From patchwork Wed Oct 4 05:40:00 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexey Kardashevskiy X-Patchwork-Id: 821163 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.ozlabs.org (lists.ozlabs.org [103.22.144.68]) (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3y6Pr450MQz9s82 for ; Wed, 4 Oct 2017 16:40:20 +1100 (AEDT) Received: from lists.ozlabs.org (lists.ozlabs.org [IPv6:2401:3900:2:1::3]) by lists.ozlabs.org (Postfix) with ESMTP id 3y6Pr31rpYzDqp4 for ; Wed, 4 Oct 2017 16:40:19 +1100 (AEDT) X-Original-To: slof@lists.ozlabs.org Delivered-To: slof@lists.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=ozlabs.ru (client-ip=107.173.13.209; helo=ozlabs.ru; envelope-from=aik@ozlabs.ru; receiver=) Received: from ozlabs.ru (ozlabs.ru [107.173.13.209]) by lists.ozlabs.org (Postfix) with ESMTP id 3y6Pqx20bxzDqls for ; Wed, 4 Oct 2017 16:40:12 +1100 (AEDT) Received: from vpl1.ozlabs.ibm.com (localhost [IPv6:::1]) by ozlabs.ru (Postfix) with ESMTP id 39A463A60050; Wed, 4 Oct 2017 01:38:52 -0400 (EDT) From: Alexey Kardashevskiy To: slof@lists.ozlabs.org Date: Wed, 4 Oct 2017 16:40:00 +1100 Message-Id: <20171004054001.42031-3-aik@ozlabs.ru> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20171004054001.42031-1-aik@ozlabs.ru> References: <20171004054001.42031-1-aik@ozlabs.ru> Subject: [SLOF] [PATCH slof v4 2/3] fdt: Pass the resulting device tree to QEMU X-BeenThere: slof@lists.ozlabs.org X-Mailman-Version: 2.1.24 Precedence: list List-Id: "Patches for https://github.com/aik/SLOF" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Greg Kurz , Aravinda Prasad MIME-Version: 1.0 Errors-To: slof-bounces+incoming=patchwork.ozlabs.org@lists.ozlabs.org Sender: "SLOF" 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: - the patch as it is: FDTsize=366024 Strings=15888 Struct=350080 Reused str=12457 351 ms - minimize strings by allowing lookup in entire blob: FDTsize=353228 Strings=3092 Struct=350080 Reused str=13211 419 ms - like previos but without strings preloading: FDTsize=353228 Strings=3092 Struct=350080 Reused str=13167 1254 ms - no strings search, simply add them all to the strings blob: FDTsize=548052 Strings=197916 Struct=350080 Reused str=0 165 ms A simple guest (one CPU, no PCI) with this patch as is: FDTsize=15940 Strings=3148 Struct=12736 Reused str=84 10 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 --- Changes: 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; this produces a warning now: aik@fstn1-p1:~$ dtc -f -I dtb -O dts -o dbg.dts dbg.dtb Warning (model_is_string): "model" property in /openprom is not a string openprom { phandle = <0x7e835f40>; relative-addressing; model = <0x534c4f46 0x2c61696b 0x0 0x0>; }; --- lib/libhvcall/libhvcall.h | 3 +- board-qemu/slof/fdt.fs | 290 +++++++++++++++++++++++++++++++++++++++++++++- board-qemu/slof/rtas.fs | 7 ++ lib/libhvcall/hvcall.code | 5 + lib/libhvcall/hvcall.in | 1 + 5 files changed, 303 insertions(+), 3 deletions(-) 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/fdt.fs b/board-qemu/slof/fdt.fs index 851645e..2389659 100644 --- a/board-qemu/slof/fdt.fs +++ b/board-qemu/slof/fdt.fs @@ -27,7 +27,7 @@ struct 4 field >fdth_boot_cpu 4 field >fdth_string_size 4 field >fdth_struct_size -drop +constant /fdth h# d00dfeed constant OF_DT_HEADER h# 1 constant OF_DT_BEGIN_NODE @@ -69,7 +69,7 @@ fdt-start fdt-init dup >fdth_version l@ 3 >= IF ." strings size : 0x" dup >fdth_string_size l@ . cr THEN - dup >fdth_version l@ 17 >= IF + dup >fdth_version l@ 11 >= IF ." struct size : 0x" dup >fdth_struct_size l@ . cr THEN THEN @@ -439,4 +439,290 @@ r> drop fdt-cas-fix? ; +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 fdt-ms \ debug only + +: fdt-skip-string ( cur -- cur ) + BEGIN + dup c@ + WHILE + 1+ + REPEAT + 4 + -4 and +; + +: 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 + fdtfl-strings @ - + -rot + 2drop + 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 + fdt-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 ( name namelen -- ) + OF_DT_BEGIN_NODE fdt-l, + 2dup 1 = swap c@ [char] / = and \ is it "/"? + IF + 2drop s" " \ dtc is still unhappy though + 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-properties ( phandle -- ) + dup encode-int s" phandle" fdt-prop + + node>properties @ cell+ @ ( cur ) + BEGIN + dup + WHILE + dup link> ( cur link ) + dup >name name>string ( cur link name len ) + 2dup s" name" str= IF + \ skipping "name" - it is useless + 2drop ( cur link ) + drop ( cur ) + ELSE ( cur link name len ) + 2 pick ( cur link name len link ) + execute ( cur link name len prop proplen ) + 2swap + fdt-prop ( cur link ) + drop + THEN + @ + REPEAT + drop +; + +: fdt-flatten-node ( node -- ) + fdt-debug 1 > IF dup node>path type cr THEN + dup node>qname fdt-begin-node + dup fdt-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 ( root -- tree ) + 200000 alloc-mem dup fdtfl-struct-here ! fdtfl-struct ! + 200000 alloc-mem dup fdtfl-strings-here ! fdtfl-strings ! + + fdt-debug IF + 0 fdtfl-strings-reused ! + milliseconds fdt-ms ! + THEN + + \ Preload strings cache + fdtfl-strings-preload + fdtfl-strings-here @ fdtfl-strings-cache ! + \ Render the blobs + fdt-flatten-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 and an empty reserved block + + fdt-debug IF + 3dup + ." FDTsize=" .d ." Strings=" .d ." Struct=" .d + ." Reused str=" fdtfl-strings-reused @ .d + milliseconds fdt-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! + 0 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+ ( struct-len strings-len cur r: fdt ) + + \ Write strings and struct blobs + fdtfl-strings @ fdt-append-blob + fdtfl-struct @ fdt-append-blob + drop + + \ Free temporary blobs + fdtfl-struct @ 200000 free-mem + fdtfl-strings @ 200000 free-mem + + \ Return fdt + r> +; + +: fdt-flatten-tree-free ( tree ) + dup >fdth_tsize l@ free-mem +; + +: fdt ( -- ) + " /" find-node + fdt-flatten-tree +; + s" /" find-node fdt-fix-phandles diff --git a/board-qemu/slof/rtas.fs b/board-qemu/slof/rtas.fs index b17157e..219bcda 100644 --- a/board-qemu/slof/rtas.fs +++ b/board-qemu/slof/rtas.fs @@ -98,6 +98,13 @@ find-qemu-rtas ; : rtas-quiesce ( -- ) + " /" find-node + 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)