linux-stable/drivers/firmware/efi/efi-init.c

242 lines
6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Extensible Firmware Interface
*
* Based on Extensible Firmware Interface Specification version 2.4
*
* Copyright (C) 2013 - 2015 Linaro Ltd.
*/
#define pr_fmt(fmt) "efi: " fmt
#include <linux/efi.h>
#include <linux/fwnode.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/mm_types.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_fdt.h>
#include <linux/platform_device.h>
#include <linux/screen_info.h>
#include <asm/efi.h>
unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR;
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
static int __init is_memory(efi_memory_desc_t *md)
{
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
if (md->attribute & (EFI_MEMORY_WB|EFI_MEMORY_WT|EFI_MEMORY_WC))
return 1;
return 0;
}
/*
* Translate a EFI virtual address into a physical address: this is necessary,
* as some data members of the EFI system table are virtually remapped after
* SetVirtualAddressMap() has been called.
*/
static phys_addr_t __init efi_to_phys(unsigned long addr)
{
efi_memory_desc_t *md;
for_each_efi_memory_desc(md) {
if (!(md->attribute & EFI_MEMORY_RUNTIME))
continue;
if (md->virt_addr == 0)
/* no virtual mapping has been installed by the stub */
break;
if (md->virt_addr <= addr &&
(addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT))
return md->phys_addr + addr - md->virt_addr;
}
return addr;
}
extern __weak const efi_config_table_type_t efi_arch_tables[];
static void __init init_screen_info(void)
{
struct screen_info *si;
if (screen_info_table != EFI_INVALID_TABLE_ADDR) {
si = early_memremap(screen_info_table, sizeof(*si));
if (!si) {
pr_err("Could not map screen_info config table\n");
return;
}
screen_info = *si;
memset(si, 0, sizeof(*si));
early_memunmap(si, sizeof(*si));
if (memblock_is_map_memory(screen_info.lfb_base))
memblock_mark_nomap(screen_info.lfb_base,
screen_info.lfb_size);
}
}
static int __init uefi_init(u64 efi_system_table)
{
efi_config_table_t *config_tables;
efi_system_table_t *systab;
size_t table_size;
int retval;
systab = early_memremap_ro(efi_system_table, sizeof(efi_system_table_t));
if (systab == NULL) {
pr_warn("Unable to map EFI system table.\n");
return -ENOMEM;
}
set_bit(EFI_BOOT, &efi.flags);
if (IS_ENABLED(CONFIG_64BIT))
set_bit(EFI_64BIT, &efi.flags);
retval = efi_systab_check_header(&systab->hdr, 2);
if (retval)
goto out;
efi.runtime = systab->runtime;
efi.runtime_version = systab->hdr.revision;
efi_systab_report_header(&systab->hdr, efi_to_phys(systab->fw_vendor));
table_size = sizeof(efi_config_table_t) * systab->nr_tables;
config_tables = early_memremap_ro(efi_to_phys(systab->tables),
table_size);
if (config_tables == NULL) {
pr_warn("Unable to map EFI config table array.\n");
retval = -ENOMEM;
goto out;
}
retval = efi_config_parse_tables(config_tables, systab->nr_tables,
efi_arch_tables);
early_memunmap(config_tables, table_size);
out:
early_memunmap(systab, sizeof(efi_system_table_t));
return retval;
}
/*
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
* Return true for regions that can be used as System RAM.
*/
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
static __init int is_usable_memory(efi_memory_desc_t *md)
{
switch (md->type) {
case EFI_LOADER_CODE:
case EFI_LOADER_DATA:
efi/arm: Don't mark ACPI reclaim memory as MEMBLOCK_NOMAP On ARM, regions of memory that are described by UEFI as having special significance to the firmware itself are omitted from the linear mapping. This is necessary since we cannot guarantee that alternate mappings of the same physical region will use attributes that are compatible with the ones we use for the linear mapping, and aliases with mismatched attributes are prohibited by the architecture. The above does not apply to ACPI reclaim regions: such regions have no special significance to the firmware, and it is up to the OS to decide whether or not to preserve them after it has consumed their contents, and for how long, after which time the OS can use the memory in any way it likes. In the Linux case, such regions are preserved indefinitely, and are simply treated the same way as other 'reserved' memory types. Punching holes into the linear mapping causes page table fragmentation, which increases TLB pressure, and so we should avoid doing so if we can. So add a special case for regions of type EFI_ACPI_RECLAIM_MEMORY, and memblock_reserve() them instead of marking them MEMBLOCK_NOMAP. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Mark Rutland <mark.rutland@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matt Fleming <matt@codeblueprint.co.uk> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20170818194947.19347-2-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-18 19:49:34 +00:00
case EFI_ACPI_RECLAIM_MEMORY:
case EFI_BOOT_SERVICES_CODE:
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;
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
/*
* According to the spec, these regions are no longer reserved
* after calling ExitBootServices(). However, we can only use
* them as System RAM if they can be mapped writeback cacheable.
*/
return (md->attribute & EFI_MEMORY_WB);
default:
break;
}
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
return false;
}
static __init void reserve_regions(void)
{
efi_memory_desc_t *md;
u64 paddr, npages, size;
if (efi_enabled(EFI_DBG))
pr_info("Processing EFI memory map:\n");
/*
* Discard memblocks discovered so far: if there are any at this
* point, they originate from memory nodes in the DT, and UEFI
* uses its own memory map instead.
*/
memblock_dump_all();
memblock_remove(0, PHYS_ADDR_MAX);
for_each_efi_memory_desc(md) {
paddr = md->phys_addr;
npages = md->num_pages;
if (efi_enabled(EFI_DBG)) {
char buf[64];
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
pr_info(" 0x%012llx-0x%012llx %s\n",
paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
efi_md_typeattr_format(buf, sizeof(buf), md));
}
memrange_efi_to_native(&paddr, &npages);
size = npages << PAGE_SHIFT;
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
if (is_memory(md)) {
early_init_dt_add_memory_arch(paddr, size);
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
if (!is_usable_memory(md))
memblock_mark_nomap(paddr, size);
efi/arm: Don't mark ACPI reclaim memory as MEMBLOCK_NOMAP On ARM, regions of memory that are described by UEFI as having special significance to the firmware itself are omitted from the linear mapping. This is necessary since we cannot guarantee that alternate mappings of the same physical region will use attributes that are compatible with the ones we use for the linear mapping, and aliases with mismatched attributes are prohibited by the architecture. The above does not apply to ACPI reclaim regions: such regions have no special significance to the firmware, and it is up to the OS to decide whether or not to preserve them after it has consumed their contents, and for how long, after which time the OS can use the memory in any way it likes. In the Linux case, such regions are preserved indefinitely, and are simply treated the same way as other 'reserved' memory types. Punching holes into the linear mapping causes page table fragmentation, which increases TLB pressure, and so we should avoid doing so if we can. So add a special case for regions of type EFI_ACPI_RECLAIM_MEMORY, and memblock_reserve() them instead of marking them MEMBLOCK_NOMAP. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Mark Rutland <mark.rutland@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matt Fleming <matt@codeblueprint.co.uk> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20170818194947.19347-2-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-18 19:49:34 +00:00
/* keep ACPI reclaim memory intact for kexec etc. */
if (md->type == EFI_ACPI_RECLAIM_MEMORY)
memblock_reserve(paddr, size);
efi/arm64: Treat regions with WT/WC set but WB cleared as memory Currently, memory regions are only recorded in the memblock memory table if they have the EFI_MEMORY_WB memory type attribute set. In case the region is of a reserved type, it is also marked as MEMBLOCK_NOMAP, which will leave it out of the linear mapping. However, memory regions may legally have the EFI_MEMORY_WT or EFI_MEMORY_WC attributes set, and the EFI_MEMORY_WB cleared, in which case the region in question is obviously backed by normal memory, but is not recorded in the memblock memory table at all. Since it would be useful to be able to identify any UEFI reported memory region using memblock_is_memory(), it makes sense to add all memory to the memblock memory table, and simply mark it as MEMBLOCK_NOMAP if it lacks the EFI_MEMORY_WB attribute. While implementing this, let's refactor the code slightly to make it easier to understand: replace is_normal_ram() with is_memory(), and make it return true for each region that has any of the WB|WT|WC bits set. (This follows the AArch64 bindings in the UEFI spec, which state that those are the attributes that map to normal memory) Also, replace is_reserve_region() with is_usable_memory(), and only invoke it if the region in question was identified as memory by is_memory() in the first place. The net result is the same (only reserved regions that are backed by memory end up in the memblock memory table with the MEMBLOCK_NOMAP flag set) but carried out in a more straightforward way. Finally, we remove the trailing asterisk in the EFI debug output. Keeping it clutters the code, and it serves no real purpose now that we no longer temporarily reserve BootServices code and data regions like we did in the early days of EFI support on arm64 Linux (which it inherited from the x86 implementation) Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Leif Lindholm <leif.lindholm@linaro.org> Tested-by: James Morse <james.morse@arm.com> Reviewed-by: James Morse <james.morse@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-08-25 16:17:09 +00:00
}
}
}
void __init efi_init(void)
{
efi: Refactor efi_memmap_init_early() into arch-neutral code Every EFI architecture apart from ia64 needs to setup the EFI memory map at efi.memmap, and the code for doing that is essentially the same across all implementations. Therefore, it makes sense to factor this out into the common code under drivers/firmware/efi/. The only slight variation is the data structure out of which we pull the initial memory map information, such as physical address, memory descriptor size and version, etc. We can address this by passing a generic data structure (struct efi_memory_map_data) as the argument to efi_memmap_init_early() which contains the minimum info required for initialising the memory map. In the process, this patch also fixes a few undesirable implementation differences: - ARM and arm64 were failing to clear the EFI_MEMMAP bit when unmapping the early EFI memory map. EFI_MEMMAP indicates whether the EFI memory map is mapped (not the regions contained within) and can be traversed. It's more correct to set the bit as soon as we memremap() the passed in EFI memmap. - Rename efi_unmmap_memmap() to efi_memmap_unmap() to adhere to the regular naming scheme. This patch also uses a read-write mapping for the memory map instead of the read-only mapping currently used on ARM and arm64. x86 needs the ability to update the memory map in-place when assigning virtual addresses to regions (efi_map_region()) and tagging regions when reserving boot services (efi_reserve_boot_services()). There's no way for the generic fake_mem code to know which mapping to use without introducing some arch-specific constant/hook, so just use read-write since read-only is of dubious value for the EFI memory map. Tested-by: Dave Young <dyoung@redhat.com> [kexec/kdump] Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> [arm] Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Leif Lindholm <leif.lindholm@linaro.org> Cc: Peter Jones <pjones@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-02-26 21:22:05 +00:00
struct efi_memory_map_data data;
u64 efi_system_table;
/* Grab UEFI information placed in FDT by stub */
efi_system_table = efi_get_fdt_params(&data);
if (!efi_system_table)
return;
efi: Refactor efi_memmap_init_early() into arch-neutral code Every EFI architecture apart from ia64 needs to setup the EFI memory map at efi.memmap, and the code for doing that is essentially the same across all implementations. Therefore, it makes sense to factor this out into the common code under drivers/firmware/efi/. The only slight variation is the data structure out of which we pull the initial memory map information, such as physical address, memory descriptor size and version, etc. We can address this by passing a generic data structure (struct efi_memory_map_data) as the argument to efi_memmap_init_early() which contains the minimum info required for initialising the memory map. In the process, this patch also fixes a few undesirable implementation differences: - ARM and arm64 were failing to clear the EFI_MEMMAP bit when unmapping the early EFI memory map. EFI_MEMMAP indicates whether the EFI memory map is mapped (not the regions contained within) and can be traversed. It's more correct to set the bit as soon as we memremap() the passed in EFI memmap. - Rename efi_unmmap_memmap() to efi_memmap_unmap() to adhere to the regular naming scheme. This patch also uses a read-write mapping for the memory map instead of the read-only mapping currently used on ARM and arm64. x86 needs the ability to update the memory map in-place when assigning virtual addresses to regions (efi_map_region()) and tagging regions when reserving boot services (efi_reserve_boot_services()). There's no way for the generic fake_mem code to know which mapping to use without introducing some arch-specific constant/hook, so just use read-write since read-only is of dubious value for the EFI memory map. Tested-by: Dave Young <dyoung@redhat.com> [kexec/kdump] Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> [arm] Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Leif Lindholm <leif.lindholm@linaro.org> Cc: Peter Jones <pjones@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-02-26 21:22:05 +00:00
if (efi_memmap_init_early(&data) < 0) {
/*
* If we are booting via UEFI, the UEFI memory map is the only
* description of memory we have, so there is little point in
* proceeding if we cannot access it.
*/
panic("Unable to map EFI memory map.\n");
}
WARN(efi.memmap.desc_version != 1,
"Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
efi.memmap.desc_version);
if (uefi_init(efi_system_table) < 0) {
efi_memmap_unmap();
return;
}
reserve_regions();
efi: apply memblock cap after memblock_add() On arm64, during kdump kernel saves vmcore, it runs into the following bug: ... [ 15.148919] usercopy: Kernel memory exposure attempt detected from SLUB object 'kmem_cache_node' (offset 0, size 4096)! [ 15.159707] ------------[ cut here ]------------ [ 15.164311] kernel BUG at mm/usercopy.c:99! [ 15.168482] Internal error: Oops - BUG: 0 [#1] SMP [ 15.173261] Modules linked in: xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 sha1_ce sbsa_gwdt ast i2c_algo_bit drm_vram_helper drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops cec drm_ttm_helper ttm drm nvme nvme_core xgene_hwmon i2c_designware_platform i2c_designware_core dm_mirror dm_region_hash dm_log dm_mod overlay squashfs zstd_decompress loop [ 15.206186] CPU: 0 PID: 542 Comm: cp Not tainted 5.16.0-rc4 #1 [ 15.212006] Hardware name: GIGABYTE R272-P30-JG/MP32-AR0-JG, BIOS F12 (SCP: 1.5.20210426) 05/13/2021 [ 15.221125] pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 15.228073] pc : usercopy_abort+0x9c/0xa0 [ 15.232074] lr : usercopy_abort+0x9c/0xa0 [ 15.236070] sp : ffff8000121abba0 [ 15.239371] x29: ffff8000121abbb0 x28: 0000000000003000 x27: 0000000000000000 [ 15.246494] x26: 0000000080000400 x25: 0000ffff885c7000 x24: 0000000000000000 [ 15.253617] x23: 000007ff80400000 x22: ffff07ff80401000 x21: 0000000000000001 [ 15.260739] x20: 0000000000001000 x19: ffff07ff80400000 x18: ffffffffffffffff [ 15.267861] x17: 656a626f2042554c x16: 53206d6f72662064 x15: 6574636574656420 [ 15.274983] x14: 74706d6574746120 x13: 2129363930342065 x12: 7a6973202c302074 [ 15.282105] x11: ffffc8b041d1b148 x10: 00000000ffff8000 x9 : ffffc8b04012812c [ 15.289228] x8 : 00000000ffff7fff x7 : ffffc8b041d1b148 x6 : 0000000000000000 [ 15.296349] x5 : 0000000000000000 x4 : 0000000000007fff x3 : 0000000000000000 [ 15.303471] x2 : 0000000000000000 x1 : ffff07ff8c064800 x0 : 000000000000006b [ 15.310593] Call trace: [ 15.313027] usercopy_abort+0x9c/0xa0 [ 15.316677] __check_heap_object+0xd4/0xf0 [ 15.320762] __check_object_size.part.0+0x160/0x1e0 [ 15.325628] __check_object_size+0x2c/0x40 [ 15.329711] copy_oldmem_page+0x7c/0x140 [ 15.333623] read_from_oldmem.part.0+0xfc/0x1c0 [ 15.338142] __read_vmcore.constprop.0+0x23c/0x350 [ 15.342920] read_vmcore+0x28/0x34 [ 15.346309] proc_reg_read+0xb4/0xf0 [ 15.349871] vfs_read+0xb8/0x1f0 [ 15.353088] ksys_read+0x74/0x100 [ 15.356390] __arm64_sys_read+0x28/0x34 ... This bug introduced by commit b261dba2fdb2 ("arm64: kdump: Remove custom linux,usable-memory-range handling"), which moves memblock_cap_memory_range() to fdt, but it breaches the rules that memblock_cap_memory_range() should come after memblock_add() etc as said in commit e888fa7bb882 ("memblock: Check memory add/cap ordering"). As a consequence, the virtual address set up by copy_oldmem_page() does not bail out from the test of virt_addr_valid() in check_heap_object(), and finally hits the BUG_ON(). Since memblock allocator has no idea about when the memblock is fully populated, while efi_init() is aware, so tackling this issue by calling the interface early_init_dt_check_for_usable_mem_range() exposed by of/fdt. Fixes: b261dba2fdb2 ("arm64: kdump: Remove custom linux,usable-memory-range handling") Signed-off-by: Pingfan Liu <kernelfans@gmail.com> Cc: Rob Herring <robh+dt@kernel.org> Cc: Zhen Lei <thunder.leizhen@huawei.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Geert Uytterhoeven <geert+renesas@glider.be> Cc: Frank Rowand <frowand.list@gmail.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Nick Terrell <terrelln@fb.com> Cc: linux-arm-kernel@lists.infradead.org To: devicetree@vger.kernel.org To: linux-efi@vger.kernel.org Acked-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Rob Herring <robh@kernel.org> Link: https://lore.kernel.org/r/20211215021348.8766-1-kernelfans@gmail.com
2021-12-15 02:13:48 +00:00
/*
* For memblock manipulation, the cap should come after the memblock_add().
* And now, memblock is fully populated, it is time to do capping.
*/
early_init_dt_check_for_usable_mem_range();
efi_find_mirror();
efi_esrt_init();
efi_mokvar_table_init();
efi/arm64: Don't apply MEMBLOCK_NOMAP to UEFI memory map mapping Commit 4dffbfc48d65 ("arm64/efi: mark UEFI reserved regions as MEMBLOCK_NOMAP") updated the mapping logic of both the RuntimeServices regions as well as the kernel's copy of the UEFI memory map to set the MEMBLOCK_NOMAP flag, which causes these regions to be omitted from the kernel direct mapping, and from being covered by a struct page. For the RuntimeServices regions, this is an obvious win, since the contents of these regions have significance to the firmware executable code itself, and are mapped in the EFI page tables using attributes that are described in the UEFI memory map, and which may differ from the attributes we use for mapping system RAM. It also prevents the contents from being modified inadvertently, since the EFI page tables are only live during runtime service invocations. None of these concerns apply to the allocation that covers the UEFI memory map, since it is entirely owned by the kernel. Setting the MEMBLOCK_NOMAP on the region did allow us to use ioremap_cache() to map it both on arm64 and on ARM, since the latter does not allow ioremap_cache() to be used on regions that are covered by a struct page. The ioremap_cache() on ARM restriction will be lifted in the v4.7 timeframe, but in the mean time, it has been reported that commit 4dffbfc48d65 causes a regression on 64k granule kernels. This is due to the fact that, given the 64 KB page size, the region that we end up removing from the kernel direct mapping is rounded up to 64 KB, and this 64 KB page frame may be shared with the initrd when booting via GRUB (which does not align its EFI_LOADER_DATA allocations to 64 KB like the stub does). This will crash the kernel as soon as it tries to access the initrd. Since the issue is specific to arm64, revert back to memblock_reserve()'ing the UEFI memory map when running on arm64. This is a temporary fix for v4.5 and v4.6, and will be superseded in the v4.7 timeframe when we will be able to move back to memblock_reserve() unconditionally. Fixes: 4dffbfc48d65 ("arm64/efi: mark UEFI reserved regions as MEMBLOCK_NOMAP") Reported-by: Mark Salter <msalter@redhat.com> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Leif Lindholm <leif.lindholm@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Jeremy Linton <jeremy.linton@arm.com> Cc: Mark Langsdorf <mlangsdo@redhat.com> Cc: <stable@vger.kernel.org> # v4.5 Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-03-30 07:46:23 +00:00
memblock_reserve(data.phys_map & PAGE_MASK,
PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK)));
init_screen_info();
}