mm/memory_hotplug: add pgprot_t to mhp_params

devm_memremap_pages() is currently used by the PCI P2PDMA code to create
struct page mappings for IO memory.  At present, these mappings are
created with PAGE_KERNEL which implies setting the PAT bits to be WB.
However, on x86, an mtrr register will typically override this and force
the cache type to be UC-.  In the case firmware doesn't set this
register it is effectively WB and will typically result in a machine
check exception when it's accessed.

Other arches are not currently likely to function correctly seeing they
don't have any MTRR registers to fall back on.

To solve this, provide a way to specify the pgprot value explicitly to
arch_add_memory().

Of the arches that support MEMORY_HOTPLUG: x86_64, and arm64 need a
simple change to pass the pgprot_t down to their respective functions
which set up the page tables.  For x86_32, set the page tables
explicitly using _set_memory_prot() (seeing they are already mapped).

For ia64, s390 and sh, reject anything but PAGE_KERNEL settings -- this
should be fine, for now, seeing these architectures don't support
ZONE_DEVICE.

A check in __add_pages() is also added to ensure the pgprot parameter
was set for all arches.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Eric Badger <ebadger@gigaio.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Link: http://lkml.kernel.org/r/20200306170846.9333-7-logang@deltatee.comSigned-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/arm64/mm/mmu.c

@@ -1382,7 +1382,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
-			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
+			     size, params->pgprot, __pgd_pgtable_alloc,
+			     flags);
 
 	memblock_clear_nomap(start, size);
 

arch/ia64/mm/init.c

@@ -676,6 +676,9 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
+	if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot))
+		return -EINVAL;
+
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	if (ret)
 		printk("%s: Problem encountered in __add_pages() as ret=%d\n",

arch/powerpc/mm/mem.c

@@ -132,7 +132,8 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
 	resize_hpt_for_hotplug(memblock_phys_mem_size());
 
 	start = (unsigned long)__va(start);
-	rc = create_section_mapping(start, start + size, nid, PAGE_KERNEL);
+	rc = create_section_mapping(start, start + size, nid,
+				    params->pgprot);
 	if (rc) {
 		pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
 			start, start + size, rc);

arch/s390/mm/init.c

@@ -277,6 +277,9 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	if (WARN_ON_ONCE(params->altmap))
 		return -EINVAL;
 
+	if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot))
+		return -EINVAL;
+
 	rc = vmem_add_mapping(start, size);
 	if (rc)
 		return rc;

arch/sh/mm/init.c

@@ -412,6 +412,9 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
+	if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot)
+		return -EINVAL;
+
 	/* We only have ZONE_NORMAL, so this is easy.. */
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	if (unlikely(ret))

arch/x86/mm/init_32.c

@@ -824,6 +824,18 @@ int arch_add_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
+	int ret;
+
+	/*
+	 * The page tables were already mapped at boot so if the caller
+	 * requests a different mapping type then we must change all the
+	 * pages with __set_memory_prot().
+	 */
+	if (params->pgprot.pgprot != PAGE_KERNEL.pgprot) {
+		ret = __set_memory_prot(start, nr_pages, params->pgprot);
+		if (ret)
+			return ret;
+	}
 
 	return __add_pages(nid, start_pfn, nr_pages, params);
 }

arch/x86/mm/init_64.c

@@ -867,7 +867,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	init_memory_mapping(start, start + size, PAGE_KERNEL);
+	init_memory_mapping(start, start + size, params->pgprot);
 
 	return add_pages(nid, start_pfn, nr_pages, params);
 }

include/linux/memory_hotplug.h

@@ -60,9 +60,12 @@ enum {
 /*
  * Extended parameters for memory hotplug:
  * altmap: alternative allocator for memmap array (optional)
+ * pgprot: page protection flags to apply to newly created page tables
+ *	(required)
  */
 struct mhp_params {
 	struct vmem_altmap *altmap;
+	pgprot_t pgprot;
 };
 
 /*

mm/memory_hotplug.c

@@ -311,6 +311,9 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 	int err;
 	struct vmem_altmap *altmap = params->altmap;
 
+	if (WARN_ON_ONCE(!params->pgprot.pgprot))
+		return -EINVAL;
+
 	err = check_hotplug_memory_addressable(pfn, nr_pages);
 	if (err)
 		return err;
@@ -1002,7 +1005,7 @@ static int online_memory_block(struct memory_block *mem, void *arg)
  */
 int __ref add_memory_resource(int nid, struct resource *res)
 {
-	struct mhp_params params = {};
+	struct mhp_params params = { .pgprot = PAGE_KERNEL };
 	u64 start, size;
 	bool new_node = false;
 	int ret;

mm/memremap.c

@@ -189,8 +189,8 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		 * We do not want any optional features only our own memmap
 		 */
 		.altmap = pgmap_altmap(pgmap),
+		.pgprot = PAGE_KERNEL,
 	};
-	pgprot_t pgprot = PAGE_KERNEL;
 	int error, is_ram;
 	bool need_devmap_managed = true;
 
@@ -282,8 +282,8 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
-			resource_size(res));
+	error = track_pfn_remap(NULL, &params.pgprot, PHYS_PFN(res->start),
+				0, resource_size(res));
 	if (error)
 		goto err_pfn_remap;