xen: move p2m list if conflicting with e820 map

Check whether the hypervisor supplied p2m list is placed at a location
which is conflicting with the target E820 map. If this is the case
relocate it to a new area unused up to now and compliant to the E820
map.

As the p2m list might by huge (up to several GB) and is required to be
mapped virtually, set up a temporary mapping for the copied list.

For pvh domains just delete the p2m related information from start
info instead of reserving the p2m memory, as we don't need it at all.

For 32 bit kernels adjust the memblock_reserve() parameters in order
to cover the page tables only. This requires to memblock_reserve() the
start_info page on it's own.

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Konrad Rzeszutek Wilk <Konrad.wilk@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

1 files changed, 235 insertions, 22 deletions

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index a36e7b462640..2c50b445884e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1094,6 +1094,16 @@ static void xen_exit_mmap(struct mm_struct *mm)
 
 static void xen_post_allocator_init(void);
 
+static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+	struct mmuext_op op;
+
+	op.cmd = cmd;
+	op.arg1.mfn = pfn_to_mfn(pfn);
+	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
+		BUG();
+}
+
 #ifdef CONFIG_X86_64
 static void __init xen_cleanhighmap(unsigned long vaddr,
 				    unsigned long vaddr_end)
@@ -1129,10 +1139,12 @@ static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size)
 	memblock_free(paddr, size);
 }
 
-static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl)
+static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin)
 {
 	unsigned long pa = __pa(pgtbl) & PHYSICAL_PAGE_MASK;
 
+	if (unpin)
+		pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(pa));
 	ClearPagePinned(virt_to_page(__va(pa)));
 	xen_free_ro_pages(pa, PAGE_SIZE);
 }
@@ -1151,7 +1163,9 @@ static void __init xen_cleanmfnmap(unsigned long vaddr)
 	pmd_t *pmd;
 	pte_t *pte;
 	unsigned int i;
+	bool unpin;
 
+	unpin = (vaddr == 2 * PGDIR_SIZE);
 	set_pgd(pgd, __pgd(0));
 	do {
 		pud = pud_page + pud_index(va);
@@ -1168,22 +1182,24 @@ static void __init xen_cleanmfnmap(unsigned long vaddr)
 				xen_free_ro_pages(pa, PMD_SIZE);
 			} else if (!pmd_none(*pmd)) {
 				pte = pte_offset_kernel(pmd, va);
+				set_pmd(pmd, __pmd(0));
 				for (i = 0; i < PTRS_PER_PTE; ++i) {
 					if (pte_none(pte[i]))
 						break;
 					pa = pte_pfn(pte[i]) << PAGE_SHIFT;
 					xen_free_ro_pages(pa, PAGE_SIZE);
 				}
-				xen_cleanmfnmap_free_pgtbl(pte);
+				xen_cleanmfnmap_free_pgtbl(pte, unpin);
 			}
 			va += PMD_SIZE;
 			if (pmd_index(va))
 				continue;
-			xen_cleanmfnmap_free_pgtbl(pmd);
+			set_pud(pud, __pud(0));
+			xen_cleanmfnmap_free_pgtbl(pmd, unpin);
 		}
 
 	} while (pud_index(va) || pmd_index(va));
-	xen_cleanmfnmap_free_pgtbl(pud_page);
+	xen_cleanmfnmap_free_pgtbl(pud_page, unpin);
 }
 
 static void __init xen_pagetable_p2m_free(void)
@@ -1219,6 +1235,12 @@ static void __init xen_pagetable_p2m_free(void)
 	} else {
 		xen_cleanmfnmap(addr);
 	}
+}
+
+static void __init xen_pagetable_cleanhighmap(void)
+{
+	unsigned long size;
+	unsigned long addr;
 
 	/* At this stage, cleanup_highmap has already cleaned __ka space
 	 * from _brk_limit way up to the max_pfn_mapped (which is the end of
@@ -1251,6 +1273,8 @@ static void __init xen_pagetable_p2m_setup(void)
 
 #ifdef CONFIG_X86_64
 	xen_pagetable_p2m_free();
+
+	xen_pagetable_cleanhighmap();
 #endif
 	/* And revector! Bye bye old array */
 	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
@@ -1586,15 +1610,6 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 	native_set_pte(ptep, pte);
 }
 
-static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
-{
-	struct mmuext_op op;
-	op.cmd = cmd;
-	op.arg1.mfn = pfn_to_mfn(pfn);
-	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
-		BUG();
-}
-
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
 static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
@@ -2002,11 +2017,189 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	xen_pt_base = PFN_PHYS(pt_base);
 	xen_pt_size = (pt_end - pt_base) * PAGE_SIZE;
 	memblock_reserve(xen_pt_base, xen_pt_size);
-	/* protect xen_start_info */
-	memblock_reserve(__pa(xen_start_info), PAGE_SIZE);
+
 	/* Revector the xen_start_info */
 	xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
 }
+
+/*
+ * Read a value from a physical address.
+ */
+static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
+{
+	unsigned long *vaddr;
+	unsigned long val;
+
+	vaddr = early_memremap_ro(addr, sizeof(val));
+	val = *vaddr;
+	early_memunmap(vaddr, sizeof(val));
+	return val;
+}
+
+/*
+ * Translate a virtual address to a physical one without relying on mapped
+ * page tables.
+ */
+static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
+{
+	phys_addr_t pa;
+	pgd_t pgd;
+	pud_t pud;
+	pmd_t pmd;
+	pte_t pte;
+
+	pa = read_cr3();
+	pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) *
+						       sizeof(pgd)));
+	if (!pgd_present(pgd))
+		return 0;
+
+	pa = pgd_val(pgd) & PTE_PFN_MASK;
+	pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) *
+						       sizeof(pud)));
+	if (!pud_present(pud))
+		return 0;
+	pa = pud_pfn(pud) << PAGE_SHIFT;
+	if (pud_large(pud))
+		return pa + (vaddr & ~PUD_MASK);
+
+	pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) *
+						       sizeof(pmd)));
+	if (!pmd_present(pmd))
+		return 0;
+	pa = pmd_pfn(pmd) << PAGE_SHIFT;
+	if (pmd_large(pmd))
+		return pa + (vaddr & ~PMD_MASK);
+
+	pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) *
+						       sizeof(pte)));
+	if (!pte_present(pte))
+		return 0;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+
+	return pa | (vaddr & ~PAGE_MASK);
+}
+
+/*
+ * Find a new area for the hypervisor supplied p2m list and relocate the p2m to
+ * this area.
+ */
+void __init xen_relocate_p2m(void)
+{
+	phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys;
+	unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end;
+	int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud;
+	pte_t *pt;
+	pmd_t *pmd;
+	pud_t *pud;
+	pgd_t *pgd;
+	unsigned long *new_p2m;
+
+	size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+	n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
+	n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT;
+	n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT;
+	n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT;
+	n_frames = n_pte + n_pt + n_pmd + n_pud;
+
+	new_area = xen_find_free_area(PFN_PHYS(n_frames));
+	if (!new_area) {
+		xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n");
+		BUG();
+	}
+
+	/*
+	 * Setup the page tables for addressing the new p2m list.
+	 * We have asked the hypervisor to map the p2m list at the user address
+	 * PUD_SIZE. It may have done so, or it may have used a kernel space
+	 * address depending on the Xen version.
+	 * To avoid any possible virtual address collision, just use
+	 * 2 * PUD_SIZE for the new area.
+	 */
+	pud_phys = new_area;
+	pmd_phys = pud_phys + PFN_PHYS(n_pud);
+	pt_phys = pmd_phys + PFN_PHYS(n_pmd);
+	p2m_pfn = PFN_DOWN(pt_phys) + n_pt;
+
+	pgd = __va(read_cr3());
+	new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
+	for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
+		pud = early_memremap(pud_phys, PAGE_SIZE);
+		clear_page(pud);
+		for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD);
+		     idx_pmd++) {
+			pmd = early_memremap(pmd_phys, PAGE_SIZE);
+			clear_page(pmd);
+			for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD);
+			     idx_pt++) {
+				pt = early_memremap(pt_phys, PAGE_SIZE);
+				clear_page(pt);
+				for (idx_pte = 0;
+				     idx_pte < min(n_pte, PTRS_PER_PTE);
+				     idx_pte++) {
+					set_pte(pt + idx_pte,
+						pfn_pte(p2m_pfn, PAGE_KERNEL));
+					p2m_pfn++;
+				}
+				n_pte -= PTRS_PER_PTE;
+				early_memunmap(pt, PAGE_SIZE);
+				make_lowmem_page_readonly(__va(pt_phys));
+				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
+						  PFN_DOWN(pt_phys));
+				set_pmd(pmd + idx_pt,
+					__pmd(_PAGE_TABLE | pt_phys));
+				pt_phys += PAGE_SIZE;
+			}
+			n_pt -= PTRS_PER_PMD;
+			early_memunmap(pmd, PAGE_SIZE);
+			make_lowmem_page_readonly(__va(pmd_phys));
+			pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
+					  PFN_DOWN(pmd_phys));
+			set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+			pmd_phys += PAGE_SIZE;
+		}
+		n_pmd -= PTRS_PER_PUD;
+		early_memunmap(pud, PAGE_SIZE);
+		make_lowmem_page_readonly(__va(pud_phys));
+		pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys));
+		set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys));
+		pud_phys += PAGE_SIZE;
+	}
+
+	/* Now copy the old p2m info to the new area. */
+	memcpy(new_p2m, xen_p2m_addr, size);
+	xen_p2m_addr = new_p2m;
+
+	/* Release the old p2m list and set new list info. */
+	p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list));
+	BUG_ON(!p2m_pfn);
+	p2m_pfn_end = p2m_pfn + PFN_DOWN(size);
+
+	if (xen_start_info->mfn_list < __START_KERNEL_map) {
+		pfn = xen_start_info->first_p2m_pfn;
+		pfn_end = xen_start_info->first_p2m_pfn +
+			  xen_start_info->nr_p2m_frames;
+		set_pgd(pgd + 1, __pgd(0));
+	} else {
+		pfn = p2m_pfn;
+		pfn_end = p2m_pfn_end;
+	}
+
+	memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn));
+	while (pfn < pfn_end) {
+		if (pfn == p2m_pfn) {
+			pfn = p2m_pfn_end;
+			continue;
+		}
+		make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+		pfn++;
+	}
+
+	xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
+	xen_start_info->first_p2m_pfn =  PFN_DOWN(new_area);
+	xen_start_info->nr_p2m_frames = n_frames;
+}
+
 #else	/* !CONFIG_X86_64 */
 static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
 static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
@@ -2047,18 +2240,41 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 
+/*
+ * For 32 bit domains xen_start_info->pt_base is the pgd address which might be
+ * not the first page table in the page table pool.
+ * Iterate through the initial page tables to find the real page table base.
+ */
+static phys_addr_t xen_find_pt_base(pmd_t *pmd)
+{
+	phys_addr_t pt_base, paddr;
+	unsigned pmdidx;
+
+	pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd));
+
+	for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++)
+		if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) {
+			paddr = m2p(pmd[pmdidx].pmd);
+			pt_base = min(pt_base, paddr);
+		}
+
+	return pt_base;
+}
+
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 
+	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
+
+	xen_pt_base = xen_find_pt_base(kernel_pmd);
+	xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE;
+
 	initial_kernel_pmd =
 		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
-				  xen_start_info->nr_pt_frames * PAGE_SIZE +
-				  512*1024);
+	max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024);
 
-	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	copy_page(initial_kernel_pmd, kernel_pmd);
 
 	xen_map_identity_early(initial_kernel_pmd, max_pfn);
@@ -2077,9 +2293,6 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 			  PFN_DOWN(__pa(initial_page_table)));
 	xen_write_cr3(__pa(initial_page_table));
 
-	xen_pt_base = __pa(xen_start_info->pt_base);
-	xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE;
-
 	memblock_reserve(xen_pt_base, xen_pt_size);
 }
 #endif	/* CONFIG_X86_64 */