[PATCH v1 1/2] x86/tsc: use logical_package as a better estimation of socket numbers

From: Feng Tang
Date: Fri Oct 21 2022 - 02:21:43 EST


Commit b50db7095fe0 ("x86/tsc: Disable clocksource watchdog for TSC
on qualified platorms") was introduced to solve problem that
sometimes TSC clocksource is wrongly judged as unstable by watchdog
like 'jiffies', HPET, etc.

In it, the hardware socket number is a key factor for judging
whether to disable the watchdog for TSC, and 'nr_online_nodes' was
chosen as an estimation due to it is needed in early boot phase
before registering 'tsc-early' clocksource, where all none-boot
CPUs are not brought up yet.

In recent patch review, Dave Hansen pointed out there are many
cases that 'nr_online_nodes' could have issue, like:
* numa emulation (numa=fake=4 etc.)
* numa=off
* platforms with CPU+DRAM nodes, CPU-less HBM nodes, CPU-less
persistent memory nodes.
* SNC (sub-numa cluster) mode is enabled

Peter Zijlstra suggested to use logical package ids, but it is
only usable after smp_init() and all CPUs are initialized.

One solution is to skip the watchdog for 'tsc-early' clocksource,
and move the check after smp_init(), while before 'tsc'
clocksoure is registered, where 'logical_packages' could be used
as a much more accurate socket number.

Signed-off-by: Feng Tang <feng.tang@xxxxxxxxx>
---
Hi reviewers,

I separate the code to 2 patches, as I think they are covering 2
problems and easy for bisect. Feel free to combine them into one,
as the 2/2 are a trivial change.

Thanks,
Feng

Changelog:

Since RFC:
* use 'logical_packages' instead of topology_max_packages(), whose
implementaion is not accurate, like for heterogeneous systems
which have combination of Core/Atom CPUs like Alderlake (Dave Hansen)

arch/x86/include/asm/topology.h | 4 ++++
arch/x86/kernel/smpboot.c | 2 +-
arch/x86/kernel/tsc.c | 42 +++++++++++++--------------------
3 files changed, 21 insertions(+), 27 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 458c891a8273..f9002549770c 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -122,8 +122,11 @@ extern unsigned int __max_die_per_package;
#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))

extern unsigned int __max_logical_packages;
+extern unsigned int logical_packages;
#define topology_max_packages() (__max_logical_packages)

+extern unsigned int logical_packages;
+
static inline int topology_max_die_per_package(void)
{
return __max_die_per_package;
@@ -144,6 +147,7 @@ bool topology_is_primary_thread(unsigned int cpu);
bool topology_smt_supported(void);
#else
#define topology_max_packages() (1)
+#define logical_packages (1)
static inline int
topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
static inline int
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3f3ea0287f69..d81156beb7e7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -102,7 +102,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
/* Logical package management. We might want to allocate that dynamically */
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
-static unsigned int logical_packages __read_mostly;
+unsigned int logical_packages __read_mostly;
static unsigned int logical_die __read_mostly;

/* Maximum number of SMT threads on any online core */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cafacb2e58cc..178448ef00c7 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1131,8 +1131,7 @@ static struct clocksource clocksource_tsc_early = {
.uncertainty_margin = 32 * NSEC_PER_MSEC,
.read = read_tsc,
.mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS |
- CLOCK_SOURCE_MUST_VERIFY,
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
.vdso_clock_mode = VDSO_CLOCKMODE_TSC,
.enable = tsc_cs_enable,
.resume = tsc_resume,
@@ -1180,12 +1179,6 @@ void mark_tsc_unstable(char *reason)

EXPORT_SYMBOL_GPL(mark_tsc_unstable);

-static void __init tsc_disable_clocksource_watchdog(void)
-{
- clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
- clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-}
-
static void __init check_system_tsc_reliable(void)
{
#if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
@@ -1202,23 +1195,6 @@ static void __init check_system_tsc_reliable(void)
#endif
if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
tsc_clocksource_reliable = 1;
-
- /*
- * Disable the clocksource watchdog when the system has:
- * - TSC running at constant frequency
- * - TSC which does not stop in C-States
- * - the TSC_ADJUST register which allows to detect even minimal
- * modifications
- * - not more than two sockets. As the number of sockets cannot be
- * evaluated at the early boot stage where this has to be
- * invoked, check the number of online memory nodes as a
- * fallback solution which is an reasonable estimate.
- */
- if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
- boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
- boot_cpu_has(X86_FEATURE_TSC_ADJUST) &&
- nr_online_nodes <= 2)
- tsc_disable_clocksource_watchdog();
}

/*
@@ -1413,6 +1389,20 @@ static int __init init_tsc_clocksource(void)
if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;

+ /*
+ * Disable the clocksource watchdog when the system has:
+ * - TSC running at constant frequency
+ * - TSC which does not stop in C-States
+ * - the TSC_ADJUST register which allows to detect even minimal
+ * modifications
+ * - not more than two sockets.
+ */
+ if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
+ boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
+ boot_cpu_has(X86_FEATURE_TSC_ADJUST) &&
+ logical_packages <= 2)
+ clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+
/*
* When TSC frequency is known (retrieved via MSR or CPUID), we skip
* the refined calibration and directly register it as a clocksource.
@@ -1547,7 +1537,7 @@ void __init tsc_init(void)
}

if (tsc_clocksource_reliable || no_tsc_watchdog)
- tsc_disable_clocksource_watchdog();
+ clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;

clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
detect_art();
--
2.34.1