April 2024 - Linux-stable-mirror

[PATCH] serial: 8250_bcm7271: use default_mux_rate if possible

by Doug Berger

There is a scenario when resuming from some power saving states with no_console_suspend where console output can be generated before the 8250_bcm7271 driver gets the opportunity to restore the baud_mux_clk frequency. Since the baud_mux_clk is at its default frequency at this time the output can be garbled until the driver gets the opportunity to resume. Since this is only an issue with console use of the serial port during that window and the console isn't likely to use baud rates that require alternate baud_mux_clk frequencies, allow the driver to select the default_mux_rate if it is accurate enough. Fixes: 41a469482de2 ("serial: 8250: Add new 8250-core based Broadcom STB driver") Signed-off-by: Doug Berger <opendmb(a)gmail.com> --- drivers/tty/serial/8250/8250_bcm7271.c | 101 +++++++++++++++---------- 1 file changed, 60 insertions(+), 41 deletions(-) diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index de270863eb5e..2569ca69223f 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -673,18 +673,46 @@ static void init_real_clk_rates(struct device *dev, struct brcmuart_priv *priv) clk_set_rate(priv->baud_mux_clk, priv->default_mux_rate); } +static u32 find_quot(struct device *dev, u32 freq, u32 baud, u32 *percent) +{ + u32 quot; + u32 rate; + u64 hires_rate; + u64 hires_baud; + u64 hires_err; + + rate = freq / 16; + quot = DIV_ROUND_CLOSEST(rate, baud); + if (!quot) + return 0; + + /* increase resolution to get xx.xx percent */ + hires_rate = div_u64((u64)rate * 10000, (u64)quot); + hires_baud = (u64)baud * 10000; + + /* get the delta */ + if (hires_rate > hires_baud) + hires_err = (hires_rate - hires_baud); + else + hires_err = (hires_baud - hires_rate); + + *percent = (unsigned long)DIV_ROUND_CLOSEST_ULL(hires_err, baud); + + dev_dbg(dev, "Baud rate: %u, MUX Clk: %u, Error: %u.%u%%\n", + baud, freq, *percent / 100, *percent % 100); + + return quot; +} + static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, u32 baud) { u32 percent; u32 best_percent = UINT_MAX; u32 quot; + u32 freq; u32 best_quot = 1; - u32 rate; - int best_index = -1; - u64 hires_rate; - u64 hires_baud; - u64 hires_err; + u32 best_freq = 0; int rc; int i; int real_baud; @@ -693,44 +721,35 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, if (priv->baud_mux_clk == NULL) return; - /* Find the closest match for specified baud */ - for (i = 0; i < ARRAY_SIZE(priv->real_rates); i++) { - if (priv->real_rates[i] == 0) - continue; - rate = priv->real_rates[i] / 16; - quot = DIV_ROUND_CLOSEST(rate, baud); - if (!quot) - continue; - - /* increase resolution to get xx.xx percent */ - hires_rate = (u64)rate * 10000; - hires_baud = (u64)baud * 10000; - - hires_err = div_u64(hires_rate, (u64)quot); - - /* get the delta */ - if (hires_err > hires_baud) - hires_err = (hires_err - hires_baud); - else - hires_err = (hires_baud - hires_err); - - percent = (unsigned long)DIV_ROUND_CLOSEST_ULL(hires_err, baud); - dev_dbg(up->dev, - "Baud rate: %u, MUX Clk: %u, Error: %u.%u%%\n", - baud, priv->real_rates[i], percent / 100, - percent % 100); - if (percent < best_percent) { - best_percent = percent; - best_index = i; - best_quot = quot; + /* Try default_mux_rate first */ + quot = find_quot(up->dev, priv->default_mux_rate, baud, &percent); + if (quot) { + best_percent = percent; + best_freq = priv->default_mux_rate; + best_quot = quot; + } + /* If more than 1% error, find the closest match for specified baud */ + if (best_percent > 100) { + for (i = 0; i < ARRAY_SIZE(priv->real_rates); i++) { + freq = priv->real_rates[i]; + if (freq == 0 || freq == priv->default_mux_rate) + continue; + quot = find_quot(up->dev, freq, baud, &percent); + if (!quot) + continue; + + if (percent < best_percent) { + best_percent = percent; + best_freq = freq; + best_quot = quot; + } } } - if (best_index == -1) { + if (!best_freq) { dev_err(up->dev, "Error, %d BAUD rate is too fast.\n", baud); return; } - rate = priv->real_rates[best_index]; - rc = clk_set_rate(priv->baud_mux_clk, rate); + rc = clk_set_rate(priv->baud_mux_clk, best_freq); if (rc) dev_err(up->dev, "Error selecting BAUD MUX clock\n"); @@ -739,8 +758,8 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, dev_err(up->dev, "Error, baud: %d has %u.%u%% error\n", baud, percent / 100, percent % 100); - real_baud = rate / 16 / best_quot; - dev_dbg(up->dev, "Selecting BAUD MUX rate: %u\n", rate); + real_baud = best_freq / 16 / best_quot; + dev_dbg(up->dev, "Selecting BAUD MUX rate: %u\n", best_freq); dev_dbg(up->dev, "Requested baud: %u, Actual baud: %u\n", baud, real_baud); @@ -749,7 +768,7 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, i += (i / 2); priv->char_wait = ns_to_ktime(i); - up->uartclk = rate; + up->uartclk = best_freq; } static void brcmstb_set_termios(struct uart_port *up, -- 2.34.1

1 year, 6 months

2
1
0 0

[PATCH] admin-guide/hw-vuln/core-scheduling: fix return type of PR_SCHED_CORE_GET

by Thomas Weißschuh

sched_core_share_pid() copies the cookie to userspace with put_user(id, (u64 __user *)uaddr), expecting 64 bits of space. The "unsigned long" datatype that is documented in core-scheduling.rst however is only 32 bits large on 32 bit architectures. Document "unsigned long long" as the correct data type that is always 64bits large. This matches what the selftest cs_prctl_test.c has been doing all along. Fixes: 0159bb020ca9 ("Documentation: Add usecases, design and interface for core scheduling") Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/util-linux/df7a25a0-7923-4f8b-a527-5e6f0064074d@t-8… Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Documentation/admin-guide/hw-vuln/core-scheduling.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/core-scheduling.rst b/Documentation/admin-guide/hw-vuln/core-scheduling.rst index cf1eeefdfc32..a92e10ec402e 100644 --- a/Documentation/admin-guide/hw-vuln/core-scheduling.rst +++ b/Documentation/admin-guide/hw-vuln/core-scheduling.rst @@ -67,8 +67,8 @@ arg4: will be performed for all tasks in the task group of ``pid``. arg5: - userspace pointer to an unsigned long for storing the cookie returned by - ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. + userspace pointer to an unsigned long long for storing the cookie returned + by ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. In order for a process to push a cookie to, or pull a cookie from a process, it is required to have the ptrace access mode: `PTRACE_MODE_READ_REALCREDS` to the --- base-commit: 71b1543c83d65af8215d7558d70fc2ecbee77dcf change-id: 20240423-core-scheduling-cookie-b0551c40b086 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

1 year, 6 months

3
2
0 0

[PATCH 1/2] KVM: arm64: vgic-v2: Check for non-NULL vCPU in vgic_v2_parse_attr()

by Oliver Upton

vgic_v2_parse_attr() is responsible for finding the vCPU that matches the user-provided CPUID, which (of course) may not be valid. If the ID is invalid, kvm_get_vcpu_by_id() returns NULL, which isn't handled gracefully. Similar to the GICv3 uaccess flow, check that kvm_get_vcpu_by_id() actually returns something and fail the ioctl if not. Cc: stable(a)vger.kernel.org Fixes: 7d450e282171 ("KVM: arm/arm64: vgic-new: Add userland access to VGIC dist registers") Reported-by: Alexander Potapenko <glider(a)google.com> Tested-by: Alexander Potapenko <glider(a)google.com> Reviewed-by: Alexander Potapenko <glider(a)google.com> Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> --- arch/arm64/kvm/vgic/vgic-kvm-device.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index f48b8dab8b3d..1d26bb5b02f4 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -338,12 +338,12 @@ int kvm_register_vgic_device(unsigned long type) int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { - int cpuid; + int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - - reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); + if (!reg_attr->vcpu) + return -EINVAL; return 0; } -- 2.44.0.769.g3c40516874-goog

1 year, 6 months

1
0
0 0

[tip: x86/urgent] x86/tdx: Preserve shared bit on mprotect()

by tip-bot2 for Kirill A. Shutemov

The following commit has been merged into the x86/urgent branch of tip: Commit-ID: a0a8d15a798be4b8f20aca2ba91bf6b688c6a640 Gitweb: https://git.kernel.org/tip/a0a8d15a798be4b8f20aca2ba91bf6b688c6a640 Author: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> AuthorDate: Wed, 24 Apr 2024 11:20:35 +03:00 Committer: Dave Hansen <dave.hansen(a)linux.intel.com> CommitterDate: Wed, 24 Apr 2024 08:11:43 -07:00 x86/tdx: Preserve shared bit on mprotect() The TDX guest platform takes one bit from the physical address to indicate if the page is shared (accessible by VMM). This bit is not part of the physical_mask and is not preserved during mprotect(). As a result, the 'shared' bit is lost during mprotect() on shared mappings. _COMMON_PAGE_CHG_MASK specifies which PTE bits need to be preserved during modification. AMD includes 'sme_me_mask' in the define to preserve the 'encrypt' bit. To cover both Intel and AMD cases, include 'cc_mask' in _COMMON_PAGE_CHG_MASK instead of 'sme_me_mask'. Reported-and-tested-by: Chris Oo <cho(a)microsoft.com> Fixes: 41394e33f3a0 ("x86/tdx: Extend the confidential computing API to support TDX guests") Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Reviewed-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Reviewed-by: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/all/20240424082035.4092071-1-kirill.shutemov%40linu… --- arch/x86/include/asm/coco.h | 1 + arch/x86/include/asm/pgtable_types.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index c086699..aa6c8f8 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -25,6 +25,7 @@ u64 cc_mkdec(u64 val); void cc_random_init(void); #else #define cc_vendor (CC_VENDOR_NONE) +static const u64 cc_mask = 0; static inline u64 cc_mkenc(u64 val) { diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0b748ee..9abb8cc 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -148,7 +148,7 @@ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | \ _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ - _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP) + _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -173,6 +173,7 @@ enum page_cache_mode { }; #endif +#define _PAGE_CC (_AT(pteval_t, cc_mask)) #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)

1 year, 6 months

1
0
0 0

[PATCH V2] workqueue: Fix divide error in wq_update_node_max_active()

by Lai Jiangshan

From: Lai Jiangshan <jiangshan.ljs(a)antgroup.com> Yue Sun and xingwei lee reported a divide error bug in wq_update_node_max_active(): divide error: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 1 PID: 21 Comm: cpuhp/1 Not tainted 6.9.0-rc5 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:wq_update_node_max_active+0x369/0x6b0 kernel/workqueue.c:1605 Code: 24 bf 00 00 00 80 44 89 fe e8 83 27 33 00 41 83 fc ff 75 0d 41 81 ff 00 00 00 80 0f 84 68 01 00 00 e8 fb 22 33 00 44 89 f8 99 <41> f7 fc 89 c5 89 c7 44 89 ee e8 a8 24 33 00 89 ef 8b 5c 24 04 89 RSP: 0018:ffffc9000018fbb0 EFLAGS: 00010293 RAX: 00000000000000ff RBX: 0000000000000001 RCX: ffff888100ada500 RDX: 0000000000000000 RSI: 00000000000000ff RDI: 0000000080000000 RBP: 0000000000000001 R08: ffffffff815b1fcd R09: 1ffff1100364ad72 R10: dffffc0000000000 R11: ffffed100364ad73 R12: 0000000000000000 R13: 0000000000000100 R14: 0000000000000000 R15: 00000000000000ff FS: 0000000000000000(0000) GS:ffff888135c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fb8c06ca6f8 CR3: 000000010d6c6000 CR4: 0000000000750ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> workqueue_offline_cpu+0x56f/0x600 kernel/workqueue.c:6525 cpuhp_invoke_callback+0x4e1/0x870 kernel/cpu.c:194 cpuhp_thread_fun+0x411/0x7d0 kernel/cpu.c:1092 smpboot_thread_fn+0x544/0xa10 kernel/smpboot.c:164 kthread+0x2ed/0x390 kernel/kthread.c:388 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:244 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- After analysis, it happens when all of the CPUs in a workqueue's affinity get offine. The problem can be easily reproduced by: # echo 8 > /sys/devices/virtual/workqueue/<any-wq-name>/cpumask # echo 0 > /sys/devices/system/cpu/cpu3/online Use the default max_actives for nodes when all of the CPUs in the workqueue's affinity get offline to fix the problem. Reported-by: Yue Sun <samsun1006219(a)gmail.com> Reported-by: xingwei lee <xrivendell7(a)gmail.com> Link: https://lore.kernel.org/lkml/CAEkJfYPGS1_4JqvpSo0=FM0S1ytB8CEbyreLTtWpR900d… Fixes: 5797b1c18919 ("workqueue: Implement system-wide nr_active enforcement for unbound workqueues") Cc: stable(a)vger.kernel.org Signed-off-by: Lai Jiangshan <jiangshan.ljs(a)antgroup.com> --- Changed from v1: when total_cpus==0, use the default values for max_active instead of forcing total_cpus>=1 [v1]: https://lore.kernel.org/lkml/20240423124548.1253842-1-jiangshanlai@gmail.co… kernel/workqueue.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0066c8f6c154..0105e3c82df4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1594,6 +1594,15 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) if (off_cpu >= 0) total_cpus--; + /* If all CPUs of the wq get offline, use the default values */ + if (unlikely(!total_cpus)) { + for_each_node(node) + wq_node_nr_active(wq, node)->max = min_active; + + wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; + return; + } + for_each_node(node) { int node_cpus; -- 2.19.1.6.gb485710b

1 year, 6 months

2
1
0 0

stable-rc: 5.10: arm: u64_stats_sync.h:136:2: error: implicit declaration of function 'preempt_disable_nested'

by Naresh Kamboju

The arm and i386 builds failed with clang-17 and gcc-12 on stable-rc linux.5.10.y branch with linked config [1]. Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> In file included from init/do_mounts.c:7: In file included from include/linux/suspend.h:5: In file included from include/linux/swap.h:9: In file included from include/linux/memcontrol.h:13: In file included from include/linux/cgroup.h:28: In file included from include/linux/cgroup-defs.h:20: include/linux/u64_stats_sync.h:136:2: error: implicit declaration of function 'preempt_disable_nested' [-Werror,-Wimplicit-function-declaration] 136 | preempt_disable_nested(); | ^ include/linux/u64_stats_sync.h:143:2: error: implicit declaration of function 'preempt_enable_nested' [-Werror,-Wimplicit-function-declaration] 143 | preempt_enable_nested(); | ^ Suspecting patch: u64_stats: fix u64_stats_init() for lockdep when used repeatedly in one file [ Upstream commit 38a15d0a50e0a43778561a5861403851f0b0194c ] Steps to reproduce: --- # tuxmake --runtime podman --target-arch arm --toolchain clang-17 --kconfig https://storage.tuxsuite.com/public/linaro/lkft/builds/2f8pIb4fiJ5NY0zeALMm… LLVM=1 LLVM_IAS=0 dtbs dtbs-legacy headers kernel kselftest modules Links: - [1] https://storage.tuxsuite.com/public/linaro/lkft/builds/2f8pIb4fiJ5NY0zeALMm… - https://storage.tuxsuite.com/public/linaro/lkft/builds/2f8pIb4fiJ5NY0zeALMm… - https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.10.y/build/v5.10… -- Linaro LKFT https://lkft.linaro.org

1 year, 6 months

4
4
0 0

[PATCH 2/8] rtla/auto-analysis: Replace \t with spaces

by Daniel Bristot de Oliveira

When copying timerlat auto-analysis from a terminal to some web pages or chats, the \t are being replaced with a single ' ' or ' ', breaking the output. For example: ## CPU 3 hit stop tracing, analyzing it ## IRQ handler delay: 1.30 us (0.11 %) IRQ latency: 1.90 us Timerlat IRQ duration: 3.00 us (0.24 %) Blocking thread: 1223.16 us (99.00 %) insync:4048 1223.16 us IRQ interference 4.93 us (0.40 %) local_timer:236 4.93 us ------------------------------------------------------------------------ Thread latency: 1235.47 us (100%) Replace \t with spaces to avoid this problem. Cc: stable(a)vger.kernel.org Fixes: 27e348b221f6 ("rtla/timerlat: Add auto-analysis core") Signed-off-by: Daniel Bristot de Oliveira <bristot(a)kernel.org> --- tools/tracing/rtla/src/timerlat_aa.c | 109 ++++++++++++++++----------- 1 file changed, 63 insertions(+), 46 deletions(-) diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c index 7093fd5333be..7bd80ee2a5b4 100644 --- a/tools/tracing/rtla/src/timerlat_aa.c +++ b/tools/tracing/rtla/src/timerlat_aa.c @@ -16,6 +16,9 @@ enum timelat_state { TIMERLAT_WAITING_THREAD, }; +/* Used to fill spaces in the output */ +static const char *spaces = " "; + #define MAX_COMM 24 /* @@ -274,14 +277,17 @@ static int timerlat_aa_nmi_handler(struct trace_seq *s, struct tep_record *recor taa_data->prev_irq_timstamp = start; trace_seq_reset(taa_data->prev_irqs_seq); - trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s \t\t\t%9.2f us\n", - "nmi", ns_to_usf(duration)); + trace_seq_printf(taa_data->prev_irqs_seq, " %24s %.*s %9.2f us\n", + "nmi", + 24, spaces, + ns_to_usf(duration)); return 0; } taa_data->thread_nmi_sum += duration; - trace_seq_printf(taa_data->nmi_seq, " %24s \t\t\t%9.2f us\n", - "nmi", ns_to_usf(duration)); + trace_seq_printf(taa_data->nmi_seq, " %24s %.*s %9.2f us\n", + "nmi", + 24, spaces, ns_to_usf(duration)); return 0; } @@ -323,8 +329,10 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor taa_data->prev_irq_timstamp = start; trace_seq_reset(taa_data->prev_irqs_seq); - trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s:%-3llu \t\t%9.2f us\n", - desc, vector, ns_to_usf(duration)); + trace_seq_printf(taa_data->prev_irqs_seq, " %24s:%-3llu %.*s %9.2f us\n", + desc, vector, + 15, spaces, + ns_to_usf(duration)); return 0; } @@ -372,8 +380,10 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor * IRQ interference. */ taa_data->thread_irq_sum += duration; - trace_seq_printf(taa_data->irqs_seq, " %24s:%-3llu \t %9.2f us\n", - desc, vector, ns_to_usf(duration)); + trace_seq_printf(taa_data->irqs_seq, " %24s:%-3llu %.*s %9.2f us\n", + desc, vector, + 24, spaces, + ns_to_usf(duration)); return 0; } @@ -408,8 +418,10 @@ static int timerlat_aa_softirq_handler(struct trace_seq *s, struct tep_record *r taa_data->thread_softirq_sum += duration; - trace_seq_printf(taa_data->softirqs_seq, "\t%24s:%-3llu \t %9.2f us\n", - softirq_name[vector], vector, ns_to_usf(duration)); + trace_seq_printf(taa_data->softirqs_seq, " %24s:%-3llu %.*s %9.2f us\n", + softirq_name[vector], vector, + 24, spaces, + ns_to_usf(duration)); return 0; } @@ -452,8 +464,10 @@ static int timerlat_aa_thread_handler(struct trace_seq *s, struct tep_record *re } else { taa_data->thread_thread_sum += duration; - trace_seq_printf(taa_data->threads_seq, "\t%24s:%-3llu \t\t%9.2f us\n", - comm, pid, ns_to_usf(duration)); + trace_seq_printf(taa_data->threads_seq, " %24s:%-12llu %.*s %9.2f us\n", + comm, pid, + 15, spaces, + ns_to_usf(duration)); } return 0; @@ -482,7 +496,8 @@ static int timerlat_aa_stack_handler(struct trace_seq *s, struct tep_record *rec function = tep_find_function(taa_ctx->tool->trace.tep, caller[i]); if (!function) break; - trace_seq_printf(taa_data->stack_seq, "\t\t-> %s\n", function); + trace_seq_printf(taa_data->stack_seq, " %.*s -> %s\n", + 14, spaces, function); } } return 0; @@ -568,23 +583,24 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay; if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) { if (taa_data->prev_irq_timstamp < taa_data->timer_irq_start_time) - printf(" Previous IRQ interference: \t\t up to %9.2f us\n", - ns_to_usf(taa_data->prev_irq_duration)); + printf(" Previous IRQ interference: %.*s up to %9.2f us\n", + 16, spaces, + ns_to_usf(taa_data->prev_irq_duration)); } /* * The delay that the IRQ suffered before starting. */ - printf(" IRQ handler delay: %16s %9.2f us (%.2f %%)\n", - (ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "", - ns_to_usf(taa_data->timer_irq_start_delay), - ns_to_per(total, taa_data->timer_irq_start_delay)); + printf(" IRQ handler delay: %.*s %16s %9.2f us (%.2f %%)\n", 16, spaces, + (ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "", + ns_to_usf(taa_data->timer_irq_start_delay), + ns_to_per(total, taa_data->timer_irq_start_delay)); /* * Timerlat IRQ. */ - printf(" IRQ latency: \t\t\t\t %9.2f us\n", - ns_to_usf(taa_data->tlat_irq_latency)); + printf(" IRQ latency: %.*s %9.2f us\n", 40, spaces, + ns_to_usf(taa_data->tlat_irq_latency)); if (irq) { /* @@ -595,15 +611,16 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * so it will be displayed, it is the key. */ printf(" Blocking thread:\n"); - printf(" %24s:%-9llu\n", - taa_data->run_thread_comm, taa_data->run_thread_pid); + printf(" %.*s %24s:%-9llu\n", 6, spaces, taa_data->run_thread_comm, + taa_data->run_thread_pid); } else { /* * The duration of the IRQ handler that handled the timerlat IRQ. */ - printf(" Timerlat IRQ duration: \t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->timer_irq_duration), - ns_to_per(total, taa_data->timer_irq_duration)); + printf(" Timerlat IRQ duration: %.*s %9.2f us (%.2f %%)\n", + 30, spaces, + ns_to_usf(taa_data->timer_irq_duration), + ns_to_per(total, taa_data->timer_irq_duration)); /* * The amount of time that the current thread postponed the scheduler. @@ -611,13 +628,13 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * Recalling that it is net from NMI/IRQ/Softirq interference, so there * is no need to compute values here. */ - printf(" Blocking thread: \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_blocking_duration), - ns_to_per(total, taa_data->thread_blocking_duration)); + printf(" Blocking thread: %.*s %9.2f us (%.2f %%)\n", 36, spaces, + ns_to_usf(taa_data->thread_blocking_duration), + ns_to_per(total, taa_data->thread_blocking_duration)); - printf(" %24s:%-9llu %9.2f us\n", - taa_data->run_thread_comm, taa_data->run_thread_pid, - ns_to_usf(taa_data->thread_blocking_duration)); + printf(" %.*s %24s:%-9llu %.*s %9.2f us\n", 6, spaces, + taa_data->run_thread_comm, taa_data->run_thread_pid, + 12, spaces, ns_to_usf(taa_data->thread_blocking_duration)); } /* @@ -629,9 +646,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * NMIs can happen during the IRQ, so they are always possible. */ if (taa_data->thread_nmi_sum) - printf(" NMI interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_nmi_sum), - ns_to_per(total, taa_data->thread_nmi_sum)); + printf(" NMI interference %.*s %9.2f us (%.2f %%)\n", 36, spaces, + ns_to_usf(taa_data->thread_nmi_sum), + ns_to_per(total, taa_data->thread_nmi_sum)); /* * If it is an IRQ latency, the other factors can be skipped. @@ -643,9 +660,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * Prints the interference caused by IRQs to the thread latency. */ if (taa_data->thread_irq_sum) { - printf(" IRQ interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_irq_sum), - ns_to_per(total, taa_data->thread_irq_sum)); + printf(" IRQ interference %.*s %9.2f us (%.2f %%)\n", 36, spaces, + ns_to_usf(taa_data->thread_irq_sum), + ns_to_per(total, taa_data->thread_irq_sum)); trace_seq_do_printf(taa_data->irqs_seq); } @@ -654,9 +671,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * Prints the interference caused by Softirqs to the thread latency. */ if (taa_data->thread_softirq_sum) { - printf(" Softirq interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_softirq_sum), - ns_to_per(total, taa_data->thread_softirq_sum)); + printf(" Softirq interference %.*s %9.2f us (%.2f %%)\n", 32, spaces, + ns_to_usf(taa_data->thread_softirq_sum), + ns_to_per(total, taa_data->thread_softirq_sum)); trace_seq_do_printf(taa_data->softirqs_seq); } @@ -670,9 +687,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * timer handling latency. */ if (taa_data->thread_thread_sum) { - printf(" Thread interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_thread_sum), - ns_to_per(total, taa_data->thread_thread_sum)); + printf(" Thread interference %.*s %9.2f us (%.2f %%)\n", 33, spaces, + ns_to_usf(taa_data->thread_thread_sum), + ns_to_per(total, taa_data->thread_thread_sum)); trace_seq_do_printf(taa_data->threads_seq); } @@ -682,8 +699,8 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, */ print_total: printf("------------------------------------------------------------------------\n"); - printf(" %s latency: \t\t\t %9.2f us (100%%)\n", irq ? "IRQ" : "Thread", - ns_to_usf(total)); + printf(" %s latency: %.*s %9.2f us (100%%)\n", irq ? " IRQ" : "Thread", + 37, spaces, ns_to_usf(total)); } static int timerlat_auto_analysis_collect_trace(struct timerlat_aa_context *taa_ctx) -- 2.44.0

1 year, 6 months

1
0
0 0

[PATCH 1/8] rtla/timerlat: Simplify "no value" printing on top

by Daniel Bristot de Oliveira

Instead of printing three times the same output, print it only once, reducing lines and being sure that all no values have the same length. It also fixes an extra '\n' when running the with kernel threads, like here: =============== %< ============== Timer Latency 0 00:00:01 | IRQ Timer Latency (us) | Thread Timer Latency (us) CPU COUNT | cur min avg max | cur min avg max 2 #0 | - - - - | 161 161 161 161 3 #0 | - - - - | 161 161 161 161 8 #1 | 54 54 54 54 | - - - -'\n' ---------------|----------------------------------------|--------------------------------------- ALL #1 e0 | 54 54 54 | 161 161 161 =============== %< ============== This '\n' should have been removed with the user-space support that added another '\n' if not running with kernel threads. Cc: stable(a)vger.kernel.org Fixes: cdca4f4e5e8e ("rtla/timerlat_top: Add timerlat user-space support") Signed-off-by: Daniel Bristot de Oliveira <bristot(a)kernel.org> --- tools/tracing/rtla/src/timerlat_top.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 8a3fa64319c6..2665e0bb5f1e 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -212,6 +212,8 @@ static void timerlat_top_header(struct osnoise_tool *top) trace_seq_printf(s, "\n"); } +static const char *no_value = " -"; + /* * timerlat_top_print - prints the output of a given CPU */ @@ -239,10 +241,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu) trace_seq_printf(s, "%3d #%-9d |", cpu, cpu_data->irq_count); if (!cpu_data->irq_count) { - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - |"); + trace_seq_printf(s, "%s %s %s %s |", no_value, no_value, no_value, no_value); } else { trace_seq_printf(s, "%9llu ", cpu_data->cur_irq / params->output_divisor); trace_seq_printf(s, "%9llu ", cpu_data->min_irq / params->output_divisor); @@ -251,10 +250,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu) } if (!cpu_data->thread_count) { - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " -\n"); + trace_seq_printf(s, "%s %s %s %s", no_value, no_value, no_value, no_value); } else { trace_seq_printf(s, "%9llu ", cpu_data->cur_thread / divisor); trace_seq_printf(s, "%9llu ", cpu_data->min_thread / divisor); @@ -271,10 +267,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu) trace_seq_printf(s, " |"); if (!cpu_data->user_count) { - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " -\n"); + trace_seq_printf(s, "%s %s %s %s\n", no_value, no_value, no_value, no_value); } else { trace_seq_printf(s, "%9llu ", cpu_data->cur_user / divisor); trace_seq_printf(s, "%9llu ", cpu_data->min_user / divisor); -- 2.44.0

1 year, 6 months

1
0
0 0

Re: [PATCH 6.8 000/158] 6.8.8-rc1 review

by Ronald Warsow

Hi Greg *no* regressions here on x86_64 (RKL, Intel 11th Gen. CPU) Thanks Tested-by: Ronald Warsow <rwarsow(a)gmx.de>

1 year, 6 months

1
0
0 0

[git:media_stage/master] media: v4l2-core: hold videodev_lock until dev reg, finishes

by Hans Verkuil

This is an automatic generated email to let you know that the following patch were queued: Subject: media: v4l2-core: hold videodev_lock until dev reg, finishes Author: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Date: Fri Feb 23 09:45:36 2024 +0100 After the new V4L2 device node was registered, some additional initialization was done before the device node was marked as 'registered'. During the time between creating the device node and marking it as 'registered' it was possible to open the device node, which would return -ENODEV since the 'registered' flag was not yet set. Hold the videodev_lock mutex from just before the device node is registered until the 'registered' flag is set. Since v4l2_open will take the same lock, it will wait until this registration process is finished. This resolves this race condition. Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Reviewed-by: Sakari Ailus <sakari.ailus(a)linux.intel.com> Cc: <stable(a)vger.kernel.org> # for vi4.18 and up drivers/media/v4l2-core/v4l2-dev.c | 3 +++ 1 file changed, 3 insertions(+) --- diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index e39e9742fdb5..be2ba7ca5de2 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -1039,8 +1039,10 @@ int __video_register_device(struct video_device *vdev, vdev->dev.devt = MKDEV(VIDEO_MAJOR, vdev->minor); vdev->dev.parent = vdev->dev_parent; dev_set_name(&vdev->dev, "%s%d", name_base, vdev->num); + mutex_lock(&videodev_lock); ret = device_register(&vdev->dev); if (ret < 0) { + mutex_unlock(&videodev_lock); pr_err("%s: device_register failed\n", __func__); goto cleanup; } @@ -1060,6 +1062,7 @@ int __video_register_device(struct video_device *vdev, /* Part 6: Activate this minor. The char device can now be used. */ set_bit(V4L2_FL_REGISTERED, &vdev->flags); + mutex_unlock(&videodev_lock); return 0;

1 year, 6 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2024