From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= <jglisse@redhat.com>
Date: Fri, 8 Sep 2017 16:12:28 -0700
Subject: mm/hmm: add new helper to hotplug CDM memory region
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Git-commit: d3df0a423397c9a1ae05c3857e8c04240dd85e68
Patch-mainline: v4.14-rc1
References: VM Functionality, FATE#323338, bsc#1047814
Unlike unaddressable memory, coherent device memory has a real resource
associated with it on the system (as CPU can address it). Add a new
helper to hotplug such memory within the HMM framework.
Link: http://lkml.kernel.org/r/20170817000548.32038-20-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
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: Ross Zwisler <ross.zwisler@linux.intel.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>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/hmm.h | 3 +
mm/hmm.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++++---
2 files changed, 86 insertions(+), 5 deletions(-)
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -443,6 +443,9 @@ struct hmm_devmem {
struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
struct device *device,
unsigned long size);
+struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
+ struct device *device,
+ struct resource *res);
void hmm_devmem_remove(struct hmm_devmem *devmem);
/*
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -839,7 +839,11 @@ static void hmm_devmem_release(struct de
zone = page_zone(page);
mem_hotplug_begin();
- __remove_pages(zone, start_pfn, npages);
+ if (resource->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY)
+ __remove_pages(zone, start_pfn, npages);
+ else
+ arch_remove_memory(start_pfn << PAGE_SHIFT,
+ npages << PAGE_SHIFT);
mem_hotplug_done();
hmm_devmem_radix_release(resource);
@@ -875,7 +879,11 @@ static int hmm_devmem_pages_create(struc
if (is_ram == REGION_INTERSECTS)
return -ENXIO;
- devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+ if (devmem->resource->desc == IORES_DESC_DEVICE_PUBLIC_MEMORY)
+ devmem->pagemap.type = MEMORY_DEVICE_PUBLIC;
+ else
+ devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+
devmem->pagemap.res = devmem->resource;
devmem->pagemap.page_fault = hmm_devmem_fault;
devmem->pagemap.page_free = hmm_devmem_free;
@@ -920,9 +928,15 @@ static int hmm_devmem_pages_create(struc
* over the device memory is un-accessible thus we do not want to
* create a linear mapping for the memory like arch_add_memory()
* would do.
+ *
+ * For device public memory, which is accesible by the CPU, we do
+ * want the linear mapping and thus use arch_add_memory().
*/
- ret = add_pages(nid, align_start >> PAGE_SHIFT,
- align_size >> PAGE_SHIFT, false);
+ if (devmem->pagemap.type == MEMORY_DEVICE_PUBLIC)
+ ret = arch_add_memory(nid, align_start, align_size, false);
+ else
+ ret = add_pages(nid, align_start >> PAGE_SHIFT,
+ align_size >> PAGE_SHIFT, false);
if (ret) {
mem_hotplug_done();
goto error_add_memory;
@@ -1069,6 +1083,67 @@ error_percpu_ref:
}
EXPORT_SYMBOL(hmm_devmem_add);
+struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
+ struct device *device,
+ struct resource *res)
+{
+ struct hmm_devmem *devmem;
+ int ret;
+
+ if (res->desc != IORES_DESC_DEVICE_PUBLIC_MEMORY)
+ return ERR_PTR(-EINVAL);
+
+ static_branch_enable(&device_private_key);
+
+ devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
+ GFP_KERNEL, dev_to_node(device));
+ if (!devmem)
+ return ERR_PTR(-ENOMEM);
+
+ init_completion(&devmem->completion);
+ devmem->pfn_first = -1UL;
+ devmem->pfn_last = -1UL;
+ devmem->resource = res;
+ devmem->device = device;
+ devmem->ops = ops;
+
+ ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release,
+ 0, GFP_KERNEL);
+ if (ret)
+ goto error_percpu_ref;
+
+ ret = devm_add_action(device, hmm_devmem_ref_exit, &devmem->ref);
+ if (ret)
+ goto error_devm_add_action;
+
+
+ devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
+ devmem->pfn_last = devmem->pfn_first +
+ (resource_size(devmem->resource) >> PAGE_SHIFT);
+
+ ret = hmm_devmem_pages_create(devmem);
+ if (ret)
+ goto error_devm_add_action;
+
+ devres_add(device, devmem);
+
+ ret = devm_add_action(device, hmm_devmem_ref_kill, &devmem->ref);
+ if (ret) {
+ hmm_devmem_remove(devmem);
+ return ERR_PTR(ret);
+ }
+
+ return devmem;
+
+error_devm_add_action:
+ hmm_devmem_ref_kill(&devmem->ref);
+ hmm_devmem_ref_exit(&devmem->ref);
+error_percpu_ref:
+ devres_free(devmem);
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(hmm_devmem_add_resource);
+
/*
* hmm_devmem_remove() - remove device memory (kill and free ZONE_DEVICE)
*
@@ -1082,6 +1157,7 @@ void hmm_devmem_remove(struct hmm_devmem
{
resource_size_t start, size;
struct device *device;
+ bool cdm = false;
if (!devmem)
return;
@@ -1090,11 +1166,13 @@ void hmm_devmem_remove(struct hmm_devmem
start = devmem->resource->start;
size = resource_size(devmem->resource);
+ cdm = devmem->resource->desc == IORES_DESC_DEVICE_PUBLIC_MEMORY;
hmm_devmem_ref_kill(&devmem->ref);
hmm_devmem_ref_exit(&devmem->ref);
hmm_devmem_pages_remove(devmem);
- devm_release_mem_region(device, start, size);
+ if (!cdm)
+ devm_release_mem_region(device, start, size);
}
EXPORT_SYMBOL(hmm_devmem_remove);