access_process_vm device memory infrastructure

In order to be able to debug things like the X server and programs using
the PPC Cell SPUs, the debugger needs to be able to access device memory
through ptrace and /proc/pid/mem.

This patch:

Add the generic_access_phys access function and put the hooks in place
to allow access_process_vm to access device or PPC Cell SPU memory.

[riel@redhat.com: Add documentation for the vm_ops->access function]
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Benjamin Herrensmidt <benh@kernel.crashing.org>
Cc: Dave Airlie <airlied@linux.ie>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/filesystems/Locking

@@ -510,6 +510,7 @@ prototypes:
 	void (*close)(struct vm_area_struct*);
 	int (*fault)(struct vm_area_struct*, struct vm_fault *);
 	int (*page_mkwrite)(struct vm_area_struct *, struct page *);
+	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 
 locking rules:
 		BKL	mmap_sem	PageLocked(page)
@@ -517,6 +518,7 @@ open:		no	yes
 close:		no	yes
 fault:		no	yes
 page_mkwrite:	no	yes		no
+access:		no	yes
 
 	->page_mkwrite() is called when a previously read-only page is
 about to become writeable. The file system is responsible for
@@ -525,6 +527,11 @@ taking to lock out truncate, the page range should be verified to be
 within i_size. The page mapping should also be checked that it is not
 NULL.
 
+	->access() is called when get_user_pages() fails in
+acces_process_vm(), typically used to debug a process through
+/proc/pid/mem or ptrace.  This function is needed only for
+VM_IO | VM_PFNMAP VMAs.
+
 ================================================================================
 			Dubious stuff
 

arch/Kconfig

@@ -31,6 +31,9 @@ config KRETPROBES
 	def_bool y
 	depends on KPROBES && HAVE_KRETPROBES
 
+config HAVE_IOREMAP_PROT
+	def_bool n
+
 config HAVE_KPROBES
 	def_bool n
 

arch/x86/Kconfig

@@ -21,6 +21,7 @@ config X86
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
+	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_DYNAMIC_FTRACE

arch/x86/mm/ioremap.c

@@ -330,6 +330,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
 	return (void __iomem *)ret;
 }
 
+void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
+				unsigned long prot_val)
+{
+	return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK),
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_prot);
+
 /**
  * iounmap - Free a IO remapping
  * @addr: virtual address from ioremap_*

include/asm-x86/io_32.h

@@ -110,6 +110,8 @@ static inline void *phys_to_virt(unsigned long address)
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+				unsigned long prot_val);
 
 /*
  * The default ioremap() behavior is non-cached:

include/asm-x86/io_64.h

@@ -175,6 +175,8 @@ extern void early_iounmap(void *addr, unsigned long size);
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+				unsigned long prot_val);
 
 /*
  * The default ioremap() behavior is non-cached:

include/linux/mm.h

@@ -170,6 +170,12 @@ struct vm_operations_struct {
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
 	int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page);
+
+	/* called by access_process_vm when get_user_pages() fails, typically
+	 * for use by special VMAs that can switch between memory and hardware
+	 */
+	int (*access)(struct vm_area_struct *vma, unsigned long addr,
+		      void *buf, int len, int write);
 #ifdef CONFIG_NUMA
 	/*
 	 * set_policy() op must add a reference to any non-NULL @new mempolicy
@@ -771,6 +777,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
 			struct vm_area_struct *vma);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows);
+int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
+			void *buf, int len, int write);
 
 static inline void unmap_shared_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen)

mm/memory.c

@@ -2751,6 +2751,86 @@ int in_gate_area_no_task(unsigned long addr)
 
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+static resource_size_t follow_phys(struct vm_area_struct *vma,
+			unsigned long address, unsigned int flags,
+			unsigned long *prot)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *ptep, pte;
+	spinlock_t *ptl;
+	resource_size_t phys_addr = 0;
+	struct mm_struct *mm = vma->vm_mm;
+
+	VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP)));
+
+	pgd = pgd_offset(mm, address);
+	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+		goto no_page_table;
+
+	pud = pud_offset(pgd, address);
+	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+		goto no_page_table;
+
+	pmd = pmd_offset(pud, address);
+	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+		goto no_page_table;
+
+	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
+	if (pmd_huge(*pmd))
+		goto no_page_table;
+
+	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	if (!ptep)
+		goto out;
+
+	pte = *ptep;
+	if (!pte_present(pte))
+		goto unlock;
+	if ((flags & FOLL_WRITE) && !pte_write(pte))
+		goto unlock;
+	phys_addr = pte_pfn(pte);
+	phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */
+
+	*prot = pgprot_val(pte_pgprot(pte));
+
+unlock:
+	pte_unmap_unlock(ptep, ptl);
+out:
+	return phys_addr;
+no_page_table:
+	return 0;
+}
+
+int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
+			void *buf, int len, int write)
+{
+	resource_size_t phys_addr;
+	unsigned long prot = 0;
+	void *maddr;
+	int offset = addr & (PAGE_SIZE-1);
+
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		return -EINVAL;
+
+	phys_addr = follow_phys(vma, addr, write, &prot);
+
+	if (!phys_addr)
+		return -EINVAL;
+
+	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
+	if (write)
+		memcpy_toio(maddr + offset, buf, len);
+	else
+		memcpy_fromio(buf, maddr + offset, len);
+	iounmap(maddr);
+
+	return len;
+}
+#endif
+
 /*
  * Access another process' address space.
  * Source/target buffer must be kernel space,
@@ -2760,7 +2840,6 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 {
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
-	struct page *page;
 	void *old_buf = buf;
 
 	mm = get_task_mm(tsk);
@@ -2772,12 +2851,27 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 	while (len) {
 		int bytes, ret, offset;
 		void *maddr;
+		struct page *page = NULL;
 
 		ret = get_user_pages(tsk, mm, addr, 1,
 				write, 1, &page, &vma);
+		if (ret <= 0) {
+			/*
+			 * Check if this is a VM_IO | VM_PFNMAP VMA, which
+			 * we can access using slightly different code.
+			 */
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+			vma = find_vma(mm, addr);
+			if (!vma)
+				break;
+			if (vma->vm_ops && vma->vm_ops->access)
+				ret = vma->vm_ops->access(vma, addr, buf,
+							  len, write);
 			if (ret <= 0)
+#endif
 				break;
-
+			bytes = ret;
+		} else {
 			bytes = len;
 			offset = addr & (PAGE_SIZE-1);
 			if (bytes > PAGE_SIZE-offset)
@@ -2794,6 +2888,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 			}
 			kunmap(page);
 			page_cache_release(page);
+		}
 		len -= bytes;
 		buf += bytes;
 		addr += bytes;