diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-21 01:58:18 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-21 01:58:18 (GMT) |
commit | 24b5e20f11a75866bbffc46c30a22fa50612a769 (patch) | |
tree | 2dab5fc6714a5ad1e31bdea1e954fbd69704ce72 /arch/x86 | |
parent | 26660a4046b171a752e72a1dd32153230234fe3a (diff) | |
parent | d367cef0a7f0c6ee86e997c0cb455b21b3c6b9ba (diff) | |
download | linux-24b5e20f11a75866bbffc46c30a22fa50612a769.tar.xz |
Merge branch 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull EFI updates from Ingo Molnar:
"The main changes are:
- Use separate EFI page tables when executing EFI firmware code.
This isolates the EFI context from the rest of the kernel, which
has security and general robustness advantages. (Matt Fleming)
- Run regular UEFI firmware with interrupts enabled. This is already
the status quo under other OSs. (Ard Biesheuvel)
- Various x86 EFI enhancements, such as the use of non-executable
attributes for EFI memory mappings. (Sai Praneeth Prakhya)
- Various arm64 UEFI enhancements. (Ard Biesheuvel)
- ... various fixes and cleanups.
The separate EFI page tables feature got delayed twice already,
because it's an intrusive change and we didn't feel confident about
it - third time's the charm we hope!"
* 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
x86/mm/pat: Fix boot crash when 1GB pages are not supported by the CPU
x86/efi: Only map kernel text for EFI mixed mode
x86/efi: Map EFI_MEMORY_{XP,RO} memory region bits to EFI page tables
x86/mm/pat: Don't implicitly allow _PAGE_RW in kernel_map_pages_in_pgd()
efi/arm*: Perform hardware compatibility check
efi/arm64: Check for h/w support before booting a >4 KB granular kernel
efi/arm: Check for LPAE support before booting a LPAE kernel
efi/arm-init: Use read-only early mappings
efi/efistub: Prevent __init annotations from being used
arm64/vmlinux.lds.S: Handle .init.rodata.xxx and .init.bss sections
efi/arm64: Drop __init annotation from handle_kernel_image()
x86/mm/pat: Use _PAGE_GLOBAL bit for EFI page table mappings
efi/runtime-wrappers: Run UEFI Runtime Services with interrupts enabled
efi: Reformat GUID tables to follow the format in UEFI spec
efi: Add Persistent Memory type name
efi: Add NV memory attribute
x86/efi: Show actual ending addresses in efi_print_memmap
x86/efi/bgrt: Don't ignore the BGRT if the 'valid' bit is 0
efivars: Use to_efivar_entry
efi: Runtime-wrapper: Get rid of the rtc_lock spinlock
...
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/include/asm/efi.h | 28 | ||||
-rw-r--r-- | arch/x86/kernel/vmlinux.lds.S | 1 | ||||
-rw-r--r-- | arch/x86/mm/pageattr.c | 34 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi-bgrt.c | 52 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi.c | 67 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi_32.c | 7 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi_64.c | 206 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi_stub_64.S | 43 | ||||
-rw-r--r-- | arch/x86/platform/efi/quirks.c | 37 |
9 files changed, 319 insertions, 156 deletions
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 08b1f2f..53748c4 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -3,6 +3,7 @@ #include <asm/fpu/api.h> #include <asm/pgtable.h> +#include <asm/tlb.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -66,6 +67,17 @@ extern u64 asmlinkage efi_call(void *fp, ...); #define efi_call_phys(f, args...) efi_call((f), args) +/* + * 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; \ @@ -73,7 +85,20 @@ extern u64 asmlinkage efi_call(void *fp, ...); efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ + \ + 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__); \ + \ + if (efi_scratch.use_pgd) { \ + write_cr3(efi_scratch.prev_cr3); \ + __flush_tlb_all(); \ + } \ + \ __kernel_fpu_end(); \ preempt_enable(); \ __s; \ @@ -113,11 +138,12 @@ 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); +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); -extern void __init efi_runtime_mkexec(void); +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); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 73de260..d239639 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -333,6 +333,7 @@ SECTIONS __brk_limit = .; } + . = ALIGN(PAGE_SIZE); _end = .; STABS_DEBUG diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 4d0b262..01be9ec 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -909,16 +909,25 @@ static void populate_pte(struct cpa_data *cpa, pte = pte_offset_kernel(pmd, start); - while (num_pages-- && start < end) { + /* + * Set the GLOBAL flags only if the PRESENT flag is + * set otherwise pte_present will return true even on + * a non present pte. The canon_pgprot will clear + * _PAGE_GLOBAL for the ancient hardware that doesn't + * support it. + */ + if (pgprot_val(pgprot) & _PAGE_PRESENT) + pgprot_val(pgprot) |= _PAGE_GLOBAL; + else + pgprot_val(pgprot) &= ~_PAGE_GLOBAL; - /* deal with the NX bit */ - if (!(pgprot_val(pgprot) & _PAGE_NX)) - cpa->pfn &= ~_PAGE_NX; + pgprot = canon_pgprot(pgprot); - set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot)); + while (num_pages-- && start < end) { + set_pte(pte, pfn_pte(cpa->pfn, pgprot)); start += PAGE_SIZE; - cpa->pfn += PAGE_SIZE; + cpa->pfn++; pte++; } } @@ -974,11 +983,11 @@ static int populate_pmd(struct cpa_data *cpa, pmd = pmd_offset(pud, start); - set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | + set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | massage_pgprot(pmd_pgprot))); start += PMD_SIZE; - cpa->pfn += PMD_SIZE; + cpa->pfn += PMD_SIZE >> PAGE_SHIFT; cur_pages += PMD_SIZE >> PAGE_SHIFT; } @@ -1046,12 +1055,12 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, /* * Map everything starting from the Gb boundary, possibly with 1G pages */ - while (end - start >= PUD_SIZE) { - set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | + while (cpu_has_gbpages && end - start >= PUD_SIZE) { + set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | massage_pgprot(pud_pgprot))); start += PUD_SIZE; - cpa->pfn += PUD_SIZE; + cpa->pfn += PUD_SIZE >> PAGE_SHIFT; cur_pages += PUD_SIZE >> PAGE_SHIFT; pud++; } @@ -1964,6 +1973,9 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, if (!(page_flags & _PAGE_NX)) cpa.mask_clr = __pgprot(_PAGE_NX); + if (!(page_flags & _PAGE_RW)) + cpa.mask_clr = __pgprot(_PAGE_RW); + cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); retval = __change_page_attr_set_clr(&cpa, 0); diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index ea48449..a243381 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -10,6 +10,9 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/init.h> #include <linux/acpi.h> @@ -28,8 +31,7 @@ struct bmp_header { void __init efi_bgrt_init(void) { acpi_status status; - void __iomem *image; - bool ioremapped = false; + void *image; struct bmp_header bmp_header; if (acpi_disabled) @@ -55,11 +57,6 @@ void __init efi_bgrt_init(void) bgrt_tab->status); return; } - if (bgrt_tab->status != 1) { - pr_debug("Ignoring BGRT: invalid status %u (expected 1)\n", - bgrt_tab->status); - return; - } if (bgrt_tab->image_type != 0) { pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n", bgrt_tab->image_type); @@ -70,20 +67,19 @@ void __init efi_bgrt_init(void) return; } - image = efi_lookup_mapped_addr(bgrt_tab->image_address); + image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB); if (!image) { - image = early_ioremap(bgrt_tab->image_address, - sizeof(bmp_header)); - ioremapped = true; - if (!image) { - pr_err("Ignoring BGRT: failed to map image header memory\n"); - return; - } + pr_err("Ignoring BGRT: failed to map image header memory\n"); + return; } - memcpy_fromio(&bmp_header, image, sizeof(bmp_header)); - if (ioremapped) - early_iounmap(image, sizeof(bmp_header)); + memcpy(&bmp_header, image, sizeof(bmp_header)); + memunmap(image); + if (bmp_header.id != 0x4d42) { + pr_err("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", + bmp_header.id); + return; + } bgrt_image_size = bmp_header.size; bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN); @@ -93,18 +89,14 @@ void __init efi_bgrt_init(void) return; } - if (ioremapped) { - image = early_ioremap(bgrt_tab->image_address, - bmp_header.size); - if (!image) { - pr_err("Ignoring BGRT: failed to map image memory\n"); - kfree(bgrt_image); - bgrt_image = NULL; - return; - } + image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); + if (!image) { + pr_err("Ignoring BGRT: failed to map image memory\n"); + kfree(bgrt_image); + bgrt_image = NULL; + return; } - memcpy_fromio(bgrt_image, image, bgrt_image_size); - if (ioremapped) - early_iounmap(image, bmp_header.size); + memcpy(bgrt_image, image, bgrt_image_size); + memunmap(image); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index ad28540..994a7df8 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -235,10 +235,10 @@ void __init efi_print_memmap(void) char buf[64]; md = p; - pr_info("mem%02u: %s range=[0x%016llx-0x%016llx) (%lluMB)\n", + pr_info("mem%02u: %s range=[0x%016llx-0x%016llx] (%lluMB)\n", i, efi_md_typeattr_format(buf, sizeof(buf), md), md->phys_addr, - md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT), + md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1, (md->num_pages >> (20 - EFI_PAGE_SHIFT))); } #endif /* EFI_DEBUG */ @@ -815,6 +815,7 @@ static void __init kexec_enter_virtual_mode(void) { #ifdef CONFIG_KEXEC_CORE efi_memory_desc_t *md; + unsigned int num_pages; void *p; efi.systab = NULL; @@ -829,6 +830,12 @@ static void __init kexec_enter_virtual_mode(void) return; } + if (efi_alloc_page_tables()) { + pr_err("Failed to allocate EFI page tables\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return; + } + /* * Map efi regions which were passed via setup_data. The virt_addr is a * fixed addr which was used in first kernel of a kexec boot. @@ -843,6 +850,14 @@ static void __init kexec_enter_virtual_mode(void) BUG_ON(!efi.systab); + num_pages = ALIGN(memmap.nr_map * memmap.desc_size, PAGE_SIZE); + num_pages >>= PAGE_SHIFT; + + if (efi_setup_page_tables(memmap.phys_map, num_pages)) { + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return; + } + efi_sync_low_kernel_mappings(); /* @@ -869,7 +884,7 @@ static void __init kexec_enter_virtual_mode(void) * This function will switch the EFI runtime services to virtual mode. * Essentially, we look through the EFI memmap and map every region that * has the runtime attribute bit set in its memory descriptor into the - * ->trampoline_pgd page table using a top-down VA allocation scheme. + * efi_pgd page table. * * The old method which used to update that memory descriptor with the * virtual address obtained from ioremap() is still supported when the @@ -879,8 +894,8 @@ static void __init kexec_enter_virtual_mode(void) * * The new method does a pagetable switch in a preemption-safe manner * so that we're in a different address space when calling a runtime - * function. For function arguments passing we do copy the PGDs of the - * kernel page table into ->trampoline_pgd prior to each call. + * function. For function arguments passing we do copy the PUDs of the + * kernel page table into efi_pgd prior to each call. * * Specially for kexec boot, efi runtime maps in previous kernel should * be passed in via setup_data. In that case runtime ranges will be mapped @@ -895,6 +910,12 @@ static void __init __efi_enter_virtual_mode(void) efi.systab = NULL; + if (efi_alloc_page_tables()) { + pr_err("Failed to allocate EFI page tables\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return; + } + efi_merge_regions(); new_memmap = efi_map_regions(&count, &pg_shift); if (!new_memmap) { @@ -913,7 +934,6 @@ static void __init __efi_enter_virtual_mode(void) } efi_sync_low_kernel_mappings(); - efi_dump_pagetable(); if (efi_is_native()) { status = phys_efi_set_virtual_address_map( @@ -951,31 +971,20 @@ static void __init __efi_enter_virtual_mode(void) efi.set_virtual_address_map = NULL; - efi_runtime_mkexec(); + /* + * Apply more restrictive page table mapping attributes now that + * SVAM() has been called and the firmware has performed all + * necessary relocation fixups for the new virtual addresses. + */ + efi_runtime_update_mappings(); + efi_dump_pagetable(); /* - * We mapped the descriptor array into the EFI pagetable above but we're - * not unmapping it here. Here's why: - * - * We're copying select PGDs from the kernel page table to the EFI page - * table and when we do so and make changes to those PGDs like unmapping - * stuff from them, those changes appear in the kernel page table and we - * go boom. - * - * From setup_real_mode(): - * - * ... - * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd; - * - * In this particular case, our allocation is in PGD 0 of the EFI page - * table but we've copied that PGD from PGD[272] of the EFI page table: - * - * pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272 - * - * where the direct memory mapping in kernel space is. - * - * new_memmap's VA comes from that direct mapping and thus clearing it, - * it would get cleared in the kernel page table too. + * We mapped the descriptor array into the EFI pagetable above + * but we're not unmapping it here because if we're running in + * EFI mixed mode we need all of memory to be accessible when + * we pass parameters to the EFI runtime services in the + * thunking code. * * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift); */ diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index ed5b673..338402b 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -38,6 +38,11 @@ * say 0 - 3G. */ +int __init efi_alloc_page_tables(void) +{ + return 0; +} + void efi_sync_low_kernel_mappings(void) {} void __init efi_dump_pagetable(void) {} int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) @@ -85,7 +90,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) __flush_tlb_all(); } -void __init efi_runtime_mkexec(void) +void __init efi_runtime_update_mappings(void) { if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index a0ac0f9..49e4dd4 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -15,6 +15,8 @@ * */ +#define pr_fmt(fmt) "efi: " fmt + #include <linux/kernel.h> #include <linux/init.h> #include <linux/mm.h> @@ -40,6 +42,7 @@ #include <asm/fixmap.h> #include <asm/realmode.h> #include <asm/time.h> +#include <asm/pgalloc.h> /* * We allocate runtime services regions bottom-up, starting from -4G, i.e. @@ -47,16 +50,7 @@ */ static u64 efi_va = EFI_VA_START; -/* - * 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; +struct efi_scratch efi_scratch; static void __init early_code_mapping_set_exec(int executable) { @@ -83,8 +77,11 @@ pgd_t * __init efi_call_phys_prolog(void) int pgd; int n_pgds; - if (!efi_enabled(EFI_OLD_MEMMAP)) - return NULL; + if (!efi_enabled(EFI_OLD_MEMMAP)) { + save_pgd = (pgd_t *)read_cr3(); + write_cr3((unsigned long)efi_scratch.efi_pgt); + goto out; + } early_code_mapping_set_exec(1); @@ -96,6 +93,7 @@ pgd_t * __init efi_call_phys_prolog(void) vaddress = (unsigned long)__va(pgd * PGDIR_SIZE); set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress)); } +out: __flush_tlb_all(); return save_pgd; @@ -109,8 +107,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) int pgd_idx; int nr_pgds; - if (!save_pgd) + if (!efi_enabled(EFI_OLD_MEMMAP)) { + write_cr3((unsigned long)save_pgd); + __flush_tlb_all(); return; + } nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); @@ -123,27 +124,98 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) early_code_mapping_set_exec(0); } +static pgd_t *efi_pgd; + +/* + * We need our own copy of the higher levels of the page tables + * because we want to avoid inserting EFI region mappings (EFI_VA_END + * to EFI_VA_START) into the standard kernel page tables. Everything + * else can be shared, see efi_sync_low_kernel_mappings(). + */ +int __init efi_alloc_page_tables(void) +{ + pgd_t *pgd; + pud_t *pud; + gfp_t gfp_mask; + + if (efi_enabled(EFI_OLD_MEMMAP)) + return 0; + + gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO; + efi_pgd = (pgd_t *)__get_free_page(gfp_mask); + if (!efi_pgd) + return -ENOMEM; + + pgd = efi_pgd + pgd_index(EFI_VA_END); + + pud = pud_alloc_one(NULL, 0); + if (!pud) { + free_page((unsigned long)efi_pgd); + return -ENOMEM; + } + + pgd_populate(NULL, pgd, pud); + + return 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); + unsigned num_entries; + pgd_t *pgd_k, *pgd_efi; + pud_t *pud_k, *pud_efi; if (efi_enabled(EFI_OLD_MEMMAP)) return; - num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET); + /* + * We can share all PGD entries apart from the one entry that + * covers the EFI runtime mapping space. + * + * Make sure the EFI runtime region mappings are guaranteed to + * only span a single PGD entry and that the entry also maps + * other important kernel regions. + */ + BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END)); + BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) != + (EFI_VA_END & PGDIR_MASK)); + + pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET); + pgd_k = pgd_offset_k(PAGE_OFFSET); - memcpy(pgd + pgd_index(PAGE_OFFSET), - init_mm.pgd + pgd_index(PAGE_OFFSET), - sizeof(pgd_t) * num_pgds); + num_entries = pgd_index(EFI_VA_END) - pgd_index(PAGE_OFFSET); + memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries); + + /* + * We share all the PUD entries apart from those that map the + * EFI regions. Copy around them. + */ + BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0); + BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0); + + pgd_efi = efi_pgd + pgd_index(EFI_VA_END); + pud_efi = pud_offset(pgd_efi, 0); + + pgd_k = pgd_offset_k(EFI_VA_END); + pud_k = pud_offset(pgd_k, 0); + + num_entries = pud_index(EFI_VA_END); + memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries); + + pud_efi = pud_offset(pgd_efi, EFI_VA_START); + pud_k = pud_offset(pgd_k, EFI_VA_START); + + num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START); + memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries); } int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { - unsigned long text; + unsigned long pfn, text; + efi_memory_desc_t *md; struct page *page; unsigned npages; pgd_t *pgd; @@ -151,8 +223,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) if (efi_enabled(EFI_OLD_MEMMAP)) return 0; - efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd; - pgd = __va(efi_scratch.efi_pgt); + efi_scratch.efi_pgt = (pgd_t *)__pa(efi_pgd); + pgd = efi_pgd; /* * It can happen that the physical address of new_memmap lands in memory @@ -160,7 +232,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * and ident-map those pages containing the map before calling * phys_efi_set_virtual_address_map(). */ - if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) { + pfn = pa_memmap >> PAGE_SHIFT; + if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, _PAGE_NX | _PAGE_RW)) { pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap); return 1; } @@ -176,6 +249,25 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) if (!IS_ENABLED(CONFIG_EFI_MIXED)) return 0; + /* + * Map all of RAM so that we can access arguments in the 1:1 + * mapping when making EFI runtime calls. + */ + for_each_efi_memory_desc(&memmap, md) { + if (md->type != EFI_CONVENTIONAL_MEMORY && + md->type != EFI_LOADER_DATA && + md->type != EFI_LOADER_CODE) + continue; + + pfn = md->phys_addr >> PAGE_SHIFT; + npages = md->num_pages; + + if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, npages, _PAGE_RW)) { + pr_err("Failed to map 1:1 memory\n"); + return 1; + } + } + page = alloc_page(GFP_KERNEL|__GFP_DMA32); if (!page) panic("Unable to allocate EFI runtime stack < 4GB\n"); @@ -183,10 +275,11 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.phys_stack = virt_to_phys(page_address(page)); efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */ - npages = (_end - _text) >> PAGE_SHIFT; + npages = (_etext - _text) >> PAGE_SHIFT; text = __pa(_text); + pfn = text >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) { + if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, _PAGE_RW)) { pr_err("Failed to map kernel text 1:1\n"); return 1; } @@ -196,20 +289,20 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) { - pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); - - kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages); + kernel_unmap_pages_in_pgd(efi_pgd, pa_memmap, num_pages); } 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; + unsigned long flags = _PAGE_RW; + unsigned long pfn; + pgd_t *pgd = efi_pgd; if (!(md->attribute & EFI_MEMORY_WB)) - pf |= _PAGE_PCD; + flags |= _PAGE_PCD; - if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf)) + pfn = md->phys_addr >> PAGE_SHIFT; + if (kernel_map_pages_in_pgd(pgd, pfn, va, md->num_pages, flags)) pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", md->phys_addr, va); } @@ -300,21 +393,56 @@ 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) +void __init efi_runtime_update_mappings(void) { - if (!efi_enabled(EFI_OLD_MEMMAP)) + unsigned long pfn; + pgd_t *pgd = efi_pgd; + efi_memory_desc_t *md; + void *p; + + if (efi_enabled(EFI_OLD_MEMMAP)) { + if (__supported_pte_mask & _PAGE_NX) + runtime_code_page_mkexec(); return; + } + + if (!efi_enabled(EFI_NX_PE_DATA)) + return; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + unsigned long pf = 0; + md = p; + + if (!(md->attribute & EFI_MEMORY_RUNTIME)) + continue; - if (__supported_pte_mask & _PAGE_NX) - runtime_code_page_mkexec(); + if (!(md->attribute & EFI_MEMORY_WB)) + pf |= _PAGE_PCD; + + if ((md->attribute & EFI_MEMORY_XP) || + (md->type == EFI_RUNTIME_SERVICES_DATA)) + pf |= _PAGE_NX; + + if (!(md->attribute & EFI_MEMORY_RO) && + (md->type != EFI_RUNTIME_SERVICES_CODE)) + pf |= _PAGE_RW; + + /* Update the 1:1 mapping */ + pfn = md->phys_addr >> PAGE_SHIFT; + if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf)) + pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + + if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf)) + pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + } } void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP - pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); - - ptdump_walk_pgd_level(NULL, pgd); + ptdump_walk_pgd_level(NULL, efi_pgd); #endif } diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 0df2dcc..92723ae 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -39,41 +39,6 @@ mov %rsi, %cr0; \ mov (%rsp), %rsp - /* stolen from gcc */ - .macro FLUSH_TLB_ALL - movq %r15, efi_scratch(%rip) - movq %r14, efi_scratch+8(%rip) - movq %cr4, %r15 - movq %r15, %r14 - andb $0x7f, %r14b - movq %r14, %cr4 - movq %r15, %cr4 - movq efi_scratch+8(%rip), %r14 - movq efi_scratch(%rip), %r15 - .endm - - .macro SWITCH_PGT - cmpb $0, efi_scratch+24(%rip) - je 1f - movq %r15, efi_scratch(%rip) # r15 - # save previous CR3 - movq %cr3, %r15 - movq %r15, efi_scratch+8(%rip) # prev_cr3 - movq efi_scratch+16(%rip), %r15 # EFI pgt - movq %r15, %cr3 - 1: - .endm - - .macro RESTORE_PGT - cmpb $0, efi_scratch+24(%rip) - je 2f - movq efi_scratch+8(%rip), %r15 - movq %r15, %cr3 - movq efi_scratch(%rip), %r15 - FLUSH_TLB_ALL - 2: - .endm - ENTRY(efi_call) FRAME_BEGIN SAVE_XMM @@ -85,17 +50,9 @@ ENTRY(efi_call) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx - SWITCH_PGT call *%rdi - RESTORE_PGT addq $48, %rsp RESTORE_XMM FRAME_END ret ENDPROC(efi_call) - - .data -ENTRY(efi_scratch) - .fill 3,8,0 - .byte 0 - .quad 0 diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index ed30e79..ab50ada 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) "efi: " fmt + #include <linux/init.h> #include <linux/kernel.h> #include <linux/string.h> @@ -55,13 +57,41 @@ void efi_delete_dummy_variable(void) } /* + * 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) +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; @@ -69,6 +99,9 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long 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) @@ -312,7 +345,7 @@ void __init efi_apply_memmap_quirks(void) * services. */ if (!efi_runtime_supported()) { - pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); + pr_info("Setup done, disabling due to 32/64-bit mismatch\n"); efi_unmap_memmap(); } |