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: <3e9cfc87e78d61310d1b628960a465327c20d895.1519305411.git.christophe.leroy@c-s.fr>
In-Reply-To: <455276187b369bf019e91715b7488e86cd932d49.1519305410.git.christophe.leroy@c-s.fr>
References: <455276187b369bf019e91715b7488e86cd932d49.1519305410.git.christophe.leroy@c-s.fr>
From:   Christophe Leroy <christophe.leroy@c-s.fr>
Subject: [PATCH v5 3/6] powerpc/mm/slice: Enhance for supporting PPC32
To:     Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Scott Wood <oss@buserror.net>, aneesh.kumar@linux.vnet.ibm.com
Cc:     linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
        Nicholas Piggin <npiggin@gmail.com>
Date:   Thu, 22 Feb 2018 15:27:24 +0100 (CET)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

In preparation for the following patch which will fix an issue on
the 8xx by re-using the 'slices', this patch enhances the
'slices' implementation to support 32 bits CPUs.

On PPC32, the address space is limited to 4Gbytes, hence only the low
slices will be used.

The high slices use bitmaps. As bitmap functions are not prepared to
handle bitmaps of size 0, this patch ensures that bitmap functions
are called only when SLICE_NUM_HIGH is not nul.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
 v2: First patch of v1 serie split in two parts ; added slice_bitmap_xxx() macros.
 v3: Moving slice related stuff in slice.h and slice_32/64.h
     slice_bitmap_xxx() are now static inline functions and platform dependent
     SLICE_LOW_TOP declared ull on PPC32 with correct casts allows to keep it 0x100000000
 v4: Moved slice_32.h and slice_64.h to respective subarch dirs
     Moved somes #ifdefs from asm/slice.h to respective subarch slice.h
     SLICE_LOW_ details distributed in repective subarch slices allthough they are identical for the moment
 v5: Split in two parts. The moving of slice related stuffs into slice.h files is now done in the preceding patch
     Based on several feedback received, this version removes the slice_bitmap_xxx() wrappers and comes back to
     the initial approach of checking that SLICE_NUM_HIGH is not nul before using bitmap_xxx() functions. Unlike
     the others, this approach has the advantage of allowing the reader to immediatly know what's going on and
     avoid all this set of copy/empty wrappers in subarch slice.h files. It also significantly reduces the size
     of the patch, which is a prerequisite for backporting it to stable releases.

 arch/powerpc/include/asm/nohash/32/slice.h | 18 +++++++++++++++
 arch/powerpc/include/asm/slice.h           |  4 +++-
 arch/powerpc/mm/slice.c                    | 37 +++++++++++++++++++++++-------
 3 files changed, 50 insertions(+), 9 deletions(-)
 create mode 100644 arch/powerpc/include/asm/nohash/32/slice.h

diff --git a/arch/powerpc/include/asm/nohash/32/slice.h b/arch/powerpc/include/asm/nohash/32/slice.h
new file mode 100644
index 000000000000..95d532e18092
--- /dev/null
+++ b/arch/powerpc/include/asm/nohash/32/slice.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_NOHASH_32_SLICE_H
+#define _ASM_POWERPC_NOHASH_32_SLICE_H
+
+#ifdef CONFIG_PPC_MM_SLICES
+
+#define SLICE_LOW_SHIFT		28
+#define SLICE_LOW_TOP		(0x100000000ull)
+#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
+#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
+
+#define SLICE_HIGH_SHIFT	0
+#define SLICE_NUM_HIGH		0ul
+#define GET_HIGH_SLICE_INDEX(addr)	(addr & 0)
+
+#endif /* CONFIG_PPC_MM_SLICES */
+
+#endif /* _ASM_POWERPC_NOHASH_32_SLICE_H */
diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h
index 17c5a5d8c418..172711fadb1c 100644
--- a/arch/powerpc/include/asm/slice.h
+++ b/arch/powerpc/include/asm/slice.h
@@ -4,8 +4,10 @@
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/book3s/64/slice.h>
-#else
+#elif defined(CONFIG_PPC64)
 #include <asm/nohash/64/slice.h>
+#elif defined(CONFIG_PPC_MMU_NOHASH)
+#include <asm/nohash/32/slice.h>
 #endif
 
 #ifdef CONFIG_PPC_MM_SLICES
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 98b53d48968f..0beca1ba2282 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -73,10 +73,12 @@ static void slice_range_to_mask(unsigned long start, unsigned long len,
 	unsigned long end = start + len - 1;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	if (start < SLICE_LOW_TOP) {
-		unsigned long mend = min(end, (SLICE_LOW_TOP - 1));
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
 
 		ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
 			- (1u << GET_LOW_SLICE_INDEX(start));
@@ -113,11 +115,13 @@ static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice)
 	unsigned long start = slice << SLICE_HIGH_SHIFT;
 	unsigned long end = start + (1ul << SLICE_HIGH_SHIFT);
 
+#ifdef CONFIG_PPC64
 	/* Hack, so that each addresses is controlled by exactly one
 	 * of the high or low area bitmaps, the first high area starts
 	 * at 4GB, not 0 */
 	if (start == 0)
 		start = SLICE_LOW_TOP;
+#endif
 
 	return !slice_area_is_free(mm, start, end - start);
 }
@@ -128,7 +132,8 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
 	unsigned long i;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	for (i = 0; i < SLICE_NUM_LOW; i++)
 		if (!slice_low_has_vma(mm, i))
@@ -151,7 +156,8 @@ static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_ma
 	u64 lpsizes;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	lpsizes = mm->context.low_slices_psize;
 	for (i = 0; i < SLICE_NUM_LOW; i++)
@@ -180,6 +186,10 @@ static int slice_check_fit(struct mm_struct *mm,
 	 */
 	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
 
+	if (!SLICE_NUM_HIGH)
+		return (mask.low_slices & available.low_slices) ==
+		       mask.low_slices;
+
 	bitmap_and(result, mask.high_slices,
 		   available.high_slices, slice_count);
 
@@ -189,6 +199,7 @@ static int slice_check_fit(struct mm_struct *mm,
 
 static void slice_flush_segments(void *parm)
 {
+#ifdef CONFIG_PPC64
 	struct mm_struct *mm = parm;
 	unsigned long flags;
 
@@ -200,6 +211,7 @@ static void slice_flush_segments(void *parm)
 	local_irq_save(flags);
 	slb_flush_and_rebolt();
 	local_irq_restore(flags);
+#endif
 }
 
 static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psize)
@@ -389,6 +401,8 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
 static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
 {
 	dst->low_slices |= src->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
 	bitmap_or(dst->high_slices, dst->high_slices, src->high_slices,
 		  SLICE_NUM_HIGH);
 }
@@ -397,6 +411,8 @@ static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *
 {
 	dst->low_slices &= ~src->low_slices;
 
+	if (!SLICE_NUM_HIGH)
+		return;
 	bitmap_andnot(dst->high_slices, dst->high_slices, src->high_slices,
 		      SLICE_NUM_HIGH);
 }
@@ -446,14 +462,17 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 * init different masks
 	 */
 	mask.low_slices = 0;
-	bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
 
 	/* silence stupid warning */;
 	potential_mask.low_slices = 0;
-	bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
 
 	compat_mask.low_slices = 0;
-	bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
+
+	if (SLICE_NUM_HIGH) {
+		bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
+		bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
+		bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
+	}
 
 	/* Sanity checks */
 	BUG_ON(mm->task_size == 0);
@@ -591,7 +610,9 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
  convert:
 	slice_andnot_mask(&mask, &good_mask);
 	slice_andnot_mask(&mask, &compat_mask);
-	if (mask.low_slices || !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
+	if (mask.low_slices ||
+	    (SLICE_NUM_HIGH &&
+	     !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH))) {
 		slice_convert(mm, mask, psize);
 		if (psize > MMU_PAGE_BASE)
 			on_each_cpu(slice_flush_segments, mm, 1);
-- 
2.13.3