LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: linux-kernel@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	Darren Hart <dvhart@infradead.org>,
	Andy Shevchenko <andy@infradead.org>,
	vishal.l.verma@intel.com, x86@kernel.org, linux-mm@kvack.org,
	keith.busch@intel.com, vishal.l.verma@intel.com,
	linux-nvdimm@lists.01.org
Subject: [RFC PATCH 1/5] efi: Detect UEFI 2.8 Special Purpose Memory
Date: Thu, 04 Apr 2019 12:08:33 -0700
Message-ID: <155440491334.3190322.44013027330479237.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <155440490809.3190322.15060922240602775809.stgit@dwillia2-desk3.amr.corp.intel.com>

UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
interpretation of the EFI Memory Types as "reserved for a special
purpose".

The proposed Linux behavior for special purpose memory is that it is
reserved for direct-access (device-dax) by default and not available for
any kernel usage, not even as an OOM fallback. Later, through udev
scripts or another init mechanism, these device-dax claimed ranges can
be reconfigured and hot-added to the available System-RAM with a unique
node identifier.

A follow-on patch integrates parsing of the ACPI HMAT to identify the
node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
now, arrange for EFI_MEMORY_SP memory to be reserved.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Andy Shevchenko <andy@infradead.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/x86/Kconfig                  |   18 ++++++++++++++++++
 arch/x86/boot/compressed/eboot.c  |    5 ++++-
 arch/x86/boot/compressed/kaslr.c  |    2 +-
 arch/x86/include/asm/e820/types.h |    9 +++++++++
 arch/x86/kernel/e820.c            |    9 +++++++--
 arch/x86/platform/efi/efi.c       |   10 +++++++++-
 include/linux/efi.h               |   14 ++++++++++++++
 include/linux/ioport.h            |    1 +
 8 files changed, 63 insertions(+), 5 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c1f9b3cf437c..cb9ca27de7a5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1961,6 +1961,24 @@ config EFI_MIXED
 
 	   If unsure, say N.
 
+config EFI_SPECIAL_MEMORY
+	bool "EFI Special Purpose Memory Support"
+	depends on EFI
+	---help---
+	  On systems that have mixed performance classes of memory EFI
+	  may indicate special purpose memory with an attribute (See
+	  EFI_MEMORY_SP in UEFI 2.8). A memory range tagged with this
+	  attribute may have unique performance characteristics compared
+	  to the system's general purpose "System RAM" pool. On the
+	  expectation that such memory has application specific usage
+	  answer Y to arrange for the kernel to reserve it for
+	  direct-access (device-dax) by default. The memory range can
+	  later be optionally assigned to the page allocator by system
+	  administrator policy. Say N to have the kernel treat this
+	  memory as general purpose by default.
+
+	  If unsure, say Y.
+
 config SECCOMP
 	def_bool y
 	prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 544ac4fafd11..9b90fae21abe 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -560,7 +560,10 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
-			e820_type = E820_TYPE_RAM;
+			if (is_efi_special(d))
+				e820_type = E820_TYPE_SPECIAL;
+			else
+				e820_type = E820_TYPE_RAM;
 			break;
 
 		case EFI_ACPI_MEMORY_NVS:
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 2e53c056ba20..897e46eb9714 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -757,7 +757,7 @@ process_efi_entries(unsigned long minimum, unsigned long image_size)
 		 *
 		 * Only EFI_CONVENTIONAL_MEMORY is guaranteed to be free.
 		 */
-		if (md->type != EFI_CONVENTIONAL_MEMORY)
+		if (md->type != EFI_CONVENTIONAL_MEMORY || is_efi_special(md))
 			continue;
 
 		if (efi_mirror_found &&
diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
index c3aa4b5e49e2..0ab8abae2e8b 100644
--- a/arch/x86/include/asm/e820/types.h
+++ b/arch/x86/include/asm/e820/types.h
@@ -28,6 +28,15 @@ enum e820_type {
 	 */
 	E820_TYPE_PRAM		= 12,
 
+	/*
+	 * Special-purpose / application-specific memory is indicated to
+	 * the system via the EFI_MEMORY_SP attribute. Define an e820
+	 * translation of this memory type for the purpose of
+	 * reserving this range and marking it with the
+	 * IORES_DESC_APPLICATION_RESERVED designation.
+	 */
+	E820_TYPE_SPECIAL	= 0xefffffff,
+
 	/*
 	 * Reserved RAM used by the kernel itself if
 	 * CONFIG_INTEL_TXT=y is enabled, memory of this type
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 2879e234e193..9f50dd0bbb04 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -176,6 +176,7 @@ static void __init e820_print_type(enum e820_type type)
 	switch (type) {
 	case E820_TYPE_RAM:		/* Fall through: */
 	case E820_TYPE_RESERVED_KERN:	pr_cont("usable");			break;
+	case E820_TYPE_SPECIAL:		/* Fall through: */
 	case E820_TYPE_RESERVED:	pr_cont("reserved");			break;
 	case E820_TYPE_ACPI:		pr_cont("ACPI data");			break;
 	case E820_TYPE_NVS:		pr_cont("ACPI NVS");			break;
@@ -1023,6 +1024,7 @@ static const char *__init e820_type_to_string(struct e820_entry *entry)
 	case E820_TYPE_UNUSABLE:	return "Unusable memory";
 	case E820_TYPE_PRAM:		return "Persistent Memory (legacy)";
 	case E820_TYPE_PMEM:		return "Persistent Memory";
+	case E820_TYPE_SPECIAL:		/* Fall-through: */
 	case E820_TYPE_RESERVED:	return "Reserved";
 	default:			return "Unknown E820 type";
 	}
@@ -1038,6 +1040,7 @@ static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
 	case E820_TYPE_PRAM:		/* Fall-through: */
 	case E820_TYPE_PMEM:		/* Fall-through: */
+	case E820_TYPE_SPECIAL:		/* Fall-through: */
 	case E820_TYPE_RESERVED:	/* Fall-through: */
 	default:			return IORESOURCE_MEM;
 	}
@@ -1050,6 +1053,7 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 	case E820_TYPE_NVS:		return IORES_DESC_ACPI_NV_STORAGE;
 	case E820_TYPE_PMEM:		return IORES_DESC_PERSISTENT_MEMORY;
 	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
+	case E820_TYPE_SPECIAL:		return IORES_DESC_APPLICATION_RESERVED;
 	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		/* Fall-through: */
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
@@ -1065,13 +1069,14 @@ static bool __init do_mark_busy(enum e820_type type, struct resource *res)
 		return true;
 
 	/*
-	 * Treat persistent memory like device memory, i.e. reserve it
-	 * for exclusive use of a driver
+	 * Treat persistent memory and other special memory ranges like
+	 * device memory, i.e. reserve it for exclusive use of a driver
 	 */
 	switch (type) {
 	case E820_TYPE_RESERVED:
 	case E820_TYPE_PRAM:
 	case E820_TYPE_PMEM:
+	case E820_TYPE_SPECIAL:
 		return false;
 	case E820_TYPE_RESERVED_KERN:
 	case E820_TYPE_RAM:
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index e1cb01a22fa8..d227751f331b 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -139,7 +139,9 @@ static void __init do_add_efi_memmap(void)
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
-			if (md->attribute & EFI_MEMORY_WB)
+			if (is_efi_special(md))
+				e820_type = E820_TYPE_SPECIAL;
+			else if (md->attribute & EFI_MEMORY_WB)
 				e820_type = E820_TYPE_RAM;
 			else
 				e820_type = E820_TYPE_RESERVED;
@@ -753,6 +755,12 @@ static bool should_map_region(efi_memory_desc_t *md)
 	if (IS_ENABLED(CONFIG_X86_32))
 		return false;
 
+	/*
+	 * Special purpose memory is not mapped by default.
+	 */
+	if (is_efi_special(md))
+		return false;
+
 	/*
 	 * Map all of RAM so that we can access arguments in the 1:1
 	 * mapping when making EFI runtime calls.
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 54357a258b35..cecbc2bda1da 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -112,6 +112,7 @@ typedef	struct {
 #define EFI_MEMORY_MORE_RELIABLE \
 				((u64)0x0000000000010000ULL)	/* higher reliability */
 #define EFI_MEMORY_RO		((u64)0x0000000000020000ULL)	/* read-only */
+#define EFI_MEMORY_SP		((u64)0x0000000000040000ULL)	/* special purpose */
 #define EFI_MEMORY_RUNTIME	((u64)0x8000000000000000ULL)	/* range requires runtime mapping */
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
@@ -128,6 +129,19 @@ typedef struct {
 	u64 attribute;
 } efi_memory_desc_t;
 
+#ifdef CONFIG_EFI_SPECIAL_MEMORY
+static inline bool is_efi_special(efi_memory_desc_t *md)
+{
+	return md->type == EFI_CONVENTIONAL_MEMORY
+		&& (md->attribute & EFI_MEMORY_SP);
+}
+#else
+static inline bool is_efi_special(efi_memory_desc_t *md)
+{
+	return false;
+}
+#endif
+
 typedef struct {
 	efi_guid_t guid;
 	u32 headersize;
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index da0ebaec25f0..2d79841ee9b9 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -133,6 +133,7 @@ enum {
 	IORES_DESC_PERSISTENT_MEMORY_LEGACY	= 5,
 	IORES_DESC_DEVICE_PRIVATE_MEMORY	= 6,
 	IORES_DESC_DEVICE_PUBLIC_MEMORY		= 7,
+	IORES_DESC_APPLICATION_RESERVED		= 8,
 };
 
 /* helpers to define resources */


  reply index

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-04 19:08 [RFC PATCH 0/5] EFI Special Purpose Memory Support Dan Williams
2019-04-04 19:08 ` Dan Williams [this message]
2019-04-06  4:21   ` [RFC PATCH 1/5] efi: Detect UEFI 2.8 Special Purpose Memory Ard Biesheuvel
2019-04-09 16:43     ` Dan Williams
2019-04-09 17:21       ` Ard Biesheuvel
2019-04-10  2:10         ` Dan Williams
2019-04-12 20:43           ` Ard Biesheuvel
2019-04-12 21:18             ` Dan Williams
2019-04-15 11:43       ` Enrico Weigelt, metux IT consult
2019-04-04 19:08 ` [RFC PATCH 2/5] lib/memregion: Uplevel the pmem "region" ida to a global allocator Dan Williams
2019-04-04 19:32   ` Matthew Wilcox
2019-04-04 21:02     ` Dan Williams
2019-04-04 19:08 ` [RFC PATCH 3/5] acpi/hmat: Track target address ranges Dan Williams
2019-04-04 20:58   ` Keith Busch
2019-04-04 20:58     ` Dan Williams
2019-04-04 19:08 ` [RFC PATCH 4/5] acpi/hmat: Register special purpose memory as a device Dan Williams
2019-04-05 11:18   ` Jonathan Cameron
2019-04-05 15:43     ` Dan Williams
2019-04-05 16:23       ` Jonathan Cameron
2019-04-05 16:56         ` Dan Williams
2019-04-05 17:39           ` Jonathan Cameron
2019-04-09 12:13   ` Christoph Hellwig
2019-04-09 14:49     ` Dan Williams
2019-04-04 19:08 ` [RFC PATCH 5/5] device-dax: Add a driver for "hmem" devices Dan Williams

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=155440491334.3190322.44013027330479237.stgit@dwillia2-desk3.amr.corp.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=andy@infradead.org \
    --cc=ard.biesheuvel@linaro.org \
    --cc=bp@alien8.de \
    --cc=dvhart@infradead.org \
    --cc=hpa@zytor.com \
    --cc=keith.busch@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=mingo@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=vishal.l.verma@intel.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git