--- /dev/null
+From 81921a828b94ce2816932c19a5ec74d302972833 Mon Sep 17 00:00:00 2001
+From: Denis Efremov <efremov@linux.com>
+Date: Fri, 5 Jun 2020 20:37:43 +0300
+Subject: drm/amd/display: Use kvfree() to free coeff in build_regamma()
+
+From: Denis Efremov <efremov@linux.com>
+
+commit 81921a828b94ce2816932c19a5ec74d302972833 upstream.
+
+Use kvfree() instead of kfree() to free coeff in build_regamma()
+because the memory is allocated with kvzalloc().
+
+Fixes: e752058b8671 ("drm/amd/display: Optimize gamma calculations")
+Cc: stable@vger.kernel.org
+Signed-off-by: Denis Efremov <efremov@linux.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/amd/display/modules/color/color_gamma.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
++++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+@@ -799,7 +799,7 @@ static bool build_regamma(struct pwl_flo
+ pow_buffer_ptr = -1; // reset back to no optimize
+ ret = true;
+ release:
+- kfree(coeff);
++ kvfree(coeff);
+ return ret;
+ }
+
--- /dev/null
+From 968d81a64a883af2d16dd3f8a6ad6b67db2fde58 Mon Sep 17 00:00:00 2001
+From: Jeykumar Sankaran <jsanka@codeaurora.org>
+Date: Tue, 2 Jun 2020 20:37:31 -0700
+Subject: drm/connector: notify userspace on hotplug after register complete
+
+From: Jeykumar Sankaran <jsanka@codeaurora.org>
+
+commit 968d81a64a883af2d16dd3f8a6ad6b67db2fde58 upstream.
+
+drm connector notifies userspace on hotplug event prematurely before
+late_register and mode_object register completes. This leads to a race
+between userspace and kernel on updating the IDR list. So, move the
+notification to end of connector register.
+
+Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
+Signed-off-by: Steve Cohen <cohens@codeaurora.org>
+Cc: stable@vger.kernel.org
+Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
+Link: https://patchwork.freedesktop.org/patch/msgid/1591155451-10393-1-git-send-email-jsanka@codeaurora.org
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/drm_connector.c | 5 +++++
+ drivers/gpu/drm/drm_sysfs.c | 3 ---
+ 2 files changed, 5 insertions(+), 3 deletions(-)
+
+--- a/drivers/gpu/drm/drm_connector.c
++++ b/drivers/gpu/drm/drm_connector.c
+@@ -27,6 +27,7 @@
+ #include <drm/drm_print.h>
+ #include <drm/drm_drv.h>
+ #include <drm/drm_file.h>
++#include <drm/drm_sysfs.h>
+
+ #include <linux/uaccess.h>
+
+@@ -511,6 +512,10 @@ int drm_connector_register(struct drm_co
+ drm_mode_object_register(connector->dev, &connector->base);
+
+ connector->registration_state = DRM_CONNECTOR_REGISTERED;
++
++ /* Let userspace know we have a new connector */
++ drm_sysfs_hotplug_event(connector->dev);
++
+ goto unlock;
+
+ err_debugfs:
+--- a/drivers/gpu/drm/drm_sysfs.c
++++ b/drivers/gpu/drm/drm_sysfs.c
+@@ -293,9 +293,6 @@ int drm_sysfs_connector_add(struct drm_c
+ return PTR_ERR(connector->kdev);
+ }
+
+- /* Let userspace know we have a new connector */
+- drm_sysfs_hotplug_event(dev);
+-
+ if (connector->ddc)
+ return sysfs_create_link(&connector->kdev->kobj,
+ &connector->ddc->dev.kobj, "ddc");
--- /dev/null
+From d96536f0fe699729a0974eb5b65eb0d87cc747e1 Mon Sep 17 00:00:00 2001
+From: Imre Deak <imre.deak@intel.com>
+Date: Thu, 14 May 2020 23:45:53 +0300
+Subject: drm/i915: Fix AUX power domain toggling across TypeC mode resets
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Imre Deak <imre.deak@intel.com>
+
+commit d96536f0fe699729a0974eb5b65eb0d87cc747e1 upstream.
+
+Make sure to select the port's AUX power domain while holding the TC
+port lock. The domain depends on the port's current TC mode, which may
+get changed under us if we're not holding the lock.
+
+This was left out from
+commit 8c10e2262663 ("drm/i915: Keep the TypeC port mode fixed for detect/AUX transfers")
+
+Cc: <stable@vger.kernel.org> # v5.4+
+Signed-off-by: Imre Deak <imre.deak@intel.com>
+Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
+Link: https://patchwork.freedesktop.org/patch/msgid/20200514204553.27193-1-imre.deak@intel.com
+(cherry picked from commit ae9b6cfe1352da25931bce3ea4acfd4dc1ac8a85)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/display/intel_dp.c | 5 +++--
+ 1 file changed, 3 insertions(+), 2 deletions(-)
+
+--- a/drivers/gpu/drm/i915/display/intel_dp.c
++++ b/drivers/gpu/drm/i915/display/intel_dp.c
+@@ -1292,8 +1292,7 @@ intel_dp_aux_xfer(struct intel_dp *intel
+ bool is_tc_port = intel_phy_is_tc(i915, phy);
+ i915_reg_t ch_ctl, ch_data[5];
+ u32 aux_clock_divider;
+- enum intel_display_power_domain aux_domain =
+- intel_aux_power_domain(intel_dig_port);
++ enum intel_display_power_domain aux_domain;
+ intel_wakeref_t aux_wakeref;
+ intel_wakeref_t pps_wakeref;
+ int i, ret, recv_bytes;
+@@ -1308,6 +1307,8 @@ intel_dp_aux_xfer(struct intel_dp *intel
+ if (is_tc_port)
+ intel_tc_port_lock(intel_dig_port);
+
++ aux_domain = intel_aux_power_domain(intel_dig_port);
++
+ aux_wakeref = intel_display_power_get(i915, aux_domain);
+ pps_wakeref = pps_lock(intel_dp);
+
--- /dev/null
+From 757a9395f33c51c4e6eff2c7c0fbd50226a58224 Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Fri, 22 May 2020 14:27:06 +0100
+Subject: drm/i915/gem: Avoid iterating an empty list
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit 757a9395f33c51c4e6eff2c7c0fbd50226a58224 upstream.
+
+Our __sgt_iter assumes that the scattergather list has at least one
+element. But during construction we may fail in allocating the first
+page, and so mark the first element as the terminator. This is
+unexpected!
+
+[22555.524752] RIP: 0010:shmem_get_pages+0x506/0x710 [i915]
+[22555.524759] Code: 49 8b 2c 24 31 c0 66 89 44 24 40 48 85 ed 0f 84 62 01 00 00 4c 8b 75 00 8b 5d 08 44 8b 7d 0c 48 8b 0d 7e 34 07 e2 49 83 e6 fc <49> 8b 16 41 01 df 48 89 cf 48 89 d0 48 c1 e8 2d 48 85 c9 0f 84 c8
+[22555.524765] RSP: 0018:ffffc9000053f9d0 EFLAGS: 00010246
+[22555.524770] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8881ffffa000
+[22555.524774] RDX: fffffffffffffff4 RSI: ffffffffffffffff RDI: ffffffff821efe00
+[22555.524778] RBP: ffff8881b099ab00 R08: 0000000000000000 R09: 00000000fffffff4
+[22555.524782] R10: 0000000000000002 R11: 00000000ffec0a02 R12: ffff8881cd3c8d60
+[22555.524786] R13: 00000000fffffff4 R14: 0000000000000000 R15: 0000000000000000
+[22555.524790] FS: 00007f4fbeb9b9c0(0000) GS:ffff8881f8580000(0000) knlGS:0000000000000000
+[22555.524795] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+[22555.524799] CR2: 0000000000000000 CR3: 00000001ec7f0004 CR4: 00000000001606e0
+[22555.524803] Call Trace:
+[22555.524919] __i915_gem_object_get_pages+0x4f/0x60 [i915]
+
+Fixes: 85d1225ec066 ("drm/i915: Introduce & use new lightweight SGL iterators")
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Cc: Matthew Auld <matthew.auld@intel.com>
+Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
+Cc: <stable@vger.kernel.org> # v4.8+
+Reviewed-by: Matthew Auld <matthew.auld@intel.com>
+Reviewed-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
+Link: https://patchwork.freedesktop.org/patch/msgid/20200522132706.5133-1-chris@chris-wilson.co.uk
+(cherry picked from commit 957ad9a02be6faa87594c58ac09460cd3d190d0e)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 15 +++++++++------
+ 1 file changed, 9 insertions(+), 6 deletions(-)
+
+--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
++++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+@@ -36,7 +36,6 @@ static int shmem_get_pages(struct drm_i9
+ unsigned long last_pfn = 0; /* suppress gcc warning */
+ unsigned int max_segment = i915_sg_segment_size();
+ unsigned int sg_page_sizes;
+- struct pagevec pvec;
+ gfp_t noreclaim;
+ int ret;
+
+@@ -188,13 +187,17 @@ err_sg:
+ sg_mark_end(sg);
+ err_pages:
+ mapping_clear_unevictable(mapping);
+- pagevec_init(&pvec);
+- for_each_sgt_page(page, sgt_iter, st) {
+- if (!pagevec_add(&pvec, page))
++ if (sg != st->sgl) {
++ struct pagevec pvec;
++
++ pagevec_init(&pvec);
++ for_each_sgt_page(page, sgt_iter, st) {
++ if (!pagevec_add(&pvec, page))
++ check_release_pagevec(&pvec);
++ }
++ if (pagevec_count(&pvec))
+ check_release_pagevec(&pvec);
+ }
+- if (pagevec_count(&pvec))
+- check_release_pagevec(&pvec);
+ sg_free_table(st);
+ kfree(st);
+
--- /dev/null
+From 27582a9c917940bc71c0df0b8e022cbde8d735d2 Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Thu, 11 Jun 2020 09:01:40 +0100
+Subject: drm/i915/gt: Move gen4 GT workarounds from init_clock_gating to workarounds
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit 27582a9c917940bc71c0df0b8e022cbde8d735d2 upstream.
+
+Rescue the GT workarounds from being buried inside init_clock_gating so
+that we remember to apply them after a GT reset, and that they are
+included in our verification that the workarounds are applied.
+
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20200611080140.30228-6-chris@chris-wilson.co.uk
+(cherry picked from commit 2bcefd0d263ab4a72f0d61921ae6b0dc81606551)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/gt/intel_workarounds.c | 27 ++++++++++++++++++++++-----
+ drivers/gpu/drm/i915/intel_pm.c | 15 ---------------
+ 2 files changed, 22 insertions(+), 20 deletions(-)
+
+--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
++++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
+@@ -656,15 +656,28 @@ int intel_engine_emit_ctx_wa(struct i915
+ }
+
+ static void
+-ilk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++gen4_gt_workarounds_init(struct drm_i915_private *i915,
++ struct i915_wa_list *wal)
+ {
+- wa_masked_en(wal, _3D_CHICKEN2, _3D_CHICKEN2_WM_READ_PIPELINED);
++ /* WaDisable_RenderCache_OperationalFlush:gen4,ilk */
++ wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
++}
++
++static void
++g4x_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++{
++ gen4_gt_workarounds_init(i915, wal);
+
+- /* WaDisableRenderCachePipelinedFlush:ilk */
++ /* WaDisableRenderCachePipelinedFlush:g4x,ilk */
+ wa_masked_en(wal, CACHE_MODE_0, CM0_PIPELINED_RENDER_FLUSH_DISABLE);
++}
+
+- /* WaDisable_RenderCache_OperationalFlush:ilk */
+- wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
++static void
++ilk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++{
++ g4x_gt_workarounds_init(i915, wal);
++
++ wa_masked_en(wal, _3D_CHICKEN2, _3D_CHICKEN2_WM_READ_PIPELINED);
+ }
+
+ static void
+@@ -1140,6 +1153,10 @@ gt_init_workarounds(struct drm_i915_priv
+ snb_gt_workarounds_init(i915, wal);
+ else if (IS_GEN(i915, 5))
+ ilk_gt_workarounds_init(i915, wal);
++ else if (IS_G4X(i915))
++ g4x_gt_workarounds_init(i915, wal);
++ else if (IS_GEN(i915, 4))
++ gen4_gt_workarounds_init(i915, wal);
+ else if (INTEL_GEN(i915) <= 8)
+ return;
+ else
+--- a/drivers/gpu/drm/i915/intel_pm.c
++++ b/drivers/gpu/drm/i915/intel_pm.c
+@@ -9425,13 +9425,6 @@ static void g4x_init_clock_gating(struct
+ dspclk_gate |= DSSUNIT_CLOCK_GATE_DISABLE;
+ I915_WRITE(DSPCLK_GATE_D, dspclk_gate);
+
+- /* WaDisableRenderCachePipelinedFlush */
+- I915_WRITE(CACHE_MODE_0,
+- _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
+-
+- /* WaDisable_RenderCache_OperationalFlush:g4x */
+- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+-
+ g4x_disable_trickle_feed(dev_priv);
+ }
+
+@@ -9447,11 +9440,6 @@ static void i965gm_init_clock_gating(str
+ intel_uncore_write(uncore,
+ MI_ARB_STATE,
+ _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
+-
+- /* WaDisable_RenderCache_OperationalFlush:gen4 */
+- intel_uncore_write(uncore,
+- CACHE_MODE_0,
+- _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+ }
+
+ static void i965g_init_clock_gating(struct drm_i915_private *dev_priv)
+@@ -9464,9 +9452,6 @@ static void i965g_init_clock_gating(stru
+ I915_WRITE(RENCLK_GATE_D2, 0);
+ I915_WRITE(MI_ARB_STATE,
+ _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
+-
+- /* WaDisable_RenderCache_OperationalFlush:gen4 */
+- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+ }
+
+ static void gen3_init_clock_gating(struct drm_i915_private *dev_priv)
--- /dev/null
+From ef50fa9bd17d13d0611e39e13b37bbd3e1ea50bf Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Thu, 11 Jun 2020 10:30:15 +0100
+Subject: drm/i915/gt: Move hsw GT workarounds from init_clock_gating to workarounds
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit ef50fa9bd17d13d0611e39e13b37bbd3e1ea50bf upstream.
+
+Rescue the GT workarounds from being buried inside init_clock_gating so
+that we remember to apply them after a GT reset, and that they are
+included in our verification that the workarounds are applied.
+
+v2: Leave HSW_SCRATCH to set an explicit value, not or in our disable
+bit.
+
+Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2011
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20200611093015.11370-1-chris@chris-wilson.co.uk
+(cherry picked from commit f93ec5fb563779bda4501890b1854526de58e0f1)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/gt/intel_workarounds.c | 48 ++++++++++++++++++++++++++++
+ drivers/gpu/drm/i915/intel_pm.c | 39 +---------------------
+ 2 files changed, 50 insertions(+), 37 deletions(-)
+
+--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
++++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
+@@ -160,6 +160,12 @@ wa_write_masked_or(struct i915_wa_list *
+ }
+
+ static void
++wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
++{
++ wa_write_masked_or(wal, reg, clr, 0);
++}
++
++static void
+ wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
+ {
+ wa_write_masked_or(wal, reg, val, _MASKED_BIT_ENABLE(val));
+@@ -650,6 +656,46 @@ int intel_engine_emit_ctx_wa(struct i915
+ }
+
+ static void
++hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++{
++ /* L3 caching of data atomics doesn't work -- disable it. */
++ wa_write(wal, HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
++
++ wa_add(wal,
++ HSW_ROW_CHICKEN3, 0,
++ _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE),
++ 0 /* XXX does this reg exist? */);
++
++ /* WaVSRefCountFullforceMissDisable:hsw */
++ wa_write_clr(wal, GEN7_FF_THREAD_MODE, GEN7_FF_VS_REF_CNT_FFME);
++
++ wa_masked_dis(wal,
++ CACHE_MODE_0_GEN7,
++ /* WaDisable_RenderCache_OperationalFlush:hsw */
++ RC_OP_FLUSH_ENABLE |
++ /* enable HiZ Raw Stall Optimization */
++ HIZ_RAW_STALL_OPT_DISABLE);
++
++ /* WaDisable4x2SubspanOptimization:hsw */
++ wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
++
++ /*
++ * BSpec recommends 8x4 when MSAA is used,
++ * however in practice 16x4 seems fastest.
++ *
++ * Note that PS/WM thread counts depend on the WIZ hashing
++ * disable bit, which we don't touch here, but it's good
++ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
++ */
++ wa_add(wal, GEN7_GT_MODE, 0,
++ _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
++ GEN6_WIZ_HASHING_16x4);
++
++ /* WaSampleCChickenBitEnable:hsw */
++ wa_masked_en(wal, HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE);
++}
++
++static void
+ gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+ {
+ /* WaDisableKillLogic:bxt,skl,kbl */
+@@ -916,6 +962,8 @@ gt_init_workarounds(struct drm_i915_priv
+ bxt_gt_workarounds_init(i915, wal);
+ else if (IS_SKYLAKE(i915))
+ skl_gt_workarounds_init(i915, wal);
++ else if (IS_HASWELL(i915))
++ hsw_gt_workarounds_init(i915, wal);
+ else if (INTEL_GEN(i915) <= 8)
+ return;
+ else
+--- a/drivers/gpu/drm/i915/intel_pm.c
++++ b/drivers/gpu/drm/i915/intel_pm.c
+@@ -9347,45 +9347,10 @@ static void bdw_init_clock_gating(struct
+
+ static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
+ {
+- /* L3 caching of data atomics doesn't work -- disable it. */
+- I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
+- I915_WRITE(HSW_ROW_CHICKEN3,
+- _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
+-
+ /* This is required by WaCatErrorRejectionIssue:hsw */
+ I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
+- I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
+- GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+-
+- /* WaVSRefCountFullforceMissDisable:hsw */
+- I915_WRITE(GEN7_FF_THREAD_MODE,
+- I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
+-
+- /* WaDisable_RenderCache_OperationalFlush:hsw */
+- I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+-
+- /* enable HiZ Raw Stall Optimization */
+- I915_WRITE(CACHE_MODE_0_GEN7,
+- _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
+-
+- /* WaDisable4x2SubspanOptimization:hsw */
+- I915_WRITE(CACHE_MODE_1,
+- _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
+-
+- /*
+- * BSpec recommends 8x4 when MSAA is used,
+- * however in practice 16x4 seems fastest.
+- *
+- * Note that PS/WM thread counts depend on the WIZ hashing
+- * disable bit, which we don't touch here, but it's good
+- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+- */
+- I915_WRITE(GEN7_GT_MODE,
+- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
+-
+- /* WaSampleCChickenBitEnable:hsw */
+- I915_WRITE(HALF_SLICE_CHICKEN3,
+- _MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE));
++ I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
++ GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+
+ /* WaSwitchSolVfFArbitrationPriority:hsw */
+ I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
--- /dev/null
+From eacf21040aa97fd1b3c6bb201bfd43820e1c49be Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Thu, 11 Jun 2020 09:01:39 +0100
+Subject: drm/i915/gt: Move ilk GT workarounds from init_clock_gating to workarounds
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit eacf21040aa97fd1b3c6bb201bfd43820e1c49be upstream.
+
+Rescue the GT workarounds from being buried inside init_clock_gating so
+that we remember to apply them after a GT reset, and that they are
+included in our verification that the workarounds are applied.
+
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20200611080140.30228-5-chris@chris-wilson.co.uk
+(cherry picked from commit 806a45c0838d253e306a6384057e851b65d11099)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/gt/intel_workarounds.c | 14 ++++++++++++++
+ drivers/gpu/drm/i915/intel_pm.c | 10 ----------
+ 2 files changed, 14 insertions(+), 10 deletions(-)
+
+--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
++++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
+@@ -656,6 +656,18 @@ int intel_engine_emit_ctx_wa(struct i915
+ }
+
+ static void
++ilk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++{
++ wa_masked_en(wal, _3D_CHICKEN2, _3D_CHICKEN2_WM_READ_PIPELINED);
++
++ /* WaDisableRenderCachePipelinedFlush:ilk */
++ wa_masked_en(wal, CACHE_MODE_0, CM0_PIPELINED_RENDER_FLUSH_DISABLE);
++
++ /* WaDisable_RenderCache_OperationalFlush:ilk */
++ wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
++}
++
++static void
+ snb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+ {
+ /* WaDisableHiZPlanesWhenMSAAEnabled:snb */
+@@ -1067,6 +1079,8 @@ gt_init_workarounds(struct drm_i915_priv
+ ivb_gt_workarounds_init(i915, wal);
+ else if (IS_GEN(i915, 6))
+ snb_gt_workarounds_init(i915, wal);
++ else if (IS_GEN(i915, 5))
++ ilk_gt_workarounds_init(i915, wal);
+ else if (INTEL_GEN(i915) <= 8)
+ return;
+ else
+--- a/drivers/gpu/drm/i915/intel_pm.c
++++ b/drivers/gpu/drm/i915/intel_pm.c
+@@ -8958,16 +8958,6 @@ static void ilk_init_clock_gating(struct
+ I915_WRITE(ILK_DISPLAY_CHICKEN2,
+ I915_READ(ILK_DISPLAY_CHICKEN2) |
+ ILK_ELPIN_409_SELECT);
+- I915_WRITE(_3D_CHICKEN2,
+- _3D_CHICKEN2_WM_READ_PIPELINED << 16 |
+- _3D_CHICKEN2_WM_READ_PIPELINED);
+-
+- /* WaDisableRenderCachePipelinedFlush:ilk */
+- I915_WRITE(CACHE_MODE_0,
+- _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
+-
+- /* WaDisable_RenderCache_OperationalFlush:ilk */
+- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+
+ g4x_disable_trickle_feed(dev_priv);
+
--- /dev/null
+From 7237b190add0794bd95979018a23eda698f2705d Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Thu, 11 Jun 2020 09:01:36 +0100
+Subject: drm/i915/gt: Move ivb GT workarounds from init_clock_gating to workarounds
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit 7237b190add0794bd95979018a23eda698f2705d upstream.
+
+Rescue the GT workarounds from being buried inside init_clock_gating so
+that we remember to apply them after a GT reset, and that they are
+included in our verification that the workarounds are applied.
+
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20200611080140.30228-2-chris@chris-wilson.co.uk
+(cherry picked from commit 19f1f627b33385a2f0855cbc7d33d86d7f4a1e78)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/gt/intel_workarounds.c | 62 ++++++++++++++++++++++++++++
+ drivers/gpu/drm/i915/i915_reg.h | 2
+ drivers/gpu/drm/i915/intel_pm.c | 48 ---------------------
+ 3 files changed, 63 insertions(+), 49 deletions(-)
+
+--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
++++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
+@@ -656,6 +656,66 @@ int intel_engine_emit_ctx_wa(struct i915
+ }
+
+ static void
++ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++{
++ /* WaDisableEarlyCull:ivb */
++ wa_masked_en(wal, _3D_CHICKEN3, _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
++
++ /* WaDisablePSDDualDispatchEnable:ivb */
++ if (IS_IVB_GT1(i915))
++ wa_masked_en(wal,
++ GEN7_HALF_SLICE_CHICKEN1,
++ GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
++
++ /* WaDisable_RenderCache_OperationalFlush:ivb */
++ wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
++
++ /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
++ wa_masked_dis(wal,
++ GEN7_COMMON_SLICE_CHICKEN1,
++ GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
++
++ /* WaApplyL3ControlAndL3ChickenMode:ivb */
++ wa_write(wal, GEN7_L3CNTLREG1, GEN7_WA_FOR_GEN7_L3_CONTROL);
++ wa_write(wal, GEN7_L3_CHICKEN_MODE_REGISTER, GEN7_WA_L3_CHICKEN_MODE);
++
++ /* WaForceL3Serialization:ivb */
++ wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE);
++
++ /*
++ * WaVSThreadDispatchOverride:ivb,vlv
++ *
++ * This actually overrides the dispatch
++ * mode for all thread types.
++ */
++ wa_write_masked_or(wal, GEN7_FF_THREAD_MODE,
++ GEN7_FF_SCHED_MASK,
++ GEN7_FF_TS_SCHED_HW |
++ GEN7_FF_VS_SCHED_HW |
++ GEN7_FF_DS_SCHED_HW);
++
++ if (0) { /* causes HiZ corruption on ivb:gt1 */
++ /* enable HiZ Raw Stall Optimization */
++ wa_masked_dis(wal, CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
++ }
++
++ /* WaDisable4x2SubspanOptimization:ivb */
++ wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
++
++ /*
++ * BSpec recommends 8x4 when MSAA is used,
++ * however in practice 16x4 seems fastest.
++ *
++ * Note that PS/WM thread counts depend on the WIZ hashing
++ * disable bit, which we don't touch here, but it's good
++ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
++ */
++ wa_add(wal, GEN7_GT_MODE, 0,
++ _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
++ GEN6_WIZ_HASHING_16x4);
++}
++
++static void
+ hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+ {
+ /* L3 caching of data atomics doesn't work -- disable it. */
+@@ -964,6 +1024,8 @@ gt_init_workarounds(struct drm_i915_priv
+ skl_gt_workarounds_init(i915, wal);
+ else if (IS_HASWELL(i915))
+ hsw_gt_workarounds_init(i915, wal);
++ else if (IS_IVYBRIDGE(i915))
++ ivb_gt_workarounds_init(i915, wal);
+ else if (INTEL_GEN(i915) <= 8)
+ return;
+ else
+--- a/drivers/gpu/drm/i915/i915_reg.h
++++ b/drivers/gpu/drm/i915/i915_reg.h
+@@ -7636,7 +7636,7 @@ enum {
+
+ /* GEN7 chicken */
+ #define GEN7_COMMON_SLICE_CHICKEN1 _MMIO(0x7010)
+- #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC ((1 << 10) | (1 << 26))
++ #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC (1 << 10)
+ #define GEN9_RHWO_OPTIMIZATION_DISABLE (1 << 14)
+
+ #define COMMON_SLICE_CHICKEN2 _MMIO(0x7014)
+--- a/drivers/gpu/drm/i915/intel_pm.c
++++ b/drivers/gpu/drm/i915/intel_pm.c
+@@ -9364,32 +9364,11 @@ static void ivb_init_clock_gating(struct
+
+ I915_WRITE(ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
+
+- /* WaDisableEarlyCull:ivb */
+- I915_WRITE(_3D_CHICKEN3,
+- _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
+-
+ /* WaDisableBackToBackFlipFix:ivb */
+ I915_WRITE(IVB_CHICKEN3,
+ CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
+ CHICKEN3_DGMG_DONE_FIX_DISABLE);
+
+- /* WaDisablePSDDualDispatchEnable:ivb */
+- if (IS_IVB_GT1(dev_priv))
+- I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
+- _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
+-
+- /* WaDisable_RenderCache_OperationalFlush:ivb */
+- I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+-
+- /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
+- I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
+- GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
+-
+- /* WaApplyL3ControlAndL3ChickenMode:ivb */
+- I915_WRITE(GEN7_L3CNTLREG1,
+- GEN7_WA_FOR_GEN7_L3_CONTROL);
+- I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
+- GEN7_WA_L3_CHICKEN_MODE);
+ if (IS_IVB_GT1(dev_priv))
+ I915_WRITE(GEN7_ROW_CHICKEN2,
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+@@ -9401,10 +9380,6 @@ static void ivb_init_clock_gating(struct
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+ }
+
+- /* WaForceL3Serialization:ivb */
+- I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
+- ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
+-
+ /*
+ * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
+ * This implements the WaDisableRCZUnitClockGating:ivb workaround.
+@@ -9419,29 +9394,6 @@ static void ivb_init_clock_gating(struct
+
+ g4x_disable_trickle_feed(dev_priv);
+
+- gen7_setup_fixed_func_scheduler(dev_priv);
+-
+- if (0) { /* causes HiZ corruption on ivb:gt1 */
+- /* enable HiZ Raw Stall Optimization */
+- I915_WRITE(CACHE_MODE_0_GEN7,
+- _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
+- }
+-
+- /* WaDisable4x2SubspanOptimization:ivb */
+- I915_WRITE(CACHE_MODE_1,
+- _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
+-
+- /*
+- * BSpec recommends 8x4 when MSAA is used,
+- * however in practice 16x4 seems fastest.
+- *
+- * Note that PS/WM thread counts depend on the WIZ hashing
+- * disable bit, which we don't touch here, but it's good
+- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+- */
+- I915_WRITE(GEN7_GT_MODE,
+- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
+-
+ snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
+ snpcr &= ~GEN6_MBC_SNPCR_MASK;
+ snpcr |= GEN6_MBC_SNPCR_MED;
--- /dev/null
+From fd2599bda5a989c3332f4956fd7760ec32bd51ee Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Thu, 11 Jun 2020 09:01:38 +0100
+Subject: drm/i915/gt: Move snb GT workarounds from init_clock_gating to workarounds
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit fd2599bda5a989c3332f4956fd7760ec32bd51ee upstream.
+
+Rescue the GT workarounds from being buried inside init_clock_gating so
+that we remember to apply them after a GT reset, and that they are
+included in our verification that the workarounds are applied.
+
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20200611080140.30228-4-chris@chris-wilson.co.uk
+(cherry picked from commit c3b93a943f2c9ee4a106db100a2fc3b2f126bfc5)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/gt/intel_workarounds.c | 41 ++++++++++++++++++++++++++++
+ drivers/gpu/drm/i915/intel_pm.c | 33 ----------------------
+ 2 files changed, 41 insertions(+), 33 deletions(-)
+
+--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
++++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
+@@ -656,6 +656,45 @@ int intel_engine_emit_ctx_wa(struct i915
+ }
+
+ static void
++snb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++{
++ /* WaDisableHiZPlanesWhenMSAAEnabled:snb */
++ wa_masked_en(wal,
++ _3D_CHICKEN,
++ _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB);
++
++ /* WaDisable_RenderCache_OperationalFlush:snb */
++ wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
++
++ /*
++ * BSpec recommends 8x4 when MSAA is used,
++ * however in practice 16x4 seems fastest.
++ *
++ * Note that PS/WM thread counts depend on the WIZ hashing
++ * disable bit, which we don't touch here, but it's good
++ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
++ */
++ wa_add(wal,
++ GEN6_GT_MODE, 0,
++ _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
++ GEN6_WIZ_HASHING_16x4);
++
++ wa_masked_dis(wal, CACHE_MODE_0, CM0_STC_EVICT_DISABLE_LRA_SNB);
++
++ wa_masked_en(wal,
++ _3D_CHICKEN3,
++ /* WaStripsFansDisableFastClipPerformanceFix:snb */
++ _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL |
++ /*
++ * Bspec says:
++ * "This bit must be set if 3DSTATE_CLIP clip mode is set
++ * to normal and 3DSTATE_SF number of SF output attributes
++ * is more than 16."
++ */
++ _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH);
++}
++
++static void
+ ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+ {
+ /* WaDisableEarlyCull:ivb */
+@@ -1026,6 +1065,8 @@ gt_init_workarounds(struct drm_i915_priv
+ hsw_gt_workarounds_init(i915, wal);
+ else if (IS_IVYBRIDGE(i915))
+ ivb_gt_workarounds_init(i915, wal);
++ else if (IS_GEN(i915, 6))
++ snb_gt_workarounds_init(i915, wal);
+ else if (INTEL_GEN(i915) <= 8)
+ return;
+ else
+--- a/drivers/gpu/drm/i915/intel_pm.c
++++ b/drivers/gpu/drm/i915/intel_pm.c
+@@ -9030,27 +9030,6 @@ static void gen6_init_clock_gating(struc
+ I915_READ(ILK_DISPLAY_CHICKEN2) |
+ ILK_ELPIN_409_SELECT);
+
+- /* WaDisableHiZPlanesWhenMSAAEnabled:snb */
+- I915_WRITE(_3D_CHICKEN,
+- _MASKED_BIT_ENABLE(_3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB));
+-
+- /* WaDisable_RenderCache_OperationalFlush:snb */
+- I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+-
+- /*
+- * BSpec recoomends 8x4 when MSAA is used,
+- * however in practice 16x4 seems fastest.
+- *
+- * Note that PS/WM thread counts depend on the WIZ hashing
+- * disable bit, which we don't touch here, but it's good
+- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+- */
+- I915_WRITE(GEN6_GT_MODE,
+- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
+-
+- I915_WRITE(CACHE_MODE_0,
+- _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
+-
+ I915_WRITE(GEN6_UCGCTL1,
+ I915_READ(GEN6_UCGCTL1) |
+ GEN6_BLBUNIT_CLOCK_GATE_DISABLE |
+@@ -9073,18 +9052,6 @@ static void gen6_init_clock_gating(struc
+ GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
+ GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
+
+- /* WaStripsFansDisableFastClipPerformanceFix:snb */
+- I915_WRITE(_3D_CHICKEN3,
+- _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL));
+-
+- /*
+- * Bspec says:
+- * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and
+- * 3DSTATE_SF number of SF output attributes is more than 16."
+- */
+- I915_WRITE(_3D_CHICKEN3,
+- _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH));
+-
+ /*
+ * According to the spec the following bits should be
+ * set in order to enable memory self-refresh and fbc:
--- /dev/null
+From 695a2b11649e99bbf15d278042247042c42b8728 Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Thu, 11 Jun 2020 09:01:37 +0100
+Subject: drm/i915/gt: Move vlv GT workarounds from init_clock_gating to workarounds
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit 695a2b11649e99bbf15d278042247042c42b8728 upstream.
+
+Rescue the GT workarounds from being buried inside init_clock_gating so
+that we remember to apply them after a GT reset, and that they are
+included in our verification that the workarounds are applied.
+
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20200611080140.30228-3-chris@chris-wilson.co.uk
+(cherry picked from commit 7331c356b6d2d8a01422cacab27478a1dba9fa2a)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/gt/intel_workarounds.c | 59 +++++++++++++++++++++++++++
+ drivers/gpu/drm/i915/intel_pm.c | 61 ----------------------------
+ 2 files changed, 59 insertions(+), 61 deletions(-)
+
+--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
++++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
+@@ -767,6 +767,63 @@ ivb_gt_workarounds_init(struct drm_i915_
+ }
+
+ static void
++vlv_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
++{
++ /* WaDisableEarlyCull:vlv */
++ wa_masked_en(wal, _3D_CHICKEN3, _3D_CHICKEN_SF_DISABLE_OBJEND_CULL);
++
++ /* WaPsdDispatchEnable:vlv */
++ /* WaDisablePSDDualDispatchEnable:vlv */
++ wa_masked_en(wal,
++ GEN7_HALF_SLICE_CHICKEN1,
++ GEN7_MAX_PS_THREAD_DEP |
++ GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE);
++
++ /* WaDisable_RenderCache_OperationalFlush:vlv */
++ wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
++
++ /* WaForceL3Serialization:vlv */
++ wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE);
++
++ /*
++ * WaVSThreadDispatchOverride:ivb,vlv
++ *
++ * This actually overrides the dispatch
++ * mode for all thread types.
++ */
++ wa_write_masked_or(wal,
++ GEN7_FF_THREAD_MODE,
++ GEN7_FF_SCHED_MASK,
++ GEN7_FF_TS_SCHED_HW |
++ GEN7_FF_VS_SCHED_HW |
++ GEN7_FF_DS_SCHED_HW);
++
++ /*
++ * BSpec says this must be set, even though
++ * WaDisable4x2SubspanOptimization isn't listed for VLV.
++ */
++ wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
++
++ /*
++ * BSpec recommends 8x4 when MSAA is used,
++ * however in practice 16x4 seems fastest.
++ *
++ * Note that PS/WM thread counts depend on the WIZ hashing
++ * disable bit, which we don't touch here, but it's good
++ * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
++ */
++ wa_add(wal, GEN7_GT_MODE, 0,
++ _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
++ GEN6_WIZ_HASHING_16x4);
++
++ /*
++ * WaIncreaseL3CreditsForVLVB0:vlv
++ * This is the hardware default actually.
++ */
++ wa_write(wal, GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE);
++}
++
++static void
+ hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+ {
+ /* L3 caching of data atomics doesn't work -- disable it. */
+@@ -1075,6 +1132,8 @@ gt_init_workarounds(struct drm_i915_priv
+ skl_gt_workarounds_init(i915, wal);
+ else if (IS_HASWELL(i915))
+ hsw_gt_workarounds_init(i915, wal);
++ else if (IS_VALLEYVIEW(i915))
++ vlv_gt_workarounds_init(i915, wal);
+ else if (IS_IVYBRIDGE(i915))
+ ivb_gt_workarounds_init(i915, wal);
+ else if (IS_GEN(i915, 6))
+--- a/drivers/gpu/drm/i915/intel_pm.c
++++ b/drivers/gpu/drm/i915/intel_pm.c
+@@ -9071,24 +9071,6 @@ static void gen6_init_clock_gating(struc
+ gen6_check_mch_setup(dev_priv);
+ }
+
+-static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv)
+-{
+- u32 reg = I915_READ(GEN7_FF_THREAD_MODE);
+-
+- /*
+- * WaVSThreadDispatchOverride:ivb,vlv
+- *
+- * This actually overrides the dispatch
+- * mode for all thread types.
+- */
+- reg &= ~GEN7_FF_SCHED_MASK;
+- reg |= GEN7_FF_TS_SCHED_HW;
+- reg |= GEN7_FF_VS_SCHED_HW;
+- reg |= GEN7_FF_DS_SCHED_HW;
+-
+- I915_WRITE(GEN7_FF_THREAD_MODE, reg);
+-}
+-
+ static void lpt_init_clock_gating(struct drm_i915_private *dev_priv)
+ {
+ /*
+@@ -9364,28 +9346,11 @@ static void ivb_init_clock_gating(struct
+
+ static void vlv_init_clock_gating(struct drm_i915_private *dev_priv)
+ {
+- /* WaDisableEarlyCull:vlv */
+- I915_WRITE(_3D_CHICKEN3,
+- _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_DISABLE_OBJEND_CULL));
+-
+ /* WaDisableBackToBackFlipFix:vlv */
+ I915_WRITE(IVB_CHICKEN3,
+ CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
+ CHICKEN3_DGMG_DONE_FIX_DISABLE);
+
+- /* WaPsdDispatchEnable:vlv */
+- /* WaDisablePSDDualDispatchEnable:vlv */
+- I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
+- _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP |
+- GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
+-
+- /* WaDisable_RenderCache_OperationalFlush:vlv */
+- I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+-
+- /* WaForceL3Serialization:vlv */
+- I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
+- ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
+-
+ /* WaDisableDopClockGating:vlv */
+ I915_WRITE(GEN7_ROW_CHICKEN2,
+ _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+@@ -9395,8 +9360,6 @@ static void vlv_init_clock_gating(struct
+ I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
+ GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+
+- gen7_setup_fixed_func_scheduler(dev_priv);
+-
+ /*
+ * According to the spec, bit 13 (RCZUNIT) must be set on IVB.
+ * This implements the WaDisableRCZUnitClockGating:vlv workaround.
+@@ -9411,30 +9374,6 @@ static void vlv_init_clock_gating(struct
+ I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
+
+ /*
+- * BSpec says this must be set, even though
+- * WaDisable4x2SubspanOptimization isn't listed for VLV.
+- */
+- I915_WRITE(CACHE_MODE_1,
+- _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
+-
+- /*
+- * BSpec recommends 8x4 when MSAA is used,
+- * however in practice 16x4 seems fastest.
+- *
+- * Note that PS/WM thread counts depend on the WIZ hashing
+- * disable bit, which we don't touch here, but it's good
+- * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+- */
+- I915_WRITE(GEN7_GT_MODE,
+- _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
+-
+- /*
+- * WaIncreaseL3CreditsForVLVB0:vlv
+- * This is the hardware default actually.
+- */
+- I915_WRITE(GEN7_L3SQCREG1, VLV_B0_WA_L3SQCREG1_VALUE);
+-
+- /*
+ * WaDisableVLVClockGating_VBIIssue:vlv
+ * Disable clock gating on th GCFG unit to prevent a delay
+ * in the reporting of vblank events.
--- /dev/null
+From a3005c2edf7e8c3478880db1ca84028a2b6819bb Mon Sep 17 00:00:00 2001
+From: Imre Deak <imre.deak@intel.com>
+Date: Fri, 12 Jun 2020 15:17:31 +0300
+Subject: drm/i915/icl+: Fix hotplug interrupt disabling after storm detection
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Imre Deak <imre.deak@intel.com>
+
+commit a3005c2edf7e8c3478880db1ca84028a2b6819bb upstream.
+
+Atm, hotplug interrupts on TypeC ports are left enabled after detecting
+an interrupt storm, fix this.
+
+Reported-by: Kunal Joshi <kunal1.joshi@intel.com>
+References: https://gitlab.freedesktop.org/drm/intel/-/issues/351
+Bugzilla: https://gitlab.freedesktop.org/drm/intel/-/issues/1964
+Cc: Kunal Joshi <kunal1.joshi@intel.com>
+Cc: stable@vger.kernel.org
+Signed-off-by: Imre Deak <imre.deak@intel.com>
+Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
+Link: https://patchwork.freedesktop.org/patch/msgid/20200612121731.19596-1-imre.deak@intel.com
+(cherry picked from commit 587a87b9d7e94927edcdea018565bc1939381eb1)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/i915_irq.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/gpu/drm/i915/i915_irq.c
++++ b/drivers/gpu/drm/i915/i915_irq.c
+@@ -3500,6 +3500,7 @@ static void gen11_hpd_irq_setup(struct d
+
+ val = I915_READ(GEN11_DE_HPD_IMR);
+ val &= ~hotplug_irqs;
++ val |= ~enabled_irqs & hotplug_irqs;
+ I915_WRITE(GEN11_DE_HPD_IMR, val);
+ POSTING_READ(GEN11_DE_HPD_IMR);
+
--- /dev/null
+From 273500ae71711c040d258a7b3f4b6f44c368fff2 Mon Sep 17 00:00:00 2001
+From: Chris Wilson <chris@chris-wilson.co.uk>
+Date: Mon, 1 Jun 2020 17:19:42 +0100
+Subject: drm/i915: Whitelist context-local timestamp in the gen9 cmdparser
+
+From: Chris Wilson <chris@chris-wilson.co.uk>
+
+commit 273500ae71711c040d258a7b3f4b6f44c368fff2 upstream.
+
+Allow batch buffers to read their own _local_ cumulative HW runtime of
+their logical context.
+
+Fixes: 0f2f39758341 ("drm/i915: Add gen9 BCS cmdparsing")
+Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
+Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Cc: <stable@vger.kernel.org> # v5.4+
+Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
+Link: https://patchwork.freedesktop.org/patch/msgid/20200601161942.30854-1-chris@chris-wilson.co.uk
+(cherry picked from commit f9496520df11de00fbafc3cbd693b9570d600ab3)
+Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/i915/i915_cmd_parser.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
++++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
+@@ -572,6 +572,9 @@ struct drm_i915_reg_descriptor {
+ #define REG32(_reg, ...) \
+ { .addr = (_reg), __VA_ARGS__ }
+
++#define REG32_IDX(_reg, idx) \
++ { .addr = _reg(idx) }
++
+ /*
+ * Convenience macro for adding 64-bit registers.
+ *
+@@ -669,6 +672,7 @@ static const struct drm_i915_reg_descrip
+ REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
+ REG32(BCS_SWCTRL),
+ REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
++ REG32_IDX(RING_CTX_TIMESTAMP, BLT_RING_BASE),
+ REG64_IDX(BCS_GPR, 0),
+ REG64_IDX(BCS_GPR, 1),
+ REG64_IDX(BCS_GPR, 2),
--- /dev/null
+From eadf79286a4badebc95af7061530bdb50a7e6f38 Mon Sep 17 00:00:00 2001
+From: Jordan Crouse <jcrouse@codeaurora.org>
+Date: Fri, 1 May 2020 13:43:26 -0600
+Subject: drm/msm: Check for powered down HW in the devfreq callbacks
+
+From: Jordan Crouse <jcrouse@codeaurora.org>
+
+commit eadf79286a4badebc95af7061530bdb50a7e6f38 upstream.
+
+Writing to the devfreq sysfs nodes while the GPU is powered down can
+result in a system crash (on a5xx) or a nasty GMU error (on a6xx):
+
+ $ /sys/class/devfreq/5000000.gpu# echo 500000000 > min_freq
+ [ 104.841625] platform 506a000.gmu: [drm:a6xx_gmu_set_oob]
+ *ERROR* Timeout waiting for GMU OOB set GPU_DCVS: 0x0
+
+Despite the fact that we carefully try to suspend the devfreq device when
+the hardware is powered down there are lots of holes in the governors that
+don't check for the suspend state and blindly call into the devfreq
+callbacks that end up triggering hardware reads in the GPU driver.
+
+Call pm_runtime_get_if_in_use() in the gpu_busy() and gpu_set_freq()
+callbacks to skip the hardware access if it isn't active.
+
+v3: Only check pm_runtime_get_if_in_use() for == 0 per Eric Anholt
+v2: Use pm_runtime_get_if_in_use() per Eric Anholt
+
+Cc: stable@vger.kernel.org
+Reviewed-by: Eric Anholt <eric@anholt.net>
+Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
+Signed-off-by: Rob Clark <robdclark@chromium.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 6 ++++++
+ drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 8 ++++++++
+ drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 7 +++++++
+ 3 files changed, 21 insertions(+)
+
+--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
++++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+@@ -1359,6 +1359,10 @@ static unsigned long a5xx_gpu_busy(struc
+ {
+ u64 busy_cycles, busy_time;
+
++ /* Only read the gpu busy if the hardware is already active */
++ if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
++ return 0;
++
+ busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO,
+ REG_A5XX_RBBM_PERFCTR_RBBM_0_HI);
+
+@@ -1367,6 +1371,8 @@ static unsigned long a5xx_gpu_busy(struc
+
+ gpu->devfreq.busy_cycles = busy_cycles;
+
++ pm_runtime_put(&gpu->pdev->dev);
++
+ if (WARN_ON(busy_time > ~0LU))
+ return ~0LU;
+
+--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
++++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+@@ -107,6 +107,13 @@ static void __a6xx_gmu_set_freq(struct a
+ struct msm_gpu *gpu = &adreno_gpu->base;
+ int ret;
+
++ /*
++ * This can get called from devfreq while the hardware is idle. Don't
++ * bring up the power if it isn't already active
++ */
++ if (pm_runtime_get_if_in_use(gmu->dev) == 0)
++ return;
++
+ gmu_write(gmu, REG_A6XX_GMU_DCVS_ACK_OPTION, 0);
+
+ gmu_write(gmu, REG_A6XX_GMU_DCVS_PERF_SETTING,
+@@ -133,6 +140,7 @@ static void __a6xx_gmu_set_freq(struct a
+ * for now leave it at max so that the performance is nominal.
+ */
+ icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
++ pm_runtime_put(gmu->dev);
+ }
+
+ void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
+--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
++++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+@@ -803,6 +803,11 @@ static unsigned long a6xx_gpu_busy(struc
+ struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+ u64 busy_cycles, busy_time;
+
++
++ /* Only read the gpu busy if the hardware is already active */
++ if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
++ return 0;
++
+ busy_cycles = gmu_read64(&a6xx_gpu->gmu,
+ REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L,
+ REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
+@@ -812,6 +817,8 @@ static unsigned long a6xx_gpu_busy(struc
+
+ gpu->devfreq.busy_cycles = busy_cycles;
+
++ pm_runtime_put(a6xx_gpu->gmu.dev);
++
+ if (WARN_ON(busy_time > ~0LU))
+ return ~0LU;
+
--- /dev/null
+From b3583fca5fb654af2cfc1c08259abb9728272538 Mon Sep 17 00:00:00 2001
+From: "Dmitry V. Levin" <ldv@altlinux.org>
+Date: Tue, 2 Jun 2020 21:00:51 +0300
+Subject: s390: fix syscall_get_error for compat processes
+
+From: Dmitry V. Levin <ldv@altlinux.org>
+
+commit b3583fca5fb654af2cfc1c08259abb9728272538 upstream.
+
+If both the tracer and the tracee are compat processes, and gprs[2]
+is assigned a value by __poke_user_compat, then the higher 32 bits
+of gprs[2] are cleared, IS_ERR_VALUE() always returns false, and
+syscall_get_error() always returns 0.
+
+Fix the implementation by sign-extending the value for compat processes
+the same way as x86 implementation does.
+
+The bug was exposed to user space by commit 201766a20e30f ("ptrace: add
+PTRACE_GET_SYSCALL_INFO request") and detected by strace test suite.
+
+This change fixes strace syscall tampering on s390.
+
+Link: https://lkml.kernel.org/r/20200602180051.GA2427@altlinux.org
+Fixes: 753c4dd6a2fa2 ("[S390] ptrace changes")
+Cc: Elvira Khabirova <lineprinter@altlinux.org>
+Cc: stable@vger.kernel.org # v2.6.28+
+Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
+Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
+Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
+index f073292e9fdb..d9d5de0f67ff 100644
+--- a/arch/s390/include/asm/syscall.h
++++ b/arch/s390/include/asm/syscall.h
+@@ -33,7 +33,17 @@ static inline void syscall_rollback(struct task_struct *task,
+ static inline long syscall_get_error(struct task_struct *task,
+ struct pt_regs *regs)
+ {
+- return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0;
++ unsigned long error = regs->gprs[2];
++#ifdef CONFIG_COMPAT
++ if (test_tsk_thread_flag(task, TIF_31BIT)) {
++ /*
++ * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
++ * and will match correctly in comparisons.
++ */
++ error = (long)(int)error;
++ }
++#endif
++ return IS_ERR_VALUE(error) ? error : 0;
+ }
+
+ static inline long syscall_get_return_value(struct task_struct *task,
net-mlx5-dr-fix-freeing-in-dr_create_rc_qp.patch
f2fs-split-f2fs_d_compare-from-f2fs_match_name.patch
f2fs-avoid-utf8_strncasecmp-with-unstable-name.patch
+s390-fix-syscall_get_error-for-compat-processes.patch
+drm-i915-fix-aux-power-domain-toggling-across-typec-mode-resets.patch
+drm-msm-check-for-powered-down-hw-in-the-devfreq-callbacks.patch
+drm-i915-gem-avoid-iterating-an-empty-list.patch
+drm-i915-whitelist-context-local-timestamp-in-the-gen9-cmdparser.patch
+drm-connector-notify-userspace-on-hotplug-after-register-complete.patch
+drm-amd-display-use-kvfree-to-free-coeff-in-build_regamma.patch
+drm-i915-icl-fix-hotplug-interrupt-disabling-after-storm-detection.patch
+drm-i915-gt-move-hsw-gt-workarounds-from-init_clock_gating-to-workarounds.patch
+drm-i915-gt-move-ivb-gt-workarounds-from-init_clock_gating-to-workarounds.patch
+drm-i915-gt-move-snb-gt-workarounds-from-init_clock_gating-to-workarounds.patch
+drm-i915-gt-move-ilk-gt-workarounds-from-init_clock_gating-to-workarounds.patch
+drm-i915-gt-move-vlv-gt-workarounds-from-init_clock_gating-to-workarounds.patch
+drm-i915-gt-move-gen4-gt-workarounds-from-init_clock_gating-to-workarounds.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
