aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/mm
diff options
context:
space:
mode:
authorBenjamin Herrenschmidt <benh@kernel.crashing.org>2008-12-18 19:13:38 +0000
committerPaul Mackerras <paulus@samba.org>2008-12-21 14:21:16 +1100
commitf048aace29e007f2b642097e2da8231e0e9cce2d (patch)
tree5e99b1d1d37817703132e97388994386a7bee8da /arch/powerpc/mm
parent7c03d653cd257793dc40520c94e229b5fd0578e7 (diff)
powerpc/mm: Add SMP support to no-hash TLB handling
This commit moves the whole no-hash TLB handling out of line into a new tlb_nohash.c file, and implements some basic SMP support using IPIs and/or broadcast tlbivax instructions. Note that I'm using local invalidations for D->I cache coherency. At worst, if another processor is trying to execute the same and has the old entry in its TLB, it will just take a fault and re-do the TLB flush locally (it won't re-do the cache flush in any case). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
Diffstat (limited to 'arch/powerpc/mm')
-rw-r--r--arch/powerpc/mm/Makefile2
-rw-r--r--arch/powerpc/mm/fault.c2
-rw-r--r--arch/powerpc/mm/mem.c2
-rw-r--r--arch/powerpc/mm/tlb_hash32.c4
-rw-r--r--arch/powerpc/mm/tlb_nohash.c209
5 files changed, 216 insertions, 3 deletions
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 923bd3fa7d6..af987df8d5a 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -9,7 +9,7 @@ endif
obj-y := fault.o mem.o pgtable.o \
init_$(CONFIG_WORD_SIZE).o \
pgtable_$(CONFIG_WORD_SIZE).o
-obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o
+obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o
hash-$(CONFIG_PPC_NATIVE) := hash_native_64.o
obj-$(CONFIG_PPC64) += hash_utils_64.o \
slb_low.o slb.o stab.o \
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 7df0409107a..87f1f955dea 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -284,7 +284,7 @@ good_area:
}
pte_update(ptep, 0, _PAGE_HWEXEC |
_PAGE_ACCESSED);
- _tlbie(address, mm->context.id);
+ local_flush_tlb_page(vma, address);
pte_unmap_unlock(ptep, ptl);
up_read(&mm->mmap_sem);
return 0;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index b9e1a1da6e5..8fee696fb79 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -488,7 +488,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
* we invalidate the TLB here, thus avoiding dcbst
* misbehaviour.
*/
- _tlbie(address, 0 /* 8xx doesn't care about PID */);
+ _tlbil_va(address, 0 /* 8xx doesn't care about PID */);
#endif
/* The _PAGE_USER test should really be _PAGE_EXEC, but
* older glibc versions execute some code from no-exec
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index f9a47fee392..65190587a36 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -137,6 +137,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
flush_range(&init_mm, start, end);
FINISH_FLUSH;
}
+EXPORT_SYMBOL(flush_tlb_kernel_range);
/*
* Flush all the (user) entries for the address space described by mm.
@@ -160,6 +161,7 @@ void flush_tlb_mm(struct mm_struct *mm)
flush_range(mp->vm_mm, mp->vm_start, mp->vm_end);
FINISH_FLUSH;
}
+EXPORT_SYMBOL(flush_tlb_mm);
void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
@@ -176,6 +178,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
FINISH_FLUSH;
}
+EXPORT_SYMBOL(flush_tlb_page);
/*
* For each address in the range, find the pte for the address
@@ -188,3 +191,4 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
flush_range(vma->vm_mm, start, end);
FINISH_FLUSH;
}
+EXPORT_SYMBOL(flush_tlb_range);
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
new file mode 100644
index 00000000000..803a64c02b0
--- /dev/null
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -0,0 +1,209 @@
+/*
+ * This file contains the routines for TLB flushing.
+ * On machines where the MMU does not use a hash table to store virtual to
+ * physical translations (ie, SW loaded TLBs or Book3E compilant processors,
+ * this does -not- include 603 however which shares the implementation with
+ * hash based processors)
+ *
+ * -- BenH
+ *
+ * Copyright 2008 Ben Herrenschmidt <benh@kernel.crashing.org>
+ * IBM Corp.
+ *
+ * Derived from arch/ppc/mm/init.c:
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ * and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ * Copyright (C) 1996 Paul Mackerras
+ *
+ * Derived from "arch/i386/mm/init.c"
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+#include "mmu_decl.h"
+
+/*
+ * Base TLB flushing operations:
+ *
+ * - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ * - flush_tlb_page(vma, vmaddr) flushes one page
+ * - flush_tlb_range(vma, start, end) flushes a range of pages
+ * - flush_tlb_kernel_range(start, end) flushes kernel pages
+ *
+ * - local_* variants of page and mm only apply to the current
+ * processor
+ */
+
+/*
+ * These are the base non-SMP variants of page and mm flushing
+ */
+void local_flush_tlb_mm(struct mm_struct *mm)
+{
+ unsigned int pid;
+
+ preempt_disable();
+ pid = mm->context.id;
+ if (pid != MMU_NO_CONTEXT)
+ _tlbil_pid(pid);
+ preempt_enable();
+}
+EXPORT_SYMBOL(local_flush_tlb_mm);
+
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+ unsigned int pid;
+
+ preempt_disable();
+ pid = vma ? vma->vm_mm->context.id : 0;
+ if (pid != MMU_NO_CONTEXT)
+ _tlbil_va(vmaddr, pid);
+ preempt_enable();
+}
+EXPORT_SYMBOL(local_flush_tlb_page);
+
+
+/*
+ * And here are the SMP non-local implementations
+ */
+#ifdef CONFIG_SMP
+
+static DEFINE_SPINLOCK(tlbivax_lock);
+
+struct tlb_flush_param {
+ unsigned long addr;
+ unsigned int pid;
+};
+
+static void do_flush_tlb_mm_ipi(void *param)
+{
+ struct tlb_flush_param *p = param;
+
+ _tlbil_pid(p ? p->pid : 0);
+}
+
+static void do_flush_tlb_page_ipi(void *param)
+{
+ struct tlb_flush_param *p = param;
+
+ _tlbil_va(p->addr, p->pid);
+}
+
+
+/* Note on invalidations and PID:
+ *
+ * We snapshot the PID with preempt disabled. At this point, it can still
+ * change either because:
+ * - our context is being stolen (PID -> NO_CONTEXT) on another CPU
+ * - we are invaliating some target that isn't currently running here
+ * and is concurrently acquiring a new PID on another CPU
+ * - some other CPU is re-acquiring a lost PID for this mm
+ * etc...
+ *
+ * However, this shouldn't be a problem as we only guarantee
+ * invalidation of TLB entries present prior to this call, so we
+ * don't care about the PID changing, and invalidating a stale PID
+ * is generally harmless.
+ */
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+ cpumask_t cpu_mask;
+ unsigned int pid;
+
+ preempt_disable();
+ pid = mm->context.id;
+ if (unlikely(pid == MMU_NO_CONTEXT))
+ goto no_context;
+ cpu_mask = mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+ if (!cpus_empty(cpu_mask)) {
+ struct tlb_flush_param p = { .pid = pid };
+ smp_call_function_mask(cpu_mask, do_flush_tlb_mm_ipi, &p, 1);
+ }
+ _tlbil_pid(pid);
+ no_context:
+ preempt_enable();
+}
+EXPORT_SYMBOL(flush_tlb_mm);
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+ cpumask_t cpu_mask;
+ unsigned int pid;
+
+ preempt_disable();
+ pid = vma ? vma->vm_mm->context.id : 0;
+ if (unlikely(pid == MMU_NO_CONTEXT))
+ goto bail;
+ cpu_mask = vma->vm_mm->cpu_vm_mask;
+ cpu_clear(smp_processor_id(), cpu_mask);
+ if (!cpus_empty(cpu_mask)) {
+ /* If broadcast tlbivax is supported, use it */
+ if (mmu_has_feature(MMU_FTR_USE_TLBIVAX_BCAST)) {
+ int lock = mmu_has_feature(MMU_FTR_LOCK_BCAST_INVAL);
+ if (lock)
+ spin_lock(&tlbivax_lock);
+ _tlbivax_bcast(vmaddr, pid);
+ if (lock)
+ spin_unlock(&tlbivax_lock);
+ goto bail;
+ } else {
+ struct tlb_flush_param p = { .pid = pid, .addr = vmaddr };
+ smp_call_function_mask(cpu_mask,
+ do_flush_tlb_page_ipi, &p, 1);
+ }
+ }
+ _tlbil_va(vmaddr, pid);
+ bail:
+ preempt_enable();
+}
+EXPORT_SYMBOL(flush_tlb_page);
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Flush kernel TLB entries in the given range
+ */
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+#ifdef CONFIG_SMP
+ preempt_disable();
+ smp_call_function(do_flush_tlb_mm_ipi, NULL, 1);
+ _tlbil_pid(0);
+ preempt_enable();
+#endif
+ _tlbil_pid(0);
+}
+EXPORT_SYMBOL(flush_tlb_kernel_range);
+
+/*
+ * Currently, for range flushing, we just do a full mm flush. This should
+ * be optimized based on a threshold on the size of the range, since
+ * some implementation can stack multiple tlbivax before a tlbsync but
+ * for now, we keep it that way
+ */
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
+
+{
+ flush_tlb_mm(vma->vm_mm);
+}
+EXPORT_SYMBOL(flush_tlb_range);