Igt-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Scott D Phillips <scott.d.phillips@intel.com>
To: Jordan Justen <jordan.l.justen@intel.com>,
	IGT GPU Tools <igt-dev@lists.freedesktop.org>
Subject: Re: [igt-dev] [PATCH i-g-t 1/3] tools/aubdump: Add gen8_map_range
Date: Wed, 07 Mar 2018 08:09:18 -0800	[thread overview]
Message-ID: <87d10fvpe9.fsf@intel.com> (raw)
In-Reply-To: <20180307083121.2955-1-jordan.l.justen@intel.com>

Jordan Justen <jordan.l.justen@intel.com> writes:

> This function should allow us to only write the page table entries
> that get used.
>
> v2:
>  * Use align; deobfuscate start addr calc. (Scott)
>
> Cc: Scott D Phillips <scott.d.phillips@intel.com>
> Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
> ---
>  tools/aubdump.c | 40 +++++++++++++++++++++++++++++-----------
>  1 file changed, 29 insertions(+), 11 deletions(-)
>
> diff --git a/tools/aubdump.c b/tools/aubdump.c
> index 5989bed4..bf4be82d 100644
> --- a/tools/aubdump.c
> +++ b/tools/aubdump.c
> @@ -382,12 +382,39 @@ register_write_out(uint32_t addr, uint32_t value)
>  	dword_out(value);
>  }
>  
> +static void
> +gen8_map_ggtt_range(uint64_t start, uint64_t end)
> +{
> +	uint64_t entry_addr;
> +	uint64_t page_num;
> +	uint64_t end_aligned = align_u64(end, 4096);
> +
> +	if (start >= end && end < 1ull << 32)

Did you mean something like (start >= end || end > 1ull << 32) ?

With that changed, this is

Reviewed-by: Scott D Phillips <scott.d.phillips@intel.com>

> +		return;
> +
> +	entry_addr = start & ~(4096 - 1);
> +	do {
> +		page_num = entry_addr >> 21;
> +		uint64_t last_page_entry =
> +			min((page_num + 1) << 21, end_aligned);
> +		uint64_t num_entries = (last_page_entry - entry_addr) >> 12;
> +		mem_trace_memory_write_header_out(
> +			entry_addr >> 9, num_entries * GEN8_PTE_SIZE,
> +			AUB_MEM_TRACE_MEMORY_ADDRESS_SPACE_GGTT_ENTRY);
> +		while (num_entries-- > 0) {
> +			dword_out((entry_addr & ~(4096 - 1)) |
> +			          3 /* read/write | present */);
> +			dword_out(entry_addr >> 32);
> +			entry_addr += 4096;
> +		}
> +	} while (entry_addr < end);
> +}
> +
>  static void
>  gen10_write_header(void)
>  {
>  	char app_name[8 * 4];
>  	int app_name_len, dwords;
> -	uint32_t entry = 0x3;	/* read/write | present */
>  
>  	app_name_len =
>  	    snprintf(app_name, sizeof(app_name), "PCI-ID=0x%X %s", device,
> @@ -403,16 +430,7 @@ gen10_write_header(void)
>  	dword_out(0);		/* version */
>  	data_out(app_name, app_name_len);
>  
> -	/* GGTT PT */
> -	for (uint32_t page = 0; page < ALIGN(PT_SIZE, 4096) / 4096; page++) {
> -		uint32_t to_write = min(PT_SIZE - page * 4096, 4096);
> -		mem_trace_memory_write_header_out(page << 12, to_write,
> -						  AUB_MEM_TRACE_MEMORY_ADDRESS_SPACE_GGTT_ENTRY);
> -		for (uint32_t i = 0; i < to_write / GEN8_PTE_SIZE; i++) {
> -			dword_out(entry + 0x1000 * i + 0x200000 * page);
> -			dword_out(0);
> -		}
> -	}
> +	gen8_map_ggtt_range(0, MEMORY_MAP_SIZE);
>  
>  	/* RENDER_RING */
>  	mem_trace_memory_write_header_out(RENDER_RING_ADDR, RING_SIZE,
> -- 
> 2.16.1
_______________________________________________
igt-dev mailing list
igt-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/igt-dev

      parent reply	other threads:[~2018-03-07 16:09 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-07  8:31 [igt-dev] [PATCH i-g-t 1/3] tools/aubdump: Add gen8_map_range Jordan Justen
2018-03-07  8:31 ` [igt-dev] [PATCH i-g-t 2/3] tools/aubdump: Add bitmap to track gtt pages that have been mapped Jordan Justen
2018-03-07 16:20   ` Scott D Phillips
2018-03-07  8:31 ` [igt-dev] [PATCH i-g-t 3/3] tools/aubdump: For gen10+ support addresses up to 4GB Jordan Justen
2018-03-07  8:42   ` Jordan Justen
2018-03-07 16:21   ` Scott D Phillips
2018-03-07  8:43 ` [igt-dev] ✗ Fi.CI.BAT: failure for series starting with [i-g-t,1/3] tools/aubdump: Add gen8_map_range Patchwork
2018-03-07 16:09 ` Scott D Phillips [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=87d10fvpe9.fsf@intel.com \
    --to=scott.d.phillips@intel.com \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=jordan.l.justen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox