MIPS: Cavium: Add EDAC support.
Drivers for EDAC on Cavium. Supported subsystems are:
o CPU primary caches. These are parity protected only, so only error
reporting.
o Second level cache - ECC protected, provides SECDED.
o Memory: ECC / SECDEC if used with suitable DRAM modules. The driver will
will only initialize if ECC is enabled on a system so is safe to run on
non-ECC memory.
o PCI: Parity error reporting
Since it is very hard to test this sort of code the implementation is very
conservative and uses polling where possible for now.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Reviewed-by: Borislav Petkov <borislav.petkov@amd.com>
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index 44e69e7..9f67553 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -5,6 +5,7 @@
*
* Copyright (C) 2005-2007 Cavium Networks
*/
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
@@ -28,6 +29,7 @@
#include <asm/octeon/octeon.h>
unsigned long long cache_err_dcache[NR_CPUS];
+EXPORT_SYMBOL_GPL(cache_err_dcache);
/**
* Octeon automatically flushes the dcache on tlb changes, so
@@ -288,42 +290,42 @@
* Handle a cache error exception
*/
-static void cache_parity_error_octeon(int non_recoverable)
+static RAW_NOTIFIER_HEAD(co_cache_error_chain);
+
+int register_co_cache_error_notifier(struct notifier_block *nb)
{
- unsigned long coreid = cvmx_get_core_num();
- uint64_t icache_err = read_octeon_c0_icacheerr();
+ return raw_notifier_chain_register(&co_cache_error_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_co_cache_error_notifier);
- pr_err("Cache error exception:\n");
- pr_err("cp0_errorepc == %lx\n", read_c0_errorepc());
- if (icache_err & 1) {
- pr_err("CacheErr (Icache) == %llx\n",
- (unsigned long long)icache_err);
- write_octeon_c0_icacheerr(0);
- }
- if (cache_err_dcache[coreid] & 1) {
- pr_err("CacheErr (Dcache) == %llx\n",
- (unsigned long long)cache_err_dcache[coreid]);
- cache_err_dcache[coreid] = 0;
- }
+int unregister_co_cache_error_notifier(struct notifier_block *nb)
+{
+ return raw_notifier_chain_unregister(&co_cache_error_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_co_cache_error_notifier);
- if (non_recoverable)
- panic("Can't handle cache error: nested exception");
+static inline int co_cache_error_call_notifiers(unsigned long val)
+{
+ return raw_notifier_call_chain(&co_cache_error_chain, val, NULL);
}
/**
* Called when the the exception is recoverable
*/
-
asmlinkage void cache_parity_error_octeon_recoverable(void)
{
- cache_parity_error_octeon(0);
+ co_cache_error_call_notifiers(0);
}
/**
* Called when the the exception is not recoverable
+ *
+ * The issue not that the cache error exception itself was non-recoverable
+ * but that due to nesting of exception may have lost some state so can't
+ * continue.
*/
-
asmlinkage void cache_parity_error_octeon_non_recoverable(void)
{
- cache_parity_error_octeon(1);
+ co_cache_error_call_notifiers(1);
+ panic("Can't handle cache error: nested exception");
}