Extend the meaning of the CTLFLAG_TUN flag to automatically check if

there is an environment variable which shall initialize the SYSCTL
during early boot. This works for all SYSCTL types both statically and
dynamically created ones, except for the SYSCTL NODE type and SYSCTLs
which belong to VNETs. A new flag, CTLFLAG_NOFETCH, has been added to
be used in the case a tunable sysctl has a custom initialisation
function allowing the sysctl to still be marked as a tunable. The
kernel SYSCTL API is mostly the same, with a few exceptions for some
special operations like iterating childrens of a static/extern SYSCTL
node. This operation should probably be made into a factored out
common macro, hence some device drivers use this. The reason for
changing the SYSCTL API was the need for a SYSCTL parent OID pointer
and not only the SYSCTL parent OID list pointer in order to quickly
generate the sysctl path. The motivation behind this patch is to avoid
parameter loading cludges inside the OFED driver subsystem. Instead of
adding special code to the OFED driver subsystem to post-load tunables
into dynamically created sysctls, we generalize this in the kernel.

Other changes:
- Corrected a possibly incorrect sysctl name from "hw.cbb.intr_mask"
to "hw.pcic.intr_mask".
- Removed redundant TUNABLE statements throughout the kernel.
- Some minor code rewrites in connection to removing not needed
TUNABLE statements.
- Added a missing SYSCTL_DECL().
- Wrapped two very long lines.
- Avoid malloc()/free() inside sysctl string handling, in case it is
called to initialize a sysctl from a tunable, hence malloc()/free() is
not ready when sysctls from the sysctl dataset are registered.
- Bumped FreeBSD version to indicate SYSCTL API change.

MFC after:	2 weeks
Sponsored by:	Mellanox Technologies

7 files changed, 6 insertions, 19 deletions

diff --git a/sys/x86/cpufreq/hwpstate.c b/sys/x86/cpufreq/hwpstate.c
index e86e31a..d4c70b7 100644
--- a/sys/x86/cpufreq/hwpstate.c
+++ b/sys/x86/cpufreq/hwpstate.c
@@ -118,9 +118,8 @@ static int	hwpstate_get_info_from_msr(device_t dev);
 static int	hwpstate_goto_pstate(device_t dev, int pstate_id);
 
 static int	hwpstate_verbose = 0;
-SYSCTL_INT(_debug, OID_AUTO, hwpstate_verbose, CTLFLAG_RW | CTLFLAG_TUN,
+SYSCTL_INT(_debug, OID_AUTO, hwpstate_verbose, CTLFLAG_RWTUN,
        &hwpstate_verbose, 0, "Debug hwpstate");
-TUNABLE_INT("debug.hwpstate_verbose", &hwpstate_verbose);
 
 static device_method_t hwpstate_methods[] = {
 	/* Device interface */
diff --git a/sys/x86/iommu/intel_utils.c b/sys/x86/iommu/intel_utils.c
index e221a1e..444329c 100644
--- a/sys/x86/iommu/intel_utils.c
+++ b/sys/x86/iommu/intel_utils.c
@@ -549,17 +549,16 @@ dmar_barrier_exit(struct dmar_unit *dmar, u_int barrier_id)
 
 int dmar_match_verbose;
 
-static SYSCTL_NODE(_hw, OID_AUTO, dmar, CTLFLAG_RD, NULL,
-    "");
-SYSCTL_INT(_hw_dmar, OID_AUTO, tbl_pagecnt, CTLFLAG_RD | CTLFLAG_TUN,
+static SYSCTL_NODE(_hw, OID_AUTO, dmar, CTLFLAG_RD, NULL, "");
+SYSCTL_INT(_hw_dmar, OID_AUTO, tbl_pagecnt, CTLFLAG_RD,
     &dmar_tbl_pagecnt, 0,
     "Count of pages used for DMAR pagetables");
-SYSCTL_INT(_hw_dmar, OID_AUTO, match_verbose, CTLFLAG_RW | CTLFLAG_TUN,
+SYSCTL_INT(_hw_dmar, OID_AUTO, match_verbose, CTLFLAG_RWTUN,
     &dmar_match_verbose, 0,
     "Verbose matching of the PCI devices to DMAR paths");
 #ifdef INVARIANTS
 int dmar_check_free;
-SYSCTL_INT(_hw_dmar, OID_AUTO, check_free, CTLFLAG_RW | CTLFLAG_TUN,
+SYSCTL_INT(_hw_dmar, OID_AUTO, check_free, CTLFLAG_RWTUN,
     &dmar_check_free, 0,
     "Check the GPA RBtree for free_down and free_after validity");
 #endif
diff --git a/sys/x86/pci/pci_bus.c b/sys/x86/pci/pci_bus.c
index 88cabc7..f64659e 100644
--- a/sys/x86/pci/pci_bus.c
+++ b/sys/x86/pci/pci_bus.c
@@ -575,7 +575,6 @@ legacy_pcib_write_ivar(device_t dev, device_t child, int which,
 SYSCTL_DECL(_hw_pci);
 
 static unsigned long host_mem_start = 0x80000000;
-TUNABLE_ULONG("hw.pci.host_mem_start", &host_mem_start);
 SYSCTL_ULONG(_hw_pci, OID_AUTO, host_mem_start, CTLFLAG_RDTUN, &host_mem_start,
     0, "Limit the host bridge memory to being above this address.");
 
diff --git a/sys/x86/x86/dump_machdep.c b/sys/x86/x86/dump_machdep.c
index 5c874f4..30fa719 100644
--- a/sys/x86/x86/dump_machdep.c
+++ b/sys/x86/x86/dump_machdep.c
@@ -53,8 +53,7 @@ __FBSDID("$FreeBSD$");
 CTASSERT(sizeof(struct kerneldumpheader) == 512);
 
 int do_minidump = 1;
-TUNABLE_INT("debug.minidump", &do_minidump);
-SYSCTL_INT(_debug, OID_AUTO, minidump, CTLFLAG_RW, &do_minidump, 0,
+SYSCTL_INT(_debug, OID_AUTO, minidump, CTLFLAG_RWTUN, &do_minidump, 0,
     "Enable mini crash dumps");
 
 /*
diff --git a/sys/x86/x86/io_apic.c b/sys/x86/x86/io_apic.c
index ec469ad..5667120 100644
--- a/sys/x86/x86/io_apic.c
+++ b/sys/x86/x86/io_apic.c
@@ -134,7 +134,6 @@ static SYSCTL_NODE(_hw, OID_AUTO, apic, CTLFLAG_RD, 0, "APIC options");
 static int enable_extint;
 SYSCTL_INT(_hw_apic, OID_AUTO, enable_extint, CTLFLAG_RDTUN, &enable_extint, 0,
     "Enable the ExtINT pin in the first I/O APIC");
-TUNABLE_INT("hw.apic.enable_extint", &enable_extint);
 
 static __inline void
 _ioapic_eoi_source(struct intsrc *isrc)
diff --git a/sys/x86/x86/mca.c b/sys/x86/x86/mca.c
index 8a0d2b1..347d570 100644
--- a/sys/x86/x86/mca.c
+++ b/sys/x86/x86/mca.c
@@ -92,12 +92,10 @@ static SYSCTL_NODE(_hw, OID_AUTO, mca, CTLFLAG_RD, NULL,
     "Machine Check Architecture");
 
 static int mca_enabled = 1;
-TUNABLE_INT("hw.mca.enabled", &mca_enabled);
 SYSCTL_INT(_hw_mca, OID_AUTO, enabled, CTLFLAG_RDTUN, &mca_enabled, 0,
     "Administrative toggle for machine check support");
 
 static int amd10h_L1TP = 1;
-TUNABLE_INT("hw.mca.amd10h_L1TP", &amd10h_L1TP);
 SYSCTL_INT(_hw_mca, OID_AUTO, amd10h_L1TP, CTLFLAG_RDTUN, &amd10h_L1TP, 0,
     "Administrative toggle for logging of level one TLB parity (L1TP) errors");
 
diff --git a/sys/x86/x86/tsc.c b/sys/x86/x86/tsc.c
index 2a6c81d..54c4d02 100644
--- a/sys/x86/x86/tsc.c
+++ b/sys/x86/x86/tsc.c
@@ -58,34 +58,28 @@ static eventhandler_tag tsc_levels_tag, tsc_pre_tag, tsc_post_tag;
 
 SYSCTL_INT(_kern_timecounter, OID_AUTO, invariant_tsc, CTLFLAG_RDTUN,
     &tsc_is_invariant, 0, "Indicates whether the TSC is P-state invariant");
-TUNABLE_INT("kern.timecounter.invariant_tsc", &tsc_is_invariant);
 
 #ifdef SMP
 int	smp_tsc;
 SYSCTL_INT(_kern_timecounter, OID_AUTO, smp_tsc, CTLFLAG_RDTUN, &smp_tsc, 0,
     "Indicates whether the TSC is safe to use in SMP mode");
-TUNABLE_INT("kern.timecounter.smp_tsc", &smp_tsc);
 
 int	smp_tsc_adjust = 0;
 SYSCTL_INT(_kern_timecounter, OID_AUTO, smp_tsc_adjust, CTLFLAG_RDTUN,
     &smp_tsc_adjust, 0, "Try to adjust TSC on APs to match BSP");
-TUNABLE_INT("kern.timecounter.smp_tsc_adjust", &smp_tsc_adjust);
 #endif
 
 static int	tsc_shift = 1;
 SYSCTL_INT(_kern_timecounter, OID_AUTO, tsc_shift, CTLFLAG_RDTUN,
     &tsc_shift, 0, "Shift to pre-apply for the maximum TSC frequency");
-TUNABLE_INT("kern.timecounter.tsc_shift", &tsc_shift);
 
 static int	tsc_disabled;
 SYSCTL_INT(_machdep, OID_AUTO, disable_tsc, CTLFLAG_RDTUN, &tsc_disabled, 0,
     "Disable x86 Time Stamp Counter");
-TUNABLE_INT("machdep.disable_tsc", &tsc_disabled);
 
 static int	tsc_skip_calibration;
 SYSCTL_INT(_machdep, OID_AUTO, disable_tsc_calibration, CTLFLAG_RDTUN,
     &tsc_skip_calibration, 0, "Disable TSC frequency calibration");
-TUNABLE_INT("machdep.disable_tsc_calibration", &tsc_skip_calibration);
 
 static void tsc_freq_changed(void *arg, const struct cf_level *level,
     int status);