VMware hypercalls use I/O port, VMCALL or VMMCALL instructions.
Add __tdx_hypercall path to support TDX guests.
No change in high bandwidth hypercalls, as only low bandwidth
ones are supported for TDX guests.
Co-developed-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Alexey Makhalov <alexey.makhalov@broadcom.com>
---
arch/x86/include/asm/vmware.h | 45 +++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/vmware.c | 51 +++++++++++++++++++++++++++++++++++
2 files changed, 96 insertions(+)
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index d83444f03969..c9cf43d5ef23 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -18,6 +18,12 @@
* arg2 - Hypercall command
* arg3 bits [15:0] - Port number, LB and direction flags
*
+ * - Low bandwidth TDX hypercalls (x86_64 only) are similar to LB
+ * hypercalls. They also have up to 6 input and 6 output on registers
+ * arguments, with different argument to register mapping:
+ * %r12 (arg0), %rbx (arg1), %r13 (arg2), %rdx (arg3),
+ * %rsi (arg4), %rdi (arg5).
+ *
* - High bandwidth (HB) hypercalls are I/O port based only. They have
* up to 7 input and 7 output arguments passed and returned using
* registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
@@ -54,6 +60,12 @@
#define VMWARE_CMD_GETHZ 45
#define VMWARE_CMD_GETVCPU_INFO 68
#define VMWARE_CMD_STEALCLOCK 91
+/*
+ * Hypercall command mask:
+ * bits [6:0] command, range [0, 127]
+ * bits [19:16] sub-command, range [0, 15]
+ */
+#define VMWARE_CMD_MASK 0xf007fU
#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
@@ -64,6 +76,15 @@ extern unsigned long vmware_hypercall_slow(unsigned long cmd,
u32 *out1, u32 *out2, u32 *out3,
u32 *out4, u32 *out5);
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC 1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5);
+
/*
* The low bandwidth call. The low word of %edx is presumed to have OUT bit
* set. The high word of %edx may contain input data from the caller.
@@ -79,6 +100,10 @@ unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ NULL, NULL, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
NULL, NULL, NULL, NULL, NULL);
@@ -100,6 +125,10 @@ unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, NULL, NULL, NULL);
@@ -121,6 +150,10 @@ unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, out3, NULL, NULL);
@@ -143,6 +176,10 @@ unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ NULL, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
NULL, out2, NULL, NULL, NULL);
@@ -167,6 +204,10 @@ unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, 0, 0,
+ NULL, out2, out3, out4, out5);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, 0, 0,
NULL, out2, out3, out4, out5);
@@ -191,6 +232,10 @@ unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
out1, out2, out3, NULL, NULL);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index d24ba03b30b8..708048b8a095 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -477,6 +477,57 @@ static bool __init vmware_legacy_x2apic_available(void)
(eax & GETVCPU_INFO_LEGACY_X2APIC);
}
+#ifdef CONFIG_INTEL_TDX_GUEST
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5)
+{
+ struct tdx_module_args args;
+
+ if (!hypervisor_is_type(X86_HYPER_VMWARE)) {
+ pr_warn_once("Incorrect usage\n");
+ return ULONG_MAX;
+ }
+
+ if (cmd & ~VMWARE_CMD_MASK) {
+ pr_warn_once("Out of range command %lx\n", cmd);
+ return ULONG_MAX;
+ }
+
+ args.rbx = in1;
+ args.rdx = in3;
+ args.rsi = in4;
+ args.rdi = in5;
+ args.r10 = VMWARE_TDX_VENDOR_LEAF;
+ args.r11 = VMWARE_TDX_HCALL_FUNC;
+ args.r12 = VMWARE_HYPERVISOR_MAGIC;
+ args.r13 = cmd;
+ args.r15 = 0; /* CPL */
+
+ __tdx_hypercall(&args);
+
+ if (out1)
+ *out1 = args.rbx;
+ if (out2)
+ *out2 = args.r13;
+ if (out3)
+ *out3 = args.rdx;
+ if (out4)
+ *out4 = args.rsi;
+ if (out5)
+ *out5 = args.rdi;
+
+ return args.r12;
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall);
+#endif
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb,
struct pt_regs *regs)
--
2.39.4On 6/13/24 12:16, Alexey Makhalov wrote:
> +unsigned long vmware_tdx_hypercall(unsigned long cmd,
> + unsigned long in1, unsigned long in3,
> + unsigned long in4, unsigned long in5,
> + u32 *out1, u32 *out2, u32 *out3,
> + u32 *out4, u32 *out5)
> +{
> + struct tdx_module_args args;
> +
> + if (!hypervisor_is_type(X86_HYPER_VMWARE)) {
> + pr_warn_once("Incorrect usage\n");
> + return ULONG_MAX;
> + }
> +
> + if (cmd & ~VMWARE_CMD_MASK) {
> + pr_warn_once("Out of range command %lx\n", cmd);
> + return ULONG_MAX;
> + }
> +
> + args.rbx = in1;
> + args.rdx = in3;
> + args.rsi = in4;
> + args.rdi = in5;
> + args.r10 = VMWARE_TDX_VENDOR_LEAF;
> + args.r11 = VMWARE_TDX_HCALL_FUNC;
> + args.r12 = VMWARE_HYPERVISOR_MAGIC;
> + args.r13 = cmd;
> + args.r15 = 0; /* CPL */
I believe this leaks stack data into the hypervisor. Or did I miss the
zeroing of rcx/r8/r9/r14?
You need to zero out all of 'args' somehow.
On Fri, Jun 14, 2024 at 09:03:22AM -0700, Dave Hansen wrote:
> On 6/13/24 12:16, Alexey Makhalov wrote:
> > +unsigned long vmware_tdx_hypercall(unsigned long cmd,
> > + unsigned long in1, unsigned long in3,
> > + unsigned long in4, unsigned long in5,
> > + u32 *out1, u32 *out2, u32 *out3,
> > + u32 *out4, u32 *out5)
> > +{
> > + struct tdx_module_args args;
> > +
> > + if (!hypervisor_is_type(X86_HYPER_VMWARE)) {
> > + pr_warn_once("Incorrect usage\n");
> > + return ULONG_MAX;
> > + }
> > +
> > + if (cmd & ~VMWARE_CMD_MASK) {
> > + pr_warn_once("Out of range command %lx\n", cmd);
> > + return ULONG_MAX;
> > + }
> > +
> > + args.rbx = in1;
> > + args.rdx = in3;
> > + args.rsi = in4;
> > + args.rdi = in5;
> > + args.r10 = VMWARE_TDX_VENDOR_LEAF;
> > + args.r11 = VMWARE_TDX_HCALL_FUNC;
> > + args.r12 = VMWARE_HYPERVISOR_MAGIC;
> > + args.r13 = cmd;
> > + args.r15 = 0; /* CPL */
>
> I believe this leaks stack data into the hypervisor. Or did I miss the
> zeroing of rcx/r8/r9/r14?
>
> You need to zero out all of 'args' somehow.
You mean like this:
struct tdx_module_args args = {};
?
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
On 6/14/24 09:14, Borislav Petkov wrote:
> On Fri, Jun 14, 2024 at 09:03:22AM -0700, Dave Hansen wrote:
...
>> You need to zero out all of 'args' somehow.
>
> You mean like this:
>
> struct tdx_module_args args = {};
>
> ?
Yes, or do all the assignments with the initializer. We seem to do it
both ways, so whatever works.
On 6/14/24 9:19 AM, Dave Hansen wrote:
> On 6/14/24 09:14, Borislav Petkov wrote:
>> On Fri, Jun 14, 2024 at 09:03:22AM -0700, Dave Hansen wrote:
> ...
>>> You need to zero out all of 'args' somehow.
>>
>> You mean like this:
>>
>> struct tdx_module_args args = {};
>>
>> ?
>
> Yes, or do all the assignments with the initializer. We seem to do it
> both ways, so whatever works.
Thanks Dave for pointing that out. I missed that at v7.
On Fri, Jun 14, 2024 at 11:32:16AM -0700, Alexey Makhalov wrote:
>
>
> On 6/14/24 9:19 AM, Dave Hansen wrote:
> > On 6/14/24 09:14, Borislav Petkov wrote:
> > > On Fri, Jun 14, 2024 at 09:03:22AM -0700, Dave Hansen wrote:
> > ...
> > > > You need to zero out all of 'args' somehow.
> > >
> > > You mean like this:
> > >
> > > struct tdx_module_args args = {};
> > >
> > > ?
> >
> > Yes, or do all the assignments with the initializer. We seem to do it
> > both ways, so whatever works.
>
> Thanks Dave for pointing that out. I missed that at v7.
Ok, I'll fold this struct initialization oneliner into the last patch.
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
On 6/14/24 12:09 PM, Borislav Petkov wrote:
> On Fri, Jun 14, 2024 at 11:32:16AM -0700, Alexey Makhalov wrote:
>>
>>
>> On 6/14/24 9:19 AM, Dave Hansen wrote:
>>> On 6/14/24 09:14, Borislav Petkov wrote:
>>>> On Fri, Jun 14, 2024 at 09:03:22AM -0700, Dave Hansen wrote:
>>> ...
>>>>> You need to zero out all of 'args' somehow.
>>>>
>>>> You mean like this:
>>>>
>>>> struct tdx_module_args args = {};
>>>>
>>>> ?
>>>
>>> Yes, or do all the assignments with the initializer. We seem to do it
>>> both ways, so whatever works.
>>
>> Thanks Dave for pointing that out. I missed that at v7.
>
> Ok, I'll fold this struct initialization oneliner into the last patch.
>
Thanks!
The following commit has been merged into the x86/vmware branch of tip:
Commit-ID: 57b7b6acb41b51087ceb40c562efe392ec8c9677
Gitweb: https://git.kernel.org/tip/57b7b6acb41b51087ceb40c562efe392ec8c9677
Author: Alexey Makhalov <alexey.makhalov@broadcom.com>
AuthorDate: Thu, 13 Jun 2024 12:16:50 -07:00
Committer: Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Tue, 25 Jun 2024 17:15:48 +02:00
x86/vmware: Add TDX hypercall support
VMware hypercalls use I/O port, VMCALL or VMMCALL instructions. Add a call to
__tdx_hypercall() in order to support TDX guests.
No change in high bandwidth hypercalls, as only low bandwidth ones are supported
for TDX guests.
[ bp: Massage, clear on-stack struct tdx_module_args variable. ]
Co-developed-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Alexey Makhalov <alexey.makhalov@broadcom.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240613191650.9913-9-alexey.makhalov@broadcom.com
---
arch/x86/include/asm/vmware.h | 45 +++++++++++++++++++++++++++++-
arch/x86/kernel/cpu/vmware.c | 52 ++++++++++++++++++++++++++++++++++-
2 files changed, 97 insertions(+)
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index d83444f..c9cf43d 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -18,6 +18,12 @@
* arg2 - Hypercall command
* arg3 bits [15:0] - Port number, LB and direction flags
*
+ * - Low bandwidth TDX hypercalls (x86_64 only) are similar to LB
+ * hypercalls. They also have up to 6 input and 6 output on registers
+ * arguments, with different argument to register mapping:
+ * %r12 (arg0), %rbx (arg1), %r13 (arg2), %rdx (arg3),
+ * %rsi (arg4), %rdi (arg5).
+ *
* - High bandwidth (HB) hypercalls are I/O port based only. They have
* up to 7 input and 7 output arguments passed and returned using
* registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
@@ -54,6 +60,12 @@
#define VMWARE_CMD_GETHZ 45
#define VMWARE_CMD_GETVCPU_INFO 68
#define VMWARE_CMD_STEALCLOCK 91
+/*
+ * Hypercall command mask:
+ * bits [6:0] command, range [0, 127]
+ * bits [19:16] sub-command, range [0, 15]
+ */
+#define VMWARE_CMD_MASK 0xf007fU
#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
@@ -64,6 +76,15 @@ extern unsigned long vmware_hypercall_slow(unsigned long cmd,
u32 *out1, u32 *out2, u32 *out3,
u32 *out4, u32 *out5);
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC 1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5);
+
/*
* The low bandwidth call. The low word of %edx is presumed to have OUT bit
* set. The high word of %edx may contain input data from the caller.
@@ -79,6 +100,10 @@ unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ NULL, NULL, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
NULL, NULL, NULL, NULL, NULL);
@@ -100,6 +125,10 @@ unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, NULL, NULL, NULL);
@@ -121,6 +150,10 @@ unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, out3, NULL, NULL);
@@ -143,6 +176,10 @@ unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ NULL, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
NULL, out2, NULL, NULL, NULL);
@@ -167,6 +204,10 @@ unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, 0, 0,
+ NULL, out2, out3, out4, out5);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, 0, 0,
NULL, out2, out3, out4, out5);
@@ -191,6 +232,10 @@ unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
out1, out2, out3, NULL, NULL);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index fc1b3f6..00189cd 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -489,6 +489,58 @@ static bool __init vmware_legacy_x2apic_available(void)
(eax & GETVCPU_INFO_LEGACY_X2APIC);
}
+#ifdef CONFIG_INTEL_TDX_GUEST
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5)
+{
+ struct tdx_module_args args = {};
+
+ if (!hypervisor_is_type(X86_HYPER_VMWARE)) {
+ pr_warn_once("Incorrect usage\n");
+ return ULONG_MAX;
+ }
+
+ if (cmd & ~VMWARE_CMD_MASK) {
+ pr_warn_once("Out of range command %lx\n", cmd);
+ return ULONG_MAX;
+ }
+
+ args.rbx = in1;
+ args.rdx = in3;
+ args.rsi = in4;
+ args.rdi = in5;
+ args.r10 = VMWARE_TDX_VENDOR_LEAF;
+ args.r11 = VMWARE_TDX_HCALL_FUNC;
+ args.r12 = VMWARE_HYPERVISOR_MAGIC;
+ args.r13 = cmd;
+ /* CPL */
+ args.r15 = 0;
+
+ __tdx_hypercall(&args);
+
+ if (out1)
+ *out1 = args.rbx;
+ if (out2)
+ *out2 = args.r13;
+ if (out3)
+ *out3 = args.rdx;
+ if (out4)
+ *out4 = args.rsi;
+ if (out5)
+ *out5 = args.rdi;
+
+ return args.r12;
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall);
+#endif
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb,
struct pt_regs *regs)The following commit has been merged into the x86/vmware branch of tip:
Commit-ID: f9e4b7a02b61631b964d53f7f24d2f81539cb0d3
Gitweb: https://git.kernel.org/tip/f9e4b7a02b61631b964d53f7f24d2f81539cb0d3
Author: Alexey Makhalov <alexey.makhalov@broadcom.com>
AuthorDate: Thu, 13 Jun 2024 12:16:50 -07:00
Committer: Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Mon, 24 Jun 2024 07:10:50 +02:00
x86/vmware: Add TDX hypercall support
VMware hypercalls use I/O port, VMCALL or VMMCALL instructions. Add a call to
__tdx_hypercall() in order to support TDX guests.
No change in high bandwidth hypercalls, as only low bandwidth ones are supported
for TDX guests.
[ bp: Massage, clear on-stack struct tdx_module_args variable. ]
Co-developed-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Alexey Makhalov <alexey.makhalov@broadcom.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240613191650.9913-9-alexey.makhalov@broadcom.com
---
arch/x86/include/asm/vmware.h | 45 +++++++++++++++++++++++++++++-
arch/x86/kernel/cpu/vmware.c | 52 ++++++++++++++++++++++++++++++++++-
2 files changed, 97 insertions(+)
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index d83444f..c9cf43d 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -18,6 +18,12 @@
* arg2 - Hypercall command
* arg3 bits [15:0] - Port number, LB and direction flags
*
+ * - Low bandwidth TDX hypercalls (x86_64 only) are similar to LB
+ * hypercalls. They also have up to 6 input and 6 output on registers
+ * arguments, with different argument to register mapping:
+ * %r12 (arg0), %rbx (arg1), %r13 (arg2), %rdx (arg3),
+ * %rsi (arg4), %rdi (arg5).
+ *
* - High bandwidth (HB) hypercalls are I/O port based only. They have
* up to 7 input and 7 output arguments passed and returned using
* registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
@@ -54,6 +60,12 @@
#define VMWARE_CMD_GETHZ 45
#define VMWARE_CMD_GETVCPU_INFO 68
#define VMWARE_CMD_STEALCLOCK 91
+/*
+ * Hypercall command mask:
+ * bits [6:0] command, range [0, 127]
+ * bits [19:16] sub-command, range [0, 15]
+ */
+#define VMWARE_CMD_MASK 0xf007fU
#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
@@ -64,6 +76,15 @@ extern unsigned long vmware_hypercall_slow(unsigned long cmd,
u32 *out1, u32 *out2, u32 *out3,
u32 *out4, u32 *out5);
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC 1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5);
+
/*
* The low bandwidth call. The low word of %edx is presumed to have OUT bit
* set. The high word of %edx may contain input data from the caller.
@@ -79,6 +100,10 @@ unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ NULL, NULL, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
NULL, NULL, NULL, NULL, NULL);
@@ -100,6 +125,10 @@ unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, NULL, NULL, NULL);
@@ -121,6 +150,10 @@ unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, out3, NULL, NULL);
@@ -143,6 +176,10 @@ unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ NULL, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
NULL, out2, NULL, NULL, NULL);
@@ -167,6 +204,10 @@ unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, 0, 0,
+ NULL, out2, out3, out4, out5);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, 0, 0,
NULL, out2, out3, out4, out5);
@@ -191,6 +232,10 @@ unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
out1, out2, out3, NULL, NULL);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index d24ba03..51d3dcc 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -477,6 +477,58 @@ static bool __init vmware_legacy_x2apic_available(void)
(eax & GETVCPU_INFO_LEGACY_X2APIC);
}
+#ifdef CONFIG_INTEL_TDX_GUEST
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5)
+{
+ struct tdx_module_args args = {};
+
+ if (!hypervisor_is_type(X86_HYPER_VMWARE)) {
+ pr_warn_once("Incorrect usage\n");
+ return ULONG_MAX;
+ }
+
+ if (cmd & ~VMWARE_CMD_MASK) {
+ pr_warn_once("Out of range command %lx\n", cmd);
+ return ULONG_MAX;
+ }
+
+ args.rbx = in1;
+ args.rdx = in3;
+ args.rsi = in4;
+ args.rdi = in5;
+ args.r10 = VMWARE_TDX_VENDOR_LEAF;
+ args.r11 = VMWARE_TDX_HCALL_FUNC;
+ args.r12 = VMWARE_HYPERVISOR_MAGIC;
+ args.r13 = cmd;
+ /* CPL */
+ args.r15 = 0;
+
+ __tdx_hypercall(&args);
+
+ if (out1)
+ *out1 = args.rbx;
+ if (out2)
+ *out2 = args.r13;
+ if (out3)
+ *out3 = args.rdx;
+ if (out4)
+ *out4 = args.rsi;
+ if (out5)
+ *out5 = args.rdi;
+
+ return args.r12;
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall);
+#endif
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb,
struct pt_regs *regs)The following commit has been merged into the x86/vmware branch of tip:
Commit-ID: ef08e7dc21307b226b5280d5e8cfea687bfd2866
Gitweb: https://git.kernel.org/tip/ef08e7dc21307b226b5280d5e8cfea687bfd2866
Author: Alexey Makhalov <alexey.makhalov@broadcom.com>
AuthorDate: Thu, 13 Jun 2024 12:16:50 -07:00
Committer: Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Fri, 14 Jun 2024 21:10:49 +02:00
x86/vmware: Add TDX hypercall support
VMware hypercalls use I/O port, VMCALL or VMMCALL instructions. Add a call to
__tdx_hypercall() in order to support TDX guests.
No change in high bandwidth hypercalls, as only low bandwidth ones are supported
for TDX guests.
[ bp: Massage, clear on-stack struct tdx_module_args args; variable. ]
Co-developed-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Tim Merrifield <tim.merrifield@broadcom.com>
Signed-off-by: Alexey Makhalov <alexey.makhalov@broadcom.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240613191650.9913-9-alexey.makhalov@broadcom.com
---
arch/x86/include/asm/vmware.h | 45 +++++++++++++++++++++++++++++-
arch/x86/kernel/cpu/vmware.c | 52 ++++++++++++++++++++++++++++++++++-
2 files changed, 97 insertions(+)
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index d83444f..c9cf43d 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -18,6 +18,12 @@
* arg2 - Hypercall command
* arg3 bits [15:0] - Port number, LB and direction flags
*
+ * - Low bandwidth TDX hypercalls (x86_64 only) are similar to LB
+ * hypercalls. They also have up to 6 input and 6 output on registers
+ * arguments, with different argument to register mapping:
+ * %r12 (arg0), %rbx (arg1), %r13 (arg2), %rdx (arg3),
+ * %rsi (arg4), %rdi (arg5).
+ *
* - High bandwidth (HB) hypercalls are I/O port based only. They have
* up to 7 input and 7 output arguments passed and returned using
* registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
@@ -54,6 +60,12 @@
#define VMWARE_CMD_GETHZ 45
#define VMWARE_CMD_GETVCPU_INFO 68
#define VMWARE_CMD_STEALCLOCK 91
+/*
+ * Hypercall command mask:
+ * bits [6:0] command, range [0, 127]
+ * bits [19:16] sub-command, range [0, 15]
+ */
+#define VMWARE_CMD_MASK 0xf007fU
#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0)
#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1)
@@ -64,6 +76,15 @@ extern unsigned long vmware_hypercall_slow(unsigned long cmd,
u32 *out1, u32 *out2, u32 *out3,
u32 *out4, u32 *out5);
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC 1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5);
+
/*
* The low bandwidth call. The low word of %edx is presumed to have OUT bit
* set. The high word of %edx may contain input data from the caller.
@@ -79,6 +100,10 @@ unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ NULL, NULL, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
NULL, NULL, NULL, NULL, NULL);
@@ -100,6 +125,10 @@ unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, NULL, NULL, NULL);
@@ -121,6 +150,10 @@ unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, 0, 0, 0,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, 0, 0, 0,
out1, out2, out3, NULL, NULL);
@@ -143,6 +176,10 @@ unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ NULL, out2, NULL, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
NULL, out2, NULL, NULL, NULL);
@@ -167,6 +204,10 @@ unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, 0, 0,
+ NULL, out2, out3, out4, out5);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, 0, 0,
NULL, out2, out3, out4, out5);
@@ -191,6 +232,10 @@ unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1,
{
unsigned long out0;
+ if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return vmware_tdx_hypercall(cmd, in1, in3, in4, in5,
+ out1, out2, out3, NULL, NULL);
+
if (unlikely(!alternatives_patched) && !__is_defined(MODULE))
return vmware_hypercall_slow(cmd, in1, in3, in4, in5,
out1, out2, out3, NULL, NULL);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index d24ba03..51d3dcc 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -477,6 +477,58 @@ static bool __init vmware_legacy_x2apic_available(void)
(eax & GETVCPU_INFO_LEGACY_X2APIC);
}
+#ifdef CONFIG_INTEL_TDX_GUEST
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ unsigned long in1, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ u32 *out1, u32 *out2, u32 *out3,
+ u32 *out4, u32 *out5)
+{
+ struct tdx_module_args args = {};
+
+ if (!hypervisor_is_type(X86_HYPER_VMWARE)) {
+ pr_warn_once("Incorrect usage\n");
+ return ULONG_MAX;
+ }
+
+ if (cmd & ~VMWARE_CMD_MASK) {
+ pr_warn_once("Out of range command %lx\n", cmd);
+ return ULONG_MAX;
+ }
+
+ args.rbx = in1;
+ args.rdx = in3;
+ args.rsi = in4;
+ args.rdi = in5;
+ args.r10 = VMWARE_TDX_VENDOR_LEAF;
+ args.r11 = VMWARE_TDX_HCALL_FUNC;
+ args.r12 = VMWARE_HYPERVISOR_MAGIC;
+ args.r13 = cmd;
+ /* CPL */
+ args.r15 = 0;
+
+ __tdx_hypercall(&args);
+
+ if (out1)
+ *out1 = args.rbx;
+ if (out2)
+ *out2 = args.r13;
+ if (out3)
+ *out3 = args.rdx;
+ if (out4)
+ *out4 = args.rsi;
+ if (out5)
+ *out5 = args.rdi;
+
+ return args.r12;
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall);
+#endif
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb,
struct pt_regs *regs)© 2016 - 2025 Red Hat, Inc.