/*
* Copyright (c) 2016, Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef SOC_NPS_COMMON_H
#define SOC_NPS_COMMON_H
#ifdef CONFIG_SMP
#define NPS_IPI_IRQ 5
#endif
#define NPS_HOST_REG_BASE 0xF6000000
#define NPS_MSU_BLKID 0x018
#define CTOP_INST_RSPI_GIC_0_R12 0x3C56117E
#define CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST 0x5B60
#define CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM 0x00010422
#ifndef __ASSEMBLY__
/* In order to increase compilation test coverage */
#ifdef CONFIG_ARC
static inline void nps_ack_gic(void)
{
__asm__ __volatile__ (
" .word %0\n"
:
: "i"(CTOP_INST_RSPI_GIC_0_R12)
: "memory");
}
#else
static inline void nps_ack_gic(void) { }
#define write_aux_reg(r, v)
#define read_aux_reg(r) 0
#endif
/* CPU global ID */
struct global_id {
union {
struct {
#ifdef CONFIG_EZNPS_MTM_EXT
u32 __reserved:20, cluster:4, core:4, thread:4;
#else
u32 __reserved:24, cluster:4, core:4;
#endif
};
u32 value;
};
};
/*
* Convert logical to physical CPU IDs
*
* The conversion swap bits 1 and 2 of cluster id (out of 4 bits)
* Now quad of logical clusters id's are adjacent physically,
* and not like the id's physically came with each cluster.
* Below table is 4x4 mesh of core clusters as it layout on chip.
* Cluster ids are in format: logical (physical)
*
* ----------------- ------------------
* 3 | 5 (3) 7 (7) | | 13 (11) 15 (15)|
*
* 2 | 4 (2) 6 (6) | | 12 (10) 14 (14)|
* ----------------- ------------------
* 1 | 1 (1) 3 (5) | | 9 (9) 11 (13)|
*
* 0 | 0 (0) 2 (4) | | 8 (8) 10 (12)|
* ----------------- ------------------
* 0 1 2 3
*/
static inline int nps_cluster_logic_to_phys(int cluster)
{
#ifdef __arc__
__asm__ __volatile__(
" mov r3,%0\n"
" .short %1\n"
" .word %2\n"
" mov %0,r3\n"
: "+r"(cluster)
: "i"(CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST),
"i"(CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM)
: "r3");
#endif
return cluster;
}
#define NPS_CPU_TO_CLUSTER_NUM(cpu) \
({ struct global_id gid; gid.value = cpu; \
nps_cluster_logic_to_phys(gid.cluster); })
struct nps_host_reg_address {
union {
struct {
u32 base:8, cl_x:4, cl_y:4,
blkid:6, reg:8, __reserved:2;
};
u32 value;
};
};
struct nps_host_reg_address_non_cl {
union {
struct {
u32 base:7, blkid:11, reg:12, __reserved:2;
};
u32 value;
};
};
static inline void *nps_host_reg_non_cl(u32 blkid, u32 reg)
{
struct nps_host_reg_address_non_cl reg_address;
reg_address.value = NPS_HOST_REG_BASE;
reg_address.blkid = blkid;
reg_address.reg = reg;
return (void *)reg_address.value;
}
static inline void *nps_host_reg(u32 cpu, u32 blkid, u32 reg)
{
struct nps_host_reg_address reg_address;
u32 cl = NPS_CPU_TO_CLUSTER_NUM(cpu);
reg_address.value = NPS_HOST_REG_BASE;
reg_address.cl_x = (cl >> 2) & 0x3;
reg_address.cl_y = cl & 0x3;
reg_address.blkid = blkid;
reg_address.reg = reg;
return (void *)reg_address.value;
}
#endif /* __ASSEMBLY__ */
#endif /* SOC_NPS_COMMON_H */
0
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return
"true" IFF they acquire a reference. But the return value from
atomic_long_inc_not_zero() is a long and may have high bits set,
e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines
is bool so the reference may actually be acquired but the routines
return "false" which results in a reference leak since the caller
assumes it does not need to do a corresponding percpu_ref_put().
This was seen when performing CPU hotplug during I/O, as hangs in
blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start)
raced with percpu_ref_tryget (blk_mq_timeout_work).
Sample stack trace:
__switch_to+0x2c0/0x450
__schedule+0x2f8/0x970
schedule+0x48/0xc0
blk_mq_freeze_queue_wait+0x94/0x120
blk_mq_queue_reinit_work+0xb8/0x180
blk_mq_queue_reinit_prepare+0x84/0xa0
cpuhp_invoke_callback+0x17c/0x600
cpuhp_up_callbacks+0x58/0x150
_cpu_up+0xf0/0x1c0
do_cpu_up+0x120/0x150
cpu_subsys_online+0x64/0xe0
device_online+0xb4/0x120
online_store+0xb4/0xc0
dev_attr_store+0x68/0xa0
sysfs_kf_write+0x80/0xb0
kernfs_fop_write+0x17c/0x250
__vfs_write+0x6c/0x1e0
vfs_write+0xd0/0x270
SyS_write+0x6c/0x110
system_call+0x38/0xe0
Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS,
and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests.
However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0
and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set.
The fix is to make the tryget routines use an actual boolean internally instead
of the atomic long result truncated to a int.
Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints
Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751
Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints")
Cc: stable@vger.kernel.org # v3.18+