Merge commit 'v2.6.39-rc7' into sched/core

2 files changed, 134 insertions, 6 deletions

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index a991b57f91fe..55c965b38c27 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1463,6 +1463,119 @@ 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
@@ -1473,30 +1586,43 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 #endif
 }
 
+#ifdef CONFIG_X86_32
 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 {
-	unsigned long pfn = pte_pfn(pte);
-
-#ifdef CONFIG_X86_32
 	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
 	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
 		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
 			       pte_val_ma(pte));
-#endif
+
+	return pte;
+}
+#else /* CONFIG_X86_64 */
+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
 	 * it is RO.
 	 */
 	if (((!is_early_ioremap_ptep(ptep) &&
-			pfn >= pgt_buf_start && pfn < pgt_buf_end)) ||
+			pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
 			(is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
 		pte = pte_wrprotect(pte);
 
 	return pte;
 }
+#endif /* CONFIG_X86_64 */
 
 /* Init-time set_pte while constructing initial pagetables, which
    doesn't allow RO pagetable pages to be remapped RW */
@@ -1992,6 +2118,8 @@ __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
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index fa0269a99377..90bac0aac3a5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -227,7 +227,7 @@ char * __init xen_memory_setup(void)
 
 	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
-	xen_extra_mem_start = mem_end;
+	xen_extra_mem_start = max((1ULL << 32), mem_end);
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end;