Merge branch 'stable/bug-fixes-for-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

* 'stable/bug-fixes-for-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  x86/mm: Fix section mismatch derived from native_pagetable_reserve()
  x86,xen: introduce x86_init.mapping.pagetable_reserve
  Revert "xen/mmu: Add workaround "x86-64, mm: Put early page table high""

5 files changed, 54 insertions, 125 deletions

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 7db7723d1f32..d56187c6b838 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -299,6 +299,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 /* Install a pte for a particular vaddr in kernel space. */
 void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
+extern void native_pagetable_reserve(u64 start, u64 end);
 #ifdef CONFIG_X86_32
 extern void native_pagetable_setup_start(pgd_t *base);
 extern void native_pagetable_setup_done(pgd_t *base);
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 643ebf2e2ad8..d3d859035af9 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -68,6 +68,17 @@ struct x86_init_oem {
 };
 
 /**
+ * struct x86_init_mapping - platform specific initial kernel pagetable setup
+ * @pagetable_reserve:  reserve a range of addresses for kernel pagetable usage
+ *
+ * For more details on the purpose of this hook, look in
+ * init_memory_mapping and the commit that added it.
+ */
+struct x86_init_mapping {
+        void (*pagetable_reserve)(u64 start, u64 end);
+};
+
+/**
  * struct x86_init_paging - platform specific paging functions
  * @pagetable_setup_start:      platform specific pre paging_init() call
  * @pagetable_setup_done:       platform specific post paging_init() call
@@ -123,6 +134,7 @@ struct x86_init_ops {
         struct x86_init_mpparse         mpparse;
         struct x86_init_irqs            irqs;
         struct x86_init_oem             oem;
+        struct x86_init_mapping         mapping;
         struct x86_init_paging          paging;
         struct x86_init_timers          timers;
         struct x86_init_iommu           iommu;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index c11514e9128b..75ef4b18e9b7 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -61,6 +61,10 @@ struct x86_init_ops x86_init __initdata = {
                 .banner                 = default_banner,
         },
 
+        .mapping = {
+                .pagetable_reserve              = native_pagetable_reserve,
+        },
+
         .paging = {
                 .pagetable_setup_start  = native_pagetable_setup_start,
                 .pagetable_setup_done   = native_pagetable_setup_done,
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 286d289b039b..37b8b0fe8320 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -81,6 +81,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
                 end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
 }
 
+void __init native_pagetable_reserve(u64 start, u64 end)
+{
+        memblock_x86_reserve_range(start, end, "PGTABLE");
+}
+
 struct map_range {
         unsigned long start;
         unsigned long end;
@@ -272,9 +277,24 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
         __flush_tlb_all();
 
+        /*
+         * Reserve the kernel pagetable pages we used (pgt_buf_start -
+         * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
+         * so that they can be reused for other purposes.
+         *
+         * On native it just means calling memblock_x86_reserve_range, on Xen it
+         * also means marking RW the pagetable pages that we allocated before
+         * but that haven't been used.
+         *
+         * In fact on xen we mark RO the whole range pgt_buf_start -
+         * pgt_buf_top, because we have to make sure that when
+         * init_memory_mapping reaches the pagetable pages area, it maps
+         * RO all the pagetable pages, including the ones that are beyond
+         * pgt_buf_end at that time.
+         */
         if (!after_bootmem && pgt_buf_end > pgt_buf_start)
-                memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
-                                 pgt_buf_end << PAGE_SHIFT, "PGTABLE");
+                x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
+                                PFN_PHYS(pgt_buf_end));
 
         if (!after_bootmem)
                 early_memtest(start, end);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 55c965b38c27..0684f3c74d53 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1275,6 +1275,20 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 }
 
+static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
+{
+        /* reserve the range used */
+        native_pagetable_reserve(start, end);
+
+        /* set as RW the rest */
+        printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
+                        PFN_PHYS(pgt_buf_top));
+        while (end < PFN_PHYS(pgt_buf_top)) {
+                make_lowmem_page_readwrite(__va(end));
+                end += PAGE_SIZE;
+        }
+}
+
 static void xen_post_allocator_init(void);
 
 static __init void xen_pagetable_setup_done(pgd_t *base)
@@ -1463,119 +1477,6 @@ static int xen_pgd_alloc(struct mm_struct *mm)
         return ret;
 }
 
-#ifdef CONFIG_X86_64
-static __initdata u64 __last_pgt_set_rw = 0;
-static __initdata u64 __pgt_buf_start = 0;
-static __initdata u64 __pgt_buf_end = 0;
-static __initdata u64 __pgt_buf_top = 0;
-/*
- * As a consequence of the commit:
- * 
- * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
- * Author: Yinghai Lu <yinghai@kernel.org>
- * Date:   Fri Dec 17 16:58:28 2010 -0800
- * 
- *     x86-64, mm: Put early page table high
- * 
- * at some point init_memory_mapping is going to reach the pagetable pages
- * area and map those pages too (mapping them as normal memory that falls
- * in the range of addresses passed to init_memory_mapping as argument).
- * Some of those pages are already pagetable pages (they are in the range
- * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
- * everything is fine.
- * Some of these pages are not pagetable pages yet (they fall in the range
- * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
- * are going to be mapped RW.  When these pages become pagetable pages and
- * are hooked into the pagetable, xen will find that the guest has already
- * a RW mapping of them somewhere and fail the operation.
- * The reason Xen requires pagetables to be RO is that the hypervisor needs
- * to verify that the pagetables are valid before using them. The validation
- * operations are called "pinning".
- * 
- * In order to fix the issue we mark all the pages in the entire range
- * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
- * is completed only the range pgt_buf_start-pgt_buf_end is reserved by
- * init_memory_mapping. Hence the kernel is going to crash as soon as one
- * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
- * ranges are RO).
- * 
- * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
- * the init_memory_mapping has completed (in a perfect world we would
- * call this function from init_memory_mapping, but lets ignore that).
- * 
- * Because we are called _after_ init_memory_mapping the pgt_buf_[start,
- * end,top] have all changed to new values (b/c init_memory_mapping
- * is called and setting up another new page-table). Hence, the first time
- * we enter this function, we save away the pgt_buf_start value and update
- * the pgt_buf_[end,top].
- * 
- * When we detect that the "old" pgt_buf_start through pgt_buf_end
- * PFNs have been reserved (so memblock_x86_reserve_range has been called),
- * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
- * 
- * And then we update those "old" pgt_buf_[end|top] with the new ones
- * so that we can redo this on the next pagetable.
- */
-static __init void mark_rw_past_pgt(void) {
-
-        if (pgt_buf_end > pgt_buf_start) {
-                u64 addr, size;
-
-                /* Save it away. */
-                if (!__pgt_buf_start) {
-                        __pgt_buf_start = pgt_buf_start;
-                        __pgt_buf_end = pgt_buf_end;
-                        __pgt_buf_top = pgt_buf_top;
-                        return;
-                }
-                /* If we get the range that starts at __pgt_buf_end that means
-                 * the range is reserved, and that in 'init_memory_mapping'
-                 * the 'memblock_x86_reserve_range' has been called with the
-                 * outdated __pgt_buf_start, __pgt_buf_end (the "new"
-                 * pgt_buf_[start|end|top] refer now to a new pagetable.
-                 * Note: we are called _after_ the pgt_buf_[..] have been
-                 * updated.*/
-
-                addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
-                                                       &size, PAGE_SIZE);
-
-                /* Still not reserved, meaning 'memblock_x86_reserve_range'
-                 * hasn't been called yet. Update the _end and _top.*/
-                if (addr == PFN_PHYS(__pgt_buf_start)) {
-                        __pgt_buf_end = pgt_buf_end;
-                        __pgt_buf_top = pgt_buf_top;
-                        return;
-                }
-
-                /* OK, the area is reserved, meaning it is time for us to
-                 * set RW for the old end->top PFNs. */
-
-                /* ..unless we had already done this. */
-                if (__pgt_buf_end == __last_pgt_set_rw)
-                        return;
-
-                addr = PFN_PHYS(__pgt_buf_end);
-                
-                /* set as RW the rest */
-                printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
-                        PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
-                
-                while (addr < PFN_PHYS(__pgt_buf_top)) {
-                        make_lowmem_page_readwrite(__va(addr));
-                        addr += PAGE_SIZE;
-                }
-                /* And update everything so that we are ready for the next
-                 * pagetable (the one created for regions past 4GB) */
-                __last_pgt_set_rw = __pgt_buf_end;
-                __pgt_buf_start = pgt_buf_start;
-                __pgt_buf_end = pgt_buf_end;
-                __pgt_buf_top = pgt_buf_top;
-        }
-        return;
-}
-#else
-static __init void mark_rw_past_pgt(void) { }
-#endif
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
@@ -1602,14 +1503,6 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
         unsigned long pfn = pte_pfn(pte);
 
         /*
-         * A bit of optimization. We do not need to call the workaround
-         * when xen_set_pte_init is called with a PTE with 0 as PFN.
-         * That is b/c the pagetable at that point are just being populated
-         * with empty values and we can save some cycles by not calling
-         * the 'memblock' code.*/
-        if (pfn)
-                mark_rw_past_pgt();
-        /*
          * If the new pfn is within the range of the newly allocated
          * kernel pagetable, and it isn't being mapped into an
          * early_ioremap fixmap slot as a freshly allocated page, make sure
@@ -2118,8 +2011,6 @@ __init void xen_ident_map_ISA(void)
 
 static __init void xen_post_allocator_init(void)
 {
-        mark_rw_past_pgt();
-
 #ifdef CONFIG_XEN_DEBUG
         pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
 #endif
@@ -2228,6 +2119,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 void __init xen_init_mmu_ops(void)
 {
+        x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
         x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
         x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
         pv_mmu_ops = xen_mmu_ops;