On Tue, Apr 28, 2020 at 05:16:35PM +0200, Joerg Roedel wrote:
> From: Tom Lendacky <thomas.lendacky@xxxxxxx>
>
> Add support for decoding and handling #VC exceptions for IOIO events.
>
> Signed-off-by: Tom Lendacky <thomas.lendacky@xxxxxxx>
> [ jroedel@xxxxxxx: Adapted code to #VC handling framework ]
> Co-developed-by: Joerg Roedel <jroedel@xxxxxxx>
> Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
> ---
> arch/x86/boot/compressed/sev-es.c | 32 +++++
> arch/x86/kernel/sev-es-shared.c | 202 ++++++++++++++++++++++++++++++
> 2 files changed, 234 insertions(+)
>
> diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c
> index 1241697dd156..17765e471e28 100644
> --- a/arch/x86/boot/compressed/sev-es.c
> +++ b/arch/x86/boot/compressed/sev-es.c
> @@ -23,6 +23,35 @@
...
> +static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
> +{
> + struct pt_regs *regs = ctxt->regs;
> + u64 exit_info_1, exit_info_2;
> + enum es_result ret;
> +
> + ret = vc_ioio_exitinfo(ctxt, &exit_info_1);
> + if (ret != ES_OK)
> + return ret;
> +
> + if (exit_info_1 & IOIO_TYPE_STR) {
> + int df = (regs->flags & X86_EFLAGS_DF) ? -1 : 1;
> + unsigned int io_bytes, exit_bytes;
> + unsigned int ghcb_count, op_count;
> + unsigned long es_base;
> + u64 sw_scratch;
> +
> + /*
> + * For the string variants with rep prefix the amount of in/out
> + * operations per #VC exception is limited so that the kernel
> + * has a chance to take interrupts an re-schedule while the
> + * instruction is emulated.
Doesn't this also suppress single-step #DBs?
> + */
> + io_bytes = (exit_info_1 >> 4) & 0x7;
> + ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes;
> +
> + op_count = (exit_info_1 & IOIO_REP) ? regs->cx : 1;
> + exit_info_2 = min(op_count, ghcb_count);
> + exit_bytes = exit_info_2 * io_bytes;
> +
> + es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
> +
> + if (!(exit_info_1 & IOIO_TYPE_IN)) {
> + ret = vc_insn_string_read(ctxt,
> + (void *)(es_base + regs->si),
SEV(-ES) is 64-bit only, why bother with the es_base charade?
> + ghcb->shared_buffer, io_bytes,
> + exit_info_2, df);
df handling is busted, it's aways non-zero. Same goes for the SI/DI
adjustments below.
> + if (ret)
> + return ret;
> + }
> +
> + sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
> + ghcb_set_sw_scratch(ghcb, sw_scratch);
> + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
> + exit_info_1, exit_info_2);
> + if (ret != ES_OK)
> + return ret;
Batching the memory accesses and I/O accesses separately is technically
wrong, e.g. a #DB on a memory access will result in bogus data being shown
in the debugger. In practice it seems unlikely to matter, but I'm curious
as to why string I/O is supported in the first place. I didn't think there
was that much string I/O in the kernel?
> +
> + /* Everything went well, write back results */
> + if (exit_info_1 & IOIO_TYPE_IN) {
> + ret = vc_insn_string_write(ctxt,
> + (void *)(es_base + regs->di),
> + ghcb->shared_buffer, io_bytes,
> + exit_info_2, df);
> + if (ret)
> + return ret;
> +
> + if (df)
> + regs->di -= exit_bytes;
> + else
> + regs->di += exit_bytes;
> + } else {
> + if (df)
> + regs->si -= exit_bytes;
> + else
> + regs->si += exit_bytes;
> + }
> +
> + if (exit_info_1 & IOIO_REP)
> + regs->cx -= exit_info_2;
> +
> + ret = regs->cx ? ES_RETRY : ES_OK;
> +
> + } else {
> + int bits = (exit_info_1 & 0x70) >> 1;
> + u64 rax = 0;
> +
> + if (!(exit_info_1 & IOIO_TYPE_IN))
> + rax = lower_bits(regs->ax, bits);
> +
> + ghcb_set_rax(ghcb, rax);
> +
> + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
> + if (ret != ES_OK)
> + return ret;
> +
> + if (exit_info_1 & IOIO_TYPE_IN) {
> + if (!ghcb_is_valid_rax(ghcb))
> + return ES_VMM_ERROR;
> + regs->ax = lower_bits(ghcb->save.rax, bits);
> + }
> + }
> +
> + return ret;
> +}
> --
> 2.17.1
>
