* [PATCH v6 01/12] acpi/numa: Establish a new drivers/acpi/numa/ directory
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
@ 2019-10-09 23:04 ` Dan Williams
2019-10-09 23:04 ` [PATCH v6 02/12] efi: Enumerate EFI_MEMORY_SP Dan Williams
` (10 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:04 UTC (permalink / raw)
To: mingo
Cc: Len Brown, Keith Busch, Rafael J. Wysocki, Dave Hansen, peterz,
vishal.l.verma, ard.biesheuvel, x86, linux-efi, linux-kernel,
linux-acpi
Currently hmat.c lives under an "hmat" directory which does not enhance
the description of the file. The initial motivation for giving hmat.c
its own directory was to delineate it as mm functionality in contrast to
ACPI device driver functionality.
As ACPI continues to play an increasing role in conveying
memory location and performance topology information to the OS take the
opportunity to co-locate these NUMA relevant tables in a combined
directory.
numa.c is renamed to srat.c and moved to drivers/acpi/numa/ along with
hmat.c.
Cc: Len Brown <lenb@kernel.org>
Cc: Keith Busch <kbusch@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/acpi/Kconfig | 9 +--------
drivers/acpi/Makefile | 3 +--
drivers/acpi/hmat/Makefile | 2 --
drivers/acpi/numa/Kconfig | 6 ++++++
drivers/acpi/numa/Makefile | 3 +++
drivers/acpi/numa/hmat.c | 0
drivers/acpi/numa/srat.c | 0
7 files changed, 11 insertions(+), 12 deletions(-)
delete mode 100644 drivers/acpi/hmat/Makefile
rename drivers/acpi/{hmat/Kconfig => numa/Kconfig} (77%)
create mode 100644 drivers/acpi/numa/Makefile
rename drivers/acpi/{hmat/hmat.c => numa/hmat.c} (100%)
rename drivers/acpi/{numa.c => numa/srat.c} (100%)
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index ebe1e9e5fd81..8c7c46065e9d 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -319,12 +319,6 @@ config ACPI_THERMAL
To compile this driver as a module, choose M here:
the module will be called thermal.
-config ACPI_NUMA
- bool "NUMA support"
- depends on NUMA
- depends on (X86 || IA64 || ARM64)
- default y if IA64 || ARM64
-
config ACPI_CUSTOM_DSDT_FILE
string "Custom DSDT Table file to include"
default ""
@@ -473,8 +467,7 @@ config ACPI_REDUCED_HARDWARE_ONLY
If you are unsure what to do, do not enable this option.
source "drivers/acpi/nfit/Kconfig"
-source "drivers/acpi/hmat/Kconfig"
-
+source "drivers/acpi/numa/Kconfig"
source "drivers/acpi/apei/Kconfig"
source "drivers/acpi/dptf/Kconfig"
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 5d361e4e3405..f08a661274e8 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -55,7 +55,6 @@ acpi-$(CONFIG_X86) += acpi_cmos_rtc.o
acpi-$(CONFIG_X86) += x86/apple.o
acpi-$(CONFIG_X86) += x86/utils.o
acpi-$(CONFIG_DEBUG_FS) += debugfs.o
-acpi-$(CONFIG_ACPI_NUMA) += numa.o
acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
acpi-y += acpi_lpat.o
acpi-$(CONFIG_ACPI_LPIT) += acpi_lpit.o
@@ -80,7 +79,7 @@ obj-$(CONFIG_ACPI_PROCESSOR) += processor.o
obj-$(CONFIG_ACPI) += container.o
obj-$(CONFIG_ACPI_THERMAL) += thermal.o
obj-$(CONFIG_ACPI_NFIT) += nfit/
-obj-$(CONFIG_ACPI_HMAT) += hmat/
+obj-$(CONFIG_ACPI_NUMA) += numa/
obj-$(CONFIG_ACPI) += acpi_memhotplug.o
obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
obj-$(CONFIG_ACPI_BATTERY) += battery.o
diff --git a/drivers/acpi/hmat/Makefile b/drivers/acpi/hmat/Makefile
deleted file mode 100644
index 1c20ef36a385..000000000000
--- a/drivers/acpi/hmat/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_ACPI_HMAT) := hmat.o
diff --git a/drivers/acpi/hmat/Kconfig b/drivers/acpi/numa/Kconfig
similarity index 77%
rename from drivers/acpi/hmat/Kconfig
rename to drivers/acpi/numa/Kconfig
index 95a29964dbea..acbd5aa76e40 100644
--- a/drivers/acpi/hmat/Kconfig
+++ b/drivers/acpi/numa/Kconfig
@@ -1,4 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
+config ACPI_NUMA
+ bool "NUMA support"
+ depends on NUMA
+ depends on (X86 || IA64 || ARM64)
+ default y if IA64 || ARM64
+
config ACPI_HMAT
bool "ACPI Heterogeneous Memory Attribute Table Support"
depends on ACPI_NUMA
diff --git a/drivers/acpi/numa/Makefile b/drivers/acpi/numa/Makefile
new file mode 100644
index 000000000000..517a6c689a94
--- /dev/null
+++ b/drivers/acpi/numa/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_ACPI_NUMA) += srat.o
+obj-$(CONFIG_ACPI_HMAT) += hmat.o
diff --git a/drivers/acpi/hmat/hmat.c b/drivers/acpi/numa/hmat.c
similarity index 100%
rename from drivers/acpi/hmat/hmat.c
rename to drivers/acpi/numa/hmat.c
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa/srat.c
similarity index 100%
rename from drivers/acpi/numa.c
rename to drivers/acpi/numa/srat.c
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH v6 02/12] efi: Enumerate EFI_MEMORY_SP
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
2019-10-09 23:04 ` [PATCH v6 01/12] acpi/numa: Establish a new drivers/acpi/numa/ directory Dan Williams
@ 2019-10-09 23:04 ` Dan Williams
2019-10-09 23:04 ` [PATCH v6 03/12] x86/efi: Push EFI_MEMMAP check into leaf routines Dan Williams
` (9 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:04 UTC (permalink / raw)
To: mingo
Cc: Ard Biesheuvel, Dave Hansen, peterz, vishal.l.verma, x86,
linux-efi, linux-kernel, linux-acpi
UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
interpretation of the EFI Memory Types as "reserved for a specific
purpose". The intent of this bit is to allow the OS to identify precious
or scarce memory resources and optionally manage it separately from
EfiConventionalMemory. As defined older OSes that do not know about this
attribute are permitted to ignore it and the memory will be handled
according to the OS default policy for the given memory type.
In other words, this "specific purpose" hint is deliberately weaker than
EfiReservedMemoryType in that the system continues to operate if the OS
takes no action on the attribute. The risk of taking no action is
potentially unwanted / unmovable kernel allocations from the designated
resource that prevent the full realization of the "specific purpose".
For example, consider a system with a high-bandwidth memory pool. Older
kernels are permitted to boot and consume that memory as conventional
"System-RAM" newer kernels may arrange for that memory to be set aside
(soft reserved) by the system administrator for a dedicated
high-bandwidth memory aware application to consume.
Specifically, this mechanism allows for the elimination of scenarios
where platform firmware tries to game OS policy by lying about ACPI SLIT
values, i.e. claiming that a precious memory resource has a high
distance to trigger the OS to avoid it by default. This reservation hint
allows platform-firmware to instead tell the truth about performance
characteristics by indicate to OS memory management to put immovable
allocations elsewhere.
Implement simple detection of the bit for EFI memory table dumps and
save the kernel policy for a follow-on change.
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/firmware/efi/efi.c | 5 +++--
include/linux/efi.h | 1 +
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 8d3e778e988b..68a4ec24b823 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -839,15 +839,16 @@ char * __init efi_md_typeattr_format(char *buf, size_t size,
if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT |
EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO |
EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP |
- EFI_MEMORY_NV |
+ EFI_MEMORY_NV | EFI_MEMORY_SP |
EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE))
snprintf(pos, size, "|attr=0x%016llx]",
(unsigned long long)attr);
else
snprintf(pos, size,
- "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+ "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
attr & EFI_MEMORY_RUNTIME ? "RUN" : "",
attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "",
+ attr & EFI_MEMORY_SP ? "SP" : "",
attr & EFI_MEMORY_NV ? "NV" : "",
attr & EFI_MEMORY_XP ? "XP" : "",
attr & EFI_MEMORY_RP ? "RP" : "",
diff --git a/include/linux/efi.h b/include/linux/efi.h
index bd3837022307..5c1dd0221384 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) /* soft reserved */
#define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */
#define EFI_MEMORY_DESCRIPTOR_VERSION 1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH v6 03/12] x86/efi: Push EFI_MEMMAP check into leaf routines
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
2019-10-09 23:04 ` [PATCH v6 01/12] acpi/numa: Establish a new drivers/acpi/numa/ directory Dan Williams
2019-10-09 23:04 ` [PATCH v6 02/12] efi: Enumerate EFI_MEMORY_SP Dan Williams
@ 2019-10-09 23:04 ` Dan Williams
2019-10-09 23:04 ` [PATCH v6 04/12] efi: Common enable/disable infrastructure for EFI soft reservation Dan Williams
` (8 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:04 UTC (permalink / raw)
To: mingo
Cc: x86, H. Peter Anvin, Andy Lutomirski, Thomas Gleixner,
Peter Zijlstra, Dave Hansen, Ard Biesheuvel, vishal.l.verma, x86,
linux-efi, linux-kernel, linux-acpi
In preparation for adding another EFI_MEMMAP dependent call that needs
to occur before e820__memblock_setup() fixup the existing efi calls to
check for EFI_MEMMAP internally. This ends up being cleaner than the
alternative of checking EFI_MEMMAP multiple times in setup_arch().
Cc: <x86@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/x86/include/asm/efi.h | 9 ++++++++-
arch/x86/kernel/setup.c | 18 ++++++++----------
arch/x86/platform/efi/efi.c | 3 +++
arch/x86/platform/efi/quirks.c | 3 +++
drivers/firmware/efi/esrt.c | 3 +++
drivers/firmware/efi/fake_mem.c | 2 +-
include/linux/efi.h | 1 -
7 files changed, 26 insertions(+), 13 deletions(-)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 43a82e59c59d..45f853bce869 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -140,7 +140,6 @@ extern void efi_delete_dummy_variable(void);
extern void efi_switch_mm(struct mm_struct *mm);
extern void efi_recover_from_page_fault(unsigned long phys_addr);
extern void efi_free_boot_services(void);
-extern void efi_reserve_boot_services(void);
struct efi_setup_data {
u64 fw_vendor;
@@ -244,6 +243,8 @@ static inline bool efi_is_64bit(void)
extern bool efi_reboot_required(void);
extern bool efi_is_table_address(unsigned long phys_addr);
+extern void efi_find_mirror(void);
+extern void efi_reserve_boot_services(void);
#else
static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
static inline bool efi_reboot_required(void)
@@ -254,6 +255,12 @@ static inline bool efi_is_table_address(unsigned long phys_addr)
{
return false;
}
+static inline void efi_find_mirror(void)
+{
+}
+static inline void efi_reserve_boot_services(void)
+{
+}
#endif /* CONFIG_EFI */
#endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 77ea96b794bd..1c4b866bc184 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1122,17 +1122,15 @@ void __init setup_arch(char **cmdline_p)
reserve_bios_regions();
- if (efi_enabled(EFI_MEMMAP)) {
- efi_fake_memmap();
- efi_find_mirror();
- efi_esrt_init();
+ efi_fake_memmap();
+ efi_find_mirror();
+ efi_esrt_init();
- /*
- * The EFI specification says that boot service code won't be
- * called after ExitBootServices(). This is, in fact, a lie.
- */
- efi_reserve_boot_services();
- }
+ /*
+ * The EFI specification says that boot service code won't be
+ * called after ExitBootServices(). This is, in fact, a lie.
+ */
+ efi_reserve_boot_services();
/* preallocate 4k for mptable mpc */
e820__memblock_alloc_reserved_mpc_new();
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index c202e1b07e29..0bb58eb33ca0 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -128,6 +128,9 @@ void __init efi_find_mirror(void)
efi_memory_desc_t *md;
u64 mirror_size = 0, total_size = 0;
+ if (!efi_enabled(EFI_MEMMAP))
+ return;
+
for_each_efi_memory_desc(md) {
unsigned long long start = md->phys_addr;
unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 3b9fd679cea9..7675cf754d90 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -320,6 +320,9 @@ void __init efi_reserve_boot_services(void)
{
efi_memory_desc_t *md;
+ if (!efi_enabled(EFI_MEMMAP))
+ return;
+
for_each_efi_memory_desc(md) {
u64 start = md->phys_addr;
u64 size = md->num_pages << EFI_PAGE_SHIFT;
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index d6dd5f503fa2..2762e0662bf4 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -246,6 +246,9 @@ void __init efi_esrt_init(void)
int rc;
phys_addr_t end;
+ if (!efi_enabled(EFI_MEMMAP))
+ return;
+
pr_debug("esrt-init: loading.\n");
if (!esrt_table_exists())
return;
diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c
index 9501edc0fcfb..526b45331d96 100644
--- a/drivers/firmware/efi/fake_mem.c
+++ b/drivers/firmware/efi/fake_mem.c
@@ -44,7 +44,7 @@ void __init efi_fake_memmap(void)
void *new_memmap;
int i;
- if (!nr_fake_mem)
+ if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
return;
/* count up the number of EFI memory descriptor */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 5c1dd0221384..baa275c56401 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1045,7 +1045,6 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos
extern efi_status_t efi_query_variable_store(u32 attributes,
unsigned long size,
bool nonblocking);
-extern void efi_find_mirror(void);
#else
static inline efi_status_t efi_query_variable_store(u32 attributes,
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH v6 04/12] efi: Common enable/disable infrastructure for EFI soft reservation
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (2 preceding siblings ...)
2019-10-09 23:04 ` [PATCH v6 03/12] x86/efi: Push EFI_MEMMAP check into leaf routines Dan Williams
@ 2019-10-09 23:04 ` Dan Williams
2019-10-10 6:36 ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration Dan Williams
` (7 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:04 UTC (permalink / raw)
To: mingo
Cc: Ard Biesheuvel, peterz, vishal.l.verma, dave.hansen, x86,
linux-efi, linux-kernel, linux-acpi
UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
interpretation of the EFI Memory Types as "reserved for a specific
purpose".
The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
the "soft reserved" designation by allowing some or all of the
reservation to be recovered as typical memory. This policy can be
disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
efi=nosoftreserve.
As for this patch, define the common helpers to determine if the
EFI_MEMORY_SP attribute should be honored. The determination needs to be
made early to prevent the kernel from being loaded into soft-reserved
memory, or otherwise allowing early allocations to land there. Follow-on
changes are needed per architecture to leverage these helpers in their
respective mem-init paths.
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
Documentation/admin-guide/kernel-parameters.txt | 9 ++++++++-
drivers/firmware/efi/Kconfig | 21 +++++++++++++++++++++
drivers/firmware/efi/efi.c | 9 +++++++++
drivers/firmware/efi/libstub/efi-stub-helper.c | 19 +++++++++++++++++++
include/linux/efi.h | 8 ++++++++
5 files changed, 65 insertions(+), 1 deletion(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index c7ac2f3ac99f..47478a730011 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1168,7 +1168,8 @@
Format: {"off" | "on" | "skip[mbr]"}
efi= [EFI]
- Format: { "old_map", "nochunk", "noruntime", "debug" }
+ Format: { "old_map", "nochunk", "noruntime", "debug",
+ "nosoftreserve" }
old_map [X86-64]: switch to the old ioremap-based EFI
runtime services mapping. 32-bit still uses this one by
default.
@@ -1177,6 +1178,12 @@
firmware implementations.
noruntime : disable EFI runtime services support
debug: enable misc debug output
+ nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
+ attribute may cause the kernel to reserve the
+ memory range for a memory mapping driver to
+ claim. Specify efi=nosoftreserve to disable this
+ reservation and treat the memory by its base type
+ (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
efi_no_storage_paranoia [EFI; X86]
Using this parameter you can use more than 50% of
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 178ee8106828..9fa79f9fa0af 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -75,6 +75,27 @@ config EFI_MAX_FAKE_MEM
Ranges can be set up to this value using comma-separated list.
The default value is 8.
+config EFI_SOFT_RESERVE
+ bool "Reserve EFI Specific Purpose Memory"
+ depends on EFI && ACPI_HMAT
+ default ACPI_HMAT
+ help
+ On systems that have mixed performance classes of memory EFI
+ may indicate specific 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,
+ and its base EFI memory type is "conventional" answer Y to
+ arrange for the kernel to reserve it as a "Soft Reserved"
+ resource, and set aside for direct-access (device-dax) by
+ default. The memory range can later be optionally assigned to
+ the page allocator by system administrator policy via the
+ device-dax kmem facility. Say N to have the kernel treat this
+ memory as "System RAM" by default.
+
+ If unsure, say Y.
+
config EFI_PARAMS_FROM_FDT
bool
help
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 68a4ec24b823..911a58be4a36 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -81,6 +81,12 @@ bool efi_runtime_disabled(void)
return disable_runtime;
}
+bool __pure efi_soft_reserve_enabled(void)
+{
+ return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) &&
+ !efi_enabled(EFI_MEM_NO_SOFT_RESERVE);
+}
+
static int __init parse_efi_cmdline(char *str)
{
if (!str) {
@@ -94,6 +100,9 @@ static int __init parse_efi_cmdline(char *str)
if (parse_option_str(str, "noruntime"))
disable_runtime = true;
+ if (parse_option_str(str, "nosoftreserve"))
+ set_bit(EFI_MEM_NO_SOFT_RESERVE, &efi.flags);
+
return 0;
}
early_param("efi", parse_efi_cmdline);
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 3caae7f2cf56..5d901c56ac5f 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -32,6 +32,7 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
static int __section(.data) __nokaslr;
static int __section(.data) __quiet;
static int __section(.data) __novamap;
+static bool __section(.data) efi_nosoftreserve;
int __pure nokaslr(void)
{
@@ -45,6 +46,10 @@ int __pure novamap(void)
{
return __novamap;
}
+bool __pure efi_soft_reserve_enabled(void)
+{
+ return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) && !efi_nosoftreserve;
+}
#define EFI_MMAP_NR_SLACK_SLOTS 8
@@ -211,6 +216,10 @@ efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
if (desc->type != EFI_CONVENTIONAL_MEMORY)
continue;
+ if (efi_soft_reserve_enabled() &&
+ (desc->attribute & EFI_MEMORY_SP))
+ continue;
+
if (desc->num_pages < nr_pages)
continue;
@@ -305,6 +314,10 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
if (desc->type != EFI_CONVENTIONAL_MEMORY)
continue;
+ if (efi_soft_reserve_enabled() &&
+ (desc->attribute & EFI_MEMORY_SP))
+ continue;
+
if (desc->num_pages < nr_pages)
continue;
@@ -489,6 +502,12 @@ efi_status_t efi_parse_options(char const *cmdline)
__novamap = 1;
}
+ if (IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) &&
+ !strncmp(str, "nosoftreserve", 7)) {
+ str += strlen("nosoftreserve");
+ efi_nosoftreserve = 1;
+ }
+
/* Group words together, delimited by "," */
while (*str && *str != ' ' && *str != ',')
str++;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index baa275c56401..959c9650018f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1202,6 +1202,7 @@ extern int __init efi_setup_pcdp_console(char *);
#define EFI_DBG 8 /* Print additional debug info at runtime */
#define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */
#define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
+#define EFI_MEM_NO_SOFT_RESERVE 11 /* Is the kernel configured to ignore soft reservations? */
#ifdef CONFIG_EFI
/*
@@ -1212,6 +1213,8 @@ static inline bool efi_enabled(int feature)
return test_bit(feature, &efi.flags) != 0;
}
extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
+
+bool __pure efi_soft_reserve_enabled(void);
#else
static inline bool efi_enabled(int feature)
{
@@ -1225,6 +1228,11 @@ efi_capsule_pending(int *reset_type)
{
return false;
}
+
+static inline bool efi_soft_reserve_enabled(void)
+{
+ return false;
+}
#endif
extern int efi_status_to_err(efi_status_t status);
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH v6 04/12] efi: Common enable/disable infrastructure for EFI soft reservation
2019-10-09 23:04 ` [PATCH v6 04/12] efi: Common enable/disable infrastructure for EFI soft reservation Dan Williams
@ 2019-10-10 6:36 ` Ard Biesheuvel
0 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-10-10 6:36 UTC (permalink / raw)
To: Dan Williams
Cc: Ingo Molnar, Peter Zijlstra, Vishal L Verma, Dave Hansen,
the arch/x86 maintainers, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
>
> UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> interpretation of the EFI Memory Types as "reserved for a specific
> purpose".
>
> The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> the "soft reserved" designation by allowing some or all of the
> reservation to be recovered as typical memory. This policy can be
> disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> efi=nosoftreserve.
>
> As for this patch, define the common helpers to determine if the
> EFI_MEMORY_SP attribute should be honored. The determination needs to be
> made early to prevent the kernel from being loaded into soft-reserved
> memory, or otherwise allowing early allocations to land there. Follow-on
> changes are needed per architecture to leverage these helpers in their
> respective mem-init paths.
>
> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> ---
> Documentation/admin-guide/kernel-parameters.txt | 9 ++++++++-
> drivers/firmware/efi/Kconfig | 21 +++++++++++++++++++++
> drivers/firmware/efi/efi.c | 9 +++++++++
> drivers/firmware/efi/libstub/efi-stub-helper.c | 19 +++++++++++++++++++
> include/linux/efi.h | 8 ++++++++
> 5 files changed, 65 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index c7ac2f3ac99f..47478a730011 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1168,7 +1168,8 @@
> Format: {"off" | "on" | "skip[mbr]"}
>
> efi= [EFI]
> - Format: { "old_map", "nochunk", "noruntime", "debug" }
> + Format: { "old_map", "nochunk", "noruntime", "debug",
> + "nosoftreserve" }
> old_map [X86-64]: switch to the old ioremap-based EFI
> runtime services mapping. 32-bit still uses this one by
> default.
> @@ -1177,6 +1178,12 @@
> firmware implementations.
> noruntime : disable EFI runtime services support
> debug: enable misc debug output
> + nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
> + attribute may cause the kernel to reserve the
> + memory range for a memory mapping driver to
> + claim. Specify efi=nosoftreserve to disable this
> + reservation and treat the memory by its base type
> + (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
>
> efi_no_storage_paranoia [EFI; X86]
> Using this parameter you can use more than 50% of
> diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
> index 178ee8106828..9fa79f9fa0af 100644
> --- a/drivers/firmware/efi/Kconfig
> +++ b/drivers/firmware/efi/Kconfig
> @@ -75,6 +75,27 @@ config EFI_MAX_FAKE_MEM
> Ranges can be set up to this value using comma-separated list.
> The default value is 8.
>
> +config EFI_SOFT_RESERVE
> + bool "Reserve EFI Specific Purpose Memory"
> + depends on EFI && ACPI_HMAT
> + default ACPI_HMAT
> + help
> + On systems that have mixed performance classes of memory EFI
> + may indicate specific 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,
> + and its base EFI memory type is "conventional" answer Y to
> + arrange for the kernel to reserve it as a "Soft Reserved"
> + resource, and set aside for direct-access (device-dax) by
> + default. The memory range can later be optionally assigned to
> + the page allocator by system administrator policy via the
> + device-dax kmem facility. Say N to have the kernel treat this
> + memory as "System RAM" by default.
> +
> + If unsure, say Y.
> +
> config EFI_PARAMS_FROM_FDT
> bool
> help
> diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
> index 68a4ec24b823..911a58be4a36 100644
> --- a/drivers/firmware/efi/efi.c
> +++ b/drivers/firmware/efi/efi.c
> @@ -81,6 +81,12 @@ bool efi_runtime_disabled(void)
> return disable_runtime;
> }
>
> +bool __pure efi_soft_reserve_enabled(void)
> +{
> + return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) &&
> + !efi_enabled(EFI_MEM_NO_SOFT_RESERVE);
> +}
> +
> static int __init parse_efi_cmdline(char *str)
> {
> if (!str) {
> @@ -94,6 +100,9 @@ static int __init parse_efi_cmdline(char *str)
> if (parse_option_str(str, "noruntime"))
> disable_runtime = true;
>
> + if (parse_option_str(str, "nosoftreserve"))
> + set_bit(EFI_MEM_NO_SOFT_RESERVE, &efi.flags);
> +
> return 0;
> }
> early_param("efi", parse_efi_cmdline);
> diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
> index 3caae7f2cf56..5d901c56ac5f 100644
> --- a/drivers/firmware/efi/libstub/efi-stub-helper.c
> +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
> @@ -32,6 +32,7 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
> static int __section(.data) __nokaslr;
> static int __section(.data) __quiet;
> static int __section(.data) __novamap;
> +static bool __section(.data) efi_nosoftreserve;
>
> int __pure nokaslr(void)
> {
> @@ -45,6 +46,10 @@ int __pure novamap(void)
> {
> return __novamap;
> }
> +bool __pure efi_soft_reserve_enabled(void)
> +{
> + return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) && !efi_nosoftreserve;
> +}
>
> #define EFI_MMAP_NR_SLACK_SLOTS 8
>
> @@ -211,6 +216,10 @@ efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
> if (desc->type != EFI_CONVENTIONAL_MEMORY)
> continue;
>
> + if (efi_soft_reserve_enabled() &&
> + (desc->attribute & EFI_MEMORY_SP))
> + continue;
> +
> if (desc->num_pages < nr_pages)
> continue;
>
> @@ -305,6 +314,10 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
> if (desc->type != EFI_CONVENTIONAL_MEMORY)
> continue;
>
> + if (efi_soft_reserve_enabled() &&
> + (desc->attribute & EFI_MEMORY_SP))
> + continue;
> +
> if (desc->num_pages < nr_pages)
> continue;
>
> @@ -489,6 +502,12 @@ efi_status_t efi_parse_options(char const *cmdline)
> __novamap = 1;
> }
>
> + if (IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) &&
> + !strncmp(str, "nosoftreserve", 7)) {
> + str += strlen("nosoftreserve");
> + efi_nosoftreserve = 1;
> + }
> +
> /* Group words together, delimited by "," */
> while (*str && *str != ' ' && *str != ',')
> str++;
> diff --git a/include/linux/efi.h b/include/linux/efi.h
> index baa275c56401..959c9650018f 100644
> --- a/include/linux/efi.h
> +++ b/include/linux/efi.h
> @@ -1202,6 +1202,7 @@ extern int __init efi_setup_pcdp_console(char *);
> #define EFI_DBG 8 /* Print additional debug info at runtime */
> #define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */
> #define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
> +#define EFI_MEM_NO_SOFT_RESERVE 11 /* Is the kernel configured to ignore soft reservations? */
>
> #ifdef CONFIG_EFI
> /*
> @@ -1212,6 +1213,8 @@ static inline bool efi_enabled(int feature)
> return test_bit(feature, &efi.flags) != 0;
> }
> extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
> +
> +bool __pure efi_soft_reserve_enabled(void);
> #else
> static inline bool efi_enabled(int feature)
> {
> @@ -1225,6 +1228,11 @@ efi_capsule_pending(int *reset_type)
> {
> return false;
> }
> +
> +static inline bool efi_soft_reserve_enabled(void)
> +{
> + return false;
> +}
> #endif
>
> extern int efi_status_to_err(efi_status_t status);
>
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (3 preceding siblings ...)
2019-10-09 23:04 ` [PATCH v6 04/12] efi: Common enable/disable infrastructure for EFI soft reservation Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
2019-10-10 6:44 ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 06/12] arm/efi: EFI soft reservation to memblock Dan Williams
` (6 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: x86, Borislav Petkov, H. Peter Anvin, Darren Hart,
Andy Shevchenko, Andy Lutomirski, Peter Zijlstra,
Thomas Gleixner, Ard Biesheuvel, kbuild test robot, Dave Hansen,
vishal.l.verma, x86, linux-efi, linux-kernel, linux-acpi
UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
interpretation of the EFI Memory Types as "reserved for a specific
purpose".
The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
the "soft reserved" designation by allowing some or all of the
reservation to be recovered as typical memory. This policy can be
disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
efi=nosoftreserve.
This patch introduces 2 new concepts at once given the entanglement
between early boot enumeration relative to memory that can optionally be
reserved from the kernel page allocator by default. The new concepts
are:
- E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
attribute on EFI_CONVENTIONAL memory, update the E820 map with this
new type. Only perform this classification if the
CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
typical ram.
- IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
a device driver to search iomem resources for application specific
memory. Teach the iomem code to identify such ranges as "Soft Reserved".
A follow-on change integrates parsing of the ACPI HMAT to identify the
node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
now, just identify and reserve memory of this type.
Cc: <x86@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Andy Shevchenko <andy@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/x86/boot/compressed/eboot.c | 6 ++++-
arch/x86/boot/compressed/kaslr.c | 4 +++
arch/x86/include/asm/e820/types.h | 8 ++++++
arch/x86/kernel/e820.c | 12 ++++++++-
arch/x86/platform/efi/efi.c | 48 +++++++++++++++++++++++++++++++++----
include/linux/ioport.h | 1 +
6 files changed, 71 insertions(+), 8 deletions(-)
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index d6662fdef300..f3b03229c44c 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -553,7 +553,11 @@ 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 (efi_soft_reserve_enabled() &&
+ (d->attribute & EFI_MEMORY_SP))
+ e820_type = E820_TYPE_SOFT_RESERVED;
+ 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..ff6fa81949cd 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -760,6 +760,10 @@ process_efi_entries(unsigned long minimum, unsigned long image_size)
if (md->type != EFI_CONVENTIONAL_MEMORY)
continue;
+ if (efi_soft_reserve_enabled() &&
+ (md->attribute & EFI_MEMORY_SP))
+ continue;
+
if (efi_mirror_found &&
!(md->attribute & EFI_MEMORY_MORE_RELIABLE))
continue;
diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
index c3aa4b5e49e2..314f75d886d0 100644
--- a/arch/x86/include/asm/e820/types.h
+++ b/arch/x86/include/asm/e820/types.h
@@ -28,6 +28,14 @@ enum e820_type {
*/
E820_TYPE_PRAM = 12,
+ /*
+ * Special-purpose 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_SOFT_RESERVED designation.
+ */
+ E820_TYPE_SOFT_RESERVED = 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 7da2bcd2b8eb..9976106b57ec 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -190,6 +190,7 @@ static void __init e820_print_type(enum e820_type type)
case E820_TYPE_RAM: /* Fall through: */
case E820_TYPE_RESERVED_KERN: pr_cont("usable"); break;
case E820_TYPE_RESERVED: pr_cont("reserved"); break;
+ case E820_TYPE_SOFT_RESERVED: pr_cont("soft reserved"); break;
case E820_TYPE_ACPI: pr_cont("ACPI data"); break;
case E820_TYPE_NVS: pr_cont("ACPI NVS"); break;
case E820_TYPE_UNUSABLE: pr_cont("unusable"); break;
@@ -1037,6 +1038,7 @@ static const char *__init e820_type_to_string(struct e820_entry *entry)
case E820_TYPE_PRAM: return "Persistent Memory (legacy)";
case E820_TYPE_PMEM: return "Persistent Memory";
case E820_TYPE_RESERVED: return "Reserved";
+ case E820_TYPE_SOFT_RESERVED: return "Soft Reserved";
default: return "Unknown E820 type";
}
}
@@ -1052,6 +1054,7 @@ static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
case E820_TYPE_PRAM: /* Fall-through: */
case E820_TYPE_PMEM: /* Fall-through: */
case E820_TYPE_RESERVED: /* Fall-through: */
+ case E820_TYPE_SOFT_RESERVED: /* Fall-through: */
default: return IORESOURCE_MEM;
}
}
@@ -1064,6 +1067,7 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY;
case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
case E820_TYPE_RESERVED: return IORES_DESC_RESERVED;
+ case E820_TYPE_SOFT_RESERVED: return IORES_DESC_SOFT_RESERVED;
case E820_TYPE_RESERVED_KERN: /* Fall-through: */
case E820_TYPE_RAM: /* Fall-through: */
case E820_TYPE_UNUSABLE: /* Fall-through: */
@@ -1078,11 +1082,12 @@ 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_SOFT_RESERVED:
case E820_TYPE_PRAM:
case E820_TYPE_PMEM:
return false;
@@ -1285,6 +1290,9 @@ void __init e820__memblock_setup(void)
if (end != (resource_size_t)end)
continue;
+ if (entry->type == E820_TYPE_SOFT_RESERVED)
+ memblock_reserve(entry->addr, entry->size);
+
if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
continue;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 0bb58eb33ca0..c96657993167 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -151,10 +151,18 @@ void __init efi_find_mirror(void)
* more than the max 128 entries that can fit in the e820 legacy
* (zeropage) memory map.
*/
+enum add_efi_mode {
+ ADD_EFI_ALL,
+ ADD_EFI_SOFT_RESERVED,
+};
-static void __init do_add_efi_memmap(void)
+static void __init do_add_efi_memmap(enum add_efi_mode mode)
{
efi_memory_desc_t *md;
+ int add = 0;
+
+ if (!efi_enabled(EFI_MEMMAP))
+ return;
for_each_efi_memory_desc(md) {
unsigned long long start = md->phys_addr;
@@ -167,7 +175,10 @@ 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 (efi_soft_reserve_enabled()
+ && (md->attribute & EFI_MEMORY_SP))
+ e820_type = E820_TYPE_SOFT_RESERVED;
+ else if (md->attribute & EFI_MEMORY_WB)
e820_type = E820_TYPE_RAM;
else
e820_type = E820_TYPE_RESERVED;
@@ -193,9 +204,17 @@ static void __init do_add_efi_memmap(void)
e820_type = E820_TYPE_RESERVED;
break;
}
+
+ if (e820_type == E820_TYPE_SOFT_RESERVED)
+ /* always add E820_TYPE_SOFT_RESERVED */;
+ else if (mode == ADD_EFI_SOFT_RESERVED)
+ continue;
+
+ add++;
e820__range_add(start, size, e820_type);
}
- e820__update_table(e820_table);
+ if (add)
+ e820__update_table(e820_table);
}
int __init efi_memblock_x86_reserve_range(void)
@@ -227,8 +246,18 @@ int __init efi_memblock_x86_reserve_range(void)
if (rv)
return rv;
- if (add_efi_memmap)
- do_add_efi_memmap();
+ if (add_efi_memmap) {
+ do_add_efi_memmap(ADD_EFI_ALL);
+ } else {
+ /*
+ * Given add_efi_memmap defaults to 0 and there there is no e820
+ * mechanism for soft-reserved memory. Explicitly scan for
+ * soft-reserved memory. Otherwise, the mechanism to disable the
+ * kernel's consideration of EFI_MEMORY_SP is the
+ * efi=nosoftreserve option.
+ */
+ do_add_efi_memmap(ADD_EFI_SOFT_RESERVED);
+ }
WARN(efi.memmap.desc_version != 1,
"Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
@@ -781,6 +810,15 @@ static bool should_map_region(efi_memory_desc_t *md)
if (IS_ENABLED(CONFIG_X86_32))
return false;
+ /*
+ * EFI specific purpose memory may be reserved by default
+ * depending on kernel config and boot options.
+ */
+ if (md->type == EFI_CONVENTIONAL_MEMORY &&
+ efi_soft_reserve_enabled() &&
+ (md->attribute & EFI_MEMORY_SP))
+ 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/ioport.h b/include/linux/ioport.h
index 7bddddfc76d6..a9b9170b5dd2 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -134,6 +134,7 @@ enum {
IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5,
IORES_DESC_DEVICE_PRIVATE_MEMORY = 6,
IORES_DESC_RESERVED = 7,
+ IORES_DESC_SOFT_RESERVED = 8,
};
/*
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-09 23:05 ` [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration Dan Williams
@ 2019-10-10 6:44 ` Ard Biesheuvel
2019-10-10 18:31 ` Dan Williams
0 siblings, 1 reply; 23+ messages in thread
From: Ard Biesheuvel @ 2019-10-10 6:44 UTC (permalink / raw)
To: Dan Williams
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Darren Hart, Andy Shevchenko, Andy Lutomirski,
Peter Zijlstra, Thomas Gleixner, kbuild test robot, Dave Hansen,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
>
> UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> interpretation of the EFI Memory Types as "reserved for a specific
> purpose".
>
> The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> the "soft reserved" designation by allowing some or all of the
> reservation to be recovered as typical memory. This policy can be
> disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> efi=nosoftreserve.
>
> This patch introduces 2 new concepts at once given the entanglement
> between early boot enumeration relative to memory that can optionally be
> reserved from the kernel page allocator by default. The new concepts
> are:
>
> - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
> attribute on EFI_CONVENTIONAL memory, update the E820 map with this
> new type. Only perform this classification if the
> CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
> typical ram.
>
> - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
> a device driver to search iomem resources for application specific
> memory. Teach the iomem code to identify such ranges as "Soft Reserved".
>
> A follow-on change integrates parsing of the ACPI HMAT to identify the
> node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
> now, just identify and reserve memory of this type.
>
> Cc: <x86@kernel.org>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> Cc: Darren Hart <dvhart@infradead.org>
> Cc: Andy Shevchenko <andy@infradead.org>
> Cc: Andy Lutomirski <luto@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> Reported-by: kbuild test robot <lkp@intel.com>
> Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
For the EFI changes
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
although I must admit I don't follow the enum add_efi_mode logic 100%
> ---
> arch/x86/boot/compressed/eboot.c | 6 ++++-
> arch/x86/boot/compressed/kaslr.c | 4 +++
> arch/x86/include/asm/e820/types.h | 8 ++++++
> arch/x86/kernel/e820.c | 12 ++++++++-
> arch/x86/platform/efi/efi.c | 48 +++++++++++++++++++++++++++++++++----
> include/linux/ioport.h | 1 +
> 6 files changed, 71 insertions(+), 8 deletions(-)
>
> diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
> index d6662fdef300..f3b03229c44c 100644
> --- a/arch/x86/boot/compressed/eboot.c
> +++ b/arch/x86/boot/compressed/eboot.c
> @@ -553,7 +553,11 @@ 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 (efi_soft_reserve_enabled() &&
> + (d->attribute & EFI_MEMORY_SP))
> + e820_type = E820_TYPE_SOFT_RESERVED;
> + 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..ff6fa81949cd 100644
> --- a/arch/x86/boot/compressed/kaslr.c
> +++ b/arch/x86/boot/compressed/kaslr.c
> @@ -760,6 +760,10 @@ process_efi_entries(unsigned long minimum, unsigned long image_size)
> if (md->type != EFI_CONVENTIONAL_MEMORY)
> continue;
>
> + if (efi_soft_reserve_enabled() &&
> + (md->attribute & EFI_MEMORY_SP))
> + continue;
> +
> if (efi_mirror_found &&
> !(md->attribute & EFI_MEMORY_MORE_RELIABLE))
> continue;
> diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
> index c3aa4b5e49e2..314f75d886d0 100644
> --- a/arch/x86/include/asm/e820/types.h
> +++ b/arch/x86/include/asm/e820/types.h
> @@ -28,6 +28,14 @@ enum e820_type {
> */
> E820_TYPE_PRAM = 12,
>
> + /*
> + * Special-purpose 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_SOFT_RESERVED designation.
> + */
> + E820_TYPE_SOFT_RESERVED = 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 7da2bcd2b8eb..9976106b57ec 100644
> --- a/arch/x86/kernel/e820.c
> +++ b/arch/x86/kernel/e820.c
> @@ -190,6 +190,7 @@ static void __init e820_print_type(enum e820_type type)
> case E820_TYPE_RAM: /* Fall through: */
> case E820_TYPE_RESERVED_KERN: pr_cont("usable"); break;
> case E820_TYPE_RESERVED: pr_cont("reserved"); break;
> + case E820_TYPE_SOFT_RESERVED: pr_cont("soft reserved"); break;
> case E820_TYPE_ACPI: pr_cont("ACPI data"); break;
> case E820_TYPE_NVS: pr_cont("ACPI NVS"); break;
> case E820_TYPE_UNUSABLE: pr_cont("unusable"); break;
> @@ -1037,6 +1038,7 @@ static const char *__init e820_type_to_string(struct e820_entry *entry)
> case E820_TYPE_PRAM: return "Persistent Memory (legacy)";
> case E820_TYPE_PMEM: return "Persistent Memory";
> case E820_TYPE_RESERVED: return "Reserved";
> + case E820_TYPE_SOFT_RESERVED: return "Soft Reserved";
> default: return "Unknown E820 type";
> }
> }
> @@ -1052,6 +1054,7 @@ static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
> case E820_TYPE_PRAM: /* Fall-through: */
> case E820_TYPE_PMEM: /* Fall-through: */
> case E820_TYPE_RESERVED: /* Fall-through: */
> + case E820_TYPE_SOFT_RESERVED: /* Fall-through: */
> default: return IORESOURCE_MEM;
> }
> }
> @@ -1064,6 +1067,7 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
> case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY;
> case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
> case E820_TYPE_RESERVED: return IORES_DESC_RESERVED;
> + case E820_TYPE_SOFT_RESERVED: return IORES_DESC_SOFT_RESERVED;
> case E820_TYPE_RESERVED_KERN: /* Fall-through: */
> case E820_TYPE_RAM: /* Fall-through: */
> case E820_TYPE_UNUSABLE: /* Fall-through: */
> @@ -1078,11 +1082,12 @@ 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_SOFT_RESERVED:
> case E820_TYPE_PRAM:
> case E820_TYPE_PMEM:
> return false;
> @@ -1285,6 +1290,9 @@ void __init e820__memblock_setup(void)
> if (end != (resource_size_t)end)
> continue;
>
> + if (entry->type == E820_TYPE_SOFT_RESERVED)
> + memblock_reserve(entry->addr, entry->size);
> +
> if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
> continue;
>
> diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
> index 0bb58eb33ca0..c96657993167 100644
> --- a/arch/x86/platform/efi/efi.c
> +++ b/arch/x86/platform/efi/efi.c
> @@ -151,10 +151,18 @@ void __init efi_find_mirror(void)
> * more than the max 128 entries that can fit in the e820 legacy
> * (zeropage) memory map.
> */
> +enum add_efi_mode {
> + ADD_EFI_ALL,
> + ADD_EFI_SOFT_RESERVED,
> +};
>
> -static void __init do_add_efi_memmap(void)
> +static void __init do_add_efi_memmap(enum add_efi_mode mode)
> {
> efi_memory_desc_t *md;
> + int add = 0;
> +
> + if (!efi_enabled(EFI_MEMMAP))
> + return;
>
> for_each_efi_memory_desc(md) {
> unsigned long long start = md->phys_addr;
> @@ -167,7 +175,10 @@ 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 (efi_soft_reserve_enabled()
> + && (md->attribute & EFI_MEMORY_SP))
> + e820_type = E820_TYPE_SOFT_RESERVED;
> + else if (md->attribute & EFI_MEMORY_WB)
> e820_type = E820_TYPE_RAM;
> else
> e820_type = E820_TYPE_RESERVED;
> @@ -193,9 +204,17 @@ static void __init do_add_efi_memmap(void)
> e820_type = E820_TYPE_RESERVED;
> break;
> }
> +
> + if (e820_type == E820_TYPE_SOFT_RESERVED)
> + /* always add E820_TYPE_SOFT_RESERVED */;
> + else if (mode == ADD_EFI_SOFT_RESERVED)
> + continue;
> +
> + add++;
> e820__range_add(start, size, e820_type);
> }
> - e820__update_table(e820_table);
> + if (add)
> + e820__update_table(e820_table);
> }
>
> int __init efi_memblock_x86_reserve_range(void)
> @@ -227,8 +246,18 @@ int __init efi_memblock_x86_reserve_range(void)
> if (rv)
> return rv;
>
> - if (add_efi_memmap)
> - do_add_efi_memmap();
> + if (add_efi_memmap) {
> + do_add_efi_memmap(ADD_EFI_ALL);
> + } else {
> + /*
> + * Given add_efi_memmap defaults to 0 and there there is no e820
> + * mechanism for soft-reserved memory. Explicitly scan for
> + * soft-reserved memory. Otherwise, the mechanism to disable the
> + * kernel's consideration of EFI_MEMORY_SP is the
> + * efi=nosoftreserve option.
> + */
> + do_add_efi_memmap(ADD_EFI_SOFT_RESERVED);
> + }
>
> WARN(efi.memmap.desc_version != 1,
> "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
> @@ -781,6 +810,15 @@ static bool should_map_region(efi_memory_desc_t *md)
> if (IS_ENABLED(CONFIG_X86_32))
> return false;
>
> + /*
> + * EFI specific purpose memory may be reserved by default
> + * depending on kernel config and boot options.
> + */
> + if (md->type == EFI_CONVENTIONAL_MEMORY &&
> + efi_soft_reserve_enabled() &&
> + (md->attribute & EFI_MEMORY_SP))
> + 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/ioport.h b/include/linux/ioport.h
> index 7bddddfc76d6..a9b9170b5dd2 100644
> --- a/include/linux/ioport.h
> +++ b/include/linux/ioport.h
> @@ -134,6 +134,7 @@ enum {
> IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5,
> IORES_DESC_DEVICE_PRIVATE_MEMORY = 6,
> IORES_DESC_RESERVED = 7,
> + IORES_DESC_SOFT_RESERVED = 8,
> };
>
> /*
>
^ permalink raw reply [flat|nested] 23+ messages in thread* Re: [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-10 6:44 ` Ard Biesheuvel
@ 2019-10-10 18:31 ` Dan Williams
2019-10-10 18:40 ` Ard Biesheuvel
0 siblings, 1 reply; 23+ messages in thread
From: Dan Williams @ 2019-10-10 18:31 UTC (permalink / raw)
To: Ard Biesheuvel
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Darren Hart, Andy Shevchenko, Andy Lutomirski,
Peter Zijlstra, Thomas Gleixner, kbuild test robot, Dave Hansen,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Wed, Oct 9, 2019 at 11:45 PM Ard Biesheuvel
<ard.biesheuvel@linaro.org> wrote:
>
> On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
> >
> > UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> > interpretation of the EFI Memory Types as "reserved for a specific
> > purpose".
> >
> > The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> > the "soft reserved" designation by allowing some or all of the
> > reservation to be recovered as typical memory. This policy can be
> > disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> > efi=nosoftreserve.
> >
> > This patch introduces 2 new concepts at once given the entanglement
> > between early boot enumeration relative to memory that can optionally be
> > reserved from the kernel page allocator by default. The new concepts
> > are:
> >
> > - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
> > attribute on EFI_CONVENTIONAL memory, update the E820 map with this
> > new type. Only perform this classification if the
> > CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
> > typical ram.
> >
> > - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
> > a device driver to search iomem resources for application specific
> > memory. Teach the iomem code to identify such ranges as "Soft Reserved".
> >
> > A follow-on change integrates parsing of the ACPI HMAT to identify the
> > node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
> > now, just identify and reserve memory of this type.
> >
> > Cc: <x86@kernel.org>
> > Cc: Borislav Petkov <bp@alien8.de>
> > Cc: Ingo Molnar <mingo@redhat.com>
> > Cc: "H. Peter Anvin" <hpa@zytor.com>
> > Cc: Darren Hart <dvhart@infradead.org>
> > Cc: Andy Shevchenko <andy@infradead.org>
> > Cc: Andy Lutomirski <luto@kernel.org>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Thomas Gleixner <tglx@linutronix.de>
> > Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > Reported-by: kbuild test robot <lkp@intel.com>
> > Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> > Signed-off-by: Dan Williams <dan.j.williams@intel.com>
>
> For the EFI changes
>
> Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
>
> although I must admit I don't follow the enum add_efi_mode logic 100%
I'm open to suggestions as I'm not sure it's the best possible
organization. The do_add_efi_memmap() routine has the logic to
translate EFI to E820, but unless "add_efi_memmap" is specified on the
kernel command line the EFI memory map is ignored. For
soft-reservation support I want to reuse do_add_efi_memmap(), but
otherwise avoid any other side effects of considering the EFI map.
What I'm missing is the rationale for why "add_efi_memmap" is required
before considering the EFI memory map.
If there is a negative side effect to always using the EFI map then
the new "add_efi_mode" designation constrains it to just the
soft-reservation case.
It seems for historical reasons the full EFI memmap requires explicit opt-in:
200001eb140e x86 boot: only pick up additional EFI memmap if add_efi_memmap flag
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-10 18:31 ` Dan Williams
@ 2019-10-10 18:40 ` Ard Biesheuvel
2019-10-11 2:39 ` Dan Williams
0 siblings, 1 reply; 23+ messages in thread
From: Ard Biesheuvel @ 2019-10-10 18:40 UTC (permalink / raw)
To: Dan Williams
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Darren Hart, Andy Shevchenko, Andy Lutomirski,
Peter Zijlstra, Thomas Gleixner, kbuild test robot, Dave Hansen,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Thu, 10 Oct 2019 at 20:31, Dan Williams <dan.j.williams@intel.com> wrote:
>
> On Wed, Oct 9, 2019 at 11:45 PM Ard Biesheuvel
> <ard.biesheuvel@linaro.org> wrote:
> >
> > On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
> > >
> > > UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> > > interpretation of the EFI Memory Types as "reserved for a specific
> > > purpose".
> > >
> > > The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> > > the "soft reserved" designation by allowing some or all of the
> > > reservation to be recovered as typical memory. This policy can be
> > > disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> > > efi=nosoftreserve.
> > >
> > > This patch introduces 2 new concepts at once given the entanglement
> > > between early boot enumeration relative to memory that can optionally be
> > > reserved from the kernel page allocator by default. The new concepts
> > > are:
> > >
> > > - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
> > > attribute on EFI_CONVENTIONAL memory, update the E820 map with this
> > > new type. Only perform this classification if the
> > > CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
> > > typical ram.
> > >
> > > - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
> > > a device driver to search iomem resources for application specific
> > > memory. Teach the iomem code to identify such ranges as "Soft Reserved".
> > >
> > > A follow-on change integrates parsing of the ACPI HMAT to identify the
> > > node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
> > > now, just identify and reserve memory of this type.
> > >
> > > Cc: <x86@kernel.org>
> > > Cc: Borislav Petkov <bp@alien8.de>
> > > Cc: Ingo Molnar <mingo@redhat.com>
> > > Cc: "H. Peter Anvin" <hpa@zytor.com>
> > > Cc: Darren Hart <dvhart@infradead.org>
> > > Cc: Andy Shevchenko <andy@infradead.org>
> > > Cc: Andy Lutomirski <luto@kernel.org>
> > > Cc: Peter Zijlstra <peterz@infradead.org>
> > > Cc: Thomas Gleixner <tglx@linutronix.de>
> > > Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > Reported-by: kbuild test robot <lkp@intel.com>
> > > Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> > > Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> >
> > For the EFI changes
> >
> > Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> >
> > although I must admit I don't follow the enum add_efi_mode logic 100%
>
> I'm open to suggestions as I'm not sure it's the best possible
> organization. The do_add_efi_memmap() routine has the logic to
> translate EFI to E820, but unless "add_efi_memmap" is specified on the
> kernel command line the EFI memory map is ignored. For
> soft-reservation support I want to reuse do_add_efi_memmap(), but
> otherwise avoid any other side effects of considering the EFI map.
> What I'm missing is the rationale for why "add_efi_memmap" is required
> before considering the EFI memory map.
>
> If there is a negative side effect to always using the EFI map then
> the new "add_efi_mode" designation constrains it to just the
> soft-reservation case.
>
Could we make the presence of any EFI_MEMORY_SP regions imply
add_efi_memmap? That way, it is guaranteed that we don't regress
existing systems, while establishing clear and unambiguous semantics
for new systems that rely on these changes in order to be able to use
the special purpose memory as intended.
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-10 18:40 ` Ard Biesheuvel
@ 2019-10-11 2:39 ` Dan Williams
2019-10-11 5:52 ` Ard Biesheuvel
0 siblings, 1 reply; 23+ messages in thread
From: Dan Williams @ 2019-10-11 2:39 UTC (permalink / raw)
To: Ard Biesheuvel
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Darren Hart, Andy Shevchenko, Andy Lutomirski,
Peter Zijlstra, Thomas Gleixner, kbuild test robot, Dave Hansen,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Thu, Oct 10, 2019 at 11:41 AM Ard Biesheuvel
<ard.biesheuvel@linaro.org> wrote:
>
> On Thu, 10 Oct 2019 at 20:31, Dan Williams <dan.j.williams@intel.com> wrote:
> >
> > On Wed, Oct 9, 2019 at 11:45 PM Ard Biesheuvel
> > <ard.biesheuvel@linaro.org> wrote:
> > >
> > > On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
> > > >
> > > > UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> > > > interpretation of the EFI Memory Types as "reserved for a specific
> > > > purpose".
> > > >
> > > > The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> > > > the "soft reserved" designation by allowing some or all of the
> > > > reservation to be recovered as typical memory. This policy can be
> > > > disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> > > > efi=nosoftreserve.
> > > >
> > > > This patch introduces 2 new concepts at once given the entanglement
> > > > between early boot enumeration relative to memory that can optionally be
> > > > reserved from the kernel page allocator by default. The new concepts
> > > > are:
> > > >
> > > > - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
> > > > attribute on EFI_CONVENTIONAL memory, update the E820 map with this
> > > > new type. Only perform this classification if the
> > > > CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
> > > > typical ram.
> > > >
> > > > - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
> > > > a device driver to search iomem resources for application specific
> > > > memory. Teach the iomem code to identify such ranges as "Soft Reserved".
> > > >
> > > > A follow-on change integrates parsing of the ACPI HMAT to identify the
> > > > node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
> > > > now, just identify and reserve memory of this type.
> > > >
> > > > Cc: <x86@kernel.org>
> > > > Cc: Borislav Petkov <bp@alien8.de>
> > > > Cc: Ingo Molnar <mingo@redhat.com>
> > > > Cc: "H. Peter Anvin" <hpa@zytor.com>
> > > > Cc: Darren Hart <dvhart@infradead.org>
> > > > Cc: Andy Shevchenko <andy@infradead.org>
> > > > Cc: Andy Lutomirski <luto@kernel.org>
> > > > Cc: Peter Zijlstra <peterz@infradead.org>
> > > > Cc: Thomas Gleixner <tglx@linutronix.de>
> > > > Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > > Reported-by: kbuild test robot <lkp@intel.com>
> > > > Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> > > > Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> > >
> > > For the EFI changes
> > >
> > > Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > >
> > > although I must admit I don't follow the enum add_efi_mode logic 100%
> >
> > I'm open to suggestions as I'm not sure it's the best possible
> > organization. The do_add_efi_memmap() routine has the logic to
> > translate EFI to E820, but unless "add_efi_memmap" is specified on the
> > kernel command line the EFI memory map is ignored. For
> > soft-reservation support I want to reuse do_add_efi_memmap(), but
> > otherwise avoid any other side effects of considering the EFI map.
> > What I'm missing is the rationale for why "add_efi_memmap" is required
> > before considering the EFI memory map.
> >
> > If there is a negative side effect to always using the EFI map then
> > the new "add_efi_mode" designation constrains it to just the
> > soft-reservation case.
> >
>
> Could we make the presence of any EFI_MEMORY_SP regions imply
> add_efi_memmap? That way, it is guaranteed that we don't regress
> existing systems, while establishing clear and unambiguous semantics
> for new systems that rely on these changes in order to be able to use
> the special purpose memory as intended.
In fact that's how it works. EFI_MEMORY_SP is unconditionally added.
Other EFI memory types are optionally added with the add_efi_memmap
option.
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-11 2:39 ` Dan Williams
@ 2019-10-11 5:52 ` Ard Biesheuvel
2019-10-11 14:35 ` Dan Williams
0 siblings, 1 reply; 23+ messages in thread
From: Ard Biesheuvel @ 2019-10-11 5:52 UTC (permalink / raw)
To: Dan Williams
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Darren Hart, Andy Shevchenko, Andy Lutomirski,
Peter Zijlstra, Thomas Gleixner, kbuild test robot, Dave Hansen,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Fri, 11 Oct 2019 at 04:39, Dan Williams <dan.j.williams@intel.com> wrote:
>
> On Thu, Oct 10, 2019 at 11:41 AM Ard Biesheuvel
> <ard.biesheuvel@linaro.org> wrote:
> >
> > On Thu, 10 Oct 2019 at 20:31, Dan Williams <dan.j.williams@intel.com> wrote:
> > >
> > > On Wed, Oct 9, 2019 at 11:45 PM Ard Biesheuvel
> > > <ard.biesheuvel@linaro.org> wrote:
> > > >
> > > > On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
> > > > >
> > > > > UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> > > > > interpretation of the EFI Memory Types as "reserved for a specific
> > > > > purpose".
> > > > >
> > > > > The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> > > > > the "soft reserved" designation by allowing some or all of the
> > > > > reservation to be recovered as typical memory. This policy can be
> > > > > disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> > > > > efi=nosoftreserve.
> > > > >
> > > > > This patch introduces 2 new concepts at once given the entanglement
> > > > > between early boot enumeration relative to memory that can optionally be
> > > > > reserved from the kernel page allocator by default. The new concepts
> > > > > are:
> > > > >
> > > > > - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
> > > > > attribute on EFI_CONVENTIONAL memory, update the E820 map with this
> > > > > new type. Only perform this classification if the
> > > > > CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
> > > > > typical ram.
> > > > >
> > > > > - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
> > > > > a device driver to search iomem resources for application specific
> > > > > memory. Teach the iomem code to identify such ranges as "Soft Reserved".
> > > > >
> > > > > A follow-on change integrates parsing of the ACPI HMAT to identify the
> > > > > node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
> > > > > now, just identify and reserve memory of this type.
> > > > >
> > > > > Cc: <x86@kernel.org>
> > > > > Cc: Borislav Petkov <bp@alien8.de>
> > > > > Cc: Ingo Molnar <mingo@redhat.com>
> > > > > Cc: "H. Peter Anvin" <hpa@zytor.com>
> > > > > Cc: Darren Hart <dvhart@infradead.org>
> > > > > Cc: Andy Shevchenko <andy@infradead.org>
> > > > > Cc: Andy Lutomirski <luto@kernel.org>
> > > > > Cc: Peter Zijlstra <peterz@infradead.org>
> > > > > Cc: Thomas Gleixner <tglx@linutronix.de>
> > > > > Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > > > Reported-by: kbuild test robot <lkp@intel.com>
> > > > > Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> > > > > Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> > > >
> > > > For the EFI changes
> > > >
> > > > Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > >
> > > > although I must admit I don't follow the enum add_efi_mode logic 100%
> > >
> > > I'm open to suggestions as I'm not sure it's the best possible
> > > organization. The do_add_efi_memmap() routine has the logic to
> > > translate EFI to E820, but unless "add_efi_memmap" is specified on the
> > > kernel command line the EFI memory map is ignored. For
> > > soft-reservation support I want to reuse do_add_efi_memmap(), but
> > > otherwise avoid any other side effects of considering the EFI map.
> > > What I'm missing is the rationale for why "add_efi_memmap" is required
> > > before considering the EFI memory map.
> > >
> > > If there is a negative side effect to always using the EFI map then
> > > the new "add_efi_mode" designation constrains it to just the
> > > soft-reservation case.
> > >
> >
> > Could we make the presence of any EFI_MEMORY_SP regions imply
> > add_efi_memmap? That way, it is guaranteed that we don't regress
> > existing systems, while establishing clear and unambiguous semantics
> > for new systems that rely on these changes in order to be able to use
> > the special purpose memory as intended.
>
> In fact that's how it works. EFI_MEMORY_SP is unconditionally added.
> Other EFI memory types are optionally added with the add_efi_memmap
> option.
That is not what I meant.
Why not behave as if 'add_efi_memmap' was passed if any EFI_MEMORY_SP
regions exist?
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-11 5:52 ` Ard Biesheuvel
@ 2019-10-11 14:35 ` Dan Williams
2019-10-11 14:38 ` Ard Biesheuvel
0 siblings, 1 reply; 23+ messages in thread
From: Dan Williams @ 2019-10-11 14:35 UTC (permalink / raw)
To: Ard Biesheuvel
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Darren Hart, Andy Shevchenko, Andy Lutomirski,
Peter Zijlstra, Thomas Gleixner, kbuild test robot, Dave Hansen,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Thu, Oct 10, 2019 at 10:52 PM Ard Biesheuvel
<ard.biesheuvel@linaro.org> wrote:
>
> On Fri, 11 Oct 2019 at 04:39, Dan Williams <dan.j.williams@intel.com> wrote:
> >
> > On Thu, Oct 10, 2019 at 11:41 AM Ard Biesheuvel
> > <ard.biesheuvel@linaro.org> wrote:
> > >
> > > On Thu, 10 Oct 2019 at 20:31, Dan Williams <dan.j.williams@intel.com> wrote:
> > > >
> > > > On Wed, Oct 9, 2019 at 11:45 PM Ard Biesheuvel
> > > > <ard.biesheuvel@linaro.org> wrote:
> > > > >
> > > > > On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
> > > > > >
> > > > > > UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> > > > > > interpretation of the EFI Memory Types as "reserved for a specific
> > > > > > purpose".
> > > > > >
> > > > > > The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> > > > > > the "soft reserved" designation by allowing some or all of the
> > > > > > reservation to be recovered as typical memory. This policy can be
> > > > > > disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> > > > > > efi=nosoftreserve.
> > > > > >
> > > > > > This patch introduces 2 new concepts at once given the entanglement
> > > > > > between early boot enumeration relative to memory that can optionally be
> > > > > > reserved from the kernel page allocator by default. The new concepts
> > > > > > are:
> > > > > >
> > > > > > - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
> > > > > > attribute on EFI_CONVENTIONAL memory, update the E820 map with this
> > > > > > new type. Only perform this classification if the
> > > > > > CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
> > > > > > typical ram.
> > > > > >
> > > > > > - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
> > > > > > a device driver to search iomem resources for application specific
> > > > > > memory. Teach the iomem code to identify such ranges as "Soft Reserved".
> > > > > >
> > > > > > A follow-on change integrates parsing of the ACPI HMAT to identify the
> > > > > > node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
> > > > > > now, just identify and reserve memory of this type.
> > > > > >
> > > > > > Cc: <x86@kernel.org>
> > > > > > Cc: Borislav Petkov <bp@alien8.de>
> > > > > > Cc: Ingo Molnar <mingo@redhat.com>
> > > > > > Cc: "H. Peter Anvin" <hpa@zytor.com>
> > > > > > Cc: Darren Hart <dvhart@infradead.org>
> > > > > > Cc: Andy Shevchenko <andy@infradead.org>
> > > > > > Cc: Andy Lutomirski <luto@kernel.org>
> > > > > > Cc: Peter Zijlstra <peterz@infradead.org>
> > > > > > Cc: Thomas Gleixner <tglx@linutronix.de>
> > > > > > Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > > > > Reported-by: kbuild test robot <lkp@intel.com>
> > > > > > Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> > > > > > Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> > > > >
> > > > > For the EFI changes
> > > > >
> > > > > Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > > >
> > > > > although I must admit I don't follow the enum add_efi_mode logic 100%
> > > >
> > > > I'm open to suggestions as I'm not sure it's the best possible
> > > > organization. The do_add_efi_memmap() routine has the logic to
> > > > translate EFI to E820, but unless "add_efi_memmap" is specified on the
> > > > kernel command line the EFI memory map is ignored. For
> > > > soft-reservation support I want to reuse do_add_efi_memmap(), but
> > > > otherwise avoid any other side effects of considering the EFI map.
> > > > What I'm missing is the rationale for why "add_efi_memmap" is required
> > > > before considering the EFI memory map.
> > > >
> > > > If there is a negative side effect to always using the EFI map then
> > > > the new "add_efi_mode" designation constrains it to just the
> > > > soft-reservation case.
> > > >
> > >
> > > Could we make the presence of any EFI_MEMORY_SP regions imply
> > > add_efi_memmap? That way, it is guaranteed that we don't regress
> > > existing systems, while establishing clear and unambiguous semantics
> > > for new systems that rely on these changes in order to be able to use
> > > the special purpose memory as intended.
> >
> > In fact that's how it works. EFI_MEMORY_SP is unconditionally added.
> > Other EFI memory types are optionally added with the add_efi_memmap
> > option.
>
> That is not what I meant.
>
> Why not behave as if 'add_efi_memmap' was passed if any EFI_MEMORY_SP
> regions exist?
Hmm, ok, on the assumption that any platform that is modern enough to
specify EFI_MEMORY_SP likely does not need the opt-in? I can get on
board with that. It's also simple enough to undo if it causes problems
in practice.
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration
2019-10-11 14:35 ` Dan Williams
@ 2019-10-11 14:38 ` Ard Biesheuvel
0 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-10-11 14:38 UTC (permalink / raw)
To: Dan Williams
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Darren Hart, Andy Shevchenko, Andy Lutomirski,
Peter Zijlstra, Thomas Gleixner, kbuild test robot, Dave Hansen,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Fri, 11 Oct 2019 at 16:35, Dan Williams <dan.j.williams@intel.com> wrote:
>
> On Thu, Oct 10, 2019 at 10:52 PM Ard Biesheuvel
> <ard.biesheuvel@linaro.org> wrote:
> >
> > On Fri, 11 Oct 2019 at 04:39, Dan Williams <dan.j.williams@intel.com> wrote:
> > >
> > > On Thu, Oct 10, 2019 at 11:41 AM Ard Biesheuvel
> > > <ard.biesheuvel@linaro.org> wrote:
> > > >
> > > > On Thu, 10 Oct 2019 at 20:31, Dan Williams <dan.j.williams@intel.com> wrote:
> > > > >
> > > > > On Wed, Oct 9, 2019 at 11:45 PM Ard Biesheuvel
> > > > > <ard.biesheuvel@linaro.org> wrote:
> > > > > >
> > > > > > On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
> > > > > > >
> > > > > > > UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> > > > > > > interpretation of the EFI Memory Types as "reserved for a specific
> > > > > > > purpose".
> > > > > > >
> > > > > > > The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> > > > > > > the "soft reserved" designation by allowing some or all of the
> > > > > > > reservation to be recovered as typical memory. This policy can be
> > > > > > > disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> > > > > > > efi=nosoftreserve.
> > > > > > >
> > > > > > > This patch introduces 2 new concepts at once given the entanglement
> > > > > > > between early boot enumeration relative to memory that can optionally be
> > > > > > > reserved from the kernel page allocator by default. The new concepts
> > > > > > > are:
> > > > > > >
> > > > > > > - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP
> > > > > > > attribute on EFI_CONVENTIONAL memory, update the E820 map with this
> > > > > > > new type. Only perform this classification if the
> > > > > > > CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as
> > > > > > > typical ram.
> > > > > > >
> > > > > > > - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for
> > > > > > > a device driver to search iomem resources for application specific
> > > > > > > memory. Teach the iomem code to identify such ranges as "Soft Reserved".
> > > > > > >
> > > > > > > A follow-on change integrates parsing of the ACPI HMAT to identify the
> > > > > > > node and sub-range boundaries of EFI_MEMORY_SP designated memory. For
> > > > > > > now, just identify and reserve memory of this type.
> > > > > > >
> > > > > > > Cc: <x86@kernel.org>
> > > > > > > Cc: Borislav Petkov <bp@alien8.de>
> > > > > > > Cc: Ingo Molnar <mingo@redhat.com>
> > > > > > > Cc: "H. Peter Anvin" <hpa@zytor.com>
> > > > > > > Cc: Darren Hart <dvhart@infradead.org>
> > > > > > > Cc: Andy Shevchenko <andy@infradead.org>
> > > > > > > Cc: Andy Lutomirski <luto@kernel.org>
> > > > > > > Cc: Peter Zijlstra <peterz@infradead.org>
> > > > > > > Cc: Thomas Gleixner <tglx@linutronix.de>
> > > > > > > Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > > > > > Reported-by: kbuild test robot <lkp@intel.com>
> > > > > > > Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> > > > > > > Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> > > > > >
> > > > > > For the EFI changes
> > > > > >
> > > > > > Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> > > > > >
> > > > > > although I must admit I don't follow the enum add_efi_mode logic 100%
> > > > >
> > > > > I'm open to suggestions as I'm not sure it's the best possible
> > > > > organization. The do_add_efi_memmap() routine has the logic to
> > > > > translate EFI to E820, but unless "add_efi_memmap" is specified on the
> > > > > kernel command line the EFI memory map is ignored. For
> > > > > soft-reservation support I want to reuse do_add_efi_memmap(), but
> > > > > otherwise avoid any other side effects of considering the EFI map.
> > > > > What I'm missing is the rationale for why "add_efi_memmap" is required
> > > > > before considering the EFI memory map.
> > > > >
> > > > > If there is a negative side effect to always using the EFI map then
> > > > > the new "add_efi_mode" designation constrains it to just the
> > > > > soft-reservation case.
> > > > >
> > > >
> > > > Could we make the presence of any EFI_MEMORY_SP regions imply
> > > > add_efi_memmap? That way, it is guaranteed that we don't regress
> > > > existing systems, while establishing clear and unambiguous semantics
> > > > for new systems that rely on these changes in order to be able to use
> > > > the special purpose memory as intended.
> > >
> > > In fact that's how it works. EFI_MEMORY_SP is unconditionally added.
> > > Other EFI memory types are optionally added with the add_efi_memmap
> > > option.
> >
> > That is not what I meant.
> >
> > Why not behave as if 'add_efi_memmap' was passed if any EFI_MEMORY_SP
> > regions exist?
>
> Hmm, ok, on the assumption that any platform that is modern enough to
> specify EFI_MEMORY_SP likely does not need the opt-in?
Indeed.
> I can get on
> board with that. It's also simple enough to undo if it causes problems
> in practice.
Yes, and we'll only have one code path to reason about here.
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH v6 06/12] arm/efi: EFI soft reservation to memblock
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (4 preceding siblings ...)
2019-10-09 23:05 ` [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
2019-10-10 6:46 ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 07/12] x86/efi: Add efi_fake_mem support for EFI_MEMORY_SP Dan Williams
` (5 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: Will Deacon, Catalin Marinas, Ard Biesheuvel, peterz,
vishal.l.verma, dave.hansen, x86, linux-efi, linux-kernel,
linux-acpi
UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
interpretation of the EFI Memory Types as "reserved for a specific
purpose".
The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
the "soft reserved" designation by allowing some or all of the
reservation to be recovered as typical memory. This policy can be
disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
efi=nosoftreserve.
For this patch, update the ARM paths that consider
EFI_CONVENTIONAL_MEMORY to optionally take the EFI_MEMORY_SP attribute
into account as a reservation indicator. Publish the soft reservation as
IORES_DESC_SOFT_RESERVED memory, similar to x86.
(Based on an original patch by Ard)
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/arm64/mm/mmu.c | 2 ++
drivers/firmware/efi/arm-init.c | 9 +++++++++
drivers/firmware/efi/arm-runtime.c | 24 ++++++++++++++++++++++++
drivers/firmware/efi/libstub/arm32-stub.c | 5 +++++
drivers/firmware/efi/libstub/random.c | 4 ++++
5 files changed, 44 insertions(+)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 60c929f3683b..2c385fe05fde 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1061,6 +1061,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
+ memblock_clear_nomap(start, size);
+
return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
restrictions);
}
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index 311cd349a862..904fa09e6a6b 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -163,6 +163,15 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
case EFI_BOOT_SERVICES_DATA:
case EFI_CONVENTIONAL_MEMORY:
case EFI_PERSISTENT_MEMORY:
+ /*
+ * Special purpose memory is 'soft reserved', which means it
+ * is set aside initially, but can be hotplugged back in or
+ * be assigned to the dax driver after boot.
+ */
+ if (efi_soft_reserve_enabled() &&
+ (md->attribute & EFI_MEMORY_SP))
+ return false;
+
/*
* According to the spec, these regions are no longer reserved
* after calling ExitBootServices(). However, we can only use
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index e2ac5fa5531b..899b803842bb 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -121,6 +121,30 @@ static int __init arm_enable_runtime_services(void)
return 0;
}
+ if (efi_soft_reserve_enabled()) {
+ efi_memory_desc_t *md;
+
+ for_each_efi_memory_desc(md) {
+ int md_size = md->num_pages << EFI_PAGE_SHIFT;
+ struct resource *res;
+
+ if (!(md->attribute & EFI_MEMORY_SP))
+ continue;
+
+ res = kzalloc(sizeof(*res), GFP_KERNEL);
+ if (WARN_ON(!res))
+ break;
+
+ res->start = md->phys_addr;
+ res->end = md->phys_addr + md_size - 1;
+ res->name = "Soft Reserved";
+ res->flags = IORESOURCE_MEM;
+ res->desc = IORES_DESC_SOFT_RESERVED;
+
+ insert_resource(&iomem_resource, res);
+ }
+ }
+
if (efi_runtime_disabled()) {
pr_info("EFI runtime services will be disabled.\n");
return 0;
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index e8f7aefb6813..3cd54d2096c6 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -146,6 +146,11 @@ static efi_status_t reserve_kernel_base(efi_system_table_t *sys_table_arg,
continue;
case EFI_CONVENTIONAL_MEMORY:
+ /* Skip soft reserved conventional memory */
+ if (efi_soft_reserve_enabled() &&
+ (desc->attribute & EFI_MEMORY_SP))
+ continue;
+
/*
* Reserve the intersection between this entry and the
* region.
diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
index b4b1d1dcb5fd..6c188695e730 100644
--- a/drivers/firmware/efi/libstub/random.c
+++ b/drivers/firmware/efi/libstub/random.c
@@ -46,6 +46,10 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
if (md->type != EFI_CONVENTIONAL_MEMORY)
return 0;
+ if (efi_soft_reserve_enabled() &&
+ (md->attribute & EFI_MEMORY_SP))
+ return 0;
+
region_end = min((u64)ULONG_MAX, md->phys_addr + md->num_pages*EFI_PAGE_SIZE - 1);
first_slot = round_up(md->phys_addr, align);
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH v6 06/12] arm/efi: EFI soft reservation to memblock
2019-10-09 23:05 ` [PATCH v6 06/12] arm/efi: EFI soft reservation to memblock Dan Williams
@ 2019-10-10 6:46 ` Ard Biesheuvel
0 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-10-10 6:46 UTC (permalink / raw)
To: Dan Williams
Cc: Ingo Molnar, Will Deacon, Catalin Marinas, Peter Zijlstra,
Vishal L Verma, Dave Hansen, the arch/x86 maintainers, linux-efi,
Linux Kernel Mailing List, ACPI Devel Maling List
On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
>
> UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the
> interpretation of the EFI Memory Types as "reserved for a specific
> purpose".
>
> The proposed Linux behavior for specific 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. This device-dax management scheme implements "soft" in
> the "soft reserved" designation by allowing some or all of the
> reservation to be recovered as typical memory. This policy can be
> disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with
> efi=nosoftreserve.
>
> For this patch, update the ARM paths that consider
> EFI_CONVENTIONAL_MEMORY to optionally take the EFI_MEMORY_SP attribute
> into account as a reservation indicator. Publish the soft reservation as
> IORES_DESC_SOFT_RESERVED memory, similar to x86.
>
> (Based on an original patch by Ard)
>
> Cc: Will Deacon <will@kernel.org>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> ---
> arch/arm64/mm/mmu.c | 2 ++
> drivers/firmware/efi/arm-init.c | 9 +++++++++
> drivers/firmware/efi/arm-runtime.c | 24 ++++++++++++++++++++++++
> drivers/firmware/efi/libstub/arm32-stub.c | 5 +++++
> drivers/firmware/efi/libstub/random.c | 4 ++++
> 5 files changed, 44 insertions(+)
>
> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
> index 60c929f3683b..2c385fe05fde 100644
> --- a/arch/arm64/mm/mmu.c
> +++ b/arch/arm64/mm/mmu.c
> @@ -1061,6 +1061,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
> __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
> size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
>
> + memblock_clear_nomap(start, size);
> +
> return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
> restrictions);
> }
> diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
> index 311cd349a862..904fa09e6a6b 100644
> --- a/drivers/firmware/efi/arm-init.c
> +++ b/drivers/firmware/efi/arm-init.c
> @@ -163,6 +163,15 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
> case EFI_BOOT_SERVICES_DATA:
> case EFI_CONVENTIONAL_MEMORY:
> case EFI_PERSISTENT_MEMORY:
> + /*
> + * Special purpose memory is 'soft reserved', which means it
> + * is set aside initially, but can be hotplugged back in or
> + * be assigned to the dax driver after boot.
> + */
> + if (efi_soft_reserve_enabled() &&
> + (md->attribute & EFI_MEMORY_SP))
> + return false;
> +
> /*
> * According to the spec, these regions are no longer reserved
> * after calling ExitBootServices(). However, we can only use
> diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
> index e2ac5fa5531b..899b803842bb 100644
> --- a/drivers/firmware/efi/arm-runtime.c
> +++ b/drivers/firmware/efi/arm-runtime.c
> @@ -121,6 +121,30 @@ static int __init arm_enable_runtime_services(void)
> return 0;
> }
>
> + if (efi_soft_reserve_enabled()) {
> + efi_memory_desc_t *md;
> +
> + for_each_efi_memory_desc(md) {
> + int md_size = md->num_pages << EFI_PAGE_SHIFT;
> + struct resource *res;
> +
> + if (!(md->attribute & EFI_MEMORY_SP))
> + continue;
> +
> + res = kzalloc(sizeof(*res), GFP_KERNEL);
> + if (WARN_ON(!res))
> + break;
> +
> + res->start = md->phys_addr;
> + res->end = md->phys_addr + md_size - 1;
> + res->name = "Soft Reserved";
> + res->flags = IORESOURCE_MEM;
> + res->desc = IORES_DESC_SOFT_RESERVED;
> +
> + insert_resource(&iomem_resource, res);
> + }
> + }
> +
> if (efi_runtime_disabled()) {
> pr_info("EFI runtime services will be disabled.\n");
> return 0;
> diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
> index e8f7aefb6813..3cd54d2096c6 100644
> --- a/drivers/firmware/efi/libstub/arm32-stub.c
> +++ b/drivers/firmware/efi/libstub/arm32-stub.c
> @@ -146,6 +146,11 @@ static efi_status_t reserve_kernel_base(efi_system_table_t *sys_table_arg,
> continue;
>
> case EFI_CONVENTIONAL_MEMORY:
> + /* Skip soft reserved conventional memory */
> + if (efi_soft_reserve_enabled() &&
> + (desc->attribute & EFI_MEMORY_SP))
> + continue;
> +
> /*
> * Reserve the intersection between this entry and the
> * region.
> diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
> index b4b1d1dcb5fd..6c188695e730 100644
> --- a/drivers/firmware/efi/libstub/random.c
> +++ b/drivers/firmware/efi/libstub/random.c
> @@ -46,6 +46,10 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
> if (md->type != EFI_CONVENTIONAL_MEMORY)
> return 0;
>
> + if (efi_soft_reserve_enabled() &&
> + (md->attribute & EFI_MEMORY_SP))
> + return 0;
> +
> region_end = min((u64)ULONG_MAX, md->phys_addr + md->num_pages*EFI_PAGE_SIZE - 1);
>
> first_slot = round_up(md->phys_addr, align);
>
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH v6 07/12] x86/efi: Add efi_fake_mem support for EFI_MEMORY_SP
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (5 preceding siblings ...)
2019-10-09 23:05 ` [PATCH v6 06/12] arm/efi: EFI soft reservation to memblock Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
2019-10-10 7:01 ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 08/12] lib: Uplevel the pmem "region" ida to a global allocator Dan Williams
` (4 subsequent siblings)
11 siblings, 1 reply; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: x86, Borislav Petkov, H. Peter Anvin, Thomas Gleixner,
Ard Biesheuvel, Dave Hansen, peterz, vishal.l.verma, x86,
linux-efi, linux-kernel, linux-acpi
Given that EFI_MEMORY_SP is platform BIOS policy decision for marking
memory ranges as "reserved for a specific purpose" there will inevitably
be scenarios where the BIOS omits the attribute in situations where it
is desired. Unlike other attributes if the OS wants to reserve this
memory from the kernel the reservation needs to happen early in init. So
early, in fact, that it needs to happen before e820__memblock_setup()
which is a pre-requisite for efi_fake_memmap() that wants to allocate
memory for the updated table.
Introduce an x86 specific efi_fake_memmap_early() that can search for
attempts to set EFI_MEMORY_SP via efi_fake_mem and update the e820 table
accordingly.
The KASLR code that scans the command line looking for user-directed
memory reservations also needs to be updated to consider
"efi_fake_mem=nn@ss:0x40000" requests.
Cc: <x86@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
Documentation/admin-guide/kernel-parameters.txt | 10 +++
arch/x86/boot/compressed/kaslr.c | 42 ++++++++++++--
arch/x86/include/asm/efi.h | 8 +++
arch/x86/platform/efi/efi.c | 2 +
drivers/firmware/efi/Makefile | 5 +-
drivers/firmware/efi/fake_mem.c | 24 ++++----
drivers/firmware/efi/fake_mem.h | 10 +++
drivers/firmware/efi/x86_fake_mem.c | 69 +++++++++++++++++++++++
8 files changed, 147 insertions(+), 23 deletions(-)
create mode 100644 drivers/firmware/efi/fake_mem.h
create mode 100644 drivers/firmware/efi/x86_fake_mem.c
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 47478a730011..9489d76b0e9f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1196,15 +1196,21 @@
updating original EFI memory map.
Region of memory which aa attribute is added to is
from ss to ss+nn.
+
If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
attribute is added to range 0x100000000-0x180000000 and
0x10a0000000-0x1120000000.
+ If efi_fake_mem=8G@9G:0x40000 is specified, the
+ EFI_MEMORY_SP(0x40000) attribute is added to
+ range 0x240000000-0x43fffffff.
+
Using this parameter you can do debugging of EFI memmap
- related feature. For example, you can do debugging of
+ related features. For example, you can do debugging of
Address Range Mirroring feature even if your box
- doesn't support it.
+ doesn't support it, or mark specific memory as
+ "soft reserved".
efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT
that is to be dynamically loaded by Linux. If there are
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index ff6fa81949cd..da0eedd5635d 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -132,8 +132,14 @@ char *skip_spaces(const char *str)
#include "../../../../lib/ctype.c"
#include "../../../../lib/cmdline.c"
+enum parse_mode {
+ PARSE_MEMMAP,
+ PARSE_EFI,
+};
+
static int
-parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
+parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
+ enum parse_mode mode)
{
char *oldp;
@@ -156,8 +162,29 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
*start = memparse(p + 1, &p);
return 0;
case '@':
- /* memmap=nn@ss specifies usable region, should be skipped */
- *size = 0;
+ if (mode == PARSE_MEMMAP) {
+ /*
+ * memmap=nn@ss specifies usable region, should
+ * be skipped
+ */
+ *size = 0;
+ } else {
+ unsigned long long flags;
+
+ /*
+ * efi_fake_mem=nn@ss:attr the attr specifies
+ * flags that might imply a soft-reservation.
+ */
+ *start = memparse(p + 1, &p);
+ if (p && *p == ':') {
+ p++;
+ if (kstrtoull(p, 0, &flags) < 0)
+ *size = 0;
+ else if (flags & EFI_MEMORY_SP)
+ return 0;
+ }
+ *size = 0;
+ }
/* Fall through */
default:
/*
@@ -172,7 +199,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
return -EINVAL;
}
-static void mem_avoid_memmap(char *str)
+static void mem_avoid_memmap(enum parse_mode mode, char *str)
{
static int i;
@@ -187,7 +214,7 @@ static void mem_avoid_memmap(char *str)
if (k)
*k++ = 0;
- rc = parse_memmap(str, &start, &size);
+ rc = parse_memmap(str, &start, &size, mode);
if (rc < 0)
break;
str = k;
@@ -238,7 +265,6 @@ static void parse_gb_huge_pages(char *param, char *val)
}
}
-
static void handle_mem_options(void)
{
char *args = (char *)get_cmd_line_ptr();
@@ -271,7 +297,7 @@ static void handle_mem_options(void)
}
if (!strcmp(param, "memmap")) {
- mem_avoid_memmap(val);
+ mem_avoid_memmap(PARSE_MEMMAP, val);
} else if (strstr(param, "hugepages")) {
parse_gb_huge_pages(param, val);
} else if (!strcmp(param, "mem")) {
@@ -284,6 +310,8 @@ static void handle_mem_options(void)
goto out;
mem_limit = mem_size;
+ } else if (!strcmp(param, "efi_fake_mem")) {
+ mem_avoid_memmap(PARSE_EFI, val);
}
}
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 45f853bce869..d028e9acdf1c 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -263,4 +263,12 @@ static inline void efi_reserve_boot_services(void)
}
#endif /* CONFIG_EFI */
+#ifdef CONFIG_EFI_FAKE_MEMMAP
+extern void __init efi_fake_memmap_early(void);
+#else
+static inline void efi_fake_memmap_early(void)
+{
+}
+#endif
+
#endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index c96657993167..188cd73cd7d6 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -259,6 +259,8 @@ int __init efi_memblock_x86_reserve_range(void)
do_add_efi_memmap(ADD_EFI_SOFT_RESERVED);
}
+ efi_fake_memmap_early();
+
WARN(efi.memmap.desc_version != 1,
"Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
efi.memmap.desc_version);
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 4ac2de4dfa72..554d795270d9 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -20,13 +20,16 @@ obj-$(CONFIG_UEFI_CPER) += cper.o
obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o
obj-$(CONFIG_EFI_RUNTIME_WRAPPERS) += runtime-wrappers.o
obj-$(CONFIG_EFI_STUB) += libstub/
-obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_mem.o
+obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_map.o
obj-$(CONFIG_EFI_BOOTLOADER_CONTROL) += efibc.o
obj-$(CONFIG_EFI_TEST) += test/
obj-$(CONFIG_EFI_DEV_PATH_PARSER) += dev-path-parser.o
obj-$(CONFIG_APPLE_PROPERTIES) += apple-properties.o
obj-$(CONFIG_EFI_RCI2_TABLE) += rci2-table.o
+fake_map-y += fake_mem.o
+fake_map-$(CONFIG_X86) += x86_fake_mem.o
+
arm-obj-$(CONFIG_EFI) := arm-init.o arm-runtime.o
obj-$(CONFIG_ARM) += $(arm-obj-y)
obj-$(CONFIG_ARM64) += $(arm-obj-y)
diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c
index 526b45331d96..bb9fc70d0cfa 100644
--- a/drivers/firmware/efi/fake_mem.c
+++ b/drivers/firmware/efi/fake_mem.c
@@ -17,12 +17,10 @@
#include <linux/memblock.h>
#include <linux/types.h>
#include <linux/sort.h>
-#include <asm/efi.h>
+#include "fake_mem.h"
-#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
-
-static struct efi_mem_range fake_mems[EFI_MAX_FAKEMEM];
-static int nr_fake_mem;
+struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
+int nr_fake_mem;
static int __init cmp_fake_mem(const void *x1, const void *x2)
{
@@ -50,7 +48,7 @@ void __init efi_fake_memmap(void)
/* count up the number of EFI memory descriptor */
for (i = 0; i < nr_fake_mem; i++) {
for_each_efi_memory_desc(md) {
- struct range *r = &fake_mems[i].range;
+ struct range *r = &efi_fake_mems[i].range;
new_nr_map += efi_memmap_split_count(md, r);
}
@@ -70,7 +68,7 @@ void __init efi_fake_memmap(void)
}
for (i = 0; i < nr_fake_mem; i++)
- efi_memmap_insert(&efi.memmap, new_memmap, &fake_mems[i]);
+ efi_memmap_insert(&efi.memmap, new_memmap, &efi_fake_mems[i]);
/* swap into new EFI memmap */
early_memunmap(new_memmap, efi.memmap.desc_size * new_nr_map);
@@ -104,22 +102,22 @@ static int __init setup_fake_mem(char *p)
if (nr_fake_mem >= EFI_MAX_FAKEMEM)
break;
- fake_mems[nr_fake_mem].range.start = start;
- fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
- fake_mems[nr_fake_mem].attribute = attribute;
+ efi_fake_mems[nr_fake_mem].range.start = start;
+ efi_fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
+ efi_fake_mems[nr_fake_mem].attribute = attribute;
nr_fake_mem++;
if (*p == ',')
p++;
}
- sort(fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
+ sort(efi_fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
cmp_fake_mem, NULL);
for (i = 0; i < nr_fake_mem; i++)
pr_info("efi_fake_mem: add attr=0x%016llx to [mem 0x%016llx-0x%016llx]",
- fake_mems[i].attribute, fake_mems[i].range.start,
- fake_mems[i].range.end);
+ efi_fake_mems[i].attribute, efi_fake_mems[i].range.start,
+ efi_fake_mems[i].range.end);
return *p == '\0' ? 0 : -EINVAL;
}
diff --git a/drivers/firmware/efi/fake_mem.h b/drivers/firmware/efi/fake_mem.h
new file mode 100644
index 000000000000..d52791af4b18
--- /dev/null
+++ b/drivers/firmware/efi/fake_mem.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __EFI_FAKE_MEM_H__
+#define __EFI_FAKE_MEM_H__
+#include <asm/efi.h>
+
+#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
+
+extern struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
+extern int nr_fake_mem;
+#endif /* __EFI_FAKE_MEM_H__ */
diff --git a/drivers/firmware/efi/x86_fake_mem.c b/drivers/firmware/efi/x86_fake_mem.c
new file mode 100644
index 000000000000..e5d6d5a1b240
--- /dev/null
+++ b/drivers/firmware/efi/x86_fake_mem.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights reserved. */
+#include <linux/efi.h>
+#include <asm/e820/api.h>
+#include "fake_mem.h"
+
+void __init efi_fake_memmap_early(void)
+{
+ int i;
+
+ /*
+ * The late efi_fake_mem() call can handle all requests if
+ * EFI_MEMORY_SP support is disabled.
+ */
+ if (!efi_soft_reserve_enabled())
+ return;
+
+ if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
+ return;
+
+ /*
+ * Given that efi_fake_memmap() needs to perform memblock
+ * allocations it needs to run after e820__memblock_setup().
+ * However, if efi_fake_mem specifies EFI_MEMORY_SP for a given
+ * address range that potentially needs to mark the memory as
+ * reserved prior to e820__memblock_setup(). Update e820
+ * directly if EFI_MEMORY_SP is specified for an
+ * EFI_CONVENTIONAL_MEMORY descriptor.
+ */
+ for (i = 0; i < nr_fake_mem; i++) {
+ struct efi_mem_range *mem = &efi_fake_mems[i];
+ efi_memory_desc_t *md;
+ u64 m_start, m_end;
+
+ if ((mem->attribute & EFI_MEMORY_SP) == 0)
+ continue;
+
+ m_start = mem->range.start;
+ m_end = mem->range.end;
+ for_each_efi_memory_desc(md) {
+ u64 start, end;
+
+ if (md->type != EFI_CONVENTIONAL_MEMORY)
+ continue;
+
+ start = md->phys_addr;
+ end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+ if (m_start <= end && m_end >= start)
+ /* fake range overlaps descriptor */;
+ else
+ continue;
+
+ /*
+ * Trim the boundary of the e820 update to the
+ * descriptor in case the fake range overlaps
+ * !EFI_CONVENTIONAL_MEMORY
+ */
+ start = max(start, m_start);
+ end = min(end, m_end);
+
+ if (end <= start)
+ continue;
+ e820__range_update(start, end - start + 1, E820_TYPE_RAM,
+ E820_TYPE_SOFT_RESERVED);
+ e820__update_table(e820_table);
+ }
+ }
+}
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH v6 07/12] x86/efi: Add efi_fake_mem support for EFI_MEMORY_SP
2019-10-09 23:05 ` [PATCH v6 07/12] x86/efi: Add efi_fake_mem support for EFI_MEMORY_SP Dan Williams
@ 2019-10-10 7:01 ` Ard Biesheuvel
0 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-10-10 7:01 UTC (permalink / raw)
To: Dan Williams
Cc: Ingo Molnar, the arch/x86 maintainers, Borislav Petkov,
H. Peter Anvin, Thomas Gleixner, Dave Hansen, Peter Zijlstra,
Vishal L Verma, linux-efi, Linux Kernel Mailing List,
ACPI Devel Maling List
On Thu, 10 Oct 2019 at 01:19, Dan Williams <dan.j.williams@intel.com> wrote:
>
> Given that EFI_MEMORY_SP is platform BIOS policy decision for marking
> memory ranges as "reserved for a specific purpose" there will inevitably
> be scenarios where the BIOS omits the attribute in situations where it
> is desired. Unlike other attributes if the OS wants to reserve this
> memory from the kernel the reservation needs to happen early in init. So
> early, in fact, that it needs to happen before e820__memblock_setup()
> which is a pre-requisite for efi_fake_memmap() that wants to allocate
> memory for the updated table.
>
> Introduce an x86 specific efi_fake_memmap_early() that can search for
> attempts to set EFI_MEMORY_SP via efi_fake_mem and update the e820 table
> accordingly.
>
> The KASLR code that scans the command line looking for user-directed
> memory reservations also needs to be updated to consider
> "efi_fake_mem=nn@ss:0x40000" requests.
>
> Cc: <x86@kernel.org>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> ---
> Documentation/admin-guide/kernel-parameters.txt | 10 +++
> arch/x86/boot/compressed/kaslr.c | 42 ++++++++++++--
> arch/x86/include/asm/efi.h | 8 +++
> arch/x86/platform/efi/efi.c | 2 +
> drivers/firmware/efi/Makefile | 5 +-
> drivers/firmware/efi/fake_mem.c | 24 ++++----
> drivers/firmware/efi/fake_mem.h | 10 +++
> drivers/firmware/efi/x86_fake_mem.c | 69 +++++++++++++++++++++++
> 8 files changed, 147 insertions(+), 23 deletions(-)
> create mode 100644 drivers/firmware/efi/fake_mem.h
> create mode 100644 drivers/firmware/efi/x86_fake_mem.c
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index 47478a730011..9489d76b0e9f 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1196,15 +1196,21 @@
> updating original EFI memory map.
> Region of memory which aa attribute is added to is
> from ss to ss+nn.
> +
> If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
> is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
> attribute is added to range 0x100000000-0x180000000 and
> 0x10a0000000-0x1120000000.
>
> + If efi_fake_mem=8G@9G:0x40000 is specified, the
> + EFI_MEMORY_SP(0x40000) attribute is added to
> + range 0x240000000-0x43fffffff.
> +
> Using this parameter you can do debugging of EFI memmap
> - related feature. For example, you can do debugging of
> + related features. For example, you can do debugging of
> Address Range Mirroring feature even if your box
> - doesn't support it.
> + doesn't support it, or mark specific memory as
> + "soft reserved".
>
> efivar_ssdt= [EFI; X86] Name of an EFI variable that contains an SSDT
> that is to be dynamically loaded by Linux. If there are
> diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
> index ff6fa81949cd..da0eedd5635d 100644
> --- a/arch/x86/boot/compressed/kaslr.c
> +++ b/arch/x86/boot/compressed/kaslr.c
> @@ -132,8 +132,14 @@ char *skip_spaces(const char *str)
> #include "../../../../lib/ctype.c"
> #include "../../../../lib/cmdline.c"
>
> +enum parse_mode {
> + PARSE_MEMMAP,
> + PARSE_EFI,
> +};
> +
> static int
> -parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
> +parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
> + enum parse_mode mode)
> {
> char *oldp;
>
> @@ -156,8 +162,29 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
> *start = memparse(p + 1, &p);
> return 0;
> case '@':
> - /* memmap=nn@ss specifies usable region, should be skipped */
> - *size = 0;
> + if (mode == PARSE_MEMMAP) {
> + /*
> + * memmap=nn@ss specifies usable region, should
> + * be skipped
> + */
> + *size = 0;
> + } else {
> + unsigned long long flags;
> +
> + /*
> + * efi_fake_mem=nn@ss:attr the attr specifies
> + * flags that might imply a soft-reservation.
> + */
> + *start = memparse(p + 1, &p);
> + if (p && *p == ':') {
> + p++;
> + if (kstrtoull(p, 0, &flags) < 0)
> + *size = 0;
> + else if (flags & EFI_MEMORY_SP)
> + return 0;
> + }
> + *size = 0;
> + }
> /* Fall through */
> default:
> /*
> @@ -172,7 +199,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
> return -EINVAL;
> }
>
> -static void mem_avoid_memmap(char *str)
> +static void mem_avoid_memmap(enum parse_mode mode, char *str)
> {
> static int i;
>
> @@ -187,7 +214,7 @@ static void mem_avoid_memmap(char *str)
> if (k)
> *k++ = 0;
>
> - rc = parse_memmap(str, &start, &size);
> + rc = parse_memmap(str, &start, &size, mode);
> if (rc < 0)
> break;
> str = k;
> @@ -238,7 +265,6 @@ static void parse_gb_huge_pages(char *param, char *val)
> }
> }
>
> -
> static void handle_mem_options(void)
> {
> char *args = (char *)get_cmd_line_ptr();
> @@ -271,7 +297,7 @@ static void handle_mem_options(void)
> }
>
> if (!strcmp(param, "memmap")) {
> - mem_avoid_memmap(val);
> + mem_avoid_memmap(PARSE_MEMMAP, val);
> } else if (strstr(param, "hugepages")) {
> parse_gb_huge_pages(param, val);
> } else if (!strcmp(param, "mem")) {
> @@ -284,6 +310,8 @@ static void handle_mem_options(void)
> goto out;
>
> mem_limit = mem_size;
> + } else if (!strcmp(param, "efi_fake_mem")) {
> + mem_avoid_memmap(PARSE_EFI, val);
> }
> }
>
> diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
> index 45f853bce869..d028e9acdf1c 100644
> --- a/arch/x86/include/asm/efi.h
> +++ b/arch/x86/include/asm/efi.h
> @@ -263,4 +263,12 @@ static inline void efi_reserve_boot_services(void)
> }
> #endif /* CONFIG_EFI */
>
> +#ifdef CONFIG_EFI_FAKE_MEMMAP
> +extern void __init efi_fake_memmap_early(void);
> +#else
> +static inline void efi_fake_memmap_early(void)
> +{
> +}
> +#endif
> +
> #endif /* _ASM_X86_EFI_H */
> diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
> index c96657993167..188cd73cd7d6 100644
> --- a/arch/x86/platform/efi/efi.c
> +++ b/arch/x86/platform/efi/efi.c
> @@ -259,6 +259,8 @@ int __init efi_memblock_x86_reserve_range(void)
> do_add_efi_memmap(ADD_EFI_SOFT_RESERVED);
> }
>
> + efi_fake_memmap_early();
> +
> WARN(efi.memmap.desc_version != 1,
> "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
> efi.memmap.desc_version);
> diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
> index 4ac2de4dfa72..554d795270d9 100644
> --- a/drivers/firmware/efi/Makefile
> +++ b/drivers/firmware/efi/Makefile
> @@ -20,13 +20,16 @@ obj-$(CONFIG_UEFI_CPER) += cper.o
> obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o
> obj-$(CONFIG_EFI_RUNTIME_WRAPPERS) += runtime-wrappers.o
> obj-$(CONFIG_EFI_STUB) += libstub/
> -obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_mem.o
> +obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_map.o
> obj-$(CONFIG_EFI_BOOTLOADER_CONTROL) += efibc.o
> obj-$(CONFIG_EFI_TEST) += test/
> obj-$(CONFIG_EFI_DEV_PATH_PARSER) += dev-path-parser.o
> obj-$(CONFIG_APPLE_PROPERTIES) += apple-properties.o
> obj-$(CONFIG_EFI_RCI2_TABLE) += rci2-table.o
>
> +fake_map-y += fake_mem.o
> +fake_map-$(CONFIG_X86) += x86_fake_mem.o
> +
> arm-obj-$(CONFIG_EFI) := arm-init.o arm-runtime.o
> obj-$(CONFIG_ARM) += $(arm-obj-y)
> obj-$(CONFIG_ARM64) += $(arm-obj-y)
> diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c
> index 526b45331d96..bb9fc70d0cfa 100644
> --- a/drivers/firmware/efi/fake_mem.c
> +++ b/drivers/firmware/efi/fake_mem.c
> @@ -17,12 +17,10 @@
> #include <linux/memblock.h>
> #include <linux/types.h>
> #include <linux/sort.h>
> -#include <asm/efi.h>
> +#include "fake_mem.h"
>
> -#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
> -
> -static struct efi_mem_range fake_mems[EFI_MAX_FAKEMEM];
> -static int nr_fake_mem;
> +struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
> +int nr_fake_mem;
>
> static int __init cmp_fake_mem(const void *x1, const void *x2)
> {
> @@ -50,7 +48,7 @@ void __init efi_fake_memmap(void)
> /* count up the number of EFI memory descriptor */
> for (i = 0; i < nr_fake_mem; i++) {
> for_each_efi_memory_desc(md) {
> - struct range *r = &fake_mems[i].range;
> + struct range *r = &efi_fake_mems[i].range;
>
> new_nr_map += efi_memmap_split_count(md, r);
> }
> @@ -70,7 +68,7 @@ void __init efi_fake_memmap(void)
> }
>
> for (i = 0; i < nr_fake_mem; i++)
> - efi_memmap_insert(&efi.memmap, new_memmap, &fake_mems[i]);
> + efi_memmap_insert(&efi.memmap, new_memmap, &efi_fake_mems[i]);
>
> /* swap into new EFI memmap */
> early_memunmap(new_memmap, efi.memmap.desc_size * new_nr_map);
> @@ -104,22 +102,22 @@ static int __init setup_fake_mem(char *p)
> if (nr_fake_mem >= EFI_MAX_FAKEMEM)
> break;
>
> - fake_mems[nr_fake_mem].range.start = start;
> - fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
> - fake_mems[nr_fake_mem].attribute = attribute;
> + efi_fake_mems[nr_fake_mem].range.start = start;
> + efi_fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
> + efi_fake_mems[nr_fake_mem].attribute = attribute;
> nr_fake_mem++;
>
> if (*p == ',')
> p++;
> }
>
> - sort(fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
> + sort(efi_fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
> cmp_fake_mem, NULL);
>
> for (i = 0; i < nr_fake_mem; i++)
> pr_info("efi_fake_mem: add attr=0x%016llx to [mem 0x%016llx-0x%016llx]",
> - fake_mems[i].attribute, fake_mems[i].range.start,
> - fake_mems[i].range.end);
> + efi_fake_mems[i].attribute, efi_fake_mems[i].range.start,
> + efi_fake_mems[i].range.end);
>
> return *p == '\0' ? 0 : -EINVAL;
> }
> diff --git a/drivers/firmware/efi/fake_mem.h b/drivers/firmware/efi/fake_mem.h
> new file mode 100644
> index 000000000000..d52791af4b18
> --- /dev/null
> +++ b/drivers/firmware/efi/fake_mem.h
> @@ -0,0 +1,10 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef __EFI_FAKE_MEM_H__
> +#define __EFI_FAKE_MEM_H__
> +#include <asm/efi.h>
> +
> +#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
> +
> +extern struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
> +extern int nr_fake_mem;
> +#endif /* __EFI_FAKE_MEM_H__ */
> diff --git a/drivers/firmware/efi/x86_fake_mem.c b/drivers/firmware/efi/x86_fake_mem.c
> new file mode 100644
> index 000000000000..e5d6d5a1b240
> --- /dev/null
> +++ b/drivers/firmware/efi/x86_fake_mem.c
> @@ -0,0 +1,69 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright(c) 2019 Intel Corporation. All rights reserved. */
> +#include <linux/efi.h>
> +#include <asm/e820/api.h>
> +#include "fake_mem.h"
> +
> +void __init efi_fake_memmap_early(void)
> +{
> + int i;
> +
> + /*
> + * The late efi_fake_mem() call can handle all requests if
> + * EFI_MEMORY_SP support is disabled.
> + */
> + if (!efi_soft_reserve_enabled())
> + return;
> +
> + if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
> + return;
> +
> + /*
> + * Given that efi_fake_memmap() needs to perform memblock
> + * allocations it needs to run after e820__memblock_setup().
> + * However, if efi_fake_mem specifies EFI_MEMORY_SP for a given
> + * address range that potentially needs to mark the memory as
> + * reserved prior to e820__memblock_setup(). Update e820
> + * directly if EFI_MEMORY_SP is specified for an
> + * EFI_CONVENTIONAL_MEMORY descriptor.
> + */
> + for (i = 0; i < nr_fake_mem; i++) {
> + struct efi_mem_range *mem = &efi_fake_mems[i];
> + efi_memory_desc_t *md;
> + u64 m_start, m_end;
> +
> + if ((mem->attribute & EFI_MEMORY_SP) == 0)
> + continue;
> +
> + m_start = mem->range.start;
> + m_end = mem->range.end;
> + for_each_efi_memory_desc(md) {
> + u64 start, end;
> +
> + if (md->type != EFI_CONVENTIONAL_MEMORY)
> + continue;
> +
> + start = md->phys_addr;
> + end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
> +
> + if (m_start <= end && m_end >= start)
> + /* fake range overlaps descriptor */;
> + else
> + continue;
> +
> + /*
> + * Trim the boundary of the e820 update to the
> + * descriptor in case the fake range overlaps
> + * !EFI_CONVENTIONAL_MEMORY
> + */
> + start = max(start, m_start);
> + end = min(end, m_end);
> +
> + if (end <= start)
> + continue;
> + e820__range_update(start, end - start + 1, E820_TYPE_RAM,
> + E820_TYPE_SOFT_RESERVED);
> + e820__update_table(e820_table);
> + }
> + }
> +}
>
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH v6 08/12] lib: Uplevel the pmem "region" ida to a global allocator
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (6 preceding siblings ...)
2019-10-09 23:05 ` [PATCH v6 07/12] x86/efi: Add efi_fake_mem support for EFI_MEMORY_SP Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
2019-10-09 23:05 ` [PATCH v6 09/12] dax: Fix alloc_dax_region() compile warning Dan Williams
` (3 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: Keith Busch, peterz, vishal.l.verma, dave.hansen, ard.biesheuvel,
x86, linux-efi, linux-kernel, linux-acpi
In preparation for handling platform differentiated memory types beyond
persistent memory, uplevel the "region" identifier to a global number
space. This enables a device-dax instance to be registered to any memory
type with guaranteed unique names.
Cc: Keith Busch <kbusch@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/nvdimm/Kconfig | 1 +
drivers/nvdimm/core.c | 1 -
drivers/nvdimm/nd-core.h | 1 -
drivers/nvdimm/region_devs.c | 13 ++++---------
include/linux/memregion.h | 19 +++++++++++++++++++
lib/Kconfig | 3 +++
lib/Makefile | 1 +
lib/memregion.c | 18 ++++++++++++++++++
8 files changed, 46 insertions(+), 11 deletions(-)
create mode 100644 include/linux/memregion.h
create mode 100644 lib/memregion.c
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 36af7af6b7cf..b7d1eb38b27d 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -4,6 +4,7 @@ menuconfig LIBNVDIMM
depends on PHYS_ADDR_T_64BIT
depends on HAS_IOMEM
depends on BLK_DEV
+ select MEMREGION
help
Generic support for non-volatile memory devices including
ACPI-6-NFIT defined resources. On platforms that define an
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 9204f1e9fd14..e592c4964674 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -455,7 +455,6 @@ static __exit void libnvdimm_exit(void)
nd_region_exit();
nvdimm_exit();
nvdimm_bus_exit();
- nd_region_devs_exit();
nvdimm_devs_exit();
}
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 25fa121104d0..aa059439fca0 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -114,7 +114,6 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
int __init nvdimm_bus_init(void);
void nvdimm_bus_exit(void);
void nvdimm_devs_exit(void);
-void nd_region_devs_exit(void);
struct nd_region;
void nd_region_advance_seeds(struct nd_region *nd_region, struct device *dev);
void nd_region_create_ns_seed(struct nd_region *nd_region);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index ef423ba1a711..fbf34cf688f4 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -3,6 +3,7 @@
* Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
*/
#include <linux/scatterlist.h>
+#include <linux/memregion.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/slab.h>
@@ -19,7 +20,6 @@
*/
#include <linux/io-64-nonatomic-hi-lo.h>
-static DEFINE_IDA(region_ida);
static DEFINE_PER_CPU(int, flush_idx);
static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm,
@@ -133,7 +133,7 @@ static void nd_region_release(struct device *dev)
put_device(&nvdimm->dev);
}
free_percpu(nd_region->lane);
- ida_simple_remove(®ion_ida, nd_region->id);
+ memregion_free(nd_region->id);
if (is_nd_blk(dev))
kfree(to_nd_blk_region(dev));
else
@@ -985,7 +985,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
if (!region_buf)
return NULL;
- nd_region->id = ida_simple_get(®ion_ida, 0, 0, GFP_KERNEL);
+ nd_region->id = memregion_alloc(GFP_KERNEL);
if (nd_region->id < 0)
goto err_id;
@@ -1044,7 +1044,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
return nd_region;
err_percpu:
- ida_simple_remove(®ion_ida, nd_region->id);
+ memregion_free(nd_region->id);
err_id:
kfree(region_buf);
return NULL;
@@ -1216,8 +1216,3 @@ int nd_region_conflict(struct nd_region *nd_region, resource_size_t start,
return device_for_each_child(&nvdimm_bus->dev, &ctx, region_conflict);
}
-
-void __exit nd_region_devs_exit(void)
-{
- ida_destroy(®ion_ida);
-}
diff --git a/include/linux/memregion.h b/include/linux/memregion.h
new file mode 100644
index 000000000000..7de7c0a1444e
--- /dev/null
+++ b/include/linux/memregion.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MEMREGION_H_
+#define _MEMREGION_H_
+#include <linux/types.h>
+#include <linux/errno.h>
+
+#ifdef CONFIG_MEMREGION
+int memregion_alloc(gfp_t gfp);
+void memregion_free(int id);
+#else
+static inline int memregion_alloc(gfp_t gfp)
+{
+ return -ENOMEM;
+}
+void memregion_free(int id)
+{
+}
+#endif
+#endif /* _MEMREGION_H_ */
diff --git a/lib/Kconfig b/lib/Kconfig
index 183f92a297ca..0dc043ac271d 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -606,6 +606,9 @@ config ARCH_NO_SG_CHAIN
config ARCH_HAS_PMEM_API
bool
+config MEMREGION
+ bool
+
# use memcpy to implement user copies for nommu architectures
config UACCESS_MEMCPY
bool
diff --git a/lib/Makefile b/lib/Makefile
index c5892807e06f..2fb7b47018f1 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -212,6 +212,7 @@ obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
obj-$(CONFIG_SG_SPLIT) += sg_split.o
obj-$(CONFIG_SG_POOL) += sg_pool.o
+obj-$(CONFIG_MEMREGION) += memregion.o
obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
obj-$(CONFIG_IRQ_POLL) += irq_poll.o
diff --git a/lib/memregion.c b/lib/memregion.c
new file mode 100644
index 000000000000..77c85b5251da
--- /dev/null
+++ b/lib/memregion.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* identifiers for device / performance-differentiated memory regions */
+#include <linux/idr.h>
+#include <linux/types.h>
+
+static DEFINE_IDA(memregion_ids);
+
+int memregion_alloc(gfp_t gfp)
+{
+ return ida_alloc(&memregion_ids, gfp);
+}
+EXPORT_SYMBOL(memregion_alloc);
+
+void memregion_free(int id)
+{
+ ida_free(&memregion_ids, id);
+}
+EXPORT_SYMBOL(memregion_free);
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH v6 09/12] dax: Fix alloc_dax_region() compile warning
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (7 preceding siblings ...)
2019-10-09 23:05 ` [PATCH v6 08/12] lib: Uplevel the pmem "region" ida to a global allocator Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
2019-10-09 23:05 ` [PATCH v6 10/12] device-dax: Add a driver for "hmem" devices Dan Williams
` (2 subsequent siblings)
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: Vishal Verma, kbuild test robot, peterz, dave.hansen,
ard.biesheuvel, x86, linux-efi, linux-kernel, linux-acpi
PFN flags are (unsigned long long), fix the alloc_dax_region() calling
convention to fix warnings of the form:
>> include/linux/pfn_t.h:18:17: warning: large integer implicitly truncated to unsigned type [-Woverflow]
#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
Cc: Vishal Verma <vishal.l.verma@intel.com>
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/dax/bus.c | 2 +-
drivers/dax/bus.h | 2 +-
drivers/dax/dax-private.h | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 8fafbeab510a..eccdda1f7b71 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -227,7 +227,7 @@ static void dax_region_unregister(void *region)
struct dax_region *alloc_dax_region(struct device *parent, int region_id,
struct resource *res, int target_node, unsigned int align,
- unsigned long pfn_flags)
+ unsigned long long pfn_flags)
{
struct dax_region *dax_region;
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index 8619e3299943..9e4eba67e8b9 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -11,7 +11,7 @@ struct dax_region;
void dax_region_put(struct dax_region *dax_region);
struct dax_region *alloc_dax_region(struct device *parent, int region_id,
struct resource *res, int target_node, unsigned int align,
- unsigned long flags);
+ unsigned long long flags);
enum dev_dax_subsys {
DEV_DAX_BUS,
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index 6ccca3b890d6..3107ce80e809 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -32,7 +32,7 @@ struct dax_region {
struct device *dev;
unsigned int align;
struct resource res;
- unsigned long pfn_flags;
+ unsigned long long pfn_flags;
};
/**
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH v6 10/12] device-dax: Add a driver for "hmem" devices
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (8 preceding siblings ...)
2019-10-09 23:05 ` [PATCH v6 09/12] dax: Fix alloc_dax_region() compile warning Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
2019-10-09 23:05 ` [PATCH v6 11/12] acpi/numa/hmat: Register HMAT at device_initcall level Dan Williams
2019-10-09 23:05 ` [PATCH v6 12/12] acpi/numa/hmat: Register "soft reserved" memory as an "hmem" device Dan Williams
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: Vishal Verma, Keith Busch, Dave Jiang, kbuild test robot,
Dave Hansen, peterz, ard.biesheuvel, x86, linux-efi,
linux-kernel, linux-acpi
Platform firmware like EFI/ACPI may publish "hmem" platform devices.
Such a device is a performance differentiated memory range likely
reserved for an application specific use case. The driver gives access
to 100% of the capacity via a device-dax mmap instance by default.
However, if over-subscription and other kernel memory management is
desired the resulting dax device can be assigned to the core-mm via the
kmem driver.
This consumes "hmem" devices the producer of "hmem" devices is saved for
a follow-on patch so that it can reference the new CONFIG_DEV_DAX_HMEM
symbol to gate performing the enumeration work.
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Keith Busch <kbusch@kernel.org>
Cc: Dave Jiang <dave.jiang@intel.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/dax/Kconfig | 27 ++++++++++++++++++----
drivers/dax/Makefile | 2 ++
drivers/dax/hmem.c | 56 +++++++++++++++++++++++++++++++++++++++++++++
include/linux/memregion.h | 4 +++
4 files changed, 84 insertions(+), 5 deletions(-)
create mode 100644 drivers/dax/hmem.c
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index f33c73e4af41..3b6c06f07326 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -32,19 +32,36 @@ config DEV_DAX_PMEM
Say M if unsure
+config DEV_DAX_HMEM
+ tristate "HMEM DAX: direct access to 'specific purpose' memory"
+ depends on EFI_SOFT_RESERVE
+ default DEV_DAX
+ help
+ EFI 2.8 platforms, and others, may advertise 'specific purpose'
+ memory. For example, a high bandwidth memory pool. The
+ indication from platform firmware is meant to reserve the
+ memory from typical usage by default. This driver creates
+ device-dax instances for these memory ranges, and that also
+ enables the possibility to assign them to the DEV_DAX_KMEM
+ driver to override the reservation and add them to kernel
+ "System RAM" pool.
+
+ Say M if unsure.
+
config DEV_DAX_KMEM
tristate "KMEM DAX: volatile-use of persistent memory"
default DEV_DAX
depends on DEV_DAX
depends on MEMORY_HOTPLUG # for add_memory() and friends
help
- Support access to persistent memory as if it were RAM. This
- allows easier use of persistent memory by unmodified
- applications.
+ Support access to persistent, or other performance
+ differentiated memory as if it were System RAM. This allows
+ easier use of persistent memory by unmodified applications, or
+ adds core kernel memory services to heterogeneous memory types
+ (HMEM) marked "reserved" by platform firmware.
To use this feature, a DAX device must be unbound from the
- device_dax driver (PMEM DAX) and bound to this kmem driver
- on each boot.
+ device_dax driver and bound to this kmem driver on each boot.
Say N if unsure.
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
index 81f7d54dadfb..80065b38b3c4 100644
--- a/drivers/dax/Makefile
+++ b/drivers/dax/Makefile
@@ -2,9 +2,11 @@
obj-$(CONFIG_DAX) += dax.o
obj-$(CONFIG_DEV_DAX) += device_dax.o
obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
dax-y := super.o
dax-y += bus.o
device_dax-y := device.o
+dax_hmem-y := hmem.o
obj-y += pmem/
diff --git a/drivers/dax/hmem.c b/drivers/dax/hmem.c
new file mode 100644
index 000000000000..fe7214daf62e
--- /dev/null
+++ b/drivers/dax/hmem.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "bus.h"
+
+static int dax_hmem_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct dev_pagemap pgmap = { };
+ struct dax_region *dax_region;
+ struct memregion_info *mri;
+ struct dev_dax *dev_dax;
+ struct resource *res;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENOMEM;
+
+ mri = dev->platform_data;
+ memcpy(&pgmap.res, res, sizeof(*res));
+
+ dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+ PMD_SIZE, PFN_DEV|PFN_MAP);
+ if (!dax_region)
+ return -ENOMEM;
+
+ dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
+ if (IS_ERR(dev_dax))
+ return PTR_ERR(dev_dax);
+
+ /* child dev_dax instances now own the lifetime of the dax_region */
+ dax_region_put(dax_region);
+ return 0;
+}
+
+static int dax_hmem_remove(struct platform_device *pdev)
+{
+ /* devm handles teardown */
+ return 0;
+}
+
+static struct platform_driver dax_hmem_driver = {
+ .probe = dax_hmem_probe,
+ .remove = dax_hmem_remove,
+ .driver = {
+ .name = "hmem",
+ },
+};
+
+module_platform_driver(dax_hmem_driver);
+
+MODULE_ALIAS("platform:hmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/memregion.h b/include/linux/memregion.h
index 7de7c0a1444e..e11595256cac 100644
--- a/include/linux/memregion.h
+++ b/include/linux/memregion.h
@@ -4,6 +4,10 @@
#include <linux/types.h>
#include <linux/errno.h>
+struct memregion_info {
+ int target_node;
+};
+
#ifdef CONFIG_MEMREGION
int memregion_alloc(gfp_t gfp);
void memregion_free(int id);
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH v6 11/12] acpi/numa/hmat: Register HMAT at device_initcall level
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (9 preceding siblings ...)
2019-10-09 23:05 ` [PATCH v6 10/12] device-dax: Add a driver for "hmem" devices Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
2019-10-09 23:05 ` [PATCH v6 12/12] acpi/numa/hmat: Register "soft reserved" memory as an "hmem" device Dan Williams
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: Rafael J. Wysocki, Len Brown, Keith Busch, Jonathan Cameron,
Dave Hansen, peterz, vishal.l.verma, ard.biesheuvel, x86,
linux-efi, linux-kernel, linux-acpi
In preparation for registering device-dax instances for accessing EFI
specific-purpose memory, arrange for the HMAT registration to occur
later in the init process. Critically HMAT initialization needs to occur
after e820__reserve_resources_late() which is the point at which the
iomem resource tree is populated with "Application Reserved"
(IORES_DESC_APPLICATION_RESERVED). e820__reserve_resources_late()
happens at subsys_initcall time.
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Keith Busch <kbusch@kernel.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/acpi/numa/hmat.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 8f9a28a870b0..4707eb9dd07b 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -748,4 +748,4 @@ static __init int hmat_init(void)
acpi_put_table(tbl);
return 0;
}
-subsys_initcall(hmat_init);
+device_initcall(hmat_init);
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH v6 12/12] acpi/numa/hmat: Register "soft reserved" memory as an "hmem" device
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
` (10 preceding siblings ...)
2019-10-09 23:05 ` [PATCH v6 11/12] acpi/numa/hmat: Register HMAT at device_initcall level Dan Williams
@ 2019-10-09 23:05 ` Dan Williams
11 siblings, 0 replies; 23+ messages in thread
From: Dan Williams @ 2019-10-09 23:05 UTC (permalink / raw)
To: mingo
Cc: Len Brown, Keith Busch, Rafael J. Wysocki, Vishal Verma,
Jonathan Cameron, Dave Hansen, peterz, ard.biesheuvel, x86,
linux-efi, linux-kernel, linux-acpi
Memory that has been tagged EFI_MEMORY_SP, and has performance
properties described by the ACPI HMAT is expected to have an application
specific consumer.
Those consumers may want 100% of the memory capacity to be reserved from
any usage by the kernel. By default, with this enabling, a platform
device is created to represent this differentiated resource.
The device-dax "hmem" driver claims these devices by default and
provides an mmap interface for the target application. If the
administrator prefers, the hmem resource range can be made available to
the core-mm via the device-dax hotplug facility, kmem, to online the
memory with its own numa node.
This was tested with an emulated HMAT produced by qemu (with the pending
HMAT enabling patches), and "efi_fake_mem=8G@9G:0x40000" on the kernel
command line to mark the memory ranges associated with node2 and node3
as EFI_MEMORY_SP.
qemu numa configuration options:
-numa node,mem=4G,cpus=0-19,nodeid=0
-numa node,mem=4G,cpus=20-39,nodeid=1
-numa node,mem=4G,nodeid=2
-numa node,mem=4G,nodeid=3
-numa dist,src=0,dst=0,val=10
-numa dist,src=0,dst=1,val=21
-numa dist,src=0,dst=2,val=21
-numa dist,src=0,dst=3,val=21
-numa dist,src=1,dst=0,val=21
-numa dist,src=1,dst=1,val=10
-numa dist,src=1,dst=2,val=21
-numa dist,src=1,dst=3,val=21
-numa dist,src=2,dst=0,val=21
-numa dist,src=2,dst=1,val=21
-numa dist,src=2,dst=2,val=10
-numa dist,src=2,dst=3,val=21
-numa dist,src=3,dst=0,val=21
-numa dist,src=3,dst=1,val=21
-numa dist,src=3,dst=2,val=21
-numa dist,src=3,dst=3,val=10
-numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-latency,base-lat=10,latency=5
-numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=5
-numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-latency,base-lat=10,latency=10
-numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=10
-numa hmat-lb,initiator=0,target=2,hierarchy=memory,data-type=access-latency,base-lat=10,latency=15
-numa hmat-lb,initiator=0,target=2,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=15
-numa hmat-lb,initiator=0,target=3,hierarchy=memory,data-type=access-latency,base-lat=10,latency=20
-numa hmat-lb,initiator=0,target=3,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=20
-numa hmat-lb,initiator=1,target=0,hierarchy=memory,data-type=access-latency,base-lat=10,latency=10
-numa hmat-lb,initiator=1,target=0,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=10
-numa hmat-lb,initiator=1,target=1,hierarchy=memory,data-type=access-latency,base-lat=10,latency=5
-numa hmat-lb,initiator=1,target=1,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=5
-numa hmat-lb,initiator=1,target=2,hierarchy=memory,data-type=access-latency,base-lat=10,latency=15
-numa hmat-lb,initiator=1,target=2,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=15
-numa hmat-lb,initiator=1,target=3,hierarchy=memory,data-type=access-latency,base-lat=10,latency=20
-numa hmat-lb,initiator=1,target=3,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=20
Result:
# daxctl list -RDu
[
{
"path":"\/platform\/hmem.1",
"id":1,
"size":"4.00 GiB (4.29 GB)",
"align":2097152,
"devices":[
{
"chardev":"dax1.0",
"size":"4.00 GiB (4.29 GB)"
}
]
},
{
"path":"\/platform\/hmem.0",
"id":0,
"size":"4.00 GiB (4.29 GB)",
"align":2097152,
"devices":[
{
"chardev":"dax0.0",
"size":"4.00 GiB (4.29 GB)"
}
]
}
]
# cat /proc/iomem
[..]
240000000-43fffffff : Soft Reserved
240000000-33fffffff : hmem.0
240000000-33fffffff : dax0.0
340000000-43fffffff : hmem.1
340000000-43fffffff : dax1.0
Cc: Len Brown <lenb@kernel.org>
Cc: Keith Busch <kbusch@kernel.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/acpi/numa/Kconfig | 1
drivers/acpi/numa/hmat.c | 136 +++++++++++++++++++++++++++++++++++++++++----
2 files changed, 125 insertions(+), 12 deletions(-)
diff --git a/drivers/acpi/numa/Kconfig b/drivers/acpi/numa/Kconfig
index acbd5aa76e40..fcf2e556d69d 100644
--- a/drivers/acpi/numa/Kconfig
+++ b/drivers/acpi/numa/Kconfig
@@ -9,6 +9,7 @@ config ACPI_HMAT
bool "ACPI Heterogeneous Memory Attribute Table Support"
depends on ACPI_NUMA
select HMEM_REPORTING
+ select MEMREGION
help
If set, this option has the kernel parse and report the
platform's ACPI HMAT (Heterogeneous Memory Attributes Table),
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 4707eb9dd07b..eaa5a0f93dec 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -8,12 +8,18 @@
* the applicable attributes with the node's interfaces.
*/
+#define pr_fmt(fmt) "acpi/hmat: " fmt
+#define dev_fmt(fmt) "acpi/hmat: " fmt
+
#include <linux/acpi.h>
#include <linux/bitops.h>
#include <linux/device.h>
#include <linux/init.h>
#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/platform_device.h>
#include <linux/list_sort.h>
+#include <linux/memregion.h>
#include <linux/memory.h>
#include <linux/mutex.h>
#include <linux/node.h>
@@ -49,6 +55,7 @@ struct memory_target {
struct list_head node;
unsigned int memory_pxm;
unsigned int processor_pxm;
+ struct resource memregions;
struct node_hmem_attrs hmem_attrs;
struct list_head caches;
struct node_cache_attrs cache_attrs;
@@ -104,22 +111,36 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
list_add_tail(&initiator->node, &initiators);
}
-static __init void alloc_memory_target(unsigned int mem_pxm)
+static __init void alloc_memory_target(unsigned int mem_pxm,
+ resource_size_t start, resource_size_t len)
{
struct memory_target *target;
target = find_mem_target(mem_pxm);
- if (target)
- return;
-
- target = kzalloc(sizeof(*target), GFP_KERNEL);
- if (!target)
- return;
+ if (!target) {
+ target = kzalloc(sizeof(*target), GFP_KERNEL);
+ if (!target)
+ return;
+ target->memory_pxm = mem_pxm;
+ target->processor_pxm = PXM_INVAL;
+ target->memregions = (struct resource) {
+ .name = "ACPI mem",
+ .start = 0,
+ .end = -1,
+ .flags = IORESOURCE_MEM,
+ };
+ list_add_tail(&target->node, &targets);
+ INIT_LIST_HEAD(&target->caches);
+ }
- target->memory_pxm = mem_pxm;
- target->processor_pxm = PXM_INVAL;
- list_add_tail(&target->node, &targets);
- INIT_LIST_HEAD(&target->caches);
+ /*
+ * There are potentially multiple ranges per PXM, so record each
+ * in the per-target memregions resource tree.
+ */
+ if (!__request_region(&target->memregions, start, len, "memory target",
+ IORESOURCE_MEM))
+ pr_warn("failed to reserve %#llx - %#llx in pxm: %d\n",
+ start, start + len, mem_pxm);
}
static __init const char *hmat_data_type(u8 type)
@@ -452,7 +473,7 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
return -EINVAL;
if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
return 0;
- alloc_memory_target(ma->proximity_domain);
+ alloc_memory_target(ma->proximity_domain, ma->base_address, ma->length);
return 0;
}
@@ -613,10 +634,91 @@ static void hmat_register_target_perf(struct memory_target *target)
node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
}
+static void hmat_register_target_device(struct memory_target *target,
+ struct resource *r)
+{
+ /* define a clean / non-busy resource for the platform device */
+ struct resource res = {
+ .start = r->start,
+ .end = r->end,
+ .flags = IORESOURCE_MEM,
+ };
+ struct platform_device *pdev;
+ struct memregion_info info;
+ int rc, id;
+
+ rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
+ IORES_DESC_SOFT_RESERVED);
+ if (rc != REGION_INTERSECTS)
+ return;
+
+ id = memregion_alloc(GFP_KERNEL);
+ if (id < 0) {
+ pr_err("memregion allocation failure for %pr\n", &res);
+ return;
+ }
+
+ pdev = platform_device_alloc("hmem", id);
+ if (!pdev) {
+ pr_err("hmem device allocation failure for %pr\n", &res);
+ goto out_pdev;
+ }
+
+ pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
+ info = (struct memregion_info) {
+ .target_node = acpi_map_pxm_to_node(target->memory_pxm),
+ };
+ rc = platform_device_add_data(pdev, &info, sizeof(info));
+ if (rc < 0) {
+ pr_err("hmem memregion_info allocation failure for %pr\n", &res);
+ goto out_pdev;
+ }
+
+ rc = platform_device_add_resources(pdev, &res, 1);
+ if (rc < 0) {
+ pr_err("hmem resource allocation failure for %pr\n", &res);
+ goto out_resource;
+ }
+
+ rc = platform_device_add(pdev);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "device add failed for %pr\n", &res);
+ goto out_resource;
+ }
+
+ return;
+
+out_resource:
+ put_device(&pdev->dev);
+out_pdev:
+ memregion_free(id);
+}
+
+static __init void hmat_register_target_devices(struct memory_target *target)
+{
+ struct resource *res;
+
+ /*
+ * Do not bother creating devices if no driver is available to
+ * consume them.
+ */
+ if (!IS_ENABLED(CONFIG_DEV_DAX_HMEM))
+ return;
+
+ for (res = target->memregions.child; res; res = res->sibling)
+ hmat_register_target_device(target, res);
+}
+
static void hmat_register_target(struct memory_target *target)
{
int nid = pxm_to_node(target->memory_pxm);
+ /*
+ * Devices may belong to either an offline or online
+ * node, so unconditionally add them.
+ */
+ hmat_register_target_devices(target);
+
/*
* Skip offline nodes. This can happen when memory
* marked EFI_MEMORY_SP, "specific purpose", is applied
@@ -677,11 +779,21 @@ static __init void hmat_free_structures(void)
struct target_cache *tcache, *cnext;
list_for_each_entry_safe(target, tnext, &targets, node) {
+ struct resource *res, *res_next;
+
list_for_each_entry_safe(tcache, cnext, &target->caches, node) {
list_del(&tcache->node);
kfree(tcache);
}
+
list_del(&target->node);
+ res = target->memregions.child;
+ while (res) {
+ res_next = res->sibling;
+ __release_region(&target->memregions, res->start,
+ resource_size(res));
+ res = res_next;
+ }
kfree(target);
}
^ permalink raw reply related [flat|nested] 23+ messages in thread