From 79a8b9aa388b0620cc1d525d7c0f0d9a8a85e08e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sun, 5 Feb 2017 11:50:21 +0100 Subject: x86/CPU/AMD: Bring back Compute Unit ID Commit: a33d331761bc ("x86/CPU/AMD: Fix Bulldozer topology") restored the initial approach we had with the Fam15h topology of enumerating CU (Compute Unit) threads as cores. And this is still correct - they're beefier than HT threads but still have some shared functionality. Our current approach has a problem with the Mad Max Steam game, for example. Yves Dionne reported a certain "choppiness" while playing on v4.9.5. That problem stems most likely from the fact that the CU threads share resources within one CU and when we schedule to a thread of a different compute unit, this incurs latency due to migrating the working set to a different CU through the caches. When the thread siblings mask mirrors that aspect of the CUs and threads, the scheduler pays attention to it and tries to schedule within one CU first. Which takes care of the latency, of course. Reported-by: Yves Dionne Signed-off-by: Borislav Petkov Cc: # 4.9 Cc: Brice Goglin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yazen Ghannam Link: http://lkml.kernel.org/r/20170205105022.8705-1-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/cpu/amd.c | 9 ++++++++- arch/x86/kernel/cpu/common.c | 1 + arch/x86/kernel/smpboot.c | 12 +++++++++--- 4 files changed, 19 insertions(+), 4 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..20dc44d1e6be 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -309,8 +309,15 @@ 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; /* * 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) { -- cgit v1.2.3 From 08b259631b5a1d912af4832847b5642f377d9101 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Sun, 5 Feb 2017 11:50:22 +0100 Subject: x86/CPU/AMD: Fix Zen SMT topology After: a33d331761bc ("x86/CPU/AMD: Fix Bulldozer topology") our SMT scheduling topology for Fam17h systems is broken, because the ThreadId is included in the ApicId when SMT is enabled. So, without further decoding cpu_core_id is unique for each thread rather than the same for threads on the same core. This didn't affect systems with SMT disabled. Make cpu_core_id be what it is defined to be. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Cc: # 4.9 Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170205105022.8705-2-bp@alien8.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/amd.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 20dc44d1e6be..2b4cf04239b6 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -319,6 +319,13 @@ static void amd_get_topology(struct cpuinfo_x86 *c) 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 * have an L3 cache by looking at the L3 cache CPUID leaf. -- cgit v1.2.3 From f2e04214ef7f7e49d1e06109ad1b2718155dab25 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Feb 2017 16:08:41 +0100 Subject: x86/tsc: Avoid the large time jump when sanitizing TSC ADJUST Olof reported that on a machine which has a BIOS wreckaged TSC the timestamps in dmesg are making a large jump because the TSC value is jumping forward after resetting the TSC ADJUST register to a sane value. This can be avoided by calling the TSC ADJUST saniziting function before initializing the per cpu sched clock machinery. That takes the offset into account and avoid the time jump. What cannot be avoided is that the 'Firmware Bug' warnings on the secondary CPUs are printed with the large time offsets because it would be too much effort and ugly hackery to print those warnings into a buffer and emit them after the adjustemt on the starting CPUs. It's a firmware bug and should be fixed in firmware. The weird timestamps are collateral damage and just illustrate the sillyness of the BIOS folks: [ 0.397445] smp: Bringing up secondary CPUs ... [ 0.402100] x86: Booting SMP configuration: [ 0.406343] .... node #0, CPUs: #1 [1265776479.930667] [Firmware Bug]: TSC ADJUST differs: Reference CPU0: -2978888639075328 CPU1: -2978888639183101 [1265776479.944664] TSC ADJUST synchronize: Reference CPU0: 0 CPU1: -2978888639183101 [ 0.508119] #2 [1265776480.032346] [Firmware Bug]: TSC ADJUST differs: Reference CPU0: -2978888639075328 CPU2: -2978888639183677 [1265776480.044192] TSC ADJUST synchronize: Reference CPU0: 0 CPU2: -2978888639183677 [ 0.607643] #3 [1265776480.131874] [Firmware Bug]: TSC ADJUST differs: Reference CPU0: -2978888639075328 CPU3: -2978888639184530 [1265776480.143720] TSC ADJUST synchronize: Reference CPU0: 0 CPU3: -2978888639184530 [ 0.707108] smp: Brought up 1 node, 4 CPUs [ 0.711271] smpboot: Total of 4 processors activated (21698.88 BogoMIPS) Reported-by: Olof Johansson Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20170209151231.411460506@linutronix.de Signed-off-by: Thomas Gleixner --- arch/x86/kernel/tsc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) 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(); -- cgit v1.2.3 From 5f2e71e71410ecb858cfec184ba092adaca61626 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Feb 2017 16:08:42 +0100 Subject: x86/tsc: Make the TSC ADJUST sanitizing work for tsc_reliable When the TSC is marked reliable then the synchronization check is skipped, but that also skips the TSC ADJUST sanitizing code. So on a machine with a wreckaged BIOS the TSC deviation between CPUs might go unnoticed. Let the TSC adjust sanitizing code run unconditionally and just skip the expensive synchronization checks when TSC is marked reliable. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Olof Johansson Link: http://lkml.kernel.org/r/20170209151231.491189912@linutronix.de Signed-off-by: Thomas Gleixner --- arch/x86/kernel/tsc_sync.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) 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; } -- cgit v1.2.3 From 146fbb766934dc003fcbf755b519acef683576bf Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 10 Feb 2017 12:54:05 +0300 Subject: x86/mm/ptdump: Fix soft lockup in page table walker CONFIG_KASAN=y needs a lot of virtual memory mapped for its shadow. In that case ptdump_walk_pgd_level_core() takes a lot of time to walk across all page tables and doing this without a rescheduling causes soft lockups: NMI watchdog: BUG: soft lockup - CPU#3 stuck for 23s! [swapper/0:1] ... Call Trace: ptdump_walk_pgd_level_core+0x40c/0x550 ptdump_walk_pgd_level_checkwx+0x17/0x20 mark_rodata_ro+0x13b/0x150 kernel_init+0x2f/0x120 ret_from_fork+0x2c/0x40 I guess that this issue might arise even without KASAN on huge machines with several terabytes of RAM. Stick cond_resched() in pgd loop to fix this. Reported-by: Tobias Regnery Signed-off-by: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Alexander Potapenko Cc: "Paul E . McKenney" Cc: Dmitry Vyukov Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20170210095405.31802-1-aryabinin@virtuozzo.com Signed-off-by: Thomas Gleixner --- arch/x86/mm/dump_pagetables.c | 2 ++ 1 file changed, 2 insertions(+) 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 #include #include +#include #include #include @@ -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++; } -- cgit v1.2.3