fix(ahci): harden command submission, DMA ownership, and timeout recovery

src/driver/storage/ctl/ahci/driver.storage.ctl.ahci.types.pas

@@ -21,6 +21,7 @@ unit driver.storage.ctl.ahci.types;
 interface
 uses
     io.syslog,
+    driver.storage.types,
     driver.mgr,
     driver.types,
     driver.storage.ctl.ide.types,
@@ -251,11 +252,13 @@ type
     { Callback signature fired from IRQ context when an async I/O command completes.
       Must be very short — set a flag or post to a queue.
       Never call kalloc/kfree/VFS from within this callback. }
-    TIOCompletion = procedure(success : boolean; userdata : puint32);
+    TIOCompletion = procedure(error : TError; userdata : puint32);
 
     { Per-slot pending operation — one entry per HBA command slot }
     TPendingOp = record
         inUse      : boolean;
+        issued     : boolean;
+        started    : uint32;
         completion : TIOCompletion;
         userdata   : puint32;
     end;
@@ -267,6 +270,11 @@ type
     }
     TAHCI_Device = record
         port         : PHBA_Port;
+        owner        : pointer; { stable PAHCI_Controller }
+        offline      : boolean;
+        recovering   : boolean;
+        recoveryTick : uint32;
+        recoveryError: TError;
         device_type  : TDeviceType;
         ata_info     : TIdentResponse;
         supportsNCQ  : boolean;
@@ -288,6 +296,7 @@ type
     }
     TAHCI_Controller = record
         pci_device : PPCI_Device;
+        offline : boolean;
         mio: PHBA_Memory;
         ata_info : TIdentResponse;
         devices : array[0..31] of TAHCI_Device;

src/driver/storage/driver.storage.metatest.pas

@@ -14,7 +14,7 @@ type
     PMock = ^TMock;
     TMock = record
         Data : puint8;
-        Writes, FailWrite, Callbacks : uint32;
+        Writes, FailWrite, Callbacks, Depth, MaxDepth : uint32;
         Error : TError;
         OutOfBounds, FailRead : boolean;
     end;
@@ -27,7 +27,10 @@ begin
        (request^.SectorCount > device^.maxSectorCount-request^.LBA) then begin
         m^.OutOfBounds := true; complete_io(request, false, eInvalidArgument); exit;
     end;
-    if (request^.RequestType <> ioWrite) and m^.FailRead then begin complete_io(request, false, eIOError); exit; end;
+    if (request^.RequestType <> ioWrite) and m^.FailRead then begin
+        Inc(m^.Depth); if m^.Depth > m^.MaxDepth then m^.MaxDepth := m^.Depth;
+        complete_io(request,false,eIOError); Dec(m^.Depth); exit;
+    end;
     offset := request^.LBA*512; size := request^.SectorCount*512;
     if request^.RequestType = ioWrite then begin
         Inc(m^.Writes);
@@ -81,7 +84,17 @@ begin
     device^.controllerId0 := uint32(mock); device^.sectorSize := 512;
     device^.maxSectorCount := 256; device^.writable := true; device^.maxActive := 1;
     device^.dispatchRead := @dispatch; device^.dispatchWrite := @dispatch;
-    device^.requestQueue := CFIFO_New(sizeof(Pointer),4);
+    device^.requestQueue := CFIFO_New(sizeof(Pointer),8);
+    device^.maxActive := 0; mock^.FailRead := true;
+    for i := 1 to 4 do
+        Assert(storage_read_async(device,0,1,puint32(mock^.Data),@completion,mock)=eNone,'queued fault request accepted');
+    Assert(mock^.Callbacks=0,'queued requests wait for dispatch');
+    device^.maxActive := 1;
+    Assert(storage_read_async(device,0,1,puint32(mock^.Data),@completion,mock)=eNone,'fault queue drain accepted');
+    Assert((mock^.Callbacks=5) and (mock^.Error=eIOError),'every queued error completes once');
+    Assert((mock^.MaxDepth=1) and (device^.activeCount=0) and (CFIFO_Size(device^.requestQueue)=0),
+           'inline failures drain without recursive driver dispatch');
+    mock^.FailRead := false; mock^.Callbacks := 0;
     device^.cachedMBR := kalloc(512);
     mbr := PMaster_Boot_Record(device^.cachedMBR);
     memset(uint32(mbr),0,512); mbr^.boot_sector := $AA55; mbr^.signature := $12345678;

src/driver/storage/driver.storage.mgr.pas

@@ -246,6 +246,7 @@ begin
     device^.removed := false;
     device^.requestQueue := CFIFO_New(SizeOf(PIORequest), 128);
     device^.activeCount := 0;
+    device^.dispatching := false;
     if device^.maxActive = 0 then device^.maxActive := 1;
     device^.cachedMBR := nil;
     device^.metadataBusy := false;
@@ -416,6 +417,8 @@ procedure dispatch_next(device : PStorage_Device);
 var
     heapReq : PIORequest;
 begin
+    if device^.dispatching then exit;
+    device^.dispatching := true;
     { Dispatch queued requests up to maxActive hardware slots }
     while device^.activeCount < device^.maxActive do begin
         if not CFIFO_Dequeue(device^.requestQueue, @heapReq) then break;  { queue empty }
@@ -441,12 +444,14 @@ begin
             end;
         end;
     end;
+    device^.dispatching := false;
 end;
 
 function submit_io(request : PIORequest) : TError;
 var
     device  : PStorage_Device;
     heapReq : PIORequest;
+    flags : uint32;
 begin
     { Pre-checks — fail fast before touching the queue }
     if request = nil then begin submit_io := eInvalidArgument; exit; end;
@@ -477,38 +482,16 @@ begin
 
     { Enqueue and attempt dispatch — must be ISR-safe and bounded.
       Reject once the fixed queue is full instead of growing with CLI held. }
-    asm pushf; cli end;
-    if (device^.activeCount < device^.maxActive) and (CFIFO_Size(device^.requestQueue) = 0) then begin
-        device^.activeCount := device^.activeCount + 1;
-        heapReq^.State := iosDispatched;
-        asm popf end;
-        case heapReq^.RequestType of
-            ioRead: begin
-                if device^.dispatchRead <> nil then
-                    device^.dispatchRead(device, heapReq)
-                else
-                    complete_io(heapReq, false, eDeviceNotFound);
-            end;
-            ioWrite: begin
-                if device^.dispatchWrite <> nil then
-                    device^.dispatchWrite(device, heapReq)
-                else
-                    complete_io(heapReq, false, eDeviceNotFound);
-            end;
-        end;
-        submit_io := eNone;
-        exit;
-    end;
-
+    asm pushfd; cli; pop flags end;
     if CFIFO_Size(device^.requestQueue) >= CFIFO_Capacity(device^.requestQueue) then begin
-        asm popf end;
+        if (flags and $200) <> 0 then asm sti end;
         ioreq_free(heapReq);
         submit_io := eQueueFull;
         exit;
     end;
     CFIFO_Enqueue(device^.requestQueue, @heapReq);
     dispatch_next(device);
-    asm popf end;
+    if (flags and $200) <> 0 then asm sti end;
 
     submit_io := eNone;
 end;

src/driver/storage/driver.storage.types.pas

@@ -270,6 +270,7 @@ type
         dispatchRead     : TDriverDispatch;   { nil if driver not yet migrated }
         dispatchWrite    : TDriverDispatch;   { nil if driver not yet migrated }
         requestQueue     : PCFIFOQueue;       { per-device I/O request CFIFO }
+        dispatching      : boolean; { prevents recursive synchronous-error queue draining }
         activeCount      : uint32;            { number of commands currently dispatched to HW }
         maxActive        : uint32;            { max concurrent commands (NCQ depth) }
 

src/test/test.pas

@@ -34,6 +34,7 @@ uses
     driver.storage.vfs,
     driver.storage.test,
     driver.storage.metatest,
+    driver.storage.ctl.ahci,
     core.enc.fnv1a,
     core.enc.djb2,
     core.ds.bloom,
@@ -70,6 +71,7 @@ begin
     driver.storage.vfs.UnitTest;
     driver.storage.test.UnitTest;
     driver.storage.metatest.UnitTest;
+    driver.storage.ctl.ahci.UnitTest;
     core.enc.fnv1a.UnitTest;
     core.enc.djb2.UnitTest;
     core.ds.bloom.UnitTest;