Linux-libre 4.8.2-gnupck-4.8.2-gnu

10 files changed, 297 insertions, 101 deletions

diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index ef7f925dd..fa7d8d379 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -40,6 +40,51 @@
 #include <asm/mips-cm.h>
 
 /*
+ * Bits describing what cache ops an SMP callback function may perform.
+ *
+ * R4K_HIT   -	Virtual user or kernel address based cache operations. The
+ *		active_mm must be checked before using user addresses, falling
+ *		back to kmap.
+ * R4K_INDEX -	Index based cache operations.
+ */
+
+#define R4K_HIT		BIT(0)
+#define R4K_INDEX	BIT(1)
+
+/**
+ * r4k_op_needs_ipi() - Decide if a cache op needs to be done on every core.
+ * @type:	Type of cache operations (R4K_HIT or R4K_INDEX).
+ *
+ * Decides whether a cache op needs to be performed on every core in the system.
+ * This may change depending on the @type of cache operation, as well as the set
+ * of online CPUs, so preemption should be disabled by the caller to prevent CPU
+ * hotplug from changing the result.
+ *
+ * Returns:	1 if the cache operation @type should be done on every core in
+ *		the system.
+ *		0 if the cache operation @type is globalized and only needs to
+ *		be performed on a simple CPU.
+ */
+static inline bool r4k_op_needs_ipi(unsigned int type)
+{
+	/* The MIPS Coherence Manager (CM) globalizes address-based cache ops */
+	if (type == R4K_HIT && mips_cm_present())
+		return false;
+
+	/*
+	 * Hardware doesn't globalize the required cache ops, so SMP calls may
+	 * be needed, but only if there are foreign CPUs (non-siblings with
+	 * separate caches).
+	 */
+	/* cpu_foreign_map[] undeclared when !CONFIG_SMP */
+#ifdef CONFIG_SMP
+	return !cpumask_empty(&cpu_foreign_map[0]);
+#else
+	return false;
+#endif
+}
+
+/*
  * Special Variant of smp_call_function for use by cache functions:
  *
  *  o No return value
@@ -48,30 +93,17 @@
  *    primary cache.
  *  o doesn't disable interrupts on the local CPU
  */
-static inline void r4k_on_each_cpu(void (*func) (void *info), void *info)
+static inline void r4k_on_each_cpu(unsigned int type,
+				   void (*func)(void *info), void *info)
 {
 	preempt_disable();
-
-	/*
-	 * The Coherent Manager propagates address-based cache ops to other
-	 * cores but not index-based ops. However, r4k_on_each_cpu is used
-	 * in both cases so there is no easy way to tell what kind of op is
-	 * executed to the other cores. The best we can probably do is
-	 * to restrict that call when a CM is not present because both
-	 * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops.
-	 */
-	if (!mips_cm_present())
-		smp_call_function_many(&cpu_foreign_map, func, info, 1);
+	if (r4k_op_needs_ipi(type))
+		smp_call_function_many(&cpu_foreign_map[smp_processor_id()],
+				       func, info, 1);
 	func(info);
 	preempt_enable();
 }
 
-#if defined(CONFIG_MIPS_CMP) || defined(CONFIG_MIPS_CPS)
-#define cpu_has_safe_index_cacheops 0
-#else
-#define cpu_has_safe_index_cacheops 1
-#endif
-
 /*
  * Must die.
  */
@@ -462,22 +494,44 @@ static inline void local_r4k___flush_cache_all(void * args)
 
 static void r4k___flush_cache_all(void)
 {
-	r4k_on_each_cpu(local_r4k___flush_cache_all, NULL);
+	r4k_on_each_cpu(R4K_INDEX, local_r4k___flush_cache_all, NULL);
 }
 
-static inline int has_valid_asid(const struct mm_struct *mm)
+/**
+ * has_valid_asid() - Determine if an mm already has an ASID.
+ * @mm:		Memory map.
+ * @type:	R4K_HIT or R4K_INDEX, type of cache op.
+ *
+ * Determines whether @mm already has an ASID on any of the CPUs which cache ops
+ * of type @type within an r4k_on_each_cpu() call will affect. If
+ * r4k_on_each_cpu() does an SMP call to a single VPE in each core, then the
+ * scope of the operation is confined to sibling CPUs, otherwise all online CPUs
+ * will need to be checked.
+ *
+ * Must be called in non-preemptive context.
+ *
+ * Returns:	1 if the CPUs affected by @type cache ops have an ASID for @mm.
+ *		0 otherwise.
+ */
+static inline int has_valid_asid(const struct mm_struct *mm, unsigned int type)
 {
-#ifdef CONFIG_MIPS_MT_SMP
-	int i;
+	unsigned int i;
+	const cpumask_t *mask = cpu_present_mask;
 
-	for_each_online_cpu(i)
+	/* cpu_sibling_map[] undeclared when !CONFIG_SMP */
+#ifdef CONFIG_SMP
+	/*
+	 * If r4k_on_each_cpu does SMP calls, it does them to a single VPE in
+	 * each foreign core, so we only need to worry about siblings.
+	 * Otherwise we need to worry about all present CPUs.
+	 */
+	if (r4k_op_needs_ipi(type))
+		mask = &cpu_sibling_map[smp_processor_id()];
+#endif
+	for_each_cpu(i, mask)
 		if (cpu_context(i, mm))
 			return 1;
-
 	return 0;
-#else
-	return cpu_context(smp_processor_id(), mm);
-#endif
 }
 
 static void r4k__flush_cache_vmap(void)
@@ -490,12 +544,16 @@ static void r4k__flush_cache_vunmap(void)
 	r4k_blast_dcache();
 }
 
+/*
+ * Note: flush_tlb_range() assumes flush_cache_range() sufficiently flushes
+ * whole caches when vma is executable.
+ */
 static inline void local_r4k_flush_cache_range(void * args)
 {
 	struct vm_area_struct *vma = args;
 	int exec = vma->vm_flags & VM_EXEC;
 
-	if (!(has_valid_asid(vma->vm_mm)))
+	if (!has_valid_asid(vma->vm_mm, R4K_INDEX))
 		return;
 
 	/*
@@ -516,14 +574,14 @@ static void r4k_flush_cache_range(struct vm_area_struct *vma,
 	int exec = vma->vm_flags & VM_EXEC;
 
 	if (cpu_has_dc_aliases || exec)
-		r4k_on_each_cpu(local_r4k_flush_cache_range, vma);
+		r4k_on_each_cpu(R4K_INDEX, local_r4k_flush_cache_range, vma);
 }
 
 static inline void local_r4k_flush_cache_mm(void * args)
 {
 	struct mm_struct *mm = args;
 
-	if (!has_valid_asid(mm))
+	if (!has_valid_asid(mm, R4K_INDEX))
 		return;
 
 	/*
@@ -548,7 +606,7 @@ static void r4k_flush_cache_mm(struct mm_struct *mm)
 	if (!cpu_has_dc_aliases)
 		return;
 
-	r4k_on_each_cpu(local_r4k_flush_cache_mm, mm);
+	r4k_on_each_cpu(R4K_INDEX, local_r4k_flush_cache_mm, mm);
 }
 
 struct flush_cache_page_args {
@@ -573,10 +631,10 @@ static inline void local_r4k_flush_cache_page(void *args)
 	void *vaddr;
 
 	/*
-	 * If ownes no valid ASID yet, cannot possibly have gotten
+	 * If owns no valid ASID yet, cannot possibly have gotten
 	 * this page into the cache.
 	 */
-	if (!has_valid_asid(mm))
+	if (!has_valid_asid(mm, R4K_HIT))
 		return;
 
 	addr &= PAGE_MASK;
@@ -643,7 +701,7 @@ static void r4k_flush_cache_page(struct vm_area_struct *vma,
 	args.addr = addr;
 	args.pfn = pfn;
 
-	r4k_on_each_cpu(local_r4k_flush_cache_page, &args);
+	r4k_on_each_cpu(R4K_HIT, local_r4k_flush_cache_page, &args);
 }
 
 static inline void local_r4k_flush_data_cache_page(void * addr)
@@ -656,18 +714,23 @@ static void r4k_flush_data_cache_page(unsigned long addr)
 	if (in_atomic())
 		local_r4k_flush_data_cache_page((void *)addr);
 	else
-		r4k_on_each_cpu(local_r4k_flush_data_cache_page, (void *) addr);
+		r4k_on_each_cpu(R4K_HIT, local_r4k_flush_data_cache_page,
+				(void *) addr);
 }
 
 struct flush_icache_range_args {
 	unsigned long start;
 	unsigned long end;
+	unsigned int type;
 };
 
-static inline void local_r4k_flush_icache_range(unsigned long start, unsigned long end)
+static inline void __local_r4k_flush_icache_range(unsigned long start,
+						  unsigned long end,
+						  unsigned int type)
 {
 	if (!cpu_has_ic_fills_f_dc) {
-		if (end - start >= dcache_size) {
+		if (type == R4K_INDEX ||
+		    (type & R4K_INDEX && end - start >= dcache_size)) {
 			r4k_blast_dcache();
 		} else {
 			R4600_HIT_CACHEOP_WAR_IMPL;
@@ -675,7 +738,8 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo
 		}
 	}
 
-	if (end - start > icache_size)
+	if (type == R4K_INDEX ||
+	    (type & R4K_INDEX && end - start > icache_size))
 		r4k_blast_icache();
 	else {
 		switch (boot_cpu_type()) {
@@ -701,23 +765,52 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo
 #endif
 }
 
+static inline void local_r4k_flush_icache_range(unsigned long start,
+						unsigned long end)
+{
+	__local_r4k_flush_icache_range(start, end, R4K_HIT | R4K_INDEX);
+}
+
 static inline void local_r4k_flush_icache_range_ipi(void *args)
 {
 	struct flush_icache_range_args *fir_args = args;
 	unsigned long start = fir_args->start;
 	unsigned long end = fir_args->end;
+	unsigned int type = fir_args->type;
 
-	local_r4k_flush_icache_range(start, end);
+	__local_r4k_flush_icache_range(start, end, type);
 }
 
 static void r4k_flush_icache_range(unsigned long start, unsigned long end)
 {
 	struct flush_icache_range_args args;
+	unsigned long size, cache_size;
 
 	args.start = start;
 	args.end = end;
+	args.type = R4K_HIT | R4K_INDEX;
 
-	r4k_on_each_cpu(local_r4k_flush_icache_range_ipi, &args);
+	/*
+	 * Indexed cache ops require an SMP call.
+	 * Consider if that can or should be avoided.
+	 */
+	preempt_disable();
+	if (r4k_op_needs_ipi(R4K_INDEX) && !r4k_op_needs_ipi(R4K_HIT)) {
+		/*
+		 * If address-based cache ops don't require an SMP call, then
+		 * use them exclusively for small flushes.
+		 */
+		size = end - start;
+		cache_size = icache_size;
+		if (!cpu_has_ic_fills_f_dc) {
+			size *= 2;
+			cache_size += dcache_size;
+		}
+		if (size <= cache_size)
+			args.type &= ~R4K_INDEX;
+	}
+	r4k_on_each_cpu(args.type, local_r4k_flush_icache_range_ipi, &args);
+	preempt_enable();
 	instruction_hazard();
 }
 
@@ -744,7 +837,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 	 * subset property so we have to flush the primary caches
 	 * explicitly
 	 */
-	if (cpu_has_safe_index_cacheops && size >= dcache_size) {
+	if (size >= dcache_size) {
 		r4k_blast_dcache();
 	} else {
 		R4600_HIT_CACHEOP_WAR_IMPL;
@@ -781,7 +874,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 		return;
 	}
 
-	if (cpu_has_safe_index_cacheops && size >= dcache_size) {
+	if (size >= dcache_size) {
 		r4k_blast_dcache();
 	} else {
 		R4600_HIT_CACHEOP_WAR_IMPL;
@@ -794,25 +887,76 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 }
 #endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
 
+struct flush_cache_sigtramp_args {
+	struct mm_struct *mm;
+	struct page *page;
+	unsigned long addr;
+};
+
 /*
  * While we're protected against bad userland addresses we don't care
  * very much about what happens in that case.  Usually a segmentation
  * fault will dump the process later on anyway ...
  */
-static void local_r4k_flush_cache_sigtramp(void * arg)
+static void local_r4k_flush_cache_sigtramp(void *args)
 {
+	struct flush_cache_sigtramp_args *fcs_args = args;
+	unsigned long addr = fcs_args->addr;
+	struct page *page = fcs_args->page;
+	struct mm_struct *mm = fcs_args->mm;
+	int map_coherent = 0;
+	void *vaddr;
+
 	unsigned long ic_lsize = cpu_icache_line_size();
 	unsigned long dc_lsize = cpu_dcache_line_size();
 	unsigned long sc_lsize = cpu_scache_line_size();
-	unsigned long addr = (unsigned long) arg;
+
+	/*
+	 * If owns no valid ASID yet, cannot possibly have gotten
+	 * this page into the cache.
+	 */
+	if (!has_valid_asid(mm, R4K_HIT))
+		return;
+
+	if (mm == current->active_mm) {
+		vaddr = NULL;
+	} else {
+		/*
+		 * Use kmap_coherent or kmap_atomic to do flushes for
+		 * another ASID than the current one.
+		 */
+		map_coherent = (cpu_has_dc_aliases &&
+				page_mapcount(page) &&
+				!Page_dcache_dirty(page));
+		if (map_coherent)
+			vaddr = kmap_coherent(page, addr);
+		else
+			vaddr = kmap_atomic(page);
+		addr = (unsigned long)vaddr + (addr & ~PAGE_MASK);
+	}
 
 	R4600_HIT_CACHEOP_WAR_IMPL;
-	if (dc_lsize)
-		protected_writeback_dcache_line(addr & ~(dc_lsize - 1));
-	if (!cpu_icache_snoops_remote_store && scache_size)
-		protected_writeback_scache_line(addr & ~(sc_lsize - 1));
+	if (!cpu_has_ic_fills_f_dc) {
+		if (dc_lsize)
+			vaddr ? flush_dcache_line(addr & ~(dc_lsize - 1))
+			      : protected_writeback_dcache_line(
+							addr & ~(dc_lsize - 1));
+		if (!cpu_icache_snoops_remote_store && scache_size)
+			vaddr ? flush_scache_line(addr & ~(sc_lsize - 1))
+			      : protected_writeback_scache_line(
+							addr & ~(sc_lsize - 1));
+	}
 	if (ic_lsize)
-		protected_flush_icache_line(addr & ~(ic_lsize - 1));
+		vaddr ? flush_icache_line(addr & ~(ic_lsize - 1))
+		      : protected_flush_icache_line(addr & ~(ic_lsize - 1));
+
+	if (vaddr) {
+		if (map_coherent)
+			kunmap_coherent();
+		else
+			kunmap_atomic(vaddr);
+	}
+
 	if (MIPS4K_ICACHE_REFILL_WAR) {
 		__asm__ __volatile__ (
 			".set push\n\t"
@@ -837,7 +981,23 @@ static void local_r4k_flush_cache_sigtramp(void * arg)
 
 static void r4k_flush_cache_sigtramp(unsigned long addr)
 {
-	r4k_on_each_cpu(local_r4k_flush_cache_sigtramp, (void *) addr);
+	struct flush_cache_sigtramp_args args;
+	int npages;
+
+	down_read(&current->mm->mmap_sem);
+
+	npages = get_user_pages_fast(addr, 1, 0, &args.page);
+	if (npages < 1)
+		goto out;
+
+	args.mm = current->mm;
+	args.addr = addr;
+
+	r4k_on_each_cpu(R4K_HIT, local_r4k_flush_cache_sigtramp, &args);
+
+	put_page(args.page);
+out:
+	up_read(&current->mm->mmap_sem);
 }
 
 static void r4k_flush_icache_all(void)
@@ -851,6 +1011,15 @@ struct flush_kernel_vmap_range_args {
 	int		size;
 };
 
+static inline void local_r4k_flush_kernel_vmap_range_index(void *args)
+{
+	/*
+	 * Aliases only affect the primary caches so don't bother with
+	 * S-caches or T-caches.
+	 */
+	r4k_blast_dcache();
+}
+
 static inline void local_r4k_flush_kernel_vmap_range(void *args)
 {
 	struct flush_kernel_vmap_range_args *vmra = args;
@@ -861,12 +1030,8 @@ static inline void local_r4k_flush_kernel_vmap_range(void *args)
 	 * Aliases only affect the primary caches so don't bother with
 	 * S-caches or T-caches.
 	 */
-	if (cpu_has_safe_index_cacheops && size >= dcache_size)
-		r4k_blast_dcache();
-	else {
-		R4600_HIT_CACHEOP_WAR_IMPL;
-		blast_dcache_range(vaddr, vaddr + size);
-	}
+	R4600_HIT_CACHEOP_WAR_IMPL;
+	blast_dcache_range(vaddr, vaddr + size);
 }
 
 static void r4k_flush_kernel_vmap_range(unsigned long vaddr, int size)
@@ -876,7 +1041,12 @@ static void r4k_flush_kernel_vmap_range(unsigned long vaddr, int size)
 	args.vaddr = (unsigned long) vaddr;
 	args.size = size;
 
-	r4k_on_each_cpu(local_r4k_flush_kernel_vmap_range, &args);
+	if (size >= dcache_size)
+		r4k_on_each_cpu(R4K_INDEX,
+				local_r4k_flush_kernel_vmap_range_index, NULL);
+	else
+		r4k_on_each_cpu(R4K_HIT, local_r4k_flush_kernel_vmap_range,
+				&args);
 }
 
 static inline void rm7k_erratum31(void)
@@ -1206,7 +1376,7 @@ static void probe_pcache(void)
 			      c->icache.linesz;
 		c->icache.waybit = __ffs(icache_size/c->icache.ways);
 
-		if (config & 0x8)		/* VI bit */
+		if (config & MIPS_CONF_VI)
 			c->icache.flags |= MIPS_CACHE_VTAG;
 
 		/*
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index cb557d28c..b2eadd6fa 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -131,7 +131,7 @@ static void *mips_dma_alloc_noncoherent(struct device *dev, size_t size,
 }
 
 static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t * dma_handle, gfp_t gfp, struct dma_attrs *attrs)
+	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
 	struct page *page = NULL;
@@ -141,7 +141,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
 	 * XXX: seems like the coherent and non-coherent implementations could
 	 * be consolidated.
 	 */
-	if (dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs))
+	if (attrs & DMA_ATTR_NON_CONSISTENT)
 		return mips_dma_alloc_noncoherent(dev, size, dma_handle, gfp);
 
 	gfp = massage_gfp_flags(dev, gfp);
@@ -176,13 +176,13 @@ static void mips_dma_free_noncoherent(struct device *dev, size_t size,
 }
 
 static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-	dma_addr_t dma_handle, struct dma_attrs *attrs)
+	dma_addr_t dma_handle, unsigned long attrs)
 {
 	unsigned long addr = (unsigned long) vaddr;
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	struct page *page = NULL;
 
-	if (dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) {
+	if (attrs & DMA_ATTR_NON_CONSISTENT) {
 		mips_dma_free_noncoherent(dev, size, vaddr, dma_handle);
 		return;
 	}
@@ -200,7 +200,7 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 
 static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	void *cpu_addr, dma_addr_t dma_addr, size_t size,
-	struct dma_attrs *attrs)
+	unsigned long attrs)
 {
 	unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
@@ -214,7 +214,7 @@ static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 
 	pfn = page_to_pfn(virt_to_page((void *)addr));
 
-	if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+	if (attrs & DMA_ATTR_WRITE_COMBINE)
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
 	else
 		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -291,7 +291,7 @@ static inline void __dma_sync(struct page *page,
 }
 
 static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction, struct dma_attrs *attrs)
+	size_t size, enum dma_data_direction direction, unsigned long attrs)
 {
 	if (cpu_needs_post_dma_flush(dev))
 		__dma_sync(dma_addr_to_page(dev, dma_addr),
@@ -301,7 +301,7 @@ static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
 }
 
 static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-	int nents, enum dma_data_direction direction, struct dma_attrs *attrs)
+	int nents, enum dma_data_direction direction, unsigned long attrs)
 {
 	int i;
 	struct scatterlist *sg;
@@ -322,7 +322,7 @@ static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
 	unsigned long offset, size_t size, enum dma_data_direction direction,
-	struct dma_attrs *attrs)
+	unsigned long attrs)
 {
 	if (!plat_device_is_coherent(dev))
 		__dma_sync(page, offset, size, direction);
@@ -332,7 +332,7 @@ static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
 
 static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	int nhwentries, enum dma_data_direction direction,
-	struct dma_attrs *attrs)
+	unsigned long attrs)
 {
 	int i;
 	struct scatterlist *sg;
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 4b88fa031..9560ad731 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -153,7 +153,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 9b58eb5fd..72f7478ee 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -261,7 +261,6 @@ unsigned __weak platform_maar_init(unsigned num_pairs)
 {
 	struct maar_config cfg[BOOT_MEM_MAP_MAX];
 	unsigned i, num_configured, num_cfg = 0;
-	phys_addr_t skip;
 
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		switch (boot_mem_map.map[i].type) {
@@ -272,14 +271,14 @@ unsigned __weak platform_maar_init(unsigned num_pairs)
 			continue;
 		}
 
-		skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
-
+		/* Round lower up */
 		cfg[num_cfg].lower = boot_mem_map.map[i].addr;
-		cfg[num_cfg].lower += skip;
+		cfg[num_cfg].lower = (cfg[num_cfg].lower + 0xffff) & ~0xffff;
 
-		cfg[num_cfg].upper = cfg[num_cfg].lower;
-		cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
-		cfg[num_cfg].upper -= skip;
+		/* Round upper down */
+		cfg[num_cfg].upper = boot_mem_map.map[i].addr +
+					boot_mem_map.map[i].size;
+		cfg[num_cfg].upper = (cfg[num_cfg].upper & ~0xffff) - 1;
 
 		cfg[num_cfg].attrs = MIPS_MAAR_S;
 		num_cfg++;
@@ -441,6 +440,9 @@ static inline void mem_init_free_highmem(void)
 #ifdef CONFIG_HIGHMEM
 	unsigned long tmp;
 
+	if (cpu_has_dc_aliases)
+		return;
+
 	for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) {
 		struct page *page = pfn_to_page(tmp);
 
@@ -504,7 +506,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 
 void (*free_init_pages_eva)(void *begin, void *end) = NULL;
 
-void __init_refok free_initmem(void)
+void __ref free_initmem(void)
 {
 	prom_free_prom_memory();
 	/*
diff --git a/arch/mips/mm/sc-debugfs.c b/arch/mips/mm/sc-debugfs.c
index 5eefe3281..01f1154cd 100644
--- a/arch/mips/mm/sc-debugfs.c
+++ b/arch/mips/mm/sc-debugfs.c
@@ -73,8 +73,8 @@ static int __init sc_debugfs_init(void)
 
 	file = debugfs_create_file("prefetch", S_IRUGO | S_IWUSR, dir,
 				   NULL, &sc_prefetch_fops);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	if (!file)
+		return -ENOMEM;
 
 	return 0;
 }
diff --git a/arch/mips/mm/sc-rm7k.c b/arch/mips/mm/sc-rm7k.c
index 9ac1efcfb..78f900c59 100644
--- a/arch/mips/mm/sc-rm7k.c
+++ b/arch/mips/mm/sc-rm7k.c
@@ -161,7 +161,7 @@ static void rm7k_tc_disable(void)
 	local_irq_save(flags);
 	blast_rm7k_tcache();
 	clear_c0_config(RM7K_CONF_TE);
-	local_irq_save(flags);
+	local_irq_restore(flags);
 }
 
 static void rm7k_sc_disable(void)
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 4004b659c..55ce39606 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -888,7 +888,7 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 		}
 	}
 	if (!did_vmalloc_branch) {
-		if (uasm_in_compat_space_p(swpd) && !uasm_rel_lo(swpd)) {
+		if (single_insn_swpd) {
 			uasm_il_b(p, r, label_vmalloc_done);
 			uasm_i_lui(p, ptr, uasm_rel_hi(swpd));
 		} else {
@@ -1025,7 +1025,7 @@ static void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep)
 	pte_off_odd += offsetof(pte_t, pte_high);
 #endif
 
-	if (config_enabled(CONFIG_XPA)) {
+	if (IS_ENABLED(CONFIG_XPA)) {
 		uasm_i_lw(p, tmp, pte_off_even, ptep); /* even pte */
 		UASM_i_ROTR(p, tmp, tmp, ilog2(_PAGE_GLOBAL));
 		UASM_i_MTC0(p, tmp, C0_ENTRYLO0);
@@ -1643,7 +1643,7 @@ iPTE_SW(u32 **p, struct uasm_reloc **r, unsigned int pte, unsigned int ptr,
 	unsigned int hwmode = mode & (_PAGE_VALID | _PAGE_DIRTY);
 	unsigned int swmode = mode & ~hwmode;
 
-	if (config_enabled(CONFIG_XPA) && !cpu_has_64bits) {
+	if (IS_ENABLED(CONFIG_XPA) && !cpu_has_64bits) {
 		uasm_i_lui(p, scratch, swmode >> 16);
 		uasm_i_or(p, pte, pte, scratch);
 		BUG_ON(swmode & 0xffff);
@@ -2432,7 +2432,7 @@ static void config_htw_params(void)
 		pwsize |= ilog2(PTRS_PER_PMD) << MIPS_PWSIZE_MDW_SHIFT;
 
 	/* Set pointer size to size of directory pointers */
-	if (config_enabled(CONFIG_64BIT))
+	if (IS_ENABLED(CONFIG_64BIT))
 		pwsize |= MIPS_PWSIZE_PS_MASK;
 	/* PTEs may be multiple pointers long (e.g. with XPA) */
 	pwsize |= ((PTE_T_LOG2 - PGD_T_LOG2) << MIPS_PWSIZE_PTEW_SHIFT)
@@ -2448,7 +2448,7 @@ static void config_htw_params(void)
 	 * the pwctl fields.
 	 */
 	config = 1 << MIPS_PWCTL_PWEN_SHIFT;
-	if (config_enabled(CONFIG_64BIT))
+	if (IS_ENABLED(CONFIG_64BIT))
 		config |= MIPS_PWCTL_XU_MASK;
 	write_c0_pwctl(config);
 	pr_info("Hardware Page Table Walker enabled\n");
@@ -2522,7 +2522,7 @@ void build_tlb_refill_handler(void)
 	 */
 	static int run_once = 0;
 
-	if (config_enabled(CONFIG_XPA) && !cpu_has_rixi)
+	if (IS_ENABLED(CONFIG_XPA) && !cpu_has_rixi)
 		panic("Kernels supporting XPA currently require CPUs with RIXI");
 
 	output_pgtable_bits_defines();
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index d78178dae..277cf52d8 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -53,8 +53,13 @@ static struct insn insn_table_MM[] = {
 	{ insn_bltzl, 0, 0 },
 	{ insn_bne, M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM },
 	{ insn_cache, M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM },
+	{ insn_cfc1, M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS },
+	{ insn_cfcmsa, M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE },
+	{ insn_ctc1, M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS },
+	{ insn_ctcmsa, M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE },
 	{ insn_daddu, 0, 0 },
 	{ insn_daddiu, 0, 0 },
+	{ insn_di, M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS },
 	{ insn_divu, M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS },
 	{ insn_dmfc0, 0, 0 },
 	{ insn_dmtc0, 0, 0 },
@@ -84,6 +89,8 @@ static struct insn insn_table_MM[] = {
 	{ insn_mfhi, M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS },
 	{ insn_mflo, M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS },
 	{ insn_mtc0, M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD },
+	{ insn_mthi, M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS },
+	{ insn_mtlo, M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS },
 	{ insn_mul, M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD },
 	{ insn_or, M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD },
 	{ insn_ori, M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM },
@@ -166,13 +173,15 @@ static void build_insn(u32 **buf, enum opcode opc, ...)
 	op = ip->match;
 	va_start(ap, opc);
 	if (ip->fields & RS) {
-		if (opc == insn_mfc0 || opc == insn_mtc0)
+		if (opc == insn_mfc0 || opc == insn_mtc0 ||
+		    opc == insn_cfc1 || opc == insn_ctc1)
 			op |= build_rt(va_arg(ap, u32));
 		else
 			op |= build_rs(va_arg(ap, u32));
 	}
 	if (ip->fields & RT) {
-		if (opc == insn_mfc0 || opc == insn_mtc0)
+		if (opc == insn_mfc0 || opc == insn_mtc0 ||
+		    opc == insn_cfc1 || opc == insn_ctc1)
 			op |= build_rs(va_arg(ap, u32));
 		else
 			op |= build_rt(va_arg(ap, u32));
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 45e3b8799..763d3f1ed 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -67,9 +67,14 @@ static struct insn insn_table[] = {
 #else
 	{ insn_cache,  M6(spec3_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
 #endif
+	{ insn_cfc1, M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD },
+	{ insn_cfcmsa, M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE },
+	{ insn_ctc1, M(cop1_op, ctc_op, 0, 0, 0, 0), RT | RD },
+	{ insn_ctcmsa, M(msa_op, 0, msa_ctc_op, 0, 0, msa_elm_op), RD | RE },
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
 	{ insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE },
+	{ insn_di, M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT },
 	{ insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE },
 	{ insn_divu, M(spec_op, 0, 0, 0, 0, divu_op), RS | RT },
 	{ insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET},
@@ -114,7 +119,13 @@ static struct insn insn_table[] = {
 	{ insn_mflo,  M(spec_op, 0, 0, 0, 0, mflo_op), RD },
 	{ insn_mtc0,  M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
 	{ insn_mthc0,  M(cop0_op, mthc0_op, 0, 0, 0, 0),  RT | RD | SET},
+	{ insn_mthi,  M(spec_op, 0, 0, 0, 0, mthi_op), RS },
+	{ insn_mtlo,  M(spec_op, 0, 0, 0, 0, mtlo_op), RS },
+#ifndef CONFIG_CPU_MIPSR6
 	{ insn_mul, M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD},
+#else
+	{ insn_mul, M(spec_op, 0, 0, 0, mult_mul_op, mult_op), RS | RT | RD},
+#endif
 	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),	RS | RT | UIMM },
 	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
 #ifndef CONFIG_CPU_MIPSR6
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index ad718debc..a82970442 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -49,18 +49,19 @@ enum opcode {
 	insn_invalid,
 	insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1,
 	insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl,
-	insn_bne, insn_cache, insn_daddiu, insn_daddu, insn_dins, insn_dinsm,
-	insn_divu, insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll,
+	insn_bne, insn_cache, insn_cfc1, insn_cfcmsa, insn_ctc1, insn_ctcmsa,
+	insn_daddiu, insn_daddu, insn_di, insn_dins, insn_dinsm, insn_divu,
+	insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll,
 	insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, insn_dsubu, insn_eret,
 	insn_ext, insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb,
 	insn_ld, insn_ldx, insn_lh, insn_ll, insn_lld, insn_lui, insn_lw,
 	insn_lwx, insn_mfc0, insn_mfhc0, insn_mfhi, insn_mflo, insn_mtc0,
-	insn_mthc0, insn_mul, insn_or, insn_ori, insn_pref, insn_rfe,
-	insn_rotr, insn_sc, insn_scd, insn_sd, insn_sll, insn_sllv, insn_slt,
-	insn_sltiu, insn_sltu, insn_sra, insn_srl, insn_srlv, insn_subu,
-	insn_sw, insn_sync, insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi,
-	insn_tlbwr, insn_wait, insn_wsbh, insn_xor, insn_xori, insn_yield,
-	insn_lddir, insn_ldpte,
+	insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_or, insn_ori,
+	insn_pref, insn_rfe, insn_rotr, insn_sc, insn_scd, insn_sd, insn_sll,
+	insn_sllv, insn_slt, insn_sltiu, insn_sltu, insn_sra, insn_srl,
+	insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, insn_tlbp,
+	insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, insn_xor,
+	insn_xori, insn_yield, insn_lddir, insn_ldpte,
 };
 
 struct insn {
@@ -268,10 +269,15 @@ I_u1s2(_bltz)
 I_u1s2(_bltzl)
 I_u1u2s3(_bne)
 I_u2s3u1(_cache)
+I_u1u2(_cfc1)
+I_u2u1(_cfcmsa)
+I_u1u2(_ctc1)
+I_u2u1(_ctcmsa)
 I_u1u2u3(_dmfc0)
 I_u1u2u3(_dmtc0)
 I_u2u1s3(_daddiu)
 I_u3u1u2(_daddu)
+I_u1(_di);
 I_u1u2(_divu)
 I_u2u1u3(_dsll)
 I_u2u1u3(_dsll32)
@@ -301,6 +307,8 @@ I_u1(_mfhi)
 I_u1(_mflo)
 I_u1u2u3(_mtc0)
 I_u1u2u3(_mthc0)
+I_u1(_mthi)
+I_u1(_mtlo)
 I_u3u1u2(_mul)
 I_u2u1u3(_ori)
 I_u3u1u2(_or)
@@ -370,11 +378,7 @@ UASM_EXPORT_SYMBOL(ISAFUNC(uasm_build_label));
 int ISAFUNC(uasm_in_compat_space_p)(long addr)
 {
 	/* Is this address in 32bit compat space? */
-#ifdef CONFIG_64BIT
-	return (((addr) & 0xffffffff00000000L) == 0xffffffff00000000L);
-#else
-	return 1;
-#endif
+	return addr == (int)addr;
 }
 UASM_EXPORT_SYMBOL(ISAFUNC(uasm_in_compat_space_p));