Revert "drm/i915: Expand subslice mask"

This reverts commit 1ac159e23c2c ("drm/i915: Expand subslice mask"),
which kills ICL due to GEM_BUG_ON() sanity checks before CI even gets a
chance to do anything.

The commit exposes an issue in commit 1e40d4aea57b ("drm/i915/cnl:
Implement WaProgramMgsrForCorrectSliceSpecificMmioReads"), which will
also need to be addressed.

There's a proposed fix [1], but considering the seeming uncertainty with
the fix as well as the size of the regressing commit (in this context,
the one that actually brings down ICL), this warrants a revert to get
ICL working, and gives us time to get all of this right without
rushing. Even if this means shooting the messenger.

<3>[    9.426327] intel_sseu_get_subslices:46 GEM_BUG_ON(slice >= sseu->max_slices)
<4>[    9.426355] ------------[ cut here ]------------
<2>[    9.426357] kernel BUG at drivers/gpu/drm/i915/gt/intel_sseu.c:46!
<4>[    9.426371] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
<4>[    9.426377] CPU: 1 PID: 364 Comm: systemd-udevd Not tainted 5.2.0-rc2-CI-CI_DRM_6159+ #1
<4>[    9.426385] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP TLC, BIOS ICLSFWR1.R00.3183.A00.1905020411 05/02/2019
<4>[    9.426444] RIP: 0010:intel_sseu_get_subslices+0x8a/0xe0 [i915]
<4>[    9.426452] Code: d5 76 b7 e0 48 8b 35 9d 24 21 00 49 c7 c0 07 f0 72 a0 b9 2e 00 00 00 48 c7 c2 00 8e 6d a0 48 c7 c7 a5 14 5b a0 e8 36 3c be e0 <0f> 0b 48 c7 c1 80 d5 6f a0 ba 30 00 00 00 48 c7 c6 00 8e 6d a0 48
<4>[    9.426468] RSP: 0018:ffffc9000037b9c8 EFLAGS: 00010282
<4>[    9.426475] RAX: 000000000000000f RBX: 0000000000000000 RCX: 0000000000000000
<4>[    9.426482] RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff88849e346f98
<4>[    9.426490] RBP: ffff88848a200000 R08: 0000000000000004 R09: ffff88849d50b000
<4>[    9.426497] R10: 0000000000000000 R11: ffff88849e346f98 R12: ffff88848a209e78
<4>[    9.426505] R13: 0000000003000000 R14: ffff88848a20b1a8 R15: 0000000000000000
<4>[    9.426513] FS:  00007f73d5ae8680(0000) GS:ffff88849fc80000(0000) knlGS:0000000000000000
<4>[    9.426521] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4>[    9.426527] CR2: 0000561417b01260 CR3: 0000000494764003 CR4: 0000000000760ee0
<4>[    9.426535] PKRU: 55555554
<4>[    9.426538] Call Trace:
<4>[    9.426585]  wa_init_mcr+0xd5/0x110 [i915]
<4>[    9.426597]  ? lock_acquire+0xa6/0x1c0
<4>[    9.426645]  icl_gt_workarounds_init+0x21/0x1a0 [i915]
<4>[    9.426694]  ? i915_driver_load+0xfcf/0x18a0 [i915]
<4>[    9.426739]  gt_init_workarounds+0x14c/0x230 [i915]
<4>[    9.426748]  ? _raw_spin_unlock_irq+0x24/0x50
<4>[    9.426789]  intel_gt_init_workarounds+0x1b/0x30 [i915]
<4>[    9.426835]  i915_driver_load+0xfd7/0x18a0 [i915]
<4>[    9.426843]  ? lock_acquire+0xa6/0x1c0
<4>[    9.426850]  ? __pm_runtime_resume+0x4f/0x80
<4>[    9.426857]  ? _raw_spin_unlock_irqrestore+0x4c/0x60
<4>[    9.426863]  ? _raw_spin_unlock_irqrestore+0x4c/0x60
<4>[    9.426870]  ? lockdep_hardirqs_on+0xe3/0x1b0
<4>[    9.426915]  i915_pci_probe+0x29/0xa0 [i915]
<4>[    9.426923]  pci_device_probe+0x9e/0x120
<4>[    9.426930]  really_probe+0xea/0x3c0
<4>[    9.426936]  driver_probe_device+0x10b/0x120
<4>[    9.426942]  device_driver_attach+0x4a/0x50
<4>[    9.426948]  __driver_attach+0x97/0x130
<4>[    9.426954]  ? device_driver_attach+0x50/0x50
<4>[    9.426960]  bus_for_each_dev+0x74/0xc0
<4>[    9.426966]  bus_add_driver+0x13f/0x210
<4>[    9.426971]  ? 0xffffffffa083b000
<4>[    9.426976]  driver_register+0x56/0xe0
<4>[    9.426982]  ? 0xffffffffa083b000
<4>[    9.426987]  do_one_initcall+0x58/0x300
<4>[    9.426994]  ? do_init_module+0x1d/0x1f6
<4>[    9.427001]  ? rcu_read_lock_sched_held+0x6f/0x80
<4>[    9.427007]  ? kmem_cache_alloc_trace+0x261/0x290
<4>[    9.427014]  do_init_module+0x56/0x1f6
<4>[    9.427020]  load_module+0x24d1/0x2990
<4>[    9.427032]  ? __se_sys_finit_module+0xd3/0xf0
<4>[    9.427037]  __se_sys_finit_module+0xd3/0xf0
<4>[    9.427047]  do_syscall_64+0x55/0x1c0
<4>[    9.427053]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[    9.427059] RIP: 0033:0x7f73d5609839
<4>[    9.427064] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1f f6 2c 00 f7 d8 64 89 01 48
<4>[    9.427082] RSP: 002b:00007ffdf34477b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
<4>[    9.427091] RAX: ffffffffffffffda RBX: 00005559fd5d7b40 RCX: 00007f73d5609839
<4>[    9.427099] RDX: 0000000000000000 RSI: 00007f73d52e8145 RDI: 000000000000000f
<4>[    9.427106] RBP: 00007f73d52e8145 R08: 0000000000000000 R09: 00007ffdf34478d0
<4>[    9.427114] R10: 000000000000000f R11: 0000000000000246 R12: 0000000000000000
<4>[    9.427121] R13: 00005559fd5c90f0 R14: 0000000000020000 R15: 00005559fd5d7b40
<4>[    9.427131] Modules linked in: i915(+) mei_hdcp x86_pkg_temp_thermal coretemp snd_hda_intel crct10dif_pclmul crc32_pclmul snd_hda_codec snd_hwdep e1000e snd_hda_core ghash_clmulni_intel ptp snd_pcm cdc_ether usbnet mii pps_core mei_me mei prime_numbers btusb btrtl btbcm btintel bluetooth ecdh_generic ecc
<4>[    9.427254] ---[ end trace af3eeb543bd66e66 ]---

[1] http://patchwork.freedesktop.org/patch/msgid/20190528200655.11605-1-chris@chris-wilson.co.uk

References: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_6159/fi-icl-u2/pstore0-1517155098_Oops_1.log
References: 1e40d4aea57b ("drm/i915/cnl: Implement WaProgramMgsrForCorrectSliceSpecificMmioReads")
Fixes: 1ac159e23c2c ("drm/i915: Expand subslice mask")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Yunwei Zhang <yunwei.zhang@intel.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190529082150.31526-1-jani.nikula@intel.com

1 files changed, 66 insertions, 56 deletions

diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 3625f777f3a3..97f742530fa1 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -92,9 +92,9 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 		   hweight8(sseu->slice_mask), sseu->slice_mask);
 	drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
+		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   intel_sseu_get_subslices(sseu, s));
+			   sseu->subslice_mask[s]);
 	}
 	drm_printf(p, "EU total: %u\n", sseu->eu_total);
 	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
@@ -117,9 +117,10 @@ void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
 static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
 		       int subslice)
 {
-	int slice_stride = sseu->max_subslices * sseu->eu_stride;
+	int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+	int slice_stride = sseu->max_subslices * subslice_stride;
 
-	return slice * slice_stride + subslice * sseu->eu_stride;
+	return slice * slice_stride + subslice * subslice_stride;
 }
 
 static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
@@ -128,7 +129,7 @@ static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 	u16 eu_mask = 0;
 
-	for (i = 0; i < sseu->eu_stride; i++) {
+	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
 		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
 			(i * BITS_PER_BYTE);
 	}
@@ -141,7 +142,7 @@ static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
 {
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 
-	for (i = 0; i < sseu->eu_stride; i++) {
+	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
 		sseu->eu_mask[offset + i] =
 			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
 	}
@@ -158,9 +159,9 @@ void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
 	}
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
+		drm_printf(p, "slice%d: %u subslice(s) (0x%hhx):\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   intel_sseu_get_subslices(sseu, s));
+			   sseu->subslice_mask[s]);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
@@ -189,10 +190,15 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 	u8 eu_en;
 	int s;
 
-	if (IS_ELKHARTLAKE(dev_priv))
-		intel_sseu_set_info(sseu, 1, 4, 8);
-	else
-		intel_sseu_set_info(sseu, 1, 8, 8);
+	if (IS_ELKHARTLAKE(dev_priv)) {
+		sseu->max_slices = 1;
+		sseu->max_subslices = 4;
+		sseu->max_eus_per_subslice = 8;
+	} else {
+		sseu->max_slices = 1;
+		sseu->max_subslices = 8;
+		sseu->max_eus_per_subslice = 8;
+	}
 
 	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
 	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
@@ -201,15 +207,15 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 
 	for (s = 0; s < sseu->max_slices; s++) {
 		if (s_en & BIT(s)) {
+			int ss_idx = sseu->max_subslices * s;
 			int ss;
 
 			sseu->slice_mask |= BIT(s);
-
-			intel_sseu_set_subslices(sseu, s, ss_en_mask);
-
-			for (ss = 0; ss < sseu->max_subslices; ss++)
-				if (intel_sseu_has_subslice(sseu, s, ss))
+			sseu->subslice_mask[s] = (ss_en >> ss_idx) & ss_en_mask;
+			for (ss = 0; ss < sseu->max_subslices; ss++) {
+				if (sseu->subslice_mask[s] & BIT(ss))
 					sseu_set_eus(sseu, s, ss, eu_en);
+			}
 		}
 	}
 	sseu->eu_per_subslice = hweight8(eu_en);
@@ -229,10 +235,23 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	const int eu_mask = 0xff;
 	u32 subslice_mask, eu_en;
 
-	intel_sseu_set_info(sseu, 6, 4, 8);
-
 	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
 			    GEN10_F2_S_ENA_SHIFT;
+	sseu->max_slices = 6;
+	sseu->max_subslices = 4;
+	sseu->max_eus_per_subslice = 8;
+
+	subslice_mask = (1 << 4) - 1;
+	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
+			   GEN10_F2_SS_DIS_SHIFT);
+
+	/*
+	 * Slice0 can have up to 3 subslices, but there are only 2 in
+	 * slice1/2.
+	 */
+	sseu->subslice_mask[0] = subslice_mask;
+	for (s = 1; s < sseu->max_slices; s++)
+		sseu->subslice_mask[s] = subslice_mask & 0x3;
 
 	/* Slice0 */
 	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
@@ -257,22 +276,14 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
 	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
 
-	subslice_mask = (1 << 4) - 1;
-	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
-			   GEN10_F2_SS_DIS_SHIFT);
-
+	/* Do a second pass where we mark the subslices disabled if all their
+	 * eus are off.
+	 */
 	for (s = 0; s < sseu->max_slices; s++) {
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			if (sseu_get_eus(sseu, s, ss) == 0)
-				subslice_mask &= ~BIT(ss);
+				sseu->subslice_mask[s] &= ~BIT(ss);
 		}
-
-		/*
-		 * Slice0 can have up to 3 subslices, but there are only 2 in
-		 * slice1/2.
-		 */
-		intel_sseu_set_subslices(sseu, s, s == 0 ? subslice_mask :
-							   subslice_mask & 0x3);
 	}
 
 	sseu->eu_total = compute_eu_total(sseu);
@@ -298,12 +309,13 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse;
-	u8 subslice_mask;
 
 	fuse = I915_READ(CHV_FUSE_GT);
 
 	sseu->slice_mask = BIT(0);
-	intel_sseu_set_info(sseu, 1, 2, 8);
+	sseu->max_slices = 1;
+	sseu->max_subslices = 2;
+	sseu->max_eus_per_subslice = 8;
 
 	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
 		u8 disabled_mask =
@@ -312,7 +324,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 			(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
 			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
 
-		subslice_mask |= BIT(0);
+		sseu->subslice_mask[0] |= BIT(0);
 		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
 	}
 
@@ -323,12 +335,10 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 			(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
 			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
 
-		subslice_mask |= BIT(1);
+		sseu->subslice_mask[0] |= BIT(1);
 		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
 	}
 
-	intel_sseu_set_subslices(sseu, 0, subslice_mask);
-
 	sseu->eu_total = compute_eu_total(sseu);
 
 	/*
@@ -361,8 +371,9 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
 
 	/* BXT has a single slice and at most 3 subslices. */
-	intel_sseu_set_info(sseu, IS_GEN9_LP(dev_priv) ? 1 : 3,
-			    IS_GEN9_LP(dev_priv) ? 3 : 4, 8);
+	sseu->max_slices = IS_GEN9_LP(dev_priv) ? 1 : 3;
+	sseu->max_subslices = IS_GEN9_LP(dev_priv) ? 3 : 4;
+	sseu->max_eus_per_subslice = 8;
 
 	/*
 	 * The subslice disable field is global, i.e. it applies
@@ -381,14 +392,14 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 			/* skip disabled slice */
 			continue;
 
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		sseu->subslice_mask[s] = subslice_mask;
 
 		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			int eu_per_ss;
 			u8 eu_disabled_mask;
 
-			if (!intel_sseu_has_subslice(sseu, s, ss))
+			if (!(sseu->subslice_mask[s] & BIT(ss)))
 				/* skip disabled subslice */
 				continue;
 
@@ -461,7 +472,9 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 
 	fuse2 = I915_READ(GEN8_FUSE2);
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
-	intel_sseu_set_info(sseu, 3, 3, 8);
+	sseu->max_slices = 3;
+	sseu->max_subslices = 3;
+	sseu->max_eus_per_subslice = 8;
 
 	/*
 	 * The subslice disable field is global, i.e. it applies
@@ -488,19 +501,18 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 			/* skip disabled slice */
 			continue;
 
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
+		sseu->subslice_mask[s] = subslice_mask;
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u8 eu_disabled_mask;
 			u32 n_disabled;
 
-			if (!intel_sseu_has_subslice(sseu, s, ss))
+			if (!(sseu->subslice_mask[s] & BIT(ss)))
 				/* skip disabled subslice */
 				continue;
 
 			eu_disabled_mask =
-				eu_disable[s] >>
-					(ss * sseu->max_eus_per_subslice);
+				eu_disable[s] >> (ss * sseu->max_eus_per_subslice);
 
 			sseu_set_eus(sseu, s, ss, ~eu_disabled_mask);
 
@@ -540,7 +552,6 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse1;
 	int s, ss;
-	u32 subslice_mask;
 
 	/*
 	 * There isn't a register to tell us how many slices/subslices. We
@@ -552,18 +563,22 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		/* fall through */
 	case 1:
 		sseu->slice_mask = BIT(0);
-		subslice_mask = BIT(0);
+		sseu->subslice_mask[0] = BIT(0);
 		break;
 	case 2:
 		sseu->slice_mask = BIT(0);
-		subslice_mask = BIT(0) | BIT(1);
+		sseu->subslice_mask[0] = BIT(0) | BIT(1);
 		break;
 	case 3:
 		sseu->slice_mask = BIT(0) | BIT(1);
-		subslice_mask = BIT(0) | BIT(1);
+		sseu->subslice_mask[0] = BIT(0) | BIT(1);
+		sseu->subslice_mask[1] = BIT(0) | BIT(1);
 		break;
 	}
 
+	sseu->max_slices = hweight8(sseu->slice_mask);
+	sseu->max_subslices = hweight8(sseu->subslice_mask[0]);
+
 	fuse1 = I915_READ(HSW_PAVP_FUSE1);
 	switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) {
 	default:
@@ -580,14 +595,9 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		sseu->eu_per_subslice = 6;
 		break;
 	}
-
-	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
-			    hweight8(subslice_mask),
-			    sseu->eu_per_subslice);
+	sseu->max_eus_per_subslice = sseu->eu_per_subslice;
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		intel_sseu_set_subslices(sseu, s, subslice_mask);
-
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			sseu_set_eus(sseu, s, ss,
 				     (1UL << sseu->eu_per_subslice) - 1);