lkml.org 
[lkml]   [2015]   [Sep]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH V2 3/3] RAS, mce_amd_inj: Inject errors on NBC for bank 4 errors
Date
Bank 4 MCEs are logged and reported only on the node base core (NBC) in
a socket. Refer to the D18F3x44[NbMcaToMstCpuEn] field in Fam10h and
later BKDGs. The node base core (NBC) is the lowest numbered core in the
node.

This patch ensures that we inject the error on the NBC for bank 4
errors. Otherwise, triggering #MC or APIC interrupts on a core which is
not the NBC would not have any effect on the system, i.e we would not
see any relevant output on kernel logs for the error we just injected.

Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
---
arch/x86/ras/mce_amd_inj.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 56 insertions(+)

diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 794ca1f..42ab672 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -17,7 +17,9 @@
#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 "../kernel/cpu/mcheck/mce-internal.h"

@@ -30,6 +32,7 @@ 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 */
@@ -196,6 +199,45 @@ 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;
@@ -230,6 +272,20 @@ static void do_inject(void)
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) {
+ /*
+ * BIOS sets D18F3x44[NbMcaToMstCpuEn] by default. But make
+ * sure of it here just in case.
+ */
+ 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;
--
2.4.0


\
 
 \ /
  Last update: 2015-09-25 21:21    [W:0.042 / U:0.588 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site