PDS Kernel Configuration

Signed-off-by: Piotr Gorski <lucjan.lucjanov@gmail.com>

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"
@@ -59,17 +59,17 @@ _kernel_on_diet="false"
 
 # Set to true to use modprobed db to clean config from unneeded modules. Speeds up compilation considerably. Requires root - https://wiki.archlinux.org/index.php/Modprobed-db
 # Using this option can trigger user prompts if the config doesn't go smoothly.
-# !!!! Make sure to have a well populated db !!!! - Leave empty to be asked about it at build time
+# !!!! Make sure to have a well populated db !!!!
 _modprobeddb="false"
 
 # modprobed-db database file location
 _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/6.5/minimal-modprobed.db

@@ -25,9 +25,9 @@ algif_hash
 algif_skcipher
 alx
 amd64_edac
-amdgpu
 amd_pmc
 amd_pstate
+amdgpu
 amdxcp
 apple_mfi_fastcharge
 appletalk
@@ -54,8 +54,8 @@ bluetooth
 bnep
 bpf
 bpf_preload
-bridge
 br_netfilter
+bridge
 btbcm
 btcoexist
 btintel
@@ -91,10 +91,10 @@ cmdlinepart
 coretemp
 cpufreq_ondemand
 crc16
-crc32c_generic
-crc32c_intel
 crc32_generic
 crc32_pclmul
+crc32c_generic
+crc32c_intel
 crc64
 crc64_rocksoft
 crc64_rocksoft_generic
@@ -109,13 +109,13 @@ cuse
 dca
 des_generic
 dm_crypt
-dmi_sysfs
 dm_log
 dm_mirror
 dm_mod
 dm_multipath
 dm_region_hash
 dm_round_robin
+dmi_sysfs
 dns_resolver
 drm
 drm_buddy
@@ -127,10 +127,10 @@ drm_ttm_helper
 dvb_core
 ebtable_filter
 ebtables
+ec_sys
 ecb
 ecc
 ecdh_generic
-ec_sys
 edac_mce_amd
 ee1004
 eeepc_wmi
@@ -178,7 +178,6 @@ hid_logitech_hidpp
 hid_microsoft
 hid_multitouch
 hid_nintendo
-hidp
 hid_playstation
 hid_roccat
 hid_roccat_common
@@ -187,6 +186,8 @@ hid_roccat_ryos
 hid_sony
 hid_steam
 hid_wiimote
+hidp
+hp_wmi
 hv_balloon
 hv_netvsc
 hv_storvsc
@@ -207,6 +208,8 @@ i2c_piix4
 i2c_smbus
 i8042
 i915
+iTCO_vendor_support
+iTCO_wdt
 ib_cm
 ib_core
 idma64
@@ -215,10 +218,12 @@ igc
 inet_diag
 input_leds
 int3400_thermal
+int3403_thermal
 int340x_thermal_zone
 intel_agp
 intel_cstate
 intel_gtt
+intel_hid
 intel_lpss
 intel_lpss_pci
 intel_pch_thermal
@@ -227,37 +232,36 @@ intel_powerclamp
 intel_rapl_common
 intel_rapl_msr
 intel_soc_dts_iosf
+intel_tcc_cooling
 intel_uncore
 intel_vsec
 intel_wmi_thunderbolt
-iommufd
 iommu_v2
+iommufd
+ip6_tables
+ip6_udp_tunnel
+ip6t_REJECT
+ip6t_rt
 ip6table_filter
 ip6table_mangle
 ip6table_nat
 ip6table_raw
-ip6_tables
 ip6table_security
-ip6t_REJECT
-ip6t_rt
-ip6_udp_tunnel
+ip_set
+ip_tables
 ipmi_devintf
 ipmi_msghandler
-ip_set
+ipt_REJECT
 iptable_filter
 iptable_mangle
 iptable_nat
 iptable_raw
-ip_tables
 iptable_security
-ipt_REJECT
 ipv6
 ir_kbd_i2c
 irqbypass
 isofs
 it87
-iTCO_vendor_support
-iTCO_wdt
 iw_cm
 iwlmei
 iwlmvm
@@ -301,15 +305,17 @@ mbcache
 mc
 mc44s803
 md4
+md_mod
 mdio
 mdio_devres
-md_mod
 mei
+mei_gsc
 mei_hdcp
 mei_me
 mei_pxp
 mii
 minix
+mmc_core
 mousedev
 mptcp_diag
 mrp
@@ -352,14 +358,14 @@ nf_nat_irc
 nf_nat_pptp
 nf_nat_sip
 nf_nat_tftp
+nf_reject_ipv4
+nf_reject_ipv6
+nf_tables
 nfnetlink
 nfnetlink_log
 nfnetlink_queue
-nf_reject_ipv4
-nf_reject_ipv6
 nfs
 nfsv4
-nf_tables
 nft_chain_nat
 nft_compat
 nft_ct
@@ -383,6 +389,7 @@ nls_utf8
 nouveau
 ntfs
 ntfs3
+nvidia_wmi_ec_backlight
 nvme
 nvme_common
 nvme_core
@@ -438,12 +445,18 @@ rt2800usb
 rt2x00lib
 rt2x00usb
 rtl8192ee
+rtl8723_common
 rtl8723ae
 rtl8723be
-rtl8723_common
 rtl8821ae
 rtl_pci
 rtlwifi
+rtsx_pci
+rtsx_pci_sdmmc
+rtw88_8821c
+rtw88_8821ce
+rtw88_core
+rtw88_pci
 sch_cake
 sch_fq_codel
 sch_ingress
@@ -460,8 +473,11 @@ ses
 sg
 sha512_ssse3
 snd
+snd_acp3x_pdm_dma
+snd_acp3x_rn
 snd_acp6x_pdm_dma
 snd_acp_config
+snd_acp_pci
 snd_aloop
 snd_compress
 snd_ctl_led
@@ -479,10 +495,12 @@ snd_intel_sdw_acpi
 snd_pci_acp3x
 snd_pci_acp5x
 snd_pci_acp6x
+snd_pci_ps
 snd_pcm
 snd_pcm_dmaengine
 snd_rawmidi
 snd_rn_pci_acp3x
+snd_rpl_pci_acp6x
 snd_seq
 snd_seq_device
 snd_seq_dummy
@@ -501,12 +519,14 @@ snd_soc_sst_dsp
 snd_soc_sst_ipc
 snd_sof
 snd_sof_amd_acp
+snd_sof_amd_rembrandt
 snd_sof_amd_renoir
 snd_sof_intel_hda
 snd_sof_intel_hda_common
 snd_sof_intel_hda_mlink
 snd_sof_pci
 snd_sof_pci_intel_cnl
+snd_sof_pci_intel_tgl
 snd_sof_probes
 snd_sof_utils
 snd_sof_xtensa_dsp
@@ -514,9 +534,9 @@ snd_timer
 snd_ua101
 snd_ump
 snd_usb_audio
-snd_usbmidi_lib
 snd_usb_us122l
 snd_usb_usx2y
+snd_usbmidi_lib
 snd_virmidi
 soundcore
 soundwire_bus
@@ -549,6 +569,7 @@ tea5767
 tee
 tg3
 thermal
+thunderbolt
 tiny_power_button
 tls
 tpm
@@ -578,14 +599,14 @@ uio
 uio_pdrv_genirq
 unix_diag
 usb_common
+usb_storage
+usb_wwan
 usbcore
 usbhid
 usbip_core
 usbip_host
 usbmon
 usbnet
-usb_storage
-usb_wwan
 uvc
 uvcvideo
 uvesafb
@@ -618,9 +639,11 @@ vsock_loopback
 wacom
 watchdog
 wireguard
+wireless_hotkey
 wmi
 wmi_bmof
 x86_pkg_temp_thermal
+x_tables
 xc2028
 xc4000
 xc5000
@@ -632,21 +655,20 @@ xhci_pci
 xhci_pci_renesas
 xor
 xpad
-x_tables
+xt_CHECKSUM
+xt_LOG
+xt_MASQUERADE
+xt_NFQUEUE
+xt_REDIRECT
 xt_addrtype
 xt_cgroup
-xt_CHECKSUM
 xt_comment
 xt_conntrack
 xt_hl
 xt_limit
-xt_LOG
 xt_mark
-xt_MASQUERADE
 xt_nat
-xt_NFQUEUE
 xt_recent
-xt_REDIRECT
 xt_state
 xt_tcpudp
 xxhash_generic

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

@@ -1,7 +1,7 @@
-From 6f9fee6b2a2ceb4561a58c152467fd5e6d5c47e8 Mon Sep 17 00:00:00 2001
+From d931ed7fc8d6728204d36d31a18d4c8b60593821 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:40 +0200
-Subject: [PATCH 01/15] sched/fair: Add cfs_rq::avg_vruntime
+Subject: [PATCH 01/16] sched/fair: Add cfs_rq::avg_vruntime
 
 In order to move to an eligibility based scheduling policy, we need
 to have a better approximation of the ideal scheduler.
@@ -295,10 +295,10 @@ index e93e006a9..4ccb73d85 100644
 2.42.0
 
 
-From 826b8e2df1d3c69e138c6c89f6872df2be4ad1cb Mon Sep 17 00:00:00 2001
+From 4e5d4ab816239fc30595a76ffcd41c323bdd4996 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:41 +0200
-Subject: [PATCH 02/15] sched/fair: Remove sched_feat(START_DEBIT)
+Subject: [PATCH 02/16] sched/fair: Remove sched_feat(START_DEBIT)
 
 With the introduction of avg_vruntime() there is no need to use worse
 approximations. Take the 0-lag point as starting point for inserting
@@ -372,10 +372,10 @@ index ee7f23c76..fa828b365 100644
 2.42.0
 
 
-From 5672ddd48026e6f590a9eae4d122bb0eed50e109 Mon Sep 17 00:00:00 2001
+From 49ba3e84689bb047d9411e8a3a6ae99020070f37 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:42 +0200
-Subject: [PATCH 03/15] sched/fair: Add lag based placement
+Subject: [PATCH 03/16] sched/fair: Add lag based placement
 
 With the introduction of avg_vruntime, it is possible to approximate
 lag (the entire purpose of introducing it in fact). Use this to do lag
@@ -410,7 +410,7 @@ index 609bde814..52910bfb9 100644
  	u64				nr_migrations;
  
 diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index c52c2eba7..3bb4df5bb 100644
+index e8f73ff12..acb9d9ff3 100644
 --- a/kernel/sched/core.c
 +++ b/kernel/sched/core.c
 @@ -4501,6 +4501,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
@@ -661,10 +661,10 @@ index fa828b365..7958a10fe 100644
 2.42.0
 
 
-From e9818f093795a5d7b1ee08248d8db84ed88411dd Mon Sep 17 00:00:00 2001
+From 31462b52019e938357395e7bd0f630fcd550e27c Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:43 +0200
-Subject: [PATCH 04/15] rbtree: Add rb_add_augmented_cached() helper
+Subject: [PATCH 04/16] rbtree: Add rb_add_augmented_cached() helper
 
 While slightly sub-optimal, updating the augmented data while going
 down the tree during lookup would be faster -- alas the augment
@@ -719,10 +719,10 @@ index 7ee7ed5de..6dbc5a1bf 100644
 2.42.0
 
 
-From cb798272c085050f0db104befcf8092da0931210 Mon Sep 17 00:00:00 2001
+From e8c55c05618756cf090470c355f2864dafe0a618 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:44 +0200
-Subject: [PATCH 05/15] sched/fair: Implement an EEVDF-like scheduling policy
+Subject: [PATCH 05/16] sched/fair: Implement an EEVDF-like scheduling policy
 
 Where CFS is currently a WFQ based scheduler with only a single knob,
 the weight. The addition of a second, latency oriented parameter,
@@ -785,7 +785,7 @@ index 52910bfb9..35331c35f 100644
  	u64				nr_migrations;
  
 diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index 3bb4df5bb..d7291206f 100644
+index acb9d9ff3..427d694ff 100644
 --- a/kernel/sched/core.c
 +++ b/kernel/sched/core.c
 @@ -4502,6 +4502,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
@@ -1398,10 +1398,10 @@ index 4ccb73d85..1fc81dd7f 100644
 2.42.0
 
 
-From 792befe9ba4d972eeb1ba144cfa3062e48fd98ff Mon Sep 17 00:00:00 2001
+From 6aa7145ce28656863846e7f67ad98e3ed89473f3 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:45 +0200
-Subject: [PATCH 06/15] sched/fair: Commit to lag based placement
+Subject: [PATCH 06/16] sched/fair: Commit to lag based placement
 
 Removes the FAIR_SLEEPERS code in favour of the new LAG based
 placement.
@@ -1526,10 +1526,10 @@ index 60cce1e6f..2a830eccd 100644
 2.42.0
 
 
-From 26b3a580ff53a5b6e3b01810b7f223b672cab5e9 Mon Sep 17 00:00:00 2001
+From 12c67a50f08fe4b97fda8f13302e2574e10351c7 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:46 +0200
-Subject: [PATCH 07/15] sched/smp: Use lag to simplify cross-runqueue placement
+Subject: [PATCH 07/16] sched/smp: Use lag to simplify cross-runqueue placement
 
 Using lag is both more correct and simpler when moving between
 runqueues.
@@ -1793,10 +1793,10 @@ index 91f25d6c8..b7daccfb2 100644
 2.42.0
 
 
-From 35645d3d36593126531a3ee2f7402c9acfdb3e6d Mon Sep 17 00:00:00 2001
+From 8e2fcd5cb320987439faec8442f7f73ccb234875 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:47 +0200
-Subject: [PATCH 08/15] sched/fair: Commit to EEVDF
+Subject: [PATCH 08/16] sched/fair: Commit to EEVDF
 
 EEVDF is a better defined scheduling policy, as a result it has less
 heuristics/tunables. There is no compelling reason to keep CFS around.
@@ -2569,10 +2569,10 @@ index 1fc81dd7f..83bbcd35c 100644
 2.42.0
 
 
-From a1bff7f7a7608a50d8b1108e68f766daa920b4a3 Mon Sep 17 00:00:00 2001
+From 55aa8349238fbe34a1f8198d56210a5e773851f1 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:48 +0200
-Subject: [PATCH 09/15] sched/debug: Rename sysctl_sched_min_granularity to
+Subject: [PATCH 09/16] sched/debug: Rename sysctl_sched_min_granularity to
  sysctl_sched_base_slice
 
 EEVDF uses this tunable as the base request/slice -- make sure the
@@ -2589,7 +2589,7 @@ Link: https://lore.kernel.org/r/20230531124604.205287511@infradead.org
  4 files changed, 10 insertions(+), 10 deletions(-)
 
 diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index d7291206f..8116ef56d 100644
+index 427d694ff..be77d999d 100644
 --- a/kernel/sched/core.c
 +++ b/kernel/sched/core.c
 @@ -4502,7 +4502,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
@@ -2685,10 +2685,10 @@ index 83bbcd35c..e21f6a048 100644
 2.42.0
 
 
-From 5ef098d5a57aa3f3a054935b500d694c4027834a Mon Sep 17 00:00:00 2001
+From d059ffad9f9729ec63ad32fc3840a1a308cbd8a7 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 31 May 2023 13:58:49 +0200
-Subject: [PATCH 10/15] sched/fair: Propagate enqueue flags into place_entity()
+Subject: [PATCH 10/16] sched/fair: Propagate enqueue flags into place_entity()
 
 This allows place_entity() to consider ENQUEUE_WAKEUP and
 ENQUEUE_MIGRATED.
@@ -2766,10 +2766,10 @@ index e21f6a048..576d371c8 100644
 2.42.0
 
 
-From 30054e00408a19d0a9ba9c2682217544b09c4937 Mon Sep 17 00:00:00 2001
+From 80cdbd469974a44e5150be88f5c696ec241f6087 Mon Sep 17 00:00:00 2001
 From: Peter Zijlstra <peterz@infradead.org>
 Date: Wed, 16 Aug 2023 15:40:59 +0200
-Subject: [PATCH 11/15] sched/eevdf: Curb wakeup-preemption
+Subject: [PATCH 11/16] sched/eevdf: Curb wakeup-preemption
 
 Mike and others noticed that EEVDF does like to over-schedule quite a
 bit -- which does hurt performance of a number of benchmarks /
@@ -2858,10 +2858,10 @@ index 54334ca5c..546d212ef 100644
 2.42.0
 
 
-From 3e8371461b6d790eb57788495c157d3092ae4ce9 Mon Sep 17 00:00:00 2001
+From 7d5bf4ed3cc74835a55db18eead11af61557a795 Mon Sep 17 00:00:00 2001
 From: Shrikanth Hegde <sshegde@linux.vnet.ibm.com>
 Date: Thu, 24 Aug 2023 13:33:42 +0530
-Subject: [PATCH 12/15] sched/eevdf/doc: Modify the documented knob to
+Subject: [PATCH 12/16] sched/eevdf/doc: Modify the documented knob to
  base_slice_ns as well
 
 After committing the scheduler to EEVDF, we renamed the 'min_granularity_ns'
@@ -2896,3 +2896,299 @@ index 03db55504..f68919800 100644
 -- 
 2.42.0
 
+
+From bff784de63e9a8567d91b630e8f2bf842aef894b Mon Sep 17 00:00:00 2001
+From: Peter Zijlstra <peterz@infradead.org>
+Date: Fri, 15 Sep 2023 00:48:55 +0200
+Subject: [PATCH 13/16] 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>
+Link: https://lkml.kernel.org/r/20230915124822.847197830@noisy.programming.kicks-ass.net
+---
+ 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 163619e41993d6e481a745466c05cc0dfb3dcda8 Mon Sep 17 00:00:00 2001
+From: Peter Zijlstra <peterz@infradead.org>
+Date: Tue, 26 Sep 2023 14:29:50 +0200
+Subject: [PATCH 14/16] sched/eevdf: Fix avg_vruntime()
+
+The expectation is that placing a task at avg_vruntime() makes it
+eligible. Turns out there is a corner case where this is not the case.
+
+Specifically, avg_vruntime() relies on the fact that integer division
+is a flooring function (eg. it discards the remainder). By this
+property the value returned is slightly left of the true average.
+
+However! when the average is a negative (relative to min_vruntime) the
+effect is flipped and it becomes a ceil, with the result that the
+returned value is just right of the average and thus not eligible.
+
+Fixes: af4cf40470c2 ("sched/fair: Add cfs_rq::avg_vruntime")
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+---
+ kernel/sched/fair.c | 10 +++++++++-
+ 1 file changed, 9 insertions(+), 1 deletion(-)
+
+diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
+index efbcdc69c..9dbf3ce61 100644
+--- a/kernel/sched/fair.c
++++ b/kernel/sched/fair.c
+@@ -664,6 +664,10 @@ void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
+ 	cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta;
+ }
+ 
++/*
++ * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
++ * For this to be so, the result of this function must have a left bias.
++ */
+ u64 avg_vruntime(struct cfs_rq *cfs_rq)
+ {
+ 	struct sched_entity *curr = cfs_rq->curr;
+@@ -677,8 +681,12 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
+ 		load += weight;
+ 	}
+ 
+-	if (load)
++	if (load) {
++		/* sign flips effective floor / ceil */
++		if (avg < 0)
++			avg -= (load - 1);
+ 		avg = div_s64(avg, load);
++	}
+ 
+ 	return cfs_rq->min_vruntime + avg;
+ }
+-- 
+2.42.0
+
+
+From 217895647edb558ce9b28d0e07418f66fdaf85bc Mon Sep 17 00:00:00 2001
+From: Peter Zijlstra <peterz@infradead.org>
+Date: Fri, 6 Oct 2023 21:24:45 +0200
+Subject: [PATCH 15/16] sched/eevdf: Fix min_deadline heap integrity
+
+Marek and Biju reported instances of:
+
+  "EEVDF scheduling fail, picking leftmost"
+
+which Mike correlated with cgroup scheduling and the min_deadline heap
+getting corrupted; some trace output confirms:
+
+> And yeah, min_deadline is hosed somehow:
+>
+>    validate_cfs_rq: --- /
+>    __print_se: ffff88845cf48080 w: 1024 ve: -58857638 lag: 870381 vd: -55861854 vmd: -66302085 E (11372/tr)
+>    __print_se:   ffff88810d165800 w: 25 ve: -80323686 lag: 22336429 vd: -41496434 vmd: -66302085 E (-1//autogroup-31)
+>    __print_se:   ffff888108379000 w: 25 ve: 0 lag: -57987257 vd: 114632828 vmd: 114632828 N (-1//autogroup-33)
+>    validate_cfs_rq: min_deadline: -55861854 avg_vruntime: -62278313462 / 1074 = -57987256
+
+Turns out that reweight_entity(), which tries really hard to be fast,
+does not do the normal dequeue+update+enqueue pattern but *does* scale
+the deadline.
+
+However, it then fails to propagate the updated deadline value up the
+heap.
+
+Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy")
+Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
+Reported-by: Biju Das <biju.das.jz@bp.renesas.com>
+Reported-by: Mike Galbraith <efault@gmx.de>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Link: https://lkml.kernel.org/r/20231006192445.GE743@noisy.programming.kicks-ass.net
+---
+ kernel/sched/fair.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
+index 9dbf3ce61..a0f1d9578 100644
+--- a/kernel/sched/fair.c
++++ b/kernel/sched/fair.c
+@@ -3612,6 +3612,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
+ 		 */
+ 		deadline = div_s64(deadline * old_weight, weight);
+ 		se->deadline = se->vruntime + deadline;
++		min_deadline_cb_propagate(&se->run_node, NULL);
+ 	}
+ 
+ #ifdef CONFIG_SMP
+-- 
+2.42.0
+
+
+From 71f1c08f8102e48a5235bb145af59edfa597cf72 Mon Sep 17 00:00:00 2001
+From: Benjamin Segall <bsegall@google.com>
+Date: Fri, 29 Sep 2023 17:09:30 -0700
+Subject: [PATCH 16/16] sched/eevdf: Fix pick_eevdf()
+
+The old pick_eevdf() could fail to find the actual earliest eligible
+deadline when it descended to the right looking for min_deadline, but
+it turned out that that min_deadline wasn't actually eligible. In that
+case we need to go back and search through any left branches we
+skipped looking for the actual best _eligible_ min_deadline.
+
+This is more expensive, but still O(log n), and at worst should only
+involve descending two branches of the rbtree.
+
+I've run this through a userspace stress test (thank you
+tools/lib/rbtree.c), so hopefully this implementation doesn't miss any
+corner cases.
+
+Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy")
+Signed-off-by: Ben Segall <bsegall@google.com>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Link: https://lkml.kernel.org/r/xm261qego72d.fsf_-_@google.com
+---
+ kernel/sched/fair.c | 72 ++++++++++++++++++++++++++++++++++++---------
+ 1 file changed, 58 insertions(+), 14 deletions(-)
+
+diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
+index a0f1d9578..caec9b43c 100644
+--- a/kernel/sched/fair.c
++++ b/kernel/sched/fair.c
+@@ -872,14 +872,16 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
+  *
+  * Which allows an EDF like search on (sub)trees.
+  */
+-static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
++static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
+ {
+ 	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+ 	struct sched_entity *curr = cfs_rq->curr;
+ 	struct sched_entity *best = NULL;
++	struct sched_entity *best_left = NULL;
+ 
+ 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
+ 		curr = NULL;
++	best = curr;
+ 
+ 	/*
+ 	 * Once selected, run a task until it either becomes non-eligible or
+@@ -900,33 +902,75 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
+ 		}
+ 
+ 		/*
+-		 * If this entity has an earlier deadline than the previous
+-		 * best, take this one. If it also has the earliest deadline
+-		 * of its subtree, we're done.
++		 * Now we heap search eligible trees for the best (min_)deadline
+ 		 */
+-		if (!best || deadline_gt(deadline, best, se)) {
++		if (!best || deadline_gt(deadline, best, se))
+ 			best = se;
+-			if (best->deadline == best->min_deadline)
+-				break;
+-		}
+ 
+ 		/*
+-		 * If the earlest deadline in this subtree is in the fully
+-		 * eligible left half of our space, go there.
++		 * Every se in a left branch is eligible, keep track of the
++		 * branch with the best min_deadline
+ 		 */
++		if (node->rb_left) {
++			struct sched_entity *left = __node_2_se(node->rb_left);
++
++			if (!best_left || deadline_gt(min_deadline, best_left, left))
++				best_left = left;
++
++			/*
++			 * min_deadline is in the left branch. rb_left and all
++			 * descendants are eligible, so immediately switch to the second
++			 * loop.
++			 */
++			if (left->min_deadline == se->min_deadline)
++				break;
++		}
++
++		/* min_deadline is at this node, no need to look right */
++		if (se->deadline == se->min_deadline)
++			break;
++
++		/* else min_deadline is in the right branch. */
++		node = node->rb_right;
++	}
++
++	/*
++	 * We ran into an eligible node which is itself the best.
++	 * (Or nr_running == 0 and both are NULL)
++	 */
++	if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0)
++		return best;
++
++	/*
++	 * Now best_left and all of its children are eligible, and we are just
++	 * looking for deadline == min_deadline
++	 */
++	node = &best_left->run_node;
++	while (node) {
++		struct sched_entity *se = __node_2_se(node);
++
++		/* min_deadline is the current node */
++		if (se->deadline == se->min_deadline)
++			return se;
++
++		/* min_deadline is in the left branch */
+ 		if (node->rb_left &&
+ 		    __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
+ 			node = node->rb_left;
+ 			continue;
+ 		}
+ 
++		/* else min_deadline is in the right branch */
+ 		node = node->rb_right;
+ 	}
++	return NULL;
++}
+ 
+-	if (!best || (curr && deadline_gt(deadline, best, curr)))
+-		best = curr;
++static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
++{
++	struct sched_entity *se = __pick_eevdf(cfs_rq);
+ 
+-	if (unlikely(!best)) {
++	if (!se) {
+ 		struct sched_entity *left = __pick_first_entity(cfs_rq);
+ 		if (left) {
+ 			pr_err("EEVDF scheduling fail, picking leftmost\n");
+@@ -934,7 +978,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
+ 		}
+ 	}
+ 
+-	return best;
++	return se;
+ }
+ 
+ #ifdef CONFIG_SCHED_DEBUG
+-- 
+2.42.0
+