x86/mm/cpa: Do the range check early

commit 9cc9f17a5a0a8564b41b7c5c460e7f078c42d712 upstream.

To avoid excessive 4k wise checks in the common case do a quick check first
whether the requested new page protections conflict with a static
protection area in the large page. If there is no conflict then the
decision whether to preserve or to split the page can be made immediately.

If the requested range covers the full large page, preserve it. Otherwise
split it up. No point in doing a slow crawl in 4k steps.

Before:

 1G pages checked:                    2
 1G pages sameprot:                   0
 1G pages preserved:                  0
 2M pages checked:                  538
 2M pages sameprot:                 466
 2M pages preserved:                 47
 4K pages checked:               560642
 4K pages set-checked:             7668

After:

 1G pages checked:                    2
 1G pages sameprot:                   0
 1G pages preserved:                  0
 2M pages checked:                  541
 2M pages sameprot:                 466
 2M pages preserved:                 47
 4K pages checked:                  514
 4K pages set-checked:             7668
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NDave Hansen <dave.hansen@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Bin Yang <bin.yang@intel.com>
Cc: Mark Gross <mark.gross@intel.com>
Link: https://lkml.kernel.org/r/20180917143546.507259989@linutronix.deSigned-off-by: NShile Zhang <shile.zhang@linux.alibaba.com>
Acked-by: NJoseph Qi <joseph.qi@linux.alibaba.com>

arch/x86/mm/pageattr.c

@@ -854,10 +854,28 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	}
 
 	/*
-	 * Make sure that the requested pgprot does not violate the static
-	 * protections. Check the full large page whether one of the pages
-	 * in it results in a different pgprot than the first one of the
-	 * requested range. If yes, then the page needs to be split.
+	 * Optimization: Check whether the requested pgprot is conflicting
+	 * with a static protection requirement in the large page. If not,
+	 * then checking whether the requested range is fully covering the
+	 * large page can be done right here.
+	 */
+	new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
+				      CPA_DETECT);
+
+	if (pgprot_val(req_prot) == pgprot_val(new_prot)) {
+		if (address != lpaddr || cpa->numpages != numpages)
+			return 1;
+		goto setlp;
+	}
+
+	/*
+	 * Slow path. The full large page check above established that the
+	 * requested pgprot cannot be applied to the full large page due to
+	 * conflicting requirements of static protection regions. It might
+	 * turn out that the whole requested range is covered by the
+	 * modified protection of the first 4k segment at @address. This
+	 * might result in the ability to preserve the large page
+	 * nevertheless.
 	 */
 	new_prot = static_protections(req_prot, address, pfn, 1, CPA_DETECT);
 	pfn = old_pfn;
@@ -882,6 +900,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	if (address != lpaddr || cpa->numpages != numpages)
 		return 1;
 
+setlp:
 	/* All checks passed. Update the large page mapping. */
 	new_pte = pfn_pte(old_pfn, new_prot);
 	__set_pmd_pte(kpte, address, new_pte);