Merge branch 'ti-sysc-fixes' into fixes

6 files changed, 95 insertions, 132 deletions

diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
index c1a6c0f31150..4d4754e6bf89 100644
--- a/arch/csky/include/asm/Kbuild
+++ b/arch/csky/include/asm/Kbuild
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 generic-y += asm-offsets.h
 generic-y += bugs.h
 generic-y += compat.h
diff --git a/arch/csky/include/asm/asid.h b/arch/csky/include/asm/asid.h
new file mode 100644
index 000000000000..ac08b0ffbe1f
--- /dev/null
+++ b/arch/csky/include/asm/asid.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ASM_ASID_H
+#define __ASM_ASM_ASID_H
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+
+struct asid_info
+{
+	atomic64_t	generation;
+	unsigned long	*map;
+	atomic64_t __percpu	*active;
+	u64 __percpu		*reserved;
+	u32			bits;
+	/* Lock protecting the structure */
+	raw_spinlock_t		lock;
+	/* Which CPU requires context flush on next call */
+	cpumask_t		flush_pending;
+	/* Number of ASID allocated by context (shift value) */
+	unsigned int		ctxt_shift;
+	/* Callback to locally flush the context. */
+	void			(*flush_cpu_ctxt_cb)(void);
+};
+
+#define NUM_ASIDS(info)			(1UL << ((info)->bits))
+#define NUM_CTXT_ASIDS(info)		(NUM_ASIDS(info) >> (info)->ctxt_shift)
+
+#define active_asid(info, cpu)	*per_cpu_ptr((info)->active, cpu)
+
+void asid_new_context(struct asid_info *info, atomic64_t *pasid,
+		      unsigned int cpu, struct mm_struct *mm);
+
+/*
+ * Check the ASID is still valid for the context. If not generate a new ASID.
+ *
+ * @pasid: Pointer to the current ASID batch
+ * @cpu: current CPU ID. Must have been acquired throught get_cpu()
+ */
+static inline void asid_check_context(struct asid_info *info,
+				      atomic64_t *pasid, unsigned int cpu,
+				      struct mm_struct *mm)
+{
+	u64 asid, old_active_asid;
+
+	asid = atomic64_read(pasid);
+
+	/*
+	 * The memory ordering here is subtle.
+	 * If our active_asid is non-zero and the ASID matches the current
+	 * generation, then we update the active_asid entry with a relaxed
+	 * cmpxchg. Racing with a concurrent rollover means that either:
+	 *
+	 * - We get a zero back from the cmpxchg and end up waiting on the
+	 *   lock. Taking the lock synchronises with the rollover and so
+	 *   we are forced to see the updated generation.
+	 *
+	 * - We get a valid ASID back from the cmpxchg, which means the
+	 *   relaxed xchg in flush_context will treat us as reserved
+	 *   because atomic RmWs are totally ordered for a given location.
+	 */
+	old_active_asid = atomic64_read(&active_asid(info, cpu));
+	if (old_active_asid &&
+	    !((asid ^ atomic64_read(&info->generation)) >> info->bits) &&
+	    atomic64_cmpxchg_relaxed(&active_asid(info, cpu),
+				     old_active_asid, asid))
+		return;
+
+	asid_new_context(info, pasid, cpu, mm);
+}
+
+int asid_allocator_init(struct asid_info *info,
+			u32 bits, unsigned int asid_per_ctxt,
+			void (*flush_cpu_ctxt_cb)(void));
+
+#endif
diff --git a/arch/csky/include/asm/mmu.h b/arch/csky/include/asm/mmu.h
index cb344675ccc4..b382a14ea4ec 100644
--- a/arch/csky/include/asm/mmu.h
+++ b/arch/csky/include/asm/mmu.h
@@ -5,7 +5,7 @@
 #define __ASM_CSKY_MMU_H
 
 typedef struct {
-	unsigned long asid[NR_CPUS];
+	atomic64_t	asid;
 	void *vdso;
 } mm_context_t;
 
diff --git a/arch/csky/include/asm/mmu_context.h b/arch/csky/include/asm/mmu_context.h
index 734db3a122e1..0285b0ad18b6 100644
--- a/arch/csky/include/asm/mmu_context.h
+++ b/arch/csky/include/asm/mmu_context.h
@@ -16,122 +16,32 @@
 
 #define TLBMISS_HANDLER_SETUP_PGD(pgd) \
 	setup_pgd(__pa(pgd), false)
+
 #define TLBMISS_HANDLER_SETUP_PGD_KERNEL(pgd) \
 	setup_pgd(__pa(pgd), true)
 
-#define cpu_context(cpu, mm)	((mm)->context.asid[cpu])
-#define cpu_asid(cpu, mm)	(cpu_context((cpu), (mm)) & ASID_MASK)
-#define asid_cache(cpu)		(cpu_data[cpu].asid_cache)
+#define ASID_MASK		((1 << CONFIG_CPU_ASID_BITS) - 1)
+#define cpu_asid(mm)		(atomic64_read(&mm->context.asid) & ASID_MASK)
 
-#define ASID_FIRST_VERSION	(1 << CONFIG_CPU_ASID_BITS)
-#define ASID_INC		0x1
-#define ASID_MASK		(ASID_FIRST_VERSION - 1)
-#define ASID_VERSION_MASK	~ASID_MASK
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.asid, 0); 0; })
+#define activate_mm(prev,next)		switch_mm(prev, next, current)
 
 #define destroy_context(mm)		do {} while (0)
 #define enter_lazy_tlb(mm, tsk)		do {} while (0)
 #define deactivate_mm(tsk, mm)		do {} while (0)
 
-/*
- *  All unused by hardware upper bits will be considered
- *  as a software asid extension.
- */
-static inline void
-get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
-{
-	unsigned long asid = asid_cache(cpu);
-
-	asid += ASID_INC;
-	if (!(asid & ASID_MASK)) {
-		flush_tlb_all();	/* start new asid cycle */
-		if (!asid)		/* fix version if needed */
-			asid = ASID_FIRST_VERSION;
-	}
-	cpu_context(cpu, mm) = asid_cache(cpu) = asid;
-}
-
-/*
- * Initialize the context related info for a new mm_struct
- * instance.
- */
-static inline int
-init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
-	int i;
-
-	for_each_online_cpu(i)
-		cpu_context(i, mm) = 0;
-	return 0;
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			struct task_struct *tsk)
-{
-	unsigned int cpu = smp_processor_id();
-	unsigned long flags;
-
-	local_irq_save(flags);
-	/* Check if our ASID is of an older version and thus invalid */
-	if ((cpu_context(cpu, next) ^ asid_cache(cpu)) & ASID_VERSION_MASK)
-		get_new_mmu_context(next, cpu);
-	write_mmu_entryhi(cpu_asid(cpu, next));
-	TLBMISS_HANDLER_SETUP_PGD(next->pgd);
-
-	/*
-	 * Mark current->active_mm as not "active" anymore.
-	 * We don't want to mislead possible IPI tlb flush routines.
-	 */
-	cpumask_clear_cpu(cpu, mm_cpumask(prev));
-	cpumask_set_cpu(cpu, mm_cpumask(next));
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-	local_irq_restore(flags);
-}
-
-/*
- * After we have set current->mm to a new value, this activates
- * the context for the new mm so we see the new mappings.
- */
 static inline void
-activate_mm(struct mm_struct *prev, struct mm_struct *next)
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	  struct task_struct *tsk)
 {
-	unsigned long flags;
-	int cpu = smp_processor_id();
-
-	local_irq_save(flags);
+	unsigned int cpu = smp_processor_id();
 
-	/* Unconditionally get a new ASID.  */
-	get_new_mmu_context(next, cpu);
+	if (prev != next)
+		check_and_switch_context(next, cpu);
 
-	write_mmu_entryhi(cpu_asid(cpu, next));
 	TLBMISS_HANDLER_SETUP_PGD(next->pgd);
-
-	/* mark mmu ownership change */
-	cpumask_clear_cpu(cpu, mm_cpumask(prev));
-	cpumask_set_cpu(cpu, mm_cpumask(next));
-
-	local_irq_restore(flags);
-}
-
-/*
- * If mm is currently active_mm, we can't really drop it. Instead,
- * we will get a new one for it.
- */
-static inline void
-drop_mmu_context(struct mm_struct *mm, unsigned int cpu)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-
-	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))  {
-		get_new_mmu_context(mm, cpu);
-		write_mmu_entryhi(cpu_asid(cpu, mm));
-	} else {
-		/* will get a new context next time */
-		cpu_context(cpu, mm) = 0;
-	}
-
-	local_irq_restore(flags);
+	write_mmu_entryhi(next->context.asid.counter);
 }
-
 #endif /* __ASM_CSKY_MMU_CONTEXT_H */
diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
index d213bb47b717..98c5716708d6 100644
--- a/arch/csky/include/asm/pgalloc.h
+++ b/arch/csky/include/asm/pgalloc.h
@@ -8,6 +8,9 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+#include <asm-generic/pgalloc.h>	/* for pte_{alloc,free}_one */
+
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 					pte_t *pte)
 {
@@ -39,33 +42,6 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 	return pte;
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm)
-{
-	struct page *pte;
-
-	pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
-	if (!pte)
-		return NULL;
-
-	if (!pgtable_page_ctor(pte)) {
-		__free_page(pte);
-		return NULL;
-	}
-
-	return pte;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_pages((unsigned long)pte, PTE_ORDER);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
-	pgtable_page_dtor(pte);
-	__free_pages(pte, PTE_ORDER);
-}
-
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	free_pages((unsigned long)pgd, PGD_ORDER);
diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h
index dcea277c09ae..c429a6f347de 100644
--- a/arch/csky/include/asm/pgtable.h
+++ b/arch/csky/include/asm/pgtable.h
@@ -290,8 +290,6 @@ static inline pte_t *pte_offset(pmd_t *dir, unsigned long address)
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern void paging_init(void);
 
-extern void show_jtlb_table(void);
-
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 		      pte_t *pte);