From patchwork Wed Sep 21 15:31:33 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dave Jiang X-Patchwork-Id: 12983893 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 77064ECAAD8 for ; Wed, 21 Sep 2022 15:37:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231266AbiIUPhJ (ORCPT ); Wed, 21 Sep 2022 11:37:09 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33844 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229512AbiIUPgw (ORCPT ); Wed, 21 Sep 2022 11:36:52 -0400 Received: from mga07.intel.com (mga07.intel.com [134.134.136.100]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 45BA83342C for ; Wed, 21 Sep 2022 08:33:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1663774397; x=1695310397; h=subject:from:to:cc:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=1nfD48fp2r0AfaA0ZGQ6qjOdAq8SksG/zOtMLOOpWO0=; b=ViESSCP9wLrdMzRdTLFVGOqXZvUUFScvRO4rWuXieE9SnMsWDz56k09L AegWEZBV2mAV6blOBrsousrxaceyg2l3tObGVGv8eWub5J3qL7mOqvHre tAmhbiDRG2dg0ivs7kxHG/eDOt+ccIGHULW2CNXugpwA28XJTamJmhJe0 ETRXFtHoCBr3Sx+FHkSu/YnOe2+26aTFfA8YeOMarFp/cnfYKwdh3z43E w0+DLQmVE3QeDIXDjOyj1NzAAsSiwKe8AxmJz6YEdFOeNjet3y7v4jYu4 BFt47KBySGzXjN8X0OhCziVBb47HEPevPtXyD+zT9uVdxSd8KqWKtZBD4 g==; X-IronPort-AV: E=McAfee;i="6500,9779,10477"; a="364012425" X-IronPort-AV: E=Sophos;i="5.93,333,1654585200"; d="scan'208";a="364012425" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 21 Sep 2022 08:31:34 -0700 X-IronPort-AV: E=Sophos;i="5.93,333,1654585200"; d="scan'208";a="652578872" Received: from djiang5-desk3.ch.intel.com ([143.182.136.137]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 21 Sep 2022 08:31:33 -0700 Subject: [PATCH v2 01/19] memregion: Add cpu_cache_invalidate_memregion() interface From: Dave Jiang To: linux-cxl@vger.kernel.org Cc: nvdimm@lists.linux.dev, dan.j.williams@intel.com, bwidawsk@kernel.org, ira.weiny@intel.com, vishal.l.verma@intel.com, alison.schofield@intel.com, dave@stgolabs.net, Jonathan.Cameron@huawei.com Date: Wed, 21 Sep 2022 08:31:33 -0700 Message-ID: <166377429297.430546.18244091321001267098.stgit@djiang5-desk3.ch.intel.com> In-Reply-To: <166377414787.430546.3863229455285366312.stgit@djiang5-desk3.ch.intel.com> References: <166377414787.430546.3863229455285366312.stgit@djiang5-desk3.ch.intel.com> User-Agent: StGit/1.4 MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-cxl@vger.kernel.org From: Davidlohr Bueso 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 --- arch/x86/Kconfig | 1 + arch/x86/mm/pat/set_memory.c | 15 +++++++++++++++ drivers/acpi/nfit/intel.c | 41 ++++++++++++++++++----------------------- include/linux/memregion.h | 35 +++++++++++++++++++++++++++++++++++ lib/Kconfig | 3 +++ 5 files changed, 72 insertions(+), 23 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f9920f1341c8..94dc39911f92 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -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 diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 1abd5438f126..4924d5a45950 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -330,6 +330,21 @@ 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; diff --git a/drivers/acpi/nfit/intel.c b/drivers/acpi/nfit/intel.c index 8dd792a55730..b2bfbf5797da 100644 --- a/drivers/acpi/nfit/intel.c +++ b/drivers/acpi/nfit/intel.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #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 -EINVAL; + 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 -EINVAL; + /* 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 -EINVAL; + /* 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, diff --git a/include/linux/memregion.h b/include/linux/memregion.h index c04c4fd2e209..f964193e4e2a 100644 --- a/include/linux/memregion.h +++ b/include/linux/memregion.h @@ -20,4 +20,39 @@ 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; +} + +int cpu_cache_invalidate_memregion(int res_desc) +{ + WARN_ON_ONCE("CPU cache invalidation required"); + return -EINVAL; +} +#endif #endif /* _MEMREGION_H_ */ diff --git a/lib/Kconfig b/lib/Kconfig index dc1ab2ed1dc6..6bb99da6011a 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -662,6 +662,9 @@ config ARCH_HAS_PMEM_API config MEMREGION bool +config ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION + bool + config ARCH_HAS_MEMREMAP_COMPAT_ALIGN bool