* [PATCH v3 02/10] powerpc/mm: Move vma_mmu_pagesize() and hugetlb_get_unmapped_area() to slice.c
From: Christophe Leroy @ 2021-11-29 14:19 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: linux-mm, linuxppc-dev, linux-kernel
In-Reply-To: <cover.1638195388.git.christophe.leroy@csgroup.eu>
vma_mmu_pagesize() is only required for slices,
otherwise there is a generic weak version.
hugetlb_get_unmapped_area() is dedicated to slices.
radix__hugetlb_get_unmapped_area() as well.
Move them to slice.c
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/book3s/64/hugetlb.h | 4 --
arch/powerpc/mm/book3s64/radix_hugetlbpage.c | 55 --------------
arch/powerpc/mm/book3s64/slice.c | 76 ++++++++++++++++++++
arch/powerpc/mm/hugetlbpage.c | 28 --------
4 files changed, 76 insertions(+), 87 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 12e150e615b7..b37a28f62cf6 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -8,10 +8,6 @@
*/
void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-extern unsigned long
-radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags);
extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index 23d3e08911d3..d2fb776febb4 100644
--- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -41,61 +41,6 @@ void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long st
radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
}
-/*
- * A vairant of hugetlb_get_unmapped_area doing topdown search
- * FIXME!! should we do as x86 does or non hugetlb area does ?
- * ie, use topdown or not based on mmap_is_legacy check ?
- */
-unsigned long
-radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
-{
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- struct hstate *h = hstate_file(file);
- int fixed = (flags & MAP_FIXED);
- unsigned long high_limit;
- struct vm_unmapped_area_info info;
-
- high_limit = DEFAULT_MAP_WINDOW;
- if (addr >= high_limit || (fixed && (addr + len > high_limit)))
- high_limit = TASK_SIZE;
-
- if (len & ~huge_page_mask(h))
- return -EINVAL;
- if (len > high_limit)
- return -ENOMEM;
-
- if (fixed) {
- if (addr > high_limit - len)
- return -ENOMEM;
- if (prepare_hugepage_range(file, addr, len))
- return -EINVAL;
- return addr;
- }
-
- if (addr) {
- addr = ALIGN(addr, huge_page_size(h));
- vma = find_vma(mm, addr);
- if (high_limit - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
- /*
- * We are always doing an topdown search here. Slice code
- * does that too.
- */
- info.flags = VM_UNMAPPED_AREA_TOPDOWN;
- info.length = len;
- info.low_limit = max(PAGE_SIZE, mmap_min_addr);
- info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
- info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
-
- return vm_unmapped_area(&info);
-}
-
void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index c83be371c6e7..4c3e9601fdf6 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -777,4 +777,80 @@ int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
return !slice_check_range_fits(mm, maskp, addr, len);
}
+
+unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
+{
+ /* With radix we don't use slice, so derive it from vma*/
+ if (radix_enabled())
+ return vma_kernel_pagesize(vma);
+
+ return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start));
+}
+
+/*
+ * A variant of hugetlb_get_unmapped_area() doing topdown search
+ * FIXME!! should we do as x86 does or non hugetlb area does ?
+ * ie, use topdown or not based on mmap_is_legacy check ?
+ */
+static unsigned long
+radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ struct hstate *h = hstate_file(file);
+ int fixed = (flags & MAP_FIXED);
+ unsigned long high_limit;
+ struct vm_unmapped_area_info info;
+
+ high_limit = DEFAULT_MAP_WINDOW;
+ if (addr >= high_limit || (fixed && (addr + len > high_limit)))
+ high_limit = TASK_SIZE;
+
+ if (len & ~huge_page_mask(h))
+ return -EINVAL;
+ if (len > high_limit)
+ return -ENOMEM;
+
+ if (fixed) {
+ if (addr > high_limit - len)
+ return -ENOMEM;
+ if (prepare_hugepage_range(file, addr, len))
+ return -EINVAL;
+ return addr;
+ }
+
+ if (addr) {
+ addr = ALIGN(addr, huge_page_size(h));
+ vma = find_vma(mm, addr);
+ if (high_limit - len >= addr && addr >= mmap_min_addr &&
+ (!vma || addr + len <= vm_start_gap(vma)))
+ return addr;
+ }
+ /*
+ * We are always doing an topdown search here. Slice code
+ * does that too.
+ */
+ info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+ info.length = len;
+ info.low_limit = max(PAGE_SIZE, mmap_min_addr);
+ info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+ info.align_offset = 0;
+
+ return vm_unmapped_area(&info);
+}
+
+unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ struct hstate *hstate = hstate_file(file);
+ int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
+
+ if (radix_enabled())
+ return radix__hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
+
+ return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
+}
#endif
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 82d8b368ca6d..eb9de09e49a3 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -542,34 +542,6 @@ struct page *follow_huge_pd(struct vm_area_struct *vma,
return page;
}
-#ifdef CONFIG_PPC_MM_SLICES
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
-{
- struct hstate *hstate = hstate_file(file);
- int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
-
-#ifdef CONFIG_PPC_RADIX_MMU
- if (radix_enabled())
- return radix__hugetlb_get_unmapped_area(file, addr, len,
- pgoff, flags);
-#endif
- return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
-}
-#endif
-
-unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
-{
- /* With radix we don't use slice, so derive it from vma*/
- if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled()) {
- unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
-
- return 1UL << mmu_psize_to_shift(psize);
- }
- return vma_kernel_pagesize(vma);
-}
-
bool __init arch_hugetlb_valid_size(unsigned long size)
{
int shift = __ffs(size);
--
2.33.1
^ permalink raw reply related
* Re: [PATCH v4 1/5] powerpc/inst: Refactor ___get_user_instr()
From: kernel test robot @ 2021-11-29 14:36 UTC (permalink / raw)
To: Christophe Leroy, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman
Cc: linuxppc-dev, kbuild-all, linux-kernel
In-Reply-To: <97a171efd8c582e2bae82c31f2a9519823a20d3f.1638186773.git.christophe.leroy@csgroup.eu>
Hi Christophe,
I love your patch! Perhaps something to improve:
[auto build test WARNING on powerpc/next]
[also build test WARNING on v5.16-rc3 next-20211129]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Christophe-Leroy/powerpc-inst-Refactor-___get_user_instr/20211129-195613
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-allyesconfig (https://download.01.org/0day-ci/archive/20211129/202111292213.TqMVcy38-lkp@intel.com/config)
compiler: powerpc-linux-gcc (GCC) 11.2.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/12f08114cece066b2640aef99e2bc74f49eebef5
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Christophe-Leroy/powerpc-inst-Refactor-___get_user_instr/20211129-195613
git checkout 12f08114cece066b2640aef99e2bc74f49eebef5
# save the config file to linux build tree
mkdir build_dir
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.2.0 make.cross O=build_dir ARCH=powerpc SHELL=/bin/bash arch/powerpc/kernel/
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All warnings (new ones prefixed by >>):
In file included from arch/powerpc/include/asm/hw_breakpoint.h:13,
from arch/powerpc/include/asm/processor.h:43,
from arch/powerpc/include/asm/thread_info.h:40,
from include/linux/thread_info.h:60,
from include/asm-generic/preempt.h:5,
from ./arch/powerpc/include/generated/asm/preempt.h:1,
from include/linux/preempt.h:78,
from include/linux/spinlock.h:55,
from include/linux/mmzone.h:8,
from include/linux/gfp.h:6,
from include/linux/mm.h:10,
from arch/powerpc/kernel/align.c:17:
arch/powerpc/kernel/align.c: In function 'fix_alignment':
>> arch/powerpc/include/asm/inst.h:12:32: warning: variable '__suffix' set but not used [-Wunused-but-set-variable]
12 | unsigned int __prefix, __suffix; \
| ^~~~~~~~
arch/powerpc/include/asm/inst.h:31:34: note: in expansion of macro '___get_user_instr'
31 | #define __get_user_instr(x, ptr) ___get_user_instr(__get_user, x, ptr)
| ^~~~~~~~~~~~~~~~~
arch/powerpc/kernel/align.c:310:21: note: in expansion of macro '__get_user_instr'
310 | r = __get_user_instr(instr, (void __user *)regs->nip);
| ^~~~~~~~~~~~~~~~
--
In file included from arch/powerpc/include/asm/hw_breakpoint.h:13,
from arch/powerpc/include/asm/processor.h:43,
from arch/powerpc/include/asm/thread_info.h:40,
from include/linux/thread_info.h:60,
from arch/powerpc/include/asm/ptrace.h:323,
from arch/powerpc/include/asm/hw_irq.h:12,
from arch/powerpc/include/asm/irqflags.h:12,
from include/linux/irqflags.h:16,
from include/asm-generic/cmpxchg-local.h:6,
from arch/powerpc/include/asm/cmpxchg.h:526,
from arch/powerpc/include/asm/atomic.h:11,
from include/linux/atomic.h:7,
from include/linux/rcupdate.h:25,
from include/linux/rculist.h:11,
from include/linux/pid.h:5,
from include/linux/sched.h:14,
from include/linux/uaccess.h:8,
from arch/powerpc/kernel/hw_breakpoint_constraints.c:3:
arch/powerpc/kernel/hw_breakpoint_constraints.c: In function 'wp_get_instr_detail':
>> arch/powerpc/include/asm/inst.h:12:32: warning: variable '__suffix' set but not used [-Wunused-but-set-variable]
12 | unsigned int __prefix, __suffix; \
| ^~~~~~~~
arch/powerpc/include/asm/inst.h:31:34: note: in expansion of macro '___get_user_instr'
31 | #define __get_user_instr(x, ptr) ___get_user_instr(__get_user, x, ptr)
| ^~~~~~~~~~~~~~~~~
arch/powerpc/kernel/hw_breakpoint_constraints.c:135:13: note: in expansion of macro '__get_user_instr'
135 | if (__get_user_instr(*instr, (void __user *)regs->nip))
| ^~~~~~~~~~~~~~~~
--
In file included from arch/powerpc/include/asm/hw_breakpoint.h:13,
from arch/powerpc/include/asm/processor.h:43,
from arch/powerpc/include/asm/thread_info.h:40,
from include/linux/thread_info.h:60,
from arch/powerpc/include/asm/ptrace.h:323,
from arch/powerpc/include/asm/hw_irq.h:12,
from arch/powerpc/include/asm/irqflags.h:12,
from include/linux/irqflags.h:16,
from include/asm-generic/cmpxchg-local.h:6,
from arch/powerpc/include/asm/cmpxchg.h:526,
from arch/powerpc/include/asm/atomic.h:11,
from include/linux/atomic.h:7,
from include/linux/rcupdate.h:25,
from include/linux/rculist.h:11,
from include/linux/pid.h:5,
from include/linux/sched.h:14,
from arch/powerpc/kernel/vecemu.c:8:
arch/powerpc/kernel/vecemu.c: In function 'emulate_altivec':
>> arch/powerpc/include/asm/inst.h:12:32: warning: variable '__suffix' set but not used [-Wunused-but-set-variable]
12 | unsigned int __prefix, __suffix; \
| ^~~~~~~~
arch/powerpc/include/asm/inst.h:29:32: note: in expansion of macro '___get_user_instr'
29 | #define get_user_instr(x, ptr) ___get_user_instr(get_user, x, ptr)
| ^~~~~~~~~~~~~~~~~
arch/powerpc/kernel/vecemu.c:269:13: note: in expansion of macro 'get_user_instr'
269 | if (get_user_instr(instr, (void __user *)regs->nip))
| ^~~~~~~~~~~~~~
vim +/__suffix +12 arch/powerpc/include/asm/inst.h
650b55b707fdfa Jordan Niethe 2020-05-15 6
35506a3e2d7c4d Christophe Leroy 2021-03-10 7 #define ___get_user_instr(gu_op, dest, ptr) \
35506a3e2d7c4d Christophe Leroy 2021-03-10 8 ({ \
042e0860e1c1d6 Christophe Leroy 2021-05-20 9 long __gui_ret; \
9134806e149ebb Christophe Leroy 2021-05-20 10 u32 __user *__gui_ptr = (u32 __user *)ptr; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 11 struct ppc_inst __gui_inst; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 @12 unsigned int __prefix, __suffix; \
b3a9e523237013 Christophe Leroy 2021-05-20 13 \
b3a9e523237013 Christophe Leroy 2021-05-20 14 __chk_user_ptr(ptr); \
9134806e149ebb Christophe Leroy 2021-05-20 15 __gui_ret = gu_op(__prefix, __gui_ptr); \
35506a3e2d7c4d Christophe Leroy 2021-03-10 16 if (__gui_ret == 0) { \
12f08114cece06 Christophe Leroy 2021-11-29 17 if (IS_ENABLED(CONFIG_PPC64) && (__prefix >> 26) == OP_PREFIX) { \
9134806e149ebb Christophe Leroy 2021-05-20 18 __gui_ret = gu_op(__suffix, __gui_ptr + 1); \
042e0860e1c1d6 Christophe Leroy 2021-05-20 19 __gui_inst = ppc_inst_prefix(__prefix, __suffix); \
35506a3e2d7c4d Christophe Leroy 2021-03-10 20 } else { \
35506a3e2d7c4d Christophe Leroy 2021-03-10 21 __gui_inst = ppc_inst(__prefix); \
35506a3e2d7c4d Christophe Leroy 2021-03-10 22 } \
35506a3e2d7c4d Christophe Leroy 2021-03-10 23 if (__gui_ret == 0) \
35506a3e2d7c4d Christophe Leroy 2021-03-10 24 (dest) = __gui_inst; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 25 } \
35506a3e2d7c4d Christophe Leroy 2021-03-10 26 __gui_ret; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 27 })
35506a3e2d7c4d Christophe Leroy 2021-03-10 28
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* Re: [PATCH 1/2] tools/perf: Include global and local variants for p_stage_cyc sort key
From: Jiri Olsa @ 2021-11-29 16:25 UTC (permalink / raw)
To: Athira Rajeev
Cc: maddy, rnsastry, Arnaldo Carvalho de Melo, linux-perf-users,
Jiri Olsa, kjain, Namhyung Kim, linuxppc-dev
In-Reply-To: <F095C610-FAEC-4764-9046-4392B3C9F37A@linux.vnet.ibm.com>
On Mon, Nov 29, 2021 at 02:43:48PM +0530, Athira Rajeev wrote:
>
>
> > On 28-Nov-2021, at 10:04 PM, Jiri Olsa <jolsa@redhat.com> wrote:
> >
> > On Thu, Nov 25, 2021 at 08:18:50AM +0530, Athira Rajeev wrote:
> >> Sort key p_stage_cyc is used to present the latency
> >> cycles spend in pipeline stages. perf tool has local
> >> p_stage_cyc sort key to display this info. There is no
> >> global variant available for this sort key. local variant
> >> shows latency in a sinlge sample, whereas, global value
> >> will be useful to present the total latency (sum of
> >> latencies) in the hist entry. It represents latency
> >> number multiplied by the number of samples.
> >>
> >> Add global (p_stage_cyc) and local variant
> >> (local_p_stage_cyc) for this sort key. Use the
> >> local_p_stage_cyc as default option for "mem" sort mode.
> >> Also add this to list of dynamic sort keys.
> >>
> >> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
> >> Reported-by: Namhyung Kim <namhyung@kernel.org>
> >
> > I can't apply this to Arnaldo's perf/core, could you please rebase?
> >
> > patching file util/hist.c
> > patching file util/hist.h
> > patching file util/sort.c
> > Hunk #3 FAILED at 1392.
> > Hunk #4 succeeded at 1878 (offset 20 lines).
> > 1 out of 4 hunks FAILED -- saving rejects to file util/sort.c.rej
> > patching file util/sort.h
> >
> > thanks,
> > jirka
>
> Hi Jiri,
>
> Thanks for checking this patch.
>
> Actually these changes are on top of three other fixes from Namhyung which are already part of upstream. Below are the commits.
>
> 784e8adda4cd ("perf sort: Fix the 'weight' sort key behavior”)
> 4d03c75363ee ("perf sort: Fix the 'ins_lat' sort key behavior”)
> db4b28402909 ("perf sort: Fix the 'p_stage_cyc' sort key behavior”)
>
> I checked in Arnaldo’s perf/core, but these commits are not there. But I could see them in 'tmp.perf/urgent'
> I think perf/core is not yet updated.
ah ok, I got it applied on perf/urgent, thanks
jirka
>
> Thanks
> Athira Rajeev
>
> >
> >> ---
> >> tools/perf/util/hist.c | 4 +++-
> >> tools/perf/util/hist.h | 3 ++-
> >> tools/perf/util/sort.c | 34 +++++++++++++++++++++++++---------
> >> tools/perf/util/sort.h | 3 ++-
> >> 4 files changed, 32 insertions(+), 12 deletions(-)
> >>
> >> diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
> >> index b776465e04ef..0a8033b09e28 100644
> >> --- a/tools/perf/util/hist.c
> >> +++ b/tools/perf/util/hist.c
> >> @@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
> >> hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10);
> >> hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13);
> >> hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
> >> - hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13);
> >> + hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
> >> + hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
> >> +
> >> if (symbol_conf.nanosecs)
> >> hists__new_col_len(hists, HISTC_TIME, 16);
> >> else
> >> diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
> >> index 5343b62476e6..2752ce681108 100644
> >> --- a/tools/perf/util/hist.h
> >> +++ b/tools/perf/util/hist.h
> >> @@ -75,7 +75,8 @@ enum hist_column {
> >> HISTC_MEM_BLOCKED,
> >> HISTC_LOCAL_INS_LAT,
> >> HISTC_GLOBAL_INS_LAT,
> >> - HISTC_P_STAGE_CYC,
> >> + HISTC_LOCAL_P_STAGE_CYC,
> >> + HISTC_GLOBAL_P_STAGE_CYC,
> >> HISTC_NR_COLS, /* Last entry */
> >> };
> >>
> >> diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
> >> index e9216a292a04..e978f7883e07 100644
> >> --- a/tools/perf/util/sort.c
> >> +++ b/tools/perf/util/sort.c
> >> @@ -37,7 +37,7 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault";
> >> const char *parent_pattern = default_parent_pattern;
> >> const char *default_sort_order = "comm,dso,symbol";
> >> const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
> >> -const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc";
> >> +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc";
> >> const char default_top_sort_order[] = "dso,symbol";
> >> const char default_diff_sort_order[] = "dso,symbol";
> >> const char default_tracepoint_sort_order[] = "trace";
> >> @@ -46,8 +46,8 @@ const char *field_order;
> >> regex_t ignore_callees_regex;
> >> int have_ignore_callees = 0;
> >> enum sort_mode sort__mode = SORT_MODE__NORMAL;
> >> -const char *dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"};
> >> -const char *arch_specific_sort_keys[] = {"p_stage_cyc"};
> >> +const char *dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"};
> >> +const char *arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"};
> >>
> >> /*
> >> * Replaces all occurrences of a char used with the:
> >> @@ -1392,22 +1392,37 @@ struct sort_entry sort_global_ins_lat = {
> >> };
> >>
> >> static int64_t
> >> -sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
> >> +sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
> >> {
> >> return left->p_stage_cyc - right->p_stage_cyc;
> >> }
> >>
> >> +static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
> >> + size_t size, unsigned int width)
> >> +{
> >> + return repsep_snprintf(bf, size, "%-*u", width,
> >> + he->p_stage_cyc * he->stat.nr_events);
> >> +}
> >> +
> >> +
> >> static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
> >> size_t size, unsigned int width)
> >> {
> >> return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
> >> }
> >>
> >> -struct sort_entry sort_p_stage_cyc = {
> >> - .se_header = "Pipeline Stage Cycle",
> >> - .se_cmp = sort__global_p_stage_cyc_cmp,
> >> +struct sort_entry sort_local_p_stage_cyc = {
> >> + .se_header = "Local Pipeline Stage Cycle",
> >> + .se_cmp = sort__p_stage_cyc_cmp,
> >> .se_snprintf = hist_entry__p_stage_cyc_snprintf,
> >> - .se_width_idx = HISTC_P_STAGE_CYC,
> >> + .se_width_idx = HISTC_LOCAL_P_STAGE_CYC,
> >> +};
> >> +
> >> +struct sort_entry sort_global_p_stage_cyc = {
> >> + .se_header = "Pipeline Stage Cycle",
> >> + .se_cmp = sort__p_stage_cyc_cmp,
> >> + .se_snprintf = hist_entry__global_p_stage_cyc_snprintf,
> >> + .se_width_idx = HISTC_GLOBAL_P_STAGE_CYC,
> >> };
> >>
> >> struct sort_entry sort_mem_daddr_sym = {
> >> @@ -1858,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = {
> >> DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
> >> DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
> >> DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
> >> - DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc),
> >> + DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc),
> >> + DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc),
> >> };
> >>
> >> #undef DIM
> >> diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
> >> index 3c7518378d62..83abe5e6812a 100644
> >> --- a/tools/perf/util/sort.h
> >> +++ b/tools/perf/util/sort.h
> >> @@ -235,7 +235,8 @@ enum sort_type {
> >> SORT_CODE_PAGE_SIZE,
> >> SORT_LOCAL_INS_LAT,
> >> SORT_GLOBAL_INS_LAT,
> >> - SORT_PIPELINE_STAGE_CYC,
> >> + SORT_LOCAL_PIPELINE_STAGE_CYC,
> >> + SORT_GLOBAL_PIPELINE_STAGE_CYC,
> >>
> >> /* branch stack specific sort keys */
> >> __SORT_BRANCH_STACK,
> >> --
> >> 2.27.0
>
^ permalink raw reply
* Re: [PATCH v5 05/12] KVM: RISC-V: Use Makefile.kvm for common files
From: David Woodhouse @ 2021-11-29 16:44 UTC (permalink / raw)
To: Anup Patel
Cc: Anup Patel, wanpengli @ tencent . com, kvm, Joao Martins,
Will Deacon, kvmarm, linux-s390, joro @ 8bytes . org, Huacai Chen,
Christian Borntraeger, Aleksandar Markovic, karahmed,
Catalin Marinas, Suzuki K Poulose, butt3rflyh4ck, Boris Ostrovsky,
Alexandru Elisei, linux-arm-kernel, jmattson @ google . com,
seanjc @ google . com, mtosatti @ redhat . com, linux-mips,
James Morse, kvm-riscv, Marc Zyngier, Paolo Bonzini,
vkuznets @ redhat . com, linuxppc-dev
In-Reply-To: <CAAhSdy307DqNuQEFCu2ze2jXJ7taDE6y6SwY9nHGA8yNPfggiQ@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 725 bytes --]
On Tue, 2021-11-23 at 14:42 +0530, Anup Patel wrote:
> On Sun, Nov 21, 2021 at 6:25 PM David Woodhouse <dwmw2@infradead.org> wrote:
>
> > From: David Woodhouse <dwmw@amazon.co.uk>
> > Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
>
> Looks good to me.
>
> For KVM RISC-V,
>
> Acked-by: Anup Patel <anup.patel@wdc.com>
> Reviewed-by: Anup Patel <anup.patel@wdc.com>
Thanks. I've included those in the tree at
https://git.infradead.org/users/dwmw2/linux.git/shortlog/refs/heads/xen-evtchn
which is based on kvm/master but rebases cleanly to kvm/queue.
I'm working on additional support (IPI, timers, etc.) to go on top but
will post that in a separate series rather than adding more to this
one.
[-- Attachment #2: smime.p7s --]
[-- Type: application/pkcs7-signature, Size: 5174 bytes --]
^ permalink raw reply
* Re: [PATCH 1/2] tools/perf: Include global and local variants for p_stage_cyc sort key
From: Jiri Olsa @ 2021-11-29 17:11 UTC (permalink / raw)
To: Athira Rajeev
Cc: maddy, rnsastry, acme, linux-perf-users, jolsa, kjain, namhyung,
linuxppc-dev
In-Reply-To: <20211125024851.22895-1-atrajeev@linux.vnet.ibm.com>
On Thu, Nov 25, 2021 at 08:18:50AM +0530, Athira Rajeev wrote:
> Sort key p_stage_cyc is used to present the latency
> cycles spend in pipeline stages. perf tool has local
> p_stage_cyc sort key to display this info. There is no
> global variant available for this sort key. local variant
> shows latency in a sinlge sample, whereas, global value
> will be useful to present the total latency (sum of
> latencies) in the hist entry. It represents latency
> number multiplied by the number of samples.
>
> Add global (p_stage_cyc) and local variant
> (local_p_stage_cyc) for this sort key. Use the
> local_p_stage_cyc as default option for "mem" sort mode.
> Also add this to list of dynamic sort keys.
>
> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
> Reported-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/util/hist.c | 4 +++-
> tools/perf/util/hist.h | 3 ++-
> tools/perf/util/sort.c | 34 +++++++++++++++++++++++++---------
> tools/perf/util/sort.h | 3 ++-
> 4 files changed, 32 insertions(+), 12 deletions(-)
>
> diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
> index b776465e04ef..0a8033b09e28 100644
> --- a/tools/perf/util/hist.c
> +++ b/tools/perf/util/hist.c
> @@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
> hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10);
> hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13);
> hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
> - hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13);
> + hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
> + hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
> +
> if (symbol_conf.nanosecs)
> hists__new_col_len(hists, HISTC_TIME, 16);
> else
> diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
> index 5343b62476e6..2752ce681108 100644
> --- a/tools/perf/util/hist.h
> +++ b/tools/perf/util/hist.h
> @@ -75,7 +75,8 @@ enum hist_column {
> HISTC_MEM_BLOCKED,
> HISTC_LOCAL_INS_LAT,
> HISTC_GLOBAL_INS_LAT,
> - HISTC_P_STAGE_CYC,
> + HISTC_LOCAL_P_STAGE_CYC,
> + HISTC_GLOBAL_P_STAGE_CYC,
> HISTC_NR_COLS, /* Last entry */
> };
>
> diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
> index e9216a292a04..e978f7883e07 100644
> --- a/tools/perf/util/sort.c
> +++ b/tools/perf/util/sort.c
> @@ -37,7 +37,7 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault";
> const char *parent_pattern = default_parent_pattern;
> const char *default_sort_order = "comm,dso,symbol";
> const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
> -const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc";
> +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc";
> const char default_top_sort_order[] = "dso,symbol";
> const char default_diff_sort_order[] = "dso,symbol";
> const char default_tracepoint_sort_order[] = "trace";
> @@ -46,8 +46,8 @@ const char *field_order;
> regex_t ignore_callees_regex;
> int have_ignore_callees = 0;
> enum sort_mode sort__mode = SORT_MODE__NORMAL;
> -const char *dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"};
> -const char *arch_specific_sort_keys[] = {"p_stage_cyc"};
> +const char *dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"};
so you also add global ins_lat, right? will this change
some default behaviour?
> +const char *arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"};
nit.. both dynamic_headers and arch_specific_sort_keys could be static right?
thanks,
jirka
>
> /*
> * Replaces all occurrences of a char used with the:
> @@ -1392,22 +1392,37 @@ struct sort_entry sort_global_ins_lat = {
> };
>
> static int64_t
> -sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
> +sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
> {
> return left->p_stage_cyc - right->p_stage_cyc;
> }
>
> +static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
> + size_t size, unsigned int width)
> +{
> + return repsep_snprintf(bf, size, "%-*u", width,
> + he->p_stage_cyc * he->stat.nr_events);
> +}
> +
> +
> static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
> size_t size, unsigned int width)
> {
> return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
> }
>
> -struct sort_entry sort_p_stage_cyc = {
> - .se_header = "Pipeline Stage Cycle",
> - .se_cmp = sort__global_p_stage_cyc_cmp,
> +struct sort_entry sort_local_p_stage_cyc = {
> + .se_header = "Local Pipeline Stage Cycle",
> + .se_cmp = sort__p_stage_cyc_cmp,
> .se_snprintf = hist_entry__p_stage_cyc_snprintf,
> - .se_width_idx = HISTC_P_STAGE_CYC,
> + .se_width_idx = HISTC_LOCAL_P_STAGE_CYC,
> +};
> +
> +struct sort_entry sort_global_p_stage_cyc = {
> + .se_header = "Pipeline Stage Cycle",
> + .se_cmp = sort__p_stage_cyc_cmp,
> + .se_snprintf = hist_entry__global_p_stage_cyc_snprintf,
> + .se_width_idx = HISTC_GLOBAL_P_STAGE_CYC,
> };
>
> struct sort_entry sort_mem_daddr_sym = {
> @@ -1858,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = {
> DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
> DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
> DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
> - DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc),
> + DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc),
> + DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc),
> };
>
> #undef DIM
> diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
> index 3c7518378d62..83abe5e6812a 100644
> --- a/tools/perf/util/sort.h
> +++ b/tools/perf/util/sort.h
> @@ -235,7 +235,8 @@ enum sort_type {
> SORT_CODE_PAGE_SIZE,
> SORT_LOCAL_INS_LAT,
> SORT_GLOBAL_INS_LAT,
> - SORT_PIPELINE_STAGE_CYC,
> + SORT_LOCAL_PIPELINE_STAGE_CYC,
> + SORT_GLOBAL_PIPELINE_STAGE_CYC,
>
> /* branch stack specific sort keys */
> __SORT_BRANCH_STACK,
> --
> 2.27.0
>
^ permalink raw reply
* Re: [PATCH v4 1/5] powerpc/inst: Refactor ___get_user_instr()
From: kernel test robot @ 2021-11-29 17:09 UTC (permalink / raw)
To: Christophe Leroy, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman
Cc: linuxppc-dev, kbuild-all, linux-kernel
In-Reply-To: <97a171efd8c582e2bae82c31f2a9519823a20d3f.1638186773.git.christophe.leroy@csgroup.eu>
Hi Christophe,
I love your patch! Yet something to improve:
[auto build test ERROR on powerpc/next]
[also build test ERROR on v5.16-rc3 next-20211129]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Christophe-Leroy/powerpc-inst-Refactor-___get_user_instr/20211129-195613
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-allnoconfig (https://download.01.org/0day-ci/archive/20211130/202111300028.pvdtx2Vc-lkp@intel.com/config)
compiler: powerpc-linux-gcc (GCC) 11.2.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/12f08114cece066b2640aef99e2bc74f49eebef5
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Christophe-Leroy/powerpc-inst-Refactor-___get_user_instr/20211129-195613
git checkout 12f08114cece066b2640aef99e2bc74f49eebef5
# save the config file to linux build tree
mkdir build_dir
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.2.0 make.cross O=build_dir ARCH=powerpc SHELL=/bin/bash arch/powerpc/kernel/
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
In file included from arch/powerpc/include/asm/hw_breakpoint.h:13,
from arch/powerpc/include/asm/processor.h:43,
from arch/powerpc/include/asm/thread_info.h:40,
from include/linux/thread_info.h:60,
from include/asm-generic/preempt.h:5,
from ./arch/powerpc/include/generated/asm/preempt.h:1,
from include/linux/preempt.h:78,
from include/linux/spinlock.h:55,
from include/linux/mmzone.h:8,
from include/linux/gfp.h:6,
from include/linux/mm.h:10,
from arch/powerpc/kernel/align.c:17:
arch/powerpc/kernel/align.c: In function 'fix_alignment':
>> arch/powerpc/include/asm/inst.h:12:32: error: variable '__suffix' set but not used [-Werror=unused-but-set-variable]
12 | unsigned int __prefix, __suffix; \
| ^~~~~~~~
arch/powerpc/include/asm/inst.h:31:34: note: in expansion of macro '___get_user_instr'
31 | #define __get_user_instr(x, ptr) ___get_user_instr(__get_user, x, ptr)
| ^~~~~~~~~~~~~~~~~
arch/powerpc/kernel/align.c:310:21: note: in expansion of macro '__get_user_instr'
310 | r = __get_user_instr(instr, (void __user *)regs->nip);
| ^~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
--
In file included from arch/powerpc/include/asm/hw_breakpoint.h:13,
from arch/powerpc/include/asm/processor.h:43,
from arch/powerpc/include/asm/thread_info.h:40,
from include/linux/thread_info.h:60,
from arch/powerpc/include/asm/ptrace.h:323,
from arch/powerpc/include/asm/hw_irq.h:12,
from arch/powerpc/include/asm/irqflags.h:12,
from include/linux/irqflags.h:16,
from include/asm-generic/cmpxchg-local.h:6,
from arch/powerpc/include/asm/cmpxchg.h:526,
from arch/powerpc/include/asm/atomic.h:11,
from include/linux/atomic.h:7,
from include/linux/rcupdate.h:25,
from include/linux/rculist.h:11,
from include/linux/pid.h:5,
from include/linux/sched.h:14,
from include/linux/uaccess.h:8,
from arch/powerpc/kernel/hw_breakpoint_constraints.c:3:
arch/powerpc/kernel/hw_breakpoint_constraints.c: In function 'wp_get_instr_detail':
>> arch/powerpc/include/asm/inst.h:12:32: error: variable '__suffix' set but not used [-Werror=unused-but-set-variable]
12 | unsigned int __prefix, __suffix; \
| ^~~~~~~~
arch/powerpc/include/asm/inst.h:31:34: note: in expansion of macro '___get_user_instr'
31 | #define __get_user_instr(x, ptr) ___get_user_instr(__get_user, x, ptr)
| ^~~~~~~~~~~~~~~~~
arch/powerpc/kernel/hw_breakpoint_constraints.c:135:13: note: in expansion of macro '__get_user_instr'
135 | if (__get_user_instr(*instr, (void __user *)regs->nip))
| ^~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
vim +/__suffix +12 arch/powerpc/include/asm/inst.h
650b55b707fdfa Jordan Niethe 2020-05-15 6
35506a3e2d7c4d Christophe Leroy 2021-03-10 7 #define ___get_user_instr(gu_op, dest, ptr) \
35506a3e2d7c4d Christophe Leroy 2021-03-10 8 ({ \
042e0860e1c1d6 Christophe Leroy 2021-05-20 9 long __gui_ret; \
9134806e149ebb Christophe Leroy 2021-05-20 10 u32 __user *__gui_ptr = (u32 __user *)ptr; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 11 struct ppc_inst __gui_inst; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 @12 unsigned int __prefix, __suffix; \
b3a9e523237013 Christophe Leroy 2021-05-20 13 \
b3a9e523237013 Christophe Leroy 2021-05-20 14 __chk_user_ptr(ptr); \
9134806e149ebb Christophe Leroy 2021-05-20 15 __gui_ret = gu_op(__prefix, __gui_ptr); \
35506a3e2d7c4d Christophe Leroy 2021-03-10 16 if (__gui_ret == 0) { \
12f08114cece06 Christophe Leroy 2021-11-29 17 if (IS_ENABLED(CONFIG_PPC64) && (__prefix >> 26) == OP_PREFIX) { \
9134806e149ebb Christophe Leroy 2021-05-20 18 __gui_ret = gu_op(__suffix, __gui_ptr + 1); \
042e0860e1c1d6 Christophe Leroy 2021-05-20 19 __gui_inst = ppc_inst_prefix(__prefix, __suffix); \
35506a3e2d7c4d Christophe Leroy 2021-03-10 20 } else { \
35506a3e2d7c4d Christophe Leroy 2021-03-10 21 __gui_inst = ppc_inst(__prefix); \
35506a3e2d7c4d Christophe Leroy 2021-03-10 22 } \
35506a3e2d7c4d Christophe Leroy 2021-03-10 23 if (__gui_ret == 0) \
35506a3e2d7c4d Christophe Leroy 2021-03-10 24 (dest) = __gui_inst; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 25 } \
35506a3e2d7c4d Christophe Leroy 2021-03-10 26 __gui_ret; \
35506a3e2d7c4d Christophe Leroy 2021-03-10 27 })
35506a3e2d7c4d Christophe Leroy 2021-03-10 28
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* RE: bug: usb: gadget: FSL_UDC_CORE Corrupted request list leads to unrecoverable loop.
From: Eugene Bordenkircher @ 2021-11-29 17:24 UTC (permalink / raw)
To: Thorsten Leemhuis, Joakim Tjernlund,
linuxppc-dev@lists.ozlabs.org, linux-usb@vger.kernel.org
Cc: gregkh@linuxfoundation.org, balbi@kernel.org, leoyang.li@nxp.com
In-Reply-To: <726d3561-1842-72c7-d4cb-9a99211bb05c@leemhuis.info>
The final result of our testing is that the patch set posted seems to address all known defects in the Linux kernel. The mentioned additional problems are entirely caused by the antivirus solution on the windows box. The antivirus solution blocks the disconnect messages from reaching the RNDIS driver so it has no idea the USB device went away. There is nothing we can do to address this in the Linux kernel.
I propose we move forward with the patchset.
Eugene T. Bordenkircher
-----Original Message-----
From: Thorsten Leemhuis <regressions@leemhuis.info>
Sent: Thursday, November 25, 2021 5:59 AM
To: Eugene Bordenkircher <Eugene_Bordenkircher@selinc.com>; Thorsten Leemhuis <regressions@leemhuis.info>; Joakim Tjernlund <Joakim.Tjernlund@infinera.com>; linuxppc-dev@lists.ozlabs.org; linux-usb@vger.kernel.org
Cc: leoyang.li@nxp.com; gregkh@linuxfoundation.org; balbi@kernel.org
Subject: Re: bug: usb: gadget: FSL_UDC_CORE Corrupted request list leads to unrecoverable loop.
Hi, this is your Linux kernel regression tracker speaking.
Top-posting for once, to make this easy to process for everyone:
Li Yang and Felipe Balbi: how to move on with this? It's quite an old regression, but nevertheless it is one and thus should be fixed. Part of my position is to make that happen and thus remind developers and maintainers about this until the regression is resolved.
Ciao, Thorsten
On 16.11.21 20:11, Eugene Bordenkircher wrote:
> On 02.11.21 22:15, Joakim Tjernlund wrote:
>> On Sat, 2021-10-30 at 14:20 +0000, Joakim Tjernlund wrote:
>>> On Fri, 2021-10-29 at 17:14 +0000, Eugene Bordenkircher wrote:
>>
>>>> We've discovered a situation where the FSL udc driver (drivers/usb/gadget/udc/fsl_udc_core.c) will enter a loop iterating over the request queue, but the queue has been corrupted at some point so it loops infinitely. I believe we have narrowed into the offending code, but we are in need of assistance trying to find an appropriate fix for the problem. The identified code appears to be in all versions of the Linux kernel the driver exists in.
>>>>
>>>> The problem appears to be when handling a USB_REQ_GET_STATUS request. The driver gets this request and then calls the ch9getstatus() function. In this function, it starts a request by "borrowing" the per device status_req, filling it in, and then queuing it with a call to list_add_tail() to add the request to the endpoint queue. Right before it exits the function however, it's calling ep0_prime_status(), which is filling out that same status_req structure and then queuing it with another call to list_add_tail() to add the request to the endpoint queue. This adds two instances of the exact same LIST_HEAD to the endpoint queue, which breaks the list since the prev and next pointers end up pointing to the wrong things. This ends up causing a hard loop the next time nuke() gets called, which happens on the next setup IRQ.
>>>>
>>>> I'm not sure what the appropriate fix to this problem is, mostly due to my lack of expertise in USB and this driver stack. The code has been this way in the kernel for a very long time, which suggests that it has been working, unless USB_REQ_GET_STATUS requests are never made. This further suggests that there is something else going on that I don't understand. Deleting the call to ep0_prime_status() and the following ep0stall() call appears, on the surface, to get the device working again, but may have side effects that I'm not seeing.
>>>>
>>>> I'm hopeful someone in the community can help provide some information on what I may be missing or help come up with a solution to the problem. A big thank you to anyone who would like to help out.
>>>
>>> Run into this to a while ago. Found the bug and a few more fixes.
>>> This is against 4.19 so you may have to tweak them a bit.
>>> Feel free to upstream them.
>>
>> Curious, did my patches help? Good to known once we upgrade as well.
>
> There's good news and bad news.
>
> The good news is that this appears to stop the driver from entering an
> infinite loop, which prevents the Linux system from locking up and
> never recovering. So I'm willing to say we've made the behavior
> better.
>
> The bad news is that once we get past this point, there is new bad
> behavior. What is on top of this driver in our system is the RNDIS
> gadget driver communicating to a Laptop running Win10 -1809.
> Everything appears to work fine with the Linux system until there is a
> USB disconnect. After the disconnect, the Linux side appears to
> continue on just fine, but the Windows side doesn't seem to recognize
> the disconnect, which causes the USB driver on that side to hang
> forever and eventually blue screen the box. This doesn't happen on
> all machines, just a select few. I think we can isolate the
> behavior to a specific antivirus/security software driver that is
> inserting itself into the USB stack and filtering the disconnect
> message, but we're still proving that.
>
> I'm about 90% certain this is a different problem and we can call this
> patchset good, at least for our test setup. My only hesitation is if
> the Linux side is sending a set of responses that are confusing the
> Windows side (specifically this antivirus) or not. I'd be content
> calling that a separate defect though and letting this one close up
> with that patchset.
P.S.: As a Linux kernel regression tracker I'm getting a lot of reports on my table. I can only look briefly into most of them. Unfortunately therefore I sometimes will get things wrong or miss something important.
I hope that's not the case here; if you think it is, don't hesitate to tell me about it in a public reply. That's in everyone's interest, as what I wrote above might be misleading to everyone reading this; any suggestion I gave they thus might sent someone reading this down the wrong rabbit hole, which none of us wants.
BTW, I have no personal interest in this issue, which is tracked using regzbot, my Linux kernel regression tracking bot (https://urldefense.com/v3/__https://linux-regtracking.leemhuis.info/regzbot/__;!!O7uE89YCNVw!aHa5_mLMnBeDjINlAtV19tBHm-He9jbusXucMA5h7oonHvNFwYpOHAaaqqewPOuGK9HAzJUz$ ). I'm only posting this mail to get things rolling again and hence don't need to be CC on all further activities wrt to this regression.
#regzbot title: usb: fsl_udc_core: corrupted request list leads to unrecoverable loop
^ permalink raw reply
* [PATCH 00/10] powerpc/pseries/vas: NXGZIP support with DLPAR
From: Haren Myneni @ 2021-11-29 17:44 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
PowerPC provides HW compression with NX coprocessor. This feature
is available on both PowerNV and PowerVM and included in Linux.
Since each powerpc chip has one NX coprocessor, the VAS introduces
the concept of windows / credits to manage access to this hardware
resource. On powerVM, these limited resources should be available
across all LPARs. So the hypervisor assigns the specific credits
to each LPAR based on processor entitlement so that one LPAR does
not overload NX. The hypervisor can reject the window open request
to a partition if exceeds its credit limit (1 credit per window).
So the total number of target credits in a partition can be changed
if the core configuration is modified. The hypervisor expects the
partition to modify its window usage depends on new target
credits. For example, if the partition uses more credits than the
new target credits, it should close the excessive windows so that
the NX resource will be available to other partitions.
This patch series enables OS to support this dynamic credit
management with DLPAR core removal/add.
Core removal operation:
- Get new VAS capabilities from the hypervisor when the DLPAR
notifier is received. This capabilities provides the new target
credits based on new processor entitlement. In the case of QoS
credit changes, the notification will be issued by updating
the target_creds via sysfs.
- If the partition is already used more than the new target credits,
the kernel selects windows, unmap the current paste address and
close them in the hypervisor, It uses LIFO to identify these
windows - last windows that are opened are the first ones to be
closed.
- When the user space issue requests on these windows, NX generates
page fault on the unmap paste address. The kernel handles the
fault by returning the paste instruction failure if the window is
not active (means unmap paste). Then up to the library / user
space to fall back to SW compression or manage with the current
windows.
Core add operation:
- The kernel can see increased target credits from the new VAS
capabilities.
- Scans the window list for the closed windows in the hypervisor
due to lost credit before and selects windows based on same LIFO.
- Make these corresponding windows active and create remap with
the same VMA on the new paste address in the fault handler.
- Then the user space should expect paste successful later.
Patch 1: Define common names for sysfs target/used/avail_creds so
that same sysfs entries can be used even on PowerNV later.
Patch 2: Add VAS notifier for DLPAR core add / removal
Patch 3: Save LPID in the vas window struct during initial window
open and use it when reopen later.
Patch 4: When credits are available, reopen windows that are closed
before with core removal.
Patch 5: Close windows in the hypervisor when the partition exceeds
its usage than the new target credits.
Patch 6: If the window is closed in the hypervisor before the user
space issue the initial mmap(), return -EACCES failure.
Patch 7: Add new mmap fault handler which handles the page fault
from NX on paste address.
Patch 8: Return the paste instruction failure if the window is not
active.
Patch 9 & 10: The user space determines the credit usage with sysfs
target/avail/used_creds interfaces. drmgr uses target_creds
to notify OS for QoS credit changes.
Thanks to Nicholas Piggin and Aneesh Kumar for the valuable suggestions
on the NXGZIP design to support DLPAR operations.
Haren Myneni (10):
powerpc/pseries/vas: Use common names in VAS capability structure
powerpc/pseries/vas: Add notifier for DLPAR core removal/add
powerpc/pseries/vas: Save partition PID in pseries_vas_window struct
powerpc/pseries/vas: Reopen windows with DLPAR core add
powerpc/pseries/vas: Close windows with DLPAR core removal
powerpc/vas: Map paste address only if window is active
powerpc/vas: Add paste address mmap fault handler
powerpc/vas: Return paste instruction failure if window is not active
powerpc/pseries/vas: sysfs interface to export capabilities
powerpc/pseries/vas: Write 'target_creds' for QoS credits change
arch/powerpc/include/asm/ppc-opcode.h | 2 +
arch/powerpc/include/asm/vas.h | 16 ++
arch/powerpc/platforms/book3s/vas-api.c | 129 ++++++++-
arch/powerpc/platforms/pseries/Makefile | 2 +-
arch/powerpc/platforms/pseries/vas-sysfs.c | 246 +++++++++++++++++
arch/powerpc/platforms/pseries/vas.c | 293 ++++++++++++++++++++-
arch/powerpc/platforms/pseries/vas.h | 16 +-
7 files changed, 691 insertions(+), 13 deletions(-)
create mode 100644 arch/powerpc/platforms/pseries/vas-sysfs.c
--
2.27.0
^ permalink raw reply
* [PATCH 01/10] powerpc/pseries/vas: Use common names in VAS capability structure
From: Haren Myneni @ 2021-11-29 17:46 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
target/used/avail_creds provides credits usage to user space via
sysfs and the same interface can be used on PowerNV in future.
Remove "lpar" from these names so that applicable on both PowerVM
and PowerNV.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/platforms/pseries/vas.c | 10 +++++-----
arch/powerpc/platforms/pseries/vas.h | 6 +++---
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index b043e3936d21..ecdd21f517c0 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -303,8 +303,8 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
cop_feat_caps = &caps->caps;
- if (atomic_inc_return(&cop_feat_caps->used_lpar_creds) >
- atomic_read(&cop_feat_caps->target_lpar_creds)) {
+ if (atomic_inc_return(&cop_feat_caps->used_creds) >
+ atomic_read(&cop_feat_caps->target_creds)) {
pr_err("Credits are not available to allocate window\n");
rc = -EINVAL;
goto out;
@@ -378,7 +378,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
free_irq_setup(txwin);
h_deallocate_vas_window(txwin->vas_win.winid);
out:
- atomic_dec(&cop_feat_caps->used_lpar_creds);
+ atomic_dec(&cop_feat_caps->used_creds);
kfree(txwin);
return ERR_PTR(rc);
}
@@ -438,7 +438,7 @@ static int vas_deallocate_window(struct vas_window *vwin)
}
list_del(&win->win_list);
- atomic_dec(&caps->used_lpar_creds);
+ atomic_dec(&caps->used_creds);
mutex_unlock(&vas_pseries_mutex);
put_vas_user_win_ref(&vwin->task_ref);
@@ -514,7 +514,7 @@ static int get_vas_capabilities(u8 feat, enum vas_cop_feat_type type,
}
caps->max_lpar_creds = be16_to_cpu(hv_caps->max_lpar_creds);
caps->max_win_creds = be16_to_cpu(hv_caps->max_win_creds);
- atomic_set(&caps->target_lpar_creds,
+ atomic_set(&caps->target_creds,
be16_to_cpu(hv_caps->target_lpar_creds));
if (feat == VAS_GZIP_DEF_FEAT) {
caps->def_lpar_creds = be16_to_cpu(hv_caps->def_lpar_creds);
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 4ecb3fcabd10..fa7ce74f1e49 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -72,9 +72,9 @@ struct vas_cop_feat_caps {
};
/* Total LPAR available credits. Can be different from max LPAR */
/* credits due to DLPAR operation */
- atomic_t target_lpar_creds;
- atomic_t used_lpar_creds; /* Used credits so far */
- u16 avail_lpar_creds; /* Remaining available credits */
+ atomic_t target_creds;
+ atomic_t used_creds; /* Used credits so far */
+ u16 avail_creds; /* Remaining available credits */
};
/*
--
2.27.0
^ permalink raw reply related
* [PATCH 02/10] powerpc/pseries/vas: Add notifier for DLPAR core removal/add
From: Haren Myneni @ 2021-11-29 17:47 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
The hypervisor assigns credits for each LPAR based on number of
cores configured in that system. So expects to release credits
(means windows) when the core is removed. This patch adds notifier
for core removal/add so that the OS closes windows if the system
looses credits due to core removal and reopen windows when the
credits available later.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/platforms/pseries/vas.c | 34 ++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index ecdd21f517c0..04a6eee2301e 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -531,6 +531,36 @@ static int get_vas_capabilities(u8 feat, enum vas_cop_feat_type type,
return 0;
}
+/*
+ * Total number of default credits available (target_credits)
+ * in LPAR depends on number of cores configured. It varies based on
+ * whether processors are in shared mode or dedicated mode.
+ * Get the notifier when CPU configuration is changed with DLPAR
+ * operation so that get the new target_credits (vas default capabilities)
+ * and then update the existing windows usage if needed.
+ */
+static int pseries_vas_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct of_reconfig_data *rd = data;
+ struct device_node *dn = rd->dn;
+ const __be32 *intserv;
+ int len, rc = 0;
+
+ intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
+ /*
+ * Processor config is not changed
+ */
+ if (!intserv)
+ return NOTIFY_OK;
+
+ return rc;
+}
+
+static struct notifier_block pseries_vas_nb = {
+ .notifier_call = pseries_vas_notifier,
+};
+
static int __init pseries_vas_init(void)
{
struct hv_vas_cop_feat_caps *hv_cop_caps;
@@ -584,6 +614,10 @@ static int __init pseries_vas_init(void)
goto out_cop;
}
+ /* Processors can be added/removed only on LPAR */
+ if (copypaste_feat && firmware_has_feature(FW_FEATURE_LPAR))
+ of_reconfig_notifier_register(&pseries_vas_nb);
+
pr_info("GZIP feature is available\n");
out_cop:
--
2.27.0
^ permalink raw reply related
* [PATCH 03/10] powerpc/pseries/vas: Save LPID in pseries_vas_window struct
From: Haren Myneni @ 2021-11-29 17:48 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
The kernel sets the VAS window with partition PID when is opened in
the hypervisor. During DLPAR operation, windows can be closed and
reopened in the hypervisor when the credit is available. So saves
this PID in pseries_vas_window struct when the window is opened
initially and reuse it later during DLPAR operation.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/platforms/pseries/vas.c | 6 +++---
arch/powerpc/platforms/pseries/vas.h | 1 +
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 04a6eee2301e..6b35f67d5175 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -107,7 +107,6 @@ static int h_deallocate_vas_window(u64 winid)
static int h_modify_vas_window(struct pseries_vas_window *win)
{
long rc;
- u32 lpid = mfspr(SPRN_PID);
/*
* AMR value is not supported in Linux VAS implementation.
@@ -115,7 +114,7 @@ static int h_modify_vas_window(struct pseries_vas_window *win)
*/
do {
rc = plpar_hcall_norets(H_MODIFY_VAS_WINDOW,
- win->vas_win.winid, lpid, 0,
+ win->vas_win.winid, win->lpid, 0,
VAS_MOD_WIN_FLAGS, 0);
rc = hcall_return_busy_check(rc);
@@ -125,7 +124,7 @@ static int h_modify_vas_window(struct pseries_vas_window *win)
return 0;
pr_err("H_MODIFY_VAS_WINDOW error: %ld, winid %u lpid %u\n",
- rc, win->vas_win.winid, lpid);
+ rc, win->vas_win.winid, win->lpid);
return -EIO;
}
@@ -353,6 +352,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
if (rc)
goto out;
+ txwin->lpid = mfspr(SPRN_PID);
/*
* Modify window and it is ready to use.
*/
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index fa7ce74f1e49..0538760d13be 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -115,6 +115,7 @@ struct pseries_vas_window {
u64 domain[6]; /* Associativity domain Ids */
/* this window is allocated */
u64 util;
+ u32 lpid;
/* List of windows opened which is used for LPM */
struct list_head win_list;
--
2.27.0
^ permalink raw reply related
* [PATCH 04/10] powerpc/pseries/vas: Reopen windows with DLPAR core add
From: Haren Myneni @ 2021-11-29 17:49 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
VAS windows can be closed in the hypervisor due to lost credits
when the core is removed. If these credits are available later
for core add, reopen these windows and set them active. When the
kernel sees page fault on the paste address, it creates new mapping
on the new paste address. Then the user space can continue to use
these windows and send HW compression requests to NX successfully.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/include/asm/vas.h | 15 +++
arch/powerpc/platforms/book3s/vas-api.c | 1 +
arch/powerpc/platforms/pseries/vas.c | 148 ++++++++++++++++++++++++
arch/powerpc/platforms/pseries/vas.h | 2 +
4 files changed, 166 insertions(+)
diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
index 57573d9c1e09..43cea69d1af1 100644
--- a/arch/powerpc/include/asm/vas.h
+++ b/arch/powerpc/include/asm/vas.h
@@ -29,6 +29,18 @@
#define VAS_THRESH_FIFO_GT_QTR_FULL 2
#define VAS_THRESH_FIFO_GT_EIGHTH_FULL 3
+/*
+ * VAS window status
+ */
+#define VAS_WIN_ACTIVE 0x0 /* Used in platform independent */
+ /* vas mmap() */
+#define VAS_WIN_CLOSED 0x1
+#define VAS_WIN_INACTIVE 0x2 /* Inactive due to HW failure */
+#define VAS_WIN_MOD_IN_PROCESS 0x3 /* Process of being modified, */
+ /* deallocated, or quiesced */
+#define VAS_WIN_NO_CRED_CLOSE 0x4 /* Linux specific status when */
+ /* window is closed due to lost */
+ /* credit */
/*
* Get/Set bit fields
*/
@@ -59,6 +71,8 @@ struct vas_user_win_ref {
struct pid *pid; /* PID of owner */
struct pid *tgid; /* Thread group ID of owner */
struct mm_struct *mm; /* Linux process mm_struct */
+ struct mutex mmap_mutex; /* protects paste address mmap() */
+ /* with DLPAR close/open windows */
};
/*
@@ -67,6 +81,7 @@ struct vas_user_win_ref {
struct vas_window {
u32 winid;
u32 wcreds_max; /* Window credits */
+ u32 status;
enum vas_cop_type cop;
struct vas_user_win_ref task_ref;
char *dbgname;
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 4d82c92ddd52..2b0ced611f32 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -316,6 +316,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg)
return PTR_ERR(txwin);
}
+ mutex_init(&txwin->task_ref.mmap_mutex);
cp_inst->txwin = txwin;
return 0;
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 6b35f67d5175..ace8ee7a99e6 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -493,6 +493,7 @@ static int get_vas_capabilities(u8 feat, enum vas_cop_feat_type type,
memset(vcaps, 0, sizeof(*vcaps));
INIT_LIST_HEAD(&vcaps->list);
+ vcaps->feat = feat;
caps = &vcaps->caps;
rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, feat,
@@ -531,6 +532,149 @@ static int get_vas_capabilities(u8 feat, enum vas_cop_feat_type type,
return 0;
}
+/*
+ * VAS windows can be closed due to lost credits when the core is
+ * removed. So reopen them if credits are available due to DLPAR
+ * core add and set the window active status. When NX sees the page
+ * fault on the unmapped paste address, the kernel handles the fault
+ * by setting the remapping to new paste address if the window is
+ * active.
+ */
+static int reconfig_open_windows(struct vas_caps *vcaps, int creds)
+{
+ long domain[PLPAR_HCALL9_BUFSIZE] = {VAS_DEFAULT_DOMAIN_ID};
+ struct vas_cop_feat_caps *caps = &vcaps->caps;
+ struct pseries_vas_window *win = NULL;
+ int rc, mv_ents = 0;
+
+ /*
+ * Nothing to do if there are no closed windows.
+ */
+ if (!vcaps->close_wins)
+ return 0;
+
+ /*
+ * For the core removal, the hypervisor reduces the credits
+ * assigned to the LPAR and the kernel closes VAS windows
+ * in the hypervisor depends on reduced credits. The kernel
+ * uses LIFO (the last windows that are opened will be closed
+ * first) and expects to open in the same order when credits
+ * are available.
+ * For example, 40 windows are closed when the LPAR lost 2 cores
+ * (dedicated). If 1 core is added, this LPAR can have 20 more
+ * credits. It means the kernel can reopen 20 windows. So move
+ * 20 entries in the VAS windows lost and reopen next 20 windows.
+ */
+ if (vcaps->close_wins > creds)
+ mv_ents = vcaps->close_wins - creds;
+
+ list_for_each_entry(win, &vcaps->list, win_list) {
+ if (!mv_ents)
+ break;
+
+ mv_ents--;
+ }
+
+ while (vcaps->close_wins && win) {
+ /*
+ * Nothing to do on this window if it is active.
+ */
+ if (win->vas_win.status != VAS_WIN_NO_CRED_CLOSE) {
+ win = list_next_entry(win, win_list);
+ continue;
+ }
+
+ rc = allocate_setup_window(win, (u64 *)&domain[0],
+ caps->win_type);
+ if (rc)
+ return rc;
+
+ rc = h_modify_vas_window(win);
+ if (rc)
+ goto out;
+
+ mutex_lock(&win->vas_win.task_ref.mmap_mutex);
+
+ /*
+ * Set window status to active
+ */
+ win->vas_win.status = VAS_WIN_ACTIVE;
+ win->win_type = caps->win_type;
+ mutex_unlock(&win->vas_win.task_ref.mmap_mutex);
+ atomic_inc(&caps->used_creds);
+ win = list_next_entry(win, win_list);
+ vcaps->close_wins--;
+ }
+
+ return 0;
+out:
+ /*
+ * Window modify HCALL failed. So close the window to the
+ * hypervisor and return.
+ */
+ free_irq_setup(win);
+ h_deallocate_vas_window(win->vas_win.winid);
+ return rc;
+}
+
+/*
+ * Get new VAS capabilities when the core add/removal configuration
+ * changes. Reconfig window configurations based on the credits
+ * availability from this new capabilities.
+ */
+static int vas_reconfig_capabilties(u8 type)
+{
+ int lpar_creds, avail_creds;
+ struct hv_vas_cop_feat_caps *hv_caps;
+ struct vas_cop_feat_caps *caps;
+ struct vas_caps *vcaps;
+ int rc = 0;
+
+ if (type >= VAS_MAX_FEAT_TYPE) {
+ pr_err("Invalid credit type %d\n", type);
+ return -EINVAL;
+ }
+
+ vcaps = &vascaps[type];
+ caps = &vcaps->caps;
+
+ hv_caps = kmalloc(sizeof(*hv_caps), GFP_KERNEL);
+ if (!hv_caps)
+ return -ENOMEM;
+
+ mutex_lock(&vas_pseries_mutex);
+ rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat,
+ (u64)virt_to_phys(hv_caps));
+ if (rc)
+ goto out;
+
+ lpar_creds = be16_to_cpu(hv_caps->target_lpar_creds);
+
+ atomic_set(&caps->target_creds, lpar_creds);
+
+ /*
+ * The total number of available credits are decreased due to
+ * DLPAR core removal. Means some windows have to be closed.
+ * Hold the vas_pseries_mutex before closing the required windows
+ * so that the user space can not open new windows.
+ */
+ if (atomic_read(&caps->used_creds) < lpar_creds) {
+ /*
+ * If the existing used credits is less than the new
+ * available credits, reopen windows if they are
+ * closed due to the previous DLPAR (core removal).
+ */
+ avail_creds = lpar_creds -
+ atomic_read(&caps->used_creds);
+ rc = reconfig_open_windows(vcaps, avail_creds);
+ }
+
+out:
+ mutex_unlock(&vas_pseries_mutex);
+ kfree(hv_caps);
+ return rc;
+}
+
/*
* Total number of default credits available (target_credits)
* in LPAR depends on number of cores configured. It varies based on
@@ -554,6 +698,10 @@ static int pseries_vas_notifier(struct notifier_block *nb,
if (!intserv)
return NOTIFY_OK;
+ rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE);
+ if (rc)
+ pr_err("Failed reconfig VAS capabilities with DLPAR\n");
+
return rc;
}
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 0538760d13be..1fbb49a34d48 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -84,6 +84,8 @@ struct vas_cop_feat_caps {
struct vas_caps {
struct vas_cop_feat_caps caps;
struct list_head list; /* List of open windows */
+ int close_wins; /* closed windows in the hypervisor for DLPAR */
+ u8 feat; /* Feature type */
};
/*
--
2.27.0
^ permalink raw reply related
* [PATCH v5 1/5] powerpc/inst: Refactor ___get_user_instr()
From: Christophe Leroy @ 2021-11-29 17:49 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
PPC64 version of ___get_user_instr() can be used for PPC32 as well,
by simply disabling the suffix part with IS_ENABLED(CONFIG_PPC64).
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v5: Force use of 'y' in ppc_inst_prefix on PPC32 to avoid 'use variable' warning with W=1
---
arch/powerpc/include/asm/inst.h | 13 ++-----------
1 file changed, 2 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h
index b11c0e2f9639..10a5c1b76ca0 100644
--- a/arch/powerpc/include/asm/inst.h
+++ b/arch/powerpc/include/asm/inst.h
@@ -4,8 +4,6 @@
#include <asm/ppc-opcode.h>
-#ifdef CONFIG_PPC64
-
#define ___get_user_instr(gu_op, dest, ptr) \
({ \
long __gui_ret; \
@@ -16,7 +14,7 @@
__chk_user_ptr(ptr); \
__gui_ret = gu_op(__prefix, __gui_ptr); \
if (__gui_ret == 0) { \
- if ((__prefix >> 26) == OP_PREFIX) { \
+ if (IS_ENABLED(CONFIG_PPC64) && (__prefix >> 26) == OP_PREFIX) { \
__gui_ret = gu_op(__suffix, __gui_ptr + 1); \
__gui_inst = ppc_inst_prefix(__prefix, __suffix); \
} else { \
@@ -27,13 +25,6 @@
} \
__gui_ret; \
})
-#else /* !CONFIG_PPC64 */
-#define ___get_user_instr(gu_op, dest, ptr) \
-({ \
- __chk_user_ptr(ptr); \
- gu_op((dest).val, (u32 __user *)(ptr)); \
-})
-#endif /* CONFIG_PPC64 */
#define get_user_instr(x, ptr) ___get_user_instr(get_user, x, ptr)
@@ -71,7 +62,7 @@ static inline u32 ppc_inst_suffix(struct ppc_inst x)
}
#else
-#define ppc_inst_prefix(x, y) ppc_inst(x)
+#define ppc_inst_prefix(x, y) ((void)y, ppc_inst(x))
static inline u32 ppc_inst_suffix(struct ppc_inst x)
{
--
2.33.1
^ permalink raw reply related
* [PATCH v5 5/5] powerpc/inst: Optimise copy_inst_from_kernel_nofault()
From: Christophe Leroy @ 2021-11-29 17:49 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <1f0ede830ccb33a659119a55cb590820c27004db.1638208156.git.christophe.leroy@csgroup.eu>
copy_inst_from_kernel_nofault() uses copy_from_kernel_nofault() to
copy one or two 32bits words. This means calling an out-of-line
function which itself calls back copy_from_kernel_nofault_allowed()
then performs a generic copy with loops.
Rewrite copy_inst_from_kernel_nofault() to do everything at a
single place and use __get_kernel_nofault() directly to perform
single accesses without loops.
Allthough the generic function uses pagefault_disable(), it is not
required on powerpc because do_page_fault() bails earlier when a
kernel mode fault happens on a kernel address.
As the function has now become very small, inline it.
With this change, on an 8xx the time spent in the loop in
ftrace_replace_code() is reduced by 23% at function tracer activation
and 27% at nop tracer activation.
The overall time to activate function tracer (measured with shell
command 'time') is 570ms before the patch and 470ms after the patch.
Even vmlinux size is reduced (by 152 instruction).
Before the patch:
00000018 <copy_inst_from_kernel_nofault>:
18: 94 21 ff e0 stwu r1,-32(r1)
1c: 7c 08 02 a6 mflr r0
20: 38 a0 00 04 li r5,4
24: 93 e1 00 1c stw r31,28(r1)
28: 7c 7f 1b 78 mr r31,r3
2c: 38 61 00 08 addi r3,r1,8
30: 90 01 00 24 stw r0,36(r1)
34: 48 00 00 01 bl 34 <copy_inst_from_kernel_nofault+0x1c>
34: R_PPC_REL24 copy_from_kernel_nofault
38: 2c 03 00 00 cmpwi r3,0
3c: 40 82 00 0c bne 48 <copy_inst_from_kernel_nofault+0x30>
40: 81 21 00 08 lwz r9,8(r1)
44: 91 3f 00 00 stw r9,0(r31)
48: 80 01 00 24 lwz r0,36(r1)
4c: 83 e1 00 1c lwz r31,28(r1)
50: 38 21 00 20 addi r1,r1,32
54: 7c 08 03 a6 mtlr r0
58: 4e 80 00 20 blr
After the patch (before inlining):
00000018 <copy_inst_from_kernel_nofault>:
18: 3d 20 b0 00 lis r9,-20480
1c: 7c 04 48 40 cmplw r4,r9
20: 7c 69 1b 78 mr r9,r3
24: 41 80 00 14 blt 38 <copy_inst_from_kernel_nofault+0x20>
28: 81 44 00 00 lwz r10,0(r4)
2c: 38 60 00 00 li r3,0
30: 91 49 00 00 stw r10,0(r9)
34: 4e 80 00 20 blr
38: 38 60 ff de li r3,-34
3c: 4e 80 00 20 blr
40: 38 60 ff f2 li r3,-14
44: 4e 80 00 20 blr
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v4: Inline and remove pagefault_disable()
v3: New
---
arch/powerpc/include/asm/inst.h | 21 ++++++++++++++++++++-
arch/powerpc/mm/maccess.c | 17 -----------------
2 files changed, 20 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h
index 53a40faf362a..631436f3f5c3 100644
--- a/arch/powerpc/include/asm/inst.h
+++ b/arch/powerpc/include/asm/inst.h
@@ -4,6 +4,8 @@
#include <asm/ppc-opcode.h>
#include <asm/reg.h>
+#include <asm/disassemble.h>
+#include <asm/uaccess.h>
#define ___get_user_instr(gu_op, dest, ptr) \
({ \
@@ -148,6 +150,23 @@ static inline char *__ppc_inst_as_str(char str[PPC_INST_STR_LEN], ppc_inst_t x)
__str; \
})
-int copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src);
+static inline int copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src)
+{
+ unsigned int val, suffix;
+
+ if (unlikely(!is_kernel_addr((unsigned long)src)))
+ return -ERANGE;
+
+ __get_kernel_nofault(&val, src, u32, Efault);
+ if (IS_ENABLED(CONFIG_PPC64) && get_op(val) == OP_PREFIX) {
+ __get_kernel_nofault(&suffix, src + 1, u32, Efault);
+ *inst = ppc_inst_prefix(val, suffix);
+ } else {
+ *inst = ppc_inst(val);
+ }
+ return 0;
+Efault:
+ return -EFAULT;
+}
#endif /* _ASM_POWERPC_INST_H */
diff --git a/arch/powerpc/mm/maccess.c b/arch/powerpc/mm/maccess.c
index 5abae96b2b46..ea821d0ffe16 100644
--- a/arch/powerpc/mm/maccess.c
+++ b/arch/powerpc/mm/maccess.c
@@ -11,20 +11,3 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
{
return is_kernel_addr((unsigned long)unsafe_src);
}
-
-int copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src)
-{
- unsigned int val, suffix;
- int err;
-
- err = copy_from_kernel_nofault(&val, src, sizeof(val));
- if (err)
- return err;
- if (IS_ENABLED(CONFIG_PPC64) && get_op(val) == OP_PREFIX) {
- err = copy_from_kernel_nofault(&suffix, src + 1, sizeof(suffix));
- *inst = ppc_inst_prefix(val, suffix);
- } else {
- *inst = ppc_inst(val);
- }
- return err;
-}
--
2.33.1
^ permalink raw reply related
* [PATCH v5 3/5] powerpc/inst: Define ppc_inst_t as u32 on PPC32
From: Christophe Leroy @ 2021-11-29 17:49 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <1f0ede830ccb33a659119a55cb590820c27004db.1638208156.git.christophe.leroy@csgroup.eu>
Unlike PPC64 ABI, PPC32 uses the stack to pass a parameter defined
as a struct, even when the struct has a single simple element.
To avoid that, define ppc_inst_t as u32 on PPC32.
Keep it as 'struct ppc_inst' when __CHECKER__ is defined so that
sparse can perform type checking.
Also revert commit 511eea5e2ccd ("powerpc/kprobes: Fix Oops by passing
ppc_inst as a pointer to emulate_step() on ppc32") as now the
instruction to be emulated is passed as a register to emulate_step().
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v2: Make it work with kprobes
---
arch/powerpc/include/asm/inst.h | 15 +++++++++++++--
arch/powerpc/kernel/optprobes.c | 8 ++------
2 files changed, 15 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h
index b3502f21e0f4..7ef5fd3bb167 100644
--- a/arch/powerpc/include/asm/inst.h
+++ b/arch/powerpc/include/asm/inst.h
@@ -34,6 +34,7 @@
* Instruction data type for POWER
*/
+#if defined(CONFIG_PPC64) || defined(__CHECKER__)
typedef struct {
u32 val;
#ifdef CONFIG_PPC64
@@ -46,13 +47,23 @@ static inline u32 ppc_inst_val(ppc_inst_t x)
return x.val;
}
+#define ppc_inst(x) ((ppc_inst_t){ .val = (x) })
+
+#else
+typedef u32 ppc_inst_t;
+
+static inline u32 ppc_inst_val(ppc_inst_t x)
+{
+ return x;
+}
+#define ppc_inst(x) (x)
+#endif
+
static inline int ppc_inst_primary_opcode(ppc_inst_t x)
{
return ppc_inst_val(x) >> 26;
}
-#define ppc_inst(x) ((ppc_inst_t){ .val = (x) })
-
#ifdef CONFIG_PPC64
#define ppc_inst_prefix(x, y) ((ppc_inst_t){ .val = (x), .suffix = (y) })
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 378db980ded3..3b1c2236cbee 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -228,12 +228,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
/*
* 3. load instruction to be emulated into relevant register, and
*/
- if (IS_ENABLED(CONFIG_PPC64)) {
- temp = ppc_inst_read(p->ainsn.insn);
- patch_imm_load_insns(ppc_inst_as_ulong(temp), 4, buff + TMPL_INSN_IDX);
- } else {
- patch_imm_load_insns((unsigned long)p->ainsn.insn, 4, buff + TMPL_INSN_IDX);
- }
+ temp = ppc_inst_read(p->ainsn.insn);
+ patch_imm_load_insns(ppc_inst_as_ulong(temp), 4, buff + TMPL_INSN_IDX);
/*
* 4. branch back from trampoline
--
2.33.1
^ permalink raw reply related
* [PATCH v5 4/5] powerpc/inst: Move ppc_inst_t definition in asm/reg.h
From: Christophe Leroy @ 2021-11-29 17:49 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <1f0ede830ccb33a659119a55cb590820c27004db.1638208156.git.christophe.leroy@csgroup.eu>
Because of circular inclusion of asm/hw_breakpoint.h, we
need to move definition of asm/reg.h outside of inst.h
so that asm/hw_breakpoint.h gets it without including
asm/inst.h
Also remove asm/inst.h from asm/uprobes.h as it's not
needed anymore.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v4: New to support inlining of copy_inst_from_kernel_nofault() in following patch.
---
arch/powerpc/include/asm/hw_breakpoint.h | 1 -
arch/powerpc/include/asm/inst.h | 10 +---------
arch/powerpc/include/asm/reg.h | 12 ++++++++++++
arch/powerpc/include/asm/uprobes.h | 1 -
4 files changed, 13 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 88053d3c68e6..84d39fd42f71 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -10,7 +10,6 @@
#define _PPC_BOOK3S_64_HW_BREAKPOINT_H
#include <asm/cpu_has_feature.h>
-#include <asm/inst.h>
#ifdef __KERNEL__
struct arch_hw_breakpoint {
diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h
index 7ef5fd3bb167..53a40faf362a 100644
--- a/arch/powerpc/include/asm/inst.h
+++ b/arch/powerpc/include/asm/inst.h
@@ -3,6 +3,7 @@
#define _ASM_POWERPC_INST_H
#include <asm/ppc-opcode.h>
+#include <asm/reg.h>
#define ___get_user_instr(gu_op, dest, ptr) \
({ \
@@ -35,13 +36,6 @@
*/
#if defined(CONFIG_PPC64) || defined(__CHECKER__)
-typedef struct {
- u32 val;
-#ifdef CONFIG_PPC64
- u32 suffix;
-#endif
-} __packed ppc_inst_t;
-
static inline u32 ppc_inst_val(ppc_inst_t x)
{
return x.val;
@@ -50,8 +44,6 @@ static inline u32 ppc_inst_val(ppc_inst_t x)
#define ppc_inst(x) ((ppc_inst_t){ .val = (x) })
#else
-typedef u32 ppc_inst_t;
-
static inline u32 ppc_inst_val(ppc_inst_t x)
{
return x;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index e9d27265253b..85501181f929 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1366,6 +1366,18 @@
/* Macros for setting and retrieving special purpose registers */
#ifndef __ASSEMBLY__
+
+#if defined(CONFIG_PPC64) || defined(__CHECKER__)
+typedef struct {
+ u32 val;
+#ifdef CONFIG_PPC64
+ u32 suffix;
+#endif
+} __packed ppc_inst_t;
+#else
+typedef u32 ppc_inst_t;
+#endif
+
#define mfmsr() ({unsigned long rval; \
asm volatile("mfmsr %0" : "=r" (rval) : \
: "memory"); rval;})
diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h
index fe683371336f..a7ae1860115a 100644
--- a/arch/powerpc/include/asm/uprobes.h
+++ b/arch/powerpc/include/asm/uprobes.h
@@ -11,7 +11,6 @@
#include <linux/notifier.h>
#include <asm/probes.h>
-#include <asm/inst.h>
typedef ppc_opcode_t uprobe_opcode_t;
--
2.33.1
^ permalink raw reply related
* [PATCH v5 2/5] powerpc/inst: Define ppc_inst_t
From: Christophe Leroy @ 2021-11-29 17:49 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <1f0ede830ccb33a659119a55cb590820c27004db.1638208156.git.christophe.leroy@csgroup.eu>
In order to stop using 'struct ppc_inst' on PPC32,
define a ppc_inst_t typedef.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v3: Rebased and resolved conflicts
v2: Anonymise the structure so that only the typedef can be used
---
arch/powerpc/include/asm/code-patching.h | 18 +++----
arch/powerpc/include/asm/hw_breakpoint.h | 4 +-
arch/powerpc/include/asm/inst.h | 36 ++++++-------
arch/powerpc/include/asm/sstep.h | 4 +-
arch/powerpc/kernel/align.c | 4 +-
arch/powerpc/kernel/epapr_paravirt.c | 2 +-
arch/powerpc/kernel/hw_breakpoint.c | 4 +-
.../kernel/hw_breakpoint_constraints.c | 4 +-
arch/powerpc/kernel/kprobes.c | 4 +-
arch/powerpc/kernel/mce_power.c | 2 +-
arch/powerpc/kernel/optprobes.c | 4 +-
arch/powerpc/kernel/process.c | 2 +-
arch/powerpc/kernel/setup_32.c | 2 +-
arch/powerpc/kernel/trace/ftrace.c | 54 +++++++++----------
arch/powerpc/kernel/vecemu.c | 2 +-
arch/powerpc/lib/code-patching.c | 38 ++++++-------
arch/powerpc/lib/feature-fixups.c | 4 +-
arch/powerpc/lib/sstep.c | 4 +-
arch/powerpc/lib/test_emulate_step.c | 10 ++--
arch/powerpc/mm/maccess.c | 2 +-
arch/powerpc/perf/8xx-pmu.c | 2 +-
arch/powerpc/xmon/xmon.c | 14 ++---
arch/powerpc/xmon/xmon_bpts.h | 4 +-
23 files changed, 112 insertions(+), 112 deletions(-)
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 4ba834599c4d..46e8c5a8ce51 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -24,20 +24,20 @@
bool is_offset_in_branch_range(long offset);
bool is_offset_in_cond_branch_range(long offset);
-int create_branch(struct ppc_inst *instr, const u32 *addr,
+int create_branch(ppc_inst_t *instr, const u32 *addr,
unsigned long target, int flags);
-int create_cond_branch(struct ppc_inst *instr, const u32 *addr,
+int create_cond_branch(ppc_inst_t *instr, const u32 *addr,
unsigned long target, int flags);
int patch_branch(u32 *addr, unsigned long target, int flags);
-int patch_instruction(u32 *addr, struct ppc_inst instr);
-int raw_patch_instruction(u32 *addr, struct ppc_inst instr);
+int patch_instruction(u32 *addr, ppc_inst_t instr);
+int raw_patch_instruction(u32 *addr, ppc_inst_t instr);
static inline unsigned long patch_site_addr(s32 *site)
{
return (unsigned long)site + *site;
}
-static inline int patch_instruction_site(s32 *site, struct ppc_inst instr)
+static inline int patch_instruction_site(s32 *site, ppc_inst_t instr)
{
return patch_instruction((u32 *)patch_site_addr(site), instr);
}
@@ -58,11 +58,11 @@ static inline int modify_instruction_site(s32 *site, unsigned int clr, unsigned
return modify_instruction((unsigned int *)patch_site_addr(site), clr, set);
}
-int instr_is_relative_branch(struct ppc_inst instr);
-int instr_is_relative_link_branch(struct ppc_inst instr);
+int instr_is_relative_branch(ppc_inst_t instr);
+int instr_is_relative_link_branch(ppc_inst_t instr);
unsigned long branch_target(const u32 *instr);
-int translate_branch(struct ppc_inst *instr, const u32 *dest, const u32 *src);
-extern bool is_conditional_branch(struct ppc_inst instr);
+int translate_branch(ppc_inst_t *instr, const u32 *dest, const u32 *src);
+bool is_conditional_branch(ppc_inst_t instr);
#ifdef CONFIG_PPC_BOOK3E_64
void __patch_exception(int exc, unsigned long addr);
#define patch_exception(exc, name) do { \
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index abebfbee5b1c..88053d3c68e6 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -56,11 +56,11 @@ static inline int nr_wp_slots(void)
return cpu_has_feature(CPU_FTR_DAWR1) ? 2 : 1;
}
-bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr,
+bool wp_check_constraints(struct pt_regs *regs, ppc_inst_t instr,
unsigned long ea, int type, int size,
struct arch_hw_breakpoint *info);
-void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr,
+void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
int *type, int *size, unsigned long *ea);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h
index 10a5c1b76ca0..b3502f21e0f4 100644
--- a/arch/powerpc/include/asm/inst.h
+++ b/arch/powerpc/include/asm/inst.h
@@ -8,7 +8,7 @@
({ \
long __gui_ret; \
u32 __user *__gui_ptr = (u32 __user *)ptr; \
- struct ppc_inst __gui_inst; \
+ ppc_inst_t __gui_inst; \
unsigned int __prefix, __suffix; \
\
__chk_user_ptr(ptr); \
@@ -34,29 +34,29 @@
* Instruction data type for POWER
*/
-struct ppc_inst {
+typedef struct {
u32 val;
#ifdef CONFIG_PPC64
u32 suffix;
#endif
-} __packed;
+} __packed ppc_inst_t;
-static inline u32 ppc_inst_val(struct ppc_inst x)
+static inline u32 ppc_inst_val(ppc_inst_t x)
{
return x.val;
}
-static inline int ppc_inst_primary_opcode(struct ppc_inst x)
+static inline int ppc_inst_primary_opcode(ppc_inst_t x)
{
return ppc_inst_val(x) >> 26;
}
-#define ppc_inst(x) ((struct ppc_inst){ .val = (x) })
+#define ppc_inst(x) ((ppc_inst_t){ .val = (x) })
#ifdef CONFIG_PPC64
-#define ppc_inst_prefix(x, y) ((struct ppc_inst){ .val = (x), .suffix = (y) })
+#define ppc_inst_prefix(x, y) ((ppc_inst_t){ .val = (x), .suffix = (y) })
-static inline u32 ppc_inst_suffix(struct ppc_inst x)
+static inline u32 ppc_inst_suffix(ppc_inst_t x)
{
return x.suffix;
}
@@ -64,14 +64,14 @@ static inline u32 ppc_inst_suffix(struct ppc_inst x)
#else
#define ppc_inst_prefix(x, y) ((void)y, ppc_inst(x))
-static inline u32 ppc_inst_suffix(struct ppc_inst x)
+static inline u32 ppc_inst_suffix(ppc_inst_t x)
{
return 0;
}
#endif /* CONFIG_PPC64 */
-static inline struct ppc_inst ppc_inst_read(const u32 *ptr)
+static inline ppc_inst_t ppc_inst_read(const u32 *ptr)
{
if (IS_ENABLED(CONFIG_PPC64) && (*ptr >> 26) == OP_PREFIX)
return ppc_inst_prefix(*ptr, *(ptr + 1));
@@ -79,17 +79,17 @@ static inline struct ppc_inst ppc_inst_read(const u32 *ptr)
return ppc_inst(*ptr);
}
-static inline bool ppc_inst_prefixed(struct ppc_inst x)
+static inline bool ppc_inst_prefixed(ppc_inst_t x)
{
return IS_ENABLED(CONFIG_PPC64) && ppc_inst_primary_opcode(x) == OP_PREFIX;
}
-static inline struct ppc_inst ppc_inst_swab(struct ppc_inst x)
+static inline ppc_inst_t ppc_inst_swab(ppc_inst_t x)
{
return ppc_inst_prefix(swab32(ppc_inst_val(x)), swab32(ppc_inst_suffix(x)));
}
-static inline bool ppc_inst_equal(struct ppc_inst x, struct ppc_inst y)
+static inline bool ppc_inst_equal(ppc_inst_t x, ppc_inst_t y)
{
if (ppc_inst_val(x) != ppc_inst_val(y))
return false;
@@ -98,7 +98,7 @@ static inline bool ppc_inst_equal(struct ppc_inst x, struct ppc_inst y)
return ppc_inst_suffix(x) == ppc_inst_suffix(y);
}
-static inline int ppc_inst_len(struct ppc_inst x)
+static inline int ppc_inst_len(ppc_inst_t x)
{
return ppc_inst_prefixed(x) ? 8 : 4;
}
@@ -109,14 +109,14 @@ static inline int ppc_inst_len(struct ppc_inst x)
*/
static inline u32 *ppc_inst_next(u32 *location, u32 *value)
{
- struct ppc_inst tmp;
+ ppc_inst_t tmp;
tmp = ppc_inst_read(value);
return (void *)location + ppc_inst_len(tmp);
}
-static inline unsigned long ppc_inst_as_ulong(struct ppc_inst x)
+static inline unsigned long ppc_inst_as_ulong(ppc_inst_t x)
{
if (IS_ENABLED(CONFIG_PPC32))
return ppc_inst_val(x);
@@ -128,7 +128,7 @@ static inline unsigned long ppc_inst_as_ulong(struct ppc_inst x)
#define PPC_INST_STR_LEN sizeof("00000000 00000000")
-static inline char *__ppc_inst_as_str(char str[PPC_INST_STR_LEN], struct ppc_inst x)
+static inline char *__ppc_inst_as_str(char str[PPC_INST_STR_LEN], ppc_inst_t x)
{
if (ppc_inst_prefixed(x))
sprintf(str, "%08x %08x", ppc_inst_val(x), ppc_inst_suffix(x));
@@ -145,6 +145,6 @@ static inline char *__ppc_inst_as_str(char str[PPC_INST_STR_LEN], struct ppc_ins
__str; \
})
-int copy_inst_from_kernel_nofault(struct ppc_inst *inst, u32 *src);
+int copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src);
#endif /* _ASM_POWERPC_INST_H */
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index 1df867c2e054..50950deedb87 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -145,7 +145,7 @@ union vsx_reg {
* otherwise.
*/
extern int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
- struct ppc_inst instr);
+ ppc_inst_t instr);
/*
* Emulate an instruction that can be executed just by updating
@@ -162,7 +162,7 @@ void emulate_update_regs(struct pt_regs *reg, struct instruction_op *op);
* 0 if it could not be emulated, or -1 for an instruction that
* should not be emulated (rfid, mtmsrd clearing MSR_RI, etc.).
*/
-extern int emulate_step(struct pt_regs *regs, struct ppc_inst instr);
+int emulate_step(struct pt_regs *regs, ppc_inst_t instr);
/*
* Emulate a load or store instruction by reading/writing the
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index bf96b954a4eb..3e37ece06739 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -105,7 +105,7 @@ static struct aligninfo spe_aligninfo[32] = {
* so we don't need the address swizzling.
*/
static int emulate_spe(struct pt_regs *regs, unsigned int reg,
- struct ppc_inst ppc_instr)
+ ppc_inst_t ppc_instr)
{
union {
u64 ll;
@@ -300,7 +300,7 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg,
int fix_alignment(struct pt_regs *regs)
{
- struct ppc_inst instr;
+ ppc_inst_t instr;
struct instruction_op op;
int r, type;
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index 93b0f3ec8fb0..d4b8aff20815 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -37,7 +37,7 @@ static int __init early_init_dt_scan_epapr(unsigned long node,
return -1;
for (i = 0; i < (len / 4); i++) {
- struct ppc_inst inst = ppc_inst(be32_to_cpu(insts[i]));
+ ppc_inst_t inst = ppc_inst(be32_to_cpu(insts[i]));
patch_instruction(epapr_hypercall_start + i, inst);
#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
patch_instruction(epapr_ev_idle_start + i, inst);
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 91a3be14808b..2669f80b3a49 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -523,7 +523,7 @@ static void larx_stcx_err(struct perf_event *bp, struct arch_hw_breakpoint *info
static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
struct arch_hw_breakpoint **info, int *hit,
- struct ppc_inst instr)
+ ppc_inst_t instr)
{
int i;
int stepped;
@@ -616,7 +616,7 @@ int hw_breakpoint_handler(struct die_args *args)
int hit[HBP_NUM_MAX] = {0};
int nr_hit = 0;
bool ptrace_bp = false;
- struct ppc_inst instr = ppc_inst(0);
+ ppc_inst_t instr = ppc_inst(0);
int type = 0;
int size = 0;
unsigned long ea;
diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c
index 42b967e3d85c..a74623025f3a 100644
--- a/arch/powerpc/kernel/hw_breakpoint_constraints.c
+++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c
@@ -80,7 +80,7 @@ static bool check_dawrx_constraints(struct pt_regs *regs, int type,
* Return true if the event is valid wrt dawr configuration,
* including extraneous exception. Otherwise return false.
*/
-bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr,
+bool wp_check_constraints(struct pt_regs *regs, ppc_inst_t instr,
unsigned long ea, int type, int size,
struct arch_hw_breakpoint *info)
{
@@ -127,7 +127,7 @@ bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr,
return false;
}
-void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr,
+void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
int *type, int *size, unsigned long *ea)
{
struct instruction_op op;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 86d77ff056a6..9a492fdec1df 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -124,7 +124,7 @@ int arch_prepare_kprobe(struct kprobe *p)
{
int ret = 0;
struct kprobe *prev;
- struct ppc_inst insn = ppc_inst_read(p->addr);
+ ppc_inst_t insn = ppc_inst_read(p->addr);
if ((unsigned long)p->addr & 0x03) {
printk("Attempt to register kprobe at an unaligned address\n");
@@ -244,7 +244,7 @@ NOKPROBE_SYMBOL(arch_prepare_kretprobe);
static int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
{
int ret;
- struct ppc_inst insn = ppc_inst_read(p->ainsn.insn);
+ ppc_inst_t insn = ppc_inst_read(p->ainsn.insn);
/* regs->nip is also adjusted if emulate_step returns 1 */
ret = emulate_step(regs, insn);
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index c2f55fe7092d..f2dd4daeddf8 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -455,7 +455,7 @@ static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
* in real-mode is tricky and can lead to recursive
* faults
*/
- struct ppc_inst instr;
+ ppc_inst_t instr;
unsigned long pfn, instr_addr;
struct instruction_op op;
struct pt_regs tmp = *regs;
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index ce1903064031..378db980ded3 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -153,7 +153,7 @@ static void patch_imm_load_insns(unsigned long val, int reg, kprobe_opcode_t *ad
int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
{
- struct ppc_inst branch_op_callback, branch_emulate_step, temp;
+ ppc_inst_t branch_op_callback, branch_emulate_step, temp;
unsigned long op_callback_addr, emulate_step_addr;
kprobe_opcode_t *buff;
long b_offset;
@@ -269,7 +269,7 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op)
void arch_optimize_kprobes(struct list_head *oplist)
{
- struct ppc_inst instr;
+ ppc_inst_t instr;
struct optimized_kprobe *op;
struct optimized_kprobe *tmp;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 5d2333d2a283..c60abfc397a5 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -628,7 +628,7 @@ static void do_break_handler(struct pt_regs *regs)
{
struct arch_hw_breakpoint null_brk = {0};
struct arch_hw_breakpoint *info;
- struct ppc_inst instr = ppc_inst(0);
+ ppc_inst_t instr = ppc_inst(0);
int type = 0;
int size = 0;
unsigned long ea;
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 7ec5c47fce0e..4017b05ef643 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -75,7 +75,7 @@ EXPORT_SYMBOL(DMA_MODE_WRITE);
notrace void __init machine_init(u64 dt_ptr)
{
u32 *addr = (u32 *)patch_site_addr(&patch__memset_nocache);
- struct ppc_inst insn;
+ ppc_inst_t insn;
/* Configure static keys first, now that we're relocated. */
setup_feature_keys();
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index d89c5df4f206..f293294ef5da 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -41,10 +41,10 @@
#define NUM_FTRACE_TRAMPS 8
static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
-static struct ppc_inst
+static ppc_inst_t
ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
{
- struct ppc_inst op;
+ ppc_inst_t op;
addr = ppc_function_entry((void *)addr);
@@ -55,9 +55,9 @@ ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
}
static int
-ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new)
+ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
{
- struct ppc_inst replaced;
+ ppc_inst_t replaced;
/*
* Note:
@@ -90,24 +90,24 @@ ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new)
*/
static int test_24bit_addr(unsigned long ip, unsigned long addr)
{
- struct ppc_inst op;
+ ppc_inst_t op;
addr = ppc_function_entry((void *)addr);
/* use the create_branch to verify that this offset can be branched */
return create_branch(&op, (u32 *)ip, addr, 0) == 0;
}
-static int is_bl_op(struct ppc_inst op)
+static int is_bl_op(ppc_inst_t op)
{
return (ppc_inst_val(op) & 0xfc000003) == 0x48000001;
}
-static int is_b_op(struct ppc_inst op)
+static int is_b_op(ppc_inst_t op)
{
return (ppc_inst_val(op) & 0xfc000003) == 0x48000000;
}
-static unsigned long find_bl_target(unsigned long ip, struct ppc_inst op)
+static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
{
int offset;
@@ -127,7 +127,7 @@ __ftrace_make_nop(struct module *mod,
{
unsigned long entry, ptr, tramp;
unsigned long ip = rec->ip;
- struct ppc_inst op, pop;
+ ppc_inst_t op, pop;
/* read where this goes */
if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
@@ -221,7 +221,7 @@ static int
__ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
- struct ppc_inst op;
+ ppc_inst_t op;
unsigned int jmp[4];
unsigned long ip = rec->ip;
unsigned long tramp;
@@ -291,7 +291,7 @@ __ftrace_make_nop(struct module *mod,
static unsigned long find_ftrace_tramp(unsigned long ip)
{
int i;
- struct ppc_inst instr;
+ ppc_inst_t instr;
/*
* We have the compiler generated long_branch tramps at the end
@@ -329,9 +329,9 @@ static int add_ftrace_tramp(unsigned long tramp)
static int setup_mcount_compiler_tramp(unsigned long tramp)
{
int i;
- struct ppc_inst op;
+ ppc_inst_t op;
unsigned long ptr;
- struct ppc_inst instr;
+ ppc_inst_t instr;
static unsigned long ftrace_plt_tramps[NUM_FTRACE_TRAMPS];
/* Is this a known long jump tramp? */
@@ -396,7 +396,7 @@ static int setup_mcount_compiler_tramp(unsigned long tramp)
static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long tramp, ip = rec->ip;
- struct ppc_inst op;
+ ppc_inst_t op;
/* Read where this goes */
if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
@@ -436,7 +436,7 @@ int ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long ip = rec->ip;
- struct ppc_inst old, new;
+ ppc_inst_t old, new;
/*
* If the calling address is more that 24 bits away,
@@ -489,7 +489,7 @@ int ftrace_make_nop(struct module *mod,
*/
#ifndef CONFIG_MPROFILE_KERNEL
static int
-expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1)
+expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
{
/*
* We expect to see:
@@ -507,7 +507,7 @@ expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1)
}
#else
static int
-expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1)
+expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
{
/* look for patched "NOP" on ppc64 with -mprofile-kernel */
if (!ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP())))
@@ -519,8 +519,8 @@ expected_nop_sequence(void *ip, struct ppc_inst op0, struct ppc_inst op1)
static int
__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
- struct ppc_inst op[2];
- struct ppc_inst instr;
+ ppc_inst_t op[2];
+ ppc_inst_t instr;
void *ip = (void *)rec->ip;
unsigned long entry, ptr, tramp;
struct module *mod = rec->arch.mod;
@@ -588,7 +588,7 @@ static int
__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
int err;
- struct ppc_inst op;
+ ppc_inst_t op;
u32 *ip = (u32 *)rec->ip;
/* read where this goes */
@@ -626,7 +626,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
{
- struct ppc_inst op;
+ ppc_inst_t op;
void *ip = (void *)rec->ip;
unsigned long tramp, entry, ptr;
@@ -674,7 +674,7 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long ip = rec->ip;
- struct ppc_inst old, new;
+ ppc_inst_t old, new;
/*
* If the calling address is more that 24 bits away,
@@ -713,7 +713,7 @@ static int
__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
- struct ppc_inst op;
+ ppc_inst_t op;
unsigned long ip = rec->ip;
unsigned long entry, ptr, tramp;
struct module *mod = rec->arch.mod;
@@ -807,7 +807,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
unsigned long ip = rec->ip;
- struct ppc_inst old, new;
+ ppc_inst_t old, new;
/*
* If the calling address is more that 24 bits away,
@@ -847,7 +847,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
- struct ppc_inst old, new;
+ ppc_inst_t old, new;
int ret;
old = ppc_inst_read((u32 *)&ftrace_call);
@@ -932,7 +932,7 @@ int ftrace_enable_ftrace_graph_caller(void)
unsigned long ip = (unsigned long)(&ftrace_graph_call);
unsigned long addr = (unsigned long)(&ftrace_graph_caller);
unsigned long stub = (unsigned long)(&ftrace_graph_stub);
- struct ppc_inst old, new;
+ ppc_inst_t old, new;
old = ftrace_call_replace(ip, stub, 0);
new = ftrace_call_replace(ip, addr, 0);
@@ -945,7 +945,7 @@ int ftrace_disable_ftrace_graph_caller(void)
unsigned long ip = (unsigned long)(&ftrace_graph_call);
unsigned long addr = (unsigned long)(&ftrace_graph_caller);
unsigned long stub = (unsigned long)(&ftrace_graph_stub);
- struct ppc_inst old, new;
+ ppc_inst_t old, new;
old = ftrace_call_replace(ip, addr, 0);
new = ftrace_call_replace(ip, stub, 0);
diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c
index ae632569446f..fd9432875ebc 100644
--- a/arch/powerpc/kernel/vecemu.c
+++ b/arch/powerpc/kernel/vecemu.c
@@ -261,7 +261,7 @@ static unsigned int rfin(unsigned int x)
int emulate_altivec(struct pt_regs *regs)
{
- struct ppc_inst instr;
+ ppc_inst_t instr;
unsigned int i, word;
unsigned int va, vb, vc, vd;
vector128 *vrs;
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index c5ed98823835..312324a26df3 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -18,7 +18,7 @@
#include <asm/setup.h>
#include <asm/inst.h>
-static int __patch_instruction(u32 *exec_addr, struct ppc_inst instr, u32 *patch_addr)
+static int __patch_instruction(u32 *exec_addr, ppc_inst_t instr, u32 *patch_addr)
{
if (!ppc_inst_prefixed(instr)) {
u32 val = ppc_inst_val(instr);
@@ -39,7 +39,7 @@ static int __patch_instruction(u32 *exec_addr, struct ppc_inst instr, u32 *patch
return -EFAULT;
}
-int raw_patch_instruction(u32 *addr, struct ppc_inst instr)
+int raw_patch_instruction(u32 *addr, ppc_inst_t instr)
{
return __patch_instruction(addr, instr, addr);
}
@@ -141,7 +141,7 @@ static inline int unmap_patch_area(unsigned long addr)
return 0;
}
-static int do_patch_instruction(u32 *addr, struct ppc_inst instr)
+static int do_patch_instruction(u32 *addr, ppc_inst_t instr)
{
int err;
u32 *patch_addr = NULL;
@@ -180,14 +180,14 @@ static int do_patch_instruction(u32 *addr, struct ppc_inst instr)
}
#else /* !CONFIG_STRICT_KERNEL_RWX */
-static int do_patch_instruction(u32 *addr, struct ppc_inst instr)
+static int do_patch_instruction(u32 *addr, ppc_inst_t instr)
{
return raw_patch_instruction(addr, instr);
}
#endif /* CONFIG_STRICT_KERNEL_RWX */
-int patch_instruction(u32 *addr, struct ppc_inst instr)
+int patch_instruction(u32 *addr, ppc_inst_t instr)
{
/* Make sure we aren't patching a freed init section */
if (init_mem_is_free && init_section_contains(addr, 4)) {
@@ -200,7 +200,7 @@ NOKPROBE_SYMBOL(patch_instruction);
int patch_branch(u32 *addr, unsigned long target, int flags)
{
- struct ppc_inst instr;
+ ppc_inst_t instr;
create_branch(&instr, addr, target, flags);
return patch_instruction(addr, instr);
@@ -237,7 +237,7 @@ bool is_offset_in_cond_branch_range(long offset)
* Helper to check if a given instruction is a conditional branch
* Derived from the conditional checks in analyse_instr()
*/
-bool is_conditional_branch(struct ppc_inst instr)
+bool is_conditional_branch(ppc_inst_t instr)
{
unsigned int opcode = ppc_inst_primary_opcode(instr);
@@ -255,7 +255,7 @@ bool is_conditional_branch(struct ppc_inst instr)
}
NOKPROBE_SYMBOL(is_conditional_branch);
-int create_branch(struct ppc_inst *instr, const u32 *addr,
+int create_branch(ppc_inst_t *instr, const u32 *addr,
unsigned long target, int flags)
{
long offset;
@@ -275,7 +275,7 @@ int create_branch(struct ppc_inst *instr, const u32 *addr,
return 0;
}
-int create_cond_branch(struct ppc_inst *instr, const u32 *addr,
+int create_cond_branch(ppc_inst_t *instr, const u32 *addr,
unsigned long target, int flags)
{
long offset;
@@ -294,22 +294,22 @@ int create_cond_branch(struct ppc_inst *instr, const u32 *addr,
return 0;
}
-static unsigned int branch_opcode(struct ppc_inst instr)
+static unsigned int branch_opcode(ppc_inst_t instr)
{
return ppc_inst_primary_opcode(instr) & 0x3F;
}
-static int instr_is_branch_iform(struct ppc_inst instr)
+static int instr_is_branch_iform(ppc_inst_t instr)
{
return branch_opcode(instr) == 18;
}
-static int instr_is_branch_bform(struct ppc_inst instr)
+static int instr_is_branch_bform(ppc_inst_t instr)
{
return branch_opcode(instr) == 16;
}
-int instr_is_relative_branch(struct ppc_inst instr)
+int instr_is_relative_branch(ppc_inst_t instr)
{
if (ppc_inst_val(instr) & BRANCH_ABSOLUTE)
return 0;
@@ -317,7 +317,7 @@ int instr_is_relative_branch(struct ppc_inst instr)
return instr_is_branch_iform(instr) || instr_is_branch_bform(instr);
}
-int instr_is_relative_link_branch(struct ppc_inst instr)
+int instr_is_relative_link_branch(ppc_inst_t instr)
{
return instr_is_relative_branch(instr) && (ppc_inst_val(instr) & BRANCH_SET_LINK);
}
@@ -364,7 +364,7 @@ unsigned long branch_target(const u32 *instr)
return 0;
}
-int translate_branch(struct ppc_inst *instr, const u32 *dest, const u32 *src)
+int translate_branch(ppc_inst_t *instr, const u32 *dest, const u32 *src)
{
unsigned long target;
target = branch_target(src);
@@ -417,7 +417,7 @@ static void __init test_trampoline(void)
static void __init test_branch_iform(void)
{
int err;
- struct ppc_inst instr;
+ ppc_inst_t instr;
u32 tmp[2];
u32 *iptr = tmp;
unsigned long addr = (unsigned long)tmp;
@@ -499,7 +499,7 @@ static void __init test_create_function_call(void)
{
u32 *iptr;
unsigned long dest;
- struct ppc_inst instr;
+ ppc_inst_t instr;
/* Check we can create a function call */
iptr = (u32 *)ppc_function_entry(test_trampoline);
@@ -513,7 +513,7 @@ static void __init test_branch_bform(void)
{
int err;
unsigned long addr;
- struct ppc_inst instr;
+ ppc_inst_t instr;
u32 tmp[2];
u32 *iptr = tmp;
unsigned int flags;
@@ -591,7 +591,7 @@ static void __init test_translate_branch(void)
{
unsigned long addr;
void *p, *q;
- struct ppc_inst instr;
+ ppc_inst_t instr;
void *buf;
buf = vmalloc(PAGE_ALIGN(0x2000000 + 1));
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index c3e06922468b..57c6bb802f6c 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -47,7 +47,7 @@ static u32 *calc_addr(struct fixup_entry *fcur, long offset)
static int patch_alt_instruction(u32 *src, u32 *dest, u32 *alt_start, u32 *alt_end)
{
int err;
- struct ppc_inst instr;
+ ppc_inst_t instr;
instr = ppc_inst_read(src);
@@ -624,7 +624,7 @@ 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 inst;
+ ppc_inst_t inst;
u32 *src, *dest, *end;
if (PHYSICAL_START == 0)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 86f49e3e7cf5..a94b0cd0bdc5 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1354,7 +1354,7 @@ static nokprobe_inline int trap_compare(long v1, long v2)
* otherwise.
*/
int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
- struct ppc_inst instr)
+ ppc_inst_t instr)
{
#ifdef CONFIG_PPC64
unsigned int suffixopcode, prefixtype, prefix_r;
@@ -3578,7 +3578,7 @@ NOKPROBE_SYMBOL(emulate_loadstore);
* or -1 if the instruction is one that should not be stepped,
* such as an rfid, or a mtmsrd that would clear MSR_RI.
*/
-int emulate_step(struct pt_regs *regs, struct ppc_inst instr)
+int emulate_step(struct pt_regs *regs, ppc_inst_t instr)
{
struct instruction_op op;
int r, err, type;
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 8b4f6b3e96c4..4f141daafcff 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -792,7 +792,7 @@ static void __init test_lxvpx_stxvpx(void)
#ifdef CONFIG_VSX
static void __init test_plxvp_pstxvp(void)
{
- struct ppc_inst instr;
+ ppc_inst_t instr;
struct pt_regs regs;
union {
vector128 a;
@@ -906,7 +906,7 @@ struct compute_test {
struct {
char *descr;
unsigned long flags;
- struct ppc_inst instr;
+ ppc_inst_t instr;
struct pt_regs regs;
} subtests[MAX_SUBTESTS + 1];
};
@@ -1600,7 +1600,7 @@ static struct compute_test compute_tests[] = {
};
static int __init emulate_compute_instr(struct pt_regs *regs,
- struct ppc_inst instr,
+ ppc_inst_t instr,
bool negative)
{
int analysed;
@@ -1627,7 +1627,7 @@ static int __init emulate_compute_instr(struct pt_regs *regs,
}
static int __init execute_compute_instr(struct pt_regs *regs,
- struct ppc_inst instr)
+ ppc_inst_t instr)
{
extern int exec_instr(struct pt_regs *regs);
@@ -1658,7 +1658,7 @@ static void __init run_tests_compute(void)
struct compute_test *test;
struct pt_regs *regs, exp, got;
unsigned int i, j, k;
- struct ppc_inst instr;
+ ppc_inst_t instr;
bool ignore_gpr, ignore_xer, ignore_ccr, passed, rc, negative;
for (i = 0; i < ARRAY_SIZE(compute_tests); i++) {
diff --git a/arch/powerpc/mm/maccess.c b/arch/powerpc/mm/maccess.c
index aad7c47e0030..5abae96b2b46 100644
--- a/arch/powerpc/mm/maccess.c
+++ b/arch/powerpc/mm/maccess.c
@@ -12,7 +12,7 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
return is_kernel_addr((unsigned long)unsafe_src);
}
-int copy_inst_from_kernel_nofault(struct ppc_inst *inst, u32 *src)
+int copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src)
{
unsigned int val, suffix;
int err;
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index f970d1510d3d..4738c4dbf567 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -153,7 +153,7 @@ static void mpc8xx_pmu_read(struct perf_event *event)
static void mpc8xx_pmu_del(struct perf_event *event, int flags)
{
- struct ppc_inst insn = ppc_inst(PPC_RAW_MFSPR(10, SPRN_SPRG_SCRATCH2));
+ ppc_inst_t insn = ppc_inst(PPC_RAW_MFSPR(10, SPRN_SPRG_SCRATCH2));
mpc8xx_pmu_read(event);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 83100c6524cc..eac2957c6614 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -125,7 +125,7 @@ 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 mread_instr(unsigned long, ppc_inst_t *);
static int handle_fault(struct pt_regs *);
static void byterev(unsigned char *, int);
static void memex(void);
@@ -908,7 +908,7 @@ static struct bpt *new_breakpoint(unsigned long a)
static void insert_bpts(void)
{
int i;
- struct ppc_inst instr, instr2;
+ ppc_inst_t instr, instr2;
struct bpt *bp, *bp2;
bp = bpts;
@@ -988,7 +988,7 @@ static void remove_bpts(void)
{
int i;
struct bpt *bp;
- struct ppc_inst instr;
+ ppc_inst_t instr;
bp = bpts;
for (i = 0; i < NBPTS; ++i, ++bp) {
@@ -1204,7 +1204,7 @@ static int do_step(struct pt_regs *regs)
*/
static int do_step(struct pt_regs *regs)
{
- struct ppc_inst instr;
+ ppc_inst_t instr;
int stepped;
force_enable_xmon();
@@ -1459,7 +1459,7 @@ csum(void)
*/
static long check_bp_loc(unsigned long addr)
{
- struct ppc_inst instr;
+ ppc_inst_t instr;
addr &= ~3;
if (!is_kernel_addr(addr)) {
@@ -2306,7 +2306,7 @@ mwrite(unsigned long adrs, void *buf, int size)
}
static int
-mread_instr(unsigned long adrs, struct ppc_inst *instr)
+mread_instr(unsigned long adrs, ppc_inst_t *instr)
{
volatile int n;
@@ -3026,7 +3026,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
{
int nr, dotted;
unsigned long first_adr;
- struct ppc_inst inst, last_inst = ppc_inst(0);
+ ppc_inst_t inst, last_inst = ppc_inst(0);
dotted = 0;
for (first_adr = adr; count > 0; --count, adr += ppc_inst_len(inst)) {
diff --git a/arch/powerpc/xmon/xmon_bpts.h b/arch/powerpc/xmon/xmon_bpts.h
index 57e6fb03de48..377068f52edb 100644
--- a/arch/powerpc/xmon/xmon_bpts.h
+++ b/arch/powerpc/xmon/xmon_bpts.h
@@ -5,8 +5,8 @@
#define NBPTS 256
#ifndef __ASSEMBLY__
#include <asm/inst.h>
-#define BPT_SIZE (sizeof(struct ppc_inst) * 2)
-#define BPT_WORDS (BPT_SIZE / sizeof(struct ppc_inst))
+#define BPT_SIZE (sizeof(ppc_inst_t) * 2)
+#define BPT_WORDS (BPT_SIZE / sizeof(ppc_inst_t))
extern unsigned int bpt_table[NBPTS * BPT_WORDS];
#endif /* __ASSEMBLY__ */
--
2.33.1
^ permalink raw reply related
* [PATCH 05/10] powerpc/pseries/vas: Close windows with DLPAR core removal
From: Haren Myneni @ 2021-11-29 17:50 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
The hypervisor reduces the available credits if the core is removed
from the LPAR. So there is possibility of using excessive credits
(windows) in the LPAR and the hypervisor expects the system to close
the excessive windows. Even though the user space can continue to use
these windows to send compression requests to NX, the hypervisor expects
the LPAR to reduce these windows usage so that NX load can be equally
distributed across all LPARs in the system.
When the DLPAR notifier is received, get the new VAS capabilities from
the hypervisor and close the excessive windows in the hypervisor. Also
the kernel unmaps the paste address so that the user space receives paste
failure until these windows are active with the later DLPAR (core add).
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/include/asm/vas.h | 1 +
arch/powerpc/platforms/book3s/vas-api.c | 2 +
arch/powerpc/platforms/pseries/vas.c | 93 ++++++++++++++++++++++++-
3 files changed, 94 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
index 43cea69d1af1..72d1df038b4b 100644
--- a/arch/powerpc/include/asm/vas.h
+++ b/arch/powerpc/include/asm/vas.h
@@ -73,6 +73,7 @@ struct vas_user_win_ref {
struct mm_struct *mm; /* Linux process mm_struct */
struct mutex mmap_mutex; /* protects paste address mmap() */
/* with DLPAR close/open windows */
+ struct vm_area_struct *vma; /* Save VMA and used in DLPAR ops */
};
/*
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 2b0ced611f32..a63fd48e34a7 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -399,6 +399,8 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
pr_devel("%s(): paste addr %llx at %lx, rc %d\n", __func__,
paste_addr, vma->vm_start, rc);
+ txwin->task_ref.vma = vma;
+
return rc;
}
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index ace8ee7a99e6..ed458620f007 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -431,14 +431,27 @@ static int vas_deallocate_window(struct vas_window *vwin)
caps = &vascaps[win->win_type].caps;
mutex_lock(&vas_pseries_mutex);
+ /*
+ * VAS window is already closed in the hypervisor when
+ * lost the credit. So just remove the entry from
+ * the list, remove task references and free vas_window
+ * struct.
+ */
+ if (win->vas_win.status == VAS_WIN_NO_CRED_CLOSE) {
+ vascaps[win->win_type].close_wins--;
+ goto out;
+ }
+
rc = deallocate_free_window(win);
if (rc) {
mutex_unlock(&vas_pseries_mutex);
return rc;
}
- list_del(&win->win_list);
atomic_dec(&caps->used_creds);
+
+out:
+ list_del(&win->win_list);
mutex_unlock(&vas_pseries_mutex);
put_vas_user_win_ref(&vwin->task_ref);
@@ -617,6 +630,74 @@ static int reconfig_open_windows(struct vas_caps *vcaps, int creds)
return rc;
}
+/*
+ * The hypervisor reduces the available credits if the LPAR lost core. It
+ * means the excessive windows should not be active and the user space
+ * should not be using these windows to send compression requests to NX.
+ * So the kernel closes the excessive windows and unmap the paste address
+ * such that the user space receives paste instruction failure. Then up to
+ * the user space to fall back to SW compression and manage with the
+ * existing windows.
+ */
+static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds)
+{
+ struct vas_cop_feat_caps *caps = &vcap->caps;
+ struct vm_area_struct *vma;
+ struct pseries_vas_window *win;
+ struct vas_user_win_ref *task_ref;
+ int rc = 0;
+
+ list_for_each_entry(win, &vcap->list, win_list) {
+ /*
+ * This window is already closed due to lost credit
+ * before. Go for next window.
+ */
+ if (win->vas_win.status == VAS_WIN_NO_CRED_CLOSE)
+ continue;
+
+ task_ref = &win->vas_win.task_ref;
+ mutex_lock(&task_ref->mmap_mutex);
+ vma = task_ref->vma;
+ /*
+ * Number of available credits are reduced, So select
+ * and close windows.
+ */
+ win->vas_win.status = VAS_WIN_NO_CRED_CLOSE;
+
+ mmap_write_lock(task_ref->mm);
+ /*
+ * vma is set in the original mapping. But this mapping
+ * is done with mmap() after the window is opened with ioctl.
+ * so we may not see the original mapping if the core remove
+ * is done before the original mmap() and after the ioctl.
+ */
+ if (vma)
+ zap_page_range(vma, vma->vm_start,
+ vma->vm_end - vma->vm_start);
+
+ mmap_write_unlock(task_ref->mm);
+ mutex_unlock(&task_ref->mmap_mutex);
+ /*
+ * Close VAS window in the hypervisor, but do not
+ * free vas_window struct since it may be reused
+ * when the credit is available later (DLPAR with
+ * adding cores). This struct will be used
+ * later when the process issued with close(FD).
+ */
+ rc = deallocate_free_window(win);
+ if (rc)
+ return rc;
+
+ atomic_dec(&caps->used_creds);
+ vcap->close_wins++;
+
+ if (!--excess_creds)
+ break;
+ }
+
+ return 0;
+}
+
/*
* Get new VAS capabilities when the core add/removal configuration
* changes. Reconfig window configurations based on the credits
@@ -624,7 +705,7 @@ static int reconfig_open_windows(struct vas_caps *vcaps, int creds)
*/
static int vas_reconfig_capabilties(u8 type)
{
- int lpar_creds, avail_creds;
+ int lpar_creds, avail_creds, excess_creds;
struct hv_vas_cop_feat_caps *hv_caps;
struct vas_cop_feat_caps *caps;
struct vas_caps *vcaps;
@@ -667,6 +748,14 @@ static int vas_reconfig_capabilties(u8 type)
avail_creds = lpar_creds -
atomic_read(&caps->used_creds);
rc = reconfig_open_windows(vcaps, avail_creds);
+ } else if (atomic_read(&caps->used_creds) > lpar_creds) {
+ /*
+ * # open windows is more than new LPAR available
+ * credits. So close the excessive windows.
+ */
+ excess_creds = atomic_read(&caps->used_creds) -
+ lpar_creds;
+ rc = reconfig_close_windows(vcaps, excess_creds);
}
out:
--
2.27.0
^ permalink raw reply related
* [PATCH 06/10] powerpc/vas: Map paste address only if window is active
From: Haren Myneni @ 2021-11-29 17:51 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
The paste address mapping is done with mmap() after the window is
opened with ioctl. But the window can be closed due to lost credit
due to core removal before mmap(). So if the window is not active,
return mmap() failure with -EACCES and expects the user space reissue
mmap() when the window is active or open new window when the credit
is available.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/platforms/book3s/vas-api.c | 21 ++++++++++++++++++++-
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/book3s/vas-api.c
b/arch/powerpc/platforms/book3s/vas-api.c
index a63fd48e34a7..2d06bd1b1935 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -379,10 +379,27 @@ static int coproc_mmap(struct file *fp, struct
vm_area_struct *vma)
return -EACCES;
}
+ /*
+ * The initial mapping is done after the window is opened
+ * with ioctl. But this window might have been closed
+ * due to lost credit (core removal on PowerVM) before mmap().
+ * So if the window is not active, return mmap() failure
+ * with -EACCES and expects the user space reconfigure (mmap)
+ * window when it is active again or open new window when
+ * the credit is available.
+ */
+ mutex_lock(&txwin->task_ref.mmap_mutex);
+ if (txwin->status != VAS_WIN_ACTIVE) {
+ pr_err("%s(): Window is not active\n", __func__);
+ rc = -EACCES;
+ goto out;
+ }
+
paste_addr = cp_inst->coproc->vops->paste_addr(txwin);
if (!paste_addr) {
pr_err("%s(): Window paste address failed\n",
__func__);
- return -EINVAL;
+ rc = -EINVAL;
+ goto out;
}
pfn = paste_addr >> PAGE_SHIFT;
@@ -401,6 +418,8 @@ static int coproc_mmap(struct file *fp, struct
vm_area_struct *vma)
txwin->task_ref.vma = vma;
+out:
+ mutex_unlock(&txwin->task_ref.mmap_mutex);
return rc;
}
--
2.27.0
^ permalink raw reply related
* Re: [PATCH] recordmcount: Support empty section from recent binutils
From: Steven Rostedt @ 2021-11-29 17:43 UTC (permalink / raw)
To: LEROY Christophe
Cc: Peter Zijlstra, linuxppc-dev@lists.ozlabs.org,
linux-kernel@vger.kernel.org
In-Reply-To: <efc0e15e-fc93-fb59-068d-602f96ec7431@csgroup.eu>
On Fri, 26 Nov 2021 08:43:23 +0000
LEROY Christophe <christophe.leroy@csgroup.eu> wrote:
> Le 24/11/2021 à 15:43, Christophe Leroy a écrit :
> > Looks like recent binutils (2.36 and over ?) may empty some section,
> > leading to failure like:
> >
> > Cannot find symbol for section 11: .text.unlikely.
> > kernel/kexec_file.o: failed
> > make[1]: *** [scripts/Makefile.build:287: kernel/kexec_file.o] Error 1
> >
> > In order to avoid that, ensure that the section has a content before
> > returning it's name in has_rel_mcount().
>
> This patch doesn't work, on PPC32 I get the following message with this
> patch applied:
>
> [ 0.000000] ftrace: No functions to be traced?
>
> Without the patch I get:
>
> [ 0.000000] ftrace: allocating 22381 entries in 66 pages
> [ 0.000000] ftrace: allocated 66 pages with 2 groups
Because of this report, I have not applied this patch (even though I was
about to push it to Linus).
I'm pulling it from my queue until this gets resolved.
Thanks,
-- Steve
^ permalink raw reply
* [PATCH 07/10] powerpc/vas: Add paste address mmap fault handler
From: Haren Myneni @ 2021-11-29 17:52 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
The user space opens VAS windows and issues NX requests by pasting
CRB on the corresponding paste address mmap. When the system looses
credits due to core removal, the kernel has to close the window in
the hypervisor and make the window inactive by unmapping this paste
address. Also the OS has to handle NX request page faults if the user
space issue NX requests.
This handler remap the new paste address with the same VMA when the
window is active again (due to core add with DLPAR). Otherwise
returns paste failure.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/platforms/book3s/vas-api.c | 60 +++++++++++++++++++++++++
1 file changed, 60 insertions(+)
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 2d06bd1b1935..5ceba75c13eb 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -351,6 +351,65 @@ static int coproc_release(struct inode *inode, struct file *fp)
return 0;
}
+/*
+ * This fault handler is invoked when the VAS/NX generates page fault on
+ * the paste address. Happens if the kernel closes window in hypervisor
+ * (on PowerVM) due to lost credit or the paste address is not mapped.
+ */
+static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ struct file *fp = vma->vm_file;
+ struct coproc_instance *cp_inst = fp->private_data;
+ struct vas_window *txwin;
+ u64 paste_addr;
+ int ret;
+
+ /*
+ * window is not opened. Shouldn't expect this error.
+ */
+ if (!cp_inst || !cp_inst->txwin) {
+ pr_err("%s(): No send window open?\n", __func__);
+ return VM_FAULT_SIGBUS;
+ }
+
+ txwin = cp_inst->txwin;
+ /*
+ * Fault is coming due to missing from the original mmap.
+ * Can happen only when the window is closed due to lost
+ * credit before mmap() or the user space issued NX request
+ * without mapping.
+ */
+ if (txwin->task_ref.vma != vmf->vma) {
+ pr_err("%s(): No previous mapping with paste address\n",
+ __func__);
+ return VM_FAULT_SIGBUS;
+ }
+
+ mutex_lock(&txwin->task_ref.mmap_mutex);
+ /*
+ * The window may be inactive due to lost credit (Ex: core
+ * removal with DLPAR). When the window is active again when
+ * the credit is available, remap with the new paste address.
+ */
+ if (txwin->status == VAS_WIN_ACTIVE) {
+ paste_addr = cp_inst->coproc->vops->paste_addr(txwin);
+ if (paste_addr) {
+ ret = vmf_insert_pfn(vma, vma->vm_start,
+ (paste_addr >> PAGE_SHIFT));
+ mutex_unlock(&txwin->task_ref.mmap_mutex);
+ return ret;
+ }
+ }
+ mutex_unlock(&txwin->task_ref.mmap_mutex);
+
+ return VM_FAULT_SIGBUS;
+
+}
+static const struct vm_operations_struct vas_vm_ops = {
+ .fault = vas_mmap_fault,
+};
+
static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
{
struct coproc_instance *cp_inst = fp->private_data;
@@ -417,6 +476,7 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
paste_addr, vma->vm_start, rc);
txwin->task_ref.vma = vma;
+ vma->vm_ops = &vas_vm_ops;
out:
mutex_unlock(&txwin->task_ref.mmap_mutex);
--
2.27.0
^ permalink raw reply related
* [PATCH 08/10] powerpc/vas: Return paste instruction failure if no active window
From: Haren Myneni @ 2021-11-29 17:53 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
The VAS window may not be active if the system looses credits and
the NX generates page fault when it receives request on unmap
paste address.
The kernel handles the fault by remap new paste address if the
window is active again, Otherwise return the paste instruction
failure if the executed instruction that caused the fault was
a paste.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/include/asm/ppc-opcode.h | 2 ++
arch/powerpc/platforms/book3s/vas-api.c | 47 ++++++++++++++++++++++++-
2 files changed, 48 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index baea657bc868..30bb3c0e07f9 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -261,6 +261,8 @@
#define PPC_INST_MFSPR_PVR 0x7c1f42a6
#define PPC_INST_MFSPR_PVR_MASK 0xfc1ffffe
#define PPC_INST_MTMSRD 0x7c000164
+#define PPC_INST_PASTE 0x7c20070d
+#define PPC_INST_PASTE_MASK 0xfc2007ff
#define PPC_INST_POPCNTB 0x7c0000f4
#define PPC_INST_POPCNTB_MASK 0xfc0007fe
#define PPC_INST_RFEBB 0x4c000124
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 5ceba75c13eb..2ffd34bc4032 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -351,6 +351,41 @@ static int coproc_release(struct inode *inode, struct file *fp)
return 0;
}
+/*
+ * If the executed instruction that caused the fault was a paste, then
+ * clear regs CR0[EQ], advance NIP, and return 0. Else return error code.
+ */
+static int do_fail_paste(void)
+{
+ struct pt_regs *regs = current->thread.regs;
+ u32 instword;
+
+ if (WARN_ON_ONCE(!regs))
+ return -EINVAL;
+
+ if (WARN_ON_ONCE(!user_mode(regs)))
+ return -EINVAL;
+
+ /*
+ * If we couldn't translate the instruction, the driver should
+ * return success without handling the fault, it will be retried
+ * or the instruction fetch will fault.
+ */
+ if (get_user(instword, (u32 __user *)(regs->nip)))
+ return -EAGAIN;
+
+ /*
+ * Not a paste instruction, driver may fail the fault.
+ */
+ if ((instword & PPC_INST_PASTE_MASK) != PPC_INST_PASTE)
+ return -ENOENT;
+
+ regs->ccr &= ~0xe0000000; /* Clear CR0[0-2] to fail paste */
+ regs_add_return_ip(regs, 4); /* Skip the paste */
+
+ return 0;
+}
+
/*
* This fault handler is invoked when the VAS/NX generates page fault on
* the paste address. Happens if the kernel closes window in hypervisor
@@ -403,9 +438,19 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
}
mutex_unlock(&txwin->task_ref.mmap_mutex);
- return VM_FAULT_SIGBUS;
+ /*
+ * Received this fault due to closing the actual window.
+ * It can happen during migration or lost credits.
+ * Since no mapping, return the paste instruction failure
+ * to the user space.
+ */
+ ret = do_fail_paste();
+ if (!ret)
+ return VM_FAULT_NOPAGE;
+ return VM_FAULT_SIGBUS;
}
+
static const struct vm_operations_struct vas_vm_ops = {
.fault = vas_mmap_fault,
};
--
2.27.0
^ permalink raw reply related
* [PATCH 09/10] powerpc/pseries/vas: sysfs interface to export capabilities
From: Haren Myneni @ 2021-11-29 17:54 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
The hypervisor provides the available VAS GZIP capabilities such
as default or QoS window type and the target available credits in
each type. This patch creates sysfs entries and exports the target,
used and the available credits for each feature.
This interface can be used by the user space to determine the credits
usage or to set the target credits in the case of QoS type (for DLPAR).
/sys/devices/vas/vas0/gzip/def_caps: (default GZIP capabilities)
avail_creds /* Available credits to use */
target_creds /* Total credits available. Can be
/* changed with DLPAR operation */
used_creds /* Used credits */
/sys/devices/vas/vas0/gzip/qos_caps (QoS GZIP capabilities)
avail_creds
target_creds
used_creds
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/platforms/pseries/Makefile | 2 +-
arch/powerpc/platforms/pseries/vas-sysfs.c | 214 +++++++++++++++++++++
arch/powerpc/platforms/pseries/vas.c | 6 +
arch/powerpc/platforms/pseries/vas.h | 6 +
4 files changed, 227 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/platforms/pseries/vas-sysfs.c
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 41d8aee98da4..349f42c31b65 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -30,6 +30,6 @@ obj-$(CONFIG_PPC_SVM) += svm.o
obj-$(CONFIG_FA_DUMP) += rtas-fadump.o
obj-$(CONFIG_SUSPEND) += suspend.o
-obj-$(CONFIG_PPC_VAS) += vas.o
+obj-$(CONFIG_PPC_VAS) += vas.o vas-sysfs.o
obj-$(CONFIG_ARCH_HAS_CC_PLATFORM) += cc_platform.o
diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c
new file mode 100644
index 000000000000..625082bebcb2
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/vas-sysfs.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2016-17 IBM Corp.
+ */
+
+#define pr_fmt(fmt) "vas: " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include "vas.h"
+
+#ifdef CONFIG_SYSFS
+static struct kobject *pseries_vas_kobj;
+static struct kobject *gzip_caps_kobj;
+
+struct vas_caps_entry {
+ struct kobject kobj;
+ struct vas_cop_feat_caps *caps;
+};
+
+#define to_caps_entry(entry) container_of(entry, struct vas_caps_entry, kobj)
+
+static ssize_t avail_creds_show(struct vas_cop_feat_caps *caps, char *buf)
+{
+ int avail_creds = atomic_read(&caps->target_creds) -
+ atomic_read(&caps->used_creds);
+ return sprintf(buf, "%d\n", avail_creds);
+}
+
+#define sysfs_capbs_entry_read(_name) \
+static ssize_t _name##_show(struct vas_cop_feat_caps *caps, char *buf) \
+{ \
+ return sprintf(buf, "%d\n", atomic_read(&caps->_name)); \
+}
+
+struct vas_sysfs_entry {
+ struct attribute attr;
+ ssize_t (*show)(struct vas_cop_feat_caps *, char *);
+ ssize_t (*store)(struct vas_cop_feat_caps *, const char *, size_t);
+};
+
+#define VAS_ATTR_RO(_name) \
+ sysfs_capbs_entry_read(_name); \
+ static struct vas_sysfs_entry _name##_attribute = __ATTR(_name, \
+ 0444, _name##_show, NULL);
+
+VAS_ATTR_RO(target_creds);
+VAS_ATTR_RO(used_creds);
+
+static struct vas_sysfs_entry avail_creds_attribute =
+ __ATTR(avail_creds, 0444, avail_creds_show, NULL);
+
+static struct attribute *vas_capab_attrs[] = {
+ &target_creds_attribute.attr,
+ &used_creds_attribute.attr,
+ &avail_creds_attribute.attr,
+ NULL,
+};
+
+static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct vas_caps_entry *centry;
+ struct vas_cop_feat_caps *caps;
+ struct vas_sysfs_entry *entry;
+
+ centry = to_caps_entry(kobj);
+ caps = centry->caps;
+ entry = container_of(attr, struct vas_sysfs_entry, attr);
+
+ if (!entry->show)
+ return -EIO;
+
+ return entry->show(caps, buf);
+}
+
+static ssize_t vas_type_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t count)
+{
+ struct vas_caps_entry *centry;
+ struct vas_cop_feat_caps *caps;
+ struct vas_sysfs_entry *entry;
+
+ centry = to_caps_entry(kobj);
+ caps = centry->caps;
+ entry = container_of(attr, struct vas_sysfs_entry, attr);
+ if (!entry->store)
+ return -EIO;
+
+ return entry->store(caps, buf, count);
+}
+
+static void vas_type_release(struct kobject *kobj)
+{
+ struct vas_caps_entry *centry = to_caps_entry(kobj);
+ kfree(centry);
+}
+
+static const struct sysfs_ops vas_sysfs_ops = {
+ .show = vas_type_show,
+ .store = vas_type_store,
+};
+
+static struct kobj_type vas_attr_type = {
+ .release = vas_type_release,
+ .sysfs_ops = &vas_sysfs_ops,
+ .default_attrs = vas_capab_attrs,
+};
+
+static char *vas_caps_kobj_name(struct vas_cop_feat_caps *caps,
+ struct kobject **kobj)
+{
+ if (caps->descriptor == VAS_GZIP_QOS_CAPABILITIES) {
+ *kobj = gzip_caps_kobj;
+ return "qos_caps";
+ } else if (caps->descriptor == VAS_GZIP_DEFAULT_CAPABILITIES) {
+ *kobj = gzip_caps_kobj;
+ return "def_caps";
+ } else
+ return "Unknown";
+}
+
+/*
+ * Add feature specific capability dir entry.
+ * Ex: VDefGzip or VQosGzip
+ */
+int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps)
+{
+ struct vas_caps_entry *centry;
+ struct kobject *kobj = NULL;
+ int ret = 0;
+ char *name;
+
+ centry = kzalloc(sizeof(*centry), GFP_KERNEL);
+ if (!centry)
+ return -ENOMEM;
+
+ kobject_init(¢ry->kobj, &vas_attr_type);
+ centry->caps = caps;
+ name = vas_caps_kobj_name(caps, &kobj);
+
+ if (kobj) {
+ ret = kobject_add(¢ry->kobj, kobj, "%s", name);
+
+ if (ret) {
+ pr_err("VAS: sysfs kobject add / event failed %d\n",
+ ret);
+ kobject_put(¢ry->kobj);
+ }
+ }
+
+ return ret;
+}
+
+static struct miscdevice vas_miscdev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "vas",
+};
+
+/*
+ * Add VAS and VasCaps (overall capabilities) dir entries.
+ */
+int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps)
+{
+ int ret;
+
+ ret = misc_register(&vas_miscdev);
+ if (ret < 0) {
+ pr_err("%s: register vas misc device failed\n", __func__);
+ return ret;
+ }
+
+ /*
+ * The hypervisor does not expose multiple VAS instances, but can
+ * see multiple VAS instances on PowerNV. So create 'vas0' directory
+ * on PowerVM.
+ */
+ pseries_vas_kobj = kobject_create_and_add("vas0",
+ &vas_miscdev.this_device->kobj);
+ if (!pseries_vas_kobj) {
+ pr_err("Failed to create VAS sysfs entry\n");
+ return -ENOMEM;
+ }
+
+ if ((vas_caps->feat_type & VAS_GZIP_QOS_FEAT_BIT) ||
+ (vas_caps->feat_type & VAS_GZIP_DEF_FEAT_BIT)) {
+ gzip_caps_kobj = kobject_create_and_add("gzip",
+ pseries_vas_kobj);
+ if (!gzip_caps_kobj) {
+ pr_err("Failed to create VAS GZIP capability entry\n");
+ kobject_put(pseries_vas_kobj);
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+#else
+int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps)
+{
+ return 0;
+}
+
+int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps)
+{
+ return 0;
+}
+#endif
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index ed458620f007..c769c8534b3a 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -540,6 +540,10 @@ static int get_vas_capabilities(u8 feat, enum vas_cop_feat_type type,
}
}
+ rc = sysfs_add_vas_caps(caps);
+ if (rc)
+ return rc;
+
copypaste_feat = true;
return 0;
@@ -826,6 +830,8 @@ static int __init pseries_vas_init(void)
caps_all.descriptor = be64_to_cpu(hv_caps->descriptor);
caps_all.feat_type = be64_to_cpu(hv_caps->feat_type);
+ sysfs_pseries_vas_init(&caps_all);
+
hv_cop_caps = kmalloc(sizeof(*hv_cop_caps), GFP_KERNEL);
if (!hv_cop_caps) {
rc = -ENOMEM;
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 1fbb49a34d48..15bcadf8872a 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -30,6 +30,9 @@
#define VAS_COPY_PASTE_USER_MODE 0x00000001
#define VAS_COP_OP_USER_MODE 0x00000010
+#define VAS_GZIP_QOS_CAPABILITIES 0x56516F73477A6970
+#define VAS_GZIP_DEFAULT_CAPABILITIES 0x56446566477A6970
+
/*
* Co-processor feature - GZIP QoS windows or GZIP default windows
*/
@@ -125,4 +128,7 @@ struct pseries_vas_window {
char *name;
int fault_virq;
};
+
+int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);
+int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps);
#endif /* _VAS_H */
--
2.27.0
^ permalink raw reply related
* [PATCH 10/10] powerpc/pseries/vas: Write 'target_creds' for QoS credits change
From: Haren Myneni @ 2021-11-29 17:55 UTC (permalink / raw)
To: mpe, linuxppc-dev, npiggin
In-Reply-To: <a2187018b4e030fe6c7e408b3a73c37c85472e10.camel@linux.ibm.com>
PowerVM support two types of credits - Default (uses normal priority
FIFO) and Qality of service (QoS uses high priproty FIFO). The user
decides the number of QoS credits and sets this value with HMC
interface. With the core add/removal, this value can be changed in HMC
which invokes drmgr to communicate to the kernel.
This patch adds an interface so that drmgr command can write the new
target QoS credits in sysfs. But the kernel gets the new QoS
capabilities from the hypervisor whenever target_creds is updated
to make sure sync with the values in the hypervisor.
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
---
arch/powerpc/platforms/pseries/vas-sysfs.c | 34 +++++++++++++++++++++-
arch/powerpc/platforms/pseries/vas.c | 2 +-
arch/powerpc/platforms/pseries/vas.h | 1 +
3 files changed, 35 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c
index 625082bebcb2..5bae2269d194 100644
--- a/arch/powerpc/platforms/pseries/vas-sysfs.c
+++ b/arch/powerpc/platforms/pseries/vas-sysfs.c
@@ -32,6 +32,34 @@ static ssize_t avail_creds_show(struct vas_cop_feat_caps *caps, char *buf)
return sprintf(buf, "%d\n", avail_creds);
}
+/*
+ * This function is used to get the notification from the drmgr when
+ * QoS credits are changed as part of DLPAR core add/removal. Though
+ * receiving the total QoS credits here, get the official QoS
+ * capabilities from the hypervisor.
+ */
+static ssize_t target_creds_store(struct vas_cop_feat_caps *caps,
+ const char *buf, size_t count)
+{
+ int err;
+ u16 creds;
+
+ /*
+ * Nothing to do for default credit type.
+ */
+ if (caps->win_type == VAS_GZIP_DEF_FEAT_TYPE)
+ return -EOPNOTSUPP;
+
+ err = kstrtou16(buf, 0, &creds);
+ if (!err)
+ err = vas_reconfig_capabilties(caps->win_type);
+
+ if (err)
+ return -EINVAL;
+
+ return count;
+}
+
#define sysfs_capbs_entry_read(_name) \
static ssize_t _name##_show(struct vas_cop_feat_caps *caps, char *buf) \
{ \
@@ -48,8 +76,12 @@ struct vas_sysfs_entry {
sysfs_capbs_entry_read(_name); \
static struct vas_sysfs_entry _name##_attribute = __ATTR(_name, \
0444, _name##_show, NULL);
+#define VAS_ATTR(_name) \
+ sysfs_capbs_entry_read(_name); \
+ static struct vas_sysfs_entry _name##_attribute = __ATTR(_name, \
+ 0644, _name##_show, _name##_store)
-VAS_ATTR_RO(target_creds);
+VAS_ATTR(target_creds);
VAS_ATTR_RO(used_creds);
static struct vas_sysfs_entry avail_creds_attribute =
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index c769c8534b3a..d271fa71bded 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -707,7 +707,7 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds)
* changes. Reconfig window configurations based on the credits
* availability from this new capabilities.
*/
-static int vas_reconfig_capabilties(u8 type)
+int vas_reconfig_capabilties(u8 type)
{
int lpar_creds, avail_creds, excess_creds;
struct hv_vas_cop_feat_caps *hv_caps;
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 15bcadf8872a..e369db35f0fd 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -130,5 +130,6 @@ struct pseries_vas_window {
};
int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);
+int vas_reconfig_capabilties(u8 type);
int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps);
#endif /* _VAS_H */
--
2.27.0
^ permalink raw reply related
* Re: [PATCH] recordmcount: Support empty section from recent binutils
From: Christophe Leroy @ 2021-11-29 17:56 UTC (permalink / raw)
To: Steven Rostedt, Segher Boessenkool
Cc: Peter Zijlstra, linuxppc-dev@lists.ozlabs.org,
linux-kernel@vger.kernel.org
In-Reply-To: <20211129124355.52474d90@gandalf.local.home>
Le 29/11/2021 à 18:43, Steven Rostedt a écrit :
> On Fri, 26 Nov 2021 08:43:23 +0000
> LEROY Christophe <christophe.leroy@csgroup.eu> wrote:
>
>> Le 24/11/2021 à 15:43, Christophe Leroy a écrit :
>>> Looks like recent binutils (2.36 and over ?) may empty some section,
>>> leading to failure like:
>>>
>>> Cannot find symbol for section 11: .text.unlikely.
>>> kernel/kexec_file.o: failed
>>> make[1]: *** [scripts/Makefile.build:287: kernel/kexec_file.o] Error 1
>>>
>>> In order to avoid that, ensure that the section has a content before
>>> returning it's name in has_rel_mcount().
>>
>> This patch doesn't work, on PPC32 I get the following message with this
>> patch applied:
>>
>> [ 0.000000] ftrace: No functions to be traced?
>>
>> Without the patch I get:
>>
>> [ 0.000000] ftrace: allocating 22381 entries in 66 pages
>> [ 0.000000] ftrace: allocated 66 pages with 2 groups
>
> Because of this report, I have not applied this patch (even though I was
> about to push it to Linus).
>
> I'm pulling it from my queue until this gets resolved.
>
I have no idea on how to fix that for the moment.
With GCC 10 (binutils 2.36) an objdump -x on kernel/kexec_file.o gives:
0000000000000000 l d .text.unlikely 0000000000000000 .text.unlikely
0000000000000000 w F .text.unlikely 0000000000000038
.arch_kexec_apply_relocations_add
0000000000000038 w F .text.unlikely 0000000000000038
.arch_kexec_apply_relocations
With GCC 11 (binutils 2.37) the same gives:
0000000000000000 w F .text.unlikely 0000000000000038
.arch_kexec_apply_relocations_add
0000000000000038 w F .text.unlikely 0000000000000038
.arch_kexec_apply_relocations
The problem is that recordmcount drops weak symbols, and it doesn't find
any non-weak symbol in .text.unlikely
Explication given at
https://elixir.bootlin.com/linux/v5.16-rc2/source/scripts/recordmcount.h#L506
I have no idea on what to do.
Thanks
Christophe
^ 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