linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Joerg Roedel <joro@8bytes.org>
To: x86@kernel.org
Cc: Joerg Roedel <joro@8bytes.org>, Joerg Roedel <jroedel@suse.de>,
	hpa@zytor.com, Andy Lutomirski <luto@kernel.org>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Jiri Slaby <jslaby@suse.cz>,
	Dan Williams <dan.j.williams@intel.com>,
	Tom Lendacky <thomas.lendacky@amd.com>,
	Juergen Gross <jgross@suse.com>,
	Kees Cook <keescook@chromium.org>,
	David Rientjes <rientjes@google.com>,
	Cfir Cohen <cfir@google.com>, Erdem Aktas <erdemaktas@google.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	Mike Stunes <mstunes@vmware.com>,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Martin Radev <martin.b.radev@gmail.com>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	virtualization@lists.linux-foundation.org
Subject: [PATCH v6 53/76] x86/sev-es: Handle MMIO String Instructions
Date: Mon, 24 Aug 2020 10:54:48 +0200	[thread overview]
Message-ID: <20200824085511.7553-54-joro@8bytes.org> (raw)
In-Reply-To: <20200824085511.7553-1-joro@8bytes.org>

From: Joerg Roedel <jroedel@suse.de>

Add handling for emulation the MOVS instruction on MMIO regions, as done
by the memcpy_toio() and memcpy_fromio() functions.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20200724160336.5435-53-joro@8bytes.org
---
 arch/x86/kernel/sev-es.c | 77 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)

diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index fa1fa55fd8e3..7bfd402c74e3 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -595,6 +595,73 @@ static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb,
 	return ret;
 }
 
+/*
+ * The MOVS instruction has two memory operands, which raises the
+ * problem that it is not known whether the access to the source or the
+ * destination caused the #VC exception (and hence whether an MMIO read
+ * or write operation needs to be emulated).
+ *
+ * Instead of playing games with walking page-tables and trying to guess
+ * whether the source or destination is an MMIO range, split the move
+ * into two operations, a read and a write with only one memory operand.
+ * This will cause a nested #VC exception on the MMIO address which can
+ * then be handled.
+ *
+ * This implementation has the benefit that it also supports MOVS where
+ * source _and_ destination are MMIO regions.
+ *
+ * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
+ * rare operation. If it turns out to be a performance problem the split
+ * operations can be moved to memcpy_fromio() and memcpy_toio().
+ */
+static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
+					  unsigned int bytes)
+{
+	unsigned long ds_base, es_base;
+	unsigned char *src, *dst;
+	unsigned char buffer[8];
+	enum es_result ret;
+	bool rep;
+	int off;
+
+	ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
+	es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
+
+	if (ds_base == -1L || es_base == -1L) {
+		ctxt->fi.vector = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		return ES_EXCEPTION;
+	}
+
+	src = ds_base + (unsigned char *)ctxt->regs->si;
+	dst = es_base + (unsigned char *)ctxt->regs->di;
+
+	ret = vc_read_mem(ctxt, src, buffer, bytes);
+	if (ret != ES_OK)
+		return ret;
+
+	ret = vc_write_mem(ctxt, dst, buffer, bytes);
+	if (ret != ES_OK)
+		return ret;
+
+	if (ctxt->regs->flags & X86_EFLAGS_DF)
+		off = -bytes;
+	else
+		off =  bytes;
+
+	ctxt->regs->si += off;
+	ctxt->regs->di += off;
+
+	rep = insn_has_rep_prefix(&ctxt->insn);
+	if (rep)
+		ctxt->regs->cx -= 1;
+
+	if (!rep || ctxt->regs->cx == 0)
+		return ES_OK;
+	else
+		return ES_RETRY;
+}
+
 static enum es_result vc_handle_mmio(struct ghcb *ghcb,
 				     struct es_em_ctxt *ctxt)
 {
@@ -655,6 +722,16 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb,
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
 
+		/* MOVS instruction */
+	case 0xa4:
+		bytes = 1;
+		fallthrough;
+	case 0xa5:
+		if (!bytes)
+			bytes = insn->opnd_bytes;
+
+		ret = vc_handle_mmio_movs(ctxt, bytes);
+		break;
 		/* Two-Byte Opcodes */
 	case 0x0f:
 		ret = vc_handle_mmio_twobyte_ops(ghcb, ctxt);
-- 
2.28.0


  parent reply	other threads:[~2020-08-24  9:07 UTC|newest]

Thread overview: 116+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-24  8:53 [PATCH v6 00/76] x86: SEV-ES Guest Support Joerg Roedel
2020-08-24  8:53 ` [PATCH v6 01/76] KVM: SVM: nested: Don't allocate VMCB structures on stack Joerg Roedel
2020-08-24  8:53 ` [PATCH v6 02/76] KVM: SVM: Add GHCB definitions Joerg Roedel
2020-08-24 10:44   ` Borislav Petkov
2020-08-25  9:22     ` Joerg Roedel
2020-08-25 11:04       ` Borislav Petkov
2020-08-27 16:01         ` Arvind Sankar
2020-08-28 11:54           ` Joerg Roedel
2020-08-24  8:53 ` [PATCH v6 03/76] KVM: SVM: Add GHCB Accessor functions Joerg Roedel
2020-08-24  8:53 ` [PATCH v6 04/76] KVM: SVM: Use __packed shorthand Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 05/76] x86/cpufeatures: Add SEV-ES CPU feature Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 06/76] x86/traps: Move pf error codes to <asm/trap_pf.h> Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 07/76] x86/insn: Make inat-tables.c suitable for pre-decompression code Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 08/76] x86/umip: Factor out instruction fetch Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 09/76] x86/umip: Factor out instruction decoding Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 10/76] x86/insn: Add insn_get_modrm_reg_off() Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 11/76] x86/insn: Add insn_has_rep_prefix() helper Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 12/76] x86/boot/compressed/64: Disable red-zone usage Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 13/76] x86/boot/compressed/64: Add IDT Infrastructure Joerg Roedel
2020-08-27 15:26   ` Arvind Sankar
2020-08-28 12:12     ` Joerg Roedel
2020-08-28 15:09       ` Arvind Sankar
2020-08-24  8:54 ` [PATCH v6 14/76] x86/boot/compressed/64: Rename kaslr_64.c to ident_map_64.c Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 15/76] x86/boot/compressed/64: Add page-fault handler Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 16/76] x86/boot/compressed/64: Always switch to own page-table Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 17/76] x86/boot/compressed/64: Don't pre-map memory in KASLR code Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 18/76] x86/boot/compressed/64: Change add_identity_map() to take start and end Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 19/76] x86/boot/compressed/64: Add stage1 #VC handler Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 20/76] x86/boot/compressed/64: Call set_sev_encryption_mask earlier Joerg Roedel
2020-08-27  9:36   ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 21/76] x86/boot/compressed/64: Check return value of kernel_ident_mapping_init() Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 22/76] x86/boot/compressed/64: Add set_page_en/decrypted() helpers Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 23/76] x86/boot/compressed/64: Setup GHCB Based VC Exception handler Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 24/76] x86/boot/compressed/64: Unmap GHCB page before booting the kernel Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 25/76] x86/sev-es: Add support for handling IOIO exceptions Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 26/76] x86/fpu: Move xgetbv()/xsetbv() into separate header Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 27/76] x86/sev-es: Add CPUID handling to #VC handler Joerg Roedel
2020-08-27 22:48   ` Arvind Sankar
2020-08-28 12:33     ` Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 28/76] x86/idt: Move IDT to data segment Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 29/76] x86/idt: Split idt_data setup out of set_intr_gate() Joerg Roedel
2020-08-28 15:16   ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 30/76] x86/head/64: Install startup GDT Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 31/76] x86/head/64: Setup MSR_GS_BASE before calling into C code Joerg Roedel
2020-08-28 18:13   ` Borislav Petkov
2020-09-01 12:09     ` Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 32/76] x86/head/64: Load GDT after switch to virtual addresses Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 33/76] x86/head/64: Load segment registers earlier Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 34/76] x86/head/64: Switch to initial stack earlier Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 35/76] x86/head/64: Make fixup_pointer() static inline Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 36/76] x86/head/64: Load IDT earlier Joerg Roedel
2020-08-29 10:24   ` Borislav Petkov
2020-09-01 12:13     ` Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 37/76] x86/head/64: Move early exception dispatch to C code Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 38/76] x86/head/64: Set CR4.FSGSBASE early Joerg Roedel
2020-08-29 15:55   ` Borislav Petkov
2020-08-31  8:58     ` Joerg Roedel
2020-08-31  9:26       ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 39/76] x86/sev-es: Add SEV-ES Feature Detection Joerg Roedel
2020-08-29 16:25   ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 40/76] x86/sev-es: Print SEV-ES info into kernel log Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 41/76] x86/sev-es: Compile early handler code into kernel image Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 42/76] x86/sev-es: Setup early #VC handler Joerg Roedel
2020-08-31  9:45   ` Borislav Petkov
2020-09-01 12:59     ` Joerg Roedel
2020-09-01 13:35       ` Borislav Petkov
2021-09-04  9:39   ` Lai Jiangshan
2021-09-06  5:07     ` Juergen Gross
2020-08-24  8:54 ` [PATCH v6 43/76] x86/sev-es: Setup GHCB based boot " Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 44/76] x86/sev-es: Setup per-cpu GHCBs for the runtime handler Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 45/76] x86/sev-es: Allocate and Map IST stack for #VC handler Joerg Roedel
2020-08-31 10:27   ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 46/76] x86/sev-es: Adjust #VC IST Stack on entering NMI handler Joerg Roedel
2020-08-31 11:05   ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 47/76] x86/dumpstack/64: Add noinstr version of get_stack_info() Joerg Roedel
2020-08-31 11:11   ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 48/76] x86/entry/64: Add entry code for #VC handler Joerg Roedel
2020-08-31 11:30   ` Borislav Petkov
2020-09-01 13:29     ` Joerg Roedel
2020-08-31 17:30   ` Borislav Petkov
2020-08-24  8:54 ` [PATCH v6 49/76] x86/sev-es: Add Runtime #VC Exception Handler Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 50/76] x86/sev-es: Wire up existing #VC exit-code handlers Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 51/76] x86/sev-es: Handle instruction fetches from user-space Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 52/76] x86/sev-es: Handle MMIO events Joerg Roedel
2020-08-31 15:47   ` Borislav Petkov
2020-08-24  8:54 ` Joerg Roedel [this message]
2020-08-24  8:54 ` [PATCH v6 54/76] x86/sev-es: Handle MSR events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 55/76] x86/sev-es: Handle DR7 read/write events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 56/76] x86/sev-es: Handle WBINVD Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 57/76] x86/sev-es: Handle RDTSC(P) Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 58/76] x86/sev-es: Handle RDPMC Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 59/76] x86/sev-es: Handle INVD Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 60/76] x86/sev-es: Handle MONITOR/MONITORX Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 61/76] x86/sev-es: Handle MWAIT/MWAITX Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 62/76] x86/sev-es: Handle VMMCALL Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 63/76] x86/sev-es: Handle #AC Events Joerg Roedel
2020-08-24  8:54 ` [PATCH v6 64/76] x86/sev-es: Handle #DB Events Joerg Roedel
2020-08-31 16:19   ` Borislav Petkov
2020-08-24  8:55 ` [PATCH v6 65/76] x86/paravirt: Allow hypervisor specific VMMCALL handling under SEV-ES Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 66/76] x86/kvm: Add KVM " Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 67/76] x86/vmware: Add VMware specific handling for VMMCALL " Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 68/76] x86/realmode: Add SEV-ES specific trampoline entry point Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 69/76] x86/realmode: Setup AP jump table Joerg Roedel
2020-08-31 17:09   ` Borislav Petkov
2020-09-01 13:55     ` Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 70/76] x86/smpboot: Setup TSS for starting AP Joerg Roedel
2020-08-31 17:25   ` Borislav Petkov
2020-08-24  8:55 ` [PATCH v6 71/76] x86/head/64: Don't call verify_cpu() on starting APs Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 72/76] x86/head/64: Rename start_cpu0 Joerg Roedel
2020-08-31 17:29   ` Borislav Petkov
2020-08-24  8:55 ` [PATCH v6 73/76] x86/sev-es: Support CPU offline/online Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 74/76] x86/sev-es: Handle NMI State Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 75/76] x86/efi: Add GHCB mappings when SEV-ES is active Joerg Roedel
2020-08-24  8:55 ` [PATCH v6 76/76] x86/sev-es: Check required CPU features for SEV-ES Joerg Roedel
2020-08-25  0:21 ` [PATCH v6 00/76] x86: SEV-ES Guest Support Mike Stunes
2020-08-25  6:24   ` Joerg Roedel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200824085511.7553-54-joro@8bytes.org \
    --to=joro@8bytes.org \
    --cc=cfir@google.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=erdemaktas@google.com \
    --cc=hpa@zytor.com \
    --cc=jgross@suse.com \
    --cc=jroedel@suse.de \
    --cc=jslaby@suse.cz \
    --cc=keescook@chromium.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=martin.b.radev@gmail.com \
    --cc=mhiramat@kernel.org \
    --cc=mstunes@vmware.com \
    --cc=peterz@infradead.org \
    --cc=rientjes@google.com \
    --cc=sean.j.christopherson@intel.com \
    --cc=thomas.lendacky@amd.com \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).