4 files changed, 69 insertions, 78 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index d51cf5f4e45e..1697e903bbf2 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -103,8 +103,7 @@ static bool store_updates_sp(unsigned int inst)
  */
 
 static int
-__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code,
-		int pkey)
+__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code)
 {
 	/*
 	 * If we are in kernel mode, bail out with a SEGV, this will
@@ -114,18 +113,17 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code,
 	if (!user_mode(regs))
 		return SIGSEGV;
 
-	_exception_pkey(SIGSEGV, regs, si_code, address, pkey);
+	_exception(SIGSEGV, regs, si_code, address);
 
 	return 0;
 }
 
 static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long address)
 {
-	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR, 0);
+	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR);
 }
 
-static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
-			int pkey)
+static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -135,54 +133,61 @@ static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
 	 */
 	up_read(&mm->mmap_sem);
 
-	return __bad_area_nosemaphore(regs, address, si_code, pkey);
+	return __bad_area_nosemaphore(regs, address, si_code);
 }
 
 static noinline int bad_area(struct pt_regs *regs, unsigned long address)
 {
-	return __bad_area(regs, address, SEGV_MAPERR, 0);
+	return __bad_area(regs, address, SEGV_MAPERR);
 }
 
 static int bad_key_fault_exception(struct pt_regs *regs, unsigned long address,
 				    int pkey)
 {
-	return __bad_area_nosemaphore(regs, address, SEGV_PKUERR, pkey);
+	/*
+	 * If we are in kernel mode, bail out with a SEGV, this will
+	 * be caught by the assembly which will restore the non-volatile
+	 * registers before calling bad_page_fault()
+	 */
+	if (!user_mode(regs))
+		return SIGSEGV;
+
+	_exception_pkey(regs, address, pkey);
+
+	return 0;
 }
 
 static noinline int bad_access(struct pt_regs *regs, unsigned long address)
 {
-	return __bad_area(regs, address, SEGV_ACCERR, 0);
+	return __bad_area(regs, address, SEGV_ACCERR);
 }
 
 static int do_sigbus(struct pt_regs *regs, unsigned long address,
 		     vm_fault_t fault)
 {
-	siginfo_t info;
-	unsigned int lsb = 0;
-
 	if (!user_mode(regs))
 		return SIGBUS;
 
 	current->thread.trap_nr = BUS_ADRERR;
-	clear_siginfo(&info);
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void __user *)address;
 #ifdef CONFIG_MEMORY_FAILURE
 	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+		unsigned int lsb = 0; /* shutup gcc */
+
 		pr_err("MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
 			current->comm, current->pid, address);
-		info.si_code = BUS_MCEERR_AR;
+
+		if (fault & VM_FAULT_HWPOISON_LARGE)
+			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+		if (fault & VM_FAULT_HWPOISON)
+			lsb = PAGE_SHIFT;
+
+		force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb,
+				 current);
+		return 0;
 	}
 
-	if (fault & VM_FAULT_HWPOISON_LARGE)
-		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
-	if (fault & VM_FAULT_HWPOISON)
-		lsb = PAGE_SHIFT;
 #endif
-	info.si_addr_lsb = lsb;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, current);
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 51ce091914f9..7a9886f98b0c 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -308,55 +308,6 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 {
 }
 
-/*
- * We do not have access to the sparsemem vmemmap, so we fallback to
- * walking the list of sparsemem blocks which we already maintain for
- * the sake of crashdump. In the long run, we might want to maintain
- * a tree if performance of that linear walk becomes a problem.
- *
- * realmode_pfn_to_page functions can fail due to:
- * 1) As real sparsemem blocks do not lay in RAM continously (they
- * are in virtual address space which is not available in the real mode),
- * the requested page struct can be split between blocks so get_page/put_page
- * may fail.
- * 2) When huge pages are used, the get_page/put_page API will fail
- * in real mode as the linked addresses in the page struct are virtual
- * too.
- */
-struct page *realmode_pfn_to_page(unsigned long pfn)
-{
-	struct vmemmap_backing *vmem_back;
-	struct page *page;
-	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
-	unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
-
-	for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
-		if (pg_va < vmem_back->virt_addr)
-			continue;
-
-		/* After vmemmap_list entry free is possible, need check all */
-		if ((pg_va + sizeof(struct page)) <=
-				(vmem_back->virt_addr + page_size)) {
-			page = (struct page *) (vmem_back->phys + pg_va -
-				vmem_back->virt_addr);
-			return page;
-		}
-	}
-
-	/* Probably that page struct is split between real pages */
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
-
-#else
-
-struct page *realmode_pfn_to_page(unsigned long pfn)
-{
-	struct page *page = pfn_to_page(pfn);
-	return page;
-}
-EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
-
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index c9ee9e23845f..56c2234cc6ae 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -18,11 +18,15 @@
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
+#include <linux/sizes.h>
 #include <asm/mmu_context.h>
 #include <asm/pte-walk.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
+#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY	0x1
+#define MM_IOMMU_TABLE_GROUP_PAGE_MASK	~(SZ_4K - 1)
+
 struct mm_iommu_table_group_mem_t {
 	struct list_head next;
 	struct rcu_head rcu;
@@ -263,6 +267,9 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
 		if (!page)
 			continue;
 
+		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
+			SetPageDirty(page);
+
 		put_page(page);
 		mem->hpas[i] = 0;
 	}
@@ -360,7 +367,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
 
 struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries)
@@ -390,7 +396,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (pageshift > mem->pageshift)
 		return -EFAULT;
 
-	*hpa = *va | (ua & ~PAGE_MASK);
+	*hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
 
 	return 0;
 }
@@ -413,11 +419,31 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (!pa)
 		return -EFAULT;
 
-	*hpa = *pa | (ua & ~PAGE_MASK);
+	*hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm);
+
+extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
+{
+	struct mm_iommu_table_group_mem_t *mem;
+	long entry;
+	void *va;
+	unsigned long *pa;
+
+	mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE);
+	if (!mem)
+		return;
+
+	entry = (ua - mem->ua) >> PAGE_SHIFT;
+	va = &mem->hpas[entry];
+
+	pa = (void *) vmalloc_to_phys(va);
+	if (!pa)
+		return;
+
+	*pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
+}
 
 long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
 {
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 6a6399108072..6a23b9ebd2a1 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -834,6 +834,15 @@ EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid);
 /*
  * Flush partition scoped translations from LPID (=LPIDR)
  */
+void radix__flush_tlb_lpid(unsigned int lpid)
+{
+	_tlbie_lpid(lpid, RIC_FLUSH_ALL);
+}
+EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid);
+
+/*
+ * Flush partition scoped translations from LPID (=LPIDR)
+ */
 void radix__local_flush_tlb_lpid(unsigned int lpid)
 {
 	_tlbiel_lpid(lpid, RIC_FLUSH_ALL);