summaryrefslogtreecommitdiff
path: root/drivers/dax/hmem
diff options
context:
space:
mode:
authorDan Williams <dan.j.williams@intel.com>2022-11-19 17:37:49 -0800
committerDan Williams <dan.j.williams@intel.com>2022-11-21 15:34:40 -0800
commit472faf72b33d80aa8e7a99c9410c1a23d3bf0cd8 (patch)
tree221fe236cbba05a3521a367929fbbdc6bad58da4 /drivers/dax/hmem
parent48d4180939e12c4bd2846f984436d895bb9699ed (diff)
device-dax: Fix duplicate 'hmem' device registration
So called "soft-reserved" memory is an EFI conventional memory range with the EFI_MEMORY_SP attribute set. That attribute indicates that the memory is not part of the platform general purpose memory pool and may want some consideration from the system administrator about whether to keep that memory set aside for dedicated access through device-dax (map a device file), or assigned to the page allocator as another general purpose memory node target. Absent an ACPI HMAT table the default device-dax registration creates coarse grained devices that are delineated by EFI Memory Map entries. With the HMAT the devices are delineated by the finer grained ranges associated with the proximity domain of the memory target. I.e. the HMAT describes the properties of performance differentiated memory and each unique performance description results in a unique target proximity domain where each memory proximity domain has an associated SRAT entry that delineates the address range. The intent was that SRAT-defined device-dax instances are registered first. Then any left-over address range with the EFI_MEMORY_SP attribute, but not covered by the SRAT, would have a coarse grained device-dax instance established. However, the scheme to detect what ranges are left to be assigned to a device was buggy and resulted in multiple overlapping device-dax instances. Fix this by using explicit tracking for which ranges have been handled. Now, this new approach may leave memory stranded in the presence of broken platform firmware that fails to fully describe all EFI_MEMORY_SP ranges in the HMAT. That requires a deeper fix if it becomes a problem in practice. Reported-by: "Tallam Mahendra Kumar" <tallam.mahendra.kumar@intel.com> Reported-by: Mustafa Hajeer <mustafa.hajeer@intel.com> Debugged-by: Vishal Verma <vishal.l.verma@intel.com> Tested-by: Vishal Verma <vishal.l.verma@intel.com> Link: https://lore.kernel.org/r/166890823379.4183293.15333502171004313377.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Diffstat (limited to 'drivers/dax/hmem')
-rw-r--r--drivers/dax/hmem/device.c24
1 files changed, 15 insertions, 9 deletions
diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
index 97086fab698e..903325aac991 100644
--- a/drivers/dax/hmem/device.c
+++ b/drivers/dax/hmem/device.c
@@ -8,6 +8,13 @@
static bool nohmem;
module_param_named(disable, nohmem, bool, 0444);
+static struct resource hmem_active = {
+ .name = "HMEM devices",
+ .start = 0,
+ .end = -1,
+ .flags = IORESOURCE_MEM,
+};
+
void hmem_register_device(int target_nid, struct resource *r)
{
/* define a clean / non-busy resource for the platform device */
@@ -41,6 +48,12 @@ void hmem_register_device(int target_nid, struct resource *r)
goto out_pdev;
}
+ if (!__request_region(&hmem_active, res.start, resource_size(&res),
+ dev_name(&pdev->dev), 0)) {
+ dev_dbg(&pdev->dev, "hmem range %pr already active\n", &res);
+ goto out_active;
+ }
+
pdev->dev.numa_node = numa_map_to_online_node(target_nid);
info = (struct memregion_info) {
.target_node = target_nid,
@@ -66,6 +79,8 @@ void hmem_register_device(int target_nid, struct resource *r)
return;
out_resource:
+ __release_region(&hmem_active, res.start, resource_size(&res));
+out_active:
platform_device_put(pdev);
out_pdev:
memregion_free(id);
@@ -73,15 +88,6 @@ out_pdev:
static __init int hmem_register_one(struct resource *res, void *data)
{
- /*
- * If the resource is not a top-level resource it was already
- * assigned to a device by the HMAT parsing.
- */
- if (res->parent != &iomem_resource) {
- pr_info("HMEM: skip %pr, already claimed\n", res);
- return 0;
- }
-
hmem_register_device(phys_to_target_node(res->start), res);
return 0;