diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-03 17:51:33 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-03 17:51:33 -0800 |
commit | b831ef2cad979912850e34f82415c0c5d59de8cb (patch) | |
tree | 38bcd57fbb4dcce38a0ca926b1b765fd5e16cab2 /arch/x86/ras/mce_amd_inj.c | |
parent | b02ac6b18cd4e2c76bf0a102c20c429b973f5f76 (diff) | |
parent | dc34bdd2367fd31744ee3ba1de1b1cc0fa2ce193 (diff) | |
download | linux-b831ef2cad979912850e34f82415c0c5d59de8cb.tar.bz2 |
Merge branch 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RAS changes from Ingo Molnar:
"The main system reliability related changes were from x86, but also
some generic RAS changes:
- AMD MCE error injection subsystem enhancements. (Aravind
Gopalakrishnan)
- Fix MCE and CPU hotplug interaction bug. (Ashok Raj)
- kcrash bootup robustness fix. (Baoquan He)
- kcrash cleanups. (Borislav Petkov)
- x86 microcode driver rework: simplify it by unmodularizing it and
other cleanups. (Borislav Petkov)"
* 'ras-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
x86/mce: Add a default case to the switch in __mcheck_cpu_ancient_init()
x86/mce: Add a Scalable MCA vendor flags bit
MAINTAINERS: Unify the microcode driver section
x86/microcode/intel: Move #ifdef DEBUG inside the function
x86/microcode/amd: Remove maintainers from comments
x86/microcode: Remove modularization leftovers
x86/microcode: Merge the early microcode loader
x86/microcode: Unmodularize the microcode driver
x86/mce: Fix thermal throttling reporting after kexec
kexec/crash: Say which char is the unrecognized
x86/setup/crash: Check memblock_reserve() retval
x86/setup/crash: Cleanup some more
x86/setup/crash: Remove alignment variable
x86/setup: Cleanup crashkernel reservation functions
x86/amd_nb, EDAC: Rename amd_get_node_id()
x86/setup: Do not reserve crashkernel high memory if low reservation failed
x86/microcode/amd: Do not overwrite final patch levels
x86/microcode/amd: Extract current patch level read to a function
x86/ras/mce_amd_inj: Inject bank 4 errors on the NBC
x86/ras/mce_amd_inj: Trigger deferred and thresholding errors interrupts
...
Diffstat (limited to 'arch/x86/ras/mce_amd_inj.c')
-rw-r--r-- | arch/x86/ras/mce_amd_inj.c | 103 |
1 files changed, 96 insertions, 7 deletions
diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 17e35b5bf779..55d38cfa46c2 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -17,7 +17,11 @@ #include <linux/cpu.h> #include <linux/string.h> #include <linux/uaccess.h> +#include <linux/pci.h> + #include <asm/mce.h> +#include <asm/amd_nb.h> +#include <asm/irq_vectors.h> #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 |