x86/mce: Dynamically size space for machine check records

Systems with a large number of CPUs may generate a large number of
machine check records when things go seriously wrong. But Linux has
a fixed-size buffer that can only capture a few dozen errors.

Allocate space based on the number of CPUs (with a minimum value based
on the historical fixed buffer that could store 80 records).

  [ bp: Rename local var from tmpp to something more telling: gpool. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Reviewed-by: Avadhut Naik <avadhut.naik@amd.com>
Link: https://lore.kernel.org/r/20240307192704.37213-1-tony.luck@intel.com

diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index fbe8b61c3413037ae30203f893f545c9782d51f9..4284749ec803738911ebe4185b27eb3695dee719 100644 (file)
--- a/arch/x86/kernel/cpu/mce/genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -16,14 +16,14 @@
  * used to save error information organized in a lock-less list.
  *
  * This memory pool is only to be used to save MCE records in MCE context.
- * MCE events are rare, so a fixed size memory pool should be enough. Use
- * 2 pages to save MCE events for now (~80 MCE records at most).
+ * MCE events are rare, so a fixed size memory pool should be enough.
+ * Allocate on a sliding scale based on number of CPUs.
  */
-#define MCE_POOLSZ     (2 * PAGE_SIZE)
+#define MCE_MIN_ENTRIES        80
+#define MCE_PER_CPU    2
 
 static struct gen_pool *mce_evt_pool;
 static LLIST_HEAD(mce_event_llist);
-static char gen_pool_buf[MCE_POOLSZ];
 
 /*
  * Compare the record "t" with each of the records on list "l" to see if
@@ -118,22 +118,32 @@ int mce_gen_pool_add(struct mce *mce)
 
 static int mce_gen_pool_create(void)
 {
-       struct gen_pool *tmpp;
+       int mce_numrecords, mce_poolsz, order;
+       struct gen_pool *gpool;
        int ret = -ENOMEM;
-
-       tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1);
-       if (!tmpp)
-               goto out;
-
-       ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1);
+       void *mce_pool;
+
+       order = order_base_2(sizeof(struct mce_evt_llist));
+       gpool = gen_pool_create(order, -1);
+       if (!gpool)
+               return ret;
+
+       mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU);
+       mce_poolsz = mce_numrecords * (1 << order);
+       mce_pool = kmalloc(mce_poolsz, GFP_KERNEL);
+       if (!mce_pool) {
+               gen_pool_destroy(gpool);
+               return ret;
+       }
+       ret = gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1);
        if (ret) {
-               gen_pool_destroy(tmpp);
-               goto out;
+               gen_pool_destroy(gpool);
+               kfree(mce_pool);
+               return ret;
        }
 
-       mce_evt_pool = tmpp;
+       mce_evt_pool = gpool;
 
-out:
        return ret;
 }