From dc023d60c5609a027887f488c9254b078adc05d6 Mon Sep 17 00:00:00 2001
From: Dominik Csapak <d.csapak@proxmox.com>
Date: Tue, 6 Aug 2024 14:21:58 +0200
Subject: [PATCH] SysFSTools: handle new nvidia syfsapi as mdev

with kernel 6.8 NVIDIAs vGPU driver has a different api than the
previous 'mediated devices'. Adapt our sysfcode to also recognize this
for the 'mdev' paths and add another 'nvidia' property so we can detect
this.

Also parse the new api when they exist instead of the mediated devices.

The biggest difference to the existing mdev api for our use is that the
devices don't report all generally available devices, only the
createable ones. So if a user wants to configure a VM, the selection is
restricted by what may currently run on the GPU (depending ont the exact
settings, e.g. mixed mode gpus where different models can be mixed on a
single GPU; not the default though)

We could overcome this, when we'd parse the general info from the
'nvidia-smi' tool, though I'm currently unsure if that interface is
stable and intended to be parsed (there is no json output or similar
AFAIK)

Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
Tested-by: Christoph Heiss <c.heiss@proxmox.com>
Reviewed-by: Christoph Heiss <c.heiss@proxmox.com>
---
 src/PVE/SysFSTools.pm | 65 ++++++++++++++++++++++++++++---------------
 1 file changed, 42 insertions(+), 23 deletions(-)

diff --git a/src/PVE/SysFSTools.pm b/src/PVE/SysFSTools.pm
index 8eb9f2e..25b2f31 100644
--- a/src/PVE/SysFSTools.pm
+++ b/src/PVE/SysFSTools.pm
@@ -112,6 +112,10 @@ sub lspci {
 
 	    if (-d "$devdir/mdev_supported_types") {
 		$res->{mdev} = 1;
+	    } elsif (-d "$devdir/nvidia") {
+		# nvidia driver for kernel 6.8 or higher
+		$res->{mdev} = 1; # for api compatibility
+		$res->{nvidia} = 1;
 	    }
 
 	    my $device_hash = $ids->{$vendor}->{devices}->{$device} // {};
@@ -159,31 +163,46 @@ sub get_mdev_types {
 
     my $types = [];
 
-    my $mdev_path = "$pcisysfs/devices/$id/mdev_supported_types";
-    if (!-d $mdev_path) {
-	return $types;
+    my $dev_path = "$pcisysfs/devices/$id";
+    my $mdev_path = "$dev_path/mdev_supported_types";
+    my $nvidia_path = "$dev_path/nvidia/creatable_vgpu_types";
+    if (-d $mdev_path) {
+	dir_glob_foreach($mdev_path, '[^\.].*', sub {
+	    my ($type) = @_;
+
+	    my $type_path = "$mdev_path/$type";
+
+	    my $available = int(file_read_firstline("$type_path/available_instances"));
+	    my $description = PVE::Tools::file_get_contents("$type_path/description");
+
+	    my $entry = {
+		type => $type,
+		description => $description,
+		available => $available,
+	    };
+
+	    my $name = file_read_firstline("$type_path/name");
+	    $entry->{name} = $name if defined($name);
+
+	    push @$types, $entry;
+	});
+    } elsif (-f $nvidia_path) {
+	my $creatable = PVE::Tools::file_get_contents($nvidia_path);
+	for my $line (split("\n", $creatable)) {
+	    next if $line =~ m/^ID/; # header
+	    next if $line !~ m/^(.*?)\s*:\s*(.*)$/;
+	    my $id = $1;
+	    my $name = $2;
+
+	    push $types->@*, {
+		type => "nvidia-$id", # backwards compatibility
+		description => "", # TODO, read from xml/nvidia-smi ?
+		available => 1,
+		name  => $name,
+	    }
+	}
     }
 
-    dir_glob_foreach($mdev_path, '[^\.].*', sub {
-	my ($type) = @_;
-
-	my $type_path = "$mdev_path/$type";
-
-	my $available = int(file_read_firstline("$type_path/available_instances"));
-	my $description = PVE::Tools::file_get_contents("$type_path/description");
-
-	my $entry = {
-	    type => $type,
-	    description => $description,
-	    available => $available,
-	};
-
-	my $name = file_read_firstline("$type_path/name");
-	$entry->{name} = $name if defined($name);
-
-	push @$types, $entry;
-    });
-
     return $types;
 }