Skip to contentSkip to conversation

treat AHCI controllers under VMD as part of VMD

PATCH In review Kevin Friedberg 3 participants 7 messages Jan 26, 2023 – Feb 13, 2023 MD RAID

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 treat AHCI controllers under VMD as part of VMD

Detect when a SATA controller has been mapped under Intel Alderlake RST VMD and list it as part of the domain, instead of independently, so that it can use the VMD controller's RAID capabilities.

---
 platform-intel.c | 15 +++++++++------
 super-intel.c    | 25 ++++++++++++++++++++++++-
 2 files changed, 33 insertions(+), 7 deletions(-)
platform-intel.c +9 -6
index 757f0b1b..859bf743 100644
@@ -64,10 +64,12 @@ struct sys_dev *find_driver_devices(const char *bus, const char *driver)
 
 	if (strcmp(driver, "isci") == 0)
 		type = SYS_DEV_SAS;
-	else if (strcmp(driver, "ahci") == 0)
+	else if (strcmp(driver, "ahci") == 0) {
+		/* if looking for sata devs, ignore vmd */
+		vmd = find_driver_devices("pci", "vmd");
 		type = SYS_DEV_SATA;
-	else if (strcmp(driver, "nvme") == 0) {
-		/* if looking for nvme devs, first look for vmd */
+	} else if (strcmp(driver, "nvme") == 0) {
+		/* if looking for nvme devs, also look for vmd */
 		vmd = find_driver_devices("pci", "vmd");
 		type = SYS_DEV_NVME;
 	} else if (strcmp(driver, "vmd") == 0)
@@ -104,8 +106,8 @@ struct sys_dev *find_driver_devices(const char *bus, const char *driver)
 		sprintf(path, "/sys/bus/%s/drivers/%s/%s",
 			bus, driver, de->d_name);
 
-		/* if searching for nvme - skip vmd connected one */
-		if (type == SYS_DEV_NVME) {
+		/* if searching for nvme or ahci - skip vmd connected one */
+		if (type == SYS_DEV_NVME || type == SYS_DEV_SATA) {
 			struct sys_dev *dev;
 			char *rp = realpath(path, NULL);
 			for (dev = vmd; dev; dev = dev->next) {
@@ -166,7 +168,8 @@ struct sys_dev *find_driver_devices(const char *bus, const char *driver)
 	}
 	closedir(driver_dir);
 
-	if (vmd) {
+	/* VMD adopts multiple types but should only be listed once */
+	if (vmd && type == SYS_DEV_NVME) {
 		if (list)
 			list->next = vmd;
 		else
super-intel.c +24 -1
index 89fac626..4ef8f0d8 100644
@@ -2680,6 +2680,8 @@ static void print_imsm_capability_export(const struct imsm_orom *orom)
 	printf("IMSM_MAX_VOLUMES_PER_CONTROLLER=%d\n",orom->vphba);
 }
 
+#define PCI_CLASS_AHCI_CNTRL "0x010601"
+
 static int detail_platform_imsm(int verbose, int enumerate_only, char *controller_path)
 {
 	/* There are two components to imsm platform support, the ahci SATA
@@ -2752,11 +2754,32 @@ static int detail_platform_imsm(int verbose, int enumerate_only, char *controlle
 			for (hba = list; hba; hba = hba->next) {
 				if (hba->type == SYS_DEV_VMD) {
 					char buf[PATH_MAX];
+					struct dirent *ent;
+					DIR *dir;
+
 					printf(" I/O Controller : %s (%s)\n",
 						vmd_domain_to_controller(hba, buf), get_sys_dev_type(hba->type));
+					dir = opendir(hba->path);
+					for (ent = readdir(dir); ent; ent = readdir(dir)) {
+						char ent_path[PATH_MAX];
+
+						sprintf(ent_path, "%s/%s", hba->path, ent->d_name);
+						devpath_to_char(ent_path, "class", buf, sizeof(buf), 0);
+						if (strcmp(buf, PCI_CLASS_AHCI_CNTRL) == 0) {
+							host_base = ahci_get_port_count(ent_path, &port_count);
+							if (ahci_enumerate_ports(ent_path, port_count, host_base, verbose)) {
+								if (verbose > 0)
+								pr_err("failed to enumerate ports on VMD SATA controller at %s.\n",
+									hba->pci_id);
+								result |= 2;
+							}
+						}
+					}
+					closedir(dir);
+
 					if (print_nvme_info(hba)) {
 						if (verbose > 0)
-							pr_err("failed to get devices attached to VMD domain.\n");
+							pr_err("failed to get NVMe devices attached to VMD domain.\n");
 						result |= 2;
 					}
 				}
Signature · 1 line
2.39.0
#1 lore raw

Hi Kevin,
Thank you for the patch. Please be aware that the RST is not officially supported on Linux. You are going to enable RST suppport using VROC Linux stack. You are using it at your own risk.
Intel will review your patch and will run regression, it could take around month (sorry, we are getting back our labs now).

Thanks,
Mariusz

Quoted 5 lines · On Wed, 25 Jan 2023 21:16:59 -0500 Kevin Friedberg <[email protected]>…

Detect when a SATA controller has been mapped under Intel Alderlake RST VMD and list it as part of the domain, instead of independently, so that it can use the VMD controller's RAID capabilities.

#2 lore raw

Thank you! Three weeks in it's stable for me (and I do have a backup just in case). But that's just on my system and having this properly tested, validated and hopefully merged would be much better. This is actually my first time working in C at this level, so any feedback is appreciated.

Cheers,
Kevin

Quoted 19 lines · Mariusz Tkaczyk

Hi Kevin,
Thank you for the patch. Please be aware that the RST is not officially supported on Linux. You are going to enable RST suppport using VROC Linux stack. You are using it at your own risk.
Intel will review your patch and will run regression, it could take around month (sorry, we are getting back our labs now).

Thanks,
Mariusz

Quoted 5 lines · On Wed, 25 Jan 2023 21:16:59 -0500 Kevin Friedberg <[email protected]>…

Detect when a SATA controller has been mapped under Intel Alderlake RST VMD and list it as part of the domain, instead of independently, so that it can use the VMD controller's RAID capabilities.

#3 lore raw
In reply to Kevin Friedberg

Hi Kevin,
I found time to take a look into it closer. I think that it is not complete solution. Please see my comments.

Quoted 42 lines · On Wed, 25 Jan 2023 21:16:59 -0500 Kevin Friedberg <[email protected]>…

Detect when a SATA controller has been mapped under Intel Alderlake RST VMD and list it as part of the domain, instead of independently, so that it can use the VMD controller's RAID capabilities.

---
 platform-intel.c | 15 +++++++++------
 super-intel.c    | 25 ++++++++++++++++++++++++-
 2 files changed, 33 insertions(+), 7 deletions(-)
platform-intel.c +7 -5
index 757f0b1b..859bf743 100644
@@ -64,10 +64,12 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) 
 	if (strcmp(driver, "isci") == 0)
 		type = SYS_DEV_SAS;
-	else if (strcmp(driver, "ahci") == 0)
+	else if (strcmp(driver, "ahci") == 0) {
+		/* if looking for sata devs, ignore vmd */
+		vmd = find_driver_devices("pci", "vmd");
 		type = SYS_DEV_SATA;
-	else if (strcmp(driver, "nvme") == 0) {
-		/* if looking for nvme devs, first look for vmd */
+	} else if (strcmp(driver, "nvme") == 0) {
+		/* if looking for nvme devs, also look for vmd */
 		vmd = find_driver_devices("pci", "vmd");
 		type = SYS_DEV_NVME;
 	} else if (strcmp(driver, "vmd") == 0)
@@ -104,8 +106,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) sprintf(path, "/sys/bus/%s/drivers/%s/%s",
 			bus, driver, de->d_name);
 
-		/* if searching for nvme - skip vmd connected one */
-		if (type == SYS_DEV_NVME) {
+		/* if searching for nvme or ahci - skip vmd connected one */
+		if (type == SYS_DEV_NVME || type == SYS_DEV_SATA) {
 			struct sys_dev *dev;
 			char *rp = realpath(path, NULL);
 			for (dev = vmd; dev; dev = dev->next) {

platform-intel.c struct sys_dev *find_driver_devices(const char *bus, · line 175

Quoted 9 lines
platform-intel.c +2 -1
@@ -166,7 +168,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) }
 	closedir(driver_dir);
 
-	if (vmd) {
+	/* VMD adopts multiple types but should only be listed once */
+	if (vmd && type == SYS_DEV_NVME) {
 		if (list)
 			list->next = vmd;
 		else

The SATA behind VMD deserves own type, let say SYS_DEV_SATA_VMD. We cannot use SYS_DEV_VMD because it will allow to use NVME devices behind VMD in SATA Raid array. It means that if you have them connected, like:
VMD___ NVME0

    |_ NVME1
    |_ SATA___SATA0
           |__SATA1

You will be able to mix SATA and NVME drives together in RAID. Mdmonitor could mix them too (if appropriate policy is set). That is not allowed from at least VROC requirements PoV.

super-intel.c static void print_imsm_capability_export(const struct · line 2683

Quoted 9 lines
super-intel.c +1 -0
index 89fac626..4ef8f0d8 100644
@@ -2680,6 +2680,8 @@ static void print_imsm_capability_export(const struct
 imsm_orom *orom) printf("IMSM_MAX_VOLUMES_PER_CONTROLLER=%d\n",orom->vphba);
 }
 
+#define PCI_CLASS_AHCI_CNTRL "0x010601"

This should be defined in platform-intel.h

Quoted 47 lines
super-intel.c +13 -0
+
 static int detail_platform_imsm(int verbose, int enumerate_only, char
 *controller_path) {
 	/* There are two components to imsm platform support, the ahci SATA
@@ -2752,11 +2754,32 @@ static int detail_platform_imsm(int verbose, int
 enumerate_only, char *controlle for (hba = list; hba; hba = hba->next) {
 				if (hba->type == SYS_DEV_VMD) {
 					char buf[PATH_MAX];
+					struct dirent *ent;
+					DIR *dir;
+
 					printf(" I/O Controller : %s (%s)\n",
 						vmd_domain_to_controller(hba,
 buf), get_sys_dev_type(hba->type));
+					dir = opendir(hba->path);
+					for (ent = readdir(dir); ent; ent =
 readdir(dir)) {
+						char ent_path[PATH_MAX];
+
+						sprintf(ent_path, "%s/%s",
 hba->path, ent->d_name);
+						devpath_to_char(ent_path,
 "class", buf, sizeof(buf), 0);
+						if (strcmp(buf,
 PCI_CLASS_AHCI_CNTRL) == 0) {
+							host_base =
 ahci_get_port_count(ent_path, &port_count);
+							if

(ahci_enumerate_ports(ent_path, port_count, host_base, verbose)) {

super-intel.c +1 -0
+								if (verbose
Quoted 1 line

0)

+
pr_err("failed to enumerate ports on VMD SATA controller at %s.\n", +
hba->pci_id);

super-intel.c +6 -1
+								result |= 2;
+							}
+						}
+					}
+					closedir(dir);
+
 					if (print_nvme_info(hba)) {
 						if (verbose > 0)
-							pr_err("failed to

get devices attached to VMD domain.\n");

super-intel.c +1 -0
+							pr_err("failed to

get NVMe devices attached to VMD domain.\n"); result |= 2;

super-intel.c

Quoted 2 lines
super-intel.c +0 -0
 					}
 				}

Similar logic is already there:
https://git.kernel.org/pub/scm/utils/mdadm/mdadm.git/tree/super-intel.c#n2780
I would like to reuse it instead of adding new code branch. Could you please extract similar parts to new function and use it in both places?

Thanks,
Mariusz

#4 lore raw
Quoted 64 lines · Mariusz Tkaczyk

Hi Kevin,
I found time to take a look into it closer. I think that it is not complete solution. Please see my comments.

Quoted 42 lines · On Wed, 25 Jan 2023 21:16:59 -0500 Kevin Friedberg <[email protected]>…

Detect when a SATA controller has been mapped under Intel Alderlake RST VMD and list it as part of the domain, instead of independently, so that it can use the VMD controller's RAID capabilities.

---
 platform-intel.c | 15 +++++++++------
 super-intel.c    | 25 ++++++++++++++++++++++++-
 2 files changed, 33 insertions(+), 7 deletions(-)
platform-intel.c +7 -5
index 757f0b1b..859bf743 100644
@@ -64,10 +64,12 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver)
      if (strcmp(driver, "isci") == 0)
              type = SYS_DEV_SAS;
-     else if (strcmp(driver, "ahci") == 0)
+     else if (strcmp(driver, "ahci") == 0) {
+             /* if looking for sata devs, ignore vmd */
+             vmd = find_driver_devices("pci", "vmd");
              type = SYS_DEV_SATA;
-     else if (strcmp(driver, "nvme") == 0) {
-             /* if looking for nvme devs, first look for vmd */
+     } else if (strcmp(driver, "nvme") == 0) {
+             /* if looking for nvme devs, also look for vmd */
              vmd = find_driver_devices("pci", "vmd");
              type = SYS_DEV_NVME;
      } else if (strcmp(driver, "vmd") == 0)
@@ -104,8 +106,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) sprintf(path, "/sys/bus/%s/drivers/%s/%s",
                      bus, driver, de->d_name);
 
-             /* if searching for nvme - skip vmd connected one */
-             if (type == SYS_DEV_NVME) {
+             /* if searching for nvme or ahci - skip vmd connected one */
+             if (type == SYS_DEV_NVME || type == SYS_DEV_SATA) {
                      struct sys_dev *dev;
                      char *rp = realpath(path, NULL);
                      for (dev = vmd; dev; dev = dev->next) {

platform-intel.c struct sys_dev *find_driver_devices(const char *bus, · line 175

Quoted 9 lines
platform-intel.c +2 -1
@@ -166,7 +168,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) }
      closedir(driver_dir);
 
-     if (vmd) {
+     /* VMD adopts multiple types but should only be listed once */
+     if (vmd && type == SYS_DEV_NVME) {
              if (list)
                      list->next = vmd;
              else

The SATA behind VMD deserves own type, let say SYS_DEV_SATA_VMD. We cannot use SYS_DEV_VMD because it will allow to use NVME devices behind VMD in SATA Raid array. It means that if you have them connected, like:
VMD___ NVME0

Quoted 6 lines
    |_ NVME1
    |_ SATA___SATA0
           |__SATA1

You will be able to mix SATA and NVME drives together in RAID. Mdmonitor could mix them too (if appropriate policy is set). That is not allowed from at least VROC requirements PoV.

Hi Mariusz

Through the description of VMD
(https://www.chipict.com/intel_vmd_vroc/), it looks like VMD only supports pcie nvme devices. Can it also connect sata devices?

And what's PoV?

Best Regards
Xiao

#5 lore raw
Quoted 74 lines · On Thu, 9 Feb 2023 08:39:21 +0800 Xiao Ni <[email protected]> wrote:
Quoted 64 lines · Mariusz Tkaczyk

Hi Kevin,
I found time to take a look into it closer. I think that it is not complete solution. Please see my comments.

Quoted 42 lines · On Wed, 25 Jan 2023 21:16:59 -0500 Kevin Friedberg <[email protected]>…

Detect when a SATA controller has been mapped under Intel Alderlake RST VMD and list it as part of the domain, instead of independently, so that it can use the VMD controller's RAID capabilities.

---
 platform-intel.c | 15 +++++++++------
 super-intel.c    | 25 ++++++++++++++++++++++++-
 2 files changed, 33 insertions(+), 7 deletions(-)
platform-intel.c +7 -5
index 757f0b1b..859bf743 100644
@@ -64,10 +64,12 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver)
      if (strcmp(driver, "isci") == 0)
              type = SYS_DEV_SAS;
-     else if (strcmp(driver, "ahci") == 0)
+     else if (strcmp(driver, "ahci") == 0) {
+             /* if looking for sata devs, ignore vmd */
+             vmd = find_driver_devices("pci", "vmd");
              type = SYS_DEV_SATA;
-     else if (strcmp(driver, "nvme") == 0) {
-             /* if looking for nvme devs, first look for vmd */
+     } else if (strcmp(driver, "nvme") == 0) {
+             /* if looking for nvme devs, also look for vmd */
              vmd = find_driver_devices("pci", "vmd");
              type = SYS_DEV_NVME;
      } else if (strcmp(driver, "vmd") == 0)
@@ -104,8 +106,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) sprintf(path, "/sys/bus/%s/drivers/%s/%s",
                      bus, driver, de->d_name);
 
-             /* if searching for nvme - skip vmd connected one */
-             if (type == SYS_DEV_NVME) {
+             /* if searching for nvme or ahci - skip vmd connected one */
+             if (type == SYS_DEV_NVME || type == SYS_DEV_SATA) {
                      struct sys_dev *dev;
                      char *rp = realpath(path, NULL);
                      for (dev = vmd; dev; dev = dev->next) {

platform-intel.c struct sys_dev *find_driver_devices(const char *bus, · line 175

Quoted 9 lines
platform-intel.c +2 -1
@@ -166,7 +168,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) }
      closedir(driver_dir);
 
-     if (vmd) {
+     /* VMD adopts multiple types but should only be listed once */
+     if (vmd && type == SYS_DEV_NVME) {
              if (list)
                      list->next = vmd;
              else  

The SATA behind VMD deserves own type, let say SYS_DEV_SATA_VMD. We cannot use SYS_DEV_VMD because it will allow to use NVME devices behind VMD in SATA Raid array. It means that if you have them connected, like:
VMD___ NVME0

Quoted 6 lines
    |_ NVME1
    |_ SATA___SATA0
           |__SATA1

You will be able to mix SATA and NVME drives together in RAID. Mdmonitor could mix them too (if appropriate policy is set). That is not allowed from at least VROC requirements PoV.

Quoted 8 lines

Hi Mariusz

Through the description of VMD
(https://www.chipict.com/intel_vmd_vroc/), it looks like VMD only supports pcie nvme devices. Can it also connect sata devices?

And what's PoV?

Hi Xiao,
Not directly, there must be SATA controller behind VMD.
In VROC on server platforms we don't use that. So far I know, the reason is to have only one driver to handle all RST devices but it could be only part of story.

Thanks,
Mariusz

#6 lore raw
In reply to Mariusz Tkaczyk

Hi Mariusz,

Thank you for the feedback. I'm working up a replacement patch based on your comments and should have it ready in the next couple days. It works in a different way and has a different commit message, so go ahead and reject this patch if there's a process for that.

Quoted 138 lines · Mariusz Tkaczyk

Hi Kevin,
I found time to take a look into it closer. I think that it is not complete solution. Please see my comments.

Quoted 42 lines · On Wed, 25 Jan 2023 21:16:59 -0500 Kevin Friedberg <[email protected]>…

Detect when a SATA controller has been mapped under Intel Alderlake RST VMD and list it as part of the domain, instead of independently, so that it can use the VMD controller's RAID capabilities.

---
 platform-intel.c | 15 +++++++++------
 super-intel.c    | 25 ++++++++++++++++++++++++-
 2 files changed, 33 insertions(+), 7 deletions(-)
platform-intel.c +7 -5
index 757f0b1b..859bf743 100644
@@ -64,10 +64,12 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver)
      if (strcmp(driver, "isci") == 0)
              type = SYS_DEV_SAS;
-     else if (strcmp(driver, "ahci") == 0)
+     else if (strcmp(driver, "ahci") == 0) {
+             /* if looking for sata devs, ignore vmd */
+             vmd = find_driver_devices("pci", "vmd");
              type = SYS_DEV_SATA;
-     else if (strcmp(driver, "nvme") == 0) {
-             /* if looking for nvme devs, first look for vmd */
+     } else if (strcmp(driver, "nvme") == 0) {
+             /* if looking for nvme devs, also look for vmd */
              vmd = find_driver_devices("pci", "vmd");
              type = SYS_DEV_NVME;
      } else if (strcmp(driver, "vmd") == 0)
@@ -104,8 +106,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) sprintf(path, "/sys/bus/%s/drivers/%s/%s",
                      bus, driver, de->d_name);
 
-             /* if searching for nvme - skip vmd connected one */
-             if (type == SYS_DEV_NVME) {
+             /* if searching for nvme or ahci - skip vmd connected one */
+             if (type == SYS_DEV_NVME || type == SYS_DEV_SATA) {
                      struct sys_dev *dev;
                      char *rp = realpath(path, NULL);
                      for (dev = vmd; dev; dev = dev->next) {

platform-intel.c struct sys_dev *find_driver_devices(const char *bus, · line 175

Quoted 9 lines
platform-intel.c +2 -1
@@ -166,7 +168,8 @@ struct sys_dev *find_driver_devices(const char *bus,
 const char *driver) }
      closedir(driver_dir);
 
-     if (vmd) {
+     /* VMD adopts multiple types but should only be listed once */
+     if (vmd && type == SYS_DEV_NVME) {
              if (list)
                      list->next = vmd;
              else

The SATA behind VMD deserves own type, let say SYS_DEV_SATA_VMD. We cannot use SYS_DEV_VMD because it will allow to use NVME devices behind VMD in SATA Raid array. It means that if you have them connected, like:
VMD___ NVME0

    |_ NVME1
    |_ SATA___SATA0
           |__SATA1

You will be able to mix SATA and NVME drives together in RAID. Mdmonitor could mix them too (if appropriate policy is set). That is not allowed from at least VROC requirements PoV.

super-intel.c static void print_imsm_capability_export(const struct · line 2683

Quoted 9 lines
super-intel.c +1 -0
index 89fac626..4ef8f0d8 100644
@@ -2680,6 +2680,8 @@ static void print_imsm_capability_export(const struct
 imsm_orom *orom) printf("IMSM_MAX_VOLUMES_PER_CONTROLLER=%d\n",orom->vphba);
 }
 
+#define PCI_CLASS_AHCI_CNTRL "0x010601"

This should be defined in platform-intel.h

Quoted 47 lines
super-intel.c +13 -0
+
 static int detail_platform_imsm(int verbose, int enumerate_only, char
 *controller_path) {
      /* There are two components to imsm platform support, the ahci SATA
@@ -2752,11 +2754,32 @@ static int detail_platform_imsm(int verbose, int
 enumerate_only, char *controlle for (hba = list; hba; hba = hba->next) {
                              if (hba->type == SYS_DEV_VMD) {
                                      char buf[PATH_MAX];
+                                     struct dirent *ent;
+                                     DIR *dir;
+
                                      printf(" I/O Controller : %s (%s)\n",
                                              vmd_domain_to_controller(hba,
 buf), get_sys_dev_type(hba->type));
+                                     dir = opendir(hba->path);
+                                     for (ent = readdir(dir); ent; ent =
 readdir(dir)) {
+                                             char ent_path[PATH_MAX];
+
+                                             sprintf(ent_path, "%s/%s",
 hba->path, ent->d_name);
+                                             devpath_to_char(ent_path,
 "class", buf, sizeof(buf), 0);
+                                             if (strcmp(buf,
 PCI_CLASS_AHCI_CNTRL) == 0) {
+                                                     host_base =
 ahci_get_port_count(ent_path, &port_count);
+                                                     if

(ahci_enumerate_ports(ent_path, port_count, host_base, verbose)) {
+ if (verbose

Quoted 1 line

0)

+
pr_err("failed to enumerate ports on VMD SATA controller at %s.\n", +
hba->pci_id);

super-intel.c +6 -1
+                                                             result |= 2;
+                                                     }
+                                             }
+                                     }
+                                     closedir(dir);
+
                                      if (print_nvme_info(hba)) {
                                              if (verbose > 0)
-                                                     pr_err("failed to

get devices attached to VMD domain.\n");
+ pr_err("failed to
get NVMe devices attached to VMD domain.\n"); result |= 2;

Quoted 2 lines
                                      }
                              }

Similar logic is already there:
https://git.kernel.org/pub/scm/utils/mdadm/mdadm.git/tree/super-intel.c#n2780
I would like to reuse it instead of adding new code branch. Could you please extract similar parts to new function and use it in both places?

Thanks,
Mariusz