[PATCH v10 7/8] x86/vmware: Remove legacy VMWARE_HYPERCALL* macros

[Alexey Makhalov]

No more direct use of these macros should be allowed.
vmware_hypercallX api still use new implementation of VMWARE_HYPERCALL
macro internally, but it is not exposed outside of the vmware.h.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 26 --
 1 file changed, 26 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 5114f4c75c54..78567920b23f 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -274,30 +274,4 @@ unsigned long vmware_hypercall_hb_in(unsigned long cmd, 
unsigned long in2,
 #undef VMW_BP_CONSTRAINT
 #undef VMWARE_HYPERCALL
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
-/*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
- */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
-/*
- * The high bandwidth in call. The low word of edx is presumed to have the
- * HB bit set.
- */
-#define VMWARE_HYPERCALL_HB_IN \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep insb",   \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
 #endif
-- 
2.39.0

[PATCH v10 8/8] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
---
 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 78567920b23f..e9acce119be0 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),
@@ -54,12 +60,27 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#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.
@@ -88,6 +109,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -106,6 +131,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -124,6 +153,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -164,6 +201,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2), "=d" (*out3), "=S" (*out4),
  "=D" (*out5)
@@ -185,6 +226,10 @@ unsigned long vmware_hypercall7(unsig

[PATCH v10 6/8] x86/vmware: Correct macro names

[Alexey Makhalov]

VCPU_RESERVED and LEGACY_X2APIC are not VMware hypercall commands.
These are bits in return value of VMWARE_CMD_GETVCPU_INFO command.
Change VMWARE_CMD_ prefix to GETVCPU_INFO_ one. And move bit-shift
operation to the macro body.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/kernel/cpu/vmware.c | 8 
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 6796425eaaa1..58442c2581e7 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -42,8 +42,8 @@
 #define CPUID_VMWARE_INFO_LEAF   0x4000
 #define CPUID_VMWARE_FEATURES_LEAF   0x4010
 
-#define VMWARE_CMD_LEGACY_X2APIC  3
-#define VMWARE_CMD_VCPU_RESERVED 31
+#define GETVCPU_INFO_LEGACY_X2APIC   BIT(3)
+#define GETVCPU_INFO_VCPU_RESERVED   BIT(31)
 
 #define STEALCLOCK_NOT_AVAILABLE (-1)
 #define STEALCLOCK_DISABLED0
@@ -424,8 +424,8 @@ static bool __init vmware_legacy_x2apic_available(void)
u32 eax;
 
eax = vmware_hypercall1(VMWARE_CMD_GETVCPU_INFO, 0);
-   return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) &&
-   (eax & BIT(VMWARE_CMD_LEGACY_X2APIC));
+   return !(eax & GETVCPU_INFO_VCPU_RESERVED) &&
+   (eax & GETVCPU_INFO_LEGACY_X2APIC);
 }
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
-- 
2.39.0

[PATCH v10 4/8] drm/vmwgfx: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 196 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 3 files changed, 196 insertions(+), 358 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SENDPAYLOAD << 16),
+ word, channe

[PATCH v10 3/8] input/vmmouse: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
---
 drivers/input/mouse/vmmouse.c | 76 ++-
 1 file changed, 22 insertions(+), 54 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ea9eff7c8099..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,28 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -145,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -172,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -247,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -271,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 
/*
 * Try enabling the device. If successful, we should be able to
 * read valid version ID back from it.
 */
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_ENABLE,
-  

[PATCH v10 2/8] ptp/vmware: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
---
 drivers/ptp/ptp_vmw.c | 12 +++-
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 7ec90359428a..20ab05c4daa8 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,15 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v10 5/8] x86/vmware: Use VMware hypercall API

[Alexey Makhalov]

Remove VMWARE_CMD macro and move to vmware_hypercall API.
No functional changes intended.

Use u32/u64 instead of uint32_t/uint64_t across the file

Signed-off-by: Alexey Makhalov 
---
 arch/x86/kernel/cpu/vmware.c | 95 ++--
 1 file changed, 25 insertions(+), 70 deletions(-)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 07b7b5b773a0..6796425eaaa1 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -49,54 +49,16 @@
 #define STEALCLOCK_DISABLED0
 #define STEALCLOCK_ENABLED 1
 
-#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
-   __asm__("inl (%%dx), %%eax" :   \
-   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
-   "a"(VMWARE_HYPERVISOR_MAGIC),   \
-   "c"(VMWARE_CMD_##cmd),  \
-   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
-   "memory")
-
-#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
-   __asm__("vmcall" :  \
-   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
-   "a"(VMWARE_HYPERVISOR_MAGIC),   \
-   "c"(VMWARE_CMD_##cmd),  \
-   "d"(0), "b"(UINT_MAX) : \
-   "memory")
-
-#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx) \
-   __asm__("vmmcall" : \
-   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
-   "a"(VMWARE_HYPERVISOR_MAGIC),   \
-   "c"(VMWARE_CMD_##cmd),  \
-   "d"(0), "b"(UINT_MAX) : \
-   "memory")
-
-#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
-   switch (vmware_hypercall_mode) {\
-   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
-   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
-   break;  \
-   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
-   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
-   break;  \
-   default:\
-   VMWARE_PORT(cmd, eax, ebx, ecx, edx);   \
-   break;  \
-   }   \
-   } while (0)
-
 struct vmware_steal_time {
union {
-   uint64_t clock; /* stolen time counter in units of vtsc */
+   u64 clock;  /* stolen time counter in units of vtsc */
struct {
/* only for little-endian */
-   uint32_t clock_low;
-   uint32_t clock_high;
+   u32 clock_low;
+   u32 clock_high;
};
};
-   uint64_t reserved[7];
+   u64 reserved[7];
 };
 
 static unsigned long vmware_tsc_khz __ro_after_init;
@@ -105,9 +67,10 @@ EXPORT_SYMBOL_GPL(vmware_hypercall_mode);
 
 static inline int __vmware_platform(void)
 {
-   uint32_t eax, ebx, ecx, edx;
-   VMWARE_CMD(GETVERSION, eax, ebx, ecx, edx);
-   return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
+   u32 eax, ebx, ecx;
+
+   eax = vmware_hypercall3(VMWARE_CMD_GETVERSION, 0, , );
+   return eax != UINT_MAX && ebx == VMWARE_HYPERVISOR_MAGIC;
 }
 
 static unsigned long vmware_get_tsc_khz(void)
@@ -159,21 +122,12 @@ static void __init vmware_cyc2ns_setup(void)
pr_info("using clock offset of %llu ns\n", d->cyc2ns_offset);
 }
 
-static int vmware_cmd_stealclock(uint32_t arg1, uint32_t arg2)
+static int vmware_cmd_stealclock(u32 addr_hi, u32 addr_lo)
 {
-   uint32_t result, info;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(result),
-   "=c"(info) :
-   "a"(VMWARE_HYPERVISOR_MAGIC),
-   "b"(0),
-   "c"(VMWARE_CMD_STEALCLOCK),
-   "d"(0),
-   "S"(arg1),
-   "D"(arg2) :
-   "memory");
-   return result;
+   u32 info;
+
+   return vmware_hype

[PATCH v10 1/8] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
The code inherits VMWARE_CMD logic from the commit mentioned above.

Move common macros from vmware.c to vmware.h.

Make vmware_hypercall_mode a global variable.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 274 --
 arch/x86/kernel/cpu/vmware.c  |  11 +-
 2 files changed, 262 insertions(+), 23 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..5114f4c75c54 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,26 +7,272 @@
 #include 
 
 /*
- * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - 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),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * into arg3 by any user and are automatically replaced by the port
+ * number if the I/O port method is used.
+ */
+
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
+
+extern u8 vmware_hypercall_mode;
+
+/*
+ * 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.
+ */
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("",   \
+ "jmp .Lport_call%=", X86_FEATURE_HYPERVISOR,  \
+ "jmp .Lvmcall%=", X86_FEATURE_VMCALL, \
+ "vmmcall\n\t" \
+ "jmp .Lend%=", X86_FEATURE_VMW_VMMCALL)   \
+ "cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg .Lvm

[PATCH v10 0/8] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

First patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there. And the last
patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v9->v10 changes:
- Restructure the patchset as was suggested by Borislav Petkov to
  introduce vmware_hypercalls API first, then move callers to use this
  API, and then remove the old mechanism.  
- Reduce alternative portion of VMWARE_HYPERCALL by moving common code
  outside of alternative block. Suggested by Borislav Petkov.
- Use u32 instead of uint32_t in vmware_hypercall API and across vmware.c
  as was suggested by Simon Horman.
- Remove previous Reviewed-by and Acked-by.
- Fix typos in comments and commit descriptions.
- No major changes in patches 2,3,4,8 compare to v9.

v8->v9 change:
First patch "x86/vmware: Move common macros to vmware.h" was split on 2 pieces:
  "x86/vmware: Move common macros to vmware.h" - just code movement, and
  "x86/vmware: Correct macro names" - macro renaming.

v7->v8 no functional changes. Updated authors and reviewers emails to
@broadcom.com

v6->v7 changes (only in patch 7):
- Addressed comments from H. Peter Anvin:
  1. Removed vmware_tdx_hypercall_args(), moved args handling inside
 vmware_tdx_hypercall().
  2. Added pr_warn_once() for !hypervisor_is_type(X86_HYPER_VMWARE) case.
- Added ack by Dave Hansen.

v5->v6 change:
- Added ack by Kirill A. Shutemov in patch 7. 

v4->v5 changes:
  [patch 2]:
- Fixed the problem reported by Simon Horman where build fails after
  patch 2 application. Do not undefine VMWARE_HYPERCALL for now, and
  update vmwgfx, vmmouse and ptp_vmw code for new VMWARE_HYPERCALL macro.
- Introduce new patch 6 to undefine VMWARE_HYPERCALL, which is safe to do
  after patches 3 to 5.
- [patch 7 (former patch 6)]: Add missing r15 (CPL) initialization.

v3->v4 changes: (no functional changes in patches 1-5)
  [patch 2]:
- Added the comment with VMware hypercall ABI description.
  [patch 6]:
- vmware_tdx_hypercall_args remove in6/out6 arguments as excessive.
- vmware_tdx_hypercall return ULONG_MAX on error to mimic bad hypercall
  command error from the hypervisor.
- Replaced pr_warn by pr_warn_once as pointed by Kirill Shutemov.
- Fixed the warning reported by Intel's kernel test robot.
- Added the comment describing VMware TDX hypercall ABI.

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

Alexey Makhalov (8):
  x86/vmware: Introduce VMware hypercall API
  ptp/vmware: Use VMware hypercall API
  input/vmmouse: Use VMware hypercall API
  drm/vmwgfx: Use VMware hypercall API
  x86/vmware: Use VMware hypercall API
  x86/vmware: Correct macro names
  x86/vmware: Remove legacy VMWARE_HYPERCALL* macros
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 333 +++---
 arch/x86/kernel/cpu/vmware.c  | 165 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 ---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 196 +
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 602 insertions(+), 538 deletions(-)

-- 
2.39.0

Re: [PATCH v9 3/8] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

Hi Simon, apologize for long delay

On 5/11/24 8:02 AM, Simon Horman wrote:

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h


...


+static inline
+unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2)


nit: u32 is preferred over uint32_t.
  Likewise elsewhere in this patch-set.

Good to know. Can you please shed a light on the reason?
I still see bunch of stdint style uint32_t in arch/x86.



...


  /*
- * The high bandwidth in call. The low word of edx is presumed to have the
- * HB bit set.
+ * High bandwidth calls are not supported on encrypted memory guests.
+ * The caller should check cc_platform_has(CC_ATTR_MEM_ENCRYPT) and use
+ * low bandwidth hypercall it memory encryption is set.
+ * This assumption simplifies HB hypercall impementation to just I/O port


nit: implementation

  checkpatch.pl --codespell is your friend

Thanks, that is useful!




+ * based approach without alternative patching.
   */


...

Re: [PATCH v9 3/8] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

On 5/7/24 2:58 AM, Borislav Petkov wrote:

On Mon, May 06, 2024 at 02:53:00PM -0700, Alexey Makhalov wrote:

+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"\
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t"   \
+ "jg 2f\n\t" \
+ "je 1f\n\t" \
+ "movw %[port], %%dx\n\t"\
+ "inl (%%dx), %%eax\n\t" \
+ "jmp 3f\n\t"\
+ "1: vmmcall\n\t"\
+ "jmp 3f\n\t"\
+ "2: vmcall\n\t" \
+ "3:\n\t",   \
+ "movw %[port], %%dx\n\t"\
+ "inl (%%dx), %%eax", X86_FEATURE_HYPERVISOR,\


That's a bunch of insns and their size would inadvertently go into the final
image.

What you should try to do is something like this:

ALTERNATIVE_3("jmp .Lend_legacy_call", "", X86_FEATURE_HYPERVISOR,
  "vmcall; jmp .Lend_legacy_call", X86_FEATURE_VMCALL,
  "vmmcall; jmp .Lend_legacy_call", X86_FEATURE_VMW_VMMCALL)

/* bunch of conditional branches and INs and V*MCALLs, etc go 
here */

.Lend_legacy_call:

so that you don't have these 26 bytes, as you say, of alternatives to patch but
only the JMPs and the VM*CALLs.

See for an example the macros in arch/x86/entry/calling.h which simply jump
over the code when not needed.

Good idea!



Also, you could restructure the alternative differently so that that bunch of
insns call is completely out-of-line because all current machines support
VM*CALL so you won't even need to patch. You only get to patch when running on
some old rust and there you can just as well go completely out-of-line.


Alternatives patching has not been performed at platform detection time.
And platform detection hypercalls should work on all machines.
That is the reason we have IN as a default hypercall behavior.


Something along those lines, anyway.


- * The high bandwidth in call. The low word of edx is presumed to have the
- * HB bit set.
+ * High bandwidth calls are not supported on encrypted memory guests.
+ * The caller should check cc_platform_has(CC_ATTR_MEM_ENCRYPT) and use
+ * low bandwidth hypercall it memory encryption is set.


s/it/if/

Acked.




-#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
-   __asm__("inl (%%dx), %%eax" : \
-   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
-   "a"(VMWARE_HYPERVISOR_MAGIC), \
-   "c"(VMWARE_CMD_##cmd),\
-   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
-   "memory")
-
-#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
-   __asm__("vmcall" :\
-   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
-   "a"(VMWARE_HYPERVISOR_MAGIC), \
-   "c"(VMWARE_CMD_##cmd),\
-   "d"(0), "b"(UINT_MAX) : \
-   "memory")
-
-#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
-   __asm__("vmmcall" :   \
-   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
-   "a"(VMWARE_HYPERVISOR_MAGIC), \
-   "c"(VMWARE_CMD_##cmd),\
-   "d"(0), "b"(UINT_MAX) : \
-   "memory")
-
-#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
-   switch (vmware_hypercall_mode) {\
-   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
-

Re: [PATCH v9 1/8] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

On 5/7/24 2:14 AM, Borislav Petkov wrote:

On Mon, May 06, 2024 at 02:52:58PM -0700, Alexey Makhalov wrote:

+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)


You can't help yourself not sneaking in any changes which are not code
movement, can ya?

Indeed! My fault.



The purpose of a sole code movement patch is to ease the review. Not to
have to look at the code movement *and* some *additional* changes which
you've done in-flight. Just because you felt like it. But which is nasty
to review.


Agree. I should not claim it as sole code movement then.
At least moving macros from .c to .h file requires changing 
vmware_hypercall_mode variable visibility from static to global.


If you think this type of changes is Ok for sole code movement patch,
then I'll continue following this path. Otherwise, will change patch
description.

Thanks for the patience.
--Alexey

[PATCH v9 7/8] x86/vmware: Undefine VMWARE_HYPERCALL

[Alexey Makhalov]

No more direct use of VMWARE_HYPERCALL macro should be allowed.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 2ac87068184a..84a31f579a30 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -273,5 +273,6 @@ unsigned long vmware_hypercall_hb_in(unsigned long cmd, 
unsigned long in2,
 }
 #undef VMW_BP_REG
 #undef VMW_BP_CONSTRAINT
+#undef VMWARE_HYPERCALL
 
 #endif
-- 
2.39.0

[PATCH v9 8/8] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Acked-by: Kirill A. Shutemov 
Acked-by: Dave Hansen 
---
 arch/x86/include/asm/vmware.h | 46 +++
 arch/x86/kernel/cpu/vmware.c  | 52 +++
 2 files changed, 98 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 84a31f579a30..cc79c14d1ac2 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),
@@ -54,12 +60,28 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#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,
+ uint32_t *out1, uint32_t *out2,
+ uint32_t *out3, uint32_t *out4,
+ uint32_t *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.
@@ -87,6 +109,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -105,6 +131,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -124,6 +154,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -143,6 +177,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -165,6 +203,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2), "=d" 

[PATCH v9 6/8] drm/vmwgfx: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 187 
 3 files changed, 197 insertions(+), 360 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SENDPAYLOAD <&

[PATCH v9 5/8] input/vmmouse: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 
---
 drivers/input/mouse/vmmouse.c | 78 ++-
 1 file changed, 22 insertions(+), 56 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ad94c835ee66..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,30 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
- [port] "i" (VMWARE_HYPERVISOR_PORT),  \
- [mode] "m" (vmware_hypercall_mode),   \
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -147,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -174,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -249,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -273,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 

[PATCH v9 4/8] ptp/vmware: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 14 +++---
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 279d191d2df9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,17 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   [port] "i" (VMWARE_HYPERVISOR_PORT),
-   [mode] "m" (vmware_hypercall_mode),
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v9 3/8] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h   | 288 +++-
 arch/x86/kernel/cpu/vmware.c|  35 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h |   6 +-
 drivers/input/mouse/vmmouse.c   |   2 +
 drivers/ptp/ptp_vmw.c   |   2 +
 5 files changed, 252 insertions(+), 81 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index de257611..2ac87068184a 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,14 +7,37 @@
 #include 
 
 /*
- * The hypercall definitions differ in the low word of the %edx argument
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - 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),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
  * in the following way: the old I/O port based interface uses the port
  * number to distinguish between high- and low bandwidth versions, and
  * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
+ * into arg3 by any user and are automatically replaced by the port
  * number if the I/O port method is used.
  */
 
@@ -37,69 +60,218 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t" 

[PATCH v9 1/8] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +--
 arch/x86/kernel/cpu/vmware.c  | 49 +---
 2 files changed, 62 insertions(+), 59 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..de257611 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,34 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * number if the I/O port method is used.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +63,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break; 

[PATCH v9 2/8] x86/vmware: Correct macro names

[Alexey Makhalov]

VCPU_RESERVED and LEGACY_X2APIC are not VMware hypercall commands.
These are bits in return value of VMWARE_CMD_GETVCPU_INFO command.
Change VMWARE_CMD_ prefix to GETVCPU_INFO_ one. And move bit-shift
operation to the macro body.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/kernel/cpu/vmware.c | 8 
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 68d812e12e52..9d804d60a11f 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -42,8 +42,8 @@
 #define CPUID_VMWARE_INFO_LEAF   0x4000
 #define CPUID_VMWARE_FEATURES_LEAF   0x4010
 
-#define VMWARE_CMD_LEGACY_X2APIC  3
-#define VMWARE_CMD_VCPU_RESERVED 31
+#define GETVCPU_INFO_LEGACY_X2APIC   BIT(3)
+#define GETVCPU_INFO_VCPU_RESERVED   BIT(31)
 
 #define STEALCLOCK_NOT_AVAILABLE (-1)
 #define STEALCLOCK_DISABLED0
@@ -431,8 +431,8 @@ static bool __init vmware_legacy_x2apic_available(void)
 {
uint32_t eax, ebx, ecx, edx;
VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx);
-   return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) &&
-   (eax & BIT(VMWARE_CMD_LEGACY_X2APIC));
+   return !(eax & GETVCPU_INFO_VCPU_RESERVED) &&
+   (eax & GETVCPU_INFO_LEGACY_X2APIC);
 }
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
-- 
2.39.0

[PATCH v9 0/8] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v8->v9 change:
First patch "x86/vmware: Move common macros to vmware.h" was split on 2 pieces:
  "x86/vmware: Move common macros to vmware.h" - just code movement, and
  "x86/vmware: Correct macro names" - macro renaming.

v7->v8 no functional changes. Updated authors and reviewers emails to
@broadcom.com

v6->v7 changes (only in patch 7):
- Addressed comments from H. Peter Anvin:
  1. Removed vmware_tdx_hypercall_args(), moved args handling inside
 vmware_tdx_hypercall().
  2. Added pr_warn_once() for !hypervisor_is_type(X86_HYPER_VMWARE) case.
- Added ack by Dave Hansen.

v5->v6 change:
- Added ack by Kirill A. Shutemov in patch 7. 

v4->v5 changes:
  [patch 2]:
- Fixed the problem reported by Simon Horman where build fails after
  patch 2 application. Do not undefine VMWARE_HYPERCALL for now, and
  update vmwgfx, vmmouse and ptp_vmw code for new VMWARE_HYPERCALL macro.
- Introduce new patch 6 to undefine VMWARE_HYPERCALL, which is safe to do
  after patches 3 to 5.
- [patch 7 (former patch 6)]: Add missing r15 (CPL) initialization.

v3->v4 changes: (no functional changes in patches 1-5)
  [patch 2]:
- Added the comment with VMware hypercall ABI description.
  [patch 6]:
- vmware_tdx_hypercall_args remove in6/out6 arguments as excessive.
- vmware_tdx_hypercall return ULONG_MAX on error to mimic bad hypercall
  command error from the hypervisor.
- Replaced pr_warn by pr_warn_once as pointed by Kirill Shutemov.
- Fixed the warning reported by Intel's kernel test robot.
- Added the comment describing VMware TDX hypercall ABI.

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

Alexey Makhalov (8):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Correct macro names
  x86/vmware: Introduce VMware hypercall API
  ptp/vmware: Use VMware hypercall API
  input/vmmouse: Use VMware hypercall API
  drm/vmwgfx: Use VMware hypercall API
  x86/vmware: Undefine VMWARE_HYPERCALL
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 331 +++---
 arch/x86/kernel/cpu/vmware.c  | 144 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 ---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 593 insertions(+), 525 deletions(-)

-- 
2.39.0

Re: [PATCH v9 1/8] x86/vmware: Correct macro names

[Alexey Makhalov]

On 4/25/24 8:21 AM, Borislav Petkov wrote:

On Wed, Apr 24, 2024 at 04:14:06PM -0700, Alexey Makhalov wrote:

VCPU_RESERVED and LEGACY_X2APIC are not VMware hypercall commands.
These are bits in return value of VMWARE_CMD_GETVCPU_INFO command.
Change VMWARE_CMD_ prefix to GETVCPU_INFO_ one. And move bit-shift
operation to the macro body.


I don't understand:

$ git grep GETVCPU_INFO
arch/x86/kernel/cpu/vmware.c:51:#define VMWARE_CMD_GETVCPU_INFO  68
arch/x86/kernel/cpu/vmware.c:478:   VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, 
edx);

so that's a VMWARE_CMD 68, at least the prefix says so.

And those two are *bits* in that eax which that hypercall returns.

Or are those two bits generic but defined in a vmware-specific
hypercall?

Hm.



These are VMware hypercall commands:
#define VMWARE_CMD_GETVERSION10
#define VMWARE_CMD_GETHZ 45
#define VMWARE_CMD_GETVCPU_INFO  68
#define VMWARE_CMD_STEALCLOCK91


These are VMware-specific macros to analyze return values of 
corresponding commands. They are prefixed with command name.

#define GETVCPU_INFO_LEGACY_X2APIC   BIT(3)
#define GETVCPU_INFO_VCPU_RESERVED   BIT(31)

#define STEALCLOCK_NOT_AVAILABLE (-1)
#define STEALCLOCK_DISABLED0
#define STEALCLOCK_ENABLED 1


Name VMWARE_CMD_LEGACY_X2APIC was not correct as LEGACY_X2APIC is not a 
command but the meaning of 3rd bit of a return value of 
VMWARE_CMD_GETVCPU_INFO. So, change it to GETVCPU_INFO_LEGACY_X2APIC.

The same change with GETVCPU_INFO_VCPU_RESERVED.
Both these bits are not generic.

--Alexey

[PATCH v9 2/8] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +--
 arch/x86/kernel/cpu/vmware.c  | 43 +
 2 files changed, 62 insertions(+), 53 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..de257611 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,34 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * number if the I/O port method is used.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +63,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break; 

[PATCH v9 1/8] x86/vmware: Correct macro names

[Alexey Makhalov]

VCPU_RESERVED and LEGACY_X2APIC are not VMware hypercall commands.
These are bits in return value of VMWARE_CMD_GETVCPU_INFO command.
Change VMWARE_CMD_ prefix to GETVCPU_INFO_ one. And move bit-shift
operation to the macro body.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/kernel/cpu/vmware.c | 9 +
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 11f83d07925e..f58c8d669bd3 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -49,10 +49,11 @@
 #define VMWARE_CMD_GETVERSION10
 #define VMWARE_CMD_GETHZ 45
 #define VMWARE_CMD_GETVCPU_INFO  68
-#define VMWARE_CMD_LEGACY_X2APIC  3
-#define VMWARE_CMD_VCPU_RESERVED 31
 #define VMWARE_CMD_STEALCLOCK91
 
+#define GETVCPU_INFO_LEGACY_X2APIC   BIT(3)
+#define GETVCPU_INFO_VCPU_RESERVED   BIT(31)
+
 #define STEALCLOCK_NOT_AVAILABLE (-1)
 #define STEALCLOCK_DISABLED0
 #define STEALCLOCK_ENABLED 1
@@ -476,8 +477,8 @@ static bool __init vmware_legacy_x2apic_available(void)
 {
uint32_t eax, ebx, ecx, edx;
VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx);
-   return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) &&
-   (eax & BIT(VMWARE_CMD_LEGACY_X2APIC));
+   return !(eax & GETVCPU_INFO_VCPU_RESERVED) &&
+   (eax & GETVCPU_INFO_LEGACY_X2APIC);
 }
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
-- 
2.39.0

Re: [PATCH v8 1/7] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

On 4/24/24 9:06 AM, Borislav Petkov wrote:

On Mon, Apr 22, 2024 at 03:56:50PM -0700, Alexey Makhalov wrote:

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.


Well, I see more.

So code movement patches should be done this way:

* first patch: sole code movement, no changes whatsoever

* follow-on patches: add changes and explain them

Because... (follow me down)...


@@ -476,8 +431,8 @@ static bool __init vmware_legacy_x2apic_available(void)
  {
uint32_t eax, ebx, ecx, edx;
VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx);
-   return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) &&
-   (eax & BIT(VMWARE_CMD_LEGACY_X2APIC));
+   return !(eax & BIT(VCPU_RESERVED)) &&
+   (eax & BIT(VCPU_LEGACY_X2APIC));


... what is that change for?

Those bit definitions are clearly vmware-specific. So why are you
changing them to something generic-ish?

In any case, this patch needs to be split as outlined above.


Thanks for prompt review. The concern is valid.
I've split this patch on 2 pieces:
1. Macro renaming - to use proper prefix GETVCPU_INFO_ instead of 
incorrect VMWARE_CMD_.

2. Code movement - the original idea of the patch.

Remaining patches will remain intact.

Thanks,
--Alexey

[PATCH v8 7/7] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Acked-by: Kirill A. Shutemov 
Acked-by: Dave Hansen 
---
 arch/x86/include/asm/vmware.h | 46 +++
 arch/x86/kernel/cpu/vmware.c  | 52 +++
 2 files changed, 98 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 84a31f579a30..cc79c14d1ac2 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),
@@ -54,12 +60,28 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#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,
+ uint32_t *out1, uint32_t *out2,
+ uint32_t *out3, uint32_t *out4,
+ uint32_t *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.
@@ -87,6 +109,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -105,6 +131,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -124,6 +154,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -143,6 +177,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -165,6 +203,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2), "=d" 

[PATCH v8 5/7] drm/vmwgfx: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 187 
 3 files changed, 197 insertions(+), 360 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SENDPAYLOAD <&

[PATCH v8 6/7] x86/vmware: Undefine VMWARE_HYPERCALL

[Alexey Makhalov]

No more direct use of VMWARE_HYPERCALL macro should be allowed.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 2ac87068184a..84a31f579a30 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -273,5 +273,6 @@ unsigned long vmware_hypercall_hb_in(unsigned long cmd, 
unsigned long in2,
 }
 #undef VMW_BP_REG
 #undef VMW_BP_CONSTRAINT
+#undef VMWARE_HYPERCALL
 
 #endif
-- 
2.39.0

[PATCH v8 4/7] input/vmmouse: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 
---
 drivers/input/mouse/vmmouse.c | 78 ++-
 1 file changed, 22 insertions(+), 56 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ad94c835ee66..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,30 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
- [port] "i" (VMWARE_HYPERVISOR_PORT),  \
- [mode] "m" (vmware_hypercall_mode),   \
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -147,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -174,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -249,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -273,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 

[PATCH v8 2/7] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h   | 288 +++-
 arch/x86/kernel/cpu/vmware.c|  35 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h |   6 +-
 drivers/input/mouse/vmmouse.c   |   2 +
 drivers/ptp/ptp_vmw.c   |   2 +
 5 files changed, 252 insertions(+), 81 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index de257611..2ac87068184a 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,14 +7,37 @@
 #include 
 
 /*
- * The hypercall definitions differ in the low word of the %edx argument
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - 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),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
  * in the following way: the old I/O port based interface uses the port
  * number to distinguish between high- and low bandwidth versions, and
  * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
+ * into arg3 by any user and are automatically replaced by the port
  * number if the I/O port method is used.
  */
 
@@ -37,69 +60,218 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t" 

[PATCH v8 3/7] ptp/vmware: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 14 +++---
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 279d191d2df9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,17 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   [port] "i" (VMWARE_HYPERVISOR_PORT),
-   [mode] "m" (vmware_hypercall_mode),
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v8 1/7] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +--
 arch/x86/kernel/cpu/vmware.c  | 57 +++
 2 files changed, 66 insertions(+), 63 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..de257611 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,34 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * number if the I/O port method is used.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +63,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break;  

[PATCH v8 0/7] VMware hypercalls enhancements

[Alexey Makhalov]

No functional changes from version 7. Peter please consider reviewing
patch 7 where we addressed your comments from version 6. Thanks!

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v7->v8 no functional changes. Updated authors and reviewers emails to
@broadcom.com

v6->v7 changes (only in patch 7):
- Addressed comments from H. Peter Anvin:
  1. Removed vmware_tdx_hypercall_args(), moved args handling inside
 vmware_tdx_hypercall().
  2. Added pr_warn_once() for !hypervisor_is_type(X86_HYPER_VMWARE) case.
- Added ack by Dave Hansen.

v5->v6 change:
- Added ack by Kirill A. Shutemov in patch 7. 

v4->v5 changes:
  [patch 2]:
- Fixed the problem reported by Simon Horman where build fails after
  patch 2 application. Do not undefine VMWARE_HYPERCALL for now, and
  update vmwgfx, vmmouse and ptp_vmw code for new VMWARE_HYPERCALL macro.
- Introduce new patch 6 to undefine VMWARE_HYPERCALL, which is safe to do
  after patches 3 to 5.
- [patch 7 (former patch 6)]: Add missing r15 (CPL) initialization.

v3->v4 changes: (no functional changes in patches 1-5)
  [patch 2]:
- Added the comment with VMware hypercall ABI description.
  [patch 6]:
- vmware_tdx_hypercall_args remove in6/out6 arguments as excessive.
- vmware_tdx_hypercall return ULONG_MAX on error to mimic bad hypercall
  command error from the hypervisor.
- Replaced pr_warn by pr_warn_once as pointed by Kirill Shutemov.
- Fixed the warning reported by Intel's kernel test robot.
- Added the comment describing VMware TDX hypercall ABI.

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.


Alexey Makhalov (7):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce VMware hypercall API
  ptp/vmware: Use VMware hypercall API
  input/vmmouse: Use VMware hypercall API
  drm/vmwgfx: Use VMware hypercall API
  x86/vmware: Undefine VMWARE_HYPERCALL
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 331 +++---
 arch/x86/kernel/cpu/vmware.c  | 144 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 ---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 593 insertions(+), 525 deletions(-)

-- 
2.39.0

Re: [PATCH v7 0/7] VMware hypercalls enhancements

[Alexey Makhalov]

Peter, can you please review version 7 of "x86/vmware: Add TDX hypercall 
support" patch.
It addresses the concern you had in previous version. Thanks.

[PATCH v7 4/7] input/vmmouse: Use VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 
---
 drivers/input/mouse/vmmouse.c | 78 ++-
 1 file changed, 22 insertions(+), 56 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ad94c835ee66..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,30 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
- [port] "i" (VMWARE_HYPERVISOR_PORT),  \
- [mode] "m" (vmware_hypercall_mode),   \
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -147,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -174,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -249,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -273,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2

[PATCH v7 5/7] drm/vmwgfx: Use VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 187 
 3 files changed, 197 insertions(+), 360 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SEND

[PATCH v7 7/7] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

From: Alexey Makhalov 

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Acked-by: Kirill A. Shutemov 
Acked-by: Dave Hansen 
---
 arch/x86/include/asm/vmware.h | 46 +++
 arch/x86/kernel/cpu/vmware.c  | 52 +++
 2 files changed, 98 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 84a31f579a30..cc79c14d1ac2 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),
@@ -54,12 +60,28 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#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,
+ uint32_t *out1, uint32_t *out2,
+ uint32_t *out3, uint32_t *out4,
+ uint32_t *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.
@@ -87,6 +109,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -105,6 +131,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -124,6 +154,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -143,6 +177,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -165,6 +203,10 @@ 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);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c"

[PATCH v7 6/7] x86/vmware: Undefine VMWARE_HYPERCALL

[Alexey Makhalov]

From: Alexey Makhalov 

No more direct use of VMWARE_HYPERCALL macro should be allowed.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 2ac87068184a..84a31f579a30 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -273,5 +273,6 @@ unsigned long vmware_hypercall_hb_in(unsigned long cmd, 
unsigned long in2,
 }
 #undef VMW_BP_REG
 #undef VMW_BP_CONSTRAINT
+#undef VMWARE_HYPERCALL
 
 #endif
-- 
2.39.0

[PATCH v7 3/7] ptp/vmware: Use VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 14 +++---
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 279d191d2df9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,17 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   [port] "i" (VMWARE_HYPERVISOR_PORT),
-   [mode] "m" (vmware_hypercall_mode),
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v7 2/7] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h   | 288 +++-
 arch/x86/kernel/cpu/vmware.c|  35 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h |   6 +-
 drivers/input/mouse/vmmouse.c   |   2 +
 drivers/ptp/ptp_vmw.c   |   2 +
 5 files changed, 252 insertions(+), 81 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index de257611..2ac87068184a 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,14 +7,37 @@
 #include 
 
 /*
- * The hypercall definitions differ in the low word of the %edx argument
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - 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),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
  * in the following way: the old I/O port based interface uses the port
  * number to distinguish between high- and low bandwidth versions, and
  * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
+ * into arg3 by any user and are automatically replaced by the port
  * number if the I/O port method is used.
  */
 
@@ -37,69 +60,218 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t" 

[PATCH v7 1/7] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

From: Alexey Makhalov 

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +--
 arch/x86/kernel/cpu/vmware.c  | 57 +++
 2 files changed, 66 insertions(+), 63 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..de257611 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,34 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * number if the I/O port method is used.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +63,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   br

[PATCH v7 0/7] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v6->v7 changes (only in patch 7):
- Addressed comments from H. Peter Anvin:
  1. Removed vmware_tdx_hypercall_args(), moved args handling inside
 vmware_tdx_hypercall().
  2. Added pr_warn_once() for !hypervisor_is_type(X86_HYPER_VMWARE) case.
- Added ack by Dave Hansen.

v5->v6 change:
- Added ack by Kirill A. Shutemov in patch 7. 

v4->v5 changes:
  [patch 2]:
- Fixed the problem reported by Simon Horman where build fails after
  patch 2 application. Do not undefine VMWARE_HYPERCALL for now, and
  update vmwgfx, vmmouse and ptp_vmw code for new VMWARE_HYPERCALL macro.
- Introduce new patch 6 to undefine VMWARE_HYPERCALL, which is safe to do
  after patches 3 to 5.
- [patch 7 (former patch 6)]: Add missing r15 (CPL) initialization.

v3->v4 changes: (no functional changes in patches 1-5)
  [patch 2]:
- Added the comment with VMware hypercall ABI description.
  [patch 6]:
- vmware_tdx_hypercall_args remove in6/out6 arguments as excessive.
- vmware_tdx_hypercall return ULONG_MAX on error to mimic bad hypercall
  command error from the hypervisor.
- Replaced pr_warn by pr_warn_once as pointed by Kirill Shutemov.
- Fixed the warning reported by Intel's kernel test robot.
- Added the comment describing VMware TDX hypercall ABI.

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

Alexey Makhalov (7):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce VMware hypercall API
  ptp/vmware: Use VMware hypercall API
  input/vmmouse: Use VMware hypercall API
  drm/vmwgfx: Use VMware hypercall API
  x86/vmware: Undefine VMWARE_HYPERCALL
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 331 +++---
 arch/x86/kernel/cpu/vmware.c  | 144 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 ---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 593 insertions(+), 525 deletions(-)

-- 
2.39.0

Re: [PATCH v6 7/7] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

On 1/22/24 4:17 PM, H. Peter Anvin wrote:

On January 22, 2024 4:04:33 PM PST, Alexey Makhalov 
 wrote:



On 1/22/24 10:28 AM, H. Peter Anvin wrote:

On January 22, 2024 8:32:22 AM PST, Dave Hansen  wrote:

On 1/9/24 00:40, Alexey Makhalov wrote:

+#ifdef CONFIG_INTEL_TDX_GUEST
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+  struct tdx_module_args *args)
+{
+   if (!hypervisor_is_type(X86_HYPER_VMWARE))
+   return ULONG_MAX;
+
+   if (cmd & ~VMWARE_CMD_MASK) {
+   pr_warn_once("Out of range command %lx\n", cmd);
+   return ULONG_MAX;
+   }
+
+   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);
+
+   return args->r12;
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall);
+#endif


This is the kind of wrapper that I was hoping for.  Thanks.

Acked-by: Dave Hansen 



I'm slightly confused by this TBH.

Why are the arguments passed in as a structure, which is modified by the 
wrapper to boot? This is analogous to a system call interface.

Furthermore, this is an out-of-line function; it should never be called with 
!X86_HYPER_VMWARE or you are introducing overhead for other hypervisors; I 
believe a pr_warn_once() is in order at least, just as you have for the 
out-of-range test.



This patch series introduces vmware_hypercall family of functions similar to 
kvm_hypercall. Similarity: both vmware and kvm implementations are static 
inline functions and both of them use __tdx_hypercall (global not exported 
symbol). Difference: kvm_hypercall functions are used _only_ within the kernel, 
but vmware_hypercall are also used by modules.
Exporting __tdx_hypercall function is an original Dave's concern.
So we ended up with exporting wrapper, not generic, but VMware specific with 
added checks against arbitrary use.
vmware_tdx_hypercall is not designed for !X86_HYPER_VMWARE callers. But such a 
calls are not forbidden.
Arguments in a structure is an API for __tdx_hypercall(). Input and output 
argument handling are done by vmware_hypercall callers, while VMware specific 
dress up is inside the wrapper.

Peter, do you think code comments are required to make it clear for the reader?




TBH that explanation didn't make much sense to me...


Peter,

I would like to understand your concerns.

1. Are you suggesting to move structure (tdx parameters) initialization 
in one please, instead of one part there another part here? Do you 
prefer to pass all arguments as is to vmware_tdx_hypercall() and only 
define tdx_module_args there?


2. And second suggestion is to add pr_warn_once under "if 
(!hypervisor_is_type(X86_HYPER_VMWARE))" ?


--Alexey

Re: [PATCH v6 7/7] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

On 1/22/24 10:28 AM, H. Peter Anvin wrote:

On January 22, 2024 8:32:22 AM PST, Dave Hansen  wrote:

On 1/9/24 00:40, Alexey Makhalov wrote:

+#ifdef CONFIG_INTEL_TDX_GUEST
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+  struct tdx_module_args *args)
+{
+   if (!hypervisor_is_type(X86_HYPER_VMWARE))
+   return ULONG_MAX;
+
+   if (cmd & ~VMWARE_CMD_MASK) {
+   pr_warn_once("Out of range command %lx\n", cmd);
+   return ULONG_MAX;
+   }
+
+   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);
+
+   return args->r12;
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall);
+#endif


This is the kind of wrapper that I was hoping for.  Thanks.

Acked-by: Dave Hansen 



I'm slightly confused by this TBH.

Why are the arguments passed in as a structure, which is modified by the 
wrapper to boot? This is analogous to a system call interface.

Furthermore, this is an out-of-line function; it should never be called with 
!X86_HYPER_VMWARE or you are introducing overhead for other hypervisors; I 
believe a pr_warn_once() is in order at least, just as you have for the 
out-of-range test.



This patch series introduces vmware_hypercall family of functions 
similar to kvm_hypercall. Similarity: both vmware and kvm 
implementations are static inline functions and both of them use 
__tdx_hypercall (global not exported symbol). Difference: kvm_hypercall 
functions are used _only_ within the kernel, but vmware_hypercall are 
also used by modules.

Exporting __tdx_hypercall function is an original Dave's concern.
So we ended up with exporting wrapper, not generic, but VMware specific 
with added checks against arbitrary use.
vmware_tdx_hypercall is not designed for !X86_HYPER_VMWARE callers. But 
such a calls are not forbidden.
Arguments in a structure is an API for __tdx_hypercall(). Input and 
output argument handling are done by vmware_hypercall callers, while 
VMware specific dress up is inside the wrapper.


Peter, do you think code comments are required to make it clear for the 
reader?

[PATCH v6 7/7] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Acked-by: Kirill A. Shutemov 
---
 arch/x86/include/asm/vmware.h | 79 +++
 arch/x86/kernel/cpu/vmware.c  | 25 +++
 2 files changed, 104 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 84a31f579a30..3bd593c6591d 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),
@@ -54,12 +60,61 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall_args(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5,
+   uint32_t *out1, uint32_t *out2,
+   uint32_t *out3, uint32_t *out4,
+   uint32_t *out5)
+{
+   unsigned long ret;
+
+   struct tdx_module_args args = {
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   };
+
+   ret = vmware_tdx_hypercall(cmd, );
+
+   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 ret;
+}
+
 /*
  * 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.
@@ -87,6 +142,10 @@ 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_args(cmd, in1, 0, 0, 0,
+NULL, NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -105,6 +164,10 @@ 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_args(cmd, in1, 0, 0, 0,
+out1, out2, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -124,6 +187,10 @@ 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_args(cmd, in1, 0, 0, 0,
+out1, out2, out3, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -143,6 +210,10 @@ unsigned long vmware_hypercall5(unsigned long cmd, 
unsigned long in1,
 {
unsigned long out0;
 
+   if (cpu_fe

[PATCH v6 6/7] x86/vmware: Undefine VMWARE_HYPERCALL

[Alexey Makhalov]

No more direct use of VMWARE_HYPERCALL macro should be allowed.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 2ac87068184a..84a31f579a30 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -273,5 +273,6 @@ unsigned long vmware_hypercall_hb_in(unsigned long cmd, 
unsigned long in2,
 }
 #undef VMW_BP_REG
 #undef VMW_BP_CONSTRAINT
+#undef VMWARE_HYPERCALL
 
 #endif
-- 
2.39.0

[PATCH v6 5/7] drm/vmwgfx: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 187 
 3 files changed, 197 insertions(+), 360 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SENDPAYLOAD <&

[PATCH v6 4/7] input/vmmouse: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 
---
 drivers/input/mouse/vmmouse.c | 78 ++-
 1 file changed, 22 insertions(+), 56 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ad94c835ee66..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,30 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
- [port] "i" (VMWARE_HYPERVISOR_PORT),  \
- [mode] "m" (vmware_hypercall_mode),   \
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -147,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -174,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -249,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -273,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 

[PATCH v6 3/7] ptp/vmware: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 14 +++---
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 279d191d2df9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,17 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   [port] "i" (VMWARE_HYPERVISOR_PORT),
-   [mode] "m" (vmware_hypercall_mode),
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v6 2/7] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h   | 288 +++-
 arch/x86/kernel/cpu/vmware.c|  35 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h |   6 +-
 drivers/input/mouse/vmmouse.c   |   2 +
 drivers/ptp/ptp_vmw.c   |   2 +
 5 files changed, 252 insertions(+), 81 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index de257611..2ac87068184a 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,14 +7,37 @@
 #include 
 
 /*
- * The hypercall definitions differ in the low word of the %edx argument
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - 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),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
  * in the following way: the old I/O port based interface uses the port
  * number to distinguish between high- and low bandwidth versions, and
  * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
+ * into arg3 by any user and are automatically replaced by the port
  * number if the I/O port method is used.
  */
 
@@ -37,69 +60,218 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t" 

[PATCH v6 1/7] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +--
 arch/x86/kernel/cpu/vmware.c  | 57 +++
 2 files changed, 66 insertions(+), 63 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..de257611 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,34 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * number if the I/O port method is used.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +63,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break;  

[PATCH v6 0/7] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v5->v6 change:
- Added ack by Kirill A. Shutemov in patch 7. 

v4->v5 changes:
  [patch 2]:
- Fixed the problem reported by Simon Horman where build fails after
  patch 2 application. Do not undefine VMWARE_HYPERCALL for now, and
  update vmwgfx, vmmouse and ptp_vmw code for new VMWARE_HYPERCALL macro.
- Introduce new patch 6 to undefine VMWARE_HYPERCALL, which is safe to do
  after patches 3 to 5.
- [patch 7 (former patch 6)]: Add missing r15 (CPL) initialization.

v3->v4 changes: (no functional changes in patches 1-5)
  [patch 2]:
- Added the comment with VMware hypercall ABI description.
  [patch 6]:
- vmware_tdx_hypercall_args remove in6/out6 arguments as excessive.
- vmware_tdx_hypercall return ULONG_MAX on error to mimic bad hypercall
  command error from the hypervisor.
- Replaced pr_warn by pr_warn_once as pointed by Kirill Shutemov.
- Fixed the warning reported by Intel's kernel test robot.
- Added the comment describing VMware TDX hypercall ABI.

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

Alexey Makhalov (7):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce VMware hypercall API
  ptp/vmware: Use VMware hypercall API
  input/vmmouse: Use VMware hypercall API
  drm/vmwgfx: Use VMware hypercall API
  x86/vmware: Undefine VMWARE_HYPERCALL
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 364 --
 arch/x86/kernel/cpu/vmware.c  | 117 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 --
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 ---
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 599 insertions(+), 525 deletions(-)

-- 
2.39.0

[PATCH v5 7/7] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 79 +++
 arch/x86/kernel/cpu/vmware.c  | 25 +++
 2 files changed, 104 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 84a31f579a30..3bd593c6591d 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),
@@ -54,12 +60,61 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall_args(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5,
+   uint32_t *out1, uint32_t *out2,
+   uint32_t *out3, uint32_t *out4,
+   uint32_t *out5)
+{
+   unsigned long ret;
+
+   struct tdx_module_args args = {
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   };
+
+   ret = vmware_tdx_hypercall(cmd, );
+
+   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 ret;
+}
+
 /*
  * 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.
@@ -87,6 +142,10 @@ 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_args(cmd, in1, 0, 0, 0,
+NULL, NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -105,6 +164,10 @@ 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_args(cmd, in1, 0, 0, 0,
+out1, out2, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -124,6 +187,10 @@ 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_args(cmd, in1, 0, 0, 0,
+out1, out2, out3, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -143,6 +210,10 @@ unsigned long vmware_hypercall5(unsigned long cmd, 
unsigned long in1,
 {
unsigned long out0;
 
+   if (cpu_fe

[PATCH v5 6/7] x86/vmware: Undefine VMWARE_HYPERCALL

[Alexey Makhalov]

No more direct use of VMWARE_HYPERCALL macro should be allowed.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 2ac87068184a..84a31f579a30 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -273,5 +273,6 @@ unsigned long vmware_hypercall_hb_in(unsigned long cmd, 
unsigned long in2,
 }
 #undef VMW_BP_REG
 #undef VMW_BP_CONSTRAINT
+#undef VMWARE_HYPERCALL
 
 #endif
-- 
2.39.0

[PATCH v5 5/7] drm/vmwgfx: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 187 
 3 files changed, 197 insertions(+), 360 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SENDPAYLOAD <&

[PATCH v5 4/7] input/vmmouse: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 
---
 drivers/input/mouse/vmmouse.c | 78 ++-
 1 file changed, 22 insertions(+), 56 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ad94c835ee66..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,30 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
- [port] "i" (VMWARE_HYPERVISOR_PORT),  \
- [mode] "m" (vmware_hypercall_mode),   \
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -147,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -174,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -249,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -273,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 

[PATCH v5 3/7] ptp/vmware: Use VMware hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 14 +++---
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 279d191d2df9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,17 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   [port] "i" (VMWARE_HYPERVISOR_PORT),
-   [mode] "m" (vmware_hypercall_mode),
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v5 2/7] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h   | 288 +++-
 arch/x86/kernel/cpu/vmware.c|  35 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h |   6 +-
 drivers/input/mouse/vmmouse.c   |   2 +
 drivers/ptp/ptp_vmw.c   |   2 +
 5 files changed, 252 insertions(+), 81 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index de257611..2ac87068184a 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,14 +7,37 @@
 #include 
 
 /*
- * The hypercall definitions differ in the low word of the %edx argument
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - 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),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
  * in the following way: the old I/O port based interface uses the port
  * number to distinguish between high- and low bandwidth versions, and
  * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
+ * into arg3 by any user and are automatically replaced by the port
  * number if the I/O port method is used.
  */
 
@@ -37,69 +60,218 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t" 

[PATCH v5 1/7] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +--
 arch/x86/kernel/cpu/vmware.c  | 57 +++
 2 files changed, 66 insertions(+), 63 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..de257611 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,34 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * number if the I/O port method is used.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +63,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break;  

[PATCH v5 0/7] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v4->v5 changes:
  [patch 2]:
- Fixed the problem reported by Simon Horman where build fails after
  patch 2 application. Do not undefine VMWARE_HYPERCALL for now, and
  update vmwgfx, vmmouse and ptp_vmw code for new VMWARE_HYPERCALL macro.
- Introduce new patch 6 to undefine VMWARE_HYPERCALL, which is safe to do
  after patches 3 to 5.
- [patch 7 (former patch 6)]: Add missing r15 (CPL) initialization.

v3->v4 changes: (no functional changes in patches 1-5)
  [patch 2]:
- Added the comment with VMware hypercall ABI description.
  [patch 6]:
- vmware_tdx_hypercall_args remove in6/out6 arguments as excessive.
- vmware_tdx_hypercall return ULONG_MAX on error to mimic bad hypercall
  command error from the hypervisor.
- Replaced pr_warn by pr_warn_once as pointed by Kirill Shutemov.
- Fixed the warning reported by Intel's kernel test robot.
- Added the comment describing VMware TDX hypercall ABI.

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

Alexey Makhalov (7):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce VMware hypercall API
  ptp/vmware: Use VMware hypercall API
  input/vmmouse: Use VMware hypercall API
  drm/vmwgfx: Use VMware hypercall API
  x86/vmware: Undefine VMWARE_HYPERCALL
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 364 --
 arch/x86/kernel/cpu/vmware.c  | 117 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 --
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 ---
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 599 insertions(+), 525 deletions(-)

-- 
2.39.0

[PATCH v4 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

From: Alexey Makhalov 

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 79 +++
 arch/x86/kernel/cpu/vmware.c  | 24 +++
 2 files changed, 103 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 84a31f579a30..3bd593c6591d 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),
@@ -54,12 +60,61 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore,
+ * we remap those registers to %r12 and %r13, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall_args(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5,
+   uint32_t *out1, uint32_t *out2,
+   uint32_t *out3, uint32_t *out4,
+   uint32_t *out5)
+{
+   unsigned long ret;
+
+   struct tdx_module_args args = {
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   };
+
+   ret = vmware_tdx_hypercall(cmd, );
+
+   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 ret;
+}
+
 /*
  * 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.
@@ -87,6 +142,10 @@ 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_args(cmd, in1, 0, 0, 0,
+NULL, NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -105,6 +164,10 @@ 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_args(cmd, in1, 0, 0, 0,
+out1, out2, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -124,6 +187,10 @@ 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_args(cmd, in1, 0, 0, 0,
+out1, out2, out3, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -143,6 +210,10 @@ unsigned long vmware_hypercall5(unsigned long cmd, 
unsigned long in1,
 {
unsigned long out0;
 
+   if (cpu_fe

[PATCH v4 4/6] input/vmmouse: Use VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 
---
 drivers/input/mouse/vmmouse.c | 76 ++-
 1 file changed, 22 insertions(+), 54 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ea9eff7c8099..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,28 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -145,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -172,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -247,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -271,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 
/*
 * Try enabling the device. If successful, we should be able to
 * read valid version ID bac

[PATCH v4 5/6] drm/vmwgfx: Use VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 3 files changed, 197 insertions(+), 358 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SEND

[PATCH v4 2/6] x86/vmware: Introduce VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h | 289 +++---
 arch/x86/kernel/cpu/vmware.c  |  35 ++--
 2 files changed, 245 insertions(+), 79 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index de257611..84a31f579a30 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -7,14 +7,37 @@
 #include 
 
 /*
- * The hypercall definitions differ in the low word of the %edx argument
+ * VMware hypercall ABI.
+ *
+ * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall)
+ * have up to 6 input and 6 output arguments passed and returned using
+ * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3),
+ * %esi (arg4), %edi (arg5).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg2 - Hypercall command
+ * arg3 bits [15:0] - Port number, LB and direction flags
+ *
+ * - 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),
+ * %esi (arg4), %edi (arg5), %ebp (arg6).
+ * The following input arguments must be initialized by the caller:
+ * arg0 - VMWARE_HYPERVISOR_MAGIC
+ * arg1 - Hypercall command
+ * arg3 bits [15:0] - Port number, HB and direction flags
+ *
+ * For compatibility purposes, x86_64 systems use only lower 32 bits
+ * for input and output arguments.
+ *
+ * The hypercall definitions differ in the low word of the %edx (arg3)
  * in the following way: the old I/O port based interface uses the port
  * number to distinguish between high- and low bandwidth versions, and
  * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
- * into %dx by any user and are automatically replaced by the port
+ * into arg3 by any user and are automatically replaced by the port
  * number if the I/O port method is used.
  */
 
@@ -37,69 +60,219 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t"   \
+ "movw %[port], %%dx\n\t"  \
+ "inl (%%dx), %%eax

[PATCH v4 1/6] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

From: Alexey Makhalov 

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +--
 arch/x86/kernel/cpu/vmware.c  | 57 +++
 2 files changed, 66 insertions(+), 63 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..de257611 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,34 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
- *
- * In short, new driver code should strictly use the new definition of
- * %dx content.
+ * number if the I/O port method is used.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
+
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +63,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   br

[PATCH v4 3/6] ptp/vmware: Use VMware hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 12 +++-
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 27c5547aa8a9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,15 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v4 0/6] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v3->v4 changes: (no functional changes in patches 1-5)
  [patch 2]:
- Added the comment with VMware hypercall ABI description.
  [patch 6]:
- vmware_tdx_hypercall_args remove in6/out6 arguments as excessive.
- vmware_tdx_hypercall return ULONG_MAX on error to mimic bad hypercall
  command error from the hypervisor.
- Replaced pr_warn by pr_warn_once as pointed by Kirill Shutemov.
- Fixed the warning reported by Intel's kernel test robot.
- Added the comment describing VMware TDX hypercall ABI.

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

Alexey Makhalov (6):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce VMware hypercall API
  ptp/vmware: Use VMware hypercall API
  input/vmmouse: Use VMware hypercall API
  drm/vmwgfx: Use VMware hypercall API
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 364 --
 arch/x86/kernel/cpu/vmware.c  | 116 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 --
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 ---
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 598 insertions(+), 525 deletions(-)

-- 
2.39.0

Re: [PATCH v3 2/6] x86/vmware: Introduce vmware_hypercall API

[Alexey Makhalov]

On 12/19/23 4:51 PM, kirill.shute...@linux.intel.com wrote:

On Tue, Dec 19, 2023 at 04:17:40PM -0800, Alexey Makhalov wrote:



On 12/19/23 3:20 PM, kirill.shute...@linux.intel.com wrote:

On Tue, Dec 19, 2023 at 01:57:47PM -0800, Alexey Makhalov wrote:

+static inline
+unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)

...

+static inline
+unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2)

...

+static inline
+unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2,
+   uint32_t *out3)

...

+static inline
+unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5, uint32_t *out2)

...

+static inline
+unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1,
+   unsigned long in3, uint32_t *out2,
+   uint32_t *out3, uint32_t *out4,
+   uint32_t *out5)

...

+static inline
+unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5, uint32_t *out1,
+   uint32_t *out2, uint32_t *out3)


Naming is weird. The number in the name doesn't help much as there seems
no system on how many of the parameters are ins and outs.


There was internal discussion on hypercall API naming. One of proposals was
using 2 digits - number of input and number of output arguments.
And it definitely looked weird. So, we agreed to have just single number  -
total number of arguments excluding cmd.


Have you considered naming them by number of input parameters? Number of
output parameters as demanded by users.

So vmware_hypercall4() will become vmware_hypercall1() and current
vmware_hypercall1() and vmware_hypercall3() will go away.

It is still awful, but /maybe/ better that this, I donno.



Deprecating vmware_hypercall1 and vmware_hypercall3 in favor of 
vmware_hypercall4 will generate less efficient code for the caller of 
first ones.
Using current vmware_hypercall4 instead of vmware_hypercall1 will force 
the caller to allocate additional variables (register or on stack 
memory) for hypercall asm inline to put additional output registers on. 
And specifically to 'usage' of *out3 - compiler will unnecessary 
'clobber' useful rdx, when hypervisor will keep it unchanged.


Unfortunately VMware hypercall ABI is not as beautiful as KVM one, 
especially in number of output arguments and their ordering. rbp 
register usage as an argument is a separate bummer((. So we have to work 
with what we have.


Current set of functions includes only 6 functions (for LB), which is 
the optimum between readability, maintainability and performance. It 
covers all current kernel callers and all new callers from yet to be 
upstreamed patches that we have in Photon OS including 2 patches for x86 
and arm64 guest support.


Regards,
--Alexey

Re: [PATCH v3 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

On 12/19/23 5:00 PM, kirill.shute...@linux.intel.com wrote:

On Tue, Dec 19, 2023 at 04:27:51PM -0800, Alexey Makhalov wrote:



On 12/19/23 3:23 PM, kirill.shute...@linux.intel.com wrote:

On Tue, Dec 19, 2023 at 01:57:51PM -0800, Alexey Makhalov wrote:

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 3aa1adaed18f..ef07ab7a07e1 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -428,6 +428,30 @@ static bool __init vmware_legacy_x2apic_available(void)
(eax & BIT(VCPU_LEGACY_X2APIC));
   }
+#ifdef CONFIG_INTEL_TDX_GUEST
+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+  struct tdx_module_args *args)
+{
+   if (!hypervisor_is_type(X86_HYPER_VMWARE))
+   return 0;


BTW, don't you want to warn here to? We don't expect vmware hypercalls to
be called by non-vmware guest, do we?


The answer is below...




+
+   if (cmd & ~VMWARE_CMD_MASK) {
+   pr_warn("Out of range command %x\n", cmd);
+   return 0;


Is zero success? Shouldn't it be an error?


VMware hypercalls do not have a standard way of signalling an error.
To generalize expectations from the caller perspective of any existing
hypercalls: error (including hypercall is not supported or disabled) is when
return value is 0 and out1/2 are unchanged or equal to in1/in2.


You are talking about signaling errors over hypercall transport. But if
kernel can see that something is wrong why cannot it signal the issue
clearly to caller. It is going to be in-kernel convention.These "return 0" blocks were introduced to protect against non-vmware 
guest or arbitrary modules trying to use __tdx_hypercall via exported 
vmware_tdx_hypercall function. In this case, it will be NOOP behavior 
with no or minor side effects.


From valid vmware_hypercall callers point of view, there is no such 
thing as a hypercall not available. Once guest detection code recognizes 
VMWare hypervisor via cpuid, it will start using hypercalls in 
accordance to per-call API.


Valid VMware guest code will never go into first return, no warning 
required.
Second return can be hit in rare cases for example during development 
phase, or, hypothetical case, when cmd was dynamically generated.

That's why we have a warning warning only for the second condition.

While speaking about it, I'm started to lean towards your 
recommendation. Yes, we can return standard error code such as -EINVAL 
or just -1 instead of "return 0" in this function. And it will be 
algorithmically correct. As if Vmware guest caller provide out of range 
cmd - it is not documented behavior.


Speaking of additional in-kernel convention for passing additional 
parameter if error happens, it does not makes sense for me because:
1. existing caller codes analyze output argument to recognize error 
error response from the hypervisor. Adding one additional check for 
in-kernel errors just for TDX path which will be never hit by valid code 
in production is an unnecessary overhead.
2. It will definitely add an overhead as an error code will require one 
more output value, or out0 should be moved from return in-register value 
to return by pointer function argument.


Summarizing, overloading vmware_tdx_hypercall return value by arg0 (from 
the hypervisor) and kernel error (-1 or any other) seems like reasonable 
change.




And to very least, it has to be pr_warn_once().


Good catch! Will change it.

Thanks,
--Alexey

Re: [PATCH v3 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

On 12/19/23 3:23 PM, kirill.shute...@linux.intel.com wrote:

On Tue, Dec 19, 2023 at 01:57:51PM -0800, Alexey Makhalov wrote:

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 3aa1adaed18f..ef07ab7a07e1 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -428,6 +428,30 @@ static bool __init vmware_legacy_x2apic_available(void)
(eax & BIT(VCPU_LEGACY_X2APIC));
  }
  
+#ifdef CONFIG_INTEL_TDX_GUEST

+unsigned long vmware_tdx_hypercall(unsigned long cmd,
+  struct tdx_module_args *args)
+{
+   if (!hypervisor_is_type(X86_HYPER_VMWARE))
+   return 0;
+
+   if (cmd & ~VMWARE_CMD_MASK) {
+   pr_warn("Out of range command %x\n", cmd);
+   return 0;


Is zero success? Shouldn't it be an error?


VMware hypercalls do not have a standard way of signalling an error.
To generalize expectations from the caller perspective of any existing 
hypercalls: error (including hypercall is not supported or disabled) is 
when return value is 0 and out1/2 are unchanged or equal to in1/in2.


All existing vmware_hypercall callers will gracefully handle returned 0.
But they should never hit this path, as 0 bail out was introduced as a 
protection for the case where exported vmware_tdx_hypercall is used by 
random caller (not following VMware hypercall ABI).





+   }
+
+   args->r10 = VMWARE_TDX_VENDOR_LEAF;
+   args->r11 = VMWARE_TDX_HCALL_FUNC;
+   args->r12 = VMWARE_HYPERVISOR_MAGIC;
+   args->r13 = cmd;
+
+   __tdx_hypercall(args);
+
+   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)
--
2.39.0

Re: [PATCH v3 2/6] x86/vmware: Introduce vmware_hypercall API

[Alexey Makhalov]

On 12/19/23 3:20 PM, kirill.shute...@linux.intel.com wrote:

On Tue, Dec 19, 2023 at 01:57:47PM -0800, Alexey Makhalov wrote:

+static inline
+unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)

...

+static inline
+unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2)

...

+static inline
+unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2,
+   uint32_t *out3)

...

+static inline
+unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5, uint32_t *out2)

...

+static inline
+unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1,
+   unsigned long in3, uint32_t *out2,
+   uint32_t *out3, uint32_t *out4,
+   uint32_t *out5)

...

+static inline
+unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5, uint32_t *out1,
+   uint32_t *out2, uint32_t *out3)


Naming is weird. The number in the name doesn't help much as there seems
no system on how many of the parameters are ins and outs.


There was internal discussion on hypercall API naming. One of proposals 
was using 2 digits - number of input and number of output arguments.
And it definitely looked weird. So, we agreed to have just single number 
 - total number of arguments excluding cmd.




Why these combinations of ins/outs are supported?


VMware hypercalls can use up to 6 ins and 6 outs for LB and 7 ins and 7 
outs for HB calls. The mapping to x86 registers is below:

in0/out0 - rax
in1/out1 - rbx
in2/out2 - rcx
in3/out3 - rdx
in4/out4 - rsi
in5/out5 - rdi
in6/out6 - rbp (only used in high bandwidth hypercalls)
args 0, 2 and 6 are remapped to r12, r13 and r14 for TDX.

There is a standard on some arguments such as cmd on in2, magic on in0 
and output value is on out0. While other arguments are not standardized 
across hypercall.


Theoreticaly max hypercall, in term of number of arguments:
vmware_hypercall9(cmd, in1, in3, in4, in5, *out1, *out2, *out3, *out4, 
*out5)

But there is no such called in a linux kernel.

Current combination of hypercalls covers all current and future (not yet 
upstreamed) callers, with round up to next number in some cases.





And as an outsider, I'm curious where in2 got lost :P


'lost' arguments:
in0 - indirectly initialized inside hypercall function.
out0 - return value from the hypercall.
[LB hypercalls] in2 <- input cmd
[HB hypercalls] in1 <- input cmd


Regards,
--Alexey

[PATCH v3 4/6] input/vmmouse: Use vmware_hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 
---
 drivers/input/mouse/vmmouse.c | 76 ++-
 1 file changed, 22 insertions(+), 54 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ea9eff7c8099..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,28 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -145,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -172,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -247,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -271,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 
/*
 * Try enabling the device. If successful, we should be able to
 * read valid version ID bac

[PATCH v3 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

From: Alexey Makhalov 

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 83 +++
 arch/x86/kernel/cpu/vmware.c  | 24 ++
 2 files changed, 107 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 719e41260ece..cad6f5b371a8 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -34,12 +34,65 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fU
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern unsigned long vmware_tdx_hypercall(unsigned long cmd,
+ struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses rax (arg0) and rcx (arg2), while the use of
+ * rbp (arg6) is discouraged by the TDX specification. Therefore, we
+ * remap those registers to r12, r13 and r14, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall_args(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5, unsigned long in6,
+   uint32_t *out1, uint32_t *out2,
+   uint32_t *out3, uint32_t *out4,
+   uint32_t *out5, uint32_t *out6)
+{
+   unsigned long ret;
+
+   struct tdx_module_args args = {
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   .r14 = in6,
+   };
+
+   ret = vmware_tdx_hypercall(cmd, );
+
+   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;
+   if (out6)
+   *out6 = args.r14;
+
+   return ret;
+}
+
 /*
  * 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.
@@ -67,6 +120,11 @@ 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_args(cmd, in1, 0, 0, 0, 0,
+NULL, NULL, NULL,
+NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -85,6 +143,11 @@ 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_args(cmd, in1, 0, 0, 0, 0,
+out1, out2, NULL,
+NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -104,6 +167,11 @@ 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_args(cmd, in1, 0, 0, 0, 0,
+out1, out2, out3,
+NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -123,6 +191,11 @@ 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_args(cmd, in1, in3, in4, in5, 0,
+NULL, out2, NULL,
+NULL, NULL, NULL);
+
   

[PATCH v3 2/6] x86/vmware: Introduce vmware_hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Introduce vmware_hypercall family of functions. It is a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

The API consists of vmware_hypercallX and vmware_hypercall_hb_{out,in}
set of functions by analogy with KVM hypercall API. Architecture
specific implementation is hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h | 262 ++
 arch/x86/kernel/cpu/vmware.c  |  35 ++---
 2 files changed, 220 insertions(+), 77 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 3636faa8b4fe..719e41260ece 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -40,69 +40,219 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t"   \
+ "movw %[port], %%dx\n\t"  \
+ "inl (%%dx), %%eax\n\t"   \
+ "jmp 3f\n\t"  \
+ "1: vmmcall\n\t"  \
+ "jmp 3f\n\t"  \
+ "2: vmcall\n\t"   \
+ "3:\n\t", \
+ "movw %[port], %%dx\n\t"  \
+ "inl (%%dx), %%eax", X86_FEATURE_HYPERVISOR,  \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
 
+static inline
+unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
+{
+   unsigned long out0;
+
+   asm_inline volatile (VMWARE_HYPERCALL
+   : "=a" (out0)
+   : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ [mode] "m" (vmware_hypercall_mode),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (0)
+   : "cc", "memory");
+   return out0;
+}
+
+static inline
+unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2)
+{
+   unsigned long out0;
+
+   asm_inline volatile (VMWARE_HYPERCALL
+   : "=a" (out0), "=b" (*out1), "=c" (*out2)
+   : [port] &q

[PATCH v3 3/6] ptp/vmware: Use vmware_hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 12 +++-
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 27c5547aa8a9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,15 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v3 5/6] drm/vmwgfx: Use vmware_hypercall API

[Alexey Makhalov]

From: Alexey Makhalov 

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall. And keep it here until introduction of ARM64
VMWare hypervisor interface.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 3 files changed, 197 insertions(+), 358 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SEND

[PATCH v3 1/6] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

From: Alexey Makhalov 

Move VMware hypercall macros to vmware.h. This is a prerequisite for
the introduction of vmware_hypercall API. No functional changes besides
exporting vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 69 ++-
 arch/x86/kernel/cpu/vmware.c  | 57 +++--
 2 files changed, 66 insertions(+), 60 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..3636faa8b4fe 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,37 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
+ * number if the I/O port method is used.
  *
  * In short, new driver code should strictly use the new definition of
  * %dx content.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564d5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
+
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +66,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   br

[PATCH v3 0/6] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v2->v3 changes: (no functional changes in patches 1-5)
- Improved commit message in patches 1, 2 and 5 as was suggested by
  Borislav Petkov.
- To address Dave Hansen's concern, patch 6 was reorganized to avoid
  exporting bare __tdx_hypercall and to make exported vmware_tdx_hypercall
  VMWare guest specific.

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

Alexey Makhalov (6):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce vmware_hypercall API
  ptp/vmware: Use vmware_hypercall API
  input/vmmouse: Use vmware_hypercall API
  drm/vmwgfx: Use vmware_hypercall API
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 338 --
 arch/x86/kernel/cpu/vmware.c  | 116 +++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 ---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 577 insertions(+), 520 deletions(-)

-- 
2.39.0

[PATCH] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

From: Alexey Makhalov 

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 83 +++
 arch/x86/kernel/cpu/vmware.c  | 22 ++
 2 files changed, 105 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 719e41260ece..04c698b905ab 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -34,12 +34,65 @@
 #define VMWARE_CMD_GETHZ   45
 #define VMWARE_CMD_GETVCPU_INFO68
 #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_MASK0xf007fULL
 
 #define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
 #define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern unsigned long vmware_tdx_hypercall(struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses rax (arg0) and rcx (arg2), while the use of
+ * rbp (arg6) is discouraged by the TDX specification. Therefore, we
+ * remap those registers to r12, r13 and r14, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall_args(unsigned long cmd, unsigned long in1,
+   unsigned long in3, unsigned long in4,
+   unsigned long in5, unsigned long in6,
+   uint32_t *out1, uint32_t *out2,
+   uint32_t *out3, uint32_t *out4,
+   uint32_t *out5, uint32_t *out6)
+{
+   unsigned long ret;
+
+   struct tdx_module_args args = {
+   .r13 = cmd,
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   .r14 = in6,
+   };
+
+   ret = vmware_tdx_hypercall();
+
+   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;
+   if (out6)
+   *out6 = args.r14;
+
+   return ret;
+}
+
 /*
  * 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.
@@ -67,6 +120,11 @@ 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_args(cmd, in1, 0, 0, 0, 0,
+NULL, NULL, NULL,
+NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -85,6 +143,11 @@ 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_args(cmd, in1, 0, 0, 0, 0,
+out1, out2, NULL,
+NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -104,6 +167,11 @@ 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_args(cmd, in1, 0, 0, 0, 0,
+out1, out2, out3,
+NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -123,6 +191,11 @@ 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_args(cmd, in1, in3, in4, in5, 0,
+NULL, out2, NULL,
+NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
  

Re: [PATCH] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

On 12/7/23 9:12 AM, Dave Hansen wrote:

On 12/5/23 23:15, Alexey Makhalov wrote:

+#ifdef CONFIG_INTEL_TDX_GUEST
+/* Export tdx hypercall and allow it only for VMware guests. */
+void vmware_tdx_hypercall_args(struct tdx_module_args *args)
+{
+   if (hypervisor_is_type(X86_HYPER_VMWARE))
+   __tdx_hypercall(args);
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall_args);
+#endif


I think this is still too generic.  This still allows anything setting
X86_HYPER_VMWARE to make any TDX hypercall.

I'd *much* rather you export something like vmware_tdx_hypercall() or
even the high-level calls like hypervisor_ppn_reset_all().  The higher
level and more specialized the interface, the less likely it is to be
abused.


Dave, I understood your point. Please take a look on the next version of 
the patch.


I export vmware_tdx_hypercall(), while vmware_tdx_hypercall_args() is a
static inline wrapper on top.
Most of the vmware hypercall logic plus sanity checks are now in 
exported function. While only input and output argument handling remains 
in the wrapper to allow compiler optimization for hypercalls with few 
argument. Exporting vmware_tdx_hypercall1, vmware_tdx_hypercall3, and so 
on is not an option either.


Regards,
--Alexey

[PATCH] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

From: Alexey Makhalov 

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +++
 arch/x86/kernel/cpu/vmware.c  | 10 +
 2 files changed, 82 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 17091eba68cb..cd58ff8ef1af 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -40,6 +40,54 @@
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1AF7E4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern void vmware_tdx_hypercall_args(struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses rax (arg0) and rcx (arg2), while the use of
+ * rbp (arg6) is discouraged by the TDX specification. Therefore, we
+ * remap those registers to r12, r13 and r14, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall(unsigned long cmd, unsigned long in1,
+  unsigned long in3, unsigned long in4,
+  unsigned long in5, unsigned long in6,
+  uint32_t *out1, uint32_t *out2,
+  uint32_t *out3, uint32_t *out4,
+  uint32_t *out5, uint32_t *out6)
+{
+   struct tdx_module_args args = {
+   .r10 = VMWARE_TDX_VENDOR_LEAF,
+   .r11 = VMWARE_TDX_HCALL_FUNC,
+   .r12 = VMWARE_HYPERVISOR_MAGIC,
+   .r13 = cmd,
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   .r14 = in6,
+   };
+
+   vmware_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;
+   if (out6)
+   *out6 = args.r14;
+
+   return args.r12;
+}
+
 /*
  * 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.
@@ -67,6 +115,10 @@ 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, 0, NULL, NULL,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -85,6 +137,10 @@ 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, 0, out1, out2,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -104,6 +160,10 @@ 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, 0, out1, out2,
+   out3, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -123,6 +183,10 @@ 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, 0, NULL,
+   out2, NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -145,6 +209,10 @@ 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, 0, NULL, out2,
+   out3, out4, out5, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2), "=d" (*out

Re: [PATCH v2 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

On 12/5/23 3:03 PM, Dave Hansen wrote:

On 12/5/23 13:41, Alexey Makhalov wrote:

I don't really like it much.  This does a generic thing (make a TDX
hypercall) with a specific name ("vmware_").  If you want to make an
argument that a certain chunk of the __tdx_hypercall() space is just for
VMWare and you also add a VMWare-specific check and then export *that*,
it might be acceptable.

But I don't want random modules able to make random, unrestricted TDX
hypercalls.  That's asking for trouble.


Considering exporting of __tdx_hypercall for random modules is not an
option, what VMware specific checks you are suggesting?


Make sure it can only be called running on VMWare guests.  A check for
X86_HYPER_VMWARE seems simple enough.

Second, unless the space is *HUGE*, you want to be exporting things like
__vmware_platform() or vmware_legacy_x2apic_available(), *NOT* the
underlying hypercall functions.

We want to make sure that the interfaces are well defined and bounded.


Thanks Dave and Tim for your suggestions. I followed Dave recommendation 
to have a simple check for X86_HYPER_VMWARE.


Please review patch 6, which I'll send shortly.

Thanks,
--Alexey

--
This electronic communication and the information and any files transmitted 
with it, or attached to it, are confidential and are intended solely for 
the use of the individual or entity to whom it is addressed and may contain 
information that is confidential, legally privileged, protected by privacy 
laws, or otherwise restricted from disclosure to anyone else. If you are 
not the intended recipient or the person responsible for delivering the 
e-mail to the intended recipient, you are hereby notified that any use, 
copying, distributing, dissemination, forwarding, printing, or copying of 
this e-mail is strictly prohibited. If you received this e-mail in error, 
please return the e-mail to the sender, delete it from your computer, and 
destroy any printed copy of it.

Re: [PATCH v2 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

On 12/5/23 1:24 PM, Dave Hansen wrote:

On 12/4/23 02:31, Borislav Petkov wrote:

On Fri, Dec 01, 2023 at 03:24:52PM -0800, Alexey Makhalov wrote:

+#ifdef CONFIG_INTEL_TDX_GUEST
+/* __tdx_hypercall() is not exported. So, export the wrapper */
+void vmware_tdx_hypercall_args(struct tdx_module_args *args)
+{
+   __tdx_hypercall(args);
+}
+EXPORT_SYMBOL_GPL(vmware_tdx_hypercall_args);

Uuuh, lovely. I'd like to see what the TDX folks think about this
export first.


I don't really like it much.  This does a generic thing (make a TDX
hypercall) with a specific name ("vmware_").  If you want to make an
argument that a certain chunk of the __tdx_hypercall() space is just for
VMWare and you also add a VMWare-specific check and then export *that*,
it might be acceptable.

But I don't want random modules able to make random, unrestricted TDX
hypercalls.  That's asking for trouble.


Considering exporting of __tdx_hypercall for random modules is not an 
option, what VMware specific checks you are suggesting?


--
This electronic communication and the information and any files transmitted 
with it, or attached to it, are confidential and are intended solely for 
the use of the individual or entity to whom it is addressed and may contain 
information that is confidential, legally privileged, protected by privacy 
laws, or otherwise restricted from disclosure to anyone else. If you are 
not the intended recipient or the person responsible for delivering the 
e-mail to the intended recipient, you are hereby notified that any use, 
copying, distributing, dissemination, forwarding, printing, or copying of 
this e-mail is strictly prohibited. If you received this e-mail in error, 
please return the e-mail to the sender, delete it from your computer, and 
destroy any printed copy of it.

Re: [PATCH v2 5/6] drm/vmwgfx: Use vmware_hypercall API

[Alexey Makhalov]

On 12/5/23 12:27 PM, Borislav Petkov wrote:

On Fri, Dec 01, 2023 at 03:24:51PM -0800, Alexey Makhalov wrote:

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall here for now. The move of these functions to
arch/arm64/include/asm/vmware.h as well as removal of
drivers/gpu/drm/vmwgfx/vmwgfx_msg_{x86,arm64}.h header files will
be performed in the follow up patchset.

Same note as for patch 1 - no commit order in git.


Thanks for the review Borislav. I'll address your comments regarding 
description messages
in v3. It is going to be sent from @broadcom.com and may take some time 
to align with

corporate legal stuff.

--Alexey

--
This electronic communication and the information and any files transmitted 
with it, or attached to it, are confidential and are intended solely for 
the use of the individual or entity to whom it is addressed and may contain 
information that is confidential, legally privileged, protected by privacy 
laws, or otherwise restricted from disclosure to anyone else. If you are 
not the intended recipient or the person responsible for delivering the 
e-mail to the intended recipient, you are hereby notified that any use, 
copying, distributing, dissemination, forwarding, printing, or copying of 
this e-mail is strictly prohibited. If you received this e-mail in error, 
please return the e-mail to the sender, delete it from your computer, and 
destroy any printed copy of it.

[PATCH v2 5/6] drm/vmwgfx: Use vmware_hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant
of vmware_hypercall here for now. The move of these functions to
arch/arm64/include/asm/vmware.h as well as removal of
drivers/gpu/drm/vmwgfx/vmwgfx_msg_{x86,arm64}.h header files will
be performed in the follow up patchset.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 3 files changed, 197 insertions(+), 358 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, s

[PATCH v2 2/6] x86/vmware: Introduce vmware_hypercall API

[Alexey Makhalov]

Introducing vmware_hypercall family of functions as a common
implementation to be used by the VMware guest code and virtual
device drivers in architecture independent manner.

By analogy with KVM hypercall API, vmware_hypercallX and
vmware_hypercall_hb_{out,in} set of functions was added to
achieve that. Architecture specific implementation should be
hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
earlier during the boot when alternatives are not yet applied.
This logic was inherited from VMWARE_CMD from the commit mentioned
above. Default alternative code was optimized by size to reduce
excessive nop alignment once alternatives are applied. Total
default code size is 26 bytes, in worse case (3 bytes alternative)
remaining 23 bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 arch/x86/include/asm/vmware.h | 262 ++
 arch/x86/kernel/cpu/vmware.c  |  35 ++---
 2 files changed, 220 insertions(+), 77 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 8cabf4a577bf..17091eba68cb 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -40,69 +40,219 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t"   \
+ "movw %[port], %%dx\n\t"  \
+ "inl (%%dx), %%eax\n\t"   \
+ "jmp 3f\n\t"  \
+ "1: vmmcall\n\t"  \
+ "jmp 3f\n\t"  \
+ "2: vmcall\n\t"   \
+ "3:\n\t", \
+ "movw %[port], %%dx\n\t"  \
+ "inl (%%dx), %%eax", X86_FEATURE_HYPERVISOR,  \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
 
+static inline
+unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
+{
+   unsigned long out0;
+
+   asm_inline volatile (VMWARE_HYPERCALL
+   : "=a" (out0)
+   : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ [mode] "m" (vmware_hypercall_mode),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (0)
+   : "cc", "memory");
+   return out0;
+}
+
+static inline
+unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2)
+{
+   unsigned long out0;
+
+   asm_inline volatile (VMWARE_HYPERCALL
+   : "=a" (out0), "=b" (*out1), "=c" (*out2)
+   : [port] "i" (VMWARE_HYPERVISOR_PORT),
+   

[PATCH v2 4/6] input/vmmouse: Use vmware_hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Zack Rusin 
Acked-by: Dmitry Torokhov 

---
 drivers/input/mouse/vmmouse.c | 76 ++-
 1 file changed, 22 insertions(+), 54 deletions(-)

diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index ea9eff7c8099..fb1d986a6895 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -21,19 +21,16 @@
 #include "psmouse.h"
 #include "vmmouse.h"
 
-#define VMMOUSE_PROTO_MAGIC0x564D5868U
-
 /*
  * Main commands supported by the vmmouse hypervisor port.
  */
-#define VMMOUSE_PROTO_CMD_GETVERSION   10
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_DATA  39
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_STATUS40
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND   41
-#define VMMOUSE_PROTO_CMD_ABSPOINTER_RESTRICT   86
+#define VMWARE_CMD_ABSPOINTER_DATA 39
+#define VMWARE_CMD_ABSPOINTER_STATUS   40
+#define VMWARE_CMD_ABSPOINTER_COMMAND  41
+#define VMWARE_CMD_ABSPOINTER_RESTRICT 86
 
 /*
- * Subcommands for VMMOUSE_PROTO_CMD_ABSPOINTER_COMMAND
+ * Subcommands for VMWARE_CMD_ABSPOINTER_COMMAND
  */
 #define VMMOUSE_CMD_ENABLE 0x45414552U
 #define VMMOUSE_CMD_DISABLE0x00f5U
@@ -76,28 +73,6 @@ struct vmmouse_data {
char dev_name[128];
 };
 
-/*
- * Hypervisor-specific bi-directional communication channel
- * implementing the vmmouse protocol. Should never execute on
- * bare metal hardware.
- */
-#define VMMOUSE_CMD(cmd, in1, out1, out2, out3, out4)  \
-({ \
-   unsigned long __dummy1, __dummy2;   \
-   __asm__ __volatile__ (VMWARE_HYPERCALL :\
-   "=a"(out1), \
-   "=b"(out2), \
-   "=c"(out3), \
-   "=d"(out4), \
-   "=S"(__dummy1), \
-   "=D"(__dummy2) :\
-   "a"(VMMOUSE_PROTO_MAGIC),   \
-   "b"(in1),   \
-   "c"(VMMOUSE_PROTO_CMD_##cmd),   \
-   "d"(0) :\
-   "memory");  \
-})
-
 /**
  * vmmouse_report_button - report button state on the correct input device
  *
@@ -145,14 +120,12 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
struct input_dev *abs_dev = priv->abs_dev;
struct input_dev *pref_dev;
u32 status, x, y, z;
-   u32 dummy1, dummy2, dummy3;
unsigned int queue_length;
unsigned int count = 255;
 
while (count--) {
/* See if we have motion data. */
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) == VMMOUSE_ERROR) {
psmouse_err(psmouse, "failed to fetch status data\n");
/*
@@ -172,7 +145,8 @@ static psmouse_ret_t vmmouse_report_events(struct psmouse 
*psmouse)
}
 
/* Now get it */
-   VMMOUSE_CMD(ABSPOINTER_DATA, 4, status, x, y, z);
+   status = vmware_hypercall4(VMWARE_CMD_ABSPOINTER_DATA, 4,
+  , , );
 
/*
 * And report what we've got. Prefer to report button
@@ -247,14 +221,10 @@ static psmouse_ret_t vmmouse_process_byte(struct psmouse 
*psmouse)
 static void vmmouse_disable(struct psmouse *psmouse)
 {
u32 status;
-   u32 dummy1, dummy2, dummy3, dummy4;
-
-   VMMOUSE_CMD(ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE,
-   dummy1, dummy2, dummy3, dummy4);
 
-   VMMOUSE_CMD(ABSPOINTER_STATUS, 0,
-   status, dummy1, dummy2, dummy3);
+   vmware_hypercall1(VMWARE_CMD_ABSPOINTER_COMMAND, VMMOUSE_CMD_DISABLE);
 
+   status = vmware_hypercall1(VMWARE_CMD_ABSPOINTER_STATUS, 0);
if ((status & VMMOUSE_ERROR) != VMMOUSE_ERROR)
psmouse_warn(psmouse, "failed to disable vmmouse device\n");
 }
@@ -271,26 +241,24 @@ static void vmmouse_disable(struct psmouse *psmouse)
 static int vmmouse_enable(struct psmouse *psmouse)
 {
u32 status, version;
-   u32 dummy1, dummy2, dummy3, dummy4;
 
/*
 * Try enabling the device. If successful, we should be able to
 * read valid version ID bac

[PATCH v2 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 72 +++
 arch/x86/kernel/cpu/vmware.c  |  9 +
 2 files changed, 81 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 17091eba68cb..cd58ff8ef1af 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -40,6 +40,54 @@
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1AF7E4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern void vmware_tdx_hypercall_args(struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses rax (arg0) and rcx (arg2), while the use of
+ * rbp (arg6) is discouraged by the TDX specification. Therefore, we
+ * remap those registers to r12, r13 and r14, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall(unsigned long cmd, unsigned long in1,
+  unsigned long in3, unsigned long in4,
+  unsigned long in5, unsigned long in6,
+  uint32_t *out1, uint32_t *out2,
+  uint32_t *out3, uint32_t *out4,
+  uint32_t *out5, uint32_t *out6)
+{
+   struct tdx_module_args args = {
+   .r10 = VMWARE_TDX_VENDOR_LEAF,
+   .r11 = VMWARE_TDX_HCALL_FUNC,
+   .r12 = VMWARE_HYPERVISOR_MAGIC,
+   .r13 = cmd,
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   .r14 = in6,
+   };
+
+   vmware_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;
+   if (out6)
+   *out6 = args.r14;
+
+   return args.r12;
+}
+
 /*
  * 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.
@@ -67,6 +115,10 @@ 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, 0, NULL, NULL,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -85,6 +137,10 @@ 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, 0, out1, out2,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -104,6 +160,10 @@ 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, 0, out1, out2,
+   out3, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -123,6 +183,10 @@ 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, 0, NULL,
+   out2, NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -145,6 +209,10 @@ 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, 0, NULL, out2,
+   out3, out4, out5, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2), "=d" (*out

[PATCH v2 3/6] ptp/vmware: Use vmware_hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
Reviewed-by: Jeff Sipek 
---
 drivers/ptp/ptp_vmw.c | 12 +++-
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 27c5547aa8a9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,15 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH v2 0/6] VMware hypercalls enhancements

[Alexey Makhalov]

From: Alexey Makhalov 

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

v1->v2 changes (no functional changes):
- Improved commit message in patches 2 and 5.
- Added Reviewed-by for all patches.
- Added Ack from Dmitry Torokhov in patch 4. No fixes regarding reported
  by Simon Horman gcc error in this patch.

x86 maintainers, please consider merging this patch set in your branch. 

Alexey Makhalov (6):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce vmware_hypercall API
  ptp/vmware: Use vmware_hypercall API
  input/vmmouse: Use vmware_hypercall API
  drm/vmwgfx: Use vmware_hypercall API
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 327 --
 arch/x86/kernel/cpu/vmware.c  | 101 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 551 insertions(+), 520 deletions(-)

-- 
2.39.0

[PATCH v2 1/6] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h as a preparation step
for the next commit. No functional changes besides exporting
vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
Reviewed-by: Nadav Amit 
---
 arch/x86/include/asm/vmware.h | 69 ++-
 arch/x86/kernel/cpu/vmware.c  | 57 +++--
 2 files changed, 66 insertions(+), 60 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..8cabf4a577bf 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,37 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
+ * number if the I/O port method is used.
  *
  * In short, new driver code should strictly use the new definition of
  * %dx content.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564D5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
+
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +66,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break;

Re: [PATCH 4/6] input/vmmouse: Use vmware_hypercall API

[Alexey Makhalov]

On Nov 24, 2023, at 11:46 AM, Simon Horman  wrote:
> 
> On Wed, Nov 22, 2023 at 03:30:49PM -0800, Alexey Makhalov wrote:
>> Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
>> Eliminate arch specific code. No functional changes intended.
>> 
>> Signed-off-by: Alexey Makhalov 
> 
> Hi Alexey,
> 
> it is not strictly related to this patch, but I notice than an x86_64
> allmodconfig build with W=1 using gcc-13 fails to compile this file.
> 
> It appears that the problem relates to both priv->phys and
> psmouse->ps2dev.serio->phys being 32 bytes.
> 
> 
> drivers/input/mouse/vmmouse.c: In function ‘vmmouse_init’:
> drivers/input/mouse/vmmouse.c:455:53: error: ‘/input1’ directive output may 
> be truncated writing 7 bytes into a region of size between 1 and 32 
> [-Werror=format-truncation=]
>  455 | snprintf(priv->phys, sizeof(priv->phys), "%s/input1",
>  | ^~~
> drivers/input/mouse/vmmouse.c:455:9: note: ‘snprintf’ output between 8 and 39 
> bytes into a destination of size 32
>  455 | snprintf(priv->phys, sizeof(priv->phys), "%s/input1",
>  | ^
>  456 |  psmouse->ps2dev.serio->phys);
>  |  
> 
> ...

Hi Simon, thanks for reporting the issue.
Zack, please take a look.

—Alexey

[PATCH 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 72 +++
 arch/x86/kernel/cpu/vmware.c  |  9 +
 2 files changed, 81 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 17091eba68cb..cd58ff8ef1af 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -40,6 +40,54 @@
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1AF7E4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern void vmware_tdx_hypercall_args(struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses rax (arg0) and rcx (arg2), while the use of
+ * rbp (arg6) is discouraged by the TDX specification. Therefore, we
+ * remap those registers to r12, r13 and r14, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall(unsigned long cmd, unsigned long in1,
+  unsigned long in3, unsigned long in4,
+  unsigned long in5, unsigned long in6,
+  uint32_t *out1, uint32_t *out2,
+  uint32_t *out3, uint32_t *out4,
+  uint32_t *out5, uint32_t *out6)
+{
+   struct tdx_module_args args = {
+   .r10 = VMWARE_TDX_VENDOR_LEAF,
+   .r11 = VMWARE_TDX_HCALL_FUNC,
+   .r12 = VMWARE_HYPERVISOR_MAGIC,
+   .r13 = cmd,
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   .r14 = in6,
+   };
+
+   vmware_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;
+   if (out6)
+   *out6 = args.r14;
+
+   return args.r12;
+}
+
 /*
  * 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.
@@ -67,6 +115,10 @@ 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, 0, NULL, NULL,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -85,6 +137,10 @@ 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, 0, out1, out2,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -104,6 +160,10 @@ 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, 0, out1, out2,
+   out3, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -123,6 +183,10 @@ 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, 0, NULL,
+   out2, NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -145,6 +209,10 @@ 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, 0, NULL, out2,
+   out3, out4, out5, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2), "=d" (*out3), "=S" (*out4),
   

[PATCH 5/6] drm/vmwgfx: Use vmware_hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code.

drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h: implement arm64 variant of
vmware_hypercall here. To be moved to arch/arm64/include/asm/vmware.h
later.

Signed-off-by: Alexey Makhalov 
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 3 files changed, 197 insertions(+), 358 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c 
b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 2651fe0ef518..1f15990d3934 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -48,8 +48,6 @@
 
 #define RETRIES 3
 
-#define VMW_HYPERVISOR_MAGIC0x564D5868
-
 #define VMW_PORT_CMD_MSG30
 #define VMW_PORT_CMD_HB_MSG 0
 #define VMW_PORT_CMD_OPEN_CHANNEL  (MSG_TYPE_OPEN << 16 | VMW_PORT_CMD_MSG)
@@ -104,20 +102,18 @@ static const char* const 
mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] =
  */
 static int vmw_open_channel(struct rpc_channel *channel, unsigned int protocol)
 {
-   unsigned long eax, ebx, ecx, edx, si = 0, di = 0;
+   u32 ecx, edx, esi, edi;
 
-   VMW_PORT(VMW_PORT_CMD_OPEN_CHANNEL,
-   (protocol | GUESTMSG_FLAG_COOKIE), si, di,
-   0,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall6(VMW_PORT_CMD_OPEN_CHANNEL,
+ (protocol | GUESTMSG_FLAG_COOKIE), 0,
+ , , , );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
 
channel->channel_id  = HIGH_WORD(edx);
-   channel->cookie_high = si;
-   channel->cookie_low  = di;
+   channel->cookie_high = esi;
+   channel->cookie_low  = edi;
 
return 0;
 }
@@ -133,17 +129,13 @@ static int vmw_open_channel(struct rpc_channel *channel, 
unsigned int protocol)
  */
 static int vmw_close_channel(struct rpc_channel *channel)
 {
-   unsigned long eax, ebx, ecx, edx, si, di;
-
-   /* Set up additional parameters */
-   si  = channel->cookie_high;
-   di  = channel->cookie_low;
+   u32 ecx;
 
-   VMW_PORT(VMW_PORT_CMD_CLOSE_CHANNEL,
-   0, si, di,
-   channel->channel_id << 16,
-   VMW_HYPERVISOR_MAGIC,
-   eax, ebx, ecx, edx, si, di);
+   vmware_hypercall5(VMW_PORT_CMD_CLOSE_CHANNEL,
+ 0, channel->channel_id << 16,
+ channel->cookie_high,
+ channel->cookie_low,
+ );
 
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0)
return -EINVAL;
@@ -163,24 +155,18 @@ static int vmw_close_channel(struct rpc_channel *channel)
 static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 const char *msg, bool hb)
 {
-   unsigned long si, di, eax, ebx, ecx, edx;
+   u32 ebx, ecx;
unsigned long msg_len = strlen(msg);
 
/* HB port can't access encrypted memory. */
if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
-   unsigned long bp = channel->cookie_high;
-   u32 channel_id = (channel->channel_id << 16);
-
-   si = (uintptr_t) msg;
-   di = channel->cookie_low;
-
-   VMW_PORT_HB_OUT(
+   vmware_hypercall_hb_out(
(MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG,
-   msg_len, si, di,
-   VMWARE_HYPERVISOR_HB | channel_id |
-   VMWARE_HYPERVISOR_OUT,
-   VMW_HYPERVISOR_MAGIC, bp,
-   eax, ebx, ecx, edx, si, di);
+   msg_len,
+   channel->channel_id << 16,
+   (uintptr_t) msg, channel->cookie_low,
+   channel->cookie_high,
+   );
 
return ebx;
}
@@ -194,14 +180,13 @@ static unsigned long vmw_port_hb_out(struct rpc_channel 
*channel,
memcpy(, msg, bytes);
msg_len -= bytes;
msg += bytes;
-   si = channel->cookie_high;
-   di = channel->cookie_low;
-
-   VMW_PORT(VMW_PORT_CMD_MSG | (MSG_TYPE_SENDPAYLOAD << 16),
-word, si, di,
-channel->channel_id << 16,
-VMW_HYPERVISOR_MAGIC,
-eax, ebx, ecx, edx, si, di);
+
+   vmware_hypercall5(VMW_PORT_CMD_MSG |
+ (MSG_TYPE_SENDPAYLOAD << 16),
+ word, channe

[PATCH 3/6] ptp/vmware: Use vmware_hypercall API

[Alexey Makhalov]

Switch from VMWARE_HYPERCALL macro to vmware_hypercall API.
Eliminate arch specific code. No functional changes intended.

Signed-off-by: Alexey Makhalov 
---
 drivers/ptp/ptp_vmw.c | 12 +++-
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
index 27c5547aa8a9..e5bb521b9b82 100644
--- a/drivers/ptp/ptp_vmw.c
+++ b/drivers/ptp/ptp_vmw.c
@@ -14,7 +14,6 @@
 #include 
 #include 
 
-#define VMWARE_MAGIC 0x564D5868
 #define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
 #define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
 
@@ -24,15 +23,10 @@ static struct ptp_clock *ptp_vmw_clock;
 
 static int ptp_vmw_pclk_read(u64 *ns)
 {
-   u32 ret, nsec_hi, nsec_lo, unused1, unused2, unused3;
-
-   asm volatile (VMWARE_HYPERCALL :
-   "=a"(ret), "=b"(nsec_hi), "=c"(nsec_lo), "=d"(unused1),
-   "=S"(unused2), "=D"(unused3) :
-   "a"(VMWARE_MAGIC), "b"(0),
-   "c"(VMWARE_CMD_PCLK_GETTIME), "d"(0) :
-   "memory");
+   u32 ret, nsec_hi, nsec_lo;
 
+   ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+   _hi, _lo);
if (ret == 0)
*ns = ((u64)nsec_hi << 32) | nsec_lo;
return ret;
-- 
2.39.0

[PATCH 1/6] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h as a preparation step
for the next commit. No functional changes besides exporting
vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 69 ++-
 arch/x86/kernel/cpu/vmware.c  | 57 +++--
 2 files changed, 66 insertions(+), 60 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..8cabf4a577bf 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,37 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
+ * number if the I/O port method is used.
  *
  * In short, new driver code should strictly use the new definition of
  * %dx content.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564D5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
+
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +66,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break;  \
+   default:   

[PATCH 0/6] VMware hypercalls enhancements

[Alexey Makhalov]

VMware hypercalls invocations were all spread out across the kernel
implementing same ABI as in-place asm-inline. With encrypted memory
and confidential computing it became harder to maintain every changes
in these hypercall implementations.

Intention of this patchset is to introduce arch independent VMware
hypercall API layer other subsystems such as device drivers can call
to, while hiding architecture specific implementation behind.

Second patch introduces the vmware_hypercall low and high bandwidth
families of functions, with little enhancements there.
Sixth patch adds tdx hypercall support

arm64 implementation of vmware_hypercalls is in drivers/gpu/drm/
vmwgfx/vmwgfx_msg_arm64.h and going to be moved to arch/arm64 with
a separate patchset with the introduction of VMware Linux guest
support for arm64.

No functional changes in drivers/input/mouse/vmmouse.c and
drivers/ptp/ptp_vmw.c

Alexey Makhalov (6):
  x86/vmware: Move common macros to vmware.h
  x86/vmware: Introduce vmware_hypercall API
  ptp/vmware: Use vmware_hypercall API
  input/vmmouse: Use vmware_hypercall API
  drm/vmwgfx: Use vmware_hypercall API
  x86/vmware: Add TDX hypercall support

 arch/x86/include/asm/vmware.h | 327 --
 arch/x86/kernel/cpu/vmware.c  | 101 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c   | 173 
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 197 +
 drivers/gpu/drm/vmwgfx/vmwgfx_msg_x86.h   | 185 
 drivers/input/mouse/vmmouse.c |  76 ++---
 drivers/ptp/ptp_vmw.c |  12 +-
 7 files changed, 551 insertions(+), 520 deletions(-)

-- 
2.39.0

[PATCH 6/6] x86/vmware: Add TDX hypercall support

[Alexey Makhalov]

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 
Signed-off-by: Tim Merrifield 
Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 72 +++
 arch/x86/kernel/cpu/vmware.c  |  9 +
 2 files changed, 81 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 17091eba68cb..cd58ff8ef1af 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -40,6 +40,54 @@
 
 extern u8 vmware_hypercall_mode;
 
+#define VMWARE_TDX_VENDOR_LEAF 0x1AF7E4909ULL
+#define VMWARE_TDX_HCALL_FUNC  1
+
+extern void vmware_tdx_hypercall_args(struct tdx_module_args *args);
+
+/*
+ * TDCALL[TDG.VP.VMCALL] uses rax (arg0) and rcx (arg2), while the use of
+ * rbp (arg6) is discouraged by the TDX specification. Therefore, we
+ * remap those registers to r12, r13 and r14, respectively.
+ */
+static inline
+unsigned long vmware_tdx_hypercall(unsigned long cmd, unsigned long in1,
+  unsigned long in3, unsigned long in4,
+  unsigned long in5, unsigned long in6,
+  uint32_t *out1, uint32_t *out2,
+  uint32_t *out3, uint32_t *out4,
+  uint32_t *out5, uint32_t *out6)
+{
+   struct tdx_module_args args = {
+   .r10 = VMWARE_TDX_VENDOR_LEAF,
+   .r11 = VMWARE_TDX_HCALL_FUNC,
+   .r12 = VMWARE_HYPERVISOR_MAGIC,
+   .r13 = cmd,
+   .rbx = in1,
+   .rdx = in3,
+   .rsi = in4,
+   .rdi = in5,
+   .r14 = in6,
+   };
+
+   vmware_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;
+   if (out6)
+   *out6 = args.r14;
+
+   return args.r12;
+}
+
 /*
  * 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.
@@ -67,6 +115,10 @@ 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, 0, NULL, NULL,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -85,6 +137,10 @@ 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, 0, out1, out2,
+   NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -104,6 +160,10 @@ 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, 0, out1, out2,
+   out3, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -123,6 +183,10 @@ 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, 0, NULL,
+   out2, NULL, NULL, NULL, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2)
: [port] "i" (VMWARE_HYPERVISOR_PORT),
@@ -145,6 +209,10 @@ 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, 0, NULL, out2,
+   out3, out4, out5, NULL);
+
asm_inline volatile (VMWARE_HYPERCALL
: "=a" (out0), "=c" (*out2), "=d" (*out3), "=S" (*out4),
   

[PATCH 2/6] x86/vmware: Introduce vmware_hypercall API

[Alexey Makhalov]

Introducing vmware_hypercall family of functions as a common
implementation to be used by the VMware guest code and virtual
device drivers in arhitecture independent manner.

By analogy with KVM hypercall API, vmware_hypercallX and
vmware_hypercall_hb_{out,in} set of functions was added to
achieve that. Architecture specific implementation should be
hidden inside.

It will simplify future enhancements in VMware hypercalls such
as SEV-ES and TDX related changes without needs to modify a
caller in device drivers code.

Current implementation extends an idea from commit bac7b4e84323
("x86/vmware: Update platform detection code for VMCALL/VMMCALL
hypercalls") to have a slow, but safe path in VMWARE_HYPERCALL
when alternatives are not yet applied. This logic was inherited
from VMWARE_CMD from the commit mentioned above. Default
alternative code was optimized by size to reduse excessive nop
alignment once alternatives are applied. Total default code size
is 26 bytes, in worse case (3 bytes alternative) remaining 23
bytes will be aligned by only 3 long NOP instructions.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 262 ++
 arch/x86/kernel/cpu/vmware.c  |  35 ++---
 2 files changed, 220 insertions(+), 77 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index 8cabf4a577bf..17091eba68cb 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -40,69 +40,219 @@
 
 extern u8 vmware_hypercall_mode;
 
-/* The low bandwidth call. The low word of edx is presumed clear. */
-#define VMWARE_HYPERCALL   \
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
- "inl (%%dx), %%eax",  \
- "vmcall", X86_FEATURE_VMCALL, \
- "vmmcall", X86_FEATURE_VMW_VMMCALL)
-
 /*
- * The high bandwidth out call. The low word of edx is presumed to have the
- * HB and OUT bits set.
+ * 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.
  */
-#define VMWARE_HYPERCALL_HB_OUT
\
-   ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; 
" \
- "rep outsb",  \
+#define VMWARE_HYPERCALL   \
+   ALTERNATIVE_3("cmpb $"  \
+   __stringify(CPUID_VMWARE_FEATURES_ECX_VMMCALL)  \
+   ", %[mode]\n\t" \
+ "jg 2f\n\t"   \
+ "je 1f\n\t"   \
+ "movw %[port], %%dx\n\t"  \
+ "inl (%%dx), %%eax\n\t"   \
+ "jmp 3f\n\t"  \
+ "1: vmmcall\n\t"  \
+ "jmp 3f\n\t"  \
+ "2: vmcall\n\t"   \
+ "3:\n\t", \
+ "movw %[port], %%dx\n\t"  \
+ "inl (%%dx), %%eax", X86_FEATURE_HYPERVISOR,  \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
 
+static inline
+unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1)
+{
+   unsigned long out0;
+
+   asm_inline volatile (VMWARE_HYPERCALL
+   : "=a" (out0)
+   : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ [mode] "m" (vmware_hypercall_mode),
+ "a" (VMWARE_HYPERVISOR_MAGIC),
+ "b" (in1),
+ "c" (cmd),
+ "d" (0)
+   : "cc", "memory");
+   return out0;
+}
+
+static inline
+unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1,
+   uint32_t *out1, uint32_t *out2)
+{
+   unsigned long out0;
+
+   asm_inline volatile (VMWARE_HYPERCALL
+   : "=a" (out0), "=b" (*out1), "=c" (*out2)
+   : [port] "i" (VMWARE_HYPERVISOR_PORT),
+ [mode] "m" (vmware_hypercall_mode),
+ 

[PATCH 1/6] x86/vmware: Move common macros to vmware.h

[Alexey Makhalov]

Move VMware hypercall macros to vmware.h as a preparation step
for the next commit. No functional changes besides exporting
vmware_hypercall_mode symbol.

Signed-off-by: Alexey Makhalov 
---
 arch/x86/include/asm/vmware.h | 69 ++-
 arch/x86/kernel/cpu/vmware.c  | 57 +++--
 2 files changed, 66 insertions(+), 60 deletions(-)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index ac9fc51e2b18..8cabf4a577bf 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -8,25 +8,37 @@
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
- * in the following way: the old port base interface uses the port
- * number to distinguish between high- and low bandwidth versions.
+ * in the following way: the old I/O port based interface uses the port
+ * number to distinguish between high- and low bandwidth versions, and
+ * uses IN/OUT instructions to define transfer direction.
  *
  * The new vmcall interface instead uses a set of flags to select
  * bandwidth mode and transfer direction. The flags should be loaded
  * into %dx by any user and are automatically replaced by the port
- * number if the VMWARE_HYPERVISOR_PORT method is used.
+ * number if the I/O port method is used.
  *
  * In short, new driver code should strictly use the new definition of
  * %dx content.
  */
 
-/* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT0x5658
-#define VMWARE_HYPERVISOR_PORT_HB 0x5659
+#define VMWARE_HYPERVISOR_HB   BIT(0)
+#define VMWARE_HYPERVISOR_OUT  BIT(1)
 
-/* Current vmcall / vmmcall version */
-#define VMWARE_HYPERVISOR_HB   BIT(0)
-#define VMWARE_HYPERVISOR_OUT  BIT(1)
+#define VMWARE_HYPERVISOR_PORT 0x5658
+#define VMWARE_HYPERVISOR_PORT_HB  (VMWARE_HYPERVISOR_PORT | \
+VMWARE_HYPERVISOR_HB)
+
+#define VMWARE_HYPERVISOR_MAGIC0x564D5868U
+
+#define VMWARE_CMD_GETVERSION  10
+#define VMWARE_CMD_GETHZ   45
+#define VMWARE_CMD_GETVCPU_INFO68
+#define VMWARE_CMD_STEALCLOCK  91
+
+#define CPUID_VMWARE_FEATURES_ECX_VMMCALL  BIT(0)
+#define CPUID_VMWARE_FEATURES_ECX_VMCALL   BIT(1)
+
+extern u8 vmware_hypercall_mode;
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL   \
@@ -54,4 +66,43 @@
  "rep insb",   \
  "vmcall", X86_FEATURE_VMCALL, \
  "vmmcall", X86_FEATURE_VMW_VMMCALL)
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)   \
+   __asm__("inl (%%dx), %%eax" :   \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) :\
+   "memory")
+
+#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \
+   __asm__("vmcall" :  \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx)
\
+   __asm__("vmmcall" : \
+   "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :\
+   "a"(VMWARE_HYPERVISOR_MAGIC),   \
+   "c"(VMWARE_CMD_##cmd),  \
+   "d"(0), "b"(UINT_MAX) : \
+   "memory")
+
+#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do {   \
+   switch (vmware_hypercall_mode) {\
+   case CPUID_VMWARE_FEATURES_ECX_VMCALL:  \
+   VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \
+   break;  \
+   case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \
+   VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx);\
+   break;  \
+   default: