From: Matt Fleming <matt.fleming@xxxxxxxxx>
There are various pieces of code in arch/x86 that require a page table
with an identity mapping. Make trampoline_pgd a proper kernel page
table, it currently only includes the kernel text and module space
mapping.
One new feature of trampoline_pgd is that it now has mappings for the
physical I/O device addresses, which are inserted at ioremap()
time. Some broken implementations of EFI firmware require these
mappings to always be around.
Signed-off-by: Matt Fleming <matt.fleming@xxxxxxxxx>
---
v2: Remove the 32-bit code for insert_identitity_mapping(). It's
unlikely that we'll successfully be able to map physical I/O addresses
because they'll probably be above PAGE_OFFSET, e.g. on machines with
multi-gigabytes of RAM. Since there's no in-kernel user of these
mappings on x86 (unlike on x86-64 where we work around the ASUS
firmware bug) just delete the code.
Also, add a check in insert_identity_mapping() to ensure we don't try
to insert any mappings above the x86-64 memory map guard hole.
arch/x86/mm/init_64.c | 9 +++-
arch/x86/mm/ioremap.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++
arch/x86/realmode/init.c | 17 +++++++-
3 files changed, 128 insertions(+), 3 deletions(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 2b6b4a3..fd4404f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -108,13 +108,13 @@ void sync_global_pgds(unsigned long start, unsigned long end)
for (address = start; address <= end; address += PGDIR_SIZE) {
const pgd_t *pgd_ref = pgd_offset_k(address);
struct page *page;
+ pgd_t *pgd;
if (pgd_none(*pgd_ref))
continue;
spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
- pgd_t *pgd;
spinlock_t *pgt_lock;
pgd = (pgd_t *)page_address(page) + pgd_index(address);
@@ -130,6 +130,13 @@ void sync_global_pgds(unsigned long start, unsigned long end)
spin_unlock(pgt_lock);
}
+
+ pgd = __va(real_mode_header->trampoline_pgd);
+ pgd += pgd_index(address);
+
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+
spin_unlock(&pgd_lock);
}
}
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 78fe3f1..e190f7b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -50,6 +50,107 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
return err;
}
+#ifdef CONFIG_X86_64
+static void ident_pte_range(unsigned long paddr, unsigned long vaddr,
+ pmd_t *ppmd, pmd_t *vpmd, unsigned long end)
+{
+ pte_t *ppte = pte_offset_kernel(ppmd, paddr);
+ pte_t *vpte = pte_offset_kernel(vpmd, vaddr);
+
+ do {
+ set_pte(ppte, *vpte);
+ } while (ppte++, vpte++, vaddr += PAGE_SIZE, vaddr != end);
+}
+
+static int ident_pmd_range(unsigned long paddr, unsigned long vaddr,
+ pud_t *ppud, pud_t *vpud, unsigned long end)
+{
+ pmd_t *ppmd = pmd_offset(ppud, paddr);
+ pmd_t *vpmd = pmd_offset(vpud, vaddr);
+ unsigned long next;
+
+ do {
+ next = pmd_addr_end(vaddr, end);
+
+ if (!pmd_present(*ppmd)) {
+ pte_t *ppte = (pte_t *)get_zeroed_page(GFP_KERNEL);
+ if (!ppte)
+ return 1;
+
+ set_pmd(ppmd, __pmd(_KERNPG_TABLE | __pa(ppte)));
+ }
+
+ ident_pte_range(paddr, vaddr, ppmd, vpmd, next);
+ } while (ppmd++, vpmd++, vaddr = next, vaddr != end);
+
+ return 0;
+}
+
+static int ident_pud_range(unsigned long paddr, unsigned long vaddr,
+ pgd_t *ppgd, pgd_t *vpgd, unsigned long end)
+{
+ pud_t *ppud = pud_offset(ppgd, paddr);
+ pud_t *vpud = pud_offset(vpgd, vaddr);
+ unsigned long next;
+
+ do {
+ next = pud_addr_end(vaddr, end);
+
+ if (!pud_present(*ppud)) {
+ pmd_t *ppmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+ if (!ppmd)
+ return 1;
+
+ set_pud(ppud, __pud(_KERNPG_TABLE | __pa(ppmd)));
+ }
+
+ if (ident_pmd_range(paddr, vaddr, ppud, vpud, next))
+ return 1;
+ } while (ppud++, vpud++, vaddr = next, vaddr != end);
+
+ return 0;
+}
+
+static int insert_identity_mapping(resource_size_t paddr, unsigned long vaddr,
+ unsigned long size)
+{
+ unsigned long end = vaddr + size;
+ unsigned long next;
+ pgd_t *vpgd, *ppgd;
+
+ /* Don't map over the guard hole. */
+ if (paddr >= 0x800000000000 || paddr + size > 0x800000000000)
+ return 1;
+
+ ppgd = __va(real_mode_header->trampoline_pgd) + pgd_index(paddr);
+
+ vpgd = pgd_offset_k(vaddr);
+ do {
+ next = pgd_addr_end(vaddr, end);
+
+ if (!pgd_present(*ppgd)) {
+ pud_t *ppud = (pud_t *)get_zeroed_page(GFP_KERNEL);
+ if (!ppud)
+ return 1;
+
+ set_pgd(ppgd, __pgd(_KERNPG_TABLE | __pa(ppud)));
+ }
+
+ if (ident_pud_range(paddr, vaddr, ppgd, vpgd, next))
+ return 1;
+ } while (ppgd++, vpgd++, vaddr = next, vaddr != end);
+
+ return 0;
+}
+#else
+static inline int insert_identity_mapping(resource_size_t paddr,
+ unsigned long vaddr,
+ unsigned long size)
+{
+ return 0;
+}
+#endif /* CONFIG_X86_64 */
+
/*
* Remap an arbitrary physical address space into the kernel virtual
* address space. Needed when the kernel wants to access high addresses
@@ -163,6 +264,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
ret_addr = (void __iomem *) (vaddr + offset);
mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
+ if (insert_identity_mapping(phys_addr, vaddr, size))
+ printk(KERN_WARNING "ioremap: unable to map 0x%llx in identity pagetable\n",
+ (unsigned long long)phys_addr);
+
/*
* Check if the request spans more than any BAR in the iomem resource
* tree.
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index cbca565..8e6ab61 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -78,8 +78,21 @@ void __init setup_real_mode(void)
*trampoline_cr4_features = read_cr4();
trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
- trampoline_pgd[0] = __pa(level3_ident_pgt) + _KERNPG_TABLE;
- trampoline_pgd[511] = __pa(level3_kernel_pgt) + _KERNPG_TABLE;
+
+ /*
+ * Create an identity mapping for all of physical memory.
+ */
+ for (i = 0; i <= pgd_index(max_pfn << PAGE_SHIFT); i++) {
+ int index = pgd_index(PAGE_OFFSET) + i;
+
+ trampoline_pgd[i] = (u64)pgd_val(swapper_pg_dir[index]);
+ }
+
+ /*
+ * Copy the upper-half of the kernel pages tables.
+ */
+ for (i = pgd_index(PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+ trampoline_pgd[i] = (u64)pgd_val(swapper_pg_dir[i]);
#endif
}
--
1.7.11.4
--
To unsubscribe from this list: send the line "unsubscribe linux-efi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
