WSL2-Linux-Kernel/arch/x86/platform/efi/quirks.c

395 строки
11 KiB
C
Исходник Обычный вид История

#define pr_fmt(fmt) "efi: " fmt
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/types.h>
#include <linux/efi.h>
#include <linux/slab.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/dmi.h>
#include <asm/efi.h>
#include <asm/uv/uv.h>
#define EFI_MIN_RESERVE 5120
#define EFI_DUMMY_GUID \
EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
static bool efi_no_storage_paranoia;
/*
* Some firmware implementations refuse to boot if there's insufficient
* space in the variable store. The implementation of garbage collection
* in some FW versions causes stale (deleted) variables to take up space
* longer than intended and space is only freed once the store becomes
* almost completely full.
*
* Enabling this option disables the space checks in
* efi_query_variable_store() and forces garbage collection.
*
* Only enable this option if deleting EFI variables does not free up
* space in your variable store, e.g. if despite deleting variables
* you're unable to create new ones.
*/
static int __init setup_storage_paranoia(char *arg)
{
efi_no_storage_paranoia = true;
return 0;
}
early_param("efi_no_storage_paranoia", setup_storage_paranoia);
/*
* Deleting the dummy variable which kicks off garbage collection
*/
void efi_delete_dummy_variable(void)
{
efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
EFI_VARIABLE_NON_VOLATILE |
EFI_VARIABLE_BOOTSERVICE_ACCESS |
EFI_VARIABLE_RUNTIME_ACCESS,
0, NULL);
}
/*
* In the nonblocking case we do not attempt to perform garbage
* collection if we do not have enough free space. Rather, we do the
* bare minimum check and give up immediately if the available space
* is below EFI_MIN_RESERVE.
*
* This function is intended to be small and simple because it is
* invoked from crash handler paths.
*/
static efi_status_t
query_variable_store_nonblocking(u32 attributes, unsigned long size)
{
efi_status_t status;
u64 storage_size, remaining_size, max_size;
status = efi.query_variable_info_nonblocking(attributes, &storage_size,
&remaining_size,
&max_size);
if (status != EFI_SUCCESS)
return status;
if (remaining_size - size < EFI_MIN_RESERVE)
return EFI_OUT_OF_RESOURCES;
return EFI_SUCCESS;
}
/*
* Some firmware implementations refuse to boot if there's insufficient space
* in the variable store. Ensure that we never use more than a safe limit.
*
* Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
* store.
*/
efi_status_t efi_query_variable_store(u32 attributes, unsigned long size,
bool nonblocking)
{
efi_status_t status;
u64 storage_size, remaining_size, max_size;
if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
return 0;
if (nonblocking)
return query_variable_store_nonblocking(attributes, size);
status = efi.query_variable_info(attributes, &storage_size,
&remaining_size, &max_size);
if (status != EFI_SUCCESS)
return status;
/*
* We account for that by refusing the write if permitting it would
* reduce the available space to under 5KB. This figure was provided by
* Samsung, so should be safe.
*/
if ((remaining_size - size < EFI_MIN_RESERVE) &&
!efi_no_storage_paranoia) {
/*
* Triggering garbage collection may require that the firmware
* generate a real EFI_OUT_OF_RESOURCES error. We can force
* that by attempting to use more space than is available.
*/
unsigned long dummy_size = remaining_size + 1024;
void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
if (!dummy)
return EFI_OUT_OF_RESOURCES;
status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
EFI_VARIABLE_NON_VOLATILE |
EFI_VARIABLE_BOOTSERVICE_ACCESS |
EFI_VARIABLE_RUNTIME_ACCESS,
dummy_size, dummy);
if (status == EFI_SUCCESS) {
/*
* This should have failed, so if it didn't make sure
* that we delete it...
*/
efi_delete_dummy_variable();
}
kfree(dummy);
/*
* The runtime code may now have triggered a garbage collection
* run, so check the variable info again
*/
status = efi.query_variable_info(attributes, &storage_size,
&remaining_size, &max_size);
if (status != EFI_SUCCESS)
return status;
/*
* There still isn't enough room, so return an error
*/
if (remaining_size - size < EFI_MIN_RESERVE)
return EFI_OUT_OF_RESOURCES;
}
return EFI_SUCCESS;
}
EXPORT_SYMBOL_GPL(efi_query_variable_store);
x86/efi: Fix boot crash by always mapping boot service regions into new EFI page tables Some machines have EFI regions in page zero (physical address 0x00000000) and historically that region has been added to the e820 map via trim_bios_range(), and ultimately mapped into the kernel page tables. It was not mapped via efi_map_regions() as one would expect. Alexis reports that with the new separate EFI page tables some boot services regions, such as page zero, are not mapped. This triggers an oops during the SetVirtualAddressMap() runtime call. For the EFI boot services quirk on x86 we need to memblock_reserve() boot services regions until after SetVirtualAddressMap(). Doing that while respecting the ownership of regions that may have already been reserved by the kernel was the motivation behind this commit: 7d68dc3f1003 ("x86, efi: Do not reserve boot services regions within reserved areas") That patch was merged at a time when the EFI runtime virtual mappings were inserted into the kernel page tables as described above, and the trick of setting ->numpages (and hence the region size) to zero to track regions that should not be freed in efi_free_boot_services() meant that we never mapped those regions in efi_map_regions(). Instead we were relying solely on the existing kernel mappings. Now that we have separate page tables we need to make sure the EFI boot services regions are mapped correctly, even if someone else has already called memblock_reserve(). Instead of stashing a tag in ->numpages, set the EFI_MEMORY_RUNTIME bit of ->attribute. Since it generally makes no sense to mark a boot services region as required at runtime, it's pretty much guaranteed the firmware will not have already set this bit. For the record, the specific circumstances under which Alexis triggered this bug was that an EFI runtime driver on his machine was responding to the EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE event during SetVirtualAddressMap(). The event handler for this driver looks like this, sub rsp,0x28 lea rdx,[rip+0x2445] # 0xaa948720 mov ecx,0x4 call func_aa9447c0 ; call to ConvertPointer(4, & 0xaa948720) mov r11,QWORD PTR [rip+0x2434] # 0xaa948720 xor eax,eax mov BYTE PTR [r11+0x1],0x1 add rsp,0x28 ret Which is pretty typical code for an EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE handler. The "mov r11, QWORD PTR [rip+0x2424]" was the faulting instruction because ConvertPointer() was being called to convert the address 0x0000000000000000, which when converted is left unchanged and remains 0x0000000000000000. The output of the oops trace gave the impression of a standard NULL pointer dereference bug, but because we're accessing physical addresses during ConvertPointer(), it wasn't. EFI boot services code is stored at that address on Alexis' machine. Reported-by: Alexis Murzeau <amurzeau@gmail.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Raphael Hertzog <hertzog@debian.org> Cc: Roger Shimizu <rogershimizu@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1457695163-29632-2-git-send-email-matt@codeblueprint.co.uk Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=815125 Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-11 14:19:23 +03:00
/*
* Helper function for efi_reserve_boot_services() to figure out if we
* can free regions in efi_free_boot_services().
*
* Use this function to ensure we do not free regions owned by somebody
* else. We must only reserve (and then free) regions:
*
* - Not within any part of the kernel
* - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc)
*/
static bool can_free_region(u64 start, u64 size)
{
if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end))
return false;
if (!e820_all_mapped(start, start+size, E820_RAM))
return false;
return true;
}
/*
* The UEFI specification makes it clear that the operating system is free to do
* whatever it wants with boot services code after ExitBootServices() has been
* called. Ignoring this recommendation a significant bunch of EFI implementations
* continue calling into boot services code (SetVirtualAddressMap). In order to
* work around such buggy implementations we reserve boot services region during
* EFI init and make sure it stays executable. Then, after SetVirtualAddressMap(), it
* is discarded.
*/
void __init efi_reserve_boot_services(void)
{
efi_memory_desc_t *md;
for_each_efi_memory_desc(md) {
u64 start = md->phys_addr;
u64 size = md->num_pages << EFI_PAGE_SHIFT;
x86/efi: Fix boot crash by always mapping boot service regions into new EFI page tables Some machines have EFI regions in page zero (physical address 0x00000000) and historically that region has been added to the e820 map via trim_bios_range(), and ultimately mapped into the kernel page tables. It was not mapped via efi_map_regions() as one would expect. Alexis reports that with the new separate EFI page tables some boot services regions, such as page zero, are not mapped. This triggers an oops during the SetVirtualAddressMap() runtime call. For the EFI boot services quirk on x86 we need to memblock_reserve() boot services regions until after SetVirtualAddressMap(). Doing that while respecting the ownership of regions that may have already been reserved by the kernel was the motivation behind this commit: 7d68dc3f1003 ("x86, efi: Do not reserve boot services regions within reserved areas") That patch was merged at a time when the EFI runtime virtual mappings were inserted into the kernel page tables as described above, and the trick of setting ->numpages (and hence the region size) to zero to track regions that should not be freed in efi_free_boot_services() meant that we never mapped those regions in efi_map_regions(). Instead we were relying solely on the existing kernel mappings. Now that we have separate page tables we need to make sure the EFI boot services regions are mapped correctly, even if someone else has already called memblock_reserve(). Instead of stashing a tag in ->numpages, set the EFI_MEMORY_RUNTIME bit of ->attribute. Since it generally makes no sense to mark a boot services region as required at runtime, it's pretty much guaranteed the firmware will not have already set this bit. For the record, the specific circumstances under which Alexis triggered this bug was that an EFI runtime driver on his machine was responding to the EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE event during SetVirtualAddressMap(). The event handler for this driver looks like this, sub rsp,0x28 lea rdx,[rip+0x2445] # 0xaa948720 mov ecx,0x4 call func_aa9447c0 ; call to ConvertPointer(4, & 0xaa948720) mov r11,QWORD PTR [rip+0x2434] # 0xaa948720 xor eax,eax mov BYTE PTR [r11+0x1],0x1 add rsp,0x28 ret Which is pretty typical code for an EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE handler. The "mov r11, QWORD PTR [rip+0x2424]" was the faulting instruction because ConvertPointer() was being called to convert the address 0x0000000000000000, which when converted is left unchanged and remains 0x0000000000000000. The output of the oops trace gave the impression of a standard NULL pointer dereference bug, but because we're accessing physical addresses during ConvertPointer(), it wasn't. EFI boot services code is stored at that address on Alexis' machine. Reported-by: Alexis Murzeau <amurzeau@gmail.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Raphael Hertzog <hertzog@debian.org> Cc: Roger Shimizu <rogershimizu@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1457695163-29632-2-git-send-email-matt@codeblueprint.co.uk Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=815125 Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-11 14:19:23 +03:00
bool already_reserved;
if (md->type != EFI_BOOT_SERVICES_CODE &&
md->type != EFI_BOOT_SERVICES_DATA)
continue;
x86/efi: Fix boot crash by always mapping boot service regions into new EFI page tables Some machines have EFI regions in page zero (physical address 0x00000000) and historically that region has been added to the e820 map via trim_bios_range(), and ultimately mapped into the kernel page tables. It was not mapped via efi_map_regions() as one would expect. Alexis reports that with the new separate EFI page tables some boot services regions, such as page zero, are not mapped. This triggers an oops during the SetVirtualAddressMap() runtime call. For the EFI boot services quirk on x86 we need to memblock_reserve() boot services regions until after SetVirtualAddressMap(). Doing that while respecting the ownership of regions that may have already been reserved by the kernel was the motivation behind this commit: 7d68dc3f1003 ("x86, efi: Do not reserve boot services regions within reserved areas") That patch was merged at a time when the EFI runtime virtual mappings were inserted into the kernel page tables as described above, and the trick of setting ->numpages (and hence the region size) to zero to track regions that should not be freed in efi_free_boot_services() meant that we never mapped those regions in efi_map_regions(). Instead we were relying solely on the existing kernel mappings. Now that we have separate page tables we need to make sure the EFI boot services regions are mapped correctly, even if someone else has already called memblock_reserve(). Instead of stashing a tag in ->numpages, set the EFI_MEMORY_RUNTIME bit of ->attribute. Since it generally makes no sense to mark a boot services region as required at runtime, it's pretty much guaranteed the firmware will not have already set this bit. For the record, the specific circumstances under which Alexis triggered this bug was that an EFI runtime driver on his machine was responding to the EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE event during SetVirtualAddressMap(). The event handler for this driver looks like this, sub rsp,0x28 lea rdx,[rip+0x2445] # 0xaa948720 mov ecx,0x4 call func_aa9447c0 ; call to ConvertPointer(4, & 0xaa948720) mov r11,QWORD PTR [rip+0x2434] # 0xaa948720 xor eax,eax mov BYTE PTR [r11+0x1],0x1 add rsp,0x28 ret Which is pretty typical code for an EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE handler. The "mov r11, QWORD PTR [rip+0x2424]" was the faulting instruction because ConvertPointer() was being called to convert the address 0x0000000000000000, which when converted is left unchanged and remains 0x0000000000000000. The output of the oops trace gave the impression of a standard NULL pointer dereference bug, but because we're accessing physical addresses during ConvertPointer(), it wasn't. EFI boot services code is stored at that address on Alexis' machine. Reported-by: Alexis Murzeau <amurzeau@gmail.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Raphael Hertzog <hertzog@debian.org> Cc: Roger Shimizu <rogershimizu@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1457695163-29632-2-git-send-email-matt@codeblueprint.co.uk Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=815125 Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-11 14:19:23 +03:00
already_reserved = memblock_is_region_reserved(start, size);
/*
* Because the following memblock_reserve() is paired
* with free_bootmem_late() for this region in
* efi_free_boot_services(), we must be extremely
* careful not to reserve, and subsequently free,
* critical regions of memory (like the kernel image) or
* those regions that somebody else has already
* reserved.
*
* A good example of a critical region that must not be
* freed is page zero (first 4Kb of memory), which may
* contain boot services code/data but is marked
* E820_RESERVED by trim_bios_range().
*/
if (!already_reserved) {
memblock_reserve(start, size);
x86/efi: Fix boot crash by always mapping boot service regions into new EFI page tables Some machines have EFI regions in page zero (physical address 0x00000000) and historically that region has been added to the e820 map via trim_bios_range(), and ultimately mapped into the kernel page tables. It was not mapped via efi_map_regions() as one would expect. Alexis reports that with the new separate EFI page tables some boot services regions, such as page zero, are not mapped. This triggers an oops during the SetVirtualAddressMap() runtime call. For the EFI boot services quirk on x86 we need to memblock_reserve() boot services regions until after SetVirtualAddressMap(). Doing that while respecting the ownership of regions that may have already been reserved by the kernel was the motivation behind this commit: 7d68dc3f1003 ("x86, efi: Do not reserve boot services regions within reserved areas") That patch was merged at a time when the EFI runtime virtual mappings were inserted into the kernel page tables as described above, and the trick of setting ->numpages (and hence the region size) to zero to track regions that should not be freed in efi_free_boot_services() meant that we never mapped those regions in efi_map_regions(). Instead we were relying solely on the existing kernel mappings. Now that we have separate page tables we need to make sure the EFI boot services regions are mapped correctly, even if someone else has already called memblock_reserve(). Instead of stashing a tag in ->numpages, set the EFI_MEMORY_RUNTIME bit of ->attribute. Since it generally makes no sense to mark a boot services region as required at runtime, it's pretty much guaranteed the firmware will not have already set this bit. For the record, the specific circumstances under which Alexis triggered this bug was that an EFI runtime driver on his machine was responding to the EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE event during SetVirtualAddressMap(). The event handler for this driver looks like this, sub rsp,0x28 lea rdx,[rip+0x2445] # 0xaa948720 mov ecx,0x4 call func_aa9447c0 ; call to ConvertPointer(4, & 0xaa948720) mov r11,QWORD PTR [rip+0x2434] # 0xaa948720 xor eax,eax mov BYTE PTR [r11+0x1],0x1 add rsp,0x28 ret Which is pretty typical code for an EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE handler. The "mov r11, QWORD PTR [rip+0x2424]" was the faulting instruction because ConvertPointer() was being called to convert the address 0x0000000000000000, which when converted is left unchanged and remains 0x0000000000000000. The output of the oops trace gave the impression of a standard NULL pointer dereference bug, but because we're accessing physical addresses during ConvertPointer(), it wasn't. EFI boot services code is stored at that address on Alexis' machine. Reported-by: Alexis Murzeau <amurzeau@gmail.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Raphael Hertzog <hertzog@debian.org> Cc: Roger Shimizu <rogershimizu@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1457695163-29632-2-git-send-email-matt@codeblueprint.co.uk Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=815125 Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-11 14:19:23 +03:00
/*
* If we are the first to reserve the region, no
* one else cares about it. We own it and can
* free it later.
*/
if (can_free_region(start, size))
continue;
}
/*
* We don't own the region. We must not free it.
*
* Setting this bit for a boot services region really
* doesn't make sense as far as the firmware is
* concerned, but it does provide us with a way to tag
* those regions that must not be paired with
* free_bootmem_late().
*/
md->attribute |= EFI_MEMORY_RUNTIME;
}
}
void __init efi_free_boot_services(void)
{
efi_memory_desc_t *md;
for_each_efi_memory_desc(md) {
unsigned long long start = md->phys_addr;
unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
x86/efi: Allocate a trampoline if needed in efi_free_boot_services() On my Dell XPS 13 9350 with firmware 1.4.4 and SGX on, if I boot Fedora 24's grub2-efi off a hard disk, my first 1MB of RAM looks like: efi: mem00: [Runtime Data |RUN| | | | | | | |WB|WT|WC|UC] range=[0x0000000000000000-0x0000000000000fff] (0MB) efi: mem01: [Boot Data | | | | | | | | |WB|WT|WC|UC] range=[0x0000000000001000-0x0000000000027fff] (0MB) efi: mem02: [Loader Data | | | | | | | | |WB|WT|WC|UC] range=[0x0000000000028000-0x0000000000029fff] (0MB) efi: mem03: [Reserved | | | | | | | | |WB|WT|WC|UC] range=[0x000000000002a000-0x000000000002bfff] (0MB) efi: mem04: [Runtime Data |RUN| | | | | | | |WB|WT|WC|UC] range=[0x000000000002c000-0x000000000002cfff] (0MB) efi: mem05: [Loader Data | | | | | | | | |WB|WT|WC|UC] range=[0x000000000002d000-0x000000000002dfff] (0MB) efi: mem06: [Conventional Memory| | | | | | | | |WB|WT|WC|UC] range=[0x000000000002e000-0x0000000000057fff] (0MB) efi: mem07: [Reserved | | | | | | | | |WB|WT|WC|UC] range=[0x0000000000058000-0x0000000000058fff] (0MB) efi: mem08: [Conventional Memory| | | | | | | | |WB|WT|WC|UC] range=[0x0000000000059000-0x000000000009ffff] (0MB) My EBDA is at 0x2c000, which blocks off everything from 0x2c000 and up, and my trampoline is 0x6000 bytes (6 pages), so it doesn't fit in the loader data range at 0x28000. Without this patch, it panics due to a failure to allocate the trampoline. With this patch, it works: [ +0.001744] Base memory trampoline at [ffff880000001000] 1000 size 24576 Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mario Limonciello <mario_limonciello@dell.com> Cc: Matt Fleming <mfleming@suse.de> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/998c77b3bf709f3dfed85cb30701ed1a5d8a438b.1470821230.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-10 12:29:17 +03:00
size_t rm_size;
if (md->type != EFI_BOOT_SERVICES_CODE &&
md->type != EFI_BOOT_SERVICES_DATA)
continue;
x86/efi: Fix boot crash by always mapping boot service regions into new EFI page tables Some machines have EFI regions in page zero (physical address 0x00000000) and historically that region has been added to the e820 map via trim_bios_range(), and ultimately mapped into the kernel page tables. It was not mapped via efi_map_regions() as one would expect. Alexis reports that with the new separate EFI page tables some boot services regions, such as page zero, are not mapped. This triggers an oops during the SetVirtualAddressMap() runtime call. For the EFI boot services quirk on x86 we need to memblock_reserve() boot services regions until after SetVirtualAddressMap(). Doing that while respecting the ownership of regions that may have already been reserved by the kernel was the motivation behind this commit: 7d68dc3f1003 ("x86, efi: Do not reserve boot services regions within reserved areas") That patch was merged at a time when the EFI runtime virtual mappings were inserted into the kernel page tables as described above, and the trick of setting ->numpages (and hence the region size) to zero to track regions that should not be freed in efi_free_boot_services() meant that we never mapped those regions in efi_map_regions(). Instead we were relying solely on the existing kernel mappings. Now that we have separate page tables we need to make sure the EFI boot services regions are mapped correctly, even if someone else has already called memblock_reserve(). Instead of stashing a tag in ->numpages, set the EFI_MEMORY_RUNTIME bit of ->attribute. Since it generally makes no sense to mark a boot services region as required at runtime, it's pretty much guaranteed the firmware will not have already set this bit. For the record, the specific circumstances under which Alexis triggered this bug was that an EFI runtime driver on his machine was responding to the EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE event during SetVirtualAddressMap(). The event handler for this driver looks like this, sub rsp,0x28 lea rdx,[rip+0x2445] # 0xaa948720 mov ecx,0x4 call func_aa9447c0 ; call to ConvertPointer(4, & 0xaa948720) mov r11,QWORD PTR [rip+0x2434] # 0xaa948720 xor eax,eax mov BYTE PTR [r11+0x1],0x1 add rsp,0x28 ret Which is pretty typical code for an EVT_SIGNAL_VIRTUAL_ADDRESS_CHANGE handler. The "mov r11, QWORD PTR [rip+0x2424]" was the faulting instruction because ConvertPointer() was being called to convert the address 0x0000000000000000, which when converted is left unchanged and remains 0x0000000000000000. The output of the oops trace gave the impression of a standard NULL pointer dereference bug, but because we're accessing physical addresses during ConvertPointer(), it wasn't. EFI boot services code is stored at that address on Alexis' machine. Reported-by: Alexis Murzeau <amurzeau@gmail.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Raphael Hertzog <hertzog@debian.org> Cc: Roger Shimizu <rogershimizu@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1457695163-29632-2-git-send-email-matt@codeblueprint.co.uk Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=815125 Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-11 14:19:23 +03:00
/* Do not free, someone else owns it: */
if (md->attribute & EFI_MEMORY_RUNTIME)
continue;
x86/efi: Allocate a trampoline if needed in efi_free_boot_services() On my Dell XPS 13 9350 with firmware 1.4.4 and SGX on, if I boot Fedora 24's grub2-efi off a hard disk, my first 1MB of RAM looks like: efi: mem00: [Runtime Data |RUN| | | | | | | |WB|WT|WC|UC] range=[0x0000000000000000-0x0000000000000fff] (0MB) efi: mem01: [Boot Data | | | | | | | | |WB|WT|WC|UC] range=[0x0000000000001000-0x0000000000027fff] (0MB) efi: mem02: [Loader Data | | | | | | | | |WB|WT|WC|UC] range=[0x0000000000028000-0x0000000000029fff] (0MB) efi: mem03: [Reserved | | | | | | | | |WB|WT|WC|UC] range=[0x000000000002a000-0x000000000002bfff] (0MB) efi: mem04: [Runtime Data |RUN| | | | | | | |WB|WT|WC|UC] range=[0x000000000002c000-0x000000000002cfff] (0MB) efi: mem05: [Loader Data | | | | | | | | |WB|WT|WC|UC] range=[0x000000000002d000-0x000000000002dfff] (0MB) efi: mem06: [Conventional Memory| | | | | | | | |WB|WT|WC|UC] range=[0x000000000002e000-0x0000000000057fff] (0MB) efi: mem07: [Reserved | | | | | | | | |WB|WT|WC|UC] range=[0x0000000000058000-0x0000000000058fff] (0MB) efi: mem08: [Conventional Memory| | | | | | | | |WB|WT|WC|UC] range=[0x0000000000059000-0x000000000009ffff] (0MB) My EBDA is at 0x2c000, which blocks off everything from 0x2c000 and up, and my trampoline is 0x6000 bytes (6 pages), so it doesn't fit in the loader data range at 0x28000. Without this patch, it panics due to a failure to allocate the trampoline. With this patch, it works: [ +0.001744] Base memory trampoline at [ffff880000001000] 1000 size 24576 Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mario Limonciello <mario_limonciello@dell.com> Cc: Matt Fleming <mfleming@suse.de> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/998c77b3bf709f3dfed85cb30701ed1a5d8a438b.1470821230.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-10 12:29:17 +03:00
/*
* Nasty quirk: if all sub-1MB memory is used for boot
* services, we can get here without having allocated the
* real mode trampoline. It's too late to hand boot services
* memory back to the memblock allocator, so instead
* try to manually allocate the trampoline if needed.
*
* I've seen this on a Dell XPS 13 9350 with firmware
* 1.4.4 with SGX enabled booting Linux via Fedora 24's
* grub2-efi on a hard disk. (And no, I don't know why
* this happened, but Linux should still try to boot rather
* panicing early.)
*/
rm_size = real_mode_size_needed();
if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
set_real_mode_mem(start, rm_size);
start += rm_size;
size -= rm_size;
}
free_bootmem_late(start, size);
}
}
/*
* A number of config table entries get remapped to virtual addresses
* after entering EFI virtual mode. However, the kexec kernel requires
* their physical addresses therefore we pass them via setup_data and
* correct those entries to their respective physical addresses here.
*
* Currently only handles smbios which is necessary for some firmware
* implementation.
*/
int __init efi_reuse_config(u64 tables, int nr_tables)
{
int i, sz, ret = 0;
void *p, *tablep;
struct efi_setup_data *data;
if (!efi_setup)
return 0;
if (!efi_enabled(EFI_64BIT))
return 0;
data = early_memremap(efi_setup, sizeof(*data));
if (!data) {
ret = -ENOMEM;
goto out;
}
if (!data->smbios)
goto out_memremap;
sz = sizeof(efi_config_table_64_t);
p = tablep = early_memremap(tables, nr_tables * sz);
if (!p) {
pr_err("Could not map Configuration table!\n");
ret = -ENOMEM;
goto out_memremap;
}
for (i = 0; i < efi.systab->nr_tables; i++) {
efi_guid_t guid;
guid = ((efi_config_table_64_t *)p)->guid;
if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
((efi_config_table_64_t *)p)->table = data->smbios;
p += sz;
}
early_memunmap(tablep, nr_tables * sz);
out_memremap:
early_memunmap(data, sizeof(*data));
out:
return ret;
}
static const struct dmi_system_id sgi_uv1_dmi[] = {
{ NULL, "SGI UV1",
{ DMI_MATCH(DMI_PRODUCT_NAME, "Stoutland Platform"),
DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
DMI_MATCH(DMI_BIOS_VENDOR, "SGI.COM"),
}
},
{ } /* NULL entry stops DMI scanning */
};
void __init efi_apply_memmap_quirks(void)
{
/*
* Once setup is done earlier, unmap the EFI memory map on mismatched
* firmware/kernel architectures since there is no support for runtime
* services.
*/
if (!efi_runtime_supported()) {
pr_info("Setup done, disabling due to 32/64-bit mismatch\n");
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>
2016-02-27 00:22:05 +03:00
efi_memmap_unmap();
}
/* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */
if (dmi_check_system(sgi_uv1_dmi))
set_bit(EFI_OLD_MEMMAP, &efi.flags);
}
/*
* For most modern platforms the preferred method of powering off is via
* ACPI. However, there are some that are known to require the use of
* EFI runtime services and for which ACPI does not work at all.
*
* Using EFI is a last resort, to be used only if no other option
* exists.
*/
bool efi_reboot_required(void)
{
if (!acpi_gbl_reduced_hardware)
return false;
efi_reboot_quirk_mode = EFI_RESET_WARM;
return true;
}
bool efi_poweroff_required(void)
{
return acpi_gbl_reduced_hardware || acpi_no_s5;
}