search for: memory_type

Hi, Here are patches which implement the support for OpenCL kernel input parameters we discussed. They also add the tgsi parsing bits for adding support for global / local mem, but no implementation yet. Regards, Hans

...iliary/tgsi/tgsi_build.c > +++ b/src/gallium/auxiliary/tgsi/tgsi_build.c > @@ -111,7 +111,7 @@ tgsi_default_declaration( void ) > declaration.Local = 0; > declaration.Array = 0; > declaration.Atomic = 0; > - declaration.Shared = 0; > + declaration.MemType = TGSI_MEMORY_TYPE_GLOBAL; > declaration.Padding = 0; > > return declaration; > @@ -128,7 +128,7 @@ tgsi_build_declaration( > unsigned local, > unsigned array, > unsigned atomic, > - unsigned shared, > + unsigned mem_type, > struct tgsi_header *header ) >...

When support for decl.Atomic and .Shared was added, tgsi_build_declaration was not updated to propagate these properly. Signed-off-by: Hans de Goede <hdegoede at redhat.com> Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> --- Changes in v2: -Add Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> --- src/gallium/auxiliary/tgsi/tgsi_build.c | 6 ++++++ 1 file changed, 6

...108ade 100644 --- a/src/gallium/auxiliary/tgsi/tgsi_build.c +++ b/src/gallium/auxiliary/tgsi/tgsi_build.c @@ -111,7 +111,7 @@ tgsi_default_declaration( void ) declaration.Local = 0; declaration.Array = 0; declaration.Atomic = 0; - declaration.Shared = 0; + declaration.MemType = TGSI_MEMORY_TYPE_GLOBAL; declaration.Padding = 0; return declaration; @@ -128,7 +128,7 @@ tgsi_build_declaration( unsigned local, unsigned array, unsigned atomic, - unsigned shared, + unsigned mem_type, struct tgsi_header *header ) { struct tgsi_declaration declaration; @@ -146,7...

...drivers to use an access mechanism for parameter reads which matches with the upload method. Signed-off-by: Hans de Goede <hdegoede at redhat.com> Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> --- Changes in v2: -Drop mention of GLSL global / GLSL local from comments -Change TGSI_MEMORY_TYPE_LOCAL to TGSI_MEMORY_TYPE_PRIVATE -Add Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> --- src/gallium/auxiliary/tgsi/tgsi_build.c | 8 +++---- src/gallium/auxiliary/tgsi/tgsi_dump.c | 9 ++++++-- src/gallium/auxiliary/tgsi/tgsi_text.c | 14 ++++++++++-...

...t; +++ b/src/gallium/auxiliary/tgsi/tgsi_build.c >> @@ -111,7 +111,7 @@ tgsi_default_declaration( void ) >> declaration.Local = 0; >> declaration.Array = 0; >> declaration.Atomic = 0; >> - declaration.Shared = 0; >> + declaration.MemType = TGSI_MEMORY_TYPE_GLOBAL; >> declaration.Padding = 0; >> >> return declaration; >> @@ -128,7 +128,7 @@ tgsi_build_declaration( >> unsigned local, >> unsigned array, >> unsigned atomic, >> - unsigned shared, >> + unsigned mem_type, &gt...

Signed-off-by: Francisco Jerez <currojerez at riseup.net> --- drivers/gpu/drm/nouveau/nv04_crtc.c | 37 +++++++++++++++++++++------------- 1 files changed, 23 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nv04_crtc.c b/drivers/gpu/drm/nouveau/nv04_crtc.c index 2ab9f30..0a5cfc1 100644 --- a/drivers/gpu/drm/nouveau/nv04_crtc.c +++ b/drivers/gpu/drm/nouveau/nv04_crtc.c

...mp; 0xffff) == 0x01f0 /*CHIPSET_NFORCE2*/) { uint32_t type; + int domain = pci_domain_nr(dev->pdev->bus); - pci_read_config_dword(pci_get_bus_and_slot(0, 1), 0x7c, &type); + pci_read_config_dword(pci_get_domain_bus_and_slot(domain, 0, 1), + 0x7c, &type); sim_data.memory_type = (type >> 12) & 1; sim_data.memory_width = 64; diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c index b985990..0c9bdf0 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c @@ -216,12 +216,15 @@ { st...

...mp; 0xffff) == 0x01f0 /*CHIPSET_NFORCE2*/) { uint32_t type; + int domain = pci_domain_nr(dev->pdev->bus); - pci_read_config_dword(pci_get_bus_and_slot(0, 1), 0x7c, &type); + pci_read_config_dword(pci_get_domain_bus_and_slot(domain, 0, 1), + 0x7c, &type); sim_data.memory_type = (type >> 12) & 1; sim_data.memory_width = 64; diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c index b985990..0c9bdf0 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c @@ -216,12 +216,15 @@ { st...

...l = pci_p2pdma_percpu_kill; addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f0628660d541..5f7f40875b35 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -63,39 +63,40 @@ enum memory_type { MEMORY_DEVICE_PCI_P2PDMA, }; -/* - * Additional notes about MEMORY_DEVICE_PRIVATE may be found in - * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief - * explanation in include/linux/memory_hotplug.h. - * - * The page_free() callback is called once the page refcount r...

...page) <= 1; > + return page_ref_count(page) == 0; > } > > #endif > diff --git a/include/linux/memremap.h b/include/linux/memremap.h > index e5862746751b..f9224f88e4cd 100644 > --- a/include/linux/memremap.h > +++ b/include/linux/memremap.h > @@ -65,9 +65,10 @@ enum memory_type { > > struct dev_pagemap_ops { > /* > - * Called once the page refcount reaches 1. (ZONE_DEVICE pages never > - * reach 0 refcount unless there is a refcount bug. This allows the > - * device driver to implement its own memory management.) > + * Called once the page r...

...pci_p2pdma_percpu_cleanup; addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1732dea030b2..1cdcfd595770 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -63,41 +63,45 @@ enum memory_type { MEMORY_DEVICE_PCI_P2PDMA, }; -/* - * Additional notes about MEMORY_DEVICE_PRIVATE may be found in - * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief - * explanation in include/linux/memory_hotplug.h. - * - * The page_free() callback is called once the page refcount r...

...System RAM i.e. DMA + * coherent and supports page pinning. In contrast to + * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax + * character device. + * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { + /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_FS_DAX, + MEMORY_DEVICE_DEVDAX, MEMORY_DEVICE_PCI_P2PDMA, }; diff --git a/kernel/memremap.c b/kernel/memremap.c index 6e1970719dc2..abda62d1e5a3 100644 --- a/kernel/memremap.c +++ b/kernel/m...

...* @ops: method table + * @owner: an opaque pointer identifying the entity that manages this + * instance. Used by various helpers to make sure that no + * foreign ZONE_DEVICE memory is accessed. */ struct dev_pagemap { struct vmem_altmap altmap; @@ -113,6 +116,7 @@ struct dev_pagemap { enum memory_type type; unsigned int flags; const struct dev_pagemap_ops *ops; + void *owner; }; static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) diff --git a/mm/memremap.c b/mm/memremap.c index 09b5b7adc773..9b2c97ceb775 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -181,6 +181,...

...@@ struct nv_sim_state { (dev->pdev->device & 0xffff) == 0x01f0 /*CHIPSET_NFORCE2*/) { uint32_t type; - pci_read_config_dword(pci_get_bus_and_slot(0, 1), 0x7c, &type); + pci_read_config_dword(pci_get_domain_bus_and_slot(0, 0, 1), + 0x7c, &type); sim_data.memory_type = (type >> 12) & 1; sim_data.memory_width = 64; diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c index b985990..4b35093 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c @@ -221,7 +221,8 @@ (de...

...void (*page_free)(struct page *page, void *data); + void (*page_free)(struct page *page); /* * Transition the percpu_ref in struct dev_pagemap to the dead state. @@ -99,7 +99,6 @@ struct dev_pagemap { struct resource res; struct percpu_ref *ref; struct device *dev; - void *data; enum memory_type type; u64 pci_p2pdma_bus_offset; const struct dev_pagemap_ops *ops; diff --git a/kernel/memremap.c b/kernel/memremap.c index 7167e717647d..5c94ad4f5783 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -337,7 +337,7 @@ void __put_devmap_managed_page(struct page *page) mem_cgroup_un...

...mp; 0xffff) == 0x01f0 /*CHIPSET_NFORCE2*/) { uint32_t type; + u32 domain = pci_domain_nr(dev->pdev->bus); - pci_read_config_dword(pci_get_bus_and_slot(0, 1), 0x7c, &type); + pci_read_config_dword(pci_get_domain_bus_and_slot(domain, 0, 1), + 0x7c, &type); sim_data.memory_type = (type >> 12) & 1; sim_data.memory_width = 64; diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c index b985990..8806b1b 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c @@ -216,12 +216,15 @@ { st...

.../) { > uint32_t type; > + int domain = pci_domain_nr(dev->pdev->bus); > > - pci_read_config_dword(pci_get_bus_and_slot(0, 1), 0x7c, &type); > + pci_read_config_dword(pci_get_domain_bus_and_slot(domain, 0, 1), > + 0x7c, &type); > > sim_data.memory_type = (type >> 12) & 1; > sim_data.memory_width = 64; > diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c > index b985990..0c9bdf0 100644 > --- a/drivers/gpu/drm/nouveau/dispnv04/hw.c > +++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c >...

...* @ops: method table + * @owner: an opaque pointer identifying the entity that manages this + * instance. Used by various helpers to make sure that no + * foreign ZONE_DEVICE memory is accessed. */ struct dev_pagemap { struct vmem_altmap altmap; @@ -113,6 +116,7 @@ struct dev_pagemap { enum memory_type type; unsigned int flags; const struct dev_pagemap_ops *ops; + void *owner; }; static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 72120061b7d4..4bbd8d732e53 100644 --- a/include/linux/migrate.h +++ b...

...get_page(page); > lock_page(page); > return page; > } > diff --git a/include/linux/memremap.h b/include/linux/memremap.h > index 4e9c738f4b31..7dd9802d2612 100644 > --- a/include/linux/memremap.h > +++ b/include/linux/memremap.h > @@ -67,9 +67,9 @@ enum memory_type { > > struct dev_pagemap_ops { > /* > - * Called once the page refcount reaches 1. (ZONE_DEVICE pages never > - * reach 0 refcount unless there is a refcount bug. This allows the > - * device driver to implement its own memory management.) > +...