From 3bff147b187d5dfccfca1ee231b0761a89f1eff5 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 23 Aug 2021 17:31:29 -0700 Subject: x86/mce: Defer processing of early errors When a fatal machine check results in a system reset, Linux does not clear the error(s) from machine check bank(s) - hardware preserves the machine check banks across a warm reset. During initialization of the kernel after the reboot, Linux reads, logs, and clears all machine check banks. But there is a problem. In: 5de97c9f6d85 ("x86/mce: Factor out and deprecate the /dev/mcelog driver") the call to mce_register_decode_chain() moved later in the boot sequence. This means that /dev/mcelog doesn't see those early error logs. This was partially fixed by: cd9c57cad3fe ("x86/MCE: Dump MCE to dmesg if no consumers") which made sure that the logs were not lost completely by printing to the console. But parsing console logs is error prone. Users of /dev/mcelog should expect to find any early errors logged to standard places. Add a new flag MCP_QUEUE_LOG to machine_check_poll() to be used in early machine check initialization to indicate that any errors found should just be queued to genpool. When mcheck_late_init() is called it will call mce_schedule_work() to actually log and flush any errors queued in the genpool. [ Based on an original patch, commit message by and completely productized by Tony Luck. ] Fixes: 5de97c9f6d85 ("x86/mce: Factor out and deprecate the /dev/mcelog driver") Reported-by: Sumanth Kamatala Signed-off-by: Borislav Petkov Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210824003129.GA1642753@agluck-desk2.amr.corp.intel.com --- arch/x86/include/asm/mce.h | 1 + arch/x86/kernel/cpu/mce/core.c | 11 ++++++++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 0607ec4f5091..da9321548f6f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -265,6 +265,7 @@ enum mcp_flags { MCP_TIMESTAMP = BIT(0), /* log time stamp */ MCP_UC = BIT(1), /* log uncorrected errors */ MCP_DONTLOG = BIT(2), /* only clear, don't log */ + MCP_QUEUE_LOG = BIT(3), /* only queue to genpool */ }; bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 22791aadc085..8cb7816d03b4 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -817,7 +817,10 @@ log_it: if (mca_cfg.dont_log_ce && !mce_usable_address(&m)) goto clear_it; - mce_log(&m); + if (flags & MCP_QUEUE_LOG) + mce_gen_pool_add(&m); + else + mce_log(&m); clear_it: /* @@ -1639,10 +1642,12 @@ static void __mcheck_cpu_init_generic(void) m_fl = MCP_DONTLOG; /* - * Log the machine checks left over from the previous reset. + * Log the machine checks left over from the previous reset. Log them + * only, do not start processing them. That will happen in mcheck_late_init() + * when all consumers have been registered on the notifier chain. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC | m_fl, &all_banks); + machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks); cr4_set_bits(X86_CR4_MCE); -- cgit v1.2.3