[POWERPC] Fix 32-bit mm operations when not using BATs

On hash table based 32 bits powerpc's, the hash management code runs with
a big spinlock. It's thus important that it never causes itself a hash
fault. That code is generally safe (it does memory accesses in real mode
among other things) with the exception of the actual access to the code
itself. That is, the kernel text needs to be accessible without taking
a hash miss exceptions.

This is currently guaranteed by having a BAT register mapping part of the
linear mapping permanently, which includes the kernel text. But this is
not true if using the "nobats" kernel command line option (which can be
useful for debugging) and will not be true when using DEBUG_PAGEALLOC
implemented in a subsequent patch.

This patch fixes this by pre-faulting in the hash table pages that hit
the kernel text, and making sure we never evict such a page under hash
pressure.

Signed-off-by: Benjamin Herrenchmidt <benh@kernel.crashing.org>
 arch/powerpc/mm/hash_low_32.S |   22 ++++++++++++++++++++--
 arch/powerpc/mm/mem.c         |    3 ---
 arch/powerpc/mm/mmu_decl.h    |    4 ++++
 arch/powerpc/mm/pgtable_32.c  |   11 +++++++----
 4 files changed, 31 insertions(+), 9 deletions(-)
Signed-off-by: Paul Mackerras <paulus@samba.org>

diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index bd68df5..ddceefc 100644 (file)
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -283,6 +283,7 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64)
 #define PTEG_SIZE      64
 #define LG_PTEG_SIZE   6
 #define LDPTEu         lwzu
+#define LDPTE          lwz
 #define STPTE          stw
 #define CMPPTE         cmpw
 #define PTE_H          0x40
@@ -389,13 +390,30 @@ _GLOBAL(hash_page_patch_C)
         * and we know there is a definite (although small) speed
         * advantage to putting the PTE in the primary PTEG, we always
         * put the PTE in the primary PTEG.
+        *
+        * In addition, we skip any slot that is mapping kernel text in
+        * order to avoid a deadlock when not using BAT mappings if
+        * trying to hash in the kernel hash code itself after it has
+        * already taken the hash table lock. This works in conjunction
+        * with pre-faulting of the kernel text.
+        *
+        * If the hash table bucket is full of kernel text entries, we'll
+        * lockup here but that shouldn't happen
         */
-       addis   r4,r7,next_slot@ha
+
+1:     addis   r4,r7,next_slot@ha              /* get next evict slot */
        lwz     r6,next_slot@l(r4)
-       addi    r6,r6,PTE_SIZE
+       addi    r6,r6,PTE_SIZE                  /* search for candidate */
        andi.   r6,r6,7*PTE_SIZE
        stw     r6,next_slot@l(r4)
        add     r4,r3,r6
+       LDPTE   r0,PTE_SIZE/2(r4)               /* get PTE second word */
+       clrrwi  r0,r0,12
+       lis     r6,etext@h
+       ori     r6,r6,etext@l                   /* get etext */
+       tophys(r6,r6)
+       cmpl    cr0,r0,r6                       /* compare and try again */
+       blt     1b
 
 #ifndef CONFIG_SMP
        /* Store PTE in PTEG */

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 52f397c..c4bcd75 100644 (file)
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -58,9 +58,6 @@ int init_bootmem_done;
 int mem_init_done;
 unsigned long memory_limit;
 
-extern void hash_preload(struct mm_struct *mm, unsigned long ea,
-                        unsigned long access, unsigned long trap);
-
 int page_is_ram(unsigned long pfn)
 {
        unsigned long paddr = (pfn << PAGE_SHIFT);

diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index bea2d21..ee55e0b 100644 (file)
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -22,6 +22,10 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu.h>
 
+extern void hash_preload(struct mm_struct *mm, unsigned long ea,
+                        unsigned long access, unsigned long trap);
+
+
 #ifdef CONFIG_PPC32
 extern void mapin_ram(void);
 extern int map_page(unsigned long va, phys_addr_t pa, int flags);

diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 95d3afe..f75f2fc 100644 (file)
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -282,16 +282,19 @@ int map_page(unsigned long va, phys_addr_t pa, int flags)
 void __init mapin_ram(void)
 {
        unsigned long v, p, s, f;
+       int ktext;
 
        s = mmu_mapin_ram();
        v = KERNELBASE + s;
        p = PPC_MEMSTART + s;
        for (; s < total_lowmem; s += PAGE_SIZE) {
-               if ((char *) v >= _stext && (char *) v < etext)
-                       f = _PAGE_RAM_TEXT;
-               else
-                       f = _PAGE_RAM;
+               ktext = ((char *) v >= _stext && (char *) v < etext);
+               f = ktext ?_PAGE_RAM_TEXT : _PAGE_RAM;
                map_page(v, p, f);
+#ifdef CONFIG_PPC_STD_MMU_32
+               if (ktext)
+                       hash_preload(&init_mm, v, 0, 0x300);
+#endif
                v += PAGE_SIZE;
                p += PAGE_SIZE;
        }