[PATCH 5/7] xen/p2m: Add logic to revector a P2M tree to use __va leafs.

From: Konrad Rzeszutek Wilk
Date: Thu Jul 26 2012 - 16:57:50 EST


During bootup Xen supplies us with a P2M array. It sticks
it right after the ramdisk, as can be seen with a 128GB PV guest:

(certain parts removed for clarity):
xc_dom_build_image: called
xc_dom_alloc_segment: kernel : 0xffffffff81000000 -> 0xffffffff81e43000 (pfn 0x1000 + 0xe43 pages)
xc_dom_pfn_to_ptr: domU mapping: pfn 0x1000+0xe43 at 0x7f097d8bf000
xc_dom_alloc_segment: ramdisk : 0xffffffff81e43000 -> 0xffffffff925c7000 (pfn 0x1e43 + 0x10784 pages)
xc_dom_pfn_to_ptr: domU mapping: pfn 0x1e43+0x10784 at 0x7f0952dd2000
xc_dom_alloc_segment: phys2mach : 0xffffffff925c7000 -> 0xffffffffa25c7000 (pfn 0x125c7 + 0x10000 pages)
xc_dom_pfn_to_ptr: domU mapping: pfn 0x125c7+0x10000 at 0x7f0942dd2000
xc_dom_alloc_page : start info : 0xffffffffa25c7000 (pfn 0x225c7)
xc_dom_alloc_page : xenstore : 0xffffffffa25c8000 (pfn 0x225c8)
xc_dom_alloc_page : console : 0xffffffffa25c9000 (pfn 0x225c9)
nr_page_tables: 0x0000ffffffffffff/48: 0xffff000000000000 -> 0xffffffffffffffff, 1 table(s)
nr_page_tables: 0x0000007fffffffff/39: 0xffffff8000000000 -> 0xffffffffffffffff, 1 table(s)
nr_page_tables: 0x000000003fffffff/30: 0xffffffff80000000 -> 0xffffffffbfffffff, 1 table(s)
nr_page_tables: 0x00000000001fffff/21: 0xffffffff80000000 -> 0xffffffffa27fffff, 276 table(s)
xc_dom_alloc_segment: page tables : 0xffffffffa25ca000 -> 0xffffffffa26e1000 (pfn 0x225ca + 0x117 pages)
xc_dom_pfn_to_ptr: domU mapping: pfn 0x225ca+0x117 at 0x7f097d7a8000
xc_dom_alloc_page : boot stack : 0xffffffffa26e1000 (pfn 0x226e1)
xc_dom_build_image : virt_alloc_end : 0xffffffffa26e2000
xc_dom_build_image : virt_pgtab_end : 0xffffffffa2800000

So the physical memory and virtual (using __START_KERNEL_map addresses)
layout looks as so:

phys __ka
/------------\ /-------------------\
| 0 | empty | 0xffffffff80000000|
| .. | | .. |
| 16MB | <= kernel starts | 0xffffffff81000000|
| .. | | |
| 30MB | <= kernel ends => | 0xffffffff81e43000|
| .. | & ramdisk starts | .. |
| 293MB | <= ramdisk ends=> | 0xffffffff925c7000|
| .. | & P2M starts | .. |
| .. | | .. |
| 549MB | <= P2M ends => | 0xffffffffa25c7000|
| .. | start_info | 0xffffffffa25c7000|
| .. | xenstore | 0xffffffffa25c8000|
| .. | cosole | 0xffffffffa25c9000|
| 549MB | <= page tables => | 0xffffffffa25ca000|
| .. | | |
| 550MB | <= PGT end => | 0xffffffffa26e1000|
| .. | boot stack | |
\------------/ \-------------------/

As can be seen, the ramdisk, P2M and pagetables are taking
a bit of __ka addresses space. Which is a problem since the
MODULES_VADDR starts at 0xffffffffa0000000 - and P2M sits
right in there! This results during bootup with the inability to
load modules, with this error:

------------[ cut here ]------------
WARNING: at /home/konrad/ssd/linux/mm/vmalloc.c:106 vmap_page_range_noflush+0x2d9/0x370()
Call Trace:
[<ffffffff810719fa>] warn_slowpath_common+0x7a/0xb0
[<ffffffff81030279>] ? __raw_callee_save_xen_pmd_val+0x11/0x1e
[<ffffffff81071a45>] warn_slowpath_null+0x15/0x20
[<ffffffff81130b89>] vmap_page_range_noflush+0x2d9/0x370
[<ffffffff81130c4d>] map_vm_area+0x2d/0x50
[<ffffffff811326d0>] __vmalloc_node_range+0x160/0x250
[<ffffffff810c5369>] ? module_alloc_update_bounds+0x19/0x80
[<ffffffff810c6186>] ? load_module+0x66/0x19c0
[<ffffffff8105cadc>] module_alloc+0x5c/0x60
[<ffffffff810c5369>] ? module_alloc_update_bounds+0x19/0x80
[<ffffffff810c5369>] module_alloc_update_bounds+0x19/0x80
[<ffffffff810c70c3>] load_module+0xfa3/0x19c0
[<ffffffff812491f6>] ? security_file_permission+0x86/0x90
[<ffffffff810c7b3a>] sys_init_module+0x5a/0x220
[<ffffffff815ce339>] system_call_fastpath+0x16/0x1b
---[ end trace fd8f7704fdea0291 ]---
vmalloc: allocation failure, allocated 16384 of 20480 bytes
modprobe: page allocation failure: order:0, mode:0xd2

Since the __va and __ka are 1:1 up to MODULES_VADDR and
cleanup_highmap rids __ka of the ramdisk mapping, what
we want to do is similar - get rid of the P2M in the __ka
address space. There are two ways of fixing this:

1) All P2M lookups instead of using the __ka address would
use the __va address. This means we can safely erase from
__ka space the PMD pointers that point to the PFNs for
P2M array and be OK.
2). Allocate a new array, copy the existing P2M into it,
revector the P2M tree to use that, and return the old
P2M to the memory allocate. This has the advantage that
it sets the stage for using XEN_ELF_NOTE_INIT_P2M
feature. That feature allows us to set the exact virtual
address space we want for the P2M - and allows us to
boot as initial domain on large machines.

So we pick option 2).

This patch only lays the groundwork in the P2M code. The patch
that modifies the MMU is called "xen/mmu: Copy and revector the P2M tree."

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
---
arch/x86/xen/p2m.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++
arch/x86/xen/xen-ops.h | 1 +
2 files changed, 71 insertions(+), 0 deletions(-)

diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 6a2bfa4..bbfd085 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -394,7 +394,77 @@ void __init xen_build_dynamic_phys_to_machine(void)
* Xen provided pagetable). Do it later in xen_reserve_internals.
*/
}
+#ifdef CONFIG_X86_64
+#include <linux/bootmem.h>
+unsigned long __init xen_revector_p2m_tree(void)
+{
+ unsigned long va_start;
+ unsigned long va_end;
+ unsigned long pfn;
+ unsigned long *mfn_list = NULL;
+ unsigned long size;
+
+ va_start = xen_start_info->mfn_list;
+ /*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long),
+ * so make sure it is rounded up to that */
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+ va_end = va_start + size;
+
+ /* If we were revectored already, don't do it again. */
+ if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET)
+ return 0;
+
+ mfn_list = alloc_bootmem_align(size, PAGE_SIZE);
+ if (!mfn_list) {
+ pr_warn("Could not allocate space for a new P2M tree!\n");
+ return xen_start_info->mfn_list;
+ }
+ /* Fill it out with INVALID_P2M_ENTRY value */
+ memset(mfn_list, 0xFF, size);
+
+ for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+ unsigned mididx;
+ unsigned long *mid_p;
+
+ if (!p2m_top[topidx])
+ continue;
+
+ if (p2m_top[topidx] == p2m_mid_missing)
+ continue;
+
+ mididx = p2m_mid_index(pfn);
+ mid_p = p2m_top[topidx][mididx];
+ if (!mid_p)
+ continue;
+ if ((mid_p == p2m_missing) || (mid_p == p2m_identity))
+ continue;
+
+ if ((unsigned long)mid_p == INVALID_P2M_ENTRY)
+ continue;
+
+ /* The old va. Rebase it on mfn_list */
+ if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) {
+ unsigned long *new;
+
+ new = &mfn_list[pfn];
+
+ copy_page(new, mid_p);
+ p2m_top[topidx][mididx] = &mfn_list[pfn];
+ p2m_top_mfn_p[topidx][mididx] = virt_to_mfn(&mfn_list[pfn]);

+ }
+ /* This should be the leafs allocated for identity from _brk. */
+ }
+ return (unsigned long)mfn_list;
+
+}
+#else
+unsigned long __init xen_revector_p2m_tree(void)
+{
+ return 0;
+}
+#endif
unsigned long get_phys_to_machine(unsigned long pfn)
{
unsigned topidx, mididx, idx;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 2230f57..bb5a810 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -45,6 +45,7 @@ void xen_hvm_init_shared_info(void);
void xen_unplug_emulated_devices(void);

void __init xen_build_dynamic_phys_to_machine(void);
+unsigned long __init xen_revector_p2m_tree(void);

void xen_init_irq_ops(void);
void xen_setup_timer(int cpu);
--
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/