* [powerpc:merge] BUILD SUCCESS 3c0356e8994ed88e5234897c0ffee4188f8b9287
From: kernel test robot @ 2020-07-01 9:40 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git merge
branch HEAD: 3c0356e8994ed88e5234897c0ffee4188f8b9287 Automatic merge of 'master', 'next' and 'fixes' (2020-06-30 22:07)
elapsed time: 1282m
configs tested: 98
configs skipped: 1
The following configs have been built successfully.
More configs may be tested in the coming days.
arm defconfig
arm allyesconfig
arm allmodconfig
arm allnoconfig
arm64 allyesconfig
arm64 defconfig
arm64 allmodconfig
arm64 allnoconfig
i386 allyesconfig
i386 defconfig
i386 debian-10.3
i386 allnoconfig
ia64 allmodconfig
ia64 defconfig
ia64 allnoconfig
ia64 allyesconfig
m68k allmodconfig
m68k allnoconfig
m68k sun3_defconfig
m68k defconfig
m68k allyesconfig
nios2 defconfig
nios2 allyesconfig
openrisc defconfig
c6x allyesconfig
c6x allnoconfig
openrisc allyesconfig
nds32 defconfig
nds32 allnoconfig
csky allyesconfig
csky defconfig
alpha defconfig
alpha allyesconfig
xtensa allyesconfig
h8300 allyesconfig
h8300 allmodconfig
xtensa defconfig
arc defconfig
arc allyesconfig
sh allmodconfig
sh allnoconfig
microblaze allnoconfig
mips allyesconfig
mips allnoconfig
mips allmodconfig
parisc allnoconfig
parisc defconfig
parisc allyesconfig
parisc allmodconfig
powerpc defconfig
powerpc allyesconfig
powerpc rhel-kconfig
powerpc allmodconfig
powerpc allnoconfig
i386 randconfig-a001-20200630
i386 randconfig-a003-20200630
i386 randconfig-a002-20200630
i386 randconfig-a004-20200630
i386 randconfig-a005-20200630
i386 randconfig-a006-20200630
x86_64 randconfig-a011-20200630
x86_64 randconfig-a014-20200630
x86_64 randconfig-a013-20200630
x86_64 randconfig-a015-20200630
x86_64 randconfig-a016-20200630
x86_64 randconfig-a012-20200630
i386 randconfig-a011-20200630
i386 randconfig-a016-20200630
i386 randconfig-a015-20200630
i386 randconfig-a012-20200630
i386 randconfig-a014-20200630
i386 randconfig-a013-20200630
riscv allyesconfig
riscv allnoconfig
riscv defconfig
riscv allmodconfig
s390 allyesconfig
s390 allnoconfig
s390 allmodconfig
s390 defconfig
sparc allyesconfig
sparc defconfig
sparc64 defconfig
sparc64 allnoconfig
sparc64 allyesconfig
sparc64 allmodconfig
um allmodconfig
um allnoconfig
um allyesconfig
um defconfig
x86_64 rhel
x86_64 rhel-7.2-clear
x86_64 lkp
x86_64 fedora-25
x86_64 rhel-7.6
x86_64 rhel-7.6-kselftests
x86_64 rhel-8.3
x86_64 kexec
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* [PATCH v2 10/10] powerpc/perf: Add extended regs support for power10 platform
From: Athira Rajeev @ 2020-07-01 9:21 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
Include capability flag `PERF_PMU_CAP_EXTENDED_REGS` for power10
and expose MMCR3, SIER2, SIER3 registers as part of extended regs.
Also introduce `PERF_REG_PMU_MASK_31` to define extended mask
value at runtime for power10
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/include/uapi/asm/perf_regs.h | 6 ++++++
arch/powerpc/perf/perf_regs.c | 10 +++++++++-
arch/powerpc/perf/power10-pmu.c | 6 ++++++
tools/arch/powerpc/include/uapi/asm/perf_regs.h | 6 ++++++
tools/perf/arch/powerpc/include/perf_regs.h | 3 +++
tools/perf/arch/powerpc/util/perf_regs.c | 6 ++++++
6 files changed, 36 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h
index 485b1d5..020b51c 100644
--- a/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -52,6 +52,9 @@ enum perf_event_powerpc_regs {
PERF_REG_POWERPC_MMCR0,
PERF_REG_POWERPC_MMCR1,
PERF_REG_POWERPC_MMCR2,
+ PERF_REG_POWERPC_MMCR3,
+ PERF_REG_POWERPC_SIER2,
+ PERF_REG_POWERPC_SIER3,
/* Max regs without the extended regs */
PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1,
};
@@ -62,4 +65,7 @@ enum perf_event_powerpc_regs {
#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) \
- PERF_REG_PMU_MASK)
+/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */
+#define PERF_REG_PMU_MASK_31 (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) \
+ - PERF_REG_PMU_MASK)
#endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index c8a7e8c..c969935 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -81,6 +81,12 @@ static u64 get_ext_regs_value(int idx)
return mfspr(SPRN_MMCR1);
case PERF_REG_POWERPC_MMCR2:
return mfspr(SPRN_MMCR2);
+ case PERF_REG_POWERPC_MMCR3:
+ return mfspr(SPRN_MMCR3);
+ case PERF_REG_POWERPC_SIER2:
+ return mfspr(SPRN_SIER2);
+ case PERF_REG_POWERPC_SIER3:
+ return mfspr(SPRN_SIER3);
default: return 0;
}
}
@@ -89,7 +95,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
{
u64 PERF_REG_EXTENDED_MAX;
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ PERF_REG_EXTENDED_MAX = PERF_REG_POWERPC_SIER3 + 1;
+ else if (cpu_has_feature(CPU_FTR_ARCH_300))
PERF_REG_EXTENDED_MAX = PERF_REG_POWERPC_MMCR2 + 1;
if (idx == PERF_REG_POWERPC_SIER &&
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index 07fb919..51082d6 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -86,6 +86,8 @@
#define POWER10_MMCRA_IFM3 0x00000000C0000000UL
#define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL
+extern u64 mask_var;
+
/* Table of alternatives, sorted by column 0 */
static const unsigned int power10_event_alternatives[][MAX_ALT] = {
{ PM_RUN_CYC_ALT, PM_RUN_CYC },
@@ -397,6 +399,7 @@ static void power10_config_bhrb(u64 pmu_bhrb_filter)
.cache_events = &power10_cache_events,
.attr_groups = power10_pmu_attr_groups,
.bhrb_nr = 32,
+ .capabilities = PERF_PMU_CAP_EXTENDED_REGS,
};
int init_power10_pmu(void)
@@ -408,6 +411,9 @@ int init_power10_pmu(void)
strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10"))
return -ENODEV;
+ /* Set the PERF_REG_EXTENDED_MASK here */
+ mask_var = PERF_REG_PMU_MASK_31;
+
rc = register_power_pmu(&power10_pmu);
if (rc)
return rc;
diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
index 485b1d5..020b51c 100644
--- a/tools/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -52,6 +52,9 @@ enum perf_event_powerpc_regs {
PERF_REG_POWERPC_MMCR0,
PERF_REG_POWERPC_MMCR1,
PERF_REG_POWERPC_MMCR2,
+ PERF_REG_POWERPC_MMCR3,
+ PERF_REG_POWERPC_SIER2,
+ PERF_REG_POWERPC_SIER3,
/* Max regs without the extended regs */
PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1,
};
@@ -62,4 +65,7 @@ enum perf_event_powerpc_regs {
#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) \
- PERF_REG_PMU_MASK)
+/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */
+#define PERF_REG_PMU_MASK_31 (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) \
+ - PERF_REG_PMU_MASK)
#endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 46ed00d..63f3ac9 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -68,6 +68,9 @@
[PERF_REG_POWERPC_MMCR0] = "mmcr0",
[PERF_REG_POWERPC_MMCR1] = "mmcr1",
[PERF_REG_POWERPC_MMCR2] = "mmcr2",
+ [PERF_REG_POWERPC_MMCR3] = "mmcr3",
+ [PERF_REG_POWERPC_SIER2] = "sier2",
+ [PERF_REG_POWERPC_SIER3] = "sier3",
};
static inline const char *perf_reg_name(int id)
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index 9179230..ccc625f 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -13,6 +13,7 @@
#include <linux/kernel.h>
#define PVR_POWER9 0x004E
+#define PVR_POWER10 0x0080
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(r0, PERF_REG_POWERPC_R0),
@@ -63,6 +64,9 @@
SMPL_REG(mmcr0, PERF_REG_POWERPC_MMCR0),
SMPL_REG(mmcr1, PERF_REG_POWERPC_MMCR1),
SMPL_REG(mmcr2, PERF_REG_POWERPC_MMCR2),
+ SMPL_REG(mmcr3, PERF_REG_POWERPC_MMCR3),
+ SMPL_REG(sier2, PERF_REG_POWERPC_SIER2),
+ SMPL_REG(sier3, PERF_REG_POWERPC_SIER3),
SMPL_REG_END
};
@@ -200,6 +204,8 @@ uint64_t arch__intr_reg_mask(void)
if (version == PVR_POWER9)
extended_mask = PERF_REG_PMU_MASK_300;
+ else if (version == PVR_POWER10)
+ extended_mask = PERF_REG_PMU_MASK_31;
else
return PERF_REGS_MASK;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 09/10] tools/perf: Add perf tools support for extended register capability in powerpc
From: Athira Rajeev @ 2020-07-01 9:21 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
From: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Add extended regs to sample_reg_mask in the tool side to use
with `-I?` option. Perf tools side uses extended mask to display
the platform supported register names (with -I? option) to the user
and also send this mask to the kernel to capture the extended registers
in each sample. Hence decide the mask value based on the processor
version.
Signed-off-by: Anju T Sudhakar <anju@linux.vnet.ibm.com>
[Decide extended mask at run time based on platform]
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Reviewed-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
---
tools/arch/powerpc/include/uapi/asm/perf_regs.h | 14 ++++++-
tools/perf/arch/powerpc/include/perf_regs.h | 5 ++-
tools/perf/arch/powerpc/util/perf_regs.c | 55 +++++++++++++++++++++++++
3 files changed, 72 insertions(+), 2 deletions(-)
diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
index f599064..485b1d5 100644
--- a/tools/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -48,6 +48,18 @@ enum perf_event_powerpc_regs {
PERF_REG_POWERPC_DSISR,
PERF_REG_POWERPC_SIER,
PERF_REG_POWERPC_MMCRA,
- PERF_REG_POWERPC_MAX,
+ /* Extended registers */
+ PERF_REG_POWERPC_MMCR0,
+ PERF_REG_POWERPC_MMCR1,
+ PERF_REG_POWERPC_MMCR2,
+ /* Max regs without the extended regs */
+ PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1,
};
+
+#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1)
+
+/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */
+#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) \
+ - PERF_REG_PMU_MASK)
+
#endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index e18a355..46ed00d 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -64,7 +64,10 @@
[PERF_REG_POWERPC_DAR] = "dar",
[PERF_REG_POWERPC_DSISR] = "dsisr",
[PERF_REG_POWERPC_SIER] = "sier",
- [PERF_REG_POWERPC_MMCRA] = "mmcra"
+ [PERF_REG_POWERPC_MMCRA] = "mmcra",
+ [PERF_REG_POWERPC_MMCR0] = "mmcr0",
+ [PERF_REG_POWERPC_MMCR1] = "mmcr1",
+ [PERF_REG_POWERPC_MMCR2] = "mmcr2",
};
static inline const char *perf_reg_name(int id)
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index 0a52429..9179230 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -6,9 +6,14 @@
#include "../../../util/perf_regs.h"
#include "../../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/header.h"
+#include "../../../perf-sys.h"
#include <linux/kernel.h>
+#define PVR_POWER9 0x004E
+
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(r0, PERF_REG_POWERPC_R0),
SMPL_REG(r1, PERF_REG_POWERPC_R1),
@@ -55,6 +60,9 @@
SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR),
SMPL_REG(sier, PERF_REG_POWERPC_SIER),
SMPL_REG(mmcra, PERF_REG_POWERPC_MMCRA),
+ SMPL_REG(mmcr0, PERF_REG_POWERPC_MMCR0),
+ SMPL_REG(mmcr1, PERF_REG_POWERPC_MMCR1),
+ SMPL_REG(mmcr2, PERF_REG_POWERPC_MMCR2),
SMPL_REG_END
};
@@ -163,3 +171,50 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
return SDT_ARG_VALID;
}
+
+uint64_t arch__intr_reg_mask(void)
+{
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .sample_type = PERF_SAMPLE_REGS_INTR,
+ .precise_ip = 1,
+ .disabled = 1,
+ .exclude_kernel = 1,
+ };
+ int fd, ret;
+ char buffer[64];
+ u32 version;
+ u64 extended_mask = 0;
+
+ /* Get the PVR value to set the extended
+ * mask specific to platform
+ */
+ get_cpuid(buffer, sizeof(buffer));
+ ret = sscanf(buffer, "%u,", &version);
+
+ if (ret != 1) {
+ pr_debug("Failed to get the processor version, unable to output extended registers\n");
+ return PERF_REGS_MASK;
+ }
+
+ if (version == PVR_POWER9)
+ extended_mask = PERF_REG_PMU_MASK_300;
+ else
+ return PERF_REGS_MASK;
+
+ attr.sample_regs_intr = extended_mask;
+ attr.sample_period = 1;
+ event_attr_init(&attr);
+
+ /*
+ * check if the pmu supports perf extended regs, before
+ * returning the register mask to sample.
+ */
+ fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+ if (fd != -1) {
+ close(fd);
+ return (extended_mask | PERF_REGS_MASK);
+ }
+ return PERF_REGS_MASK;
+}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 08/10] powerpc/perf: Add support for outputting extended regs in perf intr_regs
From: Athira Rajeev @ 2020-07-01 9:21 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
From: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Add support for perf extended register capability in powerpc.
The capability flag PERF_PMU_CAP_EXTENDED_REGS, is used to indicate the
PMU which support extended registers. The generic code define the mask
of extended registers as 0 for non supported architectures.
Patch adds extended regs support for power9 platform by
exposing MMCR0, MMCR1 and MMCR2 registers.
REG_RESERVED mask needs update to include extended regs.
`PERF_REG_EXTENDED_MASK`, contains mask value of the supported registers,
is defined at runtime in the kernel based on platform since the supported
registers may differ from one processor version to another and hence the
MASK value.
with patch
----------
available registers: r0 r1 r2 r3 r4 r5 r6 r7 r8 r9 r10 r11
r12 r13 r14 r15 r16 r17 r18 r19 r20 r21 r22 r23 r24 r25 r26
r27 r28 r29 r30 r31 nip msr orig_r3 ctr link xer ccr softe
trap dar dsisr sier mmcra mmcr0 mmcr1 mmcr2
PERF_RECORD_SAMPLE(IP, 0x1): 4784/4784: 0 period: 1 addr: 0
... intr regs: mask 0xffffffffffff ABI 64-bit
.... r0 0xc00000000012b77c
.... r1 0xc000003fe5e03930
.... r2 0xc000000001b0e000
.... r3 0xc000003fdcddf800
.... r4 0xc000003fc7880000
.... r5 0x9c422724be
.... r6 0xc000003fe5e03908
.... r7 0xffffff63bddc8706
.... r8 0x9e4
.... r9 0x0
.... r10 0x1
.... r11 0x0
.... r12 0xc0000000001299c0
.... r13 0xc000003ffffc4800
.... r14 0x0
.... r15 0x7fffdd8b8b00
.... r16 0x0
.... r17 0x7fffdd8be6b8
.... r18 0x7e7076607730
.... r19 0x2f
.... r20 0xc00000001fc26c68
.... r21 0xc0002041e4227e00
.... r22 0xc00000002018fb60
.... r23 0x1
.... r24 0xc000003ffec4d900
.... r25 0x80000000
.... r26 0x0
.... r27 0x1
.... r28 0x1
.... r29 0xc000000001be1260
.... r30 0x6008010
.... r31 0xc000003ffebb7218
.... nip 0xc00000000012b910
.... msr 0x9000000000009033
.... orig_r3 0xc00000000012b86c
.... ctr 0xc0000000001299c0
.... link 0xc00000000012b77c
.... xer 0x0
.... ccr 0x28002222
.... softe 0x1
.... trap 0xf00
.... dar 0x0
.... dsisr 0x80000000000
.... sier 0x0
.... mmcra 0x80000000000
.... mmcr0 0x82008090
.... mmcr1 0x1e000000
.... mmcr2 0x0
... thread: perf:4784
Signed-off-by: Anju T Sudhakar <anju@linux.vnet.ibm.com>
[Defined PERF_REG_EXTENDED_MASK at run time to add support for different platforms ]
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Reviewed-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/perf_event_server.h | 8 +++++++
arch/powerpc/include/uapi/asm/perf_regs.h | 14 +++++++++++-
arch/powerpc/perf/core-book3s.c | 1 +
arch/powerpc/perf/perf_regs.c | 34 +++++++++++++++++++++++++---
arch/powerpc/perf/power9-pmu.c | 6 +++++
5 files changed, 59 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index cb207f8..e8d35b6 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -15,6 +15,9 @@
#define MAX_EVENT_ALTERNATIVES 8
#define MAX_LIMITED_HWCOUNTERS 2
+extern u64 mask_var;
+#define PERF_REG_EXTENDED_MASK mask_var
+
struct perf_event;
/*
@@ -55,6 +58,11 @@ struct power_pmu {
int *blacklist_ev;
/* BHRB entries in the PMU */
int bhrb_nr;
+ /*
+ * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if
+ * the pmu supports extended perf regs capability
+ */
+ int capabilities;
};
/*
diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h
index f599064..485b1d5 100644
--- a/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -48,6 +48,18 @@ enum perf_event_powerpc_regs {
PERF_REG_POWERPC_DSISR,
PERF_REG_POWERPC_SIER,
PERF_REG_POWERPC_MMCRA,
- PERF_REG_POWERPC_MAX,
+ /* Extended registers */
+ PERF_REG_POWERPC_MMCR0,
+ PERF_REG_POWERPC_MMCR1,
+ PERF_REG_POWERPC_MMCR2,
+ /* Max regs without the extended regs */
+ PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1,
};
+
+#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1)
+
+/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */
+#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) \
+ - PERF_REG_PMU_MASK)
+
#endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 9709606..382d770 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2317,6 +2317,7 @@ int register_power_pmu(struct power_pmu *pmu)
pmu->name);
power_pmu.attr_groups = ppmu->attr_groups;
+ power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS);
#ifdef MSR_HV
/*
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index a213a0a..c8a7e8c 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -13,9 +13,11 @@
#include <asm/ptrace.h>
#include <asm/perf_regs.h>
+u64 mask_var;
+
#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
-#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1))
+#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK))
static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = {
PT_REGS_OFFSET(PERF_REG_POWERPC_R0, gpr[0]),
@@ -69,10 +71,26 @@
PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr),
};
+/* Function to return the extended register values */
+static u64 get_ext_regs_value(int idx)
+{
+ switch (idx) {
+ case PERF_REG_POWERPC_MMCR0:
+ return mfspr(SPRN_MMCR0);
+ case PERF_REG_POWERPC_MMCR1:
+ return mfspr(SPRN_MMCR1);
+ case PERF_REG_POWERPC_MMCR2:
+ return mfspr(SPRN_MMCR2);
+ default: return 0;
+ }
+}
+
u64 perf_reg_value(struct pt_regs *regs, int idx)
{
- if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX))
- return 0;
+ u64 PERF_REG_EXTENDED_MAX;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ PERF_REG_EXTENDED_MAX = PERF_REG_POWERPC_MMCR2 + 1;
if (idx == PERF_REG_POWERPC_SIER &&
(IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
@@ -85,6 +103,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
IS_ENABLED(CONFIG_PPC32)))
return 0;
+ if (idx >= PERF_REG_POWERPC_MAX && idx < PERF_REG_EXTENDED_MAX)
+ return get_ext_regs_value(idx);
+
+ /*
+ * If the idx is referring to value beyond the
+ * supported registers, return 0 with a warning
+ */
+ if (WARN_ON_ONCE(idx >= PERF_REG_EXTENDED_MAX))
+ return 0;
+
return regs_get_register(regs, pt_regs_offset[idx]);
}
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 05dae38..fb6fcad 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -90,6 +90,8 @@ enum {
#define POWER9_MMCRA_IFM3 0x00000000C0000000UL
#define POWER9_MMCRA_BHRB_MASK 0x00000000C0000000UL
+extern u64 mask_var;
+
/* Nasty Power9 specific hack */
#define PVR_POWER9_CUMULUS 0x00002000
@@ -434,6 +436,7 @@ static void power9_config_bhrb(u64 pmu_bhrb_filter)
.cache_events = &power9_cache_events,
.attr_groups = power9_pmu_attr_groups,
.bhrb_nr = 32,
+ .capabilities = PERF_PMU_CAP_EXTENDED_REGS,
};
int init_power9_pmu(void)
@@ -457,6 +460,9 @@ int init_power9_pmu(void)
}
}
+ /* Set the PERF_REG_EXTENDED_MASK here */
+ mask_var = PERF_REG_PMU_MASK_300;
+
rc = register_power_pmu(&power9_pmu);
if (rc)
return rc;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 07/10] powerpc/perf: support BHRB disable bit and new filtering modes
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
PowerISA v3.1 has few updates for the Branch History Rolling Buffer(BHRB).
First is the addition of BHRB disable bit and second new filtering
modes for BHRB.
BHRB disable is controlled via Monitor Mode Control Register A (MMCRA)
bit 26, namely "BHRB Recording Disable (BHRBRD)". This field controls
whether BHRB entries are written when BHRB recording is enabled by other
bits. Patch implements support for this BHRB disable bit.
Secondly PowerISA v3.1 introduce filtering support for
PERF_SAMPLE_BRANCH_IND_CALL/COND. The patch adds BHRB filter support
for "ind_call" and "cond" in power10_bhrb_filter_map().
'commit bb19af816025 ("powerpc/perf: Prevent kernel address leak to userspace via BHRB buffer")'
added a check in bhrb_read() to filter the kernel address from BHRB buffer. Patch here modified
it to avoid that check for PowerISA v3.1 based processors, since PowerISA v3.1 allows
only MSR[PR]=1 address to be written to BHRB buffer.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/core-book3s.c | 27 +++++++++++++++++++++------
arch/powerpc/perf/isa207-common.c | 13 +++++++++++++
arch/powerpc/perf/power10-pmu.c | 13 +++++++++++--
arch/powerpc/platforms/powernv/idle.c | 14 ++++++++++++++
4 files changed, 59 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index fad5159..9709606 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -466,9 +466,13 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *
* addresses at this point. Check the privileges before
* exporting it to userspace (avoid exposure of regions
* where we could have speculative execution)
+ * Incase of ISA 310, BHRB will capture only user-space
+ * address,hence include a check before filtering code
*/
- if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
- continue;
+ if (!(ppmu->flags & PPMU_ARCH_310S))
+ if (is_kernel_addr(addr) &&
+ perf_allow_kernel(&event->attr) != 0)
+ continue;
/* Branches are read most recent first (ie. mfbhrb 0 is
* the most recent branch).
@@ -1212,7 +1216,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0)
static void power_pmu_disable(struct pmu *pmu)
{
struct cpu_hw_events *cpuhw;
- unsigned long flags, mmcr0, val;
+ unsigned long flags, mmcr0, val, mmcra = 0;
if (!ppmu)
return;
@@ -1245,12 +1249,23 @@ static void power_pmu_disable(struct pmu *pmu)
mb();
isync();
+ val = mmcra = cpuhw->mmcr[2];
+
/*
* Disable instruction sampling if it was enabled
*/
- if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
- mtspr(SPRN_MMCRA,
- cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
+ if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE)
+ mmcra = cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE;
+
+ /* Disable BHRB via mmcra [:26] for p10 if needed */
+ if (!(cpuhw->mmcr[2] & MMCRA_BHRB_DISABLE))
+ mmcra |= MMCRA_BHRB_DISABLE;
+
+ /* Write SPRN_MMCRA if mmcra has either disabled
+ * instruction sampling or BHRB
+ */
+ if (val != mmcra) {
+ mtspr(SPRN_MMCRA, mmcra);
mb();
isync();
}
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 7d4839e..463d925 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -404,6 +404,12 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcra = mmcr1 = mmcr2 = mmcr3 = 0;
+ /* Disable bhrb unless explicitly requested
+ * by setting MMCRA [:26] bit.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mmcra |= MMCRA_BHRB_DISABLE;
+
/* Second pass: assign PMCs, set all MMCR1 fields */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
@@ -475,10 +481,17 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
}
if (event[i] & EVENT_WANTS_BHRB) {
+ /* set MMCRA[:26] to 0 for Power10 to enable BHRB */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mmcra &= ~MMCRA_BHRB_DISABLE;
val = (event[i] >> EVENT_IFM_SHIFT) & EVENT_IFM_MASK;
mmcra |= val << MMCRA_IFM_SHIFT;
}
+ /* set MMCRA[:26] to 0 if there is user request for BHRB */
+ if (cpu_has_feature(CPU_FTR_ARCH_31) && has_branch_stack(pevents[i]))
+ mmcra &= ~MMCRA_BHRB_DISABLE;
+
if (pevents[i]->attr.exclude_user)
mmcr2 |= MMCR2_FCP(pmc);
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index d64d69d..07fb919 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -82,6 +82,8 @@
/* MMCRA IFM bits - POWER10 */
#define POWER10_MMCRA_IFM1 0x0000000040000000UL
+#define POWER10_MMCRA_IFM2 0x0000000080000000UL
+#define POWER10_MMCRA_IFM3 0x00000000C0000000UL
#define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL
/* Table of alternatives, sorted by column 0 */
@@ -233,8 +235,15 @@ static u64 power10_bhrb_filter_map(u64 branch_sample_type)
if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
return -1;
- if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL)
- return -1;
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL) {
+ pmu_bhrb_filter |= POWER10_MMCRA_IFM2;
+ return pmu_bhrb_filter;
+ }
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_COND) {
+ pmu_bhrb_filter |= POWER10_MMCRA_IFM3;
+ return pmu_bhrb_filter;
+ }
if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL)
return -1;
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 2dd4673..7db99c7 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -611,6 +611,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
unsigned long srr1;
unsigned long pls;
unsigned long mmcr0 = 0;
+ unsigned long mmcra_bhrb = 0;
struct p9_sprs sprs = {}; /* avoid false used-uninitialised */
bool sprs_saved = false;
@@ -657,6 +658,15 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
*/
mmcr0 = mfspr(SPRN_MMCR0);
}
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ /* POWER10 uses MMCRA[:26] as BHRB disable bit
+ * to disable BHRB logic when not used. Hence Save and
+ * restore MMCRA after a state-loss idle.
+ */
+ mmcra_bhrb = mfspr(SPRN_MMCRA);
+ }
+
if ((psscr & PSSCR_RL_MASK) >= pnv_first_spr_loss_level) {
sprs.lpcr = mfspr(SPRN_LPCR);
sprs.hfscr = mfspr(SPRN_HFSCR);
@@ -721,6 +731,10 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
mtspr(SPRN_MMCR0, mmcr0);
}
+ /* Reload MMCRA to restore BHRB disable bit for POWER10 */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mtspr(SPRN_MMCRA, mmcra_bhrb);
+
/*
* DD2.2 and earlier need to set then clear bit 60 in MMCRA
* to ensure the PMU starts running.
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 05/10] powerpc/perf: Update Power PMU cache_events to u64 type
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
Events of type PERF_TYPE_HW_CACHE was described for Power PMU
as: int (*cache_events)[type][op][result];
where type, op, result values unpacked from the event attribute config
value is used to generate the raw event code at runtime.
So far the event code values which used to create these cache-related
events were within 32 bit and `int` type worked. In power10,
some of the event codes are of 64-bit value and hence update the
Power PMU cache_events to `u64` type in `power_pmu` struct.
Also propagate this change to existing all PMU driver code paths
which are using ppmu->cache_events.
Signed-off-by: Athira Rajeev<atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/perf_event_server.h | 2 +-
arch/powerpc/perf/core-book3s.c | 2 +-
arch/powerpc/perf/generic-compat-pmu.c | 2 +-
arch/powerpc/perf/mpc7450-pmu.c | 2 +-
arch/powerpc/perf/power5+-pmu.c | 2 +-
arch/powerpc/perf/power5-pmu.c | 2 +-
arch/powerpc/perf/power6-pmu.c | 2 +-
arch/powerpc/perf/power7-pmu.c | 2 +-
arch/powerpc/perf/power8-pmu.c | 2 +-
arch/powerpc/perf/power9-pmu.c | 2 +-
arch/powerpc/perf/ppc970-pmu.c | 2 +-
11 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 895aeaa..cb207f8 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -47,7 +47,7 @@ struct power_pmu {
const struct attribute_group **attr_groups;
int n_generic;
int *generic_events;
- int (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+ u64 (*cache_events)[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 5c64bd3..58bfb9a 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1820,7 +1820,7 @@ static void hw_perf_event_destroy(struct perf_event *event)
static int hw_perf_cache_event(u64 config, u64 *eventp)
{
unsigned long type, op, result;
- int ev;
+ u64 ev;
if (!ppmu->cache_events)
return -EINVAL;
diff --git a/arch/powerpc/perf/generic-compat-pmu.c b/arch/powerpc/perf/generic-compat-pmu.c
index 5e5a54d..eb8a6aaf 100644
--- a/arch/powerpc/perf/generic-compat-pmu.c
+++ b/arch/powerpc/perf/generic-compat-pmu.c
@@ -101,7 +101,7 @@ enum {
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0,
diff --git a/arch/powerpc/perf/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c
index 4d5ef92..cf1eb89 100644
--- a/arch/powerpc/perf/mpc7450-pmu.c
+++ b/arch/powerpc/perf/mpc7450-pmu.c
@@ -354,7 +354,7 @@ static void mpc7450_disable_pmc(unsigned int pmc, unsigned long mmcr[])
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0x225 },
[C(OP_WRITE)] = { 0, 0x227 },
diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index f857454..9252281 100644
--- a/arch/powerpc/perf/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
@@ -618,7 +618,7 @@ static void power5p_disable_pmc(unsigned int pmc, unsigned long mmcr[])
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x1c10a8, 0x3c1088 },
[C(OP_WRITE)] = { 0x2c10a8, 0xc10c3 },
diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index da52eca..3b36630 100644
--- a/arch/powerpc/perf/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
@@ -560,7 +560,7 @@ static void power5_disable_pmc(unsigned int pmc, unsigned long mmcr[])
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x4c1090, 0x3c1088 },
[C(OP_WRITE)] = { 0x3c1090, 0xc10c3 },
diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 3929cac..540b78d 100644
--- a/arch/powerpc/perf/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -481,7 +481,7 @@ static void p6_disable_pmc(unsigned int pmc, unsigned long mmcr[])
* are event codes.
* The "DTLB" and "ITLB" events relate to the DERAT and IERAT.
*/
-static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x280030, 0x80080 },
[C(OP_WRITE)] = { 0x180032, 0x80088 },
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index a137813..2b7f375 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -332,7 +332,7 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[])
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0xc880, 0x400f0 },
[C(OP_WRITE)] = { 0, 0x300f0 },
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 3a5fcc2..5282e84 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -253,7 +253,7 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter)
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 08c3ef7..05dae38 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -310,7 +310,7 @@ static void power9_config_bhrb(u64 pmu_bhrb_filter)
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index 4035d93..2970d1e 100644
--- a/arch/powerpc/perf/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -432,7 +432,7 @@ static void p970_disable_pmc(unsigned int pmc, unsigned long mmcr[])
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0x8810, 0x3810 },
[C(OP_WRITE)] = { 0x7810, 0x813 },
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 06/10] powerpc/perf: power10 Performance Monitoring support
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
Base enablement patch to register performance monitoring
hardware support for power10. Patch introduce the raw event
encoding format, defines the supported list of events, config
fields for the event attributes and their corresponding bit values
which are exported via sysfs.
Patch also enhances the support function in isa207_common.c to
include power10 pmu hardware.
[Enablement of base PMU driver code]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
[Addition of ISA macros for counter support functions]
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/Makefile | 2 +-
arch/powerpc/perf/core-book3s.c | 2 +
arch/powerpc/perf/internal.h | 1 +
arch/powerpc/perf/isa207-common.c | 59 ++++-
arch/powerpc/perf/isa207-common.h | 33 ++-
arch/powerpc/perf/power10-events-list.h | 70 ++++++
arch/powerpc/perf/power10-pmu.c | 410 ++++++++++++++++++++++++++++++++
7 files changed, 566 insertions(+), 11 deletions(-)
create mode 100644 arch/powerpc/perf/power10-events-list.h
create mode 100644 arch/powerpc/perf/power10-pmu.c
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 53d614e..c02854d 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o
obj64-$(CONFIG_PPC_PERF_CTRS) += ppc970-pmu.o power5-pmu.o \
power5+-pmu.o power6-pmu.o power7-pmu.o \
isa207-common.o power8-pmu.o power9-pmu.o \
- generic-compat-pmu.o
+ generic-compat-pmu.o power10-pmu.o
obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 58bfb9a..fad5159 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2333,6 +2333,8 @@ static int __init init_ppc64_pmu(void)
return 0;
else if (!init_power9_pmu())
return 0;
+ else if (!init_power10_pmu())
+ return 0;
else if (!init_ppc970_pmu())
return 0;
else
diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h
index f755c64..80bbf72 100644
--- a/arch/powerpc/perf/internal.h
+++ b/arch/powerpc/perf/internal.h
@@ -9,4 +9,5 @@
extern int init_power7_pmu(void);
extern int init_power8_pmu(void);
extern int init_power9_pmu(void);
+extern int init_power10_pmu(void);
extern int init_generic_compat_pmu(void);
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 4c86da5..7d4839e 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -55,7 +55,9 @@ static bool is_event_valid(u64 event)
{
u64 valid_mask = EVENT_VALID_MASK;
- if (cpu_has_feature(CPU_FTR_ARCH_300))
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ valid_mask = p10_EVENT_VALID_MASK;
+ else if (cpu_has_feature(CPU_FTR_ARCH_300))
valid_mask = p9_EVENT_VALID_MASK;
return !(event & ~valid_mask);
@@ -69,6 +71,14 @@ static inline bool is_event_marked(u64 event)
return false;
}
+static unsigned long sdar_mod_val(u64 event)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ return p10_SDAR_MODE(event);
+
+ return p9_SDAR_MODE(event);
+}
+
static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
{
/*
@@ -79,7 +89,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
* MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling
* mode and will be un-changed when setting MMCRA[63] (Marked events).
*
- * Incase of Power9:
+ * Incase of Power9/power10:
* Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
* or if group already have any marked events.
* For rest
@@ -90,8 +100,8 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE))
*mmcra &= MMCRA_SDAR_MODE_NO_UPDATES;
- else if (p9_SDAR_MODE(event))
- *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+ else if (sdar_mod_val(event))
+ *mmcra |= sdar_mod_val(event) << MMCRA_SDAR_MODE_SHIFT;
else
*mmcra |= MMCRA_SDAR_MODE_DCACHE;
} else
@@ -134,7 +144,11 @@ static bool is_thresh_cmp_valid(u64 event)
/*
* Check the mantissa upper two bits are not zero, unless the
* exponent is also zero. See the THRESH_CMP_MANTISSA doc.
+ * Power10: thresh_cmp is replaced by l2_l3 event select.
*/
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ return false;
+
cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
exp = cmp >> 7;
@@ -251,7 +265,12 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
- cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK;
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ cache = (event >> EVENT_CACHE_SEL_SHIFT) &
+ p10_EVENT_CACHE_SEL_MASK;
+ else
+ cache = (event >> EVENT_CACHE_SEL_SHIFT) &
+ EVENT_CACHE_SEL_MASK;
ebb = (event >> EVENT_EBB_SHIFT) & EVENT_EBB_MASK;
if (pmc) {
@@ -283,7 +302,10 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
}
if (unit >= 6 && unit <= 9) {
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) {
+ mask |= CNST_L2L3_GROUP_MASK;
+ value |= CNST_L2L3_GROUP_VAL(event >> p10_L2L3_EVENT_SHIFT);
+ } else if (cpu_has_feature(CPU_FTR_ARCH_300)) {
mask |= CNST_CACHE_GROUP_MASK;
value |= CNST_CACHE_GROUP_VAL(event & 0xff);
@@ -367,6 +389,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
struct perf_event *pevents[])
{
unsigned long mmcra, mmcr1, mmcr2, unit, combine, psel, cache, val;
+ unsigned long mmcr3;
unsigned int pmc, pmc_inuse;
int i;
@@ -379,7 +402,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
pmc_inuse |= 1 << pmc;
}
- mmcra = mmcr1 = mmcr2 = 0;
+ mmcra = mmcr1 = mmcr2 = mmcr3 = 0;
/* Second pass: assign PMCs, set all MMCR1 fields */
for (i = 0; i < n_ev; ++i) {
@@ -438,8 +461,17 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcra |= val << MMCRA_THR_CTL_SHIFT;
val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
mmcra |= val << MMCRA_THR_SEL_SHIFT;
- val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
- mmcra |= thresh_cmp_val(val);
+ if (!cpu_has_feature(CPU_FTR_ARCH_31)) {
+ val = (event[i] >> EVENT_THR_CMP_SHIFT) &
+ EVENT_THR_CMP_MASK;
+ mmcra |= thresh_cmp_val(val);
+ }
+ }
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) {
+ val = (event[i] >> p10_L2L3_EVENT_SHIFT) &
+ p10_EVENT_L2L3_SEL_MASK;
+ mmcr2 |= val << p10_L2L3_SEL_SHIFT;
}
if (event[i] & EVENT_WANTS_BHRB) {
@@ -460,6 +492,14 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcr2 |= MMCR2_FCS(pmc);
}
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ if (pmc <= 4) {
+ val = (event[i] >> p10_EVENT_MMCR3_SHIFT) &
+ p10_EVENT_MMCR3_MASK;
+ mmcr3 |= val << MMCR3_SHIFT(pmc);
+ }
+ }
+
hwc[i] = pmc - 1;
}
@@ -480,6 +520,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
mmcr[3] = mmcr2;
+ mmcr[4] = mmcr3;
return 0;
}
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 63fd4f3..85cbce5 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -87,6 +87,31 @@
EVENT_LINUX_MASK | \
EVENT_PSEL_MASK))
+/* Contants to support power10 raw encoding format */
+#define p10_SDAR_MODE_SHIFT 22
+#define p10_SDAR_MODE_MASK 0x3ull
+#define p10_SDAR_MODE(v) (((v) >> p10_SDAR_MODE_SHIFT) & \
+ p10_SDAR_MODE_MASK)
+#define p10_EVENT_L2L3_SEL_MASK 0x1f
+#define p10_L2L3_SEL_SHIFT 3
+#define p10_L2L3_EVENT_SHIFT 40
+#define p10_EVENT_THRESH_MASK 0xffffull
+#define p10_EVENT_CACHE_SEL_MASK 0x3ull
+#define p10_EVENT_MMCR3_MASK 0x7fffull
+#define p10_EVENT_MMCR3_SHIFT 45
+
+#define p10_EVENT_VALID_MASK \
+ ((p10_SDAR_MODE_MASK << p10_SDAR_MODE_SHIFT | \
+ (p10_EVENT_THRESH_MASK << EVENT_THRESH_SHIFT) | \
+ (EVENT_SAMPLE_MASK << EVENT_SAMPLE_SHIFT) | \
+ (p10_EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT) | \
+ (EVENT_PMC_MASK << EVENT_PMC_SHIFT) | \
+ (EVENT_UNIT_MASK << EVENT_UNIT_SHIFT) | \
+ (p9_EVENT_COMBINE_MASK << p9_EVENT_COMBINE_SHIFT) | \
+ (p10_EVENT_MMCR3_MASK << p10_EVENT_MMCR3_SHIFT) | \
+ (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \
+ EVENT_LINUX_MASK | \
+ EVENT_PSEL_MASK))
/*
* Layout of constraint bits:
*
@@ -135,6 +160,9 @@
#define CNST_CACHE_PMC4_VAL (1ull << 54)
#define CNST_CACHE_PMC4_MASK CNST_CACHE_PMC4_VAL
+#define CNST_L2L3_GROUP_VAL(v) (((v) & 0x1full) << 55)
+#define CNST_L2L3_GROUP_MASK CNST_L2L3_GROUP_VAL(0x1f)
+
/*
* For NC we are counting up to 4 events. This requires three bits, and we need
* the fifth event to overflow and set the 4th bit. To achieve that we bias the
@@ -191,7 +219,7 @@
#define MMCRA_THR_CTR_EXP(v) (((v) >> MMCRA_THR_CTR_EXP_SHIFT) &\
MMCRA_THR_CTR_EXP_MASK)
-/* MMCR1 Threshold Compare bit constant for power9 */
+/* MMCRA Threshold Compare bit constant for power9/power10 */
#define p9_MMCRA_THR_CMP_SHIFT 45
/* Bits in MMCR2 for PowerISA v2.07 */
@@ -202,6 +230,9 @@
#define MAX_ALT 2
#define MAX_PMU_COUNTERS 6
+/* Bits in MMCR3 for PowerISA v3.10 */
+#define MMCR3_SHIFT(pmc) (49 - (15 * ((pmc) - 1)))
+
#define ISA207_SIER_TYPE_SHIFT 15
#define ISA207_SIER_TYPE_MASK (0x7ull << ISA207_SIER_TYPE_SHIFT)
diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h
new file mode 100644
index 0000000..60c1b81
--- /dev/null
+++ b/arch/powerpc/perf/power10-events-list.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Performance counter support for POWER10 processors.
+ *
+ * Copyright 2020 Madhavan Srinivasan, IBM Corporation.
+ * Copyright 2020 Athira Rajeev, IBM Corporation.
+ */
+
+/*
+ * Power10 event codes.
+ */
+EVENT(PM_RUN_CYC, 0x600f4);
+EVENT(PM_DISP_STALL_CYC, 0x100f8);
+EVENT(PM_EXEC_STALL, 0x30008);
+EVENT(PM_RUN_INST_CMPL, 0x500fa);
+EVENT(PM_BR_CMPL, 0x4d05e);
+EVENT(PM_BR_MPRED_CMPL, 0x400f6);
+
+/* All L1 D cache load references counted at finish, gated by reject */
+EVENT(PM_LD_REF_L1, 0x100fc);
+/* Load Missed L1 */
+EVENT(PM_LD_MISS_L1, 0x3e054);
+/* Store Missed L1 */
+EVENT(PM_ST_MISS_L1, 0x300f0);
+/* L1 cache data prefetches */
+EVENT(PM_LD_PREFETCH_CACHE_LINE_MISS, 0x1002c);
+/* Demand iCache Miss */
+EVENT(PM_L1_ICACHE_MISS, 0x200fc);
+/* Instruction fetches from L1 */
+EVENT(PM_INST_FROM_L1, 0x04080);
+/* Instruction Demand sectors wriittent into IL1 */
+EVENT(PM_INST_FROM_L1MISS, 0x03f00000001c040);
+/* Instruction prefetch written into IL1 */
+EVENT(PM_IC_PREF_REQ, 0x040a0);
+/* The data cache was reloaded from local core's L3 due to a demand load */
+EVENT(PM_DATA_FROM_L3, 0x01340000001c040);
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+EVENT(PM_DATA_FROM_L3MISS, 0x300fe);
+/* Data PTEG reload */
+EVENT(PM_DTLB_MISS, 0x300fc);
+/* ITLB Reloaded */
+EVENT(PM_ITLB_MISS, 0x400fc);
+
+EVENT(PM_RUN_CYC_ALT, 0x0001e);
+EVENT(PM_RUN_INST_CMPL_ALT, 0x00002);
+
+/*
+ * Memory Access Events
+ *
+ * Primary PMU event used here is PM_MRK_INST_CMPL (0x401e0)
+ * To enable capturing of memory profiling, these MMCRA bits
+ * needs to be programmed and corresponding raw event format
+ * encoding.
+ *
+ * MMCRA bits encoding needed are
+ * SM (Sampling Mode)
+ * EM (Eligibility for Random Sampling)
+ * TECE (Threshold Event Counter Event)
+ * TS (Threshold Start Event)
+ * TE (Threshold End Event)
+ *
+ * Corresponding Raw Encoding bits:
+ * sample [EM,SM]
+ * thresh_sel (TECE)
+ * thresh start (TS)
+ * thresh end (TE)
+ */
+
+EVENT(MEM_LOADS, 0x34340401e0);
+EVENT(MEM_STORES, 0x343c0401e0);
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
new file mode 100644
index 0000000..d64d69d
--- /dev/null
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance counter support for POWER10 processors.
+ *
+ * Copyright 2020 Madhavan Srinivasan, IBM Corporation.
+ * Copyright 2020 Athira Rajeev, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "power10-pmu: " fmt
+
+#include "isa207-common.h"
+
+/*
+ * Raw event encoding for Power10:
+ *
+ * 60 56 52 48 44 40 36 32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ * | | [ ] [ src_match ] [ src_mask ] | [ ] [ l2l3_sel ] [ thresh_ctl ]
+ * | | | | | |
+ * | | *- IFM (Linux) | | thresh start/stop -*
+ * | *- BHRB (Linux) | src_sel
+ * *- EBB (Linux) *invert_bit
+ *
+ * 28 24 20 16 12 8 4 0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ * [ ] [ sample ] [ ] [ ] [ pmc ] [unit ] [ ] m [ pmcxsel ]
+ * | | | | | |
+ * | | | | | *- mark
+ * | | | *- L1/L2/L3 cache_sel |
+ * | | sdar_mode |
+ * | *- sampling mode for marked events *- combine
+ * |
+ * *- thresh_sel
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit (PMCxUNIT)
+ * MMCR1[24] = pmc1combine[0]
+ * MMCR1[25] = pmc1combine[1]
+ * MMCR1[26] = pmc2combine[0]
+ * MMCR1[27] = pmc2combine[1]
+ * MMCR1[28] = pmc3combine[0]
+ * MMCR1[29] = pmc3combine[1]
+ * MMCR1[30] = pmc4combine[0]
+ * MMCR1[31] = pmc4combine[1]
+ *
+ * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011
+ * MMCR1[20:27] = thresh_ctl
+ * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001
+ * MMCR1[20:27] = thresh_ctl
+ * else
+ * MMCRA[48:55] = thresh_ctl (THRESH START/END)
+ *
+ * if thresh_sel:
+ * MMCRA[45:47] = thresh_sel
+ *
+ * if l2l3_sel:
+ * MMCR2[56:60] = l2l3_sel[0:4]
+ *
+ * MMCR1[16] = cache_sel[0]
+ * MMCR1[17] = cache_sel[1]
+ *
+ * if mark:
+ * MMCRA[63] = 1 (SAMPLE_ENABLE)
+ * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG)
+ * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE)
+ *
+ * if EBB and BHRB:
+ * MMCRA[32:33] = IFM
+ *
+ * MMCRA[SDAR_MODE] = sdar_mode[0:1]
+ */
+
+/*
+ * Some power10 event codes.
+ */
+#define EVENT(_name, _code) enum{_name = _code}
+
+#include "power10-events-list.h"
+
+#undef EVENT
+
+/* MMCRA IFM bits - POWER10 */
+#define POWER10_MMCRA_IFM1 0x0000000040000000UL
+#define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL
+
+/* Table of alternatives, sorted by column 0 */
+static const unsigned int power10_event_alternatives[][MAX_ALT] = {
+ { PM_RUN_CYC_ALT, PM_RUN_CYC },
+ { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL },
+};
+
+static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+ int num_alt = 0;
+
+ num_alt = isa207_get_alternatives(event, alt,
+ ARRAY_SIZE(
+ power10_event_alternatives), flags,
+ power10_event_alternatives);
+
+ return num_alt;
+}
+
+GENERIC_EVENT_ATTR(cpu-cycles, PM_RUN_CYC);
+GENERIC_EVENT_ATTR(instructions, PM_RUN_INST_CMPL);
+GENERIC_EVENT_ATTR(branch-instructions, PM_BR_CMPL);
+GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED_CMPL);
+GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1);
+GENERIC_EVENT_ATTR(mem-loads, MEM_LOADS);
+GENERIC_EVENT_ATTR(mem-stores, MEM_STORES);
+
+CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1);
+CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1);
+CACHE_EVENT_ATTR(L1-dcache-prefetches, PM_LD_PREFETCH_CACHE_LINE_MISS);
+CACHE_EVENT_ATTR(L1-dcache-store-misses, PM_ST_MISS_L1);
+CACHE_EVENT_ATTR(L1-icache-load-misses, PM_L1_ICACHE_MISS);
+CACHE_EVENT_ATTR(L1-icache-loads, PM_INST_FROM_L1);
+CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_REQ);
+CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS);
+CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3);
+CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL);
+CACHE_EVENT_ATTR(branch-loads, PM_BR_CMPL);
+CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS);
+CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS);
+
+static struct attribute *power10_events_attr[] = {
+ GENERIC_EVENT_PTR(PM_RUN_CYC),
+ GENERIC_EVENT_PTR(PM_RUN_INST_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
+ GENERIC_EVENT_PTR(PM_LD_REF_L1),
+ GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+ GENERIC_EVENT_PTR(MEM_LOADS),
+ GENERIC_EVENT_PTR(MEM_STORES),
+ CACHE_EVENT_PTR(PM_LD_MISS_L1),
+ CACHE_EVENT_PTR(PM_LD_REF_L1),
+ CACHE_EVENT_PTR(PM_LD_PREFETCH_CACHE_LINE_MISS),
+ CACHE_EVENT_PTR(PM_ST_MISS_L1),
+ CACHE_EVENT_PTR(PM_L1_ICACHE_MISS),
+ CACHE_EVENT_PTR(PM_INST_FROM_L1),
+ CACHE_EVENT_PTR(PM_IC_PREF_REQ),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3),
+ CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
+ CACHE_EVENT_PTR(PM_BR_CMPL),
+ CACHE_EVENT_PTR(PM_DTLB_MISS),
+ CACHE_EVENT_PTR(PM_ITLB_MISS),
+ NULL
+};
+
+static struct attribute_group power10_pmu_events_group = {
+ .name = "events",
+ .attrs = power10_events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-59");
+PMU_FORMAT_ATTR(pmcxsel, "config:0-7");
+PMU_FORMAT_ATTR(mark, "config:8");
+PMU_FORMAT_ATTR(combine, "config:10-11");
+PMU_FORMAT_ATTR(unit, "config:12-15");
+PMU_FORMAT_ATTR(pmc, "config:16-19");
+PMU_FORMAT_ATTR(cache_sel, "config:20-21");
+PMU_FORMAT_ATTR(sdar_mode, "config:22-23");
+PMU_FORMAT_ATTR(sample_mode, "config:24-28");
+PMU_FORMAT_ATTR(thresh_sel, "config:29-31");
+PMU_FORMAT_ATTR(thresh_stop, "config:32-35");
+PMU_FORMAT_ATTR(thresh_start, "config:36-39");
+PMU_FORMAT_ATTR(l2l3_sel, "config:40-44");
+PMU_FORMAT_ATTR(src_sel, "config:45-46");
+PMU_FORMAT_ATTR(invert_bit, "config:47");
+PMU_FORMAT_ATTR(src_mask, "config:48-53");
+PMU_FORMAT_ATTR(src_match, "config:54-59");
+
+static struct attribute *power10_pmu_format_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_pmcxsel.attr,
+ &format_attr_mark.attr,
+ &format_attr_combine.attr,
+ &format_attr_unit.attr,
+ &format_attr_pmc.attr,
+ &format_attr_cache_sel.attr,
+ &format_attr_sdar_mode.attr,
+ &format_attr_sample_mode.attr,
+ &format_attr_thresh_sel.attr,
+ &format_attr_thresh_stop.attr,
+ &format_attr_thresh_start.attr,
+ &format_attr_l2l3_sel.attr,
+ &format_attr_src_sel.attr,
+ &format_attr_invert_bit.attr,
+ &format_attr_src_mask.attr,
+ &format_attr_src_match.attr,
+ NULL,
+};
+
+static struct attribute_group power10_pmu_format_group = {
+ .name = "format",
+ .attrs = power10_pmu_format_attr,
+};
+
+static const struct attribute_group *power10_pmu_attr_groups[] = {
+ &power10_pmu_format_group,
+ &power10_pmu_events_group,
+ NULL,
+};
+
+static int power10_generic_events[] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC,
+ [PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL,
+ [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1,
+ [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1,
+};
+
+static u64 power10_bhrb_filter_map(u64 branch_sample_type)
+{
+ u64 pmu_bhrb_filter = 0;
+
+ /* BHRB and regular PMU events share the same privilege state
+ * filter configuration. BHRB is always recorded along with a
+ * regular PMU event. As the privilege state filter is handled
+ * in the basic PMC configuration of the accompanying regular
+ * PMU event, we ignore any separate BHRB specific request.
+ */
+
+ /* No branch filter requested */
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY)
+ return pmu_bhrb_filter;
+
+ /* Invalid branch filter options - HW does not support */
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+ return -1;
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL)
+ return -1;
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL)
+ return -1;
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
+ pmu_bhrb_filter |= POWER10_MMCRA_IFM1;
+ return pmu_bhrb_filter;
+ }
+
+ /* Every thing else is unsupported */
+ return -1;
+}
+
+static void power10_config_bhrb(u64 pmu_bhrb_filter)
+{
+ pmu_bhrb_filter &= POWER10_MMCRA_BHRB_MASK;
+
+ /* Enable BHRB filter in PMU */
+ mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
+}
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_LD_REF_L1,
+ [C(RESULT_MISS)] = PM_LD_MISS_L1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ST_MISS_L1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_LD_PREFETCH_CACHE_LINE_MISS,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1,
+ [C(RESULT_MISS)] = PM_L1_ICACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1MISS,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_IC_PREF_REQ,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_DATA_FROM_L3,
+ [C(RESULT_MISS)] = PM_DATA_FROM_L3MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_DTLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_BR_CMPL,
+ [C(RESULT_MISS)] = PM_BR_MPRED_CMPL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+};
+
+#undef C
+
+static struct power_pmu power10_pmu = {
+ .name = "POWER10",
+ .n_counter = MAX_PMU_COUNTERS,
+ .add_fields = ISA207_ADD_FIELDS,
+ .test_adder = ISA207_TEST_ADDER,
+ .group_constraint_mask = CNST_CACHE_PMC4_MASK,
+ .group_constraint_val = CNST_CACHE_PMC4_VAL,
+ .compute_mmcr = isa207_compute_mmcr,
+ .config_bhrb = power10_config_bhrb,
+ .bhrb_filter_map = power10_bhrb_filter_map,
+ .get_constraint = isa207_get_constraint,
+ .get_alternatives = power10_get_alternatives,
+ .get_mem_data_src = isa207_get_mem_data_src,
+ .get_mem_weight = isa207_get_mem_weight,
+ .disable_pmc = isa207_disable_pmc,
+ .flags = PPMU_HAS_SIER | PPMU_ARCH_207S |
+ PPMU_ARCH_310S,
+ .n_generic = ARRAY_SIZE(power10_generic_events),
+ .generic_events = power10_generic_events,
+ .cache_events = &power10_cache_events,
+ .attr_groups = power10_pmu_attr_groups,
+ .bhrb_nr = 32,
+};
+
+int init_power10_pmu(void)
+{
+ int rc;
+
+ /* Comes from cpu_specs[] */
+ if (!cur_cpu_spec->oprofile_cpu_type ||
+ strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10"))
+ return -ENODEV;
+
+ rc = register_power_pmu(&power10_pmu);
+ if (rc)
+ return rc;
+
+ /* Tell userspace that EBB is supported */
+ cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+
+ return 0;
+}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 04/10] powerpc/perf: Add power10_feat to dt_cpu_ftrs
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
From: Madhavan Srinivasan <maddy@linux.ibm.com>
Add power10 feature function to dt_cpu_ftrs.c along
with a power10 specific init() to initialize pmu sprs.
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
---
arch/powerpc/include/asm/reg.h | 3 +++
arch/powerpc/kernel/cpu_setup_power.S | 7 +++++++
arch/powerpc/kernel/dt_cpu_ftrs.c | 26 ++++++++++++++++++++++++++
3 files changed, 36 insertions(+)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 21a1b2d..900ada1 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1068,6 +1068,9 @@
#define MMCR0_PMC2_LOADMISSTIME 0x5
#endif
+/* BHRB disable bit for PowerISA v3.10 */
+#define MMCRA_BHRB_DISABLE 0x0000002000000000
+
/*
* SPRG usage:
*
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index efdcfa7..e8b3370c 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -233,3 +233,10 @@ __init_PMU_ISA207:
li r5,0
mtspr SPRN_MMCRS,r5
blr
+
+__init_PMU_ISA31:
+ li r5,0
+ mtspr SPRN_MMCR3,r5
+ LOAD_REG_IMMEDIATE(r5, MMCRA_BHRB_DISABLE)
+ mtspr SPRN_MMCRA,r5
+ blr
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index a0edeb3..14a513f 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -449,6 +449,31 @@ static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f)
return 1;
}
+static void init_pmu_power10(void)
+{
+ init_pmu_power9();
+
+ mtspr(SPRN_MMCR3, 0);
+ mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+}
+
+static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)
+{
+ hfscr_pmu_enable();
+
+ init_pmu_power10();
+ init_pmu_registers = init_pmu_power10;
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+ cur_cpu_spec->num_pmcs = 6;
+ cur_cpu_spec->pmc_type = PPC_PMC_IBM;
+ cur_cpu_spec->oprofile_cpu_type = "ppc64/power10";
+
+ return 1;
+}
+
static int __init feat_enable_tm(struct dt_cpu_feature *f)
{
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -638,6 +663,7 @@ struct dt_cpu_feature_match {
{"pc-relative-addressing", feat_enable, 0},
{"machine-check-power9", feat_enable_mce_power9, 0},
{"performance-monitor-power9", feat_enable_pmu_power9, 0},
+ {"performance-monitor-power10", feat_enable_pmu_power10, 0},
{"event-based-branch-v3", feat_enable, 0},
{"random-number-generator", feat_enable, 0},
{"system-call-vectored", feat_disable, 0},
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 03/10] powerpc/xmon: Add PowerISA v3.1 PMU SPRs
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
From: Madhavan Srinivasan <maddy@linux.ibm.com>
PowerISA v3.1 added three new perfromance
monitoring unit (PMU) speical purpose register (SPR).
They are Monitor Mode Control Register 3 (MMCR3),
Sampled Instruction Event Register 2 (SIER2),
Sampled Instruction Event Register 3 (SIER3).
Patch here adds a new dump function dump_310_sprs
to print these SPR values.
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
---
arch/powerpc/xmon/xmon.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 7efe4bc..8917fe8 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2022,6 +2022,20 @@ static void dump_300_sprs(void)
#endif
}
+static void dump_310_sprs(void)
+{
+#ifdef CONFIG_PPC64
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return;
+
+ printf("mmcr3 = %.16lx\n",
+ mfspr(SPRN_MMCR3));
+
+ printf("sier2 = %.16lx sier3 = %.16lx\n",
+ mfspr(SPRN_SIER2), mfspr(SPRN_SIER3));
+#endif
+}
+
static void dump_one_spr(int spr, bool show_unimplemented)
{
unsigned long val;
@@ -2076,6 +2090,7 @@ static void super_regs(void)
dump_206_sprs();
dump_207_sprs();
dump_300_sprs();
+ dump_310_sprs();
return;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 02/10] KVM: PPC: Book3S HV: Save/restore new PMU registers
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
PowerISA v3.1 has added new performance monitoring unit (PMU)
special purpose registers (SPRs). They are
Monitor Mode Control Register 3 (MMCR3)
Sampled Instruction Event Register A (SIER2)
Sampled Instruction Event Register B (SIER3)
Patch addes support to save/restore these new
SPRs while entering/exiting guest.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/kvm_book3s_asm.h | 2 +-
arch/powerpc/include/asm/kvm_host.h | 4 ++--
arch/powerpc/kernel/asm-offsets.c | 3 +++
arch/powerpc/kvm/book3s_hv.c | 6 ++++--
arch/powerpc/kvm/book3s_hv_interrupts.S | 8 ++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 24 ++++++++++++++++++++++++
6 files changed, 42 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 45704f2..078f464 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -119,7 +119,7 @@ struct kvmppc_host_state {
void __iomem *xive_tima_virt;
u32 saved_xirr;
u64 dabr;
- u64 host_mmcr[7]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER */
+ u64 host_mmcr[10]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER, MMCR3, SIER2/3 */
u32 host_pmc[8];
u64 host_purr;
u64 host_spurr;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7e2d061..d718061 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -637,12 +637,12 @@ struct kvm_vcpu_arch {
u32 ccr1;
u32 dbsr;
- u64 mmcr[5];
+ u64 mmcr[6];
u32 pmc[8];
u32 spmc[2];
u64 siar;
u64 sdar;
- u64 sier;
+ u64 sier[3];
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
u64 tfhar;
u64 texasr;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6657dc6..20a8b1e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -696,6 +696,9 @@ int main(void)
HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]);
HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]);
HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]);
+ HSTATE_FIELD(HSTATE_MMCR3, host_mmcr[7]);
+ HSTATE_FIELD(HSTATE_SIER2, host_mmcr[8]);
+ HSTATE_FIELD(HSTATE_SIER3, host_mmcr[9]);
HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]);
HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]);
HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6bf66649..c265800 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1698,7 +1698,8 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
*val = get_reg_val(id, vcpu->arch.sdar);
break;
case KVM_REG_PPC_SIER:
- *val = get_reg_val(id, vcpu->arch.sier);
+ i = id - KVM_REG_PPC_SIER;
+ *val = get_reg_val(id, vcpu->arch.sier[i]);
break;
case KVM_REG_PPC_IAMR:
*val = get_reg_val(id, vcpu->arch.iamr);
@@ -1919,7 +1920,8 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
vcpu->arch.sdar = set_reg_val(id, *val);
break;
case KVM_REG_PPC_SIER:
- vcpu->arch.sier = set_reg_val(id, *val);
+ i = id - KVM_REG_PPC_SIER;
+ vcpu->arch.sier[i] = set_reg_val(id, *val);
break;
case KVM_REG_PPC_IAMR:
vcpu->arch.iamr = set_reg_val(id, *val);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 63fd81f..59822cb 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -140,6 +140,14 @@ BEGIN_FTR_SECTION
std r8, HSTATE_MMCR2(r13)
std r9, HSTATE_SIER(r13)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
+ mfspr r5, SPRN_MMCR3
+ mfspr r6, SPRN_SIER2
+ mfspr r7, SPRN_SIER3
+ std r5, HSTATE_MMCR3(r13)
+ std r6, HSTATE_SIER2(r13)
+ std r7, HSTATE_SIER3(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
mfspr r3, SPRN_PMC1
mfspr r5, SPRN_PMC2
mfspr r6, SPRN_PMC3
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7194389..57b6c14 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -3436,6 +3436,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
mtspr SPRN_SIAR, r7
mtspr SPRN_SDAR, r8
BEGIN_FTR_SECTION
+ ld r5, VCPU_MMCR + 40(r4)
+ ld r6, VCPU_SIER + 8(r4)
+ ld r7, VCPU_SIER + 16(r4)
+ mtspr SPRN_MMCR3, r5
+ mtspr SPRN_SIER2, r6
+ mtspr SPRN_SIER3, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
+BEGIN_FTR_SECTION
ld r5, VCPU_MMCR + 24(r4)
ld r6, VCPU_SIER(r4)
mtspr SPRN_MMCR2, r5
@@ -3496,6 +3504,14 @@ BEGIN_FTR_SECTION
mtspr SPRN_MMCR2, r8
mtspr SPRN_SIER, r9
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
+ ld r5, HSTATE_MMCR3(r13)
+ ld r6, HSTATE_SIER2(r13)
+ ld r7, HSTATE_SIER3(r13)
+ mtspr SPRN_MMCR3, r5
+ mtspr SPRN_SIER2, r6
+ mtspr SPRN_SIER3, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
mtspr SPRN_MMCR0, r3
isync
mtlr r0
@@ -3555,6 +3571,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
BEGIN_FTR_SECTION
std r10, VCPU_MMCR + 24(r9)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
+ mfspr r5, SPRN_MMCR3
+ mfspr r6, SPRN_SIER2
+ mfspr r7, SPRN_SIER3
+ std r5, VCPU_MMCR + 40(r9)
+ std r6, VCPU_SIER + 8(r9)
+ std r7, VCPU_SIER + 16(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
std r7, VCPU_SIAR(r9)
std r8, VCPU_SDAR(r9)
mfspr r3, SPRN_PMC1
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 01/10] powerpc/perf: Add support for ISA3.1 PMU SPRs
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
In-Reply-To: <1593595262-1433-1-git-send-email-atrajeev@linux.vnet.ibm.com>
From: Madhavan Srinivasan <maddy@linux.ibm.com>
PowerISA v3.1 includes new performance monitoring unit(PMU)
special purpose registers (SPRs). They are
Monitor Mode Control Register 3 (MMCR3)
Sampled Instruction Event Register 2 (SIER2)
Sampled Instruction Event Register 3 (SIER3)
MMCR3 is added for further sampling related configuration
control. SIER2/SIER3 are added to provide additional
information about the sampled instruction.
Patch adds new PPMU flag called "PPMU_ARCH_310S" to support
handling of these new SPRs, updates the struct thread_struct
to include these new SPRs, increase the size of mmcr[] array
by one to include MMCR3 in struct cpu_hw_event. This is needed
to support programming of MMCR3 SPR during event_[enable/disable].
Patch also adds the sysfs support for the MMCR3 SPR along with
SPRN_ macros for these new pmu sprs.
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
---
arch/powerpc/include/asm/perf_event_server.h | 1 +
arch/powerpc/include/asm/processor.h | 4 ++++
arch/powerpc/include/asm/reg.h | 6 ++++++
arch/powerpc/kernel/sysfs.c | 8 ++++++++
arch/powerpc/perf/core-book3s.c | 29 ++++++++++++++++++++++++++--
5 files changed, 46 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 3e9703f..895aeaa 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -69,6 +69,7 @@ struct power_pmu {
#define PPMU_HAS_SIER 0x00000040 /* Has SIER */
#define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */
#define PPMU_NO_SIAR 0x00000100 /* Do not use SIAR */
+#define PPMU_ARCH_310S 0x00000200 /* Has MMCR3, SIER2 and SIER3 */
/*
* Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 52a6783..a466e94 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -272,6 +272,10 @@ struct thread_struct {
unsigned mmcr0;
unsigned used_ebb;
+ unsigned long mmcr3;
+ unsigned long sier2;
+ unsigned long sier3;
+
#endif
};
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 88e6c78..21a1b2d 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -876,7 +876,9 @@
#define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */
#define SPRN_MMCR1 798
#define SPRN_MMCR2 785
+#define SPRN_MMCR3 754
#define SPRN_UMMCR2 769
+#define SPRN_UMMCR3 738
#define SPRN_MMCRA 0x312
#define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */
#define MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -918,6 +920,10 @@
#define SIER_SIHV 0x1000000 /* Sampled MSR_HV */
#define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */
#define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */
+#define SPRN_SIER2 752
+#define SPRN_SIER3 753
+#define SPRN_USIER2 736
+#define SPRN_USIER3 737
#define SPRN_SIAR 796
#define SPRN_SDAR 797
#define SPRN_TACR 888
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 571b325..46b4ebc 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -622,8 +622,10 @@ void ppc_enable_pmcs(void)
SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+SYSFS_PMCSETUP(mmcr3, SPRN_MMCR3);
static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
+static DEVICE_ATTR(mmcr3, 0600, show_mmcr3, store_mmcr3);
#endif /* HAS_PPC_PMC56 */
@@ -886,6 +888,9 @@ static int register_cpu_online(unsigned int cpu)
#ifdef CONFIG_PMU_SYSFS
if (cpu_has_feature(CPU_FTR_MMCRA))
device_create_file(s, &dev_attr_mmcra);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_create_file(s, &dev_attr_mmcr3);
#endif /* CONFIG_PMU_SYSFS */
if (cpu_has_feature(CPU_FTR_PURR)) {
@@ -980,6 +985,9 @@ static int unregister_cpu_online(unsigned int cpu)
#ifdef CONFIG_PMU_SYSFS
if (cpu_has_feature(CPU_FTR_MMCRA))
device_remove_file(s, &dev_attr_mmcra);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_remove_file(s, &dev_attr_mmcr3);
#endif /* CONFIG_PMU_SYSFS */
if (cpu_has_feature(CPU_FTR_PURR)) {
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index cd6a742..5c64bd3 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -39,10 +39,10 @@ struct cpu_hw_events {
unsigned int flags[MAX_HWEVENTS];
/*
* The order of the MMCR array is:
- * - 64-bit, MMCR0, MMCR1, MMCRA, MMCR2
+ * - 64-bit, MMCR0, MMCR1, MMCRA, MMCR2, MMCR3
* - 32-bit, MMCR0, MMCR1, MMCR2
*/
- unsigned long mmcr[4];
+ unsigned long mmcr[5];
struct perf_event *limited_counter[MAX_LIMITED_HWCOUNTERS];
u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS];
u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
@@ -586,6 +586,11 @@ static void ebb_switch_out(unsigned long mmcr0)
current->thread.sdar = mfspr(SPRN_SDAR);
current->thread.mmcr0 = mmcr0 & MMCR0_USER_MASK;
current->thread.mmcr2 = mfspr(SPRN_MMCR2) & MMCR2_USER_MASK;
+ if (ppmu->flags & PPMU_ARCH_310S) {
+ current->thread.mmcr3 = mfspr(SPRN_MMCR3);
+ current->thread.sier2 = mfspr(SPRN_SIER2);
+ current->thread.sier3 = mfspr(SPRN_SIER3);
+ }
}
static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
@@ -625,6 +630,12 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
* instead manage the MMCR2 entirely by itself.
*/
mtspr(SPRN_MMCR2, cpuhw->mmcr[3] | current->thread.mmcr2);
+
+ if (ppmu->flags & PPMU_ARCH_310S) {
+ mtspr(SPRN_MMCR3, current->thread.mmcr3);
+ mtspr(SPRN_SIER2, current->thread.sier2);
+ mtspr(SPRN_SIER3, current->thread.sier3);
+ }
out:
return mmcr0;
}
@@ -845,6 +856,11 @@ void perf_event_print_debug(void)
pr_info("EBBRR: %016lx BESCR: %016lx\n",
mfspr(SPRN_EBBRR), mfspr(SPRN_BESCR));
}
+
+ if (ppmu->flags & PPMU_ARCH_310S) {
+ pr_info("MMCR3: %016lx SIER2: %016lx SIER3: %016lx\n",
+ mfspr(SPRN_MMCR3), mfspr(SPRN_SIER2), mfspr(SPRN_SIER3));
+ }
#endif
pr_info("SIAR: %016lx SDAR: %016lx SIER: %016lx\n",
mfspr(SPRN_SIAR), sdar, sier);
@@ -1310,6 +1326,10 @@ static void power_pmu_enable(struct pmu *pmu)
if (!cpuhw->n_added) {
mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
+#ifdef CONFIG_PPC64
+ if (ppmu->flags & PPMU_ARCH_310S)
+ mtspr(SPRN_MMCR3, cpuhw->mmcr[4]);
+#endif /* CONFIG_PPC64 */
goto out_enable;
}
@@ -1353,6 +1373,11 @@ static void power_pmu_enable(struct pmu *pmu)
if (ppmu->flags & PPMU_ARCH_207S)
mtspr(SPRN_MMCR2, cpuhw->mmcr[3]);
+#ifdef CONFIG_PPC64
+ if (ppmu->flags & PPMU_ARCH_310S)
+ mtspr(SPRN_MMCR3, cpuhw->mmcr[4]);
+#endif /* CONFIG_PPC64 */
+
/*
* Read off any pre-existing events that need to move
* to another PMC.
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 00/10] powerpc/perf: Add support for power10 PMU Hardware
From: Athira Rajeev @ 2020-07-01 9:20 UTC (permalink / raw)
To: mpe; +Cc: mikey, maddy, linuxppc-dev
The patch series adds support for power10 PMU hardware.
Anju T Sudhakar (2):
powerpc/perf: Add support for outputting extended regs in perf
intr_regs
tools/perf: Add perf tools support for extended register capability in
powerpc
Athira Rajeev (5):
KVM: PPC: Book3S HV: Save/restore new PMU registers
powerpc/perf: Update Power PMU cache_events to u64 type
powerpc/perf: power10 Performance Monitoring support
powerpc/perf: support BHRB disable bit and new filtering modes
powerpc/perf: Add extended regs support for power10 platform
Madhavan Srinivasan (3):
powerpc/perf: Add support for ISA3.1 PMU SPRs
powerpc/xmon: Add PowerISA v3.1 PMU SPRs
powerpc/perf: Add power10_feat to dt_cpu_ftrs
---
Changes from v1 -> v2
- Added support for extended regs in powerpc
for power9/power10 platform ( patches 8, 9, 10)
- Addressed change/removal of some event codes
in the PMU driver
---
arch/powerpc/include/asm/kvm_book3s_asm.h | 2 +-
arch/powerpc/include/asm/kvm_host.h | 4 +-
arch/powerpc/include/asm/perf_event_server.h | 11 +-
arch/powerpc/include/asm/processor.h | 4 +
arch/powerpc/include/asm/reg.h | 9 +
arch/powerpc/include/uapi/asm/perf_regs.h | 20 +-
arch/powerpc/kernel/asm-offsets.c | 3 +
arch/powerpc/kernel/cpu_setup_power.S | 7 +
arch/powerpc/kernel/dt_cpu_ftrs.c | 26 ++
arch/powerpc/kernel/sysfs.c | 8 +
arch/powerpc/kvm/book3s_hv.c | 6 +-
arch/powerpc/kvm/book3s_hv_interrupts.S | 8 +
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 24 ++
arch/powerpc/perf/Makefile | 2 +-
arch/powerpc/perf/core-book3s.c | 61 +++-
arch/powerpc/perf/generic-compat-pmu.c | 2 +-
arch/powerpc/perf/internal.h | 1 +
arch/powerpc/perf/isa207-common.c | 72 +++-
arch/powerpc/perf/isa207-common.h | 33 +-
arch/powerpc/perf/mpc7450-pmu.c | 2 +-
arch/powerpc/perf/perf_regs.c | 42 ++-
arch/powerpc/perf/power10-events-list.h | 70 ++++
arch/powerpc/perf/power10-pmu.c | 425 ++++++++++++++++++++++++
arch/powerpc/perf/power5+-pmu.c | 2 +-
arch/powerpc/perf/power5-pmu.c | 2 +-
arch/powerpc/perf/power6-pmu.c | 2 +-
arch/powerpc/perf/power7-pmu.c | 2 +-
arch/powerpc/perf/power8-pmu.c | 2 +-
arch/powerpc/perf/power9-pmu.c | 8 +-
arch/powerpc/perf/ppc970-pmu.c | 2 +-
arch/powerpc/platforms/powernv/idle.c | 14 +
arch/powerpc/xmon/xmon.c | 15 +
tools/arch/powerpc/include/uapi/asm/perf_regs.h | 20 +-
tools/perf/arch/powerpc/include/perf_regs.h | 8 +-
tools/perf/arch/powerpc/util/perf_regs.c | 61 ++++
35 files changed, 939 insertions(+), 41 deletions(-)
create mode 100644 arch/powerpc/perf/power10-events-list.h
create mode 100644 arch/powerpc/perf/power10-pmu.c
--
1.8.3.1
^ permalink raw reply
* [PATCH 20/20] block: remove direct_make_request
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
Now that submit_bio_noacct has a decent blk-mq fast path there is no
more need for this bypass.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-core.c | 28 ----------------------------
drivers/md/dm.c | 5 +----
drivers/nvme/host/multipath.c | 2 +-
include/linux/blkdev.h | 1 -
4 files changed, 2 insertions(+), 34 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 2ff166f0d24ee3..bf882b8d84450c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1211,34 +1211,6 @@ blk_qc_t submit_bio_noacct(struct bio *bio)
}
EXPORT_SYMBOL(submit_bio_noacct);
-/**
- * direct_make_request - hand a buffer directly to its device driver for I/O
- * @bio: The bio describing the location in memory and on the device.
- *
- * This function behaves like submit_bio_noacct(), but does not protect
- * against recursion. Must only be used if the called driver is known
- * to be blk-mq based.
- */
-blk_qc_t direct_make_request(struct bio *bio)
-{
- struct gendisk *disk = bio->bi_disk;
-
- if (WARN_ON_ONCE(!disk->queue->mq_ops)) {
- bio_io_error(bio);
- return BLK_QC_T_NONE;
- }
- if (!submit_bio_checks(bio))
- return BLK_QC_T_NONE;
- if (unlikely(bio_queue_enter(bio)))
- return BLK_QC_T_NONE;
- if (!blk_crypto_bio_prep(&bio)) {
- blk_queue_exit(disk->queue);
- return BLK_QC_T_NONE;
- }
- return blk_mq_submit_bio(bio);
-}
-EXPORT_SYMBOL_GPL(direct_make_request);
-
/**
* submit_bio - submit a bio to the block device layer for I/O
* @bio: The &struct bio which describes the I/O
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b32b539dbace56..2cb33896198c4c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1302,10 +1302,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
/* the bio has been remapped so dispatch it */
trace_block_bio_remap(clone->bi_disk->queue, clone,
bio_dev(io->orig_bio), sector);
- if (md->type == DM_TYPE_NVME_BIO_BASED)
- ret = direct_make_request(clone);
- else
- ret = submit_bio_noacct(clone);
+ ret = submit_bio_noacct(clone);
break;
case DM_MAPIO_KILL:
free_tio(tio);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index f07fa47c251d9d..a986ac52c4cc7f 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -314,7 +314,7 @@ blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
trace_block_bio_remap(bio->bi_disk->queue, bio,
disk_devt(ns->head->disk),
bio->bi_iter.bi_sector);
- ret = direct_make_request(bio);
+ ret = submit_bio_noacct(bio);
} else if (nvme_available_path(head)) {
dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b73cfa6a5141df..1cc913ffdbe21e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -853,7 +853,6 @@ static inline void rq_flush_dcache_pages(struct request *rq)
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
blk_qc_t submit_bio_noacct(struct bio *bio);
-extern blk_qc_t direct_make_request(struct bio *bio);
extern void blk_rq_init(struct request_queue *q, struct request *rq);
extern void blk_put_request(struct request *);
extern struct request *blk_get_request(struct request_queue *, unsigned int op,
--
2.26.2
^ permalink raw reply related
* [PATCH 19/20] block: shortcut __submit_bio_noacct for blk-mq drivers
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
For blk-mq drivers bios can only be inserted for the same queue. So
bypass the complicated sorting logic in __submit_bio_noacct with
a blk-mq simpler submission helper.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-core.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/block/blk-core.c b/block/blk-core.c
index 57b5dc00d44cb1..2ff166f0d24ee3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1152,6 +1152,34 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
return ret;
}
+static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
+{
+ struct gendisk *disk = bio->bi_disk;
+ struct bio_list bio_list;
+ blk_qc_t ret = BLK_QC_T_NONE;
+
+ bio_list_init(&bio_list);
+ current->bio_list = &bio_list;
+
+ do {
+ WARN_ON_ONCE(bio->bi_disk != disk);
+
+ if (unlikely(bio_queue_enter(bio) != 0))
+ continue;
+
+ if (!blk_crypto_bio_prep(&bio)) {
+ blk_queue_exit(disk->queue);
+ ret = BLK_QC_T_NONE;
+ continue;
+ }
+
+ ret = blk_mq_submit_bio(bio);
+ } while ((bio = bio_list_pop(&bio_list)));
+
+ current->bio_list = NULL;
+ return ret;
+}
+
/**
* submit_bio_noacct - re-submit a bio to the block device layer for I/O
* @bio: The bio describing the location in memory and on the device.
@@ -1177,6 +1205,8 @@ blk_qc_t submit_bio_noacct(struct bio *bio)
return BLK_QC_T_NONE;
}
+ if (!bio->bi_disk->fops->submit_bio)
+ return __submit_bio_noacct_mq(bio);
return __submit_bio_noacct(bio);
}
EXPORT_SYMBOL(submit_bio_noacct);
--
2.26.2
^ permalink raw reply related
* [PATCH 17/20] block: rename generic_make_request to submit_bio_noacct
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
generic_make_request has always been very confusingly misnamed, so rename
it to submit_bio_noacct to make it clear that it is submit_bio minus
accounting and a few checks.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
Documentation/block/biodoc.rst | 2 +-
.../fault-injection/fault-injection.rst | 2 +-
Documentation/trace/ftrace.rst | 4 +--
block/bio.c | 14 ++++----
block/blk-core.c | 32 +++++++++----------
block/blk-crypto-fallback.c | 2 +-
block/blk-crypto.c | 2 +-
block/blk-merge.c | 2 +-
block/blk-throttle.c | 4 +--
block/bounce.c | 2 +-
drivers/block/drbd/drbd_int.h | 6 ++--
drivers/block/drbd/drbd_main.c | 2 +-
drivers/block/drbd/drbd_receiver.c | 2 +-
drivers/block/drbd/drbd_req.c | 2 +-
drivers/block/drbd/drbd_worker.c | 2 +-
drivers/block/pktcdvd.c | 2 +-
drivers/lightnvm/pblk-read.c | 2 +-
drivers/md/bcache/bcache.h | 2 +-
drivers/md/bcache/btree.c | 2 +-
drivers/md/bcache/request.c | 7 ++--
drivers/md/dm-cache-target.c | 6 ++--
drivers/md/dm-clone-target.c | 10 +++---
drivers/md/dm-crypt.c | 6 ++--
drivers/md/dm-delay.c | 2 +-
drivers/md/dm-era-target.c | 2 +-
drivers/md/dm-integrity.c | 4 +--
drivers/md/dm-mpath.c | 2 +-
drivers/md/dm-raid1.c | 2 +-
drivers/md/dm-snap-persistent.c | 2 +-
drivers/md/dm-snap.c | 6 ++--
drivers/md/dm-thin.c | 4 +--
drivers/md/dm-verity-target.c | 2 +-
drivers/md/dm-writecache.c | 2 +-
drivers/md/dm-zoned-target.c | 2 +-
drivers/md/dm.c | 10 +++---
drivers/md/md-faulty.c | 4 +--
drivers/md/md-linear.c | 4 +--
drivers/md/md-multipath.c | 4 +--
drivers/md/raid0.c | 8 ++---
drivers/md/raid1.c | 14 ++++----
drivers/md/raid10.c | 28 ++++++++--------
drivers/md/raid5.c | 10 +++---
drivers/nvme/host/multipath.c | 2 +-
include/linux/blkdev.h | 2 +-
44 files changed, 115 insertions(+), 118 deletions(-)
diff --git a/Documentation/block/biodoc.rst b/Documentation/block/biodoc.rst
index 267384159bf793..afda5e30a82e5a 100644
--- a/Documentation/block/biodoc.rst
+++ b/Documentation/block/biodoc.rst
@@ -1036,7 +1036,7 @@ Now the generic block layer performs partition-remapping early and thus
provides drivers with a sector number relative to whole device, rather than
having to take partition number into account in order to arrive at the true
sector number. The routine blk_partition_remap() is invoked by
-generic_make_request even before invoking the queue specific ->submit_bio,
+submit_bio_noacct even before invoking the queue specific ->submit_bio,
so the i/o scheduler also gets to operate on whole disk sector numbers. This
should typically not require changes to block drivers, it just never gets
to invoke its own partition sector offset calculations since all bios
diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst
index f51bb21d20e44b..f850ad018b70a8 100644
--- a/Documentation/fault-injection/fault-injection.rst
+++ b/Documentation/fault-injection/fault-injection.rst
@@ -24,7 +24,7 @@ Available fault injection capabilities
injects disk IO errors on devices permitted by setting
/sys/block/<device>/make-it-fail or
- /sys/block/<device>/<partition>/make-it-fail. (generic_make_request())
+ /sys/block/<device>/<partition>/make-it-fail. (submit_bio_noacct())
- fail_mmc_request
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 430a16283103d4..80ba765a82379e 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -1453,7 +1453,7 @@ function-trace, we get a much larger output::
=> __blk_run_queue_uncond
=> __blk_run_queue
=> blk_queue_bio
- => generic_make_request
+ => submit_bio_noacct
=> submit_bio
=> submit_bh
=> __ext3_get_inode_loc
@@ -1738,7 +1738,7 @@ tracers.
=> __blk_run_queue_uncond
=> __blk_run_queue
=> blk_queue_bio
- => generic_make_request
+ => submit_bio_noacct
=> submit_bio
=> submit_bh
=> ext3_bread
diff --git a/block/bio.c b/block/bio.c
index fc1299f9d86a24..ef91782fd668ce 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -358,7 +358,7 @@ static void bio_alloc_rescue(struct work_struct *work)
if (!bio)
break;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
@@ -416,19 +416,19 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
* submit the previously allocated bio for IO before attempting to allocate
* a new one. Failure to do so can cause deadlocks under memory pressure.
*
- * Note that when running under generic_make_request() (i.e. any block
+ * Note that when running under submit_bio_noacct() (i.e. any block
* driver), bios are not submitted until after you return - see the code in
- * generic_make_request() that converts recursion into iteration, to prevent
+ * submit_bio_noacct() that converts recursion into iteration, to prevent
* stack overflows.
*
* This would normally mean allocating multiple bios under
- * generic_make_request() would be susceptible to deadlocks, but we have
+ * submit_bio_noacct() would be susceptible to deadlocks, but we have
* deadlock avoidance code that resubmits any blocked bios from a rescuer
* thread.
*
* However, we do not guarantee forward progress for allocations from other
* mempools. Doing multiple allocations from the same mempool under
- * generic_make_request() should be avoided - instead, use bio_set's front_pad
+ * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
* for per bio allocations.
*
* RETURNS:
@@ -457,14 +457,14 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
nr_iovecs > 0))
return NULL;
/*
- * generic_make_request() converts recursion to iteration; this
+ * submit_bio_noacct() converts recursion to iteration; this
* means if we're running beneath it, any bios we allocate and
* submit will not be submitted (and thus freed) until after we
* return.
*
* This exposes us to a potential deadlock if we allocate
* multiple bios from the same bio_set() while running
- * underneath generic_make_request(). If we were to allocate
+ * underneath submit_bio_noacct(). If we were to allocate
* multiple bios (say a stacking block driver that was splitting
* bios), we would deadlock if we exhausted the mempool's
* reserve.
diff --git a/block/blk-core.c b/block/blk-core.c
index cb07a726dd7117..ff9a88d2d244cb 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -956,8 +956,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
return BLK_STS_OK;
}
-static noinline_for_stack bool
-generic_make_request_checks(struct bio *bio)
+static noinline_for_stack bool submit_bio_checks(struct bio *bio)
{
struct request_queue *q = bio->bi_disk->queue;
blk_status_t status = BLK_STS_IOERR;
@@ -985,9 +984,8 @@ generic_make_request_checks(struct bio *bio)
}
/*
- * Filter flush bio's early so that make_request based
- * drivers without flush support don't have to worry
- * about them.
+ * Filter flush bio's early so that bio based drivers without flush
+ * support don't have to worry about them.
*/
if (op_is_flush(bio->bi_opf) &&
!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
@@ -1072,7 +1070,7 @@ generic_make_request_checks(struct bio *bio)
return false;
}
-static blk_qc_t do_make_request(struct bio *bio)
+static blk_qc_t __submit_bio(struct bio *bio)
{
struct gendisk *disk = bio->bi_disk;
blk_qc_t ret = BLK_QC_T_NONE;
@@ -1087,7 +1085,7 @@ static blk_qc_t do_make_request(struct bio *bio)
}
/**
- * generic_make_request - re-submit a bio to the block device layer for I/O
+ * submit_bio_noacct - re-submit a bio to the block device layer for I/O
* @bio: The bio describing the location in memory and on the device.
*
* This is a version of submit_bio() that shall only be used for I/O that is
@@ -1095,7 +1093,7 @@ static blk_qc_t do_make_request(struct bio *bio)
* systems and other upper level users of the block layer should use
* submit_bio() instead.
*/
-blk_qc_t generic_make_request(struct bio *bio)
+blk_qc_t submit_bio_noacct(struct bio *bio)
{
/*
* bio_list_on_stack[0] contains bios submitted by the current
@@ -1106,7 +1104,7 @@ blk_qc_t generic_make_request(struct bio *bio)
struct bio_list bio_list_on_stack[2];
blk_qc_t ret = BLK_QC_T_NONE;
- if (!generic_make_request_checks(bio))
+ if (!submit_bio_checks(bio))
goto out;
/*
@@ -1114,7 +1112,7 @@ blk_qc_t generic_make_request(struct bio *bio)
* stack usage with stacked devices could be a problem. So use
* current->bio_list to keep a list of requests submited by a
* ->submit_bio method. current->bio_list is also used as a
- * flag to say if generic_make_request is currently active in this
+ * flag to say if submit_bio_noacct is currently active in this
* task or not. If it is NULL, then no make_request is active. If
* it is non-NULL, then a make_request is active, and new requests
* should be added at the tail
@@ -1132,7 +1130,7 @@ blk_qc_t generic_make_request(struct bio *bio)
* we assign bio_list to a pointer to the bio_list_on_stack,
* thus initialising the bio_list of new bios to be
* added. ->submit_bio() may indeed add some more bios
- * through a recursive call to generic_make_request. If it
+ * through a recursive call to submit_bio_noacct. If it
* did, we find a non-NULL value in bio_list and re-enter the loop
* from the top. In this case we really did just take the bio
* of the top of the list (no pretending) and so remove it from
@@ -1150,7 +1148,7 @@ blk_qc_t generic_make_request(struct bio *bio)
/* Create a fresh bio_list for all subordinate requests */
bio_list_on_stack[1] = bio_list_on_stack[0];
bio_list_init(&bio_list_on_stack[0]);
- ret = do_make_request(bio);
+ ret = __submit_bio(bio);
/* sort new bios into those for a lower level
* and those for the same level
@@ -1174,13 +1172,13 @@ blk_qc_t generic_make_request(struct bio *bio)
out:
return ret;
}
-EXPORT_SYMBOL(generic_make_request);
+EXPORT_SYMBOL(submit_bio_noacct);
/**
* direct_make_request - hand a buffer directly to its device driver for I/O
* @bio: The bio describing the location in memory and on the device.
*
- * This function behaves like generic_make_request(), but does not protect
+ * This function behaves like submit_bio_noacct(), but does not protect
* against recursion. Must only be used if the called driver is known
* to be blk-mq based.
*/
@@ -1192,7 +1190,7 @@ blk_qc_t direct_make_request(struct bio *bio)
bio_io_error(bio);
return BLK_QC_T_NONE;
}
- if (!generic_make_request_checks(bio))
+ if (!submit_bio_checks(bio))
return BLK_QC_T_NONE;
if (unlikely(bio_queue_enter(bio)))
return BLK_QC_T_NONE;
@@ -1263,13 +1261,13 @@ blk_qc_t submit_bio(struct bio *bio)
blk_qc_t ret;
psi_memstall_enter(&pflags);
- ret = generic_make_request(bio);
+ ret = submit_bio_noacct(bio);
psi_memstall_leave(&pflags);
return ret;
}
- return generic_make_request(bio);
+ return submit_bio_noacct(bio);
}
EXPORT_SYMBOL(submit_bio);
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index 6e49688a2d8023..c162b754efbd6a 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -228,7 +228,7 @@ static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr)
return false;
}
bio_chain(split_bio, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
*bio_ptr = split_bio;
}
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index 6533c9b36ab80a..2d5e60023b08bb 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -239,7 +239,7 @@ void __blk_crypto_free_request(struct request *rq)
* kernel crypto API. When the crypto API fallback is used for encryption,
* blk-crypto may choose to split the bio into 2 - the first one that will
* continue to be processed and the second one that will be resubmitted via
- * generic_make_request. A bounce bio will be allocated to encrypt the contents
+ * submit_bio_noacct. A bounce bio will be allocated to encrypt the contents
* of the aforementioned "first one", and *bio_ptr will be updated to this
* bounce bio.
*
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 20fa2290604105..5196dc14527016 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -338,7 +338,7 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
bio_chain(split, *bio);
trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
- generic_make_request(*bio);
+ submit_bio_noacct(*bio);
*bio = split;
}
}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index ad37043297ed58..fee3325edf27b9 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1339,8 +1339,8 @@ static void blk_throtl_dispatch_work_fn(struct work_struct *work)
if (!bio_list_empty(&bio_list_on_stack)) {
blk_start_plug(&plug);
- while((bio = bio_list_pop(&bio_list_on_stack)))
- generic_make_request(bio);
+ while ((bio = bio_list_pop(&bio_list_on_stack)))
+ submit_bio_noacct(bio);
blk_finish_plug(&plug);
}
}
diff --git a/block/bounce.c b/block/bounce.c
index c3aaed07012467..431be88a024050 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -309,7 +309,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
if (!passthrough && sectors < bio_sectors(*bio_orig)) {
bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
bio_chain(bio, *bio_orig);
- generic_make_request(*bio_orig);
+ submit_bio_noacct(*bio_orig);
*bio_orig = bio;
}
bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL :
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 0327408da79c7a..fe6cb99eb91764 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1576,12 +1576,12 @@ void drbd_set_my_capacity(struct drbd_device *device, sector_t size);
/*
* used to submit our private bio
*/
-static inline void drbd_generic_make_request(struct drbd_device *device,
+static inline void drbd_submit_bio_noacct(struct drbd_device *device,
int fault_type, struct bio *bio)
{
__release(local);
if (!bio->bi_disk) {
- drbd_err(device, "drbd_generic_make_request: bio->bi_disk == NULL\n");
+ drbd_err(device, "drbd_submit_bio_noacct: bio->bi_disk == NULL\n");
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
return;
@@ -1590,7 +1590,7 @@ static inline void drbd_generic_make_request(struct drbd_device *device,
if (drbd_insert_fault(device, fault_type))
bio_io_error(bio);
else
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backing_dev *bdev,
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 2b05de0896e282..7c34cc0ad8ccdf 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2325,7 +2325,7 @@ static void do_retry(struct work_struct *ws)
* workqueues instead.
*/
- /* We are not just doing generic_make_request(),
+ /* We are not just doing submit_bio_noacct(),
* as we want to keep the start_time information. */
inc_ap_bio(device);
__drbd_make_request(device, bio, start_jif);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 3a3f2b6a821f39..c74f561b4eab51 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1723,7 +1723,7 @@ int drbd_submit_peer_request(struct drbd_device *device,
bios = bios->bi_next;
bio->bi_next = NULL;
- drbd_generic_make_request(device, fault_type, bio);
+ drbd_submit_bio_noacct(device, fault_type, bio);
} while (bios);
return 0;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c7e14c9a6e5f83..674be09b2da94a 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1164,7 +1164,7 @@ drbd_submit_req_private_bio(struct drbd_request *req)
else if (bio_op(bio) == REQ_OP_DISCARD)
drbd_process_discard_or_zeroes_req(req, EE_TRIM);
else
- generic_make_request(bio);
+ submit_bio_noacct(bio);
put_ldev(device);
} else
bio_io_error(bio);
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 2b89c9f2ca7075..7c903de5c4e103 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1525,7 +1525,7 @@ int w_restart_disk_io(struct drbd_work *w, int cancel)
drbd_req_make_private_bio(req, req->master_bio);
bio_set_dev(req->private_bio, device->ldev->backing_bdev);
- generic_make_request(req->private_bio);
+ submit_bio_noacct(req->private_bio);
return 0;
}
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 5588bd4cd267e8..4becc1efe775fc 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -913,7 +913,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
}
atomic_inc(&pd->cdrw.pending_bios);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 140927ebf41e9a..c28537a489bc10 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -320,7 +320,7 @@ void pblk_submit_read(struct pblk *pblk, struct bio *bio)
split_bio = bio_split(bio, nr_secs * NR_PHY_IN_LOG, GFP_KERNEL,
&pblk_bio_set);
bio_chain(split_bio, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
/* New bio contains first N sectors of the previous one, so
* we can continue to use existing rqd, but we need to shrink
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 221e0191b6870f..3c708e8b5e2d34 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -929,7 +929,7 @@ static inline void closure_bio_submit(struct cache_set *c,
bio_endio(bio);
return;
}
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
/*
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 6548a601edf0e4..d5c51e33204679 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -959,7 +959,7 @@ static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op,
* bch_btree_node_get - find a btree node in the cache and lock it, reading it
* in from disk if necessary.
*
- * If IO is necessary and running under generic_make_request, returns -EAGAIN.
+ * If IO is necessary and running under submit_bio_noacct, returns -EAGAIN.
*
* The btree node will have either a read or a write lock held, depending on
* level and op->lock.
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index fc5702b10074d6..dd012ebface012 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1115,7 +1115,7 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
!blk_queue_discard(bdev_get_queue(dc->bdev)))
bio->bi_end_io(bio);
else
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
static void quit_max_writeback_rate(struct cache_set *c,
@@ -1197,7 +1197,7 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
if (!bio->bi_iter.bi_size) {
/*
* can't call bch_journal_meta from under
- * generic_make_request
+ * submit_bio_noacct
*/
continue_at_nobarrier(&s->cl,
cached_dev_nodata,
@@ -1311,8 +1311,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
if (!bio->bi_iter.bi_size) {
/*
- * can't call bch_journal_meta from under
- * generic_make_request
+ * can't call bch_journal_meta from under submit_bio_noacct
*/
continue_at_nobarrier(&s->cl,
flash_dev_nodata,
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index d3bb355819a421..9eccced928960a 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -886,7 +886,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio)
static void accounted_request(struct cache *cache, struct bio *bio)
{
accounted_begin(cache, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
static void issue_op(struct bio *bio, void *context)
@@ -1792,7 +1792,7 @@ static bool process_bio(struct cache *cache, struct bio *bio)
bool commit_needed;
if (map_bio(cache, bio, get_bio_block(cache, bio), &commit_needed) == DM_MAPIO_REMAPPED)
- generic_make_request(bio);
+ submit_bio_noacct(bio);
return commit_needed;
}
@@ -1858,7 +1858,7 @@ static bool process_discard_bio(struct cache *cache, struct bio *bio)
if (cache->features.discard_passdown) {
remap_to_origin(cache, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
} else
bio_endio(bio);
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 5ce96ddf1ce1eb..59ed8a67c2e34f 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -330,7 +330,7 @@ static void submit_bios(struct bio_list *bios)
blk_start_plug(&plug);
while ((bio = bio_list_pop(bios)))
- generic_make_request(bio);
+ submit_bio_noacct(bio);
blk_finish_plug(&plug);
}
@@ -346,7 +346,7 @@ static void submit_bios(struct bio_list *bios)
static void issue_bio(struct clone *clone, struct bio *bio)
{
if (!bio_triggers_commit(clone, bio)) {
- generic_make_request(bio);
+ submit_bio_noacct(bio);
return;
}
@@ -473,7 +473,7 @@ static void complete_discard_bio(struct clone *clone, struct bio *bio, bool succ
bio_region_range(clone, bio, &rs, &nr_regions);
trim_bio(bio, region_to_sector(clone, rs),
nr_regions << clone->region_shift);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
} else
bio_endio(bio);
}
@@ -865,7 +865,7 @@ static void hydration_overwrite(struct dm_clone_region_hydration *hd, struct bio
bio->bi_private = hd;
atomic_inc(&hd->clone->hydrations_in_flight);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
/*
@@ -1281,7 +1281,7 @@ static void process_deferred_flush_bios(struct clone *clone)
*/
bio_endio(bio);
} else {
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
}
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 000ddfab5ba058..ad324abb8c497e 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1789,7 +1789,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
return 1;
}
- generic_make_request(clone);
+ submit_bio_noacct(clone);
return 0;
}
@@ -1815,7 +1815,7 @@ static void kcryptd_io_write(struct dm_crypt_io *io)
{
struct bio *clone = io->ctx.bio_out;
- generic_make_request(clone);
+ submit_bio_noacct(clone);
}
#define crypt_io_from_node(node) rb_entry((node), struct dm_crypt_io, rb_node)
@@ -1893,7 +1893,7 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
clone->bi_iter.bi_sector = cc->start + io->sector;
if (likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) {
- generic_make_request(clone);
+ submit_bio_noacct(clone);
return;
}
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index f496213f8b6753..2628a832787b04 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -72,7 +72,7 @@ static void flush_bios(struct bio *bio)
while (bio) {
n = bio->bi_next;
bio->bi_next = NULL;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = n;
}
}
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index bdb84b8e71621d..566ddbdb16a4ef 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1265,7 +1265,7 @@ static void process_deferred_bios(struct era *era)
bio_io_error(bio);
else
while ((bio = bio_list_pop(&marked_bios)))
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
static void process_rpc_calls(struct era *era)
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 81dc5ff0890956..ae866e469e1b98 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2115,12 +2115,12 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
dio->in_flight = (atomic_t)ATOMIC_INIT(1);
dio->completion = NULL;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
return;
}
- generic_make_request(bio);
+ submit_bio_noacct(bio);
if (need_sync_io) {
wait_for_completion_io(&read_comp);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 78cff42d987ee5..73bb23de6336f1 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -677,7 +677,7 @@ static void process_queued_bios(struct work_struct *work)
bio_endio(bio);
break;
case DM_MAPIO_REMAPPED:
- generic_make_request(bio);
+ submit_bio_noacct(bio);
break;
case DM_MAPIO_SUBMITTED:
break;
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 2f655d9f420064..fa09bc4e4c54a1 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -779,7 +779,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
wakeup_mirrord(ms);
} else {
map_bio(get_default_mirror(ms), bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
}
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 963d3774c93e28..2d1d4a4c399cdc 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -252,7 +252,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int op,
/*
* Issue the synchronous I/O from a different thread
- * to avoid generic_make_request recursion.
+ * to avoid submit_bio_noacct recursion.
*/
INIT_WORK_ONSTACK(&req.work, do_metadata);
queue_work(ps->metadata_wq, &req.work);
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 6b11a266299f14..4668b2cd98f4e2 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1568,7 +1568,7 @@ static void flush_bios(struct bio *bio)
while (bio) {
n = bio->bi_next;
bio->bi_next = NULL;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = n;
}
}
@@ -1588,7 +1588,7 @@ static void retry_origin_bios(struct dm_snapshot *s, struct bio *bio)
bio->bi_next = NULL;
r = do_origin(s->origin, bio, false);
if (r == DM_MAPIO_REMAPPED)
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = n;
}
}
@@ -1829,7 +1829,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe,
bio->bi_end_io = full_bio_end_io;
bio->bi_private = callback_data;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
static struct dm_snap_pending_exception *
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fa8d5464c1fb51..fe2de28887096f 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -758,7 +758,7 @@ static void issue(struct thin_c *tc, struct bio *bio)
struct pool *pool = tc->pool;
if (!bio_triggers_commit(tc, bio)) {
- generic_make_request(bio);
+ submit_bio_noacct(bio);
return;
}
@@ -2394,7 +2394,7 @@ static void process_deferred_bios(struct pool *pool)
if (bio->bi_opf & REQ_PREFLUSH)
bio_endio(bio);
else
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index eec9f252e9354b..75fa4d9b761717 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -681,7 +681,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
verity_submit_prefetch(v, io);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
return DM_MAPIO_SUBMITTED;
}
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 74f3c506f08487..62421554b83851 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -1238,7 +1238,7 @@ static int writecache_flush_thread(void *data)
bio_end_sector(bio));
wc_unlock(wc);
bio_set_dev(bio, wc->dev->bdev);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
} else {
writecache_flush(wc);
wc_unlock(wc);
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index a907a9446c0b5c..05a3cfefe93728 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -140,7 +140,7 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone,
bio_advance(bio, clone->bi_iter.bi_size);
refcount_inc(&bioctx->ref);
- generic_make_request(clone);
+ submit_bio_noacct(clone);
if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
zone->wp_block += nr_blocks;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5acfaba3700dfc..b32b539dbace56 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1305,7 +1305,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
if (md->type == DM_TYPE_NVME_BIO_BASED)
ret = direct_make_request(clone);
else
- ret = generic_make_request(clone);
+ ret = submit_bio_noacct(clone);
break;
case DM_MAPIO_KILL:
free_tio(tio);
@@ -1652,7 +1652,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
error = __split_and_process_non_flush(&ci);
if (current->bio_list && ci.sector_count && !error) {
/*
- * Remainder must be passed to generic_make_request()
+ * Remainder must be passed to submit_bio_noacct()
* so that it gets handled *after* bios already submitted
* have been completely processed.
* We take a clone of the original to store in
@@ -1677,7 +1677,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
bio_chain(b, bio);
trace_block_split(md->queue, b, bio->bi_iter.bi_sector);
- ret = generic_make_request(bio);
+ ret = submit_bio_noacct(bio);
break;
}
}
@@ -1745,7 +1745,7 @@ static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struc
bio_chain(split, *bio);
trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector);
- generic_make_request(*bio);
+ submit_bio_noacct(*bio);
*bio = split;
}
}
@@ -2500,7 +2500,7 @@ static void dm_wq_work(struct work_struct *work)
break;
if (dm_request_based(md))
- (void) generic_make_request(c);
+ (void) submit_bio_noacct(c);
else
(void) dm_process_bio(md, map, c);
}
diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c
index 50ad4ba86f0e74..fda4cb3f936f39 100644
--- a/drivers/md/md-faulty.c
+++ b/drivers/md/md-faulty.c
@@ -169,7 +169,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
if (bio_data_dir(bio) == WRITE) {
/* write request */
if (atomic_read(&conf->counters[WriteAll])) {
- /* special case - don't decrement, don't generic_make_request,
+ /* special case - don't decrement, don't submit_bio_noacct,
* just fail immediately
*/
bio_io_error(bio);
@@ -214,7 +214,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
} else
bio_set_dev(bio, conf->rdev->bdev);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
return true;
}
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 26c75c0199fa1b..8efada3ee16f30 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -267,7 +267,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
struct bio *split = bio_split(bio, end_sector - bio_sector,
GFP_NOIO, &mddev->bio_set);
bio_chain(split, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = split;
}
@@ -286,7 +286,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
bio_sector);
mddev_check_writesame(mddev, bio);
mddev_check_write_zeroes(mddev, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
return true;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 152f9e65a22665..277fdfd9ee5480 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -131,7 +131,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
mp_bh->bio.bi_private = mp_bh;
mddev_check_writesame(mddev, &mp_bh->bio);
mddev_check_write_zeroes(mddev, &mp_bh->bio);
- generic_make_request(&mp_bh->bio);
+ submit_bio_noacct(&mp_bh->bio);
return true;
}
@@ -348,7 +348,7 @@ static void multipathd(struct md_thread *thread)
bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
bio->bi_end_io = multipath_end_request;
bio->bi_private = mp_bh;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
spin_unlock_irqrestore(&conf->device_lock, flags);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 322386ff5d225d..e9e91c8d8afcea 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -495,7 +495,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
&mddev->bio_set);
bio_chain(split, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = split;
end = zone->zone_end;
} else
@@ -559,7 +559,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
trace_block_bio_remap(bdev_get_queue(rdev->bdev),
discard_bio, disk_devt(mddev->gendisk),
bio->bi_iter.bi_sector);
- generic_make_request(discard_bio);
+ submit_bio_noacct(discard_bio);
}
bio_endio(bio);
}
@@ -600,7 +600,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
struct bio *split = bio_split(bio, sectors, GFP_NOIO,
&mddev->bio_set);
bio_chain(split, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = split;
}
@@ -633,7 +633,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
disk_devt(mddev->gendisk), bio_sector);
mddev_check_writesame(mddev, bio);
mddev_check_write_zeroes(mddev, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
return true;
}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index dcd27f3da84eca..2aa2649cca660e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -834,7 +834,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
/* Just ignore it */
bio_endio(bio);
else
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = next;
cond_resched();
}
@@ -1312,7 +1312,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
struct bio *split = bio_split(bio, max_sectors,
gfp, &conf->bio_split);
bio_chain(split, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = split;
r1_bio->master_bio = bio;
r1_bio->sectors = max_sectors;
@@ -1338,7 +1338,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
trace_block_bio_remap(read_bio->bi_disk->queue, read_bio,
disk_devt(mddev->gendisk), r1_bio->sector);
- generic_make_request(read_bio);
+ submit_bio_noacct(read_bio);
}
static void raid1_write_request(struct mddev *mddev, struct bio *bio,
@@ -1483,7 +1483,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
struct bio *split = bio_split(bio, max_sectors,
GFP_NOIO, &conf->bio_split);
bio_chain(split, bio);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = split;
r1_bio->master_bio = bio;
r1_bio->sectors = max_sectors;
@@ -2240,7 +2240,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
atomic_inc(&r1_bio->remaining);
md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
- generic_make_request(wbio);
+ submit_bio_noacct(wbio);
}
put_sync_write_buf(r1_bio, 1);
@@ -2926,7 +2926,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
md_sync_acct_bio(bio, nr_sectors);
if (read_targets == 1)
bio->bi_opf &= ~MD_FAILFAST;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
} else {
@@ -2935,7 +2935,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
md_sync_acct_bio(bio, nr_sectors);
if (read_targets == 1)
bio->bi_opf &= ~MD_FAILFAST;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
return nr_sectors;
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ec136e44aef7f8..e45fd56cf58450 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -917,7 +917,7 @@ static void flush_pending_writes(struct r10conf *conf)
/* Just ignore it */
bio_endio(bio);
else
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = next;
}
blk_finish_plug(&plug);
@@ -1102,7 +1102,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
/* Just ignore it */
bio_endio(bio);
else
- generic_make_request(bio);
+ submit_bio_noacct(bio);
bio = next;
}
kfree(plug);
@@ -1194,7 +1194,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
gfp, &conf->bio_split);
bio_chain(split, bio);
allow_barrier(conf);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
wait_barrier(conf);
bio = split;
r10_bio->master_bio = bio;
@@ -1221,7 +1221,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
trace_block_bio_remap(read_bio->bi_disk->queue,
read_bio, disk_devt(mddev->gendisk),
r10_bio->sector);
- generic_make_request(read_bio);
+ submit_bio_noacct(read_bio);
return;
}
@@ -1479,7 +1479,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
GFP_NOIO, &conf->bio_split);
bio_chain(split, bio);
allow_barrier(conf);
- generic_make_request(bio);
+ submit_bio_noacct(bio);
wait_barrier(conf);
bio = split;
r10_bio->master_bio = bio;
@@ -2099,7 +2099,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
tbio->bi_opf |= MD_FAILFAST;
tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset;
bio_set_dev(tbio, conf->mirrors[d].rdev->bdev);
- generic_make_request(tbio);
+ submit_bio_noacct(tbio);
}
/* Now write out to any replacement devices
@@ -2118,7 +2118,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
atomic_inc(&r10_bio->remaining);
md_sync_acct(conf->mirrors[d].replacement->bdev,
bio_sectors(tbio));
- generic_make_request(tbio);
+ submit_bio_noacct(tbio);
}
done:
@@ -2241,7 +2241,7 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
wbio = r10_bio->devs[1].bio;
wbio2 = r10_bio->devs[1].repl_bio;
/* Need to test wbio2->bi_end_io before we call
- * generic_make_request as if the former is NULL,
+ * submit_bio_noacct as if the former is NULL,
* the latter is free to free wbio2.
*/
if (wbio2 && !wbio2->bi_end_io)
@@ -2249,13 +2249,13 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
if (wbio->bi_end_io) {
atomic_inc(&conf->mirrors[d].rdev->nr_pending);
md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
- generic_make_request(wbio);
+ submit_bio_noacct(wbio);
}
if (wbio2) {
atomic_inc(&conf->mirrors[d].replacement->nr_pending);
md_sync_acct(conf->mirrors[d].replacement->bdev,
bio_sectors(wbio2));
- generic_make_request(wbio2);
+ submit_bio_noacct(wbio2);
}
}
@@ -2889,7 +2889,7 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf)
* a number of r10_bio structures, one for each out-of-sync device.
* As we setup these structures, we collect all bio's together into a list
* which we then process collectively to add pages, and then process again
- * to pass to generic_make_request.
+ * to pass to submit_bio_noacct.
*
* The r10_bio structures are linked using a borrowed master_bio pointer.
* This link is counted in ->remaining. When the r10_bio that points to NULL
@@ -3496,7 +3496,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (bio->bi_end_io == end_sync_read) {
md_sync_acct_bio(bio, nr_sectors);
bio->bi_status = 0;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
@@ -4654,7 +4654,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
md_sync_acct_bio(read_bio, r10_bio->sectors);
atomic_inc(&r10_bio->remaining);
read_bio->bi_next = NULL;
- generic_make_request(read_bio);
+ submit_bio_noacct(read_bio);
sectors_done += nr_sectors;
if (sector_nr <= last)
goto read_more;
@@ -4717,7 +4717,7 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
md_sync_acct_bio(b, r10_bio->sectors);
atomic_inc(&r10_bio->remaining);
b->bi_next = NULL;
- generic_make_request(b);
+ submit_bio_noacct(b);
}
end_reshape_request(r10_bio);
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ab8067f9ce8c68..8dea4398b191ae 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -873,7 +873,7 @@ static void dispatch_bio_list(struct bio_list *tmp)
struct bio *bio;
while ((bio = bio_list_pop(tmp)))
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
static int cmp_stripe(void *priv, struct list_head *a, struct list_head *b)
@@ -1151,7 +1151,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (should_defer && op_is_write(op))
bio_list_add(&pending_bios, bi);
else
- generic_make_request(bi);
+ submit_bio_noacct(bi);
}
if (rrdev) {
if (s->syncing || s->expanding || s->expanded
@@ -1201,7 +1201,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (should_defer && op_is_write(op))
bio_list_add(&pending_bios, rbi);
else
- generic_make_request(rbi);
+ submit_bio_noacct(rbi);
}
if (!rdev && !rrdev) {
if (op_is_write(op))
@@ -5289,7 +5289,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
trace_block_bio_remap(align_bi->bi_disk->queue,
align_bi, disk_devt(mddev->gendisk),
raid_bio->bi_iter.bi_sector);
- generic_make_request(align_bi);
+ submit_bio_noacct(align_bi);
return 1;
} else {
rcu_read_unlock();
@@ -5309,7 +5309,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
struct r5conf *conf = mddev->private;
split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split);
bio_chain(split, raid_bio);
- generic_make_request(raid_bio);
+ submit_bio_noacct(raid_bio);
raid_bio = split;
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 89afcf943bf846..f07fa47c251d9d 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -351,7 +351,7 @@ static void nvme_requeue_work(struct work_struct *work)
* path.
*/
bio->bi_disk = head->disk;
- generic_make_request(bio);
+ submit_bio_noacct(bio);
}
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 083ffc5bc51b09..b73cfa6a5141df 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -852,7 +852,7 @@ static inline void rq_flush_dcache_pages(struct request *rq)
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
-extern blk_qc_t generic_make_request(struct bio *bio);
+blk_qc_t submit_bio_noacct(struct bio *bio);
extern blk_qc_t direct_make_request(struct bio *bio);
extern void blk_rq_init(struct request_queue *q, struct request *rq);
extern void blk_put_request(struct request *);
--
2.26.2
^ permalink raw reply related
* [PATCH 18/20] block: refator submit_bio_noacct
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
Split out a __submit_bio_noacct helper for the actual de-recursion
algorithm, and simplify the loop by using a continue when we can't
enter the queue for a bio.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-core.c | 143 +++++++++++++++++++++++++----------------------
1 file changed, 75 insertions(+), 68 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index ff9a88d2d244cb..57b5dc00d44cb1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1084,6 +1084,74 @@ static blk_qc_t __submit_bio(struct bio *bio)
return ret;
}
+/*
+ * The loop in this function may be a bit non-obvious, and so deserves some
+ * explanation:
+ *
+ * - Before entering the loop, bio->bi_next is NULL (as all callers ensure
+ * that), so we have a list with a single bio.
+ * - We pretend that we have just taken it off a longer list, so we assign
+ * bio_list to a pointer to the bio_list_on_stack, thus initialising the
+ * bio_list of new bios to be added. ->submit_bio() may indeed add some more
+ * bios through a recursive call to submit_bio_noacct. If it did, we find a
+ * non-NULL value in bio_list and re-enter the loop from the top.
+ * - In this case we really did just take the bio of the top of the list (no
+ * pretending) and so remove it from bio_list, and call into ->submit_bio()
+ * again.
+ *
+ * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio.
+ * bio_list_on_stack[1] contains bios that were submitted before the current
+ * ->submit_bio_bio, but that haven't been processed yet.
+ */
+static blk_qc_t __submit_bio_noacct(struct bio *bio)
+{
+ struct bio_list bio_list_on_stack[2];
+ blk_qc_t ret = BLK_QC_T_NONE;
+
+ BUG_ON(bio->bi_next);
+
+ bio_list_init(&bio_list_on_stack[0]);
+ current->bio_list = bio_list_on_stack;
+
+ do {
+ struct request_queue *q = bio->bi_disk->queue;
+ struct bio_list lower, same;
+
+ if (unlikely(bio_queue_enter(bio) != 0))
+ continue;
+
+ /*
+ * Create a fresh bio_list for all subordinate requests.
+ */
+ bio_list_on_stack[1] = bio_list_on_stack[0];
+ bio_list_init(&bio_list_on_stack[0]);
+
+ ret = __submit_bio(bio);
+
+ /*
+ * Sort new bios into those for a lower level and those for the
+ * same level.
+ */
+ bio_list_init(&lower);
+ bio_list_init(&same);
+ while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
+ if (q == bio->bi_disk->queue)
+ bio_list_add(&same, bio);
+ else
+ bio_list_add(&lower, bio);
+
+ /*
+ * Now assemble so we handle the lowest level first.
+ */
+ bio_list_merge(&bio_list_on_stack[0], &lower);
+ bio_list_merge(&bio_list_on_stack[0], &same);
+ bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
+ } while ((bio = bio_list_pop(&bio_list_on_stack[0])));
+
+ current->bio_list = NULL;
+ return ret;
+}
+
/**
* submit_bio_noacct - re-submit a bio to the block device layer for I/O
* @bio: The bio describing the location in memory and on the device.
@@ -1095,82 +1163,21 @@ static blk_qc_t __submit_bio(struct bio *bio)
*/
blk_qc_t submit_bio_noacct(struct bio *bio)
{
- /*
- * bio_list_on_stack[0] contains bios submitted by the current
- * ->submit_bio.
- * bio_list_on_stack[1] contains bios that were submitted before the
- * current ->submit_bio_bio, but that haven't been processed yet.
- */
- struct bio_list bio_list_on_stack[2];
- blk_qc_t ret = BLK_QC_T_NONE;
-
if (!submit_bio_checks(bio))
- goto out;
+ return BLK_QC_T_NONE;
/*
- * We only want one ->submit_bio to be active at a time, else
- * stack usage with stacked devices could be a problem. So use
- * current->bio_list to keep a list of requests submited by a
- * ->submit_bio method. current->bio_list is also used as a
- * flag to say if submit_bio_noacct is currently active in this
- * task or not. If it is NULL, then no make_request is active. If
- * it is non-NULL, then a make_request is active, and new requests
- * should be added at the tail
+ * We only want one ->submit_bio to be active at a time, else stack
+ * usage with stacked devices could be a problem. Use current->bio_list
+ * to collect a list of requests submited by a ->submit_bio method while
+ * it is active, and then process them after it returned.
*/
if (current->bio_list) {
bio_list_add(¤t->bio_list[0], bio);
- goto out;
+ return BLK_QC_T_NONE;
}
- /* following loop may be a bit non-obvious, and so deserves some
- * explanation.
- * Before entering the loop, bio->bi_next is NULL (as all callers
- * ensure that) so we have a list with a single bio.
- * We pretend that we have just taken it off a longer list, so
- * we assign bio_list to a pointer to the bio_list_on_stack,
- * thus initialising the bio_list of new bios to be
- * added. ->submit_bio() may indeed add some more bios
- * through a recursive call to submit_bio_noacct. If it
- * did, we find a non-NULL value in bio_list and re-enter the loop
- * from the top. In this case we really did just take the bio
- * of the top of the list (no pretending) and so remove it from
- * bio_list, and call into ->submit_bio() again.
- */
- BUG_ON(bio->bi_next);
- bio_list_init(&bio_list_on_stack[0]);
- current->bio_list = bio_list_on_stack;
- do {
- struct request_queue *q = bio->bi_disk->queue;
-
- if (likely(bio_queue_enter(bio) == 0)) {
- struct bio_list lower, same;
-
- /* Create a fresh bio_list for all subordinate requests */
- bio_list_on_stack[1] = bio_list_on_stack[0];
- bio_list_init(&bio_list_on_stack[0]);
- ret = __submit_bio(bio);
-
- /* sort new bios into those for a lower level
- * and those for the same level
- */
- bio_list_init(&lower);
- bio_list_init(&same);
- while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
- if (q == bio->bi_disk->queue)
- bio_list_add(&same, bio);
- else
- bio_list_add(&lower, bio);
- /* now assemble so we handle the lowest level first */
- bio_list_merge(&bio_list_on_stack[0], &lower);
- bio_list_merge(&bio_list_on_stack[0], &same);
- bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
- }
- bio = bio_list_pop(&bio_list_on_stack[0]);
- } while (bio);
- current->bio_list = NULL; /* deactivate */
-
-out:
- return ret;
+ return __submit_bio_noacct(bio);
}
EXPORT_SYMBOL(submit_bio_noacct);
--
2.26.2
^ permalink raw reply related
* [PATCH 16/20] block: move ->make_request_fn to struct block_device_operations
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
The make_request_fn is a little weird in that it sits directly in
struct request_queue instead of an operation vector. Replace it with
a block_device_operations method called submit_bio (which describes much
better what it does). Also remove the request_queue argument to it, as
the queue can be derived pretty trivially from the bio.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
Documentation/block/biodoc.rst | 2 +-
.../block/writeback_cache_control.rst | 2 +-
arch/m68k/emu/nfblock.c | 5 +-
arch/xtensa/platforms/iss/simdisk.c | 5 +-
block/blk-cgroup.c | 2 +-
block/blk-core.c | 53 +++++++------------
block/blk-mq.c | 10 ++--
block/blk.h | 2 -
drivers/block/brd.c | 5 +-
drivers/block/drbd/drbd_int.h | 2 +-
drivers/block/drbd/drbd_main.c | 9 ++--
drivers/block/drbd/drbd_req.c | 2 +-
drivers/block/null_blk_main.c | 17 ++++--
drivers/block/pktcdvd.c | 11 ++--
drivers/block/ps3vram.c | 15 +++---
drivers/block/rsxx/dev.c | 7 ++-
drivers/block/umem.c | 5 +-
drivers/block/zram/zram_drv.c | 11 ++--
drivers/lightnvm/core.c | 8 +--
drivers/lightnvm/pblk-init.c | 12 +++--
drivers/md/bcache/request.c | 4 +-
drivers/md/bcache/request.h | 4 +-
drivers/md/bcache/super.c | 23 +++++---
drivers/md/dm.c | 23 ++++----
drivers/md/md.c | 5 +-
drivers/nvdimm/blk.c | 5 +-
drivers/nvdimm/btt.c | 5 +-
drivers/nvdimm/pmem.c | 5 +-
drivers/nvme/host/core.c | 1 +
drivers/nvme/host/multipath.c | 5 +-
drivers/nvme/host/nvme.h | 1 +
drivers/s390/block/dcssblk.c | 9 ++--
drivers/s390/block/xpram.c | 6 +--
include/linux/blk-mq.h | 2 +-
include/linux/blkdev.h | 7 +--
include/linux/lightnvm.h | 3 +-
36 files changed, 153 insertions(+), 140 deletions(-)
diff --git a/Documentation/block/biodoc.rst b/Documentation/block/biodoc.rst
index b964796ec9c780..267384159bf793 100644
--- a/Documentation/block/biodoc.rst
+++ b/Documentation/block/biodoc.rst
@@ -1036,7 +1036,7 @@ Now the generic block layer performs partition-remapping early and thus
provides drivers with a sector number relative to whole device, rather than
having to take partition number into account in order to arrive at the true
sector number. The routine blk_partition_remap() is invoked by
-generic_make_request even before invoking the queue specific make_request_fn,
+generic_make_request even before invoking the queue specific ->submit_bio,
so the i/o scheduler also gets to operate on whole disk sector numbers. This
should typically not require changes to block drivers, it just never gets
to invoke its own partition sector offset calculations since all bios
diff --git a/Documentation/block/writeback_cache_control.rst b/Documentation/block/writeback_cache_control.rst
index 2c752c57c14c62..b208488d0aae85 100644
--- a/Documentation/block/writeback_cache_control.rst
+++ b/Documentation/block/writeback_cache_control.rst
@@ -47,7 +47,7 @@ the Forced Unit Access is implemented. The REQ_PREFLUSH and REQ_FUA flags
may both be set on a single bio.
-Implementation details for make_request_fn based block drivers
+Implementation details for bio based block drivers
--------------------------------------------------------------
These drivers will always see the REQ_PREFLUSH and REQ_FUA bits as they sit
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 87e8b1700acd28..92d26c81244134 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -59,7 +59,7 @@ struct nfhd_device {
struct gendisk *disk;
};
-static blk_qc_t nfhd_make_request(struct request_queue *queue, struct bio *bio)
+static blk_qc_t nfhd_submit_bio(struct bio *bio)
{
struct nfhd_device *dev = bio->bi_disk->private_data;
struct bio_vec bvec;
@@ -93,6 +93,7 @@ static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
static const struct block_device_operations nfhd_ops = {
.owner = THIS_MODULE,
+ .submit_bio = nfhd_submit_bio,
.getgeo = nfhd_getgeo,
};
@@ -118,7 +119,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
dev->bsize = bsize;
dev->bshift = ffs(bsize) - 10;
- dev->queue = blk_alloc_queue(nfhd_make_request, NUMA_NO_NODE);
+ dev->queue = blk_alloc_queue(NUMA_NO_NODE);
if (dev->queue == NULL)
goto free_dev;
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 31b5020077a059..5107140dbb7edc 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -101,7 +101,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
spin_unlock(&dev->lock);
}
-static blk_qc_t simdisk_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t simdisk_submit_bio(struct bio *bio)
{
struct simdisk *dev = bio->bi_disk->private_data;
struct bio_vec bvec;
@@ -144,6 +144,7 @@ static void simdisk_release(struct gendisk *disk, fmode_t mode)
static const struct block_device_operations simdisk_ops = {
.owner = THIS_MODULE,
+ .submit_bio = simdisk_submit_bio,
.open = simdisk_open,
.release = simdisk_release,
};
@@ -267,7 +268,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
spin_lock_init(&dev->lock);
dev->users = 0;
- dev->queue = blk_alloc_queue(simdisk_make_request, NUMA_NO_NODE);
+ dev->queue = blk_alloc_queue(NUMA_NO_NODE);
if (dev->queue == NULL) {
pr_err("blk_alloc_queue failed\n");
goto out_alloc_queue;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1ce94afc03bcfd..bc1df69e371c21 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1012,7 +1012,7 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
* blkcg_init_queue - initialize blkcg part of request queue
* @q: request_queue to initialize
*
- * Called from __blk_alloc_queue(). Responsible for initializing blkcg
+ * Called from blk_alloc_queue(). Responsible for initializing blkcg
* part of new request_queue @q.
*
* RETURNS:
diff --git a/block/blk-core.c b/block/blk-core.c
index 28f60985dc75cc..cb07a726dd7117 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -283,7 +283,7 @@ EXPORT_SYMBOL(blk_dump_rq_flags);
* A block device may call blk_sync_queue to ensure that any
* such activity is cancelled, thus allowing it to release resources
* that the callbacks might use. The caller must already have made sure
- * that its ->make_request_fn will not re-add plugging prior to calling
+ * that its ->submit_bio will not re-add plugging prior to calling
* this function.
*
* This function does not cancel any asynchronous activity arising
@@ -510,7 +510,7 @@ static void blk_timeout_work(struct work_struct *work)
{
}
-struct request_queue *__blk_alloc_queue(int node_id)
+struct request_queue *blk_alloc_queue(int node_id)
{
struct request_queue *q;
int ret;
@@ -575,6 +575,7 @@ struct request_queue *__blk_alloc_queue(int node_id)
blk_queue_dma_alignment(q, 511);
blk_set_default_limits(&q->limits);
+ q->nr_requests = BLKDEV_MAX_RQ;
return q;
@@ -592,21 +593,6 @@ struct request_queue *__blk_alloc_queue(int node_id)
kmem_cache_free(blk_requestq_cachep, q);
return NULL;
}
-
-struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id)
-{
- struct request_queue *q;
-
- if (WARN_ON_ONCE(!make_request))
- return NULL;
-
- q = __blk_alloc_queue(node_id);
- if (!q)
- return NULL;
- q->make_request_fn = make_request;
- q->nr_requests = BLKDEV_MAX_RQ;
- return q;
-}
EXPORT_SYMBOL(blk_alloc_queue);
/**
@@ -1088,15 +1074,15 @@ generic_make_request_checks(struct bio *bio)
static blk_qc_t do_make_request(struct bio *bio)
{
- struct request_queue *q = bio->bi_disk->queue;
+ struct gendisk *disk = bio->bi_disk;
blk_qc_t ret = BLK_QC_T_NONE;
if (blk_crypto_bio_prep(&bio)) {
- if (!q->make_request_fn)
- return blk_mq_make_request(q, bio);
- ret = q->make_request_fn(q, bio);
+ if (!disk->fops->submit_bio)
+ return blk_mq_submit_bio(bio);
+ ret = disk->fops->submit_bio(bio);
}
- blk_queue_exit(q);
+ blk_queue_exit(disk->queue);
return ret;
}
@@ -1113,10 +1099,9 @@ blk_qc_t generic_make_request(struct bio *bio)
{
/*
* bio_list_on_stack[0] contains bios submitted by the current
- * make_request_fn.
- * bio_list_on_stack[1] contains bios that were submitted before
- * the current make_request_fn, but that haven't been processed
- * yet.
+ * ->submit_bio.
+ * bio_list_on_stack[1] contains bios that were submitted before the
+ * current ->submit_bio_bio, but that haven't been processed yet.
*/
struct bio_list bio_list_on_stack[2];
blk_qc_t ret = BLK_QC_T_NONE;
@@ -1125,10 +1110,10 @@ blk_qc_t generic_make_request(struct bio *bio)
goto out;
/*
- * We only want one ->make_request_fn to be active at a time, else
+ * We only want one ->submit_bio to be active at a time, else
* stack usage with stacked devices could be a problem. So use
* current->bio_list to keep a list of requests submited by a
- * make_request_fn function. current->bio_list is also used as a
+ * ->submit_bio method. current->bio_list is also used as a
* flag to say if generic_make_request is currently active in this
* task or not. If it is NULL, then no make_request is active. If
* it is non-NULL, then a make_request is active, and new requests
@@ -1146,12 +1131,12 @@ blk_qc_t generic_make_request(struct bio *bio)
* We pretend that we have just taken it off a longer list, so
* we assign bio_list to a pointer to the bio_list_on_stack,
* thus initialising the bio_list of new bios to be
- * added. ->make_request() may indeed add some more bios
+ * added. ->submit_bio() may indeed add some more bios
* through a recursive call to generic_make_request. If it
* did, we find a non-NULL value in bio_list and re-enter the loop
* from the top. In this case we really did just take the bio
* of the top of the list (no pretending) and so remove it from
- * bio_list, and call into ->make_request() again.
+ * bio_list, and call into ->submit_bio() again.
*/
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack[0]);
@@ -1201,9 +1186,9 @@ EXPORT_SYMBOL(generic_make_request);
*/
blk_qc_t direct_make_request(struct bio *bio)
{
- struct request_queue *q = bio->bi_disk->queue;
+ struct gendisk *disk = bio->bi_disk;
- if (WARN_ON_ONCE(q->make_request_fn)) {
+ if (WARN_ON_ONCE(!disk->queue->mq_ops)) {
bio_io_error(bio);
return BLK_QC_T_NONE;
}
@@ -1212,10 +1197,10 @@ blk_qc_t direct_make_request(struct bio *bio)
if (unlikely(bio_queue_enter(bio)))
return BLK_QC_T_NONE;
if (!blk_crypto_bio_prep(&bio)) {
- blk_queue_exit(q);
+ blk_queue_exit(disk->queue);
return BLK_QC_T_NONE;
}
- return blk_mq_make_request(q, bio);
+ return blk_mq_submit_bio(bio);
}
EXPORT_SYMBOL_GPL(direct_make_request);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index dbadb7defd618a..948987e9b6ab3e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2136,8 +2136,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
}
/**
- * blk_mq_make_request - Create and send a request to block device.
- * @q: Request queue pointer.
+ * blk_mq_submit_bio - Create and send a request to block device.
* @bio: Bio pointer.
*
* Builds up a request structure from @q and @bio and send to the device. The
@@ -2151,8 +2150,9 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
*
* Returns: Request queue cookie.
*/
-blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t blk_mq_submit_bio(struct bio *bio)
{
+ struct request_queue *q = bio->bi_disk->queue;
const int is_sync = op_is_sync(bio->bi_opf);
const int is_flush_fua = op_is_flush(bio->bi_opf);
struct blk_mq_alloc_data data = {
@@ -2277,7 +2277,7 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_exit(q);
return BLK_QC_T_NONE;
}
-EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */
+EXPORT_SYMBOL_GPL(blk_mq_submit_bio); /* only for request based dm */
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
unsigned int hctx_idx)
@@ -3017,7 +3017,7 @@ struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
{
struct request_queue *uninit_q, *q;
- uninit_q = __blk_alloc_queue(set->numa_node);
+ uninit_q = blk_alloc_queue(set->numa_node);
if (!uninit_q)
return ERR_PTR(-ENOMEM);
uninit_q->queuedata = queuedata;
diff --git a/block/blk.h b/block/blk.h
index 0114fd92c8a05b..9dcf51c94096a7 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -419,8 +419,6 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
#endif
}
-struct request_queue *__blk_alloc_queue(int node_id);
-
int bio_add_hw_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
unsigned int max_sectors, bool *same_page);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 2fb25c348d531b..2723a70eb85593 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -282,7 +282,7 @@ static int brd_do_bvec(struct brd_device *brd, struct page *page,
return err;
}
-static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t brd_submit_bio(struct bio *bio)
{
struct brd_device *brd = bio->bi_disk->private_data;
struct bio_vec bvec;
@@ -330,6 +330,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
static const struct block_device_operations brd_fops = {
.owner = THIS_MODULE,
+ .submit_bio = brd_submit_bio,
.rw_page = brd_rw_page,
};
@@ -381,7 +382,7 @@ static struct brd_device *brd_alloc(int i)
spin_lock_init(&brd->brd_lock);
INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
- brd->brd_queue = blk_alloc_queue(brd_make_request, NUMA_NO_NODE);
+ brd->brd_queue = blk_alloc_queue(NUMA_NO_NODE);
if (!brd->brd_queue)
goto out_free_dev;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 33d0831c99b613..0327408da79c7a 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1451,7 +1451,7 @@ extern void conn_free_crypto(struct drbd_connection *connection);
/* drbd_req */
extern void do_submit(struct work_struct *ws);
extern void __drbd_make_request(struct drbd_device *, struct bio *, unsigned long);
-extern blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio);
+extern blk_qc_t drbd_submit_bio(struct bio *bio);
extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req);
extern int is_valid_ar_handle(struct drbd_request *, sector_t);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 26f4e0aa7393b4..2b05de0896e282 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -132,9 +132,10 @@ wait_queue_head_t drbd_pp_wait;
DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5);
static const struct block_device_operations drbd_ops = {
- .owner = THIS_MODULE,
- .open = drbd_open,
- .release = drbd_release,
+ .owner = THIS_MODULE,
+ .submit_bio = drbd_submit_bio,
+ .open = drbd_open,
+ .release = drbd_release,
};
struct bio *bio_alloc_drbd(gfp_t gfp_mask)
@@ -2801,7 +2802,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
drbd_init_set_defaults(device);
- q = blk_alloc_queue(drbd_make_request, NUMA_NO_NODE);
+ q = blk_alloc_queue(NUMA_NO_NODE);
if (!q)
goto out_no_q;
device->rq_queue = q;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 9368680474223a..c7e14c9a6e5f83 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1593,7 +1593,7 @@ void do_submit(struct work_struct *ws)
}
}
-blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t drbd_submit_bio(struct bio *bio)
{
struct drbd_device *device = bio->bi_disk->private_data;
unsigned long start_jif;
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 93ce0a00b2ae01..907c6858aec0c3 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -1388,7 +1388,7 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
return &nullb->queues[index];
}
-static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
+static blk_qc_t null_submit_bio(struct bio *bio)
{
sector_t sector = bio->bi_iter.bi_sector;
sector_t nr_sectors = bio_sectors(bio);
@@ -1575,7 +1575,13 @@ static void null_config_discard(struct nullb *nullb)
blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q);
}
-static const struct block_device_operations null_ops = {
+static const struct block_device_operations null_bio_ops = {
+ .owner = THIS_MODULE,
+ .submit_bio = null_submit_bio,
+ .report_zones = null_report_zones,
+};
+
+static const struct block_device_operations null_rq_ops = {
.owner = THIS_MODULE,
.report_zones = null_report_zones,
};
@@ -1647,7 +1653,10 @@ static int null_gendisk_register(struct nullb *nullb)
disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
disk->major = null_major;
disk->first_minor = nullb->index;
- disk->fops = &null_ops;
+ if (queue_is_mq(nullb->q))
+ disk->fops = &null_rq_ops;
+ else
+ disk->fops = &null_bio_ops;
disk->private_data = nullb;
disk->queue = nullb->q;
strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
@@ -1792,7 +1801,7 @@ static int null_add_dev(struct nullb_device *dev)
goto out_cleanup_tags;
}
} else if (dev->queue_mode == NULL_Q_BIO) {
- nullb->q = blk_alloc_queue(null_queue_bio, dev->home_node);
+ nullb->q = blk_alloc_queue(dev->home_node);
if (!nullb->q) {
rv = -ENOMEM;
goto out_cleanup_queues;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 29b0c62dc86c1f..5588bd4cd267e8 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -36,7 +36,7 @@
* block device, assembling the pieces to full packets and queuing them to the
* packet I/O scheduler.
*
- * At the top layer there is a custom make_request_fn function that forwards
+ * At the top layer there is a custom ->submit_bio function that forwards
* read requests directly to the iosched queue and puts write requests in the
* unaligned write queue. A kernel thread performs the necessary read
* gathering to convert the unaligned writes to aligned writes and then feeds
@@ -2428,7 +2428,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
}
}
-static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t pkt_submit_bio(struct bio *bio)
{
struct pktcdvd_device *pd;
char b[BDEVNAME_SIZE];
@@ -2436,7 +2436,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
blk_queue_split(&bio);
- pd = q->queuedata;
+ pd = bio->bi_disk->queue->queuedata;
if (!pd) {
pr_err("%s incorrect request queue\n", bio_devname(bio, b));
goto end_io;
@@ -2480,7 +2480,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
split = bio;
}
- pkt_make_request_write(q, split);
+ pkt_make_request_write(bio->bi_disk->queue, split);
} while (split != bio);
return BLK_QC_T_NONE;
@@ -2685,6 +2685,7 @@ static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
static const struct block_device_operations pktcdvd_ops = {
.owner = THIS_MODULE,
+ .submit_bio = pkt_submit_bio,
.open = pkt_open,
.release = pkt_close,
.ioctl = pkt_ioctl,
@@ -2749,7 +2750,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
disk->flags = GENHD_FL_REMOVABLE;
strcpy(disk->disk_name, pd->name);
disk->private_data = pd;
- disk->queue = blk_alloc_queue(pkt_make_request, NUMA_NO_NODE);
+ disk->queue = blk_alloc_queue(NUMA_NO_NODE);
if (!disk->queue)
goto out_mem2;
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 76cc584aa76346..1088798c8dd0c9 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -90,12 +90,6 @@ struct ps3vram_priv {
static int ps3vram_major;
-
-static const struct block_device_operations ps3vram_fops = {
- .owner = THIS_MODULE,
-};
-
-
#define DMA_NOTIFIER_HANDLE_BASE 0x66604200 /* first DMA notifier handle */
#define DMA_NOTIFIER_OFFSET_BASE 0x1000 /* first DMA notifier offset */
#define DMA_NOTIFIER_SIZE 0x40
@@ -585,7 +579,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev,
return next;
}
-static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t ps3vram_submit_bio(struct bio *bio)
{
struct ps3_system_bus_device *dev = bio->bi_disk->private_data;
struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -610,6 +604,11 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
return BLK_QC_T_NONE;
}
+static const struct block_device_operations ps3vram_fops = {
+ .owner = THIS_MODULE,
+ .submit_bio = ps3vram_submit_bio,
+};
+
static int ps3vram_probe(struct ps3_system_bus_device *dev)
{
struct ps3vram_priv *priv;
@@ -737,7 +736,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
ps3vram_proc_init(dev);
- queue = blk_alloc_queue(ps3vram_make_request, NUMA_NO_NODE);
+ queue = blk_alloc_queue(NUMA_NO_NODE);
if (!queue) {
dev_err(&dev->core, "blk_alloc_queue failed\n");
error = -ENOMEM;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 1d52bc73dd0f82..edacefff6e355b 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -50,6 +50,8 @@ struct rsxx_bio_meta {
static struct kmem_cache *bio_meta_pool;
+static blk_qc_t rsxx_submit_bio(struct bio *bio);
+
/*----------------- Block Device Operations -----------------*/
static int rsxx_blkdev_ioctl(struct block_device *bdev,
fmode_t mode,
@@ -92,6 +94,7 @@ static int rsxx_getgeo(struct block_device *bdev, struct hd_geometry *geo)
static const struct block_device_operations rsxx_fops = {
.owner = THIS_MODULE,
+ .submit_bio = rsxx_submit_bio,
.getgeo = rsxx_getgeo,
.ioctl = rsxx_blkdev_ioctl,
};
@@ -117,7 +120,7 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
}
}
-static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t rsxx_submit_bio(struct bio *bio)
{
struct rsxx_cardinfo *card = bio->bi_disk->private_data;
struct rsxx_bio_meta *bio_meta;
@@ -233,7 +236,7 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
return -ENOMEM;
}
- card->queue = blk_alloc_queue(rsxx_make_request, NUMA_NO_NODE);
+ card->queue = blk_alloc_queue(NUMA_NO_NODE);
if (!card->queue) {
dev_err(CARD_TO_DEV(card), "Failed queue alloc\n");
unregister_blkdev(card->major, DRIVER_NAME);
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 3b89c07f9e9d6e..2b95d7b33b9186 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -519,7 +519,7 @@ static int mm_check_plugged(struct cardinfo *card)
return !!blk_check_plugged(mm_unplug, card, sizeof(struct blk_plug_cb));
}
-static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t mm_submit_bio(struct bio *bio)
{
struct cardinfo *card = bio->bi_disk->private_data;
@@ -779,6 +779,7 @@ static int mm_getgeo(struct block_device *bdev, struct hd_geometry *geo)
static const struct block_device_operations mm_fops = {
.owner = THIS_MODULE,
+ .submit_bio = mm_submit_bio,
.getgeo = mm_getgeo,
.revalidate_disk = mm_revalidate,
};
@@ -886,7 +887,7 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
card->biotail = &card->bio;
spin_lock_init(&card->lock);
- card->queue = blk_alloc_queue(mm_make_request, NUMA_NO_NODE);
+ card->queue = blk_alloc_queue(NUMA_NO_NODE);
if (!card->queue)
goto failed_alloc;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 0564e3f384089e..f9a57f147ee1e6 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -793,9 +793,9 @@ static void zram_sync_read(struct work_struct *work)
}
/*
- * Block layer want one ->make_request_fn to be active at a time
- * so if we use chained IO with parent IO in same context,
- * it's a deadlock. To avoid, it, it uses worker thread context.
+ * Block layer want one ->submit_bio to be active at a time, so if we use
+ * chained IO with parent IO in same context, it's a deadlock. To avoid that,
+ * use a worker thread context.
*/
static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
unsigned long entry, struct bio *bio)
@@ -1584,7 +1584,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
/*
* Handler function for all zram I/O requests.
*/
-static blk_qc_t zram_make_request(struct request_queue *queue, struct bio *bio)
+static blk_qc_t zram_submit_bio(struct bio *bio)
{
struct zram *zram = bio->bi_disk->private_data;
@@ -1813,6 +1813,7 @@ static int zram_open(struct block_device *bdev, fmode_t mode)
static const struct block_device_operations zram_devops = {
.open = zram_open,
+ .submit_bio = zram_submit_bio,
.swap_slot_free_notify = zram_slot_free_notify,
.rw_page = zram_rw_page,
.owner = THIS_MODULE
@@ -1891,7 +1892,7 @@ static int zram_add(void)
#ifdef CONFIG_ZRAM_WRITEBACK
spin_lock_init(&zram->wb_limit_lock);
#endif
- queue = blk_alloc_queue(zram_make_request, NUMA_NO_NODE);
+ queue = blk_alloc_queue(NUMA_NO_NODE);
if (!queue) {
pr_err("Error allocating disk queue for device %d\n",
device_id);
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index db38a68abb6c03..fe78bf0fdce545 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -236,10 +236,6 @@ static struct nvm_tgt_dev *nvm_create_tgt_dev(struct nvm_dev *dev,
return tgt_dev;
}
-static const struct block_device_operations nvm_fops = {
- .owner = THIS_MODULE,
-};
-
static struct nvm_tgt_type *__nvm_find_target_type(const char *name)
{
struct nvm_tgt_type *tt;
@@ -380,7 +376,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
goto err_dev;
}
- tqueue = blk_alloc_queue(tt->make_rq, dev->q->node);
+ tqueue = blk_alloc_queue(dev->q->node);
if (!tqueue) {
ret = -ENOMEM;
goto err_disk;
@@ -390,7 +386,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
tdisk->flags = GENHD_FL_EXT_DEVT;
tdisk->major = 0;
tdisk->first_minor = 0;
- tdisk->fops = &nvm_fops;
+ tdisk->fops = tt->bops;
tdisk->queue = tqueue;
targetdata = tt->init(tgt_dev, tdisk, create->flags);
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 7a4a1b7a941d2c..b6246f73895cf8 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -47,9 +47,9 @@ static struct pblk_global_caches pblk_caches = {
struct bio_set pblk_bio_set;
-static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
+static blk_qc_t pblk_submit_bio(struct bio *bio)
{
- struct pblk *pblk = q->queuedata;
+ struct pblk *pblk = bio->bi_disk->queue->queuedata;
if (bio_op(bio) == REQ_OP_DISCARD) {
pblk_discard(pblk, bio);
@@ -79,6 +79,12 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
return BLK_QC_T_NONE;
}
+static const struct block_device_operations pblk_bops = {
+ .owner = THIS_MODULE,
+ .submit_bio = pblk_submit_bio,
+};
+
+
static size_t pblk_trans_map_size(struct pblk *pblk)
{
int entry_size = 8;
@@ -1280,7 +1286,7 @@ static struct nvm_tgt_type tt_pblk = {
.name = "pblk",
.version = {1, 0, 0},
- .make_rq = pblk_make_rq,
+ .bops = &pblk_bops,
.capacity = pblk_capacity,
.init = pblk_init,
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 7acf024e99f351..fc5702b10074d6 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1158,7 +1158,7 @@ static void quit_max_writeback_rate(struct cache_set *c,
/* Cached devices - read & write stuff */
-blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t cached_dev_submit_bio(struct bio *bio)
{
struct search *s;
struct bcache_device *d = bio->bi_disk->private_data;
@@ -1291,7 +1291,7 @@ static void flash_dev_nodata(struct closure *cl)
continue_at(cl, search_free, NULL);
}
-blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t flash_dev_submit_bio(struct bio *bio)
{
struct search *s;
struct closure *cl;
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index bb005c93dd7218..82b38366a95deb 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -37,10 +37,10 @@ unsigned int bch_get_congested(const struct cache_set *c);
void bch_data_insert(struct closure *cl);
void bch_cached_dev_request_init(struct cached_dev *dc);
-blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio);
+blk_qc_t cached_dev_submit_bio(struct bio *bio);
void bch_flash_dev_request_init(struct bcache_device *d);
-blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio);
+blk_qc_t flash_dev_submit_bio(struct bio *bio);
extern struct kmem_cache *bch_search_cache;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 21aa168113d30b..de13f6e916966d 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -680,7 +680,16 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
return d->ioctl(d, mode, cmd, arg);
}
-static const struct block_device_operations bcache_ops = {
+static const struct block_device_operations bcache_cached_ops = {
+ .submit_bio = cached_dev_submit_bio,
+ .open = open_dev,
+ .release = release_dev,
+ .ioctl = ioctl_dev,
+ .owner = THIS_MODULE,
+};
+
+static const struct block_device_operations bcache_flash_ops = {
+ .submit_bio = flash_dev_submit_bio,
.open = open_dev,
.release = release_dev,
.ioctl = ioctl_dev,
@@ -820,8 +829,8 @@ static void bcache_device_free(struct bcache_device *d)
}
static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
- sector_t sectors, make_request_fn make_request_fn,
- struct block_device *cached_bdev)
+ sector_t sectors, struct block_device *cached_bdev,
+ const struct block_device_operations *ops)
{
struct request_queue *q;
const size_t max_stripes = min_t(size_t, INT_MAX,
@@ -868,10 +877,10 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
d->disk->major = bcache_major;
d->disk->first_minor = idx_to_first_minor(idx);
- d->disk->fops = &bcache_ops;
+ d->disk->fops = ops;
d->disk->private_data = d;
- q = blk_alloc_queue(make_request_fn, NUMA_NO_NODE);
+ q = blk_alloc_queue(NUMA_NO_NODE);
if (!q)
return -ENOMEM;
@@ -1355,7 +1364,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
ret = bcache_device_init(&dc->disk, block_size,
dc->bdev->bd_part->nr_sects - dc->sb.data_offset,
- cached_dev_make_request, dc->bdev);
+ dc->bdev, &bcache_cached_ops);
if (ret)
return ret;
@@ -1468,7 +1477,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
kobject_init(&d->kobj, &bch_flash_dev_ktype);
if (bcache_device_init(d, block_bytes(c), u->sectors,
- flash_dev_make_request, NULL))
+ NULL, &bcache_flash_ops))
goto err;
bcache_device_attach(d, c, u - c->uuids);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5aa7a604f4cbc5..5acfaba3700dfc 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1770,7 +1770,7 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
}
/*
- * If in ->make_request_fn we need to use blk_queue_split(), otherwise
+ * If in ->queue_bio we need to use blk_queue_split(), otherwise
* queue_limits for abnormal requests (e.g. discard, writesame, etc)
* won't be imposed.
*/
@@ -1787,7 +1787,7 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
return __split_and_process_bio(md, map, bio);
}
-static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t dm_submit_bio(struct bio *bio)
{
struct mapped_device *md = bio->bi_disk->private_data;
blk_qc_t ret = BLK_QC_T_NONE;
@@ -1798,12 +1798,12 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
/*
* We are called with a live reference on q_usage_counter, but
* that one will be released as soon as we return. Grab an
- * extra one as blk_mq_make_request expects to be able to
- * consume a reference (which lives until the request is freed
- * in case a request is allocated).
+ * extra one as blk_mq_submit_bio expects to be able to consume
+ * a reference (which lives until the request is freed in case a
+ * request is allocated).
*/
- percpu_ref_get(&q->q_usage_counter);
- return blk_mq_make_request(q, bio);
+ percpu_ref_get(&bio->bi_disk->queue->q_usage_counter);
+ return blk_mq_submit_bio(bio);
}
map = dm_get_live_table(md, &srcu_idx);
@@ -1988,11 +1988,11 @@ static struct mapped_device *alloc_dev(int minor)
spin_lock_init(&md->uevent_lock);
/*
- * default to bio-based required ->make_request_fn until DM
- * table is loaded and md->type established. If request-based
- * table is loaded: blk-mq will override accordingly.
+ * default to bio-based until DM table is loaded and md->type
+ * established. If request-based table is loaded: blk-mq will
+ * override accordingly.
*/
- md->queue = blk_alloc_queue(dm_make_request, numa_node_id);
+ md->queue = blk_alloc_queue(numa_node_id);
if (!md->queue)
goto bad;
@@ -3232,6 +3232,7 @@ static const struct pr_ops dm_pr_ops = {
};
static const struct block_device_operations dm_blk_dops = {
+ .submit_bio = dm_submit_bio,
.open = dm_blk_open,
.release = dm_blk_close,
.ioctl = dm_blk_ioctl,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index ff20868e5e1b98..7b7cb49be35114 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -463,7 +463,7 @@ void md_handle_request(struct mddev *mddev, struct bio *bio)
}
EXPORT_SYMBOL(md_handle_request);
-static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t md_submit_bio(struct bio *bio)
{
const int rw = bio_data_dir(bio);
const int sgrp = op_stat_group(bio_op(bio));
@@ -5641,7 +5641,7 @@ static int md_alloc(dev_t dev, char *name)
mddev->hold_active = UNTIL_STOP;
error = -ENOMEM;
- mddev->queue = blk_alloc_queue(md_make_request, NUMA_NO_NODE);
+ mddev->queue = blk_alloc_queue(NUMA_NO_NODE);
if (!mddev->queue)
goto abort;
@@ -7823,6 +7823,7 @@ static int md_revalidate(struct gendisk *disk)
static const struct block_device_operations md_fops =
{
.owner = THIS_MODULE,
+ .submit_bio = md_submit_bio,
.open = md_open,
.release = md_release,
.ioctl = md_ioctl,
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 39030a324d7ffe..1f718381a04553 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -162,7 +162,7 @@ static int nsblk_do_bvec(struct nd_namespace_blk *nsblk,
return err;
}
-static blk_qc_t nd_blk_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t nd_blk_submit_bio(struct bio *bio)
{
struct bio_integrity_payload *bip;
struct nd_namespace_blk *nsblk = bio->bi_disk->private_data;
@@ -225,6 +225,7 @@ static int nsblk_rw_bytes(struct nd_namespace_common *ndns,
static const struct block_device_operations nd_blk_fops = {
.owner = THIS_MODULE,
+ .submit_bio = nd_blk_submit_bio,
.revalidate_disk = nvdimm_revalidate_disk,
};
@@ -250,7 +251,7 @@ static int nsblk_attach_disk(struct nd_namespace_blk *nsblk)
internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk));
available_disk_size = internal_nlba * nsblk_sector_size(nsblk);
- q = blk_alloc_queue(nd_blk_make_request, NUMA_NO_NODE);
+ q = blk_alloc_queue(NUMA_NO_NODE);
if (!q)
return -ENOMEM;
if (devm_add_action_or_reset(dev, nd_blk_release_queue, q))
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 48e9d169b6f9ce..412d21d8f64351 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1439,7 +1439,7 @@ static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
return ret;
}
-static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t btt_submit_bio(struct bio *bio)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
struct btt *btt = bio->bi_disk->private_data;
@@ -1512,6 +1512,7 @@ static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo)
static const struct block_device_operations btt_fops = {
.owner = THIS_MODULE,
+ .submit_bio = btt_submit_bio,
.rw_page = btt_rw_page,
.getgeo = btt_getgeo,
.revalidate_disk = nvdimm_revalidate_disk,
@@ -1523,7 +1524,7 @@ static int btt_blk_init(struct btt *btt)
struct nd_namespace_common *ndns = nd_btt->ndns;
/* create a new disk and request queue for btt */
- btt->btt_queue = blk_alloc_queue(btt_make_request, NUMA_NO_NODE);
+ btt->btt_queue = blk_alloc_queue(NUMA_NO_NODE);
if (!btt->btt_queue)
return -ENOMEM;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index d25e66fd942dd6..94790e6e0e4ce1 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -189,7 +189,7 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem,
return rc;
}
-static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t pmem_submit_bio(struct bio *bio)
{
int ret = 0;
blk_status_t rc = 0;
@@ -281,6 +281,7 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
static const struct block_device_operations pmem_fops = {
.owner = THIS_MODULE,
+ .submit_bio = pmem_submit_bio,
.rw_page = pmem_rw_page,
.revalidate_disk = nvdimm_revalidate_disk,
};
@@ -423,7 +424,7 @@ static int pmem_attach_disk(struct device *dev,
return -EBUSY;
}
- q = blk_alloc_queue(pmem_make_request, dev_to_node(dev));
+ q = blk_alloc_queue(dev_to_node(dev));
if (!q)
return -ENOMEM;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 6810c8812aed26..5192a024dc1b9c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2178,6 +2178,7 @@ static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode)
const struct block_device_operations nvme_ns_head_ops = {
.owner = THIS_MODULE,
+ .submit_bio = nvme_ns_head_submit_bio,
.open = nvme_ns_head_open,
.release = nvme_ns_head_release,
.ioctl = nvme_ioctl,
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5a5205ea570a77..89afcf943bf846 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -291,8 +291,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
return false;
}
-static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
- struct bio *bio)
+blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
{
struct nvme_ns_head *head = bio->bi_disk->private_data;
struct device *dev = disk_to_dev(head->disk);
@@ -374,7 +373,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath)
return 0;
- q = blk_alloc_queue(nvme_ns_head_make_request, ctrl->numa_node);
+ q = blk_alloc_queue(ctrl->numa_node);
if (!q)
goto out;
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 61780c38f51fdb..9f2b0e0b455871 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -586,6 +586,7 @@ void nvme_mpath_stop(struct nvme_ctrl *ctrl);
bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
+blk_qc_t nvme_ns_head_submit_bio(struct bio *bio);
static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
{
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index dfe21eb7276021..35666c3537dea9 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -31,8 +31,7 @@
static int dcssblk_open(struct block_device *bdev, fmode_t mode);
static void dcssblk_release(struct gendisk *disk, fmode_t mode);
-static blk_qc_t dcssblk_make_request(struct request_queue *q,
- struct bio *bio);
+static blk_qc_t dcssblk_submit_bio(struct bio *bio);
static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
long nr_pages, void **kaddr, pfn_t *pfn);
@@ -41,6 +40,7 @@ static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
static int dcssblk_major;
static const struct block_device_operations dcssblk_devops = {
.owner = THIS_MODULE,
+ .submit_bio = dcssblk_submit_bio,
.open = dcssblk_open,
.release = dcssblk_release,
};
@@ -651,8 +651,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
}
dev_info->gd->major = dcssblk_major;
dev_info->gd->fops = &dcssblk_devops;
- dev_info->dcssblk_queue =
- blk_alloc_queue(dcssblk_make_request, NUMA_NO_NODE);
+ dev_info->dcssblk_queue = blk_alloc_queue(NUMA_NO_NODE);
dev_info->gd->queue = dev_info->dcssblk_queue;
dev_info->gd->private_data = dev_info;
blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
@@ -868,7 +867,7 @@ dcssblk_release(struct gendisk *disk, fmode_t mode)
}
static blk_qc_t
-dcssblk_make_request(struct request_queue *q, struct bio *bio)
+dcssblk_submit_bio(struct bio *bio)
{
struct dcssblk_dev_info *dev_info;
struct bio_vec bvec;
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 5456f0ad5a40a4..c2536f7767b366 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -182,7 +182,7 @@ static unsigned long xpram_highest_page_index(void)
/*
* Block device make request function.
*/
-static blk_qc_t xpram_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t xpram_submit_bio(struct bio *bio)
{
xpram_device_t *xdev = bio->bi_disk->private_data;
struct bio_vec bvec;
@@ -250,6 +250,7 @@ static int xpram_getgeo(struct block_device *bdev, struct hd_geometry *geo)
static const struct block_device_operations xpram_devops =
{
.owner = THIS_MODULE,
+ .submit_bio = xpram_submit_bio,
.getgeo = xpram_getgeo,
};
@@ -343,8 +344,7 @@ static int __init xpram_setup_blkdev(void)
xpram_disks[i] = alloc_disk(1);
if (!xpram_disks[i])
goto out;
- xpram_queues[i] = blk_alloc_queue(xpram_make_request,
- NUMA_NO_NODE);
+ xpram_queues[i] = blk_alloc_queue(NUMA_NO_NODE);
if (!xpram_queues[i]) {
put_disk(xpram_disks[i]);
goto out;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index faa340b70123b1..23230c1d031e0a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -596,6 +596,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
rq->q->mq_ops->cleanup_rq(rq);
}
-blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio);
+blk_qc_t blk_mq_submit_bio(struct bio *bio);
#endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d002defc178934..083ffc5bc51b09 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -286,8 +286,6 @@ static inline unsigned short req_get_ioprio(struct request *req)
struct blk_queue_ctx;
-typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
-
struct bio_vec;
enum blk_eh_timer_return {
@@ -398,8 +396,6 @@ struct request_queue {
struct blk_queue_stats *stats;
struct rq_qos *rq_qos;
- make_request_fn *make_request_fn;
-
const struct blk_mq_ops *mq_ops;
/* sw queues */
@@ -1162,7 +1158,7 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
extern void blk_dump_rq_flags(struct request *, char *);
bool __must_check blk_get_queue(struct request_queue *);
-struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id);
+struct request_queue *blk_alloc_queue(int node_id);
extern void blk_put_queue(struct request_queue *);
extern void blk_set_queue_dying(struct request_queue *);
@@ -1778,6 +1774,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { }
struct block_device_operations {
+ blk_qc_t (*submit_bio) (struct bio *bio);
int (*open) (struct block_device *, fmode_t);
void (*release) (struct gendisk *, fmode_t);
int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index ee8ec2e68055af..1db223710b284a 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -631,7 +631,6 @@ static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev,
return last;
}
-typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
typedef sector_t (nvm_tgt_capacity_fn)(void *);
typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *,
int flags);
@@ -650,7 +649,7 @@ struct nvm_tgt_type {
int flags;
/* target entry points */
- nvm_tgt_make_rq_fn *make_rq;
+ const struct block_device_operations *bops;
nvm_tgt_capacity_fn *capacity;
/* module-specific init/teardown */
--
2.26.2
^ permalink raw reply related
* [PATCH 15/20] block: remove the nr_sectors variable in generic_make_request_checks
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
The variable is only used once, so just open code the bio_sector()
there.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-core.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 37435d0d433564..28f60985dc75cc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -974,7 +974,6 @@ static noinline_for_stack bool
generic_make_request_checks(struct bio *bio)
{
struct request_queue *q = bio->bi_disk->queue;
- int nr_sectors = bio_sectors(bio);
blk_status_t status = BLK_STS_IOERR;
might_sleep();
@@ -1007,7 +1006,7 @@ generic_make_request_checks(struct bio *bio)
if (op_is_flush(bio->bi_opf) &&
!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
- if (!nr_sectors) {
+ if (!bio_sectors(bio)) {
status = BLK_STS_OK;
goto end_io;
}
--
2.26.2
^ permalink raw reply related
* [PATCH 12/20] block: remove the request_queue argument from blk_queue_split
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
The queue can be trivially derived from the bio, so pass one less
argument.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-merge.c | 21 ++++++++++-----------
block/blk-mq.c | 2 +-
block/blk.h | 3 +--
drivers/block/drbd/drbd_req.c | 2 +-
drivers/block/pktcdvd.c | 2 +-
drivers/block/ps3vram.c | 2 +-
drivers/block/rsxx/dev.c | 2 +-
drivers/block/umem.c | 2 +-
drivers/lightnvm/pblk-init.c | 4 ++--
drivers/md/dm.c | 2 +-
drivers/md/md.c | 2 +-
drivers/nvme/host/multipath.c | 9 ++++-----
drivers/s390/block/dcssblk.c | 2 +-
drivers/s390/block/xpram.c | 2 +-
include/linux/blkdev.h | 2 +-
15 files changed, 28 insertions(+), 31 deletions(-)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 9c9fb21584b64e..20fa2290604105 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -283,20 +283,20 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
/**
* __blk_queue_split - split a bio and submit the second half
- * @q: [in] request queue pointer
* @bio: [in, out] bio to be split
* @nr_segs: [out] number of segments in the first bio
*
* Split a bio into two bios, chain the two bios, submit the second half and
* store a pointer to the first half in *@bio. If the second bio is still too
* big it will be split by a recursive call to this function. Since this
- * function may allocate a new bio from @q->bio_split, it is the responsibility
- * of the caller to ensure that @q is only released after processing of the
+ * function may allocate a new bio from @bio->bi_disk->queue->bio_split, it is
+ * the responsibility of the caller to ensure that
+ * @bio->bi_disk->queue->bio_split is only released after processing of the
* split bio has finished.
*/
-void __blk_queue_split(struct request_queue *q, struct bio **bio,
- unsigned int *nr_segs)
+void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
{
+ struct request_queue *q = (*bio)->bi_disk->queue;
struct bio *split = NULL;
switch (bio_op(*bio)) {
@@ -345,20 +345,19 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
/**
* blk_queue_split - split a bio and submit the second half
- * @q: [in] request queue pointer
* @bio: [in, out] bio to be split
*
* Split a bio into two bios, chains the two bios, submit the second half and
* store a pointer to the first half in *@bio. Since this function may allocate
- * a new bio from @q->bio_split, it is the responsibility of the caller to
- * ensure that @q is only released after processing of the split bio has
- * finished.
+ * a new bio from @bio->bi_disk->queue->bio_split, it is the responsibility of
+ * the caller to ensure that @bio->bi_disk->queue->bio_split is only released
+ * after processing of the split bio has finished.
*/
-void blk_queue_split(struct request_queue *q, struct bio **bio)
+void blk_queue_split(struct bio **bio)
{
unsigned int nr_segs;
- __blk_queue_split(q, bio, &nr_segs);
+ __blk_queue_split(bio, &nr_segs);
}
EXPORT_SYMBOL(blk_queue_split);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 65e0846fd06519..dbadb7defd618a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2166,7 +2166,7 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_status_t ret;
blk_queue_bounce(q, &bio);
- __blk_queue_split(q, &bio, &nr_segs);
+ __blk_queue_split(&bio, &nr_segs);
if (!bio_integrity_prep(bio))
goto queue_exit;
diff --git a/block/blk.h b/block/blk.h
index 0184a31fe4dfaf..0114fd92c8a05b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -220,8 +220,7 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
ssize_t part_timeout_store(struct device *, struct device_attribute *,
const char *, size_t);
-void __blk_queue_split(struct request_queue *q, struct bio **bio,
- unsigned int *nr_segs);
+void __blk_queue_split(struct bio **bio, unsigned int *nr_segs);
int ll_back_merge_fn(struct request *req, struct bio *bio,
unsigned int nr_segs);
int ll_front_merge_fn(struct request *req, struct bio *bio,
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3f09b2ab977822..9368680474223a 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1598,7 +1598,7 @@ blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
struct drbd_device *device = bio->bi_disk->private_data;
unsigned long start_jif;
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
start_jif = jiffies;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 27a33adc41e487..29b0c62dc86c1f 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2434,7 +2434,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
char b[BDEVNAME_SIZE];
struct bio *split;
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
pd = q->queuedata;
if (!pd) {
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 5a1d1d137c7248..76cc584aa76346 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -593,7 +593,7 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
dev_dbg(&dev->core, "%s\n", __func__);
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
spin_lock_irq(&priv->lock);
busy = !bio_list_empty(&priv->list);
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 6a4d8d26e32cbd..1d52bc73dd0f82 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -123,7 +123,7 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
struct rsxx_bio_meta *bio_meta;
blk_status_t st = BLK_STS_IOERR;
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
might_sleep();
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 5498f1cf36b3fe..3b89c07f9e9d6e 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -527,7 +527,7 @@ static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio)
(unsigned long long)bio->bi_iter.bi_sector,
bio->bi_iter.bi_size);
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
spin_lock_irq(&card->lock);
*card->biotail = bio;
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 6e677ff62cc969..7a4a1b7a941d2c 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -63,7 +63,7 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
* constraint. Writes can be of arbitrary size.
*/
if (bio_data_dir(bio) == READ) {
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
pblk_submit_read(pblk, bio);
} else {
/* Prevent deadlock in the case of a modest LUN configuration
@@ -71,7 +71,7 @@ static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
* leaves at least 256KB available for user I/O.
*/
if (pblk_get_secs(bio) > pblk_rl_max_io(&pblk->rl))
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER);
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c8d91f271c272e..5aa7a604f4cbc5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1776,7 +1776,7 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
*/
if (current->bio_list) {
if (is_abnormal_io(bio))
- blk_queue_split(md->queue, &bio);
+ blk_queue_split(&bio);
else
dm_queue_split(md, ti, &bio);
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f567f536b529bd..ff20868e5e1b98 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -475,7 +475,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
return BLK_QC_T_NONE;
}
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
if (mddev == NULL || mddev->pers == NULL) {
bio_io_error(bio);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index da78e499947a9f..5a5205ea570a77 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -301,12 +301,11 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
int srcu_idx;
/*
- * The namespace might be going away and the bio might
- * be moved to a different queue via blk_steal_bios(),
- * so we need to use the bio_split pool from the original
- * queue to allocate the bvecs from.
+ * The namespace might be going away and the bio might be moved to a
+ * different queue via blk_steal_bios(), so we need to use the bio_split
+ * pool from the original queue to allocate the bvecs from.
*/
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
srcu_idx = srcu_read_lock(&head->srcu);
ns = nvme_find_path(head);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 384edffe5cb4ae..dfe21eb7276021 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -878,7 +878,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
unsigned long source_addr;
unsigned long bytes_done;
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
bytes_done = 0;
dev_info = bio->bi_disk->private_data;
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 45a04daec89ed9..5456f0ad5a40a4 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -191,7 +191,7 @@ static blk_qc_t xpram_make_request(struct request_queue *q, struct bio *bio)
unsigned long page_addr;
unsigned long bytes;
- blk_queue_split(q, &bio);
+ blk_queue_split(&bio);
if ((bio->bi_iter.bi_sector & 7) != 0 ||
(bio->bi_iter.bi_size & 4095) != 0)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 15497782c17656..d002defc178934 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -871,7 +871,7 @@ extern void blk_rq_unprep_clone(struct request *rq);
extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
extern int blk_rq_append_bio(struct request *rq, struct bio **bio);
-extern void blk_queue_split(struct request_queue *, struct bio **);
+extern void blk_queue_split(struct bio **);
extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
unsigned int, void __user *);
--
2.26.2
^ permalink raw reply related
* [PATCH 14/20] block: remove the NULL queue check in generic_make_request_checks
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
All registers disks must have a valid queue pointer, so don't bother to
log a warning for that case.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-core.c | 12 +-----------
1 file changed, 1 insertion(+), 11 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 95dca74534ff73..37435d0d433564 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -973,22 +973,12 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
static noinline_for_stack bool
generic_make_request_checks(struct bio *bio)
{
- struct request_queue *q;
+ struct request_queue *q = bio->bi_disk->queue;
int nr_sectors = bio_sectors(bio);
blk_status_t status = BLK_STS_IOERR;
- char b[BDEVNAME_SIZE];
might_sleep();
- q = bio->bi_disk->queue;
- if (unlikely(!q)) {
- printk(KERN_ERR
- "generic_make_request: Trying to access "
- "nonexistent block-device %s (%Lu)\n",
- bio_devname(bio, b), (long long)bio->bi_iter.bi_sector);
- goto end_io;
- }
-
/*
* For a REQ_NOWAIT based request, return -EOPNOTSUPP
* if queue is not a request based queue.
--
2.26.2
^ permalink raw reply related
* [PATCH 13/20] block: tidy up a warning in bio_check_ro
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
The "generic_make_request: " prefix has no value, and will soon become
stale.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/blk-core.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 76cfd5709f66cd..95dca74534ff73 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -869,8 +869,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
return false;
WARN_ONCE(1,
- "generic_make_request: Trying to write "
- "to read-only block-device %s (partno %d)\n",
+ "Trying to write to read-only block-device %s (partno %d)\n",
bio_devname(bio, b), part->partno);
/* Older lvm-tools actually trigger this */
return false;
--
2.26.2
^ permalink raw reply related
* [PATCH 11/20] fs: remove a weird comment in submit_bh_wbc
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
All bios can get remapped if submitted to partitions. No need to
comment on that.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/buffer.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 64fe82ec65ff1f..2725ebbcfdc246 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3040,12 +3040,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
clear_buffer_write_io_error(bh);
- /*
- * from here on down, it's all bio -- do the initial mapping,
- * submit_bio -> generic_make_request may further map this bio around
- */
bio = bio_alloc(GFP_NOIO, 1);
-
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio_set_dev(bio, bh->b_bdev);
bio->bi_write_hint = write_hint;
--
2.26.2
^ permalink raw reply related
* [PATCH 10/20] dm: stop using ->queuedata
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
Instead of setting up the queuedata as well just use one private data
field.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/md/dm.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e44473fe0f4873..c8d91f271c272e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1789,7 +1789,7 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
{
- struct mapped_device *md = q->queuedata;
+ struct mapped_device *md = bio->bi_disk->private_data;
blk_qc_t ret = BLK_QC_T_NONE;
int srcu_idx;
struct dm_table *map;
@@ -1995,7 +1995,6 @@ static struct mapped_device *alloc_dev(int minor)
md->queue = blk_alloc_queue(dm_make_request, numa_node_id);
if (!md->queue)
goto bad;
- md->queue->queuedata = md;
md->disk = alloc_disk_node(1, md->numa_node_id);
if (!md->disk)
--
2.26.2
^ permalink raw reply related
* [PATCH 02/20] simdisk: stop using ->queuedata
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
Instead of setting up the queuedata as well just use one private data
field.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/xtensa/platforms/iss/simdisk.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 49322b66cda931..31b5020077a059 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -103,7 +103,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
static blk_qc_t simdisk_make_request(struct request_queue *q, struct bio *bio)
{
- struct simdisk *dev = q->queuedata;
+ struct simdisk *dev = bio->bi_disk->private_data;
struct bio_vec bvec;
struct bvec_iter iter;
sector_t sector = bio->bi_iter.bi_sector;
@@ -273,8 +273,6 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
goto out_alloc_queue;
}
- dev->queue->queuedata = dev;
-
dev->gd = alloc_disk(SIMDISK_MINORS);
if (dev->gd == NULL) {
pr_err("alloc_disk failed\n");
--
2.26.2
^ permalink raw reply related
* [PATCH 09/20] bcache: stop setting ->queuedata
From: Christoph Hellwig @ 2020-07-01 8:59 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-bcache, linux-xtensa, linux-nvdimm, linux-s390, dm-devel,
linux-nvme, linux-kernel, linux-raid, linux-m68k, linuxppc-dev,
drbd-dev
In-Reply-To: <20200701085947.3354405-1-hch@lst.de>
Nothing in bcache actually uses the ->queuedata field.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/md/bcache/super.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2014016f9a60d3..21aa168113d30b 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -876,7 +876,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
return -ENOMEM;
d->disk->queue = q;
- q->queuedata = d;
q->backing_dev_info->congested_data = d;
q->limits.max_hw_sectors = UINT_MAX;
q->limits.max_sectors = UINT_MAX;
--
2.26.2
^ 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