[GIT PULL] x86 fixes

From: Ingo Molnar
Date: Sat Feb 11 2017 - 13:18:39 EST


Linus,

Please pull the latest x86-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus

# HEAD: 146fbb766934dc003fcbf755b519acef683576bf x86/mm/ptdump: Fix soft lockup in page table walker

Last minute x86 fixes:

- Fix a softlockup detector warning and long delays if using ptdump with KASAN
enabled.

- Two more TSC-adjust fixes for interesting firmware interactions.

- Two commits to fix an AMD CPU topology enumeration bug that caused a
measurable gaming performance regression.

Thanks,

Ingo

------------------>
Andrey Ryabinin (1):
x86/mm/ptdump: Fix soft lockup in page table walker

Borislav Petkov (1):
x86/CPU/AMD: Bring back Compute Unit ID

Thomas Gleixner (2):
x86/tsc: Avoid the large time jump when sanitizing TSC ADJUST
x86/tsc: Make the TSC ADJUST sanitizing work for tsc_reliable

Yazen Ghannam (1):
x86/CPU/AMD: Fix Zen SMT topology


arch/x86/include/asm/processor.h | 1 +
arch/x86/kernel/cpu/amd.c | 16 +++++++++++++++-
arch/x86/kernel/cpu/common.c | 1 +
arch/x86/kernel/smpboot.c | 12 +++++++++---
arch/x86/kernel/tsc.c | 5 +++--
arch/x86/kernel/tsc_sync.c | 16 +++++++---------
arch/x86/mm/dump_pagetables.c | 2 ++
7 files changed, 38 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1be64da0384e..e6cfe7ba2d65 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
__u8 x86_phys_bits;
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
+ __u8 cu_id;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1d3167269a67..2b4cf04239b6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c)

/* get information required for multi-node processors */
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ u32 eax, ebx, ecx, edx;

- node_id = cpuid_ecx(0x8000001e) & 7;
+ cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+ node_id = ecx & 0xff;
+ smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+ if (c->x86 == 0x15)
+ c->cu_id = ebx & 0xff;
+
+ if (c->x86 >= 0x17) {
+ c->cpu_core_id = ebx & 0xff;
+
+ if (smp_num_siblings > 1)
+ c->x86_max_cores /= smp_num_siblings;
+ }

/*
* We may have multiple LLCs if L3 caches exist, so check if we
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bab7a8a4293..ede03e849a8b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1015,6 +1015,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_max_cores = 1;
c->x86_coreid_bits = 0;
+ c->cu_id = 0xff;
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
c->x86_phys_bits = 36;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 46732dc3b73c..99b920d0e516 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;

if (c->phys_proc_id == o->phys_proc_id &&
- per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
- c->cpu_core_id == o->cpu_core_id)
- return topology_sane(c, o, "smt");
+ per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+ if (c->cpu_core_id == o->cpu_core_id)
+ return topology_sane(c, o, "smt");
+
+ if ((c->cu_id != 0xff) &&
+ (o->cu_id != 0xff) &&
+ (c->cu_id == o->cu_id))
+ return topology_sane(c, o, "smt");
+ }

} else if (c->phys_proc_id == o->phys_proc_id &&
c->cpu_core_id == o->cpu_core_id) {
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e41af597aed8..37e7cf544e51 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1356,6 +1356,9 @@ void __init tsc_init(void)
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);

+ /* Sanitize TSC ADJUST before cyc2ns gets initialized */
+ tsc_store_and_check_tsc_adjust(true);
+
/*
* Secondary CPUs do not run through tsc_init(), so set up
* all the scale factors for all CPUs, assuming the same
@@ -1386,8 +1389,6 @@ void __init tsc_init(void)

if (unsynchronized_tsc())
mark_tsc_unstable("TSCs unsynchronized");
- else
- tsc_store_and_check_tsc_adjust(true);

check_system_tsc_reliable();

diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index d0db011051a5..728f75378475 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu)
if (unsynchronized_tsc())
return;

- if (tsc_clocksource_reliable) {
- if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
- pr_info(
- "Skipped synchronization checks as TSC is reliable.\n");
- return;
- }
-
/*
* Set the maximum number of test runs to
* 1 if the CPU does not provide the TSC_ADJUST MSR
@@ -380,14 +373,19 @@ void check_tsc_sync_target(void)
int cpus = 2;

/* Also aborts if there is no TSC. */
- if (unsynchronized_tsc() || tsc_clocksource_reliable)
+ if (unsynchronized_tsc())
return;

/*
* Store, verify and sanitize the TSC adjust register. If
* successful skip the test.
+ *
+ * The test is also skipped when the TSC is marked reliable. This
+ * is true for SoCs which have no fallback clocksource. On these
+ * SoCs the TSC is frequency synchronized, but still the TSC ADJUST
+ * register might have been wreckaged by the BIOS..
*/
- if (tsc_store_and_check_tsc_adjust(false)) {
+ if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) {
atomic_inc(&skip_test);
return;
}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49adaa1f..8aa6bea1cd6c 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,6 +15,7 @@
#include <linux/debugfs.h>
#include <linux/mm.h>
#include <linux/init.h>
+#include <linux/sched.h>
#include <linux/seq_file.h>

#include <asm/pgtable.h>
@@ -406,6 +407,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
} else
note_page(m, &st, __pgprot(0), 1);

+ cond_resched();
start++;
}