x86/ras/mce_amd_inj: Inject bank 4 errors on the NBC

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>
[ Cleanup comments. ]
[ Add a missing dependency on AMD_NB caught by Randy Dunlap. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1443190851-2172-4-git-send-email-Aravind.Gopalakrishnan@amd.com
Link: http://lkml.kernel.org/r/1444641762-9437-5-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index 10fea5fc821e16f450121a550cc00ea214cc4469..df280da348255de9178c0c98cdb1f66b31f13f49 100644 (file)
--- 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 4d3bafb540c2e6cebd4ac51346c11fcc38d15c1e..55d38cfa46c2626c6d2f85587da27c05ca3e6bf7 100644 (file)
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -17,8 +17,10 @@
 #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"
@@ -32,6 +34,7 @@ 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 */
@@ -198,6 +201,45 @@ 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;
@@ -228,6 +270,16 @@ 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) {
+               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;