RAS: Report ARM processor information to userspace

Commit Message

Shengwei Luo Jan. 24, 2022, 9:30 a.m. UTC

From: Shengwei Luo <[e-mail]>

The ARM processor error section includes several ARM processor error
information, several ARM processor context information and several
vendor specific error information structures. In addition to these
info, there are error severity and cpu logical index about the event.
Report all of these information to userspace via perf i/f.

Original-Author: Jason Tian <[e-mail]>
Signed-off-by: Shengwei Luo <[e-mail]>
---
 drivers/acpi/apei/ghes.c |  3 +--
 drivers/ras/ras.c        | 46 ++++++++++++++++++++++++++++++++++++--
 include/linux/ras.h      | 15 +++++++++++--
 include/ras/ras_event.h  | 48 +++++++++++++++++++++++++++++++++++-----
 4 files changed, 101 insertions(+), 11 deletions(-)

Comments

kernel test robot Jan. 25, 2022, 2:35 a.m. UTC | #1

Hi,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linux/master]
[also build test WARNING on rafael-pm/linux-next linus/master v5.17-rc1 next-20220124]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/lostway-zju-edu-cn/RAS-Report-ARM-processor-information-to-userspace/20220124-174203
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 2c271fe77d52a0555161926c232cd5bc07178b39
config: x86_64-randconfig-m001-20220124 (https://download.01.org/0day-ci/archive/20220125/[e-mail]/config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[e-mail]>

smatch warnings:
drivers/ras/ras.c:51 log_arm_hw_error() warn: unsigned 'vsei_len' is never less than zero.

vim +/vsei_len +51 drivers/ras/ras.c

    23	
    24	void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev)
    25	{
    26		u32 pei_len;
    27		u32 ctx_len = 0;
    28		u32 vsei_len;
    29		u8 *pei_err;
    30		u8 *ctx_err;
    31		u8 *ven_err_data;
    32		struct cper_arm_err_info *err_info;
    33		struct cper_arm_ctx_info *ctx_info;
    34		int n, sz;
    35		int cpu;
    36	
    37		pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num;
    38		pei_err = (u8 *)err + sizeof(struct cper_sec_proc_arm);
    39	
    40		err_info = (struct cper_arm_err_info *)(err + 1);
    41		ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num);
    42		ctx_err = (u8 *)ctx_info;
    43		for (n = 0; n < err->context_info_num; n++) {
    44			sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
    45			ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
    46			ctx_len += sz;
    47		}
    48	
    49		vsei_len = err->section_length - (sizeof(struct cper_sec_proc_arm) +
    50							pei_len + ctx_len);
  > 51		if (vsei_len < 0) {
    52			pr_warn(FW_BUG
    53				"section length: %d\n", err->section_length);
    54			pr_warn(FW_BUG
    55				"section length is too small\n");
    56			pr_warn(FW_BUG
    57				"firmware-generated error record is incorrect\n");
    58			vsei_len = 0;
    59		}
    60		ven_err_data = (u8 *)ctx_info;
    61	
    62		cpu = GET_LOGICAL_INDEX(err->mpidr);
    63		/* when return value is invalid, set cpu index to -1 */
    64		if (cpu < 0)
    65			cpu = -1;
    66	
    67		trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len,
    68				ven_err_data, vsei_len, sev, cpu);
    69	}
    70	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[e-mail]

Patch

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0c5c9acc6254..f824c26057b1 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -490,9 +490,8 @@  static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s
 	int sec_sev, i;
 	char *p;
 
-	log_arm_hw_error(err);
-
 	sec_sev = ghes_severity(gdata->error_severity);
+	log_arm_hw_error(err, sec_sev);
 	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
 		return false;
 
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 95540ea8dd9d..1ec1e51f457c 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -21,9 +21,51 @@  void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id,
 	trace_non_standard_event(sec_type, fru_id, fru_text, sev, err, len);
 }
 
-void log_arm_hw_error(struct cper_sec_proc_arm *err)
+void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev)
 {
-	trace_arm_event(err);
+	u32 pei_len;
+	u32 ctx_len = 0;
+	u32 vsei_len;
+	u8 *pei_err;
+	u8 *ctx_err;
+	u8 *ven_err_data;
+	struct cper_arm_err_info *err_info;
+	struct cper_arm_ctx_info *ctx_info;
+	int n, sz;
+	int cpu;
+
+	pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num;
+	pei_err = (u8 *)err + sizeof(struct cper_sec_proc_arm);
+
+	err_info = (struct cper_arm_err_info *)(err + 1);
+	ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num);
+	ctx_err = (u8 *)ctx_info;
+	for (n = 0; n < err->context_info_num; n++) {
+		sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
+		ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
+		ctx_len += sz;
+	}
+
+	vsei_len = err->section_length - (sizeof(struct cper_sec_proc_arm) +
+						pei_len + ctx_len);
+	if (vsei_len < 0) {
+		pr_warn(FW_BUG
+			"section length: %d\n", err->section_length);
+		pr_warn(FW_BUG
+			"section length is too small\n");
+		pr_warn(FW_BUG
+			"firmware-generated error record is incorrect\n");
+		vsei_len = 0;
+	}
+	ven_err_data = (u8 *)ctx_info;
+
+	cpu = GET_LOGICAL_INDEX(err->mpidr);
+	/* when return value is invalid, set cpu index to -1 */
+	if (cpu < 0)
+		cpu = -1;
+
+	trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len,
+			ven_err_data, vsei_len, sev, cpu);
 }
 
 static int __init ras_init(void)
diff --git a/include/linux/ras.h b/include/linux/ras.h
index 1f4048bf2674..4529775374d0 100644
--- a/include/linux/ras.h
+++ b/include/linux/ras.h
@@ -24,7 +24,7 @@  int __init parse_cec_param(char *str);
 void log_non_standard_event(const guid_t *sec_type,
 			    const guid_t *fru_id, const char *fru_text,
 			    const u8 sev, const u8 *err, const u32 len);
-void log_arm_hw_error(struct cper_sec_proc_arm *err);
+void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev);
 #else
 static inline void
 log_non_standard_event(const guid_t *sec_type,
@@ -32,7 +32,18 @@  log_non_standard_event(const guid_t *sec_type,
 		       const u8 sev, const u8 *err, const u32 len)
 { return; }
 static inline void
-log_arm_hw_error(struct cper_sec_proc_arm *err) { return; }
+log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) { return; }
 #endif
 
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+#include <asm/smp_plat.h>
+/*
+ * Include ARM specific SMP header which provides a function mapping mpidr to
+ * cpu logical index.
+ */
+#define GET_LOGICAL_INDEX(mpidr) get_logical_index(mpidr & MPIDR_HWID_BITMASK)
+#else
+#define GET_LOGICAL_INDEX(mpidr) -EINVAL
+#endif /* CONFIG_ARM || CONFIG_ARM64 */
+
 #endif /* __RAS_H__ */
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index d0337a41141c..92cfb61bdb20 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -168,11 +168,24 @@  TRACE_EVENT(mc_event,
  * This event is generated when hardware detects an ARM processor error
  * has occurred. UEFI 2.6 spec section N.2.4.4.
  */
+#define APEIL "ARM Processor Err Info data len"
+#define APEID "ARM Processor Err Info raw data"
+#define APECIL "ARM Processor Err Context Info data len"
+#define APECID "ARM Processor Err Context Info raw data"
+#define VSEIL "Vendor Specific Err Info data len"
+#define VSEID "Vendor Specific Err Info raw data"
 TRACE_EVENT(arm_event,
 
-	TP_PROTO(const struct cper_sec_proc_arm *proc),
+	TP_PROTO(const struct cper_sec_proc_arm *proc, const u8 *pei_err,
+			const u32 pei_len,
+			const u8 *ctx_err,
+			const u32 ctx_len,
+			const u8 *oem,
+			const u32 oem_len,
+			u8 sev,
+			int cpu),
 
-	TP_ARGS(proc),
+	TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev, cpu),
 
 	TP_STRUCT__entry(
 		__field(u64, mpidr)
@@ -180,6 +193,14 @@  TRACE_EVENT(arm_event,
 		__field(u32, running_state)
 		__field(u32, psci_state)
 		__field(u8, affinity)
+		__field(u32, pei_len)
+		__dynamic_array(u8, buf, pei_len)
+		__field(u32, ctx_len)
+		__dynamic_array(u8, buf1, ctx_len)
+		__field(u32, oem_len)
+		__dynamic_array(u8, buf2, oem_len)
+		__field(u8, sev)
+		__field(int, cpu)
 	),
 
 	TP_fast_assign(
@@ -199,12 +220,29 @@  TRACE_EVENT(arm_event,
 			__entry->running_state = ~0;
 			__entry->psci_state = ~0;
 		}
+		__entry->pei_len = pei_len;
+		memcpy(__get_dynamic_array(buf), pei_err, pei_len);
+		__entry->ctx_len = ctx_len;
+		memcpy(__get_dynamic_array(buf1), ctx_err, ctx_len);
+		__entry->oem_len = oem_len;
+		memcpy(__get_dynamic_array(buf2), oem, oem_len);
+		__entry->sev = sev;
+		__entry->cpu = cpu;
 	),
 
-	TP_printk("affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
-		  "running state: %d; PSCI state: %d",
+	TP_printk("cpu: %d; error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
+		  "running state: %d; PSCI state: %d; "
+		  "%s: %d; %s: %s; %s: %d; %s: %s; %s: %d; %s: %s",
+		  __entry->cpu,
+		  __entry->sev,
 		  __entry->affinity, __entry->mpidr, __entry->midr,
-		  __entry->running_state, __entry->psci_state)
+		  __entry->running_state, __entry->psci_state,
+		  APEIL, __entry->pei_len, APEID,
+		  __print_hex(__get_dynamic_array(buf), __entry->pei_len),
+		  APECIL, __entry->ctx_len, APECID,
+		  __print_hex(__get_dynamic_array(buf1), __entry->ctx_len),
+		  VSEIL, __entry->oem_len, VSEID,
+		  __print_hex(__get_dynamic_array(buf2), __entry->oem_len))
 );
 
 /*