[PATCH v3 0/3] Fix CPER issues related to UEFI 2.9A Errata

[PATCH v3 0/3] Fix CPER issues related to UEFI 2.9A Errata

[Mauro Carvalho Chehab]

The UEFI 2.9A errata makes clear how ARM processor type encoding should
be done: it is meant to be equal to Generic processor, using a bitmask.

The current code assumes, for both generic and ARM processor types
that this is an integer, which is an incorrect assumption.

Fix it. While here, also fix a compilation issue when using W=1.

Mauro Carvalho Chehab (3):
  efi/cper: Adjust infopfx size to accept an extra space
  efi/cper: Add a new helper function to print bitmasks
  efi/cper: align ARM CPER type with UEFI 2.9A/2.10 specs

 drivers/acpi/apei/ghes.c        |  9 ++++---
 drivers/firmware/efi/cper-arm.c | 47 ++++++++++++++-------------------
 drivers/firmware/efi/cper.c     | 40 ++++++++++++++++++++++++++++
 include/linux/cper.h            | 11 ++++----
 4 files changed, 71 insertions(+), 36 deletions(-)

-- 
2.45.2

[PATCH v3 1/3] efi/cper: Adjust infopfx size to accept an extra space

[Mauro Carvalho Chehab]

Compiling with W=1 with werror enabled produces an error:

drivers/firmware/efi/cper-arm.c: In function ‘cper_print_proc_arm’:
drivers/firmware/efi/cper-arm.c:298:64: error: ‘snprintf’ output may be truncated before the last format character [-Werror=format-truncation=]
  298 |                         snprintf(infopfx, sizeof(infopfx), "%s ", newpfx);
      |                                                                ^
drivers/firmware/efi/cper-arm.c:298:25: note: ‘snprintf’ output between 2 and 65 bytes into a destination of size 64
  298 |                         snprintf(infopfx, sizeof(infopfx), "%s ", newpfx);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

As the logic there adds an space at the end of infopx buffer.
Add an extra space to avoid such warning.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/firmware/efi/cper-arm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
index fa9c1c3bf168..d9bbcea0adf4 100644
--- a/drivers/firmware/efi/cper-arm.c
+++ b/drivers/firmware/efi/cper-arm.c
@@ -240,7 +240,7 @@ void cper_print_proc_arm(const char *pfx,
 	int i, len, max_ctx_type;
 	struct cper_arm_err_info *err_info;
 	struct cper_arm_ctx_info *ctx_info;
-	char newpfx[64], infopfx[64];
+	char newpfx[64], infopfx[65];
 
 	printk("%sMIDR: 0x%016llx\n", pfx, proc->midr);
 
-- 
2.45.2

[PATCH v3 2/3] efi/cper: Add a new helper function to print bitmasks

[Mauro Carvalho Chehab]

Sometimes it is desired to produce a single log line for errors.
Add a new helper function for such purpose.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/firmware/efi/cper.c | 40 +++++++++++++++++++++++++++++++++++++
 include/linux/cper.h        |  2 ++
 2 files changed, 42 insertions(+)

diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 7d2cdd9e2227..f315acb6c19c 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -106,6 +106,46 @@ void cper_print_bits(const char *pfx, unsigned int bits,
 		printk("%s\n", buf);
 }
 
+/*
+ * cper_bits_to_str - return a string for set bits
+ * @buf: buffer to store the output string
+ * @buf_size: size of the output string buffer
+ * @bits: bit mask
+ * @strs: string array, indexed by bit position
+ * @strs_size: size of the string array: @strs
+ *
+ * add to @buf the bitmask in hexadecimal. Then, for each set bit in @bits,
+ * add the corresponding string in @strs to @buf.
+ */
+char *cper_bits_to_str(char *buf, int buf_size, unsigned int bits,
+		       const char * const strs[], unsigned int strs_size)
+{
+	int len = buf_size;
+	char *str = buf;
+	int i, size;
+
+	if (strs_size < 16)
+		size = snprintf(str, len, "%02x ", bits);
+	if (strs_size < 32)
+		size = snprintf(str, len, "%04x ", bits);
+	else
+		size = snprintf(str, len, "%08x ", bits);
+
+	len -= size;
+	str += size;
+
+	for (i = 0; i < strs_size; i++) {
+		if (!(bits & (1U << i)))
+			continue;
+
+		size = snprintf(str, buf_size - len, "%s ", strs[i]);
+		len -= size;
+		str += size;
+	}
+	return buf;
+}
+EXPORT_SYMBOL_GPL(cper_bits_to_str);
+
 static const char * const proc_type_strs[] = {
 	"IA32/X64",
 	"IA64",
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 265b0f8fc0b3..866e195819de 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -584,6 +584,8 @@ const char *cper_mem_err_type_str(unsigned int);
 const char *cper_mem_err_status_str(u64 status);
 void cper_print_bits(const char *prefix, unsigned int bits,
 		     const char * const strs[], unsigned int strs_size);
+char *cper_bits_to_str(char *buf, int buf_size, unsigned int bits,
+		       const char * const strs[], unsigned int strs_size);
 void cper_mem_err_pack(const struct cper_sec_mem_err *,
 		       struct cper_mem_err_compact *);
 const char *cper_mem_err_unpack(struct trace_seq *,
-- 
2.45.2

[PATCH v3 3/3] efi/cper: align ARM CPER type with UEFI 2.9A/2.10 specs

[Mauro Carvalho Chehab]

Up to UEFI spec, the type byte of CPER struct for ARM processor was
defined simply as:

Type at byte offset 4:

	- Cache error
	- TLB Error
	- Bus Error
	- Micro-architectural Error
	All other values are reserved

Yet, there was no information about how this would be encoded.

Spec 2.9A errata corrected it by defining:

	- Bit 1 - Cache Error
	- Bit 2 - TLB Error
	- Bit 3 - Bus Error
	- Bit 4 - Micro-architectural Error
	All other values are reserved

That actually aligns with the values already defined on older
versions at N.2.4.1. Generic Processor Error Section.

Spec 2.10 also preserve the same encoding as 2.9A

See: https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html#arm-processor-error-information

Adjust CPER and GHES handling code for both generic and ARM
processors to properly handle UEFI 2.9A and 2.10 encoding.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/acpi/apei/ghes.c        |  9 ++++---
 drivers/firmware/efi/cper-arm.c | 45 ++++++++++++++-------------------
 include/linux/cper.h            |  9 +++----
 3 files changed, 28 insertions(+), 35 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 623cc0cb4a65..9e76be42f27e 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -533,6 +533,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
 	int flags = sync ? MF_ACTION_REQUIRED : 0;
+	char error_type[120];
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
@@ -546,9 +547,8 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 	p = (char *)(err + 1);
 	for (i = 0; i < err->err_info_num; i++) {
 		struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
-		bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
+		bool is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
 		bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
-		const char *error_type = "unknown error";
 
 		/*
 		 * The field (err_info->error_info & BIT(26)) is fixed to set to
@@ -562,8 +562,9 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 			continue;
 		}
 
-		if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
-			error_type = cper_proc_error_type_strs[err_info->type];
+		cper_bits_to_str(error_type, sizeof(error_type), err_info->type,
+				 cper_proc_error_type_strs,
+				 ARRAY_SIZE(cper_proc_error_type_strs));
 
 		pr_warn_ratelimited(FW_WARN GHES_PFX
 				    "Unhandled processor error type: %s\n",
diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
index d9bbcea0adf4..d933235aa15a 100644
--- a/drivers/firmware/efi/cper-arm.c
+++ b/drivers/firmware/efi/cper-arm.c
@@ -93,15 +93,11 @@ static void cper_print_arm_err_info(const char *pfx, u32 type,
 	bool proc_context_corrupt, corrected, precise_pc, restartable_pc;
 	bool time_out, access_mode;
 
-	/* If the type is unknown, bail. */
-	if (type > CPER_ARM_MAX_TYPE)
-		return;
-
 	/*
 	 * Vendor type errors have error information values that are vendor
 	 * specific.
 	 */
-	if (type == CPER_ARM_VENDOR_ERROR)
+	if (type & CPER_ARM_VENDOR_ERROR)
 		return;
 
 	if (error_info & CPER_ARM_ERR_VALID_TRANSACTION_TYPE) {
@@ -116,43 +112,38 @@ static void cper_print_arm_err_info(const char *pfx, u32 type,
 	if (error_info & CPER_ARM_ERR_VALID_OPERATION_TYPE) {
 		op_type = ((error_info >> CPER_ARM_ERR_OPERATION_SHIFT)
 			   & CPER_ARM_ERR_OPERATION_MASK);
-		switch (type) {
-		case CPER_ARM_CACHE_ERROR:
+		if (type & CPER_ARM_CACHE_ERROR) {
 			if (op_type < ARRAY_SIZE(arm_cache_err_op_strs)) {
-				printk("%soperation type: %s\n", pfx,
+				printk("%scache error, operation type: %s\n", pfx,
 				       arm_cache_err_op_strs[op_type]);
 			}
-			break;
-		case CPER_ARM_TLB_ERROR:
+		}
+		if (type & CPER_ARM_TLB_ERROR) {
 			if (op_type < ARRAY_SIZE(arm_tlb_err_op_strs)) {
-				printk("%soperation type: %s\n", pfx,
+				printk("%sTLB error, operation type: %s\n", pfx,
 				       arm_tlb_err_op_strs[op_type]);
 			}
-			break;
-		case CPER_ARM_BUS_ERROR:
+		}
+		if (type & CPER_ARM_BUS_ERROR) {
 			if (op_type < ARRAY_SIZE(arm_bus_err_op_strs)) {
-				printk("%soperation type: %s\n", pfx,
+				printk("%sbus error, operation type: %s\n", pfx,
 				       arm_bus_err_op_strs[op_type]);
 			}
-			break;
 		}
 	}
 
 	if (error_info & CPER_ARM_ERR_VALID_LEVEL) {
 		level = ((error_info >> CPER_ARM_ERR_LEVEL_SHIFT)
 			 & CPER_ARM_ERR_LEVEL_MASK);
-		switch (type) {
-		case CPER_ARM_CACHE_ERROR:
+		if (type & CPER_ARM_CACHE_ERROR)
 			printk("%scache level: %d\n", pfx, level);
-			break;
-		case CPER_ARM_TLB_ERROR:
+
+		if (type & CPER_ARM_TLB_ERROR)
 			printk("%sTLB level: %d\n", pfx, level);
-			break;
-		case CPER_ARM_BUS_ERROR:
+
+		if (type & CPER_ARM_BUS_ERROR)
 			printk("%saffinity level at which the bus error occurred: %d\n",
 			       pfx, level);
-			break;
-		}
 	}
 
 	if (error_info & CPER_ARM_ERR_VALID_PROC_CONTEXT_CORRUPT) {
@@ -241,6 +232,7 @@ void cper_print_proc_arm(const char *pfx,
 	struct cper_arm_err_info *err_info;
 	struct cper_arm_ctx_info *ctx_info;
 	char newpfx[64], infopfx[65];
+	char error_type[120];
 
 	printk("%sMIDR: 0x%016llx\n", pfx, proc->midr);
 
@@ -289,9 +281,10 @@ void cper_print_proc_arm(const char *pfx,
 				       newpfx);
 		}
 
-		printk("%serror_type: %d, %s\n", newpfx, err_info->type,
-			err_info->type < ARRAY_SIZE(cper_proc_error_type_strs) ?
-			cper_proc_error_type_strs[err_info->type] : "unknown");
+		cper_bits_to_str(error_type, sizeof(error_type), err_info->type,
+				 cper_proc_error_type_strs,
+				 ARRAY_SIZE(cper_proc_error_type_strs));
+		printk("%serror_type: %s\n", newpfx, error_type);
 		if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO) {
 			printk("%serror_info: 0x%016llx\n", newpfx,
 			       err_info->error_info);
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 866e195819de..e66064403f98 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -293,11 +293,10 @@ enum {
 #define CPER_ARM_INFO_FLAGS_PROPAGATED		BIT(2)
 #define CPER_ARM_INFO_FLAGS_OVERFLOW		BIT(3)
 
-#define CPER_ARM_CACHE_ERROR			0
-#define CPER_ARM_TLB_ERROR			1
-#define CPER_ARM_BUS_ERROR			2
-#define CPER_ARM_VENDOR_ERROR			3
-#define CPER_ARM_MAX_TYPE			CPER_ARM_VENDOR_ERROR
+#define CPER_ARM_CACHE_ERROR			BIT(1)
+#define CPER_ARM_TLB_ERROR			BIT(2)
+#define CPER_ARM_BUS_ERROR			BIT(3)
+#define CPER_ARM_VENDOR_ERROR			BIT(4)
 
 #define CPER_ARM_ERR_VALID_TRANSACTION_TYPE	BIT(0)
 #define CPER_ARM_ERR_VALID_OPERATION_TYPE	BIT(1)
-- 
2.45.2