From a786ef152cdcfebc923a67f63c7815806eefcf81 Mon Sep 17 00:00:00 2001 From: Daniel Vacek Date: Mon, 5 Nov 2018 18:10:40 +0100 Subject: x86/tsc: Make calibration refinement more robust The threshold in tsc_read_refs() is constant which may favor slower CPUs but may not be optimal for simple reading of reference on faster ones. Hence make it proportional to tsc_khz when available to compensate for this. The threshold guards against any disturbance like IRQs, NMIs, SMIs or CPU stealing by host on guest systems so rename it accordingly and fix comments as well. Also on some systems there is noticeable DMI bus contention at some point during boot keeping the readout failing (observed with about one in ~300 boots when testing). In that case retry also the second readout instead of simply bailing out unrefined. Usually the next second the readout returns fast just fine without any issues. Signed-off-by: Daniel Vacek Signed-off-by: Thomas Gleixner Cc: Borislav Petkov Cc: "H. Peter Anvin" Link: https://lkml.kernel.org/r/1541437840-29293-1-git-send-email-neelx@redhat.com --- arch/x86/kernel/tsc.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e9f777bfed40..3fae23834069 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -297,15 +297,16 @@ static int __init tsc_setup(char *str) __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 +316,7 @@ static u64 tsc_read_refs(u64 *p, int hpet) else *p = acpi_pm_read_early(); t2 = get_cycles(); - if ((t2 - t1) < SMI_TRESHOLD) + if ((t2 - t1) < thresh) return t2; } return ULLONG_MAX; @@ -703,15 +704,15 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) * 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 +745,7 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) 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; @@ -1268,7 +1269,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); */ 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 +1284,15 @@ static void tsc_refine_calibration_work(struct work_struct *work) * 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 +1302,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) 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; -- cgit v1.2.3 From d999c0ec2498e54b9328db6b2c1037710025add1 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Fri, 30 Nov 2018 13:14:50 -0800 Subject: x86/hpet: Remove unused FSEC_PER_NSEC define The FSEC_PER_NSEC macro has had zero users since commit ab0e08f15d23 ("x86: hpet: Cleanup the clockevents init and register code"). Remove it. Signed-off-by: Roland Dreier Signed-off-by: Borislav Petkov Acked-by: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: x86-ml Link: https://lkml.kernel.org/r/20181130211450.5200-1-roland@purestorage.com --- arch/x86/kernel/hpet.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index b0acb22e5a46..dfd3aca82c61 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -21,10 +21,6 @@ #define HPET_MASK CLOCKSOURCE_MASK(32) -/* FSEC = 10^-15 - NSEC = 10^-9 */ -#define FSEC_PER_NSEC 1000000L - #define HPET_DEV_USED_BIT 2 #define HPET_DEV_USED (1 << HPET_DEV_USED_BIT) #define HPET_DEV_VALID 0x8 -- cgit v1.2.3 From 90802938f7e88045ace123e105e22e8c3e7f9c7e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 8 Jan 2019 17:38:29 +0100 Subject: x86/cache: Rename config option to CONFIG_X86_RESCTRL CONFIG_RESCTRL is too generic. The final goal is to have a generic option called like this which is selected by the arch-specific ones CONFIG_X86_RESCTRL and CONFIG_ARM64_RESCTRL. The generic one will cover the resctrl filesystem and other generic and shared bits of functionality. Signed-off-by: Borislav Petkov Suggested-by: Ingo Molnar Requested-by: Linus Torvalds Cc: Babu Moger Cc: Fenghua Yu Cc: James Morse Cc: Reinette Chatre Cc: Tony Luck Cc: x86@kernel.org Link: http://lkml.kernel.org/r/20190108171401.GC12235@zn.tnic --- Documentation/x86/resctrl_ui.txt | 2 +- arch/x86/Kconfig | 2 +- arch/x86/include/asm/resctrl_sched.h | 4 ++-- arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/kernel/cpu/resctrl/Makefile | 4 ++-- include/linux/sched.h | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'arch/x86/kernel') diff --git a/Documentation/x86/resctrl_ui.txt b/Documentation/x86/resctrl_ui.txt index d9aed8303984..e8e8d14d3c4e 100644 --- a/Documentation/x86/resctrl_ui.txt +++ b/Documentation/x86/resctrl_ui.txt @@ -9,7 +9,7 @@ Fenghua Yu Tony Luck Vikas Shivappa -This feature is enabled by the CONFIG_RESCTRL and the X86 /proc/cpuinfo +This feature is enabled by the CONFIG_X86_RESCTRL and the x86 /proc/cpuinfo flag bits: RDT (Resource Director Technology) Allocation - "rdt_a" CAT (Cache Allocation Technology) - "cat_l3", "cat_l2" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6185d4f33296..15af091611e2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -446,7 +446,7 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config RESCTRL +config X86_RESCTRL bool "Resource Control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl_sched.h index 54990fe2a3ae..40ebddde6ac2 100644 --- a/arch/x86/include/asm/resctrl_sched.h +++ b/arch/x86/include/asm/resctrl_sched.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_RESCTRL_SCHED_H #define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_RESCTRL +#ifdef CONFIG_X86_RESCTRL #include #include @@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void) static inline void resctrl_sched_in(void) {} -#endif /* CONFIG_RESCTRL */ +#endif /* CONFIG_X86_RESCTRL */ #endif /* _ASM_X86_RESCTRL_SCHED_H */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index ac78f90aea56..b6fa0869f7aa 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_X86_MCE) += mce/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ -obj-$(CONFIG_RESCTRL) += resctrl/ +obj-$(CONFIG_X86_RESCTRL) += resctrl/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index 6895049ceef7..1cabe6fd8e11 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_RESCTRL) += core.o rdtgroup.o monitor.o -obj-$(CONFIG_RESCTRL) += ctrlmondata.o pseudo_lock.o +obj-$(CONFIG_X86_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_RESCTRL) += ctrlmondata.o pseudo_lock.o CFLAGS_pseudo_lock.o = -I$(src) diff --git a/include/linux/sched.h b/include/linux/sched.h index 89541d248893..224666226e87 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_RESCTRL +#ifdef CONFIG_X86_RESCTRL u32 closid; u32 rmid; #endif -- cgit v1.2.3 From e4f358916d528d479c3c12bd2fd03f2d5a576380 Mon Sep 17 00:00:00 2001 From: WANG Chao Date: Tue, 11 Dec 2018 00:37:25 +0800 Subject: x86, modpost: Replace last remnants of RETPOLINE with CONFIG_RETPOLINE Commit 4cd24de3a098 ("x86/retpoline: Make CONFIG_RETPOLINE depend on compiler support") replaced the RETPOLINE define with CONFIG_RETPOLINE checks. Remove the remaining pieces. [ bp: Massage commit message. ] Fixes: 4cd24de3a098 ("x86/retpoline: Make CONFIG_RETPOLINE depend on compiler support") Signed-off-by: WANG Chao Signed-off-by: Borislav Petkov Reviewed-by: Zhenzhong Duan Reviewed-by: Masahiro Yamada Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Daniel Borkmann Cc: David Woodhouse Cc: Geert Uytterhoeven Cc: Jessica Yu Cc: Jiri Kosina Cc: Kees Cook Cc: Konrad Rzeszutek Wilk Cc: Luc Van Oostenryck Cc: Michal Marek Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Tim Chen Cc: Vasily Gorbik Cc: linux-kbuild@vger.kernel.org Cc: srinivas.eeda@oracle.com Cc: stable Cc: x86-ml Link: https://lkml.kernel.org/r/20181210163725.95977-1-chao.wang@ucloud.cn --- arch/x86/kernel/cpu/bugs.c | 2 +- include/linux/compiler-gcc.h | 2 +- include/linux/module.h | 2 +- scripts/mod/modpost.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8654b8b0c848..1de0f4170178 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -215,7 +215,7 @@ static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init = SPECTRE_V2_USER_NONE; -#ifdef RETPOLINE +#ifdef CONFIG_RETPOLINE static bool spectre_v2_bad_module; bool retpoline_module_ok(bool has_retpoline) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5776da43da97..dd8268f5f5f0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -68,7 +68,7 @@ */ #define uninitialized_var(x) x = x -#ifdef RETPOLINE +#ifdef CONFIG_RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif diff --git a/include/linux/module.h b/include/linux/module.h index 9a21fe3509af..8fa38d3e7538 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -828,7 +828,7 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ -#ifdef RETPOLINE +#ifdef CONFIG_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 0de2fb236640..26bf886bd168 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2185,7 +2185,7 @@ static void add_intree_flag(struct buffer *b, int is_intree) /* Cannot check for assembler */ static void add_retpoline(struct buffer *b) { - buf_printf(b, "\n#ifdef RETPOLINE\n"); + buf_printf(b, "\n#ifdef CONFIG_RETPOLINE\n"); buf_printf(b, "MODULE_INFO(retpoline, \"Y\");\n"); buf_printf(b, "#endif\n"); } -- cgit v1.2.3 From 993a110319a4a60aadbd02f6defdebe048f7773b Mon Sep 17 00:00:00 2001 From: Dave Young Date: Fri, 28 Dec 2018 09:12:47 +0800 Subject: x86/kexec: Fix a kexec_file_load() failure Commit b6664ba42f14 ("s390, kexec_file: drop arch_kexec_mem_walk()") changed the behavior of kexec_locate_mem_hole(): it will try to allocate free memory only when kbuf.mem is initialized to zero. However, x86's kexec_file_load() implementation reuses a struct kexec_buf allocated on the stack and its kbuf.mem member gets set by each kexec_add_buffer() invocation. The second kexec_add_buffer() will reuse the same kbuf but not reinitialize kbuf.mem. Therefore, explictily reset kbuf.mem each time in order for kexec_locate_mem_hole() to locate a free memory region each time. [ bp: massage commit message. ] Fixes: b6664ba42f14 ("s390, kexec_file: drop arch_kexec_mem_walk()") Signed-off-by: Dave Young Signed-off-by: Borislav Petkov Acked-by: Baoquan He Cc: "Eric W. Biederman" Cc: "H. Peter Anvin" Cc: AKASHI Takahiro Cc: Andrew Morton Cc: Ingo Molnar Cc: Martin Schwidefsky Cc: Philipp Rudo Cc: Thomas Gleixner Cc: Vivek Goyal Cc: Yannik Sembritzki Cc: Yi Wang Cc: kexec@lists.infradead.org Cc: x86-ml Link: https://lkml.kernel.org/r/20181228011247.GA9999@dhcp-128-65.nay.redhat.com --- arch/x86/kernel/crash.c | 1 + arch/x86/kernel/kexec-bzimage64.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c8b07d8ea5a2..17ffc869cab8 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image) kbuf.memsz = kbuf.bufsz; kbuf.buf_align = ELF_CORE_HEADER_ALIGN; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) { vfree((void *)image->arch.elf_headers); diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 278cd07228dd..0d5efa34f359 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -434,6 +434,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.memsz = PAGE_ALIGN(header->init_size); kbuf.buf_align = header->kernel_alignment; kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; @@ -448,6 +449,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; kbuf.buf_min = MIN_INITRD_LOAD_ADDR; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; -- cgit v1.2.3 From de81c2f912ef57917bdc6d63b410c534c3e07982 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Jan 2019 09:22:40 -0800 Subject: KVM: x86: WARN_ONCE if sending a PV IPI returns a fatal error KVM hypercalls return a negative value error code in case of a fatal error, e.g. when the hypercall isn't supported or was made with invalid parameters. WARN_ONCE on fatal errors when sending PV IPIs as any such error all but guarantees an SMP system will hang due to a missing IPI. Fixes: aaffcfd1e82d ("KVM: X86: Implement PV IPIs in linux guest") Cc: stable@vger.kernel.org Cc: Wanpeng Li Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index ba4bfb7f6a36..5c93a65ee1e5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -457,6 +457,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector) #else u64 ipi_bitmap = 0; #endif + long ret; if (cpumask_empty(mask)) return; @@ -482,8 +483,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector) } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) { max = apic_id < max ? max : apic_id; } else { - kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, + ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr); + WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret); min = max = apic_id; ipi_bitmap = 0; } @@ -491,8 +493,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector) } if (ipi_bitmap) { - kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, + ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr); + WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret); } local_irq_restore(flags); -- cgit v1.2.3 From b284909abad48b07d3071a9fc9b5692b3e64914b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 30 Jan 2019 07:13:58 -0600 Subject: cpu/hotplug: Fix "SMT disabled by BIOS" detection for KVM With the following commit: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") ... the hotplug code attempted to detect when SMT was disabled by BIOS, in which case it reported SMT as permanently disabled. However, that code broke a virt hotplug scenario, where the guest is booted with only primary CPU threads, and a sibling is brought online later. The problem is that there doesn't seem to be a way to reliably distinguish between the HW "SMT disabled by BIOS" case and the virt "sibling not yet brought online" case. So the above-mentioned commit was a bit misguided, as it permanently disabled SMT for both cases, preventing future virt sibling hotplugs. Going back and reviewing the original problems which were attempted to be solved by that commit, when SMT was disabled in BIOS: 1) /sys/devices/system/cpu/smt/control showed "on" instead of "notsupported"; and 2) vmx_vm_init() was incorrectly showing the L1TF_MSG_SMT warning. I'd propose that we instead consider #1 above to not actually be a problem. Because, at least in the virt case, it's possible that SMT wasn't disabled by BIOS and a sibling thread could be brought online later. So it makes sense to just always default the smt control to "on" to allow for that possibility (assuming cpuid indicates that the CPU supports SMT). The real problem is #2, which has a simple fix: change vmx_vm_init() to query the actual current SMT state -- i.e., whether any siblings are currently online -- instead of looking at the SMT "control" sysfs value. So fix it by: a) reverting the original "fix" and its followup fix: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") bc2d8d262cba ("cpu/hotplug: Fix SMT supported evaluation") and b) changing vmx_vm_init() to query the actual current SMT state -- instead of the sysfs control value -- to determine whether the L1TF warning is needed. This also requires the 'sched_smt_present' variable to exported, instead of 'cpu_smt_control'. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Igor Mammedov Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Joe Mario Cc: Jiri Kosina Cc: Peter Zijlstra Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/e3a85d585da28cc333ecbc1e78ee9216e6da9396.1548794349.git.jpoimboe@redhat.com --- arch/x86/kernel/cpu/bugs.c | 2 +- arch/x86/kvm/vmx/vmx.c | 3 ++- include/linux/cpu.h | 2 -- kernel/cpu.c | 33 ++++----------------------------- kernel/sched/fair.c | 1 + kernel/smp.c | 2 -- 6 files changed, 8 insertions(+), 35 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1de0f4170178..01874d54f4fd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -71,7 +71,7 @@ void __init check_bugs(void) * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_check_topology_early(); + cpu_smt_check_topology(); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4341175339f3..95d618045001 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -6823,7 +6824,7 @@ static int vmx_vm_init(struct kvm *kvm) * Warn upon starting the first VM in a potentially * insecure environment. */ - if (cpu_smt_control == CPU_SMT_ENABLED) + if (sched_smt_active()) pr_warn_once(L1TF_MSG_SMT); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) pr_warn_once(L1TF_MSG_L1D); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 218df7f4d3e1..5041357d0297 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -180,12 +180,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); -extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } -static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index c0c7f64573ed..d1c6d152da89 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -376,9 +376,6 @@ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; -EXPORT_SYMBOL_GPL(cpu_smt_control); - -static bool cpu_smt_available __read_mostly; void __init cpu_smt_disable(bool force) { @@ -397,25 +394,11 @@ void __init cpu_smt_disable(bool force) /* * The decision whether SMT is supported can only be done after the full - * CPU identification. Called from architecture code before non boot CPUs - * are brought up. - */ -void __init cpu_smt_check_topology_early(void) -{ - if (!topology_smt_supported()) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; -} - -/* - * If SMT was disabled by BIOS, detect it here, after the CPUs have been - * brought online. This ensures the smt/l1tf sysfs entries are consistent - * with reality. cpu_smt_available is set to true during the bringup of non - * boot CPUs when a SMT sibling is detected. Note, this may overwrite - * cpu_smt_control's previous setting. + * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { - if (!cpu_smt_available) + if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } @@ -428,18 +411,10 @@ early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { - if (topology_is_primary_thread(cpu)) + if (cpu_smt_control == CPU_SMT_ENABLED) return true; - /* - * If the CPU is not a 'primary' thread and the booted_once bit is - * set then the processor has SMT support. Store this information - * for the late check of SMT support in cpu_smt_check_topology(). - */ - if (per_cpu(cpuhp_state, cpu).booted_once) - cpu_smt_available = true; - - if (cpu_smt_control == CPU_SMT_ENABLED) + if (topology_is_primary_thread(cpu)) return true; /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 50aa2aba69bd..310d0637fe4b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5980,6 +5980,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p #ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); +EXPORT_SYMBOL_GPL(sched_smt_present); static inline void set_idle_cores(int cpu, int val) { diff --git a/kernel/smp.c b/kernel/smp.c index 163c451af42e..f4cf1b0bb3b8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -584,8 +584,6 @@ void __init smp_init(void) num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); - /* Final decision about SMT support */ - cpu_smt_check_topology(); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } -- cgit v1.2.3 From 912139cfbfa6a2bc1da052314d2c29338dae1f6a Mon Sep 17 00:00:00 2001 From: Thomas Lendacky Date: Thu, 31 Jan 2019 14:33:06 +0000 Subject: x86/microcode/amd: Don't falsely trick the late loading mechanism The load_microcode_amd() function searches for microcode patches and attempts to apply a microcode patch if it is of different level than the currently installed level. While the processor won't actually load a level that is less than what is already installed, the logic wrongly returns UCODE_NEW thus signaling to its caller reload_store() that a late loading should be attempted. If the file-system contains an older microcode revision than what is currently running, such a late microcode reload can result in these misleading messages: x86/CPU: CPU features have changed after loading microcode, but might not take effect. x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update. These messages were issued on a system where SME/SEV are not enabled by the BIOS (MSR C001_0010[23] = 0b) because during boot, early_detect_mem_encrypt() is called and cleared the SME and SEV features in this case. However, after the wrong late load attempt, get_cpu_cap() is called and reloads the SME and SEV feature bits, resulting in the messages. Update the microcode level check to not attempt microcode loading if the current level is greater than(!) and not only equal to the current patch level. [ bp: massage commit message. ] Fixes: 2613f36ed965 ("x86/microcode: Attempt late loading only when new microcode is present") Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/154894518427.9406.8246222496874202773.stgit@tlendack-t1.amdoffice.net --- arch/x86/kernel/cpu/microcode/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 51adde0a0f1a..e1f3ba19ba54 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -855,7 +855,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) if (!p) { return ret; } else { - if (boot_cpu_data.microcode == p->patch_id) + if (boot_cpu_data.microcode >= p->patch_id) return ret; ret = UCODE_NEW; -- cgit v1.2.3 From 2aa958c99c7fd3162b089a1a56a34a0cdb778de1 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Fri, 18 Jan 2019 19:13:08 +0800 Subject: x86/kexec: Don't setup EFI info if EFI runtime is not enabled Kexec-ing a kernel with "efi=noruntime" on the first kernel's command line causes the following null pointer dereference: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] Call Trace: efi_runtime_map_copy+0x28/0x30 bzImage64_load+0x688/0x872 arch_kexec_kernel_image_load+0x6d/0x70 kimage_file_alloc_init+0x13e/0x220 __x64_sys_kexec_file_load+0x144/0x290 do_syscall_64+0x55/0x1a0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Just skip the EFI info setup if EFI runtime services are not enabled. [ bp: Massage commit message. ] Suggested-by: Dave Young Signed-off-by: Kairui Song Signed-off-by: Borislav Petkov Acked-by: Dave Young Cc: AKASHI Takahiro Cc: Andrew Morton Cc: Ard Biesheuvel Cc: bhe@redhat.com Cc: David Howells Cc: erik.schmauss@intel.com Cc: fanc.fnst@cn.fujitsu.com Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: kexec@lists.infradead.org Cc: lenb@kernel.org Cc: linux-acpi@vger.kernel.org Cc: Philipp Rudo Cc: rafael.j.wysocki@intel.com Cc: robert.moore@intel.com Cc: Thomas Gleixner Cc: x86-ml Cc: Yannik Sembritzki Link: https://lkml.kernel.org/r/20190118111310.29589-2-kasong@redhat.com --- arch/x86/kernel/kexec-bzimage64.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 0d5efa34f359..53917a3ebf94 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, struct efi_info *current_ei = &boot_params.efi_info; struct efi_info *ei = ¶ms->efi_info; + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + if (!current_ei->efi_memmap_size) return 0; -- cgit v1.2.3 From e6d429313ea5c776d2e76b4494df69102e6b7115 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 29 Jan 2019 17:44:36 -0500 Subject: x86/resctrl: Avoid confusion over the new X86_RESCTRL config "Resource Control" is a very broad term for this CPU feature, and a term that is also associated with containers, cgroups etc. This can easily cause confusion. Make the user prompt more specific. Match the config symbol name. [ bp: In the future, the corresponding ARM arch-specific code will be under ARM_CPU_RESCTRL and the arch-agnostic bits will be carved out under the CPU_RESCTRL umbrella symbol. ] Signed-off-by: Johannes Weiner Signed-off-by: Borislav Petkov Cc: Babu Moger Cc: Fenghua Yu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Morse Cc: Jonathan Corbet Cc: "Kirill A. Shutemov" Cc: linux-doc@vger.kernel.org Cc: Peter Zijlstra Cc: Pu Wen Cc: Reinette Chatre Cc: Thomas Gleixner Cc: Tony Luck Cc: x86-ml Link: https://lkml.kernel.org/r/20190130195621.GA30653@cmpxchg.org --- Documentation/x86/resctrl_ui.txt | 2 +- arch/x86/Kconfig | 6 +++--- arch/x86/include/asm/resctrl_sched.h | 4 ++-- arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/kernel/cpu/resctrl/Makefile | 4 ++-- include/linux/sched.h | 2 +- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'arch/x86/kernel') diff --git a/Documentation/x86/resctrl_ui.txt b/Documentation/x86/resctrl_ui.txt index e8e8d14d3c4e..c1f95b59e14d 100644 --- a/Documentation/x86/resctrl_ui.txt +++ b/Documentation/x86/resctrl_ui.txt @@ -9,7 +9,7 @@ Fenghua Yu Tony Luck Vikas Shivappa -This feature is enabled by the CONFIG_X86_RESCTRL and the x86 /proc/cpuinfo +This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo flag bits: RDT (Resource Director Technology) Allocation - "rdt_a" CAT (Cache Allocation Technology) - "cat_l3", "cat_l2" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 26387c7bf305..68261430fe6e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -446,12 +446,12 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config X86_RESCTRL - bool "Resource Control support" +config X86_CPU_RESCTRL + bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS help - Enable Resource Control support. + Enable x86 CPU resource control support. Provide support for the allocation and monitoring of system resources usage by the CPU. diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl_sched.h index 40ebddde6ac2..f6b7fe2833cc 100644 --- a/arch/x86/include/asm/resctrl_sched.h +++ b/arch/x86/include/asm/resctrl_sched.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_RESCTRL_SCHED_H #define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL #include #include @@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void) static inline void resctrl_sched_in(void) {} -#endif /* CONFIG_X86_RESCTRL */ +#endif /* CONFIG_X86_CPU_RESCTRL */ #endif /* _ASM_X86_RESCTRL_SCHED_H */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index b6fa0869f7aa..cfd24f9f7614 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_X86_MCE) += mce/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ -obj-$(CONFIG_X86_RESCTRL) += resctrl/ +obj-$(CONFIG_X86_CPU_RESCTRL) += resctrl/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index 1cabe6fd8e11..4a06c37b9cf1 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_X86_RESCTRL) += core.o rdtgroup.o monitor.o -obj-$(CONFIG_X86_RESCTRL) += ctrlmondata.o pseudo_lock.o +obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o pseudo_lock.o CFLAGS_pseudo_lock.o = -I$(src) diff --git a/include/linux/sched.h b/include/linux/sched.h index 224666226e87..8c328b14c424 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif -- cgit v1.2.3 From d28af26faa0b1daf3c692603d46bc4687c16f19e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 31 Jan 2019 16:33:41 -0800 Subject: x86/MCE: Initialize mce.bank in the case of a fatal error in mce_no_way_out() Internal injection testing crashed with a console log that said: mce: [Hardware Error]: CPU 7: Machine Check Exception: f Bank 0: bd80000000100134 This caused a lot of head scratching because the MCACOD (bits 15:0) of that status is a signature from an L1 data cache error. But Linux says that it found it in "Bank 0", which on this model CPU only reports L1 instruction cache errors. The answer was that Linux doesn't initialize "m->bank" in the case that it finds a fatal error in the mce_no_way_out() pre-scan of banks. If this was a local machine check, then this partially initialized struct mce is being passed to mce_panic(). Fix is simple: just initialize m->bank in the case of a fatal error. Fixes: 40c36e2741d7 ("x86/mce: Fix incorrect "Machine check from unknown source" message") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Vishal Verma Cc: x86-ml Cc: stable@vger.kernel.org # v4.18 Note pre-v5.0 arch/x86/kernel/cpu/mce/core.c was called arch/x86/kernel/cpu/mcheck/mce.c Link: https://lkml.kernel.org/r/20190201003341.10638-1-tony.luck@intel.com --- arch/x86/kernel/cpu/mce/core.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 672c7225cb1b..6ce290c506d9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -784,6 +784,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; -- cgit v1.2.3