From 4750a0d112cbfcc744929f1530ffe3193436766c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 31 Oct 2014 23:23:43 +0100 Subject: x86, microcode, AMD: Fix early ucode loading on 32-bit Konrad triggered the following splat below in a 32-bit guest on an AMD box. As it turns out, in save_microcode_in_initrd_amd() we're using the *physical* address of the container *after* we have enabled paging and thus we #PF in load_microcode_amd() when trying to access the microcode container in the ramdisk range. Because the ramdisk is exactly there: [ 0.000000] RAMDISK: [mem 0x35e04000-0x36ef9fff] and we fault at 0x35e04304. And since this guest doesn't relocate the ramdisk, we don't do the computation which will give us the correct virtual address and we end up with the PA. So, we should actually be using virtual addresses on 32-bit too by the time we're freeing the initrd. Do that then! Unpacking initramfs... BUG: unable to handle kernel paging request at 35d4e304 IP: [] load_microcode_amd+0x25/0x4a0 *pde = 00000000 Oops: 0000 [#1] SMP Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.17.1-302.fc21.i686 #1 Hardware name: Xen HVM domU, BIOS 4.4.1 10/01/2014 task: f5098000 ti: f50d0000 task.ti: f50d0000 EIP: 0060:[] EFLAGS: 00010246 CPU: 0 EIP is at load_microcode_amd+0x25/0x4a0 EAX: 00000000 EBX: f6e9ec4c ECX: 00001ec4 EDX: 00000000 ESI: f5d4e000 EDI: 35d4e2fc EBP: f50d1ed0 ESP: f50d1e94 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 35d4e304 CR3: 00e33000 CR4: 000406d0 Stack: 00000000 00000000 f50d1ebc f50d1ec4 f5d4e000 c0d7735a f50d1ed0 15a3d17f f50d1ec4 00600f20 00001ec4 bfb83203 f6e9ec4c f5d4e000 c0d7735a f50d1ed8 c0d80861 f50d1ee0 c0d80429 f50d1ef0 c0d889a9 f5d4e000 c0000000 f50d1f04 Call Trace: ? unpack_to_rootfs ? unpack_to_rootfs save_microcode_in_initrd_amd save_microcode_in_initrd free_initrd_mem populate_rootfs ? unpack_to_rootfs do_one_initcall ? unpack_to_rootfs ? repair_env_string ? proc_mkdir kernel_init_freeable kernel_init ret_from_kernel_thread ? rest_init Reported-and-tested-by: Konrad Rzeszutek Wilk References: https://bugzilla.redhat.com/show_bug.cgi?id=1158204 Fixes: 75a1ba5b2c52 ("x86, microcode, AMD: Unify valid container checks") Signed-off-by: Borislav Petkov Cc: # v3.14+ Link: http://lkml.kernel.org/r/20141101100100.GA4462@pd.tnic Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/microcode/amd_early.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 7aa1acc79789..8b75f7050129 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -348,6 +348,7 @@ int __init save_microcode_in_initrd_amd(void) { unsigned long cont; enum ucode_state ret; + u8 *cont_va; u32 eax; if (!container) @@ -355,13 +356,15 @@ int __init save_microcode_in_initrd_amd(void) #ifdef CONFIG_X86_32 get_bsp_sig(); - cont = (unsigned long)container; + cont = (unsigned long)container; + cont_va = __va(container); #else /* * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa(container); + cont_va = container; #endif /* @@ -372,6 +375,8 @@ int __init save_microcode_in_initrd_amd(void) if (relocated_ramdisk) container = (u8 *)(__va(relocated_ramdisk) + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", -- cgit v1.2.3 From e6023367d779060fddc9a52d1f474085b2b36298 Mon Sep 17 00:00:00 2001 From: Junjie Mao Date: Fri, 31 Oct 2014 21:40:38 +0800 Subject: x86, kaslr: Prevent .bss from overlaping initrd When choosing a random address, the current implementation does not take into account the reversed space for .bss and .brk sections. Thus the relocated kernel may overlap other components in memory. Here is an example of the overlap from a x86_64 kernel in qemu (the ranges of physical addresses are presented): Physical Address 0x0fe00000 --+--------------------+ <-- randomized base / | relocated kernel | vmlinux.bin | (from vmlinux.bin) | 0x1336d000 (an ELF file) +--------------------+-- \ | | \ 0x1376d870 --+--------------------+ | | relocs table | | 0x13c1c2a8 +--------------------+ .bss and .brk | | | 0x13ce6000 +--------------------+ | | | / 0x13f77000 | initrd |-- | | 0x13fef374 +--------------------+ The initrd image will then be overwritten by the memset during early initialization: [ 1.655204] Unpacking initramfs... [ 1.662831] Initramfs unpacking failed: junk in compressed archive This patch prevents the above situation by requiring a larger space when looking for a random kernel base, so that existing logic can effectively avoids the overlap. [kees: switched to perl to avoid hex translation pain in mawk vs gawk] [kees: calculated overlap without relocs table] Fixes: 82fa9637a2 ("x86, kaslr: Select random position from e820 maps") Reported-by: Fengguang Wu Signed-off-by: Junjie Mao Signed-off-by: Kees Cook Cc: Josh Triplett Cc: Matt Fleming Cc: Ard Biesheuvel Cc: Vivek Goyal Cc: Andi Kleen Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1414762838-13067-1-git-send-email-eternal.n08@gmail.com Signed-off-by: Thomas Gleixner --- arch/x86/boot/compressed/Makefile | 4 +++- arch/x86/boot/compressed/head_32.S | 5 +++-- arch/x86/boot/compressed/head_64.S | 5 ++++- arch/x86/boot/compressed/misc.c | 13 ++++++++++--- arch/x86/boot/compressed/mkpiggy.c | 9 +++++++-- arch/x86/tools/calc_run_size.pl | 30 ++++++++++++++++++++++++++++++ 6 files changed, 57 insertions(+), 9 deletions(-) create mode 100644 arch/x86/tools/calc_run_size.pl (limited to 'arch/x86') diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 704f58aa79cd..be1e07d4b596 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -76,8 +76,10 @@ suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_LZ4) := lz4 +RUN_SIZE = $(shell objdump -h vmlinux | \ + perl $(srctree)/arch/x86/tools/calc_run_size.pl) quiet_cmd_mkpiggy = MKPIGGY $@ - cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) + cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false ) targets += piggy.S $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index cbed1407a5cd..1d7fbbcc196d 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -207,7 +207,8 @@ relocated: * Do the decompression, and jump to the new kernel.. */ /* push arguments for decompress_kernel: */ - pushl $z_output_len /* decompressed length */ + pushl $z_run_size /* size of kernel with .bss and .brk */ + pushl $z_output_len /* decompressed length, end of relocs */ leal z_extract_offset_negative(%ebx), %ebp pushl %ebp /* output address */ pushl $z_input_len /* input_len */ @@ -217,7 +218,7 @@ relocated: pushl %eax /* heap area */ pushl %esi /* real mode pointer */ call decompress_kernel /* returns kernel location in %eax */ - addl $24, %esp + addl $28, %esp /* * Jump to the decompressed kernel. diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 2884e0c3e8a5..6b1766c6c082 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -402,13 +402,16 @@ relocated: * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ + movq $z_run_size, %r9 /* size of kernel with .bss and .brk */ + pushq %r9 movq %rsi, %rdi /* real mode address */ leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movq $z_output_len, %r9 /* decompressed length */ + movq $z_output_len, %r9 /* decompressed length, end of relocs */ call decompress_kernel /* returns kernel location in %rax */ + popq %r9 popq %rsi /* diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 57ab74df7eea..30dd59a9f0b4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -358,7 +358,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, unsigned char *output, - unsigned long output_len) + unsigned long output_len, + unsigned long run_size) { real_mode = rmode; @@ -381,8 +382,14 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; - output = choose_kernel_location(input_data, input_len, - output, output_len); + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + */ + output = choose_kernel_location(input_data, input_len, output, + output_len > run_size ? output_len + : run_size); /* Validate memory location choices. */ if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1)) diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index b669ab65bf6c..d8222f213182 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -36,11 +36,13 @@ int main(int argc, char *argv[]) uint32_t olen; long ilen; unsigned long offs; + unsigned long run_size; FILE *f = NULL; int retval = 1; - if (argc < 2) { - fprintf(stderr, "Usage: %s compressed_file\n", argv[0]); + if (argc < 3) { + fprintf(stderr, "Usage: %s compressed_file run_size\n", + argv[0]); goto bail; } @@ -74,6 +76,7 @@ int main(int argc, char *argv[]) offs += olen >> 12; /* Add 8 bytes for each 32K block */ offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ + run_size = atoi(argv[2]); printf(".section \".rodata..compressed\",\"a\",@progbits\n"); printf(".globl z_input_len\n"); @@ -85,6 +88,8 @@ int main(int argc, char *argv[]) /* z_extract_offset_negative allows simplification of head_32.S */ printf(".globl z_extract_offset_negative\n"); printf("z_extract_offset_negative = -0x%lx\n", offs); + printf(".globl z_run_size\n"); + printf("z_run_size = %lu\n", run_size); printf(".globl input_data, input_data_end\n"); printf("input_data:\n"); diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl new file mode 100644 index 000000000000..0b0b124d3ece --- /dev/null +++ b/arch/x86/tools/calc_run_size.pl @@ -0,0 +1,30 @@ +#!/usr/bin/perl +# +# Calculate the amount of space needed to run the kernel, including room for +# the .bss and .brk sections. +# +# Usage: +# objdump -h a.out | perl calc_run_size.pl +use strict; + +my $mem_size = 0; +my $file_offset = 0; + +my $sections=" *[0-9]+ \.(?:bss|brk) +"; +while (<>) { + if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) { + my $size = hex($1); + my $offset = hex($2); + $mem_size += $size; + if ($file_offset == 0) { + $file_offset = $offset; + } elsif ($file_offset != $offset) { + die ".bss and .brk lack common file offset\n"; + } + } +} + +if ($file_offset == 0) { + die "Never found .bss or .brk file offset\n"; +} +printf("%d\n", $mem_size + $file_offset); -- cgit v1.2.3 From 85be07c32496dc264661308e4d9d4e9ccaff8072 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 5 Nov 2014 17:28:06 +0100 Subject: x86, microcode: Fix accessing dis_ucode_ldr on 32-bit We should be accessing it through a pointer, like on the BSP. Tested-by: Richard Hendershot Fixes: 65cef1311d5d ("x86, microcode: Add a disable chicken bit") Cc: # v3.15+ Signed-off-by: Borislav Petkov --- arch/x86/kernel/cpu/microcode/core_early.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index 5f28a64e71ea..2c017f242a78 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -124,7 +124,7 @@ void __init load_ucode_bsp(void) static bool check_loader_disabled_ap(void) { #ifdef CONFIG_X86_32 - return __pa_nodebug(dis_ucode_ldr); + return *((bool *)__pa_nodebug(&dis_ucode_ldr)); #else return dis_ucode_ldr; #endif -- cgit v1.2.3 From 54279552bd260532d90e7a59fbc931924bbb0f7b Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Fri, 31 Oct 2014 11:49:32 -0400 Subject: x86/core, x86/xen/smp: Use 'die_complete' completion when taking CPU down Commit 2ed53c0d6cc9 ("x86/smpboot: Speed up suspend/resume by avoiding 100ms sleep for CPU offline during S3") introduced completions to CPU offlining process. These completions are not initialized on Xen kernels causing a panic in play_dead_common(). Move handling of die_complete into common routines to make them available to Xen guests. Signed-off-by: Boris Ostrovsky Reviewed-by: David Vrabel Cc: tianyu.lan@intel.com Cc: konrad.wilk@oracle.com Cc: xen-devel@lists.xenproject.org Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1414770572-7950-1-git-send-email-boris.ostrovsky@oracle.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/smp.h | 1 + arch/x86/kernel/smpboot.c | 15 +++++++++++---- arch/x86/xen/smp.c | 3 +++ 3 files changed, 15 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 8cd27e08e23c..8cd1cc3bc835 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -150,6 +150,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) } void cpu_disable_common(void); +void cpu_die_common(unsigned int cpu); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); void native_smp_cpus_done(unsigned int max_cpus); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 4d2128ac70bd..668d8f2a8781 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1303,10 +1303,14 @@ static void __ref remove_cpu_from_maps(int cpu) numa_remove_cpu(cpu); } +static DEFINE_PER_CPU(struct completion, die_complete); + void cpu_disable_common(void) { int cpu = smp_processor_id(); + init_completion(&per_cpu(die_complete, smp_processor_id())); + remove_siblinginfo(cpu); /* It's now safe to remove this processor from the online map */ @@ -1316,8 +1320,6 @@ void cpu_disable_common(void) fixup_irqs(); } -static DEFINE_PER_CPU(struct completion, die_complete); - int native_cpu_disable(void) { int ret; @@ -1327,16 +1329,21 @@ int native_cpu_disable(void) return ret; clear_local_APIC(); - init_completion(&per_cpu(die_complete, smp_processor_id())); cpu_disable_common(); return 0; } +void cpu_die_common(unsigned int cpu) +{ + wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ); +} + void native_cpu_die(unsigned int cpu) { /* We don't do anything here: idle task is faking death itself. */ - wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ); + + cpu_die_common(cpu); /* They ack this in play_dead() by setting CPU_DEAD */ if (per_cpu(cpu_state, cpu) == CPU_DEAD) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 8650cdb53209..4c071aeb8417 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -510,6 +510,9 @@ static void xen_cpu_die(unsigned int cpu) current->state = TASK_UNINTERRUPTIBLE; schedule_timeout(HZ/10); } + + cpu_die_common(cpu); + xen_smp_intr_free(cpu); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); -- cgit v1.2.3 From c0a717f23dccdb6e3b03471bc846fdc636f2b353 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 5 Nov 2014 17:42:42 +0100 Subject: x86, microcode, AMD: Fix ucode patch stashing on 32-bit Save the patch while we're running on the BSP instead of later, before the initrd has been jettisoned. More importantly, on 32-bit we need to access the physical address instead of the virtual. This way we actually do find it on the APs instead of having to go through the initrd each time. Tested-by: Richard Hendershot Fixes: 5335ba5cf475 ("x86, microcode, AMD: Fix early ucode loading") Cc: # v3.13+ Signed-off-by: Borislav Petkov --- arch/x86/kernel/cpu/microcode/amd_early.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 8b75f7050129..06674473b0e6 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. */ -static void apply_ucode_in_initrd(void *ucode, size_t size) +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) { struct equiv_cpu_entry *eq; size_t *cont_sz; u32 *header; u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; u16 eq_id = 0; int offset, left; u32 rev, eax, ebx, ecx, edx; @@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); cont_sz = (size_t *)__pa_nodebug(&container_size); cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; cont_sz = &container_size; cont = &container; + patch = &amd_ucode_patch; #endif data = ucode; @@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) rev = mc->hdr.patch_id; *new_rev = rev; - /* save ucode patch */ - memcpy(amd_ucode_patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); } } @@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void) *data = cp.data; *size = cp.size; - apply_ucode_in_initrd(cp.data, cp.size); + apply_ucode_in_initrd(cp.data, cp.size, true); } #ifdef CONFIG_X86_32 @@ -263,7 +266,7 @@ void load_ucode_amd_ap(void) size_t *usize; void **ucode; - mc = (struct microcode_amd *)__pa(amd_ucode_patch); + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { __apply_microcode_amd(mc); return; @@ -275,7 +278,7 @@ void load_ucode_amd_ap(void) if (!*ucode || !*usize) return; - apply_ucode_in_initrd(*ucode, *usize); + apply_ucode_in_initrd(*ucode, *usize, false); } static void __init collect_cpu_sig_on_bsp(void *arg) @@ -339,7 +342,7 @@ void load_ucode_amd_ap(void) * AP has a different equivalence ID than BSP, looks like * mixed-steppings silicon so go through the ucode blob anew. */ - apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size); + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); } } #endif @@ -347,6 +350,7 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { unsigned long cont; + int retval = 0; enum ucode_state ret; u8 *cont_va; u32 eax; @@ -387,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void) ret = load_microcode_amd(eax, container, container_size); if (ret != UCODE_OK) - return -EINVAL; + retval = -EINVAL; /* * This will be freed any msec now, stash patches for the current @@ -396,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void) container = NULL; container_size = 0; - return 0; + return retval; } -- cgit v1.2.3