On 07.08.20 11:39, peterz@xxxxxxxxxxxxx wrote:
On Fri, Aug 07, 2020 at 10:38:23AM +0200, Juergen Gross wrote:-# else - const unsigned char cpu_iret[1]; -# endif };static const struct patch_xxl patch_data_xxl = {@@ -42,7 +38,6 @@ static const struct patch_xxl patch_data_xxl = { .irq_save_fl = { 0x9c, 0x58 }, // pushf; pop %[re]ax .mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax .mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax -# ifdef CONFIG_X86_64 .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3 .irq_restore_fl = { 0x57, 0x9d }, // push %rdi; popfq .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd @@ -50,19 +45,11 @@ static const struct patch_xxl patch_data_xxl = { 0x48, 0x0f, 0x07 }, // swapgs; sysretq .cpu_swapgs = { 0x0f, 0x01, 0xf8 }, // swapgs .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax -# else - .mmu_write_cr3 = { 0x0f, 0x22, 0xd8 }, // mov %eax, %cr3 - .irq_restore_fl = { 0x50, 0x9d }, // push %eax; popf - .cpu_iret = { 0xcf }, // iret -# endifI was looking at x86_64 paravirt the other day and found we actually have pv_ops.cpu.iret users there..
On x86_64 we have (without PARAVIRT_XXL): #define INTERRUPT_RETURN jmp native_iret and with PARAVIRT_XXL this is basically a jmp *pv_ops.cpu.iret which will then be patched to either jmp native_iret or jmp xen_iret. On x86_32 INTERRUPT_RETURN was just "iret" for the non-paravirt case. This is the reason for above dropping of the static patch data.
So we want to change the above to also patch iret on x86_64 or do we need to fix x86_64 to not have pv-iret?
We want it to stay how it is. This will let both variants (PARVIRT y/n) continue to work. Juergen _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/virtualization
