From: "Christian König" <ckoenig.leichtzumerken@gmail.com>
To: Felix Kuehling <Felix.Kuehling@amd.com>,
amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: alex.sierra@amd.com, Philip Yang <Philip.Yang@amd.com>
Subject: Re: [PATCH 32/35] drm/amdgpu: enable retry fault wptr overflow
Date: Thu, 7 Jan 2021 12:01:46 +0100 [thread overview]
Message-ID: <617f056c-b978-c2f6-f75f-7468d8ec2d82@gmail.com> (raw)
In-Reply-To: <20210107030127.20393-33-Felix.Kuehling@amd.com>
Am 07.01.21 um 04:01 schrieb Felix Kuehling:
> From: Philip Yang <Philip.Yang@amd.com>
>
> If xnack is on, VM retry fault interrupt send to IH ring1, and ring1
> will be full quickly. IH cannot receive other interrupts, this causes
> deadlock if migrating buffer using sdma and waiting for sdma done while
> handling retry fault.
>
> Remove VMC from IH storm client, enable ring1 write pointer overflow,
> then IH will drop retry fault interrupts and be able to receive other
> interrupts while driver is handling retry fault.
>
> IH ring1 write pointer doesn't writeback to memory by IH, and ring1
> write pointer recorded by self-irq is not updated, so always read
> the latest ring1 write pointer from register.
>
> Signed-off-by: Philip Yang <Philip.Yang@amd.com>
> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 32 +++++++++-----------------
> drivers/gpu/drm/amd/amdgpu/vega20_ih.c | 32 +++++++++-----------------
> 2 files changed, 22 insertions(+), 42 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> index 88626d83e07b..ca8efa5c6978 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
> @@ -220,10 +220,8 @@ static int vega10_ih_enable_ring(struct amdgpu_device *adev,
> tmp = vega10_ih_rb_cntl(ih, tmp);
> if (ih == &adev->irq.ih)
> tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RPTR_REARM, !!adev->irq.msi_enabled);
> - if (ih == &adev->irq.ih1) {
> - tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0);
> + if (ih == &adev->irq.ih1)
> tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1);
> - }
> if (amdgpu_sriov_vf(adev)) {
> if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
> dev_err(adev->dev, "PSP program IH_RB_CNTL failed!\n");
> @@ -265,7 +263,6 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
> u32 ih_chicken;
> int ret;
> int i;
> - u32 tmp;
>
> /* disable irqs */
> ret = vega10_ih_toggle_interrupts(adev, false);
> @@ -291,15 +288,6 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
> }
> }
>
> - tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
> - tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL,
> - CLIENT18_IS_STORM_CLIENT, 1);
> - WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp);
> -
> - tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL);
> - tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1);
> - WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp);
> -
> pci_set_master(adev->pdev);
>
> /* enable interrupts */
> @@ -345,11 +333,17 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
> u32 wptr, tmp;
> struct amdgpu_ih_regs *ih_regs;
>
> - wptr = le32_to_cpu(*ih->wptr_cpu);
> - ih_regs = &ih->ih_regs;
> + if (ih == &adev->irq.ih) {
> + /* Only ring0 supports writeback. On other rings fall back
> + * to register-based code with overflow checking below.
> + */
> + wptr = le32_to_cpu(*ih->wptr_cpu);
>
> - if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
> - goto out;
> + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
> + goto out;
> + }
> +
> + ih_regs = &ih->ih_regs;
>
> /* Double check that the overflow wasn't already cleared. */
> wptr = RREG32_NO_KIQ(ih_regs->ih_rb_wptr);
> @@ -440,15 +434,11 @@ static int vega10_ih_self_irq(struct amdgpu_device *adev,
> struct amdgpu_irq_src *source,
> struct amdgpu_iv_entry *entry)
> {
> - uint32_t wptr = cpu_to_le32(entry->src_data[0]);
> -
> switch (entry->ring_id) {
> case 1:
> - *adev->irq.ih1.wptr_cpu = wptr;
> schedule_work(&adev->irq.ih1_work);
> break;
> case 2:
> - *adev->irq.ih2.wptr_cpu = wptr;
> schedule_work(&adev->irq.ih2_work);
> break;
> default: break;
> diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> index 42032ca380cc..60d1bd51781e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
> @@ -220,10 +220,8 @@ static int vega20_ih_enable_ring(struct amdgpu_device *adev,
> tmp = vega20_ih_rb_cntl(ih, tmp);
> if (ih == &adev->irq.ih)
> tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RPTR_REARM, !!adev->irq.msi_enabled);
> - if (ih == &adev->irq.ih1) {
> - tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0);
> + if (ih == &adev->irq.ih1)
> tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1);
> - }
> if (amdgpu_sriov_vf(adev)) {
> if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
> dev_err(adev->dev, "PSP program IH_RB_CNTL failed!\n");
> @@ -297,7 +295,6 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
> u32 ih_chicken;
> int ret;
> int i;
> - u32 tmp;
>
> /* disable irqs */
> ret = vega20_ih_toggle_interrupts(adev, false);
> @@ -326,15 +323,6 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
> }
> }
>
> - tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
> - tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL,
> - CLIENT18_IS_STORM_CLIENT, 1);
> - WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp);
> -
> - tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL);
> - tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1);
> - WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp);
> -
> pci_set_master(adev->pdev);
>
> /* enable interrupts */
> @@ -379,11 +367,17 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
> u32 wptr, tmp;
> struct amdgpu_ih_regs *ih_regs;
>
> - wptr = le32_to_cpu(*ih->wptr_cpu);
> - ih_regs = &ih->ih_regs;
> + if (ih == &adev->irq.ih) {
> + /* Only ring0 supports writeback. On other rings fall back
> + * to register-based code with overflow checking below.
> + */
> + wptr = le32_to_cpu(*ih->wptr_cpu);
>
> - if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
> - goto out;
> + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
> + goto out;
> + }
> +
> + ih_regs = &ih->ih_regs;
>
> /* Double check that the overflow wasn't already cleared. */
> wptr = RREG32_NO_KIQ(ih_regs->ih_rb_wptr);
> @@ -473,15 +467,11 @@ static int vega20_ih_self_irq(struct amdgpu_device *adev,
> struct amdgpu_irq_src *source,
> struct amdgpu_iv_entry *entry)
> {
> - uint32_t wptr = cpu_to_le32(entry->src_data[0]);
> -
> switch (entry->ring_id) {
> case 1:
> - *adev->irq.ih1.wptr_cpu = wptr;
> schedule_work(&adev->irq.ih1_work);
> break;
> case 2:
> - *adev->irq.ih2.wptr_cpu = wptr;
> schedule_work(&adev->irq.ih2_work);
> break;
> default: break;
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2021-01-07 11:01 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-07 3:00 [PATCH 00/35] Add HMM-based SVM memory manager to KFD Felix Kuehling
2021-01-07 3:00 ` [PATCH 01/35] drm/amdkfd: select kernel DEVICE_PRIVATE option Felix Kuehling
2021-01-07 3:00 ` [PATCH 02/35] drm/amdgpu: replace per_device_list by array Felix Kuehling
2021-01-07 3:00 ` [PATCH 03/35] drm/amdkfd: helper to convert gpu id and idx Felix Kuehling
2021-01-07 3:00 ` [PATCH 04/35] drm/amdkfd: add svm ioctl API Felix Kuehling
2021-01-07 3:00 ` [PATCH 05/35] drm/amdkfd: Add SVM API support capability bits Felix Kuehling
2021-01-07 3:00 ` [PATCH 06/35] drm/amdkfd: register svm range Felix Kuehling
2021-01-07 3:00 ` [PATCH 07/35] drm/amdkfd: add svm ioctl GET_ATTR op Felix Kuehling
2021-01-07 3:01 ` [PATCH 08/35] drm/amdgpu: add common HMM get pages function Felix Kuehling
2021-01-07 10:53 ` Christian König
2021-01-07 3:01 ` [PATCH 09/35] drm/amdkfd: validate svm range system memory Felix Kuehling
2021-01-07 3:01 ` [PATCH 10/35] drm/amdkfd: register overlap system memory range Felix Kuehling
2021-01-07 3:01 ` [PATCH 11/35] drm/amdkfd: deregister svm range Felix Kuehling
2021-01-07 3:01 ` [PATCH 12/35] drm/amdgpu: export vm update mapping interface Felix Kuehling
2021-01-07 10:54 ` Christian König
2021-01-07 3:01 ` [PATCH 13/35] drm/amdkfd: map svm range to GPUs Felix Kuehling
2021-01-07 3:01 ` [PATCH 14/35] drm/amdkfd: svm range eviction and restore Felix Kuehling
2021-01-07 3:01 ` [PATCH 15/35] drm/amdkfd: add xnack enabled flag to kfd_process Felix Kuehling
2021-01-07 3:01 ` [PATCH 16/35] drm/amdkfd: add ioctl to configure and query xnack retries Felix Kuehling
2021-01-07 3:01 ` [PATCH 17/35] drm/amdkfd: register HMM device private zone Felix Kuehling
2021-03-01 8:32 ` Daniel Vetter
2021-03-01 8:46 ` Thomas Hellström (Intel)
2021-03-01 8:58 ` Daniel Vetter
2021-03-01 9:30 ` Thomas Hellström (Intel)
2021-03-04 17:58 ` Felix Kuehling
2021-03-11 12:24 ` Thomas Hellström (Intel)
2021-01-07 3:01 ` [PATCH 18/35] drm/amdkfd: validate vram svm range from TTM Felix Kuehling
2021-01-07 3:01 ` [PATCH 19/35] drm/amdkfd: support xgmi same hive mapping Felix Kuehling
2021-01-07 3:01 ` [PATCH 20/35] drm/amdkfd: copy memory through gart table Felix Kuehling
2021-01-07 3:01 ` [PATCH 21/35] drm/amdkfd: HMM migrate ram to vram Felix Kuehling
2021-01-07 3:01 ` [PATCH 22/35] drm/amdkfd: HMM migrate vram to ram Felix Kuehling
2021-01-07 3:01 ` [PATCH 23/35] drm/amdkfd: invalidate tables on page retry fault Felix Kuehling
2021-01-07 3:01 ` [PATCH 24/35] drm/amdkfd: page table restore through svm API Felix Kuehling
2021-01-07 3:01 ` [PATCH 25/35] drm/amdkfd: SVM API call to restore page tables Felix Kuehling
2021-01-07 3:01 ` [PATCH 26/35] drm/amdkfd: add svm_bo reference for eviction fence Felix Kuehling
2021-01-07 3:01 ` [PATCH 27/35] drm/amdgpu: add param bit flag to create SVM BOs Felix Kuehling
2021-01-07 3:01 ` [PATCH 28/35] drm/amdkfd: add svm_bo eviction mechanism support Felix Kuehling
2021-01-07 3:01 ` [PATCH 29/35] drm/amdgpu: svm bo enable_signal call condition Felix Kuehling
2021-01-07 10:56 ` Christian König
2021-01-07 16:16 ` Felix Kuehling
2021-01-07 16:28 ` Christian König
2021-01-07 16:53 ` Felix Kuehling
2021-01-07 3:01 ` [PATCH 30/35] drm/amdgpu: add svm_bo eviction to enable_signal cb Felix Kuehling
2021-01-07 3:01 ` [PATCH 31/35] drm/amdgpu: reserve fence slot to update page table Felix Kuehling
2021-01-07 10:57 ` Christian König
2021-01-07 3:01 ` [PATCH 32/35] drm/amdgpu: enable retry fault wptr overflow Felix Kuehling
2021-01-07 11:01 ` Christian König [this message]
2021-01-07 3:01 ` [PATCH 33/35] drm/amdkfd: refine migration policy with xnack on Felix Kuehling
2021-01-07 3:01 ` [PATCH 34/35] drm/amdkfd: add svm range validate timestamp Felix Kuehling
2021-01-07 3:01 ` [PATCH 35/35] drm/amdkfd: multiple gpu migrate vram to vram Felix Kuehling
2021-01-07 9:23 ` [PATCH 00/35] Add HMM-based SVM memory manager to KFD Daniel Vetter
2021-01-07 16:25 ` Felix Kuehling
2021-01-08 14:40 ` Daniel Vetter
2021-01-08 14:45 ` Christian König
2021-01-08 15:58 ` Felix Kuehling
2021-01-08 16:06 ` Daniel Vetter
2021-01-08 16:36 ` Felix Kuehling
2021-01-08 16:53 ` Daniel Vetter
2021-01-08 17:56 ` Felix Kuehling
2021-01-11 16:29 ` Daniel Vetter
2021-01-14 5:34 ` Felix Kuehling
2021-01-14 12:19 ` Christian König
2021-01-13 16:56 ` Jerome Glisse
2021-01-13 20:31 ` Daniel Vetter
2021-01-14 3:27 ` Jerome Glisse
2021-01-14 9:26 ` Daniel Vetter
2021-01-14 10:39 ` Daniel Vetter
2021-01-14 10:49 ` Christian König
2021-01-14 11:52 ` Daniel Vetter
2021-01-14 13:37 ` HMM fence (was Re: [PATCH 00/35] Add HMM-based SVM memory manager to KFD) Christian König
2021-01-14 13:57 ` Daniel Vetter
2021-01-14 14:13 ` Christian König
2021-01-14 14:23 ` Daniel Vetter
2021-01-14 15:08 ` Christian König
2021-01-14 15:40 ` Daniel Vetter
2021-01-14 16:01 ` Christian König
2021-01-14 16:36 ` Daniel Vetter
2021-01-14 19:08 ` Christian König
2021-01-14 20:09 ` Daniel Vetter
2021-01-14 16:51 ` Jerome Glisse
2021-01-14 21:13 ` Felix Kuehling
2021-01-15 7:47 ` Christian König
2021-01-13 16:47 ` [PATCH 00/35] Add HMM-based SVM memory manager to KFD Jerome Glisse
2021-01-14 0:06 ` Felix Kuehling
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=617f056c-b978-c2f6-f75f-7468d8ec2d82@gmail.com \
--to=ckoenig.leichtzumerken@gmail.com \
--cc=Felix.Kuehling@amd.com \
--cc=Philip.Yang@amd.com \
--cc=alex.sierra@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=dri-devel@lists.freedesktop.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).