dma mask related fixups (including full bus_dma_mask support) v2
Subsystems (5)
Hi all,
the dma_get_required_mask dma API implementation has always been a little odd, in that we by default don't wire it up struct dma_map_ops, but instead hard code a default implementation. powerpc and ia64 override this default and either call a method or otherwise duplicate the default.
This series always enabled the method and just falls back to the previous default implementation when it is not available, as well as fixing up a few bits in the default implementations. This already allows removing the ia64 override of the implementation, and will also allow to remove the powerpc one together with a few additional cleanups in the powerpc code, but those will be sent separately with other powerpc DMA API patches. Last but not least the method will allow us to return a more sensible value for typical iommu dma_ops eventually, but that is left to another series as well.
Additionally the dma-direct code has been a bit sloppy in when it was using phys_to_dma in a few places, so this gets fixed up as well as actually respecting the bus_dma_mask everywhere instead of just rejecting dma mask that don't fit into it.
Alltogether this should be all core dma-direct changes required to move powerpc over to the generic code.
Changes since v2:
- clean up a mask check
- add various acks
PATCH 1/5 dma-mapping: make the get_required_mask method available unconditionally
This save some duplication for ia64, and makes the interface more general. In the long run we want each dma_map_ops instance to fill this out, but this will take a little more prep work.
--- arch/ia64/include/asm/dma-mapping.h | 2 -- arch/ia64/include/asm/machvec.h | 7 ------- arch/ia64/include/asm/machvec_init.h | 1 - arch/ia64/include/asm/machvec_sn2.h | 2 -- arch/ia64/pci/pci.c | 26 -------------------------- arch/ia64/sn/pci/pci_dma.c | 4 ++-- drivers/base/platform.c | 13 +++++++++++-- drivers/pci/controller/vmd.c | 4 ---- include/linux/dma-mapping.h | 2 -- 9 files changed, 13 insertions(+), 48 deletions(-)
arch/ia64/include/asm/dma-mapping.h +0 -2
@@ -10,8 +10,6 @@#include <linux/scatterlist.h> #include <linux/dma-debug.h> -#define ARCH_HAS_DMA_GET_REQUIRED_MASK -extern const struct dma_map_ops *dma_ops;extern struct ia64_machine_vector ia64_mv;extern void set_iommu_machvec (void );
arch/ia64/include/asm/machvec.h +0 -7
@@ -44,7 +44,6 @@ typedef void ia64_mv_kernel_launch_event_t(void);/* DMA-mapping interface: */ typedef void ia64_mv_dma_init (void ); -typedef u64 ia64_mv_dma_get_required_mask (struct device *);typedef const struct dma_map_ops *ia64_mv_dma_get_ops (struct device *);/*
@@ -127,7 +126,6 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);# define platform_global_tlb_purge ia64_mv.global_tlb_purge# define platform_tlb_migrate_finish ia64_mv.tlb_migrate_finish# define platform_dma_init ia64_mv.dma_init -# define platform_dma_get_required_mask ia64_mv.dma_get_required_mask# define platform_dma_get_ops ia64_mv.dma_get_ops# define platform_irq_to_vector ia64_mv.irq_to_vector# define platform_local_vector_to_irq ia64_mv.local_vector_to_irq
@@ -171,7 +169,6 @@ struct ia64_machine_vector {ia64_mv_global_tlb_purge_t *global_tlb_purge;ia64_mv_tlb_migrate_finish_t *tlb_migrate_finish;ia64_mv_dma_init *dma_init; -ia64_mv_dma_get_required_mask *dma_get_required_mask;ia64_mv_dma_get_ops *dma_get_ops;ia64_mv_irq_to_vector *irq_to_vector;ia64_mv_local_vector_to_irq *local_vector_to_irq;
@@ -211,7 +208,6 @@ struct ia64_machine_vector { platform_global_tlb_purge, \ platform_tlb_migrate_finish, \ platform_dma_init, \ - platform_dma_get_required_mask, \ platform_dma_get_ops, \ platform_irq_to_vector, \ platform_local_vector_to_irq, \
@@ -286,9 +282,6 @@ extern const struct dma_map_ops *dma_get_ops(struct device *);#ifndef platform_dma_get_ops# define platform_dma_get_ops dma_get_ops#endif -#ifndef platform_dma_get_required_mask -# define platform_dma_get_required_mask ia64_dma_get_required_mask -#endif #ifndef platform_irq_to_vector# define platform_irq_to_vector __ia64_irq_to_vector#endif
arch/ia64/include/asm/machvec_init.h +0 -1
@@ -4,7 +4,6 @@extern ia64_mv_send_ipi_t ia64_send_ipi;extern ia64_mv_global_tlb_purge_t ia64_global_tlb_purge; -extern ia64_mv_dma_get_required_mask ia64_dma_get_required_mask;extern ia64_mv_irq_to_vector __ia64_irq_to_vector;extern ia64_mv_local_vector_to_irq __ia64_local_vector_to_irq;extern ia64_mv_pci_get_legacy_mem_t ia64_pci_get_legacy_mem;
arch/ia64/include/asm/machvec_sn2.h +0 -2
@@ -55,7 +55,6 @@ extern ia64_mv_readb_t __sn_readb_relaxed;extern ia64_mv_readw_t __sn_readw_relaxed;extern ia64_mv_readl_t __sn_readl_relaxed;extern ia64_mv_readq_t __sn_readq_relaxed; -extern ia64_mv_dma_get_required_mask sn_dma_get_required_mask;extern ia64_mv_dma_init sn_dma_init;extern ia64_mv_migrate_t sn_migrate;extern ia64_mv_kernel_launch_event_t sn_kernel_launch_event;
@@ -100,7 +99,6 @@ extern ia64_mv_pci_fixup_bus_t sn_pci_fixup_bus;#define platform_pci_get_legacy_mem sn_pci_get_legacy_mem#define platform_pci_legacy_read sn_pci_legacy_read#define platform_pci_legacy_write sn_pci_legacy_write -#define platform_dma_get_required_mask sn_dma_get_required_mask#define platform_dma_init sn_dma_init#define platform_migrate sn_migrate#define platform_kernel_launch_event sn_kernel_launch_event
arch/ia64/pci/pci.c +0 -26
@@ -568,32 +568,6 @@ static void __init set_pci_dfl_cacheline_size(void) pci_dfl_cache_line_size = (1 << cci.pcci_line_size) /4 ; } -u64 ia64_dma_get_required_mask (struct device *dev) -{ -u32 low_totalram = ((max_pfn -1 ) <<PAGE_SHIFT ); -u32 high_totalram = ((max_pfn -1 ) >> (32 -PAGE_SHIFT )); -u64 mask; - -if (!high_totalram) { -/* convert to mask just covering totalram */ - low_totalram = (1 << (fls (low_totalram) -1 )); - low_totalram += low_totalram -1 ; - mask = low_totalram; - }else { - high_totalram = (1 << (fls (high_totalram) -1 )); - high_totalram += high_totalram -1 ; - mask = (((u64 )high_totalram) <<32 ) +0xffffffff ; - } -return mask; -} -EXPORT_SYMBOL_GPL (ia64_dma_get_required_mask); - -u64 dma_get_required_mask (struct device *dev) -{ -return platform_dma_get_required_mask (dev); -} -EXPORT_SYMBOL_GPL (dma_get_required_mask); -static int __init pcibios_init (void ) {set_pci_dfl_cacheline_size ();
arch/ia64/sn/pci/pci_dma.c +2 -2
@@ -344,11 +344,10 @@ static int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)return 0 ; } -u64 sn_dma_get_required_mask (struct device *dev) +static u64 sn_dma_get_required_mask (struct device *dev) {return DMA_BIT_MASK (64 ); } -EXPORT_SYMBOL_GPL (sn_dma_get_required_mask);char *sn_pci_get_legacy_mem (struct pci_bus *bus) {
@@ -473,6 +472,7 @@ static struct dma_map_ops sn_dma_ops = { .sync_sg_for_device = sn_dma_sync_sg_for_device, .mapping_error = sn_dma_mapping_error, .dma_supported = sn_dma_supported, + .get_required_mask = sn_dma_get_required_mask, };void sn_dma_init (void )
drivers/base/platform.c +11 -2
@@ -1179,8 +1179,7 @@ int __init platform_bus_init(void)return error; } -#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK -u64 dma_get_required_mask (struct device *dev) +static u64 dma_default_get_required_mask (struct device *dev) {u32 low_totalram = ((max_pfn -1 ) <<PAGE_SHIFT );u32 high_totalram = ((max_pfn -1 ) >> (32 -PAGE_SHIFT ));
@@ -1198,6 +1197,16 @@ u64 dma_get_required_mask(struct device *dev) }return mask; } + +#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK +u64 dma_get_required_mask (struct device *dev) +{ +const struct dma_map_ops *ops =get_dma_ops (dev); + +if (ops->get_required_mask) +return ops->get_required_mask (dev); +return dma_default_get_required_mask (dev); +}EXPORT_SYMBOL_GPL (dma_get_required_mask);#endif
drivers/pci/controller/vmd.c +0 -4
@@ -404,12 +404,10 @@ static int vmd_dma_supported(struct device *dev, u64 mask)return vmd_dma_ops (dev)->dma_supported (to_vmd_dev (dev), mask); } -#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK static u64 vmd_get_required_mask (struct device *dev) {return vmd_dma_ops (dev)->get_required_mask (to_vmd_dev (dev)); } -#endif static void vmd_teardown_dma_ops (struct vmd_dev *vmd) {
@@ -450,9 +448,7 @@ static void vmd_setup_dma_ops(struct vmd_dev *vmd)ASSIGN_VMD_DMA_OPS (source, dest, sync_sg_for_device);ASSIGN_VMD_DMA_OPS (source, dest, mapping_error);ASSIGN_VMD_DMA_OPS (source, dest, dma_supported); -#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK ASSIGN_VMD_DMA_OPS (source, dest, get_required_mask); -#endif add_dma_domain (domain); }#undef ASSIGN_VMD_DMA_OPS
include/linux/dma-mapping.h +0 -2
@@ -130,9 +130,7 @@ struct dma_map_ops { enum dma_data_direction direction);int (*mapping_error)(struct device *dev,dma_addr_t dma_addr);int (*dma_supported)(struct device *dev,u64 mask); -#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK u64 (*get_required_mask)(struct device *dev); -#endif };extern const struct dma_map_ops dma_direct_ops;
Signature · 1 line
2.19.0
PATCH 2/5 dma-direct: add an explicit dma_direct_get_required_mask
In reply to Christoph HellwigThis is somewhat modelled after the powerpc version, and differs from the legacy fallback in use fls64 instead of pointlessly splitting up the address into low and high dwords and in that it takes (__)phys_to_dma into account.
--- include/linux/dma-direct.h | 1 + kernel/dma/direct.c | 22 +++++++++++++++++++--- 2 files changed, 20 insertions(+), 3 deletions(-)
include/linux/dma-direct.h +1 -0
@@ -55,6 +55,7 @@ static inline void dma_mark_clean(void *addr, size_t size) }#endif /* CONFIG_ARCH_HAS_DMA_MARK_CLEAN */ +u64 dma_direct_get_required_mask (struct device *dev);void *dma_direct_alloc (struct device *dev,size_t size,dma_addr_t *dma_handle,gfp_t gfp,unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
kernel/dma/direct.c +19 -3
@@ -4,6 +4,7 @@* * DMA operations that map physical memory directly without using an IOMMU. */ +#include <linux/bootmem.h> /* for max_pfn */ #include <linux/export.h> #include <linux/mm.h> #include <linux/dma-direct.h>
@@ -53,11 +54,25 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,return true; } +static inline dma_addr_t phys_to_dma_direct (struct device *dev, +phys_addr_t phys) +{ +if (force_dma_unencrypted ()) +return __phys_to_dma (dev, phys); +return phys_to_dma (dev, phys); +} + +u64 dma_direct_get_required_mask (struct device *dev) +{ +u64 max_dma =phys_to_dma_direct (dev, (max_pfn -1 ) <<PAGE_SHIFT ); + +return (1ULL << (fls64 (max_dma) -1 )) *2 -1 ; +} +static bool dma_coherent_ok (struct device *dev,phys_addr_t phys,size_t size) { -dma_addr_t addr =force_dma_unencrypted () ? -__phys_to_dma (dev, phys) :phys_to_dma (dev, phys); -return addr + size -1 <= dev->coherent_dma_mask; +return phys_to_dma_direct (dev, phys) + size -1 <= + dev->coherent_dma_mask; } void *dma_direct_alloc_pages(struct device *dev, size_t size,
@@ -296,6 +311,7 @@ const struct dma_map_ops dma_direct_ops = { .unmap_page = dma_direct_unmap_page, .unmap_sg = dma_direct_unmap_sg, #endif + .get_required_mask = dma_direct_get_required_mask, .dma_supported = dma_direct_supported, .mapping_error = dma_direct_mapping_error, .cache_sync = arch_dma_cache_sync,
Signature · 1 line
2.19.0
PATCH 3/5 dma-direct: refine dma_direct_alloc zone selection
In reply to Christoph HellwigWe need to take the DMA offset and encryption bit into account when selecting a zone. User the opportunity to factor out the zone selection into a helper for reuse.
--- kernel/dma/direct.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-)
kernel/dma/direct.c +21 -10
@@ -69,6 +69,22 @@ u64 dma_direct_get_required_mask(struct device *dev)return (1ULL << (fls64 (max_dma) -1 )) *2 -1 ; } +static gfp_t __dma_direct_optimal_gfp_mask (struct device *dev,u64 dma_mask, +u64 *phys_mask) +{ +if (force_dma_unencrypted ()) + *phys_mask =__dma_to_phys (dev, dma_mask); +else + *phys_mask =dma_to_phys (dev, dma_mask); + +/* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */ +if (*phys_mask <=DMA_BIT_MASK (ARCH_ZONE_DMA_BITS )) +return GFP_DMA ; +if (*phys_mask <=DMA_BIT_MASK (32 )) +return GFP_DMA32 ; +return 0 ; +} +static bool dma_coherent_ok (struct device *dev,phys_addr_t phys,size_t size) { return phys_to_dma_direct(dev, phys) + size - 1 <=
@@ -81,17 +97,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,unsigned int count =PAGE_ALIGN (size) >>PAGE_SHIFT ;int page_order =get_order (size);struct page *page =NULL ; +u64 phys_mask;void *ret;/* we always manually zero the memory once we are done: */ gfp &= ~__GFP_ZERO; - -/* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */ -if (dev->coherent_dma_mask <=DMA_BIT_MASK (ARCH_ZONE_DMA_BITS )) - gfp |=GFP_DMA ; -if (dev->coherent_dma_mask <=DMA_BIT_MASK (32 ) && !(gfp &GFP_DMA )) - gfp |=GFP_DMA32 ; - + gfp |=__dma_direct_optimal_gfp_mask (dev, dev->coherent_dma_mask, + &phys_mask); again:/* CMA can be used only in the context which permits sleeping */ if (gfpflags_allow_blocking (gfp)) {
@@ -110,15 +122,14 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, page =NULL ;if (IS_ENABLED (CONFIG_ZONE_DMA32 ) && - dev->coherent_dma_mask <DMA_BIT_MASK (64 ) && + phys_mask <DMA_BIT_MASK (64 ) && !(gfp & (GFP_DMA32 |GFP_DMA ))) { gfp |=GFP_DMA32 ; goto again; }if (IS_ENABLED (CONFIG_ZONE_DMA ) && - dev->coherent_dma_mask <DMA_BIT_MASK (32 ) && - !(gfp &GFP_DMA )) { + phys_mask <DMA_BIT_MASK (32 ) && !(gfp &GFP_DMA )) { gfp = (gfp & ~GFP_DMA32 ) |GFP_DMA ; goto again; }
Signature · 1 line
2.19.0
PATCH 4/5 dma-direct: implement complete bus_dma_mask handling
In reply to Christoph HellwigInstead of rejecting devices with a too small bus_dma_mask we can handle by taking the bus dma_mask into account for allocations and bounce buffering decisions.
--- include/linux/dma-direct.h | 3 ++- kernel/dma/direct.c | 21 +++++++++++---------- 2 files changed, 13 insertions(+), 11 deletions(-)
include/linux/dma-direct.h +2 -1
@@ -27,7 +27,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)if (!dev->dma_mask)return false; - return addr + size - 1 <= *dev->dma_mask; +return addr + size -1 <= + min_not_zero(*dev->dma_mask, dev->bus_dma_mask); }#endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
kernel/dma/direct.c +11 -10
@@ -44,10 +44,11 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,return false; } -if (*dev->dma_mask >=DMA_BIT_MASK (32 )) { +if (*dev->dma_mask >=DMA_BIT_MASK (32 ) || dev->bus_dma_mask) {dev_err (dev, -"%s: overflow %pad+%zu of device mask %llx\n" , - caller, &dma_addr, size, *dev->dma_mask); +"%s: overflow %pad+%zu of device mask %llx bus mask %llx\n" , + caller, &dma_addr, size, + *dev->dma_mask, dev->bus_dma_mask); }return false; }
@@ -66,12 +67,18 @@ u64 dma_direct_get_required_mask(struct device *dev) {u64 max_dma =phys_to_dma_direct (dev, (max_pfn -1 ) <<PAGE_SHIFT ); +if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma) + max_dma = dev->bus_dma_mask; +return (1ULL << (fls64 (max_dma) -1 )) *2 -1 ; }static gfp_t __dma_direct_optimal_gfp_mask (struct device *dev,u64 dma_mask,u64 *phys_mask) { +if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask) + dma_mask = dev->bus_dma_mask; +if (force_dma_unencrypted ()) *phys_mask =__dma_to_phys (dev, dma_mask);else
@@ -88,7 +95,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,static bool dma_coherent_ok (struct device *dev,phys_addr_t phys,size_t size) {return phys_to_dma_direct (dev, phys) + size -1 <= - dev->coherent_dma_mask; +min_not_zero (dev->coherent_dma_mask, dev->bus_dma_mask); } void *dma_direct_alloc_pages(struct device *dev, size_t size,
@@ -292,12 +299,6 @@ int dma_direct_supported(struct device *dev, u64 mask)if (mask <phys_to_dma (dev,DMA_BIT_MASK (32 )))return 0 ;#endif -/* -* Upstream PCI/PCIe bridges or SoC interconnects may not carry -* as many DMA address bits as the device itself supports. -*/ -if (dev->bus_dma_mask && mask > dev->bus_dma_mask) -return 0 ;return 1 ; }
Signature · 1 line
2.19.0
PATCH 5/5 dma-direct: always allow dma mask <= physiscal memory size
In reply to Christoph HellwigThis way an architecture with less than 4G of RAM can support dma_mask smaller than 32-bit without a ZONE_DMA. Apparently that is a common case on powerpc.
--- kernel/dma/direct.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-)
kernel/dma/direct.c +16 -12
@@ -284,21 +284,25 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,return nents; } +/* +* Because 32-bit DMA masks are so common we expect every architecture to be +* able to satisfy them - either by not supporting more physical memory, or by +* providing a ZONE_DMA32. If neither is the case, the architecture needs to +* use an IOMMU instead of the direct mapping. +*/ int dma_direct_supported (struct device *dev,u64 mask) { -#ifdef CONFIG_ZONE_DMA -if (mask <phys_to_dma (dev,DMA_BIT_MASK (ARCH_ZONE_DMA_BITS ))) -return 0 ; -#else -/* -* Because 32-bit DMA masks are so common we expect every architecture -* to be able to satisfy them - either by not supporting more physical -* memory, or by providing a ZONE_DMA32. If neither is the case, the -* architecture needs to use an IOMMU instead of the direct mapping. -*/ -if (mask <phys_to_dma (dev,DMA_BIT_MASK (32 ))) +u64 min_mask; + +if (IS_ENABLED (CONFIG_ZONE_DMA )) + min_mask =DMA_BIT_MASK (ARCH_ZONE_DMA_BITS ); +else + min_mask =DMA_BIT_MASK (32 ); + + min_mask =min_t (u64, min_mask, (max_pfn -1 ) <<PAGE_SHIFT ); + +if (mask >=phys_to_dma (dev, min_mask))return 0 ; -#endif return 1 ; }
Signature · 1 line
2.19.0
Re: [PATCH 5/5] dma-direct: always allow dma mask <= physiscal memory size
Quoted 42 lines · Christoph Hellwig
This way an architecture with less than 4G of RAM can support
dma_masksmaller than 32-bit without aZONE_DMA. Apparently that is a common case on powerpc.Signed-off-by Christoph Hellwig <[email protected]>Reviewed-by Robin Murphy <[email protected]>--- kernel/dma/direct.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-)kernel/dma/direct.c +10
-11@@ -284,21 +284,25 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,return nents; } +/* +* Because 32-bit DMA masks are so common we expect every architecture to be +* able to satisfy them - either by not supporting more physical memory, or by +* providing a ZONE_DMA32. If neither is the case, the architecture needs to +* use an IOMMU instead of the direct mapping. +*/ int dma_direct_supported (struct device *dev,u64 mask) { -#ifdef CONFIG_ZONE_DMA -if (mask <phys_to_dma (dev,DMA_BIT_MASK (ARCH_ZONE_DMA_BITS ))) -return 0 ; -#else -/* -* Because 32-bit DMA masks are so common we expect every architecture -* to be able to satisfy them - either by not supporting more physical -* memory, or by providing a ZONE_DMA32. If neither is the case, the -* architecture needs to use an IOMMU instead of the direct mapping. -*/ -if (mask <phys_to_dma (dev,DMA_BIT_MASK (32 ))) +u64 min_mask; + +if (IS_ENABLED (CONFIG_ZONE_DMA )) + min_mask =DMA_BIT_MASK (ARCH_ZONE_DMA_BITS );
kernel/dma/direct.c int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, · line 307
Quoted 10 lines
kernel/dma/direct.c +6
-1+else + min_mask =DMA_BIT_MASK (32 ); + + min_mask =min_t (u64, min_mask, (max_pfn -1 ) <<PAGE_SHIFT ); + +if (mask >=phys_to_dma (dev, min_mask))return 0 ; -#endif return 1 ; }
So I believe I have run into the same issue that Guenter reported. On an x86_64 system w/ Intel IOMMU. I wasn't able to complete boot and all probe attempts for various devices were failing with -EIO errors.
I believe the last mask check should be "if (mask < phys_to_dma(dev, min_mask))" not a ">=" check.
- Alex
Re: [PATCH 5/5] dma-direct: always allow dma mask <= physiscal memory size
Quoted 25 lines · Alexander Duyck
Quoted 10 lines
kernel/dma/direct.c +4
-6-* Because 32-bit DMA masks are so common we expect every architecture -* to be able to satisfy them - either by not supporting more physical -* memory, or by providing a ZONE_DMA32. If neither is the case, the -* architecture needs to use an IOMMU instead of the direct mapping. -*/ -if (mask <phys_to_dma (dev,DMA_BIT_MASK (32 ))) +u64 min_mask; + +if (IS_ENABLED (CONFIG_ZONE_DMA )) + min_mask =DMA_BIT_MASK (ARCH_ZONE_DMA_BITS );kernel/dma/direct.c int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, · line 307
Quoted 10 lines
kernel/dma/direct.c +6
-1+else + min_mask =DMA_BIT_MASK (32 ); + + min_mask =min_t (u64, min_mask, (max_pfn -1 ) <<PAGE_SHIFT ); + +if (mask >=phys_to_dma (dev, min_mask))return 0 ; -#endif return 1 ; }So I believe I have run into the same issue that Guenter reported. On an
x86_64system w/ Intel IOMMU. I wasn't able to complete boot and all probe attempts for various devices were failing with-EIOerrors.
Quoted 2 lines
I believe the last mask check should be "if (mask <
phys_to_dma(dev, min_mask))" not a ">=" check.
Right, that test is backwards. I needed to change it here too (powermac with the rest of the powerpc series).
Cheers,
Ben.
Re: [PATCH 5/5] dma-direct: always allow dma mask <= physiscal memory size
Quoted 27 lines · Benjamin Herrenschmidt
Quoted 25 lines · Alexander Duyck
Quoted 10 lines
kernel/dma/direct.c +4
-6-* Because 32-bit DMA masks are so common we expect every architecture -* to be able to satisfy them - either by not supporting more physical -* memory, or by providing a ZONE_DMA32. If neither is the case, the -* architecture needs to use an IOMMU instead of the direct mapping. -*/ -if (mask <phys_to_dma (dev,DMA_BIT_MASK (32 ))) +u64 min_mask; + +if (IS_ENABLED (CONFIG_ZONE_DMA )) + min_mask =DMA_BIT_MASK (ARCH_ZONE_DMA_BITS );kernel/dma/direct.c int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, · line 307
Quoted 10 lines
kernel/dma/direct.c +6
-1+else + min_mask =DMA_BIT_MASK (32 ); + + min_mask =min_t (u64, min_mask, (max_pfn -1 ) <<PAGE_SHIFT ); + +if (mask >=phys_to_dma (dev, min_mask))return 0 ; -#endif return 1 ; }So I believe I have run into the same issue that Guenter reported. On an
x86_64system w/ Intel IOMMU. I wasn't able to complete boot and all probe attempts for various devices were failing with-EIOerrors.
Quoted 10 lines
Quoted 2 lines
I believe the last mask check should be "if (mask <
phys_to_dma(dev, min_mask))" not a ">=" check.Right, that test is backwards. I needed to change it here too (powermac with the rest of the powerpc series).
Cheers,
Ben.
Hi, I'm working on a MIPS64 soc with PCIe root complex on it, and it appears that this series of patches are causing all PCI drivers that request 64bit mask to fail with -5.
It's broken in 4.19. However, I just checked, it working on master. We may need to backport a couple of patches to 4.19. I'm not sure though which patches should be backported as there were at least 10 patches resolving this dma_direct area recently. Christoph, Robin.
Can we ask Greg to backport all these changes ? What do you think ?
Thanks,
Ramon.
Robin Murphy
reviewerRe: [PATCH 5/5] dma-direct: always allow dma mask <= physiscal memory size
Quoted 40 lines · Ramon Fried
Quoted 27 lines · Benjamin Herrenschmidt
Quoted 25 lines · Alexander Duyck
Quoted 10 lines
kernel/dma/direct.c +4
-6-* Because 32-bit DMA masks are so common we expect every architecture -* to be able to satisfy them - either by not supporting more physical -* memory, or by providing a ZONE_DMA32. If neither is the case, the -* architecture needs to use an IOMMU instead of the direct mapping. -*/ -if (mask <phys_to_dma (dev,DMA_BIT_MASK (32 ))) +u64 min_mask; + +if (IS_ENABLED (CONFIG_ZONE_DMA )) + min_mask =DMA_BIT_MASK (ARCH_ZONE_DMA_BITS );kernel/dma/direct.c int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, · line 307
Quoted 10 lines
kernel/dma/direct.c +6
-1+else + min_mask =DMA_BIT_MASK (32 ); + + min_mask =min_t (u64, min_mask, (max_pfn -1 ) <<PAGE_SHIFT ); + +if (mask >=phys_to_dma (dev, min_mask))return 0 ; -#endif return 1 ; }So I believe I have run into the same issue that Guenter reported. On an
x86_64system w/ Intel IOMMU. I wasn't able to complete boot and all probe attempts for various devices were failing with-EIOerrors.Quoted 10 lines
Quoted 2 lines
I believe the last mask check should be "if (mask <
phys_to_dma(dev, min_mask))" not a ">=" check.Right, that test is backwards. I needed to change it here too (powermac with the rest of the powerpc series).
Cheers,
Ben.
Quoted 9 lines
Hi, I'm working on a MIPS64 soc with PCIe root complex on it, and it appears that this series of patches are causing all PCI drivers that request 64bit mask to fail with -5.
It's broken in 4.19. However, I just checked, it working on master. We may need to backport a couple of patches to 4.19. I'm not sure though which patches should be backported as there were at least 10 patches resolving thisdma_directarea recently. Christoph, Robin.
Can we ask Greg to backport all these changes ? What do you think ?
As far as I'm aware, the only real issue in 4.19 was my subtle breakage around setting bus_dma_mask - that's fixed by 6778be4e5209, which according to my inbox got picked up by autosel for 4.19 stable last week.
Robin.
Re: [PATCH 5/5] dma-direct: always allow dma mask <= physiscal memory size
Quoted 52 lines · Robin Murphy
Quoted 40 lines · Ramon Fried
Quoted 27 lines · Benjamin Herrenschmidt
Quoted 25 lines · Alexander Duyck
Quoted 10 lines
kernel/dma/direct.c +4
-6-* Because 32-bit DMA masks are so common we expect every architecture -* to be able to satisfy them - either by not supporting more physical -* memory, or by providing a ZONE_DMA32. If neither is the case, the -* architecture needs to use an IOMMU instead of the direct mapping. -*/ -if (mask <phys_to_dma (dev,DMA_BIT_MASK (32 ))) +u64 min_mask; + +if (IS_ENABLED (CONFIG_ZONE_DMA )) + min_mask =DMA_BIT_MASK (ARCH_ZONE_DMA_BITS );kernel/dma/direct.c int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, · line 307
Quoted 10 lines
kernel/dma/direct.c +6
-1+else + min_mask =DMA_BIT_MASK (32 ); + + min_mask =min_t (u64, min_mask, (max_pfn -1 ) <<PAGE_SHIFT ); + +if (mask >=phys_to_dma (dev, min_mask))return 0 ; -#endif return 1 ; }So I believe I have run into the same issue that Guenter reported. On an
x86_64system w/ Intel IOMMU. I wasn't able to complete boot and all probe attempts for various devices were failing with-EIOerrors.Quoted 10 lines
Quoted 2 lines
I believe the last mask check should be "if (mask <
phys_to_dma(dev, min_mask))" not a ">=" check.Right, that test is backwards. I needed to change it here too (powermac with the rest of the powerpc series).
Cheers,
Ben.Quoted 9 lines
Hi, I'm working on a MIPS64 soc with PCIe root complex on it, and it appears that this series of patches are causing all PCI drivers that request 64bit mask to fail with -5.
It's broken in 4.19. However, I just checked, it working on master. We may need to backport a couple of patches to 4.19. I'm not sure though which patches should be backported as there were at least 10 patches resolving thisdma_directarea recently. Christoph, Robin.
Can we ask Greg to backport all these changes ? What do you think ?
Quoted 5 lines
As far as I'm aware, the only real issue in 4.19 was my subtle breakage around setting
bus_dma_mask- that's fixed by6778be4e5209, which according to my inbox got picked up by autosel for 4.19 stable last week.Robin.
Yep, 6778be4e5209 fixes the issue.
Thanks a lot !
Ramon.
FYI, I've pulled this into the dma-mapping tree to make forward progress. All but oatch 4 had formal ACKs, and for that one Robin was fine even without and explicit ack. I'll also send a patch to better document the zone selection as it confuses even well versed people like Ben.
Quoted 5 lines · Christoph Hellwig
FYI, I've pulled this into the dma-mapping tree to make forward progress. All but oatch 4 had formal ACKs, and for that one Robin was fine even without and explicit ack. I'll also send a patch to better document the zone selection as it confuses even well versed people like Ben.
Thanks. I"ll try to dig out some older systems to test.
Cheers,
Ben.