PDS Kernel Configuration

https://bugzilla.kernel.org/show_bug.cgi?id=216823
https://github.com/Frogging-Family/linux-tkg/issues/696

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 - Options are "5.4", and from "5.7" to "5.19"
 # 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"
@@ -60,10 +60,10 @@ _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=""
@@ -97,11 +97,11 @@ _STRIP="true"
 # LEAVE AN EMPTY VALUE TO BE PROMPTED ABOUT FOLLOWING OPTIONS AT BUILD TIME
 
 # CPU scheduler - Options are "upds" (TkG's Undead PDS), "pds", "bmq", "muqss", "cacule", "tt", "bore" or "cfs" (kernel's default)
-_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.
@@ -131,7 +131,7 @@ _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.
@@ -139,7 +139,7 @@ _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="2"
 
 # 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"
@@ -154,10 +154,10 @@ _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.
@@ -186,13 +186,13 @@ _futex_waitv="false"
 _winesync="false"
 
 # Set to "true" to enable Binder and Ashmem, the kernel modules required to use the android emulator Anbox. ! This doesn't apply to 5.4.y !
-_anbox=""
+_anbox="false"
 
 # A selection of patches from Zen/Liquorix kernel and additional tweaks for a better gaming experience (ZENIFY) - Default is "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)
@@ -206,7 +206,7 @@ _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"
 
 # MuQSS only - Make IRQ threading compulsory (FORCE_IRQ_THREADING) - Default is "false"
 _irq_threading="false"
@@ -222,7 +222,7 @@ _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"
@@ -232,7 +232,7 @@ _random_trust_cpu="true"
 _runqueue_sharing=""
 
 # 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="500"
 
 # Default CPU governor - "performance", "ondemand", "schedutil" or leave empty for default (schedutil)
 _default_cpu_gov="ondemand"

linux-tkg-config/6.2/config.x86_64

@@ -1,6 +1,6 @@
 #
 # Automatically generated file; DO NOT EDIT.
-# Linux/x86 6.2.0-rc1 Kernel Configuration
+# Linux/x86 6.2.0-rc4 Kernel Configuration
 #
 CONFIG_CC_VERSION_TEXT="gcc (GCC) 12.2.0"
 CONFIG_CC_IS_GCC=y
@@ -206,6 +206,7 @@ CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y
 CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH=y
 CONFIG_CC_HAS_INT128=y
 CONFIG_CC_IMPLICIT_FALLTHROUGH="-Wimplicit-fallthrough=5"
+CONFIG_GCC11_NO_ARRAY_BOUNDS=y
 CONFIG_GCC12_NO_ARRAY_BOUNDS=y
 CONFIG_CC_NO_ARRAY_BOUNDS=y
 CONFIG_ARCH_SUPPORTS_INT128=y
@@ -241,6 +242,7 @@ CONFIG_UTS_NS=y
 CONFIG_TIME_NS=y
 CONFIG_IPC_NS=y
 CONFIG_USER_NS=y
+CONFIG_USER_NS_UNPRIVILEGED=y
 CONFIG_PID_NS=y
 CONFIG_NET_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
@@ -2546,6 +2548,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=m
 CONFIG_BLK_DEV_RAM_COUNT=16
 CONFIG_BLK_DEV_RAM_SIZE=16384
+# CONFIG_CDROM_PKTCDVD is not set
 CONFIG_ATA_OVER_ETH=m
 CONFIG_XEN_BLKDEV_FRONTEND=m
 CONFIG_XEN_BLKDEV_BACKEND=m

linux-tkg-config/prepare

@@ -284,7 +284,8 @@ _set_cpu_scheduler() {
   elif [ "$_kver" = "601" ]; then
     _avail_cpu_scheds=("cfs" "pds" "bmq" "tt" "bore")
   elif [ "$_kver" = "602" ]; then
-    _avail_cpu_scheds=("cfs" "tt" "bore")
+    _avail_cpu_scheds=("cfs" "pds" "bmq" "tt" "bore")
+    _projectc_unoff=1
   else
     _avail_cpu_scheds=("cfs")
   fi
@@ -722,7 +723,7 @@ _tkg_srcprep() {
   elif [ "$_kver" = "518" ]; then
     rev=2
   elif [ "$_kver" = "601" ]; then
-    rev=1
+    rev=3
   else
     rev=0
   fi
@@ -1572,9 +1573,13 @@ CONFIG_DEBUG_INFO_BTF_MODULES=y\r
   fi
 
   # NR_CPUS
-  if [ -n "$_NR_CPUS_value" ]; then
+  if [ "$_basever" != "601" ]; then
-    scripts/config --set-val "NR_CPUS" "$_NR_CPUS_value"
+    if [ -n "$_NR_CPUS_value" ]; then
-    _enable "FORCE_NR_CPUS"
+      scripts/config --set-val "NR_CPUS" "$_NR_CPUS_value"
+      _enable "FORCE_NR_CPUS"
+    fi
+  else
+    warning "NR_CPUS is bugged on 6.1.y, so your setting was ignored"
   fi
 
   fi

linux-tkg-patches/6.1/0009-prjc_v6.1-r3.patch

@@ -632,10 +632,10 @@ index 976092b7bd45..31d587c16ec1 100644
  obj-y += build_utility.o
 diff --git a/kernel/sched/alt_core.c b/kernel/sched/alt_core.c
 new file mode 100644
-index 000000000000..572eab74418f
+index 000000000000..acb8657e811d
 --- /dev/null
 +++ b/kernel/sched/alt_core.c
-@@ -0,0 +1,7961 @@
+@@ -0,0 +1,7978 @@
 +/*
 + *  kernel/sched/alt_core.c
 + *
@@ -665,7 +665,6 @@ index 000000000000..572eab74418f
 +#include <linux/init_task.h>
 +#include <linux/kcov.h>
 +#include <linux/kprobes.h>
-+#include <linux/profile.h>
 +#include <linux/nmi.h>
 +#include <linux/scs.h>
 +
@@ -706,7 +705,7 @@ index 000000000000..572eab74418f
 +#define sched_feat(x)	(0)
 +#endif /* CONFIG_SCHED_DEBUG */
 +
-+#define ALT_SCHED_VERSION "v6.1-r1"
++#define ALT_SCHED_VERSION "v6.1-r3"
 +
 +/* rt_prio(prio) defined in include/linux/sched/rt.h */
 +#define rt_task(p)		rt_prio((p)->prio)
@@ -815,14 +814,14 @@ index 000000000000..572eab74418f
 +clear_recorded_preempt_mask(int pr, int low, int high, int cpu)
 +{
 +	if (low < pr && pr <= high)
-+		cpumask_clear_cpu(cpu, sched_preempt_mask + SCHED_QUEUE_BITS - 1 - pr);
++		cpumask_clear_cpu(cpu, sched_preempt_mask + SCHED_QUEUE_BITS - pr);
 +}
 +
 +static inline void
 +set_recorded_preempt_mask(int pr, int low, int high, int cpu)
 +{
 +	if (low < pr && pr <= high)
-+		cpumask_set_cpu(cpu, sched_preempt_mask + SCHED_QUEUE_BITS - 1 - pr);
++		cpumask_set_cpu(cpu, sched_preempt_mask + SCHED_QUEUE_BITS - pr);
 +}
 +
 +static atomic_t sched_prio_record = ATOMIC_INIT(0);
@@ -1392,8 +1391,8 @@ index 000000000000..572eab74418f
 + * Context: rq->lock
 + */
 +#define __SCHED_DEQUEUE_TASK(p, rq, flags)					\
-+	psi_dequeue(p, flags & DEQUEUE_SLEEP);					\
 +	sched_info_dequeue(rq, p);						\
++	psi_dequeue(p, flags & DEQUEUE_SLEEP);					\
 +										\
 +	list_del(&p->sq_node);							\
 +	if (list_empty(&rq->queue.heads[p->sq_idx])) 				\
@@ -2030,11 +2029,13 @@ index 000000000000..572eab74418f
 +
 +	WARN_ON_ONCE(is_migration_disabled(p));
 +#endif
-+	if (task_cpu(p) == new_cpu)
-+		return;
 +	trace_sched_migrate_task(p, new_cpu);
-+	rseq_migrate(p);
++
-+	perf_event_task_migrate(p);
++	if (task_cpu(p) != new_cpu)
++	{
++		rseq_migrate(p);
++		perf_event_task_migrate(p);
++	}
 +
 +	__set_task_cpu(p, new_cpu);
 +}
@@ -5110,15 +5111,15 @@ index 000000000000..572eab74418f
 +				if (src_rq->nr_running < 2)
 +					cpumask_clear_cpu(i, &sched_rq_pending_mask);
 +
++				spin_release(&src_rq->lock.dep_map, _RET_IP_);
++				do_raw_spin_unlock(&src_rq->lock);
++
 +				rq->nr_running += nr_migrated;
 +				if (rq->nr_running > 1)
 +					cpumask_set_cpu(cpu, &sched_rq_pending_mask);
 +
 +				cpufreq_update_util(rq, 0);
 +
-+				spin_release(&src_rq->lock.dep_map, _RET_IP_);
-+				do_raw_spin_unlock(&src_rq->lock);
-+
 +				return 1;
 +			}
 +
@@ -5147,7 +5148,7 @@ index 000000000000..572eab74418f
 +}
 +
 +static inline struct task_struct *
-+choose_next_task(struct rq *rq, int cpu, struct task_struct *prev)
++choose_next_task(struct rq *rq, int cpu)
 +{
 +	struct task_struct *next;
 +
@@ -5334,7 +5335,7 @@ index 000000000000..572eab74418f
 +
 +	check_curr(prev, rq);
 +
-+	next = choose_next_task(rq, cpu, prev);
++	next = choose_next_task(rq, cpu);
 +	clear_tsk_need_resched(prev);
 +	clear_preempt_need_resched();
 +#ifdef CONFIG_SCHED_DEBUG
@@ -5764,6 +5765,7 @@ index 000000000000..572eab74418f
 +		return;
 +
 +	rq = __task_access_lock(p, &lock);
++	update_rq_clock(rq);
 +	/*
 +	 * Set under pi_lock && rq->lock, such that the value can be used under
 +	 * either lock.
@@ -6643,6 +6645,13 @@ index 000000000000..572eab74418f
 +	return retval;
 +}
 +
++#ifdef CONFIG_SMP
++int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
++{
++	return 0;
++}
++#endif
++
 +static int
 +__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
 +{
@@ -8027,6 +8036,14 @@ index 000000000000..572eab74418f
 +
 +	sched_smp_initialized = true;
 +}
++
++static int __init migration_init(void)
++{
++	sched_cpu_starting(smp_processor_id());
++	return 0;
++}
++early_initcall(migration_init);
++
 +#else
 +void __init sched_init_smp(void)
 +{
@@ -8636,14 +8653,15 @@ index 000000000000..1212a031700e
 +{}
 diff --git a/kernel/sched/alt_sched.h b/kernel/sched/alt_sched.h
 new file mode 100644
-index 000000000000..e3b6320a397a
+index 000000000000..c32403ed82b6
 --- /dev/null
 +++ b/kernel/sched/alt_sched.h
-@@ -0,0 +1,667 @@
+@@ -0,0 +1,668 @@
 +#ifndef ALT_SCHED_H
 +#define ALT_SCHED_H
 +
 +#include <linux/context_tracking.h>
++#include <linux/profile.h>
 +#include <linux/psi.h>
 +#include <linux/stop_machine.h>
 +#include <linux/syscalls.h>

linux-tkg-patches/6.1/0012-misc-additions.patch

@@ -2540,41 +2540,3 @@ index 41fd8352ab6561..1d2f77835de5f0 100644
 
  /**
 
-From 07fa6df737871f5e491ec70f499963aedd679f2a Mon Sep 17 00:00:00 2001
-From: Pablo Neira Ayuso <pablo@netfilter.org>
-Date: Wed, 11 Jan 2023 17:07:33 +0100
-Subject: [PATCH] netfilter: nft_payload: incorrect arithmetics when fetching
- VLAN header bits
-
-commit 696e1a48b1a1b01edad542a1ef293665864a4dd0 upstream.
-
-If the offset + length goes over the ethernet + vlan header, then the
-length is adjusted to copy the bytes that are within the boundaries of
-the vlan_ethhdr scratchpad area. The remaining bytes beyond ethernet +
-vlan header are copied directly from the skbuff data area.
-
-Fix incorrect arithmetic operator: subtract, not add, the size of the
-vlan header in case of double-tagged packets to adjust the length
-accordingly to address CVE-2023-0179.
-
-Reported-by: Davide Ornaghi <d.ornaghi97@gmail.com>
-Fixes: f6ae9f120dad ("netfilter: nft_payload: add C-VLAN support")
-Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- net/netfilter/nft_payload.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
-index 4edd899aeb9bb5..d7de2ecb287eba 100644
---- a/net/netfilter/nft_payload.c
-+++ b/net/netfilter/nft_payload.c
-@@ -62,7 +62,7 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len)
- 			return false;
-
- 		if (offset + len > VLAN_ETH_HLEN + vlan_hlen)
--			ethlen -= offset + len - VLAN_ETH_HLEN + vlan_hlen;
-+			ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen;
-
- 		memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen);
-

linux-tkg-patches/6.2/0005-glitched-pds.patch

@@ -0,0 +1,90 @@
+From f7f49141a5dbe9c99d78196b58c44307fb2e6be3 Mon Sep 17 00:00:00 2001
+From: Tk-Glitch <ti3nou@gmail.com>
+Date: Wed, 4 Jul 2018 04:30:08 +0200
+Subject: glitched - PDS
+
+diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
+index 2a202a846757..1d9c7ed79b11 100644
+--- a/kernel/Kconfig.hz
++++ b/kernel/Kconfig.hz
+@@ -4,7 +4,7 @@
+ 
+ choice
+ 	prompt "Timer frequency"
+-	default HZ_250
++	default HZ_500
+ 	help
+ 	 Allows the configuration of the timer frequency. It is customary
+ 	 to have the timer interrupt run at 1000 Hz but 100 Hz may be more
+@@ -39,6 +39,13 @@ choice
+ 	 on SMP and NUMA systems and exactly dividing by both PAL and
+ 	 NTSC frame rates for video and multimedia work.
+ 
++	config HZ_500
++		bool "500 HZ"
++	help
++	 500 Hz is a balanced timer frequency. Provides fast interactivity
++	 on desktops with great smoothness without increasing CPU power
++	 consumption and sacrificing the battery life on laptops.
++
+ 	config HZ_1000
+ 		bool "1000 HZ"
+ 	help
+@@ -52,6 +59,7 @@ config HZ
+ 	default 100 if HZ_100
+ 	default 250 if HZ_250
+ 	default 300 if HZ_300
++	default 500 if HZ_500
+ 	default 1000 if HZ_1000
+ 
+ config SCHED_HRTICK
+
+diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
+index 2a202a846757..1d9c7ed79b11 100644
+--- a/kernel/Kconfig.hz
++++ b/kernel/Kconfig.hz
+@@ -4,7 +4,7 @@
+ 
+ choice
+ 	prompt "Timer frequency"
+-	default HZ_500
++	default HZ_750
+ 	help
+ 	 Allows the configuration of the timer frequency. It is customary
+ 	 to have the timer interrupt run at 1000 Hz but 100 Hz may be more
+@@ -46,6 +46,13 @@ choice
+ 	 on desktops with great smoothness without increasing CPU power
+ 	 consumption and sacrificing the battery life on laptops.
+ 
++	config HZ_750
++		bool "750 HZ"
++	help
++	 750 Hz is a good timer frequency for desktops. Provides fast
++	 interactivity with great smoothness without sacrificing too
++	 much throughput.
++
+ 	config HZ_1000
+ 		bool "1000 HZ"
+ 	help
+@@ -60,6 +67,7 @@ config HZ
+ 	default 250 if HZ_250
+ 	default 300 if HZ_300
+ 	default 500 if HZ_500
++	default 750 if HZ_750
+ 	default 1000 if HZ_1000
+ 
+ config SCHED_HRTICK
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 9270a4370d54..30d01e647417 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -169,7 +169,7 @@  
+ /*
+  * From 0 .. 200.  Higher means more swappy.
+  */
+-int vm_swappiness = 60;
++int vm_swappiness = 20;
+ 
+ static void set_task_reclaim_state(struct task_struct *task,
+ 				   struct reclaim_state *rs)

linux-tkg-patches/6.2/0012-misc-additions.patch

@@ -64,253 +64,3 @@ index 2c7171e0b0010..85de313ddec29 100644
  	select CPU_FREQ_GOV_PERFORMANCE
  	help
 
-From 0c079d3f88df5f8286cd5c91b54bdac7c819be85 Mon Sep 17 00:00:00 2001
-From: Matthew Auld <matthew.auld@intel.com>
-Date: Tue, 6 Dec 2022 16:11:41 +0000
-Subject: [PATCH] drm/i915: improve the catch-all evict to handle lock
- contention
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-The catch-all evict can fail due to object lock contention, since it
-only goes as far as trylocking the object, due to us already holding the
-vm->mutex. Doing a full object lock here can deadlock, since the
-vm->mutex is always our inner lock. Add another execbuf pass which drops
-the vm->mutex and then tries to grab the object will the full lock,
-before then retrying the eviction. This should be good enough for now to
-fix the immediate regression with userspace seeing -ENOSPC from execbuf
-due to contended object locks during GTT eviction.
-
-Testcase: igt@gem_ppgtt@shrink-vs-evict-*
-Fixes: 7e00897be8bf ("drm/i915: Add object locking to i915_gem_evict_for_node and i915_gem_evict_something, v2.")
-References: https://gitlab.freedesktop.org/drm/intel/-/issues/7627
-References: https://gitlab.freedesktop.org/drm/intel/-/issues/7570
-References: https://bugzilla.mozilla.org/show_bug.cgi?id=1779558
-Signed-off-by: Matthew Auld <matthew.auld@intel.com>
-Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
-Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
-Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
-Cc: Andrzej Hajda <andrzej.hajda@intel.com>
-Cc: Mani Milani <mani@chromium.org>
-Cc: <stable@vger.kernel.org> # v5.18+
-
-Revision 1 of https://patchwork.freedesktop.org/series/111686/
----
- .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 25 +++++++++++--
- drivers/gpu/drm/i915/gem/i915_gem_mman.c      |  2 +-
- drivers/gpu/drm/i915/i915_gem_evict.c         | 37 ++++++++++++++-----
- drivers/gpu/drm/i915/i915_gem_evict.h         |  4 +-
- drivers/gpu/drm/i915/i915_vma.c               |  2 +-
- .../gpu/drm/i915/selftests/i915_gem_evict.c   |  4 +-
- 6 files changed, 56 insertions(+), 18 deletions(-)
-
-diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
-index 845023c14eb36f..094e92ed28db4f 100644
---- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
-+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
-@@ -741,25 +741,44 @@ static int eb_reserve(struct i915_execbuffer *eb)
- 	 *
- 	 * Defragmenting is skipped if all objects are pinned at a fixed location.
- 	 */
--	for (pass = 0; pass <= 2; pass++) {
-+	for (pass = 0; pass <= 3; pass++) {
- 		int pin_flags = PIN_USER | PIN_VALIDATE;
-
- 		if (pass == 0)
- 			pin_flags |= PIN_NONBLOCK;
-
- 		if (pass >= 1)
--			unpinned = eb_unbind(eb, pass == 2);
-+			unpinned = eb_unbind(eb, pass >= 2);
-
- 		if (pass == 2) {
- 			err = mutex_lock_interruptible(&eb->context->vm->mutex);
- 			if (!err) {
--				err = i915_gem_evict_vm(eb->context->vm, &eb->ww);
-+				err = i915_gem_evict_vm(eb->context->vm, &eb->ww, NULL);
- 				mutex_unlock(&eb->context->vm->mutex);
- 			}
- 			if (err)
- 				return err;
- 		}
-
-+		if (pass == 3) {
-+retry:
-+			err = mutex_lock_interruptible(&eb->context->vm->mutex);
-+			if (!err) {
-+				struct drm_i915_gem_object *busy_bo = NULL;
-+
-+				err = i915_gem_evict_vm(eb->context->vm, &eb->ww, &busy_bo);
-+				mutex_unlock(&eb->context->vm->mutex);
-+				if (err && busy_bo) {
-+					err = i915_gem_object_lock(busy_bo, &eb->ww);
-+					i915_gem_object_put(busy_bo);
-+					if (!err)
-+						goto retry;
-+				}
-+			}
-+			if (err)
-+				return err;
-+		}
-+
- 		list_for_each_entry(ev, &eb->unbound, bind_link) {
- 			err = eb_reserve_vma(eb, ev, pin_flags);
- 			if (err)
-diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
-index 73d9eda1d6b7a6..c83d98e1dc5da0 100644
---- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
-+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
-@@ -369,7 +369,7 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
- 		if (vma == ERR_PTR(-ENOSPC)) {
- 			ret = mutex_lock_interruptible(&ggtt->vm.mutex);
- 			if (!ret) {
--				ret = i915_gem_evict_vm(&ggtt->vm, &ww);
-+				ret = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
- 				mutex_unlock(&ggtt->vm.mutex);
- 			}
- 			if (ret)
-diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
-index f025ee4fa52618..a4b4d9b7d26c7a 100644
---- a/drivers/gpu/drm/i915/i915_gem_evict.c
-+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
-@@ -416,6 +416,11 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
-  * @vm: Address space to cleanse
-  * @ww: An optional struct i915_gem_ww_ctx. If not NULL, i915_gem_evict_vm
-  * will be able to evict vma's locked by the ww as well.
-+ * @busy_bo: Optional pointer to struct drm_i915_gem_object. If not NULL, then
-+ * in the event i915_gem_evict_vm() is unable to trylock an object for eviction,
-+ * then @busy_bo will point to it. -EBUSY is also returned. The caller must drop
-+ * the vm->mutex, before trying again to acquire the contended lock. The caller
-+ * also owns a reference to the object.
-  *
-  * This function evicts all vmas from a vm.
-  *
-@@ -425,7 +430,8 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
-  * To clarify: This is for freeing up virtual address space, not for freeing
-  * memory in e.g. the shrinker.
-  */
--int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww)
-+int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww,
-+		      struct drm_i915_gem_object **busy_bo)
- {
- 	int ret = 0;
-
-@@ -457,15 +463,22 @@ int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww)
- 			 * the resv is shared among multiple objects, we still
- 			 * need the object ref.
- 			 */
--			if (dying_vma(vma) ||
-+			if (!i915_gem_object_get_rcu(vma->obj) ||
- 			    (ww && (dma_resv_locking_ctx(vma->obj->base.resv) == &ww->ctx))) {
- 				__i915_vma_pin(vma);
- 				list_add(&vma->evict_link, &locked_eviction_list);
- 				continue;
- 			}
-
--			if (!i915_gem_object_trylock(vma->obj, ww))
-+			if (!i915_gem_object_trylock(vma->obj, ww)) {
-+				if (busy_bo) {
-+					*busy_bo = vma->obj; /* holds ref */
-+					ret = -EBUSY;
-+					break;
-+				}
-+				i915_gem_object_put(vma->obj);
- 				continue;
-+			}
-
- 			__i915_vma_pin(vma);
- 			list_add(&vma->evict_link, &eviction_list);
-@@ -473,25 +486,29 @@ int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww)
- 		if (list_empty(&eviction_list) && list_empty(&locked_eviction_list))
- 			break;
-
--		ret = 0;
- 		/* Unbind locked objects first, before unlocking the eviction_list */
- 		list_for_each_entry_safe(vma, vn, &locked_eviction_list, evict_link) {
- 			__i915_vma_unpin(vma);
-
--			if (ret == 0)
-+			if (ret == 0) {
- 				ret = __i915_vma_unbind(vma);
--			if (ret != -EINTR) /* "Get me out of here!" */
--				ret = 0;
-+				if (ret != -EINTR) /* "Get me out of here!" */
-+					ret = 0;
-+			}
-+			if (!dying_vma(vma))
-+				i915_gem_object_put(vma->obj);
- 		}
-
- 		list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) {
- 			__i915_vma_unpin(vma);
--			if (ret == 0)
-+			if (ret == 0) {
- 				ret = __i915_vma_unbind(vma);
--			if (ret != -EINTR) /* "Get me out of here!" */
--				ret = 0;
-+				if (ret != -EINTR) /* "Get me out of here!" */
-+					ret = 0;
-+			}
-
- 			i915_gem_object_unlock(vma->obj);
-+			i915_gem_object_put(vma->obj);
- 		}
- 	} while (ret == 0);
-
-diff --git a/drivers/gpu/drm/i915/i915_gem_evict.h b/drivers/gpu/drm/i915/i915_gem_evict.h
-index e593c530f9bd7a..bf0ee0e4fe6088 100644
---- a/drivers/gpu/drm/i915/i915_gem_evict.h
-+++ b/drivers/gpu/drm/i915/i915_gem_evict.h
-@@ -11,6 +11,7 @@
- struct drm_mm_node;
- struct i915_address_space;
- struct i915_gem_ww_ctx;
-+struct drm_i915_gem_object;
-
- int __must_check i915_gem_evict_something(struct i915_address_space *vm,
- 					  struct i915_gem_ww_ctx *ww,
-@@ -23,6 +24,7 @@ int __must_check i915_gem_evict_for_node(struct i915_address_space *vm,
- 					 struct drm_mm_node *node,
- 					 unsigned int flags);
- int i915_gem_evict_vm(struct i915_address_space *vm,
--		      struct i915_gem_ww_ctx *ww);
-+		      struct i915_gem_ww_ctx *ww,
-+		      struct drm_i915_gem_object **busy_bo);
-
- #endif /* __I915_GEM_EVICT_H__ */
-diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
-index f17c09ead7d778..4d06875de14a14 100644
---- a/drivers/gpu/drm/i915/i915_vma.c
-+++ b/drivers/gpu/drm/i915/i915_vma.c
-@@ -1569,7 +1569,7 @@ static int __i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
- 			 * locked objects when called from execbuf when pinning
- 			 * is removed. This would probably regress badly.
- 			 */
--			i915_gem_evict_vm(vm, NULL);
-+			i915_gem_evict_vm(vm, NULL, NULL);
- 			mutex_unlock(&vm->mutex);
- 		}
- 	} while (1);
-diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
-index 8c6517d29b8e0c..37068542aafe7f 100644
---- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
-+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
-@@ -344,7 +344,7 @@ static int igt_evict_vm(void *arg)
-
- 	/* Everything is pinned, nothing should happen */
- 	mutex_lock(&ggtt->vm.mutex);
--	err = i915_gem_evict_vm(&ggtt->vm, NULL);
-+	err = i915_gem_evict_vm(&ggtt->vm, NULL, NULL);
- 	mutex_unlock(&ggtt->vm.mutex);
- 	if (err) {
- 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
-@@ -356,7 +356,7 @@ static int igt_evict_vm(void *arg)
-
- 	for_i915_gem_ww(&ww, err, false) {
- 		mutex_lock(&ggtt->vm.mutex);
--		err = i915_gem_evict_vm(&ggtt->vm, &ww);
-+		err = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
- 		mutex_unlock(&ggtt->vm.mutex);
- 	}
-