Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Message-Id: <caa9d52e0a8ef15719bafe8002a4ad2dc359c634.1518382747.git.christophe.leroy@c-s.fr>
In-Reply-To: <02a62db83282b5ef3e0e8281fdc46fa91beffc86.1518382747.git.christophe.leroy@c-s.fr>
References: <02a62db83282b5ef3e0e8281fdc46fa91beffc86.1518382747.git.christophe.leroy@c-s.fr>
From:   Christophe Leroy <christophe.leroy@c-s.fr>
Subject: [RFC REBASED 3/5] powerpc/mm/slice: implement slice_check_range_fits
To:     Nicholas Piggin <npiggin@gmail.com>
Cc:     linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Date:   Mon, 12 Feb 2018 19:12:26 +0100 (CET)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Rather than build slice masks from a range then use that to check for
fit in a candidate mask, implement slice_check_range_fits that checks
if a range fits in a mask directly.

This allows several structures to be removed from stacks, and also we
don't expect a huge range in a lot of these cases, so building and
comparing a full mask is going to be more expensive than testing just
one or two bits of the range.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
 arch/powerpc/mm/slice.c | 68 ++++++++++++++++++++++++++-----------------------
 1 file changed, 36 insertions(+), 32 deletions(-)

diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index ddf015d2d05b..311168ca3939 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -233,22 +233,36 @@ static const struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int ps
 #error "Must define the slice masks for page sizes supported by the platform"
 #endif
 
-static int slice_check_fit(struct mm_struct *mm,
-			   const struct slice_mask *mask,
-			   const struct slice_mask *available)
+static bool slice_check_range_fits(struct mm_struct *mm,
+			   const struct slice_mask *available,
+			   unsigned long start, unsigned long len)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-	/*
-	 * Make sure we just do bit compare only to the max
-	 * addr limit and not the full bit map size.
-	 */
-	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
+	unsigned long end = start + len - 1;
+	u64 low_slices = 0;
+
+	if (start < SLICE_LOW_TOP) {
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
+
+		low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
+				- (1u << GET_LOW_SLICE_INDEX(start));
+	}
+	if ((low_slices & available->low_slices) != low_slices)
+		return false;
+
+	if ((start + len) > SLICE_LOW_TOP) {
+		unsigned long start_index = GET_HIGH_SLICE_INDEX(start);
+		unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
+		unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
+		unsigned long i;
 
-	slice_bitmap_and(result, mask->high_slices, available->high_slices,
-			 slice_count);
+		for (i = start_index; i < start_index + count; i++) {
+			if (!test_bit(i, available->high_slices))
+				return false;
+		}
+	}
 
-	return (mask->low_slices & available->low_slices) == mask->low_slices &&
-		slice_bitmap_equal(result, mask->high_slices, slice_count);
+	return true;
 }
 
 static void slice_flush_segments(void *parm)
@@ -519,12 +533,6 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 		on_each_cpu(slice_flush_segments, mm, 1);
 	}
 
-	/*
-	 * init different masks
-	 */
-	mask.low_slices = 0;
-	slice_bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
-
 	/* silence stupid warning */;
 	potential_mask.low_slices = 0;
 	slice_bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
@@ -586,15 +594,11 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 #endif
 
 	/* First check hint if it's valid or if we have MAP_FIXED */
-	if (addr != 0 || fixed) {
-		/* Build a mask for the requested range */
-		slice_range_to_mask(addr, len, &mask);
-		slice_print_mask(" mask", &mask);
-
+	if (addr || fixed) {
 		/* Check if we fit in the good mask. If we do, we just return,
 		 * nothing else to do
 		 */
-		if (slice_check_fit(mm, &mask, &good_mask)) {
+		if (slice_check_range_fits(mm, &good_mask, addr, len)) {
 			slice_dbg(" fits good !\n");
 			return addr;
 		}
@@ -620,10 +624,11 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	slice_or_mask(&potential_mask, &good_mask);
 	slice_print_mask(" potential", &potential_mask);
 
-	if ((addr != 0 || fixed) &&
-			slice_check_fit(mm, &mask, &potential_mask)) {
-		slice_dbg(" fits potential !\n");
-		goto convert;
+	if (addr || fixed) {
+		if (slice_check_range_fits(mm, &potential_mask, addr, len)) {
+			slice_dbg(" fits potential !\n");
+			goto convert;
+		}
 	}
 
 	/* If we have MAP_FIXED and failed the above steps, then error out */
@@ -829,13 +834,12 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len)
 {
-	struct slice_mask mask, available;
+	struct slice_mask available;
 	unsigned int psize = mm->context.user_psize;
 
 	if (radix_enabled())
 		return 0;
 
-	slice_range_to_mask(addr, len, &mask);
 	available = *slice_mask_for_size(mm, psize);
 #ifdef CONFIG_PPC_64K_PAGES
 	/* We need to account for 4k slices too */
@@ -852,6 +856,6 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 	slice_print_mask(" mask", &mask);
 	slice_print_mask(" available", &available);
 #endif
-	return !slice_check_fit(mm, &mask, &available);
+	return !slice_check_range_fits(mm, &available, addr, len);
 }
 #endif
-- 
2.13.3