* [PATCH v1 4/4] powerpc/boot: Add lzo support for uImage
From: Christophe Leroy @ 2019-03-29 8:40 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <3632dd9c8115965b37fd0b8fc50b3352395933fa.1553848759.git.christophe.leroy@c-s.fr>
This patch allows to generate lzo compressed uImage
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/boot/Makefile | 2 ++
arch/powerpc/boot/wrapper | 5 ++++-
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6f1d49fdae98..df3694b947ce 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -203,6 +203,7 @@ config PPC
select HAVE_KERNEL_XZ if PPC_BOOK3S || 44x
select HAVE_KERNEL_LZMA if DEFAULT_UIMAGE
select HAVE_KERNEL_BZIP2 if DEFAULT_UIMAGE
+ select HAVE_KERNEL_LZO if DEFAULT_UIMAGE
select HAVE_KPROBES
select HAVE_KPROBES_ON_FTRACE
select HAVE_KRETPROBES
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 0a7f8c2dc8af..4675575774d7 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -24,6 +24,7 @@ compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP
compress-$(CONFIG_KERNEL_XZ) := CONFIG_KERNEL_XZ
compress-$(CONFIG_KERNEL_LZMA) := CONFIG_KERNEL_LZMA
compress-$(CONFIG_KERNEL_BZIP2) := CONFIG_KERNEL_BZIP2
+compress-$(CONFIG_KERNEL_LZO) := CONFIG_KERNEL_LZO
ifdef CROSS32_COMPILE
BOOTCC := $(CROSS32_COMPILE)gcc
@@ -261,6 +262,7 @@ compressor-$(CONFIG_KERNEL_GZIP) := gz
compressor-$(CONFIG_KERNEL_XZ) := xz
compressor-$(CONFIG_KERNEL_LZMA) := lzma
compressor-$(CONFIG_KERNEL_BZIP2) := bz2
+compressor-$(CONFIG_KERNEL_LZO) := lzo
# args (to if_changed): 1 = (this rule), 2 = platform, 3 = dts 4=dtb 5=initrd
quiet_cmd_wrap = WRAP $@
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index d1384e8c0c6f..2fd3483f9d80 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -137,7 +137,7 @@ while [ "$#" -gt 0 ]; do
-Z)
shift
[ "$#" -gt 0 ] || usage
- [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "lzma" -o "$1" != "bz2" -o "$1" != "none" ] || usage
+ [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "lzma" -o "$1" != "bz2" -o "$1" != "lzo" -o "$1" != "none" ] || usage
compression=".$1"
uboot_comp=$1
@@ -383,6 +383,9 @@ if [ -z "$cacheit" -o ! -f "$vmz$compression" -o "$vmz$compression" -ot "$kernel
.bz2)
bzip2 -f "$vmz.$$"
;;
+ .lzo)
+ lzop -f -9 "$vmz.$$"
+ ;;
*)
# drop the compression suffix so the stripped vmlinux is used
compression=
--
2.13.3
^ permalink raw reply related
* [PATCH v1 1/4] powerpc/boot: don't force gzipped uImage
From: Christophe Leroy @ 2019-03-29 8:40 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
This patch modifies the generation of uImage by handing over
the selected compression type instead of forcing gzip
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/boot/wrapper | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index f9141eaec6ff..4e9beecf2502 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -41,6 +41,7 @@ dts=
cacheit=
binary=
compression=.gz
+uboot_comp=gzip
pie=
format=
@@ -131,6 +132,7 @@ while [ "$#" -gt 0 ]; do
;;
-z)
compression=.gz
+ uboot_comp=gzip
;;
-Z)
shift
@@ -138,15 +140,21 @@ while [ "$#" -gt 0 ]; do
[ "$1" != "gz" -o "$1" != "xz" -o "$1" != "none" ] || usage
compression=".$1"
+ uboot_comp=$1
if [ $compression = ".none" ]; then
compression=
+ uboot_comp=none
fi
+ if [ $uboot_comp = "gz" ]; then
+ uboot_comp=gzip
+ fi
;;
--no-gzip)
# a "feature" of the the wrapper script is that it can be used outside
# the kernel tree. So keeping this around for backwards compatibility.
compression=
+ uboot_comp=none
;;
-?)
usage
@@ -369,6 +377,7 @@ if [ -z "$cacheit" -o ! -f "$vmz$compression" -o "$vmz$compression" -ot "$kernel
*)
# drop the compression suffix so the stripped vmlinux is used
compression=
+ uboot_comp=none
;;
esac
@@ -412,7 +421,7 @@ membase=`${CROSS}objdump -p "$kernel" | grep -m 1 LOAD | awk '{print $7}'`
case "$platform" in
uboot)
rm -f "$ofile"
- ${MKIMAGE} -A ppc -O linux -T kernel -C gzip -a $membase -e $membase \
+ ${MKIMAGE} -A ppc -O linux -T kernel -C $uboot_comp -a $membase -e $membase \
$uboot_version -d "$vmz" "$ofile"
if [ -z "$cacheit" ]; then
rm -f "$vmz"
--
2.13.3
^ permalink raw reply related
* [PATCH v1 3/4] powerpc/boot: Add bzip2 support for uImage
From: Christophe Leroy @ 2019-03-29 8:40 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <3632dd9c8115965b37fd0b8fc50b3352395933fa.1553848759.git.christophe.leroy@c-s.fr>
This patch allows to generate bzip2 compressed uImage
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/boot/Makefile | 2 ++
arch/powerpc/boot/wrapper | 8 +++++++-
3 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 69ff2476490c..6f1d49fdae98 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -202,6 +202,7 @@ config PPC
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_XZ if PPC_BOOK3S || 44x
select HAVE_KERNEL_LZMA if DEFAULT_UIMAGE
+ select HAVE_KERNEL_BZIP2 if DEFAULT_UIMAGE
select HAVE_KPROBES
select HAVE_KPROBES_ON_FTRACE
select HAVE_KRETPROBES
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 9b7b11a22925..0a7f8c2dc8af 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -23,6 +23,7 @@ all: $(obj)/zImage
compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP
compress-$(CONFIG_KERNEL_XZ) := CONFIG_KERNEL_XZ
compress-$(CONFIG_KERNEL_LZMA) := CONFIG_KERNEL_LZMA
+compress-$(CONFIG_KERNEL_BZIP2) := CONFIG_KERNEL_BZIP2
ifdef CROSS32_COMPILE
BOOTCC := $(CROSS32_COMPILE)gcc
@@ -259,6 +260,7 @@ endif
compressor-$(CONFIG_KERNEL_GZIP) := gz
compressor-$(CONFIG_KERNEL_XZ) := xz
compressor-$(CONFIG_KERNEL_LZMA) := lzma
+compressor-$(CONFIG_KERNEL_BZIP2) := bz2
# args (to if_changed): 1 = (this rule), 2 = platform, 3 = dts 4=dtb 5=initrd
quiet_cmd_wrap = WRAP $@
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 51dc42f5acbc..d1384e8c0c6f 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -137,7 +137,7 @@ while [ "$#" -gt 0 ]; do
-Z)
shift
[ "$#" -gt 0 ] || usage
- [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "lzma" -o "$1" != "none" ] || usage
+ [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "lzma" -o "$1" != "bz2" -o "$1" != "none" ] || usage
compression=".$1"
uboot_comp=$1
@@ -149,6 +149,9 @@ while [ "$#" -gt 0 ]; do
if [ $uboot_comp = "gz" ]; then
uboot_comp=gzip
fi
+ if [ $uboot_comp = "bz2" ]; then
+ uboot_comp=bzip2
+ fi
;;
--no-gzip)
# a "feature" of the the wrapper script is that it can be used outside
@@ -377,6 +380,9 @@ if [ -z "$cacheit" -o ! -f "$vmz$compression" -o "$vmz$compression" -ot "$kernel
.lzma)
xz --format=lzma -f -6 "$vmz.$$"
;;
+ .bz2)
+ bzip2 -f "$vmz.$$"
+ ;;
*)
# drop the compression suffix so the stripped vmlinux is used
compression=
--
2.13.3
^ permalink raw reply related
* [PATCH v1 2/4] powerpc/boot: Add lzma support for uImage
From: Christophe Leroy @ 2019-03-29 8:40 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <3632dd9c8115965b37fd0b8fc50b3352395933fa.1553848759.git.christophe.leroy@c-s.fr>
This patch allows to generate lzma compressed uImage
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/boot/Makefile | 2 ++
arch/powerpc/boot/wrapper | 5 ++++-
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2d0be82c3061..69ff2476490c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -201,6 +201,7 @@ config PPC
select HAVE_IRQ_EXIT_ON_IRQ_STACK
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_XZ if PPC_BOOK3S || 44x
+ select HAVE_KERNEL_LZMA if DEFAULT_UIMAGE
select HAVE_KPROBES
select HAVE_KPROBES_ON_FTRACE
select HAVE_KRETPROBES
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 73d1f3562978..9b7b11a22925 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -22,6 +22,7 @@ all: $(obj)/zImage
compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP
compress-$(CONFIG_KERNEL_XZ) := CONFIG_KERNEL_XZ
+compress-$(CONFIG_KERNEL_LZMA) := CONFIG_KERNEL_LZMA
ifdef CROSS32_COMPILE
BOOTCC := $(CROSS32_COMPILE)gcc
@@ -257,6 +258,7 @@ endif
compressor-$(CONFIG_KERNEL_GZIP) := gz
compressor-$(CONFIG_KERNEL_XZ) := xz
+compressor-$(CONFIG_KERNEL_LZMA) := lzma
# args (to if_changed): 1 = (this rule), 2 = platform, 3 = dts 4=dtb 5=initrd
quiet_cmd_wrap = WRAP $@
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 4e9beecf2502..51dc42f5acbc 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -137,7 +137,7 @@ while [ "$#" -gt 0 ]; do
-Z)
shift
[ "$#" -gt 0 ] || usage
- [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "none" ] || usage
+ [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "lzma" -o "$1" != "none" ] || usage
compression=".$1"
uboot_comp=$1
@@ -374,6 +374,9 @@ if [ -z "$cacheit" -o ! -f "$vmz$compression" -o "$vmz$compression" -ot "$kernel
.gz)
gzip -n -f -9 "$vmz.$$"
;;
+ .lzma)
+ xz --format=lzma -f -6 "$vmz.$$"
+ ;;
*)
# drop the compression suffix so the stripped vmlinux is used
compression=
--
2.13.3
^ permalink raw reply related
* Re: [PATCH][next] ASoC: fsl: fix spelling mistake: "missign" -> "missing"
From: Viorel Suman @ 2019-03-29 8:39 UTC (permalink / raw)
To: dl-linux-imx, colin.king@canonical.com, timur@kernel.org,
Xiubo.Lee@gmail.com, nicoleotsuka@gmail.com, festevam@gmail.com,
broonie@kernel.org, mojha@codeaurora.org, tiwai@suse.com,
linuxppc-dev@lists.ozlabs.org, lgirdwood@gmail.com,
shawnguo@kernel.org, linux-arm-kernel@lists.infradead.org,
perex@perex.cz, kernel@pengutronix.de,
alsa-devel@alsa-project.org, s.hauer@pengutronix.de
Cc: kernel-janitors@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <acedd6b3-9234-390d-1626-ac02223c93cd@codeaurora.org>
On Jo, 2019-03-28 at 15:48 +0530, Mukesh Ojha wrote:
> On 3/28/2019 2:58 PM, Colin King wrote:
> >
> > From: Colin Ian King <colin.king@canonical.com>
> >
> > There is a spelling mistake in a dev_err message. Fix this.
> >
> > Signed-off-by: Colin Ian King <colin.king@canonical.com>
>
> Reviewed-by: Mukesh Ojha <mojha@codeaurora.org>
Acked-by: Viorel Suman <viorel.suman@nxp.com>
>
> -Mukesh
>
> >
> > ---
> > sound/soc/fsl/imx-audmix.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-
> > audmix.c
> > index 72e37ca6cfbb..7983bd339c01 100644
> > --- a/sound/soc/fsl/imx-audmix.c
> > +++ b/sound/soc/fsl/imx-audmix.c
> > @@ -161,7 +161,7 @@ static int imx_audmix_probe(struct
> > platform_device *pdev)
> > }
> >
> > if (!audmix_np) {
> > - dev_err(&pdev->dev, "Missign DT node for parent
> > device.\n");
> > + dev_err(&pdev->dev, "Missing DT node for parent
> > device.\n");
> > return -EINVAL;
> > }
> >
^ permalink raw reply
* Re: [Qemu-ppc] pseries on qemu-system-ppc64le crashes in doorbell_core_ipi()
From: Sebastian Andrzej Siewior @ 2019-03-29 8:32 UTC (permalink / raw)
To: Suraj Jitindar Singh
Cc: Nicholas Piggin, qemu-ppc, Cédric Le Goater, Paul Mackerras,
tglx, linuxppc-dev, David Gibson
In-Reply-To: <1553836851.2264.2.camel@gmail.com>
On 2019-03-29 16:20:51 [+1100], Suraj Jitindar Singh wrote:
>
> Yeah the kernel must have used msgsndp which isn't implemented for TCG
> yet. We use doorbells in linux but only for threads which are on the
> same core.
It is msgsndp as per instruction decode.
> And when I try to construct a situation with more than 1 thread per
> core (e.g. -smp 4,threads=4), I get "TCG cannot support more than 1
> thread/core on a pseries machine".
>
> So I wonder why the guest thinks it can use msgsndp...
I see
|# cat /sys/devices/system/cpu/cpu*/topology/thread_siblings_list
|0
|1
|2
|3
so this works all well. The problem is when a CPU sends an IPI to itself
then linux's doorbell_try_core_ipi() considers this as a valid sibling
and here we have the msgsndp.
Sebastian
^ permalink raw reply
* [PATCH] powerpc/64s/radix: Fix radix segment exception handling
From: Nicholas Piggin @ 2019-03-29 7:42 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Aneesh Kumar K . V, Nicholas Piggin, Anton Blanchard
Commit 48e7b76957 ("powerpc/64s/hash: Convert SLB miss handlers to C")
broke the radix-mode segment exception handler. In radix mode, this is
exception is not an SLB miss, rather it signals that the EA is outside
the range translated by any page table.
The commit lost the radix feature alternate code patch, which can
cause faults to some EAs to kernel BUG at arch/powerpc/mm/slb.c:639!
The original radix code would send faults to slb_miss_large_addr,
which would end up faulting due to slb_addr_limit being 0. This patch
sends radix directly to do_bad_slb_fault, which is a bit clearer.
Fixes: 48e7b76957 ("powerpc/64s/hash: Convert SLB miss handlers to C")
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a5b8fbae56a0..9481a117e242 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -656,11 +656,17 @@ EXC_COMMON_BEGIN(data_access_slb_common)
ld r4,PACA_EXSLB+EX_DAR(r13)
std r4,_DAR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
bl do_slb_fault
cmpdi r3,0
bne- 1f
b fast_exception_return
1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
@@ -705,11 +711,17 @@ EXC_COMMON_BEGIN(instruction_access_slb_common)
EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB)
ld r4,_NIP(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
bl do_slb_fault
cmpdi r3,0
bne- 1f
b fast_exception_return
1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
std r3,RESULT(r1)
bl save_nvgprs
RECONCILE_IRQ_STATE(r10, r11)
--
2.20.1
^ permalink raw reply related
* Re: [PATCH] powerpc/xmon: add read-only mode
From: Christophe Leroy @ 2019-03-29 7:41 UTC (permalink / raw)
To: cmr, linuxppc-dev; +Cc: andonnel
In-Reply-To: <20190329042153.25698-1-cmr@informatik.wtf>
Le 29/03/2019 à 05:21, cmr a écrit :
> Operations which write to memory should be restricted on secure systems
> and optionally to avoid self-destructive behaviors.
>
> Add a config option, XMON_RO, to control default xmon behavior along
> with kernel cmdline options xmon=ro and xmon=rw for explicit control.
> The default is to enable read-only mode.
>
> The following xmon operations are affected:
> memops:
> disable memmove
> disable memset
> memex:
> no-op'd mwrite
> super_regs:
> no-op'd write_spr
> bpt_cmds:
> disable
> proc_call:
> disable
>
> Signed-off-by: cmr <cmr@informatik.wtf>
A Fully qualified name should be used.
> ---
> arch/powerpc/Kconfig.debug | 7 +++++++
> arch/powerpc/xmon/xmon.c | 24 ++++++++++++++++++++++++
> 2 files changed, 31 insertions(+)
>
> diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
> index 4e00cb0a5464..33cc01adf4cb 100644
> --- a/arch/powerpc/Kconfig.debug
> +++ b/arch/powerpc/Kconfig.debug
> @@ -117,6 +117,13 @@ config XMON_DISASSEMBLY
> to say Y here, unless you're building for a memory-constrained
> system.
>
> +config XMON_RO
> + bool "Set xmon read-only mode"
> + depends on XMON
> + default y
Should it really be always default y ?
I would set default 'y' only when some security options are also set.
> + help
> + Disable state- and memory-altering write operations in xmon.
> +
> config DEBUGGER
> bool
> depends on KGDB || XMON
> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> index a0f44f992360..c13ee73cdfd4 100644
> --- a/arch/powerpc/xmon/xmon.c
> +++ b/arch/powerpc/xmon/xmon.c
> @@ -80,6 +80,7 @@ static int set_indicator_token = RTAS_UNKNOWN_SERVICE;
> #endif
> static unsigned long in_xmon __read_mostly = 0;
> static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT);
> +static int xmon_ro = IS_ENABLED(CONFIG_XMON_RO);
Would be better to use a 'bool' type and call it something like
'xmon_is_ro' (ref Kernel Codying Style, §17)
>
> static unsigned long adrs;
> static int size = 1;
> @@ -1042,6 +1043,8 @@ cmds(struct pt_regs *excp)
> set_lpp_cmd();
> break;
> case 'b':
> + if (xmon_ro == 1)
if (xmon_is_ro)
[Same everywhere below]
Christophe
> + break;
> bpt_cmds();
> break;
> case 'C':
> @@ -1055,6 +1058,8 @@ cmds(struct pt_regs *excp)
> bootcmds();
> break;
> case 'p':
> + if (xmon_ro == 1)
> + break;
> proccall();
> break;
> case 'P':
> @@ -1777,6 +1782,9 @@ read_spr(int n, unsigned long *vp)
> static void
> write_spr(int n, unsigned long val)
> {
> + if (xmon_ro == 1)
> + return;
> +
> if (setjmp(bus_error_jmp) == 0) {
> catch_spr_faults = 1;
> sync();
> @@ -2016,6 +2024,10 @@ mwrite(unsigned long adrs, void *buf, int size)
> char *p, *q;
>
> n = 0;
> +
> + if (xmon_ro == 1)
> + return n;
> +
> if (setjmp(bus_error_jmp) == 0) {
> catch_memory_errors = 1;
> sync();
> @@ -2884,9 +2896,13 @@ memops(int cmd)
> scanhex((void *)&mcount);
> switch( cmd ){
> case 'm':
> + if (xmon_ro == 1)
> + break;
> memmove((void *)mdest, (void *)msrc, mcount);
> break;
> case 's':
> + if (xmon_ro == 1)
> + break;
> memset((void *)mdest, mval, mcount);
> break;
> case 'd':
> @@ -3796,6 +3812,14 @@ static int __init early_parse_xmon(char *p)
> } else if (strncmp(p, "on", 2) == 0) {
> xmon_init(1);
> xmon_on = 1;
> + } else if (strncmp(p, "rw", 2) == 0) {
> + xmon_init(1);
> + xmon_on = 1;
> + xmon_ro = 0;
> + } else if (strncmp(p, "ro", 2) == 0) {
> + xmon_init(1);
> + xmon_on = 1;
> + xmon_ro = 1;
> } else if (strncmp(p, "off", 3) == 0)
> xmon_on = 0;
> else
>
^ permalink raw reply
* Re: [PATCH v8 4/4] hugetlb: allow to free gigantic pages regardless of the configuration
From: Alex Ghiti @ 2019-03-29 6:54 UTC (permalink / raw)
To: Mike Kravetz
Cc: Rich Felker, linux-sh, Peter Zijlstra, Dave Hansen,
Heiko Carstens, linux-mm, Paul Mackerras, H . Peter Anvin,
sparclinux, linux-s390, Yoshinori Sato, aneesh.kumar, x86,
Ingo Molnar, linux-arm-kernel, Catalin Marinas, Will Deacon,
Borislav Petkov, Andy Lutomirski, Thomas Gleixner,
Vlastimil Babka, linux-kernel, Martin Schwidefsky, Andrew Morton,
linuxppc-dev, David S . Miller
In-Reply-To: <c6a93f46-4d8a-e7fd-3f39-4c3c5a9ed514@oracle.com>
On 3/28/19 4:43 PM, Mike Kravetz wrote:
> On 3/26/19 11:36 PM, Alexandre Ghiti wrote:
>> On systems without CONTIG_ALLOC activated but that support gigantic pages,
>> boottime reserved gigantic pages can not be freed at all. This patch
>> simply enables the possibility to hand back those pages to memory
>> allocator.
>>
>> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
>> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
> Thanks for all the updates
>
> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Thanks for all your reviews :)
Alex
^ permalink raw reply
* [PATCH v2] powerpc/vmlinux.lds: Drop binutils < 2.18 workarounds
From: Joel Stanley @ 2019-03-29 6:44 UTC (permalink / raw)
To: linuxppc-dev
Segher added some workarounds for binutils < 2.18 and GCC < 4.2. We
now set GCC 4.6 and binutils 2.20 as the minimum, so the workarounds
can be dropped.
This is mostly a revert of c69cccc95fe4 ("powerpc: Fix build bug with
binutils < 2.18 and GCC < 4.2"), except we keep the kernel PHDRS
statement as ppc64_defconfig would fail to link without it:
powerpc64-linux-ld: .tmp_vmlinux1: Not enough room for program headers, try linking with -N
powerpc64-linux-ld: final link failed: Bad value
See https://lore.kernel.org/linuxppc-dev/20190321003253.22100-1-joel@jms.id.au/
for the discussion.
Signed-off-by: Joel Stanley <joel@jms.id.au>
---
v2: Fix ppc64_defconfig by keeping kernel PHDRS
Segher, Christophe, I did my best but to summarise your conversation.
Please suggest corrections or additions to the commit message if you
have any.
---
arch/powerpc/kernel/vmlinux.lds.S | 25 +------------------------
1 file changed, 1 insertion(+), 24 deletions(-)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 060a1acd7c6d..9ddc7c0dc672 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -19,21 +19,6 @@ ENTRY(_stext)
PHDRS {
kernel PT_LOAD FLAGS(7); /* RWX */
- notes PT_NOTE FLAGS(0);
- dummy PT_NOTE FLAGS(0);
-
- /* binutils < 2.18 has a bug that makes it misbehave when taking an
- ELF file with all segments at load address 0 as input. This
- happens when running "strip" on vmlinux, because of the AT() magic
- in this linker script. People using GCC >= 4.2 won't run into
- this problem, because the "build-id" support will put some data
- into the "notes" segment (at a non-zero load address).
-
- To work around this, we force some data into both the "dummy"
- segment and the kernel segment, so the dummy segment will get a
- non-zero load address. It's not enough to always create the
- "notes" segment, since if nothing gets assigned to it, its load
- address will be zero. */
}
#ifdef CONFIG_PPC64
@@ -177,15 +162,7 @@ SECTIONS
#endif
EXCEPTION_TABLE(0)
- NOTES :kernel :notes
-
- /* The dummy segment contents for the bug workaround mentioned above
- near PHDRS. */
- .dummy : AT(ADDR(.dummy) - LOAD_OFFSET) {
- LONG(0)
- LONG(0)
- LONG(0)
- } :kernel :dummy
+ NOTES
/*
* Init sections discarded at runtime
--
2.20.1
^ permalink raw reply related
* [PATCH kernel 2/2] powerpc/mm_iommu: Fix potential deadlock
From: Alexey Kardashevskiy @ 2019-03-29 5:46 UTC (permalink / raw)
To: linuxppc-dev
Cc: Alexey Kardashevskiy, Aneesh Kumar K.V, kvm-ppc, David Gibson
In-Reply-To: <20190329054641.48597-1-aik@ozlabs.ru>
Currently mm_iommu_do_alloc() is called in 2 cases:
- VFIO_IOMMU_SPAPR_REGISTER_MEMORY ioctl() for normal memory;
- vfio_pci_nvgpu_regops::mmap() for GPU memory.
One of the differences here is that the mmap() is called with mm::mmap_sem
help and mm_iommu_do_alloc() locks mm::mmap_sem itself (when adjusting
locked_vm and when pinning pages) which can potentially cause a deadlock.
We did not hit this yet because the mmap() path does not adjust
locked_vm and does not pin pages. However with CONFIG_DEBUG_LOCKDEP=y
there is an annoying warning (below, it is slightly confusing).
This makes a few changes to reduce the amount of time spent under a lock.
This holds mem_list_mutex only when looking or changing the mem list.
This means the list is checked twice now for the normal memory case -
before starting pinning and before adding the item to the list.
This changes mm_iommu_do_alloc() to only allocate and add an iommu memory
descriptor (used to deal with both normal and GPU memory in a rather
messy way).
This cleans the code in a way that mm_iommu_new() and mm_iommu_do_alloc()
do not need to test for (dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) which
makes the code simpler.
This moves locked_vm decrementing from under mem_list_mutex for the same
reasons.
This is one of the lockdep warnings:
======================================================
WARNING: possible circular locking dependency detected
5.1.0-rc2-le_nv2_aikATfstn1-p1 #363 Not tainted
------------------------------------------------------
qemu-system-ppc/8038 is trying to acquire lock:
000000002ec6c453 (mem_list_mutex){+.+.}, at: mm_iommu_do_alloc+0x70/0x490
but task is already holding lock:
00000000fd7da97f (&mm->mmap_sem){++++}, at: vm_mmap_pgoff+0xf0/0x160
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&mm->mmap_sem){++++}:
lock_acquire+0xf8/0x260
down_write+0x44/0xa0
mm_iommu_adjust_locked_vm.part.1+0x4c/0x190
mm_iommu_do_alloc+0x310/0x490
tce_iommu_ioctl.part.9+0xb84/0x1150 [vfio_iommu_spapr_tce]
vfio_fops_unl_ioctl+0x94/0x430 [vfio]
do_vfs_ioctl+0xe4/0x930
ksys_ioctl+0xc4/0x110
sys_ioctl+0x28/0x80
system_call+0x5c/0x70
-> #0 (mem_list_mutex){+.+.}:
__lock_acquire+0x1484/0x1900
lock_acquire+0xf8/0x260
__mutex_lock+0x88/0xa70
mm_iommu_do_alloc+0x70/0x490
vfio_pci_nvgpu_mmap+0xc0/0x130 [vfio_pci]
vfio_pci_mmap+0x198/0x2a0 [vfio_pci]
vfio_device_fops_mmap+0x44/0x70 [vfio]
mmap_region+0x5d4/0x770
do_mmap+0x42c/0x650
vm_mmap_pgoff+0x124/0x160
ksys_mmap_pgoff+0xdc/0x2f0
sys_mmap+0x40/0x80
system_call+0x5c/0x70
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&mm->mmap_sem);
lock(mem_list_mutex);
lock(&mm->mmap_sem);
lock(mem_list_mutex);
*** DEADLOCK ***
1 lock held by qemu-system-ppc/8038:
#0: 00000000fd7da97f (&mm->mmap_sem){++++}, at: vm_mmap_pgoff+0xf0/0x160
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
arch/powerpc/mm/mmu_context_iommu.c | 128 ++++++++++++++--------------
1 file changed, 65 insertions(+), 63 deletions(-)
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 6b351c79713b..36a826e23d45 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -96,50 +96,59 @@ static bool mm_iommu_find(struct mm_struct *mm, unsigned long ua,
return false;
}
-static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
- unsigned long entries, unsigned long dev_hpa,
- struct mm_iommu_table_group_mem_t **pmem)
+/* Must be called with &mem_list_mutex held */
+static int mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
+ unsigned long entries, unsigned long dev_hpa,
+ unsigned int mem_pageshift, phys_addr_t *hpas,
+ struct mm_iommu_table_group_mem_t **pmem)
{
struct mm_iommu_table_group_mem_t *mem;
- long i, ret, locked_entries = 0;
+
+ if (mm_iommu_find(mm, ua, entries))
+ return -EINVAL;
+
+ mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+ if (!mem)
+ return -ENOMEM;
+
+ atomic64_set(&mem->mapped, 1);
+ mem->dev_hpa = dev_hpa;
+ mem->used = 1;
+ mem->ua = ua;
+ mem->entries = entries;
+ mem->pageshift = mem_pageshift;
+ mem->hpas = hpas;
+ list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+ *pmem = mem;
+
+ return 0;
+}
+
+long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries,
+ struct mm_iommu_table_group_mem_t **pmem)
+{
+ long i, ret = 0, locked_entries = 0;
unsigned int pageshift, mem_pageshift;
struct page **hpages;
phys_addr_t *hpas;
mutex_lock(&mem_list_mutex);
-
if (mm_iommu_find(mm, ua, entries)) {
- ret = -EINVAL;
- goto unlock_exit;
+ mutex_unlock(&mem_list_mutex);
+ return -EINVAL;
}
+ mutex_unlock(&mem_list_mutex);
- if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
- ret = mm_iommu_adjust_locked_vm(mm, entries, true);
- if (ret)
- goto unlock_exit;
+ ret = mm_iommu_adjust_locked_vm(mm, entries, true);
+ if (ret)
+ return ret;
- locked_entries = entries;
- }
-
- mem = kzalloc(sizeof(*mem), GFP_KERNEL);
- if (!mem) {
- ret = -ENOMEM;
- goto unlock_exit;
- }
-
- if (dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) {
- mem_pageshift = __ffs(dev_hpa | (entries << PAGE_SHIFT));
- hpas = NULL;
- mem->dev_hpa = dev_hpa;
- goto good_exit;
- }
- mem->dev_hpa = MM_IOMMU_TABLE_INVALID_HPA;
+ locked_entries = entries;
hpages = vzalloc(array_size(entries, sizeof(hpages[0])));
if (!hpages) {
- kfree(mem);
ret = -ENOMEM;
- goto unlock_exit;
+ goto cleanup_exit;
}
down_read(&mm->mmap_sem);
@@ -149,11 +158,8 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
/* free the reference taken */
for (i = 0; i < ret; i++)
put_page(hpages[i]);
-
- vfree(hpages);
- kfree(mem);
ret = -EFAULT;
- goto unlock_exit;
+ goto cleanup_exit;
}
/*
@@ -184,40 +190,35 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
}
-good_exit:
- ret = 0;
- atomic64_set(&mem->mapped, 1);
- mem->used = 1;
- mem->ua = ua;
- mem->entries = entries;
- mem->hpas = hpas;
- mem->pageshift = mem_pageshift;
- *pmem = mem;
-
- list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
-
-unlock_exit:
- if (locked_entries && ret)
- mm_iommu_adjust_locked_vm(mm, locked_entries, false);
-
+ mutex_lock(&mem_list_mutex);
+ ret = mm_iommu_do_alloc(mm, ua, entries, MM_IOMMU_TABLE_INVALID_HPA,
+ mem_pageshift, hpas, pmem);
mutex_unlock(&mem_list_mutex);
+ if (ret)
+ goto cleanup_exit;
+ return 0;
+
+cleanup_exit:
+ mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+ vfree(hpages);
+
return ret;
}
-
-long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries,
- struct mm_iommu_table_group_mem_t **pmem)
-{
- return mm_iommu_do_alloc(mm, ua, entries, MM_IOMMU_TABLE_INVALID_HPA,
- pmem);
-}
EXPORT_SYMBOL_GPL(mm_iommu_new);
long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua,
unsigned long entries, unsigned long dev_hpa,
struct mm_iommu_table_group_mem_t **pmem)
{
- return mm_iommu_do_alloc(mm, ua, entries, dev_hpa, pmem);
+ int ret;
+
+ mutex_lock(&mem_list_mutex);
+ ret = mm_iommu_do_alloc(mm, ua, entries, dev_hpa,
+ __ffs(dev_hpa | (entries << PAGE_SHIFT)), NULL, pmem);
+ mutex_unlock(&mem_list_mutex);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_newdev);
@@ -270,10 +271,13 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
{
long ret = 0;
- unsigned long entries, dev_hpa;
+ unsigned long unlock_entries = 0;
mutex_lock(&mem_list_mutex);
+ if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+ unlock_entries = mem->entries;
+
if (mem->used == 0) {
ret = -ENOENT;
goto unlock_exit;
@@ -292,16 +296,14 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
}
/* @mapped became 0 so now mappings are disabled, release the region */
- entries = mem->entries;
- dev_hpa = mem->dev_hpa;
mm_iommu_release(mem);
- if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
- mm_iommu_adjust_locked_vm(mm, entries, false);
-
unlock_exit:
mutex_unlock(&mem_list_mutex);
+ if (!ret)
+ mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+
return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_put);
--
2.17.1
^ permalink raw reply related
* [PATCH kernel 1/2] powerpc/mm_iommu: Prepare for less locking
From: Alexey Kardashevskiy @ 2019-03-29 5:46 UTC (permalink / raw)
To: linuxppc-dev
Cc: Alexey Kardashevskiy, Aneesh Kumar K.V, kvm-ppc, David Gibson
In-Reply-To: <20190329054641.48597-1-aik@ozlabs.ru>
The next patch will reduce amount of time spent under locks.
This adds mm_iommu_find() to see if the region is already registered.
This removes a rather ugly union from the mm_iommu_table_group_mem_t
struct and keeps the hack local in mm_iommu_do_alloc().
This makes pageshift and hpas local and assigns them late as soon this
moves to a helper.
This should cause no behavioral change.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
arch/powerpc/mm/mmu_context_iommu.c | 82 +++++++++++++++--------------
1 file changed, 43 insertions(+), 39 deletions(-)
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e7a9c4f6bfca..6b351c79713b 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -35,18 +35,8 @@ struct mm_iommu_table_group_mem_t {
atomic64_t mapped;
unsigned int pageshift;
u64 ua; /* userspace address */
- u64 entries; /* number of entries in hpas/hpages[] */
- /*
- * in mm_iommu_get we temporarily use this to store
- * struct page address.
- *
- * We need to convert ua to hpa in real mode. Make it
- * simpler by storing physical address.
- */
- union {
- struct page **hpages; /* vmalloc'ed */
- phys_addr_t *hpas;
- };
+ u64 entries; /* number of entries in hpas */
+ phys_addr_t *hpas;
#define MM_IOMMU_TABLE_INVALID_HPA ((uint64_t)-1)
u64 dev_hpa; /* Device memory base address */
};
@@ -91,26 +81,36 @@ bool mm_iommu_preregistered(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
+/* Must be called with &mem_list_mutex held */
+static bool mm_iommu_find(struct mm_struct *mm, unsigned long ua,
+ unsigned long entries)
+{
+ struct mm_iommu_table_group_mem_t *mem;
+
+ list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
+ /* Overlap? */
+ if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
+ (ua < (mem->ua + (mem->entries << PAGE_SHIFT))))
+ return true;
+ }
+ return false;
+}
+
static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
unsigned long entries, unsigned long dev_hpa,
struct mm_iommu_table_group_mem_t **pmem)
{
struct mm_iommu_table_group_mem_t *mem;
long i, ret, locked_entries = 0;
- unsigned int pageshift;
+ unsigned int pageshift, mem_pageshift;
+ struct page **hpages;
+ phys_addr_t *hpas;
mutex_lock(&mem_list_mutex);
- list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
- next) {
- /* Overlap? */
- if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
- (ua < (mem->ua +
- (mem->entries << PAGE_SHIFT)))) {
- ret = -EINVAL;
- goto unlock_exit;
- }
-
+ if (mm_iommu_find(mm, ua, entries)) {
+ ret = -EINVAL;
+ goto unlock_exit;
}
if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
@@ -128,58 +128,60 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
}
if (dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) {
- mem->pageshift = __ffs(dev_hpa | (entries << PAGE_SHIFT));
+ mem_pageshift = __ffs(dev_hpa | (entries << PAGE_SHIFT));
+ hpas = NULL;
mem->dev_hpa = dev_hpa;
goto good_exit;
}
mem->dev_hpa = MM_IOMMU_TABLE_INVALID_HPA;
- /*
- * For a starting point for a maximum page size calculation
- * we use @ua and @entries natural alignment to allow IOMMU pages
- * smaller than huge pages but still bigger than PAGE_SIZE.
- */
- mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
- mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
- if (!mem->hpas) {
+ hpages = vzalloc(array_size(entries, sizeof(hpages[0])));
+ if (!hpages) {
kfree(mem);
ret = -ENOMEM;
goto unlock_exit;
}
down_read(&mm->mmap_sem);
- ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+ ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, hpages, NULL);
up_read(&mm->mmap_sem);
if (ret != entries) {
/* free the reference taken */
for (i = 0; i < ret; i++)
- put_page(mem->hpages[i]);
+ put_page(hpages[i]);
- vfree(mem->hpas);
+ vfree(hpages);
kfree(mem);
ret = -EFAULT;
goto unlock_exit;
}
+ /*
+ * For a starting point for a maximum page size calculation
+ * we use @ua and @entries natural alignment to allow IOMMU pages
+ * smaller than huge pages but still bigger than PAGE_SIZE.
+ */
+ mem_pageshift = __ffs(ua | (entries << PAGE_SHIFT));
+ hpas = (phys_addr_t *) hpages;
pageshift = PAGE_SHIFT;
for (i = 0; i < entries; ++i) {
- struct page *page = mem->hpages[i];
+ struct page *page = hpages[i];
/*
* Allow to use larger than 64k IOMMU pages. Only do that
* if we are backed by hugetlb.
*/
- if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) {
+ if ((mem_pageshift > PAGE_SHIFT) && PageHuge(page)) {
struct page *head = compound_head(page);
pageshift = compound_order(head) + PAGE_SHIFT;
}
- mem->pageshift = min(mem->pageshift, pageshift);
+ mem_pageshift = min(mem_pageshift, pageshift);
/*
* We don't need struct page reference any more, switch
* to physical address.
*/
- mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
+ hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
}
good_exit:
@@ -188,6 +190,8 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
mem->used = 1;
mem->ua = ua;
mem->entries = entries;
+ mem->hpas = hpas;
+ mem->pageshift = mem_pageshift;
*pmem = mem;
list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
--
2.17.1
^ permalink raw reply related
* [PATCH kernel 0/2] powerpc/mm_iommu: Fix potential deadlock
From: Alexey Kardashevskiy @ 2019-03-29 5:46 UTC (permalink / raw)
To: linuxppc-dev
Cc: Alexey Kardashevskiy, Aneesh Kumar K.V, kvm-ppc, David Gibson
I was trying the kernel with DEBUG_LOCKDEP and saw warnings. 1/2 is preparing the fix
to make 2/2 reviewable and 2/2 is the actual fix.
This is based on sha1
a3ac7917b730 Linus Torvalds "Revert "parport: daisy: use new parport device model"".
Please comment. Thanks.
Alexey Kardashevskiy (2):
powerpc/mm_iommu: Prepare for less locking
powerpc/mm_iommu: Fix potential deadlock
arch/powerpc/mm/mmu_context_iommu.c | 186 ++++++++++++++--------------
1 file changed, 96 insertions(+), 90 deletions(-)
--
2.17.1
^ permalink raw reply
* Re: [Qemu-ppc] pseries on qemu-system-ppc64le crashes in doorbell_core_ipi()
From: Suraj Jitindar Singh @ 2019-03-29 5:20 UTC (permalink / raw)
To: Cédric Le Goater, Sebastian Andrzej Siewior, linuxppc-dev,
qemu-ppc
Cc: tglx, Paul Mackerras, Nicholas Piggin, David Gibson
In-Reply-To: <2bbc1490-400d-585e-d74b-924c570b4236@kaod.org>
On Wed, 2019-03-27 at 17:51 +0100, Cédric Le Goater wrote:
> On 3/27/19 5:37 PM, Cédric Le Goater wrote:
> > On 3/27/19 1:36 PM, Sebastian Andrzej Siewior wrote:
> > > With qemu-system-ppc64le -machine pseries -smp 4 I get:
> > >
> > > > # chrt 1 hackbench
> > > > Running in process mode with 10 groups using 40 file
> > > > descriptors each (== 400 tasks)
> > > > Each sender will pass 100 messages of 100 bytes
> > > > Oops: Exception in kernel mode, sig: 4 [#1]
> > > > LE PAGE_SIZE=64K MMU=Hash PREEMPT SMP NR_CPUS=2048 NUMA pSeries
> > > > Modules linked in:
> > > > CPU: 0 PID: 629 Comm: hackbench Not tainted 5.1.0-rc2 #71
> > > > NIP: c000000000046978 LR: c000000000046a38 CTR:
> > > > c0000000000b0150
> > > > REGS: c0000001fffeb8e0 TRAP: 0700 Not tainted (5.1.0-rc2)
> > > > MSR: 8000000000089033 <SF,EE,ME,IR,DR,RI,LE> CR:
> > > > 42000874 XER: 00000000
> > > > CFAR: c000000000046a34 IRQMASK: 1
> > > > GPR00: c0000000000b0170 c0000001fffebb70 c000000000a6ba00
> > > > 0000000028000000
> > >
> > > …
> > > > NIP [c000000000046978] doorbell_core_ipi+0x28/0x30
> > > > LR [c000000000046a38] doorbell_try_core_ipi+0xb8/0xf0
> > > > Call Trace:
> > > > [c0000001fffebb70] [c0000001fffebba0] 0xc0000001fffebba0
> > > > (unreliable)
> > > > [c0000001fffebba0] [c0000000000b0170]
> > > > smp_pseries_cause_ipi+0x20/0x70
> > > > [c0000001fffebbd0] [c00000000004b02c]
> > > > arch_send_call_function_single_ipi+0x8c/0xa0
> > > > [c0000001fffebbf0] [c0000000001de600]
> > > > irq_work_queue_on+0xe0/0x130
> > > > [c0000001fffebc30] [c0000000001340c8]
> > > > rto_push_irq_work_func+0xc8/0x120
> > >
> > > …
> > > > Instruction dump:
> > > > 60000000 60000000 3c4c00a2 384250b0 3d220009 392949c8 81290000
> > > > 3929ffff
> > > > 7d231838 7c0004ac 5463017e 64632800 <7c00191c> 4e800020
> > > > 3c4c00a2 38425080
> > > > ---[ end trace eb842b544538cbdf ]---
> > >
> > > and I was wondering whether this is a qemu bug or the kernel is
> > > using an
> > > opcode it should rather not. If I skip doorbell_try_core_ipi() in
> > > smp_pseries_cause_ipi() then there is no crash. The comment says
> > > "POWER9
> > > should not use this handler" so…
> >
> > I would say Linux is using a msgsndp instruction which is not
> > implemented
> > in QEMU TCG. But why have we started using dbells in Linux ?
Yeah the kernel must have used msgsndp which isn't implemented for TCG
yet. We use doorbells in linux but only for threads which are on the
same core.
And when I try to construct a situation with more than 1 thread per
core (e.g. -smp 4,threads=4), I get "TCG cannot support more than 1
thread/core on a pseries machine".
So I wonder why the guest thinks it can use msgsndp...
>
> ah. It seems arch_local_irq_restore() / replay_interrupt() generated
> some interrupt.
>
> C.
>
^ permalink raw reply
* Re: [PATCH] powerpc/xmon: add read-only mode
From: Andrew Donnellan @ 2019-03-29 4:49 UTC (permalink / raw)
To: cmr, linuxppc-dev
In-Reply-To: <20190329042153.25698-1-cmr@informatik.wtf>
On 29/3/19 3:21 pm, cmr wrote:
> Operations which write to memory should be restricted on secure systems
> and optionally to avoid self-destructive behaviors.
For reference:
- https://github.com/linuxppc/issues/issues/219
- https://github.com/linuxppc/issues/issues/232
Perhaps clarify what is meant here by "secure systems".
Otherwise commit message looks good.
>
> Add a config option, XMON_RO, to control default xmon behavior along
> with kernel cmdline options xmon=ro and xmon=rw for explicit control.
> The default is to enable read-only mode.
>
> The following xmon operations are affected:
> memops:
> disable memmove
> disable memset
> memex:
> no-op'd mwrite
> super_regs:
> no-op'd write_spr
> bpt_cmds:
> disable
> proc_call:
> disable
>
> Signed-off-by: cmr <cmr@informatik.wtf>
You have a git config to fix :)
> ---
> arch/powerpc/Kconfig.debug | 7 +++++++
> arch/powerpc/xmon/xmon.c | 24 ++++++++++++++++++++++++
> 2 files changed, 31 insertions(+)
>
> diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
> index 4e00cb0a5464..33cc01adf4cb 100644
> --- a/arch/powerpc/Kconfig.debug
> +++ b/arch/powerpc/Kconfig.debug
> @@ -117,6 +117,13 @@ config XMON_DISASSEMBLY
> to say Y here, unless you're building for a memory-constrained
> system.
>
> +config XMON_RO
> + bool "Set xmon read-only mode"
> + depends on XMON
> + default y
> + help
> + Disable state- and memory-altering write operations in xmon.
The meaning of this option is a bit unclear.
From the code - it looks like what this option actually does is enable
RO mode *by default*. In which case it should probably be called
XMON_RO_DEFAULT and the description should note that RW mode can still
be enabled via a cmdline option.
> +
> config DEBUGGER
> bool
> depends on KGDB || XMON
> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> index a0f44f992360..c13ee73cdfd4 100644
> --- a/arch/powerpc/xmon/xmon.c
> +++ b/arch/powerpc/xmon/xmon.c
> @@ -80,6 +80,7 @@ static int set_indicator_token = RTAS_UNKNOWN_SERVICE;
> #endif
> static unsigned long in_xmon __read_mostly = 0;
> static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT);
> +static int xmon_ro = IS_ENABLED(CONFIG_XMON_RO);
>
> static unsigned long adrs;
> static int size = 1;
> @@ -1042,6 +1043,8 @@ cmds(struct pt_regs *excp)
> set_lpp_cmd();
> break;
> case 'b':
> + if (xmon_ro == 1)
> + break;
For all these cases - it would be much better to print an error message
somewhere when we abort due to read-only mode.
> bpt_cmds();
> break;
> case 'C':
> @@ -1055,6 +1058,8 @@ cmds(struct pt_regs *excp)
> bootcmds();
> break;
> case 'p':
> + if (xmon_ro == 1)
> + break;
> proccall();
> break;
> case 'P':
> @@ -1777,6 +1782,9 @@ read_spr(int n, unsigned long *vp)
> static void
> write_spr(int n, unsigned long val)
> {
> + if (xmon_ro == 1)
> + return;
> +
> if (setjmp(bus_error_jmp) == 0) {
> catch_spr_faults = 1;
> sync();
> @@ -2016,6 +2024,10 @@ mwrite(unsigned long adrs, void *buf, int size)
> char *p, *q;
>
> n = 0;
> +
> + if (xmon_ro == 1)
> + return n;
> +
> if (setjmp(bus_error_jmp) == 0) {
> catch_memory_errors = 1;
> sync();
> @@ -2884,9 +2896,13 @@ memops(int cmd)
> scanhex((void *)&mcount);
> switch( cmd ){
> case 'm':
> + if (xmon_ro == 1)
> + break;
> memmove((void *)mdest, (void *)msrc, mcount);
> break;
> case 's':
> + if (xmon_ro == 1)
> + break;
> memset((void *)mdest, mval, mcount);
> break;
> case 'd':
> @@ -3796,6 +3812,14 @@ static int __init early_parse_xmon(char *p)
> } else if (strncmp(p, "on", 2) == 0) {
> xmon_init(1);
> xmon_on = 1;
> + } else if (strncmp(p, "rw", 2) == 0) {
> + xmon_init(1);
> + xmon_on = 1;
> + xmon_ro = 0;
> + } else if (strncmp(p, "ro", 2) == 0) {
> + xmon_init(1);
> + xmon_on = 1;
> + xmon_ro = 1;
> } else if (strncmp(p, "off", 3) == 0)
> xmon_on = 0;
> else
>
--
Andrew Donnellan OzLabs, ADL Canberra
andrew.donnellan@au1.ibm.com IBM Australia Limited
^ permalink raw reply
* [PATCH] powerpc/xmon: add read-only mode
From: cmr @ 2019-03-29 4:21 UTC (permalink / raw)
To: linuxppc-dev; +Cc: cmr, andonnel
Operations which write to memory should be restricted on secure systems
and optionally to avoid self-destructive behaviors.
Add a config option, XMON_RO, to control default xmon behavior along
with kernel cmdline options xmon=ro and xmon=rw for explicit control.
The default is to enable read-only mode.
The following xmon operations are affected:
memops:
disable memmove
disable memset
memex:
no-op'd mwrite
super_regs:
no-op'd write_spr
bpt_cmds:
disable
proc_call:
disable
Signed-off-by: cmr <cmr@informatik.wtf>
---
arch/powerpc/Kconfig.debug | 7 +++++++
arch/powerpc/xmon/xmon.c | 24 ++++++++++++++++++++++++
2 files changed, 31 insertions(+)
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 4e00cb0a5464..33cc01adf4cb 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -117,6 +117,13 @@ config XMON_DISASSEMBLY
to say Y here, unless you're building for a memory-constrained
system.
+config XMON_RO
+ bool "Set xmon read-only mode"
+ depends on XMON
+ default y
+ help
+ Disable state- and memory-altering write operations in xmon.
+
config DEBUGGER
bool
depends on KGDB || XMON
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a0f44f992360..c13ee73cdfd4 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -80,6 +80,7 @@ static int set_indicator_token = RTAS_UNKNOWN_SERVICE;
#endif
static unsigned long in_xmon __read_mostly = 0;
static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT);
+static int xmon_ro = IS_ENABLED(CONFIG_XMON_RO);
static unsigned long adrs;
static int size = 1;
@@ -1042,6 +1043,8 @@ cmds(struct pt_regs *excp)
set_lpp_cmd();
break;
case 'b':
+ if (xmon_ro == 1)
+ break;
bpt_cmds();
break;
case 'C':
@@ -1055,6 +1058,8 @@ cmds(struct pt_regs *excp)
bootcmds();
break;
case 'p':
+ if (xmon_ro == 1)
+ break;
proccall();
break;
case 'P':
@@ -1777,6 +1782,9 @@ read_spr(int n, unsigned long *vp)
static void
write_spr(int n, unsigned long val)
{
+ if (xmon_ro == 1)
+ return;
+
if (setjmp(bus_error_jmp) == 0) {
catch_spr_faults = 1;
sync();
@@ -2016,6 +2024,10 @@ mwrite(unsigned long adrs, void *buf, int size)
char *p, *q;
n = 0;
+
+ if (xmon_ro == 1)
+ return n;
+
if (setjmp(bus_error_jmp) == 0) {
catch_memory_errors = 1;
sync();
@@ -2884,9 +2896,13 @@ memops(int cmd)
scanhex((void *)&mcount);
switch( cmd ){
case 'm':
+ if (xmon_ro == 1)
+ break;
memmove((void *)mdest, (void *)msrc, mcount);
break;
case 's':
+ if (xmon_ro == 1)
+ break;
memset((void *)mdest, mval, mcount);
break;
case 'd':
@@ -3796,6 +3812,14 @@ static int __init early_parse_xmon(char *p)
} else if (strncmp(p, "on", 2) == 0) {
xmon_init(1);
xmon_on = 1;
+ } else if (strncmp(p, "rw", 2) == 0) {
+ xmon_init(1);
+ xmon_on = 1;
+ xmon_ro = 0;
+ } else if (strncmp(p, "ro", 2) == 0) {
+ xmon_init(1);
+ xmon_on = 1;
+ xmon_ro = 1;
} else if (strncmp(p, "off", 3) == 0)
xmon_on = 0;
else
--
2.21.0
^ permalink raw reply related
* [RFC][PATCH 4/4 v2] syscalls: Remove start and number from syscall_set_arguments() args
From: Steven Rostedt @ 2019-03-28 23:05 UTC (permalink / raw)
To: linux-kernel
Cc: linux-ia64, Gustavo A. R. Silva, Peter Zijlstra,
Dominik Brodowski, Dmitry V. Levin, H. Peter Anvin, sparclinux,
linux-riscv, Ingo Molnar, linux-arch, linux-s390, linux-c6x-dev,
linux-sh, linux-hexagon, x86, linux-snps-arc, Dave Martin,
uclinux-h8-devel, linux-xtensa, Kees Cook, Roland McGrath,
linux-um, linux-mips, openrisc, Borislav Petkov, Andy Lutomirski,
Thomas Gleixner, linux-arm-kernel, linux-parisc, linuxppc-dev,
Oleg Nesterov, Andy Lutomirski, Eric W. Biederman, nios2-dev,
Andrew Morton, Linus Torvalds
In-Reply-To: <20190328230512.486297455@goodmis.org>
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
After removing the start and count arguments of syscall_get_arguments() it
seems reasonable to remove them from syscall_set_arguments(). Note, as of
today, there are no users of syscall_set_arguments(). But we are told that
there will be soon. But for now, at least make it consistent with
syscall_get_arguments().
Link: http://lkml.kernel.org/r/20190327222014.GA32540@altlinux.org
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Dave Martin <dave.martin@arm.com>
Cc: "Dmitry V. Levin" <ldv@altlinux.org>
Cc: x86@kernel.org
Cc: linux-snps-arc@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-c6x-dev@linux-c6x.org
Cc: uclinux-h8-devel@lists.sourceforge.jp
Cc: linux-hexagon@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-mips@vger.kernel.org
Cc: nios2-dev@lists.rocketboards.org
Cc: openrisc@lists.librecores.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-riscv@lists.infradead.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-um@lists.infradead.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linux-arch@vger.kernel.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
arch/arm/include/asm/syscall.h | 22 ++-------
arch/arm64/include/asm/syscall.h | 22 ++-------
arch/c6x/include/asm/syscall.h | 38 +++------------
arch/csky/include/asm/syscall.h | 13 ++---
arch/ia64/include/asm/syscall.h | 10 ++--
arch/ia64/kernel/ptrace.c | 7 ++-
arch/microblaze/include/asm/syscall.h | 4 +-
arch/nds32/include/asm/syscall.h | 29 ++---------
arch/nios2/include/asm/syscall.h | 42 +++-------------
arch/openrisc/include/asm/syscall.h | 6 +--
arch/powerpc/include/asm/syscall.h | 7 +--
arch/riscv/include/asm/syscall.h | 12 ++---
arch/s390/include/asm/syscall.h | 11 ++---
arch/sh/include/asm/syscall_32.h | 21 +++-----
arch/sh/include/asm/syscall_64.h | 4 +-
arch/sparc/include/asm/syscall.h | 7 ++-
arch/um/include/asm/syscall-generic.h | 39 +++------------
arch/x86/include/asm/syscall.h | 69 +++++++--------------------
arch/xtensa/include/asm/syscall.h | 17 ++-----
include/asm-generic/syscall.h | 10 +---
20 files changed, 88 insertions(+), 302 deletions(-)
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index db969a2972ae..080ce70cab12 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -65,26 +65,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->ARM_ORIG_r0 = args[0];
- args++;
- i++;
- n--;
- }
-
- memcpy(®s->ARM_r0 + i, args, n * sizeof(args[0]));
+ regs->ARM_ORIG_r0 = args[0];
+ args++;
+
+ memcpy(®s->ARM_r0 + 1, args, 5 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 55b2dab21023..a179df3674a1 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -75,26 +75,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->orig_x0 = args[0];
- args++;
- i++;
- n--;
- }
-
- memcpy(®s->regs[i], args, n * sizeof(args[0]));
+ regs->orig_x0 = args[0];
+ args++;
+
+ memcpy(®s->regs[1], args, 5 * sizeof(args[0]));
}
/*
diff --git a/arch/c6x/include/asm/syscall.h b/arch/c6x/include/asm/syscall.h
index 06db3251926b..15ba8599858e 100644
--- a/arch/c6x/include/asm/syscall.h
+++ b/arch/c6x/include/asm/syscall.h
@@ -59,40 +59,14 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- switch (i) {
- case 0:
- if (!n--)
- break;
- regs->a4 = *args++;
- case 1:
- if (!n--)
- break;
- regs->b4 = *args++;
- case 2:
- if (!n--)
- break;
- regs->a6 = *args++;
- case 3:
- if (!n--)
- break;
- regs->b6 = *args++;
- case 4:
- if (!n--)
- break;
- regs->a8 = *args++;
- case 5:
- if (!n--)
- break;
- regs->a9 = *args++;
- case 6:
- if (!n)
- break;
- default:
- BUG();
- }
+ regs->a4 = *args++;
+ regs->b4 = *args++;
+ regs->a6 = *args++;
+ regs->b6 = *args++;
+ regs->a8 = *args++;
+ regs->a9 = *args;
}
#endif /* __ASM_C6X_SYSCALLS_H */
diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h
index 5cc0b8283a69..34c02d6bb973 100644
--- a/arch/csky/include/asm/syscall.h
+++ b/arch/csky/include/asm/syscall.h
@@ -52,16 +52,11 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
static inline void
syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, const unsigned long *args)
+ const unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- regs->orig_a0 = args[0];
- args++;
- i++;
- n--;
- }
- memcpy(®s->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+ regs->orig_a0 = args[0];
+ args++;
+ memcpy(®s->a1 + sizeof(regs->a1), args, 5 * sizeof(regs->a0));
}
static inline int
diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index 8204c1ff70ce..0d9e7fab4a79 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -59,23 +59,19 @@ static inline void syscall_set_return_value(struct task_struct *task,
}
extern void ia64_syscall_get_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args, int rw);
+ struct pt_regs *regs, unsigned long *args, int rw);
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned long *args)
{
- ia64_syscall_get_set_arguments(task, regs, 0, 6, args, 0);
+ ia64_syscall_get_set_arguments(task, regs, args, 0);
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- ia64_syscall_get_set_arguments(task, regs, i, n, args, 1);
+ ia64_syscall_get_set_arguments(task, regs, args, 1);
}
static inline int syscall_get_arch(void)
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 6d50ede0ed69..bf9c24d9ce84 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -2179,12 +2179,11 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
}
void ia64_syscall_get_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args, int rw)
+ struct pt_regs *regs, unsigned long *args, int rw)
{
struct syscall_get_set_args data = {
- .i = i,
- .n = n,
+ .i = 0,
+ .n = 6,
.args = args,
.regs = regs,
.rw = rw,
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 4b23e44e5c3c..833d3a53dab3 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -93,9 +93,11 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
+
while (n--)
microblaze_set_syscall_arg(regs, i++, *args++);
}
diff --git a/arch/nds32/include/asm/syscall.h b/arch/nds32/include/asm/syscall.h
index 89a6ec8731d8..671ebd357496 100644
--- a/arch/nds32/include/asm/syscall.h
+++ b/arch/nds32/include/asm/syscall.h
@@ -129,39 +129,20 @@ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
* syscall_set_arguments - change system call parameter value
* @task: task of interest, must be in system call entry tracing
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array of argument values to store
*
- * Changes @n arguments to the system call starting with the @i'th argument.
- * Argument @i gets value @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Changes 6 arguments to the system call. The first argument gets value
+ * @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- regs->orig_r0 = args[0];
- args++;
- i++;
- n--;
- }
+ regs->orig_r0 = args[0];
+ args++;
- memcpy(®s->uregs[0] + i, args, n * sizeof(args[0]));
+ memcpy(®s->uregs[0] + 1, args, 5 * sizeof(args[0]));
}
#endif /* _ASM_NDS32_SYSCALL_H */
diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h
index 792bd449d839..d7624ed06efb 100644
--- a/arch/nios2/include/asm/syscall.h
+++ b/arch/nios2/include/asm/syscall.h
@@ -69,42 +69,14 @@ static inline void syscall_get_arguments(struct task_struct *task,
}
static inline void syscall_set_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- const unsigned long *args)
+ struct pt_regs *regs, const unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- switch (i) {
- case 0:
- if (!n--)
- break;
- regs->r4 = *args++;
- case 1:
- if (!n--)
- break;
- regs->r5 = *args++;
- case 2:
- if (!n--)
- break;
- regs->r6 = *args++;
- case 3:
- if (!n--)
- break;
- regs->r7 = *args++;
- case 4:
- if (!n--)
- break;
- regs->r8 = *args++;
- case 5:
- if (!n--)
- break;
- regs->r9 = *args++;
- case 6:
- if (!n)
- break;
- default:
- BUG();
- }
+ regs->r4 = *args++;
+ regs->r5 = *args++;
+ regs->r6 = *args++;
+ regs->r7 = *args++;
+ regs->r8 = *args++;
+ regs->r9 = *args;
}
#endif
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index 72607860cd55..b4ff07c1baed 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -63,11 +63,9 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
static inline void
syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, const unsigned long *args)
+ const unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- memcpy(®s->gpr[3 + i], args, n * sizeof(args[0]));
+ memcpy(®s->gpr[3], args, 6 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 5c9b9dc82b7e..1243045bad2d 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -86,15 +86,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(®s->gpr[3 + i], args, n * sizeof(args[0]));
+ memcpy(®s->gpr[3], args, 6 * sizeof(args[0]));
/* Also copy the first argument into orig_gpr3 */
- if (i == 0 && n > 0)
- regs->orig_gpr3 = args[0];
+ regs->orig_gpr3 = args[0];
}
static inline int syscall_get_arch(void)
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 85a31dd0f2ba..7321644be1cf 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -81,17 +81,11 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- regs->orig_a0 = args[0];
- args++;
- i++;
- n--;
- }
- memcpy(®s->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+ regs->orig_a0 = args[0];
+ args++;
+ memcpy(®s->a1 + sizeof(regs->a1), args, 5 * sizeof(regs->a0));
}
static inline int syscall_get_arch(void)
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index ee0b1f6aa36d..59c3e91f2cdb 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -74,15 +74,14 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
+ unsigned int n = 6;
+
while (n-- > 0)
- if (i + n > 0)
- regs->gprs[2 + i + n] = args[n];
- if (i == 0)
- regs->orig_gpr2 = args[0];
+ if (n > 0)
+ regs->gprs[2 + n] = args[n];
+ regs->orig_gpr2 = args[0];
}
static inline int syscall_get_arch(void)
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 2bf1199a0595..8c9d7e5e5dcc 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -62,23 +62,14 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- /* Same note as above applies */
- BUG_ON(i);
-
- switch (n) {
- case 6: regs->regs[1] = args[5];
- case 5: regs->regs[0] = args[4];
- case 4: regs->regs[7] = args[3];
- case 3: regs->regs[6] = args[2];
- case 2: regs->regs[5] = args[1];
- case 1: regs->regs[4] = args[0];
- break;
- default:
- BUG();
- }
+ regs->regs[1] = args[5];
+ regs->regs[0] = args[4];
+ regs->regs[7] = args[3];
+ regs->regs[6] = args[2];
+ regs->regs[5] = args[1];
+ regs->regs[4] = args[0];
}
static inline int syscall_get_arch(void)
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index 4e8f6460c703..22fad97da066 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -54,11 +54,9 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(®s->regs[2 + i], args, n * sizeof(args[0]));
+ memcpy(®s->regs[2], args, 6 * sizeof(args[0]));
}
static inline int syscall_get_arch(void)
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 872dfee852d6..4d075434e816 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -119,13 +119,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
- unsigned int j;
+ unsigned int i;
- for (j = 0; j < n; j++)
- regs->u_regs[UREG_I0 + i + j] = args[j];
+ for (i = 0; i < 6; i++)
+ regs->u_regs[UREG_I0 + i] = args[i];
}
static inline int syscall_get_arch(void)
diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h
index 25d00acd1322..98e50c50c12e 100644
--- a/arch/um/include/asm/syscall-generic.h
+++ b/arch/um/include/asm/syscall-generic.h
@@ -67,43 +67,16 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
struct uml_pt_regs *r = ®s->regs;
- switch (i) {
- case 0:
- if (!n--)
- break;
- UPT_SYSCALL_ARG1(r) = *args++;
- case 1:
- if (!n--)
- break;
- UPT_SYSCALL_ARG2(r) = *args++;
- case 2:
- if (!n--)
- break;
- UPT_SYSCALL_ARG3(r) = *args++;
- case 3:
- if (!n--)
- break;
- UPT_SYSCALL_ARG4(r) = *args++;
- case 4:
- if (!n--)
- break;
- UPT_SYSCALL_ARG5(r) = *args++;
- case 5:
- if (!n--)
- break;
- UPT_SYSCALL_ARG6(r) = *args++;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- break;
- }
+ UPT_SYSCALL_ARG1(r) = *args++;
+ UPT_SYSCALL_ARG2(r) = *args++;
+ UPT_SYSCALL_ARG3(r) = *args++;
+ UPT_SYSCALL_ARG4(r) = *args++;
+ UPT_SYSCALL_ARG5(r) = *args++;
+ UPT_SYSCALL_ARG6(r) = *args;
}
/* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 8dbb5c379450..4c305471ec33 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -138,63 +138,26 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task->thread_info.status & TS_COMPAT)
- switch (i) {
- case 0:
- if (!n--) break;
- regs->bx = *args++;
- case 1:
- if (!n--) break;
- regs->cx = *args++;
- case 2:
- if (!n--) break;
- regs->dx = *args++;
- case 3:
- if (!n--) break;
- regs->si = *args++;
- case 4:
- if (!n--) break;
- regs->di = *args++;
- case 5:
- if (!n--) break;
- regs->bp = *args++;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
- else
+ if (task->thread_info.status & TS_COMPAT) {
+ regs->bx = *args++;
+ regs->cx = *args++;
+ regs->dx = *args++;
+ regs->si = *args++;
+ regs->di = *args++;
+ regs->bp = *args;
+ } else
# endif
- switch (i) {
- case 0:
- if (!n--) break;
- regs->di = *args++;
- case 1:
- if (!n--) break;
- regs->si = *args++;
- case 2:
- if (!n--) break;
- regs->dx = *args++;
- case 3:
- if (!n--) break;
- regs->r10 = *args++;
- case 4:
- if (!n--) break;
- regs->r8 = *args++;
- case 5:
- if (!n--) break;
- regs->r9 = *args++;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
+ {
+ regs->di = *args++;
+ regs->si = *args++;
+ regs->dx = *args++;
+ regs->r10 = *args++;
+ regs->r8 = *args++;
+ regs->r9 = *args;
+ }
}
static inline int syscall_get_arch(void)
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index 1504ce9a233a..91dc06d58060 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -70,24 +70,13 @@ static inline void syscall_get_arguments(struct task_struct *task,
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args)
{
static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
- unsigned int j;
-
- if (n == 0)
- return;
-
- if (WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS)) {
- if (i < SYSCALL_MAX_ARGS)
- n = SYSCALL_MAX_ARGS - i;
- else
- return;
- }
+ unsigned int i;
- for (j = 0; j < n; ++j)
- regs->areg[reg[i + j]] = args[j];
+ for (i = 0; i < 6; ++i)
+ regs->areg[reg[i]] = args[i];
}
asmlinkage long xtensa_rt_sigreturn(struct pt_regs*);
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 269e9412ef42..b88239e9efe4 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -120,21 +120,15 @@ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
* syscall_set_arguments - change system call parameter value
* @task: task of interest, must be in system call entry tracing
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array of argument values to store
*
- * Changes @n arguments to the system call starting with the @i'th argument.
- * Argument @i gets value @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Changes 6 arguments to the system call.
+ * The first argument gets value @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n,
const unsigned long *args);
/**
--
2.20.1
^ permalink raw reply related
* [RFC][PATCH 3/4 v2] syscalls: Remove start and number from syscall_get_arguments() args
From: Steven Rostedt @ 2019-03-28 23:05 UTC (permalink / raw)
To: linux-kernel
Cc: linux-ia64, Gustavo A. R. Silva, Peter Zijlstra,
Dominik Brodowski, Dmitry V. Levin, H. Peter Anvin, sparclinux,
linux-riscv, Ingo Molnar, linux-arch, linux-s390, linux-c6x-dev,
linux-sh, linux-hexagon, x86, linux-snps-arc, Dave Martin,
uclinux-h8-devel, linux-xtensa, Kees Cook, Roland McGrath,
linux-um, linux-mips, openrisc, Borislav Petkov, Andy Lutomirski,
Thomas Gleixner, linux-arm-kernel, linux-parisc, linuxppc-dev,
Oleg Nesterov, Andy Lutomirski, Eric W. Biederman, nios2-dev,
Andrew Morton, Linus Torvalds
In-Reply-To: <20190328230512.486297455@goodmis.org>
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
At Linux Plumbers, Andy Lutomirski approached me and pointed out that the
function call syscall_get_arguments() implemented in x86 was horribly
written and not optimized for the standard case of passing in 0 and 6 for
the starting index and the number of system calls to get. When looking at
all the users of this function, I discovered that all instances pass in only
0 and 6 for these arguments. Instead of having this function handle
different cases that are never used, simply rewrite it to return the first 6
arguments of a system call.
This should help out the performance of tracing system calls by ptrace,
ftrace and perf.
Link: http://lkml.kernel.org/r/20161107213233.754809394@goodmis.org
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Dave Martin <dave.martin@arm.com>
Cc: "Dmitry V. Levin" <ldv@altlinux.org>
Cc: x86@kernel.org
Cc: linux-snps-arc@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-c6x-dev@linux-c6x.org
Cc: uclinux-h8-devel@lists.sourceforge.jp
Cc: linux-hexagon@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-mips@vger.kernel.org
Cc: nios2-dev@lists.rocketboards.org
Cc: openrisc@lists.librecores.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-riscv@lists.infradead.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-um@lists.infradead.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linux-arch@vger.kernel.org
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
arch/arc/include/asm/syscall.h | 7 ++-
arch/arm/include/asm/syscall.h | 23 ++-------
arch/arm64/include/asm/syscall.h | 22 ++------
arch/c6x/include/asm/syscall.h | 41 +++------------
arch/csky/include/asm/syscall.h | 13 ++---
arch/h8300/include/asm/syscall.h | 34 +++----------
arch/hexagon/include/asm/syscall.h | 4 +-
arch/ia64/include/asm/syscall.h | 5 +-
arch/microblaze/include/asm/syscall.h | 4 +-
arch/mips/include/asm/syscall.h | 3 +-
arch/mips/kernel/ptrace.c | 2 +-
arch/nds32/include/asm/syscall.h | 33 +++---------
arch/nios2/include/asm/syscall.h | 42 +++------------
arch/openrisc/include/asm/syscall.h | 6 +--
arch/parisc/include/asm/syscall.h | 30 +++--------
arch/powerpc/include/asm/syscall.h | 8 ++-
arch/riscv/include/asm/syscall.h | 12 ++---
arch/s390/include/asm/syscall.h | 17 ++-----
arch/sh/include/asm/syscall_32.h | 26 +++-------
arch/sh/include/asm/syscall_64.h | 4 +-
arch/sparc/include/asm/syscall.h | 4 +-
arch/um/include/asm/syscall-generic.h | 39 +++-----------
arch/x86/include/asm/syscall.h | 73 +++++++--------------------
arch/xtensa/include/asm/syscall.h | 16 ++----
include/asm-generic/syscall.h | 11 ++--
include/trace/events/syscalls.h | 2 +-
kernel/seccomp.c | 2 +-
kernel/trace/trace_syscalls.c | 4 +-
lib/syscall.c | 2 +-
29 files changed, 113 insertions(+), 376 deletions(-)
diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h
index 29de09804306..c7a4201ed62b 100644
--- a/arch/arc/include/asm/syscall.h
+++ b/arch/arc/include/asm/syscall.h
@@ -55,12 +55,11 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
*/
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
unsigned long *inside_ptregs = &(regs->r0);
- inside_ptregs -= i;
-
- BUG_ON((i + n) > 6);
+ unsigned int n = 6;
+ unsigned int i = 0;
while (n--) {
args[i++] = (*inside_ptregs);
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index 06dea6bce293..db969a2972ae 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -55,29 +55,12 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warn("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- n = SYSCALL_MAX_ARGS - i;
- }
-
- if (i == 0) {
- args[0] = regs->ARM_ORIG_r0;
- args++;
- i++;
- n--;
- }
+ args[0] = regs->ARM_ORIG_r0;
+ args++;
- memcpy(args, ®s->ARM_r0 + i, n * sizeof(args[0]));
+ memcpy(args, ®s->ARM_r0 + 1, 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index ad8be16a39c9..55b2dab21023 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -65,28 +65,12 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- if (n == 0)
- return;
-
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- }
-
- if (i == 0) {
- args[0] = regs->orig_x0;
- args++;
- i++;
- n--;
- }
+ args[0] = regs->orig_x0;
+ args++;
- memcpy(args, ®s->regs[i], n * sizeof(args[0]));
+ memcpy(args, ®s->regs[1], 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/c6x/include/asm/syscall.h b/arch/c6x/include/asm/syscall.h
index ae2be315ee9c..06db3251926b 100644
--- a/arch/c6x/include/asm/syscall.h
+++ b/arch/c6x/include/asm/syscall.h
@@ -46,40 +46,15 @@ static inline void syscall_set_return_value(struct task_struct *task,
}
static inline void syscall_get_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i,
- unsigned int n, unsigned long *args)
+ struct pt_regs *regs,
+ unsigned long *args)
{
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = regs->a4;
- case 1:
- if (!n--)
- break;
- *args++ = regs->b4;
- case 2:
- if (!n--)
- break;
- *args++ = regs->a6;
- case 3:
- if (!n--)
- break;
- *args++ = regs->b6;
- case 4:
- if (!n--)
- break;
- *args++ = regs->a8;
- case 5:
- if (!n--)
- break;
- *args++ = regs->b8;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- }
+ *args++ = regs->a4;
+ *args++ = regs->b4;
+ *args++ = regs->a6;
+ *args++ = regs->b6;
+ *args++ = regs->a8;
+ *args = regs->b8;
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h
index d637445737b7..5cc0b8283a69 100644
--- a/arch/csky/include/asm/syscall.h
+++ b/arch/csky/include/asm/syscall.h
@@ -43,16 +43,11 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- args[0] = regs->orig_a0;
- args++;
- i++;
- n--;
- }
- memcpy(args, ®s->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+ args[0] = regs->orig_a0;
+ args++;
+ memcpy(args, ®s->a1 + sizeof(regs->a1), 5 * sizeof(args[0]));
}
static inline void
diff --git a/arch/h8300/include/asm/syscall.h b/arch/h8300/include/asm/syscall.h
index 924990401237..ddd483c6ca95 100644
--- a/arch/h8300/include/asm/syscall.h
+++ b/arch/h8300/include/asm/syscall.h
@@ -17,34 +17,14 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- while (n > 0) {
- switch (i) {
- case 0:
- *args++ = regs->er1;
- break;
- case 1:
- *args++ = regs->er2;
- break;
- case 2:
- *args++ = regs->er3;
- break;
- case 3:
- *args++ = regs->er4;
- break;
- case 4:
- *args++ = regs->er5;
- break;
- case 5:
- *args++ = regs->er6;
- break;
- }
- i++;
- n--;
- }
+ *args++ = regs->er1;
+ *args++ = regs->er2;
+ *args++ = regs->er3;
+ *args++ = regs->er4;
+ *args++ = regs->er5;
+ *args = regs->er6;
}
diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h
index 4af9c7b6f13a..ae3a1e24fabd 100644
--- a/arch/hexagon/include/asm/syscall.h
+++ b/arch/hexagon/include/asm/syscall.h
@@ -37,10 +37,8 @@ static inline long syscall_get_nr(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, &(®s->r00)[i], n * sizeof(args[0]));
+ memcpy(args, &(®s->r00)[0], 6 * sizeof(args[0]));
}
#endif
diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index 1d0b875fec44..8204c1ff70ce 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -63,12 +63,9 @@ extern void ia64_syscall_get_set_arguments(struct task_struct *task,
unsigned long *args, int rw);
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- ia64_syscall_get_set_arguments(task, regs, i, n, args, 0);
+ ia64_syscall_get_set_arguments(task, regs, 0, 6, args, 0);
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 220decd605a4..4b23e44e5c3c 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -82,9 +82,11 @@ static inline void microblaze_set_syscall_arg(struct pt_regs *regs,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
+
while (n--)
*args++ = microblaze_get_syscall_arg(regs, i++);
}
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6cf8ffb5367e..a2b4748655df 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -116,9 +116,10 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
+ unsigned int i = 0;
+ unsigned int n = 6;
int ret;
/* O32 ABI syscall() */
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 0057c910bc2f..3a62f80958e1 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1419,7 +1419,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
sd.nr = syscall;
sd.arch = syscall_get_arch();
- syscall_get_arguments(current, regs, 0, 6, args);
+ syscall_get_arguments(current, regs, args);
for (i = 0; i < 6; i++)
sd.args[i] = args[i];
sd.instruction_pointer = KSTK_EIP(current);
diff --git a/arch/nds32/include/asm/syscall.h b/arch/nds32/include/asm/syscall.h
index f7e5e86765fe..89a6ec8731d8 100644
--- a/arch/nds32/include/asm/syscall.h
+++ b/arch/nds32/include/asm/syscall.h
@@ -108,42 +108,21 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
* syscall_get_arguments - extract system call parameter values
* @task: task of interest, must be blocked
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array filled with argument values
*
- * Fetches @n arguments to the system call starting with the @i'th argument
- * (from 0 through 5). Argument @i is stored in @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Fetches 6 arguments to the system call (from 0 through 5). The first
+ * argument is stored in @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
#define SYSCALL_MAX_ARGS 6
void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- if (n == 0)
- return;
- if (i + n > SYSCALL_MAX_ARGS) {
- unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
- unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
- pr_warning("%s called with max args %d, handling only %d\n",
- __func__, i + n, SYSCALL_MAX_ARGS);
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- memset(args_bad, 0, n_bad * sizeof(args[0]));
- }
-
- if (i == 0) {
- args[0] = regs->orig_r0;
- args++;
- i++;
- n--;
- }
-
- memcpy(args, ®s->uregs[0] + i, n * sizeof(args[0]));
+ args[0] = regs->orig_r0;
+ args++;
+ memcpy(args, ®s->uregs[0] + 1, 5 * sizeof(args[0]));
}
/**
diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h
index 9de220854c4a..792bd449d839 100644
--- a/arch/nios2/include/asm/syscall.h
+++ b/arch/nios2/include/asm/syscall.h
@@ -58,42 +58,14 @@ static inline void syscall_set_return_value(struct task_struct *task,
}
static inline void syscall_get_arguments(struct task_struct *task,
- struct pt_regs *regs, unsigned int i, unsigned int n,
- unsigned long *args)
+ struct pt_regs *regs, unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = regs->r4;
- case 1:
- if (!n--)
- break;
- *args++ = regs->r5;
- case 2:
- if (!n--)
- break;
- *args++ = regs->r6;
- case 3:
- if (!n--)
- break;
- *args++ = regs->r7;
- case 4:
- if (!n--)
- break;
- *args++ = regs->r8;
- case 5:
- if (!n--)
- break;
- *args++ = regs->r9;
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- }
+ *args++ = regs->r4;
+ *args++ = regs->r5;
+ *args++ = regs->r6;
+ *args++ = regs->r7;
+ *args++ = regs->r8;
+ *args = regs->r9;
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index 2db9f1cf0694..72607860cd55 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -56,11 +56,9 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
static inline void
syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args)
+ unsigned long *args)
{
- BUG_ON(i + n > 6);
-
- memcpy(args, ®s->gpr[3 + i], n * sizeof(args[0]));
+ memcpy(args, ®s->gpr[3], 6 * sizeof(args[0]));
}
static inline void
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 8bff1a58c97f..62a6d477fae0 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -18,29 +18,15 @@ static inline long syscall_get_nr(struct task_struct *tsk,
}
static inline void syscall_get_arguments(struct task_struct *tsk,
- struct pt_regs *regs, unsigned int i,
- unsigned int n, unsigned long *args)
+ struct pt_regs *regs,
+ unsigned long *args)
{
- BUG_ON(i);
-
- switch (n) {
- case 6:
- args[5] = regs->gr[21];
- case 5:
- args[4] = regs->gr[22];
- case 4:
- args[3] = regs->gr[23];
- case 3:
- args[2] = regs->gr[24];
- case 2:
- args[1] = regs->gr[25];
- case 1:
- args[0] = regs->gr[26];
- case 0:
- break;
- default:
- BUG();
- }
+ args[5] = regs->gr[21];
+ args[4] = regs->gr[22];
+ args[3] = regs->gr[23];
+ args[2] = regs->gr[24];
+ args[1] = regs->gr[25];
+ args[0] = regs->gr[26];
}
static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 1a0e7a8b1c81..5c9b9dc82b7e 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -65,22 +65,20 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
unsigned long val, mask = -1UL;
-
- BUG_ON(i + n > 6);
+ unsigned int n = 6;
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_32BIT))
mask = 0xffffffff;
#endif
while (n--) {
- if (n == 0 && i == 0)
+ if (n == 0)
val = regs->orig_gpr3;
else
- val = regs->gpr[3 + i + n];
+ val = regs->gpr[3 + n];
args[n] = val & mask;
}
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index bba3da6ef157..85a31dd0f2ba 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -72,17 +72,11 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- if (i == 0) {
- args[0] = regs->orig_a0;
- args++;
- i++;
- n--;
- }
- memcpy(args, ®s->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+ args[0] = regs->orig_a0;
+ args++;
+ memcpy(args, ®s->a1 + sizeof(regs->a1), 5 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 96f9a9151fde..ee0b1f6aa36d 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -56,27 +56,20 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
unsigned long mask = -1UL;
+ unsigned int n = 6;
- /*
- * No arguments for this syscall, there's nothing to do.
- */
- if (!n)
- return;
-
- BUG_ON(i + n > 6);
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_31BIT))
mask = 0xffffffff;
#endif
while (n-- > 0)
- if (i + n > 0)
- args[n] = regs->gprs[2 + i + n] & mask;
- if (i == 0)
- args[0] = regs->orig_gpr2 & mask;
+ if (n > 0)
+ args[n] = regs->gprs[2 + n] & mask;
+
+ args[0] = regs->orig_gpr2 & mask;
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 6e118799831c..2bf1199a0595 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -48,30 +48,16 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- /*
- * Do this simply for now. If we need to start supporting
- * fetching arguments from arbitrary indices, this will need some
- * extra logic. Presently there are no in-tree users that depend
- * on this behaviour.
- */
- BUG_ON(i);
/* Argument pattern is: R4, R5, R6, R7, R0, R1 */
- switch (n) {
- case 6: args[5] = regs->regs[1];
- case 5: args[4] = regs->regs[0];
- case 4: args[3] = regs->regs[7];
- case 3: args[2] = regs->regs[6];
- case 2: args[1] = regs->regs[5];
- case 1: args[0] = regs->regs[4];
- case 0:
- break;
- default:
- BUG();
- }
+ args[5] = regs->regs[1];
+ args[4] = regs->regs[0];
+ args[3] = regs->regs[7];
+ args[2] = regs->regs[6];
+ args[1] = regs->regs[5];
+ args[0] = regs->regs[4];
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index 43882580c7f9..4e8f6460c703 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -47,11 +47,9 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, ®s->regs[2 + i], n * sizeof(args[0]));
+ memcpy(args, ®s->regs[2], 6 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 053989e3f6a6..872dfee852d6 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -96,11 +96,11 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
int zero_extend = 0;
unsigned int j;
+ unsigned int n = 6;
#ifdef CONFIG_SPARC64
if (test_tsk_thread_flag(task, TIF_32BIT))
@@ -108,7 +108,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
#endif
for (j = 0; j < n; j++) {
- unsigned long val = regs->u_regs[UREG_I0 + i + j];
+ unsigned long val = regs->u_regs[UREG_I0 + j];
if (zero_extend)
args[j] = (u32) val;
diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h
index 9fb9cf8cd39a..25d00acd1322 100644
--- a/arch/um/include/asm/syscall-generic.h
+++ b/arch/um/include/asm/syscall-generic.h
@@ -53,43 +53,16 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
const struct uml_pt_regs *r = ®s->regs;
- switch (i) {
- case 0:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG1(r);
- case 1:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG2(r);
- case 2:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG3(r);
- case 3:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG4(r);
- case 4:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG5(r);
- case 5:
- if (!n--)
- break;
- *args++ = UPT_SYSCALL_ARG6(r);
- case 6:
- if (!n--)
- break;
- default:
- BUG();
- break;
- }
+ *args++ = UPT_SYSCALL_ARG1(r);
+ *args++ = UPT_SYSCALL_ARG2(r);
+ *args++ = UPT_SYSCALL_ARG3(r);
+ *args++ = UPT_SYSCALL_ARG4(r);
+ *args++ = UPT_SYSCALL_ARG5(r);
+ *args = UPT_SYSCALL_ARG6(r);
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d653139857af..8dbb5c379450 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -91,11 +91,9 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
- BUG_ON(i + n > 6);
- memcpy(args, ®s->bx + i, n * sizeof(args[0]));
+ memcpy(args, ®s->bx, 6 * sizeof(args[0]));
}
static inline void syscall_set_arguments(struct task_struct *task,
@@ -116,63 +114,26 @@ static inline int syscall_get_arch(void)
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
# ifdef CONFIG_IA32_EMULATION
- if (task->thread_info.status & TS_COMPAT)
- switch (i) {
- case 0:
- if (!n--) break;
- *args++ = regs->bx;
- case 1:
- if (!n--) break;
- *args++ = regs->cx;
- case 2:
- if (!n--) break;
- *args++ = regs->dx;
- case 3:
- if (!n--) break;
- *args++ = regs->si;
- case 4:
- if (!n--) break;
- *args++ = regs->di;
- case 5:
- if (!n--) break;
- *args++ = regs->bp;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
- else
+ if (task->thread_info.status & TS_COMPAT) {
+ *args++ = regs->bx;
+ *args++ = regs->cx;
+ *args++ = regs->dx;
+ *args++ = regs->si;
+ *args++ = regs->di;
+ *args = regs->bp;
+ } else
# endif
- switch (i) {
- case 0:
- if (!n--) break;
- *args++ = regs->di;
- case 1:
- if (!n--) break;
- *args++ = regs->si;
- case 2:
- if (!n--) break;
- *args++ = regs->dx;
- case 3:
- if (!n--) break;
- *args++ = regs->r10;
- case 4:
- if (!n--) break;
- *args++ = regs->r8;
- case 5:
- if (!n--) break;
- *args++ = regs->r9;
- case 6:
- if (!n--) break;
- default:
- BUG();
- break;
- }
+ {
+ *args++ = regs->di;
+ *args++ = regs->si;
+ *args++ = regs->dx;
+ *args++ = regs->r10;
+ *args++ = regs->r8;
+ *args = regs->r9;
+ }
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index a168bf81c7f4..1504ce9a233a 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -59,23 +59,13 @@ static inline void syscall_set_return_value(struct task_struct *task,
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
- unsigned int i, unsigned int n,
unsigned long *args)
{
static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
- unsigned int j;
-
- if (n == 0)
- return;
-
- WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS);
+ unsigned int i;
- for (j = 0; j < n; ++j) {
- if (i + j < SYSCALL_MAX_ARGS)
- args[j] = regs->areg[reg[i + j]];
- else
- args[j] = 0;
- }
+ for (i = 0; i < 6; ++i)
+ args[i] = regs->areg[reg[i]];
}
static inline void syscall_set_arguments(struct task_struct *task,
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 0c938a4354f6..269e9412ef42 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -105,21 +105,16 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
* syscall_get_arguments - extract system call parameter values
* @task: task of interest, must be blocked
* @regs: task_pt_regs() of @task
- * @i: argument index [0,5]
- * @n: number of arguments; n+i must be [1,6].
* @args: array filled with argument values
*
- * Fetches @n arguments to the system call starting with the @i'th argument
- * (from 0 through 5). Argument @i is stored in @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Fetches 6 arguments to the system call. First argument is stored in
+* @args[0], and so on.
*
* It's only valid to call this when @task is stopped for tracing on
* entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
*/
void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
- unsigned int i, unsigned int n, unsigned long *args);
+ unsigned long *args);
/**
* syscall_set_arguments - change system call parameter value
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 44a3259ed4a5..b6e0cbc2c71f 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -28,7 +28,7 @@ TRACE_EVENT_FN(sys_enter,
TP_fast_assign(
__entry->id = id;
- syscall_get_arguments(current, regs, 0, 6, __entry->args);
+ syscall_get_arguments(current, regs, __entry->args);
),
TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)",
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 54a0347ca812..df27e499956a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -149,7 +149,7 @@ static void populate_seccomp_data(struct seccomp_data *sd)
sd->nr = syscall_get_nr(task, regs);
sd->arch = syscall_get_arch();
- syscall_get_arguments(task, regs, 0, 6, args);
+ syscall_get_arguments(task, regs, args);
sd->args[0] = args[0];
sd->args[1] = args[1];
sd->args[2] = args[2];
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index e9f5bbbad6d9..fa8fbff736d6 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -348,7 +348,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
entry = ring_buffer_event_data(event);
entry->nr = syscall_nr;
- syscall_get_arguments(current, regs, 0, 6, args);
+ syscall_get_arguments(current, regs, args);
memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
event_trigger_unlock_commit(trace_file, buffer, event, entry,
@@ -616,7 +616,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
return;
rec->nr = syscall_nr;
- syscall_get_arguments(current, regs, 0, 6, args);
+ syscall_get_arguments(current, regs, args);
memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
if ((valid_prog_array &&
diff --git a/lib/syscall.c b/lib/syscall.c
index e8467e17b9a2..fb328e7ccb08 100644
--- a/lib/syscall.c
+++ b/lib/syscall.c
@@ -27,7 +27,7 @@ static int collect_syscall(struct task_struct *target, struct syscall_info *info
info->data.nr = syscall_get_nr(target, regs);
if (info->data.nr != -1L)
- syscall_get_arguments(target, regs, 0, 6,
+ syscall_get_arguments(target, regs,
(unsigned long *)&info->data.args[0]);
put_task_stack(target);
--
2.20.1
^ permalink raw reply related
* Re: [RFC PATCH 3/3] powenv/mce: print additional information about mce error.
From: Michael Ellerman @ 2019-03-29 1:31 UTC (permalink / raw)
To: Mahesh J Salgaonkar, linuxppc-dev; +Cc: Paul Mackerras, Nicholas Piggin
In-Reply-To: <155324740037.7819.10748646728863055152.stgit@jupiter.in.ibm.com>
Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com> writes:
> From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
>
> Print more information about mce error whether it is an hardware or
> software error.
>
> Some of the mce errors can be easily categorized as hardware or software
> errors e.g. UEs are due to hardware error, where as error triggered due to
> invalid usage of tlbie is a pure software bug. But not all the mce errors
> can be easily categorize into either software or hardware. There are errors
> like multihit errors which are usually result of a software bug, but in
> some rare cases a hardware failure can cause a multihit error. In past, we
> have seen case where after replacing faulty chip, multihit errors stopped
> occurring. Same with parity errors, which are usually due to faulty hardware
> but there are chances where multihit can also cause an parity error. Such
> errors are difficult to determine what really caused it. Hence this patch
> classifies mce errors into following four categorize:
> 1. Hardware error:
> UE and Link timeout failure errors.
> 2. Hardware error, small probability of software cause:
> SLB/ERAT/TLB Parity errors.
> 3. Software error
> Invalid tlbie form.
> 4. Software error, small probability of hardware failure
> SLB/ERAT/TLB Multihit errors.
I like the idea, but I think the phrasing is a little confusing.
> Sample o/p:
>
> [ 1259.331319] MCE: CPU40: (Warning) Guest SLB Multihit at 00007fff9a59dc60 DAR: 000001003d740320 [Recovered]
> [ 1259.331324] MCE: CPU40: PID: 24051 Comm: qemu-system-ppc
> [ 1259.331345] MCE: CPU40: Software error, small probability of hardware failure
"Software error, small probability of hardware failure"
That can be read as "there has been a software error, *and now* there is
a small probability of a hardware failure".
I also think "probability" suggests we actually know the mathematical
probability of it being a hardware failure, which is not true.
Instead maybe we use:
"Hardware error",
"Probable hardware error (some chance of software cause)",
"Software error",
"Probable software error (some chance of hardware cause)",
??
cheers
^ permalink raw reply
* Re: [RFC PATCH 2/3] powernv/mce: Print correct severity for mce error.
From: Michael Ellerman @ 2019-03-29 0:23 UTC (permalink / raw)
To: Mahesh J Salgaonkar, linuxppc-dev; +Cc: Paul Mackerras, Nicholas Piggin
In-Reply-To: <155324739171.7819.1095626412782166400.stgit@jupiter.in.ibm.com>
Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com> writes:
> diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
> index 8d0b1c24c636..314ed3f13d59 100644
> --- a/arch/powerpc/include/asm/mce.h
> +++ b/arch/powerpc/include/asm/mce.h
> @@ -110,17 +110,18 @@ enum MCE_LinkErrorType {
> };
>
> struct machine_check_event {
> - enum MCE_Version version:8; /* 0x00 */
> - uint8_t in_use; /* 0x01 */
> - enum MCE_Severity severity:8; /* 0x02 */
> - enum MCE_Initiator initiator:8; /* 0x03 */
> - enum MCE_ErrorType error_type:8; /* 0x04 */
> - enum MCE_Disposition disposition:8; /* 0x05 */
> - uint16_t cpu; /* 0x06 */
> - uint64_t gpr3; /* 0x08 */
> - uint64_t srr0; /* 0x10 */
> - uint64_t srr1; /* 0x18 */
> - union { /* 0x20 */
> + enum MCE_Version version:8;
> + uint8_t in_use;
> + enum MCE_Severity severity:8;
> + enum MCE_Initiator initiator:8;
> + enum MCE_ErrorType error_type:8;
> + enum MCE_Disposition disposition:8;
> + uint8_t sync_error;
> + uint16_t cpu;
> + uint64_t gpr3;
> + uint64_t srr0;
> + uint64_t srr1;
Can you switch these to use kernel types while you're at it, ie. u8, u64 etc.
> @@ -194,6 +195,7 @@ struct mce_error_info {
> } u;
> enum MCE_Severity severity:8;
> enum MCE_Initiator initiator:8;
> + uint8_t sync_error;
u8 here but bool later?
> diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
> index 6b800eec31f2..06161de19060 100644
> --- a/arch/powerpc/kernel/mce_power.c
> +++ b/arch/powerpc/kernel/mce_power.c
> @@ -133,106 +133,107 @@ struct mce_ierror_table {
> unsigned int error_subtype;
> unsigned int initiator;
> unsigned int severity;
> + bool sync_error;
> };
ie. here it's a bool?
> @@ -539,8 +543,9 @@ static int mce_handle_derror(struct pt_regs *regs,
> return handled;
>
> mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
> - mce_err->severity = MCE_SEV_ERROR_SYNC;
> + mce_err->severity = MCE_SEV_SEVERE;
> mce_err->initiator = MCE_INITIATOR_CPU;
> + mce_err->sync_error = 1;
u8 or bool?
cheers
^ permalink raw reply
* Re: [RFC PATCH 1/3] powernv/mce: reduce mce console logs to lesser lines.
From: Michael Ellerman @ 2019-03-29 0:20 UTC (permalink / raw)
To: Mahesh J Salgaonkar, linuxppc-dev; +Cc: Paul Mackerras, Nicholas Piggin
In-Reply-To: <155324738319.7819.17982472592795327790.stgit@jupiter.in.ibm.com>
Hi Mahesh,
Thanks for doing this series.
Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com> writes:
> From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
>
> Also add cpu number while displaying mce log. This will help cleaner logs
> when mce hits on multiple cpus simultaneously.
Can you include some examples of the output before and after, so it's
easier to compare what the changes are.
I think you have an example in patch 3, but it would be good to have it here.
> diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
> index b5fec1f9751a..44614462cb34 100644
> --- a/arch/powerpc/kernel/mce.c
> +++ b/arch/powerpc/kernel/mce.c
> @@ -384,101 +387,100 @@ void machine_check_print_event_info(struct machine_check_event *evt,
> break;
> }
>
> - printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
I think I'd still like the first line at least to include "machine
check" somewhere, I'm not sure everyone will understand what "MCE" means.
...
> +
> + if (ea && evt->srr0 != ea)
> + sprintf(dar_str, "DAR: %016llx ", ea);
> + else
> + memset(dar_str, 0, sizeof(dar_str));
Just dar_str[0] = '\0' would work wouldn't it?
> + if (in_guest || user_mode) {
> + printk("%sMCE: CPU%d: (%s) %s %s %s at %016llx %s[%s]\n",
> + level, evt->cpu, sevstr,
> + in_guest ? "Guest" : "Host",
> + err_type, subtype, evt->srr0, dar_str,
> + evt->disposition == MCE_DISPOSITION_RECOVERED ?
> + "Recovered" : "Not recovered");
> + printk("%sMCE: CPU%d: PID: %d Comm: %s\n",
> + level, evt->cpu, current->pid, current->comm);
> + } else {
> + printk("%sMCE: CPU%d: (%s) Host %s %s at %016llx %s[%s]\n",
> + level, evt->cpu, sevstr, err_type, subtype, evt->srr0,
> + dar_str,
> + evt->disposition == MCE_DISPOSITION_RECOVERED ?
> + "Recovered" : "Not recovered");
> + printk("%sMCE: CPU%d: NIP: [%016llx] %pS\n",
> + level, evt->cpu, evt->srr0, (void *)evt->srr0);
> + }
The first printf in the two cases is quite similar, seems like they
could be consolidated.
I also think it'd be clearer to print the NIP on the 2nd line in all
cases, rather than the first.
What about (untested) ?
printk("%sMCE: CPU%d: (%s) %s %s %s %s[%s]\n",
level, evt->cpu, sevstr,
in_guest ? "Guest" : "Host",
err_type, subtype, dar_str,
evt->disposition == MCE_DISPOSITION_RECOVERED ?
"Recovered" : "Not recovered");
if (in_guest || user_mode) {
printk("%sMCE: CPU%d: PID: %d Comm: %s %sNIP: [%016llx]\n",
level, evt->cpu, current->pid, current->comm,
in_guest ? "Guest " : "", evt->srr0);
} else {
printk("%sMCE: CPU%d: NIP: [%016llx] %pS\n",
level, evt->cpu, evt->srr0, (void *)evt->srr0);
}
cheers
^ permalink raw reply
* Re: [RFC PATCH] powerpc/book3e: KASAN Full support for 64bit
From: Daniel Axtens @ 2019-03-28 23:41 UTC (permalink / raw)
To: Christophe Leroy; +Cc: linuxppc-dev, linux-kernel
In-Reply-To: <488ecc81-ac72-ec04-380a-bd04d4def39d@c-s.fr>
Hi Christophe,
> Daniel,
>
> This patch applies on top of my series.
>
> With this patch, I've managed to enable KASAN without the changes you
> proposed on the KASAN core. This allows a full support of KASAN, ie not
> limited to KASAN_MINIMAL.
>
> There is still some details to address, but it boots OK on qemu-e500.
>
> Can you have a try and tell me if it works on your side too ?
>
> It will likely fail for modules at the time being as I did nothing about it.
>
> Tell me if you continue working on it. I don't plan to spend more time
> on it for the time being.
Thanks!! I will have a look - I've been trying to do something on 3s
Radix and was hoping to apply lessons learned from that to the 3e case.
So it may take a little while but I will eventually get back to this.
Regards,
Daniel
>
> Like I did on PPC32, it would be good to create an early_64.c file and
> move into it the few functions from setup_64.c and paca.c that are
> called before feature_fixups are done, in order to not disable KASAN on
> the entire paca.c and setup_64.c
>
> I guess we could reduce a bit the size of the IOREMAP_AREA and put KASAN
> on top of it instead of using VMEMMAP space, allthough I don't have a
> clean view of how it would cooperate with VMEMMMAP if we keep it enabled.
>
> I've not been able to identify what is the largest size of the linear
> mapping (ie the 0xc000000000000000 region).
>
> Christophe
>
> Le 28/03/2019 à 15:21, Christophe Leroy a écrit :
>> The KASAN shadow area is mapped into vmemmap space:
>> 0x8000 0400 0000 0000 to 0x8000 0600 0000 0000.
>> For this vmemmap has to be disabled.
>>
>> Cc: Daniel Axtens <dja@axtens.net>
>> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
>> ---
>> arch/powerpc/Kconfig | 1 +
>> arch/powerpc/Kconfig.debug | 3 +-
>> arch/powerpc/include/asm/kasan.h | 11 +++
>> arch/powerpc/kernel/Makefile | 2 +
>> arch/powerpc/kernel/head_64.S | 3 +
>> arch/powerpc/kernel/setup_64.c | 20 +++---
>> arch/powerpc/mm/kasan/Makefile | 1 +
>> arch/powerpc/mm/kasan/kasan_init_64.c | 129 ++++++++++++++++++++++++++++++++++
>> 8 files changed, 159 insertions(+), 11 deletions(-)
>> create mode 100644 arch/powerpc/mm/kasan/kasan_init_64.c
>>
>> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
>> index 1a2fb50126b2..e0b7c45e4dc7 100644
>> --- a/arch/powerpc/Kconfig
>> +++ b/arch/powerpc/Kconfig
>> @@ -174,6 +174,7 @@ config PPC
>> select HAVE_ARCH_AUDITSYSCALL
>> select HAVE_ARCH_JUMP_LABEL
>> select HAVE_ARCH_KASAN if PPC32
>> + select HAVE_ARCH_KASAN if PPC_BOOK3E_64 && !SPARSEMEM_VMEMMAP
>> select HAVE_ARCH_KGDB
>> select HAVE_ARCH_MMAP_RND_BITS
>> select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
>> diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
>> index 61febbbdd02b..b4140dd6b4e4 100644
>> --- a/arch/powerpc/Kconfig.debug
>> +++ b/arch/powerpc/Kconfig.debug
>> @@ -370,4 +370,5 @@ config PPC_FAST_ENDIAN_SWITCH
>> config KASAN_SHADOW_OFFSET
>> hex
>> depends on KASAN
>> - default 0xe0000000
>> + default 0xe0000000 if PPC32
>> + default 0x6800040000000000 if PPC64
>> diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
>> index 296e51c2f066..756b3d58f921 100644
>> --- a/arch/powerpc/include/asm/kasan.h
>> +++ b/arch/powerpc/include/asm/kasan.h
>> @@ -23,10 +23,21 @@
>>
>> #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET)
>>
>> +#ifdef CONFIG_PPC32
>> #define KASAN_SHADOW_END 0UL
>>
>> #define KASAN_SHADOW_SIZE (KASAN_SHADOW_END - KASAN_SHADOW_START)
>>
>> +#else
>> +
>> +#include <asm/pgtable.h>
>> +
>> +#define KASAN_SHADOW_SIZE (KERN_VIRT_SIZE >> KASAN_SHADOW_SCALE_SHIFT)
>> +
>> +#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
>> +
>> +#endif /* CONFIG_PPC32 */
>> +
>> #ifdef CONFIG_KASAN
>> void kasan_early_init(void);
>> void kasan_mmu_init(void);
>> diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
>> index 0ea6c4aa3a20..7f232c06f11d 100644
>> --- a/arch/powerpc/kernel/Makefile
>> +++ b/arch/powerpc/kernel/Makefile
>> @@ -35,6 +35,8 @@ KASAN_SANITIZE_early_32.o := n
>> KASAN_SANITIZE_cputable.o := n
>> KASAN_SANITIZE_prom_init.o := n
>> KASAN_SANITIZE_btext.o := n
>> +KASAN_SANITIZE_paca.o := n
>> +KASAN_SANITIZE_setup_64.o := n
>>
>> ifdef CONFIG_KASAN
>> CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING
>> diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
>> index 3fad8d499767..80fbd8024fb2 100644
>> --- a/arch/powerpc/kernel/head_64.S
>> +++ b/arch/powerpc/kernel/head_64.S
>> @@ -966,6 +966,9 @@ start_here_multiplatform:
>> * and SLB setup before we turn on relocation.
>> */
>>
>> +#ifdef CONFIG_KASAN
>> + bl kasan_early_init
>> +#endif
>> /* Restore parameters passed from prom_init/kexec */
>> mr r3,r31
>> bl early_setup /* also sets r13 and SPRG_PACA */
>> diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
>> index ba404dd9ce1d..d2bf860dd966 100644
>> --- a/arch/powerpc/kernel/setup_64.c
>> +++ b/arch/powerpc/kernel/setup_64.c
>> @@ -311,6 +311,16 @@ void __init early_setup(unsigned long dt_ptr)
>> DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr);
>>
>> /*
>> + * Configure exception handlers. This include setting up trampolines
>> + * if needed, setting exception endian mode, etc...
>> + */
>> + configure_exceptions();
>> +
>> + /* Apply all the dynamic patching */
>> + apply_feature_fixups();
>> + setup_feature_keys();
>> +
>> + /*
>> * Do early initialization using the flattened device
>> * tree, such as retrieving the physical memory map or
>> * calculating/retrieving the hash table size.
>> @@ -325,16 +335,6 @@ void __init early_setup(unsigned long dt_ptr)
>> setup_paca(paca_ptrs[boot_cpuid]);
>> fixup_boot_paca();
>>
>> - /*
>> - * Configure exception handlers. This include setting up trampolines
>> - * if needed, setting exception endian mode, etc...
>> - */
>> - configure_exceptions();
>> -
>> - /* Apply all the dynamic patching */
>> - apply_feature_fixups();
>> - setup_feature_keys();
>> -
>> /* Initialize the hash table or TLB handling */
>> early_init_mmu();
>>
>> diff --git a/arch/powerpc/mm/kasan/Makefile b/arch/powerpc/mm/kasan/Makefile
>> index 6577897673dd..0bfbe3892808 100644
>> --- a/arch/powerpc/mm/kasan/Makefile
>> +++ b/arch/powerpc/mm/kasan/Makefile
>> @@ -3,3 +3,4 @@
>> KASAN_SANITIZE := n
>>
>> obj-$(CONFIG_PPC32) += kasan_init_32.o
>> +obj-$(CONFIG_PPC64) += kasan_init_64.o
>> diff --git a/arch/powerpc/mm/kasan/kasan_init_64.c b/arch/powerpc/mm/kasan/kasan_init_64.c
>> new file mode 100644
>> index 000000000000..7fd71b8e883b
>> --- /dev/null
>> +++ b/arch/powerpc/mm/kasan/kasan_init_64.c
>> @@ -0,0 +1,129 @@
>> +// SPDX-License-Identifier: GPL-2.0
>> +
>> +#define DISABLE_BRANCH_PROFILING
>> +
>> +#include <linux/kasan.h>
>> +#include <linux/printk.h>
>> +#include <linux/memblock.h>
>> +#include <linux/sched/task.h>
>> +#include <asm/pgalloc.h>
>> +
>> +static void __init kasan_populate_pte(pte_t *ptep, pgprot_t prot)
>> +{
>> + unsigned long va = (unsigned long)kasan_early_shadow_page;
>> + phys_addr_t pa = __pa(kasan_early_shadow_page);
>> + int i;
>> +
>> + for (i = 0; i < PTRS_PER_PTE; i++, ptep++)
>> + __set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
>> +}
>> +
>> +static void __init kasan_populate_pmd(pmd_t *pmdp)
>> +{
>> + int i;
>> +
>> + for (i = 0; i < PTRS_PER_PMD; i++)
>> + pmd_populate_kernel(&init_mm, pmdp + i, kasan_early_shadow_pte);
>> +}
>> +
>> +static void __init kasan_populate_pud(pud_t *pudp)
>> +{
>> + int i;
>> +
>> + for (i = 0; i < PTRS_PER_PUD; i++)
>> + pud_populate(&init_mm, pudp + i, kasan_early_shadow_pmd);
>> +}
>> +
>> +static void __init *kasan_alloc_pgtable(unsigned long size)
>> +{
>> + void *ptr = memblock_alloc_try_nid(size, size, MEMBLOCK_LOW_LIMIT,
>> + __pa(MAX_DMA_ADDRESS), NUMA_NO_NODE);
>> +
>> + if (!ptr)
>> + panic("%s: Failed to allocate %lu bytes align=0x%lx max_addr=%lx\n",
>> + __func__, size, size, __pa(MAX_DMA_ADDRESS));
>> +
>> + return ptr;
>> +}
>> +
>> +static int __init kasan_map_page(unsigned long va, unsigned long pa, pgprot_t prot)
>> +{
>> + pgd_t *pgdp = pgd_offset_k(va);
>> + pud_t *pudp;
>> + pmd_t *pmdp;
>> + pte_t *ptep;
>> +
>> + if (pgd_none(*pgdp) || (void *)pgd_page_vaddr(*pgdp) == kasan_early_shadow_pud) {
>> + pudp = kasan_alloc_pgtable(PUD_TABLE_SIZE);
>> + kasan_populate_pud(pudp);
>> + pgd_populate(&init_mm, pgdp, pudp);
>> + }
>> + pudp = pud_offset(pgdp, va);
>> + if (pud_none(*pudp) || (void *)pud_page_vaddr(*pudp) == kasan_early_shadow_pmd) {
>> + pmdp = kasan_alloc_pgtable(PMD_TABLE_SIZE);
>> + kasan_populate_pmd(pmdp);
>> + pud_populate(&init_mm, pudp, pmdp);
>> + }
>> + pmdp = pmd_offset(pudp, va);
>> + if (!pmd_present(*pmdp) || (void *)pmd_page_vaddr(*pmdp) == kasan_early_shadow_pte) {
>> + ptep = kasan_alloc_pgtable(PTE_TABLE_SIZE);
>> + kasan_populate_pte(ptep, PAGE_KERNEL);
>> + pmd_populate_kernel(&init_mm, pmdp, ptep);
>> + }
>> + ptep = pte_offset_kernel(pmdp, va);
>> +
>> + __set_pte_at(&init_mm, va, ptep, pfn_pte(pa >> PAGE_SHIFT, prot), 0);
>> +
>> + return 0;
>> +}
>> +
>> +static void __init kasan_init_region(struct memblock_region *reg)
>> +{
>> + void *start = __va(reg->base);
>> + void *end = __va(reg->base + reg->size);
>> + unsigned long k_start, k_end, k_cur;
>> +
>> + if (start >= end)
>> + return;
>> +
>> + k_start = (unsigned long)kasan_mem_to_shadow(start);
>> + k_end = (unsigned long)kasan_mem_to_shadow(end);
>> +
>> + for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE) {
>> + void *va = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
>> +
>> + kasan_map_page(k_cur, __pa(va), PAGE_KERNEL);
>> + }
>> + flush_tlb_kernel_range(k_start, k_end);
>> +}
>> +
>> +void __init kasan_init(void)
>> +{
>> + struct memblock_region *reg;
>> +
>> + for_each_memblock(memory, reg)
>> + kasan_init_region(reg);
>> +
>> + /* It's too early to use clear_page() ! */
>> + memset(kasan_early_shadow_page, 0, sizeof(kasan_early_shadow_page));
>> +
>> + /* Enable error messages */
>> + init_task.kasan_depth = 0;
>> + pr_info("KASAN init done\n");
>> +}
>> +
>> +/* The early shadow maps everything to a single page of zeroes */
>> +asmlinkage void __init kasan_early_init(void)
>> +{
>> + unsigned long addr = KASAN_SHADOW_START;
>> + unsigned long end = KASAN_SHADOW_END;
>> + pgd_t *pgdp = pgd_offset_k(addr);
>> +
>> + kasan_populate_pte(kasan_early_shadow_pte, PAGE_KERNEL);
>> + kasan_populate_pmd(kasan_early_shadow_pmd);
>> + kasan_populate_pud(kasan_early_shadow_pud);
>> +
>> + do {
>> + pgd_populate(&init_mm, pgdp, kasan_early_shadow_pud);
>> + } while (pgdp++, addr = pgd_addr_end(addr, end), addr != end);
>> +}
>>
^ permalink raw reply
* Re: [PATCH v8 4/4] hugetlb: allow to free gigantic pages regardless of the configuration
From: Mike Kravetz @ 2019-03-28 20:43 UTC (permalink / raw)
To: Alexandre Ghiti, aneesh.kumar, mpe, Andrew Morton,
Vlastimil Babka, Catalin Marinas, Will Deacon,
Benjamin Herrenschmidt, Paul Mackerras, Martin Schwidefsky,
Heiko Carstens, Yoshinori Sato, Rich Felker, David S . Miller,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, H . Peter Anvin,
x86, Dave Hansen, Andy Lutomirski, Peter Zijlstra,
linux-arm-kernel, linux-kernel, linuxppc-dev, linux-s390,
linux-sh, sparclinux, linux-mm
In-Reply-To: <20190327063626.18421-5-alex@ghiti.fr>
On 3/26/19 11:36 PM, Alexandre Ghiti wrote:
> On systems without CONTIG_ALLOC activated but that support gigantic pages,
> boottime reserved gigantic pages can not be freed at all. This patch
> simply enables the possibility to hand back those pages to memory
> allocator.
>
> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
Thanks for all the updates
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
--
Mike Kravetz
^ permalink raw reply
* [PATCH V3 7/7] IB/mthca: Use the new FOLL_LONGTERM flag to get_user_pages_fast()
From: ira.weiny @ 2019-03-28 8:44 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, linuxppc-dev
In-Reply-To: <20190328084422.29911-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
Use the new FOLL_LONGTERM to get_user_pages_fast() to protect against
FS DAX pages being mapped.
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
Changes from V2:
<none>
drivers/infiniband/hw/mthca/mthca_memfree.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c
index 112d2f38e0de..8ff0e90d7564 100644
--- a/drivers/infiniband/hw/mthca/mthca_memfree.c
+++ b/drivers/infiniband/hw/mthca/mthca_memfree.c
@@ -472,7 +472,8 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
goto out;
}
- ret = get_user_pages_fast(uaddr & PAGE_MASK, 1, FOLL_WRITE, pages);
+ ret = get_user_pages_fast(uaddr & PAGE_MASK, 1,
+ FOLL_WRITE | FOLL_LONGTERM, pages);
if (ret < 0)
goto out;
--
2.20.1
^ permalink raw reply related
* [PATCH V3 6/7] IB/qib: Use the new FOLL_LONGTERM flag to get_user_pages_fast()
From: ira.weiny @ 2019-03-28 8:44 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, Dan Williams,
linuxppc-dev
In-Reply-To: <20190328084422.29911-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
Use the new FOLL_LONGTERM to get_user_pages_fast() to protect against
FS DAX pages being mapped.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
Changes from V2:
added reviewed-by
drivers/infiniband/hw/qib/qib_user_sdma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 31c523b2a9f5..b53cc0240e02 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -673,7 +673,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
else
j = npages;
- ret = get_user_pages_fast(addr, j, 0, pages);
+ ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
if (ret != j) {
i = 0;
j = ret;
--
2.20.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox