From 37f49e37ab4cb5d0bc4c60eb5c6d4dd57db767bb Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:44:59 +0000
Subject: [PATCH] gmac get mac form eeprom
---
kernel/arch/x86/kernel/tsc.c | 218 +++++++++++++++++++++++++++++++++++-------------------
1 files changed, 141 insertions(+), 77 deletions(-)
diff --git a/kernel/arch/x86/kernel/tsc.c b/kernel/arch/x86/kernel/tsc.c
index 03b7529..f9f1b45 100644
--- a/kernel/arch/x86/kernel/tsc.c
+++ b/kernel/arch/x86/kernel/tsc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
@@ -40,6 +41,7 @@
* TSC can be unstable due to cpufreq or due to unsynced TSCs
*/
static int __read_mostly tsc_unstable;
+static unsigned int __initdata tsc_early_khz;
static DEFINE_STATIC_KEY_FALSE(__use_tsc);
@@ -52,30 +54,36 @@
struct cyc2ns {
struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */
- seqcount_t seq; /* 32 + 4 = 36 */
+ seqcount_latch_t seq; /* 32 + 4 = 36 */
}; /* fits one cacheline */
static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
-void __always_inline cyc2ns_read_begin(struct cyc2ns_data *data)
+static int __init tsc_early_khz_setup(char *buf)
+{
+ return kstrtouint(buf, 0, &tsc_early_khz);
+}
+early_param("tsc_early_khz", tsc_early_khz_setup);
+
+__always_inline void cyc2ns_read_begin(struct cyc2ns_data *data)
{
int seq, idx;
preempt_disable_notrace();
do {
- seq = this_cpu_read(cyc2ns.seq.sequence);
+ seq = this_cpu_read(cyc2ns.seq.seqcount.sequence);
idx = seq & 1;
data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset);
data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul);
data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift);
- } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence)));
+ } while (unlikely(seq != this_cpu_read(cyc2ns.seq.seqcount.sequence)));
}
-void __always_inline cyc2ns_read_end(void)
+__always_inline void cyc2ns_read_end(void)
{
preempt_enable_notrace();
}
@@ -178,15 +186,14 @@
{
struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
- seqcount_init(&c2n->seq);
+ seqcount_latch_init(&c2n->seq);
__set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc());
}
/*
* Secondary CPUs do not run through tsc_init(), so set up
* all the scale factors for all CPUs, assuming the same
- * speed as the bootup CPU. (cpufreq notifiers will fix this
- * up if their speed diverges)
+ * speed as the bootup CPU.
*/
static void __init cyc2ns_init_secondary_cpus(void)
{
@@ -196,7 +203,7 @@
for_each_possible_cpu(cpu) {
if (cpu != this_cpu) {
- seqcount_init(&c2n->seq);
+ seqcount_latch_init(&c2n->seq);
c2n = per_cpu_ptr(&cyc2ns, cpu);
c2n->data[0] = data[0];
c2n->data[1] = data[1];
@@ -247,7 +254,7 @@
bool using_native_sched_clock(void)
{
- return pv_time_ops.sched_clock == native_sched_clock;
+ return pv_ops.time.sched_clock == native_sched_clock;
}
#else
unsigned long long
@@ -283,6 +290,7 @@
__setup("notsc", notsc_setup);
static int no_sched_irq_time;
+static int no_tsc_watchdog;
static int __init tsc_setup(char *str)
{
@@ -292,20 +300,23 @@
no_sched_irq_time = 1;
if (!strcmp(str, "unstable"))
mark_tsc_unstable("boot parameter");
+ if (!strcmp(str, "nowatchdog"))
+ no_tsc_watchdog = 1;
return 1;
}
__setup("tsc=", tsc_setup);
-#define MAX_RETRIES 5
-#define SMI_TRESHOLD 50000
+#define MAX_RETRIES 5
+#define TSC_DEFAULT_THRESHOLD 0x20000
/*
- * Read TSC and the reference counters. Take care of SMI disturbance
+ * Read TSC and the reference counters. Take care of any disturbances
*/
static u64 tsc_read_refs(u64 *p, int hpet)
{
u64 t1, t2;
+ u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD;
int i;
for (i = 0; i < MAX_RETRIES; i++) {
@@ -315,7 +326,7 @@
else
*p = acpi_pm_read_early();
t2 = get_cycles();
- if ((t2 - t1) < SMI_TRESHOLD)
+ if ((t2 - t1) < thresh)
return t2;
}
return ULLONG_MAX;
@@ -473,7 +484,7 @@
* transition from one expected value to another with a fairly
* high accuracy, and we didn't miss any events. We can thus
* use the TSC value at the transitions to calculate a pretty
- * good value for the TSC frequencty.
+ * good value for the TSC frequency.
*/
static inline int pit_verify_msb(unsigned char val)
{
@@ -628,31 +639,38 @@
crystal_khz = ecx_hz / 1000;
- if (crystal_khz == 0) {
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
- crystal_khz = 24000; /* 24.0 MHz */
- break;
- case INTEL_FAM6_ATOM_GOLDMONT_X:
- crystal_khz = 25000; /* 25.0 MHz */
- break;
- case INTEL_FAM6_ATOM_GOLDMONT:
- crystal_khz = 19200; /* 19.2 MHz */
- break;
- }
+ /*
+ * Denverton SoCs don't report crystal clock, and also don't support
+ * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal
+ * clock.
+ */
+ if (crystal_khz == 0 &&
+ boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_D)
+ crystal_khz = 25000;
+
+ /*
+ * TSC frequency reported directly by CPUID is a "hardware reported"
+ * frequency and is the most accurate one so far we have. This
+ * is considered a known frequency.
+ */
+ if (crystal_khz != 0)
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+ /*
+ * Some Intel SoCs like Skylake and Kabylake don't report the crystal
+ * clock, but we can easily calculate it to a high degree of accuracy
+ * by considering the crystal ratio and the CPU speed.
+ */
+ if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) {
+ unsigned int eax_base_mhz, ebx, ecx, edx;
+
+ cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx);
+ crystal_khz = eax_base_mhz * 1000 *
+ eax_denominator / ebx_numerator;
}
if (crystal_khz == 0)
return 0;
- /*
- * TSC frequency determined by CPUID is a "hardware reported"
- * frequency and is the most accurate one so far we have. This
- * is considered a known frequency.
- */
- setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
/*
* For Atom SoCs TSC is the only reliable clocksource.
@@ -660,6 +678,16 @@
*/
if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT)
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * The local APIC appears to be fed by the core crystal clock
+ * (which sounds entirely sensible). We can set the global
+ * lapic_timer_period here to avoid having to calibrate the APIC
+ * timer later.
+ */
+ lapic_timer_period = crystal_khz * 1000 / HZ;
+#endif
return crystal_khz * ebx_numerator / eax_denominator;
}
@@ -703,15 +731,15 @@
* zero. In each wait loop iteration we read the TSC and check
* the delta to the previous read. We keep track of the min
* and max values of that delta. The delta is mostly defined
- * by the IO time of the PIT access, so we can detect when a
- * SMI/SMM disturbance happened between the two reads. If the
+ * by the IO time of the PIT access, so we can detect when
+ * any disturbance happened between the two reads. If the
* maximum time is significantly larger than the minimum time,
* then we discard the result and have another try.
*
* 2) Reference counter. If available we use the HPET or the
* PMTIMER as a reference to check the sanity of that value.
* We use separate TSC readouts and check inside of the
- * reference read for a SMI/SMM disturbance. We dicard
+ * reference read for any possible disturbance. We dicard
* disturbed values here as well. We do that around the PIT
* calibration delay loop as we have to wait for a certain
* amount of time anyway.
@@ -744,7 +772,7 @@
if (ref1 == ref2)
continue;
- /* Check, whether the sampling was disturbed by an SMI */
+ /* Check, whether the sampling was disturbed */
if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
continue;
@@ -936,12 +964,12 @@
}
#ifdef CONFIG_CPU_FREQ
-/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
+/*
+ * Frequency scaling support. Adjust the TSC based timer when the CPU frequency
* changes.
*
- * RED-PEN: On SMP we assume all CPUs run with the same frequency. It's
- * not that important because current Opteron setups do not support
- * scaling on SMP anyroads.
+ * NOTE: On SMP the situation is not fixable in general, so simply mark the TSC
+ * as unstable and give up in those cases.
*
* Should fix up last_tsc too. Currently gettimeofday in the
* first tick after the change will be slightly wrong.
@@ -955,28 +983,28 @@
void *data)
{
struct cpufreq_freqs *freq = data;
- unsigned long *lpj;
- lpj = &boot_cpu_data.loops_per_jiffy;
-#ifdef CONFIG_SMP
- if (!(freq->flags & CPUFREQ_CONST_LOOPS))
- lpj = &cpu_data(freq->cpu).loops_per_jiffy;
-#endif
+ if (num_online_cpus() > 1) {
+ mark_tsc_unstable("cpufreq changes on SMP");
+ return 0;
+ }
if (!ref_freq) {
ref_freq = freq->old;
- loops_per_jiffy_ref = *lpj;
+ loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy;
tsc_khz_ref = tsc_khz;
}
+
if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
- (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
- *lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
+ (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
+ boot_cpu_data.loops_per_jiffy =
+ cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
mark_tsc_unstable("cpufreq changes");
- set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc());
+ set_cyc2ns_scale(tsc_khz, freq->policy->cpu, rdtsc());
}
return 0;
@@ -1087,17 +1115,24 @@
sched_clock_tick_stable();
}
+static int tsc_cs_enable(struct clocksource *cs)
+{
+ vclocks_set_used(VDSO_CLOCKMODE_TSC);
+ return 0;
+}
+
/*
* .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
*/
static struct clocksource clocksource_tsc_early = {
- .name = "tsc-early",
- .rating = 299,
- .read = read_tsc,
- .mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS |
+ .name = "tsc-early",
+ .rating = 299,
+ .read = read_tsc,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_MUST_VERIFY,
- .archdata = { .vclock_mode = VCLOCK_TSC },
+ .vdso_clock_mode = VDSO_CLOCKMODE_TSC,
+ .enable = tsc_cs_enable,
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
@@ -1110,14 +1145,16 @@
* been found good.
*/
static struct clocksource clocksource_tsc = {
- .name = "tsc",
- .rating = 300,
- .read = read_tsc,
- .mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS |
+ .name = "tsc",
+ .rating = 300,
+ .read = read_tsc,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_VALID_FOR_HRES |
- CLOCK_SOURCE_MUST_VERIFY,
- .archdata = { .vclock_mode = VCLOCK_TSC },
+ CLOCK_SOURCE_MUST_VERIFY |
+ CLOCK_SOURCE_VERIFY_PERCPU,
+ .vdso_clock_mode = VDSO_CLOCKMODE_TSC,
+ .enable = tsc_cs_enable,
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
@@ -1141,6 +1178,12 @@
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)
@@ -1157,6 +1200,23 @@
#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();
}
/*
@@ -1268,7 +1328,7 @@
*/
static void tsc_refine_calibration_work(struct work_struct *work)
{
- static u64 tsc_start = -1, ref_start;
+ static u64 tsc_start = ULLONG_MAX, ref_start;
static int hpet;
u64 tsc_stop, ref_stop, delta;
unsigned long freq;
@@ -1283,14 +1343,15 @@
* delayed the first time we expire. So set the workqueue
* again once we know timers are working.
*/
- if (tsc_start == -1) {
+ if (tsc_start == ULLONG_MAX) {
+restart:
/*
* Only set hpet once, to avoid mixing hardware
* if the hpet becomes enabled later.
*/
hpet = is_hpet_enabled();
- schedule_delayed_work(&tsc_irqwork, HZ);
tsc_start = tsc_read_refs(&ref_start, hpet);
+ schedule_delayed_work(&tsc_irqwork, HZ);
return;
}
@@ -1300,9 +1361,9 @@
if (ref_start == ref_stop)
goto out;
- /* Check, whether the sampling was disturbed by an SMI */
- if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
- goto out;
+ /* Check, whether the sampling was disturbed */
+ if (tsc_stop == ULLONG_MAX)
+ goto restart;
delta = tsc_stop - tsc_start;
delta *= 1000000LL;
@@ -1347,9 +1408,6 @@
if (tsc_unstable)
goto unreg;
- if (tsc_clocksource_reliable)
- clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-
if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
@@ -1382,7 +1440,10 @@
if (early) {
cpu_khz = x86_platform.calibrate_cpu();
- tsc_khz = x86_platform.calibrate_tsc();
+ if (tsc_early_khz)
+ tsc_khz = tsc_early_khz;
+ else
+ tsc_khz = x86_platform.calibrate_tsc();
} else {
/* We should not be here with non-native cpu calibration */
WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu);
@@ -1483,6 +1544,9 @@
return;
}
+ if (tsc_clocksource_reliable || no_tsc_watchdog)
+ tsc_disable_clocksource_watchdog();
+
clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
detect_art();
}
--
Gitblit v1.6.2