@@ -69,6 +69,7 @@ config X86
select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_CACHE_LINE_SIZE
+ select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION if X86_64
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE
@@ -16,6 +16,7 @@
#include <linux/pci.h>
#include <linux/vmalloc.h>
#include <linux/libnvdimm.h>
+#include <linux/memregion.h>
#include <linux/vmstat.h>
#include <linux/kernel.h>
#include <linux/cc_platform.h>
@@ -330,6 +331,21 @@ void arch_invalidate_pmem(void *addr, size_t size)
EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
#endif
+#ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
+bool cpu_cache_has_invalidate_memregion(void)
+{
+ return !cpu_feature_enabled(X86_FEATURE_HYPERVISOR);
+}
+EXPORT_SYMBOL_GPL(cpu_cache_has_invalidate_memregion);
+
+int cpu_cache_invalidate_memregion(int res_desc)
+{
+ wbinvd_on_all_cpus();
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cpu_cache_invalidate_memregion);
+#endif
+
static void __cpa_flush_all(void *arg)
{
unsigned long cache = (unsigned long)arg;
@@ -3,6 +3,7 @@
#include <linux/libnvdimm.h>
#include <linux/ndctl.h>
#include <linux/acpi.h>
+#include <linux/memregion.h>
#include <asm/smp.h>
#include "intel.h"
#include "nfit.h"
@@ -190,8 +191,6 @@ static int intel_security_change_key(struct nvdimm *nvdimm,
}
}
-static void nvdimm_invalidate_cache(void);
-
static int __maybe_unused intel_security_unlock(struct nvdimm *nvdimm,
const struct nvdimm_key_data *key_data)
{
@@ -213,6 +212,9 @@ static int __maybe_unused intel_security_unlock(struct nvdimm *nvdimm,
if (!test_bit(NVDIMM_INTEL_UNLOCK_UNIT, &nfit_mem->dsm_mask))
return -ENOTTY;
+ if (!cpu_cache_has_invalidate_memregion())
+ return -EOPNOTSUPP;
+
memcpy(nd_cmd.cmd.passphrase, key_data->data,
sizeof(nd_cmd.cmd.passphrase));
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
@@ -228,7 +230,7 @@ static int __maybe_unused intel_security_unlock(struct nvdimm *nvdimm,
}
/* DIMM unlocked, invalidate all CPU caches before we read it */
- nvdimm_invalidate_cache();
+ cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY);
return 0;
}
@@ -297,8 +299,11 @@ static int __maybe_unused intel_security_erase(struct nvdimm *nvdimm,
if (!test_bit(cmd, &nfit_mem->dsm_mask))
return -ENOTTY;
+ if (!cpu_cache_has_invalidate_memregion())
+ return -EOPNOTSUPP;
+
/* flush all cache before we erase DIMM */
- nvdimm_invalidate_cache();
+ cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY);
memcpy(nd_cmd.cmd.passphrase, key->data,
sizeof(nd_cmd.cmd.passphrase));
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
@@ -318,7 +323,7 @@ static int __maybe_unused intel_security_erase(struct nvdimm *nvdimm,
}
/* DIMM erased, invalidate all CPU caches before we read it */
- nvdimm_invalidate_cache();
+ cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY);
return 0;
}
@@ -341,6 +346,9 @@ static int __maybe_unused intel_security_query_overwrite(struct nvdimm *nvdimm)
if (!test_bit(NVDIMM_INTEL_QUERY_OVERWRITE, &nfit_mem->dsm_mask))
return -ENOTTY;
+ if (!cpu_cache_has_invalidate_memregion())
+ return -EINVAL;
+
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
if (rc < 0)
return rc;
@@ -355,7 +363,7 @@ static int __maybe_unused intel_security_query_overwrite(struct nvdimm *nvdimm)
}
/* flush all cache before we make the nvdimms available */
- nvdimm_invalidate_cache();
+ cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY);
return 0;
}
@@ -380,8 +388,11 @@ static int __maybe_unused intel_security_overwrite(struct nvdimm *nvdimm,
if (!test_bit(NVDIMM_INTEL_OVERWRITE, &nfit_mem->dsm_mask))
return -ENOTTY;
+ if (!cpu_cache_has_invalidate_memregion())
+ return -EOPNOTSUPP;
+
/* flush all cache before we erase DIMM */
- nvdimm_invalidate_cache();
+ cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY);
memcpy(nd_cmd.cmd.passphrase, nkey->data,
sizeof(nd_cmd.cmd.passphrase));
rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
@@ -401,22 +412,6 @@ static int __maybe_unused intel_security_overwrite(struct nvdimm *nvdimm,
}
}
-/*
- * TODO: define a cross arch wbinvd equivalent when/if
- * NVDIMM_FAMILY_INTEL command support arrives on another arch.
- */
-#ifdef CONFIG_X86
-static void nvdimm_invalidate_cache(void)
-{
- wbinvd_on_all_cpus();
-}
-#else
-static void nvdimm_invalidate_cache(void)
-{
- WARN_ON_ONCE("cache invalidation required after unlock\n");
-}
-#endif
-
static const struct nvdimm_security_ops __intel_security_ops = {
.get_flags = intel_security_flags,
.freeze = intel_security_freeze,
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _MEMREGION_H_
#define _MEMREGION_H_
+#include <linux/bug.h>
#include <linux/types.h>
#include <linux/errno.h>
@@ -20,4 +21,39 @@ static inline void memregion_free(int id)
{
}
#endif
+
+/**
+ * cpu_cache_invalidate_memregion - drop any CPU cached data for
+ * memregions described by @res_desc
+ * @res_desc: one of the IORES_DESC_* types
+ *
+ * Perform cache maintenance after a memory event / operation that
+ * changes the contents of physical memory in a cache-incoherent manner.
+ * For example, device memory technologies like NVDIMM and CXL have
+ * device secure erase, or dynamic region provision features where such
+ * semantics.
+ *
+ * Limit the functionality to architectures that have an efficient way
+ * to writeback and invalidate potentially terabytes of memory at once.
+ * Note that this routine may or may not write back any dirty contents
+ * while performing the invalidation.
+ *
+ * Returns 0 on success or negative error code on a failure to perform
+ * the cache maintenance.
+ */
+#ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
+int cpu_cache_invalidate_memregion(int res_desc);
+bool cpu_cache_has_invalidate_memregion(void);
+#else
+static inline bool cpu_cache_has_invalidate_memregion(void)
+{
+ return false;
+}
+
+static inline int cpu_cache_invalidate_memregion(int res_desc)
+{
+ WARN_ON_ONCE("CPU cache invalidation required");
+ return -EINVAL;
+}
+#endif
#endif /* _MEMREGION_H_ */
@@ -672,6 +672,9 @@ config ARCH_HAS_PMEM_API
config MEMREGION
bool
+config ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
+ bool
+
config ARCH_HAS_MEMREMAP_COMPAT_ALIGN
bool
With CXL security features, global CPU cache flushing nvdimm requirements are no longer specific to that subsystem, even beyond the scope of security_ops. CXL will need such semantics for features not necessarily limited to persistent memory. The functionality this is enabling is to be able to instantaneously secure erase potentially terabytes of memory at once and the kernel needs to be sure that none of the data from before the erase is still present in the cache. It is also used when unlocking a memory device where speculative reads and firmware accesses could have cached poison from before the device was unlocked. This capability is typically only used once per-boot (for unlock), or once per bare metal provisioning event (secure erase), like when handing off the system to another tenant or decommissioning a device. It may also be used for dynamic CXL region provisioning. Users must first call cpu_cache_has_invalidate_memregion() to know whether this functionality is available on the architecture. Only enable it on x86-64 via the wbinvd() hammer. Hypervisors are not supported as TDX guests may trigger a virtualization exception and may need proper handling to recover. See: e2efb6359e62 ("ACPICA: Avoid cache flush inside virtual machines") Signed-off-by: Davidlohr Bueso <dave@stgolabs.net> --- Changes from https://lore.kernel.org/all/166377429297.430546.18244091321001267098.stgit@djiang5-desk3.ch.intel.com/ None of them are actually interface related, only a return code change and some fixlets found by 0day: - use EOPNOTSUPP upon !cpu_cache_has_invalidate_memregion() (Dave) - set_memory.c includes memregion.h (0day) - memregion includes linux/bug.h (for WARN_ON_ONCE) and make cpu_cache_invalidate_memregion() stub static inline . (0day) arch/x86/Kconfig | 1 + arch/x86/mm/pat/set_memory.c | 16 ++++++++++++++ drivers/acpi/nfit/intel.c | 41 ++++++++++++++++-------------------- include/linux/memregion.h | 36 +++++++++++++++++++++++++++++++ lib/Kconfig | 3 +++ 5 files changed, 74 insertions(+), 23 deletions(-) -- 2.37.3