OpenCloudOS-Kernel/arch/x86/include/asm/efi.h

239 lines
6.4 KiB
C
Raw Normal View History

#ifndef _ASM_X86_EFI_H
#define _ASM_X86_EFI_H
#include <asm/fpu/api.h>
#include <asm/pgtable.h>
x86/efi: Hoist page table switching code into efi_call_virt() This change is a prerequisite for pending patches that switch to a dedicated EFI page table, instead of using 'trampoline_pgd' which shares PGD entries with 'swapper_pg_dir'. The pending patches make it impossible to dereference the runtime service function pointer without first switching %cr3. It's true that we now have duplicated switching code in efi_call_virt() and efi_call_phys_{prolog,epilog}() but we are sacrificing code duplication for a little more clarity and the ease of writing the page table switching code in C instead of asm. Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Acked-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1448658575-17029-5-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-11-28 05:09:33 +08:00
#include <asm/tlb.h>
/*
* We map the EFI regions needed for runtime services non-contiguously,
* with preserved alignment on virtual addresses starting from -4G down
* for a total max space of 64G. This way, we provide for stable runtime
* services addresses across kernels so that a kexec'd kernel can still
* use them.
*
* This is the main reason why we're doing stable VA mappings for RT
* services.
*
* This flag is used in conjuction with a chicken bit called
* "efi=old_map" which can be used as a fallback to the old runtime
* services mapping method in case there's some b0rkage with a
* particular EFI implementation (haha, it is hard to hold up the
* sarcasm here...).
*/
#define EFI_OLD_MEMMAP EFI_ARCH_1
2014-01-10 23:54:31 +08:00
#define EFI32_LOADER_SIGNATURE "EL32"
#define EFI64_LOADER_SIGNATURE "EL64"
#define MAX_CMDLINE_ADDRESS UINT_MAX
#ifdef CONFIG_X86_32
extern unsigned long asmlinkage efi_call_phys(void *, ...);
/*
* Wrap all the virtual calls in a way that forces the parameters on the stack.
*/
/* Use this macro if your virtual returns a non-void value */
#define efi_call_virt(f, args...) \
({ \
efi_status_t __s; \
kernel_fpu_begin(); \
__s = ((efi_##f##_t __attribute__((regparm(0)))*) \
efi.systab->runtime->f)(args); \
kernel_fpu_end(); \
__s; \
})
/* Use this macro if your virtual call does not return any value */
#define __efi_call_virt(f, args...) \
({ \
kernel_fpu_begin(); \
((efi_##f##_t __attribute__((regparm(0)))*) \
efi.systab->runtime->f)(args); \
kernel_fpu_end(); \
})
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
#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size)
#else /* !CONFIG_X86_32 */
#define EFI_LOADER_SIGNATURE "EL64"
extern u64 asmlinkage efi_call(void *fp, ...);
#define efi_call_phys(f, args...) efi_call((f), args)
x86/efi: Hoist page table switching code into efi_call_virt() This change is a prerequisite for pending patches that switch to a dedicated EFI page table, instead of using 'trampoline_pgd' which shares PGD entries with 'swapper_pg_dir'. The pending patches make it impossible to dereference the runtime service function pointer without first switching %cr3. It's true that we now have duplicated switching code in efi_call_virt() and efi_call_phys_{prolog,epilog}() but we are sacrificing code duplication for a little more clarity and the ease of writing the page table switching code in C instead of asm. Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Acked-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1448658575-17029-5-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-11-28 05:09:33 +08:00
/*
* 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;
u64 phys_stack;
} __packed;
#define efi_call_virt(f, ...) \
({ \
efi_status_t __s; \
\
efi_sync_low_kernel_mappings(); \
preempt_disable(); \
__kernel_fpu_begin(); \
x86/efi: Hoist page table switching code into efi_call_virt() This change is a prerequisite for pending patches that switch to a dedicated EFI page table, instead of using 'trampoline_pgd' which shares PGD entries with 'swapper_pg_dir'. The pending patches make it impossible to dereference the runtime service function pointer without first switching %cr3. It's true that we now have duplicated switching code in efi_call_virt() and efi_call_phys_{prolog,epilog}() but we are sacrificing code duplication for a little more clarity and the ease of writing the page table switching code in C instead of asm. Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Acked-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1448658575-17029-5-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-11-28 05:09:33 +08:00
\
if (efi_scratch.use_pgd) { \
efi_scratch.prev_cr3 = read_cr3(); \
write_cr3((unsigned long)efi_scratch.efi_pgt); \
__flush_tlb_all(); \
} \
\
__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \
x86/efi: Hoist page table switching code into efi_call_virt() This change is a prerequisite for pending patches that switch to a dedicated EFI page table, instead of using 'trampoline_pgd' which shares PGD entries with 'swapper_pg_dir'. The pending patches make it impossible to dereference the runtime service function pointer without first switching %cr3. It's true that we now have duplicated switching code in efi_call_virt() and efi_call_phys_{prolog,epilog}() but we are sacrificing code duplication for a little more clarity and the ease of writing the page table switching code in C instead of asm. Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Acked-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1448658575-17029-5-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-11-28 05:09:33 +08:00
\
if (efi_scratch.use_pgd) { \
write_cr3(efi_scratch.prev_cr3); \
__flush_tlb_all(); \
} \
\
__kernel_fpu_end(); \
preempt_enable(); \
__s; \
})
/*
* All X86_64 virt calls return non-void values. Thus, use non-void call for
* virt calls that would be void on X86_32.
*/
#define __efi_call_virt(f, args...) efi_call_virt(f, args)
extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
u32 type, u64 attribute);
#ifdef CONFIG_KASAN
/*
* CONFIG_KASAN may redefine memset to __memset. __memset function is present
* only in kernel binary. Since the EFI stub linked into a separate binary it
* doesn't have __memset(). So we should use standard memset from
* arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove.
*/
#undef memcpy
#undef memset
#undef memmove
#endif
#endif /* CONFIG_X86_32 */
extern struct efi_scratch efi_scratch;
extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable);
extern int __init efi_memblock_x86_reserve_range(void);
extern pgd_t * __init efi_call_phys_prolog(void);
extern void __init efi_call_phys_epilog(pgd_t *save_pgd);
extern void __init efi_print_memmap(void);
extern void __init efi_unmap_memmap(void);
extern void __init efi_memory_uc(u64 addr, unsigned long size);
extern void __init efi_map_region(efi_memory_desc_t *md);
extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
extern void efi_sync_low_kernel_mappings(void);
x86/efi: Build our own page table structures With commit e1a58320a38d ("x86/mm: Warn on W^X mappings") all users booting on 64-bit UEFI machines see the following warning, ------------[ cut here ]------------ WARNING: CPU: 7 PID: 1 at arch/x86/mm/dump_pagetables.c:225 note_page+0x5dc/0x780() x86/mm: Found insecure W+X mapping at address ffff88000005f000/0xffff88000005f000 ... x86/mm: Checked W+X mappings: FAILED, 165660 W+X pages found. ... This is caused by mapping EFI regions with RWX permissions. There isn't much we can do to restrict the permissions for these regions due to the way the firmware toolchains mix code and data, but we can at least isolate these mappings so that they do not appear in the regular kernel page tables. In commit d2f7cbe7b26a ("x86/efi: Runtime services virtual mapping") we started using 'trampoline_pgd' to map the EFI regions because there was an existing identity mapping there which we use during the SetVirtualAddressMap() call and for broken firmware that accesses those addresses. But 'trampoline_pgd' shares some PGD entries with 'swapper_pg_dir' and does not provide the isolation we require. Notably the virtual address for __START_KERNEL_map and MODULES_START are mapped by the same PGD entry so we need to be more careful when copying changes over in efi_sync_low_kernel_mappings(). This patch doesn't go the full mile, we still want to share some PGD entries with 'swapper_pg_dir'. Having completely separate page tables brings its own issues such as synchronising new mappings after memory hotplug and module loading. Sharing also keeps memory usage down. Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Acked-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1448658575-17029-6-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-11-28 05:09:34 +08:00
extern int __init efi_alloc_page_tables(void);
extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
extern void __init old_map_region(efi_memory_desc_t *md);
extern void __init runtime_code_page_mkexec(void);
x86/efi: Map EFI_MEMORY_{XP,RO} memory region bits to EFI page tables Now that we have EFI memory region bits that indicate which regions do not need execute permission or read/write permission in the page tables, let's use them. We also check for EFI_NX_PE_DATA and only enforce the restrictive mappings if it's present (to allow us to ignore buggy firmware that sets bits it didn't mean to and to preserve backwards compatibility). Instead of assuming that firmware would set appropriate attributes in memory descriptor like EFI_MEMORY_RO for code and EFI_MEMORY_XP for data, we can expect some firmware out there which might only set *type* in memory descriptor to be EFI_RUNTIME_SERVICES_CODE or EFI_RUNTIME_SERVICES_DATA leaving away attribute. This will lead to improper mappings of EFI runtime regions. In order to avoid it, we check attribute and type of memory descriptor to update mappings and moreover Windows works this way. Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com> Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> 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: Kees Cook <keescook@chromium.org> Cc: Lee, Chun-Yi <jlee@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Shankar <ravi.v.shankar@intel.com> Cc: Ricardo Neri <ricardo.neri@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1455712566-16727-13-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-17 20:36:05 +08:00
extern void __init efi_runtime_update_mappings(void);
extern void __init efi_dump_pagetable(void);
extern void __init efi_apply_memmap_quirks(void);
extern int __init efi_reuse_config(u64 tables, int nr_tables);
extern void efi_delete_dummy_variable(void);
struct efi_setup_data {
u64 fw_vendor;
u64 runtime;
u64 tables;
u64 smbios;
u64 reserved[8];
};
extern u64 efi_setup;
#ifdef CONFIG_EFI
static inline bool efi_is_native(void)
{
return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
}
static inline bool efi_runtime_supported(void)
{
if (efi_is_native())
return true;
if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP))
return true;
return false;
}
extern struct console early_efi_console;
extern void parse_efi_setup(u64 phys_addr, u32 data_len);
#ifdef CONFIG_EFI_MIXED
extern void efi_thunk_runtime_setup(void);
extern efi_status_t efi_thunk_set_virtual_address_map(
void *phys_set_virtual_address_map,
unsigned long memory_map_size,
unsigned long descriptor_size,
u32 descriptor_version,
efi_memory_desc_t *virtual_map);
#else
static inline void efi_thunk_runtime_setup(void) {}
static inline efi_status_t efi_thunk_set_virtual_address_map(
void *phys_set_virtual_address_map,
unsigned long memory_map_size,
unsigned long descriptor_size,
u32 descriptor_version,
efi_memory_desc_t *virtual_map)
{
return EFI_SUCCESS;
}
#endif /* CONFIG_EFI_MIXED */
/* arch specific definitions used by the stub code */
struct efi_config {
u64 image_handle;
u64 table;
u64 allocate_pool;
u64 allocate_pages;
u64 get_memory_map;
u64 free_pool;
u64 free_pages;
u64 locate_handle;
u64 handle_protocol;
u64 exit_boot_services;
u64 text_output;
efi_status_t (*call)(unsigned long, ...);
bool is64;
} __packed;
__pure const struct efi_config *__efi_early(void);
#define efi_call_early(f, ...) \
__efi_early()->call(__efi_early()->f, __VA_ARGS__);
extern bool efi_reboot_required(void);
#else
static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
static inline bool efi_reboot_required(void)
{
return false;
}
#endif /* CONFIG_EFI */
#endif /* _ASM_X86_EFI_H */