Init timing changes for SRIOV VF
Subsystems (2)
This is the second patch series merged or reimplemented from SRIOV branch. It changes the init time consuming.
Exclusive mode means that a VF occupies hardware and other VFs need to wait until this VF releases exclusive mode. The timing of exclusive mode is limited to avoid starvation causing unavailable service. If driver don't finish exclusive mode init in time, the VF will be reset and driver init fails.
The target of this series is to decrease the time consuming in exclusive mode as much as possible, and retry init if it fails due to timeout.
Please help reviewing.
[PATCH 1/7] drm/amdgpu: release VF exclusive accessing after hw_init [PATCH 2/7] drm/amdgpu: add init_log param to control logs in [PATCH 3/7] drm/amdgpu: avoid soft lockup when waiting for RLC serdes [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessing [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops [PATCH 7/7] drm/amdgpu: retry init if it fails due to exclusive mode
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-1-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
PATCH 1/7 drm/amdgpu: release VF exclusive accessing after hw_init
The subsequent operations don't need exclusive accessing hardware.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 --- 2 files changed, 5 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5 -0
@@ -1716,6 +1716,11 @@ static int amdgpu_init(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = true; } +if (amdgpu_sriov_vf (adev)) { +DRM_INFO ("rel_init\n" ); +amdgpu_virt_release_full_gpu (adev, true); + } +return 0 ; }
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +0 -3
@@ -171,9 +171,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)pm_runtime_put_autosuspend (dev->dev); } -if (amdgpu_sriov_vf (adev)) -amdgpu_virt_release_full_gpu (adev, true); - out:if (r) {/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-2-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
Deucher, Alexander
Acked-by Alex DeucherRE: [PATCH 1/7] drm/amdgpu: release VF exclusive accessing after hw_init
Quoted 9 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 1/7] drm/amdgpu: release VF exclusive accessing afterhw_init
Quoted 3 lines
The subsequent operations don't need exclusive accessing hardware.
Signed-off-by Pixel Ding <[email protected]>
Quoted 43 lines
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 --- 2 files changed, 5 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5
-0@@ -1716,6 +1716,11 @@ static int amdgpu_init(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = true; } +if (amdgpu_sriov_vf (adev)) { +DRM_INFO ("rel_init\n" ); +amdgpu_virt_release_full_gpu (adev, true); + } +return 0 ; }drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +0
-3@@ -171,9 +171,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) pm_runtime_put_autosuspend(dev->dev); } -if (amdgpu_sriov_vf (adev)) -amdgpu_virt_release_full_gpu (adev, true); - out:if (r) {/* balance
pm_runtime_get_syncinamdgpu_driver_unload_kms*/
--
2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BN6PR12MB16528E993E985FB6B21F7022F7460-/b2+HYfkarQqUD6E6FAiowdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org
Re: [PATCH 1/7] drm/amdgpu: release VF exclusive accessing after hw_init
Hi all,
I notice that this change will break KFD init on VF. KFD also load HQD which needs to be done in exclusive mode, otherwise KIQ register accessing causes LOAD VF failed at that time. However if we release EX mode after KFD init, the retry init logic will be quite complicated to handle all failures, also the EX mode time consuming is too much. Any idea?
By now I would drop this change upstream.
—
Sincerely Yours,
Pixel
Quoted 58 lines · Alexander
Quoted 9 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 1/7] drm/amdgpu: release VF exclusive accessing afterhw_initQuoted 3 lines
The subsequent operations don't need exclusive accessing hardware.
Signed-off-by Pixel Ding <[email protected]>Acked-by Alex Deucher <[email protected]>Quoted 43 lines
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 --- 2 files changed, 5 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5
-0@@ -1716,6 +1716,11 @@ static int amdgpu_init(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = true; } +if (amdgpu_sriov_vf (adev)) { +DRM_INFO ("rel_init\n" ); +amdgpu_virt_release_full_gpu (adev, true); + } +return 0 ; }drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +0
-3@@ -171,9 +171,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) pm_runtime_put_autosuspend(dev->dev); } -if (amdgpu_sriov_vf (adev)) -amdgpu_virt_release_full_gpu (adev, true); - out:if (r) {/* balance
pm_runtime_get_syncinamdgpu_driver_unload_kms*/
--
2.9.5
Quoted 4 lines
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): C93A21B6-251A-47B5-BC30-C199564D46CA-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 1/7] drm/amdgpu: release VF exclusive accessing after hw_init
Hi Shaoyun,
Can you comment on this?
Regards,
Bingley
-----Original Message-----
From: Ding, Pixel
Sent: Wednesday, October 25, 2017 9:11 AM
To: Deucher, Alexander <[email protected]>; Liu, Monk <[email protected]>; Wang, Daniel(Xiaowei) <[email protected]>
Cc: Sun, Gary <[email protected]>; Li, Bingley <[email protected]>; [email protected]
Subject: Re: [PATCH 1/7] drm/amdgpu: release VF exclusive accessing after hw_init
Hi all,
I notice that this change will break KFD init on VF. KFD also load HQD which needs to be done in exclusive mode, otherwise KIQ register accessing causes LOAD VF failed at that time. However if we release EX mode after KFD init, the retry init logic will be quite complicated to handle all failures, also the EX mode time consuming is too much. Any idea?
By now I would drop this change upstream.
—
Sincerely Yours,
Pixel
Quoted 58 lines · Alexander
Quoted 9 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 1/7] drm/amdgpu: release VF exclusive accessing afterhw_initQuoted 3 lines
The subsequent operations don't need exclusive accessing hardware.
Signed-off-by Pixel Ding <[email protected]>Acked-by Alex Deucher <[email protected]>Quoted 43 lines
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 --- 2 files changed, 5 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5
-0@@ -1716,6 +1716,11 @@ static int amdgpu_init(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = true; } +if (amdgpu_sriov_vf (adev)) { +DRM_INFO ("rel_init\n" ); +amdgpu_virt_release_full_gpu (adev, true); + } +return 0 ; }drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +0
-3@@ -171,9 +171,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) pm_runtime_put_autosuspend(dev->dev); } -if (amdgpu_sriov_vf (adev)) -amdgpu_virt_release_full_gpu (adev, true); - out:if (r) {/* balance
pm_runtime_get_syncinamdgpu_driver_unload_kms*/
--
2.9.5
Quoted 4 lines
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 2/7 drm/amdgpu: add init_log param to control logs in exclusive mode
In reply to a message not in the archiveFrom: pding <[email protected]>
When this VF stays in exclusive mode for long, other VFs will be impacted.
The redundant messages causes exclusive mode timeout when they're redirected. That is a normal use case for cloud service to redirect guest log to virtual serial port.
Introduce init_log param to control logs during exclusive mode. The default behavior is not changed. Exclusive time decreases 200ms if log direction is enabled with this change.
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 13 +++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 8 ++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 +++++++++----------- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 10 +++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8 ++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/atom.c | 2 +- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 2 +- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/si_dma.c | 2 +- drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c | 2 +- drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 4 ++-- drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 3 ++- 31 files changed, 82 insertions(+), 66 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu.h +13 -0
@@ -126,6 +126,7 @@ extern int amdgpu_param_buf_per_se;extern int amdgpu_job_hang_limit;extern int amdgpu_lbpw;extern int amdgpu_compute_multipipe; +extern int amdgpu_init_log;#ifdef CONFIG_DRM_AMDGPU_SI extern int amdgpu_si_support;
@@ -134,6 +135,18 @@ extern int amdgpu_si_support;extern int amdgpu_cik_support;#endif +#define INIT_INFO (fmt, ...) \ + do { \ + if (amdgpu_init_log) \ + DRM_INFO(fmt, ##__VA_ARGS__); \ + } while (0) \ + +#define INIT_DEV_INFO (dev, fmt, ...) \ + do { \ + if (amdgpu_init_log) \ + dev_info(dev, fmt, ##__VA_ARGS__); \ + } while (0) \ +#define AMDGPU_DEFAULT_GTT_SIZE_MB 3072ULL/* 3GB by default */ #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000#define AMDGPU_MAX_USEC_TIMEOUT 100000/* 100 ms */
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +4 -4
@@ -690,12 +690,12 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev)le32_to_cpu (firmware_info->info_21.ulDefaultDispEngineClkFreq);/* set a reasonable default for DP */ if (adev->clock.default_dispclk <53900 ) { -DRM_INFO ("Changing default dispclk from %dMhz to 600Mhz\n" , - adev->clock.default_dispclk /100 ); +INIT_INFO ("Changing default dispclk from %dMhz to 600Mhz\n" , + adev->clock.default_dispclk /100 ); adev->clock.default_dispclk =60000 ; }else if (adev->clock.default_dispclk <=60000 ) { -DRM_INFO ("Changing default dispclk from %dMhz to 625Mhz\n" , - adev->clock.default_dispclk /100 ); +INIT_INFO ("Changing default dispclk from %dMhz to 625Mhz\n" , + adev->clock.default_dispclk /100 ); adev->clock.default_dispclk =62500 ; } adev->clock.dp_extclk =
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +9 -11
@@ -613,9 +613,9 @@ void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64 mc->vram_end = mc->vram_start + mc->mc_vram_size -1 ;if (limit && limit < mc->real_vram_size) mc->real_vram_size = limit; -dev_info (adev->dev,"VRAM: %lluM 0x%016llX - 0x%016llX (%lluM used)\n" , - mc->mc_vram_size >>20 , mc->vram_start, - mc->vram_end, mc->real_vram_size >>20 ); +INIT_DEV_INFO (adev->dev,"VRAM: %lluM 0x%016llX - 0x%016llX (%lluM used)\n" , + mc->mc_vram_size >>20 , mc->vram_start, + mc->vram_end, mc->real_vram_size >>20 ); }/**
@@ -650,8 +650,8 @@ void amdgpu_gart_location(struct amdgpu_device *adev, struct amdgpu_mc *mc) mc->gart_start = mc->vram_end +1 ; } mc->gart_end = mc->gart_start + mc->gart_size -1 ; -dev_info (adev->dev,"GTT: %lluM 0x%016llX - 0x%016llX\n" , - mc->gart_size >>20 , mc->gart_start, mc->gart_end); +INIT_DEV_INFO (adev->dev,"GTT: %lluM 0x%016llX - 0x%016llX\n" , + mc->gart_size >>20 , mc->gart_start, mc->gart_end); }/*
@@ -1029,7 +1029,7 @@ static int amdgpu_atombios_init(struct amdgpu_device *adev) atom_card_info->ioreg_read = cail_ioreg_read; atom_card_info->ioreg_write = cail_ioreg_write; }else { -DRM_INFO ("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n" ); +INIT_INFO ("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n" ); atom_card_info->ioreg_read = cail_reg_read; atom_card_info->ioreg_write = cail_reg_write; }
@@ -1716,10 +1716,8 @@ static int amdgpu_init(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = true; } -if (amdgpu_sriov_vf (adev)) { -DRM_INFO ("rel_init\n" ); +if (amdgpu_sriov_vf (adev))amdgpu_virt_release_full_gpu (adev, true); - }return 0 ; }
@@ -2264,14 +2262,14 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = -EINVAL ; goto failed; } -DRM_INFO ("GPU posting now...\n" ); +INIT_INFO ("GPU posting now...\n" ); r =amdgpu_atom_asic_init (adev->mode_info.atom_context);if (r) {dev_err (adev->dev,"gpu post error!\n" ); goto failed; } }else { -DRM_INFO ("GPU post is not needed\n" ); +INIT_INFO ("GPU post is not needed\n" ); }if (adev->is_atom_fw) {
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +4 -0
@@ -128,6 +128,7 @@ int amdgpu_param_buf_per_se = 0;int amdgpu_job_hang_limit =0 ;int amdgpu_lbpw =-1 ;int amdgpu_compute_multipipe =-1 ; +int amdgpu_init_log =1 ;MODULE_PARM_DESC (vramlimit,"Restrict VRAM for testing, in megabytes" );module_param_named (vramlimit, amdgpu_vram_limit, int,0600 );
@@ -280,6 +281,9 @@ module_param_named(lbpw, amdgpu_lbpw, int, 0444);MODULE_PARM_DESC (compute_multipipe,"Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)" );module_param_named (compute_multipipe, amdgpu_compute_multipipe, int,0444 ); +MODULE_PARM_DESC (init_log,"log output during initialization (1 = enable, 0 = disable)" ); +module_param_named (init_log, amdgpu_init_log, int,0444 ); +#ifdef CONFIG_DRM_AMDGPU_SI #if defined(CONFIG_DRM_RADEON ) || defined(CONFIG_DRM_RADEON_MODULE )
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +3 -3
@@ -390,9 +390,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, ring->fence_drv.irq_type = irq_type; ring->fence_drv.initialized = true; -dev_info (adev->dev,"fence driver on ring %d use gpu addr 0x%016llx, " -"cpu addr 0x%p\n" , ring->idx, - ring->fence_drv.gpu_addr, ring->fence_drv.cpu_addr); +INIT_DEV_INFO (adev->dev,"fence driver on ring %d use gpu addr 0x%016llx, " +"cpu addr 0x%p\n" , ring->idx, + ring->fence_drv.gpu_addr, ring->fence_drv.cpu_addr);return 0 ; }
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +2 -2
@@ -370,8 +370,8 @@ int amdgpu_gart_init(struct amdgpu_device *adev)/* Compute table size */ adev->gart.num_cpu_pages = adev->mc.gart_size /PAGE_SIZE ; adev->gart.num_gpu_pages = adev->mc.gart_size /AMDGPU_GPU_PAGE_SIZE ; -DRM_INFO ("GART: num cpu pages %u, num gpu pages %u\n" , - adev->gart.num_cpu_pages, adev->gart.num_gpu_pages); +INIT_INFO ("GART: num cpu pages %u, num gpu pages %u\n" , + adev->gart.num_cpu_pages, adev->gart.num_gpu_pages);#ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS /* Allocate pages table */
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2 -2
@@ -232,7 +232,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)int ret =pci_enable_msi (adev->pdev);if (!ret) { adev->irq.msi_enabled = true; -dev_info (adev->dev,"amdgpu: using MSI.\n" ); +INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); } }
@@ -262,7 +262,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)return r; } -DRM_INFO ("amdgpu: irq initialized.\n" ); +INIT_INFO ("amdgpu: irq initialized.\n" );return 0 ; }
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +5 -5
@@ -778,11 +778,11 @@ int amdgpu_bo_init(struct amdgpu_device *adev)/* Add an MTRR for the VRAM */ adev->mc.vram_mtrr =arch_phys_wc_add (adev->mc.aper_base, adev->mc.aper_size); -DRM_INFO ("Detected VRAM RAM=%lluM, BAR=%lluM\n" , - adev->mc.mc_vram_size >>20 , - (unsigned long long )adev->mc.aper_size >>20 ); -DRM_INFO ("RAM width %dbits %s\n" , - adev->mc.vram_width, amdgpu_vram_names[adev->mc.vram_type]); +INIT_INFO ("Detected VRAM RAM=%lluM, BAR=%lluM\n" , + adev->mc.mc_vram_size >>20 , + (unsigned long long )adev->mc.aper_size >>20 ); +INIT_INFO ("RAM width %dbits %s\n" , + adev->mc.vram_width, amdgpu_vram_names[adev->mc.vram_type]);return amdgpu_ttm_init (adev); }
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +4 -4
@@ -1348,8 +1348,8 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) NULL, NULL);if (r)return r; -DRM_INFO ("amdgpu: %uM of VRAM memory ready\n" , - (unsigned ) (adev->mc.real_vram_size / (1024 *1024 ))); +INIT_INFO ("amdgpu: %uM of VRAM memory ready\n" , + (unsigned ) (adev->mc.real_vram_size / (1024 *1024 )));if (amdgpu_gtt_size ==-1 ) gtt_size = max((AMDGPU_DEFAULT_GTT_SIZE_MB << 20),
@@ -1361,8 +1361,8 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)DRM_ERROR ("Failed initializing GTT heap.\n" );return r; } -DRM_INFO ("amdgpu: %uM of GTT memory ready.\n" , - (unsigned )(gtt_size / (1024 *1024 ))); +INIT_INFO ("amdgpu: %uM of GTT memory ready.\n" , + (unsigned )(gtt_size / (1024 *1024 ))); adev->gds.mem.total_size = adev->gds.mem.total_size <<AMDGPU_GDS_SHIFT ; adev->gds.mem.gfx_partition_size = adev->gds.mem.gfx_partition_size <<AMDGPU_GDS_SHIFT ;
drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +1 -1
@@ -954,7 +954,7 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring) }if (i < timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed\n",
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +2 -2
@@ -261,7 +261,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
@@ -500,7 +500,7 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed\n",
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +3 -3
@@ -2594,9 +2594,9 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size,amdgpu_vm_set_fragment_size (adev, fragment_size_default); -DRM_INFO ("vm size is %llu GB, block size is %u-bit, fragment size is %u-bit\n" , - adev->vm_manager.vm_size, adev->vm_manager.block_size, - adev->vm_manager.fragment_size); +INIT_INFO ("vm size is %llu GB, block size is %u-bit, fragment size is %u-bit\n" , + adev->vm_manager.vm_size, adev->vm_manager.block_size, + adev->vm_manager.fragment_size); }/**
drivers/gpu/drm/amd/amdgpu/atom.c +1 -1
@@ -1344,7 +1344,7 @@ struct atom_context *amdgpu_atom_parse(struct card_info *card, void *bios) str =CSTR (idx);if (*str !='\0' ) { -pr_info ("ATOM BIOS: %s\n" , str); +INIT_INFO ("ATOM BIOS: %s\n" , str);strlcpy (ctx->vbios_version, str,sizeof (ctx->vbios_version)); }
drivers/gpu/drm/amd/amdgpu/cik_sdma.c +1 -1
@@ -657,7 +657,7 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +1 -1
@@ -1798,7 +1798,7 @@ static int gfx_v6_0_ring_test_ring(struct amdgpu_ring *ring)DRM_UDELAY (1 ); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else {DRM_ERROR ("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n" , ring->idx, scratch, tmp);
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +1 -1
@@ -2069,7 +2069,7 @@ static int gfx_v7_0_ring_test_ring(struct amdgpu_ring *ring)DRM_UDELAY (1 ); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else {DRM_ERROR ("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n" , ring->idx, scratch, tmp);
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1 -1
@@ -804,7 +804,7 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)DRM_UDELAY (1 ); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +1 -1
@@ -318,7 +318,7 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)DRM_UDELAY (1 ); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +3 -3
@@ -560,9 +560,9 @@ static int gmc_v6_0_gart_enable(struct amdgpu_device *adev)gmc_v6_0_set_fault_enable_default (adev, true);gmc_v6_0_gart_flush_gpu_tlb (adev,0 ); -dev_info (adev->dev,"PCIE GART of %uM enabled (table at 0x%016llX).\n" , - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long )adev->gart.table_addr); +INIT_DEV_INFO (adev->dev,"PCIE GART of %uM enabled (table at 0x%016llX).\n" , + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long )adev->gart.table_addr); adev->gart.ready = true;return 0 ; }
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +3 -3
@@ -674,9 +674,9 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev) }gmc_v7_0_gart_flush_gpu_tlb (adev,0 ); -DRM_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long )adev->gart.table_addr); +INIT_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long )adev->gart.table_addr); adev->gart.ready = true;return 0 ; }
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +3 -3
@@ -890,9 +890,9 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev)gmc_v8_0_set_fault_enable_default (adev, true);gmc_v8_0_gart_flush_gpu_tlb (adev,0 ); -DRM_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long )adev->gart.table_addr); +INIT_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long )adev->gart.table_addr); adev->gart.ready = true;return 0 ; }
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +3 -3
@@ -756,9 +756,9 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)mmhub_v1_0_set_fault_enable_default (adev, value);gmc_v9_0_gart_flush_gpu_tlb (adev,0 ); -DRM_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long )adev->gart.table_addr); +INIT_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long )adev->gart.table_addr); adev->gart.ready = true;return 0 ; }
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +1 -1
@@ -633,7 +633,7 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +1 -1
@@ -893,7 +893,7 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +1 -1
@@ -919,7 +919,7 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);
drivers/gpu/drm/amd/amdgpu/si_dma.c +1 -1
@@ -252,7 +252,7 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);
drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +1 -1
@@ -521,7 +521,7 @@ static int uvd_v4_2_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +1 -1
@@ -536,7 +536,7 @@ static int uvd_v5_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +2 -2
@@ -184,7 +184,7 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -1010,7 +1010,7 @@ static int uvd_v6_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +2 -2
@@ -184,7 +184,7 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -1198,7 +1198,7 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i); }else { DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
drivers/gpu/drm/amd/powerplay/amd_powerplay.c +2 -1
@@ -29,6 +29,7 @@#include "amd_powerplay.h" #include "pp_instance.h" #include "power_state.h" +#include "amdgpu.h" #define PP_DPM_DISABLED 0xCCCC
@@ -119,7 +120,7 @@ static int pp_sw_init(void *handle) ret = hwmgr->smumgr_funcs->smu_init (hwmgr); -pr_info ("amdgpu: powerplay sw initialized\n" ); +INIT_INFO ("amdgpu: powerplay sw initialized\n" ); }return ret; }
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-3-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 2/7] drm/amdgpu: add init_log param to control logs in exclusive mode
Quoted 14 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 2/7] drm/amdgpu: addinit_logparam to control logs in exclusive modeFrom: pding <[email protected]>
When this VF stays in exclusive mode for long, other VFs will be impacted.
Quoted 7 lines
The redundant messages causes exclusive mode timeout when they're redirected. That is a normal use case for cloud service to redirect guest log to virtual serial port.
Introduce
init_logparam to control logs during exclusive mode. The default behavior is not changed. Exclusive time decreases 200ms if log direction is enabled with this change.
Let's not add another module parameter. It's getting to be a mess. I'd prefer to just make some of these debug only or bare metal only. I think a few others can be dropped. See additional comments below.
Quoted 56 lines
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 13 +++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 8 ++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 +++++++++----------(quoted diff) +0
-1- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 10 +++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8 ++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/atom.c | 2 +- drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 2 +- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/si_dma.c | 2 +- drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c | 2 +- drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 4 ++-- drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 3 ++- 31 files changed, 82 insertions(+), 66 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu.h +3
-0@@ -126,6 +126,7 @@ extern int amdgpu_param_buf_per_se;extern int amdgpu_job_hang_limit;extern int amdgpu_lbpw;extern int amdgpu_compute_multipipe; +extern int amdgpu_init_log;#ifdef CONFIG_DRM_AMDGPU_SI extern int amdgpu_si_support;@@ -134,6 +135,18 @@ extern int amdgpu_si_support;extern int amdgpu_cik_support;#endif +#define INIT_INFO (fmt, ...) \ + do { \
drivers/gpu/drm/amd/amdgpu/amdgpu.h extern int amdgpu_si_support; · line 149
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu.h +10
-0+if (amdgpu_init_log) \ + DRM_INFO(fmt, ##__VA_ARGS__); \ + } while (0) \ + +#define INIT_DEV_INFO (dev, fmt, ...) \ + do { \ + if (amdgpu_init_log) \ + dev_info(dev, fmt, ##__VA_ARGS__); \ + } while (0) \ +
Rather than using a module parameter here, just disable it for SR-IOV.
Quoted 12 lines
drivers/gpu/drm/amd/amdgpu/amdgpu.h +0
-0#define AMDGPU_DEFAULT_GTT_SIZE_MB 3072ULL/* 3GB by default */
#defineAMDGPU_WAIT_IDLE_TIMEOUT_IN_MS3000
#defineAMDGPU_MAX_USEC_TIMEOUT100000 /* 100
ms */drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +0
-0@@ -690,12 +690,12 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev)
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c int amdgpu_atombios_get_clock_info(struct · line 698
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +2
-2le32_to_cpu (firmware_info- >info_21.ulDefaultDispEngineClkFreq);/* set a reasonable default for DP */ if (adev->clock.default_dispclk <53900 ) { -DRM_INFO ("Changing default dispclk from %dMhz to 600Mhz\n", - adev->clock.default_dispclk /100 ); +INIT_INFO ("Changing default dispclk from %dMhz to 600Mhz\n", + adev->clock.default_dispclk /100 );
You can use DRM_DEBUG here.
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev) · line 700
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +0
-1adev->clock.default_dispclk =60000 ; }else if (adev->clock.default_dispclk <=60000 ) { - DRM_INFO("Changing default dispclk from %dMhz to625Mhz\n",
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +1
-1- adev->clock.default_dispclk / 100); + INIT_INFO("Changing default dispclk from %dMhz to625Mhz\n",
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +1
-0+ adev->clock.default_dispclk / 100); adev->clock.default_dispclk =62500 ; }
Same here.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +0
-0adev->clock.dp_extclk =drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -613,9 +613,9 @@ void amdgpu_vram_location(struct amdgpu_device *adev, struct amdgpu_mc *mc, u64 mc->vram_end = mc->vram_start + mc->mc_vram_size - 1;
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c void amdgpu_vram_location(struct amdgpu_device · line 621
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-3if (limit && limit < mc->real_vram_size) mc->real_vram_size = limit; - dev_info(adev->dev, "VRAM: %lluM 0x%016llX - 0x%016llX (%lluM used)\n", - mc->mc_vram_size >>20 , mc->vram_start, - mc->vram_end, mc->real_vram_size >> 20); + INIT_DEV_INFO(adev->dev, "VRAM: %lluM 0x%016llX - 0x%016llX (%lluM used)\n", + mc->mc_vram_size >>20 , mc->vram_start, + mc->vram_end, mc->real_vram_size >> 20);
This one is useful. I'd suggest either dropping this hunk or making it bare metal only.
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c void amdgpu_gart_location(struct amdgpu_device · line 655
Quoted 12 lines
}
/**
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2
-2@@ -650,8 +650,8 @@ void amdgpu_gart_location(struct amdgpu_device *adev, struct amdgpu_mc *mc) mc->gart_start = mc->vram_end +1 ; } mc->gart_end = mc->gart_start + mc->gart_size -1 ; -dev_info (adev->dev,"GTT: %lluM 0x%016llX - 0x%016llX\n" , - mc->gart_size >>20 , mc->gart_start, mc->gart_end); +INIT_DEV_INFO (adev->dev,"GTT: %lluM 0x%016llX - 0x%016llX\n" , + mc->gart_size >>20 , mc->gart_start, mc->gart_end);
Same here.
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_atombios_init(struct · line 1035
Quoted 12 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0}/*
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-1@@ -1029,7 +1029,7 @@ static int amdgpu_atombios_init(struct amdgpu_device *adev) atom_card_info->ioreg_read = cail_ioreg_read; atom_card_info->ioreg_write = cail_ioreg_write; } else { - DRM_INFO("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n"); + INIT_INFO("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n");
This can be changed to DRM_DEBUG.
Quoted 17 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-3atom_card_info->ioreg_read = cail_reg_read; atom_card_info->ioreg_write = cail_reg_write; }@@ -1716,10 +1716,8 @@ static int amdgpu_init(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = true; } -if (amdgpu_sriov_vf (adev)) { -DRM_INFO ("rel_init\n" ); +if (amdgpu_sriov_vf (adev))amdgpu_virt_release_full_gpu (adev, true); - }return 0 ;}
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c int amdgpu_device_init(struct amdgpu_device · line 2266
Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-1@@ -2264,14 +2262,14 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = -EINVAL ; goto failed; } -DRM_INFO ("GPU posting now...\n" ); +INIT_INFO ("GPU posting now...\n" );
This is useful. I'd suggest either dropping this hunk or making it bare metal only.
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c int amdgpu_device_init(struct amdgpu_device *adev, · line 2272
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-1r =amdgpu_atom_asic_init (adev- >mode_info.atom_context);if (r) {dev_err (adev->dev,"gpu post error!\n" ); goto failed; } }else { -DRM_INFO ("GPU post is not needed\n" ); +INIT_INFO ("GPU post is not needed\n" );
This can be dropped.
Quoted 48 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0}drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0if (adev->is_atom_fw) {drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +1
-0@@ -128,6 +128,7 @@ int amdgpu_param_buf_per_se = 0;int amdgpu_job_hang_limit =0 ;int amdgpu_lbpw =-1 ;int amdgpu_compute_multipipe =-1 ; +int amdgpu_init_log =1 ;MODULE_PARM_DESC (vramlimit,"Restrict VRAM for testing, in megabytes");
module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +1
-0@@ -280,6 +281,9 @@ module_param_named(lbpw, amdgpu_lbpw, int, 0444); MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");module_param_named (compute_multipipe, amdgpu_compute_multipipe, int,0444 ); +MODULE_PARM_DESC(init_log, "log output during initialization (1 = enable,0 = disable)");
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +2
-0+module_param_named (init_log, amdgpu_init_log, int,0444 ); +#ifdef CONFIG_DRM_AMDGPU_SI #if defined(CONFIG_DRM_RADEON) ||
defined(CONFIG_DRM_RADEON_MODULE)drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +0
-1@@ -390,9 +390,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, ring->fence_drv.irq_type = irq_type; ring->fence_drv.initialized = true; - dev_info(adev->dev, "fence driver on ring %d use gpu addr0x%016llx, "
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +1
-2-"cpu addr 0x%p\n" , ring->idx, - ring->fence_drv.gpu_addr, ring->fence_drv.cpu_addr); + INIT_DEV_INFO(adev->dev, "fence driver on ring %d use gpu addr0x%016llx, "
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, · line 395
Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +2
-0+"cpu addr 0x%p\n" , ring->idx, + ring->fence_drv.gpu_addr, ring->fence_drv.cpu_addr);
This could be switched to DRM_DEBUG.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +0
-0return 0 ; }drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c int amdgpu_gart_init(struct amdgpu_device *adev) · line 375
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +2
-2@@ -370,8 +370,8 @@ int amdgpu_gart_init(struct amdgpu_device *adev)/* Compute table size */ adev->gart.num_cpu_pages = adev->mc.gart_size /PAGE_SIZE ; adev->gart.num_gpu_pages = adev->mc.gart_size /AMDGPU_GPU_PAGE_SIZE ; -DRM_INFO ("GART: num cpu pages %u, num gpu pages %u\n" , - adev->gart.num_cpu_pages, adev->gart.num_gpu_pages); +INIT_INFO ("GART: num cpu pages %u, num gpu pages %u\n" , + adev->gart.num_cpu_pages, adev->gart.num_gpu_pages);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +0
-0#ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS /* Allocate pages table */ drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c int amdgpu_irq_init(struct amdgpu_device *adev) · line 236
Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +1
-1@@ -232,7 +232,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)int ret =pci_enable_msi (adev->pdev);if (!ret) { adev->irq.msi_enabled = true; -dev_info (adev->dev,"amdgpu: using MSI.\n" ); + INIT_DEV_INFO(adev->dev, "amdgpu: using MSI.\n");
Make this debug only.
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c int amdgpu_irq_init(struct amdgpu_device *adev) · line 265
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +1
-1} }@@ -262,7 +262,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)return r; } -DRM_INFO ("amdgpu: irq initialized.\n" ); +INIT_INFO ("amdgpu: irq initialized.\n" );
Use DRM_DEBUG.
Quoted 14 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +0
-0return 0 ; }drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +0
-2@@ -778,11 +778,11 @@ int amdgpu_bo_init(struct amdgpu_device *adev)/* Add an MTRR for the VRAM */ adev->mc.vram_mtrr =arch_phys_wc_add (adev->mc.aper_base, adev->mc.aper_size); - DRM_INFO("Detected VRAM RAM=%lluM, BAR=%lluM\n", - adev->mc.mc_vram_size >> 20,
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c int amdgpu_bo_init(struct amdgpu_device *adev) · line 787
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +5
-3- (unsigned long long)adev->mc.aper_size >> 20); -DRM_INFO ("RAM width %dbits %s\n" , - adev->mc.vram_width, amdgpu_vram_names[adev- >mc.vram_type]); +INIT_INFO ("Detected VRAM RAM=%lluM, BAR=%lluM\n" , + adev->mc.mc_vram_size >>20 , + (unsigned long long )adev->mc.aper_size >>20 ); +INIT_INFO ("RAM width %dbits %s\n" , + adev->mc.vram_width, amdgpu_vram_names[adev- >mc.vram_type]);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +0
-0return amdgpu_ttm_init (adev);}
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c int amdgpu_ttm_init(struct amdgpu_device *adev) · line 1353
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +2
-2@@ -1348,8 +1348,8 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) NULL, NULL);if (r)return r; -DRM_INFO ("amdgpu: %uM of VRAM memory ready\n" , - (unsigned ) (adev->mc.real_vram_size / (1024 *1024 ))); +INIT_INFO ("amdgpu: %uM of VRAM memory ready\n" , + (unsigned ) (adev->mc.real_vram_size / (1024 *1024 )));
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c int amdgpu_ttm_init(struct amdgpu_device *adev) · line 1366
Quoted 11 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +2
-2if (amdgpu_gtt_size ==-1 ) gtt_size = max((AMDGPU_DEFAULT_GTT_SIZE_MB << 20),@@ -1361,8 +1361,8 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)DRM_ERROR ("Failed initializing GTT heap.\n" );return r; } -DRM_INFO ("amdgpu: %uM of GTT memory ready.\n" , - (unsigned )(gtt_size / (1024 *1024 ))); +INIT_INFO ("amdgpu: %uM of GTT memory ready.\n" , + (unsigned )(gtt_size / (1024 *1024 )));
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +0
-0adev->gds.mem.total_size = adev->gds.mem.total_size <<AMDGPU_GDS_SHIFT ;
adev->gds.mem.gfx_partition_size= adev-Quoted 1 line
gds.mem.gfx_partition_size <<
AMDGPU_GDS_SHIFT;drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c int amdgpu_vce_ring_test_ring(struct amdgpu_ring · line 959
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +1
-1@@ -954,7 +954,7 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring) }if (i < timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +0
-0DRM_ERROR("amdgpu: ring %d test failed\n",drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c int amdgpu_vcn_dec_ring_test_ring(struct · line 266
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +1
-1@@ -261,7 +261,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c int amdgpu_vcn_enc_ring_test_ring(struct · line 504
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +1
-1DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",@@ -500,7 +500,7 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { - DRM_INFO("ring test on %d succeeded in %d usecs\n", + INIT_INFO("ring test on %d succeeded in %d usecs\n",
DRM_DEBUG.
Quoted 22 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +0
-0ring->idx, i); }else {drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +0
-0DRM_ERROR("amdgpu: ring %d test failed\n",drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +1
-3@@ -2594,9 +2594,9 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size,amdgpu_vm_set_fragment_size (adev ,fragment_size_default ); - DRM_INFO("vm size is %llu GB, block size is %u-bit, fragment size is %u-bit\n", - adev->vm_manager.vm_size, adev- >vm_manager.block_size, - adev->vm_manager.fragment_size); + INIT_INFO("vm size is %llu GB, block size is %u-bit, fragment size is%u-bit\n",
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +1
-0+ adev->vm_manager.vm_size, adev-Quoted 1 line
vm_manager.block_size,
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size, · line 2599
Quoted 1 line
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +1
-0+ adev->vm_manager.fragment_size);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
}
/**
drivers/gpu/drm/amd/amdgpu/atom.c +0
-0
drivers/gpu/drm/amd/amdgpu/atom.c struct atom_context *amdgpu_atom_parse(struct · line 1348
Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/atom.c +1
-1@@ -1344,7 +1344,7 @@ struct atom_context *amdgpu_atom_parse(struct card_info *card, void *bios) str =CSTR (idx);if (*str !='\0' ) { -pr_info ("ATOM BIOS: %s\n" , str); +INIT_INFO ("ATOM BIOS: %s\n" , str);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/atom.c +0
-0strlcpy (ctx->vbios_version, str,sizeof (ctx->vbios_version)); }drivers/gpu/drm/amd/amdgpu/cik_sdma.c +0
-0
drivers/gpu/drm/amd/amdgpu/cik_sdma.c static int cik_sdma_ring_test_ring(struct amdgpu_ring · line 663
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/cik_sdma.c +1
-1@@ -657,7 +657,7 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i);
DRM_DEBUG
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/cik_sdma.c +0
-0}else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c static int gfx_v6_0_ring_test_ring(struct · line 1804
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +1
-1@@ -1798,7 +1798,7 @@ static int gfx_v6_0_ring_test_ring(struct amdgpu_ring *ring) DRM_UDELAY(1); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i);
DRM_DEBUG
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +0
-0}else { DRM_ERROR("amdgpu: ring %d test failed(scratch(0x%04X)=0x%08X)\n",
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +0
-0ring->idx, scratch, tmp);drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c static int gfx_v7_0_ring_test_ring(struct · line 2075
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +1
-1@@ -2069,7 +2069,7 @@ static int gfx_v7_0_ring_test_ring(struct amdgpu_ring *ring) DRM_UDELAY(1); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i);
DRM_DEBUG
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0
-0}else { DRM_ERROR("amdgpu: ring %d test failed(scratch(0x%04X)=0x%08X)\n",
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +0
-0ring->idx, scratch, tmp);drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static int gfx_v8_0_ring_test_ring(struct amdgpu_ring · line 809
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1
-1@@ -804,7 +804,7 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)DRM_UDELAY (1 ); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +0
-0}else {DRM_ERROR("amdgpu: ring %d test failed
(scratch(0x%04X)=0x%08X)\n",drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c static int gfx_v9_0_ring_test_ring(struct amdgpu_ring · line 323
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +1
-1@@ -318,7 +318,7 @@ static int gfx_v9_0_ring_test_ring(struct amdgpu_ring *ring)DRM_UDELAY (1 ); }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
Quoted 11 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +0
-0}else {DRM_ERROR("amdgpu: ring %d test failed
(scratch(0x%04X)=0x%08X)\n",drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +0
-0@@ -560,9 +560,9 @@ static int gmc_v6_0_gart_enable(struct amdgpu_device *adev)gmc_v6_0_set_fault_enable_default (adev ,true );
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c static int gmc_v6_0_gart_enable(struct · line 568
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +3
-3gmc_v6_0_gart_flush_gpu_tlb (adev,0 ); - dev_info(adev->dev, "PCIE GART of %uM enabled (table at 0x%016llX).\n", - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long)adev->gart.table_addr); + INIT_DEV_INFO(adev->dev, "PCIE GART of %uM enabled (table at 0x%016llX).\n", + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long)adev->gart.table_addr);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +0
-0adev->gart.ready = true;return 0 ; }drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c static int gmc_v7_0_gart_enable(struct · line 680
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +3
-3@@ -674,9 +674,9 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev) }gmc_v7_0_gart_flush_gpu_tlb (adev,0 ); -DRM_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long )adev->gart.table_addr); +INIT_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long )adev->gart.table_addr);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +0
-0adev->gart.ready = true;return 0 ;}
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c static int gmc_v8_0_gart_enable(struct · line 896
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +3
-3@@ -890,9 +890,9 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev)gmc_v8_0_set_fault_enable_default (adev ,true );gmc_v8_0_gart_flush_gpu_tlb (adev,0 ); -DRM_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long )adev->gart.table_addr); +INIT_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long )adev->gart.table_addr);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +0
-0adev->gart.ready = true;return 0 ;}
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c static int gmc_v9_0_gart_enable(struct · line 762
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +3
-3@@ -756,9 +756,9 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)mmhub_v1_0_set_fault_enable_default (adev ,value );gmc_v9_0_gart_flush_gpu_tlb (adev,0 ); -DRM_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , - (unsigned )(adev->mc.gart_size >>20 ), - (unsigned long long )adev->gart.table_addr); +INIT_INFO ("PCIE GART of %uM enabled (table at 0x%016llX).\n" , + (unsigned )(adev->mc.gart_size >>20 ), + (unsigned long long )adev->gart.table_addr);
This is also useful. I'd suggest either dropping this hunk or making it bare metal only.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +0
-0adev->gart.ready = true;return 0 ;}
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +0
-0
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c static int sdma_v2_4_ring_test_ring(struct · line 639
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +1
-1@@ -633,7 +633,7 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i);
DRM_DEBUG
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +0
-0}else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c static int sdma_v3_0_ring_test_ring(struct · line 899
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +1
-1@@ -893,7 +893,7 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i);
DRM_DEBUG.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +0
-0}else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c static int sdma_v4_0_ring_test_ring(struct · line 925
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +1
-1@@ -919,7 +919,7 @@ static int sdma_v4_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i);
DRM_DEBUG.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +0
-0}else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);drivers/gpu/drm/amd/amdgpu/si_dma.c +0
-0
drivers/gpu/drm/amd/amdgpu/si_dma.c static int si_dma_ring_test_ring(struct amdgpu_ring · line 258
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/si_dma.c +1
-1@@ -252,7 +252,7 @@ static int si_dma_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i); +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring- >idx, i);
DRM_DEBUG.
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/si_dma.c +0
-0}else {DRM_ERROR ("amdgpu: ring %d test failed (0x%08X)\n" , ring->idx, tmp);drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +0
-0
drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c static int uvd_v4_2_ring_test_ring(struct · line 526
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +1
-1@@ -521,7 +521,7 @@ static int uvd_v4_2_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +0
-0DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c static int uvd_v5_0_ring_test_ring(struct · line 541
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +1
-1@@ -536,7 +536,7 @@ static int uvd_v5_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +0
-0DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c static int uvd_v6_0_enc_ring_test_ring(struct · line 189
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +1
-1@@ -184,7 +184,7 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c static int uvd_v6_0_ring_test_ring(struct · line 1015
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +1
-1DRM_ERROR("amdgpu: ring %d test failed\n",@@ -1010,7 +1010,7 @@ static int uvd_v6_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +0
-0DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c static int uvd_v7_0_enc_ring_test_ring(struct · line 189
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +1
-1@@ -184,7 +184,7 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c static int uvd_v7_0_ring_test_ring(struct · line 1203
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +1
-1DRM_ERROR("amdgpu: ring %d test failed\n",@@ -1198,7 +1198,7 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring) }if (i < adev->usec_timeout) { -DRM_INFO ("ring test on %d succeeded in %d usecs\n" , +INIT_INFO ("ring test on %d succeeded in %d usecs\n" , ring->idx, i);
DRM_DEBUG.
Quoted 16 lines
drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +0
-0}else {drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +0
-0DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",drivers/gpu/drm/amd/powerplay/amd_powerplay.c +1
-0@@ -29,6 +29,7 @@#include "amd_powerplay.h" #include "pp_instance.h" #include "power_state.h" +#include "amdgpu.h" #define PP_DPM_DISABLED 0xCCCC
drivers/gpu/drm/amd/powerplay/amd_powerplay.c static int pp_sw_init(void *handle) · line 123
Quoted 5 lines
drivers/gpu/drm/amd/powerplay/amd_powerplay.c +1
-1@@ -119,7 +120,7 @@ static int pp_sw_init(void *handle) ret = hwmgr->smumgr_funcs->smu_init (hwmgr); -pr_info ("amdgpu: powerplay sw initialized\n" ); +INIT_INFO ("amdgpu: powerplay sw initialized\n" );
Debug.
Quoted 10 lines
drivers/gpu/drm/amd/powerplay/amd_powerplay.c +0
-1}return ret; } --2.9.5
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 3/7 drm/amdgpu: avoid soft lockup when waiting for RLC serdes
In reply to a message not in the archiveFrom: pding <[email protected]>
Normally all waiting get timeout if there's one. Release the lock and return immediately when timeout happens.
--- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 ++++++ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 ++++++ 2 files changed, 12 insertions(+)
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +6 -0
@@ -3842,6 +3842,12 @@ static void gfx_v8_0_wait_for_rlc_serdes(struct amdgpu_device *adev)break ;udelay (1 ); } +if (k == adev->usec_timeout) { +mutex_unlock (&adev->grbm_idx_mutex); +DRM_INFO ("Timeout wait for RLC serdes %u,%u\n" , + i, j); +return ; + } } }gfx_v8_0_select_se_sh (adev,0xffffffff ,0xffffffff ,0xffffffff );
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +6 -0
@@ -1628,6 +1628,12 @@ static void gfx_v9_0_wait_for_rlc_serdes(struct amdgpu_device *adev)break ;udelay (1 ); } +if (k == adev->usec_timeout) { +mutex_unlock (&adev->grbm_idx_mutex); +DRM_INFO ("Timeout wait for RLC serdes %u,%u\n" , + i, j); +return ; + } } }gfx_v9_0_select_se_sh (adev,0xffffffff ,0xffffffff ,0xffffffff );
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-4-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 3/7] drm/amdgpu: avoid soft lockup when waiting for RLC serdes
Quoted 28 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 3/7] drm/amdgpu: avoid soft lockup when waiting for RLC serdesFrom: pding <[email protected]>
Normally all waiting get timeout if there's one. Release the lock and return immediately when timeout happens.
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 6 ++++++ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 ++++++ 2 files changed, 12 insertions(+)drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c static void gfx_v8_0_wait_for_rlc_serdes(struct · line 3846
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +1
-0@@ -3842,6 +3842,12 @@ static void gfx_v8_0_wait_for_rlc_serdes(struct amdgpu_device *adev) break;udelay (1 ); } +if (k == adev->usec_timeout) {
Please reset the se_sh to broadcast here as well. gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
Quoted 15 lines
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +5
-0+mutex_unlock (&adev->grbm_idx_mutex); + DRM_INFO("Timeout wait for RLC serdes %u,%u\n", + i, j); +return ; + } }drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +0
-0}gfx_v8_0_select_se_sh (adev,0xffffffff ,0xffffffff ,0xffffffff );drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +0
-0
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c static void gfx_v9_0_wait_for_rlc_serdes(struct · line 1632
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +1
-0@@ -1628,6 +1628,12 @@ static void gfx_v9_0_wait_for_rlc_serdes(struct amdgpu_device *adev) break;udelay (1 ); } +if (k == adev->usec_timeout) {
Same here.
Quoted 12 lines
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +5
-0+mutex_unlock (&adev->grbm_idx_mutex); + DRM_INFO("Timeout wait for RLC serdes %u,%u\n", + i, j); +return ; + } }drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +0
-1}gfx_v9_0_select_se_sh (adev,0xffffffff ,0xffffffff ,0xffffffff ); --2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 4/7 drm/amdgpu/virt: add function to check MMIO accessing
In reply to a message not in the archiveFrom: pding <[email protected]>
MMIO space can be blocked on virtualised device. Add this function to check if MMIO is blocked or not.
Todo: need a reliable method such like communation with hypervisor.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 + 2 files changed, 6 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +5 -0
@@ -24,6 +24,11 @@#include "amdgpu.h" #define MAX_KIQ_REG_WAIT 100000000/* in usecs */ +bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev) +{ +return RREG32_NO_KIQ (0xc040 ) ==0xffffffff ; +} +int amdgpu_allocate_static_csa (struct amdgpu_device *adev) {int r;
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +1 -0
@@ -276,6 +276,7 @@ static inline bool is_virtual_machine(void) }struct amdgpu_vm ; +bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev);int amdgpu_allocate_static_csa (struct amdgpu_device *adev);int amdgpu_map_static_csa (struct amdgpu_device *adev,struct amdgpu_vm *vm,struct amdgpu_bo_va **bo_va);
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-5-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessing
Quoted 28 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessingFrom: pding <[email protected]>
MMIO space can be blocked on virtualised device. Add this function to check if MMIO is blocked or not.
Todo: need a reliable method such like communation with hypervisor.
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 + 2 files changed, 6 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c line 30
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +4
-0@@ -24,6 +24,11 @@#include "amdgpu.h" #define MAX_KIQ_REG_WAIT 100000000/* in usecs */ +bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev) +{ +return RREG32_NO_KIQ (0xc040 ) ==0xffffffff ; +}
Is this safe? Won't accessing non-instanced registers cause a problem? Probably also worth commenting that register this is and a note for future asics in case the register map changes.
Alex
Quoted 21 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +1
-0+int amdgpu_allocate_static_csa (struct amdgpu_device *adev) {int r;drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +1
-0@@ -276,6 +276,7 @@ static inline bool is_virtual_machine(void) }struct amdgpu_vm ; +bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev);int amdgpu_allocate_static_csa (struct amdgpu_device *adev); int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,struct
amdgpu_bo_va**bo_va);
--
2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BN6PR12MB165261DE3E8A751BD8250C77F7460-/b2+HYfkarQqUD6E6FAiowdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org
Re: [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessing
It works with current MMIO blocking policy, while all pages are blocked expect the one containing mailbox registers. But actually it’s not a good approach, as commented we should add interaction between host and guest for MMIO blocking check in future.
By now I can add more comments here, is it OK?
—
Sincerely Yours,
Pixel
Quoted 61 lines · Alexander
Quoted 28 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessingFrom: pding <[email protected]>
MMIO space can be blocked on virtualised device. Add this function to check if MMIO is blocked or not.
Todo: need a reliable method such like communation with hypervisor.
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 + 2 files changed, 6 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +0
-0drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c line 30
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +4
-0@@ -24,6 +24,11 @@#include "amdgpu.h" #define MAX_KIQ_REG_WAIT 100000000/* in usecs */ +bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev) +{ +return RREG32_NO_KIQ (0xc040 ) ==0xffffffff ; +}Is this safe? Won't accessing non-instanced registers cause a problem? Probably also worth commenting that register this is and a note for future asics in case the register map changes.
Alex
Quoted 21 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +1
-0+int amdgpu_allocate_static_csa (struct amdgpu_device *adev) {int r;drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +1
-0@@ -276,6 +276,7 @@ static inline bool is_virtual_machine(void) }struct amdgpu_vm ; +bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev);int amdgpu_allocate_static_csa (struct amdgpu_device *adev); int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,struct
amdgpu_bo_va**bo_va);
--
2.9.5
Quoted 4 lines
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): F836DB5B-E4E7-4593-A838-FB852B50510B-5C7GfCeVMHo@public.gmane.org
Deucher, Alexander
Acked-by Alex DeucherRE: [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessing
Quoted 8 lines
-----Original Message-----
From: Ding, Pixel
Sent: Monday, October 23, 2017 9:43 PM
To: Deucher, Alexander; [email protected]
Cc: Sun, Gary; Li, Bingley
Subject: Re: [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessing
Quoted 6 lines
It works with current MMIO blocking policy, while all pages are blocked expect the one containing mailbox registers. But actually it’s not a good approach, as commented we should add interaction between host and guest for MMIO blocking check in future.
By now I can add more comments here, is it OK?
Please add a comment that mentions what register this is. With that fixed the patch is:
Quoted 77 lines
—
Sincerely Yours,
PixelQuoted 2 lines · Alexander
Quoted 2 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] OnBehalf
Quoted 29 lines
Quoted 29 lines
Of Pixel Ding
Sent: Monday, October 23, 2017 6:03 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 4/7] drm/amdgpu/virt: add function to check MMIO accessingFrom: pding <[email protected]>
MMIO space can be blocked on virtualised device. Add this function to check if MMIO is blocked or not.
Todo: need a reliable method such like communation with hypervisor.
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 5 +++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 + 2 files changed, 6 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +0
-0@@ -24,6 +24,11 @@#include "amdgpu.h" #define MAX_KIQ_REG_WAIT 100000000/* in usecs */ Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c line 30
Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +4
-0+bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev) +{ +return RREG32_NO_KIQ (0xc040 ) ==0xffffffff ; +}Is this safe? Won't accessing non-instanced registers cause a problem?
Probably also worth commenting that register this is and a note for future asics in case the register map changes.
Quoted 24 lines
Alex
Quoted 21 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +1
-0+int amdgpu_allocate_static_csa (struct amdgpu_device *adev) {int r;drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +1
-0@@ -276,6 +276,7 @@ static inline bool is_virtual_machine(void) }struct amdgpu_vm ; +bool amdgpu_virt_mmio_blocked (struct amdgpu_device *adev);int amdgpu_allocate_static_csa (struct amdgpu_device *adev); int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,struct
amdgpu_bo_va**bo_va);
--
2.9.5
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 5/7 drm/amdgpu: don't disable MSI for GPU virtual function
In reply to a message not in the archiveFrom: pding <[email protected]>
After calling pci_disable_msi() and pci_enable_msi(), VF can't receive interrupt anymore. This may introduce problems in module reloading or retrying init.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2 -3
@@ -229,8 +229,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev) adev->irq.msi_enabled = false;if (amdgpu_msi_ok (adev)) { -int ret =pci_enable_msi (adev->pdev); -if (!ret) { +if (adev->pdev->msi_enabled || !pci_enable_msi (adev->pdev)) { adev->irq.msi_enabled = true;INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); }
@@ -280,7 +279,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)if (adev->irq.installed) {drm_irq_uninstall (adev->ddev); adev->irq.installed = false; -if (adev->irq.msi_enabled) +if (adev->irq.msi_enabled && !amdgpu_sriov_vf (adev))pci_disable_msi (adev->pdev);flush_work (&adev->hotplug_work);cancel_work_sync (&adev->reset_work);
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-6-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
Please check commit "5248e3d9", your issue should already be fixed by that patch, please verify
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
From: pding <[email protected]>
After calling pci_disable_msi() and pci_enable_msi(), VF can't receive interrupt anymore. This may introduce problems in module reloading or retrying init.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2 -3
@@ -229,8 +229,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev) adev->irq.msi_enabled = false;if (amdgpu_msi_ok (adev)) { -int ret =pci_enable_msi (adev->pdev); -if (!ret) { +if (adev->pdev->msi_enabled || !pci_enable_msi (adev->pdev)) { adev->irq.msi_enabled = true;INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); }
@@ -280,7 +279,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)if (adev->irq.installed) {drm_irq_uninstall (adev->ddev); adev->irq.installed = false; -if (adev->irq.msi_enabled) +if (adev->irq.msi_enabled && !amdgpu_sriov_vf (adev))pci_disable_msi (adev->pdev);flush_work (&adev->hotplug_work);cancel_work_sync (&adev->reset_work);
--
2.9.5
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BLUPR12MB04494B5ECC666B264207A24A84460-7LeqcoF/[email protected]
Re: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
Tested with 5248e3d9, however issue is still reproduced in reinit case.
+Jack,
To bypass MSI enable/disable for reinit, any comment? —
Sincerely Yours,
Pixel
Quoted 44 lines · Monk
Please check commit "
5248e3d9", your issue should already be fixed by that patch, please verify-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual functionFrom: pding <[email protected]>
After calling
pci_disable_msi()andpci_enable_msi(), VF can't receive interrupt anymore. This may introduce problems in module reloading or retrying init.Signed-off-by pding <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c| 5 ++---1 file changed, 2 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2
-4@@ -229,8 +229,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev) adev->irq.msi_enabled = false;if (amdgpu_msi_ok (adev)) { -int ret =pci_enable_msi (adev->pdev); -if (!ret) { +if (adev->pdev->msi_enabled || !pci_enable_msi (adev->pdev)) { adev->irq.msi_enabled = true;INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); }@@ -280,7 +279,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)if (adev->irq.installed) {drm_irq_uninstall (adev->ddev); adev->irq.installed = false; -if (adev->irq.msi_enabled) +if (adev->irq.msi_enabled && !amdgpu_sriov_vf (adev))pci_disable_msi (adev->pdev);flush_work (&adev->hotplug_work);cancel_work_sync (&adev->reset_work); --2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 2237B231-2EE3-4DDE-9C55-71FF3F589D40-5C7GfCeVMHo@public.gmane.org
Re: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
Sorry for the misunderstanding. Will test with similar fix instead of 5248e3d9 directly later.
—
Sincerely Yours,
Pixel
Quoted 60 lines · Pixel
Tested with
5248e3d9, however issue is still reproduced in reinit case.+Jack,
To bypass MSI enable/disable for reinit, any comment? —
Sincerely Yours,
PixelQuoted 44 lines · Monk
Please check commit "
5248e3d9", your issue should already be fixed by that patch, please verify-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual functionFrom: pding <[email protected]>
After calling
pci_disable_msi()andpci_enable_msi(), VF can't receive interrupt anymore. This may introduce problems in module reloading or retrying init.Signed-off-by pding <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c| 5 ++---1 file changed, 2 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2
-4@@ -229,8 +229,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev) adev->irq.msi_enabled = false;if (amdgpu_msi_ok (adev)) { -int ret =pci_enable_msi (adev->pdev); -if (!ret) { +if (adev->pdev->msi_enabled || !pci_enable_msi (adev->pdev)) { adev->irq.msi_enabled = true;INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); }@@ -280,7 +279,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)if (adev->irq.installed) {drm_irq_uninstall (adev->ddev); adev->irq.installed = false; -if (adev->irq.msi_enabled) +if (adev->irq.msi_enabled && !amdgpu_sriov_vf (adev))pci_disable_msi (adev->pdev);flush_work (&adev->hotplug_work);cancel_work_sync (&adev->reset_work); --2.9.5
Quoted 4 lines
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
RE: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
In reply to a message not in the archiveCan you try call pci_disable_device once you found init failed, and make sure it is called before re-init
-----Original Message-----
From: Ding, Pixel
Sent: 2017年10月24日 9:31
To: Liu, Monk <[email protected]>; [email protected]; Xiao, Jack <[email protected]>
Cc: Sun, Gary <[email protected]>; Li, Bingley <[email protected]>
Subject: Re: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
Tested with 5248e3d9, however issue is still reproduced in reinit case.
+Jack,
To bypass MSI enable/disable for reinit, any comment? —
Sincerely Yours,
Pixel
Quoted 44 lines · Monk
Please check commit "
5248e3d9", your issue should already be fixed by that patch, please verify-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual functionFrom: pding <[email protected]>
After calling
pci_disable_msi()andpci_enable_msi(), VF can't receive interrupt anymore. This may introduce problems in module reloading or retrying init.Signed-off-by pding <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c| 5 ++---1 file changed, 2 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2
-4@@ -229,8 +229,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev) adev->irq.msi_enabled = false;if (amdgpu_msi_ok (adev)) { -int ret =pci_enable_msi (adev->pdev); -if (!ret) { +if (adev->pdev->msi_enabled || !pci_enable_msi (adev->pdev)) { adev->irq.msi_enabled = true;INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); }@@ -280,7 +279,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)if (adev->irq.installed) {drm_irq_uninstall (adev->ddev); adev->irq.installed = false; -if (adev->irq.msi_enabled) +if (adev->irq.msi_enabled && !amdgpu_sriov_vf (adev))pci_disable_msi (adev->pdev);flush_work (&adev->hotplug_work);cancel_work_sync (&adev->reset_work); --2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): SN1PR12MB04627B3E054A9BF1D3408CAA84470-z7L1TMIYDg7VaWpRXmIMygdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org
Re: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
Tried but still fail. Meanwhile I also think it’s not good to disable device here since we only redo the amdgpu_device_init for exclusive mode timeout.
—
Sincerely Yours,
Pixel
Quoted 70 lines · Monk
Can you try call
pci_disable_deviceonce you found init failed, and make sure it is called before re-init-----Original Message-----
From: Ding, Pixel
Sent: 2017年10月24日 9:31
To: Liu, Monk <[email protected]>; [email protected]; Xiao, Jack <[email protected]>
Cc: Sun, Gary <[email protected]>; Li, Bingley <[email protected]>
Subject: Re: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual functionTested with
5248e3d9, however issue is still reproduced in reinit case.+Jack,
To bypass MSI enable/disable for reinit, any comment? —
Sincerely Yours,
PixelQuoted 44 lines · Monk
Please check commit "
5248e3d9", your issue should already be fixed by that patch, please verify-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual functionFrom: pding <[email protected]>
After calling
pci_disable_msi()andpci_enable_msi(), VF can't receive interrupt anymore. This may introduce problems in module reloading or retrying init.Signed-off-by pding <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c| 5 ++---1 file changed, 2 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2
-4@@ -229,8 +229,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev) adev->irq.msi_enabled = false;if (amdgpu_msi_ok (adev)) { -int ret =pci_enable_msi (adev->pdev); -if (!ret) { +if (adev->pdev->msi_enabled || !pci_enable_msi (adev->pdev)) { adev->irq.msi_enabled = true;INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); }@@ -280,7 +279,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)if (adev->irq.installed) {drm_irq_uninstall (adev->ddev); adev->irq.installed = false; -if (adev->irq.msi_enabled) +if (adev->irq.msi_enabled && !amdgpu_sriov_vf (adev))pci_disable_msi (adev->pdev);flush_work (&adev->hotplug_work);cancel_work_sync (&adev->reset_work); --2.9.5
Quoted 4 lines
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): E41D1A06-AB17-4BF4-B98A-CF0B79ABD814-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
One thing I'm concerned is whether you patch will break the kmd reload functional, but since the latest staging already broken on reload, you won't get chance to Verify your patch ....
If you have bandwidth you can try applying your patch on our private customer branch ,and see if the driver reloading still works or not.
BR Monk
-----Original Message-----
From: Ding, Pixel
Sent: 2017年10月24日 15:52
To: Liu, Monk <[email protected]>; [email protected]; Xiao, Jack <[email protected]>
Cc: Sun, Gary <[email protected]>; Li, Bingley <[email protected]>
Subject: Re: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual function
Tried but still fail. Meanwhile I also think it’s not good to disable device here since we only redo the amdgpu_device_init for exclusive mode timeout.
—
Sincerely Yours,
Pixel
Quoted 70 lines · Monk
Can you try call
pci_disable_deviceonce you found init failed, and make sure it is called before re-init-----Original Message-----
From: Ding, Pixel
Sent: 2017年10月24日 9:31
To: Liu, Monk <[email protected]>; [email protected]; Xiao, Jack <[email protected]>
Cc: Sun, Gary <[email protected]>; Li, Bingley <[email protected]>
Subject: Re: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual functionTested with
5248e3d9, however issue is still reproduced in reinit case.+Jack,
To bypass MSI enable/disable for reinit, any comment? —
Sincerely Yours,
PixelQuoted 44 lines · Monk
Please check commit "
5248e3d9", your issue should already be fixed by that patch, please verify-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 5/7] drm/amdgpu: don't disable MSI for GPU virtual functionFrom: pding <[email protected]>
After calling
pci_disable_msi()andpci_enable_msi(), VF can't receive interrupt anymore. This may introduce problems in module reloading or retrying init.Signed-off-by pding <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c| 5 ++---1 file changed, 2 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +2
-4@@ -229,8 +229,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev) adev->irq.msi_enabled = false;if (amdgpu_msi_ok (adev)) { -int ret =pci_enable_msi (adev->pdev); -if (!ret) { +if (adev->pdev->msi_enabled || !pci_enable_msi (adev->pdev)) { adev->irq.msi_enabled = true;INIT_DEV_INFO (adev->dev,"amdgpu: using MSI.\n" ); }@@ -280,7 +279,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)if (adev->irq.installed) {drm_irq_uninstall (adev->ddev); adev->irq.installed = false; -if (adev->irq.msi_enabled) +if (adev->irq.msi_enabled && !amdgpu_sriov_vf (adev))pci_disable_msi (adev->pdev);flush_work (&adev->hotplug_work);cancel_work_sync (&adev->reset_work); --2.9.5
Quoted 4 lines
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 6/7 drm/amdgpu/virt: add wait_reset virt ops
In reply to a message not in the archiveFrom: pding <[email protected]>
Driver can use this interface to check if there's a function level reset done in hypervisor.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 16 ++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 ++ drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 1 + drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 6 ++++++ 4 files changed, 25 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +16 -0
@@ -231,6 +231,22 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev) }/** +* amdgpu_virt_wait_reset() - wait for reset gpu completed +* @amdgpu: amdgpu device. +* Wait for GPU reset completed. +* Return: Zero if reset success, otherwise will return error. +*/ +int amdgpu_virt_wait_reset (struct amdgpu_device *adev) +{ +struct amdgpu_virt *virt = &adev->virt; + +if (!virt->ops || !virt->ops->wait_reset) +return -EINVAL ; + +return virt->ops->wait_reset (adev); +} + +/** * amdgpu_virt_alloc_mm_table() - alloc memory for mm table * @amdgpu: amdgpu device. * MM table is used by UVD and VCE for its initialization
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +2 -0
@@ -55,6 +55,7 @@ struct amdgpu_virt_ops {int (*req_full_gpu)(struct amdgpu_device *adev,bool init);int (*rel_full_gpu)(struct amdgpu_device *adev,bool init);int (*reset_gpu)(struct amdgpu_device *adev); +int (*wait_reset)(struct amdgpu_device *adev);void (*trans_msg)(struct amdgpu_device *adev,u32 req,u32 data1,u32 data2,u32 data3); };
@@ -286,6 +287,7 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);int amdgpu_virt_request_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_release_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_reset_gpu (struct amdgpu_device *adev); +int amdgpu_virt_wait_reset (struct amdgpu_device *adev);int amdgpu_sriov_gpu_reset (struct amdgpu_device *adev,struct amdgpu_job *job);int amdgpu_virt_alloc_mm_table (struct amdgpu_device *adev);void amdgpu_virt_free_mm_table (struct amdgpu_device *adev);
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +1 -0
@@ -353,5 +353,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .req_full_gpu = xgpu_ai_request_full_gpu_access, .rel_full_gpu = xgpu_ai_release_full_gpu_access, .reset_gpu = xgpu_ai_request_reset, + .wait_reset = NULL, .trans_msg = xgpu_ai_mailbox_trans_msg, };
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +6 -0
@@ -458,6 +458,11 @@ static int xgpu_vi_request_reset(struct amdgpu_device *adev)return xgpu_vi_send_access_requests (adev,IDH_REQ_GPU_RESET_ACCESS ); } +static int xgpu_vi_wait_reset_cmpl (struct amdgpu_device *adev) +{ +return xgpu_vi_poll_msg (adev,IDH_FLR_NOTIFICATION_CMPL ); +} +static int xgpu_vi_request_full_gpu_access (struct amdgpu_device *adev,bool init) {
@@ -613,5 +618,6 @@ const struct amdgpu_virt_ops xgpu_vi_virt_ops = { .req_full_gpu = xgpu_vi_request_full_gpu_access, .rel_full_gpu = xgpu_vi_release_full_gpu_access, .reset_gpu = xgpu_vi_request_reset, + .wait_reset = xgpu_vi_wait_reset_cmpl, .trans_msg = NULL, /* Does not need to trans VF errors to host. */ };
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-7-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops
I don't see this is a necessary patch, driver already have the implement to check if VF FLR is completed or not, see "xgpu_ai/vi_mailbox_flr_work()"
Driver won't do gpu reset until this function received the NOTIFICATION_CMPL message
Do you have any particular reason to add this wait_reset ? if so please send out the patch that use this interface
BR Monk
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops
From: pding <[email protected]>
Driver can use this interface to check if there's a function level reset done in hypervisor.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 16 ++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 ++ drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 1 + drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 6 ++++++ 4 files changed, 25 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +15 -0
@@ -231,6 +231,22 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev) }/** +* amdgpu_virt_wait_reset() - wait for reset gpu completed +* @amdgpu: amdgpu device. +* Wait for GPU reset completed. +* Return: Zero if reset success, otherwise will return error. +*/ +int amdgpu_virt_wait_reset (struct amdgpu_device *adev) { +struct amdgpu_virt *virt = &adev->virt; + +if (!virt->ops || !virt->ops->wait_reset) +return -EINVAL ; + +return virt->ops->wait_reset (adev); +} + +/** * amdgpu_virt_alloc_mm_table() - alloc memory for mm table * @amdgpu: amdgpu device. * MM table is used by UVD and VCE for its initialization diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 81efb9d..d149aca 100644
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +2 -0
@@ -55,6 +55,7 @@ struct amdgpu_virt_ops {int (*req_full_gpu)(struct amdgpu_device *adev,bool init);int (*rel_full_gpu)(struct amdgpu_device *adev,bool init);int (*reset_gpu)(struct amdgpu_device *adev); +int (*wait_reset)(struct amdgpu_device *adev);void (*trans_msg)(struct amdgpu_device *adev,u32 req,u32 data1,u32 data2,u32 data3); };
@@ -286,6 +287,7 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v); int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init); int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init); int amdgpu_virt_reset_gpu(struct amdgpu_device *adev); +int amdgpu_virt_wait_reset (struct amdgpu_device *adev); int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job); int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev); void amdgpu_virt_free_mm_table(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index b4906d2..f91aab3 100644
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +1 -0
@@ -353,5 +353,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .req_full_gpu = xgpu_ai_request_full_gpu_access, .rel_full_gpu = xgpu_ai_release_full_gpu_access, .reset_gpu = xgpu_ai_request_reset, + .wait_reset = NULL, .trans_msg = xgpu_ai_mailbox_trans_msg, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index c25a831..27b03c7 100644
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +4 -0
@@ -458,6 +458,11 @@ static int xgpu_vi_request_reset(struct amdgpu_device *adev)return xgpu_vi_send_access_requests (adev,IDH_REQ_GPU_RESET_ACCESS ); } +static int xgpu_vi_wait_reset_cmpl (struct amdgpu_device *adev) { +return xgpu_vi_poll_msg (adev,IDH_FLR_NOTIFICATION_CMPL ); } +static int xgpu_vi_request_full_gpu_access (struct amdgpu_device *adev,bool init) {
@@ -613,5 +618,6 @@ const struct amdgpu_virt_ops xgpu_vi_virt_ops = { .req_full_gpu = xgpu_vi_request_full_gpu_access, .rel_full_gpu = xgpu_vi_release_full_gpu_access, .reset_gpu = xgpu_vi_request_reset, + .wait_reset = xgpu_vi_wait_reset_cmpl, .trans_msg = NULL, /* Does not need to trans VF errors to host. */ };
--
2.9.5
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BLUPR12MB0449ECFA70529779A41D856D84460-7LeqcoF/[email protected]
Re: [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops
This is for retry init.
If the driver fails before late_init, the IRQ handler is not registered then. We need to know if the FLR is done at this point. I think maybe we also can leverage this interface to handle some special cases in future. Any concern about it? —
Sincerely Yours,
Pixel
Quoted 95 lines · Monk
I don't see this is a necessary patch, driver already have the implement to check if VF FLR is completed or not, see "xgpu_ai/vi_mailbox_flr_work()"
Driver won't do gpu reset until this function received the
NOTIFICATION_CMPLmessageDo you have any particular reason to add this
wait_reset? if so please send out the patch that use this interfaceBR Monk
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 6/7] drm/amdgpu/virt: addwait_resetvirt opsFrom: pding <[email protected]>
Driver can use this interface to check if there's a function level reset done in hypervisor.
Signed-off-by pding <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 16 ++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 ++ drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 1 + drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 6 ++++++ 4 files changed, 25 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +15
-0@@ -231,6 +231,22 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev) }/** +* amdgpu_virt_wait_reset() - wait for reset gpu completed +* @amdgpu: amdgpu device. +* Wait for GPU reset completed. +* Return: Zero if reset success, otherwise will return error. +*/ +int amdgpu_virt_wait_reset (struct amdgpu_device *adev) { +struct amdgpu_virt *virt = &adev->virt; + +if (!virt->ops || !virt->ops->wait_reset) +return -EINVAL ; + +return virt->ops->wait_reset (adev); +} + +/** * amdgpu_virt_alloc_mm_table() - alloc memory for mm table * @amdgpu: amdgpu device. * MM table is used by UVD and VCE for its initialization diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 81efb9d..d149aca 100644
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +2
-0@@ -55,6 +55,7 @@ struct amdgpu_virt_ops {int (*req_full_gpu)(struct amdgpu_device *adev,bool init);int (*rel_full_gpu)(struct amdgpu_device *adev,bool init);int (*reset_gpu)(struct amdgpu_device *adev); +int (*wait_reset)(struct amdgpu_device *adev);void (*trans_msg)(struct amdgpu_device *adev,u32 req,u32 data1,u32 data2,u32 data3); };@@ -286,6 +287,7 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v); int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init); int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init); int amdgpu_virt_reset_gpu(struct amdgpu_device *adev); +int amdgpu_virt_wait_reset (struct amdgpu_device *adev);int
amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job); intamdgpu_virt_alloc_mm_table(struct amdgpu_device *adev); voidamdgpu_virt_free_mm_table(struct amdgpu_device *adev); diff --gita/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.cb/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.cindex b4906d2..f91aab3 100644drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +1
-0@@ -353,5 +353,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .req_full_gpu = xgpu_ai_request_full_gpu_access, .rel_full_gpu = xgpu_ai_release_full_gpu_access, .reset_gpu = xgpu_ai_request_reset, + .wait_reset = NULL, .trans_msg = xgpu_ai_mailbox_trans_msg, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.cindex c25a831..27b03c7 100644
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +4
-1@@ -458,6 +458,11 @@ static int xgpu_vi_request_reset(struct amdgpu_device *adev)return xgpu_vi_send_access_requests (adev,IDH_REQ_GPU_RESET_ACCESS ); } +static int xgpu_vi_wait_reset_cmpl (struct amdgpu_device *adev) { +return xgpu_vi_poll_msg (adev,IDH_FLR_NOTIFICATION_CMPL ); } +static int xgpu_vi_request_full_gpu_access (struct amdgpu_device *adev,bool init) {@@ -613,5 +618,6 @@ const struct amdgpu_virt_ops xgpu_vi_virt_ops = { .req_full_gpu = xgpu_vi_request_full_gpu_access, .rel_full_gpu = xgpu_vi_release_full_gpu_access, .reset_gpu = xgpu_vi_request_reset, + .wait_reset = xgpu_vi_wait_reset_cmpl, .trans_msg = NULL, /* Does not need to trans VF errors to host. */ }; --2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): CC2BFABD-8E5A-4E7F-B435-3CA25B1D46C4-5C7GfCeVMHo@public.gmane.org
RE: [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops
Okay, I missed that part,
Free to add my RB
-----Original Message-----
From: Ding, Pixel
Sent: 2017年10月24日 9:33
To: Liu, Monk <[email protected]>; [email protected]
Cc: Sun, Gary <[email protected]>; Li, Bingley <[email protected]>
Subject: Re: [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops
This is for retry init.
If the driver fails before late_init, the IRQ handler is not registered then. We need to know if the FLR is done at this point. I think maybe we also can leverage this interface to handle some special cases in future. Any concern about it? —
Sincerely Yours,
Pixel
Quoted 95 lines · Monk
I don't see this is a necessary patch, driver already have the implement to check if VF FLR is completed or not, see "xgpu_ai/vi_mailbox_flr_work()"
Driver won't do gpu reset until this function received the
NOTIFICATION_CMPLmessageDo you have any particular reason to add this
wait_reset? if so please send out the patch that use this interfaceBR Monk
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: 2017年10月23日 18:04
To: [email protected]
Cc: Sun, Gary <[email protected]>; Ding, Pixel <[email protected]>; Li, Bingley <[email protected]>
Subject: [PATCH 6/7] drm/amdgpu/virt: addwait_resetvirt opsFrom: pding <[email protected]>
Driver can use this interface to check if there's a function level reset done in hypervisor.
Signed-off-by pding <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 16 ++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 ++ drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 1 + drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 6 ++++++ 4 files changed, 25 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +15
-0@@ -231,6 +231,22 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev) }/** +* amdgpu_virt_wait_reset() - wait for reset gpu completed +* @amdgpu: amdgpu device. +* Wait for GPU reset completed. +* Return: Zero if reset success, otherwise will return error. +*/ +int amdgpu_virt_wait_reset (struct amdgpu_device *adev) { +struct amdgpu_virt *virt = &adev->virt; + +if (!virt->ops || !virt->ops->wait_reset) +return -EINVAL ; + +return virt->ops->wait_reset (adev); +} + +/** * amdgpu_virt_alloc_mm_table() - alloc memory for mm table * @amdgpu: amdgpu device. * MM table is used by UVD and VCE for its initialization diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 81efb9d..d149aca 100644
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +2
-0@@ -55,6 +55,7 @@ struct amdgpu_virt_ops {int (*req_full_gpu)(struct amdgpu_device *adev,bool init);int (*rel_full_gpu)(struct amdgpu_device *adev,bool init);int (*reset_gpu)(struct amdgpu_device *adev); +int (*wait_reset)(struct amdgpu_device *adev);void (*trans_msg)(struct amdgpu_device *adev,u32 req,u32 data1,u32 data2,u32 data3); };@@ -286,6 +287,7 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v); int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init); int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init); int amdgpu_virt_reset_gpu(struct amdgpu_device *adev); +int amdgpu_virt_wait_reset (struct amdgpu_device *adev);int
amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job); intamdgpu_virt_alloc_mm_table(struct amdgpu_device *adev); voidamdgpu_virt_free_mm_table(struct amdgpu_device *adev); diff --gita/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.cb/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.cindex b4906d2..f91aab3 100644drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +1
-0@@ -353,5 +353,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .req_full_gpu = xgpu_ai_request_full_gpu_access, .rel_full_gpu = xgpu_ai_release_full_gpu_access, .reset_gpu = xgpu_ai_request_reset, + .wait_reset = NULL, .trans_msg = xgpu_ai_mailbox_trans_msg, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.cindex c25a831..27b03c7 100644
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +4
-1@@ -458,6 +458,11 @@ static int xgpu_vi_request_reset(struct amdgpu_device *adev)return xgpu_vi_send_access_requests (adev,IDH_REQ_GPU_RESET_ACCESS ); } +static int xgpu_vi_wait_reset_cmpl (struct amdgpu_device *adev) { +return xgpu_vi_poll_msg (adev,IDH_FLR_NOTIFICATION_CMPL ); } +static int xgpu_vi_request_full_gpu_access (struct amdgpu_device *adev,bool init) {@@ -613,5 +618,6 @@ const struct amdgpu_virt_ops xgpu_vi_virt_ops = { .req_full_gpu = xgpu_vi_request_full_gpu_access, .rel_full_gpu = xgpu_vi_release_full_gpu_access, .reset_gpu = xgpu_vi_request_reset, + .wait_reset = xgpu_vi_wait_reset_cmpl, .trans_msg = NULL, /* Does not need to trans VF errors to host. */ }; --2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
RE: [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops
In reply to a message not in the archiveQuoted 8 lines
-----Original Message-----
From: amd-gfx [mailto:[email protected]] On Behalf Of Pixel Ding
Sent: Monday, October 23, 2017 6:04 AM
To: [email protected]
Cc: Sun, Gary; Ding, Pixel; Li, Bingley
Subject: [PATCH 6/7] drm/amdgpu/virt: addwait_resetvirt ops
Quoted 5 lines
From: pding <[email protected]>
Driver can use this interface to check if there's a function level reset done in hypervisor.
I'd suggest splitting this patch in two, one to add the new callback, and one to add the implementation for VI.
Alex
Quoted 103 lines
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 16 ++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 ++ drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 1 + drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 6 ++++++ 4 files changed, 25 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +16
-0@@ -231,6 +231,22 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev) }/** +* amdgpu_virt_wait_reset() - wait for reset gpu completed +* @amdgpu: amdgpu device. +* Wait for GPU reset completed. +* Return: Zero if reset success, otherwise will return error. +*/ +int amdgpu_virt_wait_reset (struct amdgpu_device *adev) +{ +struct amdgpu_virt *virt = &adev->virt; + +if (!virt->ops || !virt->ops->wait_reset) +return -EINVAL ; + +return virt->ops->wait_reset (adev); +} + +/** * amdgpu_virt_alloc_mm_table() - alloc memory for mm table * @amdgpu: amdgpu device. * MM table is used by UVD and VCE for its initialization
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +2
-0@@ -55,6 +55,7 @@ struct amdgpu_virt_ops {int (*req_full_gpu)(struct amdgpu_device *adev,bool init);int (*rel_full_gpu)(struct amdgpu_device *adev,bool init);int (*reset_gpu)(struct amdgpu_device *adev); +int (*wait_reset)(struct amdgpu_device *adev);void (*trans_msg)(struct amdgpu_device *adev,u32 req,u32 data1,u32 data2,u32 data3); };@@ -286,6 +287,7 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);int amdgpu_virt_request_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_release_full_gpu (struct amdgpu_device *adev,bool init);int amdgpu_virt_reset_gpu (struct amdgpu_device *adev); +int amdgpu_virt_wait_reset (struct amdgpu_device *adev);int amdgpu_sriov_gpu_reset (struct amdgpu_device *adev,struct amdgpu_job *job);int
amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev); voidamdgpu_virt_free_mm_table(struct amdgpu_device *adev);drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +1
-0@@ -353,5 +353,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = { .req_full_gpu = xgpu_ai_request_full_gpu_access, .rel_full_gpu = xgpu_ai_release_full_gpu_access, .reset_gpu = xgpu_ai_request_reset, + .wait_reset = NULL, .trans_msg = xgpu_ai_mailbox_trans_msg, };drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +5
-0@@ -458,6 +458,11 @@ static int xgpu_vi_request_reset(struct amdgpu_device *adev)return xgpu_vi_send_access_requests (adev,IDH_REQ_GPU_RESET_ACCESS ); } +static int xgpu_vi_wait_reset_cmpl (struct amdgpu_device *adev) +{ +return xgpu_vi_poll_msg (adev,IDH_FLR_NOTIFICATION_CMPL ); +} + static int xgpu_vi_request_full_gpu_access(struct amdgpu_device *adev,drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c +1
-0bool init) {@@ -613,5 +618,6 @@ const struct amdgpu_virt_ops xgpu_vi_virt_ops = { .req_full_gpu = xgpu_vi_request_full_gpu_access, .rel_full_gpu = xgpu_vi_release_full_gpu_access, .reset_gpu = xgpu_vi_request_reset, + .wait_reset = xgpu_vi_wait_reset_cmpl, .trans_msg = NULL, /* Does not need to trans VF errorsto host. */
};
--
2.9.5
Quoted 4 lines
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
PATCH 7/7 drm/amdgpu: retry init if it fails due to exclusive mode timeout
In reply to a message not in the archiveFrom: pding <[email protected]>
The exclusive mode has real-time limitation in reality, such like being done in 300ms. It's easy observed if running many VF/VMs in single host with heavy CPU workload.
If we find the init fails due to exclusive mode timeout, try it again.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 ++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 15 +++++++++++++-- 2 files changed, 23 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +10 -0
@@ -2306,6 +2306,15 @@ int amdgpu_device_init(struct amdgpu_device *adev, r =amdgpu_init (adev);if (r) { +/* failed in exclusive mode due to timeout */ +if (amdgpu_sriov_vf (adev) && + !amdgpu_sriov_runtime (adev) && +amdgpu_virt_mmio_blocked (adev) && + !amdgpu_virt_wait_reset (adev)) { +dev_err (adev->dev,"VF exclusive mode timeout\n" ); + r = -EAGAIN ; + goto failed; + }dev_err (adev->dev,"amdgpu_init failed\n" );amdgpu_vf_error_put (adev,AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL ,0 ,0 );amdgpu_fini (adev);
@@ -2393,6 +2402,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,amdgpu_vf_error_trans_all (adev);if (runtime)vga_switcheroo_fini_domain_pm_ops (adev->dev); +return r; }
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +13 -2
@@ -86,7 +86,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)int amdgpu_driver_load_kms (struct drm_device *dev,unsigned long flags) {struct amdgpu_device *adev; -int r, acpi_status; +int r, acpi_status, retry =0 ;#ifdef CONFIG_DRM_AMDGPU_SI if (!amdgpu_si_support) {
@@ -122,6 +122,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) } }#endif +retry_init: adev =kzalloc (sizeof (struct amdgpu_device ),GFP_KERNEL );if (adev ==NULL ) {
@@ -144,7 +145,17 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)* VRAM allocation */ r =amdgpu_device_init (adev, dev, dev->pdev, flags); -if (r) { +if (++retry !=3 && r == -EAGAIN ) { + adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME ; + adev->virt.ops =NULL ; +amdgpu_device_fini (adev); +kfree (adev); + dev->dev_private =NULL ; +msleep (5000 ); +dev_err (&dev->pdev->dev,"retry init %d\n" , retry); + amdgpu_init_log =0 ; + goto retry_init; + }else if (r) {dev_err (&dev->pdev->dev,"Fatal error during GPU init\n" ); goto out; }
Signature · 6 lines
2.9.5 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1508753012-2196-8-git-send-email-Pixel.Ding-5C7GfCeVMHo@public.gmane.org
Re: [PATCH 7/7] drm/amdgpu: retry init if it fails due to exclusive mode timeout
Quoted 64 lines · Pixel Ding
From: pding <[email protected]>
The exclusive mode has real-time limitation in reality, such like being done in 300ms. It's easy observed if running many VF/VMs in single host with heavy CPU workload.
If we find the init fails due to exclusive mode timeout, try it again.
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 ++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 15 +++++++++++++-- 2 files changed, 23 insertions(+), 2 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +10
-0@@ -2306,6 +2306,15 @@ int amdgpu_device_init(struct amdgpu_device *adev, r =amdgpu_init (adev);if (r) { +/* failed in exclusive mode due to timeout */ +if (amdgpu_sriov_vf (adev) && + !amdgpu_sriov_runtime (adev) && +amdgpu_virt_mmio_blocked (adev) && + !amdgpu_virt_wait_reset (adev)) { +dev_err (adev->dev,"VF exclusive mode timeout\n" ); + r = -EAGAIN ; + goto failed; + }dev_err (adev->dev,"amdgpu_init failed\n" );amdgpu_vf_error_put (adev,AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL ,0 ,0 );amdgpu_fini (adev);@@ -2393,6 +2402,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,amdgpu_vf_error_trans_all (adev);if (runtime)vga_switcheroo_fini_domain_pm_ops (adev->dev); +return r; }drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +2
-1@@ -86,7 +86,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)int amdgpu_driver_load_kms (struct drm_device *dev,unsigned long flags) {struct amdgpu_device *adev; -int r, acpi_status; +int r, acpi_status, retry =0 ;#ifdef CONFIG_DRM_AMDGPU_SI if (!amdgpu_si_support) {@@ -122,6 +122,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) } }#endif +retry_init: adev =kzalloc (sizeof (struct amdgpu_device ),GFP_KERNEL );if (adev ==NULL ) {
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) · line 148
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +1
-1@@ -144,7 +145,17 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)* VRAM allocation */ r =amdgpu_device_init (adev, dev, dev->pdev, flags); -if (r) { +if (++retry !=3 && r == -EAGAIN ) {
Minor nitpick here. Might want to rewrite the condition so that it evaluates to false for most values of retry (currently it evaluates to false only for one value of retry).
E.g. if (++retry >= 3 ...)
Or
int retry = 3;
...
if (--retry >= 0 ...)
Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +3
-0+ adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME ; + adev->virt.ops =NULL ; +amdgpu_device_fini (adev);
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) · line 161
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +7
-0+kfree (adev); + dev->dev_private =NULL ; +msleep (5000 ); +dev_err (&dev->pdev->dev,"retry init %d\n" , retry); + amdgpu_init_log =0 ; + goto retry_init; + }else if (r) {dev_err (&dev->pdev->dev,"Fatal error during GPU init\n" ); goto out; }
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 04e77adc-085b-6bea-d08d-73a0980bcdc4-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
Re: [PATCH 7/7] drm/amdgpu: retry init if it fails due to exclusive mode timeout
Thanks Andres, revised in v2.
—
Sincerely Yours,
Pixel
Quoted 95 lines · amd-gfx on behalf of Andres Rodriguez
Quoted 64 lines · Pixel Ding
From: pding <[email protected]>
The exclusive mode has real-time limitation in reality, such like being done in 300ms. It's easy observed if running many VF/VMs in single host with heavy CPU workload.
If we find the init fails due to exclusive mode timeout, try it again.
Signed-off-by pding <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 ++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 15 +++++++++++++-- 2 files changed, 23 insertions(+), 2 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +10
-0@@ -2306,6 +2306,15 @@ int amdgpu_device_init(struct amdgpu_device *adev, r =amdgpu_init (adev);if (r) { +/* failed in exclusive mode due to timeout */ +if (amdgpu_sriov_vf (adev) && + !amdgpu_sriov_runtime (adev) && +amdgpu_virt_mmio_blocked (adev) && + !amdgpu_virt_wait_reset (adev)) { +dev_err (adev->dev,"VF exclusive mode timeout\n" ); + r = -EAGAIN ; + goto failed; + }dev_err (adev->dev,"amdgpu_init failed\n" );amdgpu_vf_error_put (adev,AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL ,0 ,0 );amdgpu_fini (adev);@@ -2393,6 +2402,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,amdgpu_vf_error_trans_all (adev);if (runtime)vga_switcheroo_fini_domain_pm_ops (adev->dev); +return r; }drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +2
-1@@ -86,7 +86,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)int amdgpu_driver_load_kms (struct drm_device *dev,unsigned long flags) {struct amdgpu_device *adev; -int r, acpi_status; +int r, acpi_status, retry =0 ;#ifdef CONFIG_DRM_AMDGPU_SI if (!amdgpu_si_support) {@@ -122,6 +122,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) } }#endif +retry_init: adev =kzalloc (sizeof (struct amdgpu_device ),GFP_KERNEL );if (adev ==NULL ) {drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) · line 148
Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +1
-1@@ -144,7 +145,17 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)* VRAM allocation */ r =amdgpu_device_init (adev, dev, dev->pdev, flags); -if (r) { +if (++retry !=3 && r == -EAGAIN ) {Minor nitpick here. Might want to rewrite the condition so that it evaluates to false for most values of retry (currently it evaluates to false only for one value of retry).
E.g. if (++retry >= 3 ...)
Or
int retry = 3;
...
if (--retry >= 0 ...)Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +10
-0+ adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME ; + adev->virt.ops =NULL ; +amdgpu_device_fini (adev); +kfree (adev); + dev->dev_private =NULL ; +msleep (5000 ); +dev_err (&dev->pdev->dev,"retry init %d\n" , retry); + amdgpu_init_log =0 ; + goto retry_init; + }else if (r) {
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) · line 161
Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +0
-0dev_err (&dev->pdev->dev,"Fatal error during GPU init\n" ); goto out; }_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx