From b4b7ff4b08e691656c9d77c758fc355833128ac0 Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Wed, 20 Jan 2016 14:01:31 -0300 Subject: Linux-libre 4.4-gnu --- arch/x86/ras/Kconfig | 4 +- arch/x86/ras/mce_amd_inj.c | 103 ++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 97 insertions(+), 10 deletions(-) (limited to 'arch/x86/ras') diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index 10fea5fc8..df280da34 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,11 +1,9 @@ config AMD_MCE_INJ tristate "Simple MCE injection interface for AMD processors" - depends on RAS && EDAC_DECODE_MCE && DEBUG_FS + depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB default n help This is a simple debugfs interface to inject MCEs and test different aspects of the MCE handling code. WARNING: Do not even assume this interface is staying stable! - - diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 17e35b5bf..55d38cfa4 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -17,7 +17,11 @@ #include #include #include +#include + #include +#include +#include #include "../kernel/cpu/mcheck/mce-internal.h" @@ -30,16 +34,21 @@ static struct dentry *dfs_inj; static u8 n_banks; #define MAX_FLAG_OPT_SIZE 3 +#define NBCFG 0x44 enum injection_type { SW_INJ = 0, /* SW injection, simply decode the error */ HW_INJ, /* Trigger a #MC */ + DFR_INT_INJ, /* Trigger Deferred error interrupt */ + THR_INT_INJ, /* Trigger threshold interrupt */ N_INJ_TYPES, }; static const char * const flags_options[] = { [SW_INJ] = "sw", [HW_INJ] = "hw", + [DFR_INT_INJ] = "df", + [THR_INT_INJ] = "th", NULL }; @@ -129,12 +138,9 @@ static ssize_t flags_write(struct file *filp, const char __user *ubuf, { char buf[MAX_FLAG_OPT_SIZE], *__buf; int err; - size_t ret; if (cnt > MAX_FLAG_OPT_SIZE) - cnt = MAX_FLAG_OPT_SIZE; - - ret = cnt; + return -EINVAL; if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; @@ -150,9 +156,9 @@ static ssize_t flags_write(struct file *filp, const char __user *ubuf, return err; } - *ppos += ret; + *ppos += cnt; - return ret; + return cnt; } static const struct file_operations flags_fops = { @@ -185,6 +191,55 @@ static void trigger_mce(void *info) asm volatile("int $18"); } +static void trigger_dfr_int(void *info) +{ + asm volatile("int %0" :: "i" (DEFERRED_ERROR_VECTOR)); +} + +static void trigger_thr_int(void *info) +{ + asm volatile("int %0" :: "i" (THRESHOLD_APIC_VECTOR)); +} + +static u32 get_nbc_for_node(int node_id) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + u32 cores_per_node; + + cores_per_node = c->x86_max_cores / amd_get_nodes_per_socket(); + + return cores_per_node * node_id; +} + +static void toggle_nb_mca_mst_cpu(u16 nid) +{ + struct pci_dev *F3 = node_to_amd_nb(nid)->misc; + u32 val; + int err; + + if (!F3) + return; + + err = pci_read_config_dword(F3, NBCFG, &val); + if (err) { + pr_err("%s: Error reading F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); + return; + } + + if (val & BIT(27)) + return; + + pr_err("%s: Set D18F3x44[NbMcaToMstCpuEn] which BIOS hasn't done.\n", + __func__); + + val |= BIT(27); + err = pci_write_config_dword(F3, NBCFG, val); + if (err) + pr_err("%s: Error writing F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); +} + static void do_inject(void) { u64 mcg_status = 0; @@ -205,6 +260,26 @@ static void do_inject(void) if (!(i_mce.status & MCI_STATUS_PCC)) mcg_status |= MCG_STATUS_RIPV; + /* + * Ensure necessary status bits for deferred errors: + * - MCx_STATUS[Deferred]: make sure it is a deferred error + * - MCx_STATUS[UC] cleared: deferred errors are _not_ UC + */ + if (inj_type == DFR_INT_INJ) { + i_mce.status |= MCI_STATUS_DEFERRED; + i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + } + + /* + * For multi node CPUs, logging and reporting of bank 4 errors happens + * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for + * Fam10h and later BKDGs. + */ + if (static_cpu_has(X86_FEATURE_AMD_DCM) && b == 4) { + toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); + cpu = get_nbc_for_node(amd_get_nb_id(cpu)); + } + get_online_cpus(); if (!cpu_online(cpu)) goto err; @@ -225,7 +300,16 @@ static void do_inject(void) toggle_hw_mce_inject(cpu, false); - smp_call_function_single(cpu, trigger_mce, NULL, 0); + switch (inj_type) { + case DFR_INT_INJ: + smp_call_function_single(cpu, trigger_dfr_int, NULL, 0); + break; + case THR_INT_INJ: + smp_call_function_single(cpu, trigger_thr_int, NULL, 0); + break; + default: + smp_call_function_single(cpu, trigger_mce, NULL, 0); + } err: put_online_cpus(); @@ -290,6 +374,11 @@ static const char readme_msg[] = "\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" "\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" "\t before injecting.\n" +"\t - \"df\": Trigger APIC interrupt for Deferred error. Causes deferred \n" +"\t error APIC interrupt handler to handle the error if the feature is \n" +"\t is present in hardware. \n" +"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" +"\t APIC interrupt handler to handle the error. \n" "\n"; static ssize_t -- cgit v1.2.3-54-g00ecf