* [powerpc:merge] BUILD SUCCESS 1bc92fe3175eb26ff37e580c0383d7a9abe06835
From: kbuild test robot @ 2020-05-04 14:39 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git merge
branch HEAD: 1bc92fe3175eb26ff37e580c0383d7a9abe06835 Automatic merge of branches 'master', 'next' and 'fixes' into merge
elapsed time: 5894m
configs tested: 248
configs skipped: 0
The following configs have been built successfully.
More configs may be tested in the coming days.
arm efm32_defconfig
arm at91_dt_defconfig
arm shmobile_defconfig
arm64 defconfig
arm multi_v5_defconfig
arm sunxi_defconfig
arm multi_v7_defconfig
arm exynos_defconfig
arm64 allyesconfig
arm allyesconfig
arm64 allmodconfig
arm allmodconfig
arm64 allnoconfig
arm allnoconfig
sparc allyesconfig
powerpc defconfig
ia64 defconfig
powerpc chrp32_defconfig
c6x evmc6678_defconfig
xtensa common_defconfig
ia64 alldefconfig
nds32 allnoconfig
mips capcella_defconfig
riscv nommu_virt_defconfig
mips allmodconfig
s390 zfcpdump_defconfig
powerpc mpc512x_defconfig
sh sh7785lcr_32bit_defconfig
xtensa iss_defconfig
um defconfig
sh rsk7269_defconfig
mips allnoconfig
csky defconfig
i386 allnoconfig
i386 allyesconfig
i386 alldefconfig
i386 defconfig
i386 debian-10.3
ia64 allmodconfig
ia64 allnoconfig
ia64 generic_defconfig
ia64 tiger_defconfig
ia64 bigsur_defconfig
ia64 allyesconfig
m68k m5475evb_defconfig
m68k allmodconfig
m68k bvme6000_defconfig
m68k sun3_defconfig
m68k multi_defconfig
nios2 3c120_defconfig
nios2 10m50_defconfig
c6x allyesconfig
openrisc simple_smp_defconfig
openrisc or1ksim_defconfig
nds32 defconfig
alpha defconfig
h8300 h8s-sim_defconfig
h8300 edosk2674_defconfig
h8300 h8300h-sim_defconfig
arc defconfig
arc allyesconfig
microblaze mmu_defconfig
microblaze nommu_defconfig
mips fuloong2e_defconfig
mips malta_kvm_defconfig
mips ar7_defconfig
mips allyesconfig
mips 64r6el_defconfig
mips 32r2_defconfig
mips malta_kvm_guest_defconfig
mips tb0287_defconfig
mips ip32_defconfig
mips decstation_64_defconfig
mips loongson3_defconfig
mips ath79_defconfig
mips bcm63xx_defconfig
parisc allnoconfig
parisc generic-64bit_defconfig
parisc generic-32bit_defconfig
parisc allyesconfig
parisc allmodconfig
powerpc holly_defconfig
powerpc ppc64_defconfig
powerpc rhel-kconfig
powerpc allnoconfig
powerpc mpc866_ads_defconfig
powerpc amigaone_defconfig
powerpc adder875_defconfig
powerpc ep8248e_defconfig
powerpc g5_defconfig
parisc randconfig-a001-20200430
mips randconfig-a001-20200430
m68k randconfig-a001-20200430
riscv randconfig-a001-20200430
alpha randconfig-a001-20200430
nds32 randconfig-a001-20200430
m68k randconfig-a001-20200502
mips randconfig-a001-20200502
nds32 randconfig-a001-20200502
alpha randconfig-a001-20200502
parisc randconfig-a001-20200502
riscv randconfig-a001-20200502
microblaze randconfig-a001-20200430
nios2 randconfig-a001-20200430
h8300 randconfig-a001-20200430
c6x randconfig-a001-20200430
sparc64 randconfig-a001-20200430
h8300 randconfig-a001-20200502
nios2 randconfig-a001-20200502
microblaze randconfig-a001-20200502
c6x randconfig-a001-20200502
sparc64 randconfig-a001-20200502
s390 randconfig-a001-20200430
xtensa randconfig-a001-20200430
csky randconfig-a001-20200430
openrisc randconfig-a001-20200430
sh randconfig-a001-20200430
s390 randconfig-a001-20200502
xtensa randconfig-a001-20200502
sh randconfig-a001-20200502
openrisc randconfig-a001-20200502
csky randconfig-a001-20200502
s390 randconfig-a001-20200501
xtensa randconfig-a001-20200501
sh randconfig-a001-20200501
openrisc randconfig-a001-20200501
csky randconfig-a001-20200501
x86_64 randconfig-a003-20200501
x86_64 randconfig-a001-20200501
i386 randconfig-a003-20200501
i386 randconfig-a002-20200501
i386 randconfig-a001-20200501
i386 randconfig-b003-20200501
x86_64 randconfig-b002-20200501
i386 randconfig-b001-20200501
x86_64 randconfig-b003-20200501
x86_64 randconfig-b001-20200501
i386 randconfig-b002-20200501
i386 randconfig-b001-20200430
i386 randconfig-b002-20200430
x86_64 randconfig-b001-20200430
i386 randconfig-b003-20200430
x86_64 randconfig-b002-20200430
x86_64 randconfig-b003-20200430
i386 randconfig-b003-20200502
i386 randconfig-b001-20200502
x86_64 randconfig-b003-20200502
x86_64 randconfig-b001-20200502
i386 randconfig-b002-20200502
x86_64 randconfig-d001-20200501
i386 randconfig-d003-20200501
x86_64 randconfig-d003-20200501
i386 randconfig-d001-20200501
x86_64 randconfig-d002-20200501
i386 randconfig-d002-20200501
x86_64 randconfig-e003-20200503
x86_64 randconfig-e002-20200503
i386 randconfig-e003-20200503
x86_64 randconfig-e001-20200503
i386 randconfig-e002-20200503
i386 randconfig-e001-20200503
x86_64 randconfig-e002-20200430
i386 randconfig-e003-20200430
x86_64 randconfig-e003-20200430
i386 randconfig-e002-20200430
x86_64 randconfig-e001-20200430
i386 randconfig-e001-20200430
i386 randconfig-f003-20200501
x86_64 randconfig-f001-20200501
x86_64 randconfig-f003-20200501
i386 randconfig-f001-20200501
i386 randconfig-f002-20200501
x86_64 randconfig-a003-20200502
x86_64 randconfig-a001-20200502
x86_64 randconfig-a002-20200502
i386 randconfig-a002-20200502
i386 randconfig-a003-20200502
i386 randconfig-a001-20200502
x86_64 randconfig-g003-20200502
i386 randconfig-g003-20200502
i386 randconfig-g002-20200502
x86_64 randconfig-g001-20200502
x86_64 randconfig-g002-20200502
i386 randconfig-g001-20200502
i386 randconfig-g003-20200501
i386 randconfig-g002-20200501
x86_64 randconfig-g002-20200501
i386 randconfig-g001-20200501
i386 randconfig-h002-20200430
i386 randconfig-h003-20200430
x86_64 randconfig-h001-20200430
x86_64 randconfig-h003-20200430
i386 randconfig-h001-20200430
i386 randconfig-h001-20200501
i386 randconfig-h002-20200501
i386 randconfig-h003-20200501
x86_64 randconfig-h001-20200501
x86_64 randconfig-h003-20200501
i386 randconfig-h001-20200502
i386 randconfig-h002-20200502
i386 randconfig-h003-20200502
x86_64 randconfig-h002-20200502
x86_64 randconfig-h001-20200502
x86_64 randconfig-h003-20200502
ia64 randconfig-a001-20200502
arm64 randconfig-a001-20200502
arc randconfig-a001-20200502
powerpc randconfig-a001-20200502
arm randconfig-a001-20200502
sparc randconfig-a001-20200502
ia64 randconfig-a001-20200501
arc randconfig-a001-20200501
powerpc randconfig-a001-20200501
arm randconfig-a001-20200501
sparc randconfig-a001-20200501
sparc randconfig-a001-20200430
arc randconfig-a001-20200430
ia64 randconfig-a001-20200430
powerpc randconfig-a001-20200430
arm randconfig-a001-20200430
riscv allyesconfig
riscv allnoconfig
riscv defconfig
riscv rv32_defconfig
riscv allmodconfig
s390 debug_defconfig
s390 allyesconfig
s390 allnoconfig
s390 allmodconfig
s390 alldefconfig
s390 defconfig
sh allmodconfig
sh titan_defconfig
sh allnoconfig
sparc defconfig
sparc64 defconfig
sparc64 allnoconfig
sparc64 allyesconfig
sparc64 allmodconfig
um x86_64_defconfig
um i386_defconfig
x86_64 rhel
x86_64 rhel-7.6
x86_64 rhel-7.6-kselftests
x86_64 rhel-7.2-clear
x86_64 lkp
x86_64 fedora-25
x86_64 kexec
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* Re: [PATCH v2] misc: new driver sram_uapi for user level SRAM access
From: kbuild test robot @ 2020-05-04 14:51 UTC (permalink / raw)
To: Wang Wenhu, gregkh, arnd, linux-kernel, linuxppc-dev, kernel,
robh, Christophe Leroy, Scott Wood, Michael Ellerman,
Randy Dunlap
Cc: robh, kbuild-all, Scott Wood, kernel, Wang Wenhu
In-Reply-To: <20200419123011.86765-1-wenhu.wang@vivo.com>
[-- Attachment #1: Type: text/plain, Size: 2329 bytes --]
Hi Wang,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on char-misc/char-misc-testing]
[also build test WARNING on arm-soc/for-next linus/master linux/master v5.7-rc3 next-20200501]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system. BTW, we also suggest to use '--base' option to specify the
base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Wang-Wenhu/misc-new-driver-sram_uapi-for-user-level-SRAM-access/20200421-105427
base: https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git ae83d0b416db002fe95601e7f97f64b59514d936
config: microblaze-allyesconfig (attached as .config)
compiler: microblaze-linux-gcc (GCC) 9.3.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day GCC_VERSION=9.3.0 make.cross ARCH=microblaze
If you fix the issue, kindly add following tag as appropriate
Reported-by: kbuild test robot <lkp@intel.com>
Note: it may well be a FALSE warning. FWIW you are at least aware of it now.
http://gcc.gnu.org/wiki/Better_Uninitialized_Warnings
All warnings (new ones prefixed by >>):
drivers/misc/sram_uapi.c: In function 'sram_uapi_ioctl':
>> drivers/misc/sram_uapi.c:100:6: warning: 'type' may be used uninitialized in this function [-Wmaybe-uninitialized]
100 | if (cur->type == type) {
| ^
drivers/misc/sram_uapi.c:188:8: note: 'type' was declared here
188 | __u32 type;
| ^~~~
vim +/type +100 drivers/misc/sram_uapi.c
93
94 static struct sram_api *get_sram_api_from_type(__u32 type)
95 {
96 struct sram_api *cur;
97
98 mutex_lock(&sram_list_lock);
99 list_for_each_entry(cur, &sram_list, list) {
> 100 if (cur->type == type) {
101 kref_get(&cur->kref);
102 mutex_unlock(&sram_list_lock);
103 return cur;
104 }
105 }
106 mutex_unlock(&sram_list_lock);
107
108 return NULL;
109 }
110
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 62734 bytes --]
^ permalink raw reply
* Re: [PATCH v2 17/20] mm: free_area_init: allow defining max_zone_pfn in descending order
From: Mike Rapoport @ 2020-05-04 15:39 UTC (permalink / raw)
To: Guenter Roeck
Cc: Rich Felker, linux-ia64, linux-doc, Catalin Marinas,
Heiko Carstens, x86, Michal Hocko, James E.J. Bottomley,
Max Filippov, Guo Ren, Ley Foon Tan, sparclinux, linux-riscv,
Greg Ungerer, linux-arch, linux-s390, linux-c6x-dev, Baoquan He,
Jonathan Corbet, linux-hexagon, Helge Deller, linux-sh,
Russell King, linux-csky, Mike Rapoport, Geert Uytterhoeven,
Hoan Tran, Mark Salter, Matt Turner, linux-snps-arc,
uclinux-h8-devel, linux-xtensa, Nick Hu, linux-alpha, linux-um,
linux-mips, Richard Weinberger, linux-m68k, Thomas Bogendoerfer,
Qian Cai, Greentime Hu, Paul Walmsley, Stafford Horne,
Guan Xuetao, linux-arm-kernel, Michal Simek, Tony Luck,
Yoshinori Sato, linux-parisc, linux-mm, Vineet Gupta, Brian Cain,
linux-kernel, openrisc, Andrew Morton, linuxppc-dev,
David S. Miller
In-Reply-To: <20200503184300.GA154219@roeck-us.net>
On Sun, May 03, 2020 at 11:43:00AM -0700, Guenter Roeck wrote:
> On Sun, May 03, 2020 at 10:41:38AM -0700, Guenter Roeck wrote:
> > Hi,
> >
> > On Wed, Apr 29, 2020 at 03:11:23PM +0300, Mike Rapoport wrote:
> > > From: Mike Rapoport <rppt@linux.ibm.com>
> > >
> > > Some architectures (e.g. ARC) have the ZONE_HIGHMEM zone below the
> > > ZONE_NORMAL. Allowing free_area_init() parse max_zone_pfn array even it is
> > > sorted in descending order allows using free_area_init() on such
> > > architectures.
> > >
> > > Add top -> down traversal of max_zone_pfn array in free_area_init() and use
> > > the latter in ARC node/zone initialization.
> > >
> > > Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
> >
> > This patch causes my microblazeel qemu boot test in linux-next to fail.
> > Reverting it fixes the problem.
> >
> The same problem is seen with s390 emulations.
Yeah, this patch breaks some others as well :(
My assumption that max_zone_pfn defines architectural limit for maximal
PFN that can belong to a zone was over-optimistic. Several arches
actually do that, but others do
max_zone_pfn[ZONE_DMA] = MAX_DMA_PFN;
max_zone_pfn[ZONE_NORMAL] = max_pfn;
where MAX_DMA_PFN is build-time constrain and max_pfn is run time limit
for the current system.
So, when max_pfn is lower than MAX_DMA_PFN, the free_init_area() will
consider max_zone_pfn as descending and will wrongly calculate zone
extents.
That said, instead of trying to create a generic way to special case
ARC, I suggest to simply use the below patch instead.
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 41eb9be1653c..386959bac3d2 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -77,6 +77,11 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
base, TO_MB(size), !in_use ? "Not used":"");
}
+bool arch_has_descending_max_zone_pfns(void)
+{
+ return true;
+}
+
/*
* First memory setup routine called from setup_arch()
* 1. setup swapper's mm @init_mm
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b990e9734474..114f0e027144 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7307,6 +7307,15 @@ static void check_for_memory(pg_data_t *pgdat, int nid)
}
}
+/*
+ * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For
+ * such cases we allow max_zone_pfn sorted in the descending order
+ */
+bool __weak arch_has_descending_max_zone_pfns(void)
+{
+ return false;
+}
+
/**
* free_area_init - Initialise all pg_data_t and zone data
* @max_zone_pfn: an array of max PFNs for each zone
@@ -7324,7 +7333,7 @@ void __init free_area_init(unsigned long *max_zone_pfn)
{
unsigned long start_pfn, end_pfn;
int i, nid, zone;
- bool descending = false;
+ bool descending;
/* Record where the zone boundaries are */
memset(arch_zone_lowest_possible_pfn, 0,
@@ -7333,14 +7342,7 @@ void __init free_area_init(unsigned long *max_zone_pfn)
sizeof(arch_zone_highest_possible_pfn));
start_pfn = find_min_pfn_with_active_regions();
-
- /*
- * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below
- * ZONE_NORMAL. For such cases we allow max_zone_pfn sorted in the
- * descending order
- */
- if (MAX_NR_ZONES > 1 && max_zone_pfn[0] > max_zone_pfn[1])
- descending = true;
+ descending = arch_has_descending_max_zone_pfns();
for (i = 0; i < MAX_NR_ZONES; i++) {
if (descending)
> Guenter
>
> > qemu command line:
> >
> > qemu-system-microblazeel -M petalogix-ml605 -m 256 \
> > -kernel arch/microblaze/boot/linux.bin -no-reboot \
> > -initrd rootfs.cpio \
> > -append 'panic=-1 slub_debug=FZPUA rdinit=/sbin/init console=ttyS0,115200' \
> > -monitor none -serial stdio -nographic
> >
> > initrd:
> > https://github.com/groeck/linux-build-test/blob/master/rootfs/microblazeel/rootfs.cpio.gz
> > configuration:
> > https://github.com/groeck/linux-build-test/blob/master/rootfs/microblazeel/qemu_microblazeel_ml605_defconfig
> >
> > Bisect log is below.
> >
> > Guenter
> >
> > ---
> > # bad: [fb9d670f57e3f6478602328bbbf71138be06ca4f] Add linux-next specific files for 20200501
> > # good: [6a8b55ed4056ea5559ebe4f6a4b247f627870d4c] Linux 5.7-rc3
> > git bisect start 'HEAD' 'v5.7-rc3'
> > # good: [068b80b68a670f0b17288c8a3d1ee751f35162ab] Merge remote-tracking branch 'drm/drm-next'
> > git bisect good 068b80b68a670f0b17288c8a3d1ee751f35162ab
> > # good: [46c70fc6a3ac35cd72ddad248dcbe4eee716d2a5] Merge remote-tracking branch 'drivers-x86/for-next'
> > git bisect good 46c70fc6a3ac35cd72ddad248dcbe4eee716d2a5
> > # good: [f39c4ad479a2f005f972a2b941b40efa6b9c9349] Merge remote-tracking branch 'rpmsg/for-next'
> > git bisect good f39c4ad479a2f005f972a2b941b40efa6b9c9349
> > # bad: [165d3ee0162fe28efc2c8180176633e33515df15] ipc-convert-ipcs_idr-to-xarray-update
> > git bisect bad 165d3ee0162fe28efc2c8180176633e33515df15
> > # good: [001f1d211ed2ed0f005838dc4390993930bbbd69] mm: remove early_pfn_in_nid() and CONFIG_NODES_SPAN_OTHER_NODES
> > git bisect good 001f1d211ed2ed0f005838dc4390993930bbbd69
> > # bad: [aaad7401bd32f10c1d591dd886b3a9b9595c6d77] mm/vmsan: fix some typos in comment
> > git bisect bad aaad7401bd32f10c1d591dd886b3a9b9595c6d77
> > # bad: [09f9d0ab1fbed85623b283995aa7a7d78daa1611] khugepaged: allow to collapse PTE-mapped compound pages
> > git bisect bad 09f9d0ab1fbed85623b283995aa7a7d78daa1611
> > # bad: [c942fc8a3e5088407bc32d94f554bab205175f8a] mm/vmstat.c: do not show lowmem reserve protection information of empty zone
> > git bisect bad c942fc8a3e5088407bc32d94f554bab205175f8a
> > # bad: [b29358d269ace3826d8521bea842fc2984cfc11b] mm/page_alloc.c: rename free_pages_check() to check_free_page()
> > git bisect bad b29358d269ace3826d8521bea842fc2984cfc11b
> > # bad: [be0fb591a1f1df20a00c8f023f9ca4891f177b0d] mm: simplify find_min_pfn_with_active_regions()
> > git bisect bad be0fb591a1f1df20a00c8f023f9ca4891f177b0d
> > # bad: [c17422a008d36dcf3e9f51469758c5762716cb0a] mm: rename free_area_init_node() to free_area_init_memoryless_node()
> > git bisect bad c17422a008d36dcf3e9f51469758c5762716cb0a
> > # bad: [51a2f644fd020d5f090044825c388444d11029d5] mm: free_area_init: allow defining max_zone_pfn in descending order
> > git bisect bad 51a2f644fd020d5f090044825c388444d11029d5
> > # first bad commit: [51a2f644fd020d5f090044825c388444d11029d5] mm: free_area_init: allow defining max_zone_pfn in descending order
--
Sincerely yours,
Mike.
^ permalink raw reply related
* Re: [PATCH V2 00/11] Subject: Remove duplicated kmap code
From: Ira Weiny @ 2020-05-04 20:17 UTC (permalink / raw)
To: Al Viro
Cc: Peter Zijlstra, Dave Hansen, dri-devel, linux-mips,
James E.J. Bottomley, Max Filippov, Huang Rui, Paul Mackerras,
H. Peter Anvin, sparclinux, Dan Williams, Helge Deller, x86,
linux-csky, Ingo Molnar, linux-snps-arc, linux-xtensa,
Borislav Petkov, Andy Lutomirski, Thomas Gleixner,
linux-arm-kernel, Chris Zankel, Thomas Bogendoerfer, linux-parisc,
linux-kernel, Christian Koenig, Andrew Morton, linuxppc-dev,
David S. Miller
In-Reply-To: <20200504053357.GV23230@ZenIV.linux.org.uk>
On Mon, May 04, 2020 at 06:33:57AM +0100, Al Viro wrote:
> On Sun, May 03, 2020 at 10:04:47PM -0700, Ira Weiny wrote:
>
> > Grepping for 'asm/highmem.h' and investigations don't reveal any issues... But
> > you do have me worried. That said 0-day has been crunching on multiple
> > versions of this series without issues such as this (save the mips issue
> > above).
> >
> > I have to say it would be nice if the relation between linux/highmem.h and
> > asm/highmem.h was more straightforward.
>
> IIRC, the headache was due to asm/pgtable.h on several architectures and
> asm/cacheflush.h on parisc.
>
> <digs the notes out>
>
> || IOW, there's one in linux/highmem.h (conditional on !CONFIG_HIGHMEM,
> || !ARCH_HAS_KMAP) and several per-architecture variants, usually declared in
> || their asm/highmem.h. In three of those (microblaze, parisc and powerpc) these
> || are inlines (parisc one identical to linux/highmem.h, lives in asm/cacheflush.h,
> || powerpc and microblaze ones calling kmap_atomic_prot() which is defined in
> || arch/$ARCH/mm/highmem.c).
> ||
> || parisc case is weird - essentially, they want to call
> || flush_kernel_dcache_page_addr() at the places where kunmap/kunmap_atomic
> || is done. And they do so despite not selecting HIGHMEM, with definitions
> || in usual place. They do have ARCH_HAS_KMAP defined, which prevents
> || getting buggered in linux/highmem.h. ARCH_HAS_KMAP is parisc-unique,
> || BTW, and checked only in linux/highmem.h.
> ||
> || All genuine arch-specific variants are defined in (or call functions
> || defined in) translation units that are only included CONFIG_HIGHMEM builds.
I agree with this statement. But IMO additional confusion is caused by the
fact that some arch's condition the declarations on CONFIG_HIGHMEM within
asm/highmem.h (arc, arm, nds32) while others depend on linux/highmem.h (and
elsewhere) to do so (csky, microblaze, mips, powerpc, sparc, x86, xtensa).
Why?
I think (perhaps naive) over time asm/highmem.h needs to be isolated to being
included in linux/highmem.h. But as you point out below that is not so easy.
I think that this series helps toward that goal.
> ||
> || It would be tempting to consolidate those, e.g. by adding __kmap_atomic()
> || and __kmap_atomic_prot() without that boilerplate, with universal kmap_atomic()
> || and kmap_atomic_prot() in linux/highmem.h. Potential problem with that would
> || be something that pulls ash/highmem.h (or asm/cacheflush.h in case of parisc)
> || directly and uses kmap_atomic/kmap_atomic_prot. There's not a lot places
> || pulling asm/highmem.h, and many of them are not even in includes:
> ||
> || arch/arm/include/asm/efi.h:13:#include <asm/highmem.h>
> || arch/arm/mm/dma-mapping.c:31:#include <asm/highmem.h>
> || arch/arm/mm/flush.c:14:#include <asm/highmem.h>
> || arch/arm/mm/mmu.c:27:#include <asm/highmem.h>
> || arch/mips/include/asm/pgtable-32.h:22:#include <asm/highmem.h>
> || arch/mips/mm/cache.c:19:#include <asm/highmem.h>
> || arch/mips/mm/fault.c:28:#include <asm/highmem.h> /* For VMALLOC_END */
> || arch/nds32/include/asm/pgtable.h:60:#include <asm/highmem.h>
> || arch/x86/kernel/setup_percpu.c:20:#include <asm/highmem.h>
> || include/linux/highmem.h:35:#include <asm/highmem.h>
> ||
> || Users of asm/cacheflush.h are rather more numerous; however, anything
> || outside of parisc-specific code has to pull linux/highmem.h, or it won't see
> || the definitions of kmap_atomic/kmap_atomic_prot at all. arch/parisc itself
> || has no callers of those.
> ||
> || Outside of arch/* there is a plenty of callers. However, the following is
> || true: all instances of kmap_atomic or kmap_atomic_prot outside of arch/*
> || are either inside the linux/highmem.h or are preceded by include of
> || linux/highmem.h on any build that sees them (there is a common include
> || chain that is conditional upon CONFIG_BLOCK, but it's only needed in
> || drivers that are BLOCK-dependent). It was not fun to verify, to put
> || it mildly...
> ||
> || So for parisc we have no problem - leaving __kmap_atomic()/__kmap_atomic_prot()
> || in asm/cachefile.h and adding universal wrappers in linux/highmem.h will be
> || fine. For other architectures the things might be trickier.
And the follow up series removes kmap_* from asm/cachefile.h in parisc which
should be cleaner going forward.
> ||
> || * arc: all users in arch/arc/ are within arch/arc/mm/{cache,highmem}.c;
> || both pull linux/highmem.h. We are fine.
Still fine.
> ||
> || * arm: much, much worse. We have several files that pull linux/highmem.h:
> || arch/arm/mm/cache-feroceon-l2.c, arch/arm/mm/cache-xsc3l2.c,
> || arch/arm/mm/copypage-*.c, arch/arm/mm/dma-mapping.c, arch/arm/mm/flush.c,
> || arch/arm/mm/highmem.c, arch/arm/probes/uprobes/core.c,
> || arch/arm/include/asm/kvm_mmu.h (kmap_atomic_pfn()).
> || Those are fine, but we also have this:
> || arch/arm/include/asm/pgtable.h:200:#define __pte_map(pmd) (pte_t *)kmap_atomic(pmd_page(*(pmd)))
> || arch/arm/include/asm/pgtable.h:208:#define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr))
> || and sure as hell, asm/pgtable.h does *NOT* pull linux/highmem.h.
It does not pull asm/highmem.h either...
> ||
> || Fortunately, the users of pte_offset_map() (__pte_map() has no other users)
> || are few, both in arch/arm and outside of arch. All arm ones are pulling
> || linux/highmem (arch/arm/mm/{pgd,fault*}.c). Outside of arch we have several
> || that pull highmem.h (by way of rmap.h or pagemap.h, usually):
> || fs/userfaultfd.c, mm/gup.c, mm/hmm.c, mm/huge_memory.c,
> || mm/khugepaged.c, mm/memory-failure.c, mm/memory.c, mm/migrate.c,
> || mm/mremap.c, mm/page_vma_mapped.c, mm/swap_state.c, mm/swapfile.c,
> || mm/vmalloc.c
> || and then there are these in linux/mm.h:
> ||
> || #define pte_offset_map_lock(mm, pmd, address, ptlp) \
> || ({ \
> || spinlock_t *__ptl = pte_lockptr(mm, pmd); \
> || pte_t *__pte = pte_offset_map(pmd, address); \
> || *(ptlp) = __ptl; \
> || spin_lock(__ptl); \
> || __pte; \
> || })
> || #define pte_alloc_map(mm, pmd, address) \
> || (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address))
> || #define pte_alloc_map_lock(mm, pmd, address, ptlp) \
> || (pte_alloc(mm, pmd) ? \
> || NULL : pte_offset_map_lock(mm, pmd, address, ptlp))
> ||
> || These have two users in arch/arm (arch/arm/mm/pgd.c and
> || arch/arm/lib/uaccess_with_memcpy.c, both pulling highmem.h). Outside of
> || arch there are several new files (plus a lot of what we'd already seen
> || in mm/*.c, unsurprisingly):
> || fs/proc/task_mmu.c, mm/ksm.c, mm/madvise.c, mm/memcontrol.c,
> || mm/mempolicy.c, mm/mincore.c, mm/mprotect.c, mm/pagewalk.c,
> || mm/shmem.c, mm/userfaultfd.c,
> || all pulling linux/highmem.h, as pretty much all core VM does. So we are
> || still fine.
This all seems the same now.
> ||
> || * csky: users in arch/csky/abiv2/cacheflush.c, arch/csky/mm/dma-mapping.c,
> || arch/csky/mm/highmem.c, all pulling linux/highmem.h
Yes still are.
> ||
> || * microblaze: users in arch/microblaze/mm/highmem.c (pulls linux/highmem.h) and,
> || arch/microblaze/include/asm/pgtable.h, this:
> || #define pte_offset_map(dir, addr) \
> || ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
> || One pte_offset_map user in arch/microblaze:
> || arch/microblaze/kernel/signal.c:207: ptep = pte_offset_map(pmdp, address);
> || Messy, but doesn't require any changes (we have asm/pgalloc.h included
> || there, and that pull linux/highmem.h).
AFAICS asm/pgtable.h does not include asm/highmem.h here...
So looks like arch/microblaze/kernel/signal.c will need linux/highmem.h
> || Outside of arch we'd already sorted it out when looking at arm.
> ||
> || * mips: users in arch/mips/kernel/crash_dump.c, arch/mips/kernel/uprobes.c,
> || arch/mips/mm/c-r4k.c, arch/mips/mm/dma-noncoherent.c, arch/mips/mm/highmem.c,
> || and arch/mips/mm/init.c (all pulling linux/highmem.h) plus this
> || arch/mips/mm/cache.c, which relies upon asm/highmem.h. This can be switched
> || to linux/highmem.h. On !CONFIG_HIGHMEM builds the call of kmap_atomic() in
> || there is eliminated, since it's conditional upon PageHighMem(). IOW, even
> || though we get a call of (inexistent) out-of-line version, it's not going to
> || survive into object file. With linux/highmem.h use it will be an equally
> || eliminated call of inlined version.
> || XXX: arch/mips/mm/cache.c
Fixed as part of this series.
> ||
> || * nds32: users in arch/nds32/kernel/dma.c, arch/nds32/mm/cacheflush.c and
> || arch/nds32/mm/highmem.c, all pulling linux/highmem.h
Still looks ok.
> ||
> || * powerpc: users in arch/powerpc/kvm/book3s_pr.c,
> || arch/powerpc/kvm/e500_mmu_host.c, arch/powerpc/mm/dma-noncoherent.c,
> || arch/powerpc/mm/highmem.c and arch/powerpc/mm/mem.c, all pulling
> || linux/highmem.h,
still good
> a user in arch/powerpc/mm/hugetlbpage.c pulling it
> || via asm/tlb.h -> linux/pagemap.h -> linux/highmem.h
good
> and
> || macros for pte_offset_map in arch/powerpc/include/asm/*/32/pgtable.h.
> || Users of that within arch/powerpc are either 64bit-only or
> || pull linux/highmem.h (arch/powerpc/mm/pgtable_32.c and
> || arch/powerpc/xmon/xmon.c).
>
Looks ok.
> || Users outside of arch - same as for arm.
> ||
> || * sparc: users in arch/sparc/kernel/uprobes.c and arch/sparc/mm/highmem.c
> || (both pulling linux/highmem.h directly) + arch/sparc/mm/init_64.c pulling
> || it via linux/pagemap.h.
Looks ok.
> Strangely, arch/sparc/mm/io-unit.c and
> || arch/sparc/mm/iommu.c both include linux/highmem.h with odd comment
> || that seems to indicate that once upon a time pte_offset_map() used to
> || requite kmap_atomic() there... Right, it used to - until 2002.
> || These includes are pointless, then...
Looks like it...
I'll throw in a patch for that.
> ||
> || * x86: users in arch/x86/kernel/crash_dump_32.c, arch/x86/kvm/svm.c,
> || arch/x86/lib/usercopy_64.c, arch/x86/mm/highmem_32.c and arch/x86/mm/iomap_32.c,
> || all pulling linux/highmem.h, users in paging_tmpl.h (included from
> || arch/x86/kvm/mmu/mmu.c, which has pulled linux/highmem.h prior to that)
> || and definition of pte_offset_map() (in asm/pgtable_32.h)
> || Users of pte_offset_map() and friends in arch/x86 are in
> || arch/x86/kernel/vm86_32.c and arch/x86/mm/dump_pagetables.c (both
> || pulling linux/highmem.h), in arch/x86/mm/mem_encrypt_identity.c
> || (64bit-only, pte_offset_map() doesn't use kmap_atomic() there) and
> || arch/x86/kernel/tboot.c (pulls linux/highmem.h via asm/pgalloc.h
> || and linux/pagemap.h)
I've built these and they seem fine.
> ||
> || * xtensa: users in arch/xtensa/kernel/pci-dma.c, arch/xtensa/mm/highmem.c,
> || arch/xtensa/mm/cache.c and arch/xtensa/platforms/iss/simdisk.c (all pull
> || linux/highmem.h).
Actually
arch/xtensa/mm/cache.c gets linux/highmem.h from linux/pagemap.h
arch/xtensa/platforms/iss/simdisk.c may have an issue?
linux/blkdev.h -> CONFIG_BLOCK -> linux/pagemap.h -> linux/highmem.h
But simdisk.c requires BLK_DEV_SIMDISK -> CONFIG_BLOCK...
<sigh>
So xtensa still seems good AFAICS.
In summary it looks like the use of kmap_atomic() in pte_offset_map() is a
potential issue in microblaze. I've fixed that in my local tree.
Ira
^ permalink raw reply
* Re: [PATCH V2 11/11] drm: Remove drm specific kmap_atomic code
From: Ira Weiny @ 2020-05-04 20:24 UTC (permalink / raw)
To: Daniel Vetter
Cc: Peter Zijlstra, Dave Hansen, dri-devel, linux-mips,
James E.J. Bottomley, Max Filippov, Huang Rui, Paul Mackerras,
H. Peter Anvin, sparclinux, Christoph Hellwig, Helge Deller,
X86 ML, linux-csky, Ingo Molnar, arcml, linux-xtensa,
Dan Williams, Borislav Petkov, Andy Lutomirski, Thomas Gleixner,
Linux ARM, Chris Zankel, Thomas Bogendoerfer, linux-parisc,
Linux Kernel Mailing List, David S. Miller, Andrew Morton,
linuxppc-dev, Christian Koenig
In-Reply-To: <CAKMK7uF4fd3upBYSQEzs==Nx7osn=wZPnxoKLKm9HTxwU_sZ+w@mail.gmail.com>
On Mon, May 04, 2020 at 01:18:51PM +0200, Daniel Vetter wrote:
> On Mon, May 4, 2020 at 3:09 AM <ira.weiny@intel.com> wrote:
> >
> > From: Ira Weiny <ira.weiny@intel.com>
> >
> > kmap_atomic_prot() is now exported by all architectures. Use this
> > function rather than open coding a driver specific kmap_atomic.
> >
> > Reviewed-by: Christian König <christian.koenig@amd.com>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > Signed-off-by: Ira Weiny <ira.weiny@intel.com>
>
> I'm assuming this lands through some other tree or a topic branch or whatever.
Yes I think Andrew queued this up before and so I hope he will continue to do
so with the subsequent versions.
Andrew, LMK if this is an issue.
Thanks,
Ira
>
> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
>
> Cheers, Daniel
>
> > ---
> > drivers/gpu/drm/ttm/ttm_bo_util.c | 56 ++--------------------------
> > drivers/gpu/drm/vmwgfx/vmwgfx_blit.c | 16 ++++----
> > include/drm/ttm/ttm_bo_api.h | 4 --
> > 3 files changed, 12 insertions(+), 64 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > index 52d2b71f1588..f09b096ba4fd 100644
> > --- a/drivers/gpu/drm/ttm/ttm_bo_util.c
> > +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
> > @@ -257,54 +257,6 @@ static int ttm_copy_io_page(void *dst, void *src, unsigned long page)
> > return 0;
> > }
> >
> > -#ifdef CONFIG_X86
> > -#define __ttm_kmap_atomic_prot(__page, __prot) kmap_atomic_prot(__page, __prot)
> > -#define __ttm_kunmap_atomic(__addr) kunmap_atomic(__addr)
> > -#else
> > -#define __ttm_kmap_atomic_prot(__page, __prot) vmap(&__page, 1, 0, __prot)
> > -#define __ttm_kunmap_atomic(__addr) vunmap(__addr)
> > -#endif
> > -
> > -
> > -/**
> > - * ttm_kmap_atomic_prot - Efficient kernel map of a single page with
> > - * specified page protection.
> > - *
> > - * @page: The page to map.
> > - * @prot: The page protection.
> > - *
> > - * This function maps a TTM page using the kmap_atomic api if available,
> > - * otherwise falls back to vmap. The user must make sure that the
> > - * specified page does not have an aliased mapping with a different caching
> > - * policy unless the architecture explicitly allows it. Also mapping and
> > - * unmapping using this api must be correctly nested. Unmapping should
> > - * occur in the reverse order of mapping.
> > - */
> > -void *ttm_kmap_atomic_prot(struct page *page, pgprot_t prot)
> > -{
> > - if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))
> > - return kmap_atomic(page);
> > - else
> > - return __ttm_kmap_atomic_prot(page, prot);
> > -}
> > -EXPORT_SYMBOL(ttm_kmap_atomic_prot);
> > -
> > -/**
> > - * ttm_kunmap_atomic_prot - Unmap a page that was mapped using
> > - * ttm_kmap_atomic_prot.
> > - *
> > - * @addr: The virtual address from the map.
> > - * @prot: The page protection.
> > - */
> > -void ttm_kunmap_atomic_prot(void *addr, pgprot_t prot)
> > -{
> > - if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))
> > - kunmap_atomic(addr);
> > - else
> > - __ttm_kunmap_atomic(addr);
> > -}
> > -EXPORT_SYMBOL(ttm_kunmap_atomic_prot);
> > -
> > static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src,
> > unsigned long page,
> > pgprot_t prot)
> > @@ -316,13 +268,13 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src,
> > return -ENOMEM;
> >
> > src = (void *)((unsigned long)src + (page << PAGE_SHIFT));
> > - dst = ttm_kmap_atomic_prot(d, prot);
> > + dst = kmap_atomic_prot(d, prot);
> > if (!dst)
> > return -ENOMEM;
> >
> > memcpy_fromio(dst, src, PAGE_SIZE);
> >
> > - ttm_kunmap_atomic_prot(dst, prot);
> > + kunmap_atomic(dst);
> >
> > return 0;
> > }
> > @@ -338,13 +290,13 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
> > return -ENOMEM;
> >
> > dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT));
> > - src = ttm_kmap_atomic_prot(s, prot);
> > + src = kmap_atomic_prot(s, prot);
> > if (!src)
> > return -ENOMEM;
> >
> > memcpy_toio(dst, src, PAGE_SIZE);
> >
> > - ttm_kunmap_atomic_prot(src, prot);
> > + kunmap_atomic(src);
> >
> > return 0;
> > }
> > diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
> > index bb46ca0c458f..94d456a1d1a9 100644
> > --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
> > +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
> > @@ -374,12 +374,12 @@ static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
> > copy_size = min_t(u32, copy_size, PAGE_SIZE - src_page_offset);
> >
> > if (unmap_src) {
> > - ttm_kunmap_atomic_prot(d->src_addr, d->src_prot);
> > + kunmap_atomic(d->src_addr);
> > d->src_addr = NULL;
> > }
> >
> > if (unmap_dst) {
> > - ttm_kunmap_atomic_prot(d->dst_addr, d->dst_prot);
> > + kunmap_atomic(d->dst_addr);
> > d->dst_addr = NULL;
> > }
> >
> > @@ -388,8 +388,8 @@ static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
> > return -EINVAL;
> >
> > d->dst_addr =
> > - ttm_kmap_atomic_prot(d->dst_pages[dst_page],
> > - d->dst_prot);
> > + kmap_atomic_prot(d->dst_pages[dst_page],
> > + d->dst_prot);
> > if (!d->dst_addr)
> > return -ENOMEM;
> >
> > @@ -401,8 +401,8 @@ static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
> > return -EINVAL;
> >
> > d->src_addr =
> > - ttm_kmap_atomic_prot(d->src_pages[src_page],
> > - d->src_prot);
> > + kmap_atomic_prot(d->src_pages[src_page],
> > + d->src_prot);
> > if (!d->src_addr)
> > return -ENOMEM;
> >
> > @@ -499,9 +499,9 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
> > }
> > out:
> > if (d.src_addr)
> > - ttm_kunmap_atomic_prot(d.src_addr, d.src_prot);
> > + kunmap_atomic(d.src_addr);
> > if (d.dst_addr)
> > - ttm_kunmap_atomic_prot(d.dst_addr, d.dst_prot);
> > + kunmap_atomic(d.dst_addr);
> >
> > return ret;
> > }
> > diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
> > index 0a9d042e075a..de1ccdcd5703 100644
> > --- a/include/drm/ttm/ttm_bo_api.h
> > +++ b/include/drm/ttm/ttm_bo_api.h
> > @@ -668,10 +668,6 @@ int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo);
> > int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
> > struct ttm_bo_device *bdev);
> >
> > -void *ttm_kmap_atomic_prot(struct page *page, pgprot_t prot);
> > -
> > -void ttm_kunmap_atomic_prot(void *addr, pgprot_t prot);
> > -
> > /**
> > * ttm_bo_io
> > *
> > --
> > 2.25.1
> >
> > _______________________________________________
> > dri-devel mailing list
> > dri-devel@lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/dri-devel
>
>
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> +41 (0) 79 365 57 48 - http://blog.ffwll.ch
^ permalink raw reply
* Re: [PATCH V2 00/11] Subject: Remove duplicated kmap code
From: Al Viro @ 2020-05-04 21:02 UTC (permalink / raw)
To: Ira Weiny
Cc: Peter Zijlstra, Dave Hansen, dri-devel, linux-mips,
James E.J. Bottomley, Max Filippov, Huang Rui, Paul Mackerras,
H. Peter Anvin, sparclinux, Dan Williams, Helge Deller, x86,
linux-csky, Ingo Molnar, linux-snps-arc, linux-xtensa,
Borislav Petkov, Andy Lutomirski, Thomas Gleixner,
linux-arm-kernel, Chris Zankel, Thomas Bogendoerfer, linux-parisc,
linux-kernel, Christian Koenig, Andrew Morton, linuxppc-dev,
David S. Miller
In-Reply-To: <20200504201740.GA985739@iweiny-DESK2.sc.intel.com>
On Mon, May 04, 2020 at 01:17:41PM -0700, Ira Weiny wrote:
> > || * arm: much, much worse. We have several files that pull linux/highmem.h:
> > || arch/arm/mm/cache-feroceon-l2.c, arch/arm/mm/cache-xsc3l2.c,
> > || arch/arm/mm/copypage-*.c, arch/arm/mm/dma-mapping.c, arch/arm/mm/flush.c,
> > || arch/arm/mm/highmem.c, arch/arm/probes/uprobes/core.c,
> > || arch/arm/include/asm/kvm_mmu.h (kmap_atomic_pfn()).
> > || Those are fine, but we also have this:
> > || arch/arm/include/asm/pgtable.h:200:#define __pte_map(pmd) (pte_t *)kmap_atomic(pmd_page(*(pmd)))
> > || arch/arm/include/asm/pgtable.h:208:#define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr))
> > || and sure as hell, asm/pgtable.h does *NOT* pull linux/highmem.h.
>
> It does not pull asm/highmem.h either...
No, but the users of those macros need to be considered.
> > || #define pte_offset_map(dir, addr) \
> > || ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
> > || One pte_offset_map user in arch/microblaze:
> > || arch/microblaze/kernel/signal.c:207: ptep = pte_offset_map(pmdp, address);
> > || Messy, but doesn't require any changes (we have asm/pgalloc.h included
> > || there, and that pull linux/highmem.h).
>
> AFAICS asm/pgtable.h does not include asm/highmem.h here...
>
> So looks like arch/microblaze/kernel/signal.c will need linux/highmem.h
See above - line 39 in there is
#include <asm/pgalloc.h>
and line 14 in arch/microblaze/include/asm/pgalloc.h is
#include <linux/highmem.h>
It's conditional upon CONFIG_MMU in there, but so's the use of
pte_offset_map() in arch/microblaze/kernel/signal.c
So it shouldn't be a problem.
> > || * xtensa: users in arch/xtensa/kernel/pci-dma.c, arch/xtensa/mm/highmem.c,
> > || arch/xtensa/mm/cache.c and arch/xtensa/platforms/iss/simdisk.c (all pull
> > || linux/highmem.h).
>
> Actually
>
> arch/xtensa/mm/cache.c gets linux/highmem.h from linux/pagemap.h
>
> arch/xtensa/platforms/iss/simdisk.c may have an issue?
> linux/blkdev.h -> CONFIG_BLOCK -> linux/pagemap.h -> linux/highmem.h
> But simdisk.c requires BLK_DEV_SIMDISK -> CONFIG_BLOCK...
> <sigh>
Yep - see above re major chain of indirect includes conditional upon CONFIG_BLOCK
and its uses in places that only build with such configs. There's a plenty of
similar considerations outside of arch/*, unfortunately...
^ permalink raw reply
* Re: [PATCH v2 0/5] Statsfs: a new ram-based file sytem for Linux kernel statistics
From: David Rientjes @ 2020-05-04 21:37 UTC (permalink / raw)
To: Emanuele Giuseppe Esposito, Jonathan Adams
Cc: linux-s390, kvm, David Hildenbrand, Cornelia Huck,
Emanuele Giuseppe Esposito, linux-kernel, kvm-ppc, linux-mips,
Christian Borntraeger, Alexander Viro, linux-fsdevel,
Paolo Bonzini, Vitaly Kuznetsov, linuxppc-dev, Jim Mattson
In-Reply-To: <20200504110344.17560-1-eesposit@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 8664 bytes --]
On Mon, 4 May 2020, Emanuele Giuseppe Esposito wrote:
> There is currently no common way for Linux kernel subsystems to expose
> statistics to userspace shared throughout the Linux kernel; subsystems
> have to take care of gathering and displaying statistics by themselves,
> for example in the form of files in debugfs. For example KVM has its own
> code section that takes care of this in virt/kvm/kvm_main.c, where it sets
> up debugfs handlers for displaying values and aggregating them from
> various subfolders to obtain information about the system state (i.e.
> displaying the total number of exits, calculated by summing all exits of
> all cpus of all running virtual machines).
>
> Allowing each section of the kernel to do so has two disadvantages. First,
> it will introduce redundant code. Second, debugfs is anyway not the right
> place for statistics (for example it is affected by lockdown)
>
> In this patch series I introduce statsfs, a synthetic ram-based virtual
> filesystem that takes care of gathering and displaying statistics for the
> Linux kernel subsystems.
>
This is exciting, we have been looking in the same area recently. Adding
Jonathan Adams <jwadams@google.com>.
In your diffstat, one thing I notice that is omitted: an update to
Documentation/* :) Any chance of getting some proposed Documentation/
updates with structure of the fs, the per subsystem breakdown, and best
practices for managing the stats from the kernel level?
> The file system is mounted on /sys/kernel/stats and would be already used
> by kvm. Statsfs was initially introduced by Paolo Bonzini [1].
>
> Statsfs offers a generic and stable API, allowing any kind of
> directory/file organization and supporting multiple kind of aggregations
> (not only sum, but also average, max, min and count_zero) and data types
> (all unsigned and signed types plus boolean). The implementation, which is
> a generalization of KVM’s debugfs statistics code, takes care of gathering
> and displaying information at run time; users only need to specify the
> values to be included in each source.
>
> Statsfs would also be a different mountpoint from debugfs, and would not
> suffer from limited access due to the security lock down patches. Its main
> function is to display each statistics as a file in the desired folder
> hierarchy defined through the API. Statsfs files can be read, and possibly
> cleared if their file mode allows it.
>
> Statsfs has two main components: the public API defined by
> include/linux/statsfs.h, and the virtual file system which should end up
> in /sys/kernel/stats.
>
> The API has two main elements, values and sources. Kernel subsystems like
> KVM can use the API to create a source, add child
> sources/values/aggregates and register it to the root source (that on the
> virtual fs would be /sys/kernel/statsfs).
>
> Sources are created via statsfs_source_create(), and each source becomes a
> directory in the file system. Sources form a parent-child relationship;
> root sources are added to the file system via statsfs_source_register().
> Every other source is added to or removed from a parent through the
> statsfs_source_add_subordinate and statsfs_source_remote_subordinate APIs.
> Once a source is created and added to the tree (via add_subordinate), it
> will be used to compute aggregate values in the parent source.
>
> Values represent quantites that are gathered by the statsfs user. Examples
> of values include the number of vm exits of a given kind, the amount of
> memory used by some data structure, the length of the longest hash table
> chain, or anything like that. Values are defined with the
> statsfs_source_add_values function. Each value is defined by a struct
> statsfs_value; the same statsfs_value can be added to many different
> sources. A value can be considered "simple" if it fetches data from a
> user-provided location, or "aggregate" if it groups all values in the
> subordinates sources that include the same statsfs_value.
>
This seems like it could have a lot of overhead if we wanted to
periodically track the totality of subsystem stats as a form of telemetry
gathering from userspace. To collect telemetry for 1,000 different stats,
do we need to issue lseek()+read() syscalls for each of them individually
(or, worse, open()+read()+close())?
Any thoughts on how that can be optimized? A couple of ideas:
- an interface that allows gathering of all stats for a particular
interface through a single file that would likely be encoded in binary
and the responsibility of userspace to disseminate, or
- an interface that extends beyond this proposal and allows the reader to
specify which stats they are interested in collecting and then the
kernel will only provide these stats in a well formed structure and
also be binary encoded.
We've found that the one-file-per-stat method is pretty much a show
stopper from the performance view and we always must execute at least two
syscalls to obtain a single stat.
Since this is becoming a generic API (good!!), maybe we can discuss
possible ways to optimize gathering of stats in mass?
> For more information, please consult the kerneldoc documentation in patch
> 2 and the sample uses in the kunit tests and in KVM.
>
> This series of patches is based on my previous series "libfs: group and
> simplify linux fs code" and the single patch sent to kvm "kvm_host: unify
> VM_STAT and VCPU_STAT definitions in a single place". The former
> simplifies code duplicated in debugfs and tracefs (from which statsfs is
> based on), the latter groups all macros definition for statistics in kvm
> in a single common file shared by all architectures.
>
> Patch 1 adds a new refcount and kref destructor wrappers that take a
> semaphore, as those are used later by statsfs. Patch 2 introduces the
> statsfs API, patch 3 provides extensive tests that can also be used as
> example on how to use the API and patch 4 adds the file system support.
> Finally, patch 5 provides a real-life example of statsfs usage in KVM.
>
> [1] https://lore.kernel.org/kvm/5d6cdcb1-d8ad-7ae6-7351-3544e2fa366d@redhat.com/?fbclid=IwAR18LHJ0PBcXcDaLzILFhHsl3qpT3z2vlG60RnqgbpGYhDv7L43n0ZXJY8M
>
> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
>
> v1->v2 remove unnecessary list_foreach_safe loops, fix wrong indentation,
> change statsfs in stats_fs
>
> Emanuele Giuseppe Esposito (5):
> refcount, kref: add dec-and-test wrappers for rw_semaphores
> stats_fs API: create, add and remove stats_fs sources and values
> kunit: tests for stats_fs API
> stats_fs fs: virtual fs to show stats to the end-user
> kvm_main: replace debugfs with stats_fs
>
> MAINTAINERS | 7 +
> arch/arm64/kvm/Kconfig | 1 +
> arch/arm64/kvm/guest.c | 2 +-
> arch/mips/kvm/Kconfig | 1 +
> arch/mips/kvm/mips.c | 2 +-
> arch/powerpc/kvm/Kconfig | 1 +
> arch/powerpc/kvm/book3s.c | 6 +-
> arch/powerpc/kvm/booke.c | 8 +-
> arch/s390/kvm/Kconfig | 1 +
> arch/s390/kvm/kvm-s390.c | 16 +-
> arch/x86/include/asm/kvm_host.h | 2 +-
> arch/x86/kvm/Kconfig | 1 +
> arch/x86/kvm/Makefile | 2 +-
> arch/x86/kvm/debugfs.c | 64 --
> arch/x86/kvm/stats_fs.c | 56 ++
> arch/x86/kvm/x86.c | 6 +-
> fs/Kconfig | 12 +
> fs/Makefile | 1 +
> fs/stats_fs/Makefile | 6 +
> fs/stats_fs/inode.c | 337 ++++++++++
> fs/stats_fs/internal.h | 35 +
> fs/stats_fs/stats_fs-tests.c | 1088 +++++++++++++++++++++++++++++++
> fs/stats_fs/stats_fs.c | 773 ++++++++++++++++++++++
> include/linux/kref.h | 11 +
> include/linux/kvm_host.h | 39 +-
> include/linux/refcount.h | 2 +
> include/linux/stats_fs.h | 304 +++++++++
> include/uapi/linux/magic.h | 1 +
> lib/refcount.c | 32 +
> tools/lib/api/fs/fs.c | 21 +
> virt/kvm/arm/arm.c | 2 +-
> virt/kvm/kvm_main.c | 314 ++-------
> 32 files changed, 2772 insertions(+), 382 deletions(-)
> delete mode 100644 arch/x86/kvm/debugfs.c
> create mode 100644 arch/x86/kvm/stats_fs.c
> create mode 100644 fs/stats_fs/Makefile
> create mode 100644 fs/stats_fs/inode.c
> create mode 100644 fs/stats_fs/internal.h
> create mode 100644 fs/stats_fs/stats_fs-tests.c
> create mode 100644 fs/stats_fs/stats_fs.c
> create mode 100644 include/linux/stats_fs.h
>
> --
> 2.25.2
>
>
^ permalink raw reply
* Re: [PATCH 1/3] ASoC: fsl_esai: introduce SoC specific data
From: Nicolin Chen @ 2020-05-04 21:39 UTC (permalink / raw)
To: Shengjiu Wang
Cc: devicetree, alsa-devel, timur, Xiubo.Lee, lgirdwood, linuxppc-dev,
tiwai, robh+dt, perex, broonie, festevam, linux-kernel
In-Reply-To: <27af074e47bf2b81e2dce67ea66a9f7301dfcb07.1588320656.git.shengjiu.wang@nxp.com>
On Fri, May 01, 2020 at 04:12:04PM +0800, Shengjiu Wang wrote:
> Introduce a SoC specific data structure which contains the
> differences between the different SoCs.
> This makes it easier to support more differences without having
> to introduce a new if/else each time.
>
> Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Though the 2nd patch is having comments to address, this one
looks fine to me and should be able to merge as long as Mark
is okay with this too:
Acked-by: Nicolin Chen <nicoleotsuka@gmail.com>
^ permalink raw reply
* [RFC][PATCH 1/2] Add a layer of abstraction to use the memory reserved by device tree for ima buffer pass.
From: Prakhar Srivastava @ 2020-05-04 20:38 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel, linuxppc-dev, devicetree,
linux-integrity, linux-security-module
Cc: kstewart, mark.rutland, catalin.marinas, bhsharma, tao.li, zohar,
paulus, vincenzo.frascino, frowand.list, nramas, masahiroy,
jmorris, takahiro.akashi, serge, pasha.tatashin, will, prsriva,
robh+dt, hsinyi, tusharsu, tglx, allison, mbrugger, balajib,
dmitry.kasatkin, james.morse, gregkh
In-Reply-To: <20200504203829.6330-1-prsriva@linux.microsoft.com>
Introduce a device tree layer for to read and store ima buffer
from the reserved memory section of a device tree.
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
---
drivers/of/Kconfig | 6 ++
drivers/of/Makefile | 1 +
drivers/of/of_ima.c | 165 ++++++++++++++++++++++++++++++++++++++++++++
include/linux/of.h | 34 +++++++++
4 files changed, 206 insertions(+)
create mode 100644 drivers/of/of_ima.c
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index d91618641be6..edb3c39740fb 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -107,4 +107,10 @@ config OF_DMA_DEFAULT_COHERENT
# arches should select this if DMA is coherent by default for OF devices
bool
+config OF_IMA
+ def_bool y
+ help
+ IMA related wrapper functions to add/remove ima measurement logs during
+ kexec_file_load call.
+
endif # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 663a4af0cccd..b4caf083df4e 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -14,5 +14,6 @@ obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
obj-$(CONFIG_OF_RESOLVE) += resolver.o
obj-$(CONFIG_OF_OVERLAY) += overlay.o
obj-$(CONFIG_OF_NUMA) += of_numa.o
+obj-$(CONFIG_OF_IMA) += of_ima.o
obj-$(CONFIG_OF_UNITTEST) += unittest-data/
diff --git a/drivers/of/of_ima.c b/drivers/of/of_ima.c
new file mode 100644
index 000000000000..131f68d81e2e
--- /dev/null
+++ b/drivers/of/of_ima.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Microsoft Corporation.
+ */
+
+#include <linux/slab.h>
+#include <linux/kexec.h>
+#include <linux/of.h>
+#include <linux/memblock.h>
+#include <linux/libfdt.h>
+#include <linux/of_address.h>
+
+static bool dtb_status_enabled;
+static struct resource mem_res;
+static void *vaddr;
+
+
+/**
+ * of_is_ima_memory_reserved - check if memory is reserved via device
+ * tree.
+ * Return: zero when memory is not reserved.
+ * positive number on success.
+ *
+ */
+int of_is_ima_memory_reserved(void)
+{
+ return dtb_status_enabled;
+}
+
+/**
+ * of_ima_write_buffer - Write the ima buffer into the reserved memory.
+ *
+ * ima_buffer - buffer starting address.
+ * ima_buffer_size - size of segment.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int of_ima_write_buffer(void *ima_buffer, size_t ima_buffer_size)
+{
+ void *addr;
+
+ if (!dtb_status_enabled)
+ return -EOPNOTSUPP;
+
+ vaddr = memremap(mem_res.start, resource_size(&mem_res), MEMREMAP_WB);
+ pr_info("Mapped reserved memory, vaddr: 0x%0llX, paddr: 0x%0llX\n , size : %lld",
+ (u64)vaddr, mem_res.start, resource_size(&mem_res));
+
+ if (vaddr) {
+ memcpy(vaddr, &ima_buffer_size, sizeof(size_t));
+ addr = vaddr + sizeof(size_t);
+ memcpy(addr, ima_buffer, ima_buffer_size);
+ memunmap(vaddr);
+ vaddr = NULL;
+ }
+
+ return 0;
+}
+
+/**
+ * of_remove_ima_buffer - Write 0(Zero length buffer to read)to the
+ * size location of the buffer.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int of_remove_ima_buffer(void)
+{
+ size_t empty_buffer_size = 0;
+
+ if (!dtb_status_enabled)
+ return -ENOTSUPP;
+
+ if (vaddr) {
+ memcpy(vaddr, &empty_buffer_size, sizeof(size_t));
+ memunmap(vaddr);
+ vaddr = NULL;
+ }
+
+ return 0;
+}
+
+/**
+ * of_ima_get_size_allocated - Get the usable buffer size thats allocated in
+ * the device-tree.
+ *
+ * Return: 0 on unavailable node, size of the memory block - (size_t)
+ */
+size_t of_ima_get_size_allocated(void)
+{
+ size_t size = 0;
+
+ if (!dtb_status_enabled)
+ return size;
+
+ size = resource_size(&mem_res) - sizeof(size_t);
+ return size;
+}
+
+/**
+ * of_get_ima_buffer - Get IMA buffer address.
+ *
+ * @addr: On successful return, set to point to the buffer contents.
+ * @size: On successful return, set to the buffer size.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int of_get_ima_buffer(void **addr, size_t *size)
+{
+ if (!dtb_status_enabled)
+ return -ENOTSUPP;
+
+ vaddr = memremap(mem_res.start, resource_size(&mem_res), MEMREMAP_WB);
+ pr_info("Mapped reserved memory, vaddr: 0x%0llX, paddr: 0x%0llX,\n allocated size : %lld, ima_buffer_size: %ld ",
+ (u64)vaddr, mem_res.start, resource_size(&mem_res), *(size_t *)vaddr);
+
+ *size = *(size_t *)vaddr;
+ *addr = vaddr + sizeof(size_t);
+ return 0;
+}
+
+static const struct of_device_id ima_buffer_pass_ids[] = {
+ {
+ .compatible = "linux,ima_buffer_pass",
+ },
+ {}
+};
+
+static const struct of_device_id ima_buffer_pass_match[] = {
+ {
+ .name = "ima_buffer_pass",
+ },
+};
+MODULE_DEVICE_TABLE(of, ima_buffer_pass_match);
+
+static int __init ima_buffer_pass_init(void)
+{
+ int ret = 0;
+ struct device_node *memnp;
+ struct device_node *ima_buffer_pass_node;
+
+ ima_buffer_pass_node = of_find_matching_node(NULL, ima_buffer_pass_ids);
+ if (!ima_buffer_pass_node)
+ return -ENOENT;
+
+ memnp = of_parse_phandle(ima_buffer_pass_node, "memory-region", 0);
+ if (!memnp)
+ return -ENXIO;
+
+ ret = of_address_to_resource(memnp, 0, &mem_res);
+ if (ret < 0)
+ return -ENOENT;
+
+ of_node_put(memnp);
+ dtb_status_enabled = true;
+
+ return ret;
+}
+
+static void __exit ima_buffer_pass_exit(void)
+{
+ pr_info("trying to exit the ima driver\n");
+}
+
+module_init(ima_buffer_pass_init);
+module_exit(ima_buffer_pass_exit);
diff --git a/include/linux/of.h b/include/linux/of.h
index c669c0a4732f..85ce2f24024f 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1485,4 +1485,38 @@ static inline int of_overlay_notifier_unregister(struct notifier_block *nb)
#endif
+#ifdef CONFIG_OF_IMA
+int of_is_ima_memory_reserved(void);
+int of_remove_ima_buffer(void);
+int of_get_ima_buffer(void **addr, size_t *size);
+size_t of_ima_get_size_allocated(void);
+int of_ima_write_buffer(void *ima_buffer,
+ size_t ima_buffer_size);
+#else
+static inline int of_is_ima_memory_reserved(void)
+{
+ return -ENOTSUPP;
+};
+static inline int of_remove_ima_buffer(void)
+{
+ return -ENOTSUPP;
+};
+
+static inline int of_get_ima_buffer(void **addr, size_t *size)
+{
+ return -ENOTSUPP;
+};
+
+static inline size_t of_ima_get_size_allocated(void)
+{
+ return 0;
+};
+
+static inline int of_ima_write_buffer(void *ima_buffer,
+ size_t ima_buffer_size)
+{
+ return -ENOTSUPP;
+};
+#endif
+
#endif /* _LINUX_OF_H */
--
2.25.1
^ permalink raw reply related
* [RFC][PATCH 0/2] Add support for using reserved memory for ima buffer pass
From: Prakhar Srivastava @ 2020-05-04 20:38 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel, linuxppc-dev, devicetree,
linux-integrity, linux-security-module
Cc: kstewart, mark.rutland, catalin.marinas, bhsharma, tao.li, zohar,
paulus, vincenzo.frascino, frowand.list, nramas, masahiroy,
jmorris, takahiro.akashi, serge, pasha.tatashin, will, prsriva,
robh+dt, hsinyi, tusharsu, tglx, allison, mbrugger, balajib,
dmitry.kasatkin, james.morse, gregkh
IMA during kexec(kexec file load) verifies the kernel signature and measures
the signature of the kernel. The signature in the logs can be used to verfiy the
authenticity of the kernel. The logs don not get carried over kexec and thus
remote attesation cannot verify the signature of the running kernel.
Introduce an ABI to carry forward the ima logs over kexec.
Memory reserved via device tree reservation can be used to store and read
via the of_* functions.
Reserved memory stores the size(sizeof(size_t)) of the buffer in the starting
address, followed by the IMA log contents.
Tested on:
arm64 with Uboot
Prakhar Srivastava (2):
Add a layer of abstraction to use the memory reserved by device tree
for ima buffer pass.
Add support for ima buffer pass using reserved memory for arm64 kexec.
Update the arch sepcific code path in kexec file load to store the
ima buffer in the reserved memory. The same reserved memory is read
on kexec or cold boot.
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/ima.h | 22 ++++
arch/arm64/include/asm/kexec.h | 5 +
arch/arm64/kernel/Makefile | 1 +
arch/arm64/kernel/ima_kexec.c | 64 ++++++++++
arch/arm64/kernel/machine_kexec_file.c | 1 +
arch/powerpc/include/asm/ima.h | 3 +-
arch/powerpc/kexec/ima.c | 14 ++-
drivers/of/Kconfig | 6 +
drivers/of/Makefile | 1 +
drivers/of/of_ima.c | 165 +++++++++++++++++++++++++
include/linux/of.h | 34 +++++
security/integrity/ima/ima_kexec.c | 15 ++-
13 files changed, 325 insertions(+), 7 deletions(-)
create mode 100644 arch/arm64/include/asm/ima.h
create mode 100644 arch/arm64/kernel/ima_kexec.c
create mode 100644 drivers/of/of_ima.c
--
2.25.1
^ permalink raw reply
* [RFC][PATCH 2/2] Add support for ima buffer pass using reserved memory arm64
From: Prakhar Srivastava @ 2020-05-04 20:38 UTC (permalink / raw)
To: linux-arm-kernel, linux-kernel, linuxppc-dev, devicetree,
linux-integrity, linux-security-module
Cc: kstewart, mark.rutland, catalin.marinas, bhsharma, tao.li, zohar,
paulus, vincenzo.frascino, frowand.list, nramas, masahiroy,
jmorris, takahiro.akashi, serge, pasha.tatashin, will, prsriva,
robh+dt, hsinyi, tusharsu, tglx, allison, mbrugger, balajib,
dmitry.kasatkin, james.morse, gregkh
In-Reply-To: <20200504203829.6330-1-prsriva@linux.microsoft.com>
Add support for ima buffer pass using reserved memory for
arm64 kexec. Update the arch sepcific code path in kexec file load to store
the ima buffer in the reserved memory. The same reserved memory is read on
kexec or cold boot.
Signed-off-by: Prakhar Srivastava <prsriva@linux.microsoft.com>
---
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/ima.h | 22 +++++++++
arch/arm64/include/asm/kexec.h | 5 ++
arch/arm64/kernel/Makefile | 1 +
arch/arm64/kernel/ima_kexec.c | 64 ++++++++++++++++++++++++++
arch/arm64/kernel/machine_kexec_file.c | 1 +
arch/powerpc/include/asm/ima.h | 3 +-
arch/powerpc/kexec/ima.c | 14 +++++-
security/integrity/ima/ima_kexec.c | 15 ++++--
9 files changed, 119 insertions(+), 7 deletions(-)
create mode 100644 arch/arm64/include/asm/ima.h
create mode 100644 arch/arm64/kernel/ima_kexec.c
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 40fb05d96c60..bc9e1a91686b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1069,6 +1069,7 @@ config KEXEC
config KEXEC_FILE
bool "kexec file based system call"
select KEXEC_CORE
+ select HAVE_IMA_KEXEC
help
This is new version of kexec system call. This system call is
file based and takes file descriptors as system call argument
diff --git a/arch/arm64/include/asm/ima.h b/arch/arm64/include/asm/ima.h
new file mode 100644
index 000000000000..58033b427e59
--- /dev/null
+++ b/arch/arm64/include/asm/ima.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_IMA_H
+#define _ASM_ARM64_IMA_H
+
+struct kimage;
+
+int is_ima_memory_reserved(void);
+int ima_get_kexec_buffer(void **addr, size_t *size);
+int ima_free_kexec_buffer(void);
+
+#ifdef CONFIG_IMA_KEXEC
+int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
+ void *buffer, size_t size);
+
+#else
+int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
+ void *buffer, size_t size)
+{
+ return 0;
+}
+#endif /* CONFIG_IMA_KEXEC */
+#endif /* _ASM_ARM64_IMA_H */
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index d24b527e8c00..2bd19ccb6c43 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -100,6 +100,11 @@ struct kimage_arch {
void *elf_headers;
unsigned long elf_headers_mem;
unsigned long elf_headers_sz;
+
+#ifdef CONFIG_IMA_KEXEC
+ phys_addr_t ima_buffer_addr;
+ size_t ima_buffer_size;
+#endif
};
extern const struct kexec_file_ops kexec_image_ops;
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 4e5b8ee31442..cd3cb7690d51 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o
obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \
cpu-reset.o
+obj-$(CONFIG_HAVE_IMA_KEXEC) += ima_kexec.o
obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o
obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o
arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
diff --git a/arch/arm64/kernel/ima_kexec.c b/arch/arm64/kernel/ima_kexec.c
new file mode 100644
index 000000000000..ff5649333c7c
--- /dev/null
+++ b/arch/arm64/kernel/ima_kexec.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Microsoft Corporation.
+ *
+ * Authors:
+ * Prakhar Srivastava <prsriva@linux.microsoft.com>
+ */
+
+#include <linux/kexec.h>
+#include <linux/of.h>
+
+
+/**
+ * is_ima_memory_reserved - check if memory is reserved via device
+ * tree.
+ * Return: negative or zero when memory is not reserved.
+ * positive number on success.
+ *
+ */
+int is_ima_memory_reserved(void)
+{
+ return of_is_ima_memory_reserved();
+}
+
+/**
+ * ima_get_kexec_buffer - get IMA buffer from the previous kernel
+ * @addr: On successful return, set to point to the buffer contents.
+ * @size: On successful return, set to the buffer size.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int ima_get_kexec_buffer(void **addr, size_t *size)
+{
+ return of_get_ima_buffer(addr, size);
+}
+
+/**
+ * ima_free_kexec_buffer - free memory used by the IMA buffer
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int ima_free_kexec_buffer(void)
+{
+ return of_remove_ima_buffer();
+}
+
+#ifdef CONFIG_IMA_KEXEC
+/**
+ * arch_ima_add_kexec_buffer - do arch-specific steps to add the IMA
+ * measurement log.
+ * @image: - pointer to the kimage, to store the address and size of the
+ * IMA measurement log.
+ * @load_addr: - the address where the IMA measurement log is stored.
+ * @size - size of the IMA measurement log.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
+ void *buffer, size_t size)
+{
+ of_ima_write_buffer(buffer, size);
+ return 0;
+}
+#endif /* CONFIG_IMA_KEXEC */
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index b40c3b0def92..8dc25511142d 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -22,6 +22,7 @@
#include <linux/types.h>
#include <linux/vmalloc.h>
#include <asm/byteorder.h>
+#include <asm/ima.h>
/* relevant device tree properties */
#define FDT_PROP_KEXEC_ELFHDR "linux,elfcorehdr"
diff --git a/arch/powerpc/include/asm/ima.h b/arch/powerpc/include/asm/ima.h
index ead488cf3981..a8febc620b42 100644
--- a/arch/powerpc/include/asm/ima.h
+++ b/arch/powerpc/include/asm/ima.h
@@ -4,6 +4,7 @@
struct kimage;
+int is_ima_memory_reserved(void);
int ima_get_kexec_buffer(void **addr, size_t *size);
int ima_free_kexec_buffer(void);
@@ -15,7 +16,7 @@ static inline void remove_ima_buffer(void *fdt, int chosen_node) {}
#ifdef CONFIG_IMA_KEXEC
int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
- size_t size);
+ void *buffer, size_t size);
int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node);
#else
diff --git a/arch/powerpc/kexec/ima.c b/arch/powerpc/kexec/ima.c
index 720e50e490b6..3823539d4e07 100644
--- a/arch/powerpc/kexec/ima.c
+++ b/arch/powerpc/kexec/ima.c
@@ -46,6 +46,18 @@ static int do_get_kexec_buffer(const void *prop, int len, unsigned long *addr,
return 0;
}
+/**
+ * is_ima_memory_reserved - check if memory is reserved via device
+ * tree.
+ * Return: negative or zero when memory is not reserved.
+ * positive number on success.
+ *
+ */
+int is_ima_memory_reserved(void)
+{
+ return -EOPNOTSUPP;
+}
+
/**
* ima_get_kexec_buffer - get IMA buffer from the previous kernel
* @addr: On successful return, set to point to the buffer contents.
@@ -137,7 +149,7 @@ void remove_ima_buffer(void *fdt, int chosen_node)
* Return: 0 on success, negative errno on error.
*/
int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
- size_t size)
+ void *buffer, size_t size)
{
image->arch.ima_buffer_addr = load_addr;
image->arch.ima_buffer_size = size;
diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c
index 121de3e04af2..3749472c7e18 100644
--- a/security/integrity/ima/ima_kexec.c
+++ b/security/integrity/ima/ima_kexec.c
@@ -116,13 +116,18 @@ void ima_add_kexec_buffer(struct kimage *image)
kbuf.buffer = kexec_buffer;
kbuf.bufsz = kexec_buffer_size;
kbuf.memsz = kexec_segment_size;
- ret = kexec_add_buffer(&kbuf);
- if (ret) {
- pr_err("Error passing over kexec measurement buffer.\n");
- return;
+
+ if (!is_ima_memory_reserved()) {
+
+ ret = kexec_add_buffer(&kbuf);
+ if (ret) {
+ pr_err("Error passing over kexec measurement buffer.\n");
+ return;
+ }
}
- ret = arch_ima_add_kexec_buffer(image, kbuf.mem, kexec_segment_size);
+ ret = arch_ima_add_kexec_buffer(image, kbuf.mem, kexec_buffer,
+ kexec_segment_size);
if (ret) {
pr_err("Error passing over kexec measurement buffer.\n");
return;
--
2.25.1
^ permalink raw reply related
* [powerpc:next] BUILD SUCCESS 140777a3d8dfdb3d3f20ea7707c0f1c0ce1b0aa5
From: kbuild test robot @ 2020-05-04 22:02 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
branch HEAD: 140777a3d8dfdb3d3f20ea7707c0f1c0ce1b0aa5 powerpc/fadump: consider reserved ranges while reserving memory
elapsed time: 481m
configs tested: 205
configs skipped: 0
The following configs have been built successfully.
More configs may be tested in the coming days.
arm64 allyesconfig
arm allyesconfig
arm64 allmodconfig
arm allmodconfig
arm64 allnoconfig
arm allnoconfig
arm efm32_defconfig
arm at91_dt_defconfig
arm shmobile_defconfig
arm64 defconfig
arm exynos_defconfig
arm multi_v5_defconfig
arm sunxi_defconfig
arm multi_v7_defconfig
sparc allyesconfig
ia64 generic_defconfig
riscv allnoconfig
parisc allmodconfig
parisc allnoconfig
powerpc holly_defconfig
s390 allmodconfig
s390 debug_defconfig
ia64 allyesconfig
i386 allnoconfig
i386 allyesconfig
i386 alldefconfig
i386 defconfig
i386 debian-10.3
ia64 allmodconfig
ia64 defconfig
ia64 allnoconfig
ia64 tiger_defconfig
ia64 bigsur_defconfig
ia64 alldefconfig
m68k m5475evb_defconfig
m68k allmodconfig
m68k bvme6000_defconfig
m68k sun3_defconfig
m68k multi_defconfig
nios2 3c120_defconfig
nios2 10m50_defconfig
c6x evmc6678_defconfig
c6x allyesconfig
openrisc simple_smp_defconfig
openrisc or1ksim_defconfig
nds32 defconfig
nds32 allnoconfig
csky defconfig
alpha defconfig
h8300 h8s-sim_defconfig
h8300 edosk2674_defconfig
xtensa iss_defconfig
h8300 h8300h-sim_defconfig
xtensa common_defconfig
arc defconfig
arc allyesconfig
microblaze mmu_defconfig
microblaze nommu_defconfig
mips fuloong2e_defconfig
mips malta_kvm_defconfig
mips ar7_defconfig
mips allyesconfig
mips 64r6el_defconfig
mips allnoconfig
mips 32r2_defconfig
mips allmodconfig
mips malta_kvm_guest_defconfig
mips tb0287_defconfig
mips capcella_defconfig
mips ip32_defconfig
mips decstation_64_defconfig
mips loongson3_defconfig
mips ath79_defconfig
mips bcm63xx_defconfig
parisc generic-64bit_defconfig
parisc generic-32bit_defconfig
parisc allyesconfig
powerpc chrp32_defconfig
powerpc defconfig
powerpc ppc64_defconfig
powerpc rhel-kconfig
powerpc allnoconfig
powerpc mpc866_ads_defconfig
powerpc amigaone_defconfig
powerpc adder875_defconfig
powerpc ep8248e_defconfig
powerpc g5_defconfig
powerpc mpc512x_defconfig
m68k randconfig-a001-20200505
mips randconfig-a001-20200505
nds32 randconfig-a001-20200505
parisc randconfig-a001-20200505
alpha randconfig-a001-20200505
riscv randconfig-a001-20200505
m68k randconfig-a001-20200503
mips randconfig-a001-20200503
nds32 randconfig-a001-20200503
alpha randconfig-a001-20200503
parisc randconfig-a001-20200503
riscv randconfig-a001-20200503
m68k randconfig-a001-20200502
mips randconfig-a001-20200502
nds32 randconfig-a001-20200502
alpha randconfig-a001-20200502
parisc randconfig-a001-20200502
riscv randconfig-a001-20200502
h8300 randconfig-a001-20200503
nios2 randconfig-a001-20200503
microblaze randconfig-a001-20200503
c6x randconfig-a001-20200503
sparc64 randconfig-a001-20200503
s390 randconfig-a001-20200504
xtensa randconfig-a001-20200504
sh randconfig-a001-20200504
openrisc randconfig-a001-20200504
csky randconfig-a001-20200504
s390 randconfig-a001-20200505
xtensa randconfig-a001-20200505
sh randconfig-a001-20200505
openrisc randconfig-a001-20200505
csky randconfig-a001-20200505
xtensa randconfig-a001-20200503
sh randconfig-a001-20200503
openrisc randconfig-a001-20200503
csky randconfig-a001-20200503
s390 randconfig-a001-20200430
xtensa randconfig-a001-20200430
csky randconfig-a001-20200430
openrisc randconfig-a001-20200430
sh randconfig-a001-20200430
i386 randconfig-b003-20200503
x86_64 randconfig-b002-20200503
i386 randconfig-b001-20200503
x86_64 randconfig-b003-20200503
x86_64 randconfig-b001-20200503
i386 randconfig-b002-20200503
x86_64 randconfig-c002-20200502
i386 randconfig-c002-20200502
i386 randconfig-c001-20200502
i386 randconfig-c003-20200502
i386 randconfig-d003-20200502
i386 randconfig-d001-20200502
x86_64 randconfig-d002-20200502
i386 randconfig-d002-20200502
x86_64 randconfig-e003-20200502
i386 randconfig-e003-20200502
x86_64 randconfig-e001-20200502
i386 randconfig-e002-20200502
i386 randconfig-e001-20200502
x86_64 randconfig-e003-20200503
x86_64 randconfig-e002-20200503
i386 randconfig-e003-20200503
x86_64 randconfig-e001-20200503
i386 randconfig-e002-20200503
i386 randconfig-e001-20200503
i386 randconfig-f003-20200505
x86_64 randconfig-f001-20200505
x86_64 randconfig-f003-20200505
i386 randconfig-f001-20200505
i386 randconfig-f002-20200505
x86_64 randconfig-a003-20200505
x86_64 randconfig-a001-20200505
i386 randconfig-a001-20200505
i386 randconfig-a003-20200505
i386 randconfig-a002-20200505
ia64 randconfig-a001-20200503
arm64 randconfig-a001-20200503
arc randconfig-a001-20200503
arm randconfig-a001-20200503
sparc randconfig-a001-20200503
ia64 randconfig-a001-20200505
arc randconfig-a001-20200505
powerpc randconfig-a001-20200505
arm randconfig-a001-20200505
sparc randconfig-a001-20200505
riscv allyesconfig
riscv nommu_virt_defconfig
riscv defconfig
riscv rv32_defconfig
riscv allmodconfig
s390 zfcpdump_defconfig
s390 allyesconfig
s390 allnoconfig
s390 alldefconfig
s390 defconfig
sh rsk7269_defconfig
sh allmodconfig
sh titan_defconfig
sh sh7785lcr_32bit_defconfig
sh allnoconfig
sparc defconfig
sparc64 defconfig
sparc64 allnoconfig
sparc64 allyesconfig
sparc64 allmodconfig
um x86_64_defconfig
um i386_defconfig
um defconfig
x86_64 rhel
x86_64 rhel-7.6
x86_64 rhel-7.6-kselftests
x86_64 rhel-7.2-clear
x86_64 lkp
x86_64 fedora-25
x86_64 kexec
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* Re: [PATCH v2 2/5] stats_fs API: create, add and remove stats_fs sources and values
From: Randy Dunlap @ 2020-05-04 22:11 UTC (permalink / raw)
To: Emanuele Giuseppe Esposito, kvm
Cc: linux-s390, David Hildenbrand, Cornelia Huck,
Emanuele Giuseppe Esposito, linux-kernel, kvm-ppc, linux-mips,
Christian Borntraeger, Alexander Viro, linux-fsdevel,
Paolo Bonzini, Vitaly Kuznetsov, linuxppc-dev, Jim Mattson
In-Reply-To: <20200504110344.17560-3-eesposit@redhat.com>
On 5/4/20 4:03 AM, Emanuele Giuseppe Esposito wrote:
> diff --git a/fs/Kconfig b/fs/Kconfig
> index f08fbbfafd9a..1b0de0f19e96 100644
> --- a/fs/Kconfig
> +++ b/fs/Kconfig
> @@ -328,4 +328,10 @@ source "fs/unicode/Kconfig"
> config IO_WQ
> bool
>
> +config STATS_FS
> + bool "Statistics Filesystem"
> + help
> + stats_fs is a virtual file system that provides counters and
> + other statistics about the running kernel.
> +
> endmenu
Hi,
This kconfig entry should be under (inside) "Pseudo filesystems",
i.e., between 'menu "Pseudo filesystems"' and its corresponding
"endmenu".
Thanks.
--
~Randy
^ permalink raw reply
* Re: [PATCH V2 00/11] Subject: Remove duplicated kmap code
From: Ira Weiny @ 2020-05-04 23:27 UTC (permalink / raw)
To: Al Viro
Cc: Peter Zijlstra, Dave Hansen, dri-devel, linux-mips,
James E.J. Bottomley, Max Filippov, Huang Rui, Paul Mackerras,
H. Peter Anvin, sparclinux, Dan Williams, Helge Deller, x86,
linux-csky, Ingo Molnar, linux-snps-arc, linux-xtensa,
Borislav Petkov, Andy Lutomirski, Thomas Gleixner,
linux-arm-kernel, Chris Zankel, Thomas Bogendoerfer, linux-parisc,
linux-kernel, Christian Koenig, Andrew Morton, linuxppc-dev,
David S. Miller
In-Reply-To: <20200504210225.GW23230@ZenIV.linux.org.uk>
On Mon, May 04, 2020 at 10:02:25PM +0100, Al Viro wrote:
> On Mon, May 04, 2020 at 01:17:41PM -0700, Ira Weiny wrote:
>
> > > || * arm: much, much worse. We have several files that pull linux/highmem.h:
> > > || arch/arm/mm/cache-feroceon-l2.c, arch/arm/mm/cache-xsc3l2.c,
> > > || arch/arm/mm/copypage-*.c, arch/arm/mm/dma-mapping.c, arch/arm/mm/flush.c,
> > > || arch/arm/mm/highmem.c, arch/arm/probes/uprobes/core.c,
> > > || arch/arm/include/asm/kvm_mmu.h (kmap_atomic_pfn()).
> > > || Those are fine, but we also have this:
> > > || arch/arm/include/asm/pgtable.h:200:#define __pte_map(pmd) (pte_t *)kmap_atomic(pmd_page(*(pmd)))
> > > || arch/arm/include/asm/pgtable.h:208:#define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr))
> > > || and sure as hell, asm/pgtable.h does *NOT* pull linux/highmem.h.
> >
> > It does not pull asm/highmem.h either...
>
> No, but the users of those macros need to be considered.
Agreed, I was trying to point out that highmem.h was being pulled from
somewhere else prior to my series, sorry.
>
> > > || #define pte_offset_map(dir, addr) \
> > > || ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
> > > || One pte_offset_map user in arch/microblaze:
> > > || arch/microblaze/kernel/signal.c:207: ptep = pte_offset_map(pmdp, address);
> > > || Messy, but doesn't require any changes (we have asm/pgalloc.h included
> > > || there, and that pull linux/highmem.h).
> >
> > AFAICS asm/pgtable.h does not include asm/highmem.h here...
> >
> > So looks like arch/microblaze/kernel/signal.c will need linux/highmem.h
>
> See above - line 39 in there is
> #include <asm/pgalloc.h>
> and line 14 in arch/microblaze/include/asm/pgalloc.h is
> #include <linux/highmem.h>
> It's conditional upon CONFIG_MMU in there, but so's the use of
> pte_offset_map() in arch/microblaze/kernel/signal.c
>
> So it shouldn't be a problem.
Ah ok, I did not see that one. Ok I'll drop that change and this series should
be good.
I was setting up to submit another version with 3 more patches you have
suggested:
kmap: Remove kmap_atomic_to_page()
parisc/kmap: Remove duplicate kmap code
sparc: Remove unnecessary includes
Would you like to see those folded in? I submitted 2 of the above as a
separate series already.
>
> > > || * xtensa: users in arch/xtensa/kernel/pci-dma.c, arch/xtensa/mm/highmem.c,
> > > || arch/xtensa/mm/cache.c and arch/xtensa/platforms/iss/simdisk.c (all pull
> > > || linux/highmem.h).
> >
> > Actually
> >
> > arch/xtensa/mm/cache.c gets linux/highmem.h from linux/pagemap.h
> >
> > arch/xtensa/platforms/iss/simdisk.c may have an issue?
> > linux/blkdev.h -> CONFIG_BLOCK -> linux/pagemap.h -> linux/highmem.h
> > But simdisk.c requires BLK_DEV_SIMDISK -> CONFIG_BLOCK...
> > <sigh>
>
> Yep - see above re major chain of indirect includes conditional upon CONFIG_BLOCK
> and its uses in places that only build with such configs. There's a plenty of
> similar considerations outside of arch/*, unfortunately...
Indeed.
FWIW the last 2 versions of this series have had no build failures with 0-day.
This series in particular just finished 164 configs without issue.
Would you like me to submit a new series? With your additional patches?
Ira
^ permalink raw reply
* Re: [PATCH v7 15/28] powerpc/kprobes: Use patch_instruction()
From: Alistair Popple @ 2020-05-05 1:41 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-16-jniethe5@gmail.com>
Without CONFIG_STRICT_KERNEL_RWX this boils down to doing the same thing
(although with a few more safety checks along the way), and with
CONFIG_STRICT_KERNEL_RWX this should make it actually work (although perhaps
there was some other mechanism that made it work anyway).
Reviewed-by: Alistair Popple <alistair@popple.id.au>
On Friday, 1 May 2020 1:42:07 PM AEST Jordan Niethe wrote:
> Instead of using memcpy() and flush_icache_range() use
> patch_instruction() which not only accomplishes both of these steps but
> will also make it easier to add support for prefixed instructions.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> v6: New to series.
> ---
> arch/powerpc/kernel/kprobes.c | 5 +----
> 1 file changed, 1 insertion(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
> index f64312dca84f..a72c8e1a42ad 100644
> --- a/arch/powerpc/kernel/kprobes.c
> +++ b/arch/powerpc/kernel/kprobes.c
> @@ -125,11 +125,8 @@ int arch_prepare_kprobe(struct kprobe *p)
> }
>
> if (!ret) {
> - memcpy(p->ainsn.insn, p->addr,
> - MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
> + patch_instruction((struct ppc_inst *)p->ainsn.insn, insn);
> p->opcode = ppc_inst_val(insn);
> - flush_icache_range((unsigned long)p->ainsn.insn,
> - (unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t));
> }
>
> p->ainsn.boostable = 0;
^ permalink raw reply
* Re: [PATCH v7 16/28] powerpc: Define and use __get_user_instr{, inatomic}()
From: Alistair Popple @ 2020-05-05 1:46 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-17-jniethe5@gmail.com>
Doesn't change any behaviour from what I can see.
Reviewed-by: Alistair Popple <alistair@popple.id.au>
On Friday, 1 May 2020 1:42:08 PM AEST Jordan Niethe wrote:
> Define specific __get_user_instr() and __get_user_instr_inatomic()
> macros for reading instructions from user space.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> arch/powerpc/include/asm/uaccess.h | 5 +++++
> arch/powerpc/kernel/align.c | 2 +-
> arch/powerpc/kernel/hw_breakpoint.c | 2 +-
> arch/powerpc/kernel/vecemu.c | 2 +-
> 4 files changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/uaccess.h
> b/arch/powerpc/include/asm/uaccess.h index 2f500debae21..c0a35e4586a5
> 100644
> --- a/arch/powerpc/include/asm/uaccess.h
> +++ b/arch/powerpc/include/asm/uaccess.h
> @@ -105,6 +105,11 @@ static inline int __access_ok(unsigned long addr,
> unsigned long size, #define __put_user_inatomic(x, ptr) \
> __put_user_nosleep((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
>
> +#define __get_user_instr(x, ptr) \
> + __get_user_nocheck((x).val, (u32 *)(ptr), sizeof(u32), true)
> +
> +#define __get_user_instr_inatomic(x, ptr) \
> + __get_user_nosleep((x).val, (u32 *)(ptr), sizeof(u32))
> extern long __put_user_bad(void);
>
> /*
> diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
> index 9e66e6c62354..b8f56052c6fe 100644
> --- a/arch/powerpc/kernel/align.c
> +++ b/arch/powerpc/kernel/align.c
> @@ -304,7 +304,7 @@ int fix_alignment(struct pt_regs *regs)
> */
> CHECK_FULL_REGS(regs);
>
> - if (unlikely(__get_user(instr.val, (unsigned int __user *)regs->nip)))
> + if (unlikely(__get_user_instr(instr, (void __user *)regs->nip)))
> return -EFAULT;
> if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) {
> /* We don't handle PPC little-endian any more... */
> diff --git a/arch/powerpc/kernel/hw_breakpoint.c
> b/arch/powerpc/kernel/hw_breakpoint.c index 2db9a7ac7bcb..423603c92c0f
> 100644
> --- a/arch/powerpc/kernel/hw_breakpoint.c
> +++ b/arch/powerpc/kernel/hw_breakpoint.c
> @@ -249,7 +249,7 @@ static bool stepping_handler(struct pt_regs *regs,
> struct perf_event *bp, struct instruction_op op;
> unsigned long addr = info->address;
>
> - if (__get_user_inatomic(instr.val, (unsigned int *)regs->nip))
> + if (__get_user_instr_inatomic(instr, (void __user *)regs->nip))
> goto fail;
>
> ret = analyse_instr(&op, regs, instr);
> diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c
> index bb262707fb5c..adcdba6d534e 100644
> --- a/arch/powerpc/kernel/vecemu.c
> +++ b/arch/powerpc/kernel/vecemu.c
> @@ -266,7 +266,7 @@ int emulate_altivec(struct pt_regs *regs)
> unsigned int va, vb, vc, vd;
> vector128 *vrs;
>
> - if (get_user(instr.val, (unsigned int __user *) regs->nip))
> + if (__get_user_instr(instr, (void __user *) regs->nip))
> return -EFAULT;
>
> word = ppc_inst_val(instr);
^ permalink raw reply
* Re: [PATCH v7 17/28] powerpc: Introduce a function for reporting instruction length
From: Alistair Popple @ 2020-05-05 2:02 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-18-jniethe5@gmail.com>
Looks good,
Reviewed-by: Alistair Popple <alistair@popple.id.au>
On Friday, 1 May 2020 1:42:09 PM AEST Jordan Niethe wrote:
> Currently all instructions have the same length, but in preparation for
> prefixed instructions introduce a function for returning instruction
> length.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> v6: - feature-fixups.c: do_final_fixups(): use here
> - ppc_inst_len(): change return type from bool to int
> - uprobes: Use ppc_inst_read() before calling ppc_inst_len()
> ---
> arch/powerpc/include/asm/inst.h | 5 +++++
> arch/powerpc/kernel/kprobes.c | 6 ++++--
> arch/powerpc/kernel/uprobes.c | 2 +-
> arch/powerpc/lib/feature-fixups.c | 14 +++++++-------
> 4 files changed, 17 insertions(+), 10 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/inst.h
> b/arch/powerpc/include/asm/inst.h index 0d581b332c20..2f3c9d5bcf7c 100644
> --- a/arch/powerpc/include/asm/inst.h
> +++ b/arch/powerpc/include/asm/inst.h
> @@ -17,6 +17,11 @@ static inline u32 ppc_inst_val(struct ppc_inst x)
> return x.val;
> }
>
> +static inline int ppc_inst_len(struct ppc_inst x)
> +{
> + return sizeof(struct ppc_inst);
> +}
> +
> static inline int ppc_inst_primary_opcode(struct ppc_inst x)
> {
> return ppc_inst_val(x) >> 26;
> diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
> index a72c8e1a42ad..33d54b091c70 100644
> --- a/arch/powerpc/kernel/kprobes.c
> +++ b/arch/powerpc/kernel/kprobes.c
> @@ -462,14 +462,16 @@ NOKPROBE_SYMBOL(trampoline_probe_handler);
> */
> int kprobe_post_handler(struct pt_regs *regs)
> {
> + int len;
> struct kprobe *cur = kprobe_running();
> struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
>
> if (!cur || user_mode(regs))
> return 0;
>
> + len = ppc_inst_len(ppc_inst_read((struct ppc_inst *)cur->ainsn.insn));
> /* make sure we got here for instruction we have a kprobe on */
> - if (((unsigned long)cur->ainsn.insn + 4) != regs->nip)
> + if (((unsigned long)cur->ainsn.insn + len) != regs->nip)
> return 0;
>
> if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
> @@ -478,7 +480,7 @@ int kprobe_post_handler(struct pt_regs *regs)
> }
>
> /* Adjust nip to after the single-stepped instruction */
> - regs->nip = (unsigned long)cur->addr + 4;
> + regs->nip = (unsigned long)cur->addr + len;
> regs->msr |= kcb->kprobe_saved_msr;
>
> /*Restore back the original saved kprobes variables and continue. */
> diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
> index 6893d40a48c5..83e883e1a42d 100644
> --- a/arch/powerpc/kernel/uprobes.c
> +++ b/arch/powerpc/kernel/uprobes.c
> @@ -112,7 +112,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe,
> struct pt_regs *regs) * support doesn't exist and have to fix-up the next
> instruction * to be executed.
> */
> - regs->nip = utask->vaddr + MAX_UINSN_BYTES;
> + regs->nip = utask->vaddr + ppc_inst_len(ppc_inst_read(&auprobe->insn));
>
> user_disable_single_step(current);
> return 0;
> diff --git a/arch/powerpc/lib/feature-fixups.c
> b/arch/powerpc/lib/feature-fixups.c index 13ec3264a565..f4845e740338 100644
> --- a/arch/powerpc/lib/feature-fixups.c
> +++ b/arch/powerpc/lib/feature-fixups.c
> @@ -390,20 +390,20 @@ void do_lwsync_fixups(unsigned long value, void
> *fixup_start, void *fixup_end) static void do_final_fixups(void)
> {
> #if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE)
> - struct ppc_inst *src, *dest;
> - unsigned long length;
> + struct ppc_inst inst, *src, *dest, *end;
>
> if (PHYSICAL_START == 0)
> return;
>
> src = (struct ppc_inst *)(KERNELBASE + PHYSICAL_START);
> dest = (struct ppc_inst *)KERNELBASE;
> - length = (__end_interrupts - _stext) / sizeof(struct ppc_inst);
> + end = (void *)src + (__end_interrupts - _stext);
>
> - while (length--) {
> - raw_patch_instruction(dest, ppc_inst_read(src));
> - src++;
> - dest++;
> + while (src < end) {
> + inst = ppc_inst_read(src);
> + raw_patch_instruction(dest, inst);
> + src = (void *)src + ppc_inst_len(inst);
> + dest = (void *)dest + ppc_inst_len(inst);
> }
> #endif
> }
^ permalink raw reply
* Re: [PATCH v7 18/28] powerpc/xmon: Use a function for reading instructions
From: Alistair Popple @ 2020-05-05 2:07 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-19-jniethe5@gmail.com>
Shouldn't change anything and will be correct once prefix instructions are
defined.
Reviewed-by: Alistair Popple <alistair@popple.id.au>
On Friday, 1 May 2020 1:42:10 PM AEST Jordan Niethe wrote:
> Currently in xmon, mread() is used for reading instructions. In
> preparation for prefixed instructions, create and use a new function,
> mread_instr(), especially for reading instructions.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> v5: New to series, seperated from "Add prefixed instructions to
> instruction data type"
> v6: mread_instr(): correctly return error status
> ---
> arch/powerpc/xmon/xmon.c | 28 ++++++++++++++++++++++++----
> 1 file changed, 24 insertions(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> index cde733a82366..1947821e425d 100644
> --- a/arch/powerpc/xmon/xmon.c
> +++ b/arch/powerpc/xmon/xmon.c
> @@ -122,6 +122,7 @@ static unsigned bpinstr = 0x7fe00008; /* trap */
> static int cmds(struct pt_regs *);
> static int mread(unsigned long, void *, int);
> static int mwrite(unsigned long, void *, int);
> +static int mread_instr(unsigned long, struct ppc_inst *);
> static int handle_fault(struct pt_regs *);
> static void byterev(unsigned char *, int);
> static void memex(void);
> @@ -896,7 +897,7 @@ static void insert_bpts(void)
> for (i = 0; i < NBPTS; ++i, ++bp) {
> if ((bp->enabled & (BP_TRAP|BP_CIABR)) == 0)
> continue;
> - if (mread(bp->address, &instr, 4) != 4) {
> + if (!mread_instr(bp->address, &instr)) {
> printf("Couldn't read instruction at %lx, "
> "disabling breakpoint there\n", bp->address);
> bp->enabled = 0;
> @@ -946,7 +947,7 @@ static void remove_bpts(void)
> for (i = 0; i < NBPTS; ++i, ++bp) {
> if ((bp->enabled & (BP_TRAP|BP_CIABR)) != BP_TRAP)
> continue;
> - if (mread(bp->address, &instr, 4) == 4
> + if (mread_instr(bp->address, &instr)
> && ppc_inst_equal(instr, ppc_inst(bpinstr))
> && patch_instruction(
> (struct ppc_inst *)bp->address, ppc_inst_read(bp->instr)) != 0)
> @@ -1162,7 +1163,7 @@ static int do_step(struct pt_regs *regs)
> force_enable_xmon();
> /* check we are in 64-bit kernel mode, translation enabled */
> if ((regs->msr & (MSR_64BIT|MSR_PR|MSR_IR)) == (MSR_64BIT|MSR_IR)) {
> - if (mread(regs->nip, &instr, 4) == 4) {
> + if (mread_instr(regs->nip, &instr)) {
> stepped = emulate_step(regs, instr);
> if (stepped < 0) {
> printf("Couldn't single-step %s instruction\n",
> @@ -1329,7 +1330,7 @@ static long check_bp_loc(unsigned long addr)
> printf("Breakpoints may only be placed at kernel addresses\n");
> return 0;
> }
> - if (!mread(addr, &instr, sizeof(instr))) {
> + if (!mread_instr(addr, &instr)) {
> printf("Can't read instruction at address %lx\n", addr);
> return 0;
> }
> @@ -2122,6 +2123,25 @@ mwrite(unsigned long adrs, void *buf, int size)
> return n;
> }
>
> +static int
> +mread_instr(unsigned long adrs, struct ppc_inst *instr)
> +{
> + volatile int n;
> +
> + n = 0;
> + if (setjmp(bus_error_jmp) == 0) {
> + catch_memory_errors = 1;
> + sync();
> + *instr = ppc_inst_read((struct ppc_inst *)adrs);
> + sync();
> + /* wait a little while to see if we get a machine check */
> + __delay(200);
> + n = ppc_inst_len(*instr);
> + }
> + catch_memory_errors = 0;
> + return n;
> +}
> +
> static int fault_type;
> static int fault_except;
> static char *fault_chars[] = { "--", "**", "##" };
^ permalink raw reply
* Re: [PATCH v7 19/28] powerpc/xmon: Move insertion of breakpoint for xol'ing
From: Alistair Popple @ 2020-05-05 2:19 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-20-jniethe5@gmail.com>
I can't see any side-effects from patching both instructions at the same time.
Reviewed-by: Alistair Popple <alistair@popple.id.au>
On Friday, 1 May 2020 1:42:11 PM AEST Jordan Niethe wrote:
> When a new breakpoint is created, the second instruction of that
> breakpoint is patched with a trap instruction. This assumes the length
> of the instruction is always the same. In preparation for prefixed
> instructions, remove this assumption. Insert the trap instruction at the
> same time the first instruction is inserted.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> arch/powerpc/xmon/xmon.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> index 1947821e425d..fb2563079046 100644
> --- a/arch/powerpc/xmon/xmon.c
> +++ b/arch/powerpc/xmon/xmon.c
> @@ -878,7 +878,6 @@ static struct bpt *new_breakpoint(unsigned long a)
> if (!bp->enabled && atomic_read(&bp->ref_count) == 0) {
> bp->address = a;
> bp->instr = (void *)(bpt_table + ((bp - bpts) * BPT_WORDS));
> - patch_instruction(bp->instr + 1, ppc_inst(bpinstr));
> return bp;
> }
> }
> @@ -910,6 +909,7 @@ static void insert_bpts(void)
> continue;
> }
> patch_instruction(bp->instr, instr);
> + patch_instruction((void *)bp->instr + ppc_inst_len(instr),
> ppc_inst(bpinstr)); if (bp->enabled & BP_CIABR)
> continue;
> if (patch_instruction((struct ppc_inst *)bp->address,
^ permalink raw reply
* Re: [PATCH v7 20/28] powerpc: Make test_translate_branch() independent of instruction length
From: Alistair Popple @ 2020-05-05 2:40 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-21-jniethe5@gmail.com>
I guess this could change if there were prefixed branch instructions, but there
aren't so:
Reviewed-by: Alistair Popple <alistair@popple.id.au>
On Friday, 1 May 2020 1:42:12 PM AEST Jordan Niethe wrote:
> test_translate_branch() uses two pointers to instructions within a
> buffer, p and q, to test patch_branch(). The pointer arithmetic done on
> them assumes a size of 4. This will not work if the instruction length
> changes. Instead do the arithmetic relative to the void * to the buffer.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> v4: New to series
> ---
> arch/powerpc/lib/code-patching.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/arch/powerpc/lib/code-patching.c
> b/arch/powerpc/lib/code-patching.c index 110f710500c8..5b2f66d06b1e 100644
> --- a/arch/powerpc/lib/code-patching.c
> +++ b/arch/powerpc/lib/code-patching.c
> @@ -569,7 +569,7 @@ static void __init test_branch_bform(void)
> static void __init test_translate_branch(void)
> {
> unsigned long addr;
> - struct ppc_inst *p, *q;
> + void *p, *q;
> struct ppc_inst instr;
> void *buf;
>
> @@ -583,7 +583,7 @@ static void __init test_translate_branch(void)
> addr = (unsigned long)p;
> patch_branch(p, addr, 0);
> check(instr_is_branch_to_addr(p, addr));
> - q = p + 1;
> + q = p + 4;
> translate_branch(&instr, q, p);
> patch_instruction(q, instr);
> check(instr_is_branch_to_addr(q, addr));
> @@ -639,7 +639,7 @@ static void __init test_translate_branch(void)
> create_cond_branch(&instr, p, addr, 0);
> patch_instruction(p, instr);
> check(instr_is_branch_to_addr(p, addr));
> - q = p + 1;
> + q = buf + 4;
> translate_branch(&instr, q, p);
> patch_instruction(q, instr);
> check(instr_is_branch_to_addr(q, addr));
^ permalink raw reply
* Re: [PATCH v7 22/28] powerpc: Define new SRR1 bits for a future ISA version
From: Alistair Popple @ 2020-05-05 2:49 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-23-jniethe5@gmail.com>
Reviewed-by: Alistair Popple <alistair@popple.id.au>
On Friday, 1 May 2020 1:42:14 PM AEST Jordan Niethe wrote:
> Add the BOUNDARY SRR1 bit definition for when the cause of an alignment
> exception is a prefixed instruction that crosses a 64-byte boundary.
> Add the PREFIXED SRR1 bit definition for exceptions caused by prefixed
> instructions.
>
> Bit 35 of SRR1 is called SRR1_ISI_N_OR_G. This name comes from it being
> used to indicate that an ISI was due to the access being no-exec or
> guarded. A future ISA version adds another purpose. It is also set if
> there is an access in a cache-inhibited location for prefixed
> instruction. Rename from SRR1_ISI_N_OR_G to SRR1_ISI_N_G_OR_CIP.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> v2: Combined all the commits concerning SRR1 bits.
> ---
> arch/powerpc/include/asm/reg.h | 4 +++-
> arch/powerpc/kvm/book3s_hv_nested.c | 2 +-
> arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
> 3 files changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
> index 773f76402392..f95eb8f97756 100644
> --- a/arch/powerpc/include/asm/reg.h
> +++ b/arch/powerpc/include/asm/reg.h
> @@ -762,7 +762,7 @@
> #endif
>
> #define SRR1_ISI_NOPT 0x40000000 /* ISI: Not found in hash */
> -#define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */
> +#define SRR1_ISI_N_G_OR_CIP 0x10000000 /* ISI: Access is no-exec or G or
> CI for a prefixed instruction */ #define SRR1_ISI_PROT 0x08000000 /*
> ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /*
> reason for wakeup */
> #define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9
> */ @@ -789,6 +789,8 @@
> #define SRR1_PROGADDR 0x00010000 /* SRR0 contains subsequent addr */
>
> #define SRR1_MCE_MCP 0x00080000 /* Machine check signal caused
interrupt
> */ +#define SRR1_BOUNDARY 0x10000000 /* Prefixed instruction crosses
> 64-byte boundary */ +#define SRR1_PREFIXED 0x20000000 /* Exception
> caused by prefixed instruction */
>
> #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */
> #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c
> b/arch/powerpc/kvm/book3s_hv_nested.c index dc97e5be76f6..6ab685227574
> 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -1169,7 +1169,7 @@ static int kvmhv_translate_addr_nested(struct kvm_vcpu
> *vcpu, } else if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) { /*
> Can we execute? */
> if (!gpte_p->may_execute) {
> - flags |= SRR1_ISI_N_OR_G;
> + flags |= SRR1_ISI_N_G_OR_CIP;
> goto forward_to_l1;
> }
> } else {
> diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
> b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 220305454c23..b53a9f1c1a46
> 100644
> --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
> +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
> @@ -1260,7 +1260,7 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu,
> unsigned long addr, status &= ~DSISR_NOHPTE; /* DSISR_NOHPTE ==
> SRR1_ISI_NOPT */
> if (!data) {
> if (gr & (HPTE_R_N | HPTE_R_G))
> - return status | SRR1_ISI_N_OR_G;
> + return status | SRR1_ISI_N_G_OR_CIP;
> if (!hpte_read_permission(pp, slb_v & key))
> return status | SRR1_ISI_PROT;
> } else if (status & DSISR_ISSTORE) {
^ permalink raw reply
* Re: [PATCH 3/3] mm/hugetlb: Introduce HAVE_ARCH_CLEAR_HUGEPAGE_FLAGS
From: Anshuman Khandual @ 2020-05-05 2:51 UTC (permalink / raw)
To: Andrew Morton
Cc: Rich Felker, linux-ia64, linux-sh, Catalin Marinas,
Heiko Carstens, linux-kernel, James E.J. Bottomley, linux-mm,
Paul Mackerras, H. Peter Anvin, sparclinux, linux-riscv,
Will Deacon, linux-arch, linux-s390, Yoshinori Sato, Helge Deller,
x86, Russell King, Christian Borntraeger, Ingo Molnar, Fenghua Yu,
Vasily Gorbik, Thomas Bogendoerfer, Borislav Petkov,
Paul Walmsley, Thomas Gleixner, linux-arm-kernel, Tony Luck,
linux-parisc, linux-mips, Palmer Dabbelt, linuxppc-dev,
David S. Miller, Mike Kravetz
In-Reply-To: <20200425200124.20d0c75fcaef05d062d3667c@linux-foundation.org>
On 04/26/2020 08:31 AM, Andrew Morton wrote:
> On Sun, 26 Apr 2020 08:13:17 +0530 Anshuman Khandual <anshuman.khandual@arm.com> wrote:
>
>>
>>
>> On 04/26/2020 06:25 AM, Andrew Morton wrote:
>>> On Tue, 14 Apr 2020 17:14:30 +0530 Anshuman Khandual <anshuman.khandual@arm.com> wrote:
>>>
>>>> There are multiple similar definitions for arch_clear_hugepage_flags() on
>>>> various platforms. This introduces HAVE_ARCH_CLEAR_HUGEPAGE_FLAGS for those
>>>> platforms that need to define their own arch_clear_hugepage_flags() while
>>>> also providing a generic fallback definition for others to use. This help
>>>> reduce code duplication.
>>>>
>>>> ...
>>>>
>>>> --- a/include/linux/hugetlb.h
>>>> +++ b/include/linux/hugetlb.h
>>>> @@ -544,6 +544,10 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
>>>> }
>>>> #endif
>>>>
>>>> +#ifndef HAVE_ARCH_CLEAR_HUGEPAGE_FLAGS
>>>> +static inline void arch_clear_hugepage_flags(struct page *page) { }
>>>> +#endif
>>>> +
>>>> #ifndef arch_make_huge_pte
>>>> static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
>>>> struct page *page, int writable)
>>>
>>> This is the rather old-school way of doing it. The Linus-suggested way is
>>>
>>> #ifndef arch_clear_hugepage_flags
>>> static inline void arch_clear_hugepage_flags(struct page *page)
>>> {
>>> }
>>> #define arch_clear_hugepage_flags arch_clear_hugepage_flags
>>
>> Do we need that above line here ? Is not that implicit.
>
> It depends if other header files want to test whether
> arch_clear_hugepage_flags is already defined. If the header heorarchy
> is well-defined and working properly, they shouldn't need to, because
> we're reliably indluding the relevant arch header before (or early
> within) include/linux/hugetlb.h.
>
> It would be nice if
>
> #define arch_clear_hugepage_flags arch_clear_hugepage_flags
> #define arch_clear_hugepage_flags arch_clear_hugepage_flags
>
> were to generate an compiler error but it doesn't. If it did we could
> detect these incorrect inclusion orders.
>
>>> #endif
>>>
>>> And the various arch headers do
>>>
>>> static inline void arch_clear_hugepage_flags(struct page *page)
>>> {
>>> <some implementation>
>>> }
>>> #define arch_clear_hugepage_flags arch_clear_hugepage_flags
>>>
>>> It's a small difference - mainly to avoid adding two variables to the
>>> overall namespace where one would do.
>>
>> Understood, will change and resend.
>
> That's OK - I've queued up that fix.
>
Hello Andrew,
I might not have searched all the relevant trees or might have just searched
earlier than required. But I dont see these patches (or your proposed fixes)
either in mmotm (2020-04-29-23-04) or in next-20200504. Wondering if you are
waiting on a V2 for this series accommodating the changes you had proposed.
- Anshuman
^ permalink raw reply
* Re: [PATCH v4 0/7] clean up redundant 'kvm_run' parameters
From: Tianjia Zhang @ 2020-05-05 4:15 UTC (permalink / raw)
To: pbonzini, tsbogend, paulus, mpe, benh, borntraeger, frankja,
david, cohuck, heiko.carstens, gor, sean.j.christopherson,
vkuznets, wanpengli, jmattson, joro, tglx, mingo, bp, x86, hpa,
maz, james.morse, julien.thierry.kdev, suzuki.poulose,
christoffer.dall, peterx, thuth, chenhuacai
Cc: linux-s390, kvm, linux-mips, kvm-ppc, linux-kernel, linuxppc-dev,
kvmarm, linux-arm-kernel
In-Reply-To: <20200427043514.16144-1-tianjia.zhang@linux.alibaba.com>
Paolo Bonzini, any opinion on this?
Thanks and best,
Tianjia
On 2020/4/27 12:35, Tianjia Zhang wrote:
> In the current kvm version, 'kvm_run' has been included in the 'kvm_vcpu'
> structure. For historical reasons, many kvm-related function parameters
> retain the 'kvm_run' and 'kvm_vcpu' parameters at the same time. This
> patch does a unified cleanup of these remaining redundant parameters.
>
> This series of patches has completely cleaned the architecture of
> arm64, mips, ppc, and s390 (no such redundant code on x86). Due to
> the large number of modified codes, a separate patch is made for each
> platform. On the ppc platform, there is also a redundant structure
> pointer of 'kvm_run' in 'vcpu_arch', which has also been cleaned
> separately.
>
> ---
> v4 change:
> mips: fixes two errors in entry.c.
>
> v3 change:
> Keep the existing `vcpu->run` in the function body unchanged.
>
> v2 change:
> s390 retains the original variable name and minimizes modification.
>
> Tianjia Zhang (7):
> KVM: s390: clean up redundant 'kvm_run' parameters
> KVM: arm64: clean up redundant 'kvm_run' parameters
> KVM: PPC: Remove redundant kvm_run from vcpu_arch
> KVM: PPC: clean up redundant 'kvm_run' parameters
> KVM: PPC: clean up redundant kvm_run parameters in assembly
> KVM: MIPS: clean up redundant 'kvm_run' parameters
> KVM: MIPS: clean up redundant kvm_run parameters in assembly
>
> arch/arm64/include/asm/kvm_coproc.h | 12 +--
> arch/arm64/include/asm/kvm_host.h | 11 +--
> arch/arm64/include/asm/kvm_mmu.h | 2 +-
> arch/arm64/kvm/handle_exit.c | 36 +++----
> arch/arm64/kvm/sys_regs.c | 13 ++-
> arch/mips/include/asm/kvm_host.h | 32 +------
> arch/mips/kvm/emulate.c | 59 ++++--------
> arch/mips/kvm/entry.c | 21 ++---
> arch/mips/kvm/mips.c | 14 +--
> arch/mips/kvm/trap_emul.c | 114 ++++++++++-------------
> arch/mips/kvm/vz.c | 26 ++----
> arch/powerpc/include/asm/kvm_book3s.h | 16 ++--
> arch/powerpc/include/asm/kvm_host.h | 1 -
> arch/powerpc/include/asm/kvm_ppc.h | 27 +++---
> arch/powerpc/kvm/book3s.c | 4 +-
> arch/powerpc/kvm/book3s.h | 2 +-
> arch/powerpc/kvm/book3s_64_mmu_hv.c | 12 +--
> arch/powerpc/kvm/book3s_64_mmu_radix.c | 4 +-
> arch/powerpc/kvm/book3s_emulate.c | 10 +-
> arch/powerpc/kvm/book3s_hv.c | 64 ++++++-------
> arch/powerpc/kvm/book3s_hv_nested.c | 12 +--
> arch/powerpc/kvm/book3s_interrupts.S | 17 ++--
> arch/powerpc/kvm/book3s_paired_singles.c | 72 +++++++-------
> arch/powerpc/kvm/book3s_pr.c | 33 ++++---
> arch/powerpc/kvm/booke.c | 39 ++++----
> arch/powerpc/kvm/booke.h | 8 +-
> arch/powerpc/kvm/booke_emulate.c | 2 +-
> arch/powerpc/kvm/booke_interrupts.S | 9 +-
> arch/powerpc/kvm/bookehv_interrupts.S | 10 +-
> arch/powerpc/kvm/e500_emulate.c | 15 ++-
> arch/powerpc/kvm/emulate.c | 10 +-
> arch/powerpc/kvm/emulate_loadstore.c | 32 +++----
> arch/powerpc/kvm/powerpc.c | 72 +++++++-------
> arch/powerpc/kvm/trace_hv.h | 6 +-
> arch/s390/kvm/kvm-s390.c | 23 +++--
> virt/kvm/arm/arm.c | 6 +-
> virt/kvm/arm/mmio.c | 11 ++-
> virt/kvm/arm/mmu.c | 5 +-
> 38 files changed, 392 insertions(+), 470 deletions(-)
>
^ permalink raw reply
* Re: [PATCH 1/4] dma-mapping: move the remaining DMA API calls out of line
From: Alexey Kardashevskiy @ 2020-05-05 4:18 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Greg Kroah-Hartman, Joerg Roedel, linuxppc-dev, linux-kernel,
iommu, Robin Murphy, Lu Baolu
In-Reply-To: <20200417075852.GA20049@lst.de>
On 17/04/2020 17:58, Christoph Hellwig wrote:
> On Wed, Apr 15, 2020 at 09:21:37PM +1000, Alexey Kardashevskiy wrote:
>> And the fact they were exported leaves possibility that there is a
>> driver somewhere relying on these symbols or distro kernel won't build
>> because the symbol disappeared from exports (I do not know what KABI
>> guarantees or if mainline kernel cares).
>
> We absolutely do not care. In fact for abuses of APIs that drivers
> should not use we almost care to make them private and break people
> abusing them.
ok :)
>> I do not care in particular but
>> some might, a line separated with empty lines in the commit log would do.
>
> I'll add a blurb for the next version.
Has it gone anywhere? Thanks,
--
Alexey
^ permalink raw reply
* Re: [PATCH v7 23/28] powerpc: Add prefixed instructions to instruction data type
From: Alistair Popple @ 2020-05-05 6:04 UTC (permalink / raw)
To: Jordan Niethe; +Cc: npiggin, bala24, naveen.n.rao, linuxppc-dev, dja
In-Reply-To: <20200501034220.8982-24-jniethe5@gmail.com>
When reviewing earlier patches in this series I assumed the data type would
eventually change size (on PPC64 at least) so I was looking for any possible
side effects this may cause, but I didn't notice any so I think this should be
ok:
Reviewed-by: Alistair Popple <alistair@popple.id.au>
However I haven't dug deeply enough into the optprobes code to fully
understand/comment on the changes there (although they look correct afaict).
On Friday, 1 May 2020 1:42:15 PM AEST Jordan Niethe wrote:
> For powerpc64, redefine the ppc_inst type so both word and prefixed
> instructions can be represented. On powerpc32 the type will remain the
> same. Update places which had assumed instructions to be 4 bytes long.
>
> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> ---
> v4: New to series
> v5: - Distinguish normal instructions from prefixed instructions with a
> 0xff marker for the suffix.
> - __patch_instruction() using std for prefixed instructions
> v6: - Return false instead of 0 in ppc_inst_prefixed()
> - Fix up types for ppc32 so it compiles
> - remove ppc_inst_write()
> - __patching_instruction(): move flush out of condition
> ---
> arch/powerpc/include/asm/inst.h | 68 +++++++++++++++++++++++++---
> arch/powerpc/include/asm/kprobes.h | 2 +-
> arch/powerpc/include/asm/uaccess.h | 32 ++++++++++++-
> arch/powerpc/include/asm/uprobes.h | 2 +-
> arch/powerpc/kernel/optprobes.c | 42 +++++++++--------
> arch/powerpc/kernel/optprobes_head.S | 3 ++
> arch/powerpc/lib/code-patching.c | 13 ++++--
> arch/powerpc/lib/feature-fixups.c | 5 +-
> arch/powerpc/lib/inst.c | 40 ++++++++++++++++
> arch/powerpc/lib/sstep.c | 4 +-
> arch/powerpc/xmon/xmon.c | 4 +-
> arch/powerpc/xmon/xmon_bpts.S | 2 +
> 12 files changed, 180 insertions(+), 37 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/inst.h
> b/arch/powerpc/include/asm/inst.h index 2f3c9d5bcf7c..1e743635c214 100644
> --- a/arch/powerpc/include/asm/inst.h
> +++ b/arch/powerpc/include/asm/inst.h
> @@ -8,23 +8,72 @@
>
> struct ppc_inst {
> u32 val;
> +#ifdef __powerpc64__
> + u32 suffix;
> +#endif /* __powerpc64__ */
> } __packed;
>
> -#define ppc_inst(x) ((struct ppc_inst){ .val = x })
> -
> static inline u32 ppc_inst_val(struct ppc_inst x)
> {
> return x.val;
> }
>
> -static inline int ppc_inst_len(struct ppc_inst x)
> +static inline int ppc_inst_primary_opcode(struct ppc_inst x)
> {
> - return sizeof(struct ppc_inst);
> + return ppc_inst_val(x) >> 26;
> }
>
> -static inline int ppc_inst_primary_opcode(struct ppc_inst x)
> +#ifdef __powerpc64__
> +#define ppc_inst(x) ((struct ppc_inst){ .val = (x), .suffix = 0xff })
> +
> +#define ppc_inst_prefix(x, y) ((struct ppc_inst){ .val = (x), .suffix = (y)
> }) +
> +static inline u32 ppc_inst_suffix(struct ppc_inst x)
> {
> - return ppc_inst_val(x) >> 26;
> + return x.suffix;
> +}
> +
> +static inline bool ppc_inst_prefixed(struct ppc_inst x)
> +{
> + return (ppc_inst_primary_opcode(x) == 1) && ppc_inst_suffix(x) != 0xff;
> +}
> +
> +static inline struct ppc_inst ppc_inst_swab(struct ppc_inst x)
> +{
> + return ppc_inst_prefix(swab32(ppc_inst_val(x)),
> + swab32(ppc_inst_suffix(x)));
> +}
> +
> +static inline struct ppc_inst ppc_inst_read(const struct ppc_inst *ptr)
> +{
> + u32 val, suffix;
> +
> + val = *(u32 *)ptr;
> + if ((val >> 26) == 1) {
> + suffix = *((u32 *)ptr + 1);
> + return ppc_inst_prefix(val, suffix);
> + } else {
> + return ppc_inst(val);
> + }
> +}
> +
> +static inline bool ppc_inst_equal(struct ppc_inst x, struct ppc_inst y)
> +{
> + return *(u64 *)&x == *(u64 *)&y;
> +}
> +
> +#else
> +
> +#define ppc_inst(x) ((struct ppc_inst){ .val = x })
> +
> +static inline bool ppc_inst_prefixed(struct ppc_inst x)
> +{
> + return false;
> +}
> +
> +static inline u32 ppc_inst_suffix(struct ppc_inst x)
> +{
> + return 0;
> }
>
> static inline struct ppc_inst ppc_inst_swab(struct ppc_inst x)
> @@ -42,6 +91,13 @@ static inline bool ppc_inst_equal(struct ppc_inst x,
> struct ppc_inst y) return ppc_inst_val(x) == ppc_inst_val(y);
> }
>
> +#endif /* __powerpc64__ */
> +
> +static inline int ppc_inst_len(struct ppc_inst x)
> +{
> + return (ppc_inst_prefixed(x)) ? 8 : 4;
> +}
> +
> int probe_user_read_inst(struct ppc_inst *inst,
> struct ppc_inst *nip);
> int probe_kernel_read_inst(struct ppc_inst *inst,
> diff --git a/arch/powerpc/include/asm/kprobes.h
> b/arch/powerpc/include/asm/kprobes.h index 66b3f2983b22..4fc0e15e23a5
> 100644
> --- a/arch/powerpc/include/asm/kprobes.h
> +++ b/arch/powerpc/include/asm/kprobes.h
> @@ -43,7 +43,7 @@ extern kprobe_opcode_t optprobe_template_ret[];
> extern kprobe_opcode_t optprobe_template_end[];
>
> /* Fixed instruction size for powerpc */
> -#define MAX_INSN_SIZE 1
> +#define MAX_INSN_SIZE 2
> #define MAX_OPTIMIZED_LENGTH sizeof(kprobe_opcode_t) /* 4 bytes */
> #define MAX_OPTINSN_SIZE (optprobe_template_end - optprobe_template_entry)
> #define RELATIVEJUMP_SIZE sizeof(kprobe_opcode_t) /* 4 bytes */
> diff --git a/arch/powerpc/include/asm/uaccess.h
> b/arch/powerpc/include/asm/uaccess.h index c0a35e4586a5..12e52aa179b6
> 100644
> --- a/arch/powerpc/include/asm/uaccess.h
> +++ b/arch/powerpc/include/asm/uaccess.h
> @@ -105,11 +105,41 @@ static inline int __access_ok(unsigned long addr,
> unsigned long size, #define __put_user_inatomic(x, ptr) \
> __put_user_nosleep((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
>
> +#ifdef __powerpc64__
> +#define __get_user_instr(x, ptr) \
> +({ \
> + long __gui_ret = 0; \
> + unsigned int prefix, suffix; \
> + __gui_ret = __get_user(prefix, (unsigned int __user *)ptr); \
> + if (!__gui_ret && (prefix >> 26) == 1) { \
> + __gui_ret = __get_user(suffix, (unsigned int __user *)ptr + 1); \
> + (x) = ppc_inst_prefix(prefix, suffix); \
> + } else { \
> + (x) = ppc_inst(prefix); \
> + } \
> + __gui_ret; \
> +})
> +
> +#define __get_user_instr_inatomic(x, ptr) \
> +({ \
> + long __gui_ret = 0; \
> + unsigned int prefix, suffix; \
> + __gui_ret = __get_user_inatomic(prefix, (unsigned int __user *)ptr); \
> + if (!__gui_ret && (prefix >> 26) == 1) { \
> + __gui_ret = __get_user_inatomic(suffix, (unsigned int __user *)ptr +
> 1); \ + (x) = ppc_inst_prefix(prefix, suffix); \
> + } else { \
> + (x) = ppc_inst(prefix); \
> + } \
> + __gui_ret; \
> +})
> +#else
> #define __get_user_instr(x, ptr) \
> __get_user_nocheck((x).val, (u32 *)(ptr), sizeof(u32), true)
> -
> #define __get_user_instr_inatomic(x, ptr) \
> __get_user_nosleep((x).val, (u32 *)(ptr), sizeof(u32))
> +#endif
> +
> extern long __put_user_bad(void);
>
> /*
> diff --git a/arch/powerpc/include/asm/uprobes.h
> b/arch/powerpc/include/asm/uprobes.h index 7e3b329ba2d3..5bf65f5d44a9
> 100644
> --- a/arch/powerpc/include/asm/uprobes.h
> +++ b/arch/powerpc/include/asm/uprobes.h
> @@ -15,7 +15,7 @@
>
> typedef ppc_opcode_t uprobe_opcode_t;
>
> -#define MAX_UINSN_BYTES 4
> +#define MAX_UINSN_BYTES 8
> #define UPROBE_XOL_SLOT_BYTES (MAX_UINSN_BYTES)
>
> /* The following alias is needed for reference from arch-agnostic code */
> diff --git a/arch/powerpc/kernel/optprobes.c
> b/arch/powerpc/kernel/optprobes.c index d704f9598f48..a67c5288cf50 100644
> --- a/arch/powerpc/kernel/optprobes.c
> +++ b/arch/powerpc/kernel/optprobes.c
> @@ -159,38 +159,38 @@ void patch_imm32_load_insns(unsigned int val,
> kprobe_opcode_t *addr)
>
> /*
> * Generate instructions to load provided immediate 64-bit value
> - * to register 'r3' and patch these instructions at 'addr'.
> + * to register 'reg' and patch these instructions at 'addr'.
> */
> -void patch_imm64_load_insns(unsigned long val, kprobe_opcode_t *addr)
> +void patch_imm64_load_insns(unsigned long val, int reg, kprobe_opcode_t
> *addr) {
> - /* lis r3,(op)@highest */
> - patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ADDIS |
> ___PPC_RT(3) | + /* lis reg,(op)@highest */
> + patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ADDIS |
> ___PPC_RT(reg) | ((val >> 48) & 0xffff)));
> addr++;
>
> - /* ori r3,r3,(op)@higher */
> - patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ORI |
> ___PPC_RA(3) | - ___PPC_RS(3) | ((val >> 32) & 0xffff)));
> + /* ori reg,reg,(op)@higher */
> + patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ORI |
> ___PPC_RA(reg) | + ___PPC_RS(reg) | ((val >> 32) & 0xffff)));
> addr++;
>
> - /* rldicr r3,r3,32,31 */
> - patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_RLDICR |
> ___PPC_RA(3) | - ___PPC_RS(3) | __PPC_SH64(32) | __PPC_ME64(31)));
> + /* rldicr reg,reg,32,31 */
> + patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_RLDICR |
> ___PPC_RA(reg) | + ___PPC_RS(reg) | __PPC_SH64(32) |
__PPC_ME64(31)));
> addr++;
>
> - /* oris r3,r3,(op)@h */
> - patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ORIS |
> ___PPC_RA(3) | - ___PPC_RS(3) | ((val >> 16) & 0xffff)));
> + /* oris reg,reg,(op)@h */
> + patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ORIS |
> ___PPC_RA(reg) | + ___PPC_RS(reg) | ((val >> 16) & 0xffff)));
> addr++;
>
> - /* ori r3,r3,(op)@l */
> - patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ORI |
> ___PPC_RA(3) | - ___PPC_RS(3) | (val & 0xffff)));
> + /* ori reg,reg,(op)@l */
> + patch_instruction((struct ppc_inst *)addr, ppc_inst(PPC_INST_ORI |
> ___PPC_RA(reg) | + ___PPC_RS(reg) | (val & 0xffff)));
> }
>
> int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct
> kprobe *p) {
> - struct ppc_inst branch_op_callback, branch_emulate_step;
> + struct ppc_inst branch_op_callback, branch_emulate_step, temp;
> kprobe_opcode_t *op_callback_addr, *emulate_step_addr, *buff;
> long b_offset;
> unsigned long nip, size;
> @@ -240,7 +240,7 @@ int arch_prepare_optimized_kprobe(struct
> optimized_kprobe *op, struct kprobe *p) * Fixup the template with
> instructions to:
> * 1. load the address of the actual probepoint
> */
> - patch_imm64_load_insns((unsigned long)op, buff + TMPL_OP_IDX);
> + patch_imm64_load_insns((unsigned long)op, 3, buff + TMPL_OP_IDX);
>
> /*
> * 2. branch to optimized_callback() and emulate_step()
> @@ -271,7 +271,11 @@ int arch_prepare_optimized_kprobe(struct
> optimized_kprobe *op, struct kprobe *p) /*
> * 3. load instruction to be emulated into relevant register, and
> */
> - patch_imm32_load_insns(*p->ainsn.insn, buff + TMPL_INSN_IDX);
> + temp = ppc_inst_read((struct ppc_inst *)p->ainsn.insn);
> + patch_imm64_load_insns(ppc_inst_val(temp) |
> + ((u64)ppc_inst_suffix(temp) << 32),
> + 4,
> + buff + TMPL_INSN_IDX);
>
> /*
> * 4. branch back from trampoline
> diff --git a/arch/powerpc/kernel/optprobes_head.S
> b/arch/powerpc/kernel/optprobes_head.S index cf383520843f..ff8ba4d3824d
> 100644
> --- a/arch/powerpc/kernel/optprobes_head.S
> +++ b/arch/powerpc/kernel/optprobes_head.S
> @@ -94,6 +94,9 @@ optprobe_template_insn:
> /* 2, Pass instruction to be emulated in r4 */
> nop
> nop
> + nop
> + nop
> + nop
>
> .global optprobe_template_call_emulate
> optprobe_template_call_emulate:
> diff --git a/arch/powerpc/lib/code-patching.c
> b/arch/powerpc/lib/code-patching.c index 5b2f66d06b1e..b32fa707725e 100644
> --- a/arch/powerpc/lib/code-patching.c
> +++ b/arch/powerpc/lib/code-patching.c
> @@ -24,13 +24,18 @@ static int __patch_instruction(struct ppc_inst
> *exec_addr, struct ppc_inst instr {
> int err = 0;
>
> - __put_user_asm(ppc_inst_val(instr), patch_addr, err, "stw");
> - if (err)
> - return err;
> + if (!ppc_inst_prefixed(instr)) {
> + __put_user_asm(ppc_inst_val(instr), patch_addr, err, "stw");
> + if (err)
> + return err;
> + } else {
> + __put_user_asm((u64)ppc_inst_suffix(instr) << 32 | ppc_inst_val(instr),
> patch_addr, err, "std"); + if (err)
> + return err;
> + }
>
> asm ("dcbst 0, %0; sync; icbi 0,%1; sync; isync" :: "r" (patch_addr),
> "r" (exec_addr));
> -
> return 0;
> }
>
> diff --git a/arch/powerpc/lib/feature-fixups.c
> b/arch/powerpc/lib/feature-fixups.c index f4845e740338..243011f85287 100644
> --- a/arch/powerpc/lib/feature-fixups.c
> +++ b/arch/powerpc/lib/feature-fixups.c
> @@ -84,12 +84,13 @@ static int patch_feature_section(unsigned long value,
> struct fixup_entry *fcur) src = alt_start;
> dest = start;
>
> - for (; src < alt_end; src++, dest++) {
> + for (; src < alt_end; src = (void *)src +
> ppc_inst_len(ppc_inst_read(src)), + (dest = (void *)dest +
> ppc_inst_len(ppc_inst_read(dest)))) { if (patch_alt_instruction(src, dest,
> alt_start, alt_end))
> return 1;
> }
>
> - for (; dest < end; dest++)
> + for (; dest < end; dest = (void *)dest +
> ppc_inst_len(ppc_inst(PPC_INST_NOP))) raw_patch_instruction(dest,
> ppc_inst(PPC_INST_NOP));
>
> return 0;
> diff --git a/arch/powerpc/lib/inst.c b/arch/powerpc/lib/inst.c
> index 08dedd927268..71101791edcc 100644
> --- a/arch/powerpc/lib/inst.c
> +++ b/arch/powerpc/lib/inst.c
> @@ -6,6 +6,45 @@
> #include <linux/uaccess.h>
> #include <asm/inst.h>
>
> +#ifdef __powerpc64__
> +int probe_user_read_inst(struct ppc_inst *inst,
> + struct ppc_inst *nip)
> +{
> + unsigned int val, suffix;
> + int err;
> +
> + err = probe_user_read(&val, nip, sizeof(val));
> + if (err)
> + return err;
> + if ((val >> 26) == 1) {
> + err = probe_user_read(&suffix, (void *)nip+4,
> + sizeof(unsigned int));
> + *inst = ppc_inst_prefix(val, suffix);
> + } else {
> + *inst = ppc_inst(val);
> + }
> + return err;
> +}
> +
> +int probe_kernel_read_inst(struct ppc_inst *inst,
> + struct ppc_inst *src)
> +{
> + unsigned int val, suffix;
> + int err;
> +
> + err = probe_kernel_read(&val, src, sizeof(val));
> + if (err)
> + return err;
> + if ((val >> 26) == 1) {
> + err = probe_kernel_read(&suffix, (void *)src+4,
> + sizeof(unsigned int));
> + *inst = ppc_inst_prefix(val, suffix);
> + } else {
> + *inst = ppc_inst(val);
> + }
> + return err;
> +}
> +#else
> int probe_user_read_inst(struct ppc_inst *inst,
> struct ppc_inst *nip)
> {
> @@ -27,3 +66,4 @@ int probe_kernel_read_inst(struct ppc_inst *inst,
> *inst = ppc_inst(val);
> return err;
> }
> +#endif /* __powerpc64__ */
> diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
> index 95a56bb1ba3f..ecd756c346fd 100644
> --- a/arch/powerpc/lib/sstep.c
> +++ b/arch/powerpc/lib/sstep.c
> @@ -1169,10 +1169,12 @@ int analyse_instr(struct instruction_op *op, const
> struct pt_regs *regs, unsigned long int imm;
> unsigned long int val, val2;
> unsigned int mb, me, sh;
> - unsigned int word;
> + unsigned int word, suffix;
> long ival;
>
> word = ppc_inst_val(instr);
> + suffix = ppc_inst_suffix(instr);
> +
> op->type = COMPUTE;
>
> opcode = ppc_inst_primary_opcode(instr);
> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
> index fb2563079046..1d6e66eb2dab 100644
> --- a/arch/powerpc/xmon/xmon.c
> +++ b/arch/powerpc/xmon/xmon.c
> @@ -758,8 +758,8 @@ static int xmon_bpt(struct pt_regs *regs)
>
> /* Are we at the trap at bp->instr[1] for some bp? */
> bp = in_breakpoint_table(regs->nip, &offset);
> - if (bp != NULL && offset == 4) {
> - regs->nip = bp->address + 4;
> + if (bp != NULL && (offset == 4 || offset == 8)) {
> + regs->nip = bp->address + offset;
> atomic_dec(&bp->ref_count);
> return 1;
> }
> diff --git a/arch/powerpc/xmon/xmon_bpts.S b/arch/powerpc/xmon/xmon_bpts.S
> index f3ad0ab50854..69726814cd27 100644
> --- a/arch/powerpc/xmon/xmon_bpts.S
> +++ b/arch/powerpc/xmon/xmon_bpts.S
> @@ -4,6 +4,8 @@
> #include <asm/asm-offsets.h>
> #include "xmon_bpts.h"
>
> +/* Prefixed instructions can not cross 64 byte boundaries */
> +.align 6
> .global bpt_table
> bpt_table:
> .space NBPTS * BPT_SIZE
^ permalink raw reply
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