x86,xen: introduce x86_init.mapping.pagetable_reserve

Introduce a new x86_init hook called pagetable_reserve that at the end
of init_memory_mapping is used to reserve a range of memory addresses for
the kernel pagetable pages we used and free the other ones.

On native it just calls memblock_x86_reserve_range while on xen it also
takes care of setting the spare memory previously allocated
for kernel pagetable pages from RO to RW, so that it can be used for
other purposes.

A detailed explanation of the reason why this hook is needed follows.

As a consequence of the commit:

commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
Author: Yinghai Lu <[e-mail]>
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" (more details in arch/x86/xen/mmu.c).

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 we need a hook to reserve the kernel pagetable pages we
used and free the other ones 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 before.

Another way to fix this is without using the hook is by adding a 'if
(xen_pv_domain)' in the 'init_memory_mapping' code and calling the Xen
counterpart, but that is just nasty.

Signed-off-by: Stefano Stabellini <[e-mail]>
Acked-by: Yinghai Lu <[e-mail]>
Acked-by: H. Peter Anvin <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Signed-off-by: Konrad Rzeszutek Wilk <[e-mail]>

arch/x86/include/asm/pgtable_types.h

···
 /* 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);

arch/x86/include/asm/x86_init.h

···
 };
 
 /**
+ * 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
···
 	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;

arch/x86/kernel/x86_init.c

···
 		.banner			= default_banner,
 	},
 
+	.mapping = {
+		.pagetable_reserve		= native_pagetable_reserve,
+	},
+
 	.paging = {
 		.pagetable_setup_start	= native_pagetable_setup_start,
 		.pagetable_setup_done	= native_pagetable_setup_done,

arch/x86/mm/init.c

···
 		end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
 }
 
+void native_pagetable_reserve(u64 start, u64 end)
+{
+	memblock_x86_reserve_range(start, end, "PGTABLE");
+}
+
 struct map_range {
 	unsigned long start;
 	unsigned long end;
···
 
 	__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);

arch/x86/xen/mmu.c

···
 {
 }
 
+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)
···
 
 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;