Linux-libre 4.3.2-gnu

3 files changed, 109 insertions, 36 deletions

diff --git a/init/Kconfig b/init/Kconfig
index a7a100c2c..581fad113 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -38,16 +38,43 @@ config PCK_INTERACTIVE
 	    Mem dirty before bg writeback..:  10 %  -> 128 MiB
 	    Mem dirty before sync writeback:  20 %  -> 256 MiB
 
-	  --- CPU Scheduler ---
+	  --- CPU Scheduler (CFS) ---
 	    Scheduling latency.............:   6    ->   3    ms
 	    Minimal granularity............:   0.75 ->   0.3  ms
 	    Wakeup granularity.............:   1    ->   0.5  ms
 	    CPU migration cost.............:   0.5  ->   0.25 ms
 	    Bandwidth slice size...........:   5    ->   3    ms
 
+	  --- CPU Scheduler (BFS) ---
+	    Scheduling interval............:   6    ->   3    ms
+	    ISO task max realtime use......:  70 %  ->  25 %
+
 	  --- CPU Frequency Scaling ---
 	    Ondemand down scaling factor...:   1    ->  10
 
+config SCHED_BFS
+	bool "BFS cpu scheduler"
+	default n
+	help
+	  The Brain Fuck CPU Scheduler for excellent interactivity and
+	  responsiveness on the desktop and solid scalability on normal
+          hardware and commodity servers. Not recommended for 4096 CPUs.
+
+	  Currently incompatible with the Group CPU scheduler, and RCU TORTURE
+          TEST so these options are disabled.
+
+config SCHED_BFS_AUTOISO
+	bool "Automatically use SCHED_ISO policy for X"
+	depends on SCHED_BFS
+	default n
+	help
+	  Selecting this option will automatically use the SCHED_ISO scheduling
+	  policy for X, resulting in an interactivity boost. This *may* cause
+	  things like skipping sound on audio applications that are not run
+	  as SCHED_ISO.
+
+	  Tasks (including X) can be run as sched_iso manually using schedtool.
+
 config BROKEN
 	bool
 
@@ -373,7 +400,7 @@ choice
 # Kind of a stub config for the pure tick based cputime accounting
 config TICK_CPU_ACCOUNTING
 	bool "Simple tick based cputime accounting"
-	depends on !S390 && !NO_HZ_FULL
+	depends on !S390 && !NO_HZ_FULL && !SCHED_BFS
 	help
 	  This is the basic tick based cputime accounting that maintains
 	  statistics about user, system and idle time spent on per jiffies
@@ -398,6 +425,7 @@ config VIRT_CPU_ACCOUNTING_GEN
 	bool "Full dynticks CPU time accounting"
 	depends on HAVE_CONTEXT_TRACKING
 	depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
+	depends on !SCHED_BFS
 	select VIRT_CPU_ACCOUNTING
 	select CONTEXT_TRACKING
 	help
@@ -571,15 +599,6 @@ config RCU_STALL_COMMON
 config CONTEXT_TRACKING
        bool
 
-config RCU_USER_QS
-	bool
-	help
-	  This option sets hooks on kernel / userspace boundaries and
-	  puts RCU in extended quiescent state when the CPU runs in
-	  userspace. It means that when a CPU runs in userspace, it is
-	  excluded from the global RCU state machine and thus doesn't
-	  try to keep the timer tick on for RCU.
-
 config CONTEXT_TRACKING_FORCE
 	bool "Force context tracking"
 	depends on CONTEXT_TRACKING
@@ -740,6 +759,8 @@ config RCU_BOOST_DELAY
 config RCU_NOCB_CPU
 	bool "Offload RCU callback processing from boot-selected CPUs"
 	depends on TREE_RCU || PREEMPT_RCU
+	depends on RCU_EXPERT || NO_HZ_FULL
+	depends on !SCHED_BFS
 	default n
 	help
 	  Use this option to reduce OS jitter for aggressive HPC or
@@ -924,6 +945,16 @@ config ARCH_SUPPORTS_NUMA_BALANCING
 	bool
 
 #
+# For architectures that prefer to flush all TLBs after a number of pages
+# are unmapped instead of sending one IPI per page to flush. The architecture
+# must provide guarantees on what happens if a clean TLB cache entry is
+# written after the unmap. Details are in mm/rmap.c near the check for
+# should_defer_flush. The architecture should also consider if the full flush
+# and the refill costs are offset by the savings of sending fewer IPIs.
+config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	bool
+
+#
 # For architectures that know their GCC __int128 support is sound
 #
 config ARCH_SUPPORTS_INT128
@@ -940,6 +971,7 @@ config NUMA_BALANCING
 	depends on ARCH_SUPPORTS_NUMA_BALANCING
 	depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
 	depends on SMP && NUMA && MIGRATION
+	depends on !SCHED_BFS
 	help
 	  This option adds support for automatic NUMA aware memory/task placement.
 	  The mechanism is quite primitive and is based on migrating memory when
@@ -958,7 +990,6 @@ config NUMA_BALANCING_DEFAULT_ENABLED
 menuconfig CGROUPS
 	bool "Control Group support"
 	select KERNFS
-	select PERCPU_RWSEM
 	help
 	  This option adds support for grouping sets of processes together, for
 	  use with process control subsystems such as Cpusets, CFS, memory
@@ -988,6 +1019,22 @@ config CGROUP_FREEZER
 	  Provides a way to freeze and unfreeze all tasks in a
 	  cgroup.
 
+config CGROUP_PIDS
+	bool "PIDs cgroup subsystem"
+	help
+	  Provides enforcement of process number limits in the scope of a
+	  cgroup. Any attempt to fork more processes than is allowed in the
+	  cgroup will fail. PIDs are fundamentally a global resource because it
+	  is fairly trivial to reach PID exhaustion before you reach even a
+	  conservative kmemcg limit. As a result, it is possible to grind a
+	  system to halt without being limited by other cgroup policies. The
+	  PIDs cgroup subsystem is designed to stop this from happening.
+
+	  It should be noted that organisational operations (such as attaching
+	  to a cgroup hierarchy will *not* be blocked by the PIDs subsystem),
+	  since the PIDs limit only affects a process's ability to fork, not to
+	  attach to a cgroup.
+
 config CGROUP_DEVICE
 	bool "Device controller for cgroups"
 	help
@@ -1011,6 +1058,7 @@ config PROC_PID_CPUSET
 
 config CGROUP_CPUACCT
 	bool "Simple CPU accounting cgroup subsystem"
+	depends on !SCHED_BFS
 	help
 	  Provides a simple Resource Controller for monitoring the
 	  total CPU consumed by the tasks in a cgroup.
@@ -1096,6 +1144,7 @@ config CGROUP_PERF
 
 menuconfig CGROUP_SCHED
 	bool "Group CPU scheduler"
+	depends on !SCHED_BFS
 	default n
 	help
 	  This feature lets CPU scheduler recognize task groups and control CPU
@@ -1243,6 +1292,7 @@ endif # NAMESPACES
 
 config SCHED_AUTOGROUP
 	bool "Automatic process group scheduling"
+	depends on !SCHED_BFS
 	select CGROUPS
 	select CGROUP_SCHED
 	select FAIR_GROUP_SCHED
@@ -1601,6 +1651,14 @@ config ADVISE_SYSCALLS
 	  applications use these syscalls, you can disable this option to save
 	  space.
 
+config USERFAULTFD
+	bool "Enable userfaultfd() system call"
+	select ANON_INODES
+	depends on MMU
+	help
+	  Enable the userfaultfd() system call that allows to intercept and
+	  handle page faults in userland.
+
 config PCI_QUIRKS
 	default y
 	bool "Enable PCI quirk workarounds" if EXPERT
@@ -1610,6 +1668,18 @@ config PCI_QUIRKS
 	  bugs/quirks. Disable this only if your target machine is
 	  unaffected by PCI quirks.
 
+config MEMBARRIER
+	bool "Enable membarrier() system call" if EXPERT
+	default y
+	help
+	  Enable the membarrier() system call that allows issuing memory
+	  barriers across all running threads, which can be used to distribute
+	  the cost of user-space memory barriers asymmetrically by transforming
+	  pairs of memory barriers into pairs consisting of membarrier() and a
+	  compiler barrier.
+
+	  If unsure, say Y.
+
 config EMBEDDED
 	bool "Embedded system"
 	option allnoconfig_y
@@ -1714,6 +1784,7 @@ choice
 	   This option allows to select a slab allocator.
 
 config SLAB
+	depends on !SCHED_BFS
 	bool "SLAB"
 	help
 	  The regular slab allocator that is established and known to work
@@ -1731,7 +1802,7 @@ config SLUB
 	   a slab allocator.
 
 config SLOB
-	depends on EXPERT
+	depends on EXPERT && !SCHED_BFS
 	bool "SLOB (Simple Allocator)"
 	help
 	   SLOB replaces the stock allocator with a drastically simpler
@@ -1773,17 +1844,23 @@ config MMAP_ALLOW_UNINITIALIZED
 
 	  See Documentation/nommu-mmap.txt for more information.
 
-config SYSTEM_TRUSTED_KEYRING
-	bool "Provide system-wide ring of trusted keys"
-	depends on KEYS
+config SYSTEM_DATA_VERIFICATION
+	def_bool n
+	select SYSTEM_TRUSTED_KEYRING
+	select KEYS
+	select CRYPTO
+	select ASYMMETRIC_KEY_TYPE
+	select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+	select PUBLIC_KEY_ALGO_RSA
+	select ASN1
+	select OID_REGISTRY
+	select X509_CERTIFICATE_PARSER
+	select PKCS7_MESSAGE_PARSER
 	help
-	  Provide a system keyring to which trusted keys can be added.  Keys in
-	  the keyring are considered to be trusted.  Keys may be added at will
-	  by the kernel from compiled-in data and from hardware key stores, but
-	  userspace may only add extra keys if those keys can be verified by
-	  keys already in the keyring.
-
-	  Keys in this keyring are used by module signature checking.
+	  Provide PKCS#7 message verification using the contents of the system
+	  trusted keyring to provide public keys.  This then can be used for
+	  module verification, kexec image verification and firmware blob
+	  verification.
 
 config PROFILING
 	bool "Profiling support"
@@ -1893,20 +1970,16 @@ config MODULE_SRCVERSION_ALL
 config MODULE_SIG
 	bool "Module signature verification"
 	depends on MODULES
-	select SYSTEM_TRUSTED_KEYRING
-	select KEYS
-	select CRYPTO
-	select ASYMMETRIC_KEY_TYPE
-	select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
-	select PUBLIC_KEY_ALGO_RSA
-	select ASN1
-	select OID_REGISTRY
-	select X509_CERTIFICATE_PARSER
+	select SYSTEM_DATA_VERIFICATION
 	help
 	  Check modules for valid signatures upon load: the signature
 	  is simply appended to the module. For more information see
 	  Documentation/module-signing.txt.
 
+	  Note that this option adds the OpenSSL development packages as a
+	  kernel build dependency so that the signing tool can use its crypto
+	  library.
+
 	  !!!WARNING!!!  If you enable this option, you MUST make sure that the
 	  module DOES NOT get stripped after being signed.  This includes the
 	  debuginfo strip done by some packagers (such as rpmbuild) and
diff --git a/init/initramfs.c b/init/initramfs.c
index ad1bd7787..b32ad7d97 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -526,14 +526,14 @@ extern unsigned long __initramfs_size;
 
 static void __init free_initrd(void)
 {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	unsigned long crashk_start = (unsigned long)__va(crashk_res.start);
 	unsigned long crashk_end   = (unsigned long)__va(crashk_res.end);
 #endif
 	if (do_retain_initrd)
 		goto skip;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	/*
 	 * If the initrd region is overlapped with crashkernel reserved region,
 	 * free only memory that is not part of crashkernel region.
diff --git a/init/main.c b/init/main.c
index 56506553d..7e98e9b86 100644
--- a/init/main.c
+++ b/init/main.c
@@ -808,7 +808,6 @@ int __init_or_module do_one_initcall(initcall_t fn)
 	return ret;
 }
 
-
 extern initcall_t __initcall_start[];
 extern initcall_t __initcall0_start[];
 extern initcall_t __initcall1_start[];
@@ -877,7 +876,6 @@ static void __init do_initcalls(void)
 static void __init do_basic_setup(void)
 {
 	cpuset_init_smp();
-	usermodehelper_init();
 	shmem_init();
 	driver_init();
 	init_irq_proc();
@@ -944,6 +942,8 @@ static int __ref kernel_init(void *unused)
 
 	flush_delayed_fput();
 
+	print_scheduler_version();
+
 	if (ramdisk_execute_command) {
 		ret = run_init_process(ramdisk_execute_command);
 		if (!ret)