From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
To: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Peter Zijlstra <peterz@infradead.org>,
Andy Lutomirski <luto@kernel.org>
Cc: Peter H Anvin <hpa@zytor.com>,
Dave Hansen <dave.hansen@intel.com>,
Tony Luck <tony.luck@intel.com>,
Dan Williams <dan.j.williams@intel.com>,
Andi Kleen <ak@linux.intel.com>,
Kirill Shutemov <kirill.shutemov@linux.intel.com>,
Kuppuswamy Sathyanarayanan <knsathya@kernel.org>,
Sean Christopherson <seanjc@google.com>,
Kuppuswamy Sathyanarayanan
<sathyanarayanan.kuppuswamy@linux.intel.com>,
linux-kernel@vger.kernel.org, x86@kernel.org
Subject: [PATCH v1 07/11] x86/traps: Add #VE support for TDX guest
Date: Tue, 1 Jun 2021 19:21:32 -0700 [thread overview]
Message-ID: <20210602022136.2186759-8-sathyanarayanan.kuppuswamy@linux.intel.com> (raw)
In-Reply-To: <20210602022136.2186759-1-sathyanarayanan.kuppuswamy@linux.intel.com>
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Virtualization Exceptions (#VE) are delivered to TDX guests due to
specific guest actions which may happen in either user space or the kernel:
* Specific instructions (WBINVD, for example)
* Specific MSR accesses
* Specific CPUID leaf accesses
* Access to TD-shared memory, which includes MMIO
In the settings that Linux will run in, virtual exceptions are never
generated on accesses to normal, TD-private memory that has been
accepted.
The entry paths do not access TD-shared memory, MMIO regions or use
those specific MSRs, instructions, CPUID leaves that might generate #VE.
In addition, all interrupts including NMIs are blocked by the hardware
starting with #VE delivery until TDGETVEINFO is called. This eliminates
the chance of a #VE during the syscall gap or paranoid entry paths and
simplifies #VE handling.
After TDGETVEINFO #VE could happen in theory (e.g. through an NMI),
but it is expected not to happen because TDX expects NMIs not to
trigger #VEs. Another case where they could happen is if the #VE
exception panics, but in this case there are no guarantees on anything
anyways.
If a guest kernel action which would normally cause a #VE occurs in the
interrupt-disabled region before TDGETVEINFO, a #DF is delivered to the
guest which will result in an oops (and should eventually be a panic, as
we would like to set panic_on_oops to 1 for TDX guests).
Add basic infrastructure to handle any #VE which occurs in the kernel or
userspace. Later patches will add handling for specific #VE scenarios.
Convert unhandled #VE's (everything, until later in this series) so that
they appear just like a #GP by calling ve_raise_fault() directly.
ve_raise_fault() is similar to #GP handler and is responsible for
sending SIGSEGV to userspace and cpu die and notifying debuggers and
other die chain users.
Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
---
arch/x86/include/asm/idtentry.h | 4 ++
arch/x86/include/asm/tdx.h | 19 +++++++++
arch/x86/kernel/idt.c | 6 +++
arch/x86/kernel/tdx.c | 36 +++++++++++++++++
arch/x86/kernel/traps.c | 69 +++++++++++++++++++++++++++++++++
5 files changed, 134 insertions(+)
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 73d45b0dfff2..d3c779abbc78 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -634,6 +634,10 @@ DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback);
DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap);
#endif
+#ifdef CONFIG_INTEL_TDX_GUEST
+DECLARE_IDTENTRY(X86_TRAP_VE, exc_virtualization_exception);
+#endif
+
/* Device interrupts common/spurious */
DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, common_interrupt);
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index fcd42119a287..f00008cf1361 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -39,6 +39,25 @@ struct tdx_hypercall_output {
u64 r15;
};
+/*
+ * Used by #VE exception handler to gather the #VE exception
+ * info from the TDX module. This is software only structure
+ * and not related to TDX module/VMM.
+ */
+struct ve_info {
+ u64 exit_reason;
+ u64 exit_qual;
+ u64 gla; /* Guest Linear (virtual) Address */
+ u64 gpa; /* Guest Physical (virtual) Address */
+ u32 instr_len;
+ u32 instr_info;
+};
+
+unsigned long tdg_get_ve_info(struct ve_info *ve);
+
+int tdg_handle_virtualization_exception(struct pt_regs *regs,
+ struct ve_info *ve);
+
/* Common API to check TDX support in decompression and common kernel code. */
bool is_tdx_guest(void);
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index d552f177eca0..39390761d9c8 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -64,6 +64,9 @@ static const __initconst struct idt_data early_idts[] = {
*/
INTG(X86_TRAP_PF, asm_exc_page_fault),
#endif
+#ifdef CONFIG_INTEL_TDX_GUEST
+ INTG(X86_TRAP_VE, asm_exc_virtualization_exception),
+#endif
};
/*
@@ -87,6 +90,9 @@ static const __initconst struct idt_data def_idts[] = {
INTG(X86_TRAP_MF, asm_exc_coprocessor_error),
INTG(X86_TRAP_AC, asm_exc_alignment_check),
INTG(X86_TRAP_XF, asm_exc_simd_coprocessor_error),
+#ifdef CONFIG_INTEL_TDX_GUEST
+ INTG(X86_TRAP_VE, asm_exc_virtualization_exception),
+#endif
#ifdef CONFIG_X86_32
TSKG(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS),
diff --git a/arch/x86/kernel/tdx.c b/arch/x86/kernel/tdx.c
index e4383b416ef3..527d2638ddae 100644
--- a/arch/x86/kernel/tdx.c
+++ b/arch/x86/kernel/tdx.c
@@ -10,6 +10,7 @@
/* TDX Module call Leaf IDs */
#define TDINFO 1
+#define TDGETVEINFO 3
static struct {
unsigned int gpa_width;
@@ -87,6 +88,41 @@ static void tdg_get_info(void)
td_info.attributes = out.rdx;
}
+unsigned long tdg_get_ve_info(struct ve_info *ve)
+{
+ u64 ret;
+ struct tdx_module_output out = {0};
+
+ /*
+ * NMIs and machine checks are suppressed. Before this point any
+ * #VE is fatal. After this point (TDGETVEINFO call), NMIs and
+ * additional #VEs are permitted (but we don't expect them to
+ * happen unless you panic).
+ */
+ ret = __tdx_module_call(TDGETVEINFO, 0, 0, 0, 0, &out);
+
+ ve->exit_reason = out.rcx;
+ ve->exit_qual = out.rdx;
+ ve->gla = out.r8;
+ ve->gpa = out.r9;
+ ve->instr_len = out.r10 & UINT_MAX;
+ ve->instr_info = out.r10 >> 32;
+
+ return ret;
+}
+
+int tdg_handle_virtualization_exception(struct pt_regs *regs,
+ struct ve_info *ve)
+{
+ /*
+ * TODO: Add handler support for various #VE exit
+ * reasons. It will be added by other patches in
+ * the series.
+ */
+ pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
+ return -EFAULT;
+}
+
void __init tdx_early_init(void)
{
if (!cpuid_has_tdx_guest())
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 853ea7a80806..d860fdee9cfe 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -61,6 +61,7 @@
#include <asm/insn.h>
#include <asm/insn-eval.h>
#include <asm/vdso.h>
+#include <asm/tdx.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -1139,6 +1140,74 @@ DEFINE_IDTENTRY(exc_device_not_available)
}
}
+#define VEFSTR "VE fault"
+static void ve_raise_fault(struct pt_regs *regs, long error_code)
+{
+ struct task_struct *tsk = current;
+
+ if (user_mode(regs)) {
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_nr = X86_TRAP_VE;
+
+ /*
+ * Not fixing up VDSO exceptions similar to #GP handler
+ * because we don't expect the VDSO to trigger #VE.
+ */
+ show_signal(tsk, SIGSEGV, "", VEFSTR, regs, error_code);
+ force_sig(SIGSEGV);
+ return;
+ }
+
+ if (fixup_exception(regs, X86_TRAP_VE, error_code, 0))
+ return;
+
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_nr = X86_TRAP_VE;
+
+ /*
+ * To be potentially processing a kprobe fault and to trust the result
+ * from kprobe_running(), we have to be non-preemptible.
+ */
+ if (!preemptible() &&
+ kprobe_running() &&
+ kprobe_fault_handler(regs, X86_TRAP_VE))
+ return;
+
+ notify_die(DIE_GPF, VEFSTR, regs, error_code, X86_TRAP_VE, SIGSEGV);
+
+ die_addr(VEFSTR, regs, error_code, 0);
+}
+
+#ifdef CONFIG_INTEL_TDX_GUEST
+DEFINE_IDTENTRY(exc_virtualization_exception)
+{
+ struct ve_info ve;
+ int ret;
+
+ RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+
+ /*
+ * NMIs/Machine-checks/Interrupts will be in a disabled state
+ * till TDGETVEINFO TDCALL is executed. This prevents #VE
+ * nesting issue.
+ */
+ ret = tdg_get_ve_info(&ve);
+
+ cond_local_irq_enable(regs);
+
+ if (!ret)
+ ret = tdg_handle_virtualization_exception(regs, &ve);
+ /*
+ * If tdg_handle_virtualization_exception() could not process
+ * it successfully, treat it as #GP(0) and handle it.
+ */
+ if (ret)
+ ve_raise_fault(regs, 0);
+
+ cond_local_irq_disable(regs);
+}
+#endif
+
#ifdef CONFIG_X86_32
DEFINE_IDTENTRY_SW(iret_error)
{
--
2.25.1
next prev parent reply other threads:[~2021-06-02 2:22 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-02 2:21 [PATCH v1 00/11] Add TDX Guest Support (Initial support) Kuppuswamy Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 01/11] x86/paravirt: Move halt paravirt calls under CONFIG_PARAVIRT Kuppuswamy Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 02/11] x86/tdx: Introduce INTEL_TDX_GUEST config option Kuppuswamy Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 03/11] x86/cpufeatures: Add TDX Guest CPU feature Kuppuswamy Sathyanarayanan
2021-06-07 14:32 ` Tom Lendacky
2021-06-07 16:59 ` Kuppuswamy, Sathyanarayanan
2021-06-10 12:28 ` Borislav Petkov
2021-06-10 14:28 ` Kuppuswamy, Sathyanarayanan
2021-06-10 14:29 ` Kirill A. Shutemov
2021-06-10 14:35 ` Borislav Petkov
2021-06-10 14:41 ` Kirill A. Shutemov
2021-06-10 15:56 ` Borislav Petkov
2021-06-12 21:02 ` [PATCH v2 03/12] " Kuppuswamy Sathyanarayanan
2021-06-16 9:52 ` Borislav Petkov
2021-06-16 16:57 ` Kuppuswamy, Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 04/11] x86/x86: Add is_tdx_guest() interface Kuppuswamy Sathyanarayanan
2021-06-10 19:59 ` Borislav Petkov
2021-06-10 21:01 ` Kuppuswamy, Sathyanarayanan
2021-06-10 21:07 ` Borislav Petkov
2021-06-12 21:04 ` [PATCH v2 04/12] x86/x86: Add early_is_tdx_guest() interface Kuppuswamy Sathyanarayanan
2021-06-17 17:05 ` Borislav Petkov
2021-06-18 19:14 ` Kuppuswamy, Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 05/11] x86/tdx: Add __tdx_module_call() and __tdx_hypercall() helper functions Kuppuswamy Sathyanarayanan
2021-06-14 8:47 ` Borislav Petkov
2021-06-14 19:45 ` Kuppuswamy, Sathyanarayanan
2021-06-14 20:11 ` Borislav Petkov
2021-06-14 21:37 ` Kuppuswamy, Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 06/11] x86/tdx: Get TD execution environment information via TDINFO Kuppuswamy Sathyanarayanan
2021-06-02 2:21 ` Kuppuswamy Sathyanarayanan [this message]
2021-06-02 2:21 ` [PATCH v1 08/11] x86/tdx: Add HLT support for TDX guest Kuppuswamy Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 09/11] x86/tdx: Wire up KVM hypercalls Kuppuswamy Sathyanarayanan
2021-06-12 21:08 ` [PATCH v2 10/12] " Kuppuswamy Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 10/11] x86/tdx: Add MSR support for TDX guest Kuppuswamy Sathyanarayanan
2021-06-02 2:21 ` [PATCH v1 11/11] x86/tdx: Handle CPUID via #VE Kuppuswamy Sathyanarayanan
-- strict thread matches above, loose matches on Subject: below --
2021-06-02 2:18 [PATCH v1 00/11] Add TDX Guest Support (Initial support) Kuppuswamy Sathyanarayanan
2021-06-02 2:18 ` [PATCH v1 07/11] x86/traps: Add #VE support for TDX guest Kuppuswamy Sathyanarayanan
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=20210602022136.2186759-8-sathyanarayanan.kuppuswamy@linux.intel.com \
--to=sathyanarayanan.kuppuswamy@linux.intel.com \
--cc=ak@linux.intel.com \
--cc=bp@alien8.de \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=hpa@zytor.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=knsathya@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.