diff mbox series

[v3,8/9] ACPI: APEI: EINJ: Enable EINJv2 error injections

Message ID 20250210183705.1114624-9-zaidal@os.amperecomputing.com (mailing list archive)
State Needs ACK
Headers show
Series Enable EINJv2 Support | expand

Commit Message

Zaid Alali Feb. 10, 2025, 6:37 p.m. UTC 
Enable the driver to inject EINJv2 type errors. The component
array values are parsed from user_input and expected to contain
hex values for component id and syndrome separated by space,
and multiple components are separated by new line as follows:

component_id1 component_syndrome1
component_id2 component_syndrome2
 :
component_id(n) component_syndrome(n)

for example:

$comp_arr="0x1 0x2
>0x1 0x4
>0x2 0x4"
$cd /sys/kernel/debug/apei/einj/
$echo "$comp_arr" > einjv2_component_array

Signed-off-by: Zaid Alali <zaidal@os.amperecomputing.com>
---
 drivers/acpi/apei/einj-core.c | 103 +++++++++++++++++++++++++++++-----
 1 file changed, 89 insertions(+), 14 deletions(-)

Comments

Jonathan Cameron Feb. 12, 2025, 5:04 p.m. UTC | #1 
On Mon, 10 Feb 2025 10:37:04 -0800
Zaid Alali <zaidal@os.amperecomputing.com> wrote:

> Enable the driver to inject EINJv2 type errors. The component
> array values are parsed from user_input and expected to contain
> hex values for component id and syndrome separated by space,
> and multiple components are separated by new line as follows:
> 
> component_id1 component_syndrome1
> component_id2 component_syndrome2
>  :
> component_id(n) component_syndrome(n)
> 
> for example:
> 
> $comp_arr="0x1 0x2
> >0x1 0x4
> >0x2 0x4"  
> $cd /sys/kernel/debug/apei/einj/
> $echo "$comp_arr" > einjv2_component_array
> 
> Signed-off-by: Zaid Alali <zaidal@os.amperecomputing.com>
> ---
>  drivers/acpi/apei/einj-core.c | 103 +++++++++++++++++++++++++++++-----
>  1 file changed, 89 insertions(+), 14 deletions(-)
> 
> diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
> index 40ebdbc4961f..46359019ca03 100644
> --- a/drivers/acpi/apei/einj-core.c
> +++ b/drivers/acpi/apei/einj-core.c
> @@ -87,6 +87,13 @@ enum {
>  	SETWA_FLAGS_APICID = 1,
>  	SETWA_FLAGS_MEM = 2,
>  	SETWA_FLAGS_PCIE_SBDF = 4,
> +	SETWA_FLAGS_EINJV2 = 8,
> +};
> +
> +enum {
> +	EINJV2_PROCESSOR_ERROR = 0x1,
> +	EINJV2_MEMORY_ERROR = 0x2,
> +	EINJV2_PCIE_ERROR = 0x4,
>  };
>  
>  /*
> @@ -111,6 +118,7 @@ static char vendor_dev[64];
>  static struct debugfs_blob_wrapper einjv2_component_arr;
>  static u64 component_count;
>  static void *user_input;
> +static int nr_components;
>  static u32 available_error_type;
>  static u32 available_error_type_v2;
>  
> @@ -181,6 +189,8 @@ static DEFINE_MUTEX(einj_mutex);
>  bool einj_initialized __ro_after_init;
>  
>  static void __iomem *einj_param;
> +static u32 v5param_size;
> +static bool is_V2;
>  
>  static void einj_exec_ctx_init(struct apei_exec_context *ctx)
>  {
> @@ -288,11 +298,23 @@ static void *einj_get_parameter_address(void)
>  		struct set_error_type_with_address v5param;
>  		void __iomem *p;
>  
> +		v5param_size = sizeof(v5param);
>  		p = acpi_os_map_iomem(pa_v5, sizeof(v5param));
>  		if (p) {
> -			memcpy_fromio(&v5param, p, sizeof(v5param));
> +			int offset, len;
> +
> +			memcpy_fromio(&v5param, p, v5param_size);

Here you clear the first part, but not the extra elements.

>  			acpi5 = 1;
>  			check_vendor_extension(pa_v5, &v5param);
> +			if (available_error_type & ACPI65_EINJV2_SUPP) {
> +				len = v5param.einjv2_struct.length;
> +				offset = offsetof(struct einjv2_extension_struct, component_arr);
> +				nr_components = (len - offset) / 32;
> +				acpi_os_unmap_iomem(p, v5param_size);
> +				v5param_size = sizeof(v5param) +
> +					(nr_components * sizeof(struct syndrome_array));

struct_size()

> +				p = acpi_os_map_iomem(pa_v5, v5param_size);
> +			}
>  			return p;
>  		}
>  	}
> @@ -486,8 +508,8 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
>  	if (acpi5) {
>  		struct set_error_type_with_address *v5param;
>  
> -		v5param = kmalloc(sizeof(*v5param), GFP_KERNEL);
> -		memcpy_fromio(v5param, einj_param, sizeof(*v5param));
> +		v5param = kmalloc(v5param_size, GFP_KERNEL);

This patch is the point where kmalloc makes sense. I'd introduce it here
rather than in earlier patch.

> +		memcpy_fromio(v5param, einj_param, v5param_size);
>  		v5param->type = type;
>  		if (type & ACPI5_VENDOR_BIT) {
>  			switch (vendor_flags) {

...

>  /* Inject the specified hardware error */
> @@ -597,10 +663,15 @@ int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
>  	u64 base_addr, size;
>  
>  	/* If user manually set "flags", make sure it is legal */
> -	if (flags && (flags &
> -		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
> +	if (flags && (flags & ~(SETWA_FLAGS_APICID | SETWA_FLAGS_MEM |
> +		      SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2)))
>  		return -EINVAL;
>  
> +	/* check if type is a valid EINJv2 error type */
> +	if (is_V2) {
> +		if (!(type & available_error_type_v2))
> +			return -EINVAL;
> +	}
>  	/*
>  	 * We need extra sanity checks for memory errors.
>  	 * Other types leap directly to injection.
> @@ -750,7 +821,7 @@ 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;
> @@ -763,12 +834,14 @@ static ssize_t error_type_set(struct file *file, const char __user *buf,
>  	u64 val;
>  
>  	memset(einj_buf, 0, BUFF_SIZE);
> +	is_V2 = false;
>  	if (copy_from_user(einj_buf, buf, count))
>  		return -EFAULT;
>  
>  	if (strncmp(einj_buf, "V2_", 3) == 0) {
>  		if (!sscanf(einj_buf, "V2_%llx", &val))
>  			return -EINVAL;
> +		is_V2 = true;

Given you have an if / else here. Set is_V2 = false
in the else rather that default and override in one leg of
the if / else.

>  	} else
>  		if (!sscanf(einj_buf, "%llx", &val))
>  			return -EINVAL;
> @@ -792,6 +865,9 @@ static int error_inject_set(void *data, u64 val)
>  	if (!error_type)
>  		return -EINVAL;
>  
> +	if (is_V2)
> +		error_flags |= SETWA_FLAGS_EINJV2;
> +
>  	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
>  				error_param3, error_param4);
>  }
> @@ -944,11 +1020,10 @@ static void __exit einj_remove(struct platform_device *pdev)
>  	struct apei_exec_context ctx;
>  
>  	if (einj_param) {
> -		acpi_size size = (acpi5) ?
> -			sizeof(struct set_error_type_with_address) :
> -			sizeof(struct einj_parameter);
> -
> -		acpi_os_unmap_iomem(einj_param, size);

Unless strong reason to change I'd keep to existing style and just
replace the true condition with v5param_size

> +		if (acpi5)
> +			acpi_os_unmap_iomem(einj_param, v5param_size);
> +		else
> +			acpi_os_unmap_iomem(einj_param,	sizeof(struct einj_parameter));
>  		if (vendor_errors.size)
>  			acpi_os_unmap_memory(vendor_errors.data, vendor_errors.size);
>  	}
diff mbox series

Patch

diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index 40ebdbc4961f..46359019ca03 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -87,6 +87,13 @@  enum {
 	SETWA_FLAGS_APICID = 1,
 	SETWA_FLAGS_MEM = 2,
 	SETWA_FLAGS_PCIE_SBDF = 4,
+	SETWA_FLAGS_EINJV2 = 8,
+};
+
+enum {
+	EINJV2_PROCESSOR_ERROR = 0x1,
+	EINJV2_MEMORY_ERROR = 0x2,
+	EINJV2_PCIE_ERROR = 0x4,
 };
 
 /*
@@ -111,6 +118,7 @@  static char vendor_dev[64];
 static struct debugfs_blob_wrapper einjv2_component_arr;
 static u64 component_count;
 static void *user_input;
+static int nr_components;
 static u32 available_error_type;
 static u32 available_error_type_v2;
 
@@ -181,6 +189,8 @@  static DEFINE_MUTEX(einj_mutex);
 bool einj_initialized __ro_after_init;
 
 static void __iomem *einj_param;
+static u32 v5param_size;
+static bool is_V2;
 
 static void einj_exec_ctx_init(struct apei_exec_context *ctx)
 {
@@ -288,11 +298,23 @@  static void *einj_get_parameter_address(void)
 		struct set_error_type_with_address v5param;
 		void __iomem *p;
 
+		v5param_size = sizeof(v5param);
 		p = acpi_os_map_iomem(pa_v5, sizeof(v5param));
 		if (p) {
-			memcpy_fromio(&v5param, p, sizeof(v5param));
+			int offset, len;
+
+			memcpy_fromio(&v5param, p, v5param_size);
 			acpi5 = 1;
 			check_vendor_extension(pa_v5, &v5param);
+			if (available_error_type & ACPI65_EINJV2_SUPP) {
+				len = v5param.einjv2_struct.length;
+				offset = offsetof(struct einjv2_extension_struct, component_arr);
+				nr_components = (len - offset) / 32;
+				acpi_os_unmap_iomem(p, v5param_size);
+				v5param_size = sizeof(v5param) +
+					(nr_components * sizeof(struct syndrome_array));
+				p = acpi_os_map_iomem(pa_v5, v5param_size);
+			}
 			return p;
 		}
 	}
@@ -486,8 +508,8 @@  static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	if (acpi5) {
 		struct set_error_type_with_address *v5param;
 
-		v5param = kmalloc(sizeof(*v5param), GFP_KERNEL);
-		memcpy_fromio(v5param, einj_param, sizeof(*v5param));
+		v5param = kmalloc(v5param_size, GFP_KERNEL);
+		memcpy_fromio(v5param, einj_param, v5param_size);
 		v5param->type = type;
 		if (type & ACPI5_VENDOR_BIT) {
 			switch (vendor_flags) {
@@ -507,8 +529,49 @@  static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 			v5param->flags = flags;
 			v5param->memory_address = param1;
 			v5param->memory_address_range = param2;
-			v5param->apicid = param3;
-			v5param->pcie_sbdf = param4;
+
+			if (is_V2) {
+				int count = 0, bytes_read, pos = 0;
+				unsigned int comp, synd;
+				struct syndrome_array *component_arr;
+
+				if (component_count > nr_components)
+					goto err_out;
+
+				v5param->einjv2_struct.component_arr_count = component_count;
+				component_arr = v5param->einjv2_struct.component_arr;
+
+				while (sscanf(user_input + pos, "%x %x\n%n", &comp, &synd,
+					&bytes_read) == 2) {
+					pos += bytes_read;
+					if (count > component_count)
+						goto err_out;
+
+					switch (type) {
+					case EINJV2_PROCESSOR_ERROR:
+						component_arr[count].comp_id.acpi_id = comp;
+						component_arr[count].comp_synd.proc_synd = synd;
+						break;
+					case EINJV2_MEMORY_ERROR:
+						component_arr[count].comp_id.device_id = comp;
+						component_arr[count].comp_synd.mem_synd = synd;
+						break;
+					case EINJV2_PCIE_ERROR:
+						component_arr[count].comp_id.pcie_sbdf = comp;
+						component_arr[count].comp_synd.pcie_synd = synd;
+						break;
+					}
+					count++;
+				}
+				if (count != component_count)
+					goto err_out;
+
+				/* clear buffer after user input for next injection */
+				memset(user_input, 0, COMP_ARR_SIZE);
+			} else {
+				v5param->apicid = param3;
+				v5param->pcie_sbdf = param4;
+			}
 		} else {
 			switch (type) {
 			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
@@ -532,7 +595,7 @@  static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 				break;
 			}
 		}
-		memcpy_toio(einj_param, v5param, sizeof(*v5param));
+		memcpy_toio(einj_param, v5param, v5param_size);
 		kfree(v5param);
 	} else {
 		rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
@@ -587,6 +650,9 @@  static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION);
 
 	return rc;
+err_out:
+	memset(user_input, 0, COMP_ARR_SIZE);
+	return -EINVAL;
 }
 
 /* Inject the specified hardware error */
@@ -597,10 +663,15 @@  int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
 	u64 base_addr, size;
 
 	/* If user manually set "flags", make sure it is legal */
-	if (flags && (flags &
-		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
+	if (flags && (flags & ~(SETWA_FLAGS_APICID | SETWA_FLAGS_MEM |
+		      SETWA_FLAGS_PCIE_SBDF | SETWA_FLAGS_EINJV2)))
 		return -EINVAL;
 
+	/* check if type is a valid EINJv2 error type */
+	if (is_V2) {
+		if (!(type & available_error_type_v2))
+			return -EINVAL;
+	}
 	/*
 	 * We need extra sanity checks for memory errors.
 	 * Other types leap directly to injection.
@@ -750,7 +821,7 @@  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;
@@ -763,12 +834,14 @@  static ssize_t error_type_set(struct file *file, const char __user *buf,
 	u64 val;
 
 	memset(einj_buf, 0, BUFF_SIZE);
+	is_V2 = false;
 	if (copy_from_user(einj_buf, buf, count))
 		return -EFAULT;
 
 	if (strncmp(einj_buf, "V2_", 3) == 0) {
 		if (!sscanf(einj_buf, "V2_%llx", &val))
 			return -EINVAL;
+		is_V2 = true;
 	} else
 		if (!sscanf(einj_buf, "%llx", &val))
 			return -EINVAL;
@@ -792,6 +865,9 @@  static int error_inject_set(void *data, u64 val)
 	if (!error_type)
 		return -EINVAL;
 
+	if (is_V2)
+		error_flags |= SETWA_FLAGS_EINJV2;
+
 	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
 				error_param3, error_param4);
 }
@@ -944,11 +1020,10 @@  static void __exit einj_remove(struct platform_device *pdev)
 	struct apei_exec_context ctx;
 
 	if (einj_param) {
-		acpi_size size = (acpi5) ?
-			sizeof(struct set_error_type_with_address) :
-			sizeof(struct einj_parameter);
-
-		acpi_os_unmap_iomem(einj_param, size);
+		if (acpi5)
+			acpi_os_unmap_iomem(einj_param, v5param_size);
+		else
+			acpi_os_unmap_iomem(einj_param,	sizeof(struct einj_parameter));
 		if (vendor_errors.size)
 			acpi_os_unmap_memory(vendor_errors.data, vendor_errors.size);
 	}