net: xfrm: use __this_cpu_read per-cpu helper

this_cpu_ptr/this_cpu_read is faster than per_cpu_ptr(p, smp_processor_id())
and can reduce  memory accesses.
The latter helper needs to find the offset for current cpu,
and needs more assembler instructions which objdump shows in following.

this_cpu_ptr relocates and address. this_cpu_read() relocates the address
and performs the fetch. this_cpu_read() saves you more instructions
since it can do the relocation and the fetch in one instruction.

per_cpu_ptr(p, smp_processor_id())：
  1e:   65 8b 04 25 00 00 00 00         mov    %gs:0x0,%eax
  26:   48 98                           cltq
  28:   31 f6                           xor    %esi,%esi
  2a:   48 c7 c7 00 00 00 00            mov    $0x0,%rdi
  31:   48 8b 04 c5 00 00 00 00         mov    0x0(,%rax,8),%rax
  39:   c7 44 10 04 14 00 00 00         movl   $0x14,0x4(%rax,%rdx,1)

this_cpu_ptr(p)
  1e:   65 48 03 14 25 00 00 00 00      add    %gs:0x0,%rdx
  27:   31 f6                           xor    %esi,%esi
  29:   c7 42 04 14 00 00 00            movl   $0x14,0x4(%rdx)
  30:   48 c7 c7 00 00 00 00            mov    $0x0,%rdi

Signed-off-by: Shan Wei <davidshan@tencent.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

net/xfrm/xfrm_ipcomp.c

@@ -276,18 +276,16 @@ static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name)
 	struct crypto_comp * __percpu *tfms;
 	int cpu;
 
-	/* This can be any valid CPU ID so we don't need locking. */
-	cpu = raw_smp_processor_id();
 
 	list_for_each_entry(pos, &ipcomp_tfms_list, list) {
 		struct crypto_comp *tfm;
 
-		tfms = pos->tfms;
-		tfm = *per_cpu_ptr(tfms, cpu);
+		/* This can be any valid CPU ID so we don't need locking. */
+		tfm = __this_cpu_read(*pos->tfms);
 
 		if (!strcmp(crypto_comp_name(tfm), alg_name)) {
 			pos->users++;
-			return tfms;
+			return pos->tfms;
 		}
 	}