x86/kexec: Debugging support: Load an IDT and basic exception entry points

[ mingo: Minor readability edits ]

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20250314173226.3062535-2-dwmw2@infradead.org

diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 5432457d23381d79db8a0ff260b0c49b3a44d1e6..fb4537c58b54a9ec75fe9be5d19ace1abdf32634 100644 (file)
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -8,6 +8,9 @@
 # define PA_PGD                        2
 # define PA_SWAP_PAGE          3
 # define PAGES_NR              4
+#else
+/* Size of each exception handler referenced by the IDT */
+# define KEXEC_DEBUG_EXC_HANDLER_SIZE  6 /* PUSHI, PUSHI, 2-byte JMP */
 #endif
 
 # define KEXEC_CONTROL_PAGE_SIZE       4096
@@ -59,6 +62,8 @@ struct kimage;
 extern unsigned long kexec_va_control_page;
 extern unsigned long kexec_pa_table_page;
 extern unsigned long kexec_pa_swap_page;
+extern gate_desc kexec_debug_idt[];
+extern unsigned char kexec_debug_exc_vectors[];
 #endif
 
 /*

diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a68f5a0a9f3708d0d3c9da8beb486b20437dddca..cc73f97084647d6d04fd3c543b38aeba3a2f2212 100644 (file)
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -304,6 +304,24 @@ static void load_segments(void)
                );
 }
 
+static void prepare_debug_idt(unsigned long control_page, unsigned long vec_ofs)
+{
+       gate_desc idtentry = { 0 };
+       int i;
+
+       idtentry.bits.p         = 1;
+       idtentry.bits.type      = GATE_TRAP;
+       idtentry.segment        = __KERNEL_CS;
+       idtentry.offset_low     = (control_page & 0xFFFF) + vec_ofs;
+       idtentry.offset_middle  = (control_page >> 16) & 0xFFFF;
+       idtentry.offset_high    = control_page >> 32;
+
+       for (i = 0; i < 16; i++) {
+               kexec_debug_idt[i] = idtentry;
+               idtentry.offset_low += KEXEC_DEBUG_EXC_HANDLER_SIZE;
+       }
+}
+
 int machine_kexec_prepare(struct kimage *image)
 {
        void *control_page = page_address(image->control_code_page);
@@ -321,6 +339,9 @@ int machine_kexec_prepare(struct kimage *image)
        if (image->type == KEXEC_TYPE_DEFAULT)
                kexec_pa_swap_page = page_to_pfn(image->swap_page) << PAGE_SHIFT;
 
+       prepare_debug_idt((unsigned long)__pa(control_page),
+                         (unsigned long)kexec_debug_exc_vectors - reloc_start);
+
        __memcpy(control_page, __relocate_kernel_start, reloc_end - reloc_start);
 
        set_memory_rox((unsigned long)control_page, 1);

diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index ac058971a38256c8d8147b2544ca2c208f1e2ca6..8f26ffd108490c5ef07e61c75446c2b11c5cba52 100644 (file)
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -50,6 +50,11 @@ SYM_DATA_START_LOCAL(kexec_debug_gdt)
        .quad   0x00cf92000000ffff      /* __KERNEL_DS */
 SYM_DATA_END_LABEL(kexec_debug_gdt, SYM_L_LOCAL, kexec_debug_gdt_end)
 
+       .balign 8
+SYM_DATA_START(kexec_debug_idt)
+       .skip 0x100, 0x00
+SYM_DATA_END(kexec_debug_idt)
+
        .section .text..relocate_kernel,"ax";
        .code64
 SYM_CODE_START_NOALIGN(relocate_kernel)
@@ -139,6 +144,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
        movq    %ds, %rax
        movq    %rax, %ds
 
+       /* Now an IDTR on the stack to load the IDT the kernel created */
+       leaq    kexec_debug_idt(%rip), %rsi
+       pushq   %rsi
+       pushw   $0xff
+       lidt    (%rsp)
+       addq    $10, %rsp
+
+       //int3
+
        /*
         * Clear X86_CR4_CET (if it was set) such that we can clear CR0_WP
         * below.
@@ -364,3 +378,66 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
        ret
        int3
 SYM_CODE_END(swap_pages)
+
+SYM_CODE_START_NOALIGN(kexec_debug_exc_vectors)
+       /* Each of these is 6 bytes. */
+.macro vec_err exc
+       UNWIND_HINT_ENTRY
+       . = kexec_debug_exc_vectors + (\exc * KEXEC_DEBUG_EXC_HANDLER_SIZE)
+       nop
+       nop
+       pushq   $\exc
+       jmp     exc_handler
+.endm
+
+.macro vec_noerr exc
+       UNWIND_HINT_ENTRY
+       . = kexec_debug_exc_vectors + (\exc * KEXEC_DEBUG_EXC_HANDLER_SIZE)
+       pushq   $0
+       pushq   $\exc
+       jmp     exc_handler
+.endm
+
+       ANNOTATE_NOENDBR
+       vec_noerr  0 // #DE
+       vec_noerr  1 // #DB
+       vec_noerr  2 // #NMI
+       vec_noerr  3 // #BP
+       vec_noerr  4 // #OF
+       vec_noerr  5 // #BR
+       vec_noerr  6 // #UD
+       vec_noerr  7 // #NM
+       vec_err    8 // #DF
+       vec_noerr  9
+       vec_err   10 // #TS
+       vec_err   11 // #NP
+       vec_err   12 // #SS
+       vec_err   13 // #GP
+       vec_err   14 // #PF
+       vec_noerr 15
+SYM_CODE_END(kexec_debug_exc_vectors)
+
+SYM_CODE_START_LOCAL_NOALIGN(exc_handler)
+       /* No need for RET mitigations during kexec */
+       VALIDATE_UNRET_END
+
+       pushq   %rax
+       pushq   %rdx
+       movw    $0x3f8, %dx
+       movb    $'A', %al
+       outb    %al, %dx
+       popq    %rdx
+       popq    %rax
+
+       /* Only return from INT3 */
+       cmpq    $3, (%rsp)
+       jne     .Ldie
+
+       addq    $16, %rsp
+       iretq
+
+.Ldie:
+       hlt
+       jmp     .Ldie
+
+SYM_CODE_END(exc_handler)