PDS Kernel Configuration

Imported from https://gitlab.freedesktop.org/agd5f/linux/-/tree/amd-staging-drm-next
Expected for 6.7. Tested on Navi32.

customization.cfg

@@ -3,7 +3,7 @@
 # Linux distribution you are using, options are "Arch", "Ubuntu", "Debian", "Fedora", "Suse", "Gentoo", "Generic".
 # It is automatically set to "Arch" when using PKGBUILD.
 # If left empty, the script will prompt
-_distro=""
+_distro="Arch"
 
 # Kernel Version - x.x format without the subversion (will always grab latest available subversion) is recommended
 # you can also set a specific kernel version, e.g. "6.0-rc4" or "5.10.51",
@@ -46,7 +46,7 @@ CUSTOM_GCC_PATH=""
 CUSTOM_LLVM_PATH=""
 
 # Set to true to bypass makepkg.conf and use all available threads for compilation. False will respect your makepkg.conf options.
-_force_all_threads="true"
+_force_all_threads="false"
 
 # Set to true to prevent ccache from being used and set CONFIG_GCC_PLUGINS=y (which needs to be disabled for ccache to work properly)
 _noccache="false"
@@ -66,10 +66,10 @@ _modprobeddb="false"
 _modprobeddb_db_path=~/.config/modprobed.db
 
 # Set to "1" to call make menuconfig, "2" to call make nconfig, "3" to call make xconfig, before building the kernel. Set to false to disable and skip the prompt.
-_menunconfig=""
+_menunconfig="false"
 
 # Set to true to generate a kernel config fragment from your changes in menuconfig/nconfig. Set to false to disable and skip the prompt.
-_diffconfig=""
+_diffconfig="false"
 
 # Set to the file name where the generated config fragment should be written to. Only used if _diffconfig is active.
 _diffconfig_name=""
@@ -104,11 +104,11 @@ _STRIP="true"
 
 # CPU scheduler - Options are "pds", "bmq", "cacule", "tt", "bore", "bore-eevdf", "eevdf" or "cfs" (kernel's default)
 # "upds" (TkG's Undead PDS) and "muqss" are also available on legacy kernel revisions
-_cpusched=""
+_cpusched="pds"
 
 # Compiler to use - Options are "gcc" or "llvm".
 # For advanced users.
-_compiler=""
+_compiler="gcc"
 
 # Force the use of the LLVM Integrated Assembler whether using LLVM, LTO or not.
 # Set to "1" to enable.
@@ -138,7 +138,7 @@ _preempt_rt_force=""
 # For BMQ:           0: No yield.
 #                    1: Deboost and requeue task. (Default)
 #                    2: Set rq skip task.
-_sched_yield_type=""
+_sched_yield_type="0"
 
 # Round Robin interval is the longest duration two tasks with the same nice level will be delayed for. When CPU time is requested by a task, it receives a time slice equal
 # to the rr_interval in addition to a virtual deadline. When using yield_type 2, a low value can help offset the disadvantages of rescheduling a process that has yielded.
@@ -146,7 +146,7 @@ _sched_yield_type=""
 # PDS default: 4ms"
 # BMQ default: 2ms"
 # Set to "1" for 2ms, "2" for 4ms, "3" for 6ms, "4" for 8ms, or "default" to keep the chosen scheduler defaults.
-_rr_interval=""
+_rr_interval="default"
 
 # Set to "true" to disable FUNCTION_TRACER/GRAPH_TRACER, lowering overhead but limiting debugging and analyzing of kernel functions - Kernel default is "false"
 _ftracedisable="false"
@@ -161,10 +161,10 @@ _misc_adds="true"
 # Full tickless can give higher performances in case you use isolation of CPUs for tasks
 # and it works only when using the nohz_full kernel parameter, otherwise behaves like idle.
 # Just tickless idle perform better for most platforms.
-_tickless=""
+_tickless="2"
 
 # Set to "true" to use ACS override patch - https://wiki.archlinux.org/index.php/PCI_passthrough_via_OVMF#Bypassing_the_IOMMU_groups_.28ACS_override_patch.29 - Kernel default is "false"
-_acs_override=""
+_acs_override="false"
 
 # Set to "true" to add Bcache filesystem support. You'll have to install bcachefs-tools-git from AUR for utilities - https://bcachefs.org/ - If in doubt, set to "false"
 # This can be buggy and isn't recommended on a production machine, also enabling this option will not allow you to enable MGLRU.
@@ -175,7 +175,7 @@ _bcachefs="false"
 _winesync="false"
 
 # Set to "true" to enable Binder modules to use Waydroid Android containers
-_waydroid=""
+_waydroid="false"
 
 # Various patches and tweaks from Zen/Liquorix, Xanmod and the community - Default is "true"
 _glitched_base="true"
@@ -185,7 +185,7 @@ _glitched_base="true"
 _zenify="true"
 
 # compiler optimization level - 1. Optimize for performance (-O2); 2. Optimize harder (-O3); 3. Optimize for size (-Os) - Kernel default is "1"
-_compileroptlevel="1"
+_compileroptlevel="2"
 
 # CPU compiler optimizations - Defaults to prompt at kernel config if left empty
 # AMD CPUs : "k8" "k8sse3" "k10" "barcelona" "bobcat" "jaguar" "bulldozer" "piledriver" "steamroller" "excavator" "zen" "zen2" "zen3" "zen4" (zen3 opt support depends on GCC11) (zen4 opt support depends on GCC13)
@@ -199,7 +199,7 @@ _compileroptlevel="1"
 # - "generic_v2" (depends on GCC11 - to share the package between machines with different CPU µarch supporting at least x86-64-v2
 # - "generic_v3" (depends on GCC11 - to share the package between machines with different CPU µarch supporting at least x86-64-v3
 # - "generic_v4" (depends on GCC11 - to share the package between machines with different CPU µarch supporting at least x86-64-v4
-_processor_opt=""
+_processor_opt="skylake"
 
 # CacULE only - Enable Response Driven Balancer, an experimental load balancer for CacULE
 _cacule_rdb="false"
@@ -212,13 +212,13 @@ _cacule_rdb_interval="19"
 _tt_high_hz="false"
 
 # MuQSS and PDS only - SMT (Hyperthreading) aware nice priority and policy support (SMT_NICE) - Kernel default is "true" - You can disable this on non-SMT/HT CPUs for lower overhead
-_smt_nice=""
+_smt_nice="true"
 
 # Trust the CPU manufacturer to initialize Linux's CRNG (RANDOM_TRUST_CPU) - Kernel default is "false"
 _random_trust_cpu="true"
 
 # Timer frequency - "100" "250" "300" "500" "750" "1000" ("2000" is available for cacule cpusched only) - More options available in kernel config prompt when left empty depending on selected cpusched with the default option pointed with a ">" (2000 for cacule, 100 for muqss and 1000 for other cpu schedulers)
-_timer_freq=""
+_timer_freq="1000"
 
 # Default CPU governor - "performance", "ondemand", "schedutil" or leave empty for default (schedutil)
 _default_cpu_gov="ondemand"
@@ -234,7 +234,7 @@ _aggressive_ondemand="true"
 _tcp_cong_alg=""
 
 # You can pass a default set of kernel command line options here - example: "intel_pstate=passive nowatchdog amdgpu.ppfeaturemask=0xfffd7fff mitigations=off"
-_custom_commandline="intel_pstate=passive split_lock_detect=off"
+_custom_commandline=""
 
 # Selection of Clearlinux patches
 _clear_patches="true"

linux-tkg-config/6.6/config.x86_64

@@ -1,6 +1,6 @@
 #
 # Automatically generated file; DO NOT EDIT.
-# Linux/x86 6.6.0-rc1 Kernel Configuration
+# Linux/x86 6.6.0-rc3 Kernel Configuration
 #
 CONFIG_CC_VERSION_TEXT="gcc (GCC) 13.2.1 20230801"
 CONFIG_CC_IS_GCC=y
@@ -4701,7 +4701,6 @@ CONFIG_I2C_MUX_REG=m
 CONFIG_I2C_MUX_MLXCPLD=m
 # end of Multiplexer I2C Chip support
 
-CONFIG_I2C_ATR=m
 CONFIG_I2C_HELPER_AUTO=y
 CONFIG_I2C_SMBUS=m
 CONFIG_I2C_ALGOBIT=m
@@ -10276,8 +10275,8 @@ CONFIG_XFS_DRAIN_INTENTS=y
 CONFIG_XFS_ONLINE_SCRUB=y
 CONFIG_XFS_ONLINE_SCRUB_STATS=y
 CONFIG_XFS_ONLINE_REPAIR=y
-# CONFIG_XFS_WARN is not set
-# CONFIG_XFS_DEBUG is not set
+CONFIG_XFS_DEBUG=y
+CONFIG_XFS_ASSERT_FATAL=y
 CONFIG_GFS2_FS=m
 CONFIG_GFS2_FS_LOCKING_DLM=y
 CONFIG_OCFS2_FS=m

linux-tkg-config/prepare

@@ -257,7 +257,7 @@ _set_cpu_scheduler() {
     ["upds"]="Undead PDS (TkG)"
     ["cacule"]="CacULE"
     ["tt"]="TT (TaskType)"
-    ["bore"]="BORE (Burst-Oriented Response Enhancer - CFS variant) CPU Scheduler"
+    ["bore"]="BORE (Burst-Oriented Response Enhancer) CPU Scheduler"
     ["bore-eevdf"]="BORE (Burst-Oriented Response Enhancer - EEVDF variant) CPU Scheduler"
     ["eevdf"]="Earliest Eligible Virtual Deadline First (EEVDF) scheduler"
   )
@@ -302,7 +302,7 @@ _set_cpu_scheduler() {
   elif [ "$_kver" = "605" ]; then
     _avail_cpu_scheds=("cfs" "eevdf" "pds" "bmq" "tt" "bore" "bore-eevdf")
   elif [ "$_kver" = "606" ]; then
-    _avail_cpu_scheds=("eevdf")
+    _avail_cpu_scheds=("eevdf" "bore")
   else
     _avail_cpu_scheds=("cfs")
   fi
@@ -859,11 +859,7 @@ _tkg_srcprep() {
 
     if [ "${_cpusched}" = "bore-eevdf" ]; then
       _msg="Applying BORE-EEVDF patch"
-      if [ "$_kver" != "605" ]; then
-        curl "https://raw.githubusercontent.com/CachyOS/kernel-patches/master/${_basekernel}/sched/0001-bore-eevdf.patch" > "$srcdir"/0001-bore-eevdf.patch
-      else
-        curl "https://raw.githubusercontent.com/sirlucjan/kernel-patches/master/${_basekernel}/bore-eevdf-patches-v2-sep/0016-linux6.5-bore3.1.3.patch" > "$srcdir"/0001-bore-eevdf.patch
-      fi
+      curl "https://raw.githubusercontent.com/CachyOS/kernel-patches/master/${_basekernel}/sched/0001-bore-eevdf.patch" > "$srcdir"/0001-bore-eevdf.patch
       tkgpatch="$srcdir/0001-bore-eevdf.patch" && _tkg_patcher
     fi
   fi

linux-tkg-patches/6.5/0003-eevdf.patch

@@ -2896,514 +2896,3 @@ index 03db55504..f68919800 100644
 --
 2.42.0
 
-
-From edbc7fe6658db891c80f244dc397f4e0247f6f3d Mon Sep 17 00:00:00 2001
-From: Peter Zijlstra <peterz@infradead.org>
-Date: Fri, 15 Sep 2023 00:48:55 +0200
-Subject: [PATCH 13/15] sched/eevdf: Also update slice on placement
-
-Tasks that never consume their full slice would not update their slice value.
-This means that tasks that are spawned before the sysctl scaling keep their
-original (UP) slice length.
-
-Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy")
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
----
- kernel/sched/fair.c | 6 ++++--
- 1 file changed, 4 insertions(+), 2 deletions(-)
-
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index 1cdc95725..efbcdc69c 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -4918,10 +4918,12 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
- static void
- place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
- {
--	u64 vslice = calc_delta_fair(se->slice, se);
--	u64 vruntime = avg_vruntime(cfs_rq);
-+	u64 vslice, vruntime = avg_vruntime(cfs_rq);
- 	s64 lag = 0;
-
-+	se->slice = sysctl_sched_base_slice;
-+	vslice = calc_delta_fair(se->slice, se);
-+
- 	/*
- 	 * Due to how V is constructed as the weighted average of entities,
- 	 * adding tasks with positive lag, or removing tasks with negative lag
---
-2.42.0
-
-
-From 0f1fadfb03ba9ba181e4631de8cd97ba765fae1d Mon Sep 17 00:00:00 2001
-From: Peter Zijlstra <peterz@infradead.org>
-Date: Fri, 15 Sep 2023 00:48:45 +0200
-Subject: [PATCH 14/15] sched/eevdf: Delay dequeue
-
-For tasks that have negative-lag (have received 'excess' service), delay the
-dequeue and keep them in the runnable tree until they're elegible again. Or
-rather, keep them until they're selected again, since finding their elegibility
-crossover point is expensive.
-
-The effect is a bit like sleeper bonus, the tasks keep contending for service
-until either they get a wakeup or until they're selected again and are really
-dequeued.
-
-This means that any actual dequeue happens with positive lag (serviced owed)
-and are more readily ran when wakeup.
-
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
----
- include/linux/sched.h   |  1 +
- kernel/sched/core.c     | 41 +++++++++++++++++++++++++++++++++++------
- kernel/sched/fair.c     |  9 +++++++++
- kernel/sched/features.h |  1 +
- kernel/sched/sched.h    |  3 ++-
- 5 files changed, 48 insertions(+), 7 deletions(-)
-
-diff --git a/include/linux/sched.h b/include/linux/sched.h
-index 35331c35f..d40d98313 100644
---- a/include/linux/sched.h
-+++ b/include/linux/sched.h
-@@ -891,6 +891,7 @@ struct task_struct {
- 	unsigned			sched_reset_on_fork:1;
- 	unsigned			sched_contributes_to_load:1;
- 	unsigned			sched_migrated:1;
-+	unsigned			sched_delayed:1;
-
- 	/* Force alignment to the next boundary: */
- 	unsigned			:0;
-diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index 8116ef56d..cfb0ffa69 100644
---- a/kernel/sched/core.c
-+++ b/kernel/sched/core.c
-@@ -6551,6 +6551,16 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
- # define SM_MASK_PREEMPT	SM_PREEMPT
- #endif
-
-+static void __deschedule_task(struct rq *rq, struct task_struct *p)
-+{
-+	deactivate_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-+
-+	if (p->in_iowait) {
-+		atomic_inc(&rq->nr_iowait);
-+		delayacct_blkio_start();
-+	}
-+}
-+
- /*
-  * __schedule() is the main scheduler function.
-  *
-@@ -6663,17 +6673,36 @@ static void __sched notrace __schedule(unsigned int sched_mode)
- 			 *
- 			 * After this, schedule() must not care about p->state any more.
- 			 */
--			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-+			if (!(sched_feat(DELAY_DEQUEUE) &&
-+			      prev->sched_class->eligible_task &&
-+			      !prev->sched_class->eligible_task(rq, prev)))
-+				__deschedule_task(rq, prev);
-+			else
-+				prev->sched_delayed = 1;
-+		}
-+		switch_count = &prev->nvcsw;
-+	}
-+
-+	for (struct task_struct *tmp = prev;;) {
-
--			if (prev->in_iowait) {
--				atomic_inc(&rq->nr_iowait);
--				delayacct_blkio_start();
-+		next = pick_next_task(rq, tmp, &rf);
-+		if (unlikely(tmp != prev))
-+			finish_task(tmp);
-+
-+		if (sched_feat(DELAY_DEQUEUE) && unlikely(next->sched_delayed)) {
-+			next->sched_delayed = 0;
-+			if (READ_ONCE(next->__state)) {
-+				prepare_task(next);
-+				smp_wmb();
-+				__deschedule_task(rq, next);
-+				tmp = next;
-+				continue;
- 			}
- 		}
--		switch_count = &prev->nvcsw;
-+
-+		break;
- 	}
-
--	next = pick_next_task(rq, prev, &rf);
- 	clear_tsk_need_resched(prev);
- 	clear_preempt_need_resched();
- #ifdef CONFIG_SCHED_DEBUG
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index efbcdc69c..729507e40 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -8174,6 +8174,14 @@ static struct task_struct *__pick_next_task_fair(struct rq *rq)
- 	return pick_next_task_fair(rq, NULL, NULL);
- }
-
-+static bool eligible_task_fair(struct rq *rq, struct task_struct *p)
-+{
-+	struct sched_entity *se = &p->se;
-+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-+
-+	return entity_eligible(cfs_rq, se);
-+}
-+
- /*
-  * Account for a descheduled task:
-  */
-@@ -12628,6 +12636,7 @@ DEFINE_SCHED_CLASS(fair) = {
-
- 	.check_preempt_curr	= check_preempt_wakeup,
-
-+	.eligible_task		= eligible_task_fair,
- 	.pick_next_task		= __pick_next_task_fair,
- 	.put_prev_task		= put_prev_task_fair,
- 	.set_next_task          = set_next_task_fair,
-diff --git a/kernel/sched/features.h b/kernel/sched/features.h
-index 546d212ef..5ae5a6f92 100644
---- a/kernel/sched/features.h
-+++ b/kernel/sched/features.h
-@@ -7,6 +7,7 @@
- SCHED_FEAT(PLACE_LAG, true)
- SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
- SCHED_FEAT(RUN_TO_PARITY, true)
-+SCHED_FEAT(DELAY_DEQUEUE, true)
-
- /*
-  * Prefer to schedule the task we woke last (assuming it failed
-diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
-index 576d371c8..c18ab7c2f 100644
---- a/kernel/sched/sched.h
-+++ b/kernel/sched/sched.h
-@@ -2219,6 +2219,7 @@ struct sched_class {
-
- 	void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
-
-+	bool (*eligible_task)(struct rq *rq, struct task_struct *p);
- 	struct task_struct *(*pick_next_task)(struct rq *rq);
-
- 	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
-@@ -2272,7 +2273,7 @@ struct sched_class {
-
- static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
- {
--	WARN_ON_ONCE(rq->curr != prev);
-+//	WARN_ON_ONCE(rq->curr != prev);
- 	prev->sched_class->put_prev_task(rq, prev);
- }
-
---
-2.42.0
-
-
-From 4aba3e1c3bbe4a36d4b9e405be8a66d7c10d6495 Mon Sep 17 00:00:00 2001
-From: Peter Zijlstra <peterz@infradead.org>
-Date: Mon, 22 May 2023 13:46:30 +0200
-Subject: [PATCH 15/15] sched/eevdf: Use sched_attr::sched_runtime to set
- request/slice suggestion
-
-Allow applications to directly set a suggested request/slice length using
-sched_attr::sched_runtime.
-
-The implementation clamps the value to: 0.1[ms] <= slice <= 100[ms]
-which is 1/10 the size of HZ=1000 and 10 times the size of HZ=100.
-
-Applications should strive to use their periodic runtime at a high
-confidence interval (95%+) as the target slice. Using a smaller slice
-will introduce undue preemptions, while using a larger value will
-increase latency.
-
-For all the following examples assume a scheduling quantum of 8, and for
-consistency all examples have W=4:
-
-  {A,B,C,D}(w=1,r=8):
-
-  ABCD...
-  +---+---+---+---
-
-  t=0, V=1.5				t=1, V=3.5
-  A  |------<				A          |------<
-  B   |------<				B   |------<
-  C    |------<				C    |------<
-  D     |------<			D     |------<
-  ---+*------+-------+---		---+--*----+-------+---
-
-  t=2, V=5.5				t=3, V=7.5
-  A          |------<			A          |------<
-  B           |------<			B           |------<
-  C    |------<				C            |------<
-  D     |------<			D     |------<
-  ---+----*--+-------+---		---+------*+-------+---
-
-Note: 4 identical tasks in FIFO order
-
-~~~
-
-  {A,B}(w=1,r=16) C(w=2,r=16)
-
-  AACCBBCC...
-  +---+---+---+---
-
-  t=0, V=1.25				t=2, V=5.25
-  A  |--------------<                   A                  |--------------<
-  B   |--------------<                  B   |--------------<
-  C    |------<                         C    |------<
-  ---+*------+-------+---               ---+----*--+-------+---
-
-  t=4, V=8.25				t=6, V=12.25
-  A                  |--------------<   A                  |--------------<
-  B   |--------------<                  B                   |--------------<
-  C            |------<                 C            |------<
-  ---+-------*-------+---               ---+-------+---*---+---
-
-Note: 1 heavy task -- because q=8, double r such that the deadline of the w=2
-      task doesn't go below q.
-
-Note: observe the full schedule becomes: W*max(r_i/w_i) = 4*2q = 8q in length.
-
-Note: the period of the heavy task is half the full period at:
-      W*(r_i/w_i) = 4*(2q/2) = 4q
-
-~~~
-
-  {A,C,D}(w=1,r=16) B(w=1,r=8):
-
-  BAACCBDD...
-  +---+---+---+---
-
-  t=0, V=1.5				t=1, V=3.5
-  A  |--------------<			A  |---------------<
-  B   |------<				B           |------<
-  C    |--------------<			C    |--------------<
-  D     |--------------<		D     |--------------<
-  ---+*------+-------+---		---+--*----+-------+---
-
-  t=3, V=7.5				t=5, V=11.5
-  A                  |---------------<  A                  |---------------<
-  B           |------<                  B           |------<
-  C    |--------------<                 C                    |--------------<
-  D     |--------------<                D     |--------------<
-  ---+------*+-------+---               ---+-------+--*----+---
-
-  t=6, V=13.5
-  A                  |---------------<
-  B                   |------<
-  C                    |--------------<
-  D     |--------------<
-  ---+-------+----*--+---
-
-Note: 1 short task -- again double r so that the deadline of the short task
-      won't be below q. Made B short because its not the leftmost task, but is
-      eligible with the 0,1,2,3 spread.
-
-Note: like with the heavy task, the period of the short task observes:
-      W*(r_i/w_i) = 4*(1q/1) = 4q
-
-~~~
-
-  A(w=1,r=16) B(w=1,r=8) C(w=2,r=16)
-
-  BCCAABCC...
-  +---+---+---+---
-
-  t=0, V=1.25				t=1, V=3.25
-  A  |--------------<                   A  |--------------<
-  B   |------<                          B           |------<
-  C    |------<                         C    |------<
-  ---+*------+-------+---               ---+--*----+-------+---
-
-  t=3, V=7.25				t=5, V=11.25
-  A  |--------------<                   A                  |--------------<
-  B           |------<                  B           |------<
-  C            |------<                 C            |------<
-  ---+------*+-------+---               ---+-------+--*----+---
-
-  t=6, V=13.25
-  A                  |--------------<
-  B                   |------<
-  C            |------<
-  ---+-------+----*--+---
-
-Note: 1 heavy and 1 short task -- combine them all.
-
-Note: both the short and heavy task end up with a period of 4q
-
-~~~
-
-  A(w=1,r=16) B(w=2,r=16) C(w=1,r=8)
-
-  BBCAABBC...
-  +---+---+---+---
-
-  t=0, V=1				t=2, V=5
-  A  |--------------<                   A  |--------------<
-  B   |------<                          B           |------<
-  C    |------<                         C    |------<
-  ---+*------+-------+---               ---+----*--+-------+---
-
-  t=3, V=7				t=5, V=11
-  A  |--------------<                   A                  |--------------<
-  B           |------<                  B           |------<
-  C            |------<                 C            |------<
-  ---+------*+-------+---               ---+-------+--*----+---
-
-  t=7, V=15
-  A                  |--------------<
-  B                   |------<
-  C            |------<
-  ---+-------+------*+---
-
-Note: as before but permuted
-
-~~~
-
-From all this it can be deduced that, for the steady state:
-
- - the total period (P) of a schedule is:	W*max(r_i/w_i)
- - the average period of a task is:		W*(r_i/w_i)
- - each task obtains the fair share:		w_i/W of each full period P
-
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
----
- include/linux/sched.h |  3 +++
- kernel/sched/core.c   | 33 ++++++++++++++++++++++++++-------
- kernel/sched/fair.c   |  6 ++++--
- 3 files changed, 33 insertions(+), 9 deletions(-)
-
-diff --git a/include/linux/sched.h b/include/linux/sched.h
-index d40d98313..93c03b162 100644
---- a/include/linux/sched.h
-+++ b/include/linux/sched.h
-@@ -555,6 +555,9 @@ struct sched_entity {
- 	struct list_head		group_node;
- 	unsigned int			on_rq;
-
-+	unsigned int			custom_slice : 1;
-+					/* 31 bits hole */
-+
- 	u64				exec_start;
- 	u64				sum_exec_runtime;
- 	u64				prev_sum_exec_runtime;
-diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index cfb0ffa69..1ae5a8272 100644
---- a/kernel/sched/core.c
-+++ b/kernel/sched/core.c
-@@ -4502,7 +4502,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
- 	p->se.nr_migrations		= 0;
- 	p->se.vruntime			= 0;
- 	p->se.vlag			= 0;
--	p->se.slice			= sysctl_sched_base_slice;
- 	INIT_LIST_HEAD(&p->se.group_node);
-
- #ifdef CONFIG_FAIR_GROUP_SCHED
-@@ -4756,6 +4755,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
-
- 		p->prio = p->normal_prio = p->static_prio;
- 		set_load_weight(p, false);
-+		p->se.custom_slice = 0;
-+		p->se.slice = sysctl_sched_base_slice;
-
- 		/*
- 		 * We don't need the reset flag anymore after the fork. It has
-@@ -7556,10 +7557,20 @@ static void __setscheduler_params(struct task_struct *p,
-
- 	p->policy = policy;
-
--	if (dl_policy(policy))
-+	if (dl_policy(policy)) {
- 		__setparam_dl(p, attr);
--	else if (fair_policy(policy))
-+	} else if (fair_policy(policy)) {
- 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
-+		if (attr->sched_runtime) {
-+			p->se.custom_slice = 1;
-+			p->se.slice = clamp_t(u64, attr->sched_runtime,
-+					      NSEC_PER_MSEC/10,   /* HZ=1000 * 10 */
-+					      NSEC_PER_MSEC*100); /* HZ=100  / 10 */
-+		} else {
-+			p->se.custom_slice = 0;
-+			p->se.slice = sysctl_sched_base_slice;
-+		}
-+	}
-
- 	/*
- 	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
-@@ -7744,7 +7755,9 @@ static int __sched_setscheduler(struct task_struct *p,
- 	 * but store a possible modification of reset_on_fork.
- 	 */
- 	if (unlikely(policy == p->policy)) {
--		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
-+		if (fair_policy(policy) &&
-+		    (attr->sched_nice != task_nice(p) ||
-+		     (attr->sched_runtime && attr->sched_runtime != p->se.slice)))
- 			goto change;
- 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
- 			goto change;
-@@ -7890,6 +7903,9 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
- 		.sched_nice	= PRIO_TO_NICE(p->static_prio),
- 	};
-
-+	if (p->se.custom_slice)
-+		attr.sched_runtime = p->se.slice;
-+
- 	/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
- 	if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
- 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-@@ -8066,12 +8082,14 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
-
- static void get_params(struct task_struct *p, struct sched_attr *attr)
- {
--	if (task_has_dl_policy(p))
-+	if (task_has_dl_policy(p)) {
- 		__getparam_dl(p, attr);
--	else if (task_has_rt_policy(p))
-+	} else if (task_has_rt_policy(p)) {
- 		attr->sched_priority = p->rt_priority;
--	else
-+	} else {
- 		attr->sched_nice = task_nice(p);
-+		attr->sched_runtime = p->se.slice;
-+	}
- }
-
- /**
-@@ -10090,6 +10108,7 @@ void __init sched_init(void)
- 	}
-
- 	set_load_weight(&init_task, false);
-+	init_task.se.slice = sysctl_sched_base_slice,
-
- 	/*
- 	 * The boot idle thread does lazy MMU switching as well:
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index 729507e40..51e19a1fb 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -973,7 +973,8 @@ static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
- 	 * nice) while the request time r_i is determined by
- 	 * sysctl_sched_base_slice.
- 	 */
--	se->slice = sysctl_sched_base_slice;
-+	if (!se->custom_slice)
-+		se->slice = sysctl_sched_base_slice;
-
- 	/*
- 	 * EEVDF: vd_i = ve_i + r_i / w_i
-@@ -4921,7 +4922,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
- 	u64 vslice, vruntime = avg_vruntime(cfs_rq);
- 	s64 lag = 0;
-
--	se->slice = sysctl_sched_base_slice;
-+	if (!se->custom_slice)
-+		se->slice = sysctl_sched_base_slice;
- 	vslice = calc_delta_fair(se->slice, se);
-
- 	/*
---
-2.42.0
-

linux-tkg-patches/6.6/0012-misc-additions.patch

@@ -64,3 +64,760 @@ index 2c7171e0b0010..85de313ddec29 100644
  	select CPU_FREQ_GOV_PERFORMANCE
  	help
 
+From 7695eb71d0872ed9633daf0ca779da3344b87dec Mon Sep 17 00:00:00 2001
+From: Evan Quan <evan.quan@amd.com>
+Date: Mon, 21 Aug 2023 14:15:13 +0800
+Subject: [PATCH] drm/amd/pm: correct SMU13 gfx voltage related OD settings
+
+The voltage offset setting will be applied to the whole v/f curve line
+instead of per anchor point base.
+
+Signed-off-by: Evan Quan <evan.quan@amd.com>
+Acked-by: Alex Deucher <alexander.deucher@amd.com>
+---
+ drivers/gpu/drm/amd/pm/amdgpu_pm.c            | 45 +++++++------------
+ .../drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c  | 31 ++++++-------
+ .../drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c  | 31 ++++++-------
+ 3 files changed, 43 insertions(+), 64 deletions(-)
+
+diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+index 1da7ece4c627..06aa5c18b40f 100644
+--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
++++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+@@ -643,18 +643,14 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
+  *   They can be used to calibrate the sclk voltage curve. This is
+  *   available for Vega20 and NV1X.
+  *
+- * - voltage offset for the six anchor points of the v/f curve labeled
+- *   OD_VDDC_CURVE. They can be used to calibrate the v/f curve. This
+- *   is only availabe for some SMU13 ASICs.
+- *
+  * - voltage offset(in mV) applied on target voltage calculation.
+- *   This is available for Sienna Cichlid, Navy Flounder and Dimgrey
+- *   Cavefish. For these ASICs, the target voltage calculation can be
+- *   illustrated by "voltage = voltage calculated from v/f curve +
+- *   overdrive vddgfx offset"
++ *   This is available for Sienna Cichlid, Navy Flounder, Dimgrey
++ *   Cavefish and some later SMU13 ASICs. For these ASICs, the target
++ *   voltage calculation can be illustrated by "voltage = voltage
++ *   calculated from v/f curve + overdrive vddgfx offset"
+  *
+- * - a list of valid ranges for sclk, mclk, and voltage curve points
+- *   labeled OD_RANGE
++ * - a list of valid ranges for sclk, mclk, voltage curve points
++ *   or voltage offset labeled OD_RANGE
+  *
+  * < For APUs >
+  *
+@@ -686,24 +682,17 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
+  *   E.g., "p 2 0 800" would set the minimum core clock on core
+  *   2 to 800Mhz.
+  *
+- *   For sclk voltage curve,
+- *     - For NV1X, enter the new values by writing a string that
+- *       contains "vc point clock voltage" to the file. The points
+- *       are indexed by 0, 1 and 2. E.g., "vc 0 300 600" will update
+- *       point1 with clock set as 300Mhz and voltage as 600mV. "vc 2
+- *       1000 1000" will update point3 with clock set as 1000Mhz and
+- *       voltage 1000mV.
+- *     - For SMU13 ASICs, enter the new values by writing a string that
+- *       contains "vc anchor_point_index voltage_offset" to the file.
+- *       There are total six anchor points defined on the v/f curve with
+- *       index as 0 - 5.
+- *       - "vc 0 10" will update the voltage offset for point1 as 10mv.
+- *       - "vc 5 -10" will update the voltage offset for point6 as -10mv.
+- *
+- *   To update the voltage offset applied for gfxclk/voltage calculation,
+- *   enter the new value by writing a string that contains "vo offset".
+- *   This is supported by Sienna Cichlid, Navy Flounder and Dimgrey Cavefish.
+- *   And the offset can be a positive or negative value.
++ *   For sclk voltage curve supported by Vega20 and NV1X, enter the new
++ *   values by writing a string that contains "vc point clock voltage"
++ *   to the file. The points are indexed by 0, 1 and 2. E.g., "vc 0 300
++ *   600" will update point1 with clock set as 300Mhz and voltage as 600mV.
++ *   "vc 2 1000 1000" will update point3 with clock set as 1000Mhz and
++ *   voltage 1000mV.
++ *
++ *   For voltage offset supported by Sienna Cichlid, Navy Flounder, Dimgrey
++ *   Cavefish and some later SMU13 ASICs, enter the new value by writing a
++ *   string that contains "vo offset". E.g., "vo -10" will update the extra
++ *   voltage offset applied to the whole v/f curve line as -10mv.
+  *
+  * - When you have edited all of the states as needed, write "c" (commit)
+  *   to the file to commit your changes
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+index 3903a47669e4..bd0d5f027cac 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+@@ -1304,16 +1304,14 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu,
+ 					od_table->OverDriveTable.UclkFmax);
+ 		break;
+
+-	case SMU_OD_VDDC_CURVE:
++	case SMU_OD_VDDGFX_OFFSET:
+ 		if (!smu_v13_0_0_is_od_feature_supported(smu,
+ 							 PP_OD_FEATURE_GFX_VF_CURVE_BIT))
+ 			break;
+
+-		size += sysfs_emit_at(buf, size, "OD_VDDC_CURVE:\n");
+-		for (i = 0; i < PP_NUM_OD_VF_CURVE_POINTS; i++)
+-			size += sysfs_emit_at(buf, size, "%d: %dmv\n",
+-						i,
+-						od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[i]);
++		size += sysfs_emit_at(buf, size, "OD_VDDGFX_OFFSET:\n");
++		size += sysfs_emit_at(buf, size, "%dmV\n",
++				      od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[0]);
+ 		break;
+
+ 	case SMU_OD_RANGE:
+@@ -1355,7 +1353,7 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu,
+ 							  PP_OD_FEATURE_GFX_VF_CURVE,
+ 							  &min_value,
+ 							  &max_value);
+-			size += sysfs_emit_at(buf, size, "VDDC_CURVE: %7dmv %10dmv\n",
++			size += sysfs_emit_at(buf, size, "VDDGFX_OFFSET: %7dmv %10dmv\n",
+ 					      min_value, max_value);
+ 		}
+ 		break;
+@@ -1504,29 +1502,26 @@ static int smu_v13_0_0_od_edit_dpm_table(struct smu_context *smu,
+ 		}
+ 		break;
+
+-	case PP_OD_EDIT_VDDC_CURVE:
++	case PP_OD_EDIT_VDDGFX_OFFSET:
+ 		if (!smu_v13_0_0_is_od_feature_supported(smu, PP_OD_FEATURE_GFX_VF_CURVE_BIT)) {
+-			dev_warn(adev->dev, "VF curve setting not supported!\n");
++			dev_warn(adev->dev, "Gfx offset setting not supported!\n");
+ 			return -ENOTSUPP;
+ 		}
+
+-		if (input[0] >= PP_NUM_OD_VF_CURVE_POINTS ||
+-		    input[0] < 0)
+-			return -EINVAL;
+-
+ 		smu_v13_0_0_get_od_setting_limits(smu,
+ 						  PP_OD_FEATURE_GFX_VF_CURVE,
+ 						  &minimum,
+ 						  &maximum);
+-		if (input[1] < minimum ||
+-		    input[1] > maximum) {
++		if (input[0] < minimum ||
++		    input[0] > maximum) {
+ 			dev_info(adev->dev, "Voltage offset (%ld) must be within [%d, %d]!\n",
+-				 input[1], minimum, maximum);
++				 input[0], minimum, maximum);
+ 			return -EINVAL;
+ 		}
+
+-		od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[input[0]] = input[1];
+-		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFX_VF_CURVE_BIT;
++		for (i = 0; i < PP_NUM_OD_VF_CURVE_POINTS; i++)
++			od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[i] = input[0];
++		od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT);
+ 		break;
+
+ 	case PP_OD_RESTORE_DEFAULT_TABLE:
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+index 94ef5b4d116d..b9b3bf41eed3 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+@@ -1284,16 +1284,14 @@ static int smu_v13_0_7_print_clk_levels(struct smu_context *smu,
+ 					od_table->OverDriveTable.UclkFmax);
+ 		break;
+
+-	case SMU_OD_VDDC_CURVE:
++	case SMU_OD_VDDGFX_OFFSET:
+ 		if (!smu_v13_0_7_is_od_feature_supported(smu,
+ 							 PP_OD_FEATURE_GFX_VF_CURVE_BIT))
+ 			break;
+
+-		size += sysfs_emit_at(buf, size, "OD_VDDC_CURVE:\n");
+-		for (i = 0; i < PP_NUM_OD_VF_CURVE_POINTS; i++)
+-			size += sysfs_emit_at(buf, size, "%d: %dmv\n",
+-						i,
+-						od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[i]);
++		size += sysfs_emit_at(buf, size, "OD_VDDGFX_OFFSET:\n");
++		size += sysfs_emit_at(buf, size, "%dmV\n",
++				      od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[0]);
+ 		break;
+
+ 	case SMU_OD_RANGE:
+@@ -1335,7 +1333,7 @@ static int smu_v13_0_7_print_clk_levels(struct smu_context *smu,
+ 							  PP_OD_FEATURE_GFX_VF_CURVE,
+ 							  &min_value,
+ 							  &max_value);
+-			size += sysfs_emit_at(buf, size, "VDDC_CURVE: %7dmv %10dmv\n",
++			size += sysfs_emit_at(buf, size, "VDDGFX_OFFSET: %7dmv %10dmv\n",
+ 					      min_value, max_value);
+ 		}
+ 		break;
+@@ -1484,29 +1482,26 @@ static int smu_v13_0_7_od_edit_dpm_table(struct smu_context *smu,
+ 		}
+ 		break;
+
+-	case PP_OD_EDIT_VDDC_CURVE:
++	case PP_OD_EDIT_VDDGFX_OFFSET:
+ 		if (!smu_v13_0_7_is_od_feature_supported(smu, PP_OD_FEATURE_GFX_VF_CURVE_BIT)) {
+-			dev_warn(adev->dev, "VF curve setting not supported!\n");
++			dev_warn(adev->dev, "Gfx offset setting not supported!\n");
+ 			return -ENOTSUPP;
+ 		}
+
+-		if (input[0] >= PP_NUM_OD_VF_CURVE_POINTS ||
+-		    input[0] < 0)
+-			return -EINVAL;
+-
+ 		smu_v13_0_7_get_od_setting_limits(smu,
+ 						  PP_OD_FEATURE_GFX_VF_CURVE,
+ 						  &minimum,
+ 						  &maximum);
+-		if (input[1] < minimum ||
+-		    input[1] > maximum) {
++		if (input[0] < minimum ||
++		    input[0] > maximum) {
+ 			dev_info(adev->dev, "Voltage offset (%ld) must be within [%d, %d]!\n",
+-				 input[1], minimum, maximum);
++				 input[0], minimum, maximum);
+ 			return -EINVAL;
+ 		}
+
+-		od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[input[0]] = input[1];
+-		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFX_VF_CURVE_BIT;
++		for (i = 0; i < PP_NUM_OD_VF_CURVE_POINTS; i++)
++			od_table->OverDriveTable.VoltageOffsetPerZoneBoundary[i] = input[0];
++		od_table->OverDriveTable.FeatureCtrlMask |= BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT);
+ 		break;
+
+ 	case PP_OD_RESTORE_DEFAULT_TABLE:
+--
+GitLab
+
+
+From 8bad128720ebc69e37f1c66767fb276088ef4fa7 Mon Sep 17 00:00:00 2001
+From: Evan Quan <evan.quan@amd.com>
+Date: Wed, 16 Aug 2023 14:51:19 +0800
+Subject: [PATCH] drm/amd/pm: fulfill the support for SMU13 `pp_dpm_dcefclk`
+ interface
+
+Fulfill the incomplete SMU13 `pp_dpm_dcefclk` implementation.
+
+Reported-by: Guan Yu <guan.yu@amd.com>
+Signed-off-by: Evan Quan <evan.quan@amd.com>
+Acked-by: Alex Deucher <alexander.deucher@amd.com>
+---
+ .../drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c  | 27 +++++++++++++++++++
+ .../drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c  | 27 +++++++++++++++++++
+ 2 files changed, 54 insertions(+)
+
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+index bd0d5f027cac..5fdb2b3c042a 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+@@ -176,6 +176,7 @@ static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = {
+ 	CLK_MAP(VCLK1,		PPCLK_VCLK_1),
+ 	CLK_MAP(DCLK,		PPCLK_DCLK_0),
+ 	CLK_MAP(DCLK1,		PPCLK_DCLK_1),
++	CLK_MAP(DCEFCLK,	PPCLK_DCFCLK),
+ };
+
+ static struct cmn2asic_mapping smu_v13_0_0_feature_mask_map[SMU_FEATURE_COUNT] = {
+@@ -707,6 +708,22 @@ static int smu_v13_0_0_set_default_dpm_table(struct smu_context *smu)
+ 		pcie_table->num_of_link_levels++;
+ 	}
+
++	/* dcefclk dpm table setup */
++	dpm_table = &dpm_context->dpm_tables.dcef_table;
++	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_DCN_BIT)) {
++		ret = smu_v13_0_set_single_dpm_table(smu,
++						     SMU_DCEFCLK,
++						     dpm_table);
++		if (ret)
++			return ret;
++	} else {
++		dpm_table->count = 1;
++		dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.dcefclk / 100;
++		dpm_table->dpm_levels[0].enabled = true;
++		dpm_table->min = dpm_table->dpm_levels[0].value;
++		dpm_table->max = dpm_table->dpm_levels[0].value;
++	}
++
+ 	return 0;
+ }
+
+@@ -794,6 +811,9 @@ static int smu_v13_0_0_get_smu_metrics_data(struct smu_context *smu,
+ 	case METRICS_CURR_FCLK:
+ 		*value = metrics->CurrClock[PPCLK_FCLK];
+ 		break;
++	case METRICS_CURR_DCEFCLK:
++		*value = metrics->CurrClock[PPCLK_DCFCLK];
++		break;
+ 	case METRICS_AVERAGE_GFXCLK:
+ 		if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD)
+ 			*value = metrics->AverageGfxclkFrequencyPostDs;
+@@ -1047,6 +1067,9 @@ static int smu_v13_0_0_get_current_clk_freq_by_table(struct smu_context *smu,
+ 	case PPCLK_DCLK_1:
+ 		member_type = METRICS_AVERAGE_DCLK1;
+ 		break;
++	case PPCLK_DCFCLK:
++		member_type = METRICS_CURR_DCEFCLK;
++		break;
+ 	default:
+ 		return -EINVAL;
+ 	}
+@@ -1196,6 +1219,9 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu,
+ 	case SMU_DCLK1:
+ 		single_dpm_table = &(dpm_context->dpm_tables.dclk_table);
+ 		break;
++	case SMU_DCEFCLK:
++		single_dpm_table = &(dpm_context->dpm_tables.dcef_table);
++		break;
+ 	default:
+ 		break;
+ 	}
+@@ -1209,6 +1235,7 @@ static int smu_v13_0_0_print_clk_levels(struct smu_context *smu,
+ 	case SMU_VCLK1:
+ 	case SMU_DCLK:
+ 	case SMU_DCLK1:
++	case SMU_DCEFCLK:
+ 		ret = smu_v13_0_0_get_current_clk_freq_by_table(smu, clk_type, &curr_freq);
+ 		if (ret) {
+ 			dev_err(smu->adev->dev, "Failed to get current clock freq!");
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+index b9b3bf41eed3..12949928e285 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+@@ -147,6 +147,7 @@ static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = {
+ 	CLK_MAP(VCLK1,		PPCLK_VCLK_1),
+ 	CLK_MAP(DCLK,		PPCLK_DCLK_0),
+ 	CLK_MAP(DCLK1,		PPCLK_DCLK_1),
++	CLK_MAP(DCEFCLK,	PPCLK_DCFCLK),
+ };
+
+ static struct cmn2asic_mapping smu_v13_0_7_feature_mask_map[SMU_FEATURE_COUNT] = {
+@@ -696,6 +697,22 @@ static int smu_v13_0_7_set_default_dpm_table(struct smu_context *smu)
+ 		pcie_table->num_of_link_levels++;
+ 	}
+
++	/* dcefclk dpm table setup */
++	dpm_table = &dpm_context->dpm_tables.dcef_table;
++	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_DPM_DCN_BIT)) {
++		ret = smu_v13_0_set_single_dpm_table(smu,
++						     SMU_DCEFCLK,
++						     dpm_table);
++		if (ret)
++			return ret;
++	} else {
++		dpm_table->count = 1;
++		dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.dcefclk / 100;
++		dpm_table->dpm_levels[0].enabled = true;
++		dpm_table->min = dpm_table->dpm_levels[0].value;
++		dpm_table->max = dpm_table->dpm_levels[0].value;
++	}
++
+ 	return 0;
+ }
+
+@@ -777,6 +794,9 @@ static int smu_v13_0_7_get_smu_metrics_data(struct smu_context *smu,
+ 	case METRICS_CURR_FCLK:
+ 		*value = metrics->CurrClock[PPCLK_FCLK];
+ 		break;
++	case METRICS_CURR_DCEFCLK:
++		*value = metrics->CurrClock[PPCLK_DCFCLK];
++		break;
+ 	case METRICS_AVERAGE_GFXCLK:
+ 		*value = metrics->AverageGfxclkFrequencyPreDs;
+ 		break;
+@@ -1027,6 +1047,9 @@ static int smu_v13_0_7_get_current_clk_freq_by_table(struct smu_context *smu,
+ 	case PPCLK_DCLK_1:
+ 		member_type = METRICS_CURR_DCLK1;
+ 		break;
++	case PPCLK_DCFCLK:
++		member_type = METRICS_CURR_DCEFCLK;
++		break;
+ 	default:
+ 		return -EINVAL;
+ 	}
+@@ -1176,6 +1199,9 @@ static int smu_v13_0_7_print_clk_levels(struct smu_context *smu,
+ 	case SMU_DCLK1:
+ 		single_dpm_table = &(dpm_context->dpm_tables.dclk_table);
+ 		break;
++	case SMU_DCEFCLK:
++		single_dpm_table = &(dpm_context->dpm_tables.dcef_table);
++		break;
+ 	default:
+ 		break;
+ 	}
+@@ -1189,6 +1215,7 @@ static int smu_v13_0_7_print_clk_levels(struct smu_context *smu,
+ 	case SMU_VCLK1:
+ 	case SMU_DCLK:
+ 	case SMU_DCLK1:
++	case SMU_DCEFCLK:
+ 		ret = smu_v13_0_7_get_current_clk_freq_by_table(smu, clk_type, &curr_freq);
+ 		if (ret) {
+ 			dev_err(smu->adev->dev, "Failed to get current clock freq!");
+--
+GitLab
+
+From 3a2fb905145e76e4bbb32e90e0c6cd532dafb1b0 Mon Sep 17 00:00:00 2001
+From: Evan Quan <evan.quan@amd.com>
+Date: Mon, 14 Aug 2023 10:16:27 +0800
+Subject: [PATCH] Revert "drm/amd/pm: disable the SMU13 OD feature support
+ temporarily"
+
+This reverts commit 3592cc20beeece83db4c50a0f400e2dd15139de9.
+
+The enablement for the new OD mechanism completed. Also, the support for
+fan control related OD feature has been added via this new mechanism.
+Thus, it is time to bring back the SMU13 OD support.
+
+Signed-off-by: Evan Quan <evan.quan@amd.com>
+Acked-by: Alex Deucher <alexander.deucher@amd.com>
+---
+ .../drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c   | 18 +++---------------
+ .../drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c   | 12 +++---------
+ 2 files changed, 6 insertions(+), 24 deletions(-)
+
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+index c48f81450d24..093962a37688 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+@@ -348,13 +348,10 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu)
+ 		table_context->power_play_table;
+ 	struct smu_baco_context *smu_baco = &smu->smu_baco;
+ 	PPTable_t *pptable = smu->smu_table.driver_pptable;
+-#if 0
+-	PPTable_t *pptable = smu->smu_table.driver_pptable;
+ 	const OverDriveLimits_t * const overdrive_upperlimits =
+ 				&pptable->SkuTable.OverDriveLimitsBasicMax;
+ 	const OverDriveLimits_t * const overdrive_lowerlimits =
+ 				&pptable->SkuTable.OverDriveLimitsMin;
+-#endif
+
+ 	if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_HARDWAREDC)
+ 		smu->dc_controlled_by_gpio = true;
+@@ -366,27 +363,18 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu)
+ 	if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO)
+ 		smu_baco->maco_support = true;
+
+-	/*
+-	 * We are in the transition to a new OD mechanism.
+-	 * Disable the OD feature support for SMU13 temporarily.
+-	 * TODO: get this reverted when new OD mechanism online
+-	 */
+-#if 0
+ 	if (!overdrive_lowerlimits->FeatureCtrlMask ||
+ 	    !overdrive_upperlimits->FeatureCtrlMask)
+ 		smu->od_enabled = false;
+
++	table_context->thermal_controller_type =
++		powerplay_table->thermal_controller_type;
++
+ 	/*
+ 	 * Instead of having its own buffer space and get overdrive_table copied,
+ 	 * smu->od_settings just points to the actual overdrive_table
+ 	 */
+ 	smu->od_settings = &powerplay_table->overdrive_table;
+-#else
+-	smu->od_enabled = false;
+-#endif
+-
+-	table_context->thermal_controller_type =
+-		powerplay_table->thermal_controller_type;
+
+ 	smu->adev->pm.no_fan =
+ 		!(pptable->SkuTable.FeaturesToRun[0] & (1 << FEATURE_FAN_CONTROL_BIT));
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+index 99bc449799a6..430ad1b05ba3 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+@@ -338,12 +338,10 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu)
+ 	struct smu_baco_context *smu_baco = &smu->smu_baco;
+ 	PPTable_t *smc_pptable = table_context->driver_pptable;
+ 	BoardTable_t *BoardTable = &smc_pptable->BoardTable;
+-#if 0
+ 	const OverDriveLimits_t * const overdrive_upperlimits =
+ 				&smc_pptable->SkuTable.OverDriveLimitsBasicMax;
+ 	const OverDriveLimits_t * const overdrive_lowerlimits =
+ 				&smc_pptable->SkuTable.OverDriveLimitsMin;
+-#endif
+
+ 	if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_HARDWAREDC)
+ 		smu->dc_controlled_by_gpio = true;
+@@ -355,22 +353,18 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu)
+ 	if (smu_baco->platform_support && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled))
+ 		smu_baco->maco_support = true;
+
+-#if 0
+ 	if (!overdrive_lowerlimits->FeatureCtrlMask ||
+ 	    !overdrive_upperlimits->FeatureCtrlMask)
+ 		smu->od_enabled = false;
+
++	table_context->thermal_controller_type =
++		powerplay_table->thermal_controller_type;
++
+ 	/*
+ 	 * Instead of having its own buffer space and get overdrive_table copied,
+ 	 * smu->od_settings just points to the actual overdrive_table
+ 	 */
+ 	smu->od_settings = &powerplay_table->overdrive_table;
+-#else
+-	smu->od_enabled = false;
+-#endif
+-
+-	table_context->thermal_controller_type =
+-		powerplay_table->thermal_controller_type;
+
+ 	return 0;
+ }
+--
+GitLab
+
+From 072a8dc3b5260ba08ba2e66036c2c63abd77df52 Mon Sep 17 00:00:00 2001
+From: Lijo Lazar <lijo.lazar@amd.com>
+Date: Thu, 24 Aug 2023 17:25:51 +0530
+Subject: [PATCH] drm/amd/pm: Fix clock reporting for SMUv13.0.6
+
+On SMU v13.0.6, effective clocks are reported by FW which won't exactly
+match with DPM level. Report the current clock based on the values
+matching closest to the effective clock. Also, when deep sleep is
+applied to a clock, report it with a special level "S:" as in sample
+clock levels below
+
+S: 19Mhz *
+0: 615Mhz
+1: 800Mhz
+2: 888Mhz
+3: 1000Mhz
+
+Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
+Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
+Reviewed-by: Evan Quan <evan.quan@amd.com>
+---
+ .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  | 159 +++++++-----------
+ 1 file changed, 62 insertions(+), 97 deletions(-)
+
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+index c2308783053c..29e1cada7667 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+@@ -91,6 +91,8 @@
+ #define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0x5
+ #define LINK_SPEED_MAX				4
+
++#define SMU_13_0_6_DSCLK_THRESHOLD 100
++
+ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COUNT] = {
+ 	MSG_MAP(TestMessage,			     PPSMC_MSG_TestMessage,			0),
+ 	MSG_MAP(GetSmuVersion,			     PPSMC_MSG_GetSmuVersion,			1),
+@@ -783,13 +785,61 @@ static int smu_v13_0_6_get_current_clk_freq_by_table(struct smu_context *smu,
+ 	return smu_v13_0_6_get_smu_metrics_data(smu, member_type, value);
+ }
+
++static int smu_v13_0_6_print_clks(struct smu_context *smu, char *buf,
++				  struct smu_13_0_dpm_table *single_dpm_table,
++				  uint32_t curr_clk, const char *clk_name)
++{
++	struct pp_clock_levels_with_latency clocks;
++	int i, ret, size = 0, level = -1;
++	uint32_t clk1, clk2;
++
++	ret = smu_v13_0_6_get_clk_table(smu, &clocks, single_dpm_table);
++	if (ret) {
++		dev_err(smu->adev->dev, "Attempt to get %s clk levels failed!",
++			clk_name);
++		return ret;
++	}
++
++	if (!clocks.num_levels)
++		return -EINVAL;
++
++	if (curr_clk < SMU_13_0_6_DSCLK_THRESHOLD) {
++		size = sysfs_emit_at(buf, size, "S: %uMhz *\n", curr_clk);
++		for (i = 0; i < clocks.num_levels; i++)
++			size += sysfs_emit_at(buf, size, "%d: %uMhz\n", i,
++					      clocks.data[i].clocks_in_khz /
++						      1000);
++
++	} else {
++		if ((clocks.num_levels == 1) ||
++		    (curr_clk < (clocks.data[0].clocks_in_khz / 1000)))
++			level = 0;
++		for (i = 0; i < clocks.num_levels; i++) {
++			clk1 = clocks.data[i].clocks_in_khz / 1000;
++
++			if (i < (clocks.num_levels - 1))
++				clk2 = clocks.data[i + 1].clocks_in_khz / 1000;
++
++			if (curr_clk >= clk1 && curr_clk < clk2) {
++				level = (curr_clk - clk1) <= (clk2 - curr_clk) ?
++						i :
++						i + 1;
++			}
++
++			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i,
++					      clk1, (level == i) ? "*" : "");
++		}
++	}
++
++	return size;
++}
++
+ static int smu_v13_0_6_print_clk_levels(struct smu_context *smu,
+ 					enum smu_clk_type type, char *buf)
+ {
+-	int i, now, size = 0;
++	int now, size = 0;
+ 	int ret = 0;
+ 	struct smu_umd_pstate_table *pstate_table = &smu->pstate_table;
+-	struct pp_clock_levels_with_latency clocks;
+ 	struct smu_13_0_dpm_table *single_dpm_table;
+ 	struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
+ 	struct smu_13_0_dpm_context *dpm_context = NULL;
+@@ -852,26 +902,9 @@ static int smu_v13_0_6_print_clk_levels(struct smu_context *smu,
+ 		}
+
+ 		single_dpm_table = &(dpm_context->dpm_tables.uclk_table);
+-		ret = smu_v13_0_6_get_clk_table(smu, &clocks, single_dpm_table);
+-		if (ret) {
+-			dev_err(smu->adev->dev,
+-				"Attempt to get memory clk levels Failed!");
+-			return ret;
+-		}
+
+-		for (i = 0; i < clocks.num_levels; i++)
+-			size += sysfs_emit_at(
+-				buf, size, "%d: %uMhz %s\n", i,
+-				clocks.data[i].clocks_in_khz / 1000,
+-				(clocks.num_levels == 1) ?
+-					"*" :
+-					(smu_v13_0_6_freqs_in_same_level(
+-						 clocks.data[i].clocks_in_khz /
+-							 1000,
+-						 now) ?
+-						 "*" :
+-						 ""));
+-		break;
++		return smu_v13_0_6_print_clks(smu, buf, single_dpm_table, now,
++					      "mclk");
+
+ 	case SMU_SOCCLK:
+ 		ret = smu_v13_0_6_get_current_clk_freq_by_table(smu, SMU_SOCCLK,
+@@ -883,26 +916,9 @@ static int smu_v13_0_6_print_clk_levels(struct smu_context *smu,
+ 		}
+
+ 		single_dpm_table = &(dpm_context->dpm_tables.soc_table);
+-		ret = smu_v13_0_6_get_clk_table(smu, &clocks, single_dpm_table);
+-		if (ret) {
+-			dev_err(smu->adev->dev,
+-				"Attempt to get socclk levels Failed!");
+-			return ret;
+-		}
+
+-		for (i = 0; i < clocks.num_levels; i++)
+-			size += sysfs_emit_at(
+-				buf, size, "%d: %uMhz %s\n", i,
+-				clocks.data[i].clocks_in_khz / 1000,
+-				(clocks.num_levels == 1) ?
+-					"*" :
+-					(smu_v13_0_6_freqs_in_same_level(
+-						 clocks.data[i].clocks_in_khz /
+-							 1000,
+-						 now) ?
+-						 "*" :
+-						 ""));
+-		break;
++		return smu_v13_0_6_print_clks(smu, buf, single_dpm_table, now,
++					      "socclk");
+
+ 	case SMU_FCLK:
+ 		ret = smu_v13_0_6_get_current_clk_freq_by_table(smu, SMU_FCLK,
+@@ -914,26 +930,9 @@ static int smu_v13_0_6_print_clk_levels(struct smu_context *smu,
+ 		}
+
+ 		single_dpm_table = &(dpm_context->dpm_tables.fclk_table);
+-		ret = smu_v13_0_6_get_clk_table(smu, &clocks, single_dpm_table);
+-		if (ret) {
+-			dev_err(smu->adev->dev,
+-				"Attempt to get fclk levels Failed!");
+-			return ret;
+-		}
+
+-		for (i = 0; i < single_dpm_table->count; i++)
+-			size += sysfs_emit_at(
+-				buf, size, "%d: %uMhz %s\n", i,
+-				single_dpm_table->dpm_levels[i].value,
+-				(clocks.num_levels == 1) ?
+-					"*" :
+-					(smu_v13_0_6_freqs_in_same_level(
+-						 clocks.data[i].clocks_in_khz /
+-							 1000,
+-						 now) ?
+-						 "*" :
+-						 ""));
+-		break;
++		return smu_v13_0_6_print_clks(smu, buf, single_dpm_table, now,
++					      "fclk");
+
+ 	case SMU_VCLK:
+ 		ret = smu_v13_0_6_get_current_clk_freq_by_table(smu, SMU_VCLK,
+@@ -945,26 +944,9 @@ static int smu_v13_0_6_print_clk_levels(struct smu_context *smu,
+ 		}
+
+ 		single_dpm_table = &(dpm_context->dpm_tables.vclk_table);
+-		ret = smu_v13_0_6_get_clk_table(smu, &clocks, single_dpm_table);
+-		if (ret) {
+-			dev_err(smu->adev->dev,
+-				"Attempt to get vclk levels Failed!");
+-			return ret;
+-		}
+
+-		for (i = 0; i < single_dpm_table->count; i++)
+-			size += sysfs_emit_at(
+-				buf, size, "%d: %uMhz %s\n", i,
+-				single_dpm_table->dpm_levels[i].value,
+-				(clocks.num_levels == 1) ?
+-					"*" :
+-					(smu_v13_0_6_freqs_in_same_level(
+-						 clocks.data[i].clocks_in_khz /
+-							 1000,
+-						 now) ?
+-						 "*" :
+-						 ""));
+-		break;
++		return smu_v13_0_6_print_clks(smu, buf, single_dpm_table, now,
++					      "vclk");
+
+ 	case SMU_DCLK:
+ 		ret = smu_v13_0_6_get_current_clk_freq_by_table(smu, SMU_DCLK,
+@@ -976,26 +958,9 @@ static int smu_v13_0_6_print_clk_levels(struct smu_context *smu,
+ 		}
+
+ 		single_dpm_table = &(dpm_context->dpm_tables.dclk_table);
+-		ret = smu_v13_0_6_get_clk_table(smu, &clocks, single_dpm_table);
+-		if (ret) {
+-			dev_err(smu->adev->dev,
+-				"Attempt to get dclk levels Failed!");
+-			return ret;
+-		}
+
+-		for (i = 0; i < single_dpm_table->count; i++)
+-			size += sysfs_emit_at(
+-				buf, size, "%d: %uMhz %s\n", i,
+-				single_dpm_table->dpm_levels[i].value,
+-				(clocks.num_levels == 1) ?
+-					"*" :
+-					(smu_v13_0_6_freqs_in_same_level(
+-						 clocks.data[i].clocks_in_khz /
+-							 1000,
+-						 now) ?
+-						 "*" :
+-						 ""));
+-		break;
++		return smu_v13_0_6_print_clks(smu, buf, single_dpm_table, now,
++					      "dclk");
+
+ 	default:
+ 		break;
+--
+GitLab
+