[PATCH v3 6/7] mm/memory_hotplug: Add pgprot_t to mhp_params

From: Logan Gunthorpe <logang@deltatee.com>
Date: 2020-02-21 18:25:39
Also in: linux-arm-kernel, linux-mm, linux-s390, linux-sh, lkml, platform-driver-x86
Subsystem: arm64 port (aarch64 architecture), linux for powerpc (32-bit and 64-bit), memory hot(un)plug, memory management, s390 architecture, superh, the rest, x86 architecture (32-bit and 64-bit), x86 mm · Maintainers: Catalin Marinas, Will Deacon, Madhavan Srinivasan, Michael Ellerman, David Hildenbrand, Oscar Salvador, Andrew Morton, Heiko Carstens, Vasily Gorbik, Alexander Gordeev, Yoshinori Sato, Rich Felker, John Paul Adrian Glaubitz, Linus Torvalds, Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, Andy Lutomirski, Peter Zijlstra

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.

Cc: Dan Williams <redacted>
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: David Hildenbrand <redacted>
Acked-by: Michal Hocko <mhocko@suse.com>
---
 arch/arm64/mm/mmu.c            | 3 ++-
 arch/ia64/mm/init.c            | 3 +++
 arch/powerpc/mm/mem.c          | 3 ++-
 arch/s390/mm/init.c            | 3 +++
 arch/sh/mm/init.c              | 3 +++
 arch/x86/mm/init_32.c          | 5 +++++
 arch/x86/mm/init_64.c          | 2 +-
 include/linux/memory_hotplug.h | 2 ++
 mm/memory_hotplug.c            | 5 ++++-
 mm/memremap.c                  | 6 +++---
 10 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index ee37bca8aba8..ea3fa844a8a2 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c

@@ -1058,7 +1058,8 @@ 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);

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 97bbc23ea1e3..d637b4ea3147 100644
--- a/arch/ia64/mm/init.c
+++ b/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",

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 19b1da5d7eca..832412bc7fad 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c

@@ -138,7 +138,8 @@ 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);

diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index e9e4a7abd0cc..87b2d024e75a 100644
--- a/arch/s390/mm/init.c
+++ b/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;

diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index e5114c053364..b9de2d4fa57e 100644
--- a/arch/sh/mm/init.c
+++ b/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))

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index e25a4218e6ff..96d8e4fb1cc8 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c

@@ -858,6 +858,11 @@ 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;
+
+	ret = _set_memory_prot(start, nr_pages, params->pgprot);
+	if (ret)
+		return ret;
 
 	return __add_pages(nid, start_pfn, nr_pages, params);
 }

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9e7692080dda..230240af38b4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c

@@ -868,7 +868,7 @@ 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);
 }

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index c5df1b3dada0..30d6c1b8847e 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h

@@ -56,9 +56,11 @@ enum {
 /*
  * Extended parameters for memory hotplug:
  * altmap: alternative allocator for memmap array (optional)
+ * pgprot: page protection flags to apply to newly added page tables (required)
  */
 struct mhp_params {
 	struct vmem_altmap *altmap;
+	pgprot_t pgprot;
 };
 
 /*

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c69469e1b40e..d7d4806ad81b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c

@@ -305,6 +305,9 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 	unsigned long nr, start_sec, end_sec;
 	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;

@@ -993,7 +996,7 @@ 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;

diff --git a/mm/memremap.c b/mm/memremap.c
index 6891a503a078..06742372a203 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c

@@ -166,8 +166,8 @@ 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;

@@ -255,8 +255,8 @@ 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;

-- 
2.20.1

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help