[RFC PATCH v2 0/7] ARM: NOMMU: MPU updates

[RFC PATCH v2 0/7] ARM: NOMMU: MPU updates

[Vladimir Murzin]

Hi,

This is an update of the existent MPU code which consist set of
clean-ups and enhancements. The most significant changes are in the way
how MPU settings sync-up for secondaries (PATCH 3/7) and more flexible
layout for memory (PATCH 7/7). Since there is no in-tree user of MPU,
support for M-class has been added (PATCH 6/7).

Thanks!

Changelog:
	    RFC -> RFC v2
	       - fixed MPU enable for v7m (PATCH 6/7)

Vladimir Murzin (7):
  ARM: NOMMU: Move out MPU setup in separate module
  ARM: NOMMU: Update MPU accessors to use cp15 helpers
  ARM: NOMMU: Rework MPU to be mostly done in C
  ARM: NOMMU: Disallow MPU for XIP
  ARM: Kconfig: Kill CONFIG_VECTORS_BASE
  ARM: V7M: Add support for MPU to M-class
  ARM: NOMMU: Use more MPU regions to cover memory

 arch/arm/Kconfig               |   9 -
 arch/arm/Kconfig-nommu         |   4 +-
 arch/arm/include/asm/cputype.h |  10 +
 arch/arm/include/asm/mpu.h     |  23 ++-
 arch/arm/include/asm/smp.h     |   2 +-
 arch/arm/include/asm/v7m.h     |  10 +
 arch/arm/kernel/asm-offsets.c  |  11 +
 arch/arm/kernel/head-nommu.S   | 128 +++++++++---
 arch/arm/kernel/smp.c          |   2 +-
 arch/arm/mm/Makefile           |   1 +
 arch/arm/mm/nommu.c            | 254 +----------------------
 arch/arm/mm/pmsa-v7.c          | 445 +++++++++++++++++++++++++++++++++++++++++
 12 files changed, 598 insertions(+), 301 deletions(-)
 create mode 100644 arch/arm/mm/pmsa-v7.c

-- 
2.0.0

[RFC PATCH v2 1/7] ARM: NOMMU: Move out MPU setup in separate module

[Vladimir Murzin]

Having MPU handling code in dedicated module makes it easier to
enhance/maintain it.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
 arch/arm/include/asm/mpu.h |  16 ++-
 arch/arm/mm/Makefile       |   1 +
 arch/arm/mm/nommu.c        | 254 +------------------------------------------
 arch/arm/mm/pmsa-v7.c      | 262 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 276 insertions(+), 257 deletions(-)
 create mode 100644 arch/arm/mm/pmsa-v7.c

diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
index c3247cc..edec5cf 100644
--- a/arch/arm/include/asm/mpu.h
+++ b/arch/arm/include/asm/mpu.h
@@ -1,8 +1,6 @@
 #ifndef __ARM_MPU_H
 #define __ARM_MPU_H
 
-#ifdef CONFIG_ARM_MPU
-
 /* MPUIR layout */
 #define MPUIR_nU		1
 #define MPUIR_DREGION		8
@@ -69,8 +67,18 @@ struct mpu_rgn_info {
 };
 extern struct mpu_rgn_info mpu_rgn_info;
 
-#endif /* __ASSEMBLY__ */
+#ifdef CONFIG_ARM_MPU
+
+extern void __init adjust_lowmem_bounds_mpu(void);
+extern void __init mpu_setup(void);
 
-#endif /* CONFIG_ARM_MPU */
+#else
+
+static inline void adjust_lowmem_bounds_mpu(void) {}
+static inline void mpu_setup(void) {}
+
+#endif /* !CONFIG_ARM_MPU */
+
+#endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index b3dea80..73f8f3c 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
 
 ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o
+obj-$(CONFIG_ARM_MPU)		+= pmsa-v7.o
 endif
 
 obj-$(CONFIG_ARM_PTDUMP)	+= dump.o
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 3b8e728..4c56b56 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -27,259 +27,7 @@ unsigned long vectors_base;
 
 #ifdef CONFIG_ARM_MPU
 struct mpu_rgn_info mpu_rgn_info;
-
-/* Region number */
-static void rgnr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c2, 0" : : "r" (v));
-}
-
-/* Data-side / unified region attributes */
-
-/* Region access control register */
-static void dracr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 4" : : "r" (v));
-}
-
-/* Region size register */
-static void drsr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 2" : : "r" (v));
-}
-
-/* Region base address register */
-static void drbar_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 0" : : "r" (v));
-}
-
-static u32 drbar_read(void)
-{
-	u32 v;
-	asm("mrc        p15, 0, %0, c6, c1, 0" : "=r" (v));
-	return v;
-}
-/* Optional instruction-side region attributes */
-
-/* I-side Region access control register */
-static void iracr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 5" : : "r" (v));
-}
-
-/* I-side Region size register */
-static void irsr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 3" : : "r" (v));
-}
-
-/* I-side Region base address register */
-static void irbar_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 1" : : "r" (v));
-}
-
-static unsigned long irbar_read(void)
-{
-	unsigned long v;
-	asm("mrc        p15, 0, %0, c6, c1, 1" : "=r" (v));
-	return v;
-}
-
-/* MPU initialisation functions */
-void __init adjust_lowmem_bounds_mpu(void)
-{
-	phys_addr_t phys_offset = PHYS_OFFSET;
-	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
-	struct memblock_region *reg;
-	bool first = true;
-	phys_addr_t mem_start;
-	phys_addr_t mem_end;
-
-	for_each_memblock(memory, reg) {
-		if (first) {
-			/*
-			 * Initially only use memory continuous from
-			 * PHYS_OFFSET */
-			if (reg->base != phys_offset)
-				panic("First memory bank must be contiguous from PHYS_OFFSET");
-
-			mem_start = reg->base;
-			mem_end = reg->base + reg->size;
-			specified_mem_size = reg->size;
-			first = false;
-		} else {
-			/*
-			 * memblock auto merges contiguous blocks, remove
-			 * all blocks afterwards in one go (we can't remove
-			 * blocks separately while iterating)
-			 */
-			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
-				  &mem_end, &reg->base);
-			memblock_remove(reg->base, 0 - reg->base);
-			break;
-		}
-	}
-
-	/*
-	 * MPU has curious alignment requirements: Size must be power of 2, and
-	 * region start must be aligned to the region size
-	 */
-	if (phys_offset != 0)
-		pr_info("PHYS_OFFSET != 0 => MPU Region size constrained by alignment requirements\n");
-
-	/*
-	 * Maximum aligned region might overflow phys_addr_t if phys_offset is
-	 * 0. Hence we keep everything below 4G until we take the smaller of
-	 * the aligned_region_size and rounded_mem_size, one of which is
-	 * guaranteed to be smaller than the maximum physical address.
-	 */
-	aligned_region_size = (phys_offset - 1) ^ (phys_offset);
-	/* Find the max power-of-two sized region that fits inside our bank */
-	rounded_mem_size = (1 <<  __fls(specified_mem_size)) - 1;
-
-	/* The actual region size is the smaller of the two */
-	aligned_region_size = aligned_region_size < rounded_mem_size
-				? aligned_region_size + 1
-				: rounded_mem_size + 1;
-
-	if (aligned_region_size != specified_mem_size) {
-		pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
-				&specified_mem_size, &aligned_region_size);
-		memblock_remove(mem_start + aligned_region_size,
-				specified_mem_size - aligned_region_size);
-
-		mem_end = mem_start + aligned_region_size;
-	}
-
-	pr_debug("MPU Region from %pa size %pa (end %pa))\n",
-		&phys_offset, &aligned_region_size, &mem_end);
-
-}
-
-static int mpu_present(void)
-{
-	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
-}
-
-static int mpu_max_regions(void)
-{
-	/*
-	 * We don't support a different number of I/D side regions so if we
-	 * have separate instruction and data memory maps then return
-	 * whichever side has a smaller number of supported regions.
-	 */
-	u32 dregions, iregions, mpuir;
-	mpuir = read_cpuid(CPUID_MPUIR);
-
-	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
-
-	/* Check for separate d-side and i-side memory maps */
-	if (mpuir & MPUIR_nU)
-		iregions = (mpuir & MPUIR_IREGION_SZMASK) >> MPUIR_IREGION;
-
-	/* Use the smallest of the two maxima */
-	return min(dregions, iregions);
-}
-
-static int mpu_iside_independent(void)
-{
-	/* MPUIR.nU specifies whether there is *not* a unified memory map */
-	return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
-}
-
-static int mpu_min_region_order(void)
-{
-	u32 drbar_result, irbar_result;
-	/* We've kept a region free for this probing */
-	rgnr_write(MPU_PROBE_REGION);
-	isb();
-	/*
-	 * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
-	 * region order
-	*/
-	drbar_write(0xFFFFFFFC);
-	drbar_result = irbar_result = drbar_read();
-	drbar_write(0x0);
-	/* If the MPU is non-unified, we use the larger of the two minima*/
-	if (mpu_iside_independent()) {
-		irbar_write(0xFFFFFFFC);
-		irbar_result = irbar_read();
-		irbar_write(0x0);
-	}
-	isb(); /* Ensure that MPU region operations have completed */
-	/* Return whichever result is larger */
-	return __ffs(max(drbar_result, irbar_result));
-}
-
-static int mpu_setup_region(unsigned int number, phys_addr_t start,
-			unsigned int size_order, unsigned int properties)
-{
-	u32 size_data;
-
-	/* We kept a region free for probing resolution of MPU regions*/
-	if (number > mpu_max_regions() || number == MPU_PROBE_REGION)
-		return -ENOENT;
-
-	if (size_order > 32)
-		return -ENOMEM;
-
-	if (size_order < mpu_min_region_order())
-		return -ENOMEM;
-
-	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
-	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
-
-	dsb(); /* Ensure all previous data accesses occur with old mappings */
-	rgnr_write(number);
-	isb();
-	drbar_write(start);
-	dracr_write(properties);
-	isb(); /* Propagate properties before enabling region */
-	drsr_write(size_data);
-
-	/* Check for independent I-side registers */
-	if (mpu_iside_independent()) {
-		irbar_write(start);
-		iracr_write(properties);
-		isb();
-		irsr_write(size_data);
-	}
-	isb();
-
-	/* Store region info (we treat i/d side the same, so only store d) */
-	mpu_rgn_info.rgns[number].dracr = properties;
-	mpu_rgn_info.rgns[number].drbar = start;
-	mpu_rgn_info.rgns[number].drsr = size_data;
-	return 0;
-}
-
-/*
-* Set up default MPU regions, doing nothing if there is no MPU
-*/
-void __init mpu_setup(void)
-{
-	int region_err;
-	if (!mpu_present())
-		return;
-
-	region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET,
-					ilog2(memblock.memory.regions[0].size),
-					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
-	if (region_err) {
-		panic("MPU region initialization failure! %d", region_err);
-	} else {
-		pr_info("Using ARMv7 PMSA Compliant MPU. "
-			 "Region independence: %s, Max regions: %d\n",
-			mpu_iside_independent() ? "Yes" : "No",
-			mpu_max_regions());
-	}
-}
-#else
-static void adjust_lowmem_bounds_mpu(void) {}
-static void __init mpu_setup(void) {}
-#endif /* CONFIG_ARM_MPU */
+#endif
 
 #ifdef CONFIG_CPU_CP15
 #ifdef CONFIG_CPU_HIGH_VECTOR
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
new file mode 100644
index 0000000..ee3cf51
--- /dev/null
+++ b/arch/arm/mm/pmsa-v7.c
@@ -0,0 +1,262 @@
+/*
+ *  linux/arch/arm/mm/nommu.c
+ *
+ * ARM uCLinux supporting functions.
+ */
+
+#include <linux/memblock.h>
+
+#include <asm/cp15.h>
+#include <asm/cputype.h>
+#include <asm/mpu.h>
+
+#include "mm.h"
+
+/* Region number */
+static void rgnr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c2, 0" : : "r" (v));
+}
+
+/* Data-side / unified region attributes */
+
+/* Region access control register */
+static void dracr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 4" : : "r" (v));
+}
+
+/* Region size register */
+static void drsr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 2" : : "r" (v));
+}
+
+/* Region base address register */
+static void drbar_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 0" : : "r" (v));
+}
+
+static u32 drbar_read(void)
+{
+	u32 v;
+	asm("mrc        p15, 0, %0, c6, c1, 0" : "=r" (v));
+	return v;
+}
+/* Optional instruction-side region attributes */
+
+/* I-side Region access control register */
+static void iracr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 5" : : "r" (v));
+}
+
+/* I-side Region size register */
+static void irsr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 3" : : "r" (v));
+}
+
+/* I-side Region base address register */
+static void irbar_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 1" : : "r" (v));
+}
+
+static unsigned long irbar_read(void)
+{
+	unsigned long v;
+	asm("mrc        p15, 0, %0, c6, c1, 1" : "=r" (v));
+	return v;
+}
+
+/* MPU initialisation functions */
+void __init adjust_lowmem_bounds_mpu(void)
+{
+	phys_addr_t phys_offset = PHYS_OFFSET;
+	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
+	struct memblock_region *reg;
+	bool first = true;
+	phys_addr_t mem_start;
+	phys_addr_t mem_end;
+
+	for_each_memblock(memory, reg) {
+		if (first) {
+			/*
+			 * Initially only use memory continuous from
+			 * PHYS_OFFSET */
+			if (reg->base != phys_offset)
+				panic("First memory bank must be contiguous from PHYS_OFFSET");
+
+			mem_start = reg->base;
+			mem_end = reg->base + reg->size;
+			specified_mem_size = reg->size;
+			first = false;
+		} else {
+			/*
+			 * memblock auto merges contiguous blocks, remove
+			 * all blocks afterwards in one go (we can't remove
+			 * blocks separately while iterating)
+			 */
+			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
+				  &mem_end, &reg->base);
+			memblock_remove(reg->base, 0 - reg->base);
+			break;
+		}
+	}
+
+	/*
+	 * MPU has curious alignment requirements: Size must be power of 2, and
+	 * region start must be aligned to the region size
+	 */
+	if (phys_offset != 0)
+		pr_info("PHYS_OFFSET != 0 => MPU Region size constrained by alignment requirements\n");
+
+	/*
+	 * Maximum aligned region might overflow phys_addr_t if phys_offset is
+	 * 0. Hence we keep everything below 4G until we take the smaller of
+	 * the aligned_region_size and rounded_mem_size, one of which is
+	 * guaranteed to be smaller than the maximum physical address.
+	 */
+	aligned_region_size = (phys_offset - 1) ^ (phys_offset);
+	/* Find the max power-of-two sized region that fits inside our bank */
+	rounded_mem_size = (1 <<  __fls(specified_mem_size)) - 1;
+
+	/* The actual region size is the smaller of the two */
+	aligned_region_size = aligned_region_size < rounded_mem_size
+				? aligned_region_size + 1
+				: rounded_mem_size + 1;
+
+	if (aligned_region_size != specified_mem_size) {
+		pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
+				&specified_mem_size, &aligned_region_size);
+		memblock_remove(mem_start + aligned_region_size,
+				specified_mem_size - aligned_region_size);
+
+		mem_end = mem_start + aligned_region_size;
+	}
+
+	pr_debug("MPU Region from %pa size %pa (end %pa))\n",
+		&phys_offset, &aligned_region_size, &mem_end);
+
+}
+
+static int mpu_present(void)
+{
+	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
+}
+
+static int mpu_max_regions(void)
+{
+	/*
+	 * We don't support a different number of I/D side regions so if we
+	 * have separate instruction and data memory maps then return
+	 * whichever side has a smaller number of supported regions.
+	 */
+	u32 dregions, iregions, mpuir;
+	mpuir = read_cpuid(CPUID_MPUIR);
+
+	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
+
+	/* Check for separate d-side and i-side memory maps */
+	if (mpuir & MPUIR_nU)
+		iregions = (mpuir & MPUIR_IREGION_SZMASK) >> MPUIR_IREGION;
+
+	/* Use the smallest of the two maxima */
+	return min(dregions, iregions);
+}
+
+static int mpu_iside_independent(void)
+{
+	/* MPUIR.nU specifies whether there is *not* a unified memory map */
+	return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
+}
+
+static int mpu_min_region_order(void)
+{
+	u32 drbar_result, irbar_result;
+	/* We've kept a region free for this probing */
+	rgnr_write(MPU_PROBE_REGION);
+	isb();
+	/*
+	 * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
+	 * region order
+	*/
+	drbar_write(0xFFFFFFFC);
+	drbar_result = irbar_result = drbar_read();
+	drbar_write(0x0);
+	/* If the MPU is non-unified, we use the larger of the two minima*/
+	if (mpu_iside_independent()) {
+		irbar_write(0xFFFFFFFC);
+		irbar_result = irbar_read();
+		irbar_write(0x0);
+	}
+	isb(); /* Ensure that MPU region operations have completed */
+	/* Return whichever result is larger */
+	return __ffs(max(drbar_result, irbar_result));
+}
+
+static int mpu_setup_region(unsigned int number, phys_addr_t start,
+			unsigned int size_order, unsigned int properties)
+{
+	u32 size_data;
+
+	/* We kept a region free for probing resolution of MPU regions*/
+	if (number > mpu_max_regions() || number == MPU_PROBE_REGION)
+		return -ENOENT;
+
+	if (size_order > 32)
+		return -ENOMEM;
+
+	if (size_order < mpu_min_region_order())
+		return -ENOMEM;
+
+	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
+	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
+
+	dsb(); /* Ensure all previous data accesses occur with old mappings */
+	rgnr_write(number);
+	isb();
+	drbar_write(start);
+	dracr_write(properties);
+	isb(); /* Propagate properties before enabling region */
+	drsr_write(size_data);
+
+	/* Check for independent I-side registers */
+	if (mpu_iside_independent()) {
+		irbar_write(start);
+		iracr_write(properties);
+		isb();
+		irsr_write(size_data);
+	}
+	isb();
+
+	/* Store region info (we treat i/d side the same, so only store d) */
+	mpu_rgn_info.rgns[number].dracr = properties;
+	mpu_rgn_info.rgns[number].drbar = start;
+	mpu_rgn_info.rgns[number].drsr = size_data;
+	return 0;
+}
+
+/*
+* Set up default MPU regions, doing nothing if there is no MPU
+*/
+void __init mpu_setup(void)
+{
+	int region_err;
+	if (!mpu_present())
+		return;
+
+	region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET,
+					ilog2(memblock.memory.regions[0].size),
+					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
+	if (region_err) {
+		panic("MPU region initialization failure! %d", region_err);
+	} else {
+		pr_info("Using ARMv7 PMSA Compliant MPU. "
+			 "Region independence: %s, Max regions: %d\n",
+			mpu_iside_independent() ? "Yes" : "No",
+			mpu_max_regions());
+	}
+}
-- 
2.0.0

[RFC PATCH v2 2/7] ARM: NOMMU: Update MPU accessors to use cp15 helpers

[Vladimir Murzin]

Currently, inline assembly for accessing to MPU's cp15 lacks volatile
keyword which opens possibility to compiler to optimise such accesses
as soon as we start using them more intensively. Rather than fixing
inline asm, lets move MPU accessors to use cp15 helpers which do the
right thing.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
 arch/arm/mm/pmsa-v7.c | 48 ++++++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index ee3cf51..5b55f8f 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -12,63 +12,67 @@
 
 #include "mm.h"
 
+#define DRBAR	__ACCESS_CP15(c6, 0, c1, 0)
+#define IRBAR	__ACCESS_CP15(c6, 0, c1, 1)
+#define DRSR	__ACCESS_CP15(c6, 0, c1, 2)
+#define IRSR	__ACCESS_CP15(c6, 0, c1, 3)
+#define DRACR	__ACCESS_CP15(c6, 0, c1, 4)
+#define IRACR	__ACCESS_CP15(c6, 0, c1, 5)
+#define RNGNR	__ACCESS_CP15(c6, 0, c2, 0)
+
 /* Region number */
-static void rgnr_write(u32 v)
+static inline void rgnr_write(u32 v)
 {
-	asm("mcr        p15, 0, %0, c6, c2, 0" : : "r" (v));
+	write_sysreg(v, RNGNR);
 }
 
 /* Data-side / unified region attributes */
 
 /* Region access control register */
-static void dracr_write(u32 v)
+static inline void dracr_write(u32 v)
 {
-	asm("mcr        p15, 0, %0, c6, c1, 4" : : "r" (v));
+	write_sysreg(v, DRACR);
 }
 
 /* Region size register */
-static void drsr_write(u32 v)
+static inline void drsr_write(u32 v)
 {
-	asm("mcr        p15, 0, %0, c6, c1, 2" : : "r" (v));
+	write_sysreg(v, DRSR);
 }
 
 /* Region base address register */
-static void drbar_write(u32 v)
+static inline void drbar_write(u32 v)
 {
-	asm("mcr        p15, 0, %0, c6, c1, 0" : : "r" (v));
+	write_sysreg(v, DRBAR);
 }
 
-static u32 drbar_read(void)
+static inline u32 drbar_read(void)
 {
-	u32 v;
-	asm("mrc        p15, 0, %0, c6, c1, 0" : "=r" (v));
-	return v;
+	return read_sysreg(DRBAR);
 }
 /* Optional instruction-side region attributes */
 
 /* I-side Region access control register */
-static void iracr_write(u32 v)
+static inline void iracr_write(u32 v)
 {
-	asm("mcr        p15, 0, %0, c6, c1, 5" : : "r" (v));
+	write_sysreg(v, IRACR);
 }
 
 /* I-side Region size register */
-static void irsr_write(u32 v)
+static inline void irsr_write(u32 v)
 {
-	asm("mcr        p15, 0, %0, c6, c1, 3" : : "r" (v));
+	write_sysreg(v, IRSR);
 }
 
 /* I-side Region base address register */
-static void irbar_write(u32 v)
+static inline void irbar_write(u32 v)
 {
-	asm("mcr        p15, 0, %0, c6, c1, 1" : : "r" (v));
+	write_sysreg(v, IRBAR);
 }
 
-static unsigned long irbar_read(void)
+static inline u32 irbar_read(void)
 {
-	unsigned long v;
-	asm("mrc        p15, 0, %0, c6, c1, 1" : "=r" (v));
-	return v;
+	return read_sysreg(IRBAR);
 }
 
 /* MPU initialisation functions */
-- 
2.0.0

[RFC PATCH v2 3/7] ARM: NOMMU: Rework MPU to be mostly done in C

[Vladimir Murzin]

Currently, there are several issues with how MPU is setup:

 1. We won't boot if MPU is missing
 2. We won't boot if use XIP
 3. Further extension of MPU setup requires asm skills

The 1st point can be relaxed, so we can continue with boot CPU even if
MPU is missed and fail boot for secondaries only. To address the 2nd
point we could create region covering CONFIG_XIP_PHYS_ADDR - _end and
that might work for the first stage of MPU enable, but due to MPU's
alignment requirement we could cover too much, IOW we need more
flexibility in how we're partitioning memory regions... and it'd be
hardly possible to archive because of the 3rd point.

This patch is trying to address 1st and 3rd issues and paves the path
for 2nd and further improvements.

The most visible change introduced with this patch is that we start
using mpu_rgn_info array (as it was supposed?), so change in MPU setup
done by boot CPU is recorded there and feed to secondaries. It
allows us to keep minimal region setup for boot CPU and do the rest in
C. Since we start programming MPU regions in C evaluation of MPU
constrains (number of regions supported and minimal region order) can
be done once, which in turn open possibility to free-up "probe"
region early.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
 arch/arm/include/asm/mpu.h    |  2 +-
 arch/arm/include/asm/smp.h    |  2 +-
 arch/arm/kernel/asm-offsets.c | 11 ++++++
 arch/arm/kernel/head-nommu.S  | 80 +++++++++++++++++++++++++++++++++----------
 arch/arm/kernel/smp.c         |  2 +-
 arch/arm/mm/pmsa-v7.c         | 70 +++++++++++++++++++++++++++----------
 6 files changed, 127 insertions(+), 40 deletions(-)

diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
index edec5cf..403462e 100644
--- a/arch/arm/include/asm/mpu.h
+++ b/arch/arm/include/asm/mpu.h
@@ -62,7 +62,7 @@ struct mpu_rgn {
 };
 
 struct mpu_rgn_info {
-	u32 mpuir;
+	unsigned int used;
 	struct mpu_rgn rgns[MPU_MAX_REGIONS];
 };
 extern struct mpu_rgn_info mpu_rgn_info;
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 3d6dc8b..709a559 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -60,7 +60,7 @@ asmlinkage void secondary_start_kernel(void);
  */
 struct secondary_data {
 	union {
-		unsigned long mpu_rgn_szr;
+		struct mpu_rgn_info *mpu_rgn_info;
 		u64 pgdir;
 	};
 	unsigned long swapper_pg_dir;
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 6080082..0098d3c4 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -23,6 +23,7 @@
 #include <asm/mach/arch.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
+#include <asm/mpu.h>
 #include <asm/procinfo.h>
 #include <asm/suspend.h>
 #include <asm/vdso_datapage.h>
@@ -183,5 +184,15 @@ int main(void)
 #ifdef CONFIG_VDSO
   DEFINE(VDSO_DATA_SIZE,	sizeof(union vdso_data_store));
 #endif
+  BLANK();
+#ifdef CONFIG_ARM_MPU
+  DEFINE(MPU_RNG_INFO_RNGS,	offsetof(struct mpu_rgn_info, rgns));
+  DEFINE(MPU_RNG_INFO_USED,	offsetof(struct mpu_rgn_info, used));
+
+  DEFINE(MPU_RNG_SIZE,		sizeof(struct mpu_rgn));
+  DEFINE(MPU_RGN_DRBAR,		offsetof(struct mpu_rgn, drbar));
+  DEFINE(MPU_RGN_DRSR,		offsetof(struct mpu_rgn, drsr));
+  DEFINE(MPU_RGN_DRACR,		offsetof(struct mpu_rgn, dracr));
+#endif
   return 0; 
 }
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 2e21e08..5f90a5f 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -13,6 +13,7 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/errno.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
@@ -110,8 +111,8 @@ ENTRY(secondary_startup)
 
 #ifdef CONFIG_ARM_MPU
 	/* Use MPU region info supplied by __cpu_up */
-	ldr	r6, [r7]			@ get secondary_data.mpu_szr
-	bl      __setup_mpu			@ Initialize the MPU
+	ldr	r6, [r7]			@ get secondary_data.mpu_rgn_info
+	bl      __secondary_setup_mpu		@ Initialize the MPU
 #endif
 
 	badr	lr, 1f				@ return (PIC) address
@@ -204,13 +205,13 @@ ENTRY(__setup_mpu)
 	mrc	p15, 0, r0, c0, c1, 4		@ Read ID_MMFR0
 	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
 	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
-	bne	__error_p			@ Fail: ARM_MPU on NOT v7 PMSA
+	bxne	lr
 
 	/* Determine whether the D/I-side memory map is unified. We set the
 	 * flags here and continue to use them for the rest of this function */
 	mrc	p15, 0, r0, c0, c0, 4		@ MPUIR
 	ands	r5, r0, #MPUIR_DREGION_SZMASK	@ 0 size d region => No MPU
-	beq	__error_p			@ Fail: ARM_MPU and no MPU
+	bxeq	lr
 	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
 
 	/* Setup second region first to free up r6 */
@@ -238,27 +239,70 @@ ENTRY(__setup_mpu)
 	setup_region r0, r5, r6, MPU_INSTR_SIDE @ 0x0, BG region, enabled
 2:	isb
 
-	/* Vectors region */
-	set_region_nr r0, #MPU_VECTORS_REGION
+	/* Enable the MPU */
+	mrc	p15, 0, r0, c1, c0, 0		@ Read SCTLR
+	bic	r0, r0, #CR_BR			@ Disable the 'default mem-map'
+	orr	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
+	mcr	p15, 0, r0, c1, c0, 0		@ Enable MPU
+	isb
+
+	ret	lr
+ENDPROC(__setup_mpu)
+
+#ifdef CONFIG_SMP
+/*
+ * r6: pointer at mpu_rgn_info
+ */
+
+ENTRY(__secondary_setup_mpu)
+	/* Probe for v7 PMSA compliance */
+	mrc	p15, 0, r0, c0, c1, 4		@ Read ID_MMFR0
+	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
+	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
+	bne	__error_p
+
+	/* Determine whether the D/I-side memory map is unified. We set the
+	 * flags here and continue to use them for the rest of this function */
+	mrc	p15, 0, r0, c0, c0, 4		@ MPUIR
+	ands	r5, r0, #MPUIR_DREGION_SZMASK	@ 0 size d region => No MPU
+	beq	__error_p
+
+	ldr	r4, [r6, #MPU_RNG_INFO_USED]
+	mov	r5, #MPU_RNG_SIZE
+	add	r3, r6, #MPU_RNG_INFO_RNGS
+	mla	r3, r4, r5, r3
+
+1:
+	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
+	sub	r3, r3, #MPU_RNG_SIZE
+	sub	r4, r4, #1
+
+	set_region_nr r0, r4
 	isb
-	/* Shared, inaccessible to PL0, rw PL1 */
-	mov	r0, #CONFIG_VECTORS_BASE	@ Cover from VECTORS_BASE
-	ldr	r5,=(MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL)
-	/* Writing N to bits 5:1 (RSR_SZ) --> region size 2^N+1 */
-	mov	r6, #(((2 * PAGE_SHIFT - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN)
 
-	setup_region r0, r5, r6, MPU_DATA_SIDE	@ VECTORS_BASE, PL0 NA, enabled
-	beq	3f				@ Memory-map not unified
-	setup_region r0, r5, r6, MPU_INSTR_SIDE	@ VECTORS_BASE, PL0 NA, enabled
-3:	isb
+	ldr	r0, [r3, #MPU_RGN_DRBAR]
+	ldr	r6, [r3, #MPU_RGN_DRSR]
+	ldr	r5, [r3, #MPU_RGN_DRACR]
+
+	setup_region r0, r5, r6, MPU_DATA_SIDE
+	beq	2f
+	setup_region r0, r5, r6, MPU_INSTR_SIDE
+2:	isb
+
+	mrc	p15, 0, r0, c0, c0, 4		@ Reevaluate the MPUIR
+	cmp	r4, #0
+	bgt	1b
 
 	/* Enable the MPU */
 	mrc	p15, 0, r0, c1, c0, 0		@ Read SCTLR
-	bic     r0, r0, #CR_BR			@ Disable the 'default mem-map'
+	bic	r0, r0, #CR_BR			@ Disable the 'default mem-map'
 	orr	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
 	mcr	p15, 0, r0, c1, c0, 0		@ Enable MPU
 	isb
+
 	ret	lr
-ENDPROC(__setup_mpu)
-#endif
+ENDPROC(__secondary_setup_mpu)
+
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_ARM_MPU */
 #include "head-common.S"
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 572a8df..5cb8cdf 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -114,7 +114,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	 */
 	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
 #ifdef CONFIG_ARM_MPU
-	secondary_data.mpu_rgn_szr = mpu_rgn_info.rgns[MPU_RAM_REGION].drsr;
+	secondary_data.mpu_rgn_info = &mpu_rgn_info;
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index 5b55f8f..029d204 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -12,6 +12,9 @@
 
 #include "mm.h"
 
+static unsigned int __initdata mpu_min_region_order;
+static unsigned int __initdata mpu_max_regions;
+
 #define DRBAR	__ACCESS_CP15(c6, 0, c1, 0)
 #define IRBAR	__ACCESS_CP15(c6, 0, c1, 1)
 #define DRSR	__ACCESS_CP15(c6, 0, c1, 2)
@@ -75,6 +78,11 @@ static inline u32 irbar_read(void)
 	return read_sysreg(IRBAR);
 }
 
+static int __init mpu_present(void)
+{
+	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
+}
+
 /* MPU initialisation functions */
 void __init adjust_lowmem_bounds_mpu(void)
 {
@@ -85,6 +93,9 @@ void __init adjust_lowmem_bounds_mpu(void)
 	phys_addr_t mem_start;
 	phys_addr_t mem_end;
 
+	if (!mpu_present())
+		return;
+
 	for_each_memblock(memory, reg) {
 		if (first) {
 			/*
@@ -146,12 +157,7 @@ void __init adjust_lowmem_bounds_mpu(void)
 
 }
 
-static int mpu_present(void)
-{
-	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
-}
-
-static int mpu_max_regions(void)
+static int __init __mpu_max_regions(void)
 {
 	/*
 	 * We don't support a different number of I/D side regions so if we
@@ -159,6 +165,7 @@ static int mpu_max_regions(void)
 	 * whichever side has a smaller number of supported regions.
 	 */
 	u32 dregions, iregions, mpuir;
+
 	mpuir = read_cpuid(CPUID_MPUIR);
 
 	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
@@ -171,15 +178,16 @@ static int mpu_max_regions(void)
 	return min(dregions, iregions);
 }
 
-static int mpu_iside_independent(void)
+static int __init mpu_iside_independent(void)
 {
 	/* MPUIR.nU specifies whether there is *not* a unified memory map */
 	return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
 }
 
-static int mpu_min_region_order(void)
+static int __init __mpu_min_region_order(void)
 {
 	u32 drbar_result, irbar_result;
+
 	/* We've kept a region free for this probing */
 	rgnr_write(MPU_PROBE_REGION);
 	isb();
@@ -198,22 +206,24 @@ static int mpu_min_region_order(void)
 	}
 	isb(); /* Ensure that MPU region operations have completed */
 	/* Return whichever result is larger */
+
 	return __ffs(max(drbar_result, irbar_result));
 }
 
-static int mpu_setup_region(unsigned int number, phys_addr_t start,
+static int __init mpu_setup_region(unsigned int number, phys_addr_t start,
 			unsigned int size_order, unsigned int properties)
 {
 	u32 size_data;
 
 	/* We kept a region free for probing resolution of MPU regions*/
-	if (number > mpu_max_regions() || number == MPU_PROBE_REGION)
+	if (number > mpu_max_regions
+	    || number >= MPU_MAX_REGIONS)
 		return -ENOENT;
 
 	if (size_order > 32)
 		return -ENOMEM;
 
-	if (size_order < mpu_min_region_order())
+	if (size_order < mpu_min_region_order)
 		return -ENOMEM;
 
 	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
@@ -240,6 +250,9 @@ static int mpu_setup_region(unsigned int number, phys_addr_t start,
 	mpu_rgn_info.rgns[number].dracr = properties;
 	mpu_rgn_info.rgns[number].drbar = start;
 	mpu_rgn_info.rgns[number].drsr = size_data;
+
+	mpu_rgn_info.used++;
+
 	return 0;
 }
 
@@ -248,19 +261,38 @@ static int mpu_setup_region(unsigned int number, phys_addr_t start,
 */
 void __init mpu_setup(void)
 {
-	int region_err;
+	int region = 0, err = 0;
+
 	if (!mpu_present())
 		return;
 
-	region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET,
-					ilog2(memblock.memory.regions[0].size),
-					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
-	if (region_err) {
-		panic("MPU region initialization failure! %d", region_err);
+	/* Free-up MPU_PROBE_REGION */
+	mpu_min_region_order = __mpu_min_region_order();
+
+	/* How many regions are supported */
+	mpu_max_regions = __mpu_max_regions();
+
+	/* Now setup MPU (order is important) */
+
+	/* Background */
+	err |= mpu_setup_region(region++, 0, 32,
+				MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA);
+
+	/* RAM */
+	err |= mpu_setup_region(region++, PHYS_OFFSET,
+				ilog2(memblock.memory.regions[0].size),
+				MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
+
+	/* Vectors */
+	err |= mpu_setup_region(region++, vectors_base,
+				ilog2(2 * PAGE_SIZE),
+				MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL);
+	if (err) {
+		panic("MPU region initialization failure! %d", err);
 	} else {
 		pr_info("Using ARMv7 PMSA Compliant MPU. "
-			 "Region independence: %s, Max regions: %d\n",
+			 "Region independence: %s, Used %d of %d regions\n",
 			mpu_iside_independent() ? "Yes" : "No",
-			mpu_max_regions());
+			mpu_rgn_info.used, mpu_max_regions);
 	}
 }
-- 
2.0.0

[RFC PATCH v2 4/7] ARM: NOMMU: Disallow MPU for XIP

[Vladimir Murzin]

It seems that MPU never worked with XIP, so we just disallow such
combination.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
 arch/arm/Kconfig-nommu | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/Kconfig-nommu b/arch/arm/Kconfig-nommu
index b757634..6d18395 100644
--- a/arch/arm/Kconfig-nommu
+++ b/arch/arm/Kconfig-nommu
@@ -52,7 +52,7 @@ config REMAP_VECTORS_TO_RAM
 
 config ARM_MPU
        bool 'Use the ARM v7 PMSA Compliant MPU'
-       depends on CPU_V7
+       depends on !XIP_KERNEL && CPU_V7
        default y
        help
          Some ARM systems without an MMU have instead a Memory Protection
-- 
2.0.0

[RFC PATCH v2 5/7] ARM: Kconfig: Kill CONFIG_VECTORS_BASE

[Vladimir Murzin]

The last user of CONFIG_VECTORS_BASE has gone, so kill it.

Reported-by: Afzal Mohammed <afzal.mohd.ma@gmail.com>
Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
 arch/arm/Kconfig | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9eb2529..332b6f2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -236,15 +236,6 @@ config NEED_RET_TO_USER
 config ARCH_MTD_XIP
 	bool
 
-config VECTORS_BASE
-	hex
-	default 0xffff0000 if MMU || CPU_HIGH_VECTOR
-	default DRAM_BASE if REMAP_VECTORS_TO_RAM
-	default 0x00000000
-	help
-	  The base address of exception vectors.  This must be two pages
-	  in size.
-
 config ARM_PATCH_PHYS_VIRT
 	bool "Patch physical to virtual translations at runtime" if EMBEDDED
 	default y
-- 
2.0.0

[RFC PATCH v2 6/7] ARM: V7M: Add support for MPU to M-class

[Vladimir Murzin]

This patch makes it possible to use MPU with v7M cores.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
 arch/arm/Kconfig-nommu         |  4 +--
 arch/arm/include/asm/cputype.h | 10 ++++++++
 arch/arm/include/asm/v7m.h     | 10 ++++++++
 arch/arm/kernel/head-nommu.S   | 56 ++++++++++++++++++++++++++++++------------
 arch/arm/mm/pmsa-v7.c          | 53 +++++++++++++++++++++++++++++++++++++--
 5 files changed, 113 insertions(+), 20 deletions(-)

diff --git a/arch/arm/Kconfig-nommu b/arch/arm/Kconfig-nommu
index 6d18395..930e000 100644
--- a/arch/arm/Kconfig-nommu
+++ b/arch/arm/Kconfig-nommu
@@ -52,8 +52,8 @@ config REMAP_VECTORS_TO_RAM
 
 config ARM_MPU
        bool 'Use the ARM v7 PMSA Compliant MPU'
-       depends on !XIP_KERNEL && CPU_V7
-       default y
+       depends on !XIP_KERNEL && (CPU_V7 || CPU_V7M)
+       default y if CPU_V7
        help
          Some ARM systems without an MMU have instead a Memory Protection
          Unit (MPU) that defines the type and permissions for regions of
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index b62eaeb..abaac5e 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -173,6 +173,11 @@ static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 	return read_cpuid(CPUID_CACHETYPE);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mputype(void)
+{
+	return read_cpuid(CPUID_MPUIR);
+}
+
 #elif defined(CONFIG_CPU_V7M)
 
 static inline unsigned int __attribute_const__ read_cpuid_id(void)
@@ -185,6 +190,11 @@ static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 	return readl(BASEADDR_V7M_SCB + V7M_SCB_CTR);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mputype(void)
+{
+	return readl(BASEADDR_V7M_SCB + MPU_TYPE);
+}
+
 #else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */
 
 static inline unsigned int __attribute_const__ read_cpuid_id(void)
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
index 1fd775c..5de776c 100644
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@@ -57,6 +57,16 @@
 #define	V7M_SCB_CCSIDR		0x80	/* Cache size ID register */
 #define	V7M_SCB_CSSELR		0x84	/* Cache size selection register */
 
+/* Memory-mapped MPU registers for M-class */
+#define MPU_TYPE		0x90
+#define MPU_CTRL		0x94
+#define MPU_CTRL_ENABLE		1
+#define MPU_CTRL_PRIVDEFENA	(1 << 2)
+
+#define MPU_RNR			0x98
+#define MPU_RBAR		0x9c
+#define MPU_RASR		0xa0
+
 /* Cache opeartions */
 #define	V7M_SCB_ICIALLU		0x250	/* I-cache invalidate all to PoU */
 #define	V7M_SCB_ICIMVAU		0x258	/* I-cache invalidate by MVA to PoU */
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 5f90a5f..0d64b8b 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -176,19 +176,33 @@ ENDPROC(__after_proc_init)
 #ifdef CONFIG_ARM_MPU
 
 
+#ifndef CONFIG_CPU_V7M
 /* Set which MPU region should be programmed */
-.macro set_region_nr tmp, rgnr
+.macro set_region_nr tmp, rgnr, unused
 	mov	\tmp, \rgnr			@ Use static region numbers
 	mcr	p15, 0, \tmp, c6, c2, 0		@ Write RGNR
 .endm
 
 /* Setup a single MPU region, either D or I side (D-side for unified) */
-.macro setup_region bar, acr, sr, side = MPU_DATA_SIDE
+.macro setup_region bar, acr, sr, side = MPU_DATA_SIDE, unused
 	mcr	p15, 0, \bar, c6, c1, (0 + \side)	@ I/DRBAR
 	mcr	p15, 0, \acr, c6, c1, (4 + \side)	@ I/DRACR
 	mcr	p15, 0, \sr, c6, c1, (2 + \side)		@ I/DRSR
 .endm
+#else
+.macro set_region_nr tmp, rgnr, base
+	mov	\tmp, \rgnr
+	str     \tmp, [\base, #MPU_RNR]
+.endm
+
+.macro setup_region bar, acr, sr, unused, base
+	lsl     \acr, \acr, #16
+	orr     \acr, \acr, \sr
+	str     \bar, [\base, #MPU_RBAR]
+	str     \acr, [\base, #MPU_RASR]
+.endm
 
+#endif
 /*
  * Setup the MPU and initial MPU Regions. We create the following regions:
  * Region 0: Use this for probing the MPU details, so leave disabled.
@@ -202,48 +216,58 @@ ENDPROC(__after_proc_init)
 ENTRY(__setup_mpu)
 
 	/* Probe for v7 PMSA compliance */
-	mrc	p15, 0, r0, c0, c1, 4		@ Read ID_MMFR0
+M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
+M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+
+AR_CLASS(mrc	p15, 0, r0, c0, c1, 4)		@ Read ID_MMFR0
+M_CLASS(ldr	r0, [r12, 0x50])
 	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
 	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
 	bxne	lr
 
 	/* Determine whether the D/I-side memory map is unified. We set the
 	 * flags here and continue to use them for the rest of this function */
-	mrc	p15, 0, r0, c0, c0, 4		@ MPUIR
+AR_CLASS(mrc	p15, 0, r0, c0, c0, 4)		@ MPUIR
+M_CLASS(ldr    r0, [r12, #MPU_TYPE])
 	ands	r5, r0, #MPUIR_DREGION_SZMASK	@ 0 size d region => No MPU
 	bxeq	lr
 	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
 
 	/* Setup second region first to free up r6 */
-	set_region_nr r0, #MPU_RAM_REGION
+	set_region_nr r0, #MPU_RAM_REGION, r12
 	isb
 	/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
 	ldr	r0, =PLAT_PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
 	ldr	r5,=(MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL)
 
-	setup_region r0, r5, r6, MPU_DATA_SIDE	@ PHYS_OFFSET, shared, enabled
-	beq	1f				@ Memory-map not unified
-	setup_region r0, r5, r6, MPU_INSTR_SIDE @ PHYS_OFFSET, shared, enabled
+	setup_region r0, r5, r6, MPU_DATA_SIDE, r12	@ PHYS_OFFSET, shared, enabled
+	beq	1f					@ Memory-map not unified
+	setup_region r0, r5, r6, MPU_INSTR_SIDE, r12	@ PHYS_OFFSET, shared, enabled
 1:	isb
 
 	/* First/background region */
-	set_region_nr r0, #MPU_BG_REGION
+	set_region_nr r0, #MPU_BG_REGION, r12
 	isb
 	/* Execute Never,  strongly ordered, inaccessible to PL0, rw PL1  */
 	mov	r0, #0				@ BG region starts at 0x0
 	ldr	r5,=(MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA)
 	mov	r6, #MPU_RSR_ALL_MEM		@ 4GB region, enabled
 
-	setup_region r0, r5, r6, MPU_DATA_SIDE	@ 0x0, BG region, enabled
-	beq	2f				@ Memory-map not unified
-	setup_region r0, r5, r6, MPU_INSTR_SIDE @ 0x0, BG region, enabled
+	setup_region r0, r5, r6, MPU_DATA_SIDE, r12	@ 0x0, BG region, enabled
+	beq	2f					@ Memory-map not unified
+	setup_region r0, r5, r6, MPU_INSTR_SIDE r12	@ 0x0, BG region, enabled
 2:	isb
 
 	/* Enable the MPU */
-	mrc	p15, 0, r0, c1, c0, 0		@ Read SCTLR
-	bic	r0, r0, #CR_BR			@ Disable the 'default mem-map'
-	orr	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
-	mcr	p15, 0, r0, c1, c0, 0		@ Enable MPU
+AR_CLASS(mrc	p15, 0, r0, c1, c0, 0)		@ Read SCTLR
+AR_CLASS(bic	r0, r0, #CR_BR)			@ Disable the 'default mem-map'
+AR_CLASS(orr	r0, r0, #CR_M)			@ Set SCTRL.M (MPU on)
+AR_CLASS(mcr	p15, 0, r0, c1, c0, 0)		@ Enable MPU
+
+M_CLASS(ldr	r0, [r12, #MPU_CTRL])
+M_CLASS(bic	r0, #MPU_CTRL_PRIVDEFENA)
+M_CLASS(orr	r0, #MPU_CTRL_ENABLE)
+M_CLASS(str	r0, [r12, #MPU_CTRL])
 	isb
 
 	ret	lr
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index 029d204..72f1a9f 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -15,6 +15,8 @@
 static unsigned int __initdata mpu_min_region_order;
 static unsigned int __initdata mpu_max_regions;
 
+#ifndef CONFIG_CPU_V7M
+
 #define DRBAR	__ACCESS_CP15(c6, 0, c1, 0)
 #define IRBAR	__ACCESS_CP15(c6, 0, c1, 1)
 #define DRSR	__ACCESS_CP15(c6, 0, c1, 2)
@@ -78,6 +80,51 @@ static inline u32 irbar_read(void)
 	return read_sysreg(IRBAR);
 }
 
+#else
+
+static inline void rgnr_write(u32 v)
+{
+	writel_relaxed(v, BASEADDR_V7M_SCB + MPU_RNR);
+}
+
+/* Data-side / unified region attributes */
+
+/* Region access control register */
+static inline void dracr_write(u32 v)
+{
+	u32 rsr = readl_relaxed(BASEADDR_V7M_SCB + MPU_RASR) & GENMASK(15, 0);
+
+	writel_relaxed((v << 16) | rsr, BASEADDR_V7M_SCB + MPU_RASR);
+}
+
+/* Region size register */
+static inline void drsr_write(u32 v)
+{
+	u32 racr = readl_relaxed(BASEADDR_V7M_SCB + MPU_RASR) & GENMASK(31, 16);
+
+	writel_relaxed(v | racr, BASEADDR_V7M_SCB + MPU_RASR);
+}
+
+/* Region base address register */
+static inline void drbar_write(u32 v)
+{
+	writel_relaxed(v, BASEADDR_V7M_SCB + MPU_RBAR);
+}
+
+static inline u32 drbar_read(void)
+{
+	return readl_relaxed(BASEADDR_V7M_SCB + MPU_RBAR);
+}
+
+/* ARMv7-M only supports a unified MPU, so I-side operations are nop */
+
+static inline void iracr_write(u32 v) {}
+static inline void irsr_write(u32 v) {}
+static inline void irbar_write(u32 v) {}
+static inline unsigned long irbar_read(void) {return 0;}
+
+#endif
+
 static int __init mpu_present(void)
 {
 	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
@@ -166,7 +213,7 @@ static int __init __mpu_max_regions(void)
 	 */
 	u32 dregions, iregions, mpuir;
 
-	mpuir = read_cpuid(CPUID_MPUIR);
+	mpuir = read_cpuid_mputype();
 
 	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
 
@@ -181,7 +228,7 @@ static int __init __mpu_max_regions(void)
 static int __init mpu_iside_independent(void)
 {
 	/* MPUIR.nU specifies whether there is *not* a unified memory map */
-	return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
+	return read_cpuid_mputype() & MPUIR_nU;
 }
 
 static int __init __mpu_min_region_order(void)
@@ -284,9 +331,11 @@ void __init mpu_setup(void)
 				MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
 
 	/* Vectors */
+#ifndef CONFIG_CPU_V7M
 	err |= mpu_setup_region(region++, vectors_base,
 				ilog2(2 * PAGE_SIZE),
 				MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL);
+#endif
 	if (err) {
 		panic("MPU region initialization failure! %d", err);
 	} else {
-- 
2.0.0

[RFC PATCH v2 7/7] ARM: NOMMU: Use more MPU regions to cover memory

[Vladimir Murzin]

PMSAv7 defines curious alignment requirements to the regions:
- size must be power of 2, and
- region start must be aligned to the region size

Because of that we currently adjust lowmem bounds plus we assign
only one MPU region to cover memory all these lead to significant amount of
memory could be wasted. As an example, consider 64Mb of memory at
0x70000000 - it fits alignment requirements nicely; now, imagine that
2Mb of memory is reserved for coherent DMA allocation, so now Linux is
expected to see 62Mb of memory... and here annoying thing happens -
memory gets truncated to 32Mb (we've lost 30Mb!), i.e. MPU layout
looks like:

0: base 0x70000000, size 0x2000000

This patch tries to allocate as much as possible MPU slots to minimise
amount of truncated memory. Moreover, with this patch MPU subregions
starting to get used. MPU subregions allow us reduce the number of MPU
slots used. For example given above, MPU layout looks like:

0: base 0x70000000, size 0x2000000
1: base 0x72000000, size 0x1000000
2: base 0x73000000, size 0x1000000, disable subreg 7 (0x73e00000 - 0x73ffffff)

Where without subregions we'd get:

0: base 0x70000000, size 0x2000000
1: base 0x72000000, size 0x1000000
2: base 0x73000000, size 0x800000
3: base 0x73800000, size 0x400000
4: base 0x73c00000, size 0x200000

To achieve better layout we fist try to cover specified memory as is
(maybe with help of subregions) and if we failed, we truncate memory
to fit alignment requirements (so it occupies one MPU slot) and
perform one more attempt with the reminder, and so on till we either
cover all memory or run out of MPU slots.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
---
 arch/arm/include/asm/mpu.h |   5 ++
 arch/arm/mm/pmsa-v7.c      | 190 ++++++++++++++++++++++++++++++++++-----------
 2 files changed, 149 insertions(+), 46 deletions(-)

diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
index 403462e..5db37a6 100644
--- a/arch/arm/include/asm/mpu.h
+++ b/arch/arm/include/asm/mpu.h
@@ -15,6 +15,11 @@
 /* MPU D/I Size Register fields */
 #define MPU_RSR_SZ		1
 #define MPU_RSR_EN		0
+#define MPU_RSR_SD		8
+
+/* Number of subregions (SD) */
+#define MPU_NR_SUBREGS		8
+#define MPU_MIN_SUBREG_SIZE	256
 
 /* The D/I RSR value for an enabled region spanning the whole of memory */
 #define MPU_RSR_ALL_MEM		63
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index 72f1a9f..c1f1fc7 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -4,6 +4,7 @@
  * ARM uCLinux supporting functions.
  */
 
+#include <linux/bitops.h>
 #include <linux/memblock.h>
 
 #include <asm/cp15.h>
@@ -12,9 +13,20 @@
 
 #include "mm.h"
 
+struct region {
+	phys_addr_t base;
+	phys_addr_t size;
+	unsigned long subreg;
+};
+
+static struct region __initdata mem[MPU_MAX_REGIONS];
+
 static unsigned int __initdata mpu_min_region_order;
 static unsigned int __initdata mpu_max_regions;
 
+static int __init __mpu_min_region_order(void);
+static int __init __mpu_max_regions(void);
+
 #ifndef CONFIG_CPU_V7M
 
 #define DRBAR	__ACCESS_CP15(c6, 0, c1, 0)
@@ -130,19 +142,120 @@ static int __init mpu_present(void)
 	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
 }
 
+static bool __init try_split_region(phys_addr_t base, phys_addr_t size, struct region *region)
+{
+	unsigned long  subreg, bslots, sslots;
+	phys_addr_t abase = base & ~(size - 1);
+	phys_addr_t asize = base + size - abase;
+	phys_addr_t p2size = 1 << __fls(asize);
+	phys_addr_t bdiff, sdiff;
+
+	if (p2size != asize)
+		p2size *= 2;
+
+	bdiff = base - abase;
+	sdiff = p2size - asize;
+	subreg = p2size / MPU_NR_SUBREGS;
+
+	if ((bdiff % subreg) || (sdiff % subreg))
+		return false;
+
+	bslots = bdiff / subreg;
+	sslots = sdiff / subreg;
+
+	if (bslots || sslots) {
+		int i;
+
+		if (subreg < MPU_MIN_SUBREG_SIZE)
+			return false;
+
+		if (bslots + sslots > MPU_NR_SUBREGS)
+			return false;
+
+		for (i = 0; i < bslots; i++)
+			_set_bit(i, &region->subreg);
+
+		for (i = 1; i <= sslots; i++)
+			_set_bit(MPU_NR_SUBREGS - i, &region->subreg);
+	}
+
+	region->base = abase;
+	region->size = p2size;
+
+	return true;
+}
+
+static int __init allocate_region(phys_addr_t base, phys_addr_t size,
+				  unsigned int limit, struct region *regions)
+{
+	int count = 0;
+	phys_addr_t diff = size;
+	int attempts = MPU_MAX_REGIONS;
+
+	while (diff) {
+		/* Try cover region as is (maybe with help of subregions) */
+		if (try_split_region(base, size, &regions[count])) {
+			count++;
+			base += size;
+			diff -= size;
+			size = diff;
+		} else {
+			/*
+			 * Maximum aligned region might overflow phys_addr_t
+			 * if "base" is 0. Hence we keep everything below 4G
+			 * until we take the smaller of the aligned region
+			 * size ("asize") and rounded region size ("p2size"),
+			 * one of which is guaranteed to be smaller than the
+			 * maximum physical address.
+			 */
+			phys_addr_t asize = (base - 1) ^ base;
+			phys_addr_t p2size = (1 <<  __fls(diff)) - 1;
+
+			size = asize < p2size ? asize + 1 : p2size + 1;
+		}
+
+		if (count > limit)
+			break;
+
+		if (!attempts)
+			break;
+
+		attempts--;
+	}
+
+	return count;
+}
+
 /* MPU initialisation functions */
 void __init adjust_lowmem_bounds_mpu(void)
 {
 	phys_addr_t phys_offset = PHYS_OFFSET;
-	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
+	phys_addr_t  specified_mem_size, total_mem_size = 0;
 	struct memblock_region *reg;
 	bool first = true;
 	phys_addr_t mem_start;
 	phys_addr_t mem_end;
+	unsigned int mem_max_regions;
+	int num, i;
 
 	if (!mpu_present())
 		return;
 
+	/* Free-up MPU_PROBE_REGION */
+	mpu_min_region_order = __mpu_min_region_order();
+
+	/* How many regions are supported */
+	mpu_max_regions = __mpu_max_regions();
+
+	mem_max_regions = min((unsigned int)MPU_MAX_REGIONS, mpu_max_regions);
+
+	/* We need to keep one slot for background region */
+	mem_max_regions--;
+
+#ifndef CONFIG_CPU_V7M
+	/* ... and one for vectors */
+	mem_max_regions--;
+#endif
 	for_each_memblock(memory, reg) {
 		if (first) {
 			/*
@@ -168,40 +281,23 @@ void __init adjust_lowmem_bounds_mpu(void)
 		}
 	}
 
-	/*
-	 * MPU has curious alignment requirements: Size must be power of 2, and
-	 * region start must be aligned to the region size
-	 */
-	if (phys_offset != 0)
-		pr_info("PHYS_OFFSET != 0 => MPU Region size constrained by alignment requirements\n");
-
-	/*
-	 * Maximum aligned region might overflow phys_addr_t if phys_offset is
-	 * 0. Hence we keep everything below 4G until we take the smaller of
-	 * the aligned_region_size and rounded_mem_size, one of which is
-	 * guaranteed to be smaller than the maximum physical address.
-	 */
-	aligned_region_size = (phys_offset - 1) ^ (phys_offset);
-	/* Find the max power-of-two sized region that fits inside our bank */
-	rounded_mem_size = (1 <<  __fls(specified_mem_size)) - 1;
+	num = allocate_region(mem_start, specified_mem_size, mem_max_regions, mem);
 
-	/* The actual region size is the smaller of the two */
-	aligned_region_size = aligned_region_size < rounded_mem_size
-				? aligned_region_size + 1
-				: rounded_mem_size + 1;
+	for (i = 0; i < num; i++) {
+		unsigned long  subreg = mem[i].size / MPU_NR_SUBREGS;
 
-	if (aligned_region_size != specified_mem_size) {
-		pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
-				&specified_mem_size, &aligned_region_size);
-		memblock_remove(mem_start + aligned_region_size,
-				specified_mem_size - aligned_region_size);
+		total_mem_size += mem[i].size - subreg * hweight_long(mem[i].subreg);
 
-		mem_end = mem_start + aligned_region_size;
+		pr_debug("MPU: base %pa size %pa disable subregions: %*pbl\n",
+			 &mem[i].base, &mem[i].size, MPU_NR_SUBREGS, &mem[i].subreg);
 	}
 
-	pr_debug("MPU Region from %pa size %pa (end %pa))\n",
-		&phys_offset, &aligned_region_size, &mem_end);
-
+	if (total_mem_size != specified_mem_size) {
+		pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
+				&specified_mem_size, &total_mem_size);
+		memblock_remove(mem_start + total_mem_size,
+				specified_mem_size - total_mem_size);
+	}
 }
 
 static int __init __mpu_max_regions(void)
@@ -258,7 +354,8 @@ static int __init __mpu_min_region_order(void)
 }
 
 static int __init mpu_setup_region(unsigned int number, phys_addr_t start,
-			unsigned int size_order, unsigned int properties)
+				   unsigned int size_order, unsigned int properties,
+				   unsigned int subregions)
 {
 	u32 size_data;
 
@@ -275,6 +372,7 @@ static int __init mpu_setup_region(unsigned int number, phys_addr_t start,
 
 	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
 	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
+	size_data |= subregions << MPU_RSR_SD;
 
 	dsb(); /* Ensure all previous data accesses occur with old mappings */
 	rgnr_write(number);
@@ -308,33 +406,33 @@ static int __init mpu_setup_region(unsigned int number, phys_addr_t start,
 */
 void __init mpu_setup(void)
 {
-	int region = 0, err = 0;
+	int i, region = 0, err = 0;
 
 	if (!mpu_present())
 		return;
 
-	/* Free-up MPU_PROBE_REGION */
-	mpu_min_region_order = __mpu_min_region_order();
-
-	/* How many regions are supported */
-	mpu_max_regions = __mpu_max_regions();
-
-	/* Now setup MPU (order is important) */
+	/* Setup MPU (order is important) */
 
 	/* Background */
 	err |= mpu_setup_region(region++, 0, 32,
-				MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA);
+				MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA,
+				0);
 
 	/* RAM */
-	err |= mpu_setup_region(region++, PHYS_OFFSET,
-				ilog2(memblock.memory.regions[0].size),
-				MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
+	for (i = 0; i < ARRAY_SIZE(mem); i++) {
+		if (!mem[i].size)
+			continue;
+
+		err |= mpu_setup_region(region++, mem[i].base, ilog2(mem[i].size),
+					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL,
+					mem[i].subreg);
+	}
 
 	/* Vectors */
 #ifndef CONFIG_CPU_V7M
-	err |= mpu_setup_region(region++, vectors_base,
-				ilog2(2 * PAGE_SIZE),
-				MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL);
+	err |= mpu_setup_region(region++, vectors_base, ilog2(2 * PAGE_SIZE),
+				MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL,
+				0);
 #endif
 	if (err) {
 		panic("MPU region initialization failure! %d", err);
-- 
2.0.0

[RFC PATCH v2 0/7] ARM: NOMMU: MPU updates

[Szemző András]

Hi,

> On 2017. May 19., at 11:46, Vladimir Murzin <vladimir.murzin@arm.com> wrote:
> 
> Hi,
> 
> This is an update of the existent MPU code which consist set of
> clean-ups and enhancements. The most significant changes are in the way
> how MPU settings sync-up for secondaries (PATCH 3/7) and more flexible
> layout for memory (PATCH 7/7). Since there is no in-tree user of MPU,
> support for M-class has been added (PATCH 6/7).
> 
> Thanks!
> 
> Changelog:
> 	    RFC -> RFC v2
> 	       - fixed MPU enable for v7m (PATCH 6/7)
> 
> Vladimir Murzin (7):
>  ARM: NOMMU: Move out MPU setup in separate module
>  ARM: NOMMU: Update MPU accessors to use cp15 helpers
>  ARM: NOMMU: Rework MPU to be mostly done in C
>  ARM: NOMMU: Disallow MPU for XIP
>  ARM: Kconfig: Kill CONFIG_VECTORS_BASE
>  ARM: V7M: Add support for MPU to M-class
>  ARM: NOMMU: Use more MPU regions to cover memory
> 
> 

 I?ve tested these patches on my custom Atmel SAME70 armv7m board, along with the 
"ARM: Fix dma_alloc_coherent() and friends for NOMMU" patches.

Both series works fine for me. These MPU patches introduce a nice feature that it simplifies the bootloader:
do not need to setup the MPU, for example for coherent DMA region, which is described in device-tree too.

So you can add my Tested-by.


Booting Linux on physical CPU 0x0
Linux version 4.12.0-rc1 (root at devel) (gcc version 4.9.2 ( 4.9.2-10) ) #1 Fri May 19 06:26:34 EDT 2017
CPU: ARMv7-M [410fc271] revision 1 (ARMv7M), cr=00000000
CPU: PIPT / VIPT nonaliasing data cache, PIPT instruction cache
OF: fdt: Machine model: SAME70-sampione board
bootconsole [earlycon0] enabled
Reserved memory: created DMA memory pool at 0x73e00000, size 2 MiB
OF: reserved mem: initialized node linux,cma, compatible id shared-dma-pool
Using ARMv7 PMSA Compliant MPU. Region independence: No, Used 4 of 16 regions
?


Thanks for the patches!

Regards,
Andras

[RFC PATCH v2 0/7] ARM: NOMMU: MPU updates

[Vladimir Murzin]

Hi,

On 22/05/17 11:05, Szemz? Andr?s wrote:
> Hi,
> 
>> On 2017. May 19., at 11:46, Vladimir Murzin <vladimir.murzin@arm.com> wrote:
>>
>> Hi,
>>
>> This is an update of the existent MPU code which consist set of
>> clean-ups and enhancements. The most significant changes are in the way
>> how MPU settings sync-up for secondaries (PATCH 3/7) and more flexible
>> layout for memory (PATCH 7/7). Since there is no in-tree user of MPU,
>> support for M-class has been added (PATCH 6/7).
>>
>> Thanks!
>>
>> Changelog:
>> 	    RFC -> RFC v2
>> 	       - fixed MPU enable for v7m (PATCH 6/7)
>>
>> Vladimir Murzin (7):
>>  ARM: NOMMU: Move out MPU setup in separate module
>>  ARM: NOMMU: Update MPU accessors to use cp15 helpers
>>  ARM: NOMMU: Rework MPU to be mostly done in C
>>  ARM: NOMMU: Disallow MPU for XIP
>>  ARM: Kconfig: Kill CONFIG_VECTORS_BASE
>>  ARM: V7M: Add support for MPU to M-class
>>  ARM: NOMMU: Use more MPU regions to cover memory
>>
>>
> 
>  I?ve tested these patches on my custom Atmel SAME70 armv7m board, along with the 
> "ARM: Fix dma_alloc_coherent() and friends for NOMMU" patches.
> 
> Both series works fine for me. These MPU patches introduce a nice feature that it simplifies the bootloader:
> do not need to setup the MPU, for example for coherent DMA region, which is described in device-tree too.
> 
> So you can add my Tested-by.
> 

Much appreciated!

> 
> Booting Linux on physical CPU 0x0
> Linux version 4.12.0-rc1 (root at devel) (gcc version 4.9.2 ( 4.9.2-10) ) #1 Fri May 19 06:26:34 EDT 2017
> CPU: ARMv7-M [410fc271] revision 1 (ARMv7M), cr=00000000
> CPU: PIPT / VIPT nonaliasing data cache, PIPT instruction cache
> OF: fdt: Machine model: SAME70-sampione board
> bootconsole [earlycon0] enabled
> Reserved memory: created DMA memory pool at 0x73e00000, size 2 MiB
> OF: reserved mem: initialized node linux,cma, compatible id shared-dma-pool
> Using ARMv7 PMSA Compliant MPU. Region independence: No, Used 4 of 16 regions
> ?
> 
> 
> Thanks for the patches!

I'm glad they work for you!

Cheers
Vladimir

> 
> Regards,
> Andras
> 
> 

[RFC PATCH v2 5/7] ARM: Kconfig: Kill CONFIG_VECTORS_BASE

[afzal mohammed]

Hi,

On Fri, May 19, 2017 at 10:46:44AM +0100, Vladimir Murzin wrote:
> The last user of CONFIG_VECTORS_BASE has gone, so kill it.
> 
> Reported-by: Afzal Mohammed <afzal.mohd.ma@gmail.com>

Ending up in this tag has left me scratching my head & amused :),
whether you keep any tag or not for me, i do not have any issues.

Regards
afzal

[RFC PATCH v2 5/7] ARM: Kconfig: Kill CONFIG_VECTORS_BASE

[Vladimir Murzin]

Hi,

On 25/05/17 12:27, afzal mohammed wrote:
> Hi,
> 
> On Fri, May 19, 2017 at 10:46:44AM +0100, Vladimir Murzin wrote:
>> The last user of CONFIG_VECTORS_BASE has gone, so kill it.
>>
>> Reported-by: Afzal Mohammed <afzal.mohd.ma@gmail.com>
> 
> Ending up in this tag has left me scratching my head & amused :),
> whether you keep any tag or not for me, i do not have any issues.

According to [1]:

"This series also does the preparation for CONFIG_VECTORS_BASE removal."

IIRC, that time only thing which stopped you from complete CONFIG_VECTORS_BASE
removal was MPU code, so I don't see a reason not to give you a credit ;)

[1] https://lkml.org/lkml/2017/1/21/251

Cheers
Vladimir

> 
> Regards
> afzal
>