[PATCH] arm64 memory accesses may cause undefined fault on Fujitsu-A64FX
From: Zhang, Lei
Date: Fri Jan 18 2019 - 08:04:04 EST
On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1),
memory accesses may cause undefined fault (Data abort, DFSC=0b111111).
This problem will be fixed by next version of Fujitsu-A64FX.
I would like to post a workaround to avoid this problem
on existing version.
The workaround is to replace the fault handler for Data abort
DFSC=0b111111 with a new one to ignore this undefined fault,
which will only affect the Fujitsu-A64FX.
I have tested this patch on A64FX and QEMU(2.9.0).The test passed.
I will test this patch on ThunderX and report the result.
I fully appreciate that if someone can test this patch on different
chips to verity no harmful effect on other chips.
If there is no problem on other chips, please merge this patch.
Below is my patch based on linux-5.0-rc2.
Signed-off-by: Lei Zhang <zhang.lei@xxxxxxxxxxxxxx>
Tested-by: Lei Zhang <zhang.lei@xxxxxxxxxxxxxx>
---
Documentation/arm64/silicon-errata.txt | 1 +
arch/arm64/Kconfig | 13 +++++++++++++
arch/arm64/include/asm/cputype.h | 4 ++++
arch/arm64/mm/fault.c | 23 +++++++++++++++++++++++
4 files changed, 41 insertions(+)
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index 1f09d04..26d64e9 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -80,3 +80,4 @@ stable kernels.
| Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 |
| Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 |
| Qualcomm Tech. | Falkor v{1,2} | E1041 | QCOM_FALKOR_ERRATUM_1041 |
+| Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a4168d3..9c09b2b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -643,6 +643,19 @@ config QCOM_FALKOR_ERRATUM_E1041
If unsure, say Y.
+config FUJITSU_ERRATUM_010001
+ bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
+ default y
+ help
+ This option adds workaround for Fujitsu-A64FX erratum E#010001.
+ On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory accesses
+ may cause undefined fault (Data abort, DFSC=0b111111).
+ The workaround is to replace the fault handler for Data abort DFSC=0b111111
+ with a new one to ignore this undefined fault, which will only affect
+ the Fujitsu-A64FX.
+
+ If unsure, say Y.
+
endmenu
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 951ed1a..166aa50 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -76,6 +76,7 @@
#define ARM_CPU_IMP_BRCM 0x42
#define ARM_CPU_IMP_QCOM 0x51
#define ARM_CPU_IMP_NVIDIA 0x4E
+#define ARM_CPU_IMP_FUJITSU 0x46
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -104,6 +105,8 @@
#define NVIDIA_CPU_PART_DENVER 0x003
#define NVIDIA_CPU_PART_CARMEL 0x004
+#define FUJTISU_CPU_PART_A64FX 0x001
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -122,6 +125,7 @@
#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
+#define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJTISU_CPU_PART_A64FX)
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index efb7b2c..c465b2f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -666,6 +666,25 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
return 0;
}
+static bool do_bad_ignore_first = FALSE;
+static int do_bad_ignore(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+ if (do_bad_ignore_first == TRUE)
+ return 0;
+ if (do_bad_ignore_first == FALSE) {
+ unsigned int current_cpu_midr = read_cpuid_id();
+ const struct midr_range fujitsu_a64fx_midr_range = {
+ MIDR_FUJITSU_A64FX, MIDR_CPU_VAR_REV(0, 0), MIDR_CPU_VAR_REV(1, 0)
+ };
+
+ if (is_midr_in_range(current_cpu_midr, &fujitsu_a64fx_midr_range) == TRUE) {
+ do_bad_ignore_first = TRUE;
+ return 0;
+ }
+ }
+ return 1; /* "fault" same as do_bad */
+}
+
static const struct fault_info fault_info[] = {
{ do_bad, SIGKILL, SI_KERNEL, "ttbr address size fault" },
{ do_bad, SIGKILL, SI_KERNEL, "level 1 address size fault" },
@@ -730,7 +749,11 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{ do_bad, SIGKILL, SI_KERNEL, "unknown 60" },
{ do_bad, SIGKILL, SI_KERNEL, "section domain fault" },
{ do_bad, SIGKILL, SI_KERNEL, "page domain fault" },
+#ifdef CONFIG_FUJITSU_ERRATUM_010001
+ { do_bad_ignore, SIGKILL, SI_KERNEL, "unknown 63" },
+#else
{ do_bad, SIGKILL, SI_KERNEL, "unknown 63" },
+#endif
};
int handle_guest_sea(phys_addr_t addr, unsigned int esr)
---
Best regards,
Lei Zhang
zhang.lei@xxxxxxxxxxxxxx