[Intel-xe] [PATCH 1/4] drm/xe: Rework size helper to be a little more correct

Matthew Auld matthew.auld at intel.com
Wed May 3 14:30:04 UTC 2023


On 03/05/2023 15:14, Ruhl, Michael J wrote:
>> -----Original Message-----
>> From: Auld, Matthew <matthew.auld at intel.com>
>> Sent: Wednesday, May 3, 2023 6:41 AM
>> To: Ruhl, Michael J <michael.j.ruhl at intel.com>; intel-
>> xe at lists.freedesktop.org
>> Cc: Brost, Matthew <matthew.brost at intel.com>; Kershner, David
>> <david.kershner at intel.com>; Ghimiray, Himal Prasad
>> <himal.prasad.ghimiray at intel.com>; Upadhyay, Tejas
>> <tejas.upadhyay at intel.com>
>> Subject: Re: [PATCH 1/4] drm/xe: Rework size helper to be a little more
>> correct
>>
>> On 01/05/2023 12:58, Michael J. Ruhl wrote:
>>> The _total_vram_size helper is device based and is not complete.
>>>
>>> Teach the helper to be tile aware and add the ability to size
>>> DG1 correctly.
>>>
>>> Signed-off-by: Michael J. Ruhl <michael.j.ruhl at intel.com>
>>> ---
>>>    drivers/gpu/drm/xe/regs/xe_gt_regs.h   |  2 +-
>>>    drivers/gpu/drm/xe/xe_mmio.c           | 73 +++++++++++++++++---------
>>>    drivers/gpu/drm/xe/xe_mmio.h           |  2 +-
>>>    drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c | 28 +++++-----
>>>    4 files changed, 64 insertions(+), 41 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
>> b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
>>> index 68e89d71cd1c..780edd4dc1bd 100644
>>> --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
>>> +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
>>> @@ -74,7 +74,7 @@
>>>    #define VE1_AUX_NV				XE_REG(0x42b8)
>>>    #define   AUX_INV				REG_BIT(0)
>>>
>>> -#define XEHP_TILE0_ADDR_RANGE			XE_REG_MCR(0x4900)
>>> +#define XEHP_TILE_ADDR_RANGE(_idx)		XE_REG_MCR(0x4900
>> + (_idx) * 4)
>>>    #define XEHP_FLAT_CCS_BASE_ADDR
>> 	XE_REG_MCR(0x4910)
>>>
>>>    #define CHICKEN_RASTER_1			XE_REG_MCR(0x6204,
>> XE_REG_OPTION_MASKED)
>>> diff --git a/drivers/gpu/drm/xe/xe_mmio.c
>> b/drivers/gpu/drm/xe/xe_mmio.c
>>> index 3b719c774efa..7d53d382976c 100644
>>> --- a/drivers/gpu/drm/xe/xe_mmio.c
>>> +++ b/drivers/gpu/drm/xe/xe_mmio.c
>>> @@ -148,34 +148,56 @@ static bool xe_pci_resource_valid(struct pci_dev
>> *pdev, int bar)
>>>    	return true;
>>>    }
>>>
>>> -int xe_mmio_total_vram_size(struct xe_device *xe, u64 *vram_size, u64
>> *usable_size)
>>> +/**
>>> + * xe_mmio_tile_vram_size - Collect vram size and off set information
>>> + * @gt: tile to get info for
>>> + * @vram_size: available vram (size - device reserved portions)
>>> + * @tile_size: actual vram size
>>> + * @tile_offset: physical start point in the vram address space
>>> + *
>>> + * There are 4 places for size information:
>>> + * - io size (from pci_resource_len of LMEM bar) (only used for small bar
>> and DG1)
>>> + * - TILEx size (actual vram size)
>>> + * - GSMBASE offset (TILEx - "stolen")
>>> + * - CSSBASE offset (TILEx - CSS space necessary)
>>> + *
>>> + * NOTE: CSSBASE is always a lower/smaller offset then GSMBASE.
>>> + *
>>> + * The actual available size of memory is to the CCS or GSM base.
>>> + * NOTE: multi-tile bases will include the tile offset.
>>> + *
>>> + */
>>> +int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64
>> *tile_size, u64 *tile_offset)
>>>    {
>>> -	struct xe_gt *gt = xe_device_get_gt(xe, 0);
>>> -	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
>>> +	u64 offset;
>>>    	int err;
>>>    	u32 reg;
>>>
>>> -	if (!xe->info.has_flat_ccs)  {
>>> -		*vram_size = pci_resource_len(pdev, GEN12_LMEM_BAR);
>>> -		if (usable_size)
>>> -			*usable_size = min(*vram_size,
>>> -					   xe_mmio_read64(gt,
>> GSMBASE.reg));
>>> -		return 0;
>>> -	}
>>> -
>>>    	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
>>>    	if (err)
>>>    		return err;
>>>
>>> -	reg = xe_gt_mcr_unicast_read_any(gt, XEHP_TILE0_ADDR_RANGE);
>>> -	*vram_size = (u64)REG_FIELD_GET(GENMASK(14, 8), reg) * SZ_1G;
>>> -	if (usable_size) {
>>> +	/* actual size */
>>> +	if (unlikely(gt->xe->info.platform == XE_DG1)) {
>>> +		*tile_size = pci_resource_len(to_pci_dev(gt->xe->drm.dev),
>> GEN12_LMEM_BAR);
>>> +		*tile_offset = 0;
>>> +	} else {
>>> +		reg = xe_gt_mcr_unicast_read_any(gt,
>> XEHP_TILE_ADDR_RANGE(gt->info.id));
>>> +		*tile_size = (u64)REG_FIELD_GET(GENMASK(14, 8), reg) *
>> SZ_1G;
>>> +		*tile_offset = (u64)REG_FIELD_GET(GENMASK(7, 1), reg) *
>> SZ_1G;
>>> +	}
>>> +
>>> +	/* minus device usage */
>>> +	if (gt->xe->info.has_flat_ccs) {
>>>    		reg = xe_gt_mcr_unicast_read_any(gt,
>> XEHP_FLAT_CCS_BASE_ADDR);
>>> -		*usable_size = (u64)REG_FIELD_GET(GENMASK(31, 8), reg) *
>> SZ_64K;
>>> -		drm_info(&xe->drm, "vram_size: 0x%llx usable_size:
>> 0x%llx\n",
>>> -			 *vram_size, *usable_size);
>>> +		offset = (u64)REG_FIELD_GET(GENMASK(31, 8), reg) *
>> SZ_64K;
>>> +	} else {
>>> +		offset = xe_mmio_read64(gt, GSMBASE.reg);
>>>    	}
>>>
>>> +	/* remove the tile offset so we have just the available size */
>>> +	*vram_size = offset - *tile_offset;
>>> +
>>>    	return xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
>>>    }
>>>
>>> @@ -183,11 +205,12 @@ int xe_mmio_probe_vram(struct xe_device *xe)
>>>    {
>>>    	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
>>>    	struct xe_gt *gt;
>>> -	u8 id;
>>> -	u64 vram_size;
>>>    	u64 original_size;
>>> -	u64 usable_size;
>>> +	u64 tile_offset;
>>> +	u64 tile_size;
>>> +	u64 vram_size;
>>>    	int err;
>>> +	u8 id;
>>>
>>>    	if (!IS_DGFX(xe)) {
>>>    		xe->mem.vram.mapping = 0;
>>> @@ -212,25 +235,25 @@ int xe_mmio_probe_vram(struct xe_device *xe)
>>>    	gt = xe_device_get_gt(xe, 0);
>>>    	original_size = pci_resource_len(pdev, GEN12_LMEM_BAR);
>>>
>>> -	err = xe_mmio_total_vram_size(xe, &vram_size, &usable_size);
>>> +	err = xe_mmio_tile_vram_size(gt, &vram_size, &tile_size,
>> &tile_offset);
>>>    	if (err)
>>>    		return err;
>>>
>>>    	xe_resize_vram_bar(xe, vram_size);
>>>    	xe->mem.vram.io_start = pci_resource_start(pdev,
>> GEN12_LMEM_BAR);
>>> -	xe->mem.vram.io_size = min(usable_size,
>>> +	xe->mem.vram.io_size = min(vram_size,
>>>    				   pci_resource_len(pdev,
>> GEN12_LMEM_BAR));
>>>    	xe->mem.vram.size = xe->mem.vram.io_size;
>>>
>>>    	if (!xe->mem.vram.size)
>>>    		return -EIO;
>>>
>>> -	if (usable_size > xe->mem.vram.io_size)
>>> +	if (vram_size > xe->mem.vram.io_size)
>>>    		drm_warn(&xe->drm, "Restricting VRAM size to PCI resource
>> size (%lluMiB->%lluMiB)\n",
>>> -			 (u64)usable_size >> 20, (u64)xe->mem.vram.io_size
>>>> 20);
>>> +			 (u64)vram_size >> 20, (u64)xe->mem.vram.io_size >>
>> 20);
>>>
>>>    	xe->mem.vram.mapping = ioremap_wc(xe->mem.vram.io_start, xe-
>>> mem.vram.io_size);
>>> -	xe->mem.vram.size = min_t(u64, xe->mem.vram.size, usable_size);
>>> +	xe->mem.vram.size = min_t(u64, xe->mem.vram.size, vram_size);
>>>
>>>    	drm_info(&xe->drm, "TOTAL VRAM: %pa, %pa\n", &xe-
>>> mem.vram.io_start, &xe->mem.vram.size);
>>>
>>> diff --git a/drivers/gpu/drm/xe/xe_mmio.h
>> b/drivers/gpu/drm/xe/xe_mmio.h
>>> index 1a32e0f52261..556cf3d9e4f5 100644
>>> --- a/drivers/gpu/drm/xe/xe_mmio.h
>>> +++ b/drivers/gpu/drm/xe/xe_mmio.h
>>> @@ -120,6 +120,6 @@ static inline bool xe_mmio_in_range(const struct
>> xe_mmio_range *range, u32 reg)
>>>    }
>>>
>>>    int xe_mmio_probe_vram(struct xe_device *xe);
>>> -int xe_mmio_total_vram_size(struct xe_device *xe, u64 *vram_size, u64
>> *flat_ccs_base);
>>> +int xe_mmio_tile_vram_size(struct xe_gt *gt, u64 *vram_size, u64
>> *tile_size, u64 *tile_base);
>>>
>>>    #endif
>>> diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
>> b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
>>> index 9ce0a0585539..a329f12f14fe 100644
>>> --- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
>>> +++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
>>> @@ -51,27 +51,27 @@ bool xe_ttm_stolen_cpu_access_needs_ggtt(struct
>> xe_device *xe)
>>>    	return GRAPHICS_VERx100(xe) < 1270 && !IS_DGFX(xe);
>>>    }
>>>
>>> -static s64 detect_bar2_dgfx(struct xe_device *xe, struct
>> xe_ttm_stolen_mgr *mgr)
>>> +static s64 detect_bar2_dgfx(struct xe_gt *gt, struct xe_ttm_stolen_mgr
>> *mgr)
>>>    {
>>> -	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
>>> -	struct xe_gt *gt = to_gt(xe);
>>> -	u64 vram_size, stolen_size;
>>> -	int err;
>>> +	u64 stolen_size;
>>> +	u64 tile_offset;
>>> +	u64 tile_size;
>>> +	u64 vram_size;
>>>
>>> -	err = xe_mmio_total_vram_size(xe, &vram_size, NULL);
>>> -	if (err) {
>>> -		drm_info(&xe->drm, "Querying total vram size failed\n");
>>> +	if (xe_mmio_tile_vram_size(gt, &vram_size, &tile_size, &tile_offset))
>> {
>>> +		drm_info(&gt->xe->drm, "Querying total vram size failed\n");
>>>    		return 0;
>>>    	}
>>>
>>>    	/* Use DSM base address instead for stolen memory */
>>> -	mgr->stolen_base = xe_mmio_read64(gt, DSMBASE.reg) &
>> BDSM_MASK;
>>> -	if (drm_WARN_ON(&xe->drm, vram_size < mgr->stolen_base))
>>> +	mgr->stolen_base = (xe_mmio_read64(gt, DSMBASE.reg) &
>> BDSM_MASK) - tile_offset;
>>> +	if (drm_WARN_ON(&gt->xe->drm, tile_size < mgr->stolen_base))
>>>    		return 0;
>>>
>>> -	stolen_size = vram_size - mgr->stolen_base;
>>> -	if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, 2))
>>> -		mgr->io_base = pci_resource_start(pdev, 2) + mgr-
>>> stolen_base;
>>> +	stolen_size = tile_size - mgr->stolen_base;
>>> +
>>> +	if (mgr->stolen_base + stolen_size <= tile_size)
>>
>> I think needs to be the pci_len() here.
> 
> For a PVC that would be 128GB for length.  That will encompass both tiles, and I think that the
> this will not check correctly.
> 
> tile_size == pci_len() for DG1...
> 
> Is that your concern?
> 
> I think that he "stolen" area has to be constrained to the tile size, not the complete area.
> Am I missing something here?

Just that we want mgr->io_base here to be zero on small-bar, which then 
signals that stolen is not directly CPU accessible. Also we only care 
about the root tile here.

> 
> Thanks
> 
> Mike
> 
>>> +		mgr->io_base = gt->mem.vram.io_start + mgr->stolen_base;
>>>
>>>    	/*
>>>    	 * There may be few KB of platform dependent reserved memory at
>> the end
>>> @@ -139,7 +139,7 @@ void xe_ttm_stolen_mgr_init(struct xe_device *xe)
>>>    	int err;
>>>
>>>    	if (IS_DGFX(xe))
>>> -		stolen_size = detect_bar2_dgfx(xe, mgr);
>>> +		stolen_size = detect_bar2_dgfx(to_gt(xe), mgr);
>>>    	else if (GRAPHICS_VERx100(xe) >= 1270)
>>>    		stolen_size = detect_bar2_integrated(xe, mgr);
>>>    	else


More information about the Intel-xe mailing list