[v6,3/6] fdt: Pass the resulting device tree to QEMU

Message ID 20171024013153.28200-4-aik@ozlabs.ru
State New
Headers show
Series
  • fdt: Pass the resulting device tree to QEMU + related fixes
Related show

Commit Message

Alexey Kardashevskiy Oct. 24, 2017, 1:31 a.m.
This creates flatten device tree and passes it to QEMU via a custom
hypercall right before jumping to RTAS.

This preloads strings with 40 property names from CPU and PCI device nodes
and the strings lookup only searches within these.

Test results on a guest with 256 CPUs and 256 virtual Intel E1000 devices
running on a POWER8 box:
FDTsize=366024 Strings=15888 Struct=350080 Reused str=12457 242 ms

A simple guest (one CPU, no PCI) with this patch as is:
FDTsize=15940 Strings=3148 Struct=12736 Reused str=84 7 ms

While we are here, fix the version handling in fdt-init. It only matters
a little for the fdt-debug==1 case though.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v6:
* fix memory sizes for free-mem
* store correct chosen-cpu to the header (used to be just 0)
* fdt-skip-string uses zcount now and works 30% faster
* moved to a new file - fdt-fl.fs

v5:
* applied latest comments from Segher
* s/fdt-property/fdt-copy-property/, s/fdt-properties/fdt-copy-properties/
* reduced the temporary buffers to 1MB each as the guest uses 1MB in total
anyway
* do not pass root phandle to fdt-flatten-tree, it fetches it from
device-tree itself
* reworked fdt-copy-properties to use for-all-words proposed by Segher

v4:
* reworked fdt-properties, works lot faster
* do not store "name" properties as nodes have names already

v3:
* fixed stack handling after hcall returned
* fixed format versions in both rendering and parsing paths
* rebased on top of removed unused hvcalls
* renamed used variables to have fdtfl- prefixes as there are already
some for parsing the initial dt

v2:
* fixed comments from review
* added strings cache
* changed last_compat_vers from 0x17 to 0x16 as suggested by dwg

---

I tested the blob by storing it from QEMU to a file and decompiling it.
---
 lib/libhvcall/libhvcall.h |   3 +-
 board-qemu/slof/OF.fs     |   2 +
 board-qemu/slof/fdt-fl.fs | 266 ++++++++++++++++++++++++++++++++++++++++++++++
 board-qemu/slof/rtas.fs   |   6 ++
 lib/libhvcall/hvcall.code |   5 +
 lib/libhvcall/hvcall.in   |   1 +
 6 files changed, 282 insertions(+), 1 deletion(-)
 create mode 100644 board-qemu/slof/fdt-fl.fs

Patch

diff --git a/lib/libhvcall/libhvcall.h b/lib/libhvcall/libhvcall.h
index 6356a62..3fa4398 100644
--- a/lib/libhvcall/libhvcall.h
+++ b/lib/libhvcall/libhvcall.h
@@ -24,7 +24,8 @@ 
 #define KVMPPC_H_LOGICAL_MEMOP  (KVMPPC_HCALL_BASE + 0x1)
 /* Client Architecture support */
 #define KVMPPC_H_CAS            (KVMPPC_HCALL_BASE + 0x2)
-#define KVMPPC_HCALL_MAX        KVMPPC_H_CAS
+#define KVMPPC_H_UPDATE_DT      (KVMPPC_HCALL_BASE + 0x3)
+#define KVMPPC_HCALL_MAX        KVMPPC_H_UPDATE_DT
 
 #ifndef __ASSEMBLY__
 
diff --git a/board-qemu/slof/OF.fs b/board-qemu/slof/OF.fs
index 4e04b84..35fe233 100644
--- a/board-qemu/slof/OF.fs
+++ b/board-qemu/slof/OF.fs
@@ -119,6 +119,8 @@  check-boot-menu
 
 380 cp
 
+#include "fdt-fl.fs"
+
 \ Grab rtas from qemu
 #include "rtas.fs"
 
diff --git a/board-qemu/slof/fdt-fl.fs b/board-qemu/slof/fdt-fl.fs
new file mode 100644
index 0000000..71b2efc
--- /dev/null
+++ b/board-qemu/slof/fdt-fl.fs
@@ -0,0 +1,266 @@ 
+\ *****************************************************************************
+\ * Copyright (c) 2017 IBM Corporation
+\ * All rights reserved.
+\ * This program and the accompanying materials
+\ * are made available under the terms of the BSD License
+\ * which accompanies this distribution, and is available at
+\ * http://www.opensource.org/licenses/bsd-license.php
+\ ****************************************************************************/
+
+0 VALUE fdtfl-debug
+
+VARIABLE fdtfl-struct
+VARIABLE fdtfl-struct-here
+VARIABLE fdtfl-strings
+VARIABLE fdtfl-strings-cache
+VARIABLE fdtfl-strings-here
+VARIABLE fdtfl-strings-reused \ debug only
+VARIABLE fdlfl-ms \ debug only
+
+: fdt-skip-string ( cur -- cur ) zcount + char+  4 #aligned ;
+
+: zstring=  ( str len zstr -- flag )
+    2dup + c@ 0<> IF
+        3drop false
+        EXIT
+    THEN
+    swap comp 0=
+;
+
+: fdt-find-string ( name namelen -- nameoff true | false )
+    fdtfl-strings @
+    BEGIN
+        dup fdtfl-strings-cache @ <
+    WHILE
+        3dup zstring= IF
+            nip nip             ( curstr )
+            fdtfl-strings @ -
+            true
+            EXIT
+        THEN
+        fdt-skip-string
+    REPEAT
+    3drop
+    false
+;
+
+: fdt-str-allot ( len -- ) fdtfl-strings-here @ + to fdtfl-strings-here ;
+: fdt-str-c, ( char -- ) fdtfl-strings-here @ 1 fdt-str-allot c! ;
+: fdt-str-align  ( -- )
+    fdtfl-strings-here @
+    dup dup 4 #aligned swap -   ( here bytes-to-erase )
+    dup -rot
+    erase
+    fdt-str-allot
+;
+: fdt-str-bytes, ( data len -- ) fdtfl-strings-here @ over fdt-str-allot swap move ;
+: fdt-str-ztr, ( str len -- ) fdt-str-bytes, 0 fdt-str-c, ;
+
+: fdt-add-string ( name namelen -- nameoff )
+    fdtfl-strings-here @ -rot
+    fdt-str-ztr,
+    fdt-str-align
+    fdtfl-strings @ -
+;
+
+: fdt-get-string ( name namelen -- nameoff )
+    2dup fdt-find-string IF
+        -rot 2drop
+        fdtfl-debug IF
+           1 fdtfl-strings-reused +!
+        THEN
+        EXIT
+    THEN
+    fdt-add-string
+;
+
+: fdt-allot ( len -- ) fdtfl-struct-here @ + to fdtfl-struct-here ;
+: fdt-c, ( char -- ) fdtfl-struct-here @ 1 fdt-allot c! ;
+: fdt-align  ( -- )
+    fdtfl-struct-here @
+    dup dup 4 #aligned swap -   ( here bytes-to-erase )
+    dup -rot
+    erase
+    fdt-allot
+;
+: fdt-bytes, ( data len -- ) fdtfl-struct-here @ over fdt-allot swap move ;
+: fdt-ztr, ( str len -- ) fdt-bytes, 0 fdt-c, ;
+: fdt-l, ( token -- ) fdtfl-struct-here @ l! /l fdt-allot ;
+
+: fdt-begin-node ( phandle -- )
+    OF_DT_BEGIN_NODE fdt-l,
+    dup device-tree @ = IF drop s" " ELSE node>qname THEN
+    fdt-ztr,
+    fdt-align
+;
+
+: fdt-end-node ( -- ) OF_DT_END_NODE fdt-l, ;
+
+: fdt-prop ( prop len name namelen -- )
+    OF_DT_PROP fdt-l,
+
+    \ get string offset
+    fdt-get-string      ( prop len nameoff )
+
+    \ store len and nameoff
+    over fdt-l,
+    fdt-l,              ( prop len )
+
+    \ now store the bytes
+    fdt-bytes,
+    fdt-align
+;
+
+: fdt-end ( -- ) OF_DT_END fdt-l, ;
+
+: fdt-copy-property ( link -- )
+    dup link> execute
+    rot
+    link>name name>string
+    2dup s" name" str= IF 4drop EXIT THEN \ skipping useless "name"
+    fdt-prop
+;
+
+: for-all-words ( wid xt -- ) \ xt has sig ( lfa -- )
+    >r
+    cell+ @ BEGIN dup WHILE dup r@ execute @ REPEAT
+    r> 2drop
+;
+
+: fdt-copy-properties ( phandle -- )
+   dup encode-int s" phandle" fdt-prop
+   node>properties @
+   ['] fdt-copy-property for-all-words
+;
+
+: fdt-copy-node ( node --  )
+    fdtfl-debug 1 > IF dup node>path type cr THEN
+    dup fdt-begin-node
+    dup fdt-copy-properties
+    child BEGIN dup WHILE dup recurse peer REPEAT
+    drop
+    fdt-end-node
+;
+
+: fdtfl-strings-preload ( -- )
+    s" reg" fdt-add-string drop
+    s" status" fdt-add-string drop
+    s" 64-bit" fdt-add-string drop
+    s" phandle" fdt-add-string drop
+    s" ibm,vmx" fdt-add-string drop
+    s" ibm,dfp" fdt-add-string drop
+    s" slb-size" fdt-add-string drop
+    s" ibm,purr" fdt-add-string drop
+    s" vendor-id" fdt-add-string drop
+    s" device-id" fdt-add-string drop
+    s" min-grant" fdt-add-string drop
+    s" class-code" fdt-add-string drop
+    s" compatible" fdt-add-string drop
+    s" interrupts" fdt-add-string drop
+    s" cpu-version" fdt-add-string drop
+    s" #size-cells" fdt-add-string drop
+    s" ibm,req#msi" fdt-add-string drop
+    s" revision-id" fdt-add-string drop
+    s" device_type" fdt-add-string drop
+    s" max-latency" fdt-add-string drop
+    s" ibm,chip-id" fdt-add-string drop
+    s" ibm,pft-size" fdt-add-string drop
+    s" ibm,slb-size" fdt-add-string drop
+    s" devsel-speed" fdt-add-string drop
+    s" ibm,loc-code" fdt-add-string drop
+    s" subsystem-id" fdt-add-string drop
+    s" d-cache-size" fdt-add-string drop
+    s" i-cache-size" fdt-add-string drop
+    s" #address-cells" fdt-add-string drop
+    s" clock-frequency" fdt-add-string drop
+    s" cache-line-size" fdt-add-string drop
+    s" ibm,pa-features" fdt-add-string drop
+    s" ibm,my-drc-index" fdt-add-string drop
+    s" d-cache-line-size" fdt-add-string drop
+    s" i-cache-line-size" fdt-add-string drop
+    s" assigned-addresses" fdt-add-string drop
+    s" d-cache-block-size" fdt-add-string drop
+    s" i-cache-block-size" fdt-add-string drop
+    s" timebase-frequency" fdt-add-string drop
+    s" subsystem-vendor-id" fdt-add-string drop
+    s" ibm,segment-page-sizes" fdt-add-string drop
+    s" ibm,ppc-interrupt-server#s" fdt-add-string drop
+    s" ibm,processor-segment-sizes" fdt-add-string drop
+    s" ibm,ppc-interrupt-gserver#s" fdt-add-string drop
+;
+
+: fdt-append-blob ( bytes cur blob -- cur )
+    3dup -rot swap move
+    drop +
+;
+
+: fdt-flatten-tree ( -- tree )
+    100000 alloc-mem dup fdtfl-struct-here ! fdtfl-struct !
+    100000 alloc-mem dup fdtfl-strings-here ! fdtfl-strings !
+
+    fdtfl-debug IF
+        0 fdtfl-strings-reused !
+        milliseconds fdlfl-ms !
+    THEN
+
+    \ Preload strings cache
+    fdtfl-strings-preload
+    fdtfl-strings-here @ fdtfl-strings-cache !
+    \ Render the blobs
+    device-tree @ fdt-copy-node
+    fdt-end
+
+    \ Calculate strings and struct sizes
+    fdtfl-struct-here @ fdtfl-struct @ -
+    fdtfl-strings-here @ fdtfl-strings @ - ( struct-len strings-len )
+
+    2dup + /fdth +
+    10 + \ Reserve 16 bytes for an empty reserved block
+
+    fdtfl-debug IF
+        3dup
+        ." FDTsize=" .d ." Strings=" .d ." Struct=" .d
+        ." Reused str=" fdtfl-strings-reused @ .d
+        milliseconds fdlfl-ms @ - .d ." ms"
+        cr
+    THEN
+
+    \ Allocate flatten DT blob
+    dup alloc-mem                   ( struct-len strings-len total-len fdt )
+    >r                              ( struct-len strings-len total-len r: fdt )
+
+    \ Write header
+    OF_DT_HEADER        r@ >fdth_magic l!
+    dup                 r@ >fdth_tsize l!
+    /fdth 10 + 2 pick + r@ >fdth_struct_off l!
+    /fdth 10 +          r@ >fdth_string_off l!
+    /fdth               r@ >fdth_rsvmap_off l!
+    11                  r@ >fdth_version l!
+    10                  r@ >fdth_compat_vers l!
+    chosen-cpu-unit     r@ >fdth_boot_cpu l!
+    over                r@ >fdth_string_size l!
+    2 pick              r@ >fdth_struct_size l!
+                                    ( struct-len strings-len total-len r: fdt )
+
+    drop                            ( struct-len strings-len r: fdt )
+    r@ /fdth +                      ( struct-len strings-len cur r: fdt )
+
+    \ Write the reserved entry
+    0 over ! cell+ 0 over ! cell+
+
+    \ Write strings and struct blobs
+    fdtfl-strings @ fdt-append-blob
+    fdtfl-struct @ fdt-append-blob
+    drop
+
+    \ Free temporary blobs
+    fdtfl-struct @ 100000 free-mem
+    fdtfl-strings @ 100000 free-mem
+
+    \ Return fdt
+    r>
+;
+
+: fdt-flatten-tree-free ( tree )
+    dup >fdth_tsize l@ free-mem
+;
diff --git a/board-qemu/slof/rtas.fs b/board-qemu/slof/rtas.fs
index b17157e..f1a4abe 100644
--- a/board-qemu/slof/rtas.fs
+++ b/board-qemu/slof/rtas.fs
@@ -98,6 +98,12 @@  find-qemu-rtas
 ;
 
 : rtas-quiesce ( -- )
+    fdt-flatten-tree
+    dup hv-update-dt ?dup IF
+        \ Ignore hcall not implemented error, print error otherwise
+        dup -2 <> IF ." HV-UPDATE-DT error: " . cr ELSE drop THEN
+    THEN
+    fdt-flatten-tree-free
     " quiesce" rtas-get-token rtas-cb rtas>token l!
     0 rtas-cb rtas>nargs l!
     0 rtas-cb rtas>nret l!
diff --git a/lib/libhvcall/hvcall.code b/lib/libhvcall/hvcall.code
index 744469f..5918c90 100644
--- a/lib/libhvcall/hvcall.code
+++ b/lib/libhvcall/hvcall.code
@@ -123,3 +123,8 @@  PRIM(check_X2d_and_X2d_patch_X2d_sc1)
 
 	patch_broken_sc1((void*)start, (void*)end, (void*)patch_ins);
 MIRP
+
+PRIM(hv_X2d_update_X2d_dt)
+	unsigned long dt = TOS.u;
+	TOS.u = hv_generic(KVMPPC_H_UPDATE_DT, dt);
+MIRP
diff --git a/lib/libhvcall/hvcall.in b/lib/libhvcall/hvcall.in
index e99d6d1..9193162 100644
--- a/lib/libhvcall/hvcall.in
+++ b/lib/libhvcall/hvcall.in
@@ -30,4 +30,5 @@  cod(RX!)
 
 cod(hv-logical-memop)
 cod(hv-cas)
+cod(hv-update-dt)
 cod(get-print-version)