Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Peter Anvin:
 "This is a huge set of several partly interrelated (and concurrently
  developed) changes, which is why the branch history is messier than
  one would like.

  The *really* big items are two humonguous patchsets mostly developed
  by Yinghai Lu at my request, which completely revamps the way we
  create initial page tables.  In particular, rather than estimating how
  much memory we will need for page tables and then build them into that
  memory -- a calculation that has shown to be incredibly fragile -- we
  now build them (on 64 bits) with the aid of a "pseudo-linear mode" --
  a #PF handler which creates temporary page tables on demand.

  This has several advantages:

  1. It makes it much easier to support things that need access to data
     very early (a followon patchset uses this to load microcode way
     early in the kernel startup).

  2. It allows the kernel and all the kernel data objects to be invoked
     from above the 4 GB limit.  This allows kdump to work on very large
     systems.

  3. It greatly reduces the difference between Xen and native (Xen's
     equivalent of the #PF handler are the temporary page tables created
     by the domain builder), eliminating a bunch of fragile hooks.

  The patch series also gets us a bit closer to W^X.

  Additional work in this pull is the 64-bit get_user() work which you
  were also involved with, and a bunch of cleanups/speedups to
  __phys_addr()/__pa()."

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (105 commits)
  x86, mm: Move reserving low memory later in initialization
  x86, doc: Clarify the use of asm("%edx") in uaccess.h
  x86, mm: Redesign get_user with a __builtin_choose_expr hack
  x86: Be consistent with data size in getuser.S
  x86, mm: Use a bitfield to mask nuisance get_user() warnings
  x86/kvm: Fix compile warning in kvm_register_steal_time()
  x86-32: Add support for 64bit get_user()
  x86-32, mm: Remove reference to alloc_remap()
  x86-32, mm: Remove reference to resume_map_numa_kva()
  x86-32, mm: Rip out x86_32 NUMA remapping code
  x86/numa: Use __pa_nodebug() instead
  x86: Don't panic if can not alloc buffer for swiotlb
  mm: Add alloc_bootmem_low_pages_nopanic()
  x86, 64bit, mm: hibernate use generic mapping_init
  x86, 64bit, mm: Mark data/bss/brk to nx
  x86: Merge early kernel reserve for 32bit and 64bit
  x86: Add Crash kernel low reservation
  x86, kdump: Remove crashkernel range find limit for 64bit
  memblock: Add memblock_mem_size()
  x86, boot: Not need to check setup_header version for setup_data
  ...

lib/swiotlb.c

@@ -122,11 +122,18 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 	return phys_to_dma(hwdev, virt_to_phys(address));
 }
 
+static bool no_iotlb_memory;
+
 void swiotlb_print_info(void)
 {
 	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 	unsigned char *vstart, *vend;
 
+	if (no_iotlb_memory) {
+		pr_warn("software IO TLB: No low mem\n");
+		return;
+	}
+
 	vstart = phys_to_virt(io_tlb_start);
 	vend = phys_to_virt(io_tlb_end);
 
@@ -136,7 +143,7 @@ void swiotlb_print_info(void)
 	       bytes >> 20, vstart, vend - 1);
 }
 
-void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 {
 	void *v_overflow_buffer;
 	unsigned long i, bytes;
@@ -150,9 +157,10 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 	/*
 	 * Get the overflow emergency buffer
 	 */
-	v_overflow_buffer = alloc_bootmem_low_pages(PAGE_ALIGN(io_tlb_overflow));
+	v_overflow_buffer = alloc_bootmem_low_pages_nopanic(
+						PAGE_ALIGN(io_tlb_overflow));
 	if (!v_overflow_buffer)
-		panic("Cannot allocate SWIOTLB overflow buffer!\n");
+		return -ENOMEM;
 
 	io_tlb_overflow_buffer = __pa(v_overflow_buffer);
 
@@ -169,15 +177,19 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 
 	if (verbose)
 		swiotlb_print_info();
+
+	return 0;
 }
 
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
  */
-static void __init
-swiotlb_init_with_default_size(size_t default_size, int verbose)
+void  __init
+swiotlb_init(int verbose)
 {
+	/* default to 64MB */
+	size_t default_size = 64UL<<20;
 	unsigned char *vstart;
 	unsigned long bytes;
 
@@ -188,20 +200,16 @@ swiotlb_init_with_default_size(size_t default_size, int verbose)
 
 	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
-	/*
-	 * Get IO TLB memory from the low pages
-	 */
-	vstart = alloc_bootmem_low_pages(PAGE_ALIGN(bytes));
-	if (!vstart)
-		panic("Cannot allocate SWIOTLB buffer");
+	/* Get IO TLB memory from the low pages */
+	vstart = alloc_bootmem_low_pages_nopanic(PAGE_ALIGN(bytes));
+	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
+		return;
 
-	swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose);
-}
-
-void __init
-swiotlb_init(int verbose)
-{
-	swiotlb_init_with_default_size(64 * (1<<20), verbose);	/* default to 64MB */
+	if (io_tlb_start)
+		free_bootmem(io_tlb_start,
+				 PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+	pr_warn("Cannot allocate SWIOTLB buffer");
+	no_iotlb_memory = true;
 }
 
 /*
@@ -405,6 +413,9 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	unsigned long offset_slots;
 	unsigned long max_slots;
 
+	if (no_iotlb_memory)
+		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+
 	mask = dma_get_seg_boundary(hwdev);
 
 	tbl_dma_addr &= mask;