[v2] Enable EINJv2 support

[RFC PATCH v2 4/8] ACPI: APEI: EINJ: Enable the discovery of EINJv2 capabilities

Posted by Zaid Alali 6 months, 1 week ago

Enable the driver to show all supported error injections for EINJ
and EINJv2 at the same time. EINJv2 capabilities can be discovered
by checking the return value of get_error_type, where bit 30 set
indicates EINJv2 support.

Signed-off-by: Zaid Alali <zaidal@os.amperecomputing.com>
---
 drivers/acpi/apei/apei-internal.h |  2 +-
 drivers/acpi/apei/einj-core.c     | 35 ++++++++++++++++++++++++-------
 drivers/acpi/apei/einj-cxl.c      |  2 +-
 3 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index cd2766c69d78..9a3dbaeed39a 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -131,7 +131,7 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus)
 
 int apei_osc_setup(void);
 
-int einj_get_available_error_type(u32 *type);
+int einj_get_available_error_type(u32 *type, int version);
 int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
 		      u64 param4);
 int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index b1bbbee9c664..cc5ad1f45ea4 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -33,6 +33,7 @@
 #define SLEEP_UNIT_MAX		5000			/* 5ms */
 /* Firmware should respond within 1 seconds */
 #define FIRMWARE_TIMEOUT	(1 * USEC_PER_SEC)
+#define ACPI65_EINJV2_SUPP	BIT(30)
 #define ACPI5_VENDOR_BIT	BIT(31)
 #define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
 				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
@@ -84,6 +85,7 @@ static struct debugfs_blob_wrapper vendor_errors;
 static char vendor_dev[64];
 
 static u32 available_error_type;
+static u32 available_error_type_v2;
 
 /*
  * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
@@ -159,13 +161,13 @@ static void einj_exec_ctx_init(struct apei_exec_context *ctx)
 			   EINJ_TAB_ENTRY(einj_tab), einj_tab->entries);
 }
 
-static int __einj_get_available_error_type(u32 *type)
+static int __einj_get_available_error_type(u32 *type, int version)
 {
 	struct apei_exec_context ctx;
 	int rc;
 
 	einj_exec_ctx_init(&ctx);
-	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_ERROR_TYPE);
+	rc = apei_exec_run(&ctx, version);
 	if (rc)
 		return rc;
 	*type = apei_exec_ctx_get_output(&ctx);
@@ -174,12 +176,12 @@ static int __einj_get_available_error_type(u32 *type)
 }
 
 /* Get error injection capabilities of the platform */
-int einj_get_available_error_type(u32 *type)
+int einj_get_available_error_type(u32 *type, int version)
 {
 	int rc;
 
 	mutex_lock(&einj_mutex);
-	rc = __einj_get_available_error_type(type);
+	rc = __einj_get_available_error_type(type, version);
 	mutex_unlock(&einj_mutex);
 
 	return rc;
@@ -647,15 +649,27 @@ static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
 	{ BIT(11), "Platform Uncorrectable fatal"},
 	{ BIT(31), "Vendor Defined Error Types" },
 };
+static struct { u32 mask; const char *str; } const einjv2_error_type_string[] = {
+	{ BIT(0), "EINJV2 Processor Error" },
+	{ BIT(1), "EINJV2 Memory Error" },
+	{ BIT(2), "EINJV2 PCI Express Error" },
+};
 
 static int available_error_type_show(struct seq_file *m, void *v)
 {
 
+	seq_printf(m, "EINJ error types:\n");
 	for (int pos = 0; pos < ARRAY_SIZE(einj_error_type_string); pos++)
 		if (available_error_type & einj_error_type_string[pos].mask)
 			seq_printf(m, "0x%08x\t%s\n", einj_error_type_string[pos].mask,
-				   einj_error_type_string[pos].str);
-
+					   einj_error_type_string[pos].str);
+	if (available_error_type & ACPI65_EINJV2_SUPP) {
+		seq_printf(m, "EINJv2 error types:\n");
+		for (int pos = 0; pos < ARRAY_SIZE(einjv2_error_type_string); pos++)
+			if (available_error_type_v2 & einjv2_error_type_string[pos].mask)
+				seq_printf(m, "0x%08x\t%s\n", einjv2_error_type_string[pos].mask,
+						   einjv2_error_type_string[pos].str);
+	}
 	return 0;
 }
 
@@ -692,7 +706,7 @@ int einj_validate_error_type(u64 type)
 	if (tval & (tval - 1))
 		return -EINVAL;
 	if (!vendor)
-		if (!(type & available_error_type))
+		if (!(type & (available_error_type | available_error_type_v2)))
 			return -EINVAL;
 
 	return 0;
@@ -769,9 +783,14 @@ static int __init einj_probe(struct platform_device *pdev)
 		goto err_put_table;
 	}
 
-	rc = einj_get_available_error_type(&available_error_type);
+	rc = einj_get_available_error_type(&available_error_type, ACPI_EINJ_GET_ERROR_TYPE);
 	if (rc)
 		return rc;
+	if (available_error_type & ACPI65_EINJV2_SUPP) {
+		rc = einj_get_available_error_type(&available_error_type_v2, ACPI_EINJV2_GET_ERROR_TYPE);
+		if (rc)
+			return rc;
+	}
 
 	rc = -ENOMEM;
 	einj_debug_dir = debugfs_create_dir("einj", apei_get_debugfs_dir());
diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c
index 8b8be0c90709..25adc9b03d18 100644
--- a/drivers/acpi/apei/einj-cxl.c
+++ b/drivers/acpi/apei/einj-cxl.c
@@ -30,7 +30,7 @@ int einj_cxl_available_error_type_show(struct seq_file *m, void *v)
 	int cxl_err, rc;
 	u32 available_error_type = 0;
 
-	rc = einj_get_available_error_type(&available_error_type);
+	rc = einj_get_available_error_type(&available_error_type, ACPI_EINJ_GET_ERROR_TYPE);
 	if (rc)
 		return rc;
 
-- 
2.34.1

Re: [RFC PATCH v2 4/8] ACPI: APEI: EINJ: Enable the discovery of EINJv2 capabilities

Posted by Ben Cheatham 6 months, 1 week ago

Hi Zaid,

I've got comments inline with a couple (mostly little) concerns, but this looks really good so far!

On 5/21/24 4:10 PM, Zaid Alali wrote:
> Enable the driver to show all supported error injections for EINJ
> and EINJv2 at the same time. EINJv2 capabilities can be discovered
> by checking the return value of get_error_type, where bit 30 set
> indicates EINJv2 support.
> 
> Signed-off-by: Zaid Alali <zaidal@os.amperecomputing.com>
> ---
>  drivers/acpi/apei/apei-internal.h |  2 +-
>  drivers/acpi/apei/einj-core.c     | 35 ++++++++++++++++++++++++-------
>  drivers/acpi/apei/einj-cxl.c      |  2 +-
>  3 files changed, 29 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
> index cd2766c69d78..9a3dbaeed39a 100644
> --- a/drivers/acpi/apei/apei-internal.h
> +++ b/drivers/acpi/apei/apei-internal.h
> @@ -131,7 +131,7 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus)
>  
>  int apei_osc_setup(void);
>  
> -int einj_get_available_error_type(u32 *type);
> +int einj_get_available_error_type(u32 *type, int version);
>  int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
>  		      u64 param4);
>  int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
> diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
> index b1bbbee9c664..cc5ad1f45ea4 100644
> --- a/drivers/acpi/apei/einj-core.c
> +++ b/drivers/acpi/apei/einj-core.c
> @@ -33,6 +33,7 @@
>  #define SLEEP_UNIT_MAX		5000			/* 5ms */
>  /* Firmware should respond within 1 seconds */
>  #define FIRMWARE_TIMEOUT	(1 * USEC_PER_SEC)
> +#define ACPI65_EINJV2_SUPP	BIT(30)
>  #define ACPI5_VENDOR_BIT	BIT(31)
>  #define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
>  				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
> @@ -84,6 +85,7 @@ static struct debugfs_blob_wrapper vendor_errors;
>  static char vendor_dev[64];
>  
>  static u32 available_error_type;
> +static u32 available_error_type_v2;
>  
>  /*
>   * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
> @@ -159,13 +161,13 @@ static void einj_exec_ctx_init(struct apei_exec_context *ctx)
>  			   EINJ_TAB_ENTRY(einj_tab), einj_tab->entries);
>  }
>  
> -static int __einj_get_available_error_type(u32 *type)
> +static int __einj_get_available_error_type(u32 *type, int version)
>  {
>  	struct apei_exec_context ctx;
>  	int rc;
>  
>  	einj_exec_ctx_init(&ctx);
> -	rc = apei_exec_run(&ctx, ACPI_EINJ_GET_ERROR_TYPE);
> +	rc = apei_exec_run(&ctx, version);
>  	if (rc)
>  		return rc;
>  	*type = apei_exec_ctx_get_output(&ctx);
> @@ -174,12 +176,12 @@ static int __einj_get_available_error_type(u32 *type)
>  }
>  
>  /* Get error injection capabilities of the platform */
> -int einj_get_available_error_type(u32 *type)
> +int einj_get_available_error_type(u32 *type, int version)
>  {
>  	int rc;
>  
>  	mutex_lock(&einj_mutex);
> -	rc = __einj_get_available_error_type(type);
> +	rc = __einj_get_available_error_type(type, version);
>  	mutex_unlock(&einj_mutex);
>  
>  	return rc;
> @@ -647,15 +649,27 @@ static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
>  	{ BIT(11), "Platform Uncorrectable fatal"},
>  	{ BIT(31), "Vendor Defined Error Types" },
>  };
> +static struct { u32 mask; const char *str; } const einjv2_error_type_string[] = {
> +	{ BIT(0), "EINJV2 Processor Error" },
> +	{ BIT(1), "EINJV2 Memory Error" },
> +	{ BIT(2), "EINJV2 PCI Express Error" },
> +};
>  
>  static int available_error_type_show(struct seq_file *m, void *v)
>  {
>  
> +	seq_printf(m, "EINJ error types:\n");
>  	for (int pos = 0; pos < ARRAY_SIZE(einj_error_type_string); pos++)
>  		if (available_error_type & einj_error_type_string[pos].mask)
>  			seq_printf(m, "0x%08x\t%s\n", einj_error_type_string[pos].mask,
> -				   einj_error_type_string[pos].str);
> -
> +					   einj_error_type_string[pos].str);
> +	if (available_error_type & ACPI65_EINJV2_SUPP) {
> +		seq_printf(m, "EINJv2 error types:\n");

I think this print and the added one above are not needed since the EINJv2 error type
strings have EINJV2 in them already.

> +		for (int pos = 0; pos < ARRAY_SIZE(einjv2_error_type_string); pos++)
> +			if (available_error_type_v2 & einjv2_error_type_string[pos].mask)
> +				seq_printf(m, "0x%08x\t%s\n", einjv2_error_type_string[pos].mask,
> +						   einjv2_error_type_string[pos].str);
> +	}
>  	return 0;
>  }
>  
> @@ -692,7 +706,7 @@ int einj_validate_error_type(u64 type)
>  	if (tval & (tval - 1))
>  		return -EINVAL;
>  	if (!vendor)
> -		if (!(type & available_error_type))
> +		if (!(type & (available_error_type | available_error_type_v2)))
>  			return -EINVAL;

I don't think this will work? Take the following scenario:

available_error_type = 0x2
available_error_type_v2 = 0x1

If I specify an error type of 0x1 and then inject a EINJv1 error I will have
injected an invalid error type, but still have passed the validation check.
I think you can just get rid of the check for the EINJv2 type here since you also
check it before the actual injection in patch 7/8.

>  
>  	return 0;
> @@ -769,9 +783,14 @@ static int __init einj_probe(struct platform_device *pdev)
>  		goto err_put_table;
>  	}
>  
> -	rc = einj_get_available_error_type(&available_error_type);
> +	rc = einj_get_available_error_type(&available_error_type, ACPI_EINJ_GET_ERROR_TYPE);
>  	if (rc)
>  		return rc;
> +	if (available_error_type & ACPI65_EINJV2_SUPP) {
> +		rc = einj_get_available_error_type(&available_error_type_v2, ACPI_EINJV2_GET_ERROR_TYPE);
> +		if (rc)
> +			return rc;
> +	}
>  
>  	rc = -ENOMEM;
>  	einj_debug_dir = debugfs_create_dir("einj", apei_get_debugfs_dir());
> diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c
> index 8b8be0c90709..25adc9b03d18 100644
> --- a/drivers/acpi/apei/einj-cxl.c
> +++ b/drivers/acpi/apei/einj-cxl.c
> @@ -30,7 +30,7 @@ int einj_cxl_available_error_type_show(struct seq_file *m, void *v)
>  	int cxl_err, rc;
>  	u32 available_error_type = 0;
>  
> -	rc = einj_get_available_error_type(&available_error_type);
> +	rc = einj_get_available_error_type(&available_error_type, ACPI_EINJ_GET_ERROR_TYPE);
>  	if (rc)
>  		return rc;
>

[RFC PATCH v2 1/8] ACPICA: Update values to hex to follow ACPI specs
[RFC PATCH v2 2/8] ACPICA: Add EINJv2 get error type action
[RFC PATCH v2 3/8] ACPI: APEI: EINJ: Remove redundant calls to einj_get_available_error_type
[RFC PATCH v2 4/8] ACPI: APEI: EINJ: Enable the discovery of EINJv2 capabilities
[RFC PATCH v2 5/8] ACPI: APEI: EINJ: Add einjv2 extension struct
[RFC PATCH v2 6/8] ACPI: APEI: EINJ: Add debugfs files for EINJv2 support
[RFC PATCH v2 7/8] ACPI: APEI: EINJ: Enable EINJv2 error injections
[RFC PATCH v2 8/8] ACPI: APEI: EINJ: Update the documentation for EINJv2 support