* [PATCH v6 04/28] powerpc/xmon: Use bitwise calculations in_breakpoint_table()
From: Jordan Niethe @ 2020-04-28 1:57 UTC (permalink / raw)
To: linuxppc-dev; +Cc: alistair, npiggin, bala24, Jordan Niethe, dja
In-Reply-To: <20200428015814.15380-1-jniethe5@gmail.com>
A modulo operation is used for calculating the current offset from a
breakpoint within the breakpoint table. As instruction lengths are
always a power of 2, this can be replaced with a bitwise 'and'. The
current check for word alignment can be replaced with checking that the
lower 2 bits are not set.
Suggested-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
---
v6: New to series
---
arch/powerpc/xmon/xmon.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index f7ce3ea8694c..e922cde99db2 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -856,8 +856,8 @@ static struct bpt *in_breakpoint_table(unsigned long nip, unsigned long *offp)
off = nip - (unsigned long) bpt_table;
if (off >= sizeof(bpt_table))
return NULL;
- *offp = off % BPT_SIZE;
- if (*offp != 0 && *offp != 4)
+ *offp = off & (BPT_SIZE - 1);
+ if (off & 3)
return NULL;
return bpts + (off / BPT_SIZE);
}
--
2.17.1
^ permalink raw reply related
* [PATCH v6 03/28] powerpc/xmon: Move breakpoints to text section
From: Jordan Niethe @ 2020-04-28 1:57 UTC (permalink / raw)
To: linuxppc-dev; +Cc: alistair, npiggin, bala24, Jordan Niethe, dja
In-Reply-To: <20200428015814.15380-1-jniethe5@gmail.com>
The instructions for xmon's breakpoint are stored bpt_table[] which is in
the data section. This is problematic as the data section may be marked
as no execute. Move bpt_table[] to the text section.
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
---
v6: - New to series. Was part of the previous patch.
- Make BPT_SIZE available in assembly
---
arch/powerpc/kernel/asm-offsets.c | 8 ++++++++
arch/powerpc/xmon/Makefile | 2 +-
arch/powerpc/xmon/xmon.c | 6 +-----
arch/powerpc/xmon/xmon_bpts.S | 9 +++++++++
arch/powerpc/xmon/xmon_bpts.h | 14 ++++++++++++++
5 files changed, 33 insertions(+), 6 deletions(-)
create mode 100644 arch/powerpc/xmon/xmon_bpts.S
create mode 100644 arch/powerpc/xmon/xmon_bpts.h
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c25e562f1cd9..2401f415f423 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -70,6 +70,10 @@
#include <asm/fixmap.h>
#endif
+#ifdef CONFIG_XMON
+#include "../xmon/xmon_bpts.h"
+#endif
+
#define STACK_PT_REGS_OFFSET(sym, val) \
DEFINE(sym, STACK_FRAME_OVERHEAD + offsetof(struct pt_regs, val))
@@ -783,5 +787,9 @@ int main(void)
DEFINE(VIRT_IMMR_BASE, (u64)__fix_to_virt(FIX_IMMR_BASE));
#endif
+#ifdef CONFIG_XMON
+ DEFINE(BPT_SIZE, BPT_SIZE);
+#endif
+
return 0;
}
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index c3842dbeb1b7..515a13ea6f28 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -21,7 +21,7 @@ endif
ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-obj-y += xmon.o nonstdio.o spr_access.o
+obj-y += xmon.o nonstdio.o spr_access.o xmon_bpts.o
ifdef CONFIG_XMON_DISASSEMBLY
obj-y += ppc-dis.o ppc-opc.o
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a064392df1b8..f7ce3ea8694c 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -62,6 +62,7 @@
#include "nonstdio.h"
#include "dis-asm.h"
+#include "xmon_bpts.h"
#ifdef CONFIG_SMP
static cpumask_t cpus_in_xmon = CPU_MASK_NONE;
@@ -108,7 +109,6 @@ struct bpt {
#define BP_TRAP 2
#define BP_DABR 4
-#define NBPTS 256
static struct bpt bpts[NBPTS];
static struct bpt dabr;
static struct bpt *iabr;
@@ -116,10 +116,6 @@ static unsigned bpinstr = 0x7fe00008; /* trap */
#define BP_NUM(bp) ((bp) - bpts + 1)
-#define BPT_SIZE (sizeof(unsigned int) * 2)
-#define BPT_WORDS (BPT_SIZE / sizeof(unsigned int))
-static unsigned int bpt_table[NBPTS * BPT_WORDS];
-
/* Prototypes */
static int cmds(struct pt_regs *);
static int mread(unsigned long, void *, int);
diff --git a/arch/powerpc/xmon/xmon_bpts.S b/arch/powerpc/xmon/xmon_bpts.S
new file mode 100644
index 000000000000..f3ad0ab50854
--- /dev/null
+++ b/arch/powerpc/xmon/xmon_bpts.S
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/ppc_asm.h>
+#include <asm/asm-compat.h>
+#include <asm/asm-offsets.h>
+#include "xmon_bpts.h"
+
+.global bpt_table
+bpt_table:
+ .space NBPTS * BPT_SIZE
diff --git a/arch/powerpc/xmon/xmon_bpts.h b/arch/powerpc/xmon/xmon_bpts.h
new file mode 100644
index 000000000000..b7e94375db86
--- /dev/null
+++ b/arch/powerpc/xmon/xmon_bpts.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef XMON_BPTS_H
+#define XMON_BPTS_H
+
+#define NBPTS 256
+#ifndef __ASSEMBLY__
+#define BPT_SIZE (sizeof(unsigned int) * 2)
+#define BPT_WORDS (BPT_SIZE / sizeof(unsigned int))
+
+extern unsigned int bpt_table[NBPTS * BPT_WORDS];
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* XMON_BPTS_H */
--
2.17.1
^ permalink raw reply related
* [PATCH v6 02/28] powerpc/xmon: Move breakpoint instructions to own array
From: Jordan Niethe @ 2020-04-28 1:57 UTC (permalink / raw)
To: linuxppc-dev; +Cc: alistair, npiggin, bala24, Jordan Niethe, dja
In-Reply-To: <20200428015814.15380-1-jniethe5@gmail.com>
To execute an instruction out of line after a breakpoint, the NIP is set
to the address of struct bpt::instr. Here a copy of the instruction that
was replaced with a breakpoint is kept, along with a trap so normal flow
can be resumed after XOLing. The struct bpt's are located within the
data section. This is problematic as the data section may be marked as
no execute.
Instead of each struct bpt holding the instructions to be XOL'd, make a
new array, bpt_table[], with enough space to hold instructions for the
number of supported breakpoints. A later patch will move this to the
text section.
Make struct bpt::instr a pointer to the instructions in bpt_table[]
associated with that breakpoint. This association is a simple mapping:
bpts[n] -> bpt_table[n * words per breakpoint]. Currently we only need
the copied instruction followed by a trap, so 2 words per breakpoint.
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
---
v4: New to series
v5: - Do not use __section(), use a .space directive in .S file
- Simplify in_breakpoint_table() calculation
- Define BPT_SIZE
v6: - Seperate moving to text section
---
arch/powerpc/xmon/xmon.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 02e3bd62cab4..a064392df1b8 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -97,7 +97,7 @@ static long *xmon_fault_jmp[NR_CPUS];
/* Breakpoint stuff */
struct bpt {
unsigned long address;
- unsigned int instr[2];
+ unsigned int *instr;
atomic_t ref_count;
int enabled;
unsigned long pad;
@@ -116,6 +116,10 @@ static unsigned bpinstr = 0x7fe00008; /* trap */
#define BP_NUM(bp) ((bp) - bpts + 1)
+#define BPT_SIZE (sizeof(unsigned int) * 2)
+#define BPT_WORDS (BPT_SIZE / sizeof(unsigned int))
+static unsigned int bpt_table[NBPTS * BPT_WORDS];
+
/* Prototypes */
static int cmds(struct pt_regs *);
static int mread(unsigned long, void *, int);
@@ -853,15 +857,13 @@ static struct bpt *in_breakpoint_table(unsigned long nip, unsigned long *offp)
{
unsigned long off;
- off = nip - (unsigned long) bpts;
- if (off >= sizeof(bpts))
+ off = nip - (unsigned long) bpt_table;
+ if (off >= sizeof(bpt_table))
return NULL;
- off %= sizeof(struct bpt);
- if (off != offsetof(struct bpt, instr[0])
- && off != offsetof(struct bpt, instr[1]))
+ *offp = off % BPT_SIZE;
+ if (*offp != 0 && *offp != 4)
return NULL;
- *offp = off - offsetof(struct bpt, instr[0]);
- return (struct bpt *) (nip - off);
+ return bpts + (off / BPT_SIZE);
}
static struct bpt *new_breakpoint(unsigned long a)
@@ -876,7 +878,8 @@ static struct bpt *new_breakpoint(unsigned long a)
for (bp = bpts; bp < &bpts[NBPTS]; ++bp) {
if (!bp->enabled && atomic_read(&bp->ref_count) == 0) {
bp->address = a;
- patch_instruction(&bp->instr[1], bpinstr);
+ bp->instr = bpt_table + ((bp - bpts) * BPT_WORDS);
+ patch_instruction(bp->instr + 1, bpinstr);
return bp;
}
}
--
2.17.1
^ permalink raw reply related
* [PATCH v6 01/28] powerpc/xmon: Remove store_inst() for patch_instruction()
From: Jordan Niethe @ 2020-04-28 1:57 UTC (permalink / raw)
To: linuxppc-dev; +Cc: alistair, npiggin, bala24, Jordan Niethe, dja
In-Reply-To: <20200428015814.15380-1-jniethe5@gmail.com>
For modifying instructions in xmon, patch_instruction() can serve the
same role that store_inst() is performing with the advantage of not
being specific to xmon. In some places patch_instruction() is already
being using followed by store_inst(). In these cases just remove the
store_inst(). Otherwise replace store_inst() with patch_instruction().
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
---
v4: Read into a local variable
---
arch/powerpc/xmon/xmon.c | 18 +++++-------------
1 file changed, 5 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index e8c84d265602..02e3bd62cab4 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -325,11 +325,6 @@ static inline void sync(void)
asm volatile("sync; isync");
}
-static inline void store_inst(void *p)
-{
- asm volatile ("dcbst 0,%0; sync; icbi 0,%0; isync" : : "r" (p));
-}
-
static inline void cflush(void *p)
{
asm volatile ("dcbf 0,%0; icbi 0,%0" : : "r" (p));
@@ -881,8 +876,7 @@ static struct bpt *new_breakpoint(unsigned long a)
for (bp = bpts; bp < &bpts[NBPTS]; ++bp) {
if (!bp->enabled && atomic_read(&bp->ref_count) == 0) {
bp->address = a;
- bp->instr[1] = bpinstr;
- store_inst(&bp->instr[1]);
+ patch_instruction(&bp->instr[1], bpinstr);
return bp;
}
}
@@ -894,25 +888,26 @@ static struct bpt *new_breakpoint(unsigned long a)
static void insert_bpts(void)
{
int i;
+ unsigned int instr;
struct bpt *bp;
bp = bpts;
for (i = 0; i < NBPTS; ++i, ++bp) {
if ((bp->enabled & (BP_TRAP|BP_CIABR)) == 0)
continue;
- if (mread(bp->address, &bp->instr[0], 4) != 4) {
+ if (mread(bp->address, &instr, 4) != 4) {
printf("Couldn't read instruction at %lx, "
"disabling breakpoint there\n", bp->address);
bp->enabled = 0;
continue;
}
- if (IS_MTMSRD(bp->instr[0]) || IS_RFID(bp->instr[0])) {
+ if (IS_MTMSRD(instr) || IS_RFID(instr)) {
printf("Breakpoint at %lx is on an mtmsrd or rfid "
"instruction, disabling it\n", bp->address);
bp->enabled = 0;
continue;
}
- store_inst(&bp->instr[0]);
+ patch_instruction(bp->instr, instr);
if (bp->enabled & BP_CIABR)
continue;
if (patch_instruction((unsigned int *)bp->address,
@@ -922,7 +917,6 @@ static void insert_bpts(void)
bp->enabled &= ~BP_TRAP;
continue;
}
- store_inst((void *)bp->address);
}
}
@@ -957,8 +951,6 @@ static void remove_bpts(void)
(unsigned int *)bp->address, bp->instr[0]) != 0)
printf("Couldn't remove breakpoint at %lx\n",
bp->address);
- else
- store_inst((void *)bp->address);
}
}
--
2.17.1
^ permalink raw reply related
* [PATCH v6 00/28] Initial Prefixed Instruction support
From: Jordan Niethe @ 2020-04-28 1:57 UTC (permalink / raw)
To: linuxppc-dev; +Cc: alistair, npiggin, bala24, Jordan Niethe, dja
A future revision of the ISA will introduce prefixed instructions. A
prefixed instruction is composed of a 4-byte prefix followed by a
4-byte suffix.
All prefixes have the major opcode 1. A prefix will never be a valid
word instruction. A suffix may be an existing word instruction or a
new instruction.
This series enables prefixed instructions and extends the instruction
emulation to support them. Then the places where prefixed instructions
might need to be emulated are updated.
v6 is based on feedback from Balamuruhan Suriyakumar, Alistair Popple,
Christophe Leroy and Segher Boessenkool.
The major changes:
- Use the instruction type in more places that had been missed before
- Fix issues with ppc32
- Introduce new self tests for code patching and feature fixups
v5 is based on feedback from Nick Piggins, Michael Ellerman, Balamuruhan
Suriyakumar and Alistair Popple.
The major changes:
- The ppc instruction type is now a struct
- Series now just based on next
- ppc_inst_masked() dropped
- Space for xmon breakpoints allocated in an assembly file
- "Add prefixed instructions to instruction data type" patch seperated in
to smaller patches
- Calling convention for create_branch() is changed
- Some places which had not been updated to use the data type are now updated
v4 is based on feedback from Nick Piggins, Christophe Leroy and Daniel Axtens.
The major changes:
- Move xmon breakpoints from data section to text section
- Introduce a data type for instructions on powerpc
v3 is based on feedback from Christophe Leroy. The major changes:
- Completely replacing store_inst() with patch_instruction() in
xmon
- Improve implementation of mread_instr() to not use mread().
- Base the series on top of
https://patchwork.ozlabs.org/patch/1232619/ as this will effect
kprobes.
- Some renaming and simplification of conditionals.
v2 incorporates feedback from Daniel Axtens and and Balamuruhan
S. The major changes are:
- Squashing together all commits about SRR1 bits
- Squashing all commits for supporting prefixed load stores
- Changing abbreviated references to sufx/prfx -> suffix/prefix
- Introducing macros for returning the length of an instruction
- Removing sign extension flag from pstd/pld in sstep.c
- Dropping patch "powerpc/fault: Use analyse_instr() to check for
store with updates to sp" from the series, it did not really fit
with prefixed enablement in the first place and as reported by Greg
Kurz did not work correctly.
Alistair Popple (1):
powerpc: Enable Prefixed Instructions
Jordan Niethe (27):
powerpc/xmon: Remove store_inst() for patch_instruction()
powerpc/xmon: Move breakpoint instructions to own array
powerpc/xmon: Move breakpoints to text section
powerpc/xmon: Use bitwise calculations in_breakpoint_table()
powerpc: Change calling convention for create_branch() et. al.
powerpc: Use a macro for creating instructions from u32s
powerpc: Use an accessor for instructions
powerpc: Use a function for getting the instruction op code
powerpc: Use a function for byte swapping instructions
powerpc: Introduce functions for instruction equality
powerpc: Use a datatype for instructions
powerpc: Use a function for reading instructions
powerpc: Add a probe_user_read_inst() function
powerpc: Add a probe_kernel_read_inst() function
powerpc/kprobes: Use patch_instruction()
powerpc: Define and use __get_user_instr{,inatomic}()
powerpc: Introduce a function for reporting instruction length
powerpc/xmon: Use a function for reading instructions
powerpc/xmon: Move insertion of breakpoint for xol'ing
powerpc: Make test_translate_branch() independent of instruction
length
powerpc: Define new SRR1 bits for a future ISA version
powerpc: Add prefixed instructions to instruction data type
powerpc: Test prefixed code patching
powerpc: Test prefixed instructions in feature fixups
powerpc: Support prefixed instructions in alignment handler
powerpc sstep: Add support for prefixed load/stores
powerpc sstep: Add support for prefixed fixed-point arithmetic
arch/powerpc/include/asm/code-patching.h | 37 +-
arch/powerpc/include/asm/inst.h | 106 ++++++
arch/powerpc/include/asm/kprobes.h | 2 +-
arch/powerpc/include/asm/reg.h | 7 +-
arch/powerpc/include/asm/sstep.h | 15 +-
arch/powerpc/include/asm/uaccess.h | 35 ++
arch/powerpc/include/asm/uprobes.h | 7 +-
arch/powerpc/kernel/align.c | 13 +-
arch/powerpc/kernel/asm-offsets.c | 8 +
arch/powerpc/kernel/epapr_paravirt.c | 7 +-
arch/powerpc/kernel/hw_breakpoint.c | 5 +-
arch/powerpc/kernel/jump_label.c | 5 +-
arch/powerpc/kernel/kgdb.c | 9 +-
arch/powerpc/kernel/kprobes.c | 24 +-
arch/powerpc/kernel/mce_power.c | 5 +-
arch/powerpc/kernel/module_64.c | 3 +-
arch/powerpc/kernel/optprobes.c | 91 +++--
arch/powerpc/kernel/optprobes_head.S | 3 +
arch/powerpc/kernel/security.c | 9 +-
arch/powerpc/kernel/setup_32.c | 8 +-
arch/powerpc/kernel/trace/ftrace.c | 160 ++++----
arch/powerpc/kernel/traps.c | 20 +-
arch/powerpc/kernel/uprobes.c | 5 +-
arch/powerpc/kernel/vecemu.c | 20 +-
arch/powerpc/kvm/book3s_hv_nested.c | 2 +-
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
arch/powerpc/kvm/emulate_loadstore.c | 2 +-
arch/powerpc/lib/Makefile | 2 +-
arch/powerpc/lib/code-patching.c | 305 ++++++++-------
arch/powerpc/lib/feature-fixups-test.S | 68 ++++
arch/powerpc/lib/feature-fixups.c | 159 ++++++--
arch/powerpc/lib/inst.c | 69 ++++
arch/powerpc/lib/sstep.c | 461 ++++++++++++++++-------
arch/powerpc/lib/test_code-patching.S | 19 +
arch/powerpc/lib/test_emulate_step.c | 56 +--
arch/powerpc/mm/fault.c | 15 +-
arch/powerpc/perf/core-book3s.c | 4 +-
arch/powerpc/xmon/Makefile | 2 +-
arch/powerpc/xmon/xmon.c | 94 +++--
arch/powerpc/xmon/xmon_bpts.S | 11 +
arch/powerpc/xmon/xmon_bpts.h | 14 +
41 files changed, 1307 insertions(+), 582 deletions(-)
create mode 100644 arch/powerpc/include/asm/inst.h
create mode 100644 arch/powerpc/lib/inst.c
create mode 100644 arch/powerpc/lib/test_code-patching.S
create mode 100644 arch/powerpc/xmon/xmon_bpts.S
create mode 100644 arch/powerpc/xmon/xmon_bpts.h
--
2.17.1
^ permalink raw reply
* [PATCH 1/2] powerpc: Discard .rela* sections if CONFIG_RELOCATABLE is undefined
From: H.J. Lu @ 2020-04-28 1:48 UTC (permalink / raw)
To: linux-kernel
Cc: linux-arch, Yu-cheng Yu, Kees Cook, Arnd Bergmann, Paul Mackerras,
Naveen N . Rao, Borislav Petkov, linuxppc-dev
arch/powerpc/kernel/vmlinux.lds.S has
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
*(.glink .iplt .plt .rela* .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
}
Since .rela* sections are needed when CONFIG_RELOCATABLE is defined,
change to discard .rela* sections if CONFIG_RELOCATABLE is undefined.
Signed-off-by: H.J. Lu <hjl.tools@gmail.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
---
arch/powerpc/kernel/vmlinux.lds.S | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 31a0f201fb6f..4ba07734a210 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -366,9 +366,12 @@ SECTIONS
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .rela* .comment)
+ *(.glink .iplt .plt .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
}
}
--
2.25.4
^ permalink raw reply related
* [PATCH 2/2] Discard .note.gnu.property sections in generic NOTES
From: H.J. Lu @ 2020-04-28 1:49 UTC (permalink / raw)
To: linux-kernel
Cc: linux-arch, Yu-cheng Yu, Kees Cook, Arnd Bergmann, Paul Mackerras,
Naveen N . Rao, Borislav Petkov, linuxppc-dev
In-Reply-To: <20200428014900.407098-1-hjl.tools@gmail.com>
With the command-line option, -mx86-used-note=yes, the x86 assembler
in binutils 2.32 and above generates a program property note in a note
section, .note.gnu.property, to encode used x86 ISAs and features. But
kernel linker script only contains a single NOTE segment:
PHDRS {
text PT_LOAD FLAGS(5);
data PT_LOAD FLAGS(6);
percpu PT_LOAD FLAGS(6);
init PT_LOAD FLAGS(7);
note PT_NOTE FLAGS(0);
}
SECTIONS
{
...
.notes : AT(ADDR(.notes) - 0xffffffff80000000) { __start_notes = .; KEEP(*(.not
e.*)) __stop_notes = .; } :text :note
...
}
The NOTE segment generated by kernel linker script is aligned to 4 bytes.
But .note.gnu.property section must be aligned to 8 bytes on x86-64 and
we get
[hjl@gnu-skx-1 linux]$ readelf -n vmlinux
Displaying notes found in: .notes
Owner Data size Description
Xen 0x00000006 Unknown note type: (0x00000006)
description data: 6c 69 6e 75 78 00
Xen 0x00000004 Unknown note type: (0x00000007)
description data: 32 2e 36 00
xen-3.0 0x00000005 Unknown note type: (0x006e6558)
description data: 08 00 00 00 03
readelf: Warning: note with invalid namesz and/or descsz found at offset 0x50
readelf: Warning: type: 0xffffffff, namesize: 0x006e6558, descsize:
0x80000000, alignment: 8
[hjl@gnu-skx-1 linux]$
Since note.gnu.property section in kernel image is never used, this patch
discards .note.gnu.property sections in kernel linker script by adding
/DISCARD/ : {
*(.note.gnu.property)
}
before kernel NOTE segment in generic NOTES.
Signed-off-by: H.J. Lu <hjl.tools@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
include/asm-generic/vmlinux.lds.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 71e387a5fe90..95cd678428f4 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -833,7 +833,14 @@
#define TRACEDATA
#endif
+/*
+ * Discard .note.gnu.property sections which are unused and have
+ * different alignment requirement from kernel note sections.
+ */
#define NOTES \
+ /DISCARD/ : { \
+ *(.note.gnu.property) \
+ } \
.notes : AT(ADDR(.notes) - LOAD_OFFSET) { \
__start_notes = .; \
KEEP(*(.note.*)) \
--
2.25.4
^ permalink raw reply related
* Re: [PATCH] ibmvfc: don't send implicit logouts prior to NPIV login
From: Martin K. Petersen @ 2020-04-28 1:48 UTC (permalink / raw)
To: Tyrel Datwyler
Cc: martin.petersen, linux-scsi, james.bottomley, Brian King, brking,
linuxppc-dev
In-Reply-To: <20200427214824.6890-1-tyreld@linux.ibm.com>
Tyrel,
> Commit ed830385a2b1 ("scsi: ibmvfc: Avoid loss of all paths during SVC
> node reboot") introduced a regression where when the client resets or
> re-enables its CRQ with the hypervisor there is a chance that if the
> server side doesn't issue its INIT handshake quick enough the client
> can issue an Implicit Logout prior to doing an NPIV Login. The server
> treats this scenario as a protocol violation and closes the CRQ on its
> end forcing the client through a reset that gets the client host state
> and next host action out of agreement leading to a BUG assert.
Applied to 5.7/scsi-fixes, thanks!
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH] ibmvscsi: fix WARN_ON during event pool release
From: Martin K. Petersen @ 2020-04-28 1:46 UTC (permalink / raw)
To: james.bottomley, Tyrel Datwyler
Cc: brking, linuxppc-dev, linux-scsi, Martin K . Petersen
In-Reply-To: <1588027793-17952-1-git-send-email-tyreld@linux.ibm.com>
On Mon, 27 Apr 2020 15:49:53 -0700, Tyrel Datwyler wrote:
> While removing an ibmvscsi client adapter a WARN_ON like the following
> is seen in the kernel log:
Applied to 5.7/scsi-fixes, thanks!
[1/1] scsi: ibmvscsi: fix WARN_ON during event pool release
https://git.kernel.org/mkp/scsi/c/cff6a5746645
--
Martin K. Petersen Oracle Linux Engineering
^ permalink raw reply
* Re: [PATCH] powerpc: Discard .rela* sections if CONFIG_RELOCATABLE is undefined
From: Michael Ellerman @ 2020-04-28 1:18 UTC (permalink / raw)
To: H.J. Lu, linux-kernel
Cc: Kees Cook, Paul Mackerras, Naveen N . Rao, Borislav Petkov,
linuxppc-dev
In-Reply-To: <20200427211628.4244-1-hjl.tools@gmail.com>
"H.J. Lu" <hjl.tools@gmail.com> writes:
> arch/powerpc/kernel/vmlinux.lds.S has
>
> DISCARDS
> /DISCARD/ : {
> *(*.EMB.apuinfo)
> *(.glink .iplt .plt .rela* .comment)
> *(.gnu.version*)
> *(.gnu.attributes)
> *(.eh_frame)
> }
>
> Since .rela* sections are needed when CONFIG_RELOCATABLE is defined,
> change to discard .rela* sections if CONFIG_RELOCATABLE is undefined.
>
> Signed-off-by: H.J. Lu <hjl.tools@gmail.com>
> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
> ---
> arch/powerpc/kernel/vmlinux.lds.S | 5 ++++-
> 1 file changed, 4 insertions(+), 1 deletion(-)
Please insert this patch into your series prior to the patch that caused
the build break.
cheers
> diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
> index 31a0f201fb6f..4ba07734a210 100644
> --- a/arch/powerpc/kernel/vmlinux.lds.S
> +++ b/arch/powerpc/kernel/vmlinux.lds.S
> @@ -366,9 +366,12 @@ SECTIONS
> DISCARDS
> /DISCARD/ : {
> *(*.EMB.apuinfo)
> - *(.glink .iplt .plt .rela* .comment)
> + *(.glink .iplt .plt .comment)
> *(.gnu.version*)
> *(.gnu.attributes)
> *(.eh_frame)
> +#ifndef CONFIG_RELOCATABLE
> + *(.rela*)
> +#endif
> }
> }
> --
> 2.25.4
^ permalink raw reply
* Re: [RFC 1/3] powernv/cpuidle : Support for pre-entry and post exit of stop state in firmware
From: Nicholas Piggin @ 2020-04-28 1:08 UTC (permalink / raw)
To: Abhishek Goel, linux-kernel, linuxppc-dev
Cc: ego, mikey, psampat, oohall, skiboot
In-Reply-To: <20200427021027.114582-1-huntbag@linux.vnet.ibm.com>
Thanks for picking this up and pushing it along. I do plan to come back
and take another look at it all, but what we do need to do first is get
a coherent approach to this proposed new calling convention and OS ops.
It's fine to work on this in the meantime, but to start merging things
my idea is:
- OPAL must leave r13-r15 untouched for the OS.
- OS ops are made available only for a "v4" OS that uses the new
calling convention, including kernel stack.
- OS ops baseline (all OSes must provide) will be console / printk
facility, trap handling and crash/symbol decoding on behalf of OPAL,
and runtime virtual memory.
Other OS ops features can be added in the versioned structure, including
this.
I'm trying to get back to cleaning these things up and start getting
them merged now. Any comments or review on those would be helpful.
Thanks,
Nick
^ permalink raw reply
* Re: [PATCH v2,RESEND] misc: new driver sram_uapi for user level SRAM access
From: Scott Wood @ 2020-04-27 22:54 UTC (permalink / raw)
To: Rob Herring, Wang Wenhu
Cc: Arnd Bergmann, Greg Kroah-Hartman, Randy Dunlap,
linux-kernel@vger.kernel.org, kernel, linuxppc-dev
In-Reply-To: <CAL_JsqK3fpM_tUjHvAMbNzf_nry_iORLXaQBFC8xDK+mxhHDRQ@mail.gmail.com>
On Mon, 2020-04-27 at 09:13 -0500, Rob Herring wrote:
> On Sun, Apr 19, 2020 at 10:06 PM Wang Wenhu <wenhu.wang@vivo.com> wrote:
> >
> > A generic User-Kernel interface that allows a misc device created
> > by it to support file-operations of ioctl and mmap to access SRAM
> > memory from user level. Different kinds of SRAM alloction and free
> > APIs could be registered by specific SRAM hardware level driver to
> > the available list and then be chosen by users to allocate and map
> > SRAM memory from user level.
> >
> > It is extremely helpful for the user space applications that require
> > high performance memory accesses, such as embedded networking devices
> > that would process data in user space, and PowerPC e500 is a case.
> >
> > Signed-off-by: Wang Wenhu <wenhu.wang@vivo.com>
> > Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> > Cc: Arnd Bergmann <arnd@arndb.de>
> > Cc: Christophe Leroy <christophe.leroy@c-s.fr>
> > Cc: Scott Wood <oss@buserror.net>
> > Cc: Michael Ellerman <mpe@ellerman.id.au>
> > Cc: Randy Dunlap <rdunlap@infradead.org>
> > Cc: linuxppc-dev@lists.ozlabs.org
> > ---
> > Changes since v1: addressed comments from Arnd
> > * Changed the ioctl cmd definitions using _IO micros
> > * Export interfaces for HW-SRAM drivers to register apis to available
> > list
> > * Modified allocation alignment to PAGE_SIZE
> > * Use phys_addr_t as type of SRAM resource size and offset
> > * Support compat_ioctl
> > * Misc device name:sram
> >
> > Note: From this on, the SRAM_UAPI driver is independent to any hardware
> > drivers, so I would only commit the patch itself as v2, while the v1 of
> > it was wrapped together with patches for Freescale L2-Cache-SRAM device.
> > Then after, I'd create patches for Freescale L2-Cache-SRAM device as
> > another series.
>
> There's work to add SRAM support to dma-buf heaps[1]. Take a look and
> see if that works for you.
>
> Rob
>
> [1] https://lore.kernel.org/lkml/20200424222740.16259-1-afd@ti.com/
>
The dma heap API itself (what makes it specific to DMA, rather than any
special-purpose allocator?) seems like it could be what we're looking for.
The issue with drivers/misc/sram.c is that it seems like its main purpose is
to get sram description from the device tree, but this sram isn't static (it's
a reconfiguration of L2 cache into SRAM mode) and thus can't be described by
mmio-sram.
-Scott
^ permalink raw reply
* [PATCH] ibmvscsi: fix WARN_ON during event pool release
From: Tyrel Datwyler @ 2020-04-27 22:49 UTC (permalink / raw)
To: james.bottomley
Cc: Tyrel Datwyler, brking, linuxppc-dev, linux-scsi, martin.petersen
While removing an ibmvscsi client adapter a WARN_ON like the following
is seen in the kernel log:
drmgr: drmgr: -r -c slot -s U9080.M9S.783AEC8-V11-C11 -w 5 -d 1
WARNING: CPU: 9 PID: 24062 at ../kernel/dma/mapping.c:311 dma_free_attrs+0x78/0x110
Supported: No, Unreleased kernel
CPU: 9 PID: 24062 Comm: drmgr Kdump: loaded Tainted: G X 5.3.18-12-default
NIP: c0000000001fa758 LR: c0000000001fa744 CTR: c0000000001fa6e0
REGS: c0000002173375d0 TRAP: 0700 Tainted: G X (5.3.18-12-default)
MSR: 8000000000029033 <SF,EE,ME,IR,DR,RI,LE> CR: 28088282 XER: 20000000
CFAR: c0000000001fbf0c IRQMASK: 1
GPR00: c0000000001fa744 c000000217337860 c00000000161ab00 0000000000000000
GPR04: 0000000000000000 c000011e12250000 0000000018010000 0000000000000000
GPR08: 0000000000000000 0000000000000001 0000000000000001 c0080000190f4fa8
GPR12: c0000000001fa6e0 c000000007fc2a00 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
GPR24: 000000011420e310 0000000000000000 0000000000000000 0000000018010000
GPR28: c00000000159de50 c000011e12250000 0000000000006600 c000011e5c994848
NIP [c0000000001fa758] dma_free_attrs+0x78/0x110
LR [c0000000001fa744] dma_free_attrs+0x64/0x110
Call Trace:
[c000000217337860] [000000011420e310] 0x11420e310 (unreliable)
[c0000002173378b0] [c0080000190f0280] release_event_pool+0xd8/0x120 [ibmvscsi]
[c000000217337930] [c0080000190f3f74] ibmvscsi_remove+0x6c/0x160 [ibmvscsi]
[c000000217337960] [c0000000000f3cac] vio_bus_remove+0x5c/0x100
[c0000002173379a0] [c00000000087a0a4] device_release_driver_internal+0x154/0x280
[c0000002173379e0] [c0000000008777cc] bus_remove_device+0x11c/0x220
[c000000217337a60] [c000000000870fc4] device_del+0x1c4/0x470
[c000000217337b10] [c0000000008712a0] device_unregister+0x30/0xa0
[c000000217337b80] [c0000000000f39ec] vio_unregister_device+0x2c/0x60
[c000000217337bb0] [c00800001a1d0964] dlpar_remove_slot+0x14c/0x250 [rpadlpar_io]
[c000000217337c50] [c00800001a1d0bcc] remove_slot_store+0xa4/0x110 [rpadlpar_io]
[c000000217337cd0] [c000000000c091a0] kobj_attr_store+0x30/0x50
[c000000217337cf0] [c00000000057c934] sysfs_kf_write+0x64/0x90
[c000000217337d10] [c00000000057be10] kernfs_fop_write+0x1b0/0x290
[c000000217337d60] [c000000000488c4c] __vfs_write+0x3c/0x70
[c000000217337d80] [c00000000048c648] vfs_write+0xd8/0x260
[c000000217337dd0] [c00000000048ca8c] ksys_write+0xdc/0x130
[c000000217337e20] [c00000000000b488] system_call+0x5c/0x70
Instruction dump:
7c840074 f8010010 f821ffb1 20840040 eb830218 7c8407b4 48002019 60000000
2fa30000 409e003c 892d0988 792907e0 <0b090000> 2fbd0000 419e0028 2fbc0000
---[ end trace 5955b3c0cc079942 ]---
rpadlpar_io: slot U9080.M9S.783AEC8-V11-C11 removed
This is tripped as a result of irqs being disabled during the call to
dma_free_coherent() by release_event_pool(). At this point in the code
path we have quiesced the adapter and its overly paranoid anyways to
be holding the host lock.
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
---
drivers/scsi/ibmvscsi/ibmvscsi.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 7f66a77..126b242 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -2326,10 +2326,7 @@ static int ibmvscsi_remove(struct vio_dev *vdev)
scsi_remove_host(hostdata->host);
purge_requests(hostdata, DID_ERROR);
-
- spin_lock_irqsave(hostdata->host->host_lock, flags);
release_event_pool(&hostdata->pool, hostdata);
- spin_unlock_irqrestore(hostdata->host->host_lock, flags);
ibmvscsi_release_crq_queue(&hostdata->queue, hostdata,
max_events);
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH 2/7] signal: factor copy_siginfo_to_external32 from copy_siginfo_to_user32
From: Andrew Morton @ 2020-04-27 22:40 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Arnd Bergmann, Jeremy Kerr, Linus Torvalds, linux-kernel,
Eric W . Biederman, linux-fsdevel, linuxppc-dev, Alexander Viro
In-Reply-To: <20200426074039.GA31501@lst.de>
On Sun, 26 Apr 2020 09:40:39 +0200 Christoph Hellwig <hch@lst.de> wrote:
> On Sat, Apr 25, 2020 at 09:47:24PM -0700, Andrew Morton wrote:
> > I looked at fixing it but surely this sort of thing:
> >
> >
> > int copy_siginfo_to_user32(struct compat_siginfo __user *to,
> > const struct kernel_siginfo *from)
> > #if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
> > {
> > return __copy_siginfo_to_user32(to, from, in_x32_syscall());
> > }
> > int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
> > const struct kernel_siginfo *from, bool x32_ABI)
> > #endif
> > {
> > ...
> >
> >
> > is too ugly to live?
>
> I fixed it up in my earlier versions, but Eric insisted to keep it,
> which is why I switched to his version given that he is the defacto
> signal.c maintainer.
>
> Here is what I would have preferred:
>
> https://www.spinics.net/lists/kernel/msg3473847.html
> https://www.spinics.net/lists/kernel/msg3473840.html
> https://www.spinics.net/lists/kernel/msg3473843.html
OK, but that doesn't necessitate the above monstrosity? How about
static int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
const struct kernel_siginfo *from, bool x32_ABI)
{
struct compat_siginfo new;
copy_siginfo_to_external32(&new, from);
...
}
int copy_siginfo_to_user32(struct compat_siginfo __user *to,
const struct kernel_siginfo *from)
{
#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
return __copy_siginfo_to_user32(to, from, in_x32_syscall());
#else
return __copy_siginfo_to_user32(to, from, 0);
#endif
}
Or something like that - I didn't try very hard. We know how to do
this stuff, and surely this thing isn't how!
^ permalink raw reply
* Re: [PATCH v2 1/2] PCI/AER: Allow Native AER Host Bridges to use AER
From: Bjorn Helgaas @ 2020-04-27 22:14 UTC (permalink / raw)
To: Derrick, Jonathan
Cc: sathyanarayanan.kuppuswamy@linux.intel.com, Patel, Mayurkumar,
fred@fredlawl.com, sbobroff@linux.ibm.com,
linuxppc-dev@lists.ozlabs.org, Wysocki, Rafael J,
linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
andriy.shevchenko@linux.intel.com, olof@lixom.net,
alex.williamson@redhat.com, oohall@gmail.com, kbusch@kernel.org,
rajatja@google.com, mika.westerberg@linux.intel.com
In-Reply-To: <ac3d3b2d3f0e678b792281a1debf5762f1d52b1f.camel@intel.com>
On Mon, Apr 27, 2020 at 04:11:07PM +0000, Derrick, Jonathan wrote:
> On Fri, 2020-04-24 at 18:30 -0500, Bjorn Helgaas wrote:
> > I'm glad you raised this because I think the way we handle
> > FIRMWARE_FIRST is really screwed up.
> >
> > On Mon, Apr 20, 2020 at 03:37:09PM -0600, Jon Derrick wrote:
> > > Some platforms have a mix of ports whose capabilities can be negotiated
> > > by _OSC, and some ports which are not described by ACPI and instead
> > > managed by Native drivers. The existing Firmware-First HEST model can
> > > incorrectly tag these Native, Non-ACPI ports as Firmware-First managed
> > > ports by advertising the HEST Global Flag and matching the type and
> > > class of the port (aer_hest_parse).
> > >
> > > If the port requests Native AER through the Host Bridge's capability
> > > settings, the AER driver should honor those settings and allow the port
> > > to bind. This patch changes the definition of Firmware-First to exclude
> > > ports whose Host Bridges request Native AER.
> > >
> > > Signed-off-by: Jon Derrick <jonathan.derrick@intel.com>
> > > ---
> > > drivers/pci/pcie/aer.c | 3 +++
> > > 1 file changed, 3 insertions(+)
> > >
> > > diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> > > index f4274d3..30fbd1f 100644
> > > --- a/drivers/pci/pcie/aer.c
> > > +++ b/drivers/pci/pcie/aer.c
> > > @@ -314,6 +314,9 @@ int pcie_aer_get_firmware_first(struct pci_dev *dev)
> > > if (pcie_ports_native)
> > > return 0;
> > >
> > > + if (pci_find_host_bridge(dev->bus)->native_aer)
> > > + return 0;
> >
> > I hope we don't have to complicate pcie_aer_get_firmware_first() by
> > adding this "native_aer" check here. I'm not sure what we actually
> > *should* do based on FIRMWARE_FIRST, but I don't think the current
> > uses really make sense.
> >
> > I think Linux makes too many assumptions based on the FIRMWARE_FIRST
> > bit. The ACPI spec really only says (ACPI v6.3, sec 18.3.2.4):
> >
> > If set, FIRMWARE_FIRST indicates to the OSPM that system firmware
> > will handle errors from this source first.
> >
> > If FIRMWARE_FIRST is set in the flags field, the Enabled field [of
> > the HEST AER structure] is ignored by the OSPM.
> >
> > I do not see anything there about who owns the AER Capability, but
> > Linux assumes that if FIRMWARE_FIRST is set, firmware must own the AER
> > Capability. I think that's reading too much into the spec.
> >
> > We already have _OSC, which *does* explicitly talk about who owns the
> > AER Capability, and I think we should rely on that. If firmware
> > doesn't want the OS to touch the AER Capability, it should decline to
> > give ownership to the OS via _OSC.
> >
> > > if (!dev->__aer_firmware_first_valid)
> > > aer_set_firmware_first(dev);
> > > return dev->__aer_firmware_first;
>
> Just a little bit of reading and my interpretation, as it seems like
> some of this is just layers upon layers of possibly conflicting yet
> intentionally vague descriptions.
>
> _OSC seems to describe that OSPM can handle AER (6.2.11.3):
> PCI Express Advanced Error Reporting (AER) control
> The OS sets this bit to 1 to request control over PCI Express AER.
> If the OS successfully receives control of this feature, it must
> handle error reporting through the AER Capability as described in
> the PCI Express Base Specification.
>
>
> For AER and DPC the ACPI root port enumeration will properly set
> native_aer/dpc based on _OSC:
>
> struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root,
> ...
> if (!(root->osc_control_set & OSC_PCI_EXPRESS_AER_CONTROL))
> host_bridge->native_aer = 0;
> if (!(root->osc_control_set & OSC_PCI_EXPRESS_PME_CONTROL))
> host_bridge->native_pme = 0;
> if (!(root->osc_control_set & OSC_PCI_EXPRESS_LTR_CONTROL))
> host_bridge->native_ltr = 0;
> if (!(root->osc_control_set & OSC_PCI_EXPRESS_DPC_CONTROL))
> host_bridge->native_dpc = 0;
>
> As DPC was defined in an ECN [1], I would imagine AER will need to
> cover DPC for legacy platforms prior to the ECN.
>
>
>
> The complication is that HEST also seems to describe how ports (and
> other devices) are managed either individually or globally:
>
> Table 18-387 PCI Express Root Port AER Structure
> ...
> Flags:
> [0] - FIRMWARE_FIRST: If set, this bit indicates to the OSPM that
> system firmware will handle errors from this source
> [1] - GLOBAL: If set, indicates that the settings contained in this
> structure apply globally to all PCI Express Devices. All other bits
> must be set to zero
>
>
> The _OSC definition seems to contradict/negate the above FIRMWARE_FIRST
> definition that says only firmware will handle errors. It's a bit
> different than the IA_32 MCE definition which allows for a GHES_ASSIST
> condition, which would cause Firmware 'First', however does allow the
> error to be received by OSPM AER via GHES:
>
> Table 18-385 IA-32 Architecture Corrected Machine Check Structure
> [0] - FIRMWARE_FIRST: If set, this bit indicates that system
> firmware will handle errors from this source first.
> [2] - GHES_ASSIST: If set, this bit indicates that although OSPM is
> responsible for directly handling the error (as expected when
> FIRMWARE_FIRST is not set), system firmware reports additional
> information in the context of an interrupt generated by the error.
> The additional information is reported in a Generic Hardware Error
> Source structure with a matching Related Source Id.
>
>
> I think Linux needs to make an assumption that devices either
> enumerated in HEST or enumerated globally by HEST should be managed by
> FFS. However it seems that Linux should also be correlating that with
> _OSC as _OSC seems to directly contradict and possibly supercede the
> HEST expectation.
That's basically what Linux been doing -- we've been assuming that if
_OSC declines to grant us control, *or* if FFS is set somewhere, we
shouldn't touch the AER capability. But this leads to lots of weird
corner cases, and I really doubt that firmware and Linux are
interpreting all these the same way.
What breaks if we change Linux to *only* use _OSC to determine
ownership of the AER capability? My argument is that firmware doesn't
want the OS to touch the AER capability registers, it should decline
to give the OS control of the AER capability via _OSC.
If _OSC grants control to the OS in a case where firmware doesn't want
the OS to have control, I'd say that's just a firmware defect that
should be worked around with some sort of quirk.
> [1] https://members.pcisig.com/wg/PCI-SIG/document/12888
^ permalink raw reply
* [PATCH] ibmvfc: don't send implicit logouts prior to NPIV login
From: Tyrel Datwyler @ 2020-04-27 21:48 UTC (permalink / raw)
To: james.bottomley
Cc: Tyrel Datwyler, martin.petersen, linux-scsi, Brian King, brking,
linuxppc-dev
From: Brian King <brking@linux.vnet.ibm.com>
Commit ed830385a2b1 ("scsi: ibmvfc: Avoid loss of all paths during
SVC node reboot") introduced a regression where when the client
resets or re-enables its CRQ with the hypervisor there is a chance
that if the server side doesn't issue its INIT handshake quick
enough the client can issue an Implicit Logout prior to doing an
NPIV Login. The server treats this scenario as a protocol violation
and closes the CRQ on its end forcing the client through a reset
that gets the client host state and next host action out of
agreement leading to a BUG assert.
ibmvfc 30000003: Partner initialization complete
ibmvfc 30000002: Partner initialization complete
ibmvfc 30000002: Host partner adapter deregistered or failed (rc=2)
ibmvfc 30000002: Partner initialized
------------[ cut here ]------------
kernel BUG at ../drivers/scsi/ibmvscsi/ibmvfc.c:4489!
Oops: Exception in kernel mode, sig: 5 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Supported: No, Unreleased kernel
CPU: 16 PID: 1290 Comm: ibmvfc_0 Tainted: G OE X 5.3.18-12-default
NIP: c00800000d84a2b4 LR: c00800000d84a040 CTR: c00800000d84a2a0
REGS: c00000000cb57a00 TRAP: 0700 Tainted: G OE X (5.3.18-12-default)
MSR: 800000000282b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 24000848 XER: 00000001
CFAR: c00800000d84a070 IRQMASK: 1
GPR00: c00800000d84a040 c00000000cb57c90 c00800000d858e00 0000000000000000
GPR04: 0000000000000000 0000000000000000 0000000000000000 00000000000000a0
GPR08: c00800000d84a074 0000000000000001 0000000000000014 c00800000d84d7d0
GPR12: 0000000000000000 c00000001ea28200 c00000000016cd98 0000000000000000
GPR16: c00800000d84b7b8 0000000000000000 0000000000000000 c00000542c706d68
GPR20: 0000000000000005 c00000542c706d88 5deadbeef0000100 5deadbeef0000122
GPR24: 000000000000000c 000000000000000b c00800000d852180 0000000000000001
GPR28: 0000000000000000 c00000542c706da0 c00000542c706860 c00000542c706828
NIP [c00800000d84a2b4] ibmvfc_work+0x3ac/0xc90 [ibmvfc]
LR [c00800000d84a040] ibmvfc_work+0x138/0xc90 [ibmvfc]
This scenario can be prevented by rejecting any attempt to send an
Implicit Logout if the client adapter is not logged in yet.
Fixes: Commit ed830385a2b1 ("scsi: ibmvfc: Avoid loss of all paths during SVC node reboot")
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
---
drivers/scsi/ibmvscsi/ibmvfc.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 7da9e060b270..2b1326d6dd1f 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3640,6 +3640,11 @@ static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *tgt)
struct ibmvfc_host *vhost = tgt->vhost;
struct ibmvfc_event *evt;
+ if (!vhost->logged_in) {
+ ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT);
+ return;
+ }
+
if (vhost->discovery_threads >= disc_threads)
return;
--
2.16.4
^ permalink raw reply related
* [PATCH v3 23/29] docs: filesystems: convert spufs/spufs.txt to ReST
From: Mauro Carvalho Chehab @ 2020-04-27 21:17 UTC (permalink / raw)
To: Linux Doc Mailing List
Cc: Mauro Carvalho Chehab, Jeremy Kerr, linuxppc-dev, linux-kernel,
Jonathan Corbet
In-Reply-To: <cover.1588021877.git.mchehab+huawei@kernel.org>
This file is at groff output format. Manually convert it to
ReST format, trying to preserve a similar output after parsed.
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
Documentation/filesystems/spufs/index.rst | 1 +
.../spufs/{spufs.txt => spufs.rst} | 59 +++++++++----------
MAINTAINERS | 2 +-
3 files changed, 30 insertions(+), 32 deletions(-)
rename Documentation/filesystems/spufs/{spufs.txt => spufs.rst} (95%)
diff --git a/Documentation/filesystems/spufs/index.rst b/Documentation/filesystems/spufs/index.rst
index 39553c6ebefd..939cf59a7d9e 100644
--- a/Documentation/filesystems/spufs/index.rst
+++ b/Documentation/filesystems/spufs/index.rst
@@ -8,4 +8,5 @@ SPU Filesystem
.. toctree::
:maxdepth: 1
+ spufs
spu_create
diff --git a/Documentation/filesystems/spufs/spufs.txt b/Documentation/filesystems/spufs/spufs.rst
similarity index 95%
rename from Documentation/filesystems/spufs/spufs.txt
rename to Documentation/filesystems/spufs/spufs.rst
index caf36aaae804..8a42859bb100 100644
--- a/Documentation/filesystems/spufs/spufs.txt
+++ b/Documentation/filesystems/spufs/spufs.rst
@@ -1,12 +1,18 @@
-SPUFS(2) Linux Programmer's Manual SPUFS(2)
+.. SPDX-License-Identifier: GPL-2.0
+=====
+spufs
+=====
+Name
+====
-NAME
spufs - the SPU file system
-DESCRIPTION
+Description
+===========
+
The SPU file system is used on PowerPC machines that implement the Cell
Broadband Engine Architecture in order to access Synergistic Processor
Units (SPUs).
@@ -21,7 +27,9 @@ DESCRIPTION
ally add or remove files.
-MOUNT OPTIONS
+Mount Options
+=============
+
uid=<uid>
set the user owning the mount point, the default is 0 (root).
@@ -29,7 +37,9 @@ MOUNT OPTIONS
set the group owning the mount point, the default is 0 (root).
-FILES
+Files
+=====
+
The files in spufs mostly follow the standard behavior for regular sys-
tem calls like read(2) or write(2), but often support only a subset of
the operations supported on regular file systems. This list details the
@@ -125,14 +135,12 @@ FILES
space is available for writing.
- /mbox_stat
- /ibox_stat
- /wbox_stat
+ /mbox_stat, /ibox_stat, /wbox_stat
Read-only files that contain the length of the current queue, i.e. how
many words can be read from mbox or ibox or how many words can be
written to wbox without blocking. The files can be read only in 4-byte
units and return a big-endian binary integer number. The possible
- operations on an open *box_stat file are:
+ operations on an open ``*box_stat`` file are:
read(2)
If a count smaller than four is requested, read returns -1 and
@@ -143,12 +151,7 @@ FILES
in EAGAIN.
- /npc
- /decr
- /decr_status
- /spu_tag_mask
- /event_mask
- /srr0
+ /npc, /decr, /decr_status, /spu_tag_mask, /event_mask, /srr0
Internal registers of the SPU. The representation is an ASCII string
with the numeric value of the next instruction to be executed. These
can be used in read/write mode for debugging, but normal operation of
@@ -157,17 +160,14 @@ FILES
The contents of these files are:
+ =================== ===================================
npc Next Program Counter
-
decr SPU Decrementer
-
decr_status Decrementer Status
-
spu_tag_mask MFC tag mask for SPU DMA
-
event_mask Event mask for SPU interrupts
-
srr0 Interrupt Return address register
+ =================== ===================================
The possible operations on an open npc, decr, decr_status,
@@ -206,8 +206,7 @@ FILES
from the data buffer, updating the value of the fpcr register.
- /signal1
- /signal2
+ /signal1, /signal2
The two signal notification channels of an SPU. These are read-write
files that operate on a 32 bit word. Writing to one of these files
triggers an interrupt on the SPU. The value written to the signal
@@ -233,8 +232,7 @@ FILES
file.
- /signal1_type
- /signal2_type
+ /signal1_type, /signal2_type
These two files change the behavior of the signal1 and signal2 notifi-
cation files. The contain a numerical ASCII string which is read as
either "1" or "0". In mode 0 (overwrite), the hardware replaces the
@@ -259,18 +257,17 @@ FILES
the previous setting.
-EXAMPLES
+Examples
+========
/etc/fstab entry
none /spu spufs gid=spu 0 0
-AUTHORS
+Authors
+=======
Arnd Bergmann <arndb@de.ibm.com>, Mark Nutter <mnutter@us.ibm.com>,
Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
-SEE ALSO
+See Also
+========
capabilities(7), close(2), spu_create(2), spu_run(2), spufs(7)
-
-
-
-Linux 2005-09-28 SPUFS(2)
diff --git a/MAINTAINERS b/MAINTAINERS
index ff9094b9310a..3b684c061677 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15938,7 +15938,7 @@ M: Jeremy Kerr <jk@ozlabs.org>
L: linuxppc-dev@lists.ozlabs.org
S: Supported
W: http://www.ibm.com/developerworks/power/cell/
-F: Documentation/filesystems/spufs.txt
+F: Documentation/filesystems/spufs/spufs.rst
F: arch/powerpc/platforms/cell/spufs/
SQUASHFS FILE SYSTEM
--
2.25.4
^ permalink raw reply related
* [PATCH v3 00/29] Convert files to ReST - part 2
From: Mauro Carvalho Chehab @ 2020-04-27 21:16 UTC (permalink / raw)
To: Linux Doc Mailing List
Cc: Jonathan Corbet, Mauro Carvalho Chehab, linux-usb, linux-kernel,
codalist, linux-xfs, linux-cachefs, linux-fsdevel, linuxppc-dev
This is the second part of a series I wrote sometime ago where I manually
convert lots of files to be properly parsed by Sphinx as ReST files.
As it touches on lot of stuff, this series is based on today's linux-next,
at tag next-20190617.
The first version of this series had 57 patches. The first part with 28 patches
were already merged. Right now, there are still ~76 patches pending applying
(including this series), and that's because I opted to do ~1 patch per converted
directory.
That sounds too much to be send on a single round. So, I'm opting to split
it on 3 parts for the conversion, plus a final patch adding orphaned books
to existing ones.
Those patches should probably be good to be merged either by subsystem
maintainers or via the docs tree.
I opted to mark new files not included yet to the main index.rst (directly or
indirectly) with the :orphan: tag, in order to avoid adding warnings to the
build system. This should be removed after we find a "home" for all
the converted files within the new document tree arrangement, after I
submit the third part.
Both this series and the other parts of this work are on my devel git tree,
at:
https://git.linuxtv.org/mchehab/experimental.git/log/?h=convert_rst_renames_v5.1
The final output in html (after all patches I currently have, including
the upcoming series) can be seen at:
https://www.infradead.org/~mchehab/rst_conversion/
It contains all pending work from my side related to the conversion, plus
the patches I finished a first version today with contains the renaming
patches and de-orphan changes.
---
Version 3:
- Rebased on the top of next-20200424
- configfs.rst conversion moved to the end of the series;
- avoided almost all markups at configfs.rst while still preserving
a reasonable output and not generating build warnings.
Version 2:
- Removed patches merged via other trees;
- rebased on the top of today's linux-next (next-20190617);
- Fix a typo on one patch's description;
- Added received acks.
Mauro Carvalho Chehab (29):
docs: filesystems: convert caching/object.txt to ReST
docs: filesystems: convert caching/fscache.txt to ReST format
docs: filesystems: caching/netfs-api.txt: convert it to ReST
docs: filesystems: caching/operations.txt: convert it to ReST
docs: filesystems: caching/cachefiles.txt: convert to ReST
docs: filesystems: caching/backend-api.txt: convert it to ReST
docs: filesystems: convert cifs/cifsroot.txt to ReST
docs: filesystems: convert automount-support.txt to ReST
docs: filesystems: convert coda.txt to ReST
docs: filesystems: convert devpts.txt to ReST
docs: filesystems: convert dnotify.txt to ReST
docs: filesystems: convert fiemap.txt to ReST
docs: filesystems: convert files.txt to ReST
docs: filesystems: convert fuse-io.txt to ReST
docs: filesystems: convert locks.txt to ReST
docs: filesystems: convert mandatory-locking.txt to ReST
docs: filesystems: convert mount_api.txt to ReST
docs: filesystems: convert quota.txt to ReST
docs: filesystems: convert seq_file.txt to ReST
docs: filesystems: convert sharedsubtree.txt to ReST
docs: filesystems: split spufs.txt into 3 separate files
docs: filesystems: convert spufs/spu_create.txt to ReST
docs: filesystems: convert spufs/spufs.txt to ReST
docs: filesystems: convert spufs/spu_run.txt to ReST
docs: filesystems: convert sysfs-pci.txt to ReST
docs: filesystems: convert sysfs-tagging.txt to ReST
docs: filesystems: convert xfs-delayed-logging-design.txt to ReST
docs: filesystems: convert xfs-self-describing-metadata.txt to ReST
docs: filesystems: convert configfs.txt to ReST
Documentation/admin-guide/sysctl/kernel.rst | 2 +-
...ount-support.txt => automount-support.rst} | 23 +-
.../{backend-api.txt => backend-api.rst} | 165 +-
.../{cachefiles.txt => cachefiles.rst} | 139 +-
Documentation/filesystems/caching/fscache.rst | 565 ++++++
Documentation/filesystems/caching/fscache.txt | 448 -----
Documentation/filesystems/caching/index.rst | 14 +
.../caching/{netfs-api.txt => netfs-api.rst} | 172 +-
.../caching/{object.txt => object.rst} | 43 +-
.../{operations.txt => operations.rst} | 45 +-
.../cifs/{cifsroot.txt => cifsroot.rst} | 56 +-
Documentation/filesystems/coda.rst | 1670 ++++++++++++++++
Documentation/filesystems/coda.txt | 1676 -----------------
.../{configfs/configfs.txt => configfs.rst} | 131 +-
Documentation/filesystems/devpts.rst | 36 +
Documentation/filesystems/devpts.txt | 26 -
.../filesystems/{dnotify.txt => dnotify.rst} | 11 +-
.../filesystems/{fiemap.txt => fiemap.rst} | 133 +-
.../filesystems/{files.txt => files.rst} | 15 +-
.../filesystems/{fuse-io.txt => fuse-io.rst} | 6 +
Documentation/filesystems/index.rst | 23 +
.../filesystems/{locks.txt => locks.rst} | 14 +-
...tory-locking.txt => mandatory-locking.rst} | 25 +-
.../{mount_api.txt => mount_api.rst} | 329 ++--
Documentation/filesystems/proc.rst | 2 +-
.../filesystems/{quota.txt => quota.rst} | 41 +-
.../{seq_file.txt => seq_file.rst} | 61 +-
.../{sharedsubtree.txt => sharedsubtree.rst} | 394 ++--
Documentation/filesystems/spufs/index.rst | 13 +
.../filesystems/spufs/spu_create.rst | 131 ++
Documentation/filesystems/spufs/spu_run.rst | 138 ++
.../{spufs.txt => spufs/spufs.rst} | 304 +--
.../{sysfs-pci.txt => sysfs-pci.rst} | 23 +-
.../{sysfs-tagging.txt => sysfs-tagging.rst} | 22 +-
...ign.txt => xfs-delayed-logging-design.rst} | 65 +-
...a.txt => xfs-self-describing-metadata.rst} | 182 +-
Documentation/iio/iio_configfs.rst | 2 +-
Documentation/usb/gadget_configfs.rst | 4 +-
MAINTAINERS | 14 +-
fs/cachefiles/Kconfig | 4 +-
fs/coda/Kconfig | 2 +-
fs/configfs/inode.c | 2 +-
fs/configfs/item.c | 2 +-
fs/fscache/Kconfig | 8 +-
fs/fscache/cache.c | 8 +-
fs/fscache/cookie.c | 2 +-
fs/fscache/object.c | 4 +-
fs/fscache/operation.c | 2 +-
fs/locks.c | 2 +-
include/linux/configfs.h | 2 +-
include/linux/fs_context.h | 2 +-
include/linux/fscache-cache.h | 4 +-
include/linux/fscache.h | 42 +-
include/linux/lsm_hooks.h | 2 +-
54 files changed, 3843 insertions(+), 3408 deletions(-)
rename Documentation/filesystems/{automount-support.txt => automount-support.rst} (92%)
rename Documentation/filesystems/caching/{backend-api.txt => backend-api.rst} (87%)
rename Documentation/filesystems/caching/{cachefiles.txt => cachefiles.rst} (90%)
create mode 100644 Documentation/filesystems/caching/fscache.rst
delete mode 100644 Documentation/filesystems/caching/fscache.txt
create mode 100644 Documentation/filesystems/caching/index.rst
rename Documentation/filesystems/caching/{netfs-api.txt => netfs-api.rst} (91%)
rename Documentation/filesystems/caching/{object.txt => object.rst} (95%)
rename Documentation/filesystems/caching/{operations.txt => operations.rst} (90%)
rename Documentation/filesystems/cifs/{cifsroot.txt => cifsroot.rst} (72%)
create mode 100644 Documentation/filesystems/coda.rst
delete mode 100644 Documentation/filesystems/coda.txt
rename Documentation/filesystems/{configfs/configfs.txt => configfs.rst} (87%)
create mode 100644 Documentation/filesystems/devpts.rst
delete mode 100644 Documentation/filesystems/devpts.txt
rename Documentation/filesystems/{dnotify.txt => dnotify.rst} (90%)
rename Documentation/filesystems/{fiemap.txt => fiemap.rst} (70%)
rename Documentation/filesystems/{files.txt => files.rst} (95%)
rename Documentation/filesystems/{fuse-io.txt => fuse-io.rst} (95%)
rename Documentation/filesystems/{locks.txt => locks.rst} (91%)
rename Documentation/filesystems/{mandatory-locking.txt => mandatory-locking.rst} (91%)
rename Documentation/filesystems/{mount_api.txt => mount_api.rst} (79%)
rename Documentation/filesystems/{quota.txt => quota.rst} (81%)
rename Documentation/filesystems/{seq_file.txt => seq_file.rst} (92%)
rename Documentation/filesystems/{sharedsubtree.txt => sharedsubtree.rst} (72%)
create mode 100644 Documentation/filesystems/spufs/index.rst
create mode 100644 Documentation/filesystems/spufs/spu_create.rst
create mode 100644 Documentation/filesystems/spufs/spu_run.rst
rename Documentation/filesystems/{spufs.txt => spufs/spufs.rst} (57%)
rename Documentation/filesystems/{sysfs-pci.txt => sysfs-pci.rst} (92%)
rename Documentation/filesystems/{sysfs-tagging.txt => sysfs-tagging.rst} (72%)
rename Documentation/filesystems/{xfs-delayed-logging-design.txt => xfs-delayed-logging-design.rst} (97%)
rename Documentation/filesystems/{xfs-self-describing-metadata.txt => xfs-self-describing-metadata.rst} (83%)
--
2.25.4
^ permalink raw reply
* [PATCH] powerpc: Discard .rela* sections if CONFIG_RELOCATABLE is undefined
From: H.J. Lu @ 2020-04-27 21:16 UTC (permalink / raw)
To: linux-kernel
Cc: Kees Cook, Paul Mackerras, Naveen N . Rao, Borislav Petkov,
linuxppc-dev
arch/powerpc/kernel/vmlinux.lds.S has
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
*(.glink .iplt .plt .rela* .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
}
Since .rela* sections are needed when CONFIG_RELOCATABLE is defined,
change to discard .rela* sections if CONFIG_RELOCATABLE is undefined.
Signed-off-by: H.J. Lu <hjl.tools@gmail.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
---
arch/powerpc/kernel/vmlinux.lds.S | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 31a0f201fb6f..4ba07734a210 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -366,9 +366,12 @@ SECTIONS
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .rela* .comment)
+ *(.glink .iplt .plt .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
}
}
--
2.25.4
^ permalink raw reply related
* Re: [PATCH 1/5] powerpc/spufs: simplify spufs core dumping
From: Al Viro @ 2020-04-27 20:49 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Arnd Bergmann, Linus Torvalds, linux-kernel, Jeremy Kerr,
linux-fsdevel, Andrew Morton, linuxppc-dev, Eric W . Biederman
In-Reply-To: <20200427200626.1622060-2-hch@lst.de>
On Mon, Apr 27, 2020 at 10:06:21PM +0200, Christoph Hellwig wrote:
> @@ -1988,7 +1984,12 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
> if (ret)
> return ret;
> spin_lock(&ctx->csa.register_lock);
> - ret = __spufs_mbox_info_read(ctx, buf, len, pos);
> + /* EOF if there's no entry in the mbox */
> + if (ctx->csa.prob.mb_stat_R & 0x0000ff) {
> + ret = simple_read_from_buffer(buf, len, pos,
> + &ctx->csa.prob.pu_mb_R,
> + sizeof(ctx->csa.prob.pu_mb_R));
> + }
> spin_unlock(&ctx->csa.register_lock);
> spu_release_saved(ctx);
Again, this really needs fixing. Preferably - as a separate commit preceding
this series, so that it could be backported. simple_read_from_buffer() is
a blocking operation. Yes, I understand that mainline has the same bug;
it really does need to be fixed and having to backport this series is not
a good idea, for obvious reasons.
^ permalink raw reply
* Re: [PATCH v3 2/4] hugetlbfs: move hugepagesz= parsing to arch independent code
From: Mike Kravetz @ 2020-04-27 20:31 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-doc, Catalin Marinas, Dave Hansen, Heiko Carstens, Peter Xu,
linux-mm, Paul Mackerras, sparclinux, linux-riscv, Will Deacon,
Mina Almasry, linux-s390, Jonathan Corbet, Christian Borntraeger,
Ingo Molnar, Longpeng, Albert Ou, Vasily Gorbik, Paul Walmsley,
Thomas Gleixner, linux-arm-kernel, Nitesh Narayan Lal,
Randy Dunlap, linux-kernel, Sandipan Das, Palmer Dabbelt,
linuxppc-dev, David S.Miller
In-Reply-To: <20200427131802.3d132055a59535a0e6780e9f@linux-foundation.org>
On 4/27/20 1:18 PM, Andrew Morton wrote:
> On Mon, 27 Apr 2020 12:09:47 -0700 Mike Kravetz <mike.kravetz@oracle.com> wrote:
>
>> Previously, a check for hugepages_supported was added before processing
>> hugetlb command line parameters. On some architectures such as powerpc,
>> hugepages_supported() is not set to true until after command line
>> processing. Therefore, no hugetlb command line parameters would be
>> accepted.
>>
>> Remove the additional checks for hugepages_supported. In hugetlb_init,
>> print a warning if !hugepages_supported and command line parameters were
>> specified.
>
> This applies to [4/4] instead of fixing [2/4]. I guess you'll
> straighten that out in v4?
Yes.
> btw, was
> http://lkml.kernel.org/r/CADYN=9Koefrq9H1Y82Q8nMNbeyN4tzhEfvDu5u=sVFjFZCYorA@mail.gmail.com
> addressed?
Yes, you pulled a patch into your tree to address this.
hugetlbfs-remove-hugetlb_add_hstate-warning-for-existing-hstate-fix.patch
I'll send out a v4 with both these issues addressed. Would like to wait
until receiving confirmation from someone who can test on powerpc.
--
Mike Kravetz
^ permalink raw reply
* Re: [PATCH v3 2/4] hugetlbfs: move hugepagesz= parsing to arch independent code
From: Andrew Morton @ 2020-04-27 20:18 UTC (permalink / raw)
To: Mike Kravetz
Cc: linux-doc, Catalin Marinas, Dave Hansen, Heiko Carstens, Peter Xu,
linux-mm, Paul Mackerras, sparclinux, linux-riscv, Will Deacon,
Mina Almasry, linux-s390, Jonathan Corbet, Christian Borntraeger,
Ingo Molnar, Longpeng, Albert Ou, Vasily Gorbik, Paul Walmsley,
Thomas Gleixner, linux-arm-kernel, Nitesh Narayan Lal,
Randy Dunlap, linux-kernel, Sandipan Das, Palmer Dabbelt,
linuxppc-dev, David S.Miller
In-Reply-To: <b1f04f9f-fa46-c2a0-7693-4a0679d2a1ee@oracle.com>
On Mon, 27 Apr 2020 12:09:47 -0700 Mike Kravetz <mike.kravetz@oracle.com> wrote:
> Previously, a check for hugepages_supported was added before processing
> hugetlb command line parameters. On some architectures such as powerpc,
> hugepages_supported() is not set to true until after command line
> processing. Therefore, no hugetlb command line parameters would be
> accepted.
>
> Remove the additional checks for hugepages_supported. In hugetlb_init,
> print a warning if !hugepages_supported and command line parameters were
> specified.
This applies to [4/4] instead of fixing [2/4]. I guess you'll
straighten that out in v4?
btw, was
http://lkml.kernel.org/r/CADYN=9Koefrq9H1Y82Q8nMNbeyN4tzhEfvDu5u=sVFjFZCYorA@mail.gmail.com
addressed?
^ permalink raw reply
* [PATCH 5/5] binfmt_elf_fdpic: remove the set_fs(KERNEL_DS) in elf_fdpic_core_dump
From: Christoph Hellwig @ 2020-04-27 20:06 UTC (permalink / raw)
To: Andrew Morton, Alexander Viro
Cc: Arnd Bergmann, Linus Torvalds, linux-kernel, Jeremy Kerr,
linux-fsdevel, linuxppc-dev, Eric W . Biederman
In-Reply-To: <20200427200626.1622060-1-hch@lst.de>
There is no logic in elf_fdpic_core_dump itself or in the various arch
helpers called from it which use uaccess routines on kernel pointers
except for the file writes thate are nicely encapsulated by using
__kernel_write in dump_emit.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/binfmt_elf_fdpic.c | 31 ++++++++++++-------------------
1 file changed, 12 insertions(+), 19 deletions(-)
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 240f666635437..c62c17a5c34a9 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1549,7 +1549,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
{
#define NUM_NOTES 6
int has_dumped = 0;
- mm_segment_t fs;
int segs;
int i;
struct vm_area_struct *vma;
@@ -1678,9 +1677,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
"LINUX", ELF_CORE_XFPREG_TYPE, sizeof(*xfpu), xfpu);
#endif
- fs = get_fs();
- set_fs(KERNEL_DS);
-
offset += sizeof(*elf); /* Elf header */
offset += segs * sizeof(struct elf_phdr); /* Program headers */
@@ -1695,7 +1691,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL);
if (!phdr4note)
- goto end_coredump;
+ goto cleanup;
fill_elf_note_phdr(phdr4note, sz, offset);
offset += sz;
@@ -1711,17 +1707,17 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
if (e_phnum == PN_XNUM) {
shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
if (!shdr4extnum)
- goto end_coredump;
+ goto cleanup;
fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
}
offset = dataoff;
if (!dump_emit(cprm, elf, sizeof(*elf)))
- goto end_coredump;
+ goto cleanup;
if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
- goto end_coredump;
+ goto cleanup;
/* write program headers for segments dump */
for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
@@ -1745,16 +1741,16 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
phdr.p_align = ELF_EXEC_PAGESIZE;
if (!dump_emit(cprm, &phdr, sizeof(phdr)))
- goto end_coredump;
+ goto cleanup;
}
if (!elf_core_write_extra_phdrs(cprm, offset))
- goto end_coredump;
+ goto cleanup;
/* write out the notes section */
for (i = 0; i < numnote; i++)
if (!writenote(notes + i, cprm))
- goto end_coredump;
+ goto cleanup;
/* write out the thread status notes section */
list_for_each(t, &thread_list) {
@@ -1763,21 +1759,21 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
for (i = 0; i < tmp->num_notes; i++)
if (!writenote(&tmp->notes[i], cprm))
- goto end_coredump;
+ goto cleanup;
}
if (!dump_skip(cprm, dataoff - cprm->pos))
- goto end_coredump;
+ goto cleanup;
if (!elf_fdpic_dump_segments(cprm))
- goto end_coredump;
+ goto cleanup;
if (!elf_core_write_extra_data(cprm))
- goto end_coredump;
+ goto cleanup;
if (e_phnum == PN_XNUM) {
if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum)))
- goto end_coredump;
+ goto cleanup;
}
if (cprm->file->f_pos != offset) {
@@ -1787,9 +1783,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
cprm->file->f_pos, offset);
}
-end_coredump:
- set_fs(fs);
-
cleanup:
while (!list_empty(&thread_list)) {
struct list_head *tmp = thread_list.next;
--
2.26.1
^ permalink raw reply related
* [PATCH 4/5] binfmt_elf: remove the set_fs(KERNEL_DS) in elf_core_dump
From: Christoph Hellwig @ 2020-04-27 20:06 UTC (permalink / raw)
To: Andrew Morton, Alexander Viro
Cc: Arnd Bergmann, Linus Torvalds, linux-kernel, Jeremy Kerr,
linux-fsdevel, linuxppc-dev, Eric W . Biederman
In-Reply-To: <20200427200626.1622060-1-hch@lst.de>
There is no logic in elf_core_dump itself or in the various arch helpers
called from it which use uaccess routines on kernel pointers except for
the file writes thate are nicely encapsulated by using __kernel_write in
dump_emit.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/binfmt_elf.c | 40 +++++++++++++---------------------------
1 file changed, 13 insertions(+), 27 deletions(-)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index a1f57e20c3cf2..b29b84595b09f 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1355,7 +1355,6 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
u32 __user *header = (u32 __user *) vma->vm_start;
u32 word;
- mm_segment_t fs = get_fs();
/*
* Doing it this way gets the constant folded by GCC.
*/
@@ -1368,14 +1367,8 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
magic.elfmag[EI_MAG1] = ELFMAG1;
magic.elfmag[EI_MAG2] = ELFMAG2;
magic.elfmag[EI_MAG3] = ELFMAG3;
- /*
- * Switch to the user "segment" for get_user(),
- * then put back what elf_core_dump() had in place.
- */
- set_fs(USER_DS);
if (unlikely(get_user(word, header)))
word = 0;
- set_fs(fs);
if (word == magic.cmp)
return PAGE_SIZE;
}
@@ -2183,7 +2176,6 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
static int elf_core_dump(struct coredump_params *cprm)
{
int has_dumped = 0;
- mm_segment_t fs;
int segs, i;
size_t vma_data_size = 0;
struct vm_area_struct *vma, *gate_vma;
@@ -2236,9 +2228,6 @@ static int elf_core_dump(struct coredump_params *cprm)
has_dumped = 1;
- fs = get_fs();
- set_fs(KERNEL_DS);
-
offset += sizeof(elf); /* Elf header */
offset += segs * sizeof(struct elf_phdr); /* Program headers */
@@ -2250,7 +2239,7 @@ static int elf_core_dump(struct coredump_params *cprm)
phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL);
if (!phdr4note)
- goto end_coredump;
+ goto cleanup;
fill_elf_note_phdr(phdr4note, sz, offset);
offset += sz;
@@ -2265,7 +2254,7 @@ static int elf_core_dump(struct coredump_params *cprm)
vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
GFP_KERNEL);
if (!vma_filesz)
- goto end_coredump;
+ goto cleanup;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
@@ -2283,17 +2272,17 @@ static int elf_core_dump(struct coredump_params *cprm)
if (e_phnum == PN_XNUM) {
shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
if (!shdr4extnum)
- goto end_coredump;
+ goto cleanup;
fill_extnum_info(&elf, shdr4extnum, e_shoff, segs);
}
offset = dataoff;
if (!dump_emit(cprm, &elf, sizeof(elf)))
- goto end_coredump;
+ goto cleanup;
if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
- goto end_coredump;
+ goto cleanup;
/* Write program headers for segments dump */
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
@@ -2315,22 +2304,22 @@ static int elf_core_dump(struct coredump_params *cprm)
phdr.p_align = ELF_EXEC_PAGESIZE;
if (!dump_emit(cprm, &phdr, sizeof(phdr)))
- goto end_coredump;
+ goto cleanup;
}
if (!elf_core_write_extra_phdrs(cprm, offset))
- goto end_coredump;
+ goto cleanup;
/* write out the notes section */
if (!write_note_info(&info, cprm))
- goto end_coredump;
+ goto cleanup;
if (elf_coredump_extra_notes_write(cprm))
- goto end_coredump;
+ goto cleanup;
/* Align to page */
if (!dump_skip(cprm, dataoff - cprm->pos))
- goto end_coredump;
+ goto cleanup;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
@@ -2352,22 +2341,19 @@ static int elf_core_dump(struct coredump_params *cprm)
} else
stop = !dump_skip(cprm, PAGE_SIZE);
if (stop)
- goto end_coredump;
+ goto cleanup;
}
}
dump_truncate(cprm);
if (!elf_core_write_extra_data(cprm))
- goto end_coredump;
+ goto cleanup;
if (e_phnum == PN_XNUM) {
if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum)))
- goto end_coredump;
+ goto cleanup;
}
-end_coredump:
- set_fs(fs);
-
cleanup:
free_note_info(&info);
kfree(shdr4extnum);
--
2.26.1
^ permalink raw reply related
* [PATCH 3/5] binfmt_elf: remove the set_fs in fill_siginfo_note
From: Christoph Hellwig @ 2020-04-27 20:06 UTC (permalink / raw)
To: Andrew Morton, Alexander Viro
Cc: Arnd Bergmann, Linus Torvalds, linux-kernel, Jeremy Kerr,
linux-fsdevel, linuxppc-dev, Eric W . Biederman
In-Reply-To: <20200427200626.1622060-1-hch@lst.de>
From: "Eric W. Biederman" <ebiederm@xmission.com>
The code in binfmt_elf.c is differnt from the rest of the code that
processes siginfo, as it sends siginfo from a kernel buffer to a file
rather than from kernel memory to userspace buffers. To remove it's
use of set_fs the code needs some different siginfo helpers.
Add the helper copy_siginfo_to_external to copy from the kernel's
internal siginfo layout to a buffer in the siginfo layout that
userspace expects.
Modify fill_siginfo_note to use copy_siginfo_to_external instead of
set_fs and copy_siginfo_to_user.
Update compat_binfmt_elf.c to use the previously added
copy_siginfo_to_external32 to handle the compat case.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/binfmt_elf.c | 5 +----
fs/compat_binfmt_elf.c | 2 +-
include/linux/signal.h | 8 ++++++++
3 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 13f25e241ac46..a1f57e20c3cf2 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1556,10 +1556,7 @@ static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm)
static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
const kernel_siginfo_t *siginfo)
{
- mm_segment_t old_fs = get_fs();
- set_fs(KERNEL_DS);
- copy_siginfo_to_user((user_siginfo_t __user *) csigdata, siginfo);
- set_fs(old_fs);
+ copy_siginfo_to_external(csigdata, siginfo);
fill_note(note, "CORE", NT_SIGINFO, sizeof(*csigdata), csigdata);
}
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index aaad4ca1217ef..fa0e24e1b7267 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -39,7 +39,7 @@
*/
#define user_long_t compat_long_t
#define user_siginfo_t compat_siginfo_t
-#define copy_siginfo_to_user copy_siginfo_to_user32
+#define copy_siginfo_to_external copy_siginfo_to_external32
/*
* The machine-dependent core note format types are defined in elfcore-compat.h,
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 05bacd2ab1350..6bb1a3f0258c2 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -24,6 +24,14 @@ static inline void clear_siginfo(kernel_siginfo_t *info)
#define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo))
+static inline void copy_siginfo_to_external(siginfo_t *to,
+ const kernel_siginfo_t *from)
+{
+ memcpy(to, from, sizeof(*from));
+ memset(((char *)to) + sizeof(struct kernel_siginfo), 0,
+ SI_EXPANSION_SIZE);
+}
+
int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from);
int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from);
--
2.26.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox