From: Guenter Roeck <[email protected]>
[ Upstream commit 0cc011c576aaa4de505046f7a6c90933d7c749a9 ]
In some circumstances, attempts are made to add entries to or to remove
entries from an uninitialized list. A prime example is
amdgpu_bo_vm_destroy(): It is indirectly called from
ttm_bo_init_reserved() if that function fails, and tries to remove an
entry from a list. However, that list is only initialized in
amdgpu_bo_create_vm() after the call to ttm_bo_init_reserved() returned
success. This results in crashes such as
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 1 PID: 1479 Comm: chrome Not tainted 5.10.110-15768-g29a72e65dae5
Hardware name: Google Grunt/Grunt, BIOS Google_Grunt.11031.149.0 07/15/2020
RIP: 0010:__list_del_entry_valid+0x26/0x7d
...
Call Trace:
amdgpu_bo_vm_destroy+0x48/0x8b
ttm_bo_init_reserved+0x1d7/0x1e0
amdgpu_bo_create+0x212/0x476
? amdgpu_bo_user_destroy+0x23/0x23
? kmem_cache_alloc+0x60/0x271
amdgpu_bo_create_vm+0x40/0x7d
amdgpu_vm_pt_create+0xe8/0x24b
...
Check if the list's prev and next pointers are NULL to catch such problems.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Guenter Roeck <[email protected]>
Cc: Steven Rostedt <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
lib/list_debug.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 5d5424b51b74..413daa72a3d8 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -20,7 +20,11 @@
bool __list_add_valid(struct list_head *new, struct list_head *prev,
struct list_head *next)
{
- if (CHECK_DATA_CORRUPTION(next->prev != prev,
+ if (CHECK_DATA_CORRUPTION(prev == NULL,
+ "list_add corruption. prev is NULL.\n") ||
+ CHECK_DATA_CORRUPTION(next == NULL,
+ "list_add corruption. next is NULL.\n") ||
+ CHECK_DATA_CORRUPTION(next->prev != prev,
"list_add corruption. next->prev should be prev (%px), but was %px. (next=%px).\n",
prev, next->prev, next) ||
CHECK_DATA_CORRUPTION(prev->next != next,
@@ -42,7 +46,11 @@ bool __list_del_entry_valid(struct list_head *entry)
prev = entry->prev;
next = entry->next;
- if (CHECK_DATA_CORRUPTION(next == LIST_POISON1,
+ if (CHECK_DATA_CORRUPTION(next == NULL,
+ "list_del corruption, %px->next is NULL\n", entry) ||
+ CHECK_DATA_CORRUPTION(prev == NULL,
+ "list_del corruption, %px->prev is NULL\n", entry) ||
+ CHECK_DATA_CORRUPTION(next == LIST_POISON1,
"list_del corruption, %px->next is LIST_POISON1 (%px)\n",
entry, LIST_POISON1) ||
CHECK_DATA_CORRUPTION(prev == LIST_POISON2,
--
2.35.1
From: Alexey Kardashevskiy <[email protected]>
[ Upstream commit d73b46c3c1449bf27f793b9d9ee86ed70c7a7163 ]
The iommu_table::it_index is a LIOBN which is not initialized on PowerNV
as it is not used except IOMMU debugfs where it is used for a node name.
This initializes it_index witn a unique number to avoid warnings and
have a node for every iommu_table.
This should not cause any behavioral change without CONFIG_IOMMU_DEBUGFS.
Signed-off-by: Alexey Kardashevskiy <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/platforms/powernv/pci-ioda.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3dd35c327d1c..624822a81019 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1618,6 +1618,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
tbl->it_ops = &pnv_ioda1_iommu_ops;
pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
+ tbl->it_index = (phb->hose->global_number << 16) | pe->pe_number;
if (!iommu_init_table(tbl, phb->hose->node, 0, 0))
panic("Failed to initialize iommu table");
@@ -1788,6 +1789,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
res_end = min(window_size, SZ_4G) >> tbl->it_page_shift;
}
+ tbl->it_index = (pe->phb->hose->global_number << 16) | pe->pe_number;
if (iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end))
rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
else
--
2.35.1
From: Schspa Shi <[email protected]>
[ Upstream commit 6641085e8d7b3f061911517f79a2a15a0a21b97b ]
On buffer resize failure, vfio_info_cap_add() will free the buffer,
report zero for the size, and return -ENOMEM. As additional
hardening, also clear the buffer pointer to prevent any chance of a
double free.
Signed-off-by: Schspa Shi <[email protected]>
Reviewed-by: Cornelia Huck <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alex Williamson <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/vfio/vfio.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 3c034fe14ccb..818e47fc0896 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1850,6 +1850,7 @@ struct vfio_info_cap_header *vfio_info_cap_add(struct vfio_info_cap *caps,
buf = krealloc(caps->buf, caps->size + size, GFP_KERNEL);
if (!buf) {
kfree(caps->buf);
+ caps->buf = NULL;
caps->size = 0;
return ERR_PTR(-ENOMEM);
}
--
2.35.1
From: Miklos Szeredi <[email protected]>
[ Upstream commit b10b85fe5149ee8b39fbbf86095b303632dde2cd ]
When mounting overlayfs in an unprivileged user namespace, trusted xattr
creation will fail. This will lead to failures in some file operations,
e.g. in the following situation:
mkdir lower upper work merged
mkdir lower/directory
mount -toverlay -olowerdir=lower,upperdir=upper,workdir=work none merged
rmdir merged/directory
mkdir merged/directory
The last mkdir will fail:
mkdir: cannot create directory 'merged/directory': Input/output error
The cause for these failures is currently extremely non-obvious and hard to
debug. Hence, warn the user and suggest using the userxattr mount option,
if it is not already supplied and xattr creation fails during the
self-check.
Reported-by: Alois Wohlschlager <[email protected]>
Signed-off-by: Miklos Szeredi <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
fs/overlayfs/super.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 7bb0a47cb615..9837aaf9caf1 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1413,11 +1413,12 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
*/
err = ovl_do_setxattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE, "0", 1);
if (err) {
+ pr_warn("failed to set xattr on upper\n");
ofs->noxattr = true;
if (ofs->config.index || ofs->config.metacopy) {
ofs->config.index = false;
ofs->config.metacopy = false;
- pr_warn("upper fs does not support xattr, falling back to index=off,metacopy=off.\n");
+ pr_warn("...falling back to index=off,metacopy=off.\n");
}
/*
* xattr support is required for persistent st_ino.
@@ -1425,8 +1426,10 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
*/
if (ofs->config.xino == OVL_XINO_AUTO) {
ofs->config.xino = OVL_XINO_OFF;
- pr_warn("upper fs does not support xattr, falling back to xino=off.\n");
+ pr_warn("...falling back to xino=off.\n");
}
+ if (err == -EPERM && !ofs->config.userxattr)
+ pr_info("try mounting with 'userxattr' option\n");
err = 0;
} else {
ovl_do_removexattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE);
--
2.35.1
From: Laurent Dufour <[email protected]>
[ Upstream commit 7c56a8733d0a2a4be2438a7512566e5ce552fccf ]
In some circumstances it may be interesting to reconfigure the watchdog
from inside the kernel.
On PowerPC, this may helpful before and after a LPAR migration (LPM) is
initiated, because it implies some latencies, watchdog, and especially NMI
watchdog is expected to be triggered during this operation. Reconfiguring
the watchdog with a factor, would prevent it to happen too frequently
during LPM.
Rename lockup_detector_reconfigure() as __lockup_detector_reconfigure() and
create a new function lockup_detector_reconfigure() calling
__lockup_detector_reconfigure() under the protection of watchdog_mutex.
Signed-off-by: Laurent Dufour <[email protected]>
[mpe: Squash in build fix from Laurent, reported by Sachin]
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
include/linux/nmi.h | 2 ++
kernel/watchdog.c | 21 ++++++++++++++++-----
2 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 750c7f395ca9..f700ff2df074 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -122,6 +122,8 @@ int watchdog_nmi_probe(void);
int watchdog_nmi_enable(unsigned int cpu);
void watchdog_nmi_disable(unsigned int cpu);
+void lockup_detector_reconfigure(void);
+
/**
* touch_nmi_watchdog - restart NMI watchdog timeout.
*
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index ad912511a0c0..1cfa269bd448 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -537,7 +537,7 @@ int lockup_detector_offline_cpu(unsigned int cpu)
return 0;
}
-static void lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(void)
{
cpus_read_lock();
watchdog_nmi_stop();
@@ -557,6 +557,13 @@ static void lockup_detector_reconfigure(void)
__lockup_detector_cleanup();
}
+void lockup_detector_reconfigure(void)
+{
+ mutex_lock(&watchdog_mutex);
+ __lockup_detector_reconfigure();
+ mutex_unlock(&watchdog_mutex);
+}
+
/*
* Create the watchdog infrastructure and configure the detector(s).
*/
@@ -573,13 +580,13 @@ static __init void lockup_detector_setup(void)
return;
mutex_lock(&watchdog_mutex);
- lockup_detector_reconfigure();
+ __lockup_detector_reconfigure();
softlockup_initialized = true;
mutex_unlock(&watchdog_mutex);
}
#else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static void lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(void)
{
cpus_read_lock();
watchdog_nmi_stop();
@@ -587,9 +594,13 @@ static void lockup_detector_reconfigure(void)
watchdog_nmi_start();
cpus_read_unlock();
}
+void lockup_detector_reconfigure(void)
+{
+ __lockup_detector_reconfigure();
+}
static inline void lockup_detector_setup(void)
{
- lockup_detector_reconfigure();
+ __lockup_detector_reconfigure();
}
#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
@@ -629,7 +640,7 @@ static void proc_watchdog_update(void)
{
/* Remove impossible cpus to keep sysctl output clean. */
cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
- lockup_detector_reconfigure();
+ __lockup_detector_reconfigure();
}
/*
--
2.35.1
From: Xianting Tian <[email protected]>
[ Upstream commit 3f1901110a89b0e2e13adb2ac8d1a7102879ea98 ]
Currently, almost all archs (x86, arm64, mips...) support fast call
of crash_kexec() when "regs && kexec_should_crash()" is true. But
RISC-V not, it can only enter crash system via panic(). However panic()
doesn't pass the regs of the real accident scene to crash_kexec(),
it caused we can't get accurate backtrace via gdb,
$ riscv64-linux-gnu-gdb vmlinux vmcore
Reading symbols from vmlinux...
[New LWP 95]
#0 console_unlock () at kernel/printk/printk.c:2557
2557 if (do_cond_resched)
(gdb) bt
#0 console_unlock () at kernel/printk/printk.c:2557
#1 0x0000000000000000 in ?? ()
With the patch we can get the accurate backtrace,
$ riscv64-linux-gnu-gdb vmlinux vmcore
Reading symbols from vmlinux...
[New LWP 95]
#0 0xffffffe00063a4e0 in test_thread (data=<optimized out>) at drivers/test_crash.c:81
81 *(int *)p = 0xdead;
(gdb)
(gdb) bt
#0 0xffffffe00064d5c0 in test_thread (data=<optimized out>) at drivers/test_crash.c:81
#1 0x0000000000000000 in ?? ()
Test code to produce NULL address dereference in test_crash.c,
void *p = NULL;
*(int *)p = 0xdead;
Reviewed-by: Guo Ren <[email protected]>
Tested-by: Xianting Tian <[email protected]>
Signed-off-by: Xianting Tian <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/riscv/kernel/traps.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 0daaa3e4630d..b938ffe129d6 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -16,6 +16,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/irq.h>
+#include <linux/kexec.h>
#include <asm/asm-prototypes.h>
#include <asm/bug.h>
@@ -44,6 +45,9 @@ void die(struct pt_regs *regs, const char *str)
ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
+ if (regs && kexec_should_crash(current))
+ crash_kexec(regs);
+
bust_spinlocks(0);
add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
spin_unlock_irq(&die_lock);
--
2.35.1
From: Zhouyi Zhou <[email protected]>
[ Upstream commit ca829e05d3d4f728810cc5e4b468d9ebc7745eb3 ]
On 64-bit, calling jump_label_init() in setup_feature_keys() is too
late because static keys may be used in subroutines of
parse_early_param() which is again subroutine of early_init_devtree().
For example booting with "threadirqs":
static_key_enable_cpuslocked(): static key '0xc000000002953260' used before call to jump_label_init()
WARNING: CPU: 0 PID: 0 at kernel/jump_label.c:166 static_key_enable_cpuslocked+0xfc/0x120
...
NIP static_key_enable_cpuslocked+0xfc/0x120
LR static_key_enable_cpuslocked+0xf8/0x120
Call Trace:
static_key_enable_cpuslocked+0xf8/0x120 (unreliable)
static_key_enable+0x30/0x50
setup_forced_irqthreads+0x28/0x40
do_early_param+0xa0/0x108
parse_args+0x290/0x4e0
parse_early_options+0x48/0x5c
parse_early_param+0x58/0x84
early_init_devtree+0xd4/0x518
early_setup+0xb4/0x214
So call jump_label_init() just before parse_early_param() in
early_init_devtree().
Suggested-by: Michael Ellerman <[email protected]>
Signed-off-by: Zhouyi Zhou <[email protected]>
[mpe: Add call trace to change log and minor wording edits.]
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/kernel/prom.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 2e67588f6f6e..86ffbabd26c6 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -751,6 +751,13 @@ void __init early_init_devtree(void *params)
of_scan_flat_dt(early_init_dt_scan_root, NULL);
of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
+ /*
+ * As generic code authors expect to be able to use static keys
+ * in early_param() handlers, we initialize the static keys just
+ * before parsing early params (it's fine to call jump_label_init()
+ * more than once).
+ */
+ jump_label_init();
parse_early_param();
/* make sure we've parsed cmdline for mem= before this */
--
2.35.1
From: Conor Dooley <[email protected]>
[ Upstream commit d9d193dea8666bbf69fc21c5bdcdabaa34a466e3 ]
The k210 has no cpu-map node, so tools like hwloc cannot correctly
parse the topology. Add the node using the existing node labels.
Reported-by: Brice Goglin <[email protected]>
Link: https://github.com/open-mpi/hwloc/issues/536
Signed-off-by: Conor Dooley <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/riscv/boot/dts/canaan/k210.dtsi | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi
index 780416d489aa..fa9162e3afa3 100644
--- a/arch/riscv/boot/dts/canaan/k210.dtsi
+++ b/arch/riscv/boot/dts/canaan/k210.dtsi
@@ -65,6 +65,18 @@ cpu1_intc: interrupt-controller {
compatible = "riscv,cpu-intc";
};
};
+
+ cpu-map {
+ cluster0 {
+ core0 {
+ cpu = <&cpu0>;
+ };
+
+ core1 {
+ cpu = <&cpu1>;
+ };
+ };
+ };
};
sram: memory@80000000 {
--
2.35.1
From: Christophe Leroy <[email protected]>
[ Upstream commit 446cda1b21d9a6b3697fe399c6a3a00ff4a285f5 ]
Since commit 4bf4f42a2feb ("powerpc/kbuild: Set default generic
machine type for 32-bit compile"), when building a 32 bits kernel
with a bi-arch version of GCC, or when building a book3s/32 kernel,
the option -mcpu=powerpc is passed to GCC at all time, relying on it
being eventually overriden by a subsequent -mcpu=xxxx.
But when building the same kernel with a 32 bits only version of GCC,
that is not done, relying on gcc being built with the expected default
CPU.
This logic has two problems. First, it is a bit fragile to rely on
whether the GCC version is bi-arch or not, because today we can have
bi-arch versions of GCC configured with a 32 bits default. Second,
there are some versions of GCC which don't support -mcpu=powerpc,
for instance for e500 SPE-only versions.
So, stop relying on this approximative logic and allow the user to
decide whether he/she wants to use the toolchain's default CPU or if
he/she wants to set one, and allow only possible CPUs based on the
selected target.
Reported-by: Pali Rohár <[email protected]>
Signed-off-by: Christophe Leroy <[email protected]>
Tested-by: Pali Rohár <[email protected]>
Reviewed-by: Arnd Bergmann <[email protected]>
Reviewed-by: Segher Boessenkool <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/d4df724691351531bf46d685d654689e5dfa0d74.1657549153.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/Makefile | 26 +-------------------------
arch/powerpc/platforms/Kconfig.cputype | 21 ++++++++++++++++++---
2 files changed, 19 insertions(+), 28 deletions(-)
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 72610e2d6176..2bb0fe9b2058 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -17,23 +17,6 @@ HAS_BIARCH := $(call cc-option-yn, -m32)
# Set default 32 bits cross compilers for vdso and boot wrapper
CROSS32_COMPILE ?=
-ifeq ($(HAS_BIARCH),y)
-ifeq ($(CROSS32_COMPILE),)
-ifdef CONFIG_PPC32
-# These options will be overridden by any -mcpu option that the CPU
-# or platform code sets later on the command line, but they are needed
-# to set a sane 32-bit cpu target for the 64-bit cross compiler which
-# may default to the wrong ISA.
-KBUILD_CFLAGS += -mcpu=powerpc
-KBUILD_AFLAGS += -mcpu=powerpc
-endif
-endif
-endif
-
-ifdef CONFIG_PPC_BOOK3S_32
-KBUILD_CFLAGS += -mcpu=powerpc
-endif
-
# If we're on a ppc/ppc64/ppc64le machine use that defconfig, otherwise just use
# ppc64_defconfig because we have nothing better to go on.
uname := $(shell uname -m)
@@ -185,6 +168,7 @@ endif
endif
CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU))
+AFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU))
# Altivec option not allowed with e500mc64 in GCC.
ifdef CONFIG_ALTIVEC
@@ -195,14 +179,6 @@ endif
CFLAGS-$(CONFIG_E5500_CPU) += $(E5500_CPU)
CFLAGS-$(CONFIG_E6500_CPU) += $(call cc-option,-mcpu=e6500,$(E5500_CPU))
-ifdef CONFIG_PPC32
-ifdef CONFIG_PPC_E500MC
-CFLAGS-y += $(call cc-option,-mcpu=e500mc,-mcpu=powerpc)
-else
-CFLAGS-$(CONFIG_E500) += $(call cc-option,-mcpu=8540 -msoft-float,-mcpu=powerpc)
-endif
-endif
-
asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
KBUILD_CPPFLAGS += -I $(srctree)/arch/$(ARCH) $(asinstr)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 87a95cbff2f3..b8c81ac281e2 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -137,9 +137,9 @@ config GENERIC_CPU
depends on PPC64 && CPU_LITTLE_ENDIAN
select ARCH_HAS_FAST_MULTIPLIER
-config GENERIC_CPU
+config POWERPC_CPU
bool "Generic 32 bits powerpc"
- depends on PPC32 && !PPC_8xx
+ depends on PPC32 && !PPC_8xx && !PPC_85xx
config CELL_CPU
bool "Cell Broadband Engine"
@@ -193,11 +193,23 @@ config G4_CPU
depends on PPC_BOOK3S_32
select ALTIVEC
+config E500_CPU
+ bool "e500 (8540)"
+ depends on PPC_85xx && !PPC_E500MC
+
+config E500MC_CPU
+ bool "e500mc"
+ depends on PPC_85xx && PPC_E500MC
+
+config TOOLCHAIN_DEFAULT_CPU
+ bool "Rely on the toolchain's implicit default CPU"
+ depends on PPC32
+
endchoice
config TARGET_CPU_BOOL
bool
- default !GENERIC_CPU
+ default !GENERIC_CPU && !TOOLCHAIN_DEFAULT_CPU
config TARGET_CPU
string
@@ -212,6 +224,9 @@ config TARGET_CPU
default "e300c2" if E300C2_CPU
default "e300c3" if E300C3_CPU
default "G4" if G4_CPU
+ default "8540" if E500_CPU
+ default "e500mc" if E500MC_CPU
+ default "powerpc" if POWERPC_CPU
config PPC_BOOK3S
def_bool y
--
2.35.1
From: Christophe Leroy <[email protected]>
[ Upstream commit 2a0fb3c155c97c75176e557d61f8e66c1bd9b735 ]
Always set an IBAT covering up to _einittext during init because when
CONFIG_MODULES is not selected there is no reason to have an exception
handler for kernel instruction TLB misses.
It implies DBAT and IBAT are now totaly independent, IBATs are set
by setibat() and DBAT by setbat().
This allows to revert commit 9bb162fa26ed ("powerpc/603: Fix
boot failure with DEBUG_PAGEALLOC and KFENCE")
Reported-by: Maxime Bizon <[email protected]>
Signed-off-by: Christophe Leroy <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/ce7f04a39593934d9b1ee68c69144ccd3d4da4a1.1655202804.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/kernel/head_book3s_32.S | 4 ++--
arch/powerpc/mm/book3s32/mmu.c | 10 ++++------
2 files changed, 6 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 2e2a8211b17b..68e5c0a7e99d 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -421,14 +421,14 @@ InstructionTLBMiss:
*/
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_IMISS
-#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+#ifdef CONFIG_MODULES
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SDR1
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
rlwinm r2, r2, 28, 0xfffff000
-#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+#ifdef CONFIG_MODULES
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 203735caf691..bfca0afe9112 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -160,7 +160,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
unsigned long done;
unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
+ unsigned long size;
+ size = roundup_pow_of_two((unsigned long)_einittext - PAGE_OFFSET);
+ setibat(0, PAGE_OFFSET, 0, size, PAGE_KERNEL_X);
if (debug_pagealloc_enabled_or_kfence() || __map_without_bats) {
pr_debug_once("Read-Write memory mapped without BATs\n");
@@ -246,10 +249,9 @@ void mmu_mark_rodata_ro(void)
}
/*
- * Set up one of the I/D BAT (block address translation) register pairs.
+ * Set up one of the D BAT (block address translation) register pairs.
* The parameters are not checked; in particular size must be a power
* of 2 between 128k and 256M.
- * On 603+, only set IBAT when _PAGE_EXEC is set
*/
void __init setbat(int index, unsigned long virt, phys_addr_t phys,
unsigned int size, pgprot_t prot)
@@ -285,10 +287,6 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys,
/* G bit must be zero in IBATs */
flags &= ~_PAGE_EXEC;
}
- if (flags & _PAGE_EXEC)
- bat[0] = bat[1];
- else
- bat[0].batu = bat[0].batl = 0;
bat_addrs[index].start = virt;
bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1;
--
2.35.1
From: Nathan Chancellor <[email protected]>
[ Upstream commit 74de14fe05dd6b151d73cb0c73c8ec874cbdcde6 ]
When CONFIG_XPA is enabled, Clang warns:
arch/mips/mm/tlbex.c:629:24: error: converting the result of '<<' to a boolean; did you mean '(1 << _PAGE_NO_EXEC_SHIFT) != 0'? [-Werror,-Wint-in-bool-context]
if (cpu_has_rixi && !!_PAGE_NO_EXEC) {
^
arch/mips/include/asm/pgtable-bits.h:174:28: note: expanded from macro '_PAGE_NO_EXEC'
# define _PAGE_NO_EXEC (1 << _PAGE_NO_EXEC_SHIFT)
^
arch/mips/mm/tlbex.c:2568:24: error: converting the result of '<<' to a boolean; did you mean '(1 << _PAGE_NO_EXEC_SHIFT) != 0'? [-Werror,-Wint-in-bool-context]
if (!cpu_has_rixi || !_PAGE_NO_EXEC) {
^
arch/mips/include/asm/pgtable-bits.h:174:28: note: expanded from macro '_PAGE_NO_EXEC'
# define _PAGE_NO_EXEC (1 << _PAGE_NO_EXEC_SHIFT)
^
2 errors generated.
_PAGE_NO_EXEC can be '0' or '1 << _PAGE_NO_EXEC_SHIFT' depending on the
build and runtime configuration, which is what the negation operators
are trying to convey. To silence the warning, explicitly compare against
0 so the result of the '<<' operator is not implicitly converted to a
boolean.
According to its documentation, GCC enables -Wint-in-bool-context with
-Wall but this warning is not visible when building the same
configuration with GCC. It appears GCC only warns when compiling C++,
not C, although the documentation makes no note of this:
https://godbolt.org/z/x39q3brxf
Reported-by: Sudip Mukherjee (Codethink) <[email protected]>
Signed-off-by: Nathan Chancellor <[email protected]>
Signed-off-by: Thomas Bogendoerfer <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/mips/mm/tlbex.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 046d51a454af..3471a089bc05 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -634,7 +634,7 @@ static __maybe_unused void build_convert_pte_to_entrylo(u32 **p,
return;
}
- if (cpu_has_rixi && !!_PAGE_NO_EXEC) {
+ if (cpu_has_rixi && _PAGE_NO_EXEC != 0) {
if (fill_includes_sw_bits) {
UASM_i_ROTR(p, reg, reg, ilog2(_PAGE_GLOBAL));
} else {
@@ -2573,7 +2573,7 @@ static void check_pabits(void)
unsigned long entry;
unsigned pabits, fillbits;
- if (!cpu_has_rixi || !_PAGE_NO_EXEC) {
+ if (!cpu_has_rixi || _PAGE_NO_EXEC == 0) {
/*
* We'll only be making use of the fact that we can rotate bits
* into the fill if the CPU supports RIXI, so don't bother
--
2.35.1
From: Liang He <[email protected]>
[ Upstream commit 7a9f743ceead60ed454c46fbc3085ee9a79cbebb ]
We should call of_node_put() for the reference 'uctl_node' returned by
of_get_parent() which will increase the refcount. Otherwise, there will
be a refcount leak bug.
Signed-off-by: Liang He <[email protected]>
Signed-off-by: Thomas Bogendoerfer <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/mips/cavium-octeon/octeon-platform.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index a994022e32c9..ce05c0dd3acd 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -86,11 +86,12 @@ static void octeon2_usb_clocks_start(struct device *dev)
"refclk-frequency", &clock_rate);
if (i) {
dev_err(dev, "No UCTL \"refclk-frequency\"\n");
+ of_node_put(uctl_node);
goto exit;
}
i = of_property_read_string(uctl_node,
"refclk-type", &clock_type);
-
+ of_node_put(uctl_node);
if (!i && strcmp("crystal", clock_type) == 0)
is_crystal_clock = true;
}
--
2.35.1
From: Steve French <[email protected]>
[ Upstream commit 5fa2cffba0b82336a2244d941322eb1627ff787b ]
Coverity complains about assigning a pointer based on
value length before checking that value length goes
beyond the end of the SMB. Although this is even more
unlikely as value length is a single byte, and the
pointer is not dereferenced until laterm, it is clearer
to check the lengths first.
Addresses-Coverity: 1467704 ("Speculative execution data leak")
Reviewed-by: Ronnie Sahlberg <[email protected]>
Signed-off-by: Steve French <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
fs/cifs/smb2ops.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 735aafee63be..07895e9d537c 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1105,9 +1105,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size,
size_t name_len, value_len, user_name_len;
while (src_size > 0) {
- name = &src->ea_data[0];
name_len = (size_t)src->ea_name_length;
- value = &src->ea_data[src->ea_name_length + 1];
value_len = (size_t)le16_to_cpu(src->ea_value_length);
if (name_len == 0)
@@ -1119,6 +1117,9 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size,
goto out;
}
+ name = &src->ea_data[0];
+ value = &src->ea_data[src->ea_name_length + 1];
+
if (ea_name) {
if (ea_name_len == name_len &&
memcmp(ea_name, name, name_len) == 0) {
--
2.35.1
From: Takashi Iwai <[email protected]>
[ Upstream commit 95cc637c1afd83fb7dd3d7c8a53710488f4caf9c ]
For avoiding the potential deadlock via kill_fasync() call, use the
new fasync helpers to defer the invocation from PCI API. Note that
it's merely a workaround.
Reported-by: [email protected]
Reported-by: [email protected]
Reported-by: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Takashi Iwai <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
sound/core/timer.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/sound/core/timer.c b/sound/core/timer.c
index b3214baa8919..e08a37c23add 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -83,7 +83,7 @@ struct snd_timer_user {
unsigned int filter;
struct timespec64 tstamp; /* trigger tstamp */
wait_queue_head_t qchange_sleep;
- struct fasync_struct *fasync;
+ struct snd_fasync *fasync;
struct mutex ioctl_lock;
};
@@ -1345,7 +1345,7 @@ static void snd_timer_user_interrupt(struct snd_timer_instance *timeri,
}
__wake:
spin_unlock(&tu->qlock);
- kill_fasync(&tu->fasync, SIGIO, POLL_IN);
+ snd_kill_fasync(tu->fasync, SIGIO, POLL_IN);
wake_up(&tu->qchange_sleep);
}
@@ -1383,7 +1383,7 @@ static void snd_timer_user_ccallback(struct snd_timer_instance *timeri,
spin_lock_irqsave(&tu->qlock, flags);
snd_timer_user_append_to_tqueue(tu, &r1);
spin_unlock_irqrestore(&tu->qlock, flags);
- kill_fasync(&tu->fasync, SIGIO, POLL_IN);
+ snd_kill_fasync(tu->fasync, SIGIO, POLL_IN);
wake_up(&tu->qchange_sleep);
}
@@ -1453,7 +1453,7 @@ static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri,
spin_unlock(&tu->qlock);
if (append == 0)
return;
- kill_fasync(&tu->fasync, SIGIO, POLL_IN);
+ snd_kill_fasync(tu->fasync, SIGIO, POLL_IN);
wake_up(&tu->qchange_sleep);
}
@@ -1521,6 +1521,7 @@ static int snd_timer_user_release(struct inode *inode, struct file *file)
snd_timer_instance_free(tu->timeri);
}
mutex_unlock(&tu->ioctl_lock);
+ snd_fasync_free(tu->fasync);
kfree(tu->queue);
kfree(tu->tqueue);
kfree(tu);
@@ -2135,7 +2136,7 @@ static int snd_timer_user_fasync(int fd, struct file * file, int on)
struct snd_timer_user *tu;
tu = file->private_data;
- return fasync_helper(fd, file, on, &tu->fasync);
+ return snd_fasync_helper(fd, file, on, &tu->fasync);
}
static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
--
2.35.1
From: Chao Yu <[email protected]>
[ Upstream commit 141170b759e03958f296033bb7001be62d1d363b ]
As Dipanjan Das <[email protected]> reported, syzkaller
found a f2fs bug as below:
RIP: 0010:f2fs_new_node_page+0x19ac/0x1fc0 fs/f2fs/node.c:1295
Call Trace:
write_all_xattrs fs/f2fs/xattr.c:487 [inline]
__f2fs_setxattr+0xe76/0x2e10 fs/f2fs/xattr.c:743
f2fs_setxattr+0x233/0xab0 fs/f2fs/xattr.c:790
f2fs_xattr_generic_set+0x133/0x170 fs/f2fs/xattr.c:86
__vfs_setxattr+0x115/0x180 fs/xattr.c:182
__vfs_setxattr_noperm+0x125/0x5f0 fs/xattr.c:216
__vfs_setxattr_locked+0x1cf/0x260 fs/xattr.c:277
vfs_setxattr+0x13f/0x330 fs/xattr.c:303
setxattr+0x146/0x160 fs/xattr.c:611
path_setxattr+0x1a7/0x1d0 fs/xattr.c:630
__do_sys_lsetxattr fs/xattr.c:653 [inline]
__se_sys_lsetxattr fs/xattr.c:649 [inline]
__x64_sys_lsetxattr+0xbd/0x150 fs/xattr.c:649
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x46/0xb0
NAT entry and nat bitmap can be inconsistent, e.g. one nid is free
in nat bitmap, and blkaddr in its NAT entry is not NULL_ADDR, it
may trigger BUG_ON() in f2fs_new_node_page(), fix it.
Reported-by: Dipanjan Das <[email protected]>
Signed-off-by: Chao Yu <[email protected]>
Signed-off-by: Jaegeuk Kim <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
fs/f2fs/node.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 69c6bcaf5aae..0e6e73bc42d4 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1291,7 +1291,11 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
dec_valid_node_count(sbi, dn->inode, !ofs);
goto fail;
}
- f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
+ if (unlikely(new_ni.blk_addr != NULL_ADDR)) {
+ err = -EFSCORRUPTED;
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ goto fail;
+ }
#endif
new_ni.nid = dn->nid;
new_ni.ino = dn->inode->i_ino;
--
2.35.1
From: Fabiano Rosas <[email protected]>
[ Upstream commit 9981bace85d816ed8724ac46e49285e8488d29e6 ]
At debugfs/kvm/<pid>/vcpu0/timings we show how long each part of the
code takes to run:
$ cat /sys/kernel/debug/kvm/*-*/vcpu0/timings
rm_entry: 123785 49398892 118 4898
rm_intr: 123780 6075890 22 390
rm_exit: 0 0 0 0 <-- NOK
guest: 123780 46732919988 402 9997638
cede: 0 0 0 0 <-- OK, no cede napping in P9
The "rm_exit" is always showing zero because it is the last one and
end_timing does not increment the counter of the previous entry.
We can fix it by calling accumulate_time again instead of
end_timing. That way the counter gets incremented. The rest of the
arithmetic can be ignored because there are no timing points after
this and the accumulators are reset before the next round.
Signed-off-by: Fabiano Rosas <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/kvm/book3s_hv_p9_entry.c | 13 ++-----------
1 file changed, 2 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index 961b3d70483c..a0e0c28408c0 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -7,15 +7,6 @@
#include <asm/ppc-opcode.h>
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
-static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
-{
- struct kvmppc_vcore *vc = vcpu->arch.vcore;
- u64 tb = mftb() - vc->tb_offset_applied;
-
- vcpu->arch.cur_activity = next;
- vcpu->arch.cur_tb_start = tb;
-}
-
static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -47,8 +38,8 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator
curr->seqcount = seq + 2;
}
-#define start_timing(vcpu, next) __start_timing(vcpu, next)
-#define end_timing(vcpu) __start_timing(vcpu, NULL)
+#define start_timing(vcpu, next) __accumulate_time(vcpu, next)
+#define end_timing(vcpu) __accumulate_time(vcpu, NULL)
#define accumulate_time(vcpu, next) __accumulate_time(vcpu, next)
#else
#define start_timing(vcpu, next) do {} while (0)
--
2.35.1
From: Kuninori Morimoto <[email protected]>
[ Upstream commit ef30911d3c39fd57884c348c29b9cbff88def155 ]
Before, ssiu.c didn't care SSI5-8, thus,
commit b1384d4c95088d0 ("ASoC: rsnd: care default case on
rsnd_ssiu_busif_err_status_clear()") cares it for status clear.
But we should care it for error irq handling, too.
This patch cares it.
Reported-by: Nguyen Bao Nguyen <[email protected]>
Reported-by: Nishiyama Kunihiko <[email protected]>
Signed-off-by: Kuninori Morimoto <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Mark Brown <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
sound/soc/sh/rcar/ssiu.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 4b8a63e336c7..d7f4646ee029 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -67,6 +67,8 @@ static void rsnd_ssiu_busif_err_irq_ctrl(struct rsnd_mod *mod, int enable)
shift = 1;
offset = 1;
break;
+ default:
+ return;
}
for (i = 0; i < 4; i++) {
--
2.35.1
From: Conor Dooley <[email protected]>
[ Upstream commit af8f260abc608c06e4466a282b53f1e2dc09f042 ]
The fu540 has no cpu-map node, so tools like hwloc cannot correctly
parse the topology. Add the node using the existing node labels.
Reported-by: Brice Goglin <[email protected]>
Link: https://github.com/open-mpi/hwloc/issues/536
Signed-off-by: Conor Dooley <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/riscv/boot/dts/sifive/fu540-c000.dtsi | 24 ++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
index 64c06c9b41dc..87d6e5a4253f 100644
--- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
@@ -133,6 +133,30 @@ cpu4_intc: interrupt-controller {
interrupt-controller;
};
};
+
+ cpu-map {
+ cluster0 {
+ core0 {
+ cpu = <&cpu0>;
+ };
+
+ core1 {
+ cpu = <&cpu1>;
+ };
+
+ core2 {
+ cpu = <&cpu2>;
+ };
+
+ core3 {
+ cpu = <&cpu3>;
+ };
+
+ core4 {
+ cpu = <&cpu4>;
+ };
+ };
+ };
};
soc {
#address-cells = <2>;
--
2.35.1
Le 14/08/2022 à 18:25, Sasha Levin a écrit :
> From: Laurent Dufour <[email protected]>
>
> [ Upstream commit 7c56a8733d0a2a4be2438a7512566e5ce552fccf ]
Hi Sasha,
Thanks for picking this patch.
Do you plan to pick the 2 others patches of this series in the older
kernels, as you did for 5.18 and 5.19 ?
The 2 other patches in this series are:
118b1366930c ("powerpc/pseries/mobility: set NMI watchdog factor during an
LPM")
f5e74e836097 ("powerpc/watchdog: introduce a NMI watchdog's factor")
I'm not sure how well they apply to these older kernels.
Thanks,
Laurent.
>
> In some circumstances it may be interesting to reconfigure the watchdog
> from inside the kernel.
>
> On PowerPC, this may helpful before and after a LPAR migration (LPM) is
> initiated, because it implies some latencies, watchdog, and especially NMI
> watchdog is expected to be triggered during this operation. Reconfiguring
> the watchdog with a factor, would prevent it to happen too frequently
> during LPM.
>
> Rename lockup_detector_reconfigure() as __lockup_detector_reconfigure() and
> create a new function lockup_detector_reconfigure() calling
> __lockup_detector_reconfigure() under the protection of watchdog_mutex.
>
> Signed-off-by: Laurent Dufour <[email protected]>
> [mpe: Squash in build fix from Laurent, reported by Sachin]
> Signed-off-by: Michael Ellerman <[email protected]>
> Link: https://lore.kernel.org/r/[email protected]
> Signed-off-by: Sasha Levin <[email protected]>
> ---
> include/linux/nmi.h | 2 ++
> kernel/watchdog.c | 21 ++++++++++++++++-----
> 2 files changed, 18 insertions(+), 5 deletions(-)
>
> diff --git a/include/linux/nmi.h b/include/linux/nmi.h
> index 750c7f395ca9..f700ff2df074 100644
> --- a/include/linux/nmi.h
> +++ b/include/linux/nmi.h
> @@ -122,6 +122,8 @@ int watchdog_nmi_probe(void);
> int watchdog_nmi_enable(unsigned int cpu);
> void watchdog_nmi_disable(unsigned int cpu);
>
> +void lockup_detector_reconfigure(void);
> +
> /**
> * touch_nmi_watchdog - restart NMI watchdog timeout.
> *
> diff --git a/kernel/watchdog.c b/kernel/watchdog.c
> index ad912511a0c0..1cfa269bd448 100644
> --- a/kernel/watchdog.c
> +++ b/kernel/watchdog.c
> @@ -537,7 +537,7 @@ int lockup_detector_offline_cpu(unsigned int cpu)
> return 0;
> }
>
> -static void lockup_detector_reconfigure(void)
> +static void __lockup_detector_reconfigure(void)
> {
> cpus_read_lock();
> watchdog_nmi_stop();
> @@ -557,6 +557,13 @@ static void lockup_detector_reconfigure(void)
> __lockup_detector_cleanup();
> }
>
> +void lockup_detector_reconfigure(void)
> +{
> + mutex_lock(&watchdog_mutex);
> + __lockup_detector_reconfigure();
> + mutex_unlock(&watchdog_mutex);
> +}
> +
> /*
> * Create the watchdog infrastructure and configure the detector(s).
> */
> @@ -573,13 +580,13 @@ static __init void lockup_detector_setup(void)
> return;
>
> mutex_lock(&watchdog_mutex);
> - lockup_detector_reconfigure();
> + __lockup_detector_reconfigure();
> softlockup_initialized = true;
> mutex_unlock(&watchdog_mutex);
> }
>
> #else /* CONFIG_SOFTLOCKUP_DETECTOR */
> -static void lockup_detector_reconfigure(void)
> +static void __lockup_detector_reconfigure(void)
> {
> cpus_read_lock();
> watchdog_nmi_stop();
> @@ -587,9 +594,13 @@ static void lockup_detector_reconfigure(void)
> watchdog_nmi_start();
> cpus_read_unlock();
> }
> +void lockup_detector_reconfigure(void)
> +{
> + __lockup_detector_reconfigure();
> +}
> static inline void lockup_detector_setup(void)
> {
> - lockup_detector_reconfigure();
> + __lockup_detector_reconfigure();
> }
> #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
>
> @@ -629,7 +640,7 @@ static void proc_watchdog_update(void)
> {
> /* Remove impossible cpus to keep sysctl output clean. */
> cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
> - lockup_detector_reconfigure();
> + __lockup_detector_reconfigure();
> }
>
> /*