- Linuxarm - mailweb.openeuler.org

[PATCH] dma-mapping: benchmark: Add support for multi-pages map/unmap
by chenxiang 02 Apr '21

02 Apr '21

From: Xiang Chen <chenxiang66(a)hisilicon.com> Currently it only support one page map/unmap once a time for dma-map benchmark, but there are some other scenaries which need to support for multi-page map/unmap: for those multi-pages interfaces such as dma_alloc_coherent() and dma_map_sg(), the time spent on multi-pages map/unmap is not the time of a single page * npages (not linear) as it may use block description instead of page description when it is satified with the size such as 2M/1G, and also it can send a single TLB invalidation command to invalidate multi-pages instead of multi-times when RIL is enabled (which will short the time of unmap). So it is necessary to add support for multi-pages map/unmap. Add a parameter "-g" to support multi-pages map/unmap. Signed-off-by: Xiang Chen <chenxiang66(a)hisilicon.com> --- kernel/dma/map_benchmark.c | 21 ++++++++++++++------- tools/testing/selftests/dma/dma_map_benchmark.c | 20 ++++++++++++++++---- 2 files changed, 30 insertions(+), 11 deletions(-) diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index e0e64f8..a5c1b01 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -38,7 +38,8 @@ struct map_benchmark { __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ - __u8 expansion[80]; /* For future use */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; struct map_benchmark_data { @@ -58,9 +59,11 @@ static int map_benchmark_thread(void *data) void *buf; dma_addr_t dma_addr; struct map_benchmark_data *map = data; + int npages = map->bparam.granule; + u64 size = npages * PAGE_SIZE; int ret = 0; - buf = (void *)__get_free_page(GFP_KERNEL); + buf = alloc_pages_exact(size, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -76,10 +79,10 @@ static int map_benchmark_thread(void *data) * 66 means evertything goes well! 66 is lucky. */ if (map->dir != DMA_FROM_DEVICE) - memset(buf, 0x66, PAGE_SIZE); + memset(buf, 0x66, size); map_stime = ktime_get(); - dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir); + dma_addr = dma_map_single(map->dev, buf, size, map->dir); if (unlikely(dma_mapping_error(map->dev, dma_addr))) { pr_err("dma_map_single failed on %s\n", dev_name(map->dev)); @@ -93,7 +96,7 @@ static int map_benchmark_thread(void *data) ndelay(map->bparam.dma_trans_ns); unmap_stime = ktime_get(); - dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir); + dma_unmap_single(map->dev, dma_addr, size, map->dir); unmap_etime = ktime_get(); unmap_delta = ktime_sub(unmap_etime, unmap_stime); @@ -112,7 +115,7 @@ static int map_benchmark_thread(void *data) } out: - free_page((unsigned long)buf); + free_pages_exact(buf, size); return ret; } @@ -203,7 +206,6 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, struct map_benchmark_data *map = file->private_data; void __user *argp = (void __user *)arg; u64 old_dma_mask; - int ret; if (copy_from_user(&map->bparam, argp, sizeof(map->bparam))) @@ -234,6 +236,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, return -EINVAL; } + if (map->bparam.granule < 1 || map->bparam.granule > 1024) { + pr_err("invalid granule size\n"); + return -EINVAL; + } + switch (map->bparam.dma_dir) { case DMA_MAP_BIDIRECTIONAL: map->dir = DMA_BIDIRECTIONAL; diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index fb23ce9..6f2caa6 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -40,7 +40,8 @@ struct map_benchmark { __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ - __u8 expansion[80]; /* For future use */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; int main(int argc, char **argv) @@ -51,11 +52,13 @@ int main(int argc, char **argv) int threads = 1, seconds = 20, node = -1; /* default dma mask 32bit, bidirectional DMA */ int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL; + /* default granule 1 PAGESIZE */ + int granule = 1; int cmd = DMA_MAP_BENCHMARK; char *p; - while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) { + while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:")) != -1) { switch (opt) { case 't': threads = atoi(optarg); @@ -75,6 +78,9 @@ int main(int argc, char **argv) case 'x': xdelay = atoi(optarg); break; + case 'g': + granule = atoi(optarg); + break; default: return -1; } @@ -110,6 +116,11 @@ int main(int argc, char **argv) exit(1); } + if (granule < 1 || granule > 1024) { + fprintf(stderr, "invalid granule size\n"); + exit(1); + } + fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR); if (fd == -1) { perror("open"); @@ -123,14 +134,15 @@ int main(int argc, char **argv) map.dma_bits = bits; map.dma_dir = dir; map.dma_trans_ns = xdelay; + map.granule = granule; if (ioctl(fd, cmd, &map)) { perror("ioctl"); exit(1); } - printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s\n", - threads, seconds, node, dir[directions]); + printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n", + threads, seconds, node, dir[directions], granule); printf("average map latency(us):%.1f standard deviation:%.1f\n", map.avg_map_100ns/10.0, map.map_stddev/10.0); printf("average unmap latency(us):%.1f standard deviation:%.1f\n", -- 2.8.1

3 2

[PATCH] tty: pty: Add a blank line after declarations
by Xiaofei Tan 02 Apr '21

02 Apr '21

Add a blank line after declarations, reported by checkpatch.pl. Signed-off-by: Xiaofei Tan <tanxiaofei(a)huawei.com> --- drivers/tty/pty.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 5e23745..106265a 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -159,6 +159,7 @@ static int pty_chars_in_buffer(struct tty_struct *tty) static int pty_set_lock(struct tty_struct *tty, int __user *arg) { int val; + if (get_user(val, arg)) return -EFAULT; if (val) @@ -171,6 +172,7 @@ static int pty_set_lock(struct tty_struct *tty, int __user *arg) static int pty_get_lock(struct tty_struct *tty, int __user *arg) { int locked = test_bit(TTY_PTY_LOCK, &tty->flags); + return put_user(locked, arg); } @@ -200,6 +202,7 @@ static int pty_set_pktmode(struct tty_struct *tty, int __user *arg) static int pty_get_pktmode(struct tty_struct *tty, int __user *arg) { int pktmode = tty->packet; + return put_user(pktmode, arg); } @@ -463,6 +466,7 @@ static int pty_install(struct tty_driver *driver, struct tty_struct *tty) static void pty_remove(struct tty_driver *driver, struct tty_struct *tty) { struct tty_struct *pair = tty->link; + driver->ttys[tty->index] = NULL; if (pair) pair->driver->ttys[pair->index] = NULL; -- 2.8.1

1 0

[PATCH v2 00/15] acpi: fix some coding style issues
by Xiaofei Tan 02 Apr '21

02 Apr '21

Fix some coding style issues reported by checkpatch.pl. Differences from v1 to v2: - Add subsystem and module name in the name of patch 05/15. - Change to use more proper module name for some patch names. Xiaofei Tan (15): ACPI: APD: fix a block comment align issue ACPI: processor: fix some coding style issues ACPI: debug: fix some coding style issues ACPI: table: replace __attribute__((packed)) by __packed ACPI: ipmi: remove useless return statement for void function ACPI: LPSS: fix some coding style issues ACPI: memhotplug: fix a coding style issue ACPI: acpi_pad: fix a coding style issue ACPI: battery: fix some coding style issues ACPI: button: fix some coding style issues ACPI: CPPC: fix some coding style issues ACPI: custom_method: fix a coding style issue ACPI: PM: fix some coding style issues ACPI: sysfs: fix some coding style issues ACPI: dock: fix some coding style issues drivers/acpi/acpi_apd.c | 8 ++--- drivers/acpi/acpi_dbg.c | 40 +++++++++++------------- drivers/acpi/acpi_fpdt.c | 6 ++-- drivers/acpi/acpi_ipmi.c | 1 - drivers/acpi/acpi_lpss.c | 4 ++- drivers/acpi/acpi_memhotplug.c | 2 +- drivers/acpi/acpi_pad.c | 4 +++ drivers/acpi/acpi_processor.c | 18 +++-------- drivers/acpi/battery.c | 64 +++++++++++++++++++++---------------- drivers/acpi/button.c | 10 +++--- drivers/acpi/cppc_acpi.c | 71 +++++++++++++++++++++--------------------- drivers/acpi/custom_method.c | 2 +- drivers/acpi/device_pm.c | 3 ++ drivers/acpi/device_sysfs.c | 15 ++++++--- drivers/acpi/dock.c | 7 +++-- 15 files changed, 138 insertions(+), 117 deletions(-) -- 2.8.1

7 36

[PATCH v1] ata: ahci: Disable SXS for Hisilicon Kunpeng920
by Luo Jiaxing 31 Mar '21

31 Mar '21

From: Xingui Yang <yangxingui(a)huawei.com> On Hisilicon Kunpeng920, ESP is set to 1 by default for all ports of SATA controller. In some scenarios, some ports are not external SATA ports, and it cause disks connected to these ports to be identified as removable disks. So disable the SXS capability on the software side to prevent users from mistakenly considering non-removable disks as removable disks and performing related operations. Signed-off-by: Xingui Yang <yangxingui(a)huawei.com> Signed-off-by: Luo Jiaxing <luojiaxing(a)huawei.com> Reviewed-by: John Garry <john.garry(a)huawei.com> --- drivers/ata/ahci.c | 5 +++++ drivers/ata/ahci.h | 1 + drivers/ata/libahci.c | 5 +++++ 3 files changed, 11 insertions(+) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 00ba8e5..33192a8 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1772,6 +1772,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) hpriv->flags |= AHCI_HFLAG_NO_DEVSLP; #ifdef CONFIG_ARM64 + if (pdev->vendor == PCI_VENDOR_ID_HUAWEI && + pdev->device == 0xa235 && + pdev->revision < 0x30) + hpriv->flags |= AHCI_HFLAG_NO_SXS; + if (pdev->vendor == 0x177d && pdev->device == 0xa01c) hpriv->irq_handler = ahci_thunderx_irq_handler; #endif diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 98b8baa..d1f284f 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -242,6 +242,7 @@ enum { suspend/resume */ AHCI_HFLAG_IGN_NOTSUPP_POWER_ON = (1 << 27), /* ignore -EOPNOTSUPP from phy_power_on() */ + AHCI_HFLAG_NO_SXS = (1 << 28), /* SXS not supported */ /* ap->flags bits */ diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index ea5bf5f..fec2e97 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -493,6 +493,11 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) cap |= HOST_CAP_ALPM; } + if ((cap & HOST_CAP_SXS) && (hpriv->flags & AHCI_HFLAG_NO_SXS)) { + dev_info(dev, "controller does not support SXS, disabling CAP_SXS\n"); + cap &= ~HOST_CAP_SXS; + } + if (hpriv->force_port_map && port_map != hpriv->force_port_map) { dev_info(dev, "forcing port_map 0x%x -> 0x%x\n", port_map, hpriv->force_port_map); -- 2.7.4

3 4

[PATCH RFC for-next 1/1] arm64: sve: Fix some compile errors about sve_cond_update_zcr_vq
by Xiaofei Tan 31 Mar '21

31 Mar '21

There are some compile errors of ARM64 KVM when ARM64_SVE is not selected, in the locations of sve_cond_update_zcr_vq used. One error log is as following: CC arch/arm64/kvm/sys_regs.o In file included from arch/arm64/kvm/hyp/vhe/switch.c:8:0: ./arch/arm64/kvm/hyp/include/hyp/switch.h: In function ‘__hyp_sve_restore_guest’: ./arch/arm64/kvm/hyp/include/hyp/switch.h:220:2: error: implicit declaration of function ‘sve_cond_update_zcr_vq’; did you mean ‘kvm_pmu_update_run’? [-Werror=implicit-function-declaration] sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); ^~~~~~~~~~~~~~~~~~~~~~ kvm_pmu_update_run The root cause is that sve_cond_update_zcr_vq is not defined when ARM64_SVE is not selected. Fix it by adding an empty definition when CONFIG_ARM64_SVE=n. Signed-off-by: Xiaofei Tan <tanxiaofei(a)huawei.com> --- arch/arm64/include/asm/fpsimd.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 05c9c55..3f93b63 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -168,6 +168,8 @@ static inline int sve_get_current_vl(void) static inline void sve_user_disable(void) { BUILD_BUG(); } static inline void sve_user_enable(void) { BUILD_BUG(); } +#define sve_cond_update_zcr_vq(val, reg) + static inline void sve_init_vq_map(void) { } static inline void sve_update_vq_map(void) { } static inline int sve_verify_vq_map(void) { return 0; } -- 2.8.1

2 1

[RESEND net-next 0/4] net: remove repeated words
by Huazhong Tan 31 Mar '21

31 Mar '21

This patch-set removes some repeated words in comments. Peng Li (4): net: i40e: remove repeated words net: bonding: remove repeated word net: phy: remove repeated word net: ipa: remove repeated words drivers/net/bonding/bond_alb.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- drivers/net/ipa/ipa_endpoint.c | 4 ++-- drivers/net/phy/mdio_bus.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) -- 2.7.4

6 9

[PATCH v2] iommu/arm-smmu-v3: Add a check to avoid invalid iotlb sync
by chenxiang 30 Mar '21

30 Mar '21

From: Xiang Chen <chenxiang66(a)hisilicon.com> It may send a invalid tlb sync for smmuv3 if iotlb_gather is not valid (iotlb_gather->pgsize = 0). So add a check to avoid invalid iotlb sync for it. Signed-off-by: Xiang Chen <chenxiang66(a)hisilicon.com> --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 8594b4a..941ba54 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2305,6 +2305,9 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + if (!gather->pgsize) + return; + arm_smmu_tlb_inv_range_domain(gather->start, gather->end - gather->start + 1, gather->pgsize, true, smmu_domain); -- 2.8.1

2 1

[PATCH] iommu: Add a check to avoid invalid iotlb sync
by chenxiang 30 Mar '21

30 Mar '21

From: Xiang Chen <chenxiang66(a)hisilicon.com> Currently it will send a iotlb sync at end of iommu unmap even if iotlb_gather is not valid (iotlb_gather->pgsize = 0). Actually it is not necessary, so add a check to avoid invalid iotlb sync. Signed-off-by: Xiang Chen <chenxiang66(a)hisilicon.com> --- include/linux/iommu.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9ca6e6b..6afa61b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -529,6 +529,9 @@ static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) static inline void iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { + if (!iotlb_gather->pgsize) + return; + if (domain->ops->iotlb_sync) domain->ops->iotlb_sync(domain, iotlb_gather); -- 2.8.1

4 5

[PATCH net-next 0/4] net: remove repeated words
by Huazhong Tan 30 Mar '21

30 Mar '21

This patch-set removes some repeated words in comments. Peng Li (4): net: i40e: remove repeated words net: bonding: remove repeated word net: phy: remove repeated word net: ipa: remove repeated words drivers/net/bonding/bond_alb.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- drivers/net/ipa/ipa_endpoint.c | 4 ++-- drivers/net/phy/mdio_bus.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) -- 2.7.4

1 5

Re: [PATCH] libata: Increase the timeout of command ATA_CMD_READ_LOG_DMA_EXT
by chenxiang (M) 30 Mar '21

30 Mar '21

Ping.... 在 2020/10/15 9:57, chenxiang 写道: > From: Xiang Chen <chenxiang66(a)hisilicon.com> > > ATA_CMD_READ_LOG_DMA_EXT command normally uses the common internal command > default timeout (5s), and it is adequate in most situations. But it is not > enough for some disks such as ST4000NM0035 which causes qc timeout > sometimes as follows: > ... > [ 157.284284] sas: Enter sas_scsi_recover_host busy: 0 failed: 0 > [ 157.290124] sas: ata8: end_device-4:0:2: dev error handler > [ 157.290128] sas: ata9: end_device-4:0:8: dev error handler > [ 157.290131] sas: ata10: end_device-4:0:11: dev error handler > [ 164.588391] ata9.00: qc timeout (cmd 0x47) > [ 164.588393] ata8.00: qc timeout (cmd 0x47) > [ 164.588395] ata10.00: qc timeout (cmd 0x47) > [ 166.582572] ata10.00: READ LOG DMA EXT failed, trying PIO > [ 166.587960] ata10.00: NCQ Send/Recv Log not supported > [ 166.592997] ata10.00: ATA-10: ST4000NM0035-1V4107, TN03, max UDMA/133 > [ 166.599414] ata10.00: 7814037168 sectors, multi 0: LBA48 NCQ (depth 32) > [ 166.606011] ata10.00: failed to set xfermode (err_mask=0x40) > [ 166.659253] ata8.00: READ LOG DMA EXT failed, trying PIO > [ 166.664559] ata8.00: NCQ Send/Recv Log not supported > [ 166.669506] ata8.00: ATA-10: ST4000NM0035-1V4107, TN03, max UDMA/133 > [ 166.675837] ata8.00: 7814037168 sectors, multi 0: LBA48 NCQ (depth 32) > [ 166.682343] ata8.00: failed to set xfermode (err_mask=0x40) > [ 166.743458] ata9.00: READ LOG DMA EXT failed, trying PIO > [ 166.748765] ata9.00: NCQ Send/Recv Log not supported > [ 166.753713] ata9.00: ATA-10: ST4000NM0035-1V4107, TN03, max UDMA/133 > [ 166.760045] ata9.00: 7814037168 sectors, multi 0: LBA48 NCQ (depth 32) > [ 166.766553] ata9.00: failed to set xfermode (err_mask=0x40) > [ 168.886378] ata10.00: configured for UDMA/133 > [ 168.999943] ata8.00: configured for UDMA/133 > [ 169.050801] ata9.00: configured for UDMA/133 > [ 169.055071] sas: --- Exit sas_scsi_recover_host: busy: 0 failed: 0 tries: 1 > ... > Actually it may takes about 9s to complete the command for disk ST4000NM0035 > sometimes. So to avoid the issue, increase the timeout of command > ATA_CMD_READ_LOG_DMA_EXT from 5s to 15s. > > Signed-off-by: Xiang Chen <chenxiang66(a)hisilicon.com> > Reviewed-by: John Garry <john.garry(a)huawei.com> > --- > drivers/ata/libata-eh.c | 9 +++++++++ > include/linux/libata.h | 2 +- > 2 files changed, 10 insertions(+), 1 deletion(-) > > diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c > index 474c6c3..6db9474 100644 > --- a/drivers/ata/libata-eh.c > +++ b/drivers/ata/libata-eh.c > @@ -100,6 +100,13 @@ static const unsigned long ata_eh_flush_timeouts[] = { > ULONG_MAX, > }; > > +static const unsigned long ata_eh_read_log_ext_timeouts[] = { > + 15000, > + 15000, > + 30000, > + ULONG_MAX, > +}; > + > static const unsigned long ata_eh_other_timeouts[] = { > 5000, /* same rationale as identify timeout */ > 10000, /* ditto */ > @@ -139,6 +146,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = { > .timeouts = ata_eh_other_timeouts, }, > { .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT), > .timeouts = ata_eh_flush_timeouts }, > + { .commands = CMDS(ATA_CMD_READ_LOG_DMA_EXT, ATA_CMD_READ_LOG_EXT), > + .timeouts = ata_eh_read_log_ext_timeouts }, > }; > #undef CMDS > > diff --git a/include/linux/libata.h b/include/linux/libata.h > index b0bd30e..bcc68b3 100644 > --- a/include/linux/libata.h > +++ b/include/linux/libata.h > @@ -390,7 +390,7 @@ enum { > /* This should match the actual table size of > * ata_eh_cmd_timeout_table in libata-eh.c. > */ > - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 6, > + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7, > > /* Horkage types. May be set by libata or controller on drives > (some horkage may be drive/controller pair dependent */

1 0