path: root/0001-first-zen-test.patch

diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index 7e061ed449aa..86f9f06bd7f0 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -513,9 +513,8 @@ Spectre variant 2
 
    Restricting indirect branch speculation on a user program will
    also prevent the program from launching a variant 2 attack
-   on x86.  All sand-boxed SECCOMP programs have indirect branch
-   speculation restricted by default.  Administrators can change
-   that behavior via the kernel command line and sysfs control files.
+   on x86.  Administrators can change that behavior via the kernel
+   command line and sysfs control files.
    See :ref:`spectre_mitigation_control_command_line`.
 
    Programs that disable their indirect branch speculation will have
@@ -618,61 +617,14 @@ kernel command line.
 		Not specifying this option is equivalent to
 		spectre_v2=auto.
 
-For user space mitigation:
-
-        spectre_v2_user=
-
-		[X86] Control mitigation of Spectre variant 2
-		(indirect branch speculation) vulnerability between
-		user space tasks
-
-		on
-			Unconditionally enable mitigations. Is
-			enforced by spectre_v2=on
-
-		off
-			Unconditionally disable mitigations. Is
-			enforced by spectre_v2=off
-
-		prctl
-			Indirect branch speculation is enabled,
-			but mitigation can be enabled via prctl
-			per thread. The mitigation control state
-			is inherited on fork.
-
-		prctl,ibpb
-			Like "prctl" above, but only STIBP is
-			controlled per thread. IBPB is issued
-			always when switching between different user
-			space processes.
-
-		seccomp
-			Same as "prctl" above, but all seccomp
-			threads will enable the mitigation unless
-			they explicitly opt out.
-
-		seccomp,ibpb
-			Like "seccomp" above, but only STIBP is
-			controlled per thread. IBPB is issued
-			always when switching between different
-			user space processes.
-
-		auto
-			Kernel selects the mitigation depending on
-			the available CPU features and vulnerability.
-
-		Default mitigation:
-		If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl"
-
-		Not specifying this option is equivalent to
-		spectre_v2_user=auto.
-
 		In general the kernel by default selects
 		reasonable mitigations for the current CPU. To
 		disable Spectre variant 2 mitigations, boot with
 		spectre_v2=off. Spectre variant 1 mitigations
 		cannot be disabled.
 
+For spectre_v2_user see :doc:`/admin-guide/kernel-parameters`.
+
 Mitigation selection guide
 --------------------------
 
@@ -698,9 +650,8 @@ Mitigation selection guide
    off by disabling their indirect branch speculation when they are run
    (See :ref:`Documentation/userspace-api/spec_ctrl.rst <set_spec_ctrl>`).
    This prevents untrusted programs from polluting the branch target
-   buffer.  All programs running in SECCOMP sandboxes have indirect
-   branch speculation restricted by default. This behavior can be
-   changed via the kernel command line and sysfs control files. See
+   buffer.  This behavior can be changed via the kernel command line
+   and sysfs control files. See
    :ref:`spectre_mitigation_control_command_line`.
 
 3. High security mode
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bcb102c91b19..8c851105d083 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1991,6 +1991,9 @@
 			disable
 			  Do not enable intel_pstate as the default
 			  scaling driver for the supported processors
+			enable
+			  Enable intel_pstate in-case "disable" was passed
+			  previously in the kernel boot parameters
 			passive
 			  Use intel_pstate as a scaling driver, but configure it
 			  to work with generic cpufreq governors (instead of
@@ -3935,6 +3938,15 @@
 		nomsi		[MSI] If the PCI_MSI kernel config parameter is
 				enabled, this kernel boot option can be used to
 				disable the use of MSI interrupts system-wide.
+		pcie_acs_override =
+					[PCIE] Override missing PCIe ACS support for:
+				downstream
+					All downstream ports - full ACS capabilities
+				multfunction
+					All multifunction devices - multifunction ACS subset
+				id:nnnn:nnnn
+					Specfic device - full ACS capabilities
+					Specified as vid:did (vendor/device ID) in hex
 		noioapicquirk	[APIC] Disable all boot interrupt quirks.
 				Safety option to keep boot IRQs enabled. This
 				should never be necessary.
@@ -5071,6 +5083,12 @@
 	sa1100ir	[NET]
 			See drivers/net/irda/sa1100_ir.c.
 
+	sched_timeslice=
+			[KNL] Time slice in ms for Project C BMQ/PDS scheduler.
+			Format: integer 2, 4
+			Default: 4
+			See Documentation/scheduler/sched-BMQ.txt
+
 	sched_verbose	[KNL] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
@@ -5394,8 +5412,7 @@
 			auto    - Kernel selects the mitigation depending on
 				  the available CPU features and vulnerability.
 
-			Default mitigation:
-			If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl"
+			Default mitigation: "prctl"
 
 			Not specifying this option is equivalent to
 			spectre_v2_user=auto.
@@ -5439,7 +5456,7 @@
 				  will disable SSB unless they explicitly opt out.
 
 			Default mitigations:
-			X86:	If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
+			X86:	"prctl"
 
 			On powerpc the options are:
 
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 609b89175408..a2a658e43699 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -1537,3 +1537,13 @@ is 10 seconds.
 
 The softlockup threshold is (``2 * watchdog_thresh``). Setting this
 tunable to zero will disable lockup detection altogether.
+
+yield_type:
+===========
+
+BMQ/PDS CPU scheduler only. This determines what type of yield calls
+to sched_yield will perform.
+
+  0 - No yield.
+  1 - Deboost and requeue task. (default)
+  2 - Set run queue skip task.
diff --git a/Makefile b/Makefile
index 86b6ca862e39..28563222ba1a 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 15
 SUBLEVEL = 74
-EXTRAVERSION =
+EXTRAVERSION = -zen1
 NAME = Trick or Treat
 
 # *DOCUMENTATION*
@@ -1042,11 +1042,6 @@ KBUILD_CFLAGS	+= -fno-strict-overflow
 # Make sure -fstack-check isn't enabled (like gentoo apparently did)
 KBUILD_CFLAGS  += -fno-stack-check
 
-# conserve stack if available
-ifdef CONFIG_CC_IS_GCC
-KBUILD_CFLAGS   += -fconserve-stack
-endif
-
 # Prohibit date/time macros, which would make the build non-deterministic
 KBUILD_CFLAGS   += -Werror=date-time
 
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 814fe0d349b0..61f0d7757499 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -157,7 +157,7 @@ config MPENTIUM4
 
 
 config MK6
-	bool "K6/K6-II/K6-III"
+	bool "AMD K6/K6-II/K6-III"
 	depends on X86_32
 	help
 	  Select this for an AMD K6-family processor.  Enables use of
@@ -165,7 +165,7 @@ config MK6
 	  flags to GCC.
 
 config MK7
-	bool "Athlon/Duron/K7"
+	bool "AMD Athlon/Duron/K7"
 	depends on X86_32
 	help
 	  Select this for an AMD Athlon K7-family processor.  Enables use of
@@ -173,12 +173,98 @@ config MK7
 	  flags to GCC.
 
 config MK8
-	bool "Opteron/Athlon64/Hammer/K8"
+	bool "AMD Opteron/Athlon64/Hammer/K8"
 	help
 	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
 	  Enables use of some extended instructions, and passes appropriate
 	  optimization flags to GCC.
 
+config MK8SSE3
+	bool "AMD Opteron/Athlon64/Hammer/K8 with SSE3"
+	help
+	  Select this for improved AMD Opteron or Athlon64 Hammer-family processors.
+	  Enables use of some extended instructions, and passes appropriate
+	  optimization flags to GCC.
+
+config MK10
+	bool "AMD 61xx/7x50/PhenomX3/X4/II/K10"
+	help
+	  Select this for an AMD 61xx Eight-Core Magny-Cours, Athlon X2 7x50,
+	  Phenom X3/X4/II, Athlon II X2/X3/X4, or Turion II-family processor.
+	  Enables use of some extended instructions, and passes appropriate
+	  optimization flags to GCC.
+
+config MBARCELONA
+	bool "AMD Barcelona"
+	help
+	  Select this for AMD Family 10h Barcelona processors.
+
+	  Enables -march=barcelona
+
+config MBOBCAT
+	bool "AMD Bobcat"
+	help
+	  Select this for AMD Family 14h Bobcat processors.
+
+	  Enables -march=btver1
+
+config MJAGUAR
+	bool "AMD Jaguar"
+	help
+	  Select this for AMD Family 16h Jaguar processors.
+
+	  Enables -march=btver2
+
+config MBULLDOZER
+	bool "AMD Bulldozer"
+	help
+	  Select this for AMD Family 15h Bulldozer processors.
+
+	  Enables -march=bdver1
+
+config MPILEDRIVER
+	bool "AMD Piledriver"
+	help
+	  Select this for AMD Family 15h Piledriver processors.
+
+	  Enables -march=bdver2
+
+config MSTEAMROLLER
+	bool "AMD Steamroller"
+	help
+	  Select this for AMD Family 15h Steamroller processors.
+
+	  Enables -march=bdver3
+
+config MEXCAVATOR
+	bool "AMD Excavator"
+	help
+	  Select this for AMD Family 15h Excavator processors.
+
+	  Enables -march=bdver4
+
+config MZEN
+	bool "AMD Zen"
+	help
+	  Select this for AMD Family 17h Zen processors.
+
+	  Enables -march=znver1
+
+config MZEN2
+	bool "AMD Zen 2"
+	help
+	  Select this for AMD Family 17h Zen 2 processors.
+
+	  Enables -march=znver2
+
+config MZEN3
+	bool "AMD Zen 3"
+	depends on (CC_IS_GCC && GCC_VERSION >= 100300) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	help
+	  Select this for AMD Family 19h Zen 3 processors.
+
+	  Enables -march=znver3
+
 config MCRUSOE
 	bool "Crusoe"
 	depends on X86_32
@@ -270,7 +356,7 @@ config MPSC
 	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
 
 config MCORE2
-	bool "Core 2/newer Xeon"
+	bool "Intel Core 2"
 	help
 
 	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
@@ -278,6 +364,8 @@ config MCORE2
 	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
 	  (not a typo)
 
+	  Enables -march=core2
+
 config MATOM
 	bool "Intel Atom"
 	help
@@ -287,6 +375,182 @@ config MATOM
 	  accordingly optimized code. Use a recent GCC with specific Atom
 	  support in order to fully benefit from selecting this option.
 
+config MNEHALEM
+	bool "Intel Nehalem"
+	select X86_P6_NOP
+	help
+
+	  Select this for 1st Gen Core processors in the Nehalem family.
+
+	  Enables -march=nehalem
+
+config MWESTMERE
+	bool "Intel Westmere"
+	select X86_P6_NOP
+	help
+
+	  Select this for the Intel Westmere formerly Nehalem-C family.
+
+	  Enables -march=westmere
+
+config MSILVERMONT
+	bool "Intel Silvermont"
+	select X86_P6_NOP
+	help
+
+	  Select this for the Intel Silvermont platform.
+
+	  Enables -march=silvermont
+
+config MGOLDMONT
+	bool "Intel Goldmont"
+	select X86_P6_NOP
+	help
+
+	  Select this for the Intel Goldmont platform including Apollo Lake and Denverton.
+
+	  Enables -march=goldmont
+
+config MGOLDMONTPLUS
+	bool "Intel Goldmont Plus"
+	select X86_P6_NOP
+	help
+
+	  Select this for the Intel Goldmont Plus platform including Gemini Lake.
+
+	  Enables -march=goldmont-plus
+
+config MSANDYBRIDGE
+	bool "Intel Sandy Bridge"
+	select X86_P6_NOP
+	help
+
+	  Select this for 2nd Gen Core processors in the Sandy Bridge family.
+
+	  Enables -march=sandybridge
+
+config MIVYBRIDGE
+	bool "Intel Ivy Bridge"
+	select X86_P6_NOP
+	help
+
+	  Select this for 3rd Gen Core processors in the Ivy Bridge family.
+
+	  Enables -march=ivybridge
+
+config MHASWELL
+	bool "Intel Haswell"
+	select X86_P6_NOP
+	help
+
+	  Select this for 4th Gen Core processors in the Haswell family.
+
+	  Enables -march=haswell
+
+config MBROADWELL
+	bool "Intel Broadwell"
+	select X86_P6_NOP
+	help
+
+	  Select this for 5th Gen Core processors in the Broadwell family.
+
+	  Enables -march=broadwell
+
+config MSKYLAKE
+	bool "Intel Skylake"
+	select X86_P6_NOP
+	help
+
+	  Select this for 6th Gen Core processors in the Skylake family.
+
+	  Enables -march=skylake
+
+config MSKYLAKEX
+	bool "Intel Skylake X"
+	select X86_P6_NOP
+	help
+
+	  Select this for 6th Gen Core processors in the Skylake X family.
+
+	  Enables -march=skylake-avx512
+
+config MCANNONLAKE
+	bool "Intel Cannon Lake"
+	select X86_P6_NOP
+	help
+
+	  Select this for 8th Gen Core processors
+
+	  Enables -march=cannonlake
+
+config MICELAKE
+	bool "Intel Ice Lake"
+	select X86_P6_NOP
+	help
+
+	  Select this for 10th Gen Core processors in the Ice Lake family.
+
+	  Enables -march=icelake-client
+
+config MCASCADELAKE
+	bool "Intel Cascade Lake"
+	select X86_P6_NOP
+	help
+
+	  Select this for Xeon processors in the Cascade Lake family.
+
+	  Enables -march=cascadelake
+
+config MCOOPERLAKE
+	bool "Intel Cooper Lake"
+	depends on (CC_IS_GCC && GCC_VERSION > 100100) || (CC_IS_CLANG && CLANG_VERSION >= 100000)
+	select X86_P6_NOP
+	help
+
+	  Select this for Xeon processors in the Cooper Lake family.
+
+	  Enables -march=cooperlake
+
+config MTIGERLAKE
+	bool "Intel Tiger Lake"
+	depends on  (CC_IS_GCC && GCC_VERSION > 100100) || (CC_IS_CLANG && CLANG_VERSION >= 100000)
+	select X86_P6_NOP
+	help
+
+	  Select this for third-generation 10 nm process processors in the Tiger Lake family.
+
+	  Enables -march=tigerlake
+
+config MSAPPHIRERAPIDS
+	bool "Intel Sapphire Rapids"
+	depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	select X86_P6_NOP
+	help
+
+	  Select this for third-generation 10 nm process processors in the Sapphire Rapids family.
+
+	  Enables -march=sapphirerapids
+
+config MROCKETLAKE
+	bool "Intel Rocket Lake"
+	depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	select X86_P6_NOP
+	help
+
+	  Select this for eleventh-generation processors in the Rocket Lake family.
+
+	  Enables -march=rocketlake
+
+config MALDERLAKE
+	bool "Intel Alder Lake"
+	depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	select X86_P6_NOP
+	help
+
+	  Select this for twelfth-generation processors in the Alder Lake family.
+
+	  Enables -march=alderlake
+
 config GENERIC_CPU
 	bool "Generic-x86-64"
 	depends on X86_64
@@ -294,6 +558,50 @@ config GENERIC_CPU
 	  Generic x86-64 CPU.
 	  Run equally well on all x86-64 CPUs.
 
+config GENERIC_CPU2
+	bool "Generic-x86-64-v2"
+	depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	depends on X86_64
+	help
+	  Generic x86-64 CPU.
+	  Run equally well on all x86-64 CPUs with min support of x86-64-v2.
+
+config GENERIC_CPU3
+	bool "Generic-x86-64-v3"
+	depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	depends on X86_64
+	help
+	  Generic x86-64-v3 CPU with v3 instructions.
+	  Run equally well on all x86-64 CPUs with min support of x86-64-v3.
+
+config GENERIC_CPU4
+	bool "Generic-x86-64-v4"
+	depends on (CC_IS_GCC && GCC_VERSION > 110000) || (CC_IS_CLANG && CLANG_VERSION >= 120000)
+	depends on X86_64
+	help
+	  Generic x86-64 CPU with v4 instructions.
+	  Run equally well on all x86-64 CPUs with min support of x86-64-v4.
+
+config MNATIVE_INTEL
+	bool "Intel-Native optimizations autodetected by the compiler"
+	help
+
+	  Clang 3.8, GCC 4.2 and above support -march=native, which automatically detects
+	  the optimum settings to use based on your processor. Do NOT use this
+	  for AMD CPUs.  Intel Only!
+
+	  Enables -march=native
+
+config MNATIVE_AMD
+	bool "AMD-Native optimizations autodetected by the compiler"
+	help
+
+	  Clang 3.8, GCC 4.2 and above support -march=native, which automatically detects
+	  the optimum settings to use based on your processor. Do NOT use this
+	  for Intel CPUs.  AMD Only!
+
+	  Enables -march=native
+
 endchoice
 
 config X86_GENERIC
@@ -318,7 +626,7 @@ config X86_INTERNODE_CACHE_SHIFT
 config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || MPSC
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
+	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL || MNATIVE_AMD || X86_GENERIC || GENERIC_CPU || GENERIC_CPU2 || GENERIC_CPU3 || GENERIC_CPU4
 	default "4" if MELAN || M486SX || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
@@ -336,11 +644,11 @@ config X86_ALIGNMENT_16
 
 config X86_INTEL_USERCOPY
 	def_bool y
-	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL
 
 config X86_USE_PPRO_CHECKSUM
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL || MNATIVE_AMD
 
 config X86_USE_3DNOW
 	def_bool y
@@ -360,26 +668,26 @@ config X86_USE_3DNOW
 config X86_P6_NOP
 	def_bool y
 	depends on X86_64
-	depends on (MCORE2 || MPENTIUM4 || MPSC)
+	depends on (MCORE2 || MPENTIUM4 || MPSC || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL)
 
 config X86_TSC
 	def_bool y
-	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
+	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL || MNATIVE_AMD) || X86_64
 
 config X86_CMPXCHG64
 	def_bool y
-	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8
+	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL || MNATIVE_AMD
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX)
+	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL || MNATIVE_AMD)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8 ||  MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MNATIVE_INTEL || MNATIVE_AMD)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 9c09bbd390ce..5b288b4a6644 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -119,8 +119,44 @@ else
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
         cflags-$(CONFIG_MK8)		+= -march=k8
         cflags-$(CONFIG_MPSC)		+= -march=nocona
-        cflags-$(CONFIG_MCORE2)		+= -march=core2
-        cflags-$(CONFIG_MATOM)		+= -march=atom
+        cflags-$(CONFIG_MK8SSE3)	+= -march=k8-sse3
+        cflags-$(CONFIG_MK10) 		+= -march=amdfam10
+        cflags-$(CONFIG_MBARCELONA) 	+= -march=barcelona
+        cflags-$(CONFIG_MBOBCAT) 	+= -march=btver1
+        cflags-$(CONFIG_MJAGUAR) 	+= -march=btver2
+        cflags-$(CONFIG_MBULLDOZER) 	+= -march=bdver1
+        cflags-$(CONFIG_MPILEDRIVER)	+= -march=bdver2
+        cflags-$(CONFIG_MSTEAMROLLER) 	+= -march=bdver3
+        cflags-$(CONFIG_MEXCAVATOR) 	+= -march=bdver4
+        cflags-$(CONFIG_MZEN) 		+= -march=znver1
+        cflags-$(CONFIG_MZEN2) 	+= -march=znver2
+        cflags-$(CONFIG_MZEN3) 	+= -march=znver3
+        cflags-$(CONFIG_MNATIVE_INTEL) += -march=native
+        cflags-$(CONFIG_MNATIVE_AMD) 	+= -march=native
+        cflags-$(CONFIG_MATOM) 	+= -march=bonnell
+        cflags-$(CONFIG_MCORE2) 	+= -march=core2
+        cflags-$(CONFIG_MNEHALEM) 	+= -march=nehalem
+        cflags-$(CONFIG_MWESTMERE) 	+= -march=westmere
+        cflags-$(CONFIG_MSILVERMONT) 	+= -march=silvermont
+        cflags-$(CONFIG_MGOLDMONT) 	+= -march=goldmont
+        cflags-$(CONFIG_MGOLDMONTPLUS) += -march=goldmont-plus
+        cflags-$(CONFIG_MSANDYBRIDGE) 	+= -march=sandybridge
+        cflags-$(CONFIG_MIVYBRIDGE) 	+= -march=ivybridge
+        cflags-$(CONFIG_MHASWELL) 	+= -march=haswell
+        cflags-$(CONFIG_MBROADWELL) 	+= -march=broadwell
+        cflags-$(CONFIG_MSKYLAKE) 	+= -march=skylake
+        cflags-$(CONFIG_MSKYLAKEX) 	+= -march=skylake-avx512
+        cflags-$(CONFIG_MCANNONLAKE) 	+= -march=cannonlake
+        cflags-$(CONFIG_MICELAKE) 	+= -march=icelake-client
+        cflags-$(CONFIG_MCASCADELAKE) 	+= -march=cascadelake
+        cflags-$(CONFIG_MCOOPERLAKE) 	+= -march=cooperlake
+        cflags-$(CONFIG_MTIGERLAKE) 	+= -march=tigerlake
+        cflags-$(CONFIG_MSAPPHIRERAPIDS) += -march=sapphirerapids
+        cflags-$(CONFIG_MROCKETLAKE) 	+= -march=rocketlake
+        cflags-$(CONFIG_MALDERLAKE) 	+= -march=alderlake
+        cflags-$(CONFIG_GENERIC_CPU2) 	+= -march=x86-64-v2
+        cflags-$(CONFIG_GENERIC_CPU3) 	+= -march=x86-64-v3
+        cflags-$(CONFIG_GENERIC_CPU4) 	+= -march=x86-64-v4
         cflags-$(CONFIG_GENERIC_CPU)	+= -mtune=generic
         KBUILD_CFLAGS += $(cflags-y)
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 960a021d543e..7e25543693de 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -453,3 +453,4 @@
 446	i386	landlock_restrict_self	sys_landlock_restrict_self
 447	i386	memfd_secret		sys_memfd_secret
 448	i386	process_mrelease	sys_process_mrelease
+449	i386	futex_waitv		sys_futex_waitv
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 18b5500ea8bf..fe8f8dd157b4 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -370,6 +370,7 @@
 446	common	landlock_restrict_self	sys_landlock_restrict_self
 447	common	memfd_secret		sys_memfd_secret
 448	common	process_mrelease	sys_process_mrelease
+449	common	futex_waitv		sys_futex_waitv
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d2c76c8d8cfd..47c3b333f2c6 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -27,6 +27,7 @@ struct pci_sysdata {
 #if IS_ENABLED(CONFIG_VMD)
 	struct pci_dev	*vmd_dev;	/* VMD Device if in Intel VMD domain */
 #endif
+	struct pci_dev	*nvme_remap_dev;	/* AHCI Device if NVME remapped bus */
 };
 
 extern int pci_routeirq;
@@ -70,6 +71,11 @@ static inline bool is_vmd(struct pci_bus *bus)
 #define is_vmd(bus)		false
 #endif /* CONFIG_VMD */
 
+static inline bool is_nvme_remap(struct pci_bus *bus)
+{
+	return to_pci_sysdata(bus)->nvme_remap_dev != NULL;
+}
+
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
index 75884d2cdec3..4e6a08d4c7e5 100644
--- a/arch/x86/include/asm/vermagic.h
+++ b/arch/x86/include/asm/vermagic.h
@@ -17,6 +17,48 @@
 #define MODULE_PROC_FAMILY "586MMX "
 #elif defined CONFIG_MCORE2
 #define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_MNATIVE_INTEL
+#define MODULE_PROC_FAMILY "NATIVE_INTEL "
+#elif defined CONFIG_MNATIVE_AMD
+#define MODULE_PROC_FAMILY "NATIVE_AMD "
+#elif defined CONFIG_MNEHALEM
+#define MODULE_PROC_FAMILY "NEHALEM "
+#elif defined CONFIG_MWESTMERE
+#define MODULE_PROC_FAMILY "WESTMERE "
+#elif defined CONFIG_MSILVERMONT
+#define MODULE_PROC_FAMILY "SILVERMONT "
+#elif defined CONFIG_MGOLDMONT
+#define MODULE_PROC_FAMILY "GOLDMONT "
+#elif defined CONFIG_MGOLDMONTPLUS
+#define MODULE_PROC_FAMILY "GOLDMONTPLUS "
+#elif defined CONFIG_MSANDYBRIDGE
+#define MODULE_PROC_FAMILY "SANDYBRIDGE "
+#elif defined CONFIG_MIVYBRIDGE
+#define MODULE_PROC_FAMILY "IVYBRIDGE "
+#elif defined CONFIG_MHASWELL
+#define MODULE_PROC_FAMILY "HASWELL "
+#elif defined CONFIG_MBROADWELL
+#define MODULE_PROC_FAMILY "BROADWELL "
+#elif defined CONFIG_MSKYLAKE
+#define MODULE_PROC_FAMILY "SKYLAKE "
+#elif defined CONFIG_MSKYLAKEX
+#define MODULE_PROC_FAMILY "SKYLAKEX "
+#elif defined CONFIG_MCANNONLAKE
+#define MODULE_PROC_FAMILY "CANNONLAKE "
+#elif defined CONFIG_MICELAKE
+#define MODULE_PROC_FAMILY "ICELAKE "
+#elif defined CONFIG_MCASCADELAKE
+#define MODULE_PROC_FAMILY "CASCADELAKE "
+#elif defined CONFIG_MCOOPERLAKE
+#define MODULE_PROC_FAMILY "COOPERLAKE "
+#elif defined CONFIG_MTIGERLAKE
+#define MODULE_PROC_FAMILY "TIGERLAKE "
+#elif defined CONFIG_MSAPPHIRERAPIDS
+#define MODULE_PROC_FAMILY "SAPPHIRERAPIDS "
+#elif defined CONFIG_ROCKETLAKE
+#define MODULE_PROC_FAMILY "ROCKETLAKE "
+#elif defined CONFIG_MALDERLAKE
+#define MODULE_PROC_FAMILY "ALDERLAKE "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -35,6 +77,30 @@
 #define MODULE_PROC_FAMILY "K7 "
 #elif defined CONFIG_MK8
 #define MODULE_PROC_FAMILY "K8 "
+#elif defined CONFIG_MK8SSE3
+#define MODULE_PROC_FAMILY "K8SSE3 "
+#elif defined CONFIG_MK10
+#define MODULE_PROC_FAMILY "K10 "
+#elif defined CONFIG_MBARCELONA
+#define MODULE_PROC_FAMILY "BARCELONA "
+#elif defined CONFIG_MBOBCAT
+#define MODULE_PROC_FAMILY "BOBCAT "
+#elif defined CONFIG_MBULLDOZER
+#define MODULE_PROC_FAMILY "BULLDOZER "
+#elif defined CONFIG_MPILEDRIVER
+#define MODULE_PROC_FAMILY "PILEDRIVER "
+#elif defined CONFIG_MSTEAMROLLER
+#define MODULE_PROC_FAMILY "STEAMROLLER "
+#elif defined CONFIG_MJAGUAR
+#define MODULE_PROC_FAMILY "JAGUAR "
+#elif defined CONFIG_MEXCAVATOR
+#define MODULE_PROC_FAMILY "EXCAVATOR "
+#elif defined CONFIG_MZEN
+#define MODULE_PROC_FAMILY "ZEN "
+#elif defined CONFIG_MZEN2
+#define MODULE_PROC_FAMILY "ZEN2 "
+#elif defined CONFIG_MZEN3
+#define MODULE_PROC_FAMILY "ZEN3 "
 #elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 7de599eba7f0..62a5986d625a 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -79,6 +79,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 		 */
 		flags->bm_control = 0;
 	}
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		/*
+		 * For all AMD CPUs that support C3, caches should not be
+		 * flushed by software while entering C3 type state. Set
+		 * bm->check to 1 so that kernel doesn't need to execute
+		 * cache flush operation.
+		 */
+		flags->bm_check = 1;
+		/*
+		 * In current AMD C state implementation ARB_DIS is no longer
+		 * used. So set bm_control to zero to indicate ARB_DIS is not
+		 * required while entering C3 type state.
+		 */
+		flags->bm_control = 0;
+	}
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7b15f7ef760d..d72989d1b117 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1117,11 +1117,11 @@ spectre_v2_user_select_mitigation(void)
 	case SPECTRE_V2_USER_CMD_FORCE:
 		mode = SPECTRE_V2_USER_STRICT;
 		break;
+	case SPECTRE_V2_USER_CMD_AUTO:
 	case SPECTRE_V2_USER_CMD_PRCTL:
 	case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
 		mode = SPECTRE_V2_USER_PRCTL;
 		break;
-	case SPECTRE_V2_USER_CMD_AUTO:
 	case SPECTRE_V2_USER_CMD_SECCOMP:
 	case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
 		if (IS_ENABLED(CONFIG_SECCOMP))
@@ -1759,7 +1759,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 		return mode;
 
 	switch (cmd) {
-	case SPEC_STORE_BYPASS_CMD_AUTO:
 	case SPEC_STORE_BYPASS_CMD_SECCOMP:
 		/*
 		 * Choose prctl+seccomp as the default mode if seccomp is
@@ -1773,6 +1772,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 	case SPEC_STORE_BYPASS_CMD_ON:
 		mode = SPEC_STORE_BYPASS_DISABLE;
 		break;
+	case SPEC_STORE_BYPASS_CMD_AUTO:
 	case SPEC_STORE_BYPASS_CMD_PRCTL:
 		mode = SPEC_STORE_BYPASS_PRCTL;
 		break;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 3507f456fcd0..732b4cf516b5 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -715,12 +715,15 @@ int pci_ext_cfg_avail(void)
 		return 0;
 }
 
-#if IS_ENABLED(CONFIG_VMD)
 struct pci_dev *pci_real_dma_dev(struct pci_dev *dev)
 {
+#if IS_ENABLED(CONFIG_VMD)
 	if (is_vmd(dev->bus))
 		return to_pci_sysdata(dev->bus)->vmd_dev;
+#endif
+
+	if (is_nvme_remap(dev->bus))
+		return to_pci_sysdata(dev->bus)->nvme_remap_dev;
 
 	return dev;
 }
-#endif
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 2f2158e05a91..92a47e48fb3e 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -9,6 +9,15 @@ config MQ_IOSCHED_DEADLINE
 	help
 	  MQ version of the deadline IO scheduler.
 
+config MQ_IOSCHED_DEADLINE_NODEFAULT
+	bool "Rename mq-deadline scheduler to mq-deadline-nodefault"
+	depends on MQ_IOSCHED_DEADLINE
+	default n
+	help
+	  This renames the mq-deadline scheduler to "mq-deadline-nodefault" and
+	  also drops its alias of "deadline". This can prevent existing
+	  userspace from forcing this scheduler over the kernel's choice.
+
 config MQ_IOSCHED_KYBER
 	tristate "Kyber I/O scheduler"
 	default y
diff --git a/block/elevator.c b/block/elevator.c
index 1b5e57f6115f..ace772d99596 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -634,11 +634,19 @@ static struct elevator_type *elevator_get_default(struct request_queue *q)
 	if (q->tag_set && q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT)
 		return NULL;
 
+#ifndef CONFIG_ZEN_INTERACTIVE
 	if (q->nr_hw_queues != 1 &&
 			!blk_mq_is_sbitmap_shared(q->tag_set->flags))
 		return NULL;
+#endif
 
+#if defined(CONFIG_ZEN_INTERACTIVE) && defined(CONFIG_IOSCHED_BFQ)
+	return elevator_get(q, "bfq", false);
+#elif defined(CONFIG_MQ_IOSCHED_DEADLINE_NODEFAULT)
+	return elevator_get(q, "mq-deadline-nodefault", false);
+#else
 	return elevator_get(q, "mq-deadline", false);
+#endif
 }
 
 /*
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index cd2342d29704..c831f8551417 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -1081,12 +1081,21 @@ static struct elevator_type mq_deadline = {
 	.queue_debugfs_attrs = deadline_queue_debugfs_attrs,
 #endif
 	.elevator_attrs = deadline_attrs,
+#ifdef CONFIG_MQ_IOSCHED_DEADLINE_NODEFAULT
+	.elevator_name = "mq-deadline-nodefault",
+	.elevator_alias = "deadline-nodefault",
+#else
 	.elevator_name = "mq-deadline",
 	.elevator_alias = "deadline",
+#endif
 	.elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE,
 	.elevator_owner = THIS_MODULE,
 };
+#ifdef CONFIG_MQ_IOSCHED_DEADLINE_NODEFAULT
+MODULE_ALIAS("mq-deadline-nodefault-iosched");
+#else
 MODULE_ALIAS("mq-deadline-iosched");
+#endif
 
 static int __init deadline_init(void)
 {
diff --git a/drivers/Makefile b/drivers/Makefile
index a110338c860c..f91099276a78 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -59,15 +59,8 @@ obj-y				+= char/
 # iommu/ comes before gpu as gpu are using iommu controllers
 obj-y				+= iommu/
 
-# gpu/ comes after char for AGP vs DRM startup and after iommu
-obj-y				+= gpu/
-
 obj-$(CONFIG_CONNECTOR)		+= connector/
 
-# i810fb and intelfb depend on char/agp/
-obj-$(CONFIG_FB_I810)           += video/fbdev/i810/
-obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
-
 obj-$(CONFIG_PARPORT)		+= parport/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
@@ -79,6 +72,14 @@ obj-y				+= macintosh/
 obj-y				+= scsi/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
+
+# gpu/ comes after char for AGP vs DRM startup and after iommu
+obj-y				+= gpu/
+
+# i810fb and intelfb depend on char/agp/
+obj-$(CONFIG_FB_I810)           += video/fbdev/i810/
+obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
+
 obj-$(CONFIG_TARGET_CORE)	+= target/
 obj-$(CONFIG_MTD)		+= mtd/
 obj-$(CONFIG_SPI)		+= spi/
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 812731e80f8e..d7bf77ff58b8 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1502,7 +1502,7 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance)
 }
 #endif
 
-static void ahci_remap_check(struct pci_dev *pdev, int bar,
+static int ahci_remap_check(struct pci_dev *pdev, int bar,
 		struct ahci_host_priv *hpriv)
 {
 	int i;
@@ -1515,7 +1515,7 @@ static void ahci_remap_check(struct pci_dev *pdev, int bar,
 	    pci_resource_len(pdev, bar) < SZ_512K ||
 	    bar != AHCI_PCI_BAR_STANDARD ||
 	    !(readl(hpriv->mmio + AHCI_VSCAP) & 1))
-		return;
+		return 0;
 
 	cap = readq(hpriv->mmio + AHCI_REMAP_CAP);
 	for (i = 0; i < AHCI_MAX_REMAP; i++) {
@@ -1530,18 +1530,11 @@ static void ahci_remap_check(struct pci_dev *pdev, int bar,
 	}
 
 	if (!hpriv->remapped_nvme)
-		return;
-
-	dev_warn(&pdev->dev, "Found %u remapped NVMe devices.\n",
-		 hpriv->remapped_nvme);
-	dev_warn(&pdev->dev,
-		 "Switch your BIOS from RAID to AHCI mode to use them.\n");
+		return 0;
 
-	/*
-	 * Don't rely on the msi-x capability in the remap case,
-	 * share the legacy interrupt across ahci and remapped devices.
-	 */
-	hpriv->flags |= AHCI_HFLAG_NO_MSI;
+	/* Abort probe, allowing intel-nvme-remap to step in when available */
+	dev_info(&pdev->dev, "Device will be handled by intel-nvme-remap.\n");
+	return -ENODEV;
 }
 
 static int ahci_get_irq_vector(struct ata_host *host, int port)
@@ -1766,7 +1759,9 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hpriv->mmio = pcim_iomap_table(pdev)[ahci_pci_bar];
 
 	/* detect remapped nvme devices */
-	ahci_remap_check(pdev, ahci_pci_bar, hpriv);
+	rc = ahci_remap_check(pdev, ahci_pci_bar, hpriv);
+	if (rc)
+		return rc;
 
 	sysfs_add_file_to_group(&pdev->dev.kobj,
 				&dev_attr_remapped_nvme.attr,
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index eb4320b619c9..38e8ac70ac71 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -18,10 +18,22 @@
 #include "cpufreq_ondemand.h"
 
 /* On-demand governor macros */
+#if defined(CONFIG_ZEN_INTERACTIVE) && defined(CONFIG_SCHED_MUQSS)
+/* MuQSS is less likely to keep a single threaded task on the same core, so
+   have on-demand run at max speed from a much lower core utilization */
+#define DEF_FREQUENCY_UP_THRESHOLD		(40)
+#define MICRO_FREQUENCY_UP_THRESHOLD		(45)
+#define DEF_SAMPLING_DOWN_FACTOR		(5)
+#elif defined(CONFIG_ZEN_INTERACTIVE)
+#define DEF_FREQUENCY_UP_THRESHOLD		(55)
+#define MICRO_FREQUENCY_UP_THRESHOLD		(60)
+#define DEF_SAMPLING_DOWN_FACTOR		(5)
+#else
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
+#define MICRO_FREQUENCY_UP_THRESHOLD		(95)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
+#endif
 #define MAX_SAMPLING_DOWN_FACTOR		(100000)
-#define MICRO_FREQUENCY_UP_THRESHOLD		(95)
 #define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
 #define MIN_FREQUENCY_UP_THRESHOLD		(1)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 8a2c6b58b652..db1174d789c2 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -3362,6 +3362,8 @@ static int __init intel_pstate_setup(char *str)
 
 	if (!strcmp(str, "disable"))
 		no_load = 1;
+	else if (!strcmp(str, "enable"))
+		no_load = 0;
 	else if (!strcmp(str, "active"))
 		default_driver = &intel_pstate;
 	else if (!strcmp(str, "passive"))
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index fea403431f22..87ad7a436564 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -219,6 +219,15 @@ config I2C_CHT_WC
 	  combined with a FUSB302 Type-C port-controller as such it is advised
 	  to also select CONFIG_TYPEC_FUSB302=m.
 
+config I2C_NCT6775
+	tristate "Nuvoton NCT6775 and compatible SMBus controller"
+	help
+		If you say yes to this option, support will be included for the
+		Nuvoton NCT6775 and compatible SMBus controllers.
+
+		This driver can also be built as a module.  If so, the module
+		will be called i2c-nct6775.
+
 config I2C_NFORCE2
 	tristate "Nvidia nForce2, nForce3 and nForce4"
 	depends on PCI
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 1336b04f40e2..ccbe82704a78 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_I2C_CHT_WC)	+= i2c-cht-wc.o
 obj-$(CONFIG_I2C_I801)		+= i2c-i801.o
 obj-$(CONFIG_I2C_ISCH)		+= i2c-isch.o
 obj-$(CONFIG_I2C_ISMT)		+= i2c-ismt.o
+obj-$(CONFIG_I2C_NCT6775)   += i2c-nct6775.o
 obj-$(CONFIG_I2C_NFORCE2)	+= i2c-nforce2.o
 obj-$(CONFIG_I2C_NFORCE2_S4985)	+= i2c-nforce2-s4985.o
 obj-$(CONFIG_I2C_NVIDIA_GPU)	+= i2c-nvidia-gpu.o
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 39cb1b7bb865..9d0b0c24b94e 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -568,11 +568,11 @@ static int piix4_transaction(struct i2c_adapter *piix4_adapter)
 	if (srvrworks_csb5_delay) /* Extra delay for SERVERWORKS_CSB5 */
 		usleep_range(2000, 2100);
 	else
-		usleep_range(250, 500);
+		usleep_range(25, 50);
 
 	while ((++timeout < MAX_TIMEOUT) &&
 	       ((temp = inb_p(SMBHSTSTS)) & 0x01))
-		usleep_range(250, 500);
+		usleep_range(25, 50);
 
 	/* If the SMBus is still busy, we give up */
 	if (timeout == MAX_TIMEOUT) {
diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile
index aaf30b3dcc14..c4660839e3b8 100644
--- a/drivers/pci/controller/Makefile
+++ b/drivers/pci/controller/Makefile
@@ -1,4 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
+ifdef CONFIG_X86_64
+ifdef CONFIG_SATA_AHCI
+obj-y += intel-nvme-remap.o
+endif
+endif
+
 obj-$(CONFIG_PCIE_CADENCE) += cadence/
 obj-$(CONFIG_PCI_FTPCI100) += pci-ftpci100.o
 obj-$(CONFIG_PCI_IXP4XX) += pci-ixp4xx.o
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index a531064233f9..48ded281e434 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3600,6 +3600,106 @@ static void quirk_no_bus_reset(struct pci_dev *dev)
 	dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET;
 }
 
+static bool acs_on_downstream;
+static bool acs_on_multifunction;
+
+#define NUM_ACS_IDS 16
+struct acs_on_id {
+	unsigned short vendor;
+	unsigned short device;
+};
+static struct acs_on_id acs_on_ids[NUM_ACS_IDS];
+static u8 max_acs_id;
+
+static __init int pcie_acs_override_setup(char *p)
+{
+	if (!p)
+		return -EINVAL;
+
+	while (*p) {
+		if (!strncmp(p, "downstream", 10))
+			acs_on_downstream = true;
+		if (!strncmp(p, "multifunction", 13))
+			acs_on_multifunction = true;
+		if (!strncmp(p, "id:", 3)) {
+			char opt[5];
+			int ret;
+			long val;
+
+			if (max_acs_id >= NUM_ACS_IDS - 1) {
+				pr_warn("Out of PCIe ACS override slots (%d)\n",
+						NUM_ACS_IDS);
+				goto next;
+			}
+
+			p += 3;
+			snprintf(opt, 5, "%s", p);
+			ret = kstrtol(opt, 16, &val);
+			if (ret) {
+				pr_warn("PCIe ACS ID parse error %d\n", ret);
+				goto next;
+			}
+			acs_on_ids[max_acs_id].vendor = val;
+
+			p += strcspn(p, ":");
+			if (*p != ':') {
+				pr_warn("PCIe ACS invalid ID\n");
+				goto next;
+			}
+
+			p++;
+			snprintf(opt, 5, "%s", p);
+			ret = kstrtol(opt, 16, &val);
+			if (ret) {
+				pr_warn("PCIe ACS ID parse error %d\n", ret);
+				goto next;
+			}
+			acs_on_ids[max_acs_id].device = val;
+			max_acs_id++;
+		}
+next:
+		p += strcspn(p, ",");
+		if (*p == ',')
+			p++;
+	}
+
+	if (acs_on_downstream || acs_on_multifunction || max_acs_id)
+		pr_warn("Warning: PCIe ACS overrides enabled; This may allow non-IOMMU protected peer-to-peer DMA\n");
+
+	return 0;
+}
+early_param("pcie_acs_override", pcie_acs_override_setup);
+
+static int pcie_acs_overrides(struct pci_dev *dev, u16 acs_flags)
+{
+	int i;
+
+	/* Never override ACS for legacy devices or devices with ACS caps */
+	if (!pci_is_pcie(dev) ||
+		pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS))
+			return -ENOTTY;
+
+	for (i = 0; i < max_acs_id; i++)
+		if (acs_on_ids[i].vendor == dev->vendor &&
+			acs_on_ids[i].device == dev->device)
+				return 1;
+
+	switch (pci_pcie_type(dev)) {
+	case PCI_EXP_TYPE_DOWNSTREAM:
+	case PCI_EXP_TYPE_ROOT_PORT:
+		if (acs_on_downstream)
+			return 1;
+		break;
+	case PCI_EXP_TYPE_ENDPOINT:
+	case PCI_EXP_TYPE_UPSTREAM:
+	case PCI_EXP_TYPE_LEG_END:
+	case PCI_EXP_TYPE_RC_END:
+		if (acs_on_multifunction && dev->multifunction)
+			return 1;
+	}
+
+	return -ENOTTY;
+}
 /*
  * Some NVIDIA GPU devices do not work with bus reset, SBR needs to be
  * prevented for those affected devices.
@@ -4968,6 +5068,7 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_NXP, 0x8d9b, pci_quirk_nxp_rp_acs },
 	/* Zhaoxin Root/Downstream Ports */
 	{ PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs },
+	{ PCI_ANY_ID, PCI_ANY_ID, pcie_acs_overrides },
 	{ 0 }
 };
 
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 19814c26c908..e65448e9a8bc 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -153,6 +153,7 @@ obj-$(CONFIG_CHR_DEV_SCH)	+= ch.o
 obj-$(CONFIG_SCSI_ENCLOSURE)	+= ses.o
 
 obj-$(CONFIG_SCSI_HISI_SAS) += hisi_sas/
+obj-$(CONFIG_VHBA)		+= vhba/
 
 # This goes last, so that "real" scsi devices probe earlier
 obj-$(CONFIG_SCSI_DEBUG)	+= scsi_debug.o
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 6c5934dbe9b3..9a18d9654bb5 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2819,7 +2819,6 @@ int usb_add_hcd(struct usb_hcd *hcd,
 {
 	int retval;
 	struct usb_device *rhdev;
-	struct usb_hcd *shared_hcd;
 
 	if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) {
 		hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev);
@@ -2981,26 +2980,13 @@ int usb_add_hcd(struct usb_hcd *hcd,
 		goto err_hcd_driver_start;
 	}
 
-	/* starting here, usbcore will pay attention to the shared HCD roothub */
-	shared_hcd = hcd->shared_hcd;
-	if (!usb_hcd_is_primary_hcd(hcd) && shared_hcd && HCD_DEFER_RH_REGISTER(shared_hcd)) {
-		retval = register_root_hub(shared_hcd);
-		if (retval != 0)
-			goto err_register_root_hub;
-
-		if (shared_hcd->uses_new_polling && HCD_POLL_RH(shared_hcd))
-			usb_hcd_poll_rh_status(shared_hcd);
-	}
-
 	/* starting here, usbcore will pay attention to this root hub */
-	if (!HCD_DEFER_RH_REGISTER(hcd)) {
-		retval = register_root_hub(hcd);
-		if (retval != 0)
-			goto err_register_root_hub;
+	retval = register_root_hub(hcd);
+	if (retval != 0)
+		goto err_register_root_hub;
 
-		if (hcd->uses_new_polling && HCD_POLL_RH(hcd))
-			usb_hcd_poll_rh_status(hcd);
-	}
+	if (hcd->uses_new_polling && HCD_POLL_RH(hcd))
+		usb_hcd_poll_rh_status(hcd);
 
 	return retval;
 
@@ -3038,7 +3024,6 @@ EXPORT_SYMBOL_GPL(usb_add_hcd);
 void usb_remove_hcd(struct usb_hcd *hcd)
 {
 	struct usb_device *rhdev = hcd->self.root_hub;
-	bool rh_registered;
 
 	dev_info(hcd->self.controller, "remove, state %x\n", hcd->state);
 
@@ -3049,7 +3034,6 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 
 	dev_dbg(hcd->self.controller, "roothub graceful disconnect\n");
 	spin_lock_irq (&hcd_root_hub_lock);
-	rh_registered = hcd->rh_registered;
 	hcd->rh_registered = 0;
 	spin_unlock_irq (&hcd_root_hub_lock);
 
@@ -3059,8 +3043,7 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	cancel_work_sync(&hcd->died_work);
 
 	mutex_lock(&usb_bus_idr_lock);
-	if (rh_registered)
-		usb_disconnect(&rhdev);		/* Sets rhdev to NULL */
+	usb_disconnect(&rhdev);		/* Sets rhdev to NULL */
 	mutex_unlock(&usb_bus_idr_lock);
 
 	/*
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 300d53ee7040..806509ebcfea 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -480,7 +480,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
 		seq_puts(m, "0 0 0\n");
 	else
 		seq_printf(m, "%llu %llu %lu\n",
-		   (unsigned long long)task->se.sum_exec_runtime,
+		   (unsigned long long)tsk_seruntime(task),
 		   (unsigned long long)task->sched_info.run_delay,
 		   task->sched_info.pcount);
 
diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h
index 8874f681b056..59eb72bf7d5f 100644
--- a/include/asm-generic/resource.h
+++ b/include/asm-generic/resource.h
@@ -23,7 +23,7 @@
 	[RLIMIT_LOCKS]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
 	[RLIMIT_SIGPENDING]	= { 		0,	       0 },	\
 	[RLIMIT_MSGQUEUE]	= {   MQ_BYTES_MAX,   MQ_BYTES_MAX },	\
-	[RLIMIT_NICE]		= { 0, 0 },				\
+	[RLIMIT_NICE]		= { 30, 30 },				\
 	[RLIMIT_RTPRIO]		= { 0, 0 },				\
 	[RLIMIT_RTTIME]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
 }
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index ef9ceead3db1..b6c59500c06c 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -52,7 +52,7 @@ struct elevator_mq_ops {
 	void (*exit_icq)(struct io_cq *);
 };
 
-#define ELV_NAME_MAX	(16)
+#define ELV_NAME_MAX	(24)
 
 struct elv_fs_entry {
 	struct attribute attr;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dcba347cbffa..78bc8efdaaa0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -748,12 +748,18 @@ struct task_struct {
 	unsigned int			ptrace;
 
 #ifdef CONFIG_SMP
-	int				on_cpu;
 	struct __call_single_node	wake_entry;
+#endif
+#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_ALT)
+	int				on_cpu;
+#endif
+
+#ifdef CONFIG_SMP
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/* Current CPU: */
 	unsigned int			cpu;
 #endif
+#ifndef CONFIG_SCHED_ALT
 	unsigned int			wakee_flips;
 	unsigned long			wakee_flip_decay_ts;
 	struct task_struct		*last_wakee;
@@ -767,6 +773,7 @@ struct task_struct {
 	 */
 	int				recent_used_cpu;
 	int				wake_cpu;
+#endif /* !CONFIG_SCHED_ALT */
 #endif
 	int				on_rq;
 
@@ -775,6 +782,20 @@ struct task_struct {
 	int				normal_prio;
 	unsigned int			rt_priority;
 
+#ifdef CONFIG_SCHED_ALT
+	u64				last_ran;
+	s64				time_slice;
+	int				sq_idx;
+	struct list_head		sq_node;
+#ifdef CONFIG_SCHED_BMQ
+	int				boost_prio;
+#endif /* CONFIG_SCHED_BMQ */
+#ifdef CONFIG_SCHED_PDS
+	u64				deadline;
+#endif /* CONFIG_SCHED_PDS */
+	/* sched_clock time spent running */
+	u64				sched_time;
+#else /* !CONFIG_SCHED_ALT */
 	const struct sched_class	*sched_class;
 	struct sched_entity		se;
 	struct sched_rt_entity		rt;
@@ -785,6 +806,7 @@ struct task_struct {
 	unsigned long			core_cookie;
 	unsigned int			core_occupation;
 #endif
+#endif /* !CONFIG_SCHED_ALT */
 
 #ifdef CONFIG_CGROUP_SCHED
 	struct task_group		*sched_task_group;
@@ -1506,6 +1528,15 @@ struct task_struct {
 	 */
 };
 
+#ifdef CONFIG_SCHED_ALT
+#define tsk_seruntime(t)		((t)->sched_time)
+/* replace the uncertian rt_timeout with 0UL */
+#define tsk_rttimeout(t)		(0UL)
+#else /* CFS */
+#define tsk_seruntime(t)	((t)->se.sum_exec_runtime)
+#define tsk_rttimeout(t)	((t)->rt.timeout)
+#endif /* !CONFIG_SCHED_ALT */
+
 static inline struct pid *task_pid(struct task_struct *task)
 {
 	return task->thread_pid;
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 1aff00b65f3c..216fdf2fe90c 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -1,5 +1,24 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
+#ifdef CONFIG_SCHED_ALT
+
+static inline int dl_task(struct task_struct *p)
+{
+	return 0;
+}
+
+#ifdef CONFIG_SCHED_BMQ
+#define __tsk_deadline(p)	(0UL)
+#endif
+
+#ifdef CONFIG_SCHED_PDS
+#define __tsk_deadline(p)	((((u64) ((p)->prio))<<56) | (p)->deadline)
+#endif
+
+#else
+
+#define __tsk_deadline(p)	((p)->dl.deadline)
+
 /*
  * SCHED_DEADLINE tasks has negative priorities, reflecting
  * the fact that any of them has higher prio than RT and
@@ -19,6 +38,7 @@ static inline int dl_task(struct task_struct *p)
 {
 	return dl_prio(p->prio);
 }
+#endif /* CONFIG_SCHED_ALT */
 
 static inline bool dl_time_before(u64 a, u64 b)
 {
diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
index ab83d85e1183..6af9ae681116 100644
--- a/include/linux/sched/prio.h
+++ b/include/linux/sched/prio.h
@@ -18,6 +18,32 @@
 #define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
 #define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)
 
+#ifdef CONFIG_SCHED_ALT
+
+/* Undefine MAX_PRIO and DEFAULT_PRIO */
+#undef MAX_PRIO
+#undef DEFAULT_PRIO
+
+/* +/- priority levels from the base priority */
+#ifdef CONFIG_SCHED_BMQ
+#define MAX_PRIORITY_ADJ	(7)
+
+#define MIN_NORMAL_PRIO		(MAX_RT_PRIO)
+#define MAX_PRIO		(MIN_NORMAL_PRIO + NICE_WIDTH)
+#define DEFAULT_PRIO		(MIN_NORMAL_PRIO + NICE_WIDTH / 2)
+#endif
+
+#ifdef CONFIG_SCHED_PDS
+#define MAX_PRIORITY_ADJ	(0)
+
+#define MIN_NORMAL_PRIO		(128)
+#define NORMAL_PRIO_NUM		(64)
+#define MAX_PRIO		(MIN_NORMAL_PRIO + NORMAL_PRIO_NUM)
+#define DEFAULT_PRIO		(MAX_PRIO - NICE_WIDTH / 2)
+#endif
+
+#endif /* CONFIG_SCHED_ALT */
+
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 994c25640e15..8c050a59ece1 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -24,8 +24,10 @@ static inline bool task_is_realtime(struct task_struct *tsk)
 
 	if (policy == SCHED_FIFO || policy == SCHED_RR)
 		return true;
+#ifndef CONFIG_SCHED_ALT
 	if (policy == SCHED_DEADLINE)
 		return true;
+#endif
 	return false;
 }
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 63a04a65e310..b54bf39e1758 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -226,7 +226,8 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 
 #endif	/* !CONFIG_SMP */
 
-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) && \
+	!defined(CONFIG_SCHED_ALT)
 extern void rebuild_sched_domains_energy(void);
 #else
 static inline void rebuild_sched_domains_energy(void)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 252243c7783d..af8f7044c87b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -58,6 +58,7 @@ struct mq_attr;
 struct compat_stat;
 struct old_timeval32;
 struct robust_list_head;
+struct futex_waitv;
 struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
@@ -623,6 +624,11 @@ asmlinkage long sys_get_robust_list(int pid,
 asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 				    size_t len);
 
+asmlinkage long sys_futex_waitv(struct futex_waitv *waiters,
+				unsigned int nr_futexes, unsigned int flags,
+				struct __kernel_timespec __user *timeout, clockid_t clockid);
+
+
 /* kernel/hrtimer.c */
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
 			      struct __kernel_timespec __user *rmtp);
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 48d8a363319e..1bd559c69e83 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -225,7 +225,8 @@ struct tcp_sock {
 	u8	compressed_ack;
 	u8	dup_ack_counter:2,
 		tlp_retrans:1,	/* TLP is a retransmission */
-		unused:5;
+		fast_ack_mode:2, /* which fast ack mode ? */
+		unused:3;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 98d1921f02b1..17ccba2bc2ba 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -125,7 +125,6 @@ struct usb_hcd {
 #define HCD_FLAG_RH_RUNNING		5	/* root hub is running? */
 #define HCD_FLAG_DEAD			6	/* controller has died? */
 #define HCD_FLAG_INTF_AUTHORIZED	7	/* authorize interfaces? */
-#define HCD_FLAG_DEFER_RH_REGISTER	8	/* Defer roothub registration */
 
 	/* The flags can be tested using these macros; they are likely to
 	 * be slightly faster than test_bit().
@@ -136,7 +135,6 @@ struct usb_hcd {
 #define HCD_WAKEUP_PENDING(hcd)	((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING))
 #define HCD_RH_RUNNING(hcd)	((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING))
 #define HCD_DEAD(hcd)		((hcd)->flags & (1U << HCD_FLAG_DEAD))
-#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER))
 
 	/*
 	 * Specifies if interfaces are authorized by default
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 33a4240e6a6f..82213f9c4c17 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -139,6 +139,8 @@ static inline void set_rlimit_ucount_max(struct user_namespace *ns,
 
 #ifdef CONFIG_USER_NS
 
+extern int unprivileged_userns_clone;
+
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
 {
 	if (ns)
@@ -172,6 +174,8 @@ extern bool current_in_userns(const struct user_namespace *target_ns);
 struct ns_common *ns_get_owner(struct ns_common *ns);
 #else
 
+#define unprivileged_userns_clone 0
+
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
 {
 	return &init_user_ns;
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 1c5fb86d455a..4557a8b6086f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret)
 #define __NR_process_mrelease 448
 __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 450
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h
index 235e5b2facaa..417c5d89b745 100644
--- a/include/uapi/linux/futex.h
+++ b/include/uapi/linux/futex.h
@@ -22,6 +22,7 @@
 #define FUTEX_WAIT_REQUEUE_PI	11
 #define FUTEX_CMP_REQUEUE_PI	12
 #define FUTEX_LOCK_PI2		13
+#define FUTEX_WAIT_MULTIPLE	31
 
 #define FUTEX_PRIVATE_FLAG	128
 #define FUTEX_CLOCK_REALTIME	256
@@ -43,6 +44,43 @@
 #define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
 					 FUTEX_PRIVATE_FLAG)
 
+ /*
+ * Flags to specify the bit length of the futex word for futex2 syscalls.
+ * Currently, only 32 is supported.
+ */
+#define FUTEX_32		2
+
+/*
+ * Max numbers of elements in a futex_waitv array
+ */
+#define FUTEX_WAITV_MAX		128
+
+/**
+ * struct futex_waitv - A waiter for vectorized wait
+ * @val:	Expected value at uaddr
+ * @uaddr:	User address to wait on
+ * @flags:	Flags for this waiter
+ * @__reserved:	Reserved member to preserve data alignment. Should be 0.
+ */
+struct futex_waitv {
+	__u64 val;
+	__u64 uaddr;
+	__u32 flags;
+	__u32 __reserved;
+};
+
+/**
+ * struct futex_wait_block - Block of futexes to be waited for
+ * @uaddr:	User address of the futex
+ * @val:	Futex value expected by userspace
+ * @bitset:	Bitset for the optional bitmasked wakeup
+ */
+struct futex_wait_block {
+	__u32 __user *uaddr;
+	__u32 val;
+	__u32 bitset;
+};
+
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.
diff --git a/init/Kconfig b/init/Kconfig
index d19ed66aba3b..0a87e54fe954 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -112,6 +112,40 @@ config THREAD_INFO_IN_TASK
 
 menu "General setup"
 
+config ZEN_INTERACTIVE
+	bool "Tune kernel for interactivity"
+	default y
+	help
+	  Tunes the kernel for responsiveness at the cost of throughput and power usage.
+
+	  --- Block Layer ----------------------------------------
+
+	    Default scheduler.........: mq-deadline -> bfq
+
+	  --- Virtual Memory Subsystem ---------------------------
+
+	    Background-reclaim hugepages...:   no   ->   yes
+	    MG-LRU minimum cache TTL.......:   0    ->   1000 ms
+
+	  --- CFS CPU Scheduler ----------------------------------
+
+	    Scheduling latency.............:   6    ->   4    ms
+	    Minimal granularity............:   0.75 ->   0.4  ms
+	    Wakeup granularity.............:   1    ->   0.5  ms
+	    CPU migration cost.............:   0.5  ->   0.25 ms
+	    Bandwidth slice size...........:   5    ->   3    ms
+	    Task rebalancing threshold.....:  32    -> 128
+
+	  --- PDS/BMQ CPU Scheduler ------------------------------
+
+	    Scheduling timeslice...........:   4    ->   2    ms
+
+	  --- CPUFreq Settings -----------------------------------
+
+	    Ondemand sampling down factor..:   1    ->   5
+	    Ondemand default up threshold..:  80    ->  55
+	    Ondemand micro up threshold....:  95    ->  60
+
 config BROKEN
 	bool
 
@@ -819,9 +853,41 @@ config GENERIC_SCHED_CLOCK
 
 menu "Scheduler features"
 
+menuconfig SCHED_ALT
+	bool "Alternative CPU Schedulers"
+	default n
+	help
+	  This feature enable alternative CPU scheduler"
+
+if SCHED_ALT
+
+choice
+	prompt "Alternative CPU Scheduler"
+	default SCHED_PDS
+
+config SCHED_BMQ
+	bool "BMQ CPU scheduler"
+	help
+	  The BitMap Queue CPU scheduler for excellent interactivity and
+	  responsiveness on the desktop and solid scalability on normal
+	  hardware and commodity servers.
+
+config SCHED_PDS
+	bool "PDS CPU scheduler"
+	help
+	  The Priority and Deadline based Skip list multiple queue CPU
+	  scheduler for excellent interactivity and responsiveness on the
+	  desktop and solid scalability on normal hardware and commodity
+	  servers.
+
+endchoice
+
+endif
+
 config UCLAMP_TASK
 	bool "Enable utilization clamping for RT/FAIR tasks"
 	depends on CPU_FREQ_GOV_SCHEDUTIL
+	depends on !SCHED_ALT
 	help
 	  This feature enables the scheduler to track the clamped utilization
 	  of each CPU based on RUNNABLE tasks scheduled on that CPU.
@@ -907,6 +973,7 @@ config NUMA_BALANCING
 	depends on ARCH_SUPPORTS_NUMA_BALANCING
 	depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
 	depends on SMP && NUMA && MIGRATION
+	depends on !SCHED_ALT
 	help
 	  This option adds support for automatic NUMA aware memory/task placement.
 	  The mechanism is quite primitive and is based on migrating memory when
@@ -999,6 +1066,7 @@ config FAIR_GROUP_SCHED
 	depends on CGROUP_SCHED
 	default CGROUP_SCHED
 
+if !SCHED_ALT
 config CFS_BANDWIDTH
 	bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
 	depends on FAIR_GROUP_SCHED
@@ -1021,6 +1089,7 @@ config RT_GROUP_SCHED
 	  realtime bandwidth for them.
 	  See Documentation/scheduler/sched-rt-group.rst for more information.
 
+endif #!SCHED_ALT
 endif #CGROUP_SCHED
 
 config UCLAMP_TASK_GROUP
@@ -1231,6 +1300,22 @@ config USER_NS
 
 	  If unsure, say N.
 
+config USER_NS_UNPRIVILEGED
+	bool "Allow unprivileged users to create namespaces"
+	default y
+	depends on USER_NS
+	help
+	  When disabled, unprivileged users will not be able to create
+	  new namespaces. Allowing users to create their own namespaces
+	  has been part of several recent local privilege escalation
+	  exploits, so if you need user namespaces but are
+	  paranoid^Wsecurity-conscious you want to disable this.
+
+	  This setting can be overridden at runtime via the
+	  kernel.unprivileged_userns_clone sysctl.
+
+	  If unsure, say Y.
+
 config PID_NS
 	bool "PID Namespaces"
 	default y
@@ -1264,6 +1349,7 @@ config CHECKPOINT_RESTORE
 
 config SCHED_AUTOGROUP
 	bool "Automatic process group scheduling"
+	depends on !SCHED_ALT
 	select CGROUPS
 	select CGROUP_SCHED
 	select FAIR_GROUP_SCHED
@@ -1370,7 +1456,6 @@ config CC_OPTIMIZE_FOR_PERFORMANCE
 
 config CC_OPTIMIZE_FOR_PERFORMANCE_O3
 	bool "Optimize more for performance (-O3)"
-	depends on ARC
 	help
 	  Choosing this option will pass "-O3" to your compiler to optimize
 	  the kernel yet more for performance.
diff --git a/init/init_task.c b/init/init_task.c
index 2d024066e27b..49f706df0904 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -75,9 +75,15 @@ struct task_struct init_task
 	.stack		= init_stack,
 	.usage		= REFCOUNT_INIT(2),
 	.flags		= PF_KTHREAD,
+#ifdef CONFIG_SCHED_ALT
+	.prio		= DEFAULT_PRIO + MAX_PRIORITY_ADJ,
+	.static_prio	= DEFAULT_PRIO,
+	.normal_prio	= DEFAULT_PRIO + MAX_PRIORITY_ADJ,
+#else
 	.prio		= MAX_PRIO - 20,
 	.static_prio	= MAX_PRIO - 20,
 	.normal_prio	= MAX_PRIO - 20,
+#endif
 	.policy		= SCHED_NORMAL,
 	.cpus_ptr	= &init_task.cpus_mask,
 	.user_cpus_ptr	= NULL,
@@ -88,6 +94,17 @@ struct task_struct init_task
 	.restart_block	= {
 		.fn = do_no_restart_syscall,
 	},
+#ifdef CONFIG_SCHED_ALT
+	.sq_node	= LIST_HEAD_INIT(init_task.sq_node),
+#ifdef CONFIG_SCHED_BMQ
+	.boost_prio	= 0,
+	.sq_idx		= 15,
+#endif
+#ifdef CONFIG_SCHED_PDS
+	.deadline	= 0,
+#endif
+	.time_slice	= HZ,
+#else
 	.se		= {
 		.group_node 	= LIST_HEAD_INIT(init_task.se.group_node),
 	},
@@ -95,6 +112,7 @@ struct task_struct init_task
 		.run_list	= LIST_HEAD_INIT(init_task.rt.run_list),
 		.time_slice	= RR_TIMESLICE,
 	},
+#endif
 	.tasks		= LIST_HEAD_INIT(init_task.tasks),
 #ifdef CONFIG_SMP
 	.pushable_tasks	= PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 5876e30c5740..7594d0a31869 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -102,7 +102,7 @@ config PREEMPT_DYNAMIC
 
 config SCHED_CORE
 	bool "Core Scheduling for SMT"
-	depends on SCHED_SMT
+	depends on SCHED_SMT && !SCHED_ALT
 	help
 	  This option permits Core Scheduling, a means of coordinated task
 	  selection across SMT siblings. When enabled -- see
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 3213d3c8ea0a..9133d34714a3 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -664,7 +664,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	return ret;
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_ALT)
 /*
  * Helper routine for generate_sched_domains().
  * Do cpusets a, b have overlapping effective cpus_allowed masks?
@@ -1060,7 +1060,7 @@ static void rebuild_sched_domains_locked(void)
 	/* Have scheduler rebuild the domains */
 	partition_and_rebuild_sched_domains(ndoms, doms, attr);
 }
-#else /* !CONFIG_SMP */
+#else /* !CONFIG_SMP || CONFIG_SCHED_ALT */
 static void rebuild_sched_domains_locked(void)
 {
 }
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 51530d5b15a8..e542d71bb94b 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -139,7 +139,7 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	 */
 	t1 = tsk->sched_info.pcount;
 	t2 = tsk->sched_info.run_delay;
-	t3 = tsk->se.sum_exec_runtime;
+	t3 = tsk_seruntime(tsk);
 
 	d->cpu_count += t1;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index aefe7445508d..ae16f41fe7e6 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -122,7 +122,7 @@ static void __exit_signal(struct task_struct *tsk)
 			sig->curr_target = next_thread(tsk);
 	}
 
-	add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
+	add_device_randomness((const void*) &tsk_seruntime(tsk),
 			      sizeof(unsigned long long));
 
 	/*
@@ -143,7 +143,7 @@ static void __exit_signal(struct task_struct *tsk)
 	sig->inblock += task_io_get_inblock(tsk);
 	sig->oublock += task_io_get_oublock(tsk);
 	task_io_accounting_add(&sig->ioac, &tsk->ioac);
-	sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
+	sig->sum_sched_runtime += tsk_seruntime(tsk);
 	sig->nr_threads--;
 	__unhash_process(tsk, group_dead);
 	write_sequnlock(&sig->stats_lock);
diff --git a/kernel/fork.c b/kernel/fork.c
index 908ba3c93893..b4982474fb93 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -98,6 +98,10 @@
 #include <linux/io_uring.h>
 #include <linux/bpf.h>
 
+#ifdef CONFIG_USER_NS
+#include <linux/user_namespace.h>
+#endif
+
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1951,6 +1955,10 @@ static __latent_entropy struct task_struct *copy_process(
 	if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
 		return ERR_PTR(-EINVAL);
 
+	if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone)
+		if (!capable(CAP_SYS_ADMIN))
+			return ERR_PTR(-EPERM);
+
 	/*
 	 * Thread groups must share signals as well, and detached threads
 	 * can only be started up within the thread group.
@@ -3067,6 +3075,12 @@ int ksys_unshare(unsigned long unshare_flags)
 	if (unshare_flags & CLONE_NEWNS)
 		unshare_flags |= CLONE_FS;
 
+	if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) {
+		err = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto bad_unshare_out;
+	}
+
 	err = check_unshare_flags(unshare_flags);
 	if (err)
 		goto bad_unshare_out;
diff --git a/kernel/futex.c b/kernel/futex.c
index c15ad276fd15..c3f2e65afab8 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -285,6 +285,18 @@ static const struct futex_q futex_q_init = {
 	.requeue_state	= ATOMIC_INIT(Q_REQUEUE_PI_NONE),
 };
 
+/**
+ * struct futex_vector - Auxiliary struct for futex_waitv()
+ * @w: Userspace provided data
+ * @q: Kernel side data
+ *
+ * Struct used to build an array with all data need for futex_waitv()
+ */
+struct futex_vector {
+	struct futex_waitv w;
+	struct futex_q q;
+};
+
 /*
  * Hash buckets are shared by all the futex_keys that hash to the same
  * location.  Each key may have multiple futex_q structures, one for each task
@@ -4000,6 +4012,7 @@ static __always_inline bool futex_cmd_has_timeout(u32 cmd)
 	case FUTEX_LOCK_PI2:
 	case FUTEX_WAIT_BITSET:
 	case FUTEX_WAIT_REQUEUE_PI:
+	case FUTEX_WAIT_MULTIPLE:
 		return true;
 	}
 	return false;
@@ -4012,13 +4025,79 @@ futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t)
 		return -EINVAL;
 
 	*t = timespec64_to_ktime(*ts);
-	if (cmd == FUTEX_WAIT)
+	if (cmd == FUTEX_WAIT || cmd == FUTEX_WAIT_MULTIPLE)
 		*t = ktime_add_safe(ktime_get(), *t);
 	else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME))
 		*t = timens_ktime_to_host(CLOCK_MONOTONIC, *t);
 	return 0;
 }
 
+/**
+ * futex_read_wait_block - Read an array of futex_wait_block from userspace
+ * @uaddr:	Userspace address of the block
+ * @count:	Number of blocks to be read
+ *
+ * This function creates and allocate an array of futex_q (we zero it to
+ * initialize the fields) and then, for each futex_wait_block element from
+ * userspace, fill a futex_q element with proper values.
+ */
+inline struct futex_vector *futex_read_wait_block(u32 __user *uaddr, u32 count)
+{
+	unsigned int i;
+	struct futex_vector *futexv;
+	struct futex_wait_block fwb;
+	struct futex_wait_block __user *entry =
+		(struct futex_wait_block __user *)uaddr;
+
+	if (!count || count > FUTEX_WAITV_MAX)
+		return ERR_PTR(-EINVAL);
+
+	futexv = kcalloc(count, sizeof(*futexv), GFP_KERNEL);
+	if (!futexv)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < count; i++) {
+		if (copy_from_user(&fwb, &entry[i], sizeof(fwb))) {
+			kfree(futexv);
+			return ERR_PTR(-EFAULT);
+		}
+
+		futexv[i].w.flags = FUTEX_32;
+		futexv[i].w.val = fwb.val;
+		futexv[i].w.uaddr = (uintptr_t) (fwb.uaddr);
+		futexv[i].q = futex_q_init;
+	}
+
+	return futexv;
+}
+
+int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
+			struct hrtimer_sleeper *to);
+
+int futex_opcode_31(ktime_t *abs_time, u32 __user *uaddr, int count)
+{
+	int ret;
+	struct futex_vector *vs;
+	struct hrtimer_sleeper *to = NULL, timeout;
+
+	to = futex_setup_timer(abs_time, &timeout, 0, 0);
+
+	vs = futex_read_wait_block(uaddr, count);
+
+	if (IS_ERR(vs))
+		return PTR_ERR(vs);
+
+	ret = futex_wait_multiple(vs, count, abs_time ? to : NULL);
+	kfree(vs);
+
+	if (to) {
+		hrtimer_cancel(&to->timer);
+		destroy_hrtimer_on_stack(&to->timer);
+	}
+
+	return ret;
+}
+
 SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 		const struct __kernel_timespec __user *, utime,
 		u32 __user *, uaddr2, u32, val3)
@@ -4038,6 +4117,9 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 		tp = &t;
 	}
 
+	if (cmd == FUTEX_WAIT_MULTIPLE)
+		return futex_opcode_31(tp, uaddr, val);
+
 	return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
 }
 
@@ -4199,6 +4281,328 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
 }
 #endif /* CONFIG_COMPAT */
 
+/* Mask of available flags for each futex in futex_waitv list */
+#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG)
+
+/**
+ * futex_parse_waitv - Parse a waitv array from userspace
+ * @futexv:	Kernel side list of waiters to be filled
+ * @uwaitv:     Userspace list to be parsed
+ * @nr_futexes: Length of futexv
+ *
+ * Return: Error code on failure, 0 on success
+ */
+static int futex_parse_waitv(struct futex_vector *futexv,
+			     struct futex_waitv __user *uwaitv,
+			     unsigned int nr_futexes)
+{
+	struct futex_waitv aux;
+	unsigned int i;
+
+	for (i = 0; i < nr_futexes; i++) {
+		if (copy_from_user(&aux, &uwaitv[i], sizeof(aux)))
+			return -EFAULT;
+
+		if ((aux.flags & ~FUTEXV_WAITER_MASK) || aux.__reserved)
+			return -EINVAL;
+
+		if (!(aux.flags & FUTEX_32))
+			return -EINVAL;
+
+		futexv[i].w.flags = aux.flags;
+		futexv[i].w.val = aux.val;
+		futexv[i].w.uaddr = aux.uaddr;
+		futexv[i].q = futex_q_init;
+	}
+
+	return 0;
+}
+
+/**
+ * unqueue_multiple - Remove various futexes from their hash bucket
+ * @v:	   The list of futexes to unqueue
+ * @count: Number of futexes in the list
+ *
+ * Helper to unqueue a list of futexes. This can't fail.
+ *
+ * Return:
+ *  - >=0 - Index of the last futex that was awoken;
+ *  - -1  - No futex was awoken
+ */
+static int unqueue_multiple(struct futex_vector *v, int count)
+{
+	int ret = -1, i;
+
+	for (i = 0; i < count; i++) {
+		if (!unqueue_me(&v[i].q))
+			ret = i;
+	}
+
+	return ret;
+}
+
+/**
+ * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes
+ * @vs:		The futex list to wait on
+ * @count:	The size of the list
+ * @woken:	Index of the last woken futex, if any. Used to notify the
+ *		caller that it can return this index to userspace (return parameter)
+ *
+ * Prepare multiple futexes in a single step and enqueue them. This may fail if
+ * the futex list is invalid or if any futex was already awoken. On success the
+ * task is ready to interruptible sleep.
+ *
+ * Return:
+ *  -  1 - One of the futexes was woken by another thread
+ *  -  0 - Success
+ *  - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL
+ */
+static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken)
+{
+	struct futex_hash_bucket *hb;
+	bool retry = false;
+	int ret, i;
+	u32 uval;
+
+	/*
+	 * Enqueuing multiple futexes is tricky, because we need to enqueue
+	 * each futex on the list before dealing with the next one to avoid
+	 * deadlocking on the hash bucket. But, before enqueuing, we need to
+	 * make sure that current->state is TASK_INTERRUPTIBLE, so we don't
+	 * lose any wake events, which cannot be done before the get_futex_key
+	 * of the next key, because it calls get_user_pages, which can sleep.
+	 * Thus, we fetch the list of futexes keys in two steps, by first
+	 * pinning all the memory keys in the futex key, and only then we read
+	 * each key and queue the corresponding futex.
+	 *
+	 * Private futexes doesn't need to recalculate hash in retry, so skip
+	 * get_futex_key() when retrying.
+	 */
+retry:
+	for (i = 0; i < count; i++) {
+		if ((vs[i].w.flags & FUTEX_PRIVATE_FLAG) && retry)
+			continue;
+
+		ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr),
+				    !(vs[i].w.flags & FUTEX_PRIVATE_FLAG),
+				    &vs[i].q.key, FUTEX_READ);
+
+		if (unlikely(ret))
+			return ret;
+	}
+
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	for (i = 0; i < count; i++) {
+		u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr;
+		struct futex_q *q = &vs[i].q;
+		u32 val = (u32)vs[i].w.val;
+
+		hb = queue_lock(q);
+		ret = get_futex_value_locked(&uval, uaddr);
+
+		if (!ret && uval == val) {
+			/*
+			 * The bucket lock can't be held while dealing with the
+			 * next futex. Queue each futex at this moment so hb can
+			 * be unlocked.
+			 */
+			queue_me(q, hb);
+			continue;
+		}
+
+		queue_unlock(hb);
+		__set_current_state(TASK_RUNNING);
+
+		/*
+		 * Even if something went wrong, if we find out that a futex
+		 * was woken, we don't return error and return this index to
+		 * userspace
+		 */
+		*woken = unqueue_multiple(vs, i);
+		if (*woken >= 0)
+			return 1;
+
+		if (ret) {
+			/*
+			 * If we need to handle a page fault, we need to do so
+			 * without any lock and any enqueued futex (otherwise
+			 * we could lose some wakeup). So we do it here, after
+			 * undoing all the work done so far. In success, we
+			 * retry all the work.
+			 */
+			if (get_user(uval, uaddr))
+				return -EFAULT;
+
+			retry = true;
+			goto retry;
+		}
+
+		if (uval != val)
+			return -EWOULDBLOCK;
+	}
+
+	return 0;
+}
+
+/**
+ * futex_sleep_multiple - Check sleeping conditions and sleep
+ * @vs:    List of futexes to wait for
+ * @count: Length of vs
+ * @to:    Timeout
+ *
+ * Sleep if and only if the timeout hasn't expired and no futex on the list has
+ * been woken up.
+ */
+static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count,
+				 struct hrtimer_sleeper *to)
+{
+	if (to && !to->task)
+		return;
+
+	for (; count; count--, vs++) {
+		if (!READ_ONCE(vs->q.lock_ptr))
+			return;
+	}
+
+	freezable_schedule();
+}
+
+/**
+ * futex_wait_multiple - Prepare to wait on and enqueue several futexes
+ * @vs:		The list of futexes to wait on
+ * @count:	The number of objects
+ * @to:		Timeout before giving up and returning to userspace
+ *
+ * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function
+ * sleeps on a group of futexes and returns on the first futex that is
+ * wake, or after the timeout has elapsed.
+ *
+ * Return:
+ *  - >=0 - Hint to the futex that was awoken
+ *  - <0  - On error
+ */
+int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
+			struct hrtimer_sleeper *to)
+{
+	int ret, hint = 0;
+
+	if (to)
+		hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS);
+
+	while (1) {
+		ret = futex_wait_multiple_setup(vs, count, &hint);
+		if (ret) {
+			if (ret > 0) {
+				/* A futex was woken during setup */
+				ret = hint;
+			}
+			return ret;
+		}
+
+		futex_sleep_multiple(vs, count, to);
+
+		__set_current_state(TASK_RUNNING);
+
+		ret = unqueue_multiple(vs, count);
+		if (ret >= 0)
+			return ret;
+
+		if (to && !to->task)
+			return -ETIMEDOUT;
+		else if (signal_pending(current))
+			return -ERESTARTSYS;
+		/*
+		 * The final case is a spurious wakeup, for
+		 * which just retry.
+		 */
+	}
+}
+/* Mask of available flags for each futex in futex_waitv list */
+#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG)
+
+/**
+ * sys_futex_waitv - Wait on a list of futexes
+ * @waiters:    List of futexes to wait on
+ * @nr_futexes: Length of futexv
+ * @flags:      Flag for timeout (monotonic/realtime)
+ * @timeout:	Optional absolute timeout.
+ * @clockid:	Clock to be used for the timeout, realtime or monotonic.
+ *
+ * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes
+ * if a futex_wake() is performed at any uaddr. The syscall returns immediately
+ * if any waiter has *uaddr != val. *timeout is an optional timeout value for
+ * the operation. Each waiter has individual flags. The `flags` argument for
+ * the syscall should be used solely for specifying the timeout as realtime, if
+ * needed. Flags for private futexes, sizes, etc. should be used on the
+ * individual flags of each waiter.
+ *
+ * Returns the array index of one of the woken futexes. No further information
+ * is provided: any number of other futexes may also have been woken by the
+ * same event, and if more than one futex was woken, the retrned index may
+ * refer to any one of them. (It is not necessaryily the futex with the
+ * smallest index, nor the one most recently woken, nor...)
+ */
+
+SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters,
+		unsigned int, nr_futexes, unsigned int, flags,
+		struct __kernel_timespec __user *, timeout, clockid_t, clockid)
+{
+	struct hrtimer_sleeper to;
+	struct futex_vector *futexv;
+	struct timespec64 ts;
+	ktime_t time;
+	int ret;
+
+	/* This syscall supports no flags for now */
+	if (flags)
+		return -EINVAL;
+
+	if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters)
+		return -EINVAL;
+
+	if (timeout) {
+		int flag_clkid = 0, flag_init = 0;
+
+		if (clockid == CLOCK_REALTIME) {
+			flag_clkid = FLAGS_CLOCKRT;
+			flag_init = FUTEX_CLOCK_REALTIME;
+		}
+
+		if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC)
+			return -EINVAL;
+
+		if (get_timespec64(&ts, timeout))
+			return -EFAULT;
+
+		/*
+		 * Since there's no opcode for futex_waitv, use
+		 * FUTEX_WAIT_BITSET that uses absolute timeout as well
+		 */
+		ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time);
+		if (ret)
+			return ret;
+
+		futex_setup_timer(&time, &to, flag_clkid, 0);
+	}
+
+	futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL);
+	if (!futexv)
+		return -ENOMEM;
+
+	ret = futex_parse_waitv(futexv, waiters, nr_futexes);
+	if (!ret)
+		ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL);
+
+	if (timeout) {
+		hrtimer_cancel(&to.timer);
+		destroy_hrtimer_on_stack(&to.timer);
+	}
+
+	kfree(futexv);
+	return ret;
+}
+
 #ifdef CONFIG_COMPAT_32BIT_TIME
 SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
 		const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
@@ -4217,6 +4621,9 @@ SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
 		tp = &t;
 	}
 
+	if (cmd == FUTEX_WAIT_MULTIPLE)
+		return futex_opcode_31(tp, uaddr, val);
+
 	return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
 }
 #endif /* CONFIG_COMPAT_32BIT_TIME */
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 00d58588ea95..79abf976bbe1 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -114,6 +114,23 @@ config GENERIC_IRQ_RESERVATION_MODE
 config IRQ_FORCED_THREADING
        bool
 
+config FORCE_IRQ_THREADING
+	bool "Make IRQ threading compulsory"
+	depends on IRQ_FORCED_THREADING
+	default n
+	help
+
+	  Make IRQ threading mandatory for any IRQ handlers that support it
+	  instead of being optional and requiring the threadirqs kernel
+	  parameter. Instead they can be optionally disabled with the
+	  nothreadirqs kernel parameter.
+
+	  Enabling this may make some architectures not boot with runqueue
+	  sharing and MuQSS.
+
+	  Enable if you are building for a desktop or low latency system,
+	  otherwise say N.
+
 config SPARSE_IRQ
 	bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ
 	help
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0c3c26fb054f..272ee36dc647 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -25,7 +25,18 @@
 #include "internals.h"
 
 #if defined(CONFIG_IRQ_FORCED_THREADING) && !defined(CONFIG_PREEMPT_RT)
+#ifdef CONFIG_FORCE_IRQ_THREADING
+DEFINE_STATIC_KEY_TRUE(force_irqthreads_key);
+#else
 DEFINE_STATIC_KEY_FALSE(force_irqthreads_key);
+#endif
+
+static int __init setup_noforced_irqthreads(char *arg)
+{
+	static_branch_disable(&force_irqthreads_key);
+	return 0;
+}
+early_param("nothreadirqs", setup_noforced_irqthreads);
 
 static int __init setup_forced_irqthreads(char *arg)
 {
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 291b857a6e20..f3480cdb7497 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -307,7 +307,11 @@ static bool klp_try_switch_task(struct task_struct *task)
 	 */
 	rq = task_rq_lock(task, &flags);
 
+#ifdef	CONFIG_SCHED_ALT
+	if (task_running(task) && task != current) {
+#else
 	if (task_running(rq, task) && task != current) {
+#endif
 		snprintf(err_buf, STACK_ERR_BUF_SIZE,
 			 "%s: %s:%d is running\n", __func__, task->comm,
 			 task->pid);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index ea5a701ab240..68b9d6e09a6b 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -298,21 +298,25 @@ static __always_inline void
 waiter_update_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
 {
 	waiter->prio = __waiter_prio(task);
-	waiter->deadline = task->dl.deadline;
+	waiter->deadline = __tsk_deadline(task);
 }
 
 /*
  * Only use with rt_mutex_waiter_{less,equal}()
  */
 #define task_to_waiter(p)	\
-	&(struct rt_mutex_waiter){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
+	&(struct rt_mutex_waiter){ .prio = __waiter_prio(p), .deadline = __tsk_deadline(p) }
 
 static __always_inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 						struct rt_mutex_waiter *right)
 {
+#ifdef CONFIG_SCHED_PDS
+	return (left->deadline < right->deadline);
+#else
 	if (left->prio < right->prio)
 		return 1;
 
+#ifndef CONFIG_SCHED_BMQ
 	/*
 	 * If both waiters have dl_prio(), we check the deadlines of the
 	 * associated tasks.
@@ -321,16 +325,22 @@ static __always_inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 	 */
 	if (dl_prio(left->prio))
 		return dl_time_before(left->deadline, right->deadline);
+#endif
 
 	return 0;
+#endif
 }
 
 static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
 						 struct rt_mutex_waiter *right)
 {
+#ifdef CONFIG_SCHED_PDS
+	return (left->deadline == right->deadline);
+#else
 	if (left->prio != right->prio)
 		return 0;
 
+#ifndef CONFIG_SCHED_BMQ
 	/*
 	 * If both waiters have dl_prio(), we check the deadlines of the
 	 * associated tasks.
@@ -339,8 +349,10 @@ static __always_inline int rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
 	 */
 	if (dl_prio(left->prio))
 		return left->deadline == right->deadline;
+#endif
 
 	return 1;
+#endif
 }
 
 static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 978fcfca5871..0425ee149b4d 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -22,14 +22,21 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o loadavg.o clock.o cputime.o
-obj-y += idle.o fair.o rt.o deadline.o
-obj-y += wait.o wait_bit.o swait.o completion.o
-
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
+ifdef CONFIG_SCHED_ALT
+obj-y += alt_core.o
+obj-$(CONFIG_SCHED_DEBUG) += alt_debug.o
+else
+obj-y += core.o
+obj-y += fair.o rt.o deadline.o
+obj-$(CONFIG_SMP) += cpudeadline.o stop_task.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
-obj-$(CONFIG_SCHEDSTATS) += stats.o
+endif
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-y += loadavg.o clock.o cputime.o
+obj-y += idle.o
+obj-y += wait.o wait_bit.o swait.o completion.o
+obj-$(CONFIG_SMP) += cpupri.o pelt.o topology.o
+obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
 obj-$(CONFIG_CPU_FREQ) += cpufreq.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 85be684687b0..dd689ecd06cb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -75,7 +75,11 @@ __read_mostly int sysctl_resched_latency_warn_once = 1;
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
  */
+#ifdef CONFIG_ZEN_INTERACTIVE
+const_debug unsigned int sysctl_sched_nr_migrate = 128;
+#else
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
+#endif
 
 /*
  * period over which we measure -rt task CPU usage in us.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 7f6bb37d3a2f..5aaa1b4d54a8 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -167,9 +167,14 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);
 
 	sg_cpu->max = max;
+#ifndef CONFIG_SCHED_ALT
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
 	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(rq), max,
 					  FREQUENCY_UTIL, NULL);
+#else
+	sg_cpu->bw_dl = 0;
+	sg_cpu->util = rq_load_util(rq, max);
+#endif /* CONFIG_SCHED_ALT */
 }
 
 /**
@@ -313,8 +318,10 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
+#ifndef CONFIG_SCHED_ALT
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
 		sg_cpu->sg_policy->limits_changed = true;
+#endif
 }
 
 static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -608,6 +615,7 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
 	}
 
 	ret = sched_setattr_nocheck(thread, &attr);
+
 	if (ret) {
 		kthread_stop(thread);
 		pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
@@ -840,7 +848,9 @@ cpufreq_governor_init(schedutil_gov);
 #ifdef CONFIG_ENERGY_MODEL
 static void rebuild_sd_workfn(struct work_struct *work)
 {
+#ifndef CONFIG_SCHED_ALT
 	rebuild_sched_domains_energy();
+#endif /* CONFIG_SCHED_ALT */
 }
 static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 042a6dbce8f3..fb082e6c7b3c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -123,7 +123,7 @@ void account_user_time(struct task_struct *p, u64 cputime)
 	p->utime += cputime;
 	account_group_user_time(p, cputime);
 
-	index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+  index = task_running_nice(p) ? CPUTIME_NICE : CPUTIME_USER;
 
 	/* Add user time to cpustat. */
 	task_group_account_field(p, index, cputime);
@@ -147,7 +147,7 @@ void account_guest_time(struct task_struct *p, u64 cputime)
 	p->gtime += cputime;
 
 	/* Add guest time to cpustat. */
-	if (task_nice(p) > 0) {
+	if (task_running_nice(p)) {
 		task_group_account_field(p, CPUTIME_NICE, cputime);
 		cpustat[CPUTIME_GUEST_NICE] += cputime;
 	} else {
@@ -270,7 +270,7 @@ static inline u64 account_other_time(u64 max)
 #ifdef CONFIG_64BIT
 static inline u64 read_sum_exec_runtime(struct task_struct *t)
 {
-	return t->se.sum_exec_runtime;
+	return tsk_seruntime(t);
 }
 #else
 static u64 read_sum_exec_runtime(struct task_struct *t)
@@ -280,7 +280,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t)
 	struct rq *rq;
 
 	rq = task_rq_lock(t, &rf);
-	ns = t->se.sum_exec_runtime;
+	ns = tsk_seruntime(t);
 	task_rq_unlock(rq, t, &rf);
 
 	return ns;
@@ -612,7 +612,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 {
 	struct task_cputime cputime = {
-		.sum_exec_runtime = p->se.sum_exec_runtime,
+		.sum_exec_runtime = tsk_seruntime(p),
 	};
 
 	task_cputime(p, &cputime.utime, &cputime.stime);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 34c5ff3a0669..f42aa1fa2d18 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -8,6 +8,7 @@
  */
 #include "sched.h"
 
+#ifndef CONFIG_SCHED_ALT
 /*
  * This allows printing both to /proc/sched_debug and
  * to the console
@@ -216,6 +217,7 @@ static const struct file_operations sched_scaling_fops = {
 };
 
 #endif /* SMP */
+#endif /* !CONFIG_SCHED_ALT */
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
@@ -279,6 +281,7 @@ static const struct file_operations sched_dynamic_fops = {
 
 #endif /* CONFIG_PREEMPT_DYNAMIC */
 
+#ifndef CONFIG_SCHED_ALT
 __read_mostly bool sched_debug_verbose;
 
 static const struct seq_operations sched_debug_sops;
@@ -294,6 +297,7 @@ static const struct file_operations sched_debug_fops = {
 	.llseek		= seq_lseek,
 	.release	= seq_release,
 };
+#endif /* !CONFIG_SCHED_ALT */
 
 static struct dentry *debugfs_sched;
 
@@ -303,12 +307,15 @@ static __init int sched_init_debug(void)
 
 	debugfs_sched = debugfs_create_dir("sched", NULL);
 
+#ifndef CONFIG_SCHED_ALT
 	debugfs_create_file("features", 0644, debugfs_sched, NULL, &sched_feat_fops);
 	debugfs_create_bool("verbose", 0644, debugfs_sched, &sched_debug_verbose);
+#endif /* !CONFIG_SCHED_ALT */
 #ifdef CONFIG_PREEMPT_DYNAMIC
 	debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
 #endif
 
+#ifndef CONFIG_SCHED_ALT
 	debugfs_create_u32("latency_ns", 0644, debugfs_sched, &sysctl_sched_latency);
 	debugfs_create_u32("min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_min_granularity);
 	debugfs_create_u32("wakeup_granularity_ns", 0644, debugfs_sched, &sysctl_sched_wakeup_granularity);
@@ -336,11 +343,13 @@ static __init int sched_init_debug(void)
 #endif
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
+#endif /* !CONFIG_SCHED_ALT */
 
 	return 0;
 }
 late_initcall(sched_init_debug);
 
+#ifndef CONFIG_SCHED_ALT
 #ifdef CONFIG_SMP
 
 static cpumask_var_t		sd_sysctl_cpus;
@@ -1053,6 +1062,7 @@ void proc_sched_set_task(struct task_struct *p)
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 }
+#endif /* !CONFIG_SCHED_ALT */
 
 void resched_latency_warn(int cpu, u64 latency)
 {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a853e4e9e3c3..17f6315e57ad 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -35,8 +35,13 @@
  *
  * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  */
+#ifdef CONFIG_ZEN_INTERACTIVE
+unsigned int sysctl_sched_latency			= 4000000ULL;
+static unsigned int normalized_sysctl_sched_latency	= 4000000ULL;
+#else
 unsigned int sysctl_sched_latency			= 6000000ULL;
 static unsigned int normalized_sysctl_sched_latency	= 6000000ULL;
+#endif
 
 /*
  * The initial- and re-scaling of tunables is configurable
@@ -56,13 +61,22 @@ unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
  *
  * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
+#ifdef CONFIG_ZEN_INTERACTIVE
+unsigned int sysctl_sched_min_granularity			= 400000ULL;
+static unsigned int normalized_sysctl_sched_min_granularity	= 400000ULL;
+#else
 unsigned int sysctl_sched_min_granularity			= 750000ULL;
 static unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
+#endif
 
 /*
  * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
  */
+#ifdef CONFIG_ZEN_INTERACTIVE
+static unsigned int sched_nr_latency = 10;
+#else
 static unsigned int sched_nr_latency = 8;
+#endif
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -79,10 +93,19 @@ unsigned int sysctl_sched_child_runs_first __read_mostly;
  *
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
+#ifdef CONFIG_ZEN_INTERACTIVE
+unsigned int sysctl_sched_wakeup_granularity			= 500000UL;
+static unsigned int normalized_sysctl_sched_wakeup_granularity	= 500000UL;
+#else
 unsigned int sysctl_sched_wakeup_granularity			= 1000000UL;
 static unsigned int normalized_sysctl_sched_wakeup_granularity	= 1000000UL;
+#endif
 
+#ifdef CONFIG_ZEN_INTERACTIVE
+const_debug unsigned int sysctl_sched_migration_cost	= 250000UL;
+#else
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
+#endif
 
 int sched_thermal_decay_shift;
 static int __init setup_sched_thermal_decay_shift(char *str)
@@ -133,8 +156,12 @@ int __weak arch_asym_cpu_priority(int cpu)
  *
  * (default: 5 msec, units: microseconds)
  */
+#ifdef CONFIG_ZEN_INTERACTIVE
+unsigned int sysctl_sched_cfs_bandwidth_slice		= 3000UL;
+#else
 unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
 #endif
+#endif
 
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 499a3e286cd0..32ba8aed701f 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -403,6 +403,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 		do_idle();
 }
 
+#ifndef CONFIG_SCHED_ALT
 /*
  * idle-task scheduling class.
  */
@@ -525,3 +526,4 @@ DEFINE_SCHED_CLASS(idle) = {
 	.switched_to		= switched_to_idle,
 	.update_curr		= update_curr_idle,
 };
+#endif
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a554e3bbab2b..3e56f5e6ff5c 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -270,6 +270,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load)
 	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
 }
 
+#ifndef CONFIG_SCHED_ALT
 /*
  * sched_entity:
  *
@@ -387,8 +388,9 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 
 	return 0;
 }
+#endif
 
-#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+#if defined(CONFIG_SCHED_THERMAL_PRESSURE) && !defined(CONFIG_SCHED_ALT)
 /*
  * thermal:
  *
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 4ff2ed4f8fa1..226eeed61318 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -1,13 +1,15 @@
 #ifdef CONFIG_SMP
 #include "sched-pelt.h"
 
+#ifndef CONFIG_SCHED_ALT
 int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
 int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
 int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+#endif
 
-#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+#if defined(CONFIG_SCHED_THERMAL_PRESSURE) && !defined(CONFIG_SCHED_ALT)
 int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);
 
 static inline u64 thermal_load_avg(struct rq *rq)
@@ -44,6 +46,7 @@ static inline u32 get_pelt_divider(struct sched_avg *avg)
 	return PELT_MIN_DIVIDER + avg->period_contrib;
 }
 
+#ifndef CONFIG_SCHED_ALT
 static inline void cfs_se_util_change(struct sched_avg *avg)
 {
 	unsigned int enqueued;
@@ -155,9 +158,11 @@ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
 	return rq_clock_pelt(rq_of(cfs_rq));
 }
 #endif
+#endif /* CONFIG_SCHED_ALT */
 
 #else
 
+#ifndef CONFIG_SCHED_ALT
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
@@ -175,6 +180,7 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 {
 	return 0;
 }
+#endif
 
 static inline int
 update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e49902898253..5bf1ea5b65cf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,10 @@
 /*
  * Scheduler internal types and methods:
  */
+#ifdef CONFIG_SCHED_ALT
+#include "alt_sched.h"
+#else
+
 #include <linux/sched.h>
 
 #include <linux/sched/autogroup.h>
@@ -3088,3 +3092,8 @@ extern int sched_dynamic_mode(const char *str);
 extern void sched_dynamic_update(int mode);
 #endif
 
+static inline int task_running_nice(struct task_struct *p)
+{
+	return (task_nice(p) > 0);
+}
+#endif /* !CONFIG_SCHED_ALT */
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 3f93fc3b5648..528b71e144e9 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -22,8 +22,10 @@ static int show_schedstat(struct seq_file *seq, void *v)
 	} else {
 		struct rq *rq;
 #ifdef CONFIG_SMP
+#ifndef CONFIG_SCHED_ALT
 		struct sched_domain *sd;
 		int dcount = 0;
+#endif
 #endif
 		cpu = (unsigned long)(v - 2);
 		rq = cpu_rq(cpu);
@@ -40,6 +42,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 
 #ifdef CONFIG_SMP
+#ifndef CONFIG_SCHED_ALT
 		/* domain-specific stats */
 		rcu_read_lock();
 		for_each_domain(cpu, sd) {
@@ -68,6 +71,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 			    sd->ttwu_move_balance);
 		}
 		rcu_read_unlock();
+#endif
 #endif
 	}
 	return 0;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 4e8698e62f07..36c61551252e 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -4,6 +4,7 @@
  */
 #include "sched.h"
 
+#ifndef CONFIG_SCHED_ALT
 DEFINE_MUTEX(sched_domains_mutex);
 
 /* Protected by sched_domains_mutex: */
@@ -1382,8 +1383,10 @@ static void asym_cpu_capacity_scan(void)
  */
 
 static int default_relax_domain_level = -1;
+#endif /* CONFIG_SCHED_ALT */
 int sched_domain_level_max;
 
+#ifndef CONFIG_SCHED_ALT
 static int __init setup_relax_domain_level(char *str)
 {
 	if (kstrtoint(str, 0, &default_relax_domain_level))
@@ -1619,6 +1622,7 @@ sd_init(struct sched_domain_topology_level *tl,
 
 	return sd;
 }
+#endif /* CONFIG_SCHED_ALT */
 
 /*
  * Topology list, bottom-up.
@@ -1648,6 +1652,7 @@ void set_sched_topology(struct sched_domain_topology_level *tl)
 	sched_domain_topology = tl;
 }
 
+#ifndef CONFIG_SCHED_ALT
 #ifdef CONFIG_NUMA
 
 static const struct cpumask *sd_numa_mask(int cpu)
@@ -2516,3 +2521,17 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
 	mutex_unlock(&sched_domains_mutex);
 }
+#else /* CONFIG_SCHED_ALT */
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+			     struct sched_domain_attr *dattr_new)
+{}
+
+#ifdef CONFIG_NUMA
+int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
+
+int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
+{
+	return best_mask_cpu(cpu, cpus);
+}
+#endif /* CONFIG_NUMA */
+#endif
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 126380696f9c..2234b6c710a4 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -150,6 +150,7 @@ COND_SYSCALL(set_robust_list);
 COND_SYSCALL_COMPAT(set_robust_list);
 COND_SYSCALL(get_robust_list);
 COND_SYSCALL_COMPAT(get_robust_list);
+COND_SYSCALL(futex_waitv);
 
 /* kernel/hrtimer.c */
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 23c08bf3db58..8d1de94cf087 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -106,6 +106,15 @@
 #include <linux/nmi.h>
 #endif
 
+#ifdef CONFIG_USER_NS
+#include <linux/user_namespace.h>
+#endif
+
+#ifdef CONFIG_SCHED_ALT
+static int __maybe_unused zero = 0;
+extern int sched_yield_type;
+#endif
+
 #if defined(CONFIG_SYSCTL)
 
 /* Constants used for minimum and  maximum */
@@ -1775,6 +1784,24 @@ int proc_do_static_key(struct ctl_table *table, int write,
 }
 
 static struct ctl_table kern_table[] = {
+#ifdef CONFIG_SCHED_ALT
+/* In ALT, only supported "sched_schedstats" */
+#ifdef CONFIG_SCHED_DEBUG
+#ifdef CONFIG_SMP
+#ifdef CONFIG_SCHEDSTATS
+	{
+		.procname	= "sched_schedstats",
+		.data		= NULL,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_schedstats,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif /* CONFIG_SCHEDSTATS */
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_SCHED_DEBUG */
+#else  /* !CONFIG_SCHED_ALT */
 	{
 		.procname	= "sched_child_runs_first",
 		.data		= &sysctl_sched_child_runs_first,
@@ -1905,6 +1932,7 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
+#endif /* !CONFIG_SCHED_ALT */
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname	= "prove_locking",
@@ -1953,6 +1981,15 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_USER_NS
+	{
+		.procname	= "unprivileged_userns_clone",
+		.data		= &unprivileged_userns_clone,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#endif
 #ifdef CONFIG_PROC_SYSCTL
 	{
 		.procname	= "tainted",
@@ -2481,6 +2518,17 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_SCHED_ALT
+	{
+		.procname	= "yield_type",
+		.data		= &sched_yield_type,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &two,
+	},
+#endif
 #if defined(CONFIG_S390) && defined(CONFIG_SMP)
 	{
 		.procname	= "spin_retry",
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 23af5eca11b1..792f94ce4d80 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2088,8 +2088,10 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	int ret = 0;
 	u64 slack;
 
+#ifndef CONFIG_SCHED_ALT
 	slack = current->timer_slack_ns;
 	if (dl_task(current) || rt_task(current))
+#endif
 		slack = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clockid, mode);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 96b4e7810426..83457e8bb5d2 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -216,7 +216,7 @@ static void task_sample_cputime(struct task_struct *p, u64 *samples)
 	u64 stime, utime;
 
 	task_cputime(p, &utime, &stime);
-	store_samples(samples, stime, utime, p->se.sum_exec_runtime);
+	store_samples(samples, stime, utime, tsk_seruntime(p));
 }
 
 static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
@@ -859,6 +859,7 @@ static void collect_posix_cputimers(struct posix_cputimers *pct, u64 *samples,
 	}
 }
 
+#ifndef CONFIG_SCHED_ALT
 static inline void check_dl_overrun(struct task_struct *tsk)
 {
 	if (tsk->dl.dl_overrun) {
@@ -866,6 +867,7 @@ static inline void check_dl_overrun(struct task_struct *tsk)
 		__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
 	}
 }
+#endif
 
 static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
 {
@@ -893,8 +895,10 @@ static void check_thread_timers(struct task_struct *tsk,
 	u64 samples[CPUCLOCK_MAX];
 	unsigned long soft;
 
+#ifndef CONFIG_SCHED_ALT
 	if (dl_task(tsk))
 		check_dl_overrun(tsk);
+#endif
 
 	if (expiry_cache_is_inactive(pct))
 		return;
@@ -908,7 +912,7 @@ static void check_thread_timers(struct task_struct *tsk,
 	soft = task_rlimit(tsk, RLIMIT_RTTIME);
 	if (soft != RLIM_INFINITY) {
 		/* Task RT timeout is accounted in jiffies. RTTIME is usec */
-		unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ);
+		unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ);
 		unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
 
 		/* At the hard limit, send SIGKILL. No further action. */
@@ -1144,8 +1148,10 @@ static inline bool fastpath_timer_check(struct task_struct *tsk)
 			return true;
 	}
 
+#ifndef CONFIG_SCHED_ALT
 	if (dl_task(tsk) && tsk->dl.dl_overrun)
 		return true;
+#endif
 
 	return false;
 }
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index adf7ef194005..11c8f36e281b 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1052,10 +1052,15 @@ static int trace_wakeup_test_thread(void *data)
 {
 	/* Make this a -deadline thread */
 	static const struct sched_attr attr = {
+#ifdef CONFIG_SCHED_ALT
+		/* No deadline on BMQ/PDS, use RR */
+		.sched_policy = SCHED_RR,
+#else
 		.sched_policy = SCHED_DEADLINE,
 		.sched_runtime = 100000ULL,
 		.sched_deadline = 10000000ULL,
 		.sched_period = 10000000ULL
+#endif
 	};
 	struct wakeup_test_data *x = data;
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 5481ba44a8d6..423ab2563ad7 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -21,6 +21,13 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 
+/* sysctl */
+#ifdef CONFIG_USER_NS_UNPRIVILEGED
+int unprivileged_userns_clone = 1;
+#else
+int unprivileged_userns_clone;
+#endif
+
 static struct kmem_cache *user_ns_cachep __read_mostly;
 static DEFINE_MUTEX(userns_state_mutex);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 07941a1540cb..e0ecd596521e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -54,7 +54,11 @@ unsigned long transparent_hugepage_flags __read_mostly =
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
 	(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
 #endif
+#ifdef CONFIG_ZEN_INTERACTIVE
+	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG)|
+#else
 	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)|
+#endif
 	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
 	(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
 
diff --git a/mm/internal.h b/mm/internal.h
index cf3cb933eba3..77b3bce68329 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -202,6 +202,7 @@ extern void prep_compound_page(struct page *page, unsigned int order);
 extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);
 extern int user_min_free_kbytes;
+extern atomic_long_t kswapd_waiters;
 
 extern void free_unref_page(struct page *page, unsigned int order);
 extern void free_unref_page_list(struct list_head *list);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a71722b4e464..f14e3d9b75d6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -118,6 +118,8 @@ typedef int __bitwise fpi_t;
  */
 #define FPI_SKIP_KASAN_POISON	((__force fpi_t)BIT(2))
 
+atomic_long_t kswapd_waiters = ATOMIC_LONG_INIT(0);
+
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
 #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
@@ -338,7 +340,7 @@ compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = {
 
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
-int watermark_boost_factor __read_mostly = 15000;
+int watermark_boost_factor __read_mostly;
 int watermark_scale_factor = 10;
 
 static unsigned long nr_kernel_pages __initdata;
@@ -4914,6 +4916,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned int cpuset_mems_cookie;
 	unsigned int zonelist_iter_cookie;
 	int reserve_flags;
+	bool woke_kswapd = false;
 
 	/*
 	 * We also sanity check to catch abuse of atomic reserves being used by
@@ -4948,8 +4951,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	if (!ac->preferred_zoneref->zone)
 		goto nopage;
 
-	if (alloc_flags & ALLOC_KSWAPD)
+	if (alloc_flags & ALLOC_KSWAPD) {
+		if (!woke_kswapd) {
+			atomic_long_inc(&kswapd_waiters);
+			woke_kswapd = true;
+		}
 		wake_all_kswapds(order, gfp_mask, ac);
+	}
 
 	/*
 	 * The adjusted alloc_flags might result in immediate success, so try
@@ -5162,9 +5170,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		goto retry;
 	}
 fail:
-	warn_alloc(gfp_mask, ac->nodemask,
-			"page allocation failure: order:%u", order);
 got_pg:
+	if (woke_kswapd)
+		atomic_long_dec(&kswapd_waiters);
+	if (!page)
+		warn_alloc(gfp_mask, ac->nodemask,
+				"page allocation failure: order:%u", order);
 	return page;
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 74296c2d1fed..0d7a5a61b286 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4082,7 +4082,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
 		__fs_reclaim_release(_THIS_IP_);
 		ret = try_to_freeze();
 		__fs_reclaim_acquire(_THIS_IP_);
-		if (ret || kthread_should_stop())
+		if (ret || kthread_should_stop() ||
+		    !atomic_long_read(&kswapd_waiters))
 			break;
 
 		/*
diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
index 6a2a04d92f42..85e1d2e8c368 100755
--- a/scripts/mkcompile_h
+++ b/scripts/mkcompile_h
@@ -39,8 +39,8 @@ else
 fi
 
 UTS_VERSION="#$VERSION"
-CONFIG_FLAGS=""
-if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi
+CONFIG_FLAGS="ZEN"
+if [ -n "$SMP" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS SMP"; fi
 if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi
 if [ -n "$PREEMPT_RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT_RT"; fi