From cdd219834f93c2e83bf8045b212332e221727bda Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 25 Oct 2018 18:37:28 -0600 Subject: acpi/nfit, x86/mce: Handle only uncorrectable machine checks commit 5d96c9342c23ee1d084802dcf064caa67ecaa45b upstream. The MCE handler for nfit devices is called for memory errors on a Non-Volatile DIMM and adds the error location to a 'badblocks' list. This list is used by the various NVDIMM drivers to avoid consuming known poison locations during IO. The MCE handler gets called for both corrected and uncorrectable errors. Until now, both kinds of errors have been added to the badblocks list. However, corrected memory errors indicate that the problem has already been fixed by hardware, and the resulting interrupt is merely a notification to Linux. As far as future accesses to that location are concerned, it is perfectly fine to use, and thus doesn't need to be included in the above badblocks list. Add a check in the nfit MCE handler to filter out corrected mce events, and only process uncorrectable errors. Fixes: 6839a6d96f4e ("nfit: do an ARS scrub on hitting a latent media error") Reported-by: Omar Avelar Signed-off-by: Vishal Verma Signed-off-by: Borislav Petkov CC: Arnd Bergmann CC: Dan Williams CC: Dave Jiang CC: elliott@hpe.com CC: "H. Peter Anvin" CC: Ingo Molnar CC: Len Brown CC: linux-acpi@vger.kernel.org CC: linux-edac CC: linux-nvdimm@lists.01.org CC: Qiuxu Zhuo CC: "Rafael J. Wysocki" CC: Ross Zwisler CC: stable CC: Thomas Gleixner CC: Tony Luck CC: x86-ml CC: Yazen Ghannam Link: http://lkml.kernel.org/r/20181026003729.8420-1-vishal.l.verma@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/mcheck/mce.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c50754c09c1..f442115a3725 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -538,7 +538,7 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); -static bool mce_is_correctable(struct mce *m) +bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) return false; @@ -548,6 +548,7 @@ static bool mce_is_correctable(struct mce *m) return true; } +EXPORT_SYMBOL_GPL(mce_is_correctable); static bool cec_add_mce(struct mce *m) { -- cgit v1.2.3 From 13bb0de8e25c9f2fa846ee92c1f8a736a54423aa Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 25 Oct 2018 18:37:29 -0600 Subject: acpi/nfit, x86/mce: Validate a MCE's address before using it commit e8a308e5f47e545e0d41d0686c00f5f5217c5f61 upstream. The NFIT machine check handler uses the physical address from the mce structure, and compares it against information in the ACPI NFIT table to determine whether that location lies on an NVDIMM. The mce->addr field however may not always be valid, and this is indicated by the MCI_STATUS_ADDRV bit in the status field. Export mce_usable_address() which already performs validation for the address, and use it in the NFIT handler. Fixes: 6839a6d96f4e ("nfit: do an ARS scrub on hitting a latent media error") Reported-by: Robert Elliott Signed-off-by: Vishal Verma Signed-off-by: Borislav Petkov CC: Arnd Bergmann Cc: Dan Williams CC: Dave Jiang CC: elliott@hpe.com CC: "H. Peter Anvin" CC: Ingo Molnar CC: Len Brown CC: linux-acpi@vger.kernel.org CC: linux-edac CC: linux-nvdimm@lists.01.org CC: Qiuxu Zhuo CC: "Rafael J. Wysocki" CC: Ross Zwisler CC: stable CC: Thomas Gleixner CC: Tony Luck CC: x86-ml CC: Yazen Ghannam Link: http://lkml.kernel.org/r/20181026003729.8420-2-vishal.l.verma@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/mce.h | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 3 ++- drivers/acpi/nfit/mce.c | 4 ++++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 3111b3cee2ee..eb786f90f2d3 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -217,6 +217,7 @@ static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *s int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); +int mce_usable_address(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index f442115a3725..c51b9d116be1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -489,7 +489,7 @@ static void mce_report_event(struct pt_regs *regs) * be somewhat complicated (e.g. segment offset would require an instruction * parser). So only support physical addresses up to page granuality for now. */ -static int mce_usable_address(struct mce *m) +int mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_ADDRV)) return 0; @@ -509,6 +509,7 @@ static int mce_usable_address(struct mce *m) return 1; } +EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index 7a51707f87e9..d6c1b10f6c25 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -29,6 +29,10 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, if (!mce_is_memory_error(mce) || mce_is_correctable(mce)) return NOTIFY_DONE; + /* Verify the address reported in the MCE is valid. */ + if (!mce_usable_address(mce)) + return NOTIFY_DONE; + /* * mce->addr contains the physical addr accessed that caused the * machine check. We need to walk through the list of NFITs, and see -- cgit v1.2.3 From bcdff99a9348344424d25994dda9dedef5d3edd3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 9 Nov 2018 15:22:07 -0500 Subject: x86/cpu/vmware: Do not trace vmware_sched_clock() commit 15035388439f892017d38b05214d3cda6578af64 upstream. When running function tracing on a Linux guest running on VMware Workstation, the guest would crash. This is due to tracing of the sched_clock internal call of the VMware vmware_sched_clock(), which causes an infinite recursion within the tracing code (clock calls must not be traced). Make vmware_sched_clock() not traced by ftrace. Fixes: 80e9a4f21fd7c ("x86/vmware: Add paravirt sched clock") Reported-by: GwanYeong Kim Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Borislav Petkov CC: Alok Kataria CC: GwanYeong Kim CC: "H. Peter Anvin" CC: Ingo Molnar Cc: stable@vger.kernel.org CC: Thomas Gleixner CC: virtualization@lists.linux-foundation.org CC: x86-ml Link: http://lkml.kernel.org/r/20181109152207.4d3e7d70@gandalf.local.home Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/vmware.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 8e005329648b..d805202c63cd 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s) } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); -static unsigned long long vmware_sched_clock(void) +static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; -- cgit v1.2.3 From d74a4fc841cf6384aa3f4b5cdf3ea86fd94e2bae Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Nov 2018 03:48:57 +0000 Subject: x86/hyper-v: Enable PIT shutdown quirk commit 1de72c706488b7be664a601cf3843bd01e327e58 upstream. Hyper-V emulation of the PIT has a quirk such that the normal PIT shutdown path doesn't work, because clearing the counter register restarts the timer. Disable the counter clearing on PIT shutdown. Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Cc: "gregkh@linuxfoundation.org" Cc: "devel@linuxdriverproject.org" Cc: "daniel.lezcano@linaro.org" Cc: "virtualization@lists.linux-foundation.org" Cc: "jgross@suse.com" Cc: "akataria@vmware.com" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: vkuznets Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: KY Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1541303219-11142-3-git-send-email-mikelley@microsoft.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/mshyperv.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 031082c96db8..12a67046fefb 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -285,6 +286,16 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + /* + * Hyper-V VMs have a PIT emulation quirk such that zeroing the + * counter register during PIT shutdown restarts the PIT. So it + * continues to interrupt @18.2 HZ. Setting i8253_clear_counter + * to false tells pit_shutdown() not to zero the counter so that + * the PIT really is shutdown. Generation 2 VMs don't have a PIT, + * and setting this value has no effect. + */ + i8253_clear_counter_on_shutdown = false; + #if IS_ENABLED(CONFIG_HYPERV) /* * Setup the hook to get control post apic initialization. -- cgit v1.2.3