diff mbox series

[v3,2/3] ACPI, APEI, EINJ: Add CXL 1.1 EINJ error type support

Message ID 20230905184406.135851-3-Benjamin.Cheatham@amd.com
State Superseded
Headers show
Series CXL, ACPI, APEI, EINJ: Update EINJ for CXL 1.1 error types | expand

Commit Message

Ben Cheatham Sept. 5, 2023, 6:44 p.m. UTC
Add support for CXL EINJ error types for CXL 1.1 hosts added in ACPI
v6.5. Because these error types target memory-mapped CXL 1.1 compliant
downstream ports and not physical (normal/persistent) memory, these
error types are not currently  allowed through the memory range
validation done by the EINJ driver.

The MMIO address of a CXL 1.1 downstream port can be found in the
cxl_rcrb_addr file in the corresponding dport directory under
/sys/bus/cxl/devices/portX. CXL 1.1 error types follow the same
procedure as a memory error type, but with param1 set to the
downstream port MMIO address.

Example usage:
$ cd /sys/kernel/debug/apei/einj
$ cat available_error_type
    0x00000008      Memory Correctable
    0x00000010      Memory Uncorrectable non-fatal
    0x00000020      Memory Uncorrectable fatal
    0x00000040      PCI Express Correctable
    0x00000080      PCI Express Uncorrectable non-fatal
    0x00000100      PCI Express Uncorrectable fatal
    0x00008000      CXL.mem Protocol Correctable
    0x00020000      CXL.mem Protocol Uncorrectable fatal
$ echo 0x8000 > error_type
$ echo 0xfffffffffffff000 > param2
$ echo 0x3 > flags
$ cat /sys/bus/cxl/devices/portX/dportY/cxl_rcrb_addr
0xb2f00000
$ echo 0xb2f00000 > param1
$ echo 1 > error_inject

Signed-off-by: Ben Cheatham <Benjamin.Cheatham@amd.com>
---
 drivers/acpi/apei/einj.c | 26 +++++++++++++++++++++++++-
 drivers/cxl/core/port.c  | 17 +++++++++++++++++
 drivers/cxl/cxl.h        |  1 +
 include/linux/cxl.h      | 18 ++++++++++++++++++
 4 files changed, 61 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/cxl.h

Comments

kernel test robot Sept. 5, 2023, 8:22 p.m. UTC | #1
Hi Ben,

kernel test robot noticed the following build warnings:

[auto build test WARNING on rafael-pm/linux-next]
[also build test WARNING on linus/master v6.5 next-20230905]
[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#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Ben-Cheatham/CXL-PCIE-Add-cxl_rcrb_addr-file-to-dport_dev/20230906-025405
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link:    https://lore.kernel.org/r/20230905184406.135851-3-Benjamin.Cheatham%40amd.com
patch subject: [PATCH v3 2/3] ACPI, APEI, EINJ: Add CXL 1.1 EINJ error type support
config: alpha-allyesconfig (https://download.01.org/0day-ci/archive/20230906/202309060439.NyMjpqql-lkp@intel.com/config)
compiler: alpha-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230906/202309060439.NyMjpqql-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202309060439.NyMjpqql-lkp@intel.com/

All warnings (new ones prefixed by >>):

   In file included from drivers/cxl/cxl.h:11,
                    from drivers/cxl/cxlmem.h:9,
                    from drivers/cxl/core/port.c:11:
>> include/linux/cxl.h:12:19: warning: no previous prototype for 'cxl_find_rch_dport_by_rcrb' [-Wmissing-prototypes]
      12 | struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base)
         |                   ^~~~~~~~~~~~~~~~~~~~~~~~~~
   drivers/cxl/core/port.c:1125:19: error: redefinition of 'cxl_find_rch_dport_by_rcrb'
    1125 | struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base)
         |                   ^~~~~~~~~~~~~~~~~~~~~~~~~~
   include/linux/cxl.h:12:19: note: previous definition of 'cxl_find_rch_dport_by_rcrb' with type 'struct cxl_dport *(resource_size_t)' {aka 'struct cxl_dport *(long long unsigned int)'}
      12 | struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base)
         |                   ^~~~~~~~~~~~~~~~~~~~~~~~~~
--
   In file included from drivers/cxl/cxl.h:11,
                    from drivers/cxl/cxlmem.h:9,
                    from drivers/cxl/core/pmem.c:6:
>> include/linux/cxl.h:12:19: warning: no previous prototype for 'cxl_find_rch_dport_by_rcrb' [-Wmissing-prototypes]
      12 | struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base)
         |                   ^~~~~~~~~~~~~~~~~~~~~~~~~~


vim +/cxl_find_rch_dport_by_rcrb +12 include/linux/cxl.h

     8	
     9	#if IS_ENABLED(CONFIG_CXL_ACPI)
    10	struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base);
    11	#else
  > 12	struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base)
    13	{
    14		return NULL;
    15	}
    16	#endif
    17
kernel test robot Sept. 6, 2023, 4:04 a.m. UTC | #2
Hi Ben,

kernel test robot noticed the following build errors:

[auto build test ERROR on rafael-pm/linux-next]
[also build test ERROR on linus/master v6.5 next-20230905]
[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#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Ben-Cheatham/CXL-PCIE-Add-cxl_rcrb_addr-file-to-dport_dev/20230906-025405
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link:    https://lore.kernel.org/r/20230905184406.135851-3-Benjamin.Cheatham%40amd.com
patch subject: [PATCH v3 2/3] ACPI, APEI, EINJ: Add CXL 1.1 EINJ error type support
config: alpha-allmodconfig (https://download.01.org/0day-ci/archive/20230906/202309061156.nyIdvSmV-lkp@intel.com/config)
compiler: alpha-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230906/202309061156.nyIdvSmV-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202309061156.nyIdvSmV-lkp@intel.com/

All errors (new ones prefixed by >>):

   alpha-linux-ld: drivers/cxl/security.o: in function `cxl_find_rch_dport_by_rcrb':
>> (.text+0x8d0): multiple definition of `cxl_find_rch_dport_by_rcrb'; drivers/cxl/pmem.o:(.text+0x1090): first defined here
diff mbox series

Patch

diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 013eb621dc92..0783ddd3ab4d 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -21,6 +21,7 @@ 
 #include <linux/nmi.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
+#include <linux/cxl.h>
 #include <asm/unaligned.h>
 
 #include "apei-internal.h"
@@ -36,6 +37,7 @@ 
 #define MEM_ERROR_MASK		(ACPI_EINJ_MEMORY_CORRECTABLE | \
 				ACPI_EINJ_MEMORY_UNCORRECTABLE | \
 				ACPI_EINJ_MEMORY_FATAL)
+#define CXL_ERROR_MASK		GENMASK(17, 12)
 
 /*
  * ACPI version 5 provides a SET_ERROR_TYPE_WITH_ADDRESS action.
@@ -512,6 +514,24 @@  static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	return rc;
 }
 
+static int is_valid_cxl_addr(u64 addr)
+{
+	struct cxl_dport *dport;
+
+	if (IS_REACHABLE(CONFIG_CXL_ACPI)) {
+		dport = cxl_find_rch_dport_by_rcrb((resource_size_t) addr);
+
+		if (!IS_ERR_OR_NULL(dport))
+			return 1;
+	} else {
+		pr_err("CONFIG_CXL_ACPI is not reachable.\n");
+		return 0;
+	}
+
+	pr_info("Could not find dport with rcrb 0x%llx\n", addr);
+	return 0;
+}
+
 /* Inject the specified hardware error */
 static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 			     u64 param3, u64 param4)
@@ -537,8 +557,11 @@  static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	if (type & ACPI5_VENDOR_BIT) {
 		if (vendor_flags != SETWA_FLAGS_MEM)
 			goto inject;
-	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM))
+	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) {
 		goto inject;
+	} else if (type & CXL_ERROR_MASK && is_valid_cxl_addr(param1)) {
+		goto inject;
+	}
 
 	/*
 	 * Disallow crazy address masks that give BIOS leeway to pick
@@ -807,3 +830,4 @@  module_exit(einj_exit);
 MODULE_AUTHOR("Huang Ying");
 MODULE_DESCRIPTION("APEI Error INJection support");
 MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(CXL);
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b69fd1c1d5d6..3961f099a775 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1122,6 +1122,23 @@  struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_add_rch_dport, CXL);
 
+struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base)
+{
+	struct cxl_dport *dport;
+	unsigned long index;
+
+	if (!cxl_root)
+		return ERR_PTR(-ENODEV);
+
+	xa_for_each(&cxl_root->dports, index, dport)
+		if ((dport->rch && dport->rcrb.base != CXL_RESOURCE_NONE)
+		    && dport->rcrb.base == rcrb_base)
+			return dport;
+
+	return NULL;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_find_rch_dport_by_rcrb, CXL);
+
 static int add_ep(struct cxl_ep *new)
 {
 	struct cxl_port *port = new->dport->port;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 4d5bce4bae7e..3e6779dbcd23 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -8,6 +8,7 @@ 
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/cxl.h>
 #include <linux/io.h>
 
 /**
diff --git a/include/linux/cxl.h b/include/linux/cxl.h
new file mode 100644
index 000000000000..09889581d9f1
--- /dev/null
+++ b/include/linux/cxl.h
@@ -0,0 +1,18 @@ 
+#ifndef _LINUX_CXL_H
+#define _LINUX_CXL_H
+
+#include <linux/xarray.h>
+#include <linux/errno.h>
+
+struct cxl_dport;
+
+#if IS_ENABLED(CONFIG_CXL_ACPI)
+struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base);
+#else
+struct cxl_dport *cxl_find_rch_dport_by_rcrb(resource_size_t rcrb_base)
+{
+	return NULL;
+}
+#endif
+
+#endif