linux_dsm_epyc7002/drivers/firmware/efi/fake_mem.c

142 lines
3.5 KiB
C
Raw Normal View History

/*
* fake_mem.c
*
* Copyright (C) 2015 FUJITSU LIMITED
* Author: Taku Izumi <izumi.taku@jp.fujitsu.com>
*
* This code introduces new boot option named "efi_fake_mem"
* By specifying this parameter, you can add arbitrary attribute to
* specific memory range by updating original (firmware provided) EFI
* memmap.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along with
* this program; if not, see <http://www.gnu.org/licenses/>.
*
* The full GNU General Public License is included in this distribution in
* the file called "COPYING".
*/
#include <linux/kernel.h>
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/types.h>
#include <linux/sort.h>
#include <asm/efi.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;
static int __init cmp_fake_mem(const void *x1, const void *x2)
{
const struct efi_mem_range *m1 = x1;
const struct efi_mem_range *m2 = x2;
if (m1->range.start < m2->range.start)
return -1;
if (m1->range.start > m2->range.start)
return 1;
return 0;
}
void __init efi_fake_memmap(void)
{
int new_nr_map = efi.memmap.nr_map;
efi_memory_desc_t *md;
phys_addr_t new_memmap_phy;
void *new_memmap;
int i;
if (!nr_fake_mem)
return;
/* 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;
new_nr_map += efi_memmap_split_count(md, r);
}
}
/* allocate memory for new EFI memmap */
x86/efi: Don't allocate memmap through memblock after mm_init() With the following commit: 4bc9f92e64c8 ("x86/efi-bgrt: Use efi_mem_reserve() to avoid copying image data") ... efi_bgrt_init() calls into the memblock allocator through efi_mem_reserve() => efi_arch_mem_reserve() *after* mm_init() has been called. Indeed, KASAN reports a bad read access later on in efi_free_boot_services(): BUG: KASAN: use-after-free in efi_free_boot_services+0xae/0x24c at addr ffff88022de12740 Read of size 4 by task swapper/0/0 page:ffffea0008b78480 count:0 mapcount:-127 mapping: (null) index:0x1 flags: 0x5fff8000000000() [...] Call Trace: dump_stack+0x68/0x9f kasan_report_error+0x4c8/0x500 kasan_report+0x58/0x60 __asan_load4+0x61/0x80 efi_free_boot_services+0xae/0x24c start_kernel+0x527/0x562 x86_64_start_reservations+0x24/0x26 x86_64_start_kernel+0x157/0x17a start_cpu+0x5/0x14 The instruction at the given address is the first read from the memmap's memory, i.e. the read of md->type in efi_free_boot_services(). Note that the writes earlier in efi_arch_mem_reserve() don't splat because they're done through early_memremap()ed addresses. So, after memblock is gone, allocations should be done through the "normal" page allocator. Introduce a helper, efi_memmap_alloc() for this. Use it from efi_arch_mem_reserve(), efi_free_boot_services() and, for the sake of consistency, from efi_fake_memmap() as well. Note that for the latter, the memmap allocations cease to be page aligned. This isn't needed though. Tested-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Nicolai Stange <nicstange@gmail.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: <stable@vger.kernel.org> # v4.9 Cc: Dave Young <dyoung@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matt Fleming <matt@codeblueprint.co.uk> Cc: Mika Penttilä <mika.penttila@nextfour.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-efi@vger.kernel.org Fixes: 4bc9f92e64c8 ("x86/efi-bgrt: Use efi_mem_reserve() to avoid copying image data") Link: http://lkml.kernel.org/r/20170105125130.2815-1-nicstange@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-05 19:51:29 +07:00
new_memmap_phy = efi_memmap_alloc(new_nr_map);
if (!new_memmap_phy)
return;
/* create new EFI memmap */
new_memmap = early_memremap(new_memmap_phy,
efi.memmap.desc_size * new_nr_map);
if (!new_memmap) {
memblock_free(new_memmap_phy, efi.memmap.desc_size * new_nr_map);
return;
}
for (i = 0; i < nr_fake_mem; i++)
efi_memmap_insert(&efi.memmap, new_memmap, &fake_mems[i]);
/* swap into new EFI memmap */
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 04:22:05 +07:00
early_memunmap(new_memmap, efi.memmap.desc_size * new_nr_map);
efi_memmap_install(new_memmap_phy, new_nr_map);
/* print new EFI memmap */
efi_print_memmap();
}
static int __init setup_fake_mem(char *p)
{
u64 start = 0, mem_size = 0, attribute = 0;
int i;
if (!p)
return -EINVAL;
while (*p != '\0') {
mem_size = memparse(p, &p);
if (*p == '@')
start = memparse(p+1, &p);
else
break;
if (*p == ':')
attribute = simple_strtoull(p+1, &p, 0);
else
break;
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;
nr_fake_mem++;
if (*p == ',')
p++;
}
sort(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);
return *p == '\0' ? 0 : -EINVAL;
}
early_param("efi_fake_mem", setup_fake_mem);