Setting register to force ordering to prevent read/write or write/read
hazards for un-cached modes.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c| 8
.../gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h| 2 ++
2 files changed, 10
Setting register to force ordering to prevent read/write or write/read
hazards for un-cached modes.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c| 22 +--
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c| 8 +++
.../include/asic_reg/gc
Split SVM ranges that have been mapped into 2MB page table entries,
require to be remap in case the split has happened in a non-aligned
VA.
[WHY]:
This condition causes the 2MB page table entries be split into 4KB
PTEs.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 43
Split SVM ranges that have been mapped into 2MB page table entries,
require to be remap in case the split has happened in a non-aligned
VA.
[WHY]:
This condition causes the 2MB page table entries be split into 4KB
PTEs.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 45
Interrupt sq data bits were not taken properly from contextid0 and contextid1.
Use macro KFD_CONTEXT_ID_GET_SQ_INT_DATA instead.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd
if hmm_range_get_pages returns EBUSY error during
svm_range_validate_and_map, within the context of a page fault
interrupt. This should retry through svm_range_restore_pages
callback. Therefore we treat this as EAGAIN error instead, and defer
it to restore pages fallback.
Signed-off-by: Alex
This causes error compilation if CONFIG_DYNAMIC_DEBUG_CORE is not
defined.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index a69994ff1c2f
DMA address reference within svm_ranges should be unmapped only after
the memory has been released from the system. In case of range
splitting, the DMA address information should be copied to the
corresponding range after this has split. But leaving dma mapping
intact.
Signed-off-by: Alex Sierra
DMA address reference within svm_ranges should be unmapped only after
the memory has been released from the system. In case of range
splitting, the DMA address information should be copied to the
corresponding range after this has split. But leaving dma mapping
intact.
Signed-off-by: Alex Sierra
to print svm_range_debug_dump debug traces.
Signed-off-by: Alex Sierra
Tested-by: Alex Sierra
Signed-off-by: Philip Yang
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd
to print svm_range_debug_dump debug traces.
Signed-off-by: Alex Sierra
Tested-by: Alex Sierra
Signed-off-by: Philip Yang
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_svm.h | 3 +++
2 files changed, 4 insertions(+), 1 deletion
svm_range_debug_dump should not be called at all when dynamic debug
is disabled to avoid iterating over SVM lists. This could drop
performance, specially with big number of SVM ranges.
Signed-off-by: Alex Sierra
Signed-off-by: Philip Yang
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 6 --
1
This flag determines whether the host possesses coherent access to
the memory of the device.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
b/drivers/gpu/drm/amd/amdkfd
This flag determines whether the host possesses coherent access to
the memory of the device.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
b/drivers/gpu/drm/amd/amdkfd
during the retry.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 3 ++-
drivers/gpu/drm/amd/amdkfd/kfd_svm.h | 1 +
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index fcfde9140bce
during the retry.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 12 +++-
include/uapi/linux/kfd_ioctl.h | 2 ++
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index
Accomplish this by reading the seq number right away instead of sleep
for 5us. There are certain cases where the fence is ready almost
immediately. Sleep number granularity was also reduced as the majority
of the kiq tlb flush takes between 2us to 6us.
Signed-off-by: Alex Sierra
---
drivers/gpu
[Why] Devices with CPU XGMI iolink do not support PCIe peer access.
Signed-off-by: Alex Sierra
Acked-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu
[Why] Devices with CPU XGMI iolink do not support PCIe peer access.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu
uot;mm/gup: migrate device coherent pages when pinning instead of failing"
with changes based on David Hildenbrand comments.
- Replace moving page zone helpers into new header-specific file.
Instead, those were moved to mmzone.h.
Patch "mm: move page zone helpers from mm.h to mmzone.h"
new ioctl cmd added to query zone device type. This will be
used once the test_hmm adds zone device coherent type.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
lib/test_hmm.c | 11 +--
lib/test_hmm_uapi.h
: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 4 ++
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 23 ---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 60 +--
3 files changed, 60 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
Add two more parameters to set spm_addr_dev0 & spm_addr_dev1
addresses. These two parameters configure the start SP
addresses for each device in test_hmm driver.
Consequently, this configures zone device type as coherent.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alis
.
Also, MIGRATE_VMA_SELECT_DEVICE_COHERENT flag is selected for
coherent type case during migration to device.
Signed-off-by: Alex Sierra
Reviewed-by: Felix Kuehling
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 34 +++-
1 file changed, 21
ently don't expect ZONE_DEVICE pages,
however, with DEVICE_COHERENT we might now return ZONE_DEVICE. Check
for ZONE_DEVICE pages in applicable users of follow_page() as well.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling (v2)
Reviewed-by: Alistair Popple (v6)
---
fs/proc/task_mmu.c |
are duplicated directly from device
memory.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
---
tools/testing/selftests/vm/hmm-tests.c | 80 ++
1 file changed, 80 insertions(+)
diff --git a/tools/testing/selftests/vm/hmm-tests.c
b/tools/testing/selftests/vm/hmm
From: Alistair Popple
Currently any attempts to pin a device coherent page will fail. This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.
However this is no reason to fail pinning of these pages.
The intention is to test hmm device coherent type under different get
user pages paths. Also, test gup with FOLL_LONGTERM flag set in
device coherent pages. These pages should get migrated back to system
memory.
Signed-off-by: Alex Sierra
Reviewed-by: Alistair Popple
---
tools/testing
In order to configure device coherent in test_hmm, two module parameters
should be passed, which correspond to the SP start address of each
device (2) spm_addr_dev0 & spm_addr_dev1. If no parameters are passed,
private device type is configured.
Signed-off-by: Alex Sierra
Acked-by: F
e easily accessed from user
space through /dev/hmm_mirror. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by:
.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
[hch: rebased ontop of the refcount changes,
removed is_dev_private_or_coherent_page]
Signed-off-by: Christoph Hellwig
Acked-by: David Hildenbrand
---
include/linux/memremap.h | 19 +++
include
migrate_ping_pong test case
added to test explicit migration from device to sys memory for both
private and coherent zone types.
Helpers to migrate from device to sys memory and vicerversa
were also added.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
Signed-off-by
is_pinnable_page() and folio_is_pinnable() were renamed to
is_longterm_pinnable_page() and folio_is_longterm_pinnable()
respectively. These functions are used in the FOLL_LONGTERM flag
context.
Signed-off-by: Alex Sierra
Reviewed-by: David Hildenbrand
---
include/linux/mm.h | 8
mm
[WHY]
It makes more sense to have these helpers in zone specific header
file, rather than the generic mm.h
Signed-off-by: Alex Sierra
---
include/linux/memremap.h | 2 +-
include/linux/mm.h | 78 ---
include/linux/mmzone.h | 80
This case is used to migrate pages from device memory, back to system
memory. Device coherent type memory is cache coherent from device and CPU
point of view.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
Reviewed-by: David
[WHY]
It makes more sense to have these helpers in zone specific header
file, rather than the generic mm.h
Signed-off-by: Alex Sierra
---
include/linux/memremap.h | 2 +-
include/linux/mm.h | 78 ---
include/linux/mmzone.h | 80
This keeps track of kfd system mem used and kfd ttm mem used.
Signed-off-by: Alex Sierra
Reviewed-by: Philip Yang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 3 +++
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 19 +++
drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 4 ++
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 25
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 60 +--
3 files changed, 60 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
need to
track it any more.
Signed-off-by: Alex Sierra
Reviewed-by: Philip Yang
Reviewed-by: Felix Kuehling
Acked-by: Christian König
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 60 ++-
1 file changed, 17 insertions(+), 43 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
are duplicated directly from device
memory.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
---
tools/testing/selftests/vm/hmm-tests.c | 80 ++
1 file changed, 80 insertions(+)
diff --git a/tools/testing/selftests/vm/hmm-tests.c
b/tools/testing/selftests/vm/hmm
migrate_ping_pong test case
added to test explicit migration from device to sys memory for both
private and coherent zone types.
Helpers to migrate from device to sys memory and vicerversa
were also added.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
Signed-off-by
The intention is to test hmm device coherent type under different get
user pages paths. Also, test gup with FOLL_LONGTERM flag set in
device coherent pages. These pages should get migrated back to system
memory.
Signed-off-by: Alex Sierra
Reviewed-by: Alistair Popple
---
tools/testing
In order to configure device coherent in test_hmm, two module parameters
should be passed, which correspond to the SP start address of each
device (2) spm_addr_dev0 & spm_addr_dev1. If no parameters are passed,
private device type is configured.
Signed-off-by: Alex Sierra
Acked-by: F
Add two more parameters to set spm_addr_dev0 & spm_addr_dev1
addresses. These two parameters configure the start SP
addresses for each device in test_hmm driver.
Consequently, this configures zone device type as coherent.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alis
e easily accessed from user
space through /dev/hmm_mirror. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by:
new ioctl cmd added to query zone device type. This will be
used once the test_hmm adds zone device coherent type.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
lib/test_hmm.c | 11 +--
lib/test_hmm_uapi.h
From: Alistair Popple
Currently any attempts to pin a device coherent page will fail. This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.
However this is no reason to fail pinning of these pages.
.
Also, MIGRATE_VMA_SELECT_DEVICE_COHERENT flag is selected for
coherent type case during migration to device.
Signed-off-by: Alex Sierra
Reviewed-by: Felix Kuehling
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 34 +++-
1 file changed, 21
From: Alistair Popple
migrate_vma_setup() checks that a valid vma is passed so that the page
tables can be walked to find the pfns associated with a given address
range. However in some cases the pfns are already known, such as when
migrating device coherent pages during pin_user_pages() meaning
is_pinnable_page() and folio_is_pinnable() were renamed to
is_longterm_pinnable_page() and folio_is_longterm_pinnable()
respectively. These functions are used in the FOLL_LONGTERM flag
context.
Signed-off-by: Alex Sierra
---
include/linux/mm.h | 8
mm/gup.c | 4 ++--
mm
ently don't expect ZONE_DEVICE pages,
however, with DEVICE_COHERENT we might now return ZONE_DEVICE. Check
for ZONE_DEVICE pages in applicable users of follow_page() as well.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling (v2)
Reviewed-by: Alistair Popple (v6)
---
fs/proc/task_mmu.c |
This case is used to migrate pages from device memory, back to system
memory. Device coherent type memory is cache coherent from device and CPU
point of view.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
Reviewed-by: David
[WHY]
Have a cleaner way to expose all page zone helpers in one header
file, rather than split them between mm.h and memremap.h files.
Signed-off-by: Alex Sierra
---
drivers/infiniband/core/rw.c | 1 -
drivers/nvme/target/io-cmd-bdev.c | 1 -
include/linux/memremap.h | 113
.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
[hch: rebased ontop of the refcount changes,
removed is_dev_private_or_coherent_page]
Signed-off-by: Christoph Hellwig
Acked-by: David Hildenbrand
---
include/linux/mm.h| 4 +++-
include/linux
er for LRU pages handling
instead.
v8:
- Add "mm: move page zone helpers into new header-specific file"
patch. The intention is to centralize all page zone helpers and keep
them independent from mm.h and memremap.h.
Alex Sierra (13):
mm: rename is_pinnable_pages to is_longterm_pinn
are duplicated directly from device
memory.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
---
tools/testing/selftests/vm/hmm-tests.c | 80 ++
1 file changed, 80 insertions(+)
diff --git a/tools/testing/selftests/vm/hmm-tests.c
b/tools/testing/selftests/vm/hmm
The intention is to test hmm device coherent type under different get
user pages paths. Also, test gup with FOLL_LONGTERM flag set in
device coherent pages. These pages should get migrated back to system
memory.
Signed-off-by: Alex Sierra
Reviewed-by: Alistair Popple
---
tools/testing
migrate_ping_pong test case
added to test explicit migration from device to sys memory for both
private and coherent zone types.
Helpers to migrate from device to sys memory and vicerversa
were also added.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
Signed-off-by
From: Alistair Popple
migrate_vma_setup() checks that a valid vma is passed so that the page
tables can be walked to find the pfns associated with a given address
range. However in some cases the pfns are already known, such as when
migrating device coherent pages during pin_user_pages() meaning
In order to configure device coherent in test_hmm, two module parameters
should be passed, which correspond to the SP start address of each
device (2) spm_addr_dev0 & spm_addr_dev1. If no parameters are passed,
private device type is configured.
Signed-off-by: Alex Sierra
Acked-by: F
Add two more parameters to set spm_addr_dev0 & spm_addr_dev1
addresses. These two parameters configure the start SP
addresses for each device in test_hmm driver.
Consequently, this configures zone device type as coherent.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alis
new ioctl cmd added to query zone device type. This will be
used once the test_hmm adds zone device coherent type.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
lib/test_hmm.c | 11 +--
lib/test_hmm_uapi.h
.
Also, MIGRATE_VMA_SELECT_DEVICE_COHERENT flag is selected for
coherent type case during migration to device.
Signed-off-by: Alex Sierra
Reviewed-by: Felix Kuehling
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 34 +++-
1 file changed, 21
From: Alistair Popple
Currently any attempts to pin a device coherent page will fail. This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.
However this is no reason to fail pinning of these pages.
e easily accessed from user
space through /dev/hmm_mirror. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by:
xpect LRU pages, are also checked for
device zone pages due to DEVICE_COHERENT type.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling (v2)
Reviewed-by: Alistair Popple (v6)
---
fs/proc/task_mmu.c | 2 +-
mm/huge_memory.c | 2 +-
mm/khugepaged.c| 9 ++---
mm/ksm.c | 6 +++--
This case is used to migrate pages from device memory, back to system
memory. Device coherent type memory is cache coherent from device and CPU
point of view.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
include/linux
is_pinnable_page() and folio_is_pinnable() were renamed to
is_longterm_pinnable_page() and folio_is_longterm_pinnable()
respectively. These functions are used in the FOLL_LONGTERM flag
context.
Signed-off-by: Alex Sierra
---
include/linux/memremap.h | 24
include/linux
.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
[hch: rebased ontop of the refcount changes,
removed is_dev_private_or_coherent_page]
Signed-off-by: Christoph Hellwig
---
include/linux/memremap.h | 22 +-
mm/memcontrol.c | 7
hmm and
selftest/vm/hmm-test.c.
v6:
- Rebase to 5.19.0-rc4
- Rename is_pinnable_page to is_longterm_pinnable_page and add a
coherent device checker.
- Add a new gup test to hmm-test to cover fast pinnable case with
FOLL_LONGTERM.
v7:
- Reorder patch series.
- Remove FOLL_LRU and check on each
This keeps track of kfd system mem used and kfd ttm mem used.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 3 +++
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 19 +++
drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c | 2 ++
3 files changed, 24
: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 4 ++
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 25
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 58 +--
3 files changed, 58 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
need to
track it any more.
Signed-off-by: Alex Sierra
Reviewed-by: Philip Yang
Reviewed-by: Felix Kuehling
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 60 ++-
1 file changed, 17 insertions(+), 43 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
b/d
Add two more parameters to set spm_addr_dev0 & spm_addr_dev1
addresses. These two parameters configure the start SP
addresses for each device in test_hmm driver.
Consequently, this configures zone device type as coherent.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alis
e easily accessed from user
space through /dev/hmm_mirror. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by:
The intention is to test hmm device coherent type under different get
user pages paths. Also, test gup with FOLL_LONGTERM flag set in
device coherent pages. These pages should get migrated back to system
memory.
Signed-off-by: Alex Sierra
Reviewed-by: Alistair Popple
---
tools/testing
migrate_ping_pong test case
added to test explicit migration from device to sys memory for both
private and coherent zone types.
Helpers to migrate from device to sys memory and vicerversa
were also added.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
Signed-off-by
are duplicated directly from device
memory.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
---
tools/testing/selftests/vm/hmm-tests.c | 80 ++
1 file changed, 80 insertions(+)
diff --git a/tools/testing/selftests/vm/hmm-tests.c
b/tools/testing/selftests/vm/hmm
new ioctl cmd added to query zone device type. This will be
used once the test_hmm adds zone device coherent type.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
lib/test_hmm.c | 11 +--
lib/test_hmm_uapi.h
.
Also, MIGRATE_VMA_SELECT_DEVICE_COHERENT flag is selected for
coherent type case during migration to device.
Signed-off-by: Alex Sierra
Reviewed-by: Felix Kuehling
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 34 +++-
1 file changed, 21
is_device_coherent checker was added to is_pinnable_page and renamed
to is_longterm_pinnable_page. The reason is that device coherent
pages are not supported for longterm pinning.
Signed-off-by: Alex Sierra
---
include/linux/memremap.h | 25 +
include/linux/mm.h
In order to configure device coherent in test_hmm, two module parameters
should be passed, which correspond to the SP start address of each
device (2) spm_addr_dev0 & spm_addr_dev1. If no parameters are passed,
private device type is configured.
Signed-off-by: Alex Sierra
Acked-by: F
This case is used to migrate pages from device memory, back to system
memory. Device coherent type memory is cache coherent from device and CPU
point of view.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
include/linux
From: Alistair Popple
migrate_vma_setup() checks that a valid vma is passed so that the page
tables can be walked to find the pfns associated with a given address
range. However in some cases the pfns are already known, such as when
migrating device coherent pages during pin_user_pages() meaning
From: Alistair Popple
Currently any attempts to pin a device coherent page will fail. This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.
However this is no reason to fail pinning of these pages.
flag that adds the same behaviour to
follow_page and related APIs, to allow callers to specify that they
expect to put pages on an LRU list.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
---
fs/proc/task_mmu.c | 2 +-
include/linux/mm.h | 3 ++-
mm/
.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
[hch: rebased ontop of the refcount changes,
removed is_dev_private_or_coherent_page]
Signed-off-by: Christoph Hellwig
---
include/linux/memremap.h | 19 +++
mm/memcontrol.c | 7
hmm and
selftest/vm/hmm-test.c.
v6:
- Rebase to 5.19.0-rc4
- Rename is_pinnable_page to is_longterm_pinnable_page and add a
coherent device checker.
- Add a new gup test to hmm-test to cover fast pinnable case with
FOLL_LONGTERM
Alex Sierra (12):
mm: add zone device coherent type memory sup
: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 4 ++
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 27 ++-
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 47 +--
3 files changed, 51 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
need to
track it any more.
Signed-off-by: Alex Sierra
Reviewed-by: Philip Yang
Reviewed-by: Felix Kuehling
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 59 ++-
1 file changed, 17 insertions(+), 42 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
b/d
The intention is to test hmm device coherent type under different get
user pages paths. Also, test gup with FOLL_LONGTERM flag set in
device coherent pages. These pages should get migrated back to system
memory.
Signed-off-by: Alex Sierra
Reviewed-by: Alistair Popple
---
tools/testing
are duplicated directly from device
memory.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
---
tools/testing/selftests/vm/hmm-tests.c | 80 ++
1 file changed, 80 insertions(+)
diff --git a/tools/testing/selftests/vm/hmm-tests.c
b/tools/testing/selftests/vm/hmm
Add two more parameters to set spm_addr_dev0 & spm_addr_dev1
addresses. These two parameters configure the start SP
addresses for each device in test_hmm driver.
Consequently, this configures zone device type as coherent.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alis
migrate_ping_pong test case
added to test explicit migration from device to sys memory for both
private and coherent zone types.
Helpers to migrate from device to sys memory and vicerversa
were also added.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Popple
Signed-off-by
e easily accessed from user
space through /dev/hmm_mirror. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by:
This case is used to migrate pages from device memory, back to system
memory. Device coherent type memory is cache coherent from device and CPU
point of view.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
include/linux
.
Also, MIGRATE_VMA_SELECT_DEVICE_COHERENT flag is selected for
coherent type case during migration to device.
Signed-off-by: Alex Sierra
Reviewed-by: Felix Kuehling
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 34 +++-
1 file changed, 21
new ioctl cmd added to query zone device type. This will be
used once the test_hmm adds zone device coherent type.
Signed-off-by: Alex Sierra
Acked-by: Felix Kuehling
Reviewed-by: Alistair Poppple
Signed-off-by: Christoph Hellwig
---
lib/test_hmm.c | 11 +--
lib/test_hmm_uapi.h
From: Alistair Popple
migrate_vma_setup() checks that a valid vma is passed so that the page
tables can be walked to find the pfns associated with a given address
range. However in some cases the pfns are already known, such as when
migrating device coherent pages during pin_user_pages() meaning
In order to configure device coherent in test_hmm, two module parameters
should be passed, which correspond to the SP start address of each
device (2) spm_addr_dev0 & spm_addr_dev1. If no parameters are passed,
private device type is configured.
Signed-off-by: Alex Sierra
Acked-by: F
1 - 100 of 491 matches
Mail list logo
