[PATCH 1/2] x86/vmware: Log kmsg dump on panic

[PATCH 1/2] x86/vmware: Log kmsg dump on panic

[Alexey Makhalov]

Improve debugability of VMware Linux guests by dumping
kernel messages during a panic to VM log file (vmware.log).

Co-developed-by: Bo Gan <bo.gan@broadcom.com>
Signed-off-by: Bo Gan <bo.gan@broadcom.com>
Signed-off-by: Alexey Makhalov <alexey.makhalov@broadcom.com>
---
 arch/x86/include/asm/vmware.h |   1 +
 arch/x86/kernel/cpu/vmware.c  | 132 ++++++++++++++++++++++++++++++++++
 2 files changed, 133 insertions(+)

diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index c9cf43d5ef23..433755b41a27 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -57,6 +57,7 @@
 #define VMWARE_HYPERVISOR_MAGIC		0x564d5868U
 
 #define VMWARE_CMD_GETVERSION		10
+#define VMWARE_CMD_MESSAGE		30
 #define VMWARE_CMD_GETHZ		45
 #define VMWARE_CMD_GETVCPU_INFO		68
 #define VMWARE_CMD_STEALCLOCK		91
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 00189cdeb775..9883766715fe 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -28,6 +28,7 @@
 #include <linux/cpu.h>
 #include <linux/reboot.h>
 #include <linux/static_call.h>
+#include <linux/kmsg_dump.h>
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
@@ -139,6 +140,13 @@ static unsigned long vmware_get_tsc_khz(void)
 	return vmware_tsc_khz;
 }
 
+static void kmsg_dumper_vmware_log(struct kmsg_dumper *dumper,
+				enum kmsg_dump_reason reason);
+
+static struct kmsg_dumper kmsg_dumper = {
+	.dump = kmsg_dumper_vmware_log
+};
+
 #ifdef CONFIG_PARAVIRT
 static struct cyc2ns_data vmware_cyc2ns __ro_after_init;
 static bool vmw_sched_clock __initdata = true;
@@ -436,6 +444,8 @@ static void __init vmware_platform_setup(void)
 #endif
 
 	vmware_set_capabilities();
+
+	kmsg_dump_register(&kmsg_dumper);
 }
 
 static u8 __init vmware_select_hypercall(void)
@@ -587,3 +597,125 @@ const __initconst struct hypervisor_x86 x86_hyper_vmware = {
 	.runtime.sev_es_hcall_finish	= vmware_sev_es_hcall_finish,
 #endif
 };
+
+#define VMWARE_HB_CMD_MESSAGE	0
+#define MESSAGE_STATUS_SUCCESS	(0x01 << 16)
+#define MESSAGE_STATUS_CPT	(0x10 << 16)
+#define MESSAGE_STATUS_HB	(0x80 << 16)
+
+#define RPCI_PROTOCOL_NUM	0x49435052 /* 'RPCI' */
+#define GUESTMSG_FLAG_COOKIE	0x80000000
+
+#define MESSAGE_TYPE_OPEN	(0 << 16)
+#define MESSAGE_TYPE_SENDSIZE	(1 << 16)
+#define MESSAGE_TYPE_SEND	(2 << 16)
+#define MESSAGE_TYPE_CLOSE	(6 << 16)
+
+struct vmw_msg {
+	u32 id;
+	u32 cookie_high;
+	u32 cookie_low;
+};
+
+static int
+vmware_log_open(struct vmw_msg *msg)
+{
+	u32 info;
+
+	vmware_hypercall6(VMWARE_CMD_MESSAGE | MESSAGE_TYPE_OPEN,
+			  RPCI_PROTOCOL_NUM | GUESTMSG_FLAG_COOKIE,
+			  0, &info, &msg->id, &msg->cookie_high,
+			  &msg->cookie_low);
+
+	if ((info & MESSAGE_STATUS_SUCCESS) == 0)
+		return 1;
+
+	msg->id &= 0xffff0000UL;
+	return 0;
+}
+
+static int
+vmware_log_close(struct vmw_msg *msg)
+{
+	u32 info;
+
+	vmware_hypercall5(VMWARE_CMD_MESSAGE | MESSAGE_TYPE_CLOSE, 0, msg->id,
+			  msg->cookie_high, msg->cookie_low, &info);
+
+	if ((info & MESSAGE_STATUS_SUCCESS) == 0)
+		return 1;
+	return 0;
+}
+
+static int
+vmware_log_send(struct vmw_msg *msg, const char *string)
+{
+	u32 info;
+	u32 len = strlen(string);
+
+retry:
+	vmware_hypercall5(VMWARE_CMD_MESSAGE | MESSAGE_TYPE_SENDSIZE, len,
+			  msg->id, msg->cookie_high, msg->cookie_low, &info);
+
+	if (!(info & MESSAGE_STATUS_SUCCESS))
+		return 1;
+
+	/* HB port can't access encrypted memory. */
+	if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT) && (info & MESSAGE_STATUS_HB)) {
+		vmware_hypercall_hb_out(
+			VMWARE_HB_CMD_MESSAGE | MESSAGE_STATUS_SUCCESS,
+			len, msg->id, (uintptr_t) string, msg->cookie_low,
+			msg->cookie_high, &info);
+	} else {
+		do {
+			u32 word;
+			size_t s = min_t(u32, len, sizeof(word));
+
+			memcpy(&word, string, s);
+			len -= s;
+			string += s;
+
+			vmware_hypercall5(VMWARE_CMD_MESSAGE | MESSAGE_TYPE_SEND,
+					  word, msg->id, msg->cookie_high,
+					  msg->cookie_low, &info);
+		} while (len && (info & MESSAGE_STATUS_SUCCESS));
+	}
+
+	if ((info & MESSAGE_STATUS_SUCCESS) == 0) {
+		if (info & MESSAGE_STATUS_CPT)
+			/* A checkpoint occurred. Retry. */
+			goto retry;
+		return 1;
+	}
+	return 0;
+}
+STACK_FRAME_NON_STANDARD(vmware_log_send);
+
+/**
+ * kmsg_dumper_vmware_log - dumps kmsg to vmware.log file on the host
+ */
+static void kmsg_dumper_vmware_log(struct kmsg_dumper *dumper,
+				enum kmsg_dump_reason reason)
+{
+	struct vmw_msg msg;
+	struct kmsg_dump_iter iter;
+	static char line[1024];
+	size_t len = 0;
+
+	/* Line prefix to send to VM log file. */
+	line[0] = 'l';
+	line[1] = 'o';
+	line[2] = 'g';
+	line[3] = ' ';
+
+	kmsg_dump_rewind(&iter);
+	while (kmsg_dump_get_line(&iter, true, line + 4, sizeof(line) - 4,
+				  &len)) {
+		line[len + 4] = '\0';
+		if (vmware_log_open(&msg))
+			return;
+		if (vmware_log_send(&msg, line))
+			return;
+		vmware_log_close(&msg);
+	}
+}
-- 
2.39.4

[PATCH 2/2] x86/vmware: Fix steal time clock under SEV

[Alexey Makhalov]

Shared memory containing steal time counter should be set to
decrypted when SEV is active.

Co-developed-by: Bo Gan <bo.gan@broadcom.com>
Signed-off-by: Bo Gan <bo.gan@broadcom.com>
Signed-off-by: Alexey Makhalov <alexey.makhalov@broadcom.com>
---
 arch/x86/kernel/cpu/vmware.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 9883766715fe..f20bdc3128f3 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -306,9 +306,30 @@ static struct notifier_block vmware_pv_reboot_nb = {
 	.notifier_call = vmware_pv_reboot_notify,
 };
 
+static void __init sev_map_percpu_data(void)
+{
+	int cpu;
+
+	if (cc_vendor != CC_VENDOR_AMD ||
+	    !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		early_set_memory_decrypted(
+			(unsigned long)&per_cpu(vmw_steal_time, cpu),
+			sizeof(vmw_steal_time));
+	}
+}
+
 #ifdef CONFIG_SMP
 static void __init vmware_smp_prepare_boot_cpu(void)
 {
+	/*
+	 * Map the per-cpu variables as decrypted before vmware_guest_cpu_init()
+	 * shares the guest physical address with the hypervisor.
+	 */
+	sev_map_percpu_data();
+
 	vmware_guest_cpu_init();
 	native_smp_prepare_boot_cpu();
 }
@@ -371,6 +392,7 @@ static void __init vmware_paravirt_ops_setup(void)
 					      vmware_cpu_down_prepare) < 0)
 			pr_err("vmware_guest: Failed to install cpu hotplug callbacks\n");
 #else
+		sev_map_percpu_data();
 		vmware_guest_cpu_init();
 #endif
 	}
-- 
2.39.4

Re: [PATCH 2/2] x86/vmware: Fix steal time clock under SEV

[kernel test robot]

Hi Alexey,

kernel test robot noticed the following build errors:

[auto build test ERROR on tip/x86/vmware]
[also build test ERROR on linus/master v6.11-rc3 next-20240815]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Alexey-Makhalov/x86-vmware-Fix-steal-time-clock-under-SEV/20240815-050918
base:   tip/x86/vmware
patch link:    https://lore.kernel.org/r/20240814210731.761010-2-alexey.makhalov%40broadcom.com
patch subject: [PATCH 2/2] x86/vmware: Fix steal time clock under SEV
config: i386-randconfig-003-20240815 (https://download.01.org/0day-ci/archive/20240815/202408151826.9369lzwV-lkp@intel.com/config)
compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240815/202408151826.9369lzwV-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202408151826.9369lzwV-lkp@intel.com/

All errors (new ones prefixed by >>):

>> arch/x86/kernel/cpu/vmware.c:313:6: error: use of undeclared identifier 'cc_vendor'
     313 |         if (cc_vendor != CC_VENDOR_AMD ||
         |             ^
>> arch/x86/kernel/cpu/vmware.c:313:19: error: use of undeclared identifier 'CC_VENDOR_AMD'
     313 |         if (cc_vendor != CC_VENDOR_AMD ||
         |                          ^
   2 errors generated.


vim +/cc_vendor +313 arch/x86/kernel/cpu/vmware.c

   308	
   309	static void __init sev_map_percpu_data(void)
   310	{
   311		int cpu;
   312	
 > 313		if (cc_vendor != CC_VENDOR_AMD ||
   314		    !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
   315			return;
   316	
   317		for_each_possible_cpu(cpu) {
   318			early_set_memory_decrypted(
   319				(unsigned long)&per_cpu(vmw_steal_time, cpu),
   320				sizeof(vmw_steal_time));
   321		}
   322	}
   323	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 2/2] x86/vmware: Fix steal time clock under SEV

[kernel test robot]

Hi Alexey,

kernel test robot noticed the following build errors:

[auto build test ERROR on tip/x86/vmware]
[also build test ERROR on linus/master v6.11-rc3 next-20240815]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Alexey-Makhalov/x86-vmware-Fix-steal-time-clock-under-SEV/20240815-050918
base:   tip/x86/vmware
patch link:    https://lore.kernel.org/r/20240814210731.761010-2-alexey.makhalov%40broadcom.com
patch subject: [PATCH 2/2] x86/vmware: Fix steal time clock under SEV
config: i386-randconfig-001-20240815 (https://download.01.org/0day-ci/archive/20240815/202408152054.7LIuKvYe-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240815/202408152054.7LIuKvYe-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202408152054.7LIuKvYe-lkp@intel.com/

All errors (new ones prefixed by >>):

   arch/x86/kernel/cpu/vmware.c: In function 'sev_map_percpu_data':
>> arch/x86/kernel/cpu/vmware.c:313:13: error: 'cc_vendor' undeclared (first use in this function)
     313 |         if (cc_vendor != CC_VENDOR_AMD ||
         |             ^~~~~~~~~
   arch/x86/kernel/cpu/vmware.c:313:13: note: each undeclared identifier is reported only once for each function it appears in
>> arch/x86/kernel/cpu/vmware.c:313:26: error: 'CC_VENDOR_AMD' undeclared (first use in this function); did you mean 'X86_VENDOR_AMD'?
     313 |         if (cc_vendor != CC_VENDOR_AMD ||
         |                          ^~~~~~~~~~~~~
         |                          X86_VENDOR_AMD


vim +/cc_vendor +313 arch/x86/kernel/cpu/vmware.c

   308	
   309	static void __init sev_map_percpu_data(void)
   310	{
   311		int cpu;
   312	
 > 313		if (cc_vendor != CC_VENDOR_AMD ||
   314		    !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
   315			return;
   316	
   317		for_each_possible_cpu(cpu) {
   318			early_set_memory_decrypted(
   319				(unsigned long)&per_cpu(vmw_steal_time, cpu),
   320				sizeof(vmw_steal_time));
   321		}
   322	}
   323	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH v2 2/2] x86/vmware: Fix steal time clock under SEV

[Alexey Makhalov]

Shared memory containing steal time counter should be set to
decrypted when SEV is active.

Co-developed-by: Bo Gan <bo.gan@broadcom.com>
Signed-off-by: Bo Gan <bo.gan@broadcom.com>
Signed-off-by: Alexey Makhalov <alexey.makhalov@broadcom.com>
---
 arch/x86/kernel/cpu/vmware.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 9883766715fe..b4e57d6ec2f5 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -36,6 +36,7 @@
 #include <asm/apic.h>
 #include <asm/vmware.h>
 #include <asm/svm.h>
+#include <asm/coco.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)	"vmware: " fmt
@@ -306,9 +307,30 @@ static struct notifier_block vmware_pv_reboot_nb = {
 	.notifier_call = vmware_pv_reboot_notify,
 };
 
+static void __init sev_map_percpu_data(void)
+{
+	int cpu;
+
+	if (cc_vendor != CC_VENDOR_AMD ||
+	    !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		early_set_memory_decrypted(
+			(unsigned long)&per_cpu(vmw_steal_time, cpu),
+			sizeof(vmw_steal_time));
+	}
+}
+
 #ifdef CONFIG_SMP
 static void __init vmware_smp_prepare_boot_cpu(void)
 {
+	/*
+	 * Map the per-cpu variables as decrypted before vmware_guest_cpu_init()
+	 * shares the guest physical address with the hypervisor.
+	 */
+	sev_map_percpu_data();
+
 	vmware_guest_cpu_init();
 	native_smp_prepare_boot_cpu();
 }
@@ -371,6 +393,7 @@ static void __init vmware_paravirt_ops_setup(void)
 					      vmware_cpu_down_prepare) < 0)
 			pr_err("vmware_guest: Failed to install cpu hotplug callbacks\n");
 #else
+		sev_map_percpu_data();
 		vmware_guest_cpu_init();
 #endif
 	}
-- 
2.39.4