From 35b69a420bfb56b7b74cb635ea903db05e357bec Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Nov 2018 03:48:54 +0000 Subject: clockevents/drivers/i8253: Add support for PIT shutdown quirk Add support for platforms where pit_shutdown() doesn't work because of a quirk in the PIT emulation. On these platforms setting the counter register to zero causes the PIT to start running again, negating the shutdown. Provide a global variable that controls whether the counter register is zero'ed, which platform specific code can override. 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/1541303219-11142-2-git-send-email-mikelley@microsoft.com --- drivers/clocksource/i8253.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 9c38895542f4..d4350bb10b83 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -20,6 +20,13 @@ DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); +/* + * Handle PIT quirk in pit_shutdown() where zeroing the counter register + * restarts the PIT, negating the shutdown. On platforms with the quirk, + * platform specific code can set this to false. + */ +bool i8253_clear_counter_on_shutdown __ro_after_init = true; + #ifdef CONFIG_CLKSRC_I8253 /* * Since the PIT overflows every tick, its not very useful @@ -109,8 +116,11 @@ static int pit_shutdown(struct clock_event_device *evt) raw_spin_lock(&i8253_lock); outb_p(0x30, PIT_MODE); - outb_p(0, PIT_CH0); - outb_p(0, PIT_CH0); + + if (i8253_clear_counter_on_shutdown) { + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); + } raw_spin_unlock(&i8253_lock); return 0; -- cgit v1.2.3-58-ga151 From 5d96c9342c23ee1d084802dcf064caa67ecaa45b 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 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 --- arch/x86/include/asm/mce.h | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 3 ++- drivers/acpi/nfit/mce.c | 4 ++-- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4da9b1c58d28..dbd9fe2f6163 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -221,6 +221,7 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); +bool mce_is_correctable(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 8c66d2fc8f81..77527b8ea982 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -534,7 +534,7 @@ 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; @@ -547,6 +547,7 @@ static bool mce_is_correctable(struct mce *m) return true; } +EXPORT_SYMBOL_GPL(mce_is_correctable); static bool cec_add_mce(struct mce *m) { diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index e9626bf6ca29..7a51707f87e9 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -25,8 +25,8 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, struct acpi_nfit_desc *acpi_desc; struct nfit_spa *nfit_spa; - /* We only care about memory errors */ - if (!mce_is_memory_error(mce)) + /* We only care about uncorrectable memory errors */ + if (!mce_is_memory_error(mce) || mce_is_correctable(mce)) return NOTIFY_DONE; /* -- cgit v1.2.3-58-ga151 From e8a308e5f47e545e0d41d0686c00f5f5217c5f61 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 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 --- 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 'drivers') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index dbd9fe2f6163..c1a812bd5a27 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -222,6 +222,7 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am 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 77527b8ea982..36d2696c9563 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -485,7 +485,7 @@ 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; @@ -505,6 +505,7 @@ 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 v1.2.3-58-ga151