diff options
59 files changed, 522 insertions, 390 deletions
diff --git a/Documentation/arch/riscv/zicfilp.rst b/Documentation/arch/riscv/zicfilp.rst index 78a3e01ff68c..ab7d8e62ddaf 100644 --- a/Documentation/arch/riscv/zicfilp.rst +++ b/Documentation/arch/riscv/zicfilp.rst @@ -76,34 +76,49 @@ the program. 4. prctl() enabling -------------------- -:c:macro:`PR_SET_INDIR_BR_LP_STATUS` / :c:macro:`PR_GET_INDIR_BR_LP_STATUS` / -:c:macro:`PR_LOCK_INDIR_BR_LP_STATUS` are three prctls added to manage indirect -branch tracking. These prctls are architecture-agnostic and return -EINVAL if -the underlying functionality is not supported. +Per-task indirect branch tracking state can be monitored and +controlled via the :c:macro:`PR_GET_CFI` and :c:macro:`PR_SET_CFI` +``prctl()` arguments (respectively), by supplying +:c:macro:`PR_CFI_BRANCH_LANDING_PADS` as the second argument. These +are architecture-agnostic, and will return -EINVAL if the underlying +functionality is not supported. -* prctl(PR_SET_INDIR_BR_LP_STATUS, unsigned long arg) +* prctl(:c:macro:`PR_SET_CFI`, :c:macro:`PR_CFI_BRANCH_LANDING_PADS`, unsigned long arg) -If arg1 is :c:macro:`PR_INDIR_BR_LP_ENABLE` and if CPU supports -``zicfilp`` then the kernel will enable indirect branch tracking for the -task. The dynamic loader can issue this :c:macro:`prctl` once it has -determined that all the objects loaded in the address space support -indirect branch tracking. Additionally, if there is a `dlopen` to an -object which wasn't compiled with ``zicfilp``, the dynamic loader can -issue this prctl with arg1 set to 0 (i.e. :c:macro:`PR_INDIR_BR_LP_ENABLE` -cleared). - -* prctl(PR_GET_INDIR_BR_LP_STATUS, unsigned long * arg) +arg is a bitmask. -Returns the current status of indirect branch tracking. If enabled -it'll return :c:macro:`PR_INDIR_BR_LP_ENABLE` - -* prctl(PR_LOCK_INDIR_BR_LP_STATUS, unsigned long arg) +If :c:macro:`PR_CFI_ENABLE` is set in arg, and the CPU supports +``zicfilp``, then the kernel will enable indirect branch tracking for +the task. The dynamic loader can issue this ``prctl()`` once it has +determined that all the objects loaded in the address space support +indirect branch tracking. + +Indirect branch tracking state can also be locked once enabled. This +prevents the task from subsequently disabling it. This is done by +setting the bit :c:macro:`PR_CFI_LOCK` in arg. Either indirect branch +tracking must already be enabled for the task, or the bit +:c:macro:`PR_CFI_ENABLE` must also be set in arg. This is intended +for environments that wish to run with a strict security posture that +do not wish to load objects without ``zicfilp`` support. + +Indirect branch tracking can also be disabled for the task, assuming +that it has not previously been enabled and locked. If there is a +``dlopen()`` to an object which wasn't compiled with ``zicfilp``, the +dynamic loader can issue this ``prctl()`` with arg set to +:c:macro:`PR_CFI_DISABLE`. Disabling indirect branch tracking for the +task is not possible if it has previously been enabled and locked. + + +* prctl(:c:macro:`PR_GET_CFI`, :c:macro:`PR_CFI_BRANCH_LANDING_PADS`, unsigned long * arg) + +Returns the current status of indirect branch tracking into a bitmask +stored into the memory location pointed to by arg. The bitmask will +have the :c:macro:`PR_CFI_ENABLE` bit set if indirect branch tracking +is currently enabled for the task, and if it is locked, will +additionally have the :c:macro:`PR_CFI_LOCK` bit set. If indirect +branch tracking is currently disabled for the task, the +:c:macro:`PR_CFI_DISABLE` bit will be set. -Locks the current status of indirect branch tracking on the task. User -space may want to run with a strict security posture and wouldn't want -loading of objects without ``zicfilp`` support in them, to disallow -disabling of indirect branch tracking. In this case, user space can -use this prctl to lock the current settings. 5. violations related to indirect branch tracking -------------------------------------------------- diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index 7495baae1e3c..f56966edbf5c 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -39,7 +39,7 @@ void set_active_shstk(struct task_struct *task, unsigned long shstk_addr); bool is_shstk_enabled(struct task_struct *task); bool is_shstk_locked(struct task_struct *task); bool is_shstk_allocated(struct task_struct *task); -void set_shstk_lock(struct task_struct *task); +void set_shstk_lock(struct task_struct *task, bool lock); void set_shstk_status(struct task_struct *task, bool enable); unsigned long get_active_shstk(struct task_struct *task); int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr); @@ -47,7 +47,7 @@ int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr); bool is_indir_lp_enabled(struct task_struct *task); bool is_indir_lp_locked(struct task_struct *task); void set_indir_lp_status(struct task_struct *task, bool enable); -void set_indir_lp_lock(struct task_struct *task); +void set_indir_lp_lock(struct task_struct *task, bool lock); #define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK (PR_SHADOW_STACK_ENABLE) @@ -69,7 +69,7 @@ void set_indir_lp_lock(struct task_struct *task); #define is_shstk_allocated(task) false -#define set_shstk_lock(task) do {} while (0) +#define set_shstk_lock(task, lock) do {} while (0) #define set_shstk_status(task, enable) do {} while (0) @@ -79,7 +79,7 @@ void set_indir_lp_lock(struct task_struct *task); #define set_indir_lp_status(task, enable) do {} while (0) -#define set_indir_lp_lock(task) do {} while (0) +#define set_indir_lp_lock(task, lock) do {} while (0) #define restore_user_shstk(tsk, shstk_ptr) -EINVAL diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 70a74adad914..3de2b7124aff 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -132,26 +132,28 @@ struct __sc_riscv_cfi_state { unsigned long ss_ptr; /* shadow stack pointer */ }; -#define PTRACE_CFI_LP_EN_BIT 0 -#define PTRACE_CFI_LP_LOCK_BIT 1 -#define PTRACE_CFI_ELP_BIT 2 -#define PTRACE_CFI_SS_EN_BIT 3 -#define PTRACE_CFI_SS_LOCK_BIT 4 -#define PTRACE_CFI_SS_PTR_BIT 5 - -#define PTRACE_CFI_LP_EN_STATE _BITUL(PTRACE_CFI_LP_EN_BIT) -#define PTRACE_CFI_LP_LOCK_STATE _BITUL(PTRACE_CFI_LP_LOCK_BIT) -#define PTRACE_CFI_ELP_STATE _BITUL(PTRACE_CFI_ELP_BIT) -#define PTRACE_CFI_SS_EN_STATE _BITUL(PTRACE_CFI_SS_EN_BIT) -#define PTRACE_CFI_SS_LOCK_STATE _BITUL(PTRACE_CFI_SS_LOCK_BIT) -#define PTRACE_CFI_SS_PTR_STATE _BITUL(PTRACE_CFI_SS_PTR_BIT) - -#define PRACE_CFI_STATE_INVALID_MASK ~(PTRACE_CFI_LP_EN_STATE | \ - PTRACE_CFI_LP_LOCK_STATE | \ - PTRACE_CFI_ELP_STATE | \ - PTRACE_CFI_SS_EN_STATE | \ - PTRACE_CFI_SS_LOCK_STATE | \ - PTRACE_CFI_SS_PTR_STATE) +#define PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT 0 +#define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT 1 +#define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT 2 +#define PTRACE_CFI_SHADOW_STACK_EN_BIT 3 +#define PTRACE_CFI_SHADOW_STACK_LOCK_BIT 4 +#define PTRACE_CFI_SHADOW_STACK_PTR_BIT 5 + +#define PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE _BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT) +#define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE \ + _BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT) +#define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE \ + _BITUL(PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT) +#define PTRACE_CFI_SHADOW_STACK_EN_STATE _BITUL(PTRACE_CFI_SHADOW_STACK_EN_BIT) +#define PTRACE_CFI_SHADOW_STACK_LOCK_STATE _BITUL(PTRACE_CFI_SHADOW_STACK_LOCK_BIT) +#define PTRACE_CFI_SHADOW_STACK_PTR_STATE _BITUL(PTRACE_CFI_SHADOW_STACK_PTR_BIT) + +#define PTRACE_CFI_STATE_INVALID_MASK ~(PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | \ + PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE | \ + PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE | \ + PTRACE_CFI_SHADOW_STACK_EN_STATE | \ + PTRACE_CFI_SHADOW_STACK_LOCK_STATE | \ + PTRACE_CFI_SHADOW_STACK_PTR_STATE) struct __cfi_status { __u64 cfi_state; diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 5957effab57c..b2df7f72241a 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -160,6 +160,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, * clear shadow stack state on exec. * libc will set it later via prctl. */ + set_shstk_lock(current, false); set_shstk_status(current, false); set_shstk_base(current, 0, 0); set_active_shstk(current, 0); @@ -167,6 +168,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc, * disable indirect branch tracking on exec. * libc will enable it later via prctl. */ + set_indir_lp_lock(current, false); set_indir_lp_status(current, false); #ifdef CONFIG_64BIT diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index e592bd6b7665..93de2e7a3074 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -303,18 +303,18 @@ static int riscv_cfi_get(struct task_struct *target, regs = task_pt_regs(target); if (is_indir_lp_enabled(target)) { - user_cfi.cfi_status.cfi_state |= PTRACE_CFI_LP_EN_STATE; + user_cfi.cfi_status.cfi_state |= PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE; user_cfi.cfi_status.cfi_state |= is_indir_lp_locked(target) ? - PTRACE_CFI_LP_LOCK_STATE : 0; + PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE : 0; user_cfi.cfi_status.cfi_state |= (regs->status & SR_ELP) ? - PTRACE_CFI_ELP_STATE : 0; + PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE : 0; } if (is_shstk_enabled(target)) { - user_cfi.cfi_status.cfi_state |= (PTRACE_CFI_SS_EN_STATE | - PTRACE_CFI_SS_PTR_STATE); + user_cfi.cfi_status.cfi_state |= (PTRACE_CFI_SHADOW_STACK_EN_STATE | + PTRACE_CFI_SHADOW_STACK_PTR_STATE); user_cfi.cfi_status.cfi_state |= is_shstk_locked(target) ? - PTRACE_CFI_SS_LOCK_STATE : 0; + PTRACE_CFI_SHADOW_STACK_LOCK_STATE : 0; user_cfi.shstk_ptr = get_active_shstk(target); } @@ -349,15 +349,15 @@ static int riscv_cfi_set(struct task_struct *target, * rsvd field should be set to zero so that if those fields are needed in future */ if ((user_cfi.cfi_status.cfi_state & - (PTRACE_CFI_LP_EN_STATE | PTRACE_CFI_LP_LOCK_STATE | - PTRACE_CFI_SS_EN_STATE | PTRACE_CFI_SS_LOCK_STATE)) || - (user_cfi.cfi_status.cfi_state & PRACE_CFI_STATE_INVALID_MASK)) + (PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE | + PTRACE_CFI_SHADOW_STACK_EN_STATE | PTRACE_CFI_SHADOW_STACK_LOCK_STATE)) || + (user_cfi.cfi_status.cfi_state & PTRACE_CFI_STATE_INVALID_MASK)) return -EINVAL; /* If lpad is enabled on target and ptrace requests to set / clear elp, do that */ if (is_indir_lp_enabled(target)) { if (user_cfi.cfi_status.cfi_state & - PTRACE_CFI_ELP_STATE) /* set elp state */ + PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE) /* set elp state */ regs->status |= SR_ELP; else regs->status &= ~SR_ELP; /* clear elp state */ @@ -365,7 +365,7 @@ static int riscv_cfi_set(struct task_struct *target, /* If shadow stack enabled on target, set new shadow stack pointer */ if (is_shstk_enabled(target) && - (user_cfi.cfi_status.cfi_state & PTRACE_CFI_SS_PTR_STATE)) + (user_cfi.cfi_status.cfi_state & PTRACE_CFI_SHADOW_STACK_PTR_STATE)) set_active_shstk(target, user_cfi.shstk_ptr); return 0; diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 1adba746f164..2c535737511d 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -74,9 +74,9 @@ void set_shstk_status(struct task_struct *task, bool enable) csr_write(CSR_ENVCFG, task->thread.envcfg); } -void set_shstk_lock(struct task_struct *task) +void set_shstk_lock(struct task_struct *task, bool lock) { - task->thread_info.user_cfi_state.ubcfi_locked = 1; + task->thread_info.user_cfi_state.ubcfi_locked = lock; } bool is_indir_lp_enabled(struct task_struct *task) @@ -104,9 +104,9 @@ void set_indir_lp_status(struct task_struct *task, bool enable) csr_write(CSR_ENVCFG, task->thread.envcfg); } -void set_indir_lp_lock(struct task_struct *task) +void set_indir_lp_lock(struct task_struct *task, bool lock) { - task->thread_info.user_cfi_state.ufcfi_locked = 1; + task->thread_info.user_cfi_state.ufcfi_locked = lock; } /* * If size is 0, then to be compatible with regular stack we want it to be as big as @@ -452,28 +452,27 @@ int arch_lock_shadow_stack_status(struct task_struct *task, !is_shstk_enabled(task) || arg != 0) return -EINVAL; - set_shstk_lock(task); + set_shstk_lock(task, true); return 0; } -int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status) +int arch_prctl_get_branch_landing_pad_state(struct task_struct *t, + unsigned long __user *state) { unsigned long fcfi_status = 0; if (!is_user_lpad_enabled()) return -EINVAL; - /* indirect branch tracking is enabled on the task or not */ - fcfi_status |= (is_indir_lp_enabled(t) ? PR_INDIR_BR_LP_ENABLE : 0); + fcfi_status = (is_indir_lp_enabled(t) ? PR_CFI_ENABLE : PR_CFI_DISABLE); + fcfi_status |= (is_indir_lp_locked(t) ? PR_CFI_LOCK : 0); - return copy_to_user(status, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0; + return copy_to_user(state, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0; } -int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status) +int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state) { - bool enable_indir_lp = false; - if (!is_user_lpad_enabled()) return -EINVAL; @@ -481,28 +480,28 @@ int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status) if (is_indir_lp_locked(t)) return -EINVAL; - /* Reject unknown flags */ - if (status & ~PR_INDIR_BR_LP_ENABLE) + if (!(state & (PR_CFI_ENABLE | PR_CFI_DISABLE))) + return -EINVAL; + + if (state & PR_CFI_ENABLE && state & PR_CFI_DISABLE) return -EINVAL; - enable_indir_lp = (status & PR_INDIR_BR_LP_ENABLE); - set_indir_lp_status(t, enable_indir_lp); + set_indir_lp_status(t, !!(state & PR_CFI_ENABLE)); return 0; } -int arch_lock_indir_br_lp_status(struct task_struct *task, - unsigned long arg) +int arch_prctl_lock_branch_landing_pad_state(struct task_struct *task) { /* * If indirect branch tracking is not supported or not enabled on task, * nothing to lock here */ if (!is_user_lpad_enabled() || - !is_indir_lp_enabled(task) || arg != 0) + !is_indir_lp_enabled(task)) return -EINVAL; - set_indir_lp_lock(task); + set_indir_lp_lock(task, true); return 0; } diff --git a/drivers/accel/ethosu/Kconfig b/drivers/accel/ethosu/Kconfig index d25f9b3eb317..f68e6e286903 100644 --- a/drivers/accel/ethosu/Kconfig +++ b/drivers/accel/ethosu/Kconfig @@ -4,6 +4,7 @@ config DRM_ACCEL_ARM_ETHOSU tristate "Arm Ethos-U65/U85 NPU" depends on HAS_IOMEM depends on DRM_ACCEL + depends on ARM || ARM64 || COMPILE_TEST select DRM_GEM_DMA_HELPER select DRM_SCHED select GENERIC_ALLOCATOR diff --git a/drivers/base/class.c b/drivers/base/class.c index 827fc7adacc7..ffab0a9c8ccb 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -127,7 +127,7 @@ static const struct kobj_type class_ktype = { }; int class_create_file_ns(const struct class *cls, const struct class_attribute *attr, - const void *ns) + const struct ns_common *ns) { struct subsys_private *sp = class_to_subsys(cls); int error; @@ -143,7 +143,7 @@ int class_create_file_ns(const struct class *cls, const struct class_attribute * EXPORT_SYMBOL_GPL(class_create_file_ns); void class_remove_file_ns(const struct class *cls, const struct class_attribute *attr, - const void *ns) + const struct ns_common *ns) { struct subsys_private *sp = class_to_subsys(cls); diff --git a/drivers/base/core.c b/drivers/base/core.c index 09b98f02f559..0613de0fbe44 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2570,15 +2570,14 @@ static void device_release(struct kobject *kobj) kfree(p); } -static const void *device_namespace(const struct kobject *kobj) +static const struct ns_common *device_namespace(const struct kobject *kobj) { const struct device *dev = kobj_to_dev(kobj); - const void *ns = NULL; if (dev->class && dev->class->namespace) - ns = dev->class->namespace(dev); + return dev->class->namespace(dev); - return ns; + return NULL; } static void device_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) diff --git a/drivers/gpio/gpio-bd72720.c b/drivers/gpio/gpio-bd72720.c index 6549dbf4c7ad..d0f936ed80af 100644 --- a/drivers/gpio/gpio-bd72720.c +++ b/drivers/gpio/gpio-bd72720.c @@ -256,6 +256,8 @@ static int gpo_bd72720_probe(struct platform_device *pdev) g->dev = dev; g->chip.parent = parent; g->regmap = dev_get_regmap(parent, NULL); + if (!g->regmap) + return -ENODEV; return devm_gpiochip_add_data(dev, &g->chip, g); } diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index 15a5762a82c2..df06b56a2ade 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -595,7 +595,7 @@ static void tegra_gpio_irq_release_resources(struct irq_data *d) struct tegra_gpio_info *tgi = gpiochip_get_data(chip); gpiochip_relres_irq(chip, d->hwirq); - tegra_gpio_enable(tgi, d->hwirq); + tegra_gpio_disable(tgi, d->hwirq); } static void tegra_gpio_irq_print_chip(struct irq_data *d, struct seq_file *s) @@ -698,7 +698,7 @@ static int tegra_gpio_probe(struct platform_device *pdev) tgi = devm_kzalloc(&pdev->dev, sizeof(*tgi), GFP_KERNEL); if (!tgi) - return -ENODEV; + return -ENOMEM; tgi->soc = of_device_get_match_data(&pdev->dev); tgi->dev = &pdev->dev; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 3791944389db..097e18c1adb2 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -2678,9 +2678,9 @@ static u32 psr2_pipe_srcsz_early_tpt_calc(struct intel_crtc_state *crtc_state, static void clip_area_update(struct drm_rect *overlap_damage_area, struct drm_rect *damage_area, - struct drm_rect *pipe_src) + struct drm_rect *display_area) { - if (!drm_rect_intersect(damage_area, pipe_src)) + if (!drm_rect_intersect(damage_area, display_area)) return; if (overlap_damage_area->y1 == -1) { @@ -2731,6 +2731,7 @@ static bool intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st static void intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state, struct intel_crtc *crtc, + struct drm_rect *display_area, bool *cursor_in_su_area) { struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); @@ -2758,7 +2759,7 @@ intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state, continue; clip_area_update(&crtc_state->psr2_su_area, &new_plane_state->uapi.dst, - &crtc_state->pipe_src); + display_area); *cursor_in_su_area = true; } } @@ -2855,6 +2856,12 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_plane_state *new_plane_state, *old_plane_state; struct intel_plane *plane; + struct drm_rect display_area = { + .x1 = 0, + .y1 = 0, + .x2 = crtc_state->hw.adjusted_mode.crtc_hdisplay, + .y2 = crtc_state->hw.adjusted_mode.crtc_vdisplay, + }; bool full_update = false, su_area_changed; int i, ret; @@ -2868,7 +2875,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, crtc_state->psr2_su_area.x1 = 0; crtc_state->psr2_su_area.y1 = -1; - crtc_state->psr2_su_area.x2 = drm_rect_width(&crtc_state->pipe_src); + crtc_state->psr2_su_area.x2 = drm_rect_width(&display_area); crtc_state->psr2_su_area.y2 = -1; /* @@ -2906,14 +2913,14 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, damaged_area.y1 = old_plane_state->uapi.dst.y1; damaged_area.y2 = old_plane_state->uapi.dst.y2; clip_area_update(&crtc_state->psr2_su_area, &damaged_area, - &crtc_state->pipe_src); + &display_area); } if (new_plane_state->uapi.visible) { damaged_area.y1 = new_plane_state->uapi.dst.y1; damaged_area.y2 = new_plane_state->uapi.dst.y2; clip_area_update(&crtc_state->psr2_su_area, &damaged_area, - &crtc_state->pipe_src); + &display_area); } continue; } else if (new_plane_state->uapi.alpha != old_plane_state->uapi.alpha) { @@ -2921,7 +2928,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, damaged_area.y1 = new_plane_state->uapi.dst.y1; damaged_area.y2 = new_plane_state->uapi.dst.y2; clip_area_update(&crtc_state->psr2_su_area, &damaged_area, - &crtc_state->pipe_src); + &display_area); continue; } @@ -2937,7 +2944,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, damaged_area.x1 += new_plane_state->uapi.dst.x1 - src.x1; damaged_area.x2 += new_plane_state->uapi.dst.x1 - src.x1; - clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &crtc_state->pipe_src); + clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &display_area); } /* @@ -2972,7 +2979,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, * cursor is added into affected planes even when * cursor is not updated by itself. */ - intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area); + intel_psr2_sel_fetch_et_alignment(state, crtc, &display_area, + &cursor_in_su_area); su_area_changed = intel_psr2_sel_fetch_pipe_alignment(crtc_state); @@ -3048,8 +3056,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, skip_sel_fetch_set_loop: if (full_update) - clip_area_update(&crtc_state->psr2_su_area, &crtc_state->pipe_src, - &crtc_state->pipe_src); + clip_area_update(&crtc_state->psr2_su_area, &display_area, + &display_area); psr2_man_trk_ctl_calc(crtc_state, full_update); crtc_state->pipe_srcsz_early_tpt = diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 942f4eed817f..65ce54b20ec2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -896,7 +896,7 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) rcu_read_lock(); vma = radix_tree_lookup(&eb->gem_context->handles_vma, handle); - if (likely(vma && vma->vm == vm)) + if (likely(vma)) vma = i915_vma_tryget(vma); else vma = NULL; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index b279878dca29..6424ecce8bcb 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -148,10 +148,12 @@ static void heartbeat(struct work_struct *wrk) /* Just in case everything has gone horribly wrong, give it a kick */ intel_engine_flush_submission(engine); - rq = engine->heartbeat.systole; - if (rq && i915_request_completed(rq)) { - i915_request_put(rq); - engine->heartbeat.systole = NULL; + rq = xchg(&engine->heartbeat.systole, NULL); + if (rq) { + if (i915_request_completed(rq)) + i915_request_put(rq); + else + engine->heartbeat.systole = rq; } if (!intel_engine_pm_get_if_awake(engine)) @@ -232,8 +234,11 @@ static void heartbeat(struct work_struct *wrk) unlock: mutex_unlock(&ce->timeline->mutex); out: - if (!engine->i915->params.enable_hangcheck || !next_heartbeat(engine)) - i915_request_put(fetch_and_zero(&engine->heartbeat.systole)); + if (!engine->i915->params.enable_hangcheck || !next_heartbeat(engine)) { + rq = xchg(&engine->heartbeat.systole, NULL); + if (rq) + i915_request_put(rq); + } intel_engine_pm_put(engine); } @@ -247,8 +252,13 @@ void intel_engine_unpark_heartbeat(struct intel_engine_cs *engine) void intel_engine_park_heartbeat(struct intel_engine_cs *engine) { - if (cancel_delayed_work(&engine->heartbeat.work)) - i915_request_put(fetch_and_zero(&engine->heartbeat.systole)); + if (cancel_delayed_work(&engine->heartbeat.work)) { + struct i915_request *rq; + + rq = xchg(&engine->heartbeat.systole, NULL); + if (rq) + i915_request_put(rq); + } } void intel_gt_unpark_heartbeats(struct intel_gt *gt) diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 1f93bc5a3d02..cb2b62a41972 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -738,12 +738,15 @@ static int vc4_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct return -EINVAL; } + mutex_lock(&bo->madv_lock); if (bo->madv != VC4_MADV_WILLNEED) { DRM_DEBUG("mmapping of %s BO not allowed\n", bo->madv == VC4_MADV_DONTNEED ? "purgeable" : "purged"); + mutex_unlock(&bo->madv_lock); return -EINVAL; } + mutex_unlock(&bo->madv_lock); return drm_gem_dma_mmap(&bo->base, vma); } diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index ad8cbd727b80..34bdac107ce1 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -62,6 +62,7 @@ vc4_free_hang_state(struct drm_device *dev, struct vc4_hang_state *state) for (i = 0; i < state->user_state.bo_count; i++) drm_gem_object_put(state->bo[i]); + kfree(state->bo); kfree(state); } @@ -170,10 +171,8 @@ vc4_save_hang_state(struct drm_device *dev) spin_lock_irqsave(&vc4->job_lock, irqflags); exec[0] = vc4_first_bin_job(vc4); exec[1] = vc4_first_render_job(vc4); - if (!exec[0] && !exec[1]) { - spin_unlock_irqrestore(&vc4->job_lock, irqflags); - return; - } + if (!exec[0] && !exec[1]) + goto err_free_state; /* Get the bos from both binner and renderer into hang state. */ state->bo_count = 0; @@ -190,10 +189,8 @@ vc4_save_hang_state(struct drm_device *dev) kernel_state->bo = kzalloc_objs(*kernel_state->bo, state->bo_count, GFP_ATOMIC); - if (!kernel_state->bo) { - spin_unlock_irqrestore(&vc4->job_lock, irqflags); - return; - } + if (!kernel_state->bo) + goto err_free_state; k = 0; for (i = 0; i < 2; i++) { @@ -285,6 +282,12 @@ vc4_save_hang_state(struct drm_device *dev) vc4->hang_state = kernel_state; spin_unlock_irqrestore(&vc4->job_lock, irqflags); } + + return; + +err_free_state: + spin_unlock_irqrestore(&vc4->job_lock, irqflags); + kfree(kernel_state); } static void diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index 3ffe09bc89d2..d31b906cb8e7 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -481,6 +481,7 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, 40); /* a little over 2 frames. */ + pm_runtime_put_autosuspend(dev); return 0; diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c index 688d645e0e73..aa0b7a427f0b 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine.c +++ b/drivers/gpu/drm/xe/xe_hw_engine.c @@ -595,9 +595,8 @@ static void adjust_idledly(struct xe_hw_engine *hwe) maxcnt *= maxcnt_units_ns; if (xe_gt_WARN_ON(gt, idledly >= maxcnt || inhibit_switch)) { - idledly = DIV_ROUND_CLOSEST(((maxcnt - 1) * maxcnt_units_ns), + idledly = DIV_ROUND_CLOSEST(((maxcnt - 1) * 1000), idledly_units_ps); - idledly = DIV_ROUND_CLOSEST(idledly, 1000); xe_mmio_write32(>->mmio, RING_IDLEDLY(hwe->mmio_base), idledly); } } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 558b73940d66..7945614be36d 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -509,12 +509,13 @@ static int ib_device_uevent(const struct device *device, return 0; } -static const void *net_namespace(const struct device *d) +static const struct ns_common *net_namespace(const struct device *d) { const struct ib_core_device *coredev = container_of(d, struct ib_core_device, dev); + struct net *net = read_pnet(&coredev->rdma_net); - return read_pnet(&coredev->rdma_net); + return net ? to_ns_common(net) : NULL; } static struct class ib_class = { diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 30339dcabb4d..b58868e1cf11 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -43,6 +43,7 @@ #include <linux/jiffies.h> #include <linux/lockdep.h> #include <linux/inet.h> +#include <net/net_namespace.h> #include <rdma/ib_cache.h> #include <linux/atomic.h> @@ -1048,7 +1049,7 @@ static void srp_remove_target(struct srp_target_port *target) scsi_remove_host(target->scsi_host); srp_stop_rport_timers(target->rport); srp_disconnect_target(target); - kobj_ns_drop(KOBJ_NS_TYPE_NET, target->net); + kobj_ns_drop(KOBJ_NS_TYPE_NET, to_ns_common(target->net)); for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; srp_free_ch_ib(target, ch); @@ -3713,7 +3714,7 @@ static ssize_t add_target_store(struct device *dev, target = host_to_target(target_host); - target->net = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); + target->net = to_net_ns(kobj_ns_grab_current(KOBJ_NS_TYPE_NET)); target->io_class = SRP_REV16A_IB_IO_CLASS; target->scsi_host = target_host; target->srp_host = host; @@ -3905,7 +3906,7 @@ put: * earlier in this function. */ if (target->state != SRP_TARGET_REMOVED) - kobj_ns_drop(KOBJ_NS_TYPE_NET, target->net); + kobj_ns_drop(KOBJ_NS_TYPE_NET, to_ns_common(target->net)); scsi_host_put(target->scsi_host); } diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 9a75ad3181ab..eaba44c76a5e 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -808,7 +808,7 @@ int __net_init bond_create_sysfs(struct bond_net *bn) sysfs_attr_init(&bn->class_attr_bonding_masters.attr); ret = netdev_class_create_file_ns(&bn->class_attr_bonding_masters, - bn->net); + to_ns_common(bn->net)); /* Permit multiple loads of the module by ignoring failures to * create the bonding_masters sysfs file. Bonding devices * created by second or subsequent loads of the module will @@ -835,7 +835,7 @@ int __net_init bond_create_sysfs(struct bond_net *bn) /* Remove /sys/class/net/bonding_masters. */ void __net_exit bond_destroy_sysfs(struct bond_net *bn) { - netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net); + netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, to_ns_common(bn->net)); } /* Initialize sysfs for each bond. This sets up and registers diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index edd13916831a..2d6bbddd1edd 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -30,10 +30,11 @@ static dev_t ipvtap_major; static struct cdev ipvtap_cdev; -static const void *ipvtap_net_namespace(const struct device *d) +static const struct ns_common *ipvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); - return dev_net(dev); + + return to_ns_common(dev_net(dev)); } static struct class ipvtap_class = { diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index b391a0f740a3..cc975dfb7380 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -35,10 +35,11 @@ struct macvtap_dev { */ static dev_t macvtap_major; -static const void *macvtap_net_namespace(const struct device *d) +static const struct ns_common *macvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); - return dev_net(dev); + + return to_ns_common(dev_net(dev)); } static struct class macvtap_class = { diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 9d32bb8bc13a..97bf5ec78db4 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -53,8 +53,6 @@ #define PADOWN_MASK(p) (GENMASK(3, 0) << PADOWN_SHIFT(p)) #define PADOWN_GPP(p) ((p) / 8) -#define PWMC 0x204 - /* Offset from pad_regs */ #define PADCFG0 0x000 #define PADCFG0_RXEVCFG_MASK GENMASK(26, 25) @@ -205,19 +203,25 @@ static bool intel_pad_owned_by_host(const struct intel_pinctrl *pctrl, unsigned community = intel_get_community(pctrl, pin); if (!community) return false; - if (!community->padown_offset) + + /* If padown_offset is not provided, assume host ownership */ + padown = community->regs + community->padown_offset; + if (padown == community->regs) return true; + /* New HW generations have extended PAD_OWN registers */ + if (community->features & PINCTRL_FEATURE_3BIT_PAD_OWN) + return !(readl(padown + pin_to_padno(community, pin) * 4) & 7); + padgrp = intel_community_get_padgroup(community, pin); if (!padgrp) return false; gpp_offset = padgroup_offset(padgrp, pin); gpp = PADOWN_GPP(gpp_offset); - offset = community->padown_offset + padgrp->padown_num * 4 + gpp * 4; - padown = community->regs + offset; + offset = padgrp->padown_num * 4 + gpp * 4; - return !(readl(padown) & PADOWN_MASK(gpp_offset)); + return !(readl(padown + offset) & PADOWN_MASK(gpp_offset)); } static bool intel_pad_acpi_mode(const struct intel_pinctrl *pctrl, unsigned int pin) @@ -1549,8 +1553,10 @@ static int intel_pinctrl_pm_init(struct intel_pinctrl *pctrl) } static int intel_pinctrl_probe_pwm(struct intel_pinctrl *pctrl, - struct intel_community *community) + struct intel_community *community, + unsigned short capability_offset) { + void __iomem *base = community->regs + capability_offset + 4; static const struct pwm_lpss_boardinfo info = { .clk_rate = 19200000, .npwm = 1, @@ -1564,7 +1570,7 @@ static int intel_pinctrl_probe_pwm(struct intel_pinctrl *pctrl, if (!IS_REACHABLE(CONFIG_PWM_LPSS)) return 0; - chip = devm_pwm_lpss_probe(pctrl->dev, community->regs + PWMC, &info); + chip = devm_pwm_lpss_probe(pctrl->dev, base, &info); return PTR_ERR_OR_ZERO(chip); } @@ -1595,7 +1601,9 @@ int intel_pinctrl_probe(struct platform_device *pdev, for (i = 0; i < pctrl->ncommunities; i++) { struct intel_community *community = &pctrl->communities[i]; + unsigned short capability_offset[6]; void __iomem *regs; + u32 revision; u32 offset; u32 value; @@ -1610,10 +1618,14 @@ int intel_pinctrl_probe(struct platform_device *pdev, value = readl(regs + REVID); if (value == ~0u) return -ENODEV; - if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x94) { + + revision = (value & REVID_MASK) >> REVID_SHIFT; + if (revision >= 0x092) { community->features |= PINCTRL_FEATURE_DEBOUNCE; community->features |= PINCTRL_FEATURE_1K_PD; } + if (revision >= 0x110) + community->features |= PINCTRL_FEATURE_3BIT_PAD_OWN; /* Determine community features based on the capabilities */ offset = CAPLIST; @@ -1622,15 +1634,19 @@ int intel_pinctrl_probe(struct platform_device *pdev, switch ((value & CAPLIST_ID_MASK) >> CAPLIST_ID_SHIFT) { case CAPLIST_ID_GPIO_HW_INFO: community->features |= PINCTRL_FEATURE_GPIO_HW_INFO; + capability_offset[CAPLIST_ID_GPIO_HW_INFO] = offset; break; case CAPLIST_ID_PWM: community->features |= PINCTRL_FEATURE_PWM; + capability_offset[CAPLIST_ID_PWM] = offset; break; case CAPLIST_ID_BLINK: community->features |= PINCTRL_FEATURE_BLINK; + capability_offset[CAPLIST_ID_BLINK] = offset; break; case CAPLIST_ID_EXP: community->features |= PINCTRL_FEATURE_EXP; + capability_offset[CAPLIST_ID_EXP] = offset; break; default: break; @@ -1653,7 +1669,7 @@ int intel_pinctrl_probe(struct platform_device *pdev, if (ret) return ret; - ret = intel_pinctrl_probe_pwm(pctrl, community); + ret = intel_pinctrl_probe_pwm(pctrl, community, capability_offset[CAPLIST_ID_PWM]); if (ret) return ret; } diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h index 2f37109d5860..b5476b9de0db 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -150,6 +150,7 @@ struct intel_community { #define PINCTRL_FEATURE_PWM BIT(3) #define PINCTRL_FEATURE_BLINK BIT(4) #define PINCTRL_FEATURE_EXP BIT(5) +#define PINCTRL_FEATURE_3BIT_PAD_OWN BIT(6) #define __INTEL_COMMUNITY(b, s, e, g, n, gs, gn, soc) \ { \ diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 586f2f67c617..b89b3169e8be 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -664,6 +664,15 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, if (mcp->irq && mcp->irq_controller) { struct gpio_irq_chip *girq = &mcp->chip.irq; + /* + * Disable all pin interrupts, to prevent the interrupt handler from + * calling nested handlers for any currently-enabled interrupts that + * do not (yet) have an actual handler. + */ + ret = mcp_write(mcp, MCP_GPINTEN, 0); + if (ret < 0) + return dev_err_probe(dev, ret, "can't disable interrupts\n"); + gpio_irq_chip_set_chip(girq, &mcp23s08_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index e5ec90dccc27..eb9eb7683e3c 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -810,6 +810,11 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, if (ret < 0) goto error_unlock; + /* + * cachefiles_bury_object() expects 2 references to 'victim', + * and drops one. + */ + dget(victim); ret = cachefiles_bury_object(cache, NULL, dir, victim, FSCACHE_OBJECT_WAS_CULLED); dput(victim); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 5714e900567c..4b43bf41296d 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -226,6 +226,9 @@ struct eventpoll { */ refcount_t refcount; + /* used to defer freeing past ep_get_upwards_depth_proc() RCU walk */ + struct rcu_head rcu; + #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; @@ -819,7 +822,8 @@ static void ep_free(struct eventpoll *ep) mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); - kfree(ep); + /* ep_get_upwards_depth_proc() may still hold epi->ep under RCU */ + kfree_rcu(ep, rcu); } /* diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 8d40c4b1db9f..22a4dff2a3af 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/security.h> #include <linux/hash.h> +#include <linux/ns_common.h> #include "kernfs-internal.h" @@ -306,6 +307,18 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) return parent; } +/* + * kernfs_ns_id - return the namespace id for a given namespace + * @ns: namespace tag (may be NULL) + * + * Use the 64-bit namespace id instead of raw pointers for hashing + * and comparison to avoid leaking kernel addresses to userspace. + */ +static u64 kernfs_ns_id(const struct ns_common *ns) +{ + return ns ? ns->ns_id : 0; +} + /** * kernfs_name_hash - calculate hash of @ns + @name * @name: Null terminated string to hash @@ -313,9 +326,10 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) * * Return: 31-bit hash of ns + name (so it fits in an off_t) */ -static unsigned int kernfs_name_hash(const char *name, const void *ns) +static unsigned int kernfs_name_hash(const char *name, + const struct ns_common *ns) { - unsigned long hash = init_name_hash(ns); + unsigned long hash = init_name_hash(kernfs_ns_id(ns)); unsigned int len = strlen(name); while (len--) hash = partial_name_hash(*name++, hash); @@ -330,15 +344,18 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns) } static int kernfs_name_compare(unsigned int hash, const char *name, - const void *ns, const struct kernfs_node *kn) + const struct ns_common *ns, const struct kernfs_node *kn) { + u64 ns_id = kernfs_ns_id(ns); + u64 kn_ns_id = kernfs_ns_id(kn->ns); + if (hash < kn->hash) return -1; if (hash > kn->hash) return 1; - if (ns < kn->ns) + if (ns_id < kn_ns_id) return -1; - if (ns > kn->ns) + if (ns_id > kn_ns_id) return 1; return strcmp(name, kernfs_rcu_name(kn)); } @@ -856,7 +873,7 @@ out_unlock: */ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, const unsigned char *name, - const void *ns) + const struct ns_common *ns) { struct rb_node *node = parent->dir.children.rb_node; bool has_ns = kernfs_ns_enabled(parent); @@ -889,7 +906,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, const unsigned char *path, - const void *ns) + const struct ns_common *ns) { ssize_t len; char *p, *name; @@ -930,7 +947,8 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, - const char *name, const void *ns) + const char *name, + const struct ns_common *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); @@ -956,7 +974,8 @@ EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, - const char *path, const void *ns) + const char *path, + const struct ns_common *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); @@ -1079,7 +1098,8 @@ struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root) struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, - void *priv, const void *ns) + void *priv, + const struct ns_common *ns) { struct kernfs_node *kn; int rc; @@ -1199,7 +1219,7 @@ static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, /* The kernfs node has been moved to a different namespace */ if (parent && kernfs_ns_enabled(parent) && - kernfs_info(dentry->d_sb)->ns != kn->ns) + kernfs_ns_id(kernfs_info(dentry->d_sb)->ns) != kernfs_ns_id(kn->ns)) goto out_bad; up_read(&root->kernfs_rwsem); @@ -1221,7 +1241,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, struct kernfs_node *kn; struct kernfs_root *root; struct inode *inode = NULL; - const void *ns = NULL; + const struct ns_common *ns = NULL; root = kernfs_root(parent); down_read(&root->kernfs_rwsem); @@ -1702,7 +1722,7 @@ bool kernfs_remove_self(struct kernfs_node *kn) * Return: %0 on success, -ENOENT if such entry doesn't exist. */ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, - const void *ns) + const struct ns_common *ns) { struct kernfs_node *kn; struct kernfs_root *root; @@ -1741,7 +1761,7 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, * Return: %0 on success, -errno on failure. */ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, - const char *new_name, const void *new_ns) + const char *new_name, const struct ns_common *new_ns) { struct kernfs_node *old_parent; struct kernfs_root *root; @@ -1771,7 +1791,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, old_name = kernfs_rcu_name(kn); if (!new_name) new_name = old_name; - if ((old_parent == new_parent) && (kn->ns == new_ns) && + if ((old_parent == new_parent) && + (kernfs_ns_id(kn->ns) == kernfs_ns_id(new_ns)) && (strcmp(old_name, new_name) == 0)) goto out; /* nothing to rename */ @@ -1832,7 +1853,7 @@ static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) return 0; } -static struct kernfs_node *kernfs_dir_pos(const void *ns, +static struct kernfs_node *kernfs_dir_pos(const struct ns_common *ns, struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos) { if (pos) { @@ -1845,6 +1866,7 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, } if (!pos && (hash > 1) && (hash < INT_MAX)) { struct rb_node *node = parent->dir.children.rb_node; + u64 ns_id = kernfs_ns_id(ns); while (node) { pos = rb_to_kn(node); @@ -1852,12 +1874,17 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, node = node->rb_left; else if (hash > pos->hash) node = node->rb_right; + else if (ns_id < kernfs_ns_id(pos->ns)) + node = node->rb_left; + else if (ns_id > kernfs_ns_id(pos->ns)) + node = node->rb_right; else break; } } /* Skip over entries which are dying/dead or in the wrong namespace */ - while (pos && (!kernfs_active(pos) || pos->ns != ns)) { + while (pos && (!kernfs_active(pos) || + kernfs_ns_id(pos->ns) != kernfs_ns_id(ns))) { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; @@ -1867,7 +1894,7 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, return pos; } -static struct kernfs_node *kernfs_dir_next_pos(const void *ns, +static struct kernfs_node *kernfs_dir_next_pos(const struct ns_common *ns, struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos) { pos = kernfs_dir_pos(ns, parent, ino, pos); @@ -1878,7 +1905,8 @@ static struct kernfs_node *kernfs_dir_next_pos(const void *ns, pos = NULL; else pos = rb_to_kn(node); - } while (pos && (!kernfs_active(pos) || pos->ns != ns)); + } while (pos && (!kernfs_active(pos) || + kernfs_ns_id(pos->ns) != kernfs_ns_id(ns))); } return pos; } @@ -1889,7 +1917,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) struct kernfs_node *parent = kernfs_dentry_node(dentry); struct kernfs_node *pos = file->private_data; struct kernfs_root *root; - const void *ns = NULL; + const struct ns_common *ns = NULL; if (!dir_emit_dots(file, ctx)) return 0; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e32406d62c0d..1163aa769738 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -1045,7 +1045,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, - void *priv, const void *ns, + void *priv, const struct ns_common *ns, struct lock_class_key *key) { struct kernfs_node *kn; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 6061b6f70d2a..b1fd9622a5e3 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -97,7 +97,7 @@ struct kernfs_super_info { * instance. If multiple tags become necessary, make the following * an array and compare kernfs_node tag against every entry. */ - const void *ns; + const struct ns_common *ns; /* anchored at kernfs_root->supers, protected by kernfs_rwsem */ struct list_head node; diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 048f00b73b71..6e3217b6e481 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -345,7 +345,7 @@ static int kernfs_set_super(struct super_block *sb, struct fs_context *fc) * * Return: the namespace tag associated with kernfs super_block @sb. */ -const void *kernfs_super_ns(struct super_block *sb) +const struct ns_common *kernfs_super_ns(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index 7d8921f524a6..1da4f707f9ef 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include <linux/string.h> #include <linux/nfs_fs.h> +#include <net/net_namespace.h> #include <linux/rcupdate.h> #include <linux/lockd/lockd.h> @@ -127,9 +128,10 @@ static void nfs_netns_client_release(struct kobject *kobj) kfree(rcu_dereference_raw(c->identifier)); } -static const void *nfs_netns_client_namespace(const struct kobject *kobj) +static const struct ns_common *nfs_netns_client_namespace(const struct kobject *kobj) { - return container_of(kobj, struct nfs_netns_client, kobject)->net; + return to_ns_common(container_of(kobj, struct nfs_netns_client, + kobject)->net); } static struct kobj_attribute nfs_netns_client_id = __ATTR(identifier, @@ -156,9 +158,10 @@ static void nfs_netns_object_release(struct kobject *kobj) kfree(c); } -static const void *nfs_netns_namespace(const struct kobject *kobj) +static const struct ns_common *nfs_netns_namespace(const struct kobject *kobj) { - return container_of(kobj, struct nfs_netns_client, nfs_net_kobj)->net; + return to_ns_common(container_of(kobj, struct nfs_netns_client, + nfs_net_kobj)->net); } static struct kobj_type nfs_netns_object_type = { @@ -350,9 +353,10 @@ static void nfs_sysfs_sb_release(struct kobject *kobj) /* no-op: why? see lib/kobject.c kobject_cleanup() */ } -static const void *nfs_netns_server_namespace(const struct kobject *kobj) +static const struct ns_common *nfs_netns_server_namespace(const struct kobject *kobj) { - return container_of(kobj, struct nfs_server, kobj)->nfs_client->cl_net; + return to_ns_common(container_of(kobj, struct nfs_server, + kobj)->nfs_client->cl_net); } static struct kobj_type nfs_sb_ktype = { diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 94e12efd92f2..ffdcd4153c58 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -37,7 +37,7 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name) * @kobj: object we're creating directory for * @ns: the namespace tag to use */ -int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) +int sysfs_create_dir_ns(struct kobject *kobj, const struct ns_common *ns) { struct kernfs_node *parent, *kn; kuid_t uid; @@ -103,7 +103,7 @@ void sysfs_remove_dir(struct kobject *kobj) } int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, - const void *new_ns) + const struct ns_common *new_ns) { struct kernfs_node *parent; int ret; @@ -115,7 +115,7 @@ int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, } int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, - const void *new_ns) + const struct ns_common *new_ns) { struct kernfs_node *kn = kobj->sd; struct kernfs_node *new_parent; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index a8176c875f55..5709cede1d75 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -272,7 +272,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = { int sysfs_add_file_mode_ns(struct kernfs_node *parent, const struct attribute *attr, umode_t mode, kuid_t uid, - kgid_t gid, const void *ns) + kgid_t gid, const struct ns_common *ns) { struct kobject *kobj = parent->priv; const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops; @@ -322,7 +322,7 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent, int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent, const struct bin_attribute *battr, umode_t mode, size_t size, - kuid_t uid, kgid_t gid, const void *ns) + kuid_t uid, kgid_t gid, const struct ns_common *ns) { const struct attribute *attr = &battr->attr; struct lock_class_key *key = NULL; @@ -362,7 +362,7 @@ int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent, * @ns: namespace the new file should belong to */ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, - const void *ns) + const struct ns_common *ns) { kuid_t uid; kgid_t gid; @@ -505,7 +505,7 @@ EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection); * Hash the attribute name and namespace tag and kill the victim. */ void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, - const void *ns) + const struct ns_common *ns) { struct kernfs_node *parent = kobj->sd; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index e65c60158a04..b199e8ff79b1 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -55,7 +55,7 @@ static const struct fs_context_operations sysfs_fs_context_ops = { static int sysfs_init_fs_context(struct fs_context *fc) { struct kernfs_fs_context *kfc; - struct net *netns; + struct ns_common *ns; if (!(fc->sb_flags & SB_KERNMOUNT)) { if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) @@ -66,12 +66,14 @@ static int sysfs_init_fs_context(struct fs_context *fc) if (!kfc) return -ENOMEM; - kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); + kfc->ns_tag = ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); kfc->root = sysfs_root; kfc->magic = SYSFS_MAGIC; fc->fs_private = kfc; fc->ops = &sysfs_fs_context_ops; - if (netns) { + if (ns) { + struct net *netns = to_net_ns(ns); + put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(netns->user_ns); } @@ -81,7 +83,7 @@ static int sysfs_init_fs_context(struct fs_context *fc) static void sysfs_kill_sb(struct super_block *sb) { - void *ns = (void *)kernfs_super_ns(sb); + struct ns_common *ns = (struct ns_common *)kernfs_super_ns(sb); kernfs_kill_sb(sb); kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 5603530a1a52..5f9c05fb1394 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -121,7 +121,7 @@ EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn); void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, const char *name) { - const void *ns = NULL; + const struct ns_common *ns = NULL; /* * We don't own @target and it may be removed at any time. @@ -164,10 +164,11 @@ EXPORT_SYMBOL_GPL(sysfs_remove_link); * A helper function for the common rename symlink idiom. */ int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ, - const char *old, const char *new, const void *new_ns) + const char *old, const char *new, + const struct ns_common *new_ns) { struct kernfs_node *parent, *kn = NULL; - const void *old_ns = NULL; + const struct ns_common *old_ns = NULL; int result; if (!kobj) diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 8e012f25e1c0..f4583dcafcd1 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -29,10 +29,10 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name); */ int sysfs_add_file_mode_ns(struct kernfs_node *parent, const struct attribute *attr, umode_t amode, kuid_t uid, - kgid_t gid, const void *ns); + kgid_t gid, const struct ns_common *ns); int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent, const struct bin_attribute *battr, umode_t mode, size_t size, - kuid_t uid, kgid_t gid, const void *ns); + kuid_t uid, kgid_t gid, const struct ns_common *ns); /* * symlink.c diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 8239cd95a005..9b6b0d87fdb0 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -229,8 +229,8 @@ static inline bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v) #define smt_mitigations SMT_MITIGATIONS_OFF #endif -int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status); -int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status); -int arch_lock_indir_br_lp_status(struct task_struct *t, unsigned long status); +int arch_prctl_get_branch_landing_pad_state(struct task_struct *t, unsigned long __user *state); +int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state); +int arch_prctl_lock_branch_landing_pad_state(struct task_struct *t); #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 65880e60c720..021da0d61796 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -62,7 +62,7 @@ struct class { int (*shutdown_pre)(struct device *dev); const struct kobj_ns_type_operations *ns_type; - const void *(*namespace)(const struct device *dev); + const struct ns_common *(*namespace)(const struct device *dev); void (*get_ownership)(const struct device *dev, kuid_t *uid, kgid_t *gid); @@ -180,9 +180,9 @@ struct class_attribute { struct class_attribute class_attr_##_name = __ATTR_WO(_name) int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr, - const void *ns); + const struct ns_common *ns); void class_remove_file_ns(const struct class *class, const struct class_attribute *attr, - const void *ns); + const struct ns_common *ns); static inline int __must_check class_create_file(const struct class *class, const struct class_attribute *attr) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index b5a5f32fdfd1..4f0ab88a1b31 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -23,6 +23,7 @@ struct file; struct dentry; struct iattr; +struct ns_common; struct seq_file; struct vm_area_struct; struct vm_operations_struct; @@ -209,7 +210,7 @@ struct kernfs_node { struct rb_node rb; - const void *ns; /* namespace tag */ + const struct ns_common *ns; /* namespace tag */ unsigned int hash; /* ns + name hash */ unsigned short flags; umode_t mode; @@ -331,7 +332,7 @@ struct kernfs_ops { */ struct kernfs_fs_context { struct kernfs_root *root; /* Root of the hierarchy being mounted */ - void *ns_tag; /* Namespace tag of the mount (or NULL) */ + struct ns_common *ns_tag; /* Namespace tag of the mount (or NULL) */ unsigned long magic; /* File system specific magic number */ /* The following are set/used by kernfs_mount() */ @@ -406,9 +407,11 @@ void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn); struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, - const char *name, const void *ns); + const char *name, + const struct ns_common *ns); struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, - const char *path, const void *ns); + const char *path, + const struct ns_common *ns); void kernfs_get(struct kernfs_node *kn); void kernfs_put(struct kernfs_node *kn); @@ -426,7 +429,8 @@ unsigned int kernfs_root_flags(struct kernfs_node *kn); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, - void *priv, const void *ns); + void *priv, + const struct ns_common *ns); struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, @@ -434,7 +438,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, - void *priv, const void *ns, + void *priv, + const struct ns_common *ns, struct lock_class_key *key); struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, @@ -446,9 +451,9 @@ void kernfs_break_active_protection(struct kernfs_node *kn); void kernfs_unbreak_active_protection(struct kernfs_node *kn); bool kernfs_remove_self(struct kernfs_node *kn); int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, - const void *ns); + const struct ns_common *ns); int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, - const char *new_name, const void *new_ns); + const char *new_name, const struct ns_common *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); __poll_t kernfs_generic_poll(struct kernfs_open_file *of, struct poll_table_struct *pt); @@ -459,7 +464,7 @@ int kernfs_xattr_get(struct kernfs_node *kn, const char *name, int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags); -const void *kernfs_super_ns(struct super_block *sb); +const struct ns_common *kernfs_super_ns(struct super_block *sb); int kernfs_get_tree(struct fs_context *fc); void kernfs_free_fs_context(struct fs_context *fc); void kernfs_kill_sb(struct super_block *sb); @@ -494,11 +499,11 @@ static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) static inline struct kernfs_node * kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, - const void *ns) + const struct ns_common *ns) { return NULL; } static inline struct kernfs_node * kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, - const void *ns) + const struct ns_common *ns) { return NULL; } static inline void kernfs_get(struct kernfs_node *kn) { } @@ -526,14 +531,15 @@ static inline unsigned int kernfs_root_flags(struct kernfs_node *kn) static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, - void *priv, const void *ns) + void *priv, const struct ns_common *ns) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, - void *priv, const void *ns, struct lock_class_key *key) + void *priv, const struct ns_common *ns, + struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * @@ -549,12 +555,14 @@ static inline bool kernfs_remove_self(struct kernfs_node *kn) { return false; } static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn, - const char *name, const void *ns) + const char *name, + const struct ns_common *ns) { return -ENOSYS; } static inline int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, - const char *new_name, const void *new_ns) + const char *new_name, + const struct ns_common *new_ns) { return -ENOSYS; } static inline int kernfs_setattr(struct kernfs_node *kn, @@ -575,7 +583,7 @@ static inline int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags) { return -ENOSYS; } -static inline const void *kernfs_super_ns(struct super_block *sb) +static inline const struct ns_common *kernfs_super_ns(struct super_block *sb) { return NULL; } static inline int kernfs_get_tree(struct fs_context *fc) diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c8219505a79f..bcb5d4e32001 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -109,7 +109,7 @@ struct kobject *kobject_get(struct kobject *kobj); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj); void kobject_put(struct kobject *kobj); -const void *kobject_namespace(const struct kobject *kobj); +const struct ns_common *kobject_namespace(const struct kobject *kobj); void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); char *kobject_get_path(const struct kobject *kobj, gfp_t flag); @@ -118,7 +118,7 @@ struct kobj_type { const struct sysfs_ops *sysfs_ops; const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(const struct kobject *kobj); - const void *(*namespace)(const struct kobject *kobj); + const struct ns_common *(*namespace)(const struct kobject *kobj); void (*get_ownership)(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); }; diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index 150fe2ae1b6b..4f0990e09b93 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -16,6 +16,7 @@ #ifndef _LINUX_KOBJECT_NS_H #define _LINUX_KOBJECT_NS_H +struct ns_common; struct sock; struct kobject; @@ -39,10 +40,10 @@ enum kobj_ns_type { struct kobj_ns_type_operations { enum kobj_ns_type type; bool (*current_may_mount)(void); - void *(*grab_current_ns)(void); - const void *(*netlink_ns)(struct sock *sk); - const void *(*initial_ns)(void); - void (*drop_ns)(void *); + struct ns_common *(*grab_current_ns)(void); + const struct ns_common *(*netlink_ns)(struct sock *sk); + const struct ns_common *(*initial_ns)(void); + void (*drop_ns)(struct ns_common *); }; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); @@ -51,7 +52,7 @@ const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *pa const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj); bool kobj_ns_current_may_mount(enum kobj_ns_type type); -void *kobj_ns_grab_current(enum kobj_ns_type type); -void kobj_ns_drop(enum kobj_ns_type type, void *ns); +struct ns_common *kobj_ns_grab_current(enum kobj_ns_type type); +void kobj_ns_drop(enum kobj_ns_type type, struct ns_common *ns); #endif /* _LINUX_KOBJECT_NS_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7ca01eb3f7d2..85c20bdd36fb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5339,9 +5339,9 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi } int netdev_class_create_file_ns(const struct class_attribute *class_attr, - const void *ns); + const struct ns_common *ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, - const void *ns); + const struct ns_common *ns); extern const struct kobj_ns_type_operations net_ns_type_operations; diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 99b775f3ff46..468259fb6049 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -396,13 +396,13 @@ struct sysfs_ops { #ifdef CONFIG_SYSFS -int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns); +int __must_check sysfs_create_dir_ns(struct kobject *kobj, const struct ns_common *ns); void sysfs_remove_dir(struct kobject *kobj); int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, - const void *new_ns); + const struct ns_common *new_ns); int __must_check sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, - const void *new_ns); + const struct ns_common *new_ns); int __must_check sysfs_create_mount_point(struct kobject *parent_kobj, const char *name); void sysfs_remove_mount_point(struct kobject *parent_kobj, @@ -410,7 +410,7 @@ void sysfs_remove_mount_point(struct kobject *parent_kobj, int __must_check sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, - const void *ns); + const struct ns_common *ns); int __must_check sysfs_create_files(struct kobject *kobj, const struct attribute * const *attr); int __must_check sysfs_chmod_file(struct kobject *kobj, @@ -419,7 +419,7 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, const struct attribute *attr); void sysfs_unbreak_active_protection(struct kernfs_node *kn); void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, - const void *ns); + const struct ns_common *ns); bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr); void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *attr); @@ -437,7 +437,7 @@ void sysfs_remove_link(struct kobject *kobj, const char *name); int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *target, const char *old_name, const char *new_name, - const void *new_ns); + const struct ns_common *new_ns); void sysfs_delete_link(struct kobject *dir, struct kobject *targ, const char *name); @@ -502,7 +502,7 @@ ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, #else /* CONFIG_SYSFS */ -static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) +static inline int sysfs_create_dir_ns(struct kobject *kobj, const struct ns_common *ns) { return 0; } @@ -512,14 +512,14 @@ static inline void sysfs_remove_dir(struct kobject *kobj) } static inline int sysfs_rename_dir_ns(struct kobject *kobj, - const char *new_name, const void *new_ns) + const char *new_name, const struct ns_common *new_ns) { return 0; } static inline int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, - const void *new_ns) + const struct ns_common *new_ns) { return 0; } @@ -537,7 +537,7 @@ static inline void sysfs_remove_mount_point(struct kobject *parent_kobj, static inline int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, - const void *ns) + const struct ns_common *ns) { return 0; } @@ -567,7 +567,7 @@ static inline void sysfs_unbreak_active_protection(struct kernfs_node *kn) static inline void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, - const void *ns) + const struct ns_common *ns) { } @@ -612,7 +612,7 @@ static inline void sysfs_remove_link(struct kobject *kobj, const char *name) static inline int sysfs_rename_link_ns(struct kobject *k, struct kobject *t, const char *old_name, - const char *new_name, const void *ns) + const char *new_name, const struct ns_common *ns) { return 0; } diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index d7bec49ee9ea..80de5e98a66d 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -264,14 +264,14 @@ void ipx_unregister_sysctl(void); #define ipx_unregister_sysctl() #endif -#ifdef CONFIG_NET_NS -void __put_net(struct net *net); - static inline struct net *to_net_ns(struct ns_common *ns) { return container_of(ns, struct net, ns); } +#ifdef CONFIG_NET_NS +void __put_net(struct net *net); + /* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { @@ -309,7 +309,7 @@ static inline int check_net(const struct net *net) return ns_ref_read(net) != 0; } -void net_drop_ns(void *); +void net_drop_ns(struct ns_common *); void net_passive_dec(struct net *net); #else diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 55b0446fff9d..b6ec6f693719 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -397,30 +397,23 @@ struct prctl_mm_map { # define PR_RSEQ_SLICE_EXT_ENABLE 0x01 /* - * Get the current indirect branch tracking configuration for the current - * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS. + * Get or set the control flow integrity (CFI) configuration for the + * current thread. + * + * Some per-thread control flow integrity settings are not yet + * controlled through this prctl(); see for example + * PR_{GET,SET,LOCK}_SHADOW_STACK_STATUS */ -#define PR_GET_INDIR_BR_LP_STATUS 80 - +#define PR_GET_CFI 80 +#define PR_SET_CFI 81 /* - * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will - * enable cpu feature for user thread, to track all indirect branches and ensure - * they land on arch defined landing pad instruction. - * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction. - * arch64 - If enabled, an indirect branch must land on a BTI instruction. - * riscv - If enabled, an indirect branch must land on an lpad instruction. - * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect - * branches will no more be tracked by cpu to land on arch defined landing pad - * instruction. - */ -#define PR_SET_INDIR_BR_LP_STATUS 81 -# define PR_INDIR_BR_LP_ENABLE (1UL << 0) - -/* - * Prevent further changes to the specified indirect branch tracking - * configuration. All bits may be locked via this call, including - * undefined bits. + * Forward-edge CFI variants (excluding ARM64 BTI, which has its own + * prctl()s). */ -#define PR_LOCK_INDIR_BR_LP_STATUS 82 +#define PR_CFI_BRANCH_LANDING_PADS 0 +/* Return and control values for PR_{GET,SET}_CFI */ +# define PR_CFI_ENABLE _BITUL(0) +# define PR_CFI_DISABLE _BITUL(1) +# define PR_CFI_LOCK _BITUL(2) #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index c86eba9aa7e9..62e842055cc9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2388,17 +2388,18 @@ int __weak arch_lock_shadow_stack_status(struct task_struct *t, unsigned long st return -EINVAL; } -int __weak arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status) +int __weak arch_prctl_get_branch_landing_pad_state(struct task_struct *t, + unsigned long __user *state) { return -EINVAL; } -int __weak arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status) +int __weak arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state) { return -EINVAL; } -int __weak arch_lock_indir_br_lp_status(struct task_struct *t, unsigned long status) +int __weak arch_prctl_lock_branch_landing_pad_state(struct task_struct *t) { return -EINVAL; } @@ -2888,20 +2889,23 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = rseq_slice_extension_prctl(arg2, arg3); break; - case PR_GET_INDIR_BR_LP_STATUS: - if (arg3 || arg4 || arg5) + case PR_GET_CFI: + if (arg2 != PR_CFI_BRANCH_LANDING_PADS) return -EINVAL; - error = arch_get_indir_br_lp_status(me, (unsigned long __user *)arg2); - break; - case PR_SET_INDIR_BR_LP_STATUS: - if (arg3 || arg4 || arg5) + if (arg4 || arg5) return -EINVAL; - error = arch_set_indir_br_lp_status(me, arg2); + error = arch_prctl_get_branch_landing_pad_state(me, (unsigned long __user *)arg3); break; - case PR_LOCK_INDIR_BR_LP_STATUS: - if (arg3 || arg4 || arg5) + case PR_SET_CFI: + if (arg2 != PR_CFI_BRANCH_LANDING_PADS) return -EINVAL; - error = arch_lock_indir_br_lp_status(me, arg2); + if (arg4 || arg5) + return -EINVAL; + error = arch_prctl_set_branch_landing_pad_state(me, arg3); + if (error) + break; + if (arg3 & PR_CFI_LOCK && !(arg3 & PR_CFI_DISABLE)) + error = arch_prctl_lock_branch_landing_pad_state(me); break; default: trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5); diff --git a/lib/kobject.c b/lib/kobject.c index cfdb2c3f20a2..9c9ff0f5175f 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -27,7 +27,7 @@ * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ -const void *kobject_namespace(const struct kobject *kobj) +const struct ns_common *kobject_namespace(const struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); @@ -1083,9 +1083,9 @@ bool kobj_ns_current_may_mount(enum kobj_ns_type type) return may_mount; } -void *kobj_ns_grab_current(enum kobj_ns_type type) +struct ns_common *kobj_ns_grab_current(enum kobj_ns_type type) { - void *ns = NULL; + struct ns_common *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) @@ -1096,7 +1096,7 @@ void *kobj_ns_grab_current(enum kobj_ns_type type) } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); -void kobj_ns_drop(enum kobj_ns_type type, void *ns) +void kobj_ns_drop(enum kobj_ns_type type, struct ns_common *ns) { spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 871941c9830c..ddbc4d7482d2 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -238,7 +238,7 @@ static int kobj_usermode_filter(struct kobject *kobj) ops = kobj_ns_ops(kobj); if (ops) { - const void *init_ns, *ns; + const struct ns_common *init_ns, *ns; ns = kobj->ktype->namespace(kobj); init_ns = ops->initial_ns(); @@ -388,7 +388,7 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj, #ifdef CONFIG_NET const struct kobj_ns_type_operations *ops; - const struct net *net = NULL; + const struct ns_common *ns = NULL; ops = kobj_ns_ops(kobj); if (!ops && kobj->kset) { @@ -404,14 +404,17 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj, */ if (ops && ops->netlink_ns && kobj->ktype->namespace) if (ops->type == KOBJ_NS_TYPE_NET) - net = kobj->ktype->namespace(kobj); + ns = kobj->ktype->namespace(kobj); - if (!net) + if (!ns) ret = uevent_net_broadcast_untagged(env, action_string, devpath); - else + else { + const struct net *net = container_of(ns, struct net, ns); + ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env, action_string, devpath); + } #endif return ret; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 07624b682b08..b9740a397f55 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1181,24 +1181,24 @@ static void rx_queue_release(struct kobject *kobj) netdev_put(queue->dev, &queue->dev_tracker); } -static const void *rx_queue_namespace(const struct kobject *kobj) +static const struct ns_common *rx_queue_namespace(const struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); struct device *dev = &queue->dev->dev; - const void *ns = NULL; if (dev->class && dev->class->namespace) - ns = dev->class->namespace(dev); + return dev->class->namespace(dev); - return ns; + return NULL; } static void rx_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { - const struct net *net = rx_queue_namespace(kobj); + const struct ns_common *ns = rx_queue_namespace(kobj); - net_ns_get_ownership(net, uid, gid); + net_ns_get_ownership(ns ? container_of(ns, struct net, ns) : NULL, + uid, gid); } static const struct kobj_type rx_queue_ktype = { @@ -1931,24 +1931,24 @@ static void netdev_queue_release(struct kobject *kobj) netdev_put(queue->dev, &queue->dev_tracker); } -static const void *netdev_queue_namespace(const struct kobject *kobj) +static const struct ns_common *netdev_queue_namespace(const struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); struct device *dev = &queue->dev->dev; - const void *ns = NULL; if (dev->class && dev->class->namespace) - ns = dev->class->namespace(dev); + return dev->class->namespace(dev); - return ns; + return NULL; } static void netdev_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { - const struct net *net = netdev_queue_namespace(kobj); + const struct ns_common *ns = netdev_queue_namespace(kobj); - net_ns_get_ownership(net, uid, gid); + net_ns_get_ownership(ns ? container_of(ns, struct net, ns) : NULL, + uid, gid); } static const struct kobj_type netdev_queue_ktype = { @@ -2185,24 +2185,24 @@ static bool net_current_may_mount(void) return ns_capable(net->user_ns, CAP_SYS_ADMIN); } -static void *net_grab_current_ns(void) +static struct ns_common *net_grab_current_ns(void) { - struct net *ns = current->nsproxy->net_ns; + struct net *net = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS - if (ns) - refcount_inc(&ns->passive); + if (net) + refcount_inc(&net->passive); #endif - return ns; + return net ? to_ns_common(net) : NULL; } -static const void *net_initial_ns(void) +static const struct ns_common *net_initial_ns(void) { - return &init_net; + return to_ns_common(&init_net); } -static const void *net_netlink_ns(struct sock *sk) +static const struct ns_common *net_netlink_ns(struct sock *sk) { - return sock_net(sk); + return to_ns_common(sock_net(sk)); } const struct kobj_ns_type_operations net_ns_type_operations = { @@ -2252,11 +2252,11 @@ static void netdev_release(struct device *d) kvfree(dev); } -static const void *net_namespace(const struct device *d) +static const struct ns_common *net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d); - return dev_net(dev); + return to_ns_common(dev_net(dev)); } static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid) @@ -2402,14 +2402,14 @@ int netdev_change_owner(struct net_device *ndev, const struct net *net_old, } int netdev_class_create_file_ns(const struct class_attribute *class_attr, - const void *ns) + const struct ns_common *ns) { return class_create_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_create_file_ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, - const void *ns) + const struct ns_common *ns) { class_remove_file_ns(&net_class, class_attr, ns); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 1057d16d5dd2..24aa10a1d0ea 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -540,12 +540,10 @@ void net_passive_dec(struct net *net) } } -void net_drop_ns(void *p) +void net_drop_ns(struct ns_common *ns) { - struct net *net = (struct net *)p; - - if (net) - net_passive_dec(net); + if (ns) + net_passive_dec(to_net_ns(ns)); } struct net *copy_net_ns(u64 flags, diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index af8fac9cedd4..a90480f80154 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -6,6 +6,7 @@ #include <linux/kobject.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/xprtsock.h> +#include <net/net_namespace.h> #include "sysfs.h" @@ -553,20 +554,22 @@ static void rpc_sysfs_xprt_release(struct kobject *kobj) kfree(xprt); } -static const void *rpc_sysfs_client_namespace(const struct kobject *kobj) +static const struct ns_common *rpc_sysfs_client_namespace(const struct kobject *kobj) { - return container_of(kobj, struct rpc_sysfs_client, kobject)->net; + return to_ns_common(container_of(kobj, struct rpc_sysfs_client, + kobject)->net); } -static const void *rpc_sysfs_xprt_switch_namespace(const struct kobject *kobj) +static const struct ns_common *rpc_sysfs_xprt_switch_namespace(const struct kobject *kobj) { - return container_of(kobj, struct rpc_sysfs_xprt_switch, kobject)->net; + return to_ns_common(container_of(kobj, struct rpc_sysfs_xprt_switch, + kobject)->net); } -static const void *rpc_sysfs_xprt_namespace(const struct kobject *kobj) +static const struct ns_common *rpc_sysfs_xprt_namespace(const struct kobject *kobj) { - return container_of(kobj, struct rpc_sysfs_xprt, - kobject)->xprt->xprt_net; + return to_ns_common(container_of(kobj, struct rpc_sysfs_xprt, + kobject)->xprt->xprt_net); } static struct kobj_attribute rpc_sysfs_clnt_version = __ATTR(rpc_version, diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 2e0ea69b9604..0b9abe70d39d 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -154,11 +154,11 @@ static SIMPLE_DEV_PM_OPS(wiphy_pm_ops, wiphy_suspend, wiphy_resume); #define WIPHY_PM_OPS NULL #endif -static const void *wiphy_namespace(const struct device *d) +static const struct ns_common *wiphy_namespace(const struct device *d) { struct wiphy *wiphy = container_of(d, struct wiphy, dev); - return wiphy_net(wiphy); + return to_ns_common(wiphy_net(wiphy)); } struct class ieee80211_class = { diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 0ec946f9b905..6d36786ba31c 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -195,7 +195,7 @@ tar%-pkg: linux-$(KERNELRELEASE)-$(ARCH).tar.% FORCE .tmp_modules_cpio: FORCE $(Q)$(MAKE) -f $(srctree)/Makefile $(Q)rm -rf $@ - $(Q)$(MAKE) -f $(srctree)/Makefile INSTALL_MOD_PATH=$@ modules_install + $(Q)$(MAKE) -f $(srctree)/Makefile INSTALL_MOD_PATH=$@/$(INSTALL_MOD_PATH) modules_install quiet_cmd_cpio = CPIO $@ cmd_cpio = $(CONFIG_SHELL) $(srctree)/usr/gen_initramfs.sh -o $@ $< @@ -264,6 +264,7 @@ help: @echo ' tarxz-pkg - Build the kernel as a xz compressed tarball' @echo ' tarzst-pkg - Build the kernel as a zstd compressed tarball' @echo ' modules-cpio-pkg - Build the kernel modules as cpio archive' + @echo ' (uses INSTALL_MOD_PATH inside the archive)' @echo ' perf-tar-src-pkg - Build the perf source tarball with no compression' @echo ' perf-targz-src-pkg - Build the perf source tarball with gzip compression' @echo ' perf-tarbz2-src-pkg - Build the perf source tarball with bz2 compression' diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 0c25b5ad497b..c3bc801d8b2d 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -56,7 +56,7 @@ static bool allow_missing_ns_imports; static bool error_occurred; -static bool extra_warn; +static bool extra_warn __attribute__((unused)); bool target_is_big_endian; bool host_is_big_endian; diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 55b0446fff9d..560f99bc4782 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -397,30 +397,24 @@ struct prctl_mm_map { # define PR_RSEQ_SLICE_EXT_ENABLE 0x01 /* - * Get the current indirect branch tracking configuration for the current - * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS. + * Get or set the control flow integrity (CFI) configuration for the + * current thread. + * + * Some per-thread control flow integrity settings are not yet + * controlled through this prctl(); see for example + * PR_{GET,SET,LOCK}_SHADOW_STACK_STATUS */ -#define PR_GET_INDIR_BR_LP_STATUS 80 - +#define PR_GET_CFI 80 +#define PR_SET_CFI 81 /* - * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will - * enable cpu feature for user thread, to track all indirect branches and ensure - * they land on arch defined landing pad instruction. - * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction. - * arch64 - If enabled, an indirect branch must land on a BTI instruction. - * riscv - If enabled, an indirect branch must land on an lpad instruction. - * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect - * branches will no more be tracked by cpu to land on arch defined landing pad - * instruction. + * Forward-edge CFI variants (excluding ARM64 BTI, which has its own + * prctl()s). */ -#define PR_SET_INDIR_BR_LP_STATUS 81 -# define PR_INDIR_BR_LP_ENABLE (1UL << 0) +#define PR_CFI_BRANCH_LANDING_PADS 0 +/* Return and control values for PR_{GET,SET}_CFI */ +# define PR_CFI_ENABLE _BITUL(0) +# define PR_CFI_DISABLE _BITUL(1) +# define PR_CFI_LOCK _BITUL(2) -/* - * Prevent further changes to the specified indirect branch tracking - * configuration. All bits may be locked via this call, including - * undefined bits. - */ -#define PR_LOCK_INDIR_BR_LP_STATUS 82 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 1a2671c28209..e9e8ef72395a 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2409,7 +2409,7 @@ struct topo_params { int max_l3_id; int max_node_num; int nodes_per_pkg; - int cores_per_node; + int cores_per_pkg; int threads_per_core; } topo; @@ -2837,30 +2837,29 @@ static inline int print_name(int width, int *printed, char *delim, char *name, e UNUSED(type); if (format == FORMAT_RAW && width >= 64) - return (sprintf(outp, "%s%-8s", (*printed++ ? delim : ""), name)); + return (sprintf(outp, "%s%-8s", ((*printed)++ ? delim : ""), name)); else - return (sprintf(outp, "%s%s", (*printed++ ? delim : ""), name)); + return (sprintf(outp, "%s%s", ((*printed)++ ? delim : ""), name)); } static inline int print_hex_value(int width, int *printed, char *delim, unsigned long long value) { if (width <= 32) - return (sprintf(outp, "%s%08x", (*printed++ ? delim : ""), (unsigned int)value)); + return (sprintf(outp, "%s%08x", ((*printed)++ ? delim : ""), (unsigned int)value)); else - return (sprintf(outp, "%s%016llx", (*printed++ ? delim : ""), value)); + return (sprintf(outp, "%s%016llx", ((*printed)++ ? delim : ""), value)); } static inline int print_decimal_value(int width, int *printed, char *delim, unsigned long long value) { - if (width <= 32) - return (sprintf(outp, "%s%d", (*printed++ ? delim : ""), (unsigned int)value)); - else - return (sprintf(outp, "%s%-8lld", (*printed++ ? delim : ""), value)); + UNUSED(width); + + return (sprintf(outp, "%s%lld", ((*printed)++ ? delim : ""), value)); } static inline int print_float_value(int *printed, char *delim, double value) { - return (sprintf(outp, "%s%0.2f", (*printed++ ? delim : ""), value)); + return (sprintf(outp, "%s%0.2f", ((*printed)++ ? delim : ""), value)); } void print_header(char *delim) @@ -3469,7 +3468,7 @@ int format_counters(PER_THREAD_PARAMS) for (i = 0, pp = sys.perf_tp; pp; ++i, pp = pp->next) { if (pp->format == FORMAT_RAW) outp += print_hex_value(pp->width, &printed, delim, t->perf_counter[i]); - else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE) + else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE) outp += print_decimal_value(pp->width, &printed, delim, t->perf_counter[i]); else if (pp->format == FORMAT_PERCENT) { if (pp->type == COUNTER_USEC) @@ -3490,12 +3489,12 @@ int format_counters(PER_THREAD_PARAMS) case PMT_TYPE_XTAL_TIME: value_converted = pct(value_raw / crystal_hz, interval_float); - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); + outp += print_float_value(&printed, delim, value_converted); break; case PMT_TYPE_TCORE_CLOCK: value_converted = pct(value_raw / tcore_clock_freq_hz, interval_float); - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); + outp += print_float_value(&printed, delim, value_converted); } } @@ -3539,7 +3538,7 @@ int format_counters(PER_THREAD_PARAMS) for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) { if (pp->format == FORMAT_RAW) outp += print_hex_value(pp->width, &printed, delim, c->perf_counter[i]); - else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE) + else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE) outp += print_decimal_value(pp->width, &printed, delim, c->perf_counter[i]); else if (pp->format == FORMAT_PERCENT) outp += print_float_value(&printed, delim, pct(c->perf_counter[i], tsc)); @@ -3695,7 +3694,7 @@ int format_counters(PER_THREAD_PARAMS) outp += print_hex_value(pp->width, &printed, delim, p->perf_counter[i]); else if (pp->type == COUNTER_K2M) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), (unsigned int)p->perf_counter[i] / 1000); - else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE) + else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE) outp += print_decimal_value(pp->width, &printed, delim, p->perf_counter[i]); else if (pp->format == FORMAT_PERCENT) outp += print_float_value(&printed, delim, pct(p->perf_counter[i], tsc)); @@ -9122,10 +9121,13 @@ void process_cpuid() cpuid_has_hv = ecx_flags & (1 << 31); if (!no_msr) { - if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) + if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) { warnx("get_msr(UCODE)"); - else + } else { ucode_patch_valid = true; + if (!authentic_amd && !hygon_genuine) + ucode_patch >>= 32; + } } /* @@ -9139,7 +9141,7 @@ void process_cpuid() if (!quiet) { fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)", family, model, stepping, family, model, stepping); if (ucode_patch_valid) - fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF)); + fprintf(outf, " microcode 0x%x", (unsigned int)ucode_patch); fputc('\n', outf); fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level); @@ -9403,13 +9405,13 @@ void perf_l2_init(void) if (!is_hybrid) { fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.uniform, perf_model_support->first.refs, -1, PERF_FORMAT_GROUP); if (fd_l2_percpu[cpu] == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.refs); + warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.refs); free_fd_l2_percpu(); return; } retval = open_perf_counter(cpu, perf_pmu_types.uniform, perf_model_support->first.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP); if (retval == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.hits); + warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.hits); free_fd_l2_percpu(); return; } @@ -9418,39 +9420,39 @@ void perf_l2_init(void) if (perf_pcore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_pcore_set)) { fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.pcore, perf_model_support->first.refs, -1, PERF_FORMAT_GROUP); if (fd_l2_percpu[cpu] == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.refs); + warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.refs); free_fd_l2_percpu(); return; } retval = open_perf_counter(cpu, perf_pmu_types.pcore, perf_model_support->first.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP); if (retval == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.hits); + warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.hits); free_fd_l2_percpu(); return; } } else if (perf_ecore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_ecore_set)) { fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.ecore, perf_model_support->second.refs, -1, PERF_FORMAT_GROUP); if (fd_l2_percpu[cpu] == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->second.refs); + warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.ecore, perf_model_support->second.refs); free_fd_l2_percpu(); return; } retval = open_perf_counter(cpu, perf_pmu_types.ecore, perf_model_support->second.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP); if (retval == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->second.hits); + warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.ecore, perf_model_support->second.hits); free_fd_l2_percpu(); return; } } else if (perf_lcore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_lcore_set)) { fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.lcore, perf_model_support->third.refs, -1, PERF_FORMAT_GROUP); if (fd_l2_percpu[cpu] == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->third.refs); + warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.lcore, perf_model_support->third.refs); free_fd_l2_percpu(); return; } retval = open_perf_counter(cpu, perf_pmu_types.lcore, perf_model_support->third.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP); if (retval == -1) { - err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->third.hits); + warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.lcore, perf_model_support->third.hits); free_fd_l2_percpu(); return; } @@ -9634,9 +9636,9 @@ void topology_probe(bool startup) topo.max_core_id = max_core_id; /* within a package */ topo.max_package_id = max_package_id; - topo.cores_per_node = max_core_id + 1; + topo.cores_per_pkg = max_core_id + 1; if (debug > 1) - fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_node); + fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_pkg); if (!summary_only) BIC_PRESENT(BIC_Core); @@ -9701,14 +9703,13 @@ error: void allocate_counters(struct counters *counters) { int i; - int num_cores = topo.cores_per_node * topo.nodes_per_pkg * topo.num_packages; - int num_threads = topo.threads_per_core * num_cores; + int num_cores = topo.cores_per_pkg * topo.num_packages; - counters->threads = calloc(num_threads, sizeof(struct thread_data)); + counters->threads = calloc(topo.max_cpu_num + 1, sizeof(struct thread_data)); if (counters->threads == NULL) goto error; - for (i = 0; i < num_threads; i++) + for (i = 0; i < topo.max_cpu_num + 1; i++) (counters->threads)[i].cpu_id = -1; counters->cores = calloc(num_cores, sizeof(struct core_data)); @@ -11284,6 +11285,14 @@ void probe_cpuidle_residency(void) } } +static bool cpuidle_counter_wanted(char *name) +{ + if (is_deferred_skip(name)) + return false; + + return DO_BIC(BIC_cpuidle) || is_deferred_add(name); +} + void probe_cpuidle_counts(void) { char path[64]; @@ -11293,7 +11302,7 @@ void probe_cpuidle_counts(void) int min_state = 1024, max_state = 0; char *sp; - if (!DO_BIC(BIC_cpuidle)) + if (!DO_BIC(BIC_cpuidle) && !deferred_add_index) return; for (state = 10; state >= 0; --state) { @@ -11308,12 +11317,6 @@ void probe_cpuidle_counts(void) remove_underbar(name_buf); - if (!DO_BIC(BIC_cpuidle) && !is_deferred_add(name_buf)) - continue; - - if (is_deferred_skip(name_buf)) - continue; - /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ sp = strchr(name_buf, '-'); if (!sp) @@ -11328,16 +11331,19 @@ void probe_cpuidle_counts(void) * Add 'C1+' for C1, and so on. The 'below' sysfs file always contains 0 for * the last state, so do not add it. */ - *sp = '+'; *(sp + 1) = '\0'; - sprintf(path, "cpuidle/state%d/below", state); - add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0); + if (cpuidle_counter_wanted(name_buf)) { + sprintf(path, "cpuidle/state%d/below", state); + add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0); + } } *sp = '\0'; - sprintf(path, "cpuidle/state%d/usage", state); - add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0); + if (cpuidle_counter_wanted(name_buf)) { + sprintf(path, "cpuidle/state%d/usage", state); + add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0); + } /* * The 'above' sysfs file always contains 0 for the shallowest state (smallest @@ -11346,8 +11352,10 @@ void probe_cpuidle_counts(void) if (state != min_state) { *sp = '-'; *(sp + 1) = '\0'; - sprintf(path, "cpuidle/state%d/above", state); - add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0); + if (cpuidle_counter_wanted(name_buf)) { + sprintf(path, "cpuidle/state%d/above", state); + add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0); + } } } } diff --git a/tools/testing/selftests/riscv/cfi/cfitests.c b/tools/testing/selftests/riscv/cfi/cfitests.c index 298544854415..39d097b6881f 100644 --- a/tools/testing/selftests/riscv/cfi/cfitests.c +++ b/tools/testing/selftests/riscv/cfi/cfitests.c @@ -94,9 +94,9 @@ bool cfi_ptrace_test(void) } switch (ptrace_test_num) { -#define CFI_ENABLE_MASK (PTRACE_CFI_LP_EN_STATE | \ - PTRACE_CFI_SS_EN_STATE | \ - PTRACE_CFI_SS_PTR_STATE) +#define CFI_ENABLE_MASK (PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | \ + PTRACE_CFI_SHADOW_STACK_EN_STATE | \ + PTRACE_CFI_SHADOW_STACK_PTR_STATE) case 0: if ((cfi_reg.cfi_status.cfi_state & CFI_ENABLE_MASK) != CFI_ENABLE_MASK) ksft_exit_fail_msg("%s: ptrace_getregset failed, %llu\n", __func__, @@ -106,7 +106,8 @@ bool cfi_ptrace_test(void) __func__); break; case 1: - if (!(cfi_reg.cfi_status.cfi_state & PTRACE_CFI_ELP_STATE)) + if (!(cfi_reg.cfi_status.cfi_state & + PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE)) ksft_exit_fail_msg("%s: elp must have been set\n", __func__); /* clear elp state. not interested in anything else */ cfi_reg.cfi_status.cfi_state = 0; @@ -145,11 +146,11 @@ int main(int argc, char *argv[]) * pads for user mode except lighting up a bit in senvcfg via a prctl. * Enable landing pad support throughout the execution of the test binary. */ - ret = my_syscall5(__NR_prctl, PR_GET_INDIR_BR_LP_STATUS, &lpad_status, 0, 0, 0); + ret = my_syscall5(__NR_prctl, PR_GET_CFI, PR_CFI_BRANCH_LANDING_PADS, &lpad_status, 0, 0); if (ret) ksft_exit_fail_msg("Get landing pad status failed with %d\n", ret); - if (!(lpad_status & PR_INDIR_BR_LP_ENABLE)) + if (!(lpad_status & PR_CFI_ENABLE)) ksft_exit_fail_msg("Landing pad is not enabled, should be enabled via glibc\n"); ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0); |