powerpc/mm: Add Strong Access Ordering support

Allow an application to enable Strong Access Ordering on specific pages of
memory on Power 7 hardware. Currently, power has a weaker memory model than
x86. Implementing a stronger memory model allows an emulator to more
efficiently translate x86 code into power code, resulting in faster code
execution.

On Power 7 hardware, storing 0b1110 in the WIMG bits of the hpte enables
strong access ordering mode for the memory page.  This patchset allows a
user to specify which pages are thus enabled by passing a new protection
bit through mmap() and mprotect().  I have defined PROT_SAO to be 0x10.

Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index 4fe69ca244818e78fb86c37c2091a023b4e77b0b..c04832c4a02e3965834a48adbaad9450e76ef378 100644 (file)
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -143,6 +143,9 @@ static inline unsigned long do_mmap2(unsigned long addr, size_t len,
        struct file * file = NULL;
        unsigned long ret = -EINVAL;
 
+       if (!arch_validate_prot(prot))
+               goto out;
+
        if (shift) {
                if (off & ((1 << shift) - 1))
                        goto out;

diff --git a/include/asm-powerpc/mman.h b/include/asm-powerpc/mman.h
index 0c46bf2c7d5fe6557272cc51d0444aa72b4a438a..f8a32e20ba04ad02443ca320deb06580922b3a20 100644 (file)
--- a/include/asm-powerpc/mman.h
+++ b/include/asm-powerpc/mman.h
@@ -1,7 +1,9 @@
 #ifndef _ASM_POWERPC_MMAN_H
 #define _ASM_POWERPC_MMAN_H
 
+#include <asm/cputable.h>
 #include <asm-generic/mman.h>
+#include <linux/mm.h>
 
 /*
  * This program is free software; you can redistribute it and/or
@@ -26,4 +28,32 @@
 #define MAP_POPULATE   0x8000          /* populate (prefault) pagetables */
 #define MAP_NONBLOCK   0x10000         /* do not block on IO */
 
+#ifdef CONFIG_PPC64
+/*
+ * This file is included by linux/mman.h, so we can't use cacl_vm_prot_bits()
+ * here.  How important is the optimization?
+ */
+static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot)
+{
+       return (prot & PROT_SAO) ? VM_SAO : 0;
+}
+#define arch_calc_vm_prot_bits(prot) arch_calc_vm_prot_bits(prot)
+
+static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
+{
+       return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : 0;
+}
+#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
+
+static inline int arch_validate_prot(unsigned long prot)
+{
+       if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
+               return 0;
+       if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO))
+               return 0;
+       return 1;
+}
+#define arch_validate_prot(prot) arch_validate_prot(prot)
+
+#endif /* CONFIG_PPC64 */
 #endif /* _ASM_POWERPC_MMAN_H */