summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorJérôme Glisse <jglisse@redhat.com>2017-09-08 16:11:43 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-09-08 18:26:46 -0700
commit5042db43cc26f51eed51c56192e2c2317e44315f (patch)
treed4115135f5aad384fb173537a2c397170a86f29a /mm
parent3072e413e305e353cd4654f8a57d953b66e85bf3 (diff)
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory
HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig11
-rw-r--r--mm/memory.c61
-rw-r--r--mm/memory_hotplug.c10
-rw-r--r--mm/mprotect.c14
4 files changed, 93 insertions, 3 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 254db99f263d..ec27855db133 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -676,7 +676,7 @@ config ARCH_HAS_ZONE_DEVICE
bool
config ZONE_DEVICE
- bool "Device memory (pmem, etc...) hotplug support"
+ bool "Device memory (pmem, HMM, etc...) hotplug support"
depends on MEMORY_HOTPLUG
depends on MEMORY_HOTREMOVE
depends on SPARSEMEM_VMEMMAP
@@ -717,6 +717,15 @@ config HMM_MIRROR
page tables (at PAGE_SIZE granularity), and must be able to recover from
the resulting potential page faults.
+config DEVICE_PRIVATE
+ bool "Unaddressable device memory (GPU memory, ...)"
+ depends on ARCH_HAS_HMM
+
+ help
+ Allows creation of struct pages to represent unaddressable device
+ memory; i.e., memory that is only accessible from the device (or
+ group of devices). You likely also want to select HMM_MIRROR.
+
config FRAME_VECTOR
bool
diff --git a/mm/memory.c b/mm/memory.c
index 886033b95fd2..079eeac0b009 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -49,6 +49,7 @@
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
+#include <linux/memremap.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
@@ -956,6 +957,35 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte = pte_swp_mksoft_dirty(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
+ } else if (is_device_private_entry(entry)) {
+ page = device_private_entry_to_page(entry);
+
+ /*
+ * Update rss count even for unaddressable pages, as
+ * they should treated just like normal pages in this
+ * respect.
+ *
+ * We will likely want to have some new rss counters
+ * for unaddressable pages, at some point. But for now
+ * keep things as they are.
+ */
+ get_page(page);
+ rss[mm_counter(page)]++;
+ page_dup_rmap(page, false);
+
+ /*
+ * We do not preserve soft-dirty information, because so
+ * far, checkpoint/restore is the only feature that
+ * requires that. And checkpoint/restore does not work
+ * when a device driver is involved (you cannot easily
+ * save and restore device driver state).
+ */
+ if (is_write_device_private_entry(entry) &&
+ is_cow_mapping(vm_flags)) {
+ make_device_private_entry_read(&entry);
+ pte = swp_entry_to_pte(entry);
+ set_pte_at(src_mm, addr, src_pte, pte);
+ }
}
goto out_set_pte;
}
@@ -1274,6 +1304,29 @@ again:
}
continue;
}
+
+ entry = pte_to_swp_entry(ptent);
+ if (non_swap_entry(entry) && is_device_private_entry(entry)) {
+ struct page *page = device_private_entry_to_page(entry);
+
+ if (unlikely(details && details->check_mapping)) {
+ /*
+ * unmap_shared_mapping_pages() wants to
+ * invalidate cache without truncating:
+ * unmap shared but keep private pages.
+ */
+ if (details->check_mapping !=
+ page_rmapping(page))
+ continue;
+ }
+
+ pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+ rss[mm_counter(page)]--;
+ page_remove_rmap(page, false);
+ put_page(page);
+ continue;
+ }
+
/* If details->check_mapping, we leave swap entries. */
if (unlikely(details))
continue;
@@ -2776,6 +2829,14 @@ int do_swap_page(struct vm_fault *vmf)
if (is_migration_entry(entry)) {
migration_entry_wait(vma->vm_mm, vmf->pmd,
vmf->address);
+ } else if (is_device_private_entry(entry)) {
+ /*
+ * For un-addressable device memory we call the pgmap
+ * fault handler callback. The callback must migrate
+ * the page back to some CPU accessible page.
+ */
+ ret = device_private_entry_fault(vma, vmf->address, entry,
+ vmf->flags, vmf->pmd);
} else if (is_hwpoison_entry(entry)) {
ret = VM_FAULT_HWPOISON;
} else {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1f92fb84770d..e882cb6da994 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -99,7 +99,7 @@ void mem_hotplug_done(void)
/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
- struct resource *res;
+ struct resource *res, *conflict;
res = kzalloc(sizeof(struct resource), GFP_KERNEL);
if (!res)
return ERR_PTR(-ENOMEM);
@@ -108,7 +108,13 @@ static struct resource *register_memory_resource(u64 start, u64 size)
res->start = start;
res->end = start + size - 1;
res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
- if (request_resource(&iomem_resource, res) < 0) {
+ conflict = request_resource_conflict(&iomem_resource, res);
+ if (conflict) {
+ if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) {
+ pr_debug("Device unaddressable memory block "
+ "memory hotplug at %#010llx !\n",
+ (unsigned long long)start);
+ }
pr_debug("System RAM resource %pR cannot be added\n", res);
kfree(res);
return ERR_PTR(-EEXIST);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a1bfe9545770..6d3e2f082290 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -125,6 +125,20 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
pages++;
}
+
+ if (is_write_device_private_entry(entry)) {
+ pte_t newpte;
+
+ /*
+ * We do not preserve soft-dirtiness. See
+ * copy_one_pte() for explanation.
+ */
+ make_device_private_entry_read(&entry);
+ newpte = swp_entry_to_pte(entry);
+ set_pte_at(mm, addr, pte, newpte);
+
+ pages++;
+ }
}
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();