February 2025 - Linux-stable-mirror

[PATCH RFT 4/5] phy: renesas: rcar-gen3-usb2: Assert PLL reset on PHY power off

by Claudiu

From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Assert PLL reset on PHY power off. This saves power. Fixes: f3b5a8d9b50d ("phy: rcar-gen3-usb2: Add R-Car Gen3 USB2 PHY driver") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> --- drivers/phy/renesas/phy-rcar-gen3-usb2.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 5c0ceba09b67..087937407b0b 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -537,9 +537,16 @@ static int rcar_gen3_phy_usb2_power_off(struct phy *p) struct rcar_gen3_chan *channel = rphy->ch; int ret = 0; - scoped_guard(spinlock_irqsave, &channel->lock) + scoped_guard(spinlock_irqsave, &channel->lock) { rphy->powered = false; + if (rcar_gen3_are_all_rphys_power_off(channel)) { + u32 val = readl(channel->base + USB2_USBCTR); + val |= USB2_USBCTR_PLL_RST; + writel(val, channel->base + USB2_USBCTR); + } + } + if (channel->vbus) ret = regulator_disable(channel->vbus); -- 2.43.0

6 months, 1 week

2
1
0 0

[PATCH V5 2/4] x86/tdx: Route safe halt execution via tdx_safe_halt()

by Vishal Annapurve

Direct HLT instruction execution causes #VEs for TDX VMs which is routed to hypervisor via TDCALL. safe_halt() routines execute HLT in STI-shadow so IRQs need to remain disabled until the TDCALL to ensure that pending IRQs are correctly treated as wake events. So "sti;hlt" sequence needs to be replaced for TDX VMs with "TDCALL; *_irq_enable()" to keep interrupts disabled during TDCALL execution. Commit bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests") prevented the idle routines from using "sti;hlt". But it missed the paravirt routine which can be reached like this as an example: acpi_safe_halt() => raw_safe_halt() => arch_safe_halt() => irq.safe_halt() => pv_native_safe_halt() Modify tdx_safe_halt() to implement the sequence "TDCALL; raw_local_irq_enable()" and invoke tdx_halt() from idle routine which just executes TDCALL without toggling interrupt state. Introduce dependency on CONFIG_PARAVIRT and override paravirt halt()/safe_halt() routines for TDX VMs. Cc: stable(a)vger.kernel.org Fixes: bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests") Signed-off-by: Vishal Annapurve <vannapurve(a)google.com> --- arch/x86/Kconfig | 1 + arch/x86/coco/tdx/tdx.c | 22 +++++++++++++++++++++- arch/x86/include/asm/tdx.h | 2 +- arch/x86/kernel/process.c | 2 +- 4 files changed, 24 insertions(+), 3 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 87198d957e2f..afcdbc9693dc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -902,6 +902,7 @@ config INTEL_TDX_GUEST depends on X86_64 && CPU_SUP_INTEL depends on X86_X2APIC depends on EFI_STUB + depends on PARAVIRT select ARCH_HAS_CC_PLATFORM select X86_MEM_ENCRYPT select X86_MCE diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 32809a06dab4..7ab427e85bd3 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -14,6 +14,7 @@ #include <asm/ia32.h> #include <asm/insn.h> #include <asm/insn-eval.h> +#include <asm/paravirt_types.h> #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/traps.h> @@ -398,7 +399,7 @@ static int handle_halt(struct ve_info *ve) return ve_instr_len(ve); } -void __cpuidle tdx_safe_halt(void) +void __cpuidle tdx_halt(void) { const bool irq_disabled = false; @@ -409,6 +410,16 @@ void __cpuidle tdx_safe_halt(void) WARN_ONCE(1, "HLT instruction emulation failed\n"); } +static void __cpuidle tdx_safe_halt(void) +{ + tdx_halt(); + /* + * "__cpuidle" section doesn't support instrumentation, so stick + * with raw_* variant that avoids tracing hooks. + */ + raw_local_irq_enable(); +} + static int read_msr(struct pt_regs *regs, struct ve_info *ve) { struct tdx_module_args args = { @@ -1109,6 +1120,15 @@ void __init tdx_early_init(void) x86_platform.guest.enc_kexec_begin = tdx_kexec_begin; x86_platform.guest.enc_kexec_finish = tdx_kexec_finish; + /* + * "sti;hlt" execution in TDX guests will induce a #VE in the STI-shadow + * which will enable interrupts before HLT TDCALL inocation possibly + * resulting in missed wakeup events. Modify all possible HLT + * execution paths to use TDCALL for performance/reliability reasons. + */ + pv_ops.irq.safe_halt = tdx_safe_halt; + pv_ops.irq.halt = tdx_halt; + /* * TDX intercepts the RDMSR to read the X2APIC ID in the parallel * bringup low level code. That raises #VE which cannot be handled diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index b4b16dafd55e..393ee2dfaab1 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -58,7 +58,7 @@ void tdx_get_ve_info(struct ve_info *ve); bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve); -void tdx_safe_halt(void); +void tdx_halt(void); bool tdx_early_handle_ve(struct pt_regs *regs); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6da6769d7254..d11956a178df 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -934,7 +934,7 @@ void __init select_idle_routine(void) static_call_update(x86_idle, mwait_idle); } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { pr_info("using TDX aware idle routine\n"); - static_call_update(x86_idle, tdx_safe_halt); + static_call_update(x86_idle, tdx_halt); } else { static_call_update(x86_idle, default_idle); } -- 2.48.1.601.g30ceb7b040-goog

6 months, 1 week

2
2
0 0

[PATCH v3 1/5] ftrace: Fix accounting of adding subops to a manager ops

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Function graph uses a subops and manager ops mechanism to attach to ftrace. The manager ops connects to ftrace and the functions it connects to is defined by a list of subops that it manages. The function hash that defines what the above ops attaches to limits the functions to attach if the hash has any content. If the hash is empty, it means to trace all functions. The creation of the manager ops hash is done by iterating over all the subops hashes. If any of the subops hashes is empty, it means that the manager ops hash must trace all functions as well. The issue is in the creation of the manager ops. When a second subops is attached, a new hash is created by starting it as NULL and adding the subops one at a time. But the NULL ops is mistaken as an empty hash, and once an empty hash is found, it stops the loop of subops and just enables all functions. # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions trace_initcall_start_cb (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 try_to_run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 x86_pmu_show_pmu_cap (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 cleanup_rapl_pmus (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_free_pcibus_map (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_types_exit (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_pci_exit.part.0 (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 kvm_shutdown (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_dump_msrs (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_cleanup_l1d_flush (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 [..] Fix this by initializing the new hash to NULL and if the hash is NULL do not treat it as an empty hash but instead allocate by copying the content of the first sub ops. Then on subsequent iterations, the new hash will not be NULL, but the content of the previous subops. If that first subops attached to all functions, then new hash may assume that the manager ops also needs to attach to all functions. Cc: stable(a)vger.kernel.org Fixes: 5fccc7552ccbc ("ftrace: Add subops logic to allow one ops to manage many") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- Changes since v2: https://lore.kernel.org/20250219220510.888959028@goodmis.org - Have append_hashes() return EMPTY_HASH and not NULL if the resulting new hash is empty. kernel/trace/ftrace.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 728ecda6e8d4..bec54dc27204 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3220,15 +3220,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src) * The filter_hash updates uses just the append_hash() function * and the notrace_hash does not. */ -static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash) +static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash, + int size_bits) { struct ftrace_func_entry *entry; int size; int i; - /* An empty hash does everything */ - if (ftrace_hash_empty(*hash)) - return 0; + if (*hash) { + /* An empty hash does everything */ + if (ftrace_hash_empty(*hash)) + return 0; + } else { + *hash = alloc_ftrace_hash(size_bits); + if (!*hash) + return -ENOMEM; + } /* If new_hash has everything make hash have everything */ if (ftrace_hash_empty(new_hash)) { @@ -3292,16 +3299,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has /* Return a new hash that has a union of all @ops->filter_hash entries */ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) { - struct ftrace_hash *new_hash; + struct ftrace_hash *new_hash = NULL; struct ftrace_ops *subops; + int size_bits; int ret; - new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits); - if (!new_hash) - return NULL; + if (ops->func_hash->filter_hash) + size_bits = ops->func_hash->filter_hash->size_bits; + else + size_bits = FTRACE_HASH_DEFAULT_BITS; list_for_each_entry(subops, &ops->subop_list, list) { - ret = append_hash(&new_hash, subops->func_hash->filter_hash); + ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits); if (ret < 0) { free_ftrace_hash(new_hash); return NULL; @@ -3310,7 +3319,8 @@ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) if (ftrace_hash_empty(new_hash)) break; } - return new_hash; + /* Can't return NULL as that means this failed */ + return new_hash ? : EMPTY_HASH; } /* Make @ops trace evenything except what all its subops do not trace */ @@ -3505,7 +3515,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash); if (!filter_hash) return -ENOMEM; - ret = append_hash(&filter_hash, subops->func_hash->filter_hash); + ret = append_hash(&filter_hash, subops->func_hash->filter_hash, + size_bits); if (ret < 0) { free_ftrace_hash(filter_hash); return ret; -- 2.47.2

6 months, 1 week

2
1
0 0

[PATCH v2 1/2] asm-generic/vmlinux.lds: Move .data.rel.ro input into .rodata segment

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> When using -fPIE codegen, the compiler will emit const global objects (which are useless unless statically initialized) into .data.rel.ro rather than .rodata if the object contains fields that carry absolute addresses of other code or data objects. This permits the linker to annotate such regions as requiring read-write access only at load time, but not at execution time (in user space). This distinction does not matter for the kernel, but it does imply that const data will end up in writable memory if the .data.rel.ro sections are not treated in a special way. So emit .data.rel.ro into the .rodata segment. Cc: <stable(a)vger.kernel.org> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- include/asm-generic/vmlinux.lds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 02a4adb4a999..0d5b186abee8 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -457,7 +457,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) . = ALIGN((align)); \ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ __start_rodata = .; \ - *(.rodata) *(.rodata.*) \ + *(.rodata) *(.rodata.*) *(.data.rel.ro*) \ SCHED_DATA \ RO_AFTER_INIT_DATA /* Read only after init */ \ . = ALIGN(8); \ -- 2.48.1.601.g30ceb7b040-goog

6 months, 1 week

3
2
0 0

[PATCH] firmware: cs_dsp: test_control_parse: null-terminate test strings

by Thomas Weißschuh

The char pointers in 'struct cs_dsp_mock_coeff_def' are expected to point to C strings. They need to be terminated by a null byte. However the code does not allocate that trailing null byte and only works if by chance the allocation is followed by such a null byte. Refactor the repeated string allocation logic into a new helper which makes sure the terminating null is always present. It also makes the code more readable. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> Fixes: 83baecd92e7c ("firmware: cs_dsp: Add KUnit testing of control parsing") Cc: stable(a)vger.kernel.org --- .../cirrus/test/cs_dsp_test_control_parse.c | 51 ++++++++-------------- 1 file changed, 19 insertions(+), 32 deletions(-) diff --git a/drivers/firmware/cirrus/test/cs_dsp_test_control_parse.c b/drivers/firmware/cirrus/test/cs_dsp_test_control_parse.c index cb90964740ea351113dac274f0366de7cedfd3d1..942ba1af5e7c1e47e8a2fbe548a7993b94f96515 100644 --- a/drivers/firmware/cirrus/test/cs_dsp_test_control_parse.c +++ b/drivers/firmware/cirrus/test/cs_dsp_test_control_parse.c @@ -73,6 +73,18 @@ static const struct cs_dsp_mock_coeff_def mock_coeff_template = { .length_bytes = 4, }; +static char *cs_dsp_ctl_alloc_test_string(struct kunit *test, char c, size_t len) +{ + char *str; + + str = kunit_kmalloc(test, len + 1, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, str); + memset(str, c, len); + str[len] = '\0'; + + return str; +} + /* Algorithm info block without controls should load */ static void cs_dsp_ctl_parse_no_coeffs(struct kunit *test) { @@ -160,12 +172,8 @@ static void cs_dsp_ctl_parse_max_v1_name(struct kunit *test) struct cs_dsp_mock_coeff_def def = mock_coeff_template; struct cs_dsp_coeff_ctl *ctl; struct firmware *wmfw; - char *name; - name = kunit_kzalloc(test, 256, GFP_KERNEL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, name); - memset(name, 'A', 255); - def.fullname = name; + def.fullname = cs_dsp_ctl_alloc_test_string(test, 'A', 255); cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, cs_dsp_ctl_parse_test_algs[0].id, @@ -252,14 +260,9 @@ static void cs_dsp_ctl_parse_max_short_name(struct kunit *test) struct cs_dsp_test_local *local = priv->local; struct cs_dsp_mock_coeff_def def = mock_coeff_template; struct cs_dsp_coeff_ctl *ctl; - char *name; struct firmware *wmfw; - name = kunit_kmalloc(test, 255, GFP_KERNEL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, name); - memset(name, 'A', 255); - - def.shortname = name; + def.shortname = cs_dsp_ctl_alloc_test_string(test, 'A', 255); cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, cs_dsp_ctl_parse_test_algs[0].id, @@ -273,7 +276,7 @@ static void cs_dsp_ctl_parse_max_short_name(struct kunit *test) ctl = list_first_entry_or_null(&priv->dsp->ctl_list, struct cs_dsp_coeff_ctl, list); KUNIT_ASSERT_NOT_NULL(test, ctl); KUNIT_EXPECT_EQ(test, ctl->subname_len, 255); - KUNIT_EXPECT_MEMEQ(test, ctl->subname, name, ctl->subname_len); + KUNIT_EXPECT_MEMEQ(test, ctl->subname, def.shortname, ctl->subname_len); KUNIT_EXPECT_EQ(test, ctl->flags, def.flags); KUNIT_EXPECT_EQ(test, ctl->type, def.type); KUNIT_EXPECT_EQ(test, ctl->len, def.length_bytes); @@ -323,12 +326,8 @@ static void cs_dsp_ctl_parse_with_max_fullname(struct kunit *test) struct cs_dsp_mock_coeff_def def = mock_coeff_template; struct cs_dsp_coeff_ctl *ctl; struct firmware *wmfw; - char *fullname; - fullname = kunit_kmalloc(test, 255, GFP_KERNEL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, fullname); - memset(fullname, 'A', 255); - def.fullname = fullname; + def.fullname = cs_dsp_ctl_alloc_test_string(test, 'A', 255); cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, cs_dsp_ctl_parse_test_algs[0].id, @@ -392,12 +391,8 @@ static void cs_dsp_ctl_parse_with_max_description(struct kunit *test) struct cs_dsp_mock_coeff_def def = mock_coeff_template; struct cs_dsp_coeff_ctl *ctl; struct firmware *wmfw; - char *description; - description = kunit_kmalloc(test, 65535, GFP_KERNEL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, description); - memset(description, 'A', 65535); - def.description = description; + def.description = cs_dsp_ctl_alloc_test_string(test, 'A', 65535); cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, cs_dsp_ctl_parse_test_algs[0].id, @@ -429,17 +424,9 @@ static void cs_dsp_ctl_parse_with_max_fullname_and_description(struct kunit *tes struct cs_dsp_mock_coeff_def def = mock_coeff_template; struct cs_dsp_coeff_ctl *ctl; struct firmware *wmfw; - char *fullname, *description; - - fullname = kunit_kmalloc(test, 255, GFP_KERNEL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, fullname); - memset(fullname, 'A', 255); - def.fullname = fullname; - description = kunit_kmalloc(test, 65535, GFP_KERNEL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, description); - memset(description, 'A', 65535); - def.description = description; + def.fullname = cs_dsp_ctl_alloc_test_string(test, 'A', 255); + def.description = cs_dsp_ctl_alloc_test_string(test, 'A', 65535); cs_dsp_mock_wmfw_start_alg_info_block(local->wmfw_builder, cs_dsp_ctl_parse_test_algs[0].id, --- base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b change-id: 20250211-cs_dsp-kunit-strings-f43e27078ed2 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

6 months, 1 week

3
5
0 0

[net PATCH] net: phy: qcom: qca807x fix condition for DAC_DSP_BIAS_CURRENT

by Christian Marangi

From: George Moussalem <george.moussalem(a)outlook.com> While setting the DAC value, the wrong boolean value is evaluated to set the DSP bias current. So let's correct the conditional statement and use the right boolean value read from the DTS set in the priv. Cc: stable(a)vger.kernel.org Fixes: d1cb613efbd3 ("net: phy: qcom: add support for QCA807x PHY Family") Signed-off-by: George Moussalem <george.moussalem(a)outlook.com> Signed-off-by: Christian Marangi <ansuelsmth(a)gmail.com> --- drivers/net/phy/qcom/qca807x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 3279de857b47..2ad8c2586d64 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -774,7 +774,7 @@ static int qca807x_config_init(struct phy_device *phydev) control_dac &= ~QCA807X_CONTROL_DAC_MASK; if (!priv->dac_full_amplitude) control_dac |= QCA807X_CONTROL_DAC_DSP_AMPLITUDE; - if (!priv->dac_full_amplitude) + if (!priv->dac_full_bias_current) control_dac |= QCA807X_CONTROL_DAC_DSP_BIAS_CURRENT; if (!priv->dac_disable_bias_current_tweak) control_dac |= QCA807X_CONTROL_DAC_BIAS_CURRENT_TWEAK; -- 2.47.1

6 months, 1 week

3
2
0 0

[PATCH v3 4/5] fprobe: Fix accounting of when to unregister from function graph

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> When adding a new fprobe, it will update the function hash to the functions the fprobe is attached to and register with function graph to have it call the registered functions. The fprobe_graph_active variable keeps track of the number of fprobes that are using function graph. If two fprobes attach to the same function, it increments the fprobe_graph_active for each of them. But when they are removed, the first fprobe to be removed will see that the function it is attached to is also used by another fprobe and it will not remove that function from function_graph. The logic will skip decrementing the fprobe_graph_active variable. This causes the fprobe_graph_active variable to not go to zero when all fprobes are removed, and in doing so it does not unregister from function graph. As the fgraph ops hash will now be empty, and an empty filter hash means all functions are enabled, this triggers function graph to add a callback to the fprobe infrastructure for every function! # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # echo "f:myevent2 kernel_clone%return" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc0024000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # > /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions trace_initcall_start_cb (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 run_init_process (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 try_to_run_init_process (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 x86_pmu_show_pmu_cap (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 cleanup_rapl_pmus (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_free_pcibus_map (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_types_exit (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_pci_exit.part.0 (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 kvm_shutdown (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 vmx_dump_msrs (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 [..] # cat /sys/kernel/tracing/enabled_functions | wc -l 54702 If a fprobe is being removed and all its functions are also traced by other fprobes, still decrement the fprobe_graph_active counter. Cc: stable(a)vger.kernel.org Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") Closes: https://lore.kernel.org/all/20250217114918.10397-A-hca@linux.ibm.com/ Reported-by: Heiko Carstens <hca(a)linux.ibm.com> Tested-by: Heiko Carstens <hca(a)linux.ibm.com> Acked-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/fprobe.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 62e8f7d56602..33082c4e8154 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -407,7 +407,8 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); + if (num) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } static int symbols_cmp(const void *a, const void *b) @@ -677,8 +678,7 @@ int unregister_fprobe(struct fprobe *fp) } del_fprobe_hash(fp); - if (count) - fprobe_graph_remove_ips(addrs, count); + fprobe_graph_remove_ips(addrs, count); kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; -- 2.47.2

6 months, 1 week

1
0
0 0

[PATCH v3 3/5] fprobe: Always unregister fgraph function from ops

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> When the last fprobe is removed, it calls unregister_ftrace_graph() to remove the graph_ops from function graph. The issue is when it does so, it calls return before removing the function from its graph ops via ftrace_set_filter_ips(). This leaves the last function lingering in the fprobe's fgraph ops and if a probe is added it also enables that last function (even though the callback will just drop it, it does add unneeded overhead to make that call). # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 schedule_timeout (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # > /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions # echo "f:myevent3 kmem_cache_free" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kmem_cache_free (1) tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 schedule_timeout (1) tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 The above enabled a fprobe on kernel_clone, and then on schedule_timeout. The content of the enabled_functions shows the functions that have a callback attached to them. The fprobe attached to those functions properly. Then the fprobes were cleared, and enabled_functions was empty after that. But after adding a fprobe on kmem_cache_free, the enabled_functions shows that the schedule_timeout was attached again. This is because it was still left in the fprobe ops that is used to tell function graph what functions it wants callbacks from. Cc: stable(a)vger.kernel.org Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") Tested-by: Heiko Carstens <hca(a)linux.ibm.com> Acked-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/fprobe.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 2560b312ad57..62e8f7d56602 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -403,11 +403,9 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) lockdep_assert_held(&fprobe_mutex); fprobe_graph_active--; - if (!fprobe_graph_active) { - /* Q: should we unregister it ? */ + /* Q: should we unregister it ? */ + if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - return; - } ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } -- 2.47.2

6 months, 1 week

1
0
0 0

[PATCH v3 2/5] ftrace: Do not add duplicate entries in subops manager ops

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Check if a function is already in the manager ops of a subops. A manager ops contains multiple subops, and if two or more subops are tracing the same function, the manager ops only needs a single entry in its hash. Cc: stable(a)vger.kernel.org Fixes: 4f554e955614f ("ftrace: Add ftrace_set_filter_ips function") Tested-by: Heiko Carstens <hca(a)linux.ibm.com> Reviewed-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/ftrace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index bec54dc27204..6b0c25761ccb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5718,6 +5718,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return -ENOENT; free_hash_entry(hash, entry); return 0; + } else if (__ftrace_lookup_ip(hash, ip) != NULL) { + /* Already exists */ + return 0; } entry = add_hash_entry(hash, ip); -- 2.47.2

6 months, 1 week

1
0
0 0

[PATCH v2 1/5] ftrace: Fix accounting of adding subops to a manager ops

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Function graph uses a subops and manager ops mechanism to attach to ftrace. The manager ops connects to ftrace and the functions it connects to is defined by a list of subops that it manages. The function hash that defines what the above ops attaches to limits the functions to attach if the hash has any content. If the hash is empty, it means to trace all functions. The creation of the manager ops hash is done by iterating over all the subops hashes. If any of the subops hashes is empty, it means that the manager ops hash must trace all functions as well. The issue is in the creation of the manager ops. When a second subops is attached, a new hash is created by starting it as NULL and adding the subops one at a time. But the NULL ops is mistaken as an empty hash, and once an empty hash is found, it stops the loop of subops and just enables all functions. # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions trace_initcall_start_cb (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 try_to_run_init_process (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 x86_pmu_show_pmu_cap (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 cleanup_rapl_pmus (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_free_pcibus_map (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_types_exit (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 uncore_pci_exit.part.0 (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 kvm_shutdown (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_dump_msrs (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 vmx_cleanup_l1d_flush (1) tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 [..] Fix this by initializing the new hash to NULL and if the hash is NULL do not treat it as an empty hash but instead allocate by copying the content of the first sub ops. Then on subsequent iterations, the new hash will not be NULL, but the content of the previous subops. If that first subops attached to all functions, then new hash may assume that the manager ops also needs to attach to all functions. Cc: stable(a)vger.kernel.org Fixes: 5fccc7552ccbc ("ftrace: Add subops logic to allow one ops to manage many") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/ftrace.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 728ecda6e8d4..03b35a05808c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3220,15 +3220,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src) * The filter_hash updates uses just the append_hash() function * and the notrace_hash does not. */ -static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash) +static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash, + int size_bits) { struct ftrace_func_entry *entry; int size; int i; - /* An empty hash does everything */ - if (ftrace_hash_empty(*hash)) - return 0; + if (*hash) { + /* An empty hash does everything */ + if (ftrace_hash_empty(*hash)) + return 0; + } else { + *hash = alloc_ftrace_hash(size_bits); + if (!*hash) + return -ENOMEM; + } /* If new_hash has everything make hash have everything */ if (ftrace_hash_empty(new_hash)) { @@ -3292,16 +3299,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has /* Return a new hash that has a union of all @ops->filter_hash entries */ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) { - struct ftrace_hash *new_hash; + struct ftrace_hash *new_hash = NULL; struct ftrace_ops *subops; + int size_bits; int ret; - new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits); - if (!new_hash) - return NULL; + if (ops->func_hash->filter_hash) + size_bits = ops->func_hash->filter_hash->size_bits; + else + size_bits = FTRACE_HASH_DEFAULT_BITS; list_for_each_entry(subops, &ops->subop_list, list) { - ret = append_hash(&new_hash, subops->func_hash->filter_hash); + ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits); if (ret < 0) { free_ftrace_hash(new_hash); return NULL; @@ -3505,7 +3514,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash); if (!filter_hash) return -ENOMEM; - ret = append_hash(&filter_hash, subops->func_hash->filter_hash); + ret = append_hash(&filter_hash, subops->func_hash->filter_hash, + size_bits); if (ret < 0) { free_ftrace_hash(filter_hash); return ret; -- 2.47.2

6 months, 1 week

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2025