[tip:ras/core] x86/RAS/AMD: Reduce the number of IPIs when prepping error injection

[tip-bot for Yazen Ghannam]

Commit-ID:  340e983ab8afd02b59d698dd1365d7773bf136b3
Gitweb:     http://git.kernel.org/tip/340e983ab8afd02b59d698dd1365d7773bf136b3
Author:     Yazen Ghannam <Yazen.Ghannam@xxxxxxx>
AuthorDate: Fri, 8 Jul 2016 11:09:39 +0200
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Fri, 8 Jul 2016 11:29:26 +0200

x86/RAS/AMD: Reduce the number of IPIs when prepping error injection

We currently use wrmsr_on_cpu() 4 times when prepping for an error
injection. This will generate 4 IPIs for each MSR write. We can reduce
the number of IPIs to 1 by grouping the MSR writes and executing them
serially on the appropriate CPU.

Suggested-by: Borislav Petkov <bp@xxxxxxx>
Signed-off-by: Yazen Ghannam <Yazen.Ghannam@xxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Aravind Gopalakrishnan <aravindksg.lkml@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: linux-edac <linux-edac@xxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1467968983-4874-3-git-send-email-bp@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/ras/mce_amd_inj.c | 58 ++++++++++++++++++++++------------------------
 1 file changed, 28 insertions(+), 30 deletions(-)

diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index e69f470..1104515 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -241,6 +241,31 @@ static void toggle_nb_mca_mst_cpu(u16 nid)
 		       __func__, PCI_FUNC(F3->devfn), NBCFG);
 }
 
+static void prepare_msrs(void *info)
+{
+	struct mce i_mce = *(struct mce *)info;
+	u8 b = i_mce.bank;
+
+	wrmsrl(MSR_IA32_MCG_STATUS, i_mce.mcgstatus);
+
+	if (boot_cpu_has(X86_FEATURE_SMCA)) {
+		if (i_mce.inject_flags == DFR_INT_INJ) {
+			wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), i_mce.status);
+			wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), i_mce.addr);
+		} else {
+			wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), i_mce.status);
+			wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), i_mce.addr);
+		}
+
+		wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), i_mce.misc);
+	} else {
+		wrmsrl(MSR_IA32_MCx_STATUS(b), i_mce.status);
+		wrmsrl(MSR_IA32_MCx_ADDR(b), i_mce.addr);
+		wrmsrl(MSR_IA32_MCx_MISC(b), i_mce.misc);
+	}
+
+}
+
 static void do_inject(void)
 {
 	u64 mcg_status = 0;
@@ -287,36 +312,9 @@ static void do_inject(void)
 
 	toggle_hw_mce_inject(cpu, true);
 
-	wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS,
-		     (u32)mcg_status, (u32)(mcg_status >> 32));
-
-	if (boot_cpu_has(X86_FEATURE_SMCA)) {
-		if (inj_type == DFR_INT_INJ) {
-			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DESTAT(b),
-				     (u32)i_mce.status, (u32)(i_mce.status >> 32));
-
-			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DEADDR(b),
-				     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
-		} else {
-			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_STATUS(b),
-				     (u32)i_mce.status, (u32)(i_mce.status >> 32));
-
-			wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_ADDR(b),
-				     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
-		}
-
-		wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(b),
-			     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
-	} else {
-		wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b),
-			     (u32)i_mce.status, (u32)(i_mce.status >> 32));
-
-		wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b),
-			     (u32)i_mce.addr, (u32)(i_mce.addr >> 32));
-
-		wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b),
-			     (u32)i_mce.misc, (u32)(i_mce.misc >> 32));
-	}
+	i_mce.mcgstatus = mcg_status;
+	i_mce.inject_flags = inj_type;
+	smp_call_function_single(cpu, prepare_msrs, &i_mce, 0);
 
 	toggle_hw_mce_inject(cpu, false);