From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Matthew Auld <matthew.auld@intel.com>, intel-gfx@lists.freedesktop.org
Subject: Re: [Intel-gfx] [CI 1/4] drm/i915/gt: Explicitly clear BB_OFFSET for new contexts
Date: Tue, 29 Mar 2022 08:50:00 +0100 [thread overview]
Message-ID: <f47d7b98-31ac-5b65-ed47-a27fa52d5de2@linux.intel.com> (raw)
In-Reply-To: <20220328172551.43309-1-matthew.auld@intel.com>
On 28/03/2022 18:25, Matthew Auld wrote:
> From: Chris Wilson <chris@chris-wilson.co.uk>
>
> Even though the initial protocontext we load onto HW has the register
> cleared, by the time we save it into the default image, BB_OFFSET has
> had the enable bit set. Reclear BB_OFFSET for each new context.
Intriguing - is there any impact to this which would require cc: stable?
Regards,
Tvrtko
> Testcase: igt/i915_selftests/gt_lrc
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
> ---
> drivers/gpu/drm/i915/gt/intel_engine_regs.h | 1 +
> drivers/gpu/drm/i915/gt/intel_lrc.c | 17 +++++++++++++++++
> drivers/gpu/drm/i915/gt/selftest_lrc.c | 5 +++++
> 3 files changed, 23 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
> index 0bf8b45c9319..d6da3bbf66f8 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
> +++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
> @@ -109,6 +109,7 @@
> #define RING_SBBSTATE(base) _MMIO((base) + 0x118) /* hsw+ */
> #define RING_SBBADDR_UDW(base) _MMIO((base) + 0x11c) /* gen8+ */
> #define RING_BBADDR(base) _MMIO((base) + 0x140)
> +#define RING_BB_OFFSET(base) _MMIO((base) + 0x158)
> #define RING_BBADDR_UDW(base) _MMIO((base) + 0x168) /* gen8+ */
> #define CCID(base) _MMIO((base) + 0x180)
> #define CCID_EN BIT(0)
> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> index 07bef7128fdb..f673bae97a03 100644
> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> @@ -662,6 +662,18 @@ static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
> return -1;
> }
>
> +static int lrc_ring_bb_offset(const struct intel_engine_cs *engine)
> +{
> + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
> + return 0x80;
> + else if (GRAPHICS_VER(engine->i915) >= 12)
> + return 0x70;
> + else if (GRAPHICS_VER(engine->i915) >= 9)
> + return 0x64;
> + else
> + return -1;
> +}
> +
> static int lrc_ring_gpr0(const struct intel_engine_cs *engine)
> {
> if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
> @@ -768,6 +780,7 @@ static void init_common_regs(u32 * const regs,
> bool inhibit)
> {
> u32 ctl;
> + int loc;
>
> ctl = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
> ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
> @@ -779,6 +792,10 @@ static void init_common_regs(u32 * const regs,
> regs[CTX_CONTEXT_CONTROL] = ctl;
>
> regs[CTX_TIMESTAMP] = ce->runtime.last;
> +
> + loc = lrc_ring_bb_offset(engine);
> + if (loc != -1)
> + regs[loc + 1] = 0;
> }
>
> static void init_wa_bb_regs(u32 * const regs,
> diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
> index 21c29d315cc0..13f57c7c4224 100644
> --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
> @@ -323,6 +323,11 @@ static int live_lrc_fixed(void *arg)
> lrc_ring_cmd_buf_cctl(engine),
> "RING_CMD_BUF_CCTL"
> },
> + {
> + i915_mmio_reg_offset(RING_BB_OFFSET(engine->mmio_base)),
> + lrc_ring_bb_offset(engine),
> + "RING_BB_OFFSET"
> + },
> { },
> }, *t;
> u32 *hw;
next prev parent reply other threads:[~2022-03-29 7:50 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-28 17:25 [Intel-gfx] [CI 1/4] drm/i915/gt: Explicitly clear BB_OFFSET for new contexts Matthew Auld
2022-03-28 17:25 ` [Intel-gfx] [CI 2/4] drm/i915/selftests: Check for incomplete LRI from the context image Matthew Auld
2022-03-28 17:25 ` [Intel-gfx] [CI 3/4] drm/i915/selftest: Clear the output buffers before GPU writes Matthew Auld
2022-03-28 17:25 ` [Intel-gfx] [CI 4/4] drm/i915/selftest: Always cancel semaphore on error Matthew Auld
2022-03-29 0:10 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [CI,1/4] drm/i915/gt: Explicitly clear BB_OFFSET for new contexts Patchwork
2022-03-29 0:11 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2022-03-29 0:15 ` [Intel-gfx] ✗ Fi.CI.DOCS: " Patchwork
2022-03-29 0:34 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2022-03-29 3:11 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
2022-03-29 7:50 ` Tvrtko Ursulin [this message]
2022-03-29 10:33 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [CI,1/4] drm/i915/gt: Explicitly clear BB_OFFSET for new contexts (rev2) Patchwork
2022-03-29 10:34 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2022-03-29 10:38 ` [Intel-gfx] ✗ Fi.CI.DOCS: " Patchwork
2022-03-29 11:16 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
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=f47d7b98-31ac-5b65-ed47-a27fa52d5de2@linux.intel.com \
--to=tvrtko.ursulin@linux.intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=matthew.auld@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