public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: Michel Thierry <michel.thierry@intel.com>
To: Mika Kuoppala <mika.kuoppala@linux.intel.com>,
	"intel-gfx@lists.freedesktop.org"
	<intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 02/21] drm/i915/gtt: Workaround for HW preload not flushing pdps
Date: Fri, 29 May 2015 13:53:21 +0100	[thread overview]
Message-ID: <55686141.9090107@intel.com> (raw)
In-Reply-To: <556847E6.2050801@intel.com>

On 5/29/2015 12:05 PM, Michel Thierry wrote:
> On 5/22/2015 6:04 PM, Mika Kuoppala wrote:
>> With BDW/SKL and 32bit addressing mode only, the hardware preloads
>> pdps. However the TLB invalidation only has effect on levels below
>> the pdps. This means that if pdps change, hw might access with
>> stale pdp entry.
>>
>> To combat this problem, preallocate the top pdps so that hw sees
>> them as immutable for each context.
>>
>> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
>> Cc: Rafael Barbalho <rafael.barbalho@intel.com>
>> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
>> ---
>>   drivers/gpu/drm/i915/i915_gem_gtt.c | 50 
>> +++++++++++++++++++++++++++++++++++++
>>   drivers/gpu/drm/i915/i915_reg.h     | 17 +++++++++++++
>>   drivers/gpu/drm/i915/intel_lrc.c    | 15 +----------
>>   3 files changed, 68 insertions(+), 14 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c 
>> b/drivers/gpu/drm/i915/i915_gem_gtt.c
>> index 0ffd459..1a5ad4c 100644
>> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
>> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
>> @@ -941,6 +941,48 @@ err_out:
>>          return ret;
>>   }
>>
>> +/* With some architectures and 32bit legacy mode, hardware pre-loads 
>> the
>> + * top level pdps but the tlb invalidation only invalidates the 
>> lower levels.
>> + * This might lead to hw fetching with stale pdp entries if top level
>> + * structure changes, ie va space grows with dynamic page tables.
>> + */
>> +static bool hw_wont_flush_pdp_tlbs(struct i915_hw_ppgtt *ppgtt)
>> +{
>> +       struct drm_device *dev = ppgtt->base.dev;
>> +
>> +       if (GEN8_CTX_ADDRESSING_MODE != LEGACY_32B_CONTEXT)
>> +               return false;
>> +
>> +       if (IS_BROADWELL(dev) || IS_SKYLAKE(dev))
>> +               return true;
> The pd load restriction is also true for chv and bxt.
> And to be safe, we can set reg 0x4030 bit14 to '1' (PD load disable). 
> Since this register is not part of the context state, it can be added 
> with the other platform workarounds in intel_pm.c.
>
>> +
>> +       return false;
>> +}
>> +
>> +static int gen8_preallocate_top_level_pdps(struct i915_hw_ppgtt *ppgtt)
>> +{
>> +       unsigned long *new_page_dirs, **new_page_tables;
>> +       int ret;
>> +
>> +       /* We allocate temp bitmap for page tables for no gain
>> +        * but as this is for init only, lets keep the things simple
>> +        */
>> +       ret = alloc_gen8_temp_bitmaps(&new_page_dirs, &new_page_tables);
>> +       if (ret)
>> +               return ret;
>> +
>> +       /* Allocate for all pdps regardless of how the ppgtt
>> +        * was defined.
>> +        */
>> +       ret = gen8_ppgtt_alloc_page_directories(ppgtt, &ppgtt->pdp,
>> +                                               0, 1ULL << 32,
>> +                                               new_page_dirs);
>> +
>> +       free_gen8_temp_bitmaps(new_page_dirs, new_page_tables);
>> +
>> +       return ret;
>> +}
>> +
>>   /*
>>    * GEN8 legacy ppgtt programming is accomplished through a max 4 
>> PDP registers
>>    * with a net effect resembling a 2-level page table in normal x86 
>> terms. Each
>> @@ -972,6 +1014,14 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt 
>> *ppgtt)
>>
>>          ppgtt->switch_mm = gen8_mm_switch;
>>
>> +       if (hw_wont_flush_pdp_tlbs(ppgtt)) {
>> +               /* Avoid the tlb flush bug by preallocating
>> +                * whole top level pdp structure so it stays
>> +                * static even if our va space grows.
>> +                */
>> +               return gen8_preallocate_top_level_pdps(ppgtt);
>> +       }
>> +
Also, we will need the same hw_wont_flush check in the cleanup function, 
and iterate each_pdpe (pd) from 0 to 4GiB (otherwise we will leak some 
of the preallocated page dirs).

>>          return 0;
>>   }
>>
>> diff --git a/drivers/gpu/drm/i915/i915_reg.h 
>> b/drivers/gpu/drm/i915/i915_reg.h
>> index 6eeba63..334324b 100644
>> --- a/drivers/gpu/drm/i915/i915_reg.h
>> +++ b/drivers/gpu/drm/i915/i915_reg.h
>> @@ -2777,6 +2777,23 @@ enum skl_disp_power_wells {
>>   #define VLV_CLK_CTL2                   0x101104
>>   #define   CLK_CTL2_CZCOUNT_30NS_SHIFT  28
>>
>> +/* Context descriptor format bits */
>> +#define GEN8_CTX_VALID                 (1<<0)
>> +#define GEN8_CTX_FORCE_PD_RESTORE      (1<<1)
>> +#define GEN8_CTX_FORCE_RESTORE         (1<<2)
>> +#define GEN8_CTX_L3LLC_COHERENT                (1<<5)
>> +#define GEN8_CTX_PRIVILEGE             (1<<8)
>> +
>> +enum {
>> +       ADVANCED_CONTEXT = 0,
>> +       LEGACY_32B_CONTEXT,
>> +       ADVANCED_AD_CONTEXT,
>> +       LEGACY_64B_CONTEXT
>> +};
>> +
>> +#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
>> +#define GEN8_CTX_ADDRESSING_MODE       LEGACY_32B_CONTEXT
>> +
>>   /*
>>    * Overlay regs
>>    */
>> diff --git a/drivers/gpu/drm/i915/intel_lrc.c 
>> b/drivers/gpu/drm/i915/intel_lrc.c
>> index 96ae90a..d793d4e 100644
>> --- a/drivers/gpu/drm/i915/intel_lrc.c
>> +++ b/drivers/gpu/drm/i915/intel_lrc.c
>> @@ -183,12 +183,6 @@
>>   #define CTX_R_PWR_CLK_STATE            0x42
>>   #define CTX_GPGPU_CSR_BASE_ADDRESS     0x44
>>
>> -#define GEN8_CTX_VALID (1<<0)
>> -#define GEN8_CTX_FORCE_PD_RESTORE (1<<1)
>> -#define GEN8_CTX_FORCE_RESTORE (1<<2)
>> -#define GEN8_CTX_L3LLC_COHERENT (1<<5)
>> -#define GEN8_CTX_PRIVILEGE (1<<8)
>> -
>>   #define ASSIGN_CTX_PDP(ppgtt, reg_state, n) { \
>>          const u64 _addr = test_bit(n, ppgtt->pdp.used_pdpes) ? \
>>                  ppgtt->pdp.page_directory[n]->daddr : \
>> @@ -198,13 +192,6 @@
>>   }
>>
>>   enum {
>> -       ADVANCED_CONTEXT = 0,
>> -       LEGACY_CONTEXT,
>> -       ADVANCED_AD_CONTEXT,
>> -       LEGACY_64B_CONTEXT
>> -};
>> -#define GEN8_CTX_MODE_SHIFT 3
>> -enum {
>>          FAULT_AND_HANG = 0,
>>          FAULT_AND_HALT, /* Debug only */
>>          FAULT_AND_STREAM,
>> @@ -273,7 +260,7 @@ static uint64_t execlists_ctx_descriptor(struct 
>> intel_engine_cs *ring,
>>          WARN_ON(lrca & 0xFFFFFFFF00000FFFULL);
>>
>>          desc = GEN8_CTX_VALID;
>> -       desc |= LEGACY_CONTEXT << GEN8_CTX_MODE_SHIFT;
>> +       desc |= GEN8_CTX_ADDRESSING_MODE << 
>> GEN8_CTX_ADDRESSING_MODE_SHIFT;
>>          if (IS_GEN8(ctx_obj->base.dev))
>>                  desc |= GEN8_CTX_L3LLC_COHERENT;
>>          desc |= GEN8_CTX_PRIVILEGE;
>> -- 
>> 1.9.1
>>
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx@lists.freedesktop.org
>> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2015-05-29 12:53 UTC|newest]

Thread overview: 86+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-22 17:04 [PATCH 00/21] ppgtt cleanups / scratch merge (V2) Mika Kuoppala
2015-05-22 17:04 ` [PATCH 01/21] drm/i915/gtt: Mark TLBS dirty for gen8+ Mika Kuoppala
2015-06-01 14:51   ` Joonas Lahtinen
2015-06-11 17:37     ` Mika Kuoppala
2015-06-23 11:10       ` Joonas Lahtinen
2015-06-01 15:52   ` Michel Thierry
2015-05-22 17:04 ` [PATCH 02/21] drm/i915/gtt: Workaround for HW preload not flushing pdps Mika Kuoppala
2015-05-29 11:05   ` Michel Thierry
2015-05-29 12:53     ` Michel Thierry [this message]
2015-06-10 11:42       ` Michel Thierry
2015-06-11  7:31         ` Dave Gordon
2015-06-11 10:46           ` Michel Thierry
2015-06-11 13:57           ` Mika Kuoppala
2015-08-11  5:05             ` Zhiyuan Lv
2015-08-12  7:56               ` Michel Thierry
2015-08-12 15:09                 ` Dave Gordon
2015-08-13  9:36                   ` Zhiyuan Lv
2015-08-13  9:54                     ` Michel Thierry
2015-08-13  9:08                 ` Zhiyuan Lv
2015-08-13 10:12                   ` Michel Thierry
2015-08-13 11:42                     ` Dave Gordon
2015-08-13 12:03                       ` Dave Gordon
2015-08-13 14:56                         ` Zhiyuan Lv
2015-05-22 17:04 ` [PATCH 03/21] drm/i915/gtt: Check va range against vm size Mika Kuoppala
2015-06-01 15:33   ` Joonas Lahtinen
2015-06-11 14:23     ` Mika Kuoppala
2015-06-24 14:48       ` Michel Thierry
2015-05-22 17:04 ` [PATCH 04/21] drm/i915/gtt: Allow >= 4GB sizes for vm Mika Kuoppala
2015-05-26  7:15   ` Daniel Vetter
2015-06-11 17:38     ` Mika Kuoppala
2015-05-22 17:04 ` [PATCH 05/21] drm/i915/gtt: Don't leak scratch page on mapping error Mika Kuoppala
2015-06-01 15:02   ` Joonas Lahtinen
2015-06-15 10:13     ` Daniel Vetter
2015-05-22 17:04 ` [PATCH 06/21] drm/i915/gtt: Remove _single from page table allocator Mika Kuoppala
2015-06-02  9:53   ` Joonas Lahtinen
2015-06-02  9:56   ` Michel Thierry
2015-06-15 10:14     ` Daniel Vetter
2015-05-22 17:05 ` [PATCH 07/21] drm/i915/gtt: Introduce i915_page_dir_dma_addr Mika Kuoppala
2015-06-02 10:11   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 08/21] drm/i915/gtt: Introduce struct i915_page_dma Mika Kuoppala
2015-06-02 12:39   ` Michel Thierry
2015-06-11 17:48     ` Mika Kuoppala
2015-06-22 14:05       ` Michel Thierry
2015-05-22 17:05 ` [PATCH 09/21] drm/i915/gtt: Rename unmap_and_free_px to free_px Mika Kuoppala
2015-06-02 13:08   ` Michel Thierry
2015-06-11 17:48     ` Mika Kuoppala
2015-06-22 14:09       ` Michel Thierry
2015-06-22 14:43         ` Daniel Vetter
2015-05-22 17:05 ` [PATCH 10/21] drm/i915/gtt: Remove superfluous free_pd with gen6/7 Mika Kuoppala
2015-06-02 14:07   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 11/21] drm/i915/gtt: Introduce fill_page_dma() Mika Kuoppala
2015-06-02 14:51   ` Michel Thierry
2015-06-02 15:01     ` Ville Syrjälä
2015-06-15 10:16       ` Daniel Vetter
2015-06-11 17:50     ` Mika Kuoppala
2015-06-24 15:05       ` Michel Thierry
2015-05-22 17:05 ` [PATCH 12/21] drm/i915/gtt: Introduce kmap|kunmap for dma page Mika Kuoppala
2015-06-03 10:55   ` Michel Thierry
2015-06-11 17:50     ` Mika Kuoppala
2015-06-24 15:06       ` Michel Thierry
2015-05-22 17:05 ` [PATCH 13/21] drm/i915/gtt: Use macros to access dma mapped pages Mika Kuoppala
2015-06-03 10:57   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 14/21] drm/i915/gtt: Make scratch page i915_page_dma compatible Mika Kuoppala
2015-06-03 13:44   ` Michel Thierry
2015-06-11 16:30     ` Mika Kuoppala
2015-06-24 14:59       ` Michel Thierry
2015-05-22 17:05 ` [PATCH 15/21] drm/i915/gtt: Fill scratch page Mika Kuoppala
2015-05-27 18:12   ` Tomas Elf
2015-06-01 15:53     ` Chris Wilson
2015-06-04 11:08       ` Tomas Elf
2015-06-04 11:24         ` Chris Wilson
2015-06-11 16:37     ` Mika Kuoppala
2015-06-03 14:03   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 16/21] drm/i915/gtt: Pin vma during virtual address allocation Mika Kuoppala
2015-06-03 14:27   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 17/21] drm/i915/gtt: Cleanup page directory encoding Mika Kuoppala
2015-06-03 14:58   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 18/21] drm/i915/gtt: Move scratch_pd and scratch_pt into vm area Mika Kuoppala
2015-06-03 16:46   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 19/21] drm/i915/gtt: One instance of scratch page table/directory Mika Kuoppala
2015-06-03 16:57   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 20/21] drm/i915/gtt: Use nonatomic bitmap ops Mika Kuoppala
2015-06-03 17:07   ` Michel Thierry
2015-05-22 17:05 ` [PATCH 21/21] drm/i915/gtt: Reorder page alloc/free/init functions Mika Kuoppala
2015-06-03 17:14   ` Michel Thierry
2015-06-11 17:52     ` Mika Kuoppala

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=55686141.9090107@intel.com \
    --to=michel.thierry@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=mika.kuoppala@linux.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