linux/arch/x86/platform/efi/efi_64.c

245 lines
5.9 KiB
C
Raw Normal View History

/*
* x86_64 specific EFI support functions
* Based on Extensible Firmware Interface Specification version 1.0
*
* Copyright (C) 2005-2008 Intel Co.
* Fenghua Yu <fenghua.yu@intel.com>
* Bibo Mao <bibo.mao@intel.com>
* Chandramouli Narayanan <mouli@linux.intel.com>
* Huang Ying <ying.huang@intel.com>
*
* Code to convert EFI to E820 map has been implemented in elilo bootloader
* based on a EFI patch by Edgar Hucek. Based on the E820 map, the page table
* is setup appropriately for EFI runtime code.
* - mouli 06/14/2007.
*
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/bootmem.h>
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/efi.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/slab.h>
#include <asm/setup.h>
#include <asm/page.h>
#include <asm/e820.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/proto.h>
#include <asm/efi.h>
#include <asm/cacheflush.h>
#include <asm/fixmap.h>
#include <asm/realmode.h>
efi, x86: Pass a proper identity mapping in efi_call_phys_prelog Update efi_call_phys_prelog to install an identity mapping of all available memory. This corrects a bug on very large systems with more then 512 GB in which bios would not be able to access addresses above not in the mapping. The result is a crash that looks much like this. BUG: unable to handle kernel paging request at 000000effd870020 IP: [<0000000078bce331>] 0x78bce330 PGD 0 Oops: 0000 [#1] SMP Modules linked in: CPU 0 Pid: 0, comm: swapper/0 Tainted: G W 3.8.0-rc1-next-20121224-medusa_ntz+ #2 Intel Corp. Stoutland Platform RIP: 0010:[<0000000078bce331>] [<0000000078bce331>] 0x78bce330 RSP: 0000:ffffffff81601d28 EFLAGS: 00010006 RAX: 0000000078b80e18 RBX: 0000000000000004 RCX: 0000000000000004 RDX: 0000000078bcf958 RSI: 0000000000002400 RDI: 8000000000000000 RBP: 0000000078bcf760 R08: 000000effd870000 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000000c3 R12: 0000000000000030 R13: 000000effd870000 R14: 0000000000000000 R15: ffff88effd870000 FS: 0000000000000000(0000) GS:ffff88effe400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000effd870020 CR3: 000000000160c000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper/0 (pid: 0, threadinfo ffffffff81600000, task ffffffff81614400) Stack: 0000000078b80d18 0000000000000004 0000000078bced7b ffff880078b81fff 0000000000000000 0000000000000082 0000000078bce3a8 0000000000002400 0000000060000202 0000000078b80da0 0000000078bce45d ffffffff8107cb5a Call Trace: [<ffffffff8107cb5a>] ? on_each_cpu+0x77/0x83 [<ffffffff8102f4eb>] ? change_page_attr_set_clr+0x32f/0x3ed [<ffffffff81035946>] ? efi_call4+0x46/0x80 [<ffffffff816c5abb>] ? efi_enter_virtual_mode+0x1f5/0x305 [<ffffffff816aeb24>] ? start_kernel+0x34a/0x3d2 [<ffffffff816ae5ed>] ? repair_env_string+0x60/0x60 [<ffffffff816ae2be>] ? x86_64_start_reservations+0xba/0xc1 [<ffffffff816ae120>] ? early_idt_handlers+0x120/0x120 [<ffffffff816ae419>] ? x86_64_start_kernel+0x154/0x163 Code: Bad RIP value. RIP [<0000000078bce331>] 0x78bce330 RSP <ffffffff81601d28> CR2: 000000effd870020 ---[ end trace ead828934fef5eab ]--- Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Nathan Zimmer <nzimmer@sgi.com> Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-01-08 23:02:43 +08:00
static pgd_t *save_pgd __initdata;
static unsigned long efi_flags __initdata;
/*
* We allocate runtime services regions bottom-up, starting from -4G, i.e.
* 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
*/
static u64 efi_va = -4 * (1UL << 30);
#define EFI_VA_END (-68 * (1UL << 30))
/*
* Scratch space used for switching the pagetable in the EFI stub
*/
struct efi_scratch {
u64 r15;
u64 prev_cr3;
pgd_t *efi_pgt;
bool use_pgd;
};
static void __init early_code_mapping_set_exec(int executable)
{
efi_memory_desc_t *md;
void *p;
if (!(__supported_pte_mask & _PAGE_NX))
return;
x86, efi: Retain boot service code until after switching to virtual mode UEFI stands for "Unified Extensible Firmware Interface", where "Firmware" is an ancient African word meaning "Why do something right when you can do it so wrong that children will weep and brave adults will cower before you", and "UEI" is Celtic for "We missed DOS so we burned it into your ROMs". The UEFI specification provides for runtime services (ie, another way for the operating system to be forced to depend on the firmware) and we rely on these for certain trivial tasks such as setting up the bootloader. But some hardware fails to work if we attempt to use these runtime services from physical mode, and so we have to switch into virtual mode. So far so dreadful. The specification makes it clear that the operating system is free to do whatever it wants with boot services code after ExitBootServices() has been called. SetVirtualAddressMap() can't be called until ExitBootServices() has been. So, obviously, a whole bunch of EFI implementations call into boot services code when we do that. Since we've been charmingly naive and trusted that the specification may be somehow relevant to the real world, we've already stuffed a picture of a penguin or something in that address space. And just to make things more entertaining, we've also marked it non-executable. This patch allocates the boot services regions during EFI init and makes sure that they're executable. Then, after SetVirtualAddressMap(), it discards them and everyone lives happily ever after. Except for the ones who have to work on EFI, who live sad lives haunted by the knowledge that someone's eventually going to write yet another firmware specification. [ hpa: adding this to urgent with a stable tag since it fixes currently-broken hardware. However, I do not know what the dependencies are and so I do not know which -stable versions this may be a candidate for. ] Signed-off-by: Matthew Garrett <mjg@redhat.com> Link: http://lkml.kernel.org/r/1306331593-28715-1-git-send-email-mjg@redhat.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: <stable@kernel.org>
2011-05-25 21:53:13 +08:00
/* Make EFI service code area executable */
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
md = p;
x86, efi: Retain boot service code until after switching to virtual mode UEFI stands for "Unified Extensible Firmware Interface", where "Firmware" is an ancient African word meaning "Why do something right when you can do it so wrong that children will weep and brave adults will cower before you", and "UEI" is Celtic for "We missed DOS so we burned it into your ROMs". The UEFI specification provides for runtime services (ie, another way for the operating system to be forced to depend on the firmware) and we rely on these for certain trivial tasks such as setting up the bootloader. But some hardware fails to work if we attempt to use these runtime services from physical mode, and so we have to switch into virtual mode. So far so dreadful. The specification makes it clear that the operating system is free to do whatever it wants with boot services code after ExitBootServices() has been called. SetVirtualAddressMap() can't be called until ExitBootServices() has been. So, obviously, a whole bunch of EFI implementations call into boot services code when we do that. Since we've been charmingly naive and trusted that the specification may be somehow relevant to the real world, we've already stuffed a picture of a penguin or something in that address space. And just to make things more entertaining, we've also marked it non-executable. This patch allocates the boot services regions during EFI init and makes sure that they're executable. Then, after SetVirtualAddressMap(), it discards them and everyone lives happily ever after. Except for the ones who have to work on EFI, who live sad lives haunted by the knowledge that someone's eventually going to write yet another firmware specification. [ hpa: adding this to urgent with a stable tag since it fixes currently-broken hardware. However, I do not know what the dependencies are and so I do not know which -stable versions this may be a candidate for. ] Signed-off-by: Matthew Garrett <mjg@redhat.com> Link: http://lkml.kernel.org/r/1306331593-28715-1-git-send-email-mjg@redhat.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: <stable@kernel.org>
2011-05-25 21:53:13 +08:00
if (md->type == EFI_RUNTIME_SERVICES_CODE ||
md->type == EFI_BOOT_SERVICES_CODE)
efi_set_executable(md, executable);
}
}
void __init efi_call_phys_prelog(void)
{
unsigned long vaddress;
efi, x86: Pass a proper identity mapping in efi_call_phys_prelog Update efi_call_phys_prelog to install an identity mapping of all available memory. This corrects a bug on very large systems with more then 512 GB in which bios would not be able to access addresses above not in the mapping. The result is a crash that looks much like this. BUG: unable to handle kernel paging request at 000000effd870020 IP: [<0000000078bce331>] 0x78bce330 PGD 0 Oops: 0000 [#1] SMP Modules linked in: CPU 0 Pid: 0, comm: swapper/0 Tainted: G W 3.8.0-rc1-next-20121224-medusa_ntz+ #2 Intel Corp. Stoutland Platform RIP: 0010:[<0000000078bce331>] [<0000000078bce331>] 0x78bce330 RSP: 0000:ffffffff81601d28 EFLAGS: 00010006 RAX: 0000000078b80e18 RBX: 0000000000000004 RCX: 0000000000000004 RDX: 0000000078bcf958 RSI: 0000000000002400 RDI: 8000000000000000 RBP: 0000000078bcf760 R08: 000000effd870000 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000000c3 R12: 0000000000000030 R13: 000000effd870000 R14: 0000000000000000 R15: ffff88effd870000 FS: 0000000000000000(0000) GS:ffff88effe400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000effd870020 CR3: 000000000160c000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper/0 (pid: 0, threadinfo ffffffff81600000, task ffffffff81614400) Stack: 0000000078b80d18 0000000000000004 0000000078bced7b ffff880078b81fff 0000000000000000 0000000000000082 0000000078bce3a8 0000000000002400 0000000060000202 0000000078b80da0 0000000078bce45d ffffffff8107cb5a Call Trace: [<ffffffff8107cb5a>] ? on_each_cpu+0x77/0x83 [<ffffffff8102f4eb>] ? change_page_attr_set_clr+0x32f/0x3ed [<ffffffff81035946>] ? efi_call4+0x46/0x80 [<ffffffff816c5abb>] ? efi_enter_virtual_mode+0x1f5/0x305 [<ffffffff816aeb24>] ? start_kernel+0x34a/0x3d2 [<ffffffff816ae5ed>] ? repair_env_string+0x60/0x60 [<ffffffff816ae2be>] ? x86_64_start_reservations+0xba/0xc1 [<ffffffff816ae120>] ? early_idt_handlers+0x120/0x120 [<ffffffff816ae419>] ? x86_64_start_kernel+0x154/0x163 Code: Bad RIP value. RIP [<0000000078bce331>] 0x78bce330 RSP <ffffffff81601d28> CR2: 000000effd870020 ---[ end trace ead828934fef5eab ]--- Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Nathan Zimmer <nzimmer@sgi.com> Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-01-08 23:02:43 +08:00
int pgd;
int n_pgds;
if (!efi_enabled(EFI_OLD_MEMMAP))
return;
early_code_mapping_set_exec(1);
local_irq_save(efi_flags);
efi, x86: Pass a proper identity mapping in efi_call_phys_prelog Update efi_call_phys_prelog to install an identity mapping of all available memory. This corrects a bug on very large systems with more then 512 GB in which bios would not be able to access addresses above not in the mapping. The result is a crash that looks much like this. BUG: unable to handle kernel paging request at 000000effd870020 IP: [<0000000078bce331>] 0x78bce330 PGD 0 Oops: 0000 [#1] SMP Modules linked in: CPU 0 Pid: 0, comm: swapper/0 Tainted: G W 3.8.0-rc1-next-20121224-medusa_ntz+ #2 Intel Corp. Stoutland Platform RIP: 0010:[<0000000078bce331>] [<0000000078bce331>] 0x78bce330 RSP: 0000:ffffffff81601d28 EFLAGS: 00010006 RAX: 0000000078b80e18 RBX: 0000000000000004 RCX: 0000000000000004 RDX: 0000000078bcf958 RSI: 0000000000002400 RDI: 8000000000000000 RBP: 0000000078bcf760 R08: 000000effd870000 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000000c3 R12: 0000000000000030 R13: 000000effd870000 R14: 0000000000000000 R15: ffff88effd870000 FS: 0000000000000000(0000) GS:ffff88effe400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000effd870020 CR3: 000000000160c000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper/0 (pid: 0, threadinfo ffffffff81600000, task ffffffff81614400) Stack: 0000000078b80d18 0000000000000004 0000000078bced7b ffff880078b81fff 0000000000000000 0000000000000082 0000000078bce3a8 0000000000002400 0000000060000202 0000000078b80da0 0000000078bce45d ffffffff8107cb5a Call Trace: [<ffffffff8107cb5a>] ? on_each_cpu+0x77/0x83 [<ffffffff8102f4eb>] ? change_page_attr_set_clr+0x32f/0x3ed [<ffffffff81035946>] ? efi_call4+0x46/0x80 [<ffffffff816c5abb>] ? efi_enter_virtual_mode+0x1f5/0x305 [<ffffffff816aeb24>] ? start_kernel+0x34a/0x3d2 [<ffffffff816ae5ed>] ? repair_env_string+0x60/0x60 [<ffffffff816ae2be>] ? x86_64_start_reservations+0xba/0xc1 [<ffffffff816ae120>] ? early_idt_handlers+0x120/0x120 [<ffffffff816ae419>] ? x86_64_start_kernel+0x154/0x163 Code: Bad RIP value. RIP [<0000000078bce331>] 0x78bce330 RSP <ffffffff81601d28> CR2: 000000effd870020 ---[ end trace ead828934fef5eab ]--- Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Nathan Zimmer <nzimmer@sgi.com> Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-01-08 23:02:43 +08:00
n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
for (pgd = 0; pgd < n_pgds; pgd++) {
save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
}
__flush_tlb_all();
}
void __init efi_call_phys_epilog(void)
{
/*
* After the lock is released, the original page table is restored.
*/
efi, x86: Pass a proper identity mapping in efi_call_phys_prelog Update efi_call_phys_prelog to install an identity mapping of all available memory. This corrects a bug on very large systems with more then 512 GB in which bios would not be able to access addresses above not in the mapping. The result is a crash that looks much like this. BUG: unable to handle kernel paging request at 000000effd870020 IP: [<0000000078bce331>] 0x78bce330 PGD 0 Oops: 0000 [#1] SMP Modules linked in: CPU 0 Pid: 0, comm: swapper/0 Tainted: G W 3.8.0-rc1-next-20121224-medusa_ntz+ #2 Intel Corp. Stoutland Platform RIP: 0010:[<0000000078bce331>] [<0000000078bce331>] 0x78bce330 RSP: 0000:ffffffff81601d28 EFLAGS: 00010006 RAX: 0000000078b80e18 RBX: 0000000000000004 RCX: 0000000000000004 RDX: 0000000078bcf958 RSI: 0000000000002400 RDI: 8000000000000000 RBP: 0000000078bcf760 R08: 000000effd870000 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000000c3 R12: 0000000000000030 R13: 000000effd870000 R14: 0000000000000000 R15: ffff88effd870000 FS: 0000000000000000(0000) GS:ffff88effe400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000effd870020 CR3: 000000000160c000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper/0 (pid: 0, threadinfo ffffffff81600000, task ffffffff81614400) Stack: 0000000078b80d18 0000000000000004 0000000078bced7b ffff880078b81fff 0000000000000000 0000000000000082 0000000078bce3a8 0000000000002400 0000000060000202 0000000078b80da0 0000000078bce45d ffffffff8107cb5a Call Trace: [<ffffffff8107cb5a>] ? on_each_cpu+0x77/0x83 [<ffffffff8102f4eb>] ? change_page_attr_set_clr+0x32f/0x3ed [<ffffffff81035946>] ? efi_call4+0x46/0x80 [<ffffffff816c5abb>] ? efi_enter_virtual_mode+0x1f5/0x305 [<ffffffff816aeb24>] ? start_kernel+0x34a/0x3d2 [<ffffffff816ae5ed>] ? repair_env_string+0x60/0x60 [<ffffffff816ae2be>] ? x86_64_start_reservations+0xba/0xc1 [<ffffffff816ae120>] ? early_idt_handlers+0x120/0x120 [<ffffffff816ae419>] ? x86_64_start_kernel+0x154/0x163 Code: Bad RIP value. RIP [<0000000078bce331>] 0x78bce330 RSP <ffffffff81601d28> CR2: 000000effd870020 ---[ end trace ead828934fef5eab ]--- Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Nathan Zimmer <nzimmer@sgi.com> Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-01-08 23:02:43 +08:00
int pgd;
int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
if (!efi_enabled(EFI_OLD_MEMMAP))
return;
efi, x86: Pass a proper identity mapping in efi_call_phys_prelog Update efi_call_phys_prelog to install an identity mapping of all available memory. This corrects a bug on very large systems with more then 512 GB in which bios would not be able to access addresses above not in the mapping. The result is a crash that looks much like this. BUG: unable to handle kernel paging request at 000000effd870020 IP: [<0000000078bce331>] 0x78bce330 PGD 0 Oops: 0000 [#1] SMP Modules linked in: CPU 0 Pid: 0, comm: swapper/0 Tainted: G W 3.8.0-rc1-next-20121224-medusa_ntz+ #2 Intel Corp. Stoutland Platform RIP: 0010:[<0000000078bce331>] [<0000000078bce331>] 0x78bce330 RSP: 0000:ffffffff81601d28 EFLAGS: 00010006 RAX: 0000000078b80e18 RBX: 0000000000000004 RCX: 0000000000000004 RDX: 0000000078bcf958 RSI: 0000000000002400 RDI: 8000000000000000 RBP: 0000000078bcf760 R08: 000000effd870000 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000000c3 R12: 0000000000000030 R13: 000000effd870000 R14: 0000000000000000 R15: ffff88effd870000 FS: 0000000000000000(0000) GS:ffff88effe400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000effd870020 CR3: 000000000160c000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper/0 (pid: 0, threadinfo ffffffff81600000, task ffffffff81614400) Stack: 0000000078b80d18 0000000000000004 0000000078bced7b ffff880078b81fff 0000000000000000 0000000000000082 0000000078bce3a8 0000000000002400 0000000060000202 0000000078b80da0 0000000078bce45d ffffffff8107cb5a Call Trace: [<ffffffff8107cb5a>] ? on_each_cpu+0x77/0x83 [<ffffffff8102f4eb>] ? change_page_attr_set_clr+0x32f/0x3ed [<ffffffff81035946>] ? efi_call4+0x46/0x80 [<ffffffff816c5abb>] ? efi_enter_virtual_mode+0x1f5/0x305 [<ffffffff816aeb24>] ? start_kernel+0x34a/0x3d2 [<ffffffff816ae5ed>] ? repair_env_string+0x60/0x60 [<ffffffff816ae2be>] ? x86_64_start_reservations+0xba/0xc1 [<ffffffff816ae120>] ? early_idt_handlers+0x120/0x120 [<ffffffff816ae419>] ? x86_64_start_kernel+0x154/0x163 Code: Bad RIP value. RIP [<0000000078bce331>] 0x78bce330 RSP <ffffffff81601d28> CR2: 000000effd870020 ---[ end trace ead828934fef5eab ]--- Cc: stable@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Nathan Zimmer <nzimmer@sgi.com> Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com>
2013-01-08 23:02:43 +08:00
for (pgd = 0; pgd < n_pgds; pgd++)
set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
kfree(save_pgd);
__flush_tlb_all();
local_irq_restore(efi_flags);
early_code_mapping_set_exec(0);
}
/*
* Add low kernel mappings for passing arguments to EFI functions.
*/
void efi_sync_low_kernel_mappings(void)
{
unsigned num_pgds;
pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
if (efi_enabled(EFI_OLD_MEMMAP))
return;
num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
memcpy(pgd + pgd_index(PAGE_OFFSET),
init_mm.pgd + pgd_index(PAGE_OFFSET),
sizeof(pgd_t) * num_pgds);
}
void efi_setup_page_tables(void)
{
efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
if (!efi_enabled(EFI_OLD_MEMMAP))
efi_scratch.use_pgd = true;
}
static void __init __map_region(efi_memory_desc_t *md, u64 va)
{
pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
unsigned long pf = 0;
if (!(md->attribute & EFI_MEMORY_WB))
pf |= _PAGE_PCD;
if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
md->phys_addr, va);
}
void __init efi_map_region(efi_memory_desc_t *md)
{
unsigned long size = md->num_pages << PAGE_SHIFT;
u64 pa = md->phys_addr;
if (efi_enabled(EFI_OLD_MEMMAP))
return old_map_region(md);
/*
* Make sure the 1:1 mappings are present as a catch-all for b0rked
* firmware which doesn't update all internal pointers after switching
* to virtual mode and would otherwise crap on us.
*/
__map_region(md, md->phys_addr);
efi_va -= size;
/* Is PA 2M-aligned? */
if (!(pa & (PMD_SIZE - 1))) {
efi_va &= PMD_MASK;
} else {
u64 pa_offset = pa & (PMD_SIZE - 1);
u64 prev_va = efi_va;
/* get us the same offset within this 2M page */
efi_va = (efi_va & PMD_MASK) + pa_offset;
if (efi_va > prev_va)
efi_va -= PMD_SIZE;
}
if (efi_va < EFI_VA_END) {
pr_warn(FW_WARN "VA address range overflow!\n");
return;
}
/* Do the VA map */
__map_region(md, efi_va);
md->virt_addr = efi_va;
}
/*
* kexec kernel will use efi_map_region_fixed to map efi runtime memory ranges.
* md->virt_addr is the original virtual address which had been mapped in kexec
* 1st kernel.
*/
void __init efi_map_region_fixed(efi_memory_desc_t *md)
{
__map_region(md, md->virt_addr);
}
void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
x86/efi: Fix oops caused by incorrect set_memory_uc() usage Calling __pa() with an ioremap'd address is invalid. If we encounter an efi_memory_desc_t without EFI_MEMORY_WB set in ->attribute we currently call set_memory_uc(), which in turn calls __pa() on a potentially ioremap'd address. On CONFIG_X86_32 this results in the following oops: BUG: unable to handle kernel paging request at f7f22280 IP: [<c10257b9>] reserve_ram_pages_type+0x89/0x210 *pdpt = 0000000001978001 *pde = 0000000001ffb067 *pte = 0000000000000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: Pid: 0, comm: swapper Not tainted 3.0.0-acpi-efi-0805 #3 EIP: 0060:[<c10257b9>] EFLAGS: 00010202 CPU: 0 EIP is at reserve_ram_pages_type+0x89/0x210 EAX: 0070e280 EBX: 38714000 ECX: f7814000 EDX: 00000000 ESI: 00000000 EDI: 38715000 EBP: c189fef0 ESP: c189fea8 DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 Process swapper (pid: 0, ti=c189e000 task=c18bbe60 task.ti=c189e000) Stack: 80000200 ff108000 00000000 c189ff00 00038714 00000000 00000000 c189fed0 c104f8ca 00038714 00000000 00038715 00000000 00000000 00038715 00000000 00000010 38715000 c189ff48 c1025aff 38715000 00000000 00000010 00000000 Call Trace: [<c104f8ca>] ? page_is_ram+0x1a/0x40 [<c1025aff>] reserve_memtype+0xdf/0x2f0 [<c1024dc9>] set_memory_uc+0x49/0xa0 [<c19334d0>] efi_enter_virtual_mode+0x1c2/0x3aa [<c19216d4>] start_kernel+0x291/0x2f2 [<c19211c7>] ? loglevel+0x1b/0x1b [<c19210bf>] i386_start_kernel+0xbf/0xc8 The only time we can call set_memory_uc() for a memory region is when it is part of the direct kernel mapping. For the case where we ioremap a memory region we must leave it alone. This patch reimplements the fix from e8c7106280a3 ("x86, efi: Calling __pa() with an ioremap()ed address is invalid") which was reverted in e1ad783b12ec because it caused a regression on some MacBooks (they hung at boot). The regression was caused because the commit only marked EFI_RUNTIME_SERVICES_DATA as E820_RESERVED_EFI, when it should have marked all regions that have the EFI_MEMORY_RUNTIME attribute. Despite first impressions, it's not possible to use ioremap_cache() to map all cached memory regions on CONFIG_X86_64 because of the way that the memory map might be configured as detailed in the following bug report, https://bugzilla.redhat.com/show_bug.cgi?id=748516 e.g. some of the EFI memory regions *need* to be mapped as part of the direct kernel mapping. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Cc: Matthew Garrett <mjg@redhat.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Huang Ying <huang.ying.caritas@gmail.com> Cc: Keith Packard <keithp@keithp.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/1350649546-23541-1-git-send-email-matt@console-pimps.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-19 20:25:46 +08:00
u32 type, u64 attribute)
{
unsigned long last_map_pfn;
if (type == EFI_MEMORY_MAPPED_IO)
return ioremap(phys_addr, size);
last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
unsigned long top = last_map_pfn << PAGE_SHIFT;
x86/efi: Fix oops caused by incorrect set_memory_uc() usage Calling __pa() with an ioremap'd address is invalid. If we encounter an efi_memory_desc_t without EFI_MEMORY_WB set in ->attribute we currently call set_memory_uc(), which in turn calls __pa() on a potentially ioremap'd address. On CONFIG_X86_32 this results in the following oops: BUG: unable to handle kernel paging request at f7f22280 IP: [<c10257b9>] reserve_ram_pages_type+0x89/0x210 *pdpt = 0000000001978001 *pde = 0000000001ffb067 *pte = 0000000000000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: Pid: 0, comm: swapper Not tainted 3.0.0-acpi-efi-0805 #3 EIP: 0060:[<c10257b9>] EFLAGS: 00010202 CPU: 0 EIP is at reserve_ram_pages_type+0x89/0x210 EAX: 0070e280 EBX: 38714000 ECX: f7814000 EDX: 00000000 ESI: 00000000 EDI: 38715000 EBP: c189fef0 ESP: c189fea8 DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 Process swapper (pid: 0, ti=c189e000 task=c18bbe60 task.ti=c189e000) Stack: 80000200 ff108000 00000000 c189ff00 00038714 00000000 00000000 c189fed0 c104f8ca 00038714 00000000 00038715 00000000 00000000 00038715 00000000 00000010 38715000 c189ff48 c1025aff 38715000 00000000 00000010 00000000 Call Trace: [<c104f8ca>] ? page_is_ram+0x1a/0x40 [<c1025aff>] reserve_memtype+0xdf/0x2f0 [<c1024dc9>] set_memory_uc+0x49/0xa0 [<c19334d0>] efi_enter_virtual_mode+0x1c2/0x3aa [<c19216d4>] start_kernel+0x291/0x2f2 [<c19211c7>] ? loglevel+0x1b/0x1b [<c19210bf>] i386_start_kernel+0xbf/0xc8 The only time we can call set_memory_uc() for a memory region is when it is part of the direct kernel mapping. For the case where we ioremap a memory region we must leave it alone. This patch reimplements the fix from e8c7106280a3 ("x86, efi: Calling __pa() with an ioremap()ed address is invalid") which was reverted in e1ad783b12ec because it caused a regression on some MacBooks (they hung at boot). The regression was caused because the commit only marked EFI_RUNTIME_SERVICES_DATA as E820_RESERVED_EFI, when it should have marked all regions that have the EFI_MEMORY_RUNTIME attribute. Despite first impressions, it's not possible to use ioremap_cache() to map all cached memory regions on CONFIG_X86_64 because of the way that the memory map might be configured as detailed in the following bug report, https://bugzilla.redhat.com/show_bug.cgi?id=748516 e.g. some of the EFI memory regions *need* to be mapped as part of the direct kernel mapping. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Cc: Matthew Garrett <mjg@redhat.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Huang Ying <huang.ying.caritas@gmail.com> Cc: Keith Packard <keithp@keithp.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/1350649546-23541-1-git-send-email-matt@console-pimps.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-19 20:25:46 +08:00
efi_ioremap(top, size - (top - phys_addr), type, attribute);
}
x86/efi: Fix oops caused by incorrect set_memory_uc() usage Calling __pa() with an ioremap'd address is invalid. If we encounter an efi_memory_desc_t without EFI_MEMORY_WB set in ->attribute we currently call set_memory_uc(), which in turn calls __pa() on a potentially ioremap'd address. On CONFIG_X86_32 this results in the following oops: BUG: unable to handle kernel paging request at f7f22280 IP: [<c10257b9>] reserve_ram_pages_type+0x89/0x210 *pdpt = 0000000001978001 *pde = 0000000001ffb067 *pte = 0000000000000000 Oops: 0000 [#1] PREEMPT SMP Modules linked in: Pid: 0, comm: swapper Not tainted 3.0.0-acpi-efi-0805 #3 EIP: 0060:[<c10257b9>] EFLAGS: 00010202 CPU: 0 EIP is at reserve_ram_pages_type+0x89/0x210 EAX: 0070e280 EBX: 38714000 ECX: f7814000 EDX: 00000000 ESI: 00000000 EDI: 38715000 EBP: c189fef0 ESP: c189fea8 DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 Process swapper (pid: 0, ti=c189e000 task=c18bbe60 task.ti=c189e000) Stack: 80000200 ff108000 00000000 c189ff00 00038714 00000000 00000000 c189fed0 c104f8ca 00038714 00000000 00038715 00000000 00000000 00038715 00000000 00000010 38715000 c189ff48 c1025aff 38715000 00000000 00000010 00000000 Call Trace: [<c104f8ca>] ? page_is_ram+0x1a/0x40 [<c1025aff>] reserve_memtype+0xdf/0x2f0 [<c1024dc9>] set_memory_uc+0x49/0xa0 [<c19334d0>] efi_enter_virtual_mode+0x1c2/0x3aa [<c19216d4>] start_kernel+0x291/0x2f2 [<c19211c7>] ? loglevel+0x1b/0x1b [<c19210bf>] i386_start_kernel+0xbf/0xc8 The only time we can call set_memory_uc() for a memory region is when it is part of the direct kernel mapping. For the case where we ioremap a memory region we must leave it alone. This patch reimplements the fix from e8c7106280a3 ("x86, efi: Calling __pa() with an ioremap()ed address is invalid") which was reverted in e1ad783b12ec because it caused a regression on some MacBooks (they hung at boot). The regression was caused because the commit only marked EFI_RUNTIME_SERVICES_DATA as E820_RESERVED_EFI, when it should have marked all regions that have the EFI_MEMORY_RUNTIME attribute. Despite first impressions, it's not possible to use ioremap_cache() to map all cached memory regions on CONFIG_X86_64 because of the way that the memory map might be configured as detailed in the following bug report, https://bugzilla.redhat.com/show_bug.cgi?id=748516 e.g. some of the EFI memory regions *need* to be mapped as part of the direct kernel mapping. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Cc: Matthew Garrett <mjg@redhat.com> Cc: Zhang Rui <rui.zhang@intel.com> Cc: Huang Ying <huang.ying.caritas@gmail.com> Cc: Keith Packard <keithp@keithp.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/1350649546-23541-1-git-send-email-matt@console-pimps.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-19 20:25:46 +08:00
if (!(attribute & EFI_MEMORY_WB))
efi_memory_uc((u64)(unsigned long)__va(phys_addr), size);
return (void __iomem *)__va(phys_addr);
}
void __init parse_efi_setup(u64 phys_addr, u32 data_len)
{
efi_setup = phys_addr + sizeof(struct setup_data);
}
void __init efi_runtime_mkexec(void)
{
if (!efi_enabled(EFI_OLD_MEMMAP))
return;
if (__supported_pte_mask & _PAGE_NX)
runtime_code_page_mkexec();
}