sibyte/common/dma.c
+++ b/arch/mips/sibyte/common/dma.c
@@ -10,5 +10,5 @@
void __init plat_swiotlb_setup(void)
{
- swiotlb_init(1);
+ swiotlb_init(true, SWIOTLB_VERBOSE);
}
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 8e301cd8925b2..e1519e2edc656 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -17,6 +17,7 @@
#include
#include
+#include
#include
#include
#include
@@ -251,7 +252,7 @@ void __init mem_init(void)
if (is_secure_guest())
svm_swiotlb_init();
else
- swiotlb_init(0);
+ swiotlb_init(ppc_swiotlb_enable, 0);
#endif
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
diff --git a/arch/powerpc/platforms/pseries/setup.c
b/arch/powerpc/platforms/pseries/setup.c
index 069d7b3bb142e..c6e06d91b6602 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -838,9 +838,6 @@ static void __init pSeries_setup_arch(void)
}
ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
-
- if (swiotlb_force == SWIOTLB_FORCE)
- ppc_swiotlb_enable
[PATCH 10/15] swiotlb: add a SWIOTLB_ANY flag to lift the low memory restriction
Power SVM wants to allocate a swiotlb buffer that is not restricted to
low memory for the trusted hypervisor scheme. Consolidate the support
for this into the swiotlb_init interface by adding a new flag.
Signed-off-by: Christoph Hellwig
---
arch/powerpc/include/asm/svm.h | 4
arch/powerpc/include/asm/swiotlb.h | 1 +
arch/powerpc/kernel/dma-swiotlb.c| 1 +
arch/powerpc/mm/mem.c| 5 +
arch/powerpc/platforms/pseries/svm.c | 26 +-
include/linux/swiotlb.h | 1 +
kernel/dma/swiotlb.c | 11 +--
7 files changed, 14 insertions(+), 35 deletions(-)
diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h
index 7546402d796af..85580b30aba48 100644
--- a/arch/powerpc/include/asm/svm.h
+++ b/arch/powerpc/include/asm/svm.h
@@ -15,8 +15,6 @@ static inline bool is_secure_guest(void)
return mfmsr() & MSR_S;
}
-void __init svm_swiotlb_init(void);
-
void dtl_cache_ctor(void *addr);
#define get_dtl_cache_ctor() (is_secure_guest() ? dtl_cache_ctor : NULL)
@@ -27,8 +25,6 @@ static inline bool is_secure_guest(void)
return false;
}
-static inline void svm_swiotlb_init(void) {}
-
#define get_dtl_cache_ctor() NULL
#endif /* CONFIG_PPC_SVM */
diff --git a/arch/powerpc/include/asm/swiotlb.h
b/arch/powerpc/include/asm/swiotlb.h
index 3c1a1cd161286..4203b5e0a88ed 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -9,6 +9,7 @@
#include
extern unsigned int ppc_swiotlb_enable;
+extern unsigned int ppc_swiotlb_flags;
#ifdef CONFIG_SWIOTLB
void swiotlb_detect_4g(void);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c
b/arch/powerpc/kernel/dma-swiotlb.c
index fc7816126a401..ba256c37bcc0f 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -10,6 +10,7 @@
#include
unsigned int ppc_swiotlb_enable;
+unsigned int ppc_swiotlb_flags;
void __init swiotlb_detect_4g(void)
{
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index e1519e2edc656..a4d65418c30a9 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -249,10 +249,7 @@ void __init mem_init(void)
* back to to-down.
*/
memblock_set_bottom_up(true);
- if (is_secure_guest())
- svm_swiotlb_init();
- else
- swiotlb_init(ppc_swiotlb_enable, 0);
+ swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags);
#endif
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
diff --git a/arch/powerpc/platforms/pseries/svm.c
b/arch/powerpc/platforms/pseries/svm.c
index c5228f4969eb2..3b4045d508ec8 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -28,7 +28,7 @@ static int __init init_svm(void)
* need to use the SWIOTLB buffer for DMA even if dma_capable() says
* otherwise.
*/
- swiotlb_force = SWIOTLB_FORCE;
+ ppc_swiotlb_flags |= SWIOTLB_ANY | SWIOTLB_FORCE;
/* Share the SWIOTLB buffer with the host. */
swiotlb_update_mem_attributes();
@@ -37,30 +37,6 @@ static int __init init_svm(void)
}
machine_early_initcall(pseries, init_svm);
-/*
- * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it
- * can allocate the buffer anywhere in memory. Since the hypervisor doesn't
have
- * any addressing limitation, we don't need to allocate it in low addresses.
- */
-void __init svm_swiotlb_init(void)
-{
- unsigned char *vstart;
- unsigned long bytes, io_tlb_nslabs;
-
- io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT);
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
-
- bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-
- vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE);
- if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false))
- return;
-
-
- memblock_free(vstart, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
- panic("SVM: Cannot allocate SWIOTLB buffer");
-}
-
int set_memory_encrypted(unsigned long addr, int numpages)
{
if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ae0407173e845..eabdd89987027 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -15,6 +15,7 @@ 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 */
/*
* Maximum allowable number of contiguous slabs to map,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 86e877a96b828..f6e091424af3d 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -266,8 +266,15 @@ void __init swiotlb_init(bool addressing_limit, unsigned
int flags)
if (swiotlb_force_disable)
return;
- /* Get IO TLB
[PATCH 08/15] x86: centralize setting SWIOTLB_FORCE when guest memory encryption is enabled
Move enabling SWIOTLB_FORCE for guest memory encryption into common code.
Signed-off-by: Christoph Hellwig
---
arch/x86/kernel/cpu/mshyperv.c | 8
arch/x86/kernel/pci-dma.c | 8
arch/x86/mm/mem_encrypt_amd.c | 3 ---
3 files changed, 8 insertions(+), 11 deletions(-)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 4b67094215bba..5b8f2c3571601 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -337,14 +337,6 @@ static void __init ms_hyperv_init_platform(void)
swiotlb_unencrypted_base =
ms_hyperv.shared_gpa_boundary;
#endif
}
-
-#ifdef CONFIG_SWIOTLB
- /*
-* Enable swiotlb force mode in Isolation VM to
-* use swiotlb bounce buffer for dma transaction.
-*/
- swiotlb_force = SWIOTLB_FORCE;
-#endif
/* Isolation VMs are unenlightened SEV-based VMs, thus this
check: */
if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
if (hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index df96926421be0..04140e20ef1a3 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -53,6 +53,14 @@ static void __init pci_swiotlb_detect(void)
if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
x86_swiotlb_enable = true;
+ /*
+* Guest with guest memory encryption currently perform all DMA through
+* 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))
+ swiotlb_force = SWIOTLB_FORCE;
+
if (swiotlb_force == SWIOTLB_FORCE)
x86_swiotlb_enable = true;
}
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 6169053c28541..d732d727d3dee 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -432,9 +432,6 @@ void __init sme_early_init(void)
for (i = 0; i < ARRAY_SIZE(protection_map); i++)
protection_map[i] = pgprot_encrypted(protection_map[i]);
- if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
- swiotlb_force = SWIOTLB_FORCE;
-
x86_platform.guest.enc_status_change_prepare =
amd_enc_status_change_prepare;
x86_platform.guest.enc_status_change_finish =
amd_enc_status_change_finish;
x86_platform.guest.enc_tlb_flush_required=
amd_enc_tlb_flush_required;
--
2.30.2
[PATCH 07/15] x86: remove the IOMMU table infrastructure
The IOMMU table tries to separate the different IOMMUs into different
backends, but actually requires various cross calls.
Rewrite the code to do the generic swiotlb/swiotlb-xen setup directly
in pci-dma.c and then just call into the IOMMU drivers.
Signed-off-by: Christoph Hellwig
---
arch/ia64/include/asm/iommu_table.h| 7 --
arch/x86/include/asm/dma-mapping.h | 1 -
arch/x86/include/asm/gart.h| 5 +-
arch/x86/include/asm/iommu.h | 6 ++
arch/x86/include/asm/iommu_table.h | 102 ---
arch/x86/include/asm/swiotlb.h | 30 ---
arch/x86/include/asm/xen/swiotlb-xen.h | 2 -
arch/x86/kernel/Makefile | 2 -
arch/x86/kernel/amd_gart_64.c | 5 +-
arch/x86/kernel/aperture_64.c | 14 ++--
arch/x86/kernel/pci-dma.c | 107 -
arch/x86/kernel/pci-iommu_table.c | 77 --
arch/x86/kernel/pci-swiotlb.c | 77 --
arch/x86/kernel/tboot.c| 1 -
arch/x86/kernel/vmlinux.lds.S | 12 ---
arch/x86/xen/Makefile | 2 -
arch/x86/xen/pci-swiotlb-xen.c | 96 --
drivers/iommu/amd/init.c | 6 --
drivers/iommu/amd/iommu.c | 5 +-
drivers/iommu/intel/dmar.c | 6 +-
include/linux/dmar.h | 6 +-
21 files changed, 110 insertions(+), 459 deletions(-)
delete mode 100644 arch/ia64/include/asm/iommu_table.h
delete mode 100644 arch/x86/include/asm/iommu_table.h
delete mode 100644 arch/x86/include/asm/swiotlb.h
delete mode 100644 arch/x86/kernel/pci-iommu_table.c
delete mode 100644 arch/x86/kernel/pci-swiotlb.c
delete mode 100644 arch/x86/xen/pci-swiotlb-xen.c
diff --git a/arch/ia64/include/asm/iommu_table.h
b/arch/ia64/include/asm/iommu_table.h
deleted file mode 100644
index cc96116ac276a..0
--- a/arch/ia64/include/asm/iommu_table.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_IA64_IOMMU_TABLE_H
-#define _ASM_IA64_IOMMU_TABLE_H
-
-#define IOMMU_INIT_POST(_detect)
-
-#endif /* _ASM_IA64_IOMMU_TABLE_H */
diff --git a/arch/x86/include/asm/dma-mapping.h
b/arch/x86/include/asm/dma-mapping.h
index bb1654fe0ce74..256fd8115223d 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -9,7 +9,6 @@
#include
#include
-#include
extern int iommu_merge;
extern int panic_on_overflow;
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 3185565743459..5af8088a10df6 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -38,7 +38,7 @@ extern int gart_iommu_aperture_disabled;
extern void early_gart_iommu_check(void);
extern int gart_iommu_init(void);
extern void __init gart_parse_options(char *);
-extern int gart_iommu_hole_init(void);
+void gart_iommu_hole_init(void);
#else
#define gart_iommu_aperture0
@@ -51,9 +51,8 @@ static inline void early_gart_iommu_check(void)
static inline void gart_parse_options(char *options)
{
}
-static inline int gart_iommu_hole_init(void)
+static inline void gart_iommu_hole_init(void)
{
- return -ENODEV;
}
#endif
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index bf1ed2ddc74bd..dba89ed40d38d 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -9,6 +9,12 @@
extern int force_iommu, no_iommu;
extern int iommu_detected;
+#ifdef CONFIG_SWIOTLB
+extern bool x86_swiotlb_enable;
+#else
+#define x86_swiotlb_enable false
+#endif
+
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/iommu_table.h
b/arch/x86/include/asm/iommu_table.h
deleted file mode 100644
index 1fb3fd1a83c25..0
--- a/arch/x86/include/asm/iommu_table.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_IOMMU_TABLE_H
-#define _ASM_X86_IOMMU_TABLE_H
-
-#include
-
-/*
- * History lesson:
- * The execution chain of IOMMUs in 2.6.36 looks as so:
- *
- *[xen-swiotlb]
- * |
- * +[swiotlb *]--+
- */ | \
- * / | \
- *[GART] [Calgary] [Intel VT-d]
- * /
- */
- * [AMD-Vi]
- *
- * *: if SWIOTLB detected 'iommu=soft'/'swiotlb=force' it would skip
- * over the rest of IOMMUs and unconditionally initialize the SWIOTLB.
- * Also it would surreptitiously initialize set the swiotlb=1 if there were
- * more than 4GB and if the user did not pass in 'iommu=off'. The swiotlb
- * flag would be turned off by all IOMMUs except the Calgary one.
- *
- * The IOMMU_INIT* macros allow a similar tree (or more complex if desired)
- * to be built by defining who we depend on.
- *
- * And all that needs to be done is to use one of the macros in the IOMMU
- * and the pci-dma.c will take care of the rest.
- */
-
-struct
[PATCH 06/15] MIPS/octeon: use swiotlb_init instead of open coding it
Use the generic swiotlb initialization helper instead of open coding it.
Signed-off-by: Christoph Hellwig
Acked-by: Thomas Bogendoerfer
---
arch/mips/cavium-octeon/dma-octeon.c | 15 ++-
arch/mips/pci/pci-octeon.c | 2 +-
2 files changed, 3 insertions(+), 14 deletions(-)
diff --git a/arch/mips/cavium-octeon/dma-octeon.c
b/arch/mips/cavium-octeon/dma-octeon.c
index df70308db0e69..fb7547e217263 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -186,15 +186,12 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t
daddr)
return daddr;
}
-char *octeon_swiotlb;
-
void __init plat_swiotlb_setup(void)
{
phys_addr_t start, end;
phys_addr_t max_addr;
phys_addr_t addr_size;
size_t swiotlbsize;
- unsigned long swiotlb_nslabs;
u64 i;
max_addr = 0;
@@ -236,15 +233,7 @@ void __init plat_swiotlb_setup(void)
if (OCTEON_IS_OCTEON2() && max_addr >= 0x1ul)
swiotlbsize = 64 * (1<<20);
#endif
- swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT;
- swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE);
- swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT;
-
- octeon_swiotlb = memblock_alloc_low(swiotlbsize, PAGE_SIZE);
- if (!octeon_swiotlb)
- panic("%s: Failed to allocate %zu bytes align=%lx\n",
- __func__, swiotlbsize, PAGE_SIZE);
- if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
- panic("Cannot allocate SWIOTLB buffer");
+ swiotlb_adjust_size(swiotlbsize);
+ swiotlb_init(1);
}
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index fc29b85cfa926..e457a18cbdc59 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -664,7 +664,7 @@ static int __init octeon_pci_setup(void)
/* BAR1 movable regions contiguous to cover the swiotlb */
octeon_bar1_pci_phys =
- virt_to_phys(octeon_swiotlb) & ~((1ull << 22) - 1);
+ io_tlb_default_mem.start & ~((1ull << 22) - 1);
for (index = 0; index < 32; index++) {
union cvmx_pci_bar1_indexx bar1_index;
--
2.30.2
[PATCH 05/15] arm/xen: don't check for xen_initial_domain() in xen_create_contiguous_region
From: Stefano Stabellini
It used to be that Linux enabled swiotlb-xen when running a dom0 on ARM.
Since f5079a9a2a31 "xen/arm: introduce XENFEAT_direct_mapped and
XENFEAT_not_direct_mapped", Linux detects whether to enable or disable
swiotlb-xen based on the new feature flags: XENFEAT_direct_mapped and
XENFEAT_not_direct_mapped.
However, there is still a leftover xen_initial_domain() check in
xen_create_contiguous_region. Remove the check as
xen_create_contiguous_region is only called by swiotlb-xen during
initialization. If xen_create_contiguous_region is called, we know Linux
is running 1:1 mapped so there is no need for additional checks.
Also update the in-code comment.
Signed-off-by: Stefano Stabellini
Signed-off-by: Christoph Hellwig
---
arch/arm/xen/mm.c | 5 +
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index a7e54a087b802..28c2070602535 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -122,10 +122,7 @@ int xen_create_contiguous_region(phys_addr_t pstart,
unsigned int order,
unsigned int address_bits,
dma_addr_t *dma_handle)
{
- if (!xen_initial_domain())
- return -EINVAL;
-
- /* we assume that dom0 is mapped 1:1 for now */
+ /* the domain is 1:1 mapped to use swiotlb-xen */
*dma_handle = pstart;
return 0;
}
--
2.30.2
[PATCH 04/15] swiotlb: rename swiotlb_late_init_with_default_size
swiotlb_late_init_with_default_size is an overly verbose name that
doesn't even catch what the function is doing, given that the size is
not just a default but the actual requested size.
Rename it to swiotlb_init_late.
Signed-off-by: Christoph Hellwig
Reviewed-by: Anshuman Khandual
---
arch/x86/pci/sta2x11-fixup.c | 2 +-
include/linux/swiotlb.h | 2 +-
kernel/dma/swiotlb.c | 6 ++
3 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 101081ad64b6d..e0c039a75b2db 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -57,7 +57,7 @@ static void sta2x11_new_instance(struct pci_dev *pdev)
int size = STA2X11_SWIOTLB_SIZE;
/* First instance: register your own swiotlb area */
dev_info(>dev, "Using SWIOTLB (size %i)\n", size);
- if (swiotlb_late_init_with_default_size(size))
+ if (swiotlb_init_late(size))
dev_emerg(>dev, "init swiotlb failed\n");
}
list_add(>list, _instance_list);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 9fb3a568f0c51..b48b26bfa0edb 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -40,7 +40,7 @@ extern void swiotlb_init(int verbose);
int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
unsigned long swiotlb_size_or_default(void);
extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
-extern int swiotlb_late_init_with_default_size(size_t default_size);
+int swiotlb_init_late(size_t size);
extern void __init swiotlb_update_mem_attributes(void);
phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index e0127e397335e..9a4fe6e48a074 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -281,11 +281,9 @@ swiotlb_init(int verbose)
* initialize the swiotlb later using the slab allocator if needed.
* This should be just like above, but with some error catching.
*/
-int
-swiotlb_late_init_with_default_size(size_t default_size)
+int swiotlb_init_late(size_t size)
{
- unsigned long nslabs =
- ALIGN(default_size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+ unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
unsigned long bytes;
unsigned char *vstart = NULL;
unsigned int order;
--
2.30.2
[PATCH 02/15] swiotlb: make swiotlb_exit a no-op if SWIOTLB_FORCE is set
If force bouncing is enabled we can't release the buffers. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual --- kernel/dma/swiotlb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 73a41cec9e386..98bb0eb44a7bf 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -369,6 +369,9 @@ void __init swiotlb_exit(void) unsigned long tbl_vaddr; size_t tbl_size, slots_size; + if (swiotlb_force == SWIOTLB_FORCE) + return; + if (!mem->nslabs) return; -- 2.30.2
[PATCH 01/15] dma-direct: use is_swiotlb_active in dma_direct_map_page
Use the more specific is_swiotlb_active check instead of checking the
global swiotlb_force variable.
Signed-off-by: Christoph Hellwig
Reviewed-by: Anshuman Khandual
---
kernel/dma/direct.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index 4632b0f4f72eb..4dc16e08c7e1a 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -91,7 +91,7 @@ static inline dma_addr_t dma_direct_map_page(struct device
*dev,
return swiotlb_map(dev, phys, size, dir, attrs);
if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
- if (swiotlb_force != SWIOTLB_NO_FORCE)
+ if (is_swiotlb_active(dev))
return swiotlb_map(dev, phys, size, dir, attrs);
dev_WARN_ONCE(dev, 1,
--
2.30.2
cleanup swiotlb initialization v8
Hi all, this series tries to clean up the swiotlb initialization, including that of swiotlb-xen. To get there is also removes the x86 iommu table infrastructure that massively obsfucates the initialization path. Git tree: git://git.infradead.org/users/hch/misc.git swiotlb-init-cleanup Gitweb: http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/swiotlb-init-cleanup Changes since v7: - rebased to Linux 5.18-rc1 - better document the lower bound swiotlb size for xen-swiotlb - improve the nslabs calculation for the retry case in swiotlb_init_remap and swiotlb_init_late Changes since v6: - use IO_TLB_MIN_SLABS instead of open coding the constant - call the remap callback later in swiotlb_init_late - set SWIOTLB_ANY for xen/x86 Changes since v5: - split a patch into three - fix setting x86_swiotlb_enable for Xen - fix a comment about forced bounce buffering for guest memory encryption - remove the xen_initial_domain check from xen_create_contiguous_region Changes since v3: - fix a compilation issue on some powerpc configfs - fix and cleanup how forced bounce buffering is enabled for guest memory encryption Changes since v2: - make ppc_swiotlb_flags actually work again - also force enable swiotlb for guest encrypted memory to cater to hyperv which doesn't set the host encrypted memory flag Changes since v1: - skip IOMMU initialization on Xen PV kernels - various small whitespace / typo fixes Diffstat: arch/ia64/include/asm/iommu_table.h |7 - arch/x86/include/asm/iommu_table.h | 102 --- arch/x86/include/asm/swiotlb.h | 30 - arch/x86/kernel/pci-iommu_table.c| 77 -- arch/x86/kernel/pci-swiotlb.c| 77 -- arch/x86/xen/pci-swiotlb-xen.c | 96 -- b/arch/arm/mm/init.c |6 - b/arch/arm/xen/mm.c | 26 ++-- b/arch/arm64/mm/init.c |6 - b/arch/ia64/mm/init.c|4 b/arch/mips/cavium-octeon/dma-octeon.c | 15 -- b/arch/mips/loongson64/dma.c |2 b/arch/mips/pci/pci-octeon.c |2 b/arch/mips/sibyte/common/dma.c |2 b/arch/powerpc/include/asm/svm.h |4 b/arch/powerpc/include/asm/swiotlb.h |1 b/arch/powerpc/kernel/dma-swiotlb.c |1 b/arch/powerpc/mm/mem.c |6 - b/arch/powerpc/platforms/pseries/setup.c |3 b/arch/powerpc/platforms/pseries/svm.c | 26 b/arch/riscv/mm/init.c |8 - b/arch/s390/mm/init.c|3 b/arch/x86/include/asm/dma-mapping.h | 12 -- b/arch/x86/include/asm/gart.h|5 b/arch/x86/include/asm/iommu.h |8 + b/arch/x86/include/asm/xen/page.h|5 b/arch/x86/include/asm/xen/swiotlb-xen.h |2 b/arch/x86/kernel/Makefile |2 b/arch/x86/kernel/amd_gart_64.c |5 b/arch/x86/kernel/aperture_64.c | 14 -- b/arch/x86/kernel/cpu/mshyperv.c |8 - b/arch/x86/kernel/pci-dma.c | 114 + b/arch/x86/kernel/tboot.c|1 b/arch/x86/kernel/vmlinux.lds.S | 12 -- b/arch/x86/mm/mem_encrypt_amd.c |3 b/arch/x86/pci/sta2x11-fixup.c |2 b/arch/x86/xen/Makefile |2 b/drivers/iommu/amd/init.c |6 - b/drivers/iommu/amd/iommu.c |5 b/drivers/iommu/intel/dmar.c |6 - b/drivers/xen/swiotlb-xen.c | 132 - b/include/linux/dmar.h |6 - b/include/linux/swiotlb.h| 22 ++-- b/include/trace/events/swiotlb.h | 29 + b/include/xen/arm/page.h |1 b/include/xen/swiotlb-xen.h |8 + b/kernel/dma/direct.h|2 b/kernel/dma/swiotlb.c | 163 ++- 48 files changed, 252 insertions(+), 827 deletions(-)
[PATCH 03/15] swiotlb: simplify swiotlb_max_segment
Remove the bogus Xen override that was usually larger than the actual
size and just calculate the value on demand. Note that
swiotlb_max_segment still doesn't make sense as an interface and should
eventually be removed.
Signed-off-by: Christoph Hellwig
Reviewed-by: Anshuman Khandual
---
drivers/xen/swiotlb-xen.c | 2 --
include/linux/swiotlb.h | 1 -
kernel/dma/swiotlb.c | 20 +++-
3 files changed, 3 insertions(+), 20 deletions(-)
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 47aebd98f52f5..485cd06ed39e7 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -202,7 +202,6 @@ int xen_swiotlb_init(void)
rc = swiotlb_late_init_with_tbl(start, nslabs);
if (rc)
return rc;
- swiotlb_set_max_segment(PAGE_SIZE);
return 0;
error:
if (nslabs > 1024 && repeat--) {
@@ -254,7 +253,6 @@ void __init xen_swiotlb_init_early(void)
if (swiotlb_init_with_tbl(start, nslabs, true))
panic("Cannot allocate SWIOTLB buffer");
- swiotlb_set_max_segment(PAGE_SIZE);
}
#endif /* CONFIG_X86 */
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index f6c3638255d54..9fb3a568f0c51 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -164,7 +164,6 @@ static inline void swiotlb_adjust_size(unsigned long size)
#endif /* CONFIG_SWIOTLB */
extern void swiotlb_print_info(void);
-extern void swiotlb_set_max_segment(unsigned int);
#ifdef CONFIG_DMA_RESTRICTED_POOL
struct page *swiotlb_alloc(struct device *dev, size_t size);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 98bb0eb44a7bf..e0127e397335e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -68,12 +68,6 @@ struct io_tlb_mem io_tlb_default_mem;
phys_addr_t swiotlb_unencrypted_base;
-/*
- * Max segment that we can provide which (if pages are contingous) will
- * not be bounced (unless SWIOTLB_FORCE is set).
- */
-static unsigned int max_segment;
-
static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
static int __init
@@ -97,18 +91,12 @@ early_param("swiotlb", setup_io_tlb_npages);
unsigned int swiotlb_max_segment(void)
{
- return io_tlb_default_mem.nslabs ? max_segment : 0;
+ if (!io_tlb_default_mem.nslabs)
+ return 0;
+ return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE);
}
EXPORT_SYMBOL_GPL(swiotlb_max_segment);
-void swiotlb_set_max_segment(unsigned int val)
-{
- if (swiotlb_force == SWIOTLB_FORCE)
- max_segment = 1;
- else
- max_segment = rounddown(val, PAGE_SIZE);
-}
-
unsigned long swiotlb_size_or_default(void)
{
return default_nslabs << IO_TLB_SHIFT;
@@ -258,7 +246,6 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long
nslabs, int verbose)
if (verbose)
swiotlb_print_info();
- swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
return 0;
}
@@ -359,7 +346,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
swiotlb_print_info();
- swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT);
return 0;
}
--
2.30.2
Re: [PATCH] powerpc/85xx: Remove fsl,85... bindings
Borislav Petkov writes:
> On Thu, Mar 31, 2022 at 12:13:10PM +0200, Christophe Leroy wrote:
>> Since commit 8a4ab218ef70 ("powerpc/85xx: Change deprecated binding
>> for 85xx-based boards"), those bindings are not used anymore.
>>
>> A comment in drivers/edac/mpc85xx_edac.c say they are to be removed
>> with kernel 2.6.30.
>>
>> Remove them now.
>>
>> Signed-off-by: Christophe Leroy
>> ---
>> .../bindings/memory-controllers/fsl/fsl,ddr.yaml | 6 --
>> .../devicetree/bindings/powerpc/fsl/l2cache.txt| 6 --
>> drivers/edac/mpc85xx_edac.c| 14 --
>> 3 files changed, 26 deletions(-)
>
>
> I'll take it through the EDAC tree of there are no objections.
Fine by me, thanks.
cheers
[PATCH] [Rebased for 5.4] powerpc/kasan: Fix early region not updated correctly
From: Chen Jingwen
This is backport for 5.4
Upstream commit dd75080aa8409ce10d50fb58981c6b59bf8707d3
The shadow's page table is not updated when PTE_RPN_SHIFT is 24
and PAGE_SHIFT is 12. It not only causes false positives but
also false negative as shown the following text.
Fix it by bringing the logic of kasan_early_shadow_page_entry here.
1. False Positive:
==
BUG: KASAN: vmalloc-out-of-bounds in pcpu_alloc+0x508/0xa50
Write of size 16 at addr f57f3be0 by task swapper/0/1
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.15.0-12267-gdebe436e77c7 #1
Call Trace:
[c80d1c20] [c07fe7b8] dump_stack_lvl+0x4c/0x6c (unreliable)
[c80d1c40] [c02ff668] print_address_description.constprop.0+0x88/0x300
[c80d1c70] [c02ff45c] kasan_report+0x1ec/0x200
[c80d1cb0] [c0300b20] kasan_check_range+0x160/0x2f0
[c80d1cc0] [c03018a4] memset+0x34/0x90
[c80d1ce0] [c0280108] pcpu_alloc+0x508/0xa50
[c80d1d40] [c02fd7bc] __kmem_cache_create+0xfc/0x570
[c80d1d70] [c0283d64] kmem_cache_create_usercopy+0x274/0x3e0
[c80d1db0] [c2036580] init_sd+0xc4/0x1d0
[c80d1de0] [c00044a0] do_one_initcall+0xc0/0x33c
[c80d1eb0] [c2001624] kernel_init_freeable+0x2c8/0x384
[c80d1ef0] [c0004b14] kernel_init+0x24/0x170
[c80d1f10] [c001b26c] ret_from_kernel_thread+0x5c/0x64
Memory state around the buggy address:
f57f3a80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
f57f3b00: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
>f57f3b80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
^
f57f3c00: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
f57f3c80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
==
2. False Negative (with KASAN tests):
==
Before fix:
ok 45 - kmalloc_double_kzfree
# vmalloc_oob: EXPECTATION FAILED at lib/test_kasan.c:1039
KASAN failure expected in "((volatile char *)area)[3100]", but none occurred
not ok 46 - vmalloc_oob
not ok 1 - kasan
==
After fix:
ok 1 - kasan
Fixes: cbd18991e24fe ("powerpc/mm: Fix an Oops in kasan_mmu_init()")
Cc: sta...@vger.kernel.org # 5.4.x
Signed-off-by: Chen Jingwen
Reviewed-by: Christophe Leroy
Signed-off-by: Michael Ellerman
Link: https://lore.kernel.org/r/20211229035226.59159-1-chenjingw...@huawei.com
[chleroy: Backport for 5.4]
Signed-off-by: Christophe Leroy
---
arch/powerpc/mm/kasan/kasan_init_32.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c
b/arch/powerpc/mm/kasan/kasan_init_32.c
index 1cfe57b51d7e..3f78007a7282 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -121,7 +121,7 @@ static void __init kasan_remap_early_shadow_ro(void)
pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur),
k_cur);
pte_t *ptep = pte_offset_kernel(pmd, k_cur);
- if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
+ if (pte_page(*ptep) !=
virt_to_page(lm_alias(kasan_early_shadow_page)))
continue;
__set_pte_at(_mm, k_cur, ptep, pfn_pte(PHYS_PFN(pa),
prot), 0);
--
2.35.1
Re: [PATCH] [Rebased for 5.4] powerpc/kasan: Fix early region not updated correctly
On Sun, Apr 03, 2022 at 11:54:55AM +, Christophe Leroy wrote: > > > Le 03/04/2022 à 12:25, Greg KH a écrit : > > On Sat, Apr 02, 2022 at 06:13:31PM +0200, Christophe Leroy wrote: > >> From: Chen Jingwen > >> > >> This is backport for 5.4 > >> > >> Upstream commit 5647a94a26e352beed61788b46e035d9d12664cd > > > > This is not a commit in Linus's tree :( > > > > Oops. Don't know what I did, that's indeed the commit after I > cherry-picked it on top of 5.4.188 and before I modified it. > > According to the mail you sent me yesterday to tell it FAILED to apply > on 5.4, the upstream commit is dd75080aa8409ce10d50fb58981c6b59bf8707d3 Can you resend with this fixed up please? thanks, greg k-h
[PATCH] soc: fsl: qe: Fix refcount leak in par_io_of_config
The device_node pointer is returned by of_parse_phandle() with
refcount incremented. We should use of_node_put() on it when done.
This function only calls of_node_put() in the regular path.
And it will cause refcount leak in error path.
Fixes: 986585385131 ("[POWERPC] Add QUICC Engine (QE) infrastructure")
Signed-off-by: Miaoqian Lin
---
drivers/soc/fsl/qe/qe_io.c | 8 ++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/soc/fsl/qe/qe_io.c b/drivers/soc/fsl/qe/qe_io.c
index a5e2d0e5ab51..9f5f746bea88 100644
--- a/drivers/soc/fsl/qe/qe_io.c
+++ b/drivers/soc/fsl/qe/qe_io.c
@@ -159,12 +159,12 @@ int par_io_of_config(struct device_node *np)
pio_map = of_get_property(pio, "pio-map", _map_len);
if (pio_map == NULL) {
printk(KERN_ERR "pio-map is not set!\n");
- return -1;
+ goto err_node_put;
}
pio_map_len /= sizeof(unsigned int);
if ((pio_map_len % 6) != 0) {
printk(KERN_ERR "pio-map format wrong!\n");
- return -1;
+ goto err_node_put;
}
while (pio_map_len > 0) {
@@ -182,5 +182,9 @@ int par_io_of_config(struct device_node *np)
}
of_node_put(pio);
return 0;
+
+err_node_put:
+ of_node_put(pio);
+ return -1;
}
EXPORT_SYMBOL(par_io_of_config);
--
2.17.1
Re: [PATCH] [Rebased for 5.4] powerpc/kasan: Fix early region not updated correctly
Le 03/04/2022 à 12:25, Greg KH a écrit : > On Sat, Apr 02, 2022 at 06:13:31PM +0200, Christophe Leroy wrote: >> From: Chen Jingwen >> >> This is backport for 5.4 >> >> Upstream commit 5647a94a26e352beed61788b46e035d9d12664cd > > This is not a commit in Linus's tree :( > Oops. Don't know what I did, that's indeed the commit after I cherry-picked it on top of 5.4.188 and before I modified it. According to the mail you sent me yesterday to tell it FAILED to apply on 5.4, the upstream commit is dd75080aa8409ce10d50fb58981c6b59bf8707d3 Thanks Christophe
Re: [PATCH] [Rebased for 5.4] powerpc/kasan: Fix early region not updated correctly
On Sat, Apr 02, 2022 at 06:13:31PM +0200, Christophe Leroy wrote: > From: Chen Jingwen > > This is backport for 5.4 > > Upstream commit 5647a94a26e352beed61788b46e035d9d12664cd This is not a commit in Linus's tree :(
Re: [PATCH] char: tpm: Prepare cleanup of powerpc's asm/prom.h
On Sat, Apr 02, 2022 at 12:29:19PM +0200, Christophe Leroy wrote:
> powerpc's asm/prom.h brings some headers that it doesn't
> need itself.
>
> In order to clean it up, first add missing headers in
> users of asm/prom.h
>
> Signed-off-by: Christophe Leroy
I don't understand this. It changes nothing as far as kernel is concerned.
> ---
> drivers/char/tpm/tpm_atmel.h | 2 --
> drivers/char/tpm/tpm_ibmvtpm.c | 1 -
> 2 files changed, 3 deletions(-)
>
> diff --git a/drivers/char/tpm/tpm_atmel.h b/drivers/char/tpm/tpm_atmel.h
> index ba37e77e8af3..959f7cce8301 100644
> --- a/drivers/char/tpm/tpm_atmel.h
> +++ b/drivers/char/tpm/tpm_atmel.h
> @@ -26,8 +26,6 @@ struct tpm_atmel_priv {
>
> #ifdef CONFIG_PPC64
>
> -#include
> -
> #define atmel_getb(priv, offset) readb(priv->iobase + offset)
> #define atmel_putb(val, priv, offset) writeb(val, priv->iobase + offset)
> #define atmel_request_region request_mem_region
> diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
> index 3af4c07a9342..1180cce7067a 100644
> --- a/drivers/char/tpm/tpm_ibmvtpm.c
> +++ b/drivers/char/tpm/tpm_ibmvtpm.c
> @@ -20,7 +20,6 @@
> #include
> #include
> #include
> -#include
>
> #include "tpm.h"
> #include "tpm_ibmvtpm.h"
> --
> 2.35.1
>
BR, Jarkko
