Re: [PATCH] drm/amdgpu: enable 48-bit IH timestamp counter
Yes, exactly.
Is the timer guaranteed to monotonous increment? I strongly suspect yes
and then a simple "if (old > new) ++upper_32_bits;" should be sufficient.
Regards,
Christian.
Am 13.11.20 um 18:15 schrieb Felix Kuehling:
I'd feel better with wrap-around handling. I think having a system up
for that long is not likely but not impossible. Having a known hard
limit on uptime is probably a bad thing. Imagine someone trying to
reproduce the problem ...
Regards,
Felix
Am 2020-11-16 um 6:31 a.m. schrieb Christian König:
Feel free to keep my rb for this, but is 455 days enough in general or
should we add wrap around handling?
Christian.
Am 10.11.20 um 18:57 schrieb Sierra Guiza, Alejandro (Alex):
[AMD Public Use]
I just added support for vega10_ih too.
Regards,
Alex
-Original Message-
From: Sierra Guiza, Alejandro (Alex)
Sent: Tuesday, November 10, 2020 11:55 AM
To: amd-gfx@lists.freedesktop.org
Cc: Koenig, Christian ; Kuehling, Felix
; Sierra Guiza, Alejandro (Alex)
Subject: [PATCH] drm/amdgpu: enable 48-bit IH timestamp counter
By default this timestamp is based on a 32 bit counter.
This is used by the amdgpu_gmc_filter_faults, to avoid process the same
interrupt in retry configuration.
Apparently there's a problem when the timestamp coming from IH
overflows
and compares against timestamp coming from the the hash table.
This patch only extends the time overflow from 10 minutes to aprx
455 days.
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/navi10_ih.c | 6 ++
drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 6 ++
2 files changed, 12 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 837769fcb35b..bda916f33805 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -94,6 +94,8 @@ static void navi10_ih_enable_interrupts(struct
amdgpu_device *adev)
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 1);
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR,
1);
+ ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL,
+ RB_GPU_TS_ENABLE, 1);
if (amdgpu_sriov_vf(adev) && adev->asic_type < CHIP_NAVI10) {
if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL,
ih_rb_cntl)) {
DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
@@ -109,6 +111,8 @@ static void navi10_ih_enable_interrupts(struct
amdgpu_device *adev)
ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
mmIH_RB_CNTL_RING1);
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
RB_ENABLE, 1);
+ ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
+ RB_GPU_TS_ENABLE, 1);
if (amdgpu_sriov_vf(adev) && adev->asic_type <
CHIP_NAVI10) {
if (psp_reg_program(&adev->psp,
PSP_REG_IH_RB_CNTL_RING1,
ih_rb_cntl)) {
@@ -125,6 +129,8 @@ static void navi10_ih_enable_interrupts(struct
amdgpu_device *adev)
ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
mmIH_RB_CNTL_RING2);
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2,
RB_ENABLE, 1);
+ ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2,
+ RB_GPU_TS_ENABLE, 1);
if (amdgpu_sriov_vf(adev) && adev->asic_type <
CHIP_NAVI10) {
if (psp_reg_program(&adev->psp,
PSP_REG_IH_RB_CNTL_RING2,
ih_rb_cntl)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 407c6093c2ec..35d68bc5d95e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -50,6 +50,8 @@ static void vega10_ih_enable_interrupts(struct
amdgpu_device *adev)
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 1);
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR,
1);
+ ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL,
+ RB_GPU_TS_ENABLE, 1);
if (amdgpu_sriov_vf(adev)) {
if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL,
ih_rb_cntl)) {
DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
@@ -64,6 +66,8 @@ static void vega10_ih_enable_interrupts(struct
amdgpu_device *adev)
ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
mmIH_RB_CNTL_RING1);
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
RB_ENABLE, 1);
+ ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1,
+ RB_GPU_TS_ENABLE, 1);
if (amdgpu_sriov_vf(adev)) {
if (psp_reg_program(&adev->psp,
PSP_REG_IH_RB_CNTL_RING1,
ih_rb_cntl)) {
@@ -80,6 +84,8 @@ static void vega10_ih_enable_interrupts(struct
amdgpu_device *adev)
ih_rb_cntl = RREG32_SOC15(OSSSYS, 0,
mmIH_RB_CNTL_RING2);
ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RI
Re: [PATCH v2 1/8] drm: Add dummy page per device or GEM object
Am 13.11.20 um 21:52 schrieb Andrey Grodzovsky:
On 6/22/20 1:50 PM, Daniel Vetter wrote:
On Mon, Jun 22, 2020 at 7:45 PM Christian König
wrote:
Am 22.06.20 um 16:32 schrieb Andrey Grodzovsky:
On 6/22/20 9:18 AM, Christian König wrote:
Am 21.06.20 um 08:03 schrieb Andrey Grodzovsky:
Will be used to reroute CPU mapped BO's page faults once
device is removed.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/drm_file.c | 8
drivers/gpu/drm/drm_prime.c | 10 ++
include/drm/drm_file.h | 2 ++
include/drm/drm_gem.h | 2 ++
4 files changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index c4c704e..67c0770 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -188,6 +188,12 @@ struct drm_file *drm_file_alloc(struct
drm_minor *minor)
goto out_prime_destroy;
}
+ file->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!file->dummy_page) {
+ ret = -ENOMEM;
+ goto out_prime_destroy;
+ }
+
return file;
out_prime_destroy:
@@ -284,6 +290,8 @@ void drm_file_free(struct drm_file *file)
if (dev->driver->postclose)
dev->driver->postclose(dev, file);
+ __free_page(file->dummy_page);
+
drm_prime_destroy_file_private(&file->prime);
WARN_ON(!list_empty(&file->event_list));
diff --git a/drivers/gpu/drm/drm_prime.c
b/drivers/gpu/drm/drm_prime.c
index 1de2cde..c482e9c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -335,6 +335,13 @@ int drm_gem_prime_fd_to_handle(struct
drm_device *dev,
ret = drm_prime_add_buf_handle(&file_priv->prime,
dma_buf, *handle);
+
+ if (!ret) {
+ obj->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!obj->dummy_page)
+ ret = -ENOMEM;
+ }
+
While the per file case still looks acceptable this is a clear NAK
since it will massively increase the memory needed for a prime
exported object.
I think that this is quite overkill in the first place and for the
hot unplug case we can just use the global dummy page as well.
Christian.
Global dummy page is good for read access, what do you do on write
access ? My first approach was indeed to map at first global dummy
page as read only and mark the vma->vm_flags as !VM_SHARED assuming
that this would trigger Copy On Write flow in core mm
(https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.bootlin.com%2Flinux%2Fv5.7-rc7%2Fsource%2Fmm%2Fmemory.c%23L3977&data=02%7C01%7CAndrey.Grodzovsky%40amd.com%7C3753451d037544e7495408d816d4c4ee%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637284450384586120&sdata=ZpRaQgqA5K4jRfidOiedey0AleeYQ97WNUkGA29ERA0%3D&reserved=0)
on the next page fault to same address triggered by a write access but
then i realized a new COW page will be allocated for each such mapping
and this is much more wasteful then having a dedicated page per GEM
object.
Yeah, but this is only for a very very small corner cases. What we need
to prevent is increasing the memory usage during normal operation to
much.
Using memory during the unplug is completely unproblematic because we
just released quite a bunch of it by releasing all those system memory
buffers.
And I'm pretty sure that COWed pages are correctly accounted towards
the
used memory of a process.
So I think if that approach works as intended and the COW pages are
released again on unmapping it would be the perfect solution to the
problem.
Daniel what do you think?
If COW works, sure sounds reasonable. And if we can make sure we
managed to drop all the system allocations (otherwise suddenly 2x
memory usage, worst case). But I have no idea whether we can
retroshoehorn that into an established vma, you might have fun stuff
like a mkwrite handler there (which I thought is the COW handler
thing, but really no idea).
If we need to massively change stuff then I think rw dummy page,
allocated on first fault after hotunplug (maybe just make it one per
object, that's simplest) seems like the much safer option. Much less
code that can go wrong.
-Daniel
Regarding COW, i was looking into how to properly implement it from
within the fault handler (i.e. ttm_bo_vm_fault)
and the main obstacle I hit is that of exclusive access to the
vm_area_struct, i need to be able to modify
vma->vm_flags (and vm_page_prot) to remove VM_SHARED bit so COW can
be triggered on subsequent write access
fault (here
https://elixir.bootlin.com/linux/latest/source/mm/memory.c#L4128)
but core mm takes only read side mm_sem (here for example
https://elixir.bootlin.com/linux/latest/source/drivers/iommu/amd/iommu_v2.c#L488)
and so I am not supposed to modify vm_area_struct in this case. I am
not sure if it's legit to write lock tthe mm_sem from this point.
I found some discussions about this here
http://lkml.iu.edu/hypermail/linux/kernel/1909.1/02754.html but it
wasn't really clear to me
wha
Re: [PATCH 1/1] drm/amdgpu: fix usable gart size calculation
Am 13.11.20 um 18:33 schrieb Nirmoy Das: amdgpu_do_test_moves() is failing because of wrong usable gart size calculation and throwing: [drm:amdgpu_do_test_moves [amdgpu]] *ERROR* 20bdc9f3 bind failed Signed-off-by: Nirmoy Das Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_test.c | 13 - 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c index 6042b3b81a4c..7b230bcbf2c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c @@ -42,16 +42,11 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev) size = 1024 * 1024; /* Number of tests = -* (Total GTT - IB pool - writeback page - ring buffers) / test size +* (Total GTT - gart_pin_size - (2 transfer windows for buffer moves)) / test size */ - n = adev->gmc.gart_size - AMDGPU_IB_POOL_SIZE; - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) - if (adev->rings[i]) - n -= adev->rings[i]->ring_size; - if (adev->wb.wb_obj) - n -= AMDGPU_GPU_PAGE_SIZE; - if (adev->irq.ih.ring_obj) - n -= adev->irq.ih.ring_size; + n = adev->gmc.gart_size - atomic64_read(&adev->gart_pin_size); + n -= AMDGPU_GTT_MAX_TRANSFER_SIZE * AMDGPU_GTT_NUM_TRANSFER_WINDOWS * + AMDGPU_GPU_PAGE_SIZE; n /= size; gtt_obj = kcalloc(n, sizeof(*gtt_obj), GFP_KERNEL); ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH v2 1/8] drm: Add dummy page per device or GEM object
On Sat, Nov 14, 2020 at 9:41 AM Christian König
wrote:
>
> Am 13.11.20 um 21:52 schrieb Andrey Grodzovsky:
> >
> > On 6/22/20 1:50 PM, Daniel Vetter wrote:
> >> On Mon, Jun 22, 2020 at 7:45 PM Christian König
> >> wrote:
> >>> Am 22.06.20 um 16:32 schrieb Andrey Grodzovsky:
> On 6/22/20 9:18 AM, Christian König wrote:
> > Am 21.06.20 um 08:03 schrieb Andrey Grodzovsky:
> >> Will be used to reroute CPU mapped BO's page faults once
> >> device is removed.
> >>
> >> Signed-off-by: Andrey Grodzovsky
> >> ---
> >>drivers/gpu/drm/drm_file.c | 8
> >>drivers/gpu/drm/drm_prime.c | 10 ++
> >>include/drm/drm_file.h | 2 ++
> >>include/drm/drm_gem.h | 2 ++
> >>4 files changed, 22 insertions(+)
> >>
> >> diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
> >> index c4c704e..67c0770 100644
> >> --- a/drivers/gpu/drm/drm_file.c
> >> +++ b/drivers/gpu/drm/drm_file.c
> >> @@ -188,6 +188,12 @@ struct drm_file *drm_file_alloc(struct
> >> drm_minor *minor)
> >>goto out_prime_destroy;
> >>}
> >>+file->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
> >> +if (!file->dummy_page) {
> >> +ret = -ENOMEM;
> >> +goto out_prime_destroy;
> >> +}
> >> +
> >>return file;
> >> out_prime_destroy:
> >> @@ -284,6 +290,8 @@ void drm_file_free(struct drm_file *file)
> >>if (dev->driver->postclose)
> >>dev->driver->postclose(dev, file);
> >>+__free_page(file->dummy_page);
> >> +
> >> drm_prime_destroy_file_private(&file->prime);
> >> WARN_ON(!list_empty(&file->event_list));
> >> diff --git a/drivers/gpu/drm/drm_prime.c
> >> b/drivers/gpu/drm/drm_prime.c
> >> index 1de2cde..c482e9c 100644
> >> --- a/drivers/gpu/drm/drm_prime.c
> >> +++ b/drivers/gpu/drm/drm_prime.c
> >> @@ -335,6 +335,13 @@ int drm_gem_prime_fd_to_handle(struct
> >> drm_device *dev,
> >> ret = drm_prime_add_buf_handle(&file_priv->prime,
> >>dma_buf, *handle);
> >> +
> >> +if (!ret) {
> >> +obj->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
> >> +if (!obj->dummy_page)
> >> +ret = -ENOMEM;
> >> +}
> >> +
> > While the per file case still looks acceptable this is a clear NAK
> > since it will massively increase the memory needed for a prime
> > exported object.
> >
> > I think that this is quite overkill in the first place and for the
> > hot unplug case we can just use the global dummy page as well.
> >
> > Christian.
>
> Global dummy page is good for read access, what do you do on write
> access ? My first approach was indeed to map at first global dummy
> page as read only and mark the vma->vm_flags as !VM_SHARED assuming
> that this would trigger Copy On Write flow in core mm
> (https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.bootlin.com%2Flinux%2Fv5.7-rc7%2Fsource%2Fmm%2Fmemory.c%23L3977&data=02%7C01%7CAndrey.Grodzovsky%40amd.com%7C3753451d037544e7495408d816d4c4ee%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637284450384586120&sdata=ZpRaQgqA5K4jRfidOiedey0AleeYQ97WNUkGA29ERA0%3D&reserved=0)
>
> on the next page fault to same address triggered by a write access but
> then i realized a new COW page will be allocated for each such mapping
> and this is much more wasteful then having a dedicated page per GEM
> object.
> >>> Yeah, but this is only for a very very small corner cases. What we need
> >>> to prevent is increasing the memory usage during normal operation to
> >>> much.
> >>>
> >>> Using memory during the unplug is completely unproblematic because we
> >>> just released quite a bunch of it by releasing all those system memory
> >>> buffers.
> >>>
> >>> And I'm pretty sure that COWed pages are correctly accounted towards
> >>> the
> >>> used memory of a process.
> >>>
> >>> So I think if that approach works as intended and the COW pages are
> >>> released again on unmapping it would be the perfect solution to the
> >>> problem.
> >>>
> >>> Daniel what do you think?
> >> If COW works, sure sounds reasonable. And if we can make sure we
> >> managed to drop all the system allocations (otherwise suddenly 2x
> >> memory usage, worst case). But I have no idea whether we can
> >> retroshoehorn that into an established vma, you might have fun stuff
> >> like a mkwrite handler there (which I thought is the COW handler
> >> thing, but really no idea).
> >>
> >> If we need to massively change stuff then I think rw dummy page,
> >> allocated on first fault after hotunplug (maybe just make it one per
> >> object, that's simplest) seems like the much safer option. Much less
> >> code that can go wrong.
> >> -Daniel
> >
> >
> > Reg
Re: [PATCH v2 1/8] drm: Add dummy page per device or GEM object
On Sat, Nov 14, 2020 at 10:51 AM Daniel Vetter wrote:
>
> On Sat, Nov 14, 2020 at 9:41 AM Christian König
> wrote:
> >
> > Am 13.11.20 um 21:52 schrieb Andrey Grodzovsky:
> > >
> > > On 6/22/20 1:50 PM, Daniel Vetter wrote:
> > >> On Mon, Jun 22, 2020 at 7:45 PM Christian König
> > >> wrote:
> > >>> Am 22.06.20 um 16:32 schrieb Andrey Grodzovsky:
> > On 6/22/20 9:18 AM, Christian König wrote:
> > > Am 21.06.20 um 08:03 schrieb Andrey Grodzovsky:
> > >> Will be used to reroute CPU mapped BO's page faults once
> > >> device is removed.
> > >>
> > >> Signed-off-by: Andrey Grodzovsky
> > >> ---
> > >>drivers/gpu/drm/drm_file.c | 8
> > >>drivers/gpu/drm/drm_prime.c | 10 ++
> > >>include/drm/drm_file.h | 2 ++
> > >>include/drm/drm_gem.h | 2 ++
> > >>4 files changed, 22 insertions(+)
> > >>
> > >> diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
> > >> index c4c704e..67c0770 100644
> > >> --- a/drivers/gpu/drm/drm_file.c
> > >> +++ b/drivers/gpu/drm/drm_file.c
> > >> @@ -188,6 +188,12 @@ struct drm_file *drm_file_alloc(struct
> > >> drm_minor *minor)
> > >>goto out_prime_destroy;
> > >>}
> > >>+file->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
> > >> +if (!file->dummy_page) {
> > >> +ret = -ENOMEM;
> > >> +goto out_prime_destroy;
> > >> +}
> > >> +
> > >>return file;
> > >> out_prime_destroy:
> > >> @@ -284,6 +290,8 @@ void drm_file_free(struct drm_file *file)
> > >>if (dev->driver->postclose)
> > >>dev->driver->postclose(dev, file);
> > >>+__free_page(file->dummy_page);
> > >> +
> > >> drm_prime_destroy_file_private(&file->prime);
> > >> WARN_ON(!list_empty(&file->event_list));
> > >> diff --git a/drivers/gpu/drm/drm_prime.c
> > >> b/drivers/gpu/drm/drm_prime.c
> > >> index 1de2cde..c482e9c 100644
> > >> --- a/drivers/gpu/drm/drm_prime.c
> > >> +++ b/drivers/gpu/drm/drm_prime.c
> > >> @@ -335,6 +335,13 @@ int drm_gem_prime_fd_to_handle(struct
> > >> drm_device *dev,
> > >> ret = drm_prime_add_buf_handle(&file_priv->prime,
> > >>dma_buf, *handle);
> > >> +
> > >> +if (!ret) {
> > >> +obj->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
> > >> +if (!obj->dummy_page)
> > >> +ret = -ENOMEM;
> > >> +}
> > >> +
> > > While the per file case still looks acceptable this is a clear NAK
> > > since it will massively increase the memory needed for a prime
> > > exported object.
> > >
> > > I think that this is quite overkill in the first place and for the
> > > hot unplug case we can just use the global dummy page as well.
> > >
> > > Christian.
> >
> > Global dummy page is good for read access, what do you do on write
> > access ? My first approach was indeed to map at first global dummy
> > page as read only and mark the vma->vm_flags as !VM_SHARED assuming
> > that this would trigger Copy On Write flow in core mm
> > (https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.bootlin.com%2Flinux%2Fv5.7-rc7%2Fsource%2Fmm%2Fmemory.c%23L3977&data=02%7C01%7CAndrey.Grodzovsky%40amd.com%7C3753451d037544e7495408d816d4c4ee%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637284450384586120&sdata=ZpRaQgqA5K4jRfidOiedey0AleeYQ97WNUkGA29ERA0%3D&reserved=0)
> >
> > on the next page fault to same address triggered by a write access but
> > then i realized a new COW page will be allocated for each such mapping
> > and this is much more wasteful then having a dedicated page per GEM
> > object.
> > >>> Yeah, but this is only for a very very small corner cases. What we need
> > >>> to prevent is increasing the memory usage during normal operation to
> > >>> much.
> > >>>
> > >>> Using memory during the unplug is completely unproblematic because we
> > >>> just released quite a bunch of it by releasing all those system memory
> > >>> buffers.
> > >>>
> > >>> And I'm pretty sure that COWed pages are correctly accounted towards
> > >>> the
> > >>> used memory of a process.
> > >>>
> > >>> So I think if that approach works as intended and the COW pages are
> > >>> released again on unmapping it would be the perfect solution to the
> > >>> problem.
> > >>>
> > >>> Daniel what do you think?
> > >> If COW works, sure sounds reasonable. And if we can make sure we
> > >> managed to drop all the system allocations (otherwise suddenly 2x
> > >> memory usage, worst case). But I have no idea whether we can
> > >> retroshoehorn that into an established vma, you might have fun stuff
> > >> like a mkwrite handler there (which I thought is the COW handler
> > >> thing, but really no idea).
> > >>
> > >> If
Re: [PATCH v2 1/8] drm: Add dummy page per device or GEM object
On 11/14/20 4:51 AM, Daniel Vetter wrote:
On Sat, Nov 14, 2020 at 9:41 AM Christian König
wrote:
Am 13.11.20 um 21:52 schrieb Andrey Grodzovsky:
On 6/22/20 1:50 PM, Daniel Vetter wrote:
On Mon, Jun 22, 2020 at 7:45 PM Christian König
wrote:
Am 22.06.20 um 16:32 schrieb Andrey Grodzovsky:
On 6/22/20 9:18 AM, Christian König wrote:
Am 21.06.20 um 08:03 schrieb Andrey Grodzovsky:
Will be used to reroute CPU mapped BO's page faults once
device is removed.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/drm_file.c | 8
drivers/gpu/drm/drm_prime.c | 10 ++
include/drm/drm_file.h | 2 ++
include/drm/drm_gem.h | 2 ++
4 files changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index c4c704e..67c0770 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -188,6 +188,12 @@ struct drm_file *drm_file_alloc(struct
drm_minor *minor)
goto out_prime_destroy;
}
+file->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+if (!file->dummy_page) {
+ret = -ENOMEM;
+goto out_prime_destroy;
+}
+
return file;
out_prime_destroy:
@@ -284,6 +290,8 @@ void drm_file_free(struct drm_file *file)
if (dev->driver->postclose)
dev->driver->postclose(dev, file);
+__free_page(file->dummy_page);
+
drm_prime_destroy_file_private(&file->prime);
WARN_ON(!list_empty(&file->event_list));
diff --git a/drivers/gpu/drm/drm_prime.c
b/drivers/gpu/drm/drm_prime.c
index 1de2cde..c482e9c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -335,6 +335,13 @@ int drm_gem_prime_fd_to_handle(struct
drm_device *dev,
ret = drm_prime_add_buf_handle(&file_priv->prime,
dma_buf, *handle);
+
+if (!ret) {
+obj->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+if (!obj->dummy_page)
+ret = -ENOMEM;
+}
+
While the per file case still looks acceptable this is a clear NAK
since it will massively increase the memory needed for a prime
exported object.
I think that this is quite overkill in the first place and for the
hot unplug case we can just use the global dummy page as well.
Christian.
Global dummy page is good for read access, what do you do on write
access ? My first approach was indeed to map at first global dummy
page as read only and mark the vma->vm_flags as !VM_SHARED assuming
that this would trigger Copy On Write flow in core mm
(https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.bootlin.com%2Flinux%2Fv5.7-rc7%2Fsource%2Fmm%2Fmemory.c%23L3977&data=04%7C01%7CAndrey.Grodzovsky%40amd.com%7C00053e9d983041ed63ae08d2ed87%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637409443224016377%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=kghiG3VpCJod6YefExoDVPl9X03zNhw3SN5GAxgbnmU%3D&reserved=0)
on the next page fault to same address triggered by a write access but
then i realized a new COW page will be allocated for each such mapping
and this is much more wasteful then having a dedicated page per GEM
object.
Yeah, but this is only for a very very small corner cases. What we need
to prevent is increasing the memory usage during normal operation to
much.
Using memory during the unplug is completely unproblematic because we
just released quite a bunch of it by releasing all those system memory
buffers.
And I'm pretty sure that COWed pages are correctly accounted towards
the
used memory of a process.
So I think if that approach works as intended and the COW pages are
released again on unmapping it would be the perfect solution to the
problem.
Daniel what do you think?
If COW works, sure sounds reasonable. And if we can make sure we
managed to drop all the system allocations (otherwise suddenly 2x
memory usage, worst case). But I have no idea whether we can
retroshoehorn that into an established vma, you might have fun stuff
like a mkwrite handler there (which I thought is the COW handler
thing, but really no idea).
If we need to massively change stuff then I think rw dummy page,
allocated on first fault after hotunplug (maybe just make it one per
object, that's simplest) seems like the much safer option. Much less
code that can go wrong.
-Daniel
Regarding COW, i was looking into how to properly implement it from
within the fault handler (i.e. ttm_bo_vm_fault)
and the main obstacle I hit is that of exclusive access to the
vm_area_struct, i need to be able to modify
vma->vm_flags (and vm_page_prot) to remove VM_SHARED bit so COW can
be triggered on subsequent write access
fault (here
https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Felixir.bootlin.com%2Flinux%2Flatest%2Fsource%2Fmm%2Fmemory.c%23L4128&data=04%7C01%7CAndrey.Grodzovsky%40amd.com%7C00053e9d983041ed63ae08d2ed87%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637409443224016377%7CUnknow
Re: [PATCH v2 1/8] drm: Add dummy page per device or GEM object
On 6/22/20 5:35 AM, Daniel Vetter wrote:
On Sun, Jun 21, 2020 at 02:03:01AM -0400, Andrey Grodzovsky wrote:
Will be used to reroute CPU mapped BO's page faults once
device is removed.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/drm_file.c | 8
drivers/gpu/drm/drm_prime.c | 10 ++
include/drm/drm_file.h | 2 ++
include/drm/drm_gem.h | 2 ++
4 files changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index c4c704e..67c0770 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -188,6 +188,12 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor)
goto out_prime_destroy;
}
+ file->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!file->dummy_page) {
+ ret = -ENOMEM;
+ goto out_prime_destroy;
+ }
+
return file;
out_prime_destroy:
@@ -284,6 +290,8 @@ void drm_file_free(struct drm_file *file)
if (dev->driver->postclose)
dev->driver->postclose(dev, file);
+ __free_page(file->dummy_page);
+
drm_prime_destroy_file_private(&file->prime);
WARN_ON(!list_empty(&file->event_list));
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 1de2cde..c482e9c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -335,6 +335,13 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev,
ret = drm_prime_add_buf_handle(&file_priv->prime,
dma_buf, *handle);
+
+ if (!ret) {
+ obj->dummy_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!obj->dummy_page)
+ ret = -ENOMEM;
+ }
+
mutex_unlock(&file_priv->prime.lock);
if (ret)
goto fail;
@@ -1006,6 +1013,9 @@ void drm_prime_gem_destroy(struct drm_gem_object *obj,
struct sg_table *sg)
dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL);
dma_buf = attach->dmabuf;
dma_buf_detach(attach->dmabuf, attach);
+
+ __free_page(obj->dummy_page);
+
/* remove the reference */
dma_buf_put(dma_buf);
}
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index 19df802..349a658 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -335,6 +335,8 @@ struct drm_file {
*/
struct drm_prime_file_private prime;
Kerneldoc for these please, including why we need them and when. E.g. the
one in gem_bo should say it's only for exported buffers, so that we're not
colliding security spaces.
+ struct page *dummy_page;
+
/* private: */
#if IS_ENABLED(CONFIG_DRM_LEGACY)
unsigned long lock_count; /* DRI1 legacy lock count */
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 0b37506..47460d1 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -310,6 +310,8 @@ struct drm_gem_object {
*
*/
const struct drm_gem_object_funcs *funcs;
+
+ struct page *dummy_page;
};
I think amdgpu doesn't care, but everyone else still might care somewhat
about flink. That also shares buffers, so also needs to allocate the
per-bo dummy page.
Not familiar with FLINK so I read a bit here https://lwn.net/Articles/283798/
sections 3 and 4 about FLINK naming and later mapping, I don't see a difference
between FLINK and local BO mapping as opening by FLINK name returns handle
to the same BO as the original. Why then we need a special handling for FLINK ?
Andrey
I also wonder whether we shouldn't have a helper to look up the dummy
page, just to encode in core code how it's supposedo to cascade.
-Daniel
/**
--
2.7.4
___
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
