x86, mm: Make DEBUG_VIRTUAL work earlier in boot

The KVM code has some repeated bugs in it around use of __pa() on
per-cpu data.  Those data are not in an area on which using
__pa() is valid.  However, they are also called early enough in
boot that __vmalloc_start_set is not set, and thus the
CONFIG_DEBUG_VIRTUAL debugging does not catch them.

This adds a check to also verify __pa() calls against max_low_pfn,
which we can use earler in boot than is_vmalloc_addr().  However,
if we are super-early in boot, max_low_pfn=0 and this will trip
on every call, so also make sure that max_low_pfn is set before
we try to use it.

With this patch applied, CONFIG_DEBUG_VIRTUAL will actually
catch the bug I was chasing (and fix later in this series).

I'd love to find a generic way so that any __pa() call on percpu
areas could do a BUG_ON(), but there don't appear to be any nice
and easy ways to check if an address is a percpu one.  Anybody
have ideas on a way to do this?

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20130122212430.F46F8159@kernel.stglabs.ibm.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 2d125be..76604eb 100644 (file)
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -219,7 +219,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
         */
        nd = alloc_remap(nid, nd_size);
        if (nd) {
-               nd_pa = __pa(nd);
+               nd_pa = __phys_addr_nodebug(nd);
                remapped = true;
        } else {
                nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 0eb572e..2610bd9 100644 (file)
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -560,10 +560,10 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
 {
        unsigned long id_sz;
 
-       if (base >= __pa(high_memory))
+       if (base > __pa(high_memory-1))
                return 0;
 
-       id_sz = (__pa(high_memory) < base + size) ?
+       id_sz = (__pa(high_memory-1) <= base + size) ?
                                __pa(high_memory) - base :
                                size;
 

diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c
index c73fedd..e666cbb 100644 (file)
--- a/arch/x86/mm/physaddr.c
+++ b/arch/x86/mm/physaddr.c
@@ -1,3 +1,4 @@
+#include <linux/bootmem.h>
 #include <linux/mmdebug.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -68,10 +69,16 @@ EXPORT_SYMBOL(__virt_addr_valid);
 #ifdef CONFIG_DEBUG_VIRTUAL
 unsigned long __phys_addr(unsigned long x)
 {
+       unsigned long phys_addr = x - PAGE_OFFSET;
        /* VMALLOC_* aren't constants  */
        VIRTUAL_BUG_ON(x < PAGE_OFFSET);
        VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x));
-       return x - PAGE_OFFSET;
+       /* max_low_pfn is set early, but not _that_ early */
+       if (max_low_pfn) {
+               VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn);
+               BUG_ON(slow_virt_to_phys((void *)x) != phys_addr);
+       }
+       return phys_addr;
 }
 EXPORT_SYMBOL(__phys_addr);
 #endif